Compare commits
134
Commits
885e8045fe
...
8b6e3070dd
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
8b6e3070dd | ||
|
|
b860c67ea2 | ||
|
|
533477c2e7 | ||
|
|
5aa2dc579a | ||
|
|
280b3d2a25 | ||
|
|
ec74f4cdc4 | ||
|
|
5af9dc8e4a | ||
|
|
ca6d4b4b72 | ||
|
|
cccecbe7ca | ||
|
|
7a64c38493 | ||
|
|
b1361d86e9 | ||
|
|
6181426abd | ||
|
|
cd331b93c6 | ||
|
|
60eabea19a | ||
|
|
7394ec6784 | ||
|
|
28b7cc414b | ||
|
|
86d5cf9403 | ||
|
|
6f0a23e5cc | ||
|
|
2f4a46bbdb | ||
|
|
4872cf2aac | ||
|
|
734d4b44ae | ||
|
|
6810f51f46 | ||
|
|
a1748b552c | ||
|
|
62b2d27b4a | ||
|
|
62e2b44305 | ||
|
|
aa0fb2f787 | ||
|
|
1b6d4dbfd8 | ||
|
|
4ef7b03651 | ||
|
|
af615ab177 | ||
|
|
338e39bcdb | ||
|
|
3cfe04be3a | ||
|
|
70d153b365 | ||
|
|
ce93849948 | ||
|
|
3c499719fe | ||
|
|
9e1d3df7ad | ||
|
|
18bac16a23 | ||
|
|
9005856f77 | ||
|
|
e39372a52a | ||
|
|
223a74a9e2 | ||
|
|
f38d9a16ea | ||
|
|
b135fa5e99 | ||
|
|
07b8b6d41b | ||
|
|
8017c55d82 | ||
|
|
b8e548b92d | ||
|
|
90e38551cf | ||
|
|
3e8164e757 | ||
|
|
3b3381900f | ||
|
|
00ad02d047 | ||
|
|
a774925dec | ||
|
|
8f759911ab | ||
|
|
daf1f6ed50 | ||
|
|
86602240fa | ||
|
|
bfeee487fd | ||
|
|
f9830fe7dd | ||
|
|
de96c5b577 | ||
|
|
6e729ed06c | ||
|
|
f38b2a52b1 | ||
|
|
dd5384df3b | ||
|
|
6576850b7a | ||
|
|
4555aace28 | ||
|
|
47b32ef6ab | ||
|
|
bb5c50f9ab | ||
|
|
32a409c15d | ||
|
|
19514a5d6a | ||
|
|
887184796e | ||
|
|
cd0eb5eb00 | ||
|
|
e8dfb3e68d | ||
|
|
434ce34da7 | ||
|
|
bfb51b7ca9 | ||
|
|
38d9069632 | ||
|
|
e5749b9be0 | ||
|
|
387b5ff7df | ||
|
|
ec6c5beda0 | ||
|
|
8e40fae6f4 | ||
|
|
c961f244ab | ||
|
|
cea0225a6e | ||
|
|
b3189d8e85 | ||
|
|
24bc45a31e | ||
|
|
b02360fd75 | ||
|
|
41c9d2d5c7 | ||
|
|
cc66bd5052 | ||
|
|
d1408d3a2f | ||
|
|
19122fb5ea | ||
|
|
1fb216e6ae | ||
|
|
4b14f7e6b3 | ||
|
|
67767eeee7 | ||
|
|
1bfb4ce119 | ||
|
|
651820dc6d | ||
|
|
75b1557d63 | ||
|
|
23ff518209 | ||
|
|
fab9e0f4b5 | ||
|
|
5ee42b8db8 | ||
|
|
daf438701f | ||
|
|
23ee401287 | ||
|
|
8f598da931 | ||
|
|
956aeed6b2 | ||
|
|
adfa422973 | ||
|
|
10d200d9ba | ||
|
|
7a5228b8e6 | ||
|
|
0eabdf3a1f | ||
|
|
b1808b7c4d | ||
|
|
6645ea0a47 | ||
|
|
b544e53bd7 | ||
|
|
04a4e59100 | ||
|
|
52e914eebc | ||
|
|
9c12fb4372 | ||
|
|
3c18916118 | ||
|
|
be1c030350 | ||
|
|
a7faf2cea6 | ||
|
|
5cc5ece997 | ||
|
|
ffaaf2ecb0 | ||
|
|
6667985883 | ||
|
|
22dcd8a29f | ||
|
|
a2816a053d | ||
|
|
d74660d1d1 | ||
|
|
24c6f772f7 | ||
|
|
a060ffada8 | ||
|
|
b8b12442a0 | ||
|
|
d22899d39e | ||
|
|
af008f802d | ||
|
|
7042ec7d50 | ||
|
|
a2cec5afd1 | ||
|
|
b5a307811b | ||
|
|
5bd49760e5 | ||
|
|
9debf43645 | ||
|
|
81af1f085c | ||
|
|
b67aa2de7d | ||
|
|
9f1cbbd385 | ||
|
|
8a3d9d67d2 | ||
|
|
6218c27fb6 | ||
|
|
b744efd104 | ||
|
|
18384482f6 | ||
|
|
c2df3041f9 | ||
|
|
aabc502f30 |
Generated
+12
-2
@@ -5266,6 +5266,7 @@ dependencies = [
|
||||
"thiserror 2.0.18",
|
||||
"tokio",
|
||||
"tracing",
|
||||
"uuid",
|
||||
"workdir",
|
||||
]
|
||||
|
||||
@@ -6496,6 +6497,7 @@ name = "workdir"
|
||||
version = "0.1.0"
|
||||
dependencies = [
|
||||
"async-trait",
|
||||
"axum",
|
||||
"fs-operation",
|
||||
"libc",
|
||||
"manifest",
|
||||
@@ -6519,7 +6521,6 @@ dependencies = [
|
||||
"axum",
|
||||
"base64 0.22.1",
|
||||
"chrono",
|
||||
"clap",
|
||||
"client",
|
||||
"config-source",
|
||||
"dotenv",
|
||||
@@ -6548,6 +6549,7 @@ dependencies = [
|
||||
"session-metrics",
|
||||
"session-store",
|
||||
"sha2 0.11.0",
|
||||
"subjektiv",
|
||||
"tempfile",
|
||||
"thiserror 2.0.18",
|
||||
"ticket",
|
||||
@@ -6556,6 +6558,7 @@ dependencies = [
|
||||
"toml",
|
||||
"tools",
|
||||
"tracing",
|
||||
"tracing-subscriber",
|
||||
"tungstenite 0.28.0",
|
||||
"uuid",
|
||||
"wip-client",
|
||||
@@ -6595,6 +6598,7 @@ dependencies = [
|
||||
"tokio",
|
||||
"tokio-tungstenite 0.29.0",
|
||||
"toml",
|
||||
"tools",
|
||||
"tower",
|
||||
"tracing",
|
||||
"tracing-subscriber",
|
||||
@@ -6682,6 +6686,7 @@ dependencies = [
|
||||
"futures",
|
||||
"manifest",
|
||||
"project-record",
|
||||
"protocol",
|
||||
"reqwest",
|
||||
"serde",
|
||||
"serde_json",
|
||||
@@ -6697,19 +6702,23 @@ dependencies = [
|
||||
"tui",
|
||||
"uuid",
|
||||
"workdir",
|
||||
"worker",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "yoi-e2e"
|
||||
version = "0.0.0"
|
||||
dependencies = [
|
||||
"chrono",
|
||||
"libc",
|
||||
"reqwest",
|
||||
"serde",
|
||||
"serde_json",
|
||||
"server-api",
|
||||
"sha2 0.11.0",
|
||||
"tempfile",
|
||||
"webauthn-authenticator-rs",
|
||||
"webauthn-rs-proto",
|
||||
"yoi-workspace-server",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -6770,6 +6779,7 @@ dependencies = [
|
||||
"uuid",
|
||||
"webauthn-authenticator-rs",
|
||||
"webauthn-rs",
|
||||
"webauthn-rs-proto",
|
||||
"wip-protocol",
|
||||
"workdir",
|
||||
"worker",
|
||||
|
||||
+10
@@ -91,6 +91,16 @@ debug = "line-tables-only"
|
||||
[profile.dev.package."*"]
|
||||
debug = false
|
||||
|
||||
# Keep the real SQLite engine in schema/transaction tests without paying for
|
||||
# an unoptimized C interpreter on every statement. Rust test assertions stay enabled.
|
||||
[profile.test.package.libsqlite3-sys]
|
||||
opt-level = 2
|
||||
|
||||
# Schema/authority integration tests execute substantial parsing and validation.
|
||||
# Optimize that code without disabling test/debug assertions or overflow checks.
|
||||
[profile.test.package.yoi-workspace-server]
|
||||
opt-level = 1
|
||||
|
||||
[workspace.dependencies]
|
||||
# Internal crates
|
||||
client = { path = "crates/client" }
|
||||
|
||||
@@ -1,13 +1,38 @@
|
||||
//! Compile the real public macro through a renamed dependency in an isolated consumer.
|
||||
//! Only Cargo artifacts are shared; Cargo checks the fresh consumer on every invocation.
|
||||
|
||||
use std::{fs, path::PathBuf, process::Command};
|
||||
|
||||
struct Fixture(PathBuf);
|
||||
|
||||
impl Fixture {
|
||||
fn new() -> Self {
|
||||
for attempt in 0..1000 {
|
||||
let path = std::env::temp_dir().join(format!(
|
||||
"api-macros-renamed-dependency-{}-{attempt}",
|
||||
std::process::id()
|
||||
));
|
||||
match fs::create_dir(&path) {
|
||||
Ok(()) => return Self(path),
|
||||
Err(error) if error.kind() == std::io::ErrorKind::AlreadyExists => continue,
|
||||
Err(error) => panic!("create renamed dependency fixture: {error}"),
|
||||
}
|
||||
}
|
||||
panic!("could not allocate a renamed dependency fixture directory");
|
||||
}
|
||||
}
|
||||
|
||||
impl Drop for Fixture {
|
||||
fn drop(&mut self) {
|
||||
let _ = fs::remove_dir_all(&self.0);
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn macro_expansion_resolves_a_renamed_support_dependency() {
|
||||
let fixture = std::env::temp_dir().join(format!(
|
||||
"api-macros-renamed-dependency-{}",
|
||||
std::process::id()
|
||||
));
|
||||
let _ = fs::remove_dir_all(&fixture);
|
||||
fs::create_dir_all(fixture.join("src")).expect("create fixture source directory");
|
||||
let fixture = Fixture::new();
|
||||
let fixture = &fixture.0;
|
||||
fs::create_dir(fixture.join("src")).expect("create fixture source directory");
|
||||
|
||||
let package_path = PathBuf::from(env!("CARGO_MANIFEST_DIR"));
|
||||
let package_path = package_path
|
||||
@@ -49,13 +74,21 @@ pub fn operation_count() -> usize {
|
||||
)
|
||||
.expect("write fixture source");
|
||||
|
||||
// Keep nested Cargo checks off the outer build's target lock. Cargo owns cache
|
||||
// invalidation and locking between concurrent consumers, not a saved
|
||||
// test-success marker.
|
||||
let executable = std::env::current_exe().expect("current test executable");
|
||||
let target_dir = executable
|
||||
.parent()
|
||||
.and_then(|deps| deps.parent())
|
||||
.expect("test executable has a profile directory")
|
||||
.join("compile-tests/api-macros-renamed");
|
||||
let output = Command::new(env!("CARGO"))
|
||||
.args(["check", "--quiet", "--offline"])
|
||||
.current_dir(&fixture)
|
||||
.env("CARGO_TARGET_DIR", fixture.join("target"))
|
||||
.current_dir(fixture)
|
||||
.env("CARGO_TARGET_DIR", target_dir)
|
||||
.output()
|
||||
.expect("run cargo check for renamed dependency fixture");
|
||||
let _ = fs::remove_dir_all(&fixture);
|
||||
|
||||
assert!(
|
||||
output.status.success(),
|
||||
|
||||
@@ -81,6 +81,16 @@ pub const BUILTIN_PROFILE_RESOURCES: &[BuiltinProfileResource] = &[
|
||||
resolved_path: "profiles/job.dcdl",
|
||||
}],
|
||||
},
|
||||
BuiltinProfileResource {
|
||||
selector: Some("builtin:subjektiv-journal-recording"),
|
||||
path: "profiles/subjektiv-journal-recording.dcdl",
|
||||
source: include_str!("../../../resources/profiles/subjektiv-journal-recording.dcdl"),
|
||||
description: "Journal recording policy with Host-bound sequential Job tools.",
|
||||
imports: &[BuiltinProfileImport {
|
||||
specifier: "./job.dcdl",
|
||||
resolved_path: "profiles/job.dcdl",
|
||||
}],
|
||||
},
|
||||
BuiltinProfileResource {
|
||||
selector: Some("builtin:ticket-worker"),
|
||||
path: "profiles/ticket-worker.dcdl",
|
||||
@@ -123,7 +133,7 @@ pub const BUILTIN_PROFILE_RESOURCES: &[BuiltinProfileResource] = &[
|
||||
selector: Some("builtin:orchestrator"),
|
||||
path: "profiles/orchestrator.dcdl",
|
||||
source: include_str!("../../../resources/profiles/orchestrator.dcdl"),
|
||||
description: "Intent-led Ticket orchestration with separate guarded MR integration authority.",
|
||||
description: "Outcome-led orchestration, selection of candidate changes, and risk-proportionate validation.",
|
||||
imports: BASE_IMPORT,
|
||||
},
|
||||
BuiltinProfileResource {
|
||||
|
||||
@@ -908,6 +908,7 @@ mod tests {
|
||||
workdir_attachments: Vec::new(),
|
||||
feature_connections: Default::default(),
|
||||
control_operation_id: None,
|
||||
execution_grant: None,
|
||||
};
|
||||
|
||||
let response = create_backend_worker_with_client(&target, &create, &api)
|
||||
|
||||
@@ -567,6 +567,7 @@ impl BackendWorkspaceProductClient {
|
||||
workdir_attachments: Vec::new(),
|
||||
feature_connections: Default::default(),
|
||||
control_operation_id: None,
|
||||
execution_grant: None,
|
||||
};
|
||||
let workspace_id = self.workspace_id.clone();
|
||||
let response: BrowserCreateWorkerResponse = self.generated(move |client| async move {
|
||||
|
||||
@@ -200,6 +200,7 @@ fn run_read_with_limits(
|
||||
total_lines,
|
||||
content_hash: content_hasher.finalize().into(),
|
||||
truncated: end < total_lines || byte_truncated,
|
||||
byte_truncated,
|
||||
})
|
||||
}
|
||||
|
||||
@@ -885,6 +886,34 @@ mod bounded_read_tests {
|
||||
assert!(error.to_string().contains("exceeds provider limit 4096"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn bounded_read_distinguishes_utf8_byte_cut_from_complete_line_continuation() {
|
||||
let temp = tempfile::tempdir().unwrap();
|
||||
let root = temp.path().canonicalize().unwrap();
|
||||
fs::write(root.join("text"), "雪雪needle\nnext").unwrap();
|
||||
for (offset, max_bytes, bytes, more, cut) in [
|
||||
(0, 5, "雪", true, true),
|
||||
(0, 64, "雪雪needle\n", true, false),
|
||||
(1, 64, "next", false, false),
|
||||
] {
|
||||
let result = run_read_bounded(
|
||||
&root,
|
||||
ReadRequest {
|
||||
path: FsPath::new("text").unwrap(),
|
||||
offset,
|
||||
limit: 1,
|
||||
max_bytes,
|
||||
},
|
||||
&RootAccess(root.clone()),
|
||||
BoundedReadLimits::new(1024, 64).unwrap(),
|
||||
)
|
||||
.unwrap();
|
||||
assert_eq!(result.bytes, bytes.as_bytes());
|
||||
assert_eq!(result.truncated, more);
|
||||
assert_eq!(result.byte_truncated, cut);
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn bounded_read_caps_retained_response_independently_of_request() {
|
||||
let temp = tempfile::tempdir().unwrap();
|
||||
@@ -907,6 +936,7 @@ mod bounded_read_tests {
|
||||
assert_eq!(result.bytes, b"alpha");
|
||||
assert_eq!(result.total_lines, 3);
|
||||
assert!(result.truncated);
|
||||
assert!(result.byte_truncated);
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -204,7 +204,11 @@ pub struct ReadResult {
|
||||
#[schemars(range(min = 0, max = 9_007_199_254_740_991_usize))]
|
||||
pub total_lines: usize,
|
||||
pub content_hash: ContentHash,
|
||||
/// More source lines remain, or the selected window exceeded the response byte budget.
|
||||
pub truncated: bool,
|
||||
/// The selected line window was cut by its byte budget, possibly within a line.
|
||||
/// Line-based cursors must not treat such a window as completely scanned.
|
||||
pub byte_truncated: bool,
|
||||
}
|
||||
|
||||
/// Binary-safe byte range read with an optional whole-file version fence.
|
||||
|
||||
@@ -100,21 +100,6 @@ pub fn worker_allocation_path() -> Option<PathBuf> {
|
||||
worker_allocation_path_from_runtime_dir(runtime_dir())
|
||||
}
|
||||
|
||||
/// `<runtime_dir>/<worker_name>/` — per-Worker runtime directory.
|
||||
pub fn worker_runtime_dir(worker_name: &str) -> Option<PathBuf> {
|
||||
worker_runtime_dir_from_runtime_dir(runtime_dir(), worker_name)
|
||||
}
|
||||
|
||||
/// `<runtime_dir>/<worker_name>/sock` — Worker's Unix socket path.
|
||||
///
|
||||
/// The `worker` crate's `RuntimeDir::socket_path()` creates the socket inside the
|
||||
/// Worker process. This function **predicts** the path for external callers that
|
||||
/// know the Worker name, such as the TUI attach flow. Both should return the same
|
||||
/// path.
|
||||
pub fn worker_socket_path(worker_name: &str) -> Option<PathBuf> {
|
||||
worker_socket_path_from_runtime_dir(runtime_dir(), worker_name)
|
||||
}
|
||||
|
||||
// ---- internals --------------------------------------------------------------
|
||||
|
||||
fn resolve_config_dir_from_parts(
|
||||
@@ -204,20 +189,6 @@ fn worker_allocation_path_from_runtime_dir(runtime_dir: Option<PathBuf>) -> Opti
|
||||
Some(runtime_dir?.join("workers.json"))
|
||||
}
|
||||
|
||||
fn worker_runtime_dir_from_runtime_dir(
|
||||
runtime_dir: Option<PathBuf>,
|
||||
worker_name: &str,
|
||||
) -> Option<PathBuf> {
|
||||
Some(runtime_dir?.join(worker_name))
|
||||
}
|
||||
|
||||
fn worker_socket_path_from_runtime_dir(
|
||||
runtime_dir: Option<PathBuf>,
|
||||
worker_name: &str,
|
||||
) -> Option<PathBuf> {
|
||||
Some(worker_runtime_dir_from_runtime_dir(runtime_dir, worker_name)?.join("sock"))
|
||||
}
|
||||
|
||||
/// Treats empty environment values as unset. `std::env::var` distinguishes
|
||||
/// `Ok("")` from `Err(NotPresent)`, but path resolution treats both as unset
|
||||
/// for intuitive behavior.
|
||||
@@ -455,16 +426,8 @@ mod tests {
|
||||
PathBuf::from("/sand/sessions")
|
||||
);
|
||||
assert_eq!(
|
||||
worker_allocation_path_from_runtime_dir(runtime_dir.clone()).unwrap(),
|
||||
worker_allocation_path_from_runtime_dir(runtime_dir).unwrap(),
|
||||
PathBuf::from("/sand/run/workers.json")
|
||||
);
|
||||
assert_eq!(
|
||||
worker_runtime_dir_from_runtime_dir(runtime_dir.clone(), "foo").unwrap(),
|
||||
PathBuf::from("/sand/run/foo")
|
||||
);
|
||||
assert_eq!(
|
||||
worker_socket_path_from_runtime_dir(runtime_dir, "foo").unwrap(),
|
||||
PathBuf::from("/sand/run/foo/sock")
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1746,7 +1746,7 @@ mod tests {
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn builtin_orchestrator_keeps_cleanup_tool_providers_enabled() {
|
||||
fn builtin_orchestrator_enables_reviewer_handoff_and_cleanup_without_self_review() {
|
||||
let tmp = TempDir::new().unwrap();
|
||||
let resolved = ProfileResolver::new()
|
||||
.with_workspace_base(tmp.path())
|
||||
@@ -1757,6 +1757,7 @@ mod tests {
|
||||
.unwrap();
|
||||
let feature = resolved.manifest.feature;
|
||||
|
||||
assert!(feature.sub_worker.enabled);
|
||||
assert!(feature.worker.enabled);
|
||||
assert!(!feature.worker.direct_spawn);
|
||||
assert!(feature.manage_workdir.enabled);
|
||||
|
||||
@@ -826,7 +826,7 @@ impl MergeRequestStore {
|
||||
));
|
||||
}
|
||||
let mr = self.get_for_operation(&i.auth.workspace_id, &i.merge_request_id, &i.ticket_id)?;
|
||||
self.assigned(&i.auth, &i.ticket_id, &mr.repository_id)?;
|
||||
self.current_assignment_auth(&i.auth, &i.ticket_id, &mr.repository_id)?;
|
||||
if mr.state == MergeRequestState::Closed
|
||||
|| (mr.state == MergeRequestState::Open && mr.selector_from.is_none())
|
||||
{
|
||||
@@ -1035,7 +1035,7 @@ impl MergeRequestStore {
|
||||
) -> Result<ReviewRevokedEvent, MergeRequestError> {
|
||||
bounded_body("revocation reason", &i.reason)?;
|
||||
let mr = self.get_for_operation(&i.auth.workspace_id, &i.merge_request_id, &i.ticket_id)?;
|
||||
self.assigned(&i.auth, &i.ticket_id, &mr.repository_id)?;
|
||||
self.current_assignment_auth(&i.auth, &i.ticket_id, &mr.repository_id)?;
|
||||
let r = mr
|
||||
.thread
|
||||
.iter()
|
||||
@@ -1152,7 +1152,7 @@ impl MergeRequestStore {
|
||||
"operation fingerprint mismatch".into(),
|
||||
));
|
||||
}
|
||||
self.completion_auth(&i.auth, &i.ticket_id, &mr.repository_id)?;
|
||||
self.current_assignment_auth(&i.auth, &i.ticket_id, &mr.repository_id)?;
|
||||
if mr.state != MergeRequestState::Open {
|
||||
return Err(MergeRequestError::Conflict(
|
||||
"Merge Request is not open".into(),
|
||||
@@ -1186,7 +1186,7 @@ impl MergeRequestStore {
|
||||
));
|
||||
}
|
||||
// Case openness is not an integration phase. Exact source approval,
|
||||
// current Ticket content and active assignment fencing above remain
|
||||
// current Ticket content and current assignment fencing above remain
|
||||
// the independent MR integration guards.
|
||||
Ok(())
|
||||
}
|
||||
@@ -1229,7 +1229,7 @@ impl MergeRequestStore {
|
||||
}
|
||||
let assignment_is_current: bool = transaction.query_row(
|
||||
"SELECT EXISTS(
|
||||
SELECT 1 FROM ticket_active_worker_assignments
|
||||
SELECT 1 FROM ticket_current_worker_assignments
|
||||
WHERE workspace_id=?1 AND ticket_id=?2 AND assignment_id=?3
|
||||
)",
|
||||
params![i.auth.workspace_id, i.ticket_id, i.auth.assignment_id],
|
||||
@@ -1548,7 +1548,7 @@ impl MergeRequestStore {
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
fn completion_auth(
|
||||
fn current_assignment_auth(
|
||||
&self,
|
||||
a: &MergeRequestAuth,
|
||||
t: &str,
|
||||
|
||||
@@ -1,3 +1,6 @@
|
||||
//! Check the shipped templates against the real PDK and WIT for the guest target.
|
||||
//! Each check owns its source and lockfile; Cargo alone shares and validates artifacts.
|
||||
|
||||
use std::fs;
|
||||
use std::path::Path;
|
||||
use std::process::Command;
|
||||
@@ -135,36 +138,86 @@ fn embedded_service_template_cargo_checks_for_wasm_target() {
|
||||
|
||||
fn cargo_check_template(template: &str) {
|
||||
let crate_dir = Path::new(env!("CARGO_MANIFEST_DIR"));
|
||||
let template_dir = crate_dir.join(format!("../../resources/plugin/templates/{template}"));
|
||||
let manifest_path = template_dir.join("Cargo.toml");
|
||||
let lock_path = template_dir.join("Cargo.lock");
|
||||
let _ = fs::remove_file(&lock_path);
|
||||
let templates_dir = crate_dir.join("../../resources/plugin/templates");
|
||||
let template_dir = templates_dir.join(template);
|
||||
|
||||
let target_dir = tempfile::tempdir().expect("temporary cargo target dir");
|
||||
let cargo = std::env::var("CARGO").unwrap_or_else(|_| "cargo".to_string());
|
||||
let output = Command::new(cargo)
|
||||
// A sibling fixture preserves the shipped relative PDK and WIT paths verbatim.
|
||||
// Never create or remove a lockfile in the shipped template: another invocation
|
||||
// may be checking it at the same time, or a developer may own that lockfile.
|
||||
let fixture = tempfile::Builder::new()
|
||||
.prefix(".cargo-check-")
|
||||
.tempdir_in(&templates_dir)
|
||||
.expect("temporary template fixture");
|
||||
copy_template_tree(&template_dir, fixture.path(), true);
|
||||
|
||||
// Both templates share the PDK dependencies. A separate persistent target
|
||||
// reuses those artifacts without sharing source or the outer Cargo build lock.
|
||||
// Cargo fingerprints and its target lock handle changes and concurrent checks.
|
||||
let executable = std::env::current_exe().expect("current test executable");
|
||||
let target_dir = executable
|
||||
.parent()
|
||||
.and_then(|deps| deps.parent())
|
||||
.expect("test executable has a profile directory")
|
||||
.join("compile-tests/plugin-pdk-templates");
|
||||
let output = Command::new(env!("CARGO"))
|
||||
.arg("check")
|
||||
.arg("--manifest-path")
|
||||
.arg(&manifest_path)
|
||||
.arg(fixture.path().join("Cargo.toml"))
|
||||
.arg("--target")
|
||||
.arg("wasm32-unknown-unknown")
|
||||
.arg("--offline")
|
||||
.arg("--target-dir")
|
||||
.arg(target_dir.path())
|
||||
.arg(target_dir)
|
||||
.current_dir(fixture.path())
|
||||
.env("CARGO_TERM_COLOR", "never")
|
||||
.output()
|
||||
.expect("spawn cargo check for embedded template");
|
||||
|
||||
let _ = fs::remove_file(&lock_path);
|
||||
assert!(
|
||||
output.status.success(),
|
||||
"template cargo check failed\nstatus: {}\nstdout:\n{}\nstderr:\n{}",
|
||||
"template {template} cargo check failed\nstatus: {}\nstdout:\n{}\nstderr:\n{}",
|
||||
output.status,
|
||||
String::from_utf8_lossy(&output.stdout),
|
||||
String::from_utf8_lossy(&output.stderr)
|
||||
);
|
||||
}
|
||||
|
||||
fn copy_template_tree(source: &Path, destination: &Path, is_root: bool) {
|
||||
let metadata = fs::symlink_metadata(source).expect("read template directory metadata");
|
||||
assert!(
|
||||
metadata.is_dir() && !metadata.file_type().is_symlink(),
|
||||
"template input must be a real directory: {}",
|
||||
source.display()
|
||||
);
|
||||
for entry in fs::read_dir(source).expect("read template directory") {
|
||||
let entry = entry.expect("read template entry");
|
||||
let path = entry.path();
|
||||
let kind = entry.file_type().expect("read template entry type");
|
||||
assert!(
|
||||
!kind.is_symlink() && (kind.is_dir() || kind.is_file()),
|
||||
"unsupported template input (including symlinks): {}",
|
||||
path.display()
|
||||
);
|
||||
|
||||
let name = entry.file_name();
|
||||
// Preserve all compiler inputs, including build scripts and nested assets.
|
||||
// Only omit the root build output and lockfile: each isolated consumer must
|
||||
// resolve its own lockfile, as the original unlocked template check did.
|
||||
if is_root
|
||||
&& ((kind.is_dir() && name == "target") || (kind.is_file() && name == "Cargo.lock"))
|
||||
{
|
||||
continue;
|
||||
}
|
||||
let copied = destination.join(name);
|
||||
if kind.is_dir() {
|
||||
fs::create_dir(&copied).expect("create template fixture directory");
|
||||
copy_template_tree(&path, &copied, false);
|
||||
} else {
|
||||
fs::copy(&path, &copied).expect("copy unmodified template input");
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn pdk_runtime_dependencies_are_guest_side_only() {
|
||||
let cargo: Value = toml::from_str(PDK_CARGO).expect("PDK Cargo.toml parses");
|
||||
|
||||
+81
-26
@@ -52,7 +52,7 @@ pub enum AuthenticatedInputSource {
|
||||
/// Assigned whenever a serialized tracked method crosses an untrusted
|
||||
/// protocol boundary. Receivers must handle it exactly like public input.
|
||||
UntrustedWire,
|
||||
/// Stamped only by the operator-owned standalone in-process transport.
|
||||
/// Stamped only by the operator-owned Standalone Host after local admission.
|
||||
/// This is not a Backend Account or authority accepted from wire fields.
|
||||
LocalOperator,
|
||||
Account {
|
||||
@@ -399,16 +399,13 @@ pub enum Method {
|
||||
|
||||
/// Typed lifecycle events sent from a child Worker to its parent.
|
||||
///
|
||||
/// Delivered as `Method::WorkerEvent` over the parent's Unix socket. The
|
||||
/// parent Controller always applies variant-specific side effects
|
||||
/// (registry / worker-allocation updates). Agent-visible variants are also
|
||||
/// queued into the notification buffer; control-plane-only variants are
|
||||
/// not injected into the parent's LLM context.
|
||||
/// Delivered in-process to the parent Controller's protocol intake. Agent-visible variants
|
||||
/// are queued into the notification buffer. Reports are advisory: receivers must check the
|
||||
/// actual child session before treating its work as complete.
|
||||
///
|
||||
/// Transport is fire-and-forget; receivers must tolerate out-of-order
|
||||
/// delivery (e.g. `TurnEnded` arriving after `ShutDown` for the same
|
||||
/// child Worker).
|
||||
#[derive(Debug, Clone, Serialize, Deserialize)]
|
||||
/// Retained legacy control-only variants can be decoded from saved history, but do not
|
||||
/// register live children, delegate scope, or establish a socket callback.
|
||||
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq)]
|
||||
#[cfg_attr(feature = "typescript", derive(ts_rs::TS))]
|
||||
#[cfg_attr(feature = "json-schema", derive(schemars::JsonSchema))]
|
||||
#[serde(tag = "kind", rename_all = "snake_case")]
|
||||
@@ -429,16 +426,8 @@ pub enum WorkerEvent {
|
||||
/// Child has stopped (controller loop is exiting).
|
||||
ShutDown { worker_name: String },
|
||||
|
||||
/// Child SubWorker sub-delegated scope to a grandchild SubWorker via `SubWorkerSpawn`.
|
||||
///
|
||||
/// Control-plane only: receivers apply registry side effects and
|
||||
/// propagate upward, but do not expose this as an agent notification.
|
||||
///
|
||||
/// The parent uses this to add the grandchild to its own
|
||||
/// `spawned_workers.json` so it can manage the grandchild directly
|
||||
/// even if the intermediate child dies. The parent then re-fires
|
||||
/// this event upward (if it has a parent of its own) to maintain
|
||||
/// the chain to root.
|
||||
/// Legacy process-child scope report retained for saved Session decoding only.
|
||||
/// Live Controllers ignore it; only the Host-owned Internal registry grants child scope.
|
||||
ScopeSubDelegated {
|
||||
/// Sub-delegating Worker (= the sender itself).
|
||||
parent_worker: String,
|
||||
@@ -982,6 +971,17 @@ pub enum SessionEntryProvenance {
|
||||
LegacyUnknown,
|
||||
}
|
||||
|
||||
/// Public use decisions contain no Feature identity or private payload. Absence
|
||||
/// denotes the older projection contract, not permission to expose System input.
|
||||
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[cfg_attr(feature = "typescript", derive(ts_rs::TS))]
|
||||
#[cfg_attr(feature = "json-schema", derive(schemars::JsonSchema))]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct SessionEntryUsePolicy {
|
||||
pub observation_readable: bool,
|
||||
pub memory_evidence: bool,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
|
||||
#[cfg_attr(feature = "typescript", derive(ts_rs::TS))]
|
||||
#[cfg_attr(feature = "json-schema", derive(schemars::JsonSchema))]
|
||||
@@ -994,6 +994,8 @@ pub struct SessionSnapshotEntry {
|
||||
pub provenance: SessionEntryProvenance,
|
||||
#[serde(default, skip_serializing_if = "Vec::is_empty")]
|
||||
pub derived_from: Vec<String>,
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub use_policy: Option<SessionEntryUsePolicy>,
|
||||
#[serde(flatten)]
|
||||
pub data: SessionSnapshotEntryData,
|
||||
}
|
||||
@@ -1180,12 +1182,10 @@ pub enum Event {
|
||||
},
|
||||
/// One agent-injected system item committed to history.
|
||||
///
|
||||
/// Carries the JSON form of `session_store::SystemItem`. Covers
|
||||
/// `Method::Notify` echoes, child-Worker lifecycle events from
|
||||
/// `Method::WorkerEvent`, `@<path>` resolution payloads, and any future
|
||||
/// Clients dispatch on the `kind` tag for typed rendering instead
|
||||
/// of parsing free-text prefixes like `[Notification] …` or
|
||||
/// `[File: …]`.
|
||||
/// Carries the allowlisted JSON form of `session_store::PublicSystemItem`,
|
||||
/// not the storage record. Its descriptive `kind` is independent from the
|
||||
/// typed `presentation` used for notification, reminder, or context rendering.
|
||||
/// Private Feature payloads and prompt provenance are never event data.
|
||||
///
|
||||
/// One event per `LogEntry::AnnotatedSystemItem` commit. Disk-side and
|
||||
/// wire-side are 1:1.
|
||||
@@ -1497,6 +1497,11 @@ pub enum Event {
|
||||
#[cfg_attr(feature = "typescript", derive(ts_rs::TS))]
|
||||
#[cfg_attr(feature = "json-schema", derive(schemars::JsonSchema))]
|
||||
pub struct Alert {
|
||||
/// Stable only within the emitting live Worker; not durable alert history.
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub id: Option<String>,
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub position: Option<AlertPosition>,
|
||||
pub level: AlertLevel,
|
||||
pub source: AlertSource,
|
||||
pub message: String,
|
||||
@@ -1504,6 +1509,18 @@ pub struct Alert {
|
||||
pub timestamp_ms: i64,
|
||||
}
|
||||
|
||||
/// Display anchor captured at emission, resolved when pending text is committed.
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[cfg_attr(feature = "typescript", derive(ts_rs::TS))]
|
||||
#[cfg_attr(feature = "json-schema", derive(schemars::JsonSchema))]
|
||||
#[serde(tag = "kind", rename_all = "snake_case")]
|
||||
pub enum AlertPosition {
|
||||
Start,
|
||||
AfterEntry { entry_id: String },
|
||||
AfterToolCall { call_id: String },
|
||||
AfterInFlight { block_id: u64 },
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, Serialize, Deserialize)]
|
||||
#[cfg_attr(feature = "typescript", derive(ts_rs::TS))]
|
||||
#[cfg_attr(feature = "json-schema", derive(schemars::JsonSchema))]
|
||||
@@ -1704,6 +1721,9 @@ pub struct InFlightCompaction {
|
||||
#[cfg_attr(feature = "typescript", derive(ts_rs::TS))]
|
||||
#[cfg_attr(feature = "json-schema", derive(schemars::JsonSchema))]
|
||||
pub struct InFlightSnapshot {
|
||||
/// Live-Worker identities parallel to the blocks actually included below.
|
||||
#[serde(default, skip_serializing_if = "Vec::is_empty")]
|
||||
pub block_ids: Vec<u64>,
|
||||
#[serde(default, skip_serializing_if = "Vec::is_empty")]
|
||||
pub blocks: Vec<InFlightBlock>,
|
||||
#[serde(default, skip_serializing_if = "Vec::is_empty")]
|
||||
@@ -2601,6 +2621,7 @@ mod tests {
|
||||
session: SessionSnapshot {
|
||||
pending_submissions: PendingSubmissionsSnapshot::default(),
|
||||
entries: vec![SessionSnapshotEntry {
|
||||
use_policy: None,
|
||||
entry_id: "entry-1".into(),
|
||||
timestamp: 1,
|
||||
provenance: SessionEntryProvenance::HumanInput,
|
||||
@@ -2721,6 +2742,7 @@ mod tests {
|
||||
},
|
||||
state: WorkerStatus::Running.into(),
|
||||
in_flight: InFlightSnapshot {
|
||||
block_ids: Vec::new(),
|
||||
blocks: vec![
|
||||
InFlightBlock::Text {
|
||||
text: "hel".into(),
|
||||
@@ -3048,9 +3070,42 @@ mod tests {
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn alert_ordering_metadata_is_optional_and_uses_tagged_wire_anchors() {
|
||||
let legacy = serde_json::json!({ "level": "warn", "source": "worker", "message": "old", "timestamp_ms": 42 });
|
||||
let alert: Alert = serde_json::from_value(legacy.clone()).unwrap();
|
||||
assert!(alert.id.is_none());
|
||||
assert!(alert.position.is_none());
|
||||
assert_eq!(serde_json::to_value(alert).unwrap(), legacy);
|
||||
for position in [
|
||||
serde_json::json!({ "kind": "start" }),
|
||||
serde_json::json!({ "kind": "after_entry", "entry_id": "entry-1" }),
|
||||
serde_json::json!({ "kind": "after_tool_call", "call_id": "call-1" }),
|
||||
serde_json::json!({ "kind": "after_in_flight", "block_id": 7 }),
|
||||
] {
|
||||
let mut wire = legacy.clone();
|
||||
wire["id"] = serde_json::json!("alert-1");
|
||||
wire["position"] = position;
|
||||
let alert: Alert = serde_json::from_value(wire.clone()).unwrap();
|
||||
assert_eq!(serde_json::to_value(alert).unwrap(), wire);
|
||||
}
|
||||
let old_snapshot: InFlightSnapshot = serde_json::from_value(serde_json::json!({})).unwrap();
|
||||
assert!(old_snapshot.block_ids.is_empty());
|
||||
assert_eq!(
|
||||
serde_json::to_value(old_snapshot).unwrap(),
|
||||
serde_json::json!({})
|
||||
);
|
||||
let wire =
|
||||
serde_json::json!({"blocks": [{"kind": "text", "text": "pending"}], "block_ids": [7]});
|
||||
let snapshot: InFlightSnapshot = serde_json::from_value(wire.clone()).unwrap();
|
||||
assert_eq!(serde_json::to_value(snapshot).unwrap(), wire);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn event_alert_format() {
|
||||
let event = Event::Alert(Alert {
|
||||
id: None,
|
||||
position: None,
|
||||
level: AlertLevel::Warn,
|
||||
source: AlertSource::Compactor,
|
||||
message: "compaction failed".into(),
|
||||
|
||||
@@ -4,25 +4,25 @@ use serde_json::{Map, Value};
|
||||
use ts_rs::{Config, TS};
|
||||
|
||||
use crate::{
|
||||
Alert, AlertLevel, AlertSource, CommandEvent, CommandSnapshot, CommandStatus, CommandStream,
|
||||
CommandStreamSlice, CompactionLifecycle, CompactionLifecycleState, CompactionPhase,
|
||||
CompactionTrigger, CompletionContext, CompletionEntry, CompletionKind, ContextTokenSource,
|
||||
ContextUsage, ErrorCode, Event, FeatureInvocation, FeatureInvocationDescriptor,
|
||||
FeatureInvocationIdentity, FeatureInvocationResult, FeatureInvocationStatus,
|
||||
FeatureInvocationSyntax, Greeting, InFlightBlock, InFlightCompaction, InFlightSnapshot,
|
||||
InFlightToolCallState, InternalWorkerKind, InternalWorkerRef, InternalWorkerSnapshot,
|
||||
InvocationArgumentDescriptor, InvocationArgumentType, InvocationArgumentValue,
|
||||
InvocationClientAdapter, InvocationCompletion, InvocationValue, InvokeKind, MemoryWorkerEvent,
|
||||
Method, PasteArtifactAvailability, PasteArtifactMediaType, PasteArtifactRef,
|
||||
PendingSubmissionSummary, PendingSubmissionsSnapshot, Permission, ReasoningConfig,
|
||||
RewindSummary, RunFailureKind, RunResult, RunResumeSource, RunYieldReason, ScopeRule, Segment,
|
||||
SessionContentPart, SessionConversationTurn, SessionEntryProvenance,
|
||||
SessionHistoryLineageBoundary, SessionHistoryPage, SessionMessageRole, SessionSnapshot,
|
||||
SessionSnapshotEntry, SessionSnapshotEntryData, SessionToolAttachment, SubmissionDisposition,
|
||||
SymlinkPolicy, ToolResultDisposition, TurnResult, UploadedFileAvailability, UploadedFileRef,
|
||||
WorkerBusyState, WorkerCommandAcknowledgement, WorkerCommandDisposition, WorkerCommandEnvelope,
|
||||
WorkerCommandKind, WorkerEvent, WorkerMaintenanceState, WorkerRunState, WorkerState,
|
||||
WorkerStateSnapshot, WorkerStatus,
|
||||
Alert, AlertLevel, AlertPosition, AlertSource, CommandEvent, CommandSnapshot, CommandStatus,
|
||||
CommandStream, CommandStreamSlice, CompactionLifecycle, CompactionLifecycleState,
|
||||
CompactionPhase, CompactionTrigger, CompletionContext, CompletionEntry, CompletionKind,
|
||||
ContextTokenSource, ContextUsage, ErrorCode, Event, FeatureInvocation,
|
||||
FeatureInvocationDescriptor, FeatureInvocationIdentity, FeatureInvocationResult,
|
||||
FeatureInvocationStatus, FeatureInvocationSyntax, Greeting, InFlightBlock, InFlightCompaction,
|
||||
InFlightSnapshot, InFlightToolCallState, InternalWorkerKind, InternalWorkerRef,
|
||||
InternalWorkerSnapshot, InvocationArgumentDescriptor, InvocationArgumentType,
|
||||
InvocationArgumentValue, InvocationClientAdapter, InvocationCompletion, InvocationValue,
|
||||
InvokeKind, MemoryWorkerEvent, Method, PasteArtifactAvailability, PasteArtifactMediaType,
|
||||
PasteArtifactRef, PendingSubmissionSummary, PendingSubmissionsSnapshot, Permission,
|
||||
ReasoningConfig, RewindSummary, RunFailureKind, RunResult, RunResumeSource, RunYieldReason,
|
||||
ScopeRule, Segment, SessionContentPart, SessionConversationTurn, SessionEntryProvenance,
|
||||
SessionEntryUsePolicy, SessionHistoryLineageBoundary, SessionHistoryPage, SessionMessageRole,
|
||||
SessionSnapshot, SessionSnapshotEntry, SessionSnapshotEntryData, SessionToolAttachment,
|
||||
SubmissionDisposition, SymlinkPolicy, ToolResultDisposition, TurnResult,
|
||||
UploadedFileAvailability, UploadedFileRef, WorkerBusyState, WorkerCommandAcknowledgement,
|
||||
WorkerCommandDisposition, WorkerCommandEnvelope, WorkerCommandKind, WorkerEvent,
|
||||
WorkerMaintenanceState, WorkerRunState, WorkerState, WorkerStateSnapshot, WorkerStatus,
|
||||
subscription::{
|
||||
EventSubscriptionSelector, MAX_CORRELATION_ID_BYTES, MAX_REJECTION_MESSAGE_BYTES,
|
||||
MAX_RESOURCE_ID_BYTES, MAX_SUBSCRIPTION_COLLECTION_ITEMS,
|
||||
@@ -65,6 +65,7 @@ pub fn generated_protocol_types() -> String {
|
||||
);
|
||||
|
||||
push_decl::<AlertLevel>(&cfg, &mut output);
|
||||
push_decl::<AlertPosition>(&cfg, &mut output);
|
||||
push_decl::<AlertSource>(&cfg, &mut output);
|
||||
push_decl::<CompletionKind>(&cfg, &mut output);
|
||||
push_decl::<CompletionContext>(&cfg, &mut output);
|
||||
@@ -116,6 +117,7 @@ pub fn generated_protocol_types() -> String {
|
||||
push_decl::<InFlightCompaction>(&cfg, &mut output);
|
||||
push_decl::<InFlightSnapshot>(&cfg, &mut output);
|
||||
push_decl::<SessionEntryProvenance>(&cfg, &mut output);
|
||||
push_decl::<SessionEntryUsePolicy>(&cfg, &mut output);
|
||||
push_decl::<SessionMessageRole>(&cfg, &mut output);
|
||||
push_decl::<SessionContentPart>(&cfg, &mut output);
|
||||
push_decl::<SessionToolAttachment>(&cfg, &mut output);
|
||||
|
||||
@@ -425,6 +425,8 @@ pub struct BackendJobExecutionBinding {
|
||||
pub input_digest: Option<String>,
|
||||
#[serde(default)]
|
||||
pub subjektiv_consolidation: bool,
|
||||
#[serde(default)]
|
||||
pub subjektiv_journal: bool,
|
||||
}
|
||||
|
||||
#[derive(Clone, Debug, Deserialize, Eq, PartialEq, Serialize)]
|
||||
@@ -516,9 +518,10 @@ pub struct WorkerRestorePreparation {
|
||||
pub workspace_api: Option<WorkspaceApiRef>,
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub workdir_attachments: Option<Vec<LogicalWorkdirAttachment>>,
|
||||
/// Retained in saved Restore intents; Restore does not apply Repository access.
|
||||
#[serde(default, skip_serializing_if = "Vec::is_empty")]
|
||||
pub repository_access: Vec<WorkingDirectoryRepositoryAccessRequest>,
|
||||
/// Read-only references resolved by Workspace only after this operation owns admission.
|
||||
/// Retained references from saved resource preparation, not Restore prerequisites.
|
||||
#[serde(default, skip_serializing_if = "Vec::is_empty")]
|
||||
pub repository_access_workdirs: Vec<RepositoryAccessWorkdirReference>,
|
||||
}
|
||||
@@ -712,6 +715,8 @@ pub struct WorkerSessionArchiveManifest {
|
||||
pub source_runtime_id: String,
|
||||
pub source_worker_id: WorkerId,
|
||||
pub source_session_id: String,
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub source_active_segment_id: Option<String>,
|
||||
pub segment_ids: Vec<String>,
|
||||
pub source_created_at: String,
|
||||
pub removed_at: String,
|
||||
@@ -787,6 +792,118 @@ pub enum SessionPublicSource {
|
||||
Archived { archive_id: String },
|
||||
}
|
||||
|
||||
/// Canonical Session metadata, distinct from Memory's evidence/public-index projection.
|
||||
/// `origin_json` is the exact serialized saved origin; it is not model-authored evidence.
|
||||
#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize)]
|
||||
pub struct SessionMaterialDescriptor {
|
||||
pub segment_id: String,
|
||||
pub entry_ref: String,
|
||||
pub canonical_order: u64,
|
||||
pub origin_json: String,
|
||||
pub sha256: String,
|
||||
pub total_bytes: u64,
|
||||
}
|
||||
|
||||
/// Explicit Host erasure, distinct from ordinary retention policy or pin release.
|
||||
#[derive(Clone, Debug, Serialize, Deserialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct SessionMaterialEraseRequest {
|
||||
pub workspace_id: String,
|
||||
pub source: SessionPublicSource,
|
||||
pub expected_session_id: String,
|
||||
}
|
||||
|
||||
/// Acknowledges the permanent fence and physical erasure of Session originals,
|
||||
/// including archived diagnostics bound to the same removal operations. Historical
|
||||
/// retention receipts remain immutable; their old retained flags are not current availability.
|
||||
#[derive(Clone, Debug, Serialize, Deserialize)]
|
||||
pub struct SessionMaterialEraseResponse {
|
||||
pub session_id: String,
|
||||
}
|
||||
|
||||
#[derive(Clone, Debug, Serialize, Deserialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct SessionMaterialPinRequest {
|
||||
pub workspace_id: String,
|
||||
pub source: SessionPublicSource,
|
||||
pub expected_session_id: String,
|
||||
pub pin_id: String,
|
||||
}
|
||||
|
||||
#[derive(Clone, Debug, Serialize, Deserialize)]
|
||||
pub struct SessionMaterialPinResponse {
|
||||
pub session_id: String,
|
||||
pub pin_id: String,
|
||||
}
|
||||
|
||||
#[derive(Clone, Debug, Serialize, Deserialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct SessionMaterialCatalogRequest {
|
||||
pub workspace_id: String,
|
||||
pub source: SessionPublicSource,
|
||||
pub expected_session_id: String,
|
||||
pub expected_catalog_sha256: Option<String>,
|
||||
pub offset: u64,
|
||||
pub limit: usize,
|
||||
}
|
||||
|
||||
#[derive(Clone, Debug, Serialize, Deserialize)]
|
||||
pub struct SessionMaterialCatalogPage {
|
||||
pub session_id: String,
|
||||
pub active_segment_id: String,
|
||||
pub catalog_sha256: String,
|
||||
pub descriptors: Vec<SessionMaterialDescriptor>,
|
||||
pub next_offset: Option<u64>,
|
||||
}
|
||||
|
||||
#[derive(Clone, Debug, Serialize, Deserialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct SessionMaterialReadRequest {
|
||||
pub workspace_id: String,
|
||||
pub source: SessionPublicSource,
|
||||
pub expected_session_id: String,
|
||||
/// Compared with a freshly resolved saved descriptor, never adopted as evidence.
|
||||
pub expected_descriptor: SessionMaterialDescriptor,
|
||||
pub byte_offset: u64,
|
||||
pub max_content_bytes: usize,
|
||||
}
|
||||
|
||||
#[derive(Clone, Debug, Serialize, Deserialize)]
|
||||
pub struct SessionMaterialReadPage {
|
||||
pub descriptor: SessionMaterialDescriptor,
|
||||
pub content: String,
|
||||
pub next_offset: u64,
|
||||
}
|
||||
|
||||
#[derive(Clone, Debug, Serialize, Deserialize)]
|
||||
#[serde(tag = "availability", rename_all = "snake_case")]
|
||||
pub enum SessionMaterialCatalogAvailability {
|
||||
/// The saved active pointer is pending and storage proves no Session material
|
||||
/// has ever been published. Missing/corrupt materialized sources are not empty.
|
||||
NotMaterialized {
|
||||
session_id: String,
|
||||
},
|
||||
Page {
|
||||
page: SessionMaterialCatalogPage,
|
||||
},
|
||||
Unavailable {
|
||||
reason: SessionPublicUnavailableReason,
|
||||
message: String,
|
||||
},
|
||||
}
|
||||
|
||||
#[derive(Clone, Debug, Serialize, Deserialize)]
|
||||
#[serde(tag = "availability", rename_all = "snake_case")]
|
||||
pub enum SessionMaterialReadAvailability {
|
||||
Page {
|
||||
page: SessionMaterialReadPage,
|
||||
},
|
||||
Unavailable {
|
||||
reason: SessionPublicUnavailableReason,
|
||||
message: String,
|
||||
},
|
||||
}
|
||||
|
||||
#[derive(Clone, Copy, Debug, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(rename_all = "snake_case")]
|
||||
pub enum SessionPublicEntryKind {
|
||||
@@ -988,8 +1105,78 @@ pub enum WorkerSessionAvailability {
|
||||
},
|
||||
}
|
||||
|
||||
/// Host-owned Subject release operation. A reservation has no timeout: uncertainty retains
|
||||
/// occupancy and mutation exclusion until the same operation is explicitly reconciled.
|
||||
#[derive(Clone, Debug, Deserialize, Eq, PartialEq, Serialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct SubjectReleaseRequest {
|
||||
pub workspace_id: String,
|
||||
pub worker_id: WorkerId,
|
||||
pub binding_id: String,
|
||||
pub operation_id: String,
|
||||
pub action: SubjectReleaseAction,
|
||||
}
|
||||
|
||||
#[derive(Clone, Copy, Debug, Deserialize, Eq, PartialEq, Serialize)]
|
||||
#[serde(rename_all = "snake_case")]
|
||||
pub enum SubjectReleaseAction {
|
||||
Reserve,
|
||||
Disconnect,
|
||||
Cancel,
|
||||
}
|
||||
|
||||
#[derive(Clone, Copy, Debug, Deserialize, Eq, PartialEq, Serialize)]
|
||||
#[serde(rename_all = "snake_case")]
|
||||
pub enum SubjectReleaseState {
|
||||
Reserved,
|
||||
Disconnected,
|
||||
Cancelled,
|
||||
}
|
||||
|
||||
#[derive(Clone, Debug, Deserialize, Eq, PartialEq, Serialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct SubjectReleaseResponse {
|
||||
pub operation_id: String,
|
||||
pub binding_id: String,
|
||||
pub state: SubjectReleaseState,
|
||||
}
|
||||
|
||||
/// Irreversibly fence an unpublished failed Subject create. Exact retries must retain
|
||||
/// all four fields; this is distinct from releasing an existing Subject Controller.
|
||||
#[derive(Clone, Debug, Deserialize, Eq, PartialEq, Serialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct SubjectCreateRecoveryRequest {
|
||||
pub workspace_id: String,
|
||||
pub worker_id: WorkerId,
|
||||
pub create_fingerprint: String,
|
||||
pub operation_id: String,
|
||||
}
|
||||
|
||||
/// Durable admission-fence proof plus freshly confirmed execution absence.
|
||||
/// An error (including a lost response) is never evidence of absence.
|
||||
#[derive(Clone, Debug, Deserialize, Eq, PartialEq, Serialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct SubjectCreateRecoveryResponse {
|
||||
pub workspace_id: String,
|
||||
pub worker_id: WorkerId,
|
||||
pub create_fingerprint: String,
|
||||
pub operation_id: String,
|
||||
}
|
||||
|
||||
#[api(reqwest, axum)]
|
||||
pub trait RuntimeApi {
|
||||
#[post("/v1/subject-create-recovery", status = 200, error_status = 400)]
|
||||
async fn recover_subject_create(
|
||||
&self,
|
||||
#[body] request: SubjectCreateRecoveryRequest,
|
||||
) -> Result<SubjectCreateRecoveryResponse, RuntimeApiError>;
|
||||
|
||||
#[post("/v1/subject-release", status = 200, error_status = 400)]
|
||||
async fn subject_release(
|
||||
&self,
|
||||
#[body] request: SubjectReleaseRequest,
|
||||
) -> Result<SubjectReleaseResponse, RuntimeApiError>;
|
||||
|
||||
#[get("/v1/ping", status = 200, error_status = 400)]
|
||||
async fn ping(
|
||||
&self,
|
||||
@@ -1029,6 +1216,52 @@ pub trait RuntimeApi {
|
||||
#[query] request: WorkerSessionHistoryRequest,
|
||||
) -> Result<WorkerSessionHistoryAvailability, RuntimeApiError>;
|
||||
|
||||
#[post(
|
||||
"/v1/session-public/material/retention/erase",
|
||||
status = 200,
|
||||
error_status = 400
|
||||
)]
|
||||
async fn session_material_erase(
|
||||
&self,
|
||||
#[body] request: SessionMaterialEraseRequest,
|
||||
) -> Result<SessionMaterialEraseResponse, RuntimeApiError>;
|
||||
|
||||
#[post(
|
||||
"/v1/session-public/material/retention/pin",
|
||||
status = 200,
|
||||
error_status = 400
|
||||
)]
|
||||
async fn session_material_pin(
|
||||
&self,
|
||||
#[body] request: SessionMaterialPinRequest,
|
||||
) -> Result<SessionMaterialPinResponse, RuntimeApiError>;
|
||||
|
||||
#[post(
|
||||
"/v1/session-public/material/retention/release",
|
||||
status = 200,
|
||||
error_status = 400
|
||||
)]
|
||||
async fn session_material_release(
|
||||
&self,
|
||||
#[body] request: SessionMaterialPinRequest,
|
||||
) -> Result<SessionMaterialPinResponse, RuntimeApiError>;
|
||||
|
||||
#[post(
|
||||
"/v1/session-public/material/catalog",
|
||||
status = 200,
|
||||
error_status = 400
|
||||
)]
|
||||
async fn session_material_catalog(
|
||||
&self,
|
||||
#[body] request: SessionMaterialCatalogRequest,
|
||||
) -> Result<SessionMaterialCatalogAvailability, RuntimeApiError>;
|
||||
|
||||
#[post("/v1/session-public/material/read", status = 200, error_status = 400)]
|
||||
async fn session_material_read(
|
||||
&self,
|
||||
#[body] request: SessionMaterialReadRequest,
|
||||
) -> Result<SessionMaterialReadAvailability, RuntimeApiError>;
|
||||
|
||||
#[post("/v1/session-public/search", status = 200, error_status = 400)]
|
||||
async fn session_public_search(
|
||||
&self,
|
||||
@@ -1277,6 +1510,22 @@ pub const REMAINING_RUNTIME_ROUTES: &[RemainingRuntimeRoute] = &[
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
#[test]
|
||||
fn backend_job_journal_grant_defaults_off_and_does_not_enable_memory_grant() {
|
||||
let legacy = serde_json::json!({"job_id":"job", "attempt_id":"attempt", "subjektiv_consolidation":true});
|
||||
let binding: BackendJobExecutionBinding = serde_json::from_value(legacy).unwrap();
|
||||
assert!(binding.subjektiv_consolidation);
|
||||
assert!(!binding.subjektiv_journal);
|
||||
let journal =
|
||||
serde_json::json!({"job_id":"job", "attempt_id":"attempt", "subjektiv_journal":true});
|
||||
let binding: BackendJobExecutionBinding = serde_json::from_value(journal.clone()).unwrap();
|
||||
assert!(binding.subjektiv_journal);
|
||||
assert!(!binding.subjektiv_consolidation);
|
||||
let roundtrip: BackendJobExecutionBinding =
|
||||
serde_json::from_value(serde_json::to_value(&binding).unwrap()).unwrap();
|
||||
assert_eq!(roundtrip, binding);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn restore_request_is_mandatory_and_conflict_is_not_an_operation_state() {
|
||||
for invalid in [
|
||||
@@ -1442,6 +1691,59 @@ mod tests {
|
||||
})
|
||||
}
|
||||
|
||||
async fn session_material_erase(
|
||||
&self,
|
||||
_request: SessionMaterialEraseRequest,
|
||||
) -> Result<SessionMaterialEraseResponse, RuntimeApiError> {
|
||||
Err(test_error(501))
|
||||
}
|
||||
|
||||
async fn session_material_pin(
|
||||
&self,
|
||||
_request: SessionMaterialPinRequest,
|
||||
) -> Result<SessionMaterialPinResponse, RuntimeApiError> {
|
||||
Err(test_error(501))
|
||||
}
|
||||
async fn recover_subject_create(
|
||||
&self,
|
||||
request: SubjectCreateRecoveryRequest,
|
||||
) -> Result<SubjectCreateRecoveryResponse, RuntimeApiError> {
|
||||
Ok(SubjectCreateRecoveryResponse {
|
||||
workspace_id: request.workspace_id,
|
||||
worker_id: request.worker_id,
|
||||
create_fingerprint: request.create_fingerprint,
|
||||
operation_id: request.operation_id,
|
||||
})
|
||||
}
|
||||
|
||||
async fn subject_release(
|
||||
&self,
|
||||
_request: SubjectReleaseRequest,
|
||||
) -> Result<SubjectReleaseResponse, RuntimeApiError> {
|
||||
Err(test_error(501))
|
||||
}
|
||||
|
||||
async fn session_material_release(
|
||||
&self,
|
||||
_request: SessionMaterialPinRequest,
|
||||
) -> Result<SessionMaterialPinResponse, RuntimeApiError> {
|
||||
Err(test_error(501))
|
||||
}
|
||||
|
||||
async fn session_material_catalog(
|
||||
&self,
|
||||
_request: SessionMaterialCatalogRequest,
|
||||
) -> Result<SessionMaterialCatalogAvailability, RuntimeApiError> {
|
||||
Err(test_error(501))
|
||||
}
|
||||
|
||||
async fn session_material_read(
|
||||
&self,
|
||||
_request: SessionMaterialReadRequest,
|
||||
) -> Result<SessionMaterialReadAvailability, RuntimeApiError> {
|
||||
Err(test_error(501))
|
||||
}
|
||||
|
||||
async fn session_public_search(
|
||||
&self,
|
||||
_request: SessionPublicSearchRequest,
|
||||
@@ -1559,6 +1861,21 @@ mod tests {
|
||||
.build()
|
||||
.unwrap();
|
||||
|
||||
let recovery = SubjectCreateRecoveryRequest {
|
||||
workspace_id: "workspace-a".into(),
|
||||
worker_id: WorkerId::now_v7(),
|
||||
create_fingerprint: "failed-create-fingerprint".into(),
|
||||
operation_id: "recovery-1".into(),
|
||||
};
|
||||
let response = client
|
||||
.recover_subject_create(recovery.clone())
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(response.workspace_id, recovery.workspace_id);
|
||||
assert_eq!(response.worker_id, recovery.worker_id);
|
||||
assert_eq!(response.create_fingerprint, recovery.create_fingerprint);
|
||||
assert_eq!(response.operation_id, recovery.operation_id);
|
||||
|
||||
let summary = client.runtime_summary().await.unwrap();
|
||||
assert_eq!(summary.runtime.display_name.as_deref(), Some("round-trip"));
|
||||
let workers = client
|
||||
@@ -1603,9 +1920,8 @@ mod tests {
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn contract_inventory_is_complete_and_unique() {
|
||||
fn contract_inventory_has_unique_routes_under_api_base_path() {
|
||||
let operations = RuntimeApiMetadata::OPERATIONS;
|
||||
assert_eq!(operations.len(), 20);
|
||||
let mut routes = operations
|
||||
.iter()
|
||||
.map(|operation| (format!("{:?}", operation.method), operation.path))
|
||||
|
||||
@@ -0,0 +1,475 @@
|
||||
//! Neutral explicit-allow authorization contracts. Resource containment never crosses kinds.
|
||||
//!
|
||||
//! # Trusted Feature boundary
|
||||
//!
|
||||
//! A Profile requests execution configuration, not authority. The Worker asks the
|
||||
//! Host for each enabled Feature's exact activation name before initialization,
|
||||
//! then trusted Feature code asks for each protected operation and its semantic
|
||||
//! resource before access or effects. `ticket` on [`PermissionResource::Feature`]
|
||||
//! activates Ticket; it implies neither `ticket.create` nor any future operation.
|
||||
//! `ticket.create` on a Workspace permits creation there but cannot activate the
|
||||
//! Feature. There are no wildcard permissions or implicit dotted-name inheritance.
|
||||
//!
|
||||
//! Identity is absent from the authorization request intentionally: the Host
|
||||
//! authenticates the bound Runtime/Worker and resolves current source permissions,
|
||||
//! body ownership and any per-Worker execution grant. A shared client, Profile,
|
||||
//! remembered receipt or caller-supplied Subject claim is not authority. Features
|
||||
//! depend on this contract, never on a particular Subject policy implementation.
|
||||
//!
|
||||
//! Supported cooperative boundaries are Feature activation, ordinary Worker
|
||||
//! delegation, Ticket creation (Tool/native WIP/typed service), Workdir filesystem
|
||||
//! read/write and whole-attachment command execution, and scoped result notify.
|
||||
//! Workdir providers still enforce resolved paths, traversal, capability, Ticket
|
||||
//! and provider ceilings. The returned scope is for provider narrowing, not a
|
||||
//! transferable credential. Scoped checkout/overlap operations are refused until
|
||||
//! their complete access semantics are adapted. Other Feature operations retain
|
||||
//! their existing owner checks; they do not automatically acquire this operation
|
||||
//! policy. Missing calls are trusted Feature bugs, not interception by a universal
|
||||
//! Tool executor or protection against malicious Feature code. Connection tests
|
||||
//! must exercise each exposed surface, assert a genuine permitted effect and
|
||||
//! assert zero downstream calls on denial, including revocation and provider denial.
|
||||
//!
|
||||
//! # Delegation callers and recovery
|
||||
//!
|
||||
//! Callers such as a chat Feature supply explicit operation/resource selections
|
||||
//! and retain the same public operation ID and full request after an unknown
|
||||
//! result. Normal Profile/Worker allocation and control/resource grants are reused;
|
||||
//! there is no Subject Worker registry. Effective grants bind immutable Profile
|
||||
//! resolution, the reserved Worker and source assignment. Permission replacement
|
||||
//! invalidates existing children rather than refreshing them. Body replacement,
|
||||
//! retirement and restore must recheck current authority; historical result lookup
|
||||
//! is not new execution permission. Cancellation acceptance is distinct from
|
||||
//! terminal confirmation and does not undo completed effects.
|
||||
//!
|
||||
//! A child receives no Subject body identity, singleton, whole Memory or public
|
||||
//! conversation-post authority. `worker.result` is explicit notify authority to a
|
||||
//! named origin Worker, not arbitrary control or publication. Chat delivery and
|
||||
//! conversation correlation belong to the caller integration, not this contract.
|
||||
//! Unset existing Subject policies deny new Subject execution/delegation; ordinary
|
||||
//! non-Subject Workers explicitly retain existing Backend/provider contracts.
|
||||
//! Standalone non-Workspace activation compatibility grants no Workspace operation.
|
||||
use schemars::JsonSchema;
|
||||
use serde::{Deserialize, Serialize};
|
||||
|
||||
pub const MAX_SCOPED_PERMISSIONS: usize = 256;
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, JsonSchema)]
|
||||
#[cfg_attr(feature = "typescript", derive(ts_rs::TS))]
|
||||
#[serde(tag = "kind", rename_all = "snake_case", deny_unknown_fields)]
|
||||
pub enum PermissionResource {
|
||||
Feature,
|
||||
Workspace {
|
||||
workspace_id: String,
|
||||
},
|
||||
Workdir {
|
||||
working_directory_id: String,
|
||||
path: String,
|
||||
recursive: bool,
|
||||
},
|
||||
Worker {
|
||||
runtime_id: String,
|
||||
worker_id: String,
|
||||
},
|
||||
}
|
||||
|
||||
// Serde's internally tagged unit variants ignore extra fields even with deny_unknown_fields.
|
||||
// A struct-shaped wire variant preserves the public unit variant while rejecting those claims.
|
||||
impl<'de> Deserialize<'de> for PermissionResource {
|
||||
fn deserialize<D: serde::Deserializer<'de>>(deserializer: D) -> Result<Self, D::Error> {
|
||||
#[derive(Deserialize)]
|
||||
#[serde(tag = "kind", rename_all = "snake_case", deny_unknown_fields)]
|
||||
enum Wire {
|
||||
Feature {},
|
||||
Workspace {
|
||||
workspace_id: String,
|
||||
},
|
||||
Workdir {
|
||||
working_directory_id: String,
|
||||
path: String,
|
||||
recursive: bool,
|
||||
},
|
||||
Worker {
|
||||
runtime_id: String,
|
||||
worker_id: String,
|
||||
},
|
||||
}
|
||||
Ok(match Wire::deserialize(deserializer)? {
|
||||
Wire::Feature {} => Self::Feature,
|
||||
Wire::Workspace { workspace_id } => Self::Workspace { workspace_id },
|
||||
Wire::Workdir {
|
||||
working_directory_id,
|
||||
path,
|
||||
recursive,
|
||||
} => Self::Workdir {
|
||||
working_directory_id,
|
||||
path,
|
||||
recursive,
|
||||
},
|
||||
Wire::Worker {
|
||||
runtime_id,
|
||||
worker_id,
|
||||
} => Self::Worker {
|
||||
runtime_id,
|
||||
worker_id,
|
||||
},
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
impl PermissionResource {
|
||||
pub fn validate(&self) -> Result<(), String> {
|
||||
match self {
|
||||
Self::Feature => Ok(()),
|
||||
Self::Workspace { workspace_id } => validate_authorization_identifier(workspace_id),
|
||||
Self::Workdir {
|
||||
working_directory_id,
|
||||
path,
|
||||
..
|
||||
} => {
|
||||
validate_authorization_identifier(working_directory_id)?;
|
||||
validate_relative_permission_path(path)
|
||||
}
|
||||
Self::Worker {
|
||||
runtime_id,
|
||||
worker_id,
|
||||
} => {
|
||||
validate_authorization_identifier(runtime_id)?;
|
||||
validate_authorization_identifier(worker_id)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
pub fn covers(&self, other: &Self) -> bool {
|
||||
if self.validate().is_err() || other.validate().is_err() {
|
||||
return false;
|
||||
}
|
||||
match (self, other) {
|
||||
(Self::Feature, Self::Feature) => true,
|
||||
(Self::Workspace { workspace_id: a }, Self::Workspace { workspace_id: b }) => a == b,
|
||||
(
|
||||
Self::Worker {
|
||||
runtime_id: ar,
|
||||
worker_id: aw,
|
||||
},
|
||||
Self::Worker {
|
||||
runtime_id: br,
|
||||
worker_id: bw,
|
||||
},
|
||||
) => ar == br && aw == bw,
|
||||
(
|
||||
Self::Workdir {
|
||||
working_directory_id: a,
|
||||
path: ap,
|
||||
recursive: ar,
|
||||
},
|
||||
Self::Workdir {
|
||||
working_directory_id: b,
|
||||
path: bp,
|
||||
recursive: br,
|
||||
},
|
||||
) => {
|
||||
a == b
|
||||
&& if *ar {
|
||||
ap == "."
|
||||
|| ap == bp
|
||||
|| bp
|
||||
.strip_prefix(ap)
|
||||
.is_some_and(|tail| tail.starts_with('/'))
|
||||
} else {
|
||||
ap == bp && !br
|
||||
}
|
||||
}
|
||||
_ => false,
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize, JsonSchema)]
|
||||
#[cfg_attr(feature = "typescript", derive(ts_rs::TS))]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct ScopedPermission {
|
||||
pub operation: String,
|
||||
pub resource: PermissionResource,
|
||||
}
|
||||
|
||||
impl ScopedPermission {
|
||||
pub fn validate(&self) -> Result<(), String> {
|
||||
validate_operation_name(&self.operation)?;
|
||||
self.resource.validate()?;
|
||||
if matches!(self.resource, PermissionResource::Feature) && self.operation.contains('.') {
|
||||
return Err("Feature resources authorize activation names only, not operations".into());
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
pub fn covers(&self, other: &Self) -> bool {
|
||||
self.validate().is_ok()
|
||||
&& other.validate().is_ok()
|
||||
&& self.operation == other.operation
|
||||
&& self.resource.covers(&other.resource)
|
||||
}
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize, JsonSchema)]
|
||||
#[cfg_attr(feature = "typescript", derive(ts_rs::TS))]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct SubjectPermissions {
|
||||
pub change_id: String,
|
||||
pub execution: Vec<ScopedPermission>,
|
||||
pub delegation: Vec<ScopedPermission>,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize, JsonSchema)]
|
||||
#[cfg_attr(feature = "typescript", derive(ts_rs::TS))]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct SubjectPermissionsUpdate {
|
||||
pub operation_id: String,
|
||||
pub expected_change_id: Option<String>,
|
||||
pub execution: Vec<ScopedPermission>,
|
||||
pub delegation: Vec<ScopedPermission>,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize, JsonSchema)]
|
||||
#[cfg_attr(feature = "typescript", derive(ts_rs::TS))]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct WorkerExecutionGrant {
|
||||
pub subject_id: String,
|
||||
pub origin_runtime_id: String,
|
||||
pub origin_worker_id: String,
|
||||
pub source_change_id: String,
|
||||
pub runtime_id: String,
|
||||
pub worker_id: String,
|
||||
pub profile: String,
|
||||
pub profile_digest: String,
|
||||
pub permissions: Vec<ScopedPermission>,
|
||||
pub redelegation: Vec<ScopedPermission>,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize, JsonSchema)]
|
||||
#[cfg_attr(feature = "typescript", derive(ts_rs::TS))]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct WorkerDelegationRequest {
|
||||
pub permissions: Vec<ScopedPermission>,
|
||||
pub redelegation: Vec<ScopedPermission>,
|
||||
}
|
||||
|
||||
impl WorkerDelegationRequest {
|
||||
pub fn validate(&self) -> Result<(), String> {
|
||||
validate_scoped_permissions(&self.permissions)?;
|
||||
validate_scoped_permissions(&self.redelegation)
|
||||
}
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize, JsonSchema)]
|
||||
#[cfg_attr(feature = "typescript", derive(ts_rs::TS))]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct OperationAuthorizationRequest {
|
||||
pub operation: String,
|
||||
pub resource: PermissionResource,
|
||||
}
|
||||
|
||||
impl OperationAuthorizationRequest {
|
||||
pub fn validate(&self) -> Result<(), String> {
|
||||
ScopedPermission {
|
||||
operation: self.operation.clone(),
|
||||
resource: self.resource.clone(),
|
||||
}
|
||||
.validate()
|
||||
}
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, Default, PartialEq, Eq, Serialize, Deserialize, JsonSchema)]
|
||||
#[cfg_attr(feature = "typescript", derive(ts_rs::TS))]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct OperationAuthorizationResponse {
|
||||
/// Matching granted scope for provider-resolved checks, not a credential.
|
||||
/// `None` identifies the explicit non-Subject legacy authorization path.
|
||||
#[serde(default)]
|
||||
pub scope: Option<PermissionResource>,
|
||||
}
|
||||
|
||||
pub fn validate_operation_name(value: &str) -> Result<(), String> {
|
||||
if value.is_empty()
|
||||
|| value.len() > 256
|
||||
|| !value.split('.').all(|part| {
|
||||
!part.is_empty()
|
||||
&& part
|
||||
.bytes()
|
||||
.all(|b| b.is_ascii_alphanumeric() || b == b'_' || b == b'-')
|
||||
})
|
||||
{
|
||||
return Err(
|
||||
"permission operation must be an exact, nonempty dot-separated name (no wildcards)"
|
||||
.into(),
|
||||
);
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
pub fn validate_scoped_permissions(permissions: &[ScopedPermission]) -> Result<(), String> {
|
||||
if permissions.len() > MAX_SCOPED_PERMISSIONS {
|
||||
return Err("too many scoped permissions".into());
|
||||
}
|
||||
for permission in permissions {
|
||||
permission.validate()?;
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
pub fn validate_authorization_identifier(value: &str) -> Result<(), String> {
|
||||
if value.is_empty()
|
||||
|| value.len() > 256
|
||||
|| value.trim() != value
|
||||
|| value.chars().any(|c| c.is_control() || c == '*')
|
||||
{
|
||||
return Err("authorization identity must be nonempty, bounded and exact".into());
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Paths are already-normalized lexical paths, not host filesystem paths. The Host must
|
||||
/// still enforce symlink/provider boundaries; lexical containment grants no filesystem access.
|
||||
pub fn validate_relative_permission_path(path: &str) -> Result<(), String> {
|
||||
if path == "." {
|
||||
return Ok(());
|
||||
}
|
||||
if path.is_empty()
|
||||
|| path.len() > 4096
|
||||
|| path.contains(['\\', ':'])
|
||||
|| path.chars().any(char::is_control)
|
||||
|| path
|
||||
.split('/')
|
||||
.any(|part| part.is_empty() || part == "." || part == "..")
|
||||
{
|
||||
return Err("permission path must be a normalized relative path without escape".into());
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
fn workdir(path: &str, recursive: bool) -> PermissionResource {
|
||||
PermissionResource::Workdir {
|
||||
working_directory_id: "wd".into(),
|
||||
path: path.into(),
|
||||
recursive,
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn lexical_containment_rejects_escape_and_respects_component_and_recursion_boundaries() {
|
||||
for path in [
|
||||
"",
|
||||
"/src",
|
||||
"../src",
|
||||
"src/../secret",
|
||||
"src/./a",
|
||||
"src//a",
|
||||
"src/",
|
||||
"C:/src",
|
||||
"src\\a",
|
||||
] {
|
||||
assert!(workdir(path, true).validate().is_err(), "{path}");
|
||||
}
|
||||
let root = workdir(".", true);
|
||||
let src = workdir("src", true);
|
||||
assert!(root.covers(&src));
|
||||
assert!(src.covers(&workdir("src/a", true)));
|
||||
assert!(!src.covers(&workdir("src-other", false)));
|
||||
assert!(!workdir("src", false).covers(&src));
|
||||
assert!(workdir("src", false).covers(&workdir("src", false)));
|
||||
assert!(!workdir("src", false).covers(&workdir("src/a", false)));
|
||||
assert!(!src.covers(&PermissionResource::Workdir {
|
||||
working_directory_id: "other".into(),
|
||||
path: "src".into(),
|
||||
recursive: false
|
||||
}));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn operation_hierarchy_never_implies_inheritance_or_feature_activation() {
|
||||
for name in [
|
||||
"",
|
||||
"*",
|
||||
"ticket.*",
|
||||
".ticket",
|
||||
"ticket.",
|
||||
"ticket..read",
|
||||
"ticket read",
|
||||
] {
|
||||
assert!(validate_operation_name(name).is_err(), "{name}");
|
||||
}
|
||||
let activation = ScopedPermission {
|
||||
operation: "ticket".into(),
|
||||
resource: PermissionResource::Feature,
|
||||
};
|
||||
let create = ScopedPermission {
|
||||
operation: "ticket.create".into(),
|
||||
resource: PermissionResource::Workspace {
|
||||
workspace_id: "ws".into(),
|
||||
},
|
||||
};
|
||||
let parent_name = ScopedPermission {
|
||||
operation: "ticket".into(),
|
||||
resource: create.resource.clone(),
|
||||
};
|
||||
assert!(!parent_name.covers(&create));
|
||||
assert!(!create.covers(&parent_name));
|
||||
assert!(!activation.covers(&create));
|
||||
assert!(!create.covers(&activation));
|
||||
assert!(
|
||||
ScopedPermission {
|
||||
operation: "ticket.create".into(),
|
||||
resource: PermissionResource::Feature
|
||||
}
|
||||
.validate()
|
||||
.is_err()
|
||||
);
|
||||
assert!(
|
||||
!PermissionResource::Workspace {
|
||||
workspace_id: "ws".into()
|
||||
}
|
||||
.covers(&workdir(".", true))
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn wire_contract_rejects_self_claimed_identity_and_unknown_fields() {
|
||||
let request = serde_json::json!({"permissions":[],"redelegation":[],"subject_id":"forged"});
|
||||
assert!(serde_json::from_value::<WorkerDelegationRequest>(request).is_err());
|
||||
let resource: PermissionResource =
|
||||
serde_json::from_value(serde_json::json!({"kind":"feature"})).unwrap();
|
||||
assert_eq!(resource, PermissionResource::Feature);
|
||||
assert!(
|
||||
serde_json::from_value::<PermissionResource>(
|
||||
serde_json::json!({"kind":"feature","workspace_id":"ws"})
|
||||
)
|
||||
.is_err()
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn authorization_response_carries_matching_scope_and_defaults_legacy_absence() {
|
||||
let legacy: OperationAuthorizationResponse =
|
||||
serde_json::from_value(serde_json::json!({})).unwrap();
|
||||
assert_eq!(legacy.scope, None);
|
||||
assert_eq!(
|
||||
serde_json::to_value(legacy).unwrap(),
|
||||
serde_json::json!({"scope":null})
|
||||
);
|
||||
let granted = OperationAuthorizationResponse {
|
||||
scope: Some(workdir("src", true)),
|
||||
};
|
||||
let wire = serde_json::to_value(&granted).unwrap();
|
||||
assert_eq!(
|
||||
wire,
|
||||
serde_json::json!({"scope":{"kind":"workdir","working_directory_id":"wd","path":"src","recursive":true}})
|
||||
);
|
||||
assert_eq!(
|
||||
serde_json::from_value::<OperationAuthorizationResponse>(wire).unwrap(),
|
||||
granted
|
||||
);
|
||||
}
|
||||
}
|
||||
@@ -134,6 +134,14 @@ pub enum DriveEntryKind {
|
||||
File,
|
||||
}
|
||||
|
||||
/// Current caller's advisory publication ceiling, never a grant or execution credential.
|
||||
#[derive(Debug, Clone, Copy, Serialize, Deserialize, PartialEq, Eq, JsonSchema)]
|
||||
#[cfg_attr(feature = "typescript", derive(ts_rs::TS))]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct DriveCapabilities {
|
||||
pub write: bool,
|
||||
}
|
||||
|
||||
/// Metadata only: content is returned through bounded text or binary routes.
|
||||
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq, JsonSchema)]
|
||||
#[cfg_attr(feature = "typescript", derive(ts_rs::TS))]
|
||||
@@ -491,6 +499,7 @@ impl api_macros::HttpRequestError for DriveApiError {
|
||||
|
||||
impl api_macros::openapi::OpenApiSchema for DriveApiError {}
|
||||
impl api_macros::openapi::OpenApiSchema for DriveEntry {}
|
||||
impl api_macros::openapi::OpenApiSchema for DriveCapabilities {}
|
||||
impl api_macros::openapi::OpenApiSchema for DriveEntryQuery {}
|
||||
impl api_macros::openapi::OpenApiSchema for DriveListQuery {}
|
||||
impl api_macros::openapi::OpenApiSchema for DriveSearchQuery {}
|
||||
@@ -518,6 +527,7 @@ pub fn drive_api_typescript() -> String {
|
||||
DriveEntryRef::decl(&config),
|
||||
DriveEntryKind::decl(&config),
|
||||
DriveEntry::decl(&config),
|
||||
DriveCapabilities::decl(&config),
|
||||
DriveEntryQuery::decl(&config),
|
||||
DriveListQuery::decl(&config),
|
||||
DriveSearchQuery::decl(&config),
|
||||
|
||||
@@ -6,9 +6,12 @@ use api_macros::api;
|
||||
pub use api_macros::axum as server_support;
|
||||
pub use api_macros::reqwest as client_support;
|
||||
pub use api_macros::{ApiContract, BinaryBody, HttpMethod, TransportMetadata, WebSocketOperation};
|
||||
pub mod authorization;
|
||||
mod drive;
|
||||
mod notification;
|
||||
pub use notification::*;
|
||||
mod ticket_browse;
|
||||
pub use ticket_browse::*;
|
||||
pub mod repository_openapi_typescript;
|
||||
pub use drive::*;
|
||||
mod workspace_config;
|
||||
@@ -21,6 +24,34 @@ use webauthn_rs_proto::{
|
||||
};
|
||||
pub use workspace_config::*;
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize, JsonSchema)]
|
||||
#[cfg_attr(feature = "typescript", derive(ts_rs::TS))]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct SubjectPermissionsResponse {
|
||||
pub permissions: Option<authorization::SubjectPermissions>,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize, JsonSchema)]
|
||||
#[cfg_attr(feature = "typescript", derive(ts_rs::TS))]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct SubjectPermissionsMutationResponse {
|
||||
pub permissions: authorization::SubjectPermissions,
|
||||
/// New operations are already fenced. These are cancellation requests and
|
||||
/// Backend command cleanup evidence, not proof that a Runtime turn stopped.
|
||||
pub interruptions: Vec<SubjectPermissionInterruption>,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize, JsonSchema)]
|
||||
#[cfg_attr(feature = "typescript", derive(ts_rs::TS))]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct SubjectPermissionInterruption {
|
||||
pub runtime_id: String,
|
||||
pub worker_id: String,
|
||||
pub cancellation_accepted: bool,
|
||||
pub backend_command_sessions_closed: bool,
|
||||
pub diagnostics: Vec<String>,
|
||||
}
|
||||
|
||||
#[allow(dead_code)]
|
||||
#[derive(JsonSchema)]
|
||||
struct ServerJsonSafeU64(#[schemars(range(min = 0, max = 9_007_199_254_740_991_u64))] u64);
|
||||
@@ -94,6 +125,8 @@ pub struct WorkdirOperationApiError {
|
||||
pub message: String,
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub diagnostics: Option<Vec<Diagnostic>>,
|
||||
#[serde(default, skip_serializing_if = "Vec::is_empty")]
|
||||
pub audit_failures: Vec<workdir::http::WorkdirAuditFailure>,
|
||||
#[serde(skip, default = "default_repository_error_status")]
|
||||
status: u16,
|
||||
/// Server-local metadata retained by generated error response extensions, never the wire body.
|
||||
@@ -101,6 +134,8 @@ pub struct WorkdirOperationApiError {
|
||||
pub workdir_log: Option<WorkdirOperationLogContext>,
|
||||
#[serde(skip)]
|
||||
pub denial_reason: Option<workdir::WorkdirDenialReason>,
|
||||
#[serde(skip)]
|
||||
pub failure_reason: Option<workdir::WorkdirFailureReason>,
|
||||
}
|
||||
|
||||
/// Internal operational correlation. Producers supply fixed-length ID fingerprints and
|
||||
@@ -123,9 +158,11 @@ impl WorkdirOperationApiError {
|
||||
code: None,
|
||||
message: error.message,
|
||||
diagnostics: Some(error.diagnostics),
|
||||
audit_failures: Vec::new(),
|
||||
status: error.status,
|
||||
workdir_log: None,
|
||||
denial_reason: None,
|
||||
failure_reason: None,
|
||||
}
|
||||
}
|
||||
|
||||
@@ -136,9 +173,11 @@ impl WorkdirOperationApiError {
|
||||
code: Some(error.code),
|
||||
message: error.message,
|
||||
diagnostics: None,
|
||||
audit_failures: Vec::new(),
|
||||
status,
|
||||
workdir_log: None,
|
||||
denial_reason: error.denial_reason,
|
||||
failure_reason: error.failure_reason,
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -166,8 +205,18 @@ macro_rules! impl_openapi_schema {
|
||||
}
|
||||
|
||||
impl_openapi_schema!(
|
||||
SubjectPermissionsResponse,
|
||||
SubjectPermissionsMutationResponse,
|
||||
SubjectPermissionInterruption,
|
||||
authorization::SubjectPermissions,
|
||||
authorization::SubjectPermissionsUpdate,
|
||||
AuthBootstrapUserRequest,
|
||||
AuthPublicConfig,
|
||||
HostingSettings,
|
||||
HostingAccess,
|
||||
ProvisionalAccountRequest,
|
||||
ActivationCodeResponse,
|
||||
ActivationOptionsRequest,
|
||||
AuthUserResponse,
|
||||
DeviceLoginApproveRequest,
|
||||
DeviceLoginApproveResponse,
|
||||
@@ -179,6 +228,7 @@ impl_openapi_schema!(
|
||||
PasskeyLoginOptionsRequest,
|
||||
PasskeyLoginOptionsResponse,
|
||||
PasskeyLoginCompleteRequest,
|
||||
PasskeyAdditionOptionsRequest,
|
||||
PasskeyRegistrationOptionsRequest,
|
||||
PasskeyRegistrationOptionsResponse,
|
||||
PasskeyRegistrationCompleteRequest,
|
||||
@@ -376,6 +426,8 @@ impl_openapi_schema!(
|
||||
TicketAssignmentDiagnosticsPage,
|
||||
TicketQueryRequest,
|
||||
TicketQueryResponse,
|
||||
TicketBrowseQueryRequest,
|
||||
TicketBrowseQueryResponse,
|
||||
TicketQueueResponse,
|
||||
TicketRecord,
|
||||
TicketRecordRef,
|
||||
@@ -510,6 +562,60 @@ pub trait ServerApi {
|
||||
#[get("/api/auth/config", status = 200, error_status = 400)]
|
||||
async fn auth_config(&self) -> Result<AuthPublicConfig, RepositoryApiError>;
|
||||
|
||||
#[get("/api/auth/registration-policy", status = 200, error_status = 400)]
|
||||
async fn auth_registration_policy(&self) -> Result<HostingSettings, RepositoryApiError>;
|
||||
|
||||
#[get("/api/hosting/access", status = 200, error_status = 403, additional_error_statuses = [400, 500], bearer_auth = true, browser_auth = true)]
|
||||
async fn hosting_access(
|
||||
&self,
|
||||
#[extension] context: ServerRequestContext,
|
||||
) -> Result<HostingAccess, RepositoryApiError>;
|
||||
|
||||
#[get("/api/hosting/settings", status = 200, error_status = 403, additional_error_statuses = [400, 500], bearer_auth = true, browser_auth = true)]
|
||||
async fn hosting_settings(
|
||||
&self,
|
||||
#[extension] context: ServerRequestContext,
|
||||
) -> Result<HostingSettings, RepositoryApiError>;
|
||||
|
||||
#[put("/api/hosting/settings", status = 200, error_status = 403, additional_error_statuses = [400, 500], bearer_auth = true, browser_auth = true)]
|
||||
async fn hosting_settings_update(
|
||||
&self,
|
||||
#[extension] context: ServerRequestContext,
|
||||
#[body] request: HostingSettings,
|
||||
) -> Result<HostingSettings, RepositoryApiError>;
|
||||
|
||||
#[post("/api/hosting/accounts", status = 200, error_status = 400, additional_error_statuses = [403, 500], bearer_auth = true, browser_auth = true)]
|
||||
async fn hosting_account_create(
|
||||
&self,
|
||||
#[extension] context: ServerRequestContext,
|
||||
#[body] request: ProvisionalAccountRequest,
|
||||
) -> Result<ActivationCodeResponse, RepositoryApiError>;
|
||||
|
||||
#[post("/api/hosting/accounts/activation-code", status = 200, error_status = 400, additional_error_statuses = [403, 500], bearer_auth = true, browser_auth = true)]
|
||||
async fn hosting_activation_code_reissue(
|
||||
&self,
|
||||
#[extension] context: ServerRequestContext,
|
||||
#[body] request: ProvisionalAccountRequest,
|
||||
) -> Result<ActivationCodeResponse, RepositoryApiError>;
|
||||
|
||||
#[post("/api/auth/activation/options", status = 200, error_status = 400, additional_error_statuses = [500])]
|
||||
async fn auth_activation_options(
|
||||
&self,
|
||||
#[extension] context: ServerRequestContext,
|
||||
#[body] request: ActivationOptionsRequest,
|
||||
) -> Result<PasskeyRegistrationOptionsResponse, RepositoryApiError>;
|
||||
|
||||
#[post(
|
||||
"/api/auth/activation/complete",
|
||||
responses = [(status = 200, body = AuthUserResponse, headers = [("set-cookie", SetCookieHeader)])],
|
||||
error_status = 400,
|
||||
additional_error_statuses = [500]
|
||||
)]
|
||||
async fn auth_activation_complete(
|
||||
&self,
|
||||
#[body] request: PasskeyRegistrationCompleteRequest,
|
||||
) -> Result<server_api_responses::AuthActivationComplete, RepositoryApiError>;
|
||||
|
||||
#[post(
|
||||
"/api/auth/bootstrap-user",
|
||||
status = 200,
|
||||
@@ -546,6 +652,36 @@ pub trait ServerApi {
|
||||
#[body] request: PasskeyRegistrationCompleteRequest,
|
||||
) -> Result<server_api_responses::AuthPasskeyRegistrationComplete, RepositoryApiError>;
|
||||
|
||||
#[post(
|
||||
"/api/auth/passkeys/addition/options",
|
||||
status = 200,
|
||||
error_status = 400,
|
||||
additional_error_statuses = [403, 500, 502],
|
||||
bearer_auth = true,
|
||||
browser_auth = true
|
||||
)]
|
||||
async fn auth_passkey_addition_options(
|
||||
&self,
|
||||
#[extension] context: ServerRequestContext,
|
||||
#[body] request: PasskeyAdditionOptionsRequest,
|
||||
) -> Result<PasskeyRegistrationOptionsResponse, RepositoryApiError>;
|
||||
|
||||
#[post(
|
||||
"/api/auth/passkeys/addition/complete",
|
||||
responses = [
|
||||
(status = 200, body = AuthUserResponse, headers = [("set-cookie", SetCookieHeader)])
|
||||
],
|
||||
error_status = 400,
|
||||
additional_error_statuses = [403, 500],
|
||||
bearer_auth = true,
|
||||
browser_auth = true
|
||||
)]
|
||||
async fn auth_passkey_addition_complete(
|
||||
&self,
|
||||
#[extension] context: ServerRequestContext,
|
||||
#[body] request: PasskeyRegistrationCompleteRequest,
|
||||
) -> Result<server_api_responses::AuthPasskeyAdditionComplete, RepositoryApiError>;
|
||||
|
||||
#[post(
|
||||
"/api/auth/passkeys/login/options",
|
||||
status = 200,
|
||||
@@ -1204,6 +1340,51 @@ pub trait ServerApi {
|
||||
#[body] request: MemoryConsolidateStagingRequest,
|
||||
) -> Result<MemoryConsolidationResponse, RepositoryApiError>;
|
||||
|
||||
#[post(
|
||||
"/api/w/{workspace_id}/authorization/check",
|
||||
status = 200,
|
||||
error_status = 400,
|
||||
additional_error_statuses = [401, 403, 404, 409, 500],
|
||||
openapi = false,
|
||||
)]
|
||||
async fn operation_authorize(
|
||||
&self,
|
||||
#[extension] context: ServerRequestContext,
|
||||
#[path] workspace_id: String,
|
||||
#[body] request: authorization::OperationAuthorizationRequest,
|
||||
) -> Result<authorization::OperationAuthorizationResponse, RepositoryApiError>;
|
||||
|
||||
#[get(
|
||||
"/api/w/{workspace_id}/subjektiv/subjects/{subject_id}/permissions",
|
||||
status = 200,
|
||||
error_status = 400,
|
||||
additional_error_statuses = [401, 403, 404, 500],
|
||||
bearer_auth = true,
|
||||
browser_auth = true,
|
||||
)]
|
||||
async fn subjektiv_subject_permissions_get(
|
||||
&self,
|
||||
#[extension] context: ServerRequestContext,
|
||||
#[path] workspace_id: String,
|
||||
#[path] subject_id: String,
|
||||
) -> Result<SubjectPermissionsResponse, RepositoryApiError>;
|
||||
|
||||
#[post(
|
||||
"/api/w/{workspace_id}/subjektiv/subjects/{subject_id}/permissions",
|
||||
status = 200,
|
||||
error_status = 400,
|
||||
additional_error_statuses = [401, 403, 404, 409, 500],
|
||||
bearer_auth = true,
|
||||
browser_auth = true,
|
||||
)]
|
||||
async fn subjektiv_subject_permissions_set(
|
||||
&self,
|
||||
#[extension] context: ServerRequestContext,
|
||||
#[path] workspace_id: String,
|
||||
#[path] subject_id: String,
|
||||
#[body] request: authorization::SubjectPermissionsUpdate,
|
||||
) -> Result<SubjectPermissionsMutationResponse, RepositoryApiError>;
|
||||
|
||||
#[post(
|
||||
"/api/w/{workspace_id}/subjektiv/subjects",
|
||||
status = 201,
|
||||
@@ -2668,6 +2849,12 @@ pub trait ServerApi {
|
||||
#[extension] context: ServerRequestContext,
|
||||
#[path] workspace_id: String,
|
||||
) -> Result<DriveEntry, DriveApiError>;
|
||||
#[get("/api/w/{workspace_id}/drive/capabilities", status = 200, error_status = 400, additional_error_statuses = [401,403,404,409,413,503], bearer_auth = true, browser_auth = true)]
|
||||
async fn drive_capabilities(
|
||||
&self,
|
||||
#[extension] context: ServerRequestContext,
|
||||
#[path] workspace_id: String,
|
||||
) -> Result<DriveCapabilities, DriveApiError>;
|
||||
#[get("/api/w/{workspace_id}/drive/metadata", status = 200, error_status = 400, additional_error_statuses = [401,403,404,409,413,503], bearer_auth = true, browser_auth = true)]
|
||||
async fn drive_metadata(
|
||||
&self,
|
||||
@@ -3033,6 +3220,14 @@ pub trait ServerApi {
|
||||
#[body] request: TicketTagsSetRequest,
|
||||
) -> Result<WorkspaceTicketTagList, RepositoryApiError>;
|
||||
|
||||
/// Lightweight browser list; deliberately excludes live MR evidence and external observations.
|
||||
#[post("/api/w/{workspace_id}/tickets/browse", status = 200, error_status = 400, additional_error_statuses = [401, 403, 404, 500], bearer_auth = true, browser_auth = true)]
|
||||
async fn ticket_browse(
|
||||
&self,
|
||||
#[path] workspace_id: String,
|
||||
#[body] request: TicketBrowseQueryRequest,
|
||||
) -> Result<TicketBrowseQueryResponse, RepositoryApiError>;
|
||||
|
||||
#[post("/api/w/{workspace_id}/tickets/query", status = 200, error_status = 400, additional_error_statuses = [401, 403, 404, 500], bearer_auth = true, browser_auth = true)]
|
||||
async fn ticket_query(
|
||||
&self,
|
||||
@@ -3803,6 +3998,76 @@ pub struct AuthPublicConfig {
|
||||
pub cookie_name: String,
|
||||
}
|
||||
|
||||
/// The only public registration policy. No administrator identities or host secrets are exposed.
|
||||
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq, JsonSchema)]
|
||||
#[cfg_attr(feature = "typescript", derive(ts_rs::TS))]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct HostingSettings {
|
||||
pub self_registration_enabled: bool,
|
||||
}
|
||||
|
||||
/// Hosting authority for the current authenticated human, not Workspace permissions.
|
||||
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq, JsonSchema)]
|
||||
#[cfg_attr(feature = "typescript", derive(ts_rs::TS))]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct HostingAccess {
|
||||
pub is_admin: bool,
|
||||
}
|
||||
|
||||
/// A hosting administrator reserves the same normalized ID used by passkey login.
|
||||
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq, JsonSchema)]
|
||||
#[cfg_attr(feature = "typescript", derive(ts_rs::TS))]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct ProvisionalAccountRequest {
|
||||
pub handle: String,
|
||||
}
|
||||
|
||||
/// The only response allowed to disclose an activation code. Clients must keep it
|
||||
/// out of URLs, persistent browser storage and diagnostics. A lost response is
|
||||
/// recovered by reissuing, which invalidates the previous code and its ceremonies.
|
||||
#[derive(Clone, Serialize, Deserialize, PartialEq, Eq, JsonSchema)]
|
||||
#[cfg_attr(feature = "typescript", derive(ts_rs::TS))]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct ActivationCodeResponse {
|
||||
pub user: AuthenticatedUser,
|
||||
pub code: String,
|
||||
pub expires_at: String,
|
||||
}
|
||||
|
||||
impl std::fmt::Debug for ActivationCodeResponse {
|
||||
fn fmt(&self, formatter: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
|
||||
formatter
|
||||
.debug_struct("ActivationCodeResponse")
|
||||
.field("user", &self.user)
|
||||
.field("code", &"[REDACTED]")
|
||||
.field("expires_at", &self.expires_at)
|
||||
.finish()
|
||||
}
|
||||
}
|
||||
|
||||
/// Proof for a pending account's initial passkey ceremony, never a bearer token
|
||||
/// or browser session. No caller-selected account ID or enrollment purpose is accepted.
|
||||
#[derive(Clone, Serialize, Deserialize, PartialEq, Eq, JsonSchema)]
|
||||
#[cfg_attr(feature = "typescript", derive(ts_rs::TS))]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct ActivationOptionsRequest {
|
||||
pub handle: String,
|
||||
pub code: String,
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub browser_origin: Option<String>,
|
||||
}
|
||||
|
||||
impl std::fmt::Debug for ActivationOptionsRequest {
|
||||
fn fmt(&self, formatter: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
|
||||
formatter
|
||||
.debug_struct("ActivationOptionsRequest")
|
||||
.field("handle", &self.handle)
|
||||
.field("code", &"[REDACTED]")
|
||||
.field("browser_origin", &self.browser_origin)
|
||||
.finish()
|
||||
}
|
||||
}
|
||||
|
||||
/// Authentication method that established the current request actor.
|
||||
#[derive(Debug, Clone, Copy, Serialize, Deserialize, PartialEq, Eq, JsonSchema)]
|
||||
#[cfg_attr(feature = "typescript", derive(ts_rs::TS))]
|
||||
@@ -3853,6 +4118,17 @@ impl RequestActor {
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct WhoamiResponse {
|
||||
pub actor: Option<RequestActor>,
|
||||
pub session: BrowserSessionState,
|
||||
}
|
||||
|
||||
/// Browser navigation evidence, not an authorization grant or a generic 401 classification.
|
||||
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq, JsonSchema)]
|
||||
#[cfg_attr(feature = "typescript", derive(ts_rs::TS))]
|
||||
#[serde(tag = "kind", rename_all = "snake_case", deny_unknown_fields)]
|
||||
pub enum BrowserSessionState {
|
||||
Anonymous {},
|
||||
Authenticated { expires_at: Option<String> },
|
||||
Expired {},
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq, JsonSchema)]
|
||||
@@ -3872,6 +4148,7 @@ pub struct AuthUserResponse {
|
||||
pub user: AuthenticatedUser,
|
||||
}
|
||||
|
||||
/// Starts new-account registration only; an existing handle is never interpreted as key addition.
|
||||
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq, JsonSchema)]
|
||||
#[cfg_attr(feature = "typescript", derive(ts_rs::TS))]
|
||||
#[serde(deny_unknown_fields)]
|
||||
@@ -3885,6 +4162,16 @@ pub struct PasskeyRegistrationOptionsRequest {
|
||||
pub browser_origin: Option<String>,
|
||||
}
|
||||
|
||||
/// Adds a credential to the current authenticated actor; target identity is never public input.
|
||||
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq, JsonSchema)]
|
||||
#[cfg_attr(feature = "typescript", derive(ts_rs::TS))]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct PasskeyAdditionOptionsRequest {
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
#[cfg_attr(feature = "typescript", ts(optional = nullable))]
|
||||
pub browser_origin: Option<String>,
|
||||
}
|
||||
|
||||
#[derive(Debug, Serialize, Deserialize, JsonSchema)]
|
||||
#[cfg_attr(feature = "typescript", derive(ts_rs::TS))]
|
||||
#[serde(deny_unknown_fields)]
|
||||
@@ -3905,6 +4192,11 @@ pub struct PasskeyRegistrationCompleteRequest {
|
||||
pub credential: RegisterPublicKeyCredential,
|
||||
}
|
||||
|
||||
/// Normal discoverable login omits the handle: the authenticator selects a credential.
|
||||
/// An explicit handle selects legacy identified-account login, for non-resident keys or
|
||||
/// keys registered with an old random WebAuthn user handle. This never adds a key or
|
||||
/// falls back to another identity. Authenticate first, then enroll an RK from Account.
|
||||
/// Existing challenge states are short-lived and are not migrated to the new ceremony.
|
||||
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq, JsonSchema)]
|
||||
#[cfg_attr(feature = "typescript", derive(ts_rs::TS))]
|
||||
#[serde(deny_unknown_fields)]
|
||||
@@ -7222,6 +7514,9 @@ pub struct CurrentWorkerWorkdirAttachmentResponse {
|
||||
pub alias: String,
|
||||
pub working_directory_id: String,
|
||||
pub capabilities: workdir::WorkdirSessionCapabilities,
|
||||
/// Present for attachment responses, absent after detach.
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub environment: Option<workdir::WorkdirSessionEnvironment>,
|
||||
pub attached: bool,
|
||||
}
|
||||
|
||||
@@ -7234,7 +7529,9 @@ pub struct CurrentWorkerWorkdirOperationRequest {
|
||||
|
||||
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq, JsonSchema)]
|
||||
#[serde(transparent)]
|
||||
pub struct CurrentWorkerWorkdirOperationResponse(pub workdir::http::WorkdirSessionOperationResult);
|
||||
pub struct CurrentWorkerWorkdirOperationResponse(
|
||||
pub workdir::http::WorkdirSessionOperationResponse,
|
||||
);
|
||||
|
||||
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq, JsonSchema)]
|
||||
#[cfg_attr(feature = "typescript", derive(ts_rs::TS))]
|
||||
@@ -8058,9 +8355,8 @@ pub enum TicketImplementationResultKind {
|
||||
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq, JsonSchema)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct TicketImplementationResultRequest {
|
||||
/// Host-owned replay identity; model-facing tools derive it from the Tool call.
|
||||
pub operation_key: String,
|
||||
pub assignment_id: String,
|
||||
pub orchestrator_assignment_id: String,
|
||||
pub kind: TicketImplementationResultKind,
|
||||
pub body: String,
|
||||
pub merge_request: Option<MergeRequestReviewSubject>,
|
||||
@@ -10241,6 +10537,10 @@ pub struct CreateWorkspaceWorkerRequest {
|
||||
/// Backend idempotency key used only for authenticated Worker-owned spawn/control.
|
||||
#[serde(default)]
|
||||
pub control_operation_id: Option<String>,
|
||||
/// Requested least-authority child permissions. Host derives the origin; this
|
||||
/// input cannot assert Subject identity or create a body/singleton attachment.
|
||||
#[serde(default)]
|
||||
pub execution_grant: Option<authorization::WorkerDelegationRequest>,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq, JsonSchema)]
|
||||
@@ -11338,12 +11638,19 @@ pub fn auth_api_typescript() -> String {
|
||||
let config = ts_rs::Config::default();
|
||||
let declarations = [
|
||||
AuthPublicConfig::decl(&config),
|
||||
HostingSettings::decl(&config),
|
||||
HostingAccess::decl(&config),
|
||||
ProvisionalAccountRequest::decl(&config),
|
||||
ActivationCodeResponse::decl(&config),
|
||||
ActivationOptionsRequest::decl(&config),
|
||||
ActorAuthMethod::decl(&config),
|
||||
AuthenticatedUser::decl(&config),
|
||||
RequestActor::decl(&config),
|
||||
BrowserSessionState::decl(&config),
|
||||
WhoamiResponse::decl(&config),
|
||||
AuthBootstrapUserRequest::decl(&config),
|
||||
AuthUserResponse::decl(&config),
|
||||
PasskeyAdditionOptionsRequest::decl(&config),
|
||||
PasskeyRegistrationOptionsRequest::decl(&config),
|
||||
PasskeyRegistrationOptionsResponse::decl(&config),
|
||||
PasskeyRegistrationCompleteRequest::decl(&config),
|
||||
@@ -12061,6 +12368,16 @@ mod tests {
|
||||
HttpMethod::Post,
|
||||
"/api/auth/passkeys/registration/options",
|
||||
),
|
||||
(
|
||||
"auth_passkey_addition_options",
|
||||
HttpMethod::Post,
|
||||
"/api/auth/passkeys/addition/options",
|
||||
),
|
||||
(
|
||||
"auth_passkey_addition_complete",
|
||||
HttpMethod::Post,
|
||||
"/api/auth/passkeys/addition/complete",
|
||||
),
|
||||
(
|
||||
"auth_passkey_login_options",
|
||||
HttpMethod::Post,
|
||||
@@ -12726,6 +13043,7 @@ mod tests {
|
||||
workdir_attachments: Vec::new(),
|
||||
feature_connections: Default::default(),
|
||||
control_operation_id: None,
|
||||
execution_grant: None,
|
||||
})
|
||||
.unwrap();
|
||||
assert_eq!(
|
||||
@@ -12740,6 +13058,7 @@ mod tests {
|
||||
"workdir_attachments": [],
|
||||
"feature_connections": {},
|
||||
"control_operation_id": null,
|
||||
"execution_grant": null,
|
||||
})
|
||||
);
|
||||
}
|
||||
@@ -12970,6 +13289,7 @@ mod tests {
|
||||
alias: "checkout".to_string(),
|
||||
working_directory_id: "workdir".to_string(),
|
||||
capabilities: workdir::WorkdirSessionCapabilities::EMPTY,
|
||||
environment: None,
|
||||
attached: false,
|
||||
};
|
||||
let value = serde_json::to_value(&response).unwrap();
|
||||
@@ -13758,7 +14078,8 @@ mod tests {
|
||||
"handle": "hare",
|
||||
"display_name": "Hare",
|
||||
"auth_method": "browser_session"
|
||||
}
|
||||
},
|
||||
"session": { "kind": "authenticated", "expires_at": "2026-10-20T00:00:00Z" }
|
||||
});
|
||||
let decoded = serde_json::from_value::<WhoamiResponse>(whoami.clone())
|
||||
.expect("server whoami fixture should match shared DTO");
|
||||
@@ -13940,11 +14261,36 @@ mod tests {
|
||||
|
||||
let unexpected_field = serde_json::json!({
|
||||
"actor": null,
|
||||
"session": { "kind": "anonymous" },
|
||||
"access_token": "must-not-be-accepted"
|
||||
});
|
||||
assert!(serde_json::from_value::<WhoamiResponse>(unexpected_field).is_err());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn whoami_session_json_distinguishes_anonymous_expired_and_token_auth() {
|
||||
for session in [
|
||||
serde_json::json!({"kind":"anonymous"}),
|
||||
serde_json::json!({"kind":"expired"}),
|
||||
serde_json::json!({"kind":"authenticated", "expires_at":null}),
|
||||
] {
|
||||
let value = serde_json::json!({"actor":null, "session":session});
|
||||
let response: WhoamiResponse = serde_json::from_value(value.clone()).unwrap();
|
||||
assert_eq!(serde_json::to_value(response).unwrap(), value);
|
||||
}
|
||||
for session in [
|
||||
serde_json::json!({"kind":"unknown"}),
|
||||
serde_json::json!({"kind":"expired", "expires_at":null}),
|
||||
] {
|
||||
assert!(
|
||||
serde_json::from_value::<WhoamiResponse>(
|
||||
serde_json::json!({"actor":null, "session":session})
|
||||
)
|
||||
.is_err()
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn device_login_debug_output_redacts_secret_material() {
|
||||
let start = DeviceLoginStartResponse {
|
||||
@@ -14312,6 +14658,9 @@ mod openapi_artifact_tests {
|
||||
const PUBLIC_UNAUTHENTICATED: &[&str] = &[
|
||||
"health",
|
||||
"auth_config",
|
||||
"auth_registration_policy",
|
||||
"auth_activation_options",
|
||||
"auth_activation_complete",
|
||||
"auth_bootstrap_user",
|
||||
"auth_passkey_registration_options",
|
||||
"auth_passkey_registration_complete",
|
||||
@@ -14326,6 +14675,7 @@ mod openapi_artifact_tests {
|
||||
// identity, or a one-use Reviewer capability. They remain generated Rust client/Axum
|
||||
// operations, but must not appear as unauthenticated operations in the public OpenAPI.
|
||||
const SIGNED_INTERNAL: &[&str] = &[
|
||||
"operation_authorize",
|
||||
"current_worker_workspace_config_get",
|
||||
"current_worker_workspace_config_attach",
|
||||
"current_worker_workspace_config_observe",
|
||||
@@ -14452,6 +14802,20 @@ mod openapi_artifact_tests {
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn passkey_addition_rejects_caller_selected_target_fields() {
|
||||
for field in ["handle", "user_id", "account_id"] {
|
||||
let payload = serde_json::json!({ (field): "other-user" });
|
||||
assert!(
|
||||
serde_json::from_value::<PasskeyAdditionOptionsRequest>(payload).is_err(),
|
||||
"addition must reject caller-selected {field}"
|
||||
);
|
||||
}
|
||||
assert!(
|
||||
serde_json::from_value::<PasskeyAdditionOptionsRequest>(serde_json::json!({})).is_ok()
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn auth_workspace_catalog_and_typed_header_contract_is_strict() {
|
||||
let document = canonical_openapi_document().expect("canonical OpenAPI contract must build");
|
||||
@@ -14465,6 +14829,8 @@ mod openapi_artifact_tests {
|
||||
("/api/auth/bootstrap-user", "post"),
|
||||
("/api/auth/passkeys/registration/options", "post"),
|
||||
("/api/auth/passkeys/registration/complete", "post"),
|
||||
("/api/auth/passkeys/addition/options", "post"),
|
||||
("/api/auth/passkeys/addition/complete", "post"),
|
||||
("/api/auth/passkeys/login/options", "post"),
|
||||
("/api/auth/passkeys/login/complete", "post"),
|
||||
("/api/auth/logout", "post"),
|
||||
@@ -14503,6 +14869,7 @@ mod openapi_artifact_tests {
|
||||
}
|
||||
for path in [
|
||||
"/api/auth/passkeys/registration/complete",
|
||||
"/api/auth/passkeys/addition/complete",
|
||||
"/api/auth/passkeys/login/complete",
|
||||
"/api/auth/logout",
|
||||
] {
|
||||
@@ -14694,10 +15061,12 @@ mod workdir_error_diagnostic_tests {
|
||||
#[test]
|
||||
fn workdir_internal_diagnostics_never_enter_public_error_body_or_schema() {
|
||||
let mut error = WorkdirOperationApiError::provider(workdir::http::WorkdirTransportError {
|
||||
failure_reason: None,
|
||||
code: workdir::http::WorkdirTransportErrorCode::Denied,
|
||||
message: "Workdir operation was denied".to_string(),
|
||||
denial_reason: Some(workdir::WorkdirDenialReason::OsPermissionDenied),
|
||||
});
|
||||
error.failure_reason = Some(workdir::WorkdirFailureReason::HttpTimeout);
|
||||
error.workdir_log = Some(WorkdirOperationLogContext {
|
||||
operation: "write",
|
||||
workspace_id_hash: "internal-workspace-fingerprint".to_string(),
|
||||
@@ -14711,9 +15080,55 @@ mod workdir_error_diagnostic_tests {
|
||||
assert_eq!(api_macros::HttpError::status_code(&error), 403);
|
||||
let decoded: WorkdirOperationApiError = serde_json::from_value(wire).unwrap();
|
||||
assert!(decoded.denial_reason.is_none());
|
||||
assert!(decoded.failure_reason.is_none());
|
||||
assert!(decoded.workdir_log.is_none());
|
||||
let schema = serde_json::to_value(schemars::schema_for!(WorkdirOperationApiError)).unwrap();
|
||||
assert!(schema["properties"].get("workdir_log").is_none());
|
||||
assert!(schema["properties"].get("denial_reason").is_none());
|
||||
assert!(schema["properties"].get("failure_reason").is_none());
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod activation_contract_tests {
|
||||
use super::*;
|
||||
|
||||
#[test]
|
||||
fn activation_inputs_reject_caller_selected_authority_and_debug_redacts_codes() {
|
||||
for field in [
|
||||
"account_id",
|
||||
"user_id",
|
||||
"purpose",
|
||||
"is_admin",
|
||||
"authentication",
|
||||
] {
|
||||
let mut body = serde_json::json!({"handle":"new-user","code":"activation-secret"});
|
||||
body[field] = serde_json::json!("caller-controlled");
|
||||
assert!(serde_json::from_value::<ActivationOptionsRequest>(body).is_err());
|
||||
let mut body = serde_json::json!({"handle":"new-user"});
|
||||
body[field] = serde_json::json!("caller-controlled");
|
||||
assert!(serde_json::from_value::<ProvisionalAccountRequest>(body).is_err());
|
||||
}
|
||||
let request = ActivationOptionsRequest {
|
||||
handle: "new-user".into(),
|
||||
code: "activation-secret".into(),
|
||||
browser_origin: None,
|
||||
};
|
||||
assert!(!format!("{request:?}").contains(&request.code));
|
||||
let response = ActivationCodeResponse {
|
||||
user: AuthenticatedUser {
|
||||
user_id: "u".into(),
|
||||
account_id: "a".into(),
|
||||
handle: "new-user".into(),
|
||||
display_name: "new-user".into(),
|
||||
},
|
||||
code: "activation-secret".into(),
|
||||
expires_at: "2030-01-01T00:00:00Z".into(),
|
||||
};
|
||||
assert!(!format!("{response:?}").contains(&response.code));
|
||||
assert_eq!(
|
||||
serde_json::to_value(&response).unwrap()["code"],
|
||||
"activation-secret"
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -459,6 +459,13 @@ fn validate_ticket_browser_operations(
|
||||
request: Some("TicketTagSetRequest"),
|
||||
successes: &[("200", "Array_of_WorkspaceTag")],
|
||||
},
|
||||
OperationContract {
|
||||
path: "/api/w/{workspace_id}/tickets/browse",
|
||||
method: "post",
|
||||
operation_id: "ticket_browse",
|
||||
request: Some("TicketBrowseQueryRequest"),
|
||||
successes: &[("200", "TicketBrowseQueryResponse")],
|
||||
},
|
||||
OperationContract {
|
||||
path: "/api/w/{workspace_id}/tickets/query",
|
||||
method: "post",
|
||||
|
||||
@@ -0,0 +1,65 @@
|
||||
//! Lightweight Tickets browser contract, separate from authoritative evidence queries.
|
||||
use crate::{BrowserTicketState, QueryPage};
|
||||
use schemars::JsonSchema;
|
||||
use serde::{Deserialize, Serialize};
|
||||
|
||||
#[derive(Debug, Clone, Default, Serialize, Deserialize, PartialEq, Eq, JsonSchema)]
|
||||
#[cfg_attr(feature = "typescript", derive(ts_rs::TS))]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct TicketBrowseQueryRequest {
|
||||
pub query: Option<String>,
|
||||
#[serde(default)]
|
||||
#[cfg_attr(feature = "typescript", ts(type = "Array<BrowserTicketState>"))]
|
||||
pub states: Vec<ticket::TicketState>,
|
||||
/// Every supplied active tag ID must match (AND).
|
||||
#[serde(default)]
|
||||
pub tag_ids: Vec<String>,
|
||||
#[cfg_attr(
|
||||
feature = "typescript",
|
||||
ts(type = "TicketAssignmentPrincipalSnapshot | null")
|
||||
)]
|
||||
pub assigned_principal: Option<ticket::TicketAssignmentPrincipalSnapshot>,
|
||||
#[cfg_attr(
|
||||
feature = "typescript",
|
||||
ts(type = "TicketAssignmentTrackingStatus | null")
|
||||
)]
|
||||
pub handling_status: Option<ticket::TicketAssignmentTrackingStatus>,
|
||||
/// Exact current closed-case reason; historical reasons do not match this filter.
|
||||
#[cfg_attr(feature = "typescript", ts(type = "TicketClosureReason | null"))]
|
||||
pub closure_reason: Option<ticket::TicketClosureReason>,
|
||||
/// Only updated_desc is supported; defaults to updated_desc.
|
||||
pub sort: Option<String>,
|
||||
#[schemars(range(min = 0, max = 1000))]
|
||||
pub limit: Option<usize>,
|
||||
/// Browse-only cursor bound to the Workspace, canonical filters, and sort.
|
||||
pub cursor: Option<String>,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq, JsonSchema)]
|
||||
#[cfg_attr(feature = "typescript", derive(ts_rs::TS))]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct TicketBrowseQueryItem {
|
||||
pub id: String,
|
||||
pub resource_key: String,
|
||||
pub title: String,
|
||||
pub state: BrowserTicketState,
|
||||
pub updated_at: Option<String>,
|
||||
#[cfg_attr(feature = "typescript", ts(type = "Array<WorkspaceTag>"))]
|
||||
pub tags: Vec<ticket::WorkspaceTag>,
|
||||
#[cfg_attr(feature = "typescript", ts(type = "TicketClosureJudgment | null"))]
|
||||
pub current_closure: Option<ticket::TicketClosureJudgment>,
|
||||
#[cfg_attr(
|
||||
feature = "typescript",
|
||||
ts(type = "Array<TicketAssignmentTrackingProjection>")
|
||||
)]
|
||||
pub assignment_tracking: Vec<ticket::TicketAssignmentTrackingProjection>,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq, JsonSchema)]
|
||||
#[cfg_attr(feature = "typescript", derive(ts_rs::TS))]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct TicketBrowseQueryResponse {
|
||||
pub items: Vec<TicketBrowseQueryItem>,
|
||||
pub page: QueryPage,
|
||||
pub record_authority: String,
|
||||
}
|
||||
@@ -48,17 +48,48 @@ pub struct FsStore {
|
||||
/// `write_all` may have extended the file, so rollback is safe only while
|
||||
/// no sibling writer can append behind it.
|
||||
append_lock: Arc<Mutex<()>>,
|
||||
retention: crate::retention::SessionRetentionStore,
|
||||
}
|
||||
|
||||
impl FsStore {
|
||||
/// Create a new `FsStore` rooted at the given directory.
|
||||
/// Creates the directory if it does not exist.
|
||||
pub fn new(root: impl Into<PathBuf>) -> Result<Self, StoreError> {
|
||||
let root = root.into();
|
||||
let retention = crate::retention::fs_retention(&root);
|
||||
Self::new_with_retention(root, retention)
|
||||
}
|
||||
|
||||
/// Hosts that relocate Worker originals must keep control state outside the relocated
|
||||
/// aggregate and pass the same store to readers and deletion/transfer operations.
|
||||
pub fn new_with_retention(
|
||||
root: impl Into<PathBuf>,
|
||||
retention: crate::retention::SessionRetentionStore,
|
||||
) -> Result<Self, StoreError> {
|
||||
let root = root.into();
|
||||
fs::create_dir_all(&root)?;
|
||||
for entry in fs::read_dir(&root)? {
|
||||
let entry = entry?;
|
||||
if entry.file_type()?.is_dir()
|
||||
&& let Some(session_id) = entry
|
||||
.file_name()
|
||||
.to_str()
|
||||
.and_then(|name| name.parse().ok())
|
||||
{
|
||||
let _guard = match retention.lock_live(session_id) {
|
||||
Ok(guard) => guard,
|
||||
// Interrupted erasure may leave bytes behind. Never read or
|
||||
// upgrade them, and do not block unrelated live Sessions.
|
||||
Err(StoreError::SessionErased(_)) => continue,
|
||||
Err(error) => return Err(error),
|
||||
};
|
||||
crate::worker_session_store::migrate_fs_session(&entry.path(), session_id)?;
|
||||
}
|
||||
}
|
||||
Ok(Self {
|
||||
root,
|
||||
append_lock: Arc::new(Mutex::new(())),
|
||||
retention,
|
||||
})
|
||||
}
|
||||
|
||||
@@ -98,12 +129,46 @@ impl FsStore {
|
||||
/// Returns `Ok(true)` when a Session directory was removed and `Ok(false)`
|
||||
/// when it was already absent.
|
||||
pub fn delete_session(&self, session_id: SessionId) -> Result<bool, StoreError> {
|
||||
let session_dir = self.session_dir(session_id);
|
||||
match fs::remove_dir_all(&session_dir) {
|
||||
Ok(()) => Ok(true),
|
||||
Err(error) if error.kind() == std::io::ErrorKind::NotFound => Ok(false),
|
||||
Err(error) => Err(error.into()),
|
||||
}
|
||||
self.delete_session_with_intent(
|
||||
session_id,
|
||||
crate::retention::SessionDeletionIntent::Ordinary,
|
||||
)
|
||||
}
|
||||
|
||||
pub fn retention(&self) -> crate::retention::SessionRetentionStore {
|
||||
self.retention.clone()
|
||||
}
|
||||
|
||||
pub fn pin_session(
|
||||
&self,
|
||||
session_id: SessionId,
|
||||
pin: crate::retention::SessionRetentionPin,
|
||||
) -> Result<(), StoreError> {
|
||||
self.retention().pin(session_id, pin, || {
|
||||
Ok(self.session_dir(session_id).is_dir())
|
||||
})
|
||||
}
|
||||
|
||||
pub fn release_session_pin(
|
||||
&self,
|
||||
session_id: SessionId,
|
||||
pin: crate::retention::SessionRetentionPin,
|
||||
) -> Result<(), StoreError> {
|
||||
self.retention().release(session_id, pin)
|
||||
}
|
||||
|
||||
pub fn delete_session_with_intent(
|
||||
&self,
|
||||
session_id: SessionId,
|
||||
intent: crate::retention::SessionDeletionIntent,
|
||||
) -> Result<bool, StoreError> {
|
||||
self.retention().delete(session_id, intent, || {
|
||||
match fs::remove_dir_all(self.session_dir(session_id)) {
|
||||
Ok(()) => Ok(true),
|
||||
Err(error) if error.kind() == std::io::ErrorKind::NotFound => Ok(false),
|
||||
Err(error) => Err(error.into()),
|
||||
}
|
||||
})
|
||||
}
|
||||
|
||||
fn session_dir(&self, session_id: SessionId) -> PathBuf {
|
||||
@@ -282,12 +347,22 @@ impl FsStore {
|
||||
}
|
||||
|
||||
impl Store for FsStore {
|
||||
fn retain_session_before_publication(
|
||||
&self,
|
||||
session_id: SessionId,
|
||||
pin: crate::retention::SessionRetentionPin,
|
||||
) -> Result<(), StoreError> {
|
||||
self.retention().retain_before_publication(session_id, pin)
|
||||
}
|
||||
|
||||
fn append(
|
||||
&self,
|
||||
session_id: SessionId,
|
||||
segment_id: SegmentId,
|
||||
entry: &LogEntry,
|
||||
) -> Result<(), StoreError> {
|
||||
entry.validate_input_metadata()?;
|
||||
let _retention = self.retention().lock_live(session_id)?;
|
||||
let line = serde_json::to_string(entry)?;
|
||||
self.append_line(&self.log_path(session_id, segment_id), &line)
|
||||
}
|
||||
@@ -374,9 +449,14 @@ impl Store for FsStore {
|
||||
segment_id: SegmentId,
|
||||
entries: &[LogEntry],
|
||||
) -> Result<(), StoreError> {
|
||||
for entry in entries {
|
||||
entry.validate_input_metadata()?;
|
||||
}
|
||||
let _retention = self.retention().lock_live(session_id)?;
|
||||
let path = self.log_path(session_id, segment_id);
|
||||
if let Some(parent) = path.parent() {
|
||||
fs::create_dir_all(parent)?;
|
||||
crate::worker_session_store::migrate_fs_session(parent, session_id)?;
|
||||
}
|
||||
let mut content = String::new();
|
||||
for entry in entries {
|
||||
@@ -423,6 +503,7 @@ impl Store for FsStore {
|
||||
content: &str,
|
||||
limits: PasteArtifactLimits,
|
||||
) -> Result<PasteArtifactRef, StoreError> {
|
||||
let _retention = self.retention().lock_live(session_id)?;
|
||||
let _guard = self
|
||||
.append_lock
|
||||
.lock()
|
||||
@@ -451,6 +532,7 @@ impl Store for FsStore {
|
||||
content: &[u8],
|
||||
limits: UploadedFileLimits,
|
||||
) -> Result<UploadedFileRef, StoreError> {
|
||||
let _retention = self.retention().lock_live(session_id)?;
|
||||
let _guard = self
|
||||
.append_lock
|
||||
.lock()
|
||||
@@ -474,6 +556,7 @@ impl Store for FsStore {
|
||||
context: &UploadedFileUploadContext,
|
||||
limits: UploadedFileLimits,
|
||||
) -> Result<UploadedFileRef, StoreError> {
|
||||
let _retention = self.retention().lock_live(session_id)?;
|
||||
let _guard = self
|
||||
.append_lock
|
||||
.lock()
|
||||
@@ -510,6 +593,7 @@ impl Store for FsStore {
|
||||
reference: &UploadedFileRef,
|
||||
source_entry_id: &str,
|
||||
) -> Result<UploadedFileRef, StoreError> {
|
||||
let _retention = self.retention().lock_live(session_id)?;
|
||||
let _guard = self
|
||||
.append_lock
|
||||
.lock()
|
||||
@@ -537,6 +621,7 @@ impl Store for FsStore {
|
||||
reference: &UploadedFileRef,
|
||||
owner_id: &str,
|
||||
) -> Result<(), StoreError> {
|
||||
let _retention = self.retention().lock_live(session_id)?;
|
||||
let _guard = self
|
||||
.append_lock
|
||||
.lock()
|
||||
@@ -550,6 +635,7 @@ impl Store for FsStore {
|
||||
artifact_id: &str,
|
||||
owner_id: &str,
|
||||
) -> Result<(), StoreError> {
|
||||
let _retention = self.retention().lock_live(session_id)?;
|
||||
let _guard = self
|
||||
.append_lock
|
||||
.lock()
|
||||
@@ -563,6 +649,7 @@ impl Store for FsStore {
|
||||
artifact_id: &str,
|
||||
source_entry_id: &str,
|
||||
) -> Result<(), StoreError> {
|
||||
let _retention = self.retention().lock_live(session_id)?;
|
||||
let _guard = self
|
||||
.append_lock
|
||||
.lock()
|
||||
@@ -579,6 +666,7 @@ impl Store for FsStore {
|
||||
session_id: SessionId,
|
||||
live_owner_ids: &[String],
|
||||
) -> Result<u64, StoreError> {
|
||||
let _retention = self.retention().lock_live(session_id)?;
|
||||
let _guard = self
|
||||
.append_lock
|
||||
.lock()
|
||||
@@ -591,6 +679,7 @@ impl Store for FsStore {
|
||||
session_id: SessionId,
|
||||
artifact_id: &str,
|
||||
) -> Result<bool, StoreError> {
|
||||
let _retention = self.retention().lock_live(session_id)?;
|
||||
let _guard = self
|
||||
.append_lock
|
||||
.lock()
|
||||
@@ -599,6 +688,7 @@ impl Store for FsStore {
|
||||
}
|
||||
|
||||
fn delete_uncommitted_uploaded_files(&self, session_id: SessionId) -> Result<u64, StoreError> {
|
||||
let _retention = self.retention().lock_live(session_id)?;
|
||||
let _guard = self
|
||||
.append_lock
|
||||
.lock()
|
||||
@@ -631,6 +721,13 @@ impl Store for FsStore {
|
||||
source_session_id: SessionId,
|
||||
target_session_id: SessionId,
|
||||
) -> Result<u64, StoreError> {
|
||||
let mut sessions = vec![source_session_id, target_session_id];
|
||||
sessions.sort();
|
||||
sessions.dedup();
|
||||
let _retention = sessions
|
||||
.into_iter()
|
||||
.map(|id| self.retention().lock_live(id))
|
||||
.collect::<Result<Vec<_>, _>>()?;
|
||||
let _guard = self
|
||||
.append_lock
|
||||
.lock()
|
||||
@@ -647,6 +744,7 @@ impl Store for FsStore {
|
||||
segment_id: SegmentId,
|
||||
entry: &TraceEntry,
|
||||
) -> Result<(), StoreError> {
|
||||
let _retention = self.retention().lock_live(session_id)?;
|
||||
let line = serde_json::to_string(entry)?;
|
||||
self.append_line(&self.trace_path(session_id, segment_id), &line)
|
||||
}
|
||||
|
||||
@@ -67,8 +67,14 @@ pub enum LoggedSessionHistoryOrigin {
|
||||
ToolOutput {
|
||||
worker: LoggedWorkerSubject,
|
||||
},
|
||||
/// Descriptive producer identity; use policies live in separate metadata.
|
||||
Provided {
|
||||
producer: String,
|
||||
},
|
||||
/// Host-produced opening context summary; not auto-read or TaskStore material.
|
||||
CompactionSummary,
|
||||
/// Frozen Host Journal reference, never independent observation evidence.
|
||||
JournalContext,
|
||||
DerivedSummary,
|
||||
LegacyUnknown,
|
||||
}
|
||||
@@ -79,19 +85,32 @@ pub struct LoggedHistoryDerivation {
|
||||
}
|
||||
|
||||
#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct LoggedSessionHistoryMetadata {
|
||||
pub entry_id: LoggedSessionHistoryEntryId,
|
||||
pub origin: LoggedSessionHistoryOrigin,
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub derivation: Option<LoggedHistoryDerivation>,
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub input_metadata: Option<crate::HistoryInputMetadata>,
|
||||
}
|
||||
|
||||
impl LoggedSessionHistoryMetadata {
|
||||
pub(crate) fn validate_input_metadata(&self) -> Result<(), crate::InputMetadataError> {
|
||||
if matches!(self.origin, LoggedSessionHistoryOrigin::Provided { .. })
|
||||
&& self.input_metadata.is_none()
|
||||
{
|
||||
return Err(crate::InputMetadataError::MissingMetadata);
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
pub fn legacy_unknown() -> Self {
|
||||
Self {
|
||||
entry_id: LoggedSessionHistoryEntryId::new(),
|
||||
origin: LoggedSessionHistoryOrigin::LegacyUnknown,
|
||||
derivation: None,
|
||||
input_metadata: None,
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -99,20 +118,146 @@ impl LoggedSessionHistoryMetadata {
|
||||
/// Persisted item and metadata are one value so transforms cannot reorder or
|
||||
/// truncate one without the other.
|
||||
#[derive(Clone, Debug, PartialEq, Serialize, Deserialize)]
|
||||
#[serde(try_from = "HistoryEntryWire")]
|
||||
pub struct LoggedHistoryEntry {
|
||||
pub item: LoggedItem,
|
||||
pub metadata: LoggedSessionHistoryMetadata,
|
||||
}
|
||||
|
||||
#[derive(Deserialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
struct HistoryEntryWire {
|
||||
item: LoggedItem,
|
||||
metadata: LoggedSessionHistoryMetadata,
|
||||
}
|
||||
|
||||
impl TryFrom<HistoryEntryWire> for LoggedHistoryEntry {
|
||||
type Error = crate::InputMetadataError;
|
||||
|
||||
fn try_from(wire: HistoryEntryWire) -> Result<Self, Self::Error> {
|
||||
let entry = Self {
|
||||
item: wire.item,
|
||||
metadata: wire.metadata,
|
||||
};
|
||||
entry.validate_input_metadata()?;
|
||||
Ok(entry)
|
||||
}
|
||||
}
|
||||
|
||||
impl LoggedHistoryEntry {
|
||||
pub fn validate_input_metadata(&self) -> Result<(), crate::InputMetadataError> {
|
||||
self.metadata.validate_input_metadata()?;
|
||||
if let Some(input) = &self.metadata.input_metadata {
|
||||
match &self.item {
|
||||
LoggedItem::Message {
|
||||
role: crate::LoggedRole::System,
|
||||
content,
|
||||
} => {
|
||||
let [crate::LoggedContentPart::Text { text }] = content.as_slice() else {
|
||||
return Err(crate::InputMetadataError::InconsistentRecord);
|
||||
};
|
||||
if text.len() > crate::input_metadata::MAX_SYSTEM_INPUT_BYTES {
|
||||
return Err(crate::InputMetadataError::ResourceLimit);
|
||||
}
|
||||
}
|
||||
// Other logical roles may carry use policy, but cannot masquerade
|
||||
// as the System-only public/payload extension contract.
|
||||
_ if input.feature_payload().is_some() || input.public_item().is_some() => {
|
||||
return Err(crate::InputMetadataError::InconsistentRecord);
|
||||
}
|
||||
_ => {}
|
||||
}
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
}
|
||||
|
||||
/// Typed system-item history record. The typed system event remains available
|
||||
/// to client replay while its model-visible projection carries the same stable
|
||||
/// metadata used by live history.
|
||||
#[derive(Clone, Debug, Serialize, Deserialize)]
|
||||
#[serde(try_from = "SystemEntryWire")]
|
||||
pub struct LoggedSystemHistoryEntry {
|
||||
pub item: crate::SystemItem,
|
||||
pub metadata: LoggedSessionHistoryMetadata,
|
||||
}
|
||||
|
||||
#[derive(Deserialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
struct SystemEntryWire {
|
||||
item: crate::SystemItem,
|
||||
metadata: LoggedSessionHistoryMetadata,
|
||||
}
|
||||
|
||||
impl TryFrom<SystemEntryWire> for LoggedSystemHistoryEntry {
|
||||
type Error = crate::InputMetadataError;
|
||||
|
||||
fn try_from(wire: SystemEntryWire) -> Result<Self, Self::Error> {
|
||||
let entry = Self {
|
||||
item: wire.item,
|
||||
metadata: wire.metadata,
|
||||
};
|
||||
entry.validate_input_metadata()?;
|
||||
Ok(entry)
|
||||
}
|
||||
}
|
||||
|
||||
impl LoggedSystemHistoryEntry {
|
||||
pub fn from_input(
|
||||
origin: LoggedSessionHistoryOrigin,
|
||||
derivation: Option<LoggedHistoryDerivation>,
|
||||
input: crate::SystemInputEnvelope,
|
||||
) -> Self {
|
||||
let (body, input_metadata) = input.into_parts();
|
||||
Self {
|
||||
item: crate::SystemItem::Input { body },
|
||||
metadata: LoggedSessionHistoryMetadata {
|
||||
entry_id: LoggedSessionHistoryEntryId::new(),
|
||||
origin,
|
||||
derivation,
|
||||
input_metadata: Some(input_metadata),
|
||||
},
|
||||
}
|
||||
}
|
||||
|
||||
pub fn validate_input_metadata(&self) -> Result<(), crate::InputMetadataError> {
|
||||
self.metadata.validate_input_metadata()?;
|
||||
match (&self.item, &self.metadata.input_metadata) {
|
||||
(crate::SystemItem::Input { body }, Some(_)) => {
|
||||
if body.len() > crate::input_metadata::MAX_SYSTEM_INPUT_BYTES {
|
||||
return Err(crate::InputMetadataError::ResourceLimit);
|
||||
}
|
||||
}
|
||||
(crate::SystemItem::Input { .. }, None) => {
|
||||
return Err(crate::InputMetadataError::MissingMetadata);
|
||||
}
|
||||
(_, Some(_)) => return Err(crate::InputMetadataError::InconsistentRecord),
|
||||
(_, None) => {}
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
pub fn to_history_entry(&self) -> LoggedHistoryEntry {
|
||||
LoggedHistoryEntry {
|
||||
item: self.item.to_history_item().into(),
|
||||
metadata: self.metadata.clone(),
|
||||
}
|
||||
}
|
||||
|
||||
pub fn public_item(&self) -> crate::PublicSystemItem {
|
||||
if matches!(self.item, crate::SystemItem::Input { .. }) {
|
||||
return self
|
||||
.metadata
|
||||
.input_metadata
|
||||
.as_ref()
|
||||
.and_then(crate::HistoryInputMetadata::public_item)
|
||||
.cloned()
|
||||
.unwrap_or_else(|| self.item.public_item());
|
||||
}
|
||||
self.item.public_item()
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
@@ -130,6 +275,7 @@ mod tests {
|
||||
}],
|
||||
},
|
||||
metadata: LoggedSessionHistoryMetadata {
|
||||
input_metadata: None,
|
||||
entry_id: LoggedSessionHistoryEntryId::new(),
|
||||
origin: LoggedSessionHistoryOrigin::HumanInput {
|
||||
account_id: "account-1".into(),
|
||||
@@ -148,6 +294,64 @@ mod tests {
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn external_system_records_reject_missing_policy_role_mismatch_and_overlimit_body() {
|
||||
let valid = serde_json::json!({
|
||||
"item": { "kind": "input", "body": "context" },
|
||||
"metadata": {
|
||||
"entry_id": "stable-entry", "origin": { "kind": "provided", "producer": "owner" },
|
||||
"input_metadata": { "usage": {
|
||||
"recording_material": "exclude", "memory_evidence": "exclude",
|
||||
"observation": "hidden", "compaction": "reference_input"
|
||||
} }
|
||||
}
|
||||
});
|
||||
let restored: LoggedSystemHistoryEntry = serde_json::from_value(valid.clone()).unwrap();
|
||||
let flat = serde_json::to_value(restored.to_history_entry()).unwrap();
|
||||
assert!(serde_json::from_value::<LoggedHistoryEntry>(flat.clone()).is_ok());
|
||||
for generic in [true, false] {
|
||||
let wire = if generic { &valid } else { &flat };
|
||||
let decode = |wire| {
|
||||
if generic {
|
||||
serde_json::from_value::<LoggedSystemHistoryEntry>(wire).is_err()
|
||||
} else {
|
||||
serde_json::from_value::<LoggedHistoryEntry>(wire).is_err()
|
||||
}
|
||||
};
|
||||
let mut missing = wire.clone();
|
||||
missing["metadata"]
|
||||
.as_object_mut()
|
||||
.unwrap()
|
||||
.remove("input_metadata");
|
||||
assert!(decode(missing));
|
||||
let mut absent_policy = wire.clone();
|
||||
absent_policy["metadata"]["input_metadata"]
|
||||
.as_object_mut()
|
||||
.unwrap()
|
||||
.remove("usage");
|
||||
assert!(decode(absent_policy));
|
||||
let mut invalid_role = wire.clone();
|
||||
invalid_role["item"] =
|
||||
serde_json::to_value(LoggedItem::from(agen::Item::user_message("not system")))
|
||||
.unwrap();
|
||||
invalid_role["metadata"]["input_metadata"]["public"] = serde_json::json!({
|
||||
"kind": "context", "body": "public system projection", "presentation": {"kind": "context"}
|
||||
});
|
||||
assert!(decode(invalid_role));
|
||||
let mut oversized = wire.clone();
|
||||
if generic {
|
||||
oversized["item"]["body"] = "x"
|
||||
.repeat(crate::input_metadata::MAX_SYSTEM_INPUT_BYTES + 1)
|
||||
.into();
|
||||
} else {
|
||||
oversized["item"]["content"][0]["text"] = "x"
|
||||
.repeat(crate::input_metadata::MAX_SYSTEM_INPUT_BYTES + 1)
|
||||
.into();
|
||||
}
|
||||
assert!(decode(oversized));
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn annotated_segment_start_is_restore_visible_without_projecting_metadata() {
|
||||
let session_id = uuid::Uuid::now_v7();
|
||||
|
||||
@@ -0,0 +1,563 @@
|
||||
//! Validated, Feature-neutral history-input policy and System extensions.
|
||||
//!
|
||||
//! The enclosing history annotation owns identity, origin and derivation. None of
|
||||
//! those descriptive facts selects a use policy here. Model text, independent use
|
||||
//! policies, private Feature data and an explicit public projection travel as one
|
||||
//! value. Restoring this value does not load a Feature or invoke domain behavior.
|
||||
//!
|
||||
//! Payload validation bounds the decoded value; enclosing log readers must also
|
||||
//! enforce their record allocation limit before decoding untrusted persisted input.
|
||||
|
||||
use agen::Item;
|
||||
use serde::de::DeserializeOwned;
|
||||
use serde::{Deserialize, Serialize};
|
||||
use serde_json::Value;
|
||||
|
||||
use crate::PublicSystemItem;
|
||||
|
||||
pub const MAX_FEATURE_PAYLOAD_BYTES: usize = 128 * 1024;
|
||||
pub const MAX_SYSTEM_INPUT_BYTES: usize = 4 * 1024 * 1024;
|
||||
pub const MAX_SYSTEM_PUBLIC_BYTES: usize = 256 * 1024;
|
||||
const MAX_SCHEMA_BYTES: usize = 128;
|
||||
const MAX_JSON_DEPTH: usize = 16;
|
||||
const MAX_JSON_NODES: usize = 8192;
|
||||
|
||||
#[derive(Debug, Clone, Copy, PartialEq, Eq, thiserror::Error)]
|
||||
pub enum InputMetadataError {
|
||||
#[error("history input payload schema is invalid")]
|
||||
InvalidSchema,
|
||||
#[error("history input payload version must be nonzero")]
|
||||
InvalidVersion,
|
||||
#[error("system input resource limit exceeded")]
|
||||
ResourceLimit,
|
||||
#[error("history input payload could not be serialized")]
|
||||
Serialization,
|
||||
#[error("history input payload schema or version is unsupported by this consumer")]
|
||||
UnsupportedPayload,
|
||||
#[error("history input payload does not match the owner's typed contract")]
|
||||
InvalidTypedPayload,
|
||||
#[error("provided input is missing explicit metadata")]
|
||||
MissingMetadata,
|
||||
#[error("input metadata does not match its logical record")]
|
||||
InconsistentRecord,
|
||||
}
|
||||
|
||||
/// One private payload owned by a Feature's versioned typed decoder.
|
||||
/// Unknown valid schemas/versions remain data, never execution instructions.
|
||||
#[derive(Clone, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(try_from = "PayloadWire")]
|
||||
pub struct FeatureInputPayload {
|
||||
schema: String,
|
||||
version: u32,
|
||||
value: Value,
|
||||
}
|
||||
|
||||
impl std::fmt::Debug for FeatureInputPayload {
|
||||
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
|
||||
f.debug_struct("FeatureInputPayload")
|
||||
.field("schema", &self.schema)
|
||||
.field("version", &self.version)
|
||||
.finish_non_exhaustive()
|
||||
}
|
||||
}
|
||||
|
||||
#[derive(Deserialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
struct PayloadWire {
|
||||
schema: String,
|
||||
version: u32,
|
||||
value: Value,
|
||||
}
|
||||
|
||||
impl TryFrom<PayloadWire> for FeatureInputPayload {
|
||||
type Error = InputMetadataError;
|
||||
|
||||
fn try_from(wire: PayloadWire) -> Result<Self, Self::Error> {
|
||||
if wire.schema.is_empty()
|
||||
|| wire.schema.len() > MAX_SCHEMA_BYTES
|
||||
|| !wire.schema.as_bytes()[0].is_ascii_lowercase()
|
||||
|| !wire.schema.bytes().all(|byte| {
|
||||
byte.is_ascii_lowercase() || byte.is_ascii_digit() || b"-_.:/".contains(&byte)
|
||||
})
|
||||
{
|
||||
return Err(InputMetadataError::InvalidSchema);
|
||||
}
|
||||
if wire.version == 0 {
|
||||
return Err(InputMetadataError::InvalidVersion);
|
||||
}
|
||||
validate_json(&wire.value, MAX_FEATURE_PAYLOAD_BYTES)?;
|
||||
Ok(Self {
|
||||
schema: wire.schema,
|
||||
version: wire.version,
|
||||
value: wire.value,
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
impl FeatureInputPayload {
|
||||
pub fn encode<T: Serialize>(
|
||||
schema: impl Into<String>,
|
||||
version: u32,
|
||||
value: &T,
|
||||
) -> Result<Self, InputMetadataError> {
|
||||
PayloadWire {
|
||||
schema: schema.into(),
|
||||
version,
|
||||
value: serde_json::to_value(value).map_err(|_| InputMetadataError::Serialization)?,
|
||||
}
|
||||
.try_into()
|
||||
}
|
||||
|
||||
pub fn schema(&self) -> &str {
|
||||
&self.schema
|
||||
}
|
||||
|
||||
pub fn version(&self) -> u32 {
|
||||
self.version
|
||||
}
|
||||
|
||||
/// The owner explicitly selects its contract before decoding. A valid unknown
|
||||
/// payload can be retained and round-tripped without calling this operation.
|
||||
pub fn decode<T: DeserializeOwned>(
|
||||
&self,
|
||||
schema: &str,
|
||||
version: u32,
|
||||
) -> Result<T, InputMetadataError> {
|
||||
if self.schema != schema || self.version != version {
|
||||
return Err(InputMetadataError::UnsupportedPayload);
|
||||
}
|
||||
serde_json::from_value(self.value.clone())
|
||||
.map_err(|_| InputMetadataError::InvalidTypedPayload)
|
||||
}
|
||||
}
|
||||
|
||||
/// Eligibility is supplied independently for recording and Memory evidence.
|
||||
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(rename_all = "snake_case")]
|
||||
pub enum InputEvidenceUse {
|
||||
Include,
|
||||
Exclude,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(rename_all = "snake_case")]
|
||||
pub enum InputObservationUse {
|
||||
Readable,
|
||||
Hidden,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(rename_all = "snake_case")]
|
||||
pub enum InputCompactionUse {
|
||||
/// Ordinary history eligible for the selected retained tail.
|
||||
Retain,
|
||||
/// A full opening summary consumed separately and superseded by compaction.
|
||||
OpeningSummary,
|
||||
/// Full historical context for the compactor, not an accumulating retained tail.
|
||||
ReferenceInput,
|
||||
}
|
||||
|
||||
/// No permissive defaults: malformed/unknown policies cannot turn into eligibility.
|
||||
/// Public presentation is deliberately not one of these use decisions.
|
||||
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct HistoryInputUsePolicy {
|
||||
pub recording_material: InputEvidenceUse,
|
||||
pub memory_evidence: InputEvidenceUse,
|
||||
pub observation: InputObservationUse,
|
||||
pub compaction: InputCompactionUse,
|
||||
}
|
||||
|
||||
/// Use policy is independent of logical role. Non-System derived Tool context
|
||||
/// carries policy only; private Feature payload and public presentation belong
|
||||
/// to the System envelope and are rejected on other roles at the history boundary.
|
||||
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq)]
|
||||
#[serde(try_from = "MetadataWire")]
|
||||
pub struct HistoryInputMetadata {
|
||||
usage: HistoryInputUsePolicy,
|
||||
feature_payload: Option<FeatureInputPayload>,
|
||||
public: Option<PublicSystemItem>,
|
||||
}
|
||||
|
||||
#[derive(Deserialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
struct MetadataWire {
|
||||
usage: HistoryInputUsePolicy,
|
||||
feature_payload: Option<FeatureInputPayload>,
|
||||
public: Option<PublicSystemItem>,
|
||||
}
|
||||
|
||||
impl TryFrom<MetadataWire> for HistoryInputMetadata {
|
||||
type Error = InputMetadataError;
|
||||
|
||||
fn try_from(wire: MetadataWire) -> Result<Self, Self::Error> {
|
||||
if let Some(public) = &wire.public {
|
||||
// Kind is a descriptive label, not a Feature dispatch or authority key.
|
||||
if public.kind.is_empty()
|
||||
|| public.kind.len() > MAX_SCHEMA_BYTES
|
||||
|| public.kind.chars().any(char::is_control)
|
||||
{
|
||||
return Err(InputMetadataError::InvalidSchema);
|
||||
}
|
||||
let value =
|
||||
serde_json::to_value(public).map_err(|_| InputMetadataError::Serialization)?;
|
||||
validate_json(&value, MAX_SYSTEM_PUBLIC_BYTES)?;
|
||||
}
|
||||
Ok(Self {
|
||||
usage: wire.usage,
|
||||
feature_payload: wire.feature_payload,
|
||||
public: wire.public,
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
impl HistoryInputMetadata {
|
||||
pub fn new(
|
||||
usage: HistoryInputUsePolicy,
|
||||
feature_payload: Option<FeatureInputPayload>,
|
||||
public: Option<PublicSystemItem>,
|
||||
) -> Result<Self, InputMetadataError> {
|
||||
MetadataWire {
|
||||
usage,
|
||||
feature_payload,
|
||||
public,
|
||||
}
|
||||
.try_into()
|
||||
}
|
||||
|
||||
pub fn usage(&self) -> HistoryInputUsePolicy {
|
||||
self.usage
|
||||
}
|
||||
|
||||
pub fn feature_payload(&self) -> Option<&FeatureInputPayload> {
|
||||
self.feature_payload.as_ref()
|
||||
}
|
||||
|
||||
pub fn public_item(&self) -> Option<&PublicSystemItem> {
|
||||
self.public.as_ref()
|
||||
}
|
||||
|
||||
pub fn public_use_policy(&self) -> protocol::SessionEntryUsePolicy {
|
||||
protocol::SessionEntryUsePolicy {
|
||||
observation_readable: self.usage.observation == InputObservationUse::Readable,
|
||||
memory_evidence: self.usage.memory_evidence == InputEvidenceUse::Include,
|
||||
}
|
||||
}
|
||||
|
||||
pub fn public_system_use_policy(&self) -> protocol::SessionEntryUsePolicy {
|
||||
if self.public.is_some() {
|
||||
self.public_use_policy()
|
||||
} else {
|
||||
protocol::SessionEntryUsePolicy {
|
||||
observation_readable: false,
|
||||
memory_evidence: false,
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
pub fn public_projection(&self) -> PublicSystemItem {
|
||||
self.public.clone().unwrap_or_else(|| PublicSystemItem {
|
||||
kind: "input".into(),
|
||||
body: String::new(),
|
||||
presentation: crate::PublicSystemPresentation::Ignored,
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
/// System role is invariant; provenance and use policies are attached data.
|
||||
/// An absent public projection never implicitly publishes the model body.
|
||||
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq)]
|
||||
#[serde(try_from = "InputWire")]
|
||||
pub struct SystemInputEnvelope {
|
||||
body: String,
|
||||
metadata: HistoryInputMetadata,
|
||||
}
|
||||
|
||||
#[derive(Deserialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
struct InputWire {
|
||||
body: String,
|
||||
metadata: HistoryInputMetadata,
|
||||
}
|
||||
|
||||
impl TryFrom<InputWire> for SystemInputEnvelope {
|
||||
type Error = InputMetadataError;
|
||||
|
||||
fn try_from(wire: InputWire) -> Result<Self, Self::Error> {
|
||||
if wire.body.len() > MAX_SYSTEM_INPUT_BYTES {
|
||||
return Err(InputMetadataError::ResourceLimit);
|
||||
}
|
||||
Ok(Self {
|
||||
body: wire.body,
|
||||
metadata: wire.metadata,
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
impl SystemInputEnvelope {
|
||||
pub fn new(
|
||||
body: impl Into<String>,
|
||||
metadata: HistoryInputMetadata,
|
||||
) -> Result<Self, InputMetadataError> {
|
||||
InputWire {
|
||||
body: body.into(),
|
||||
metadata,
|
||||
}
|
||||
.try_into()
|
||||
}
|
||||
|
||||
pub fn body(&self) -> &str {
|
||||
&self.body
|
||||
}
|
||||
|
||||
pub fn metadata(&self) -> &HistoryInputMetadata {
|
||||
&self.metadata
|
||||
}
|
||||
|
||||
pub fn to_history_item(&self) -> Item {
|
||||
Item::system_message(self.body.clone())
|
||||
}
|
||||
|
||||
pub fn into_parts(self) -> (String, HistoryInputMetadata) {
|
||||
(self.body, self.metadata)
|
||||
}
|
||||
}
|
||||
|
||||
fn validate_json(value: &Value, max_bytes: usize) -> Result<(), InputMetadataError> {
|
||||
fn walk(value: &Value, depth: usize, remaining: &mut usize) -> Result<(), InputMetadataError> {
|
||||
if depth > MAX_JSON_DEPTH || *remaining == 0 {
|
||||
return Err(InputMetadataError::ResourceLimit);
|
||||
}
|
||||
*remaining -= 1;
|
||||
match value {
|
||||
Value::Array(values) => {
|
||||
for value in values {
|
||||
walk(value, depth + 1, remaining)?;
|
||||
}
|
||||
}
|
||||
Value::Object(values) => {
|
||||
for value in values.values() {
|
||||
walk(value, depth + 1, remaining)?;
|
||||
}
|
||||
}
|
||||
_ => {}
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
let mut remaining = MAX_JSON_NODES;
|
||||
walk(value, 0, &mut remaining)?;
|
||||
let bytes = serde_json::to_vec(value).map_err(|_| InputMetadataError::Serialization)?;
|
||||
if bytes.len() > max_bytes {
|
||||
return Err(InputMetadataError::ResourceLimit);
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
use crate::{LoggedItem, LoggedRole, PublicSystemPresentation};
|
||||
|
||||
#[derive(Debug, PartialEq, Serialize, Deserialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
struct OwnerPayload {
|
||||
source_digest: String,
|
||||
omitted: bool,
|
||||
}
|
||||
|
||||
fn reference_policy() -> HistoryInputUsePolicy {
|
||||
HistoryInputUsePolicy {
|
||||
recording_material: InputEvidenceUse::Exclude,
|
||||
memory_evidence: InputEvidenceUse::Exclude,
|
||||
observation: InputObservationUse::Hidden,
|
||||
compaction: InputCompactionUse::ReferenceInput,
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn unknown_valid_payload_round_trips_without_domain_decode_or_public_exposure() {
|
||||
let payload = FeatureInputPayload::encode(
|
||||
"future-owner:context",
|
||||
99,
|
||||
&OwnerPayload {
|
||||
source_digest: "private-digest".into(),
|
||||
omitted: true,
|
||||
},
|
||||
)
|
||||
.unwrap();
|
||||
let envelope = SystemInputEnvelope::new(
|
||||
"private model context",
|
||||
HistoryInputMetadata::new(reference_policy(), Some(payload), None).unwrap(),
|
||||
)
|
||||
.unwrap();
|
||||
let restored: SystemInputEnvelope =
|
||||
serde_json::from_slice(&serde_json::to_vec(&envelope).unwrap()).unwrap();
|
||||
assert_eq!(restored.body(), "private model context");
|
||||
assert!(restored.metadata().public_item().is_none());
|
||||
let saved_payload = restored.metadata().feature_payload().unwrap();
|
||||
assert_eq!(saved_payload.schema(), "future-owner:context");
|
||||
assert_eq!(saved_payload.version(), 99);
|
||||
assert_eq!(
|
||||
saved_payload.decode::<OwnerPayload>("known-owner:context", 1),
|
||||
Err(InputMetadataError::UnsupportedPayload)
|
||||
);
|
||||
assert_eq!(
|
||||
serde_json::to_value(&restored).unwrap(),
|
||||
serde_json::to_value(&envelope).unwrap()
|
||||
);
|
||||
assert!(!format!("{saved_payload:?}").contains("private-digest"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn owner_decodes_typed_payload_only_for_its_explicit_contract() {
|
||||
let input = OwnerPayload {
|
||||
source_digest: "rev".into(),
|
||||
omitted: false,
|
||||
};
|
||||
let payload = FeatureInputPayload::encode("owner:context", 1, &input).unwrap();
|
||||
assert_eq!(
|
||||
payload.decode::<OwnerPayload>("owner:context", 1).unwrap(),
|
||||
input
|
||||
);
|
||||
let invalid = FeatureInputPayload::encode(
|
||||
"owner:context",
|
||||
1,
|
||||
&serde_json::json!({ "omitted": "not a bool" }),
|
||||
)
|
||||
.unwrap();
|
||||
assert_eq!(
|
||||
invalid.decode::<OwnerPayload>("owner:context", 1),
|
||||
Err(InputMetadataError::InvalidTypedPayload)
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn malformed_or_oversized_payload_is_rejected_at_construction_and_restore() {
|
||||
for (schema, version, value) in [
|
||||
("", 1, Value::Null),
|
||||
("invalid schema", 1, Value::Null),
|
||||
("owner:context", 0, Value::Null),
|
||||
(
|
||||
"owner:context",
|
||||
1,
|
||||
Value::String("x".repeat(MAX_FEATURE_PAYLOAD_BYTES)),
|
||||
),
|
||||
(
|
||||
"owner:context",
|
||||
1,
|
||||
Value::Array(vec![Value::Null; MAX_JSON_NODES]),
|
||||
),
|
||||
(
|
||||
"owner:context",
|
||||
1,
|
||||
(0..=MAX_JSON_DEPTH).fold(Value::Null, |inner, _| Value::Array(vec![inner])),
|
||||
),
|
||||
] {
|
||||
assert!(FeatureInputPayload::encode(schema, version, &value).is_err());
|
||||
assert!(
|
||||
serde_json::from_value::<FeatureInputPayload>(
|
||||
serde_json::json!({ "schema": schema, "version": version, "value": value })
|
||||
)
|
||||
.is_err()
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn policy_is_required_and_unknown_or_malformed_fields_fail_closed() {
|
||||
let valid = serde_json::to_value(reference_policy()).unwrap();
|
||||
for field in [
|
||||
"recording_material",
|
||||
"memory_evidence",
|
||||
"observation",
|
||||
"compaction",
|
||||
] {
|
||||
let mut absent = valid.clone();
|
||||
absent.as_object_mut().unwrap().remove(field);
|
||||
assert!(serde_json::from_value::<HistoryInputUsePolicy>(absent).is_err());
|
||||
let mut unknown = valid.clone();
|
||||
unknown[field] = Value::String("future-allow".into());
|
||||
assert!(serde_json::from_value::<HistoryInputUsePolicy>(unknown).is_err());
|
||||
}
|
||||
let mut extra = valid;
|
||||
extra["feature_name"] = Value::String("infer-policy-from-me".into());
|
||||
assert!(serde_json::from_value::<HistoryInputUsePolicy>(extra).is_err());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn feature_name_and_model_body_do_not_select_policies_or_public_projection() {
|
||||
for (schema, body) in [
|
||||
("owner:journal", "past context"),
|
||||
("unrelated:skill", "do not extract this; legitimate wording"),
|
||||
] {
|
||||
let public = PublicSystemItem {
|
||||
kind: "context-label".into(),
|
||||
body: "explicit public text".into(),
|
||||
presentation: PublicSystemPresentation::Context,
|
||||
};
|
||||
let metadata = HistoryInputMetadata::new(
|
||||
reference_policy(),
|
||||
Some(
|
||||
FeatureInputPayload::encode(
|
||||
schema,
|
||||
1,
|
||||
&OwnerPayload {
|
||||
source_digest: "private".into(),
|
||||
omitted: false,
|
||||
},
|
||||
)
|
||||
.unwrap(),
|
||||
),
|
||||
Some(public),
|
||||
)
|
||||
.unwrap();
|
||||
let input = SystemInputEnvelope::new(body, metadata).unwrap();
|
||||
assert_eq!(input.metadata().usage(), reference_policy());
|
||||
let history: LoggedItem = input.to_history_item().into();
|
||||
assert!(matches!(
|
||||
history,
|
||||
LoggedItem::Message {
|
||||
role: LoggedRole::System,
|
||||
..
|
||||
}
|
||||
));
|
||||
assert_eq!(input.to_history_item().as_text(), Some(body));
|
||||
let public = serde_json::to_string(input.metadata().public_item().unwrap()).unwrap();
|
||||
assert!(!public.contains("private"));
|
||||
assert!(!public.contains(schema));
|
||||
assert!(!public.contains(body));
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn use_policies_remain_independent_of_each_other_and_of_public_display() {
|
||||
let usage = HistoryInputUsePolicy {
|
||||
recording_material: InputEvidenceUse::Include,
|
||||
memory_evidence: InputEvidenceUse::Exclude,
|
||||
observation: InputObservationUse::Readable,
|
||||
compaction: InputCompactionUse::Retain,
|
||||
};
|
||||
let metadata = HistoryInputMetadata::new(usage, None, None).unwrap();
|
||||
let restored: HistoryInputMetadata =
|
||||
serde_json::from_value(serde_json::to_value(&metadata).unwrap()).unwrap();
|
||||
assert_eq!(restored.usage(), usage);
|
||||
assert!(restored.public_item().is_none());
|
||||
assert!(restored.feature_payload().is_none());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn model_body_and_public_projection_have_independent_resource_limits() {
|
||||
let metadata = HistoryInputMetadata::new(reference_policy(), None, None).unwrap();
|
||||
assert!(
|
||||
SystemInputEnvelope::new("x".repeat(MAX_SYSTEM_INPUT_BYTES + 1), metadata).is_err()
|
||||
);
|
||||
let public = PublicSystemItem {
|
||||
kind: "context".into(),
|
||||
body: "x".repeat(MAX_SYSTEM_PUBLIC_BYTES),
|
||||
presentation: PublicSystemPresentation::Context,
|
||||
};
|
||||
assert!(HistoryInputMetadata::new(reference_policy(), None, Some(public)).is_err());
|
||||
let invalid = serde_json::json!({ "body": "small", "metadata": { "public": null, "feature_payload": null } });
|
||||
assert!(serde_json::from_value::<SystemInputEnvelope>(invalid).is_err());
|
||||
}
|
||||
}
|
||||
@@ -1,12 +1,15 @@
|
||||
//! Versioned decoder for Session schemas that predate canonical annotated history.
|
||||
//! Versioned decoder for Session schemas v1-5, including frozen Feature wire.
|
||||
//!
|
||||
//! These types are intentionally private to `session-store`. Current writers,
|
||||
//! replay, and public projections use [`crate::LogEntry`] exclusively; only the
|
||||
//! Worker Session schema migration is allowed to deserialize these shapes.
|
||||
//! explicit Session schema migration is allowed to deserialize these shapes.
|
||||
|
||||
use agen::llm_client::types::RequestConfig;
|
||||
use protocol::Segment;
|
||||
use serde::Deserialize;
|
||||
use serde::{Deserialize, Serialize};
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests;
|
||||
|
||||
use crate::{
|
||||
LogEntry, LoggedHistoryEntry, LoggedItem, LoggedSessionHistoryEntryId,
|
||||
@@ -14,6 +17,212 @@ use crate::{
|
||||
SegmentOrigin, SessionExtension, SessionId, SystemItem,
|
||||
};
|
||||
|
||||
// Frozen v1-4 Feature wire. These types are deliberately not exported and are
|
||||
// never used by LogEntry/SystemItem's current deserializers. Payload structs
|
||||
// retain the owner's v1 shape rather than erasing typed fields into arbitrary JSON.
|
||||
#[derive(Debug, Serialize, Deserialize)]
|
||||
struct JournalStartupPayload {
|
||||
snapshot: serde_json::Value,
|
||||
snapshot_sha256: String,
|
||||
prompt_provenance: crate::PromptRenderProvenance,
|
||||
}
|
||||
|
||||
#[derive(Debug, Serialize, Deserialize)]
|
||||
struct ResidentSummaryPayload {
|
||||
#[serde(default)]
|
||||
prompt_provenance: Option<crate::PromptRenderProvenance>,
|
||||
}
|
||||
|
||||
#[derive(Debug, Serialize, Deserialize)]
|
||||
struct SubjectBehaviorPayload {
|
||||
#[serde(default)]
|
||||
behavior_md: String,
|
||||
#[serde(default)]
|
||||
prompt_provenance: Option<crate::PromptRenderProvenance>,
|
||||
}
|
||||
|
||||
#[derive(Debug, Serialize, Deserialize)]
|
||||
struct SkillActivationPayload {
|
||||
name: String,
|
||||
}
|
||||
|
||||
#[derive(Debug, Serialize, Deserialize)]
|
||||
struct InvocationResultPayload {
|
||||
result: protocol::FeatureInvocationResult,
|
||||
}
|
||||
|
||||
#[derive(Debug, Deserialize)]
|
||||
#[serde(tag = "kind", rename_all = "snake_case")]
|
||||
enum LegacyFeatureSystemItem {
|
||||
JournalStartup {
|
||||
body: String,
|
||||
#[serde(flatten)]
|
||||
payload: JournalStartupPayload,
|
||||
},
|
||||
ResidentSummaryRefresh {
|
||||
body: String,
|
||||
#[serde(flatten)]
|
||||
payload: ResidentSummaryPayload,
|
||||
},
|
||||
SubjectBehaviorRefresh {
|
||||
body: String,
|
||||
#[serde(flatten)]
|
||||
payload: SubjectBehaviorPayload,
|
||||
},
|
||||
SkillActivation {
|
||||
body: String,
|
||||
#[serde(flatten)]
|
||||
payload: SkillActivationPayload,
|
||||
},
|
||||
FeatureInvocationResult {
|
||||
body: String,
|
||||
#[serde(flatten)]
|
||||
payload: InvocationResultPayload,
|
||||
},
|
||||
}
|
||||
|
||||
#[derive(Debug, Deserialize)]
|
||||
#[serde(untagged)]
|
||||
enum LegacySystemItem {
|
||||
Feature(LegacyFeatureSystemItem),
|
||||
// Includes already-migrated Input records for interrupted migration retry.
|
||||
Core(SystemItem),
|
||||
}
|
||||
|
||||
impl LegacySystemItem {
|
||||
fn into_entry(
|
||||
self,
|
||||
mut metadata: LoggedSessionHistoryMetadata,
|
||||
) -> Result<LoggedSystemHistoryEntry, crate::InputMetadataError> {
|
||||
use crate::InputCompactionUse::{ReferenceInput, Retain};
|
||||
let item = match self {
|
||||
Self::Core(item) => item,
|
||||
Self::Feature(feature) => {
|
||||
metadata.validate_input_metadata()?;
|
||||
if metadata.input_metadata.is_some() {
|
||||
return Err(crate::InputMetadataError::InconsistentRecord);
|
||||
}
|
||||
let (body, input_metadata) = match feature {
|
||||
LegacyFeatureSystemItem::JournalStartup { body, payload } => {
|
||||
migrated_feature_input(
|
||||
body,
|
||||
"journal_startup",
|
||||
"journal:startup",
|
||||
payload,
|
||||
ReferenceInput,
|
||||
)?
|
||||
}
|
||||
LegacyFeatureSystemItem::ResidentSummaryRefresh { body, payload } => {
|
||||
migrated_feature_input(
|
||||
body,
|
||||
"resident_summary_refresh",
|
||||
"memory:resident-summary",
|
||||
payload,
|
||||
Retain,
|
||||
)?
|
||||
}
|
||||
LegacyFeatureSystemItem::SubjectBehaviorRefresh { body, payload } => {
|
||||
migrated_feature_input(
|
||||
body,
|
||||
"subject_behavior_refresh",
|
||||
"subject:behavior",
|
||||
payload,
|
||||
Retain,
|
||||
)?
|
||||
}
|
||||
LegacyFeatureSystemItem::SkillActivation { body, payload } => {
|
||||
migrated_feature_input(
|
||||
body,
|
||||
"skill_activation",
|
||||
"skill:activation",
|
||||
payload,
|
||||
Retain,
|
||||
)?
|
||||
}
|
||||
LegacyFeatureSystemItem::FeatureInvocationResult { body, payload } => {
|
||||
migrated_feature_input(
|
||||
body,
|
||||
"feature_invocation_result",
|
||||
"feature:invocation-result",
|
||||
payload,
|
||||
Retain,
|
||||
)?
|
||||
}
|
||||
};
|
||||
// Identity/origin/derivation are retained, never re-inferred.
|
||||
metadata.input_metadata = Some(input_metadata);
|
||||
SystemItem::Input { body }
|
||||
}
|
||||
};
|
||||
let entry = LoggedSystemHistoryEntry { item, metadata };
|
||||
entry.validate_input_metadata()?;
|
||||
Ok(entry)
|
||||
}
|
||||
}
|
||||
|
||||
fn migrated_feature_input<T: Serialize>(
|
||||
body: String,
|
||||
label: &str,
|
||||
schema: &str,
|
||||
payload: T,
|
||||
compaction: crate::InputCompactionUse,
|
||||
) -> Result<(String, crate::HistoryInputMetadata), crate::InputMetadataError> {
|
||||
let metadata = crate::HistoryInputMetadata::new(
|
||||
migration_policy(compaction),
|
||||
Some(crate::FeatureInputPayload::encode(schema, 1, &payload)?),
|
||||
Some(crate::PublicSystemItem {
|
||||
kind: label.into(),
|
||||
body: body.clone(),
|
||||
presentation: crate::PublicSystemPresentation::Context,
|
||||
}),
|
||||
)?;
|
||||
Ok((body, metadata))
|
||||
}
|
||||
|
||||
/// Annotated old wire used by v3/v4, and by already-converted files when an
|
||||
/// older marker survived an interrupted migration. No ordinary decoder uses it.
|
||||
#[derive(Debug, Deserialize)]
|
||||
#[serde(tag = "kind", rename_all = "snake_case")]
|
||||
enum LegacyAnnotatedLogEntry {
|
||||
AnnotatedSystemItem {
|
||||
ts: u64,
|
||||
entry: LegacySystemHistoryEntry,
|
||||
#[serde(default)]
|
||||
extensions: Vec<SessionExtension>,
|
||||
},
|
||||
}
|
||||
|
||||
#[derive(Debug, Deserialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
struct LegacySystemHistoryEntry {
|
||||
item: LegacySystemItem,
|
||||
metadata: LoggedSessionHistoryMetadata,
|
||||
}
|
||||
|
||||
#[derive(Debug, Deserialize)]
|
||||
#[serde(untagged)]
|
||||
enum LegacyAnnotatedOrCurrent {
|
||||
Annotated(LegacyAnnotatedLogEntry),
|
||||
Current(LogEntry),
|
||||
}
|
||||
|
||||
impl LegacyAnnotatedOrCurrent {
|
||||
fn into_current(self) -> Result<LogEntry, crate::InputMetadataError> {
|
||||
match self {
|
||||
Self::Annotated(LegacyAnnotatedLogEntry::AnnotatedSystemItem {
|
||||
ts,
|
||||
entry,
|
||||
extensions,
|
||||
}) => Ok(LogEntry::AnnotatedSystemItem {
|
||||
ts,
|
||||
entry: entry.item.into_entry(entry.metadata)?,
|
||||
extensions,
|
||||
}),
|
||||
Self::Current(entry) => Ok(entry),
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[derive(Debug, Deserialize)]
|
||||
#[serde(tag = "kind", rename_all = "snake_case")]
|
||||
enum LegacyHistoryLogEntry {
|
||||
@@ -44,7 +253,9 @@ enum LegacyHistoryLogEntry {
|
||||
},
|
||||
SystemItem {
|
||||
ts: u64,
|
||||
item: SystemItem,
|
||||
item: LegacySystemItem,
|
||||
#[serde(default)]
|
||||
extensions: Vec<SessionExtension>,
|
||||
},
|
||||
}
|
||||
|
||||
@@ -54,7 +265,7 @@ enum LegacyHistoryLogEntry {
|
||||
#[serde(untagged)]
|
||||
enum LegacySessionLogEntryV1 {
|
||||
History(LegacyHistoryLogEntry),
|
||||
Current(LogEntry),
|
||||
Current(LegacyAnnotatedOrCurrent),
|
||||
}
|
||||
|
||||
/// Schema v2 retained the v1 history shapes while adding non-history records.
|
||||
@@ -64,7 +275,7 @@ enum LegacySessionLogEntryV1 {
|
||||
#[serde(untagged)]
|
||||
enum LegacySessionLogEntryV2 {
|
||||
History(LegacyHistoryLogEntry),
|
||||
Current(LogEntry),
|
||||
Current(LegacyAnnotatedOrCurrent),
|
||||
}
|
||||
|
||||
pub(crate) fn decode_entry(
|
||||
@@ -74,28 +285,207 @@ pub(crate) fn decode_entry(
|
||||
segment_id: SegmentId,
|
||||
line_index: usize,
|
||||
) -> Result<LogEntry, serde_json::Error> {
|
||||
let mut wire: serde_json::Value = serde_json::from_str(line)?;
|
||||
migrate_legacy_metadata_field(&mut wire)?;
|
||||
let entry = match schema_version {
|
||||
1 => match serde_json::from_str::<LegacySessionLogEntryV1>(line)? {
|
||||
1 => match serde_json::from_value::<LegacySessionLogEntryV1>(wire)? {
|
||||
LegacySessionLogEntryV1::History(entry) => Entry::History(entry),
|
||||
LegacySessionLogEntryV1::Current(entry) => Entry::Current(entry),
|
||||
},
|
||||
2 => match serde_json::from_str::<LegacySessionLogEntryV2>(line)? {
|
||||
2 => match serde_json::from_value::<LegacySessionLogEntryV2>(wire)? {
|
||||
LegacySessionLogEntryV2::History(entry) => Entry::History(entry),
|
||||
LegacySessionLogEntryV2::Current(entry) => Entry::Current(entry),
|
||||
},
|
||||
3 | 4 => Entry::Current(serde_json::from_value(wire)?),
|
||||
5 => return serde_json::from_value(wire),
|
||||
_ => unreachable!("legacy decoder called for unsupported schema {schema_version}"),
|
||||
};
|
||||
Ok(match entry {
|
||||
match entry {
|
||||
Entry::History(entry) => {
|
||||
canonicalize_history_entry(session_id, segment_id, line_index, entry)
|
||||
}
|
||||
Entry::Current(entry) => entry,
|
||||
})
|
||||
Entry::Current(entry) => entry.into_current(),
|
||||
}
|
||||
.map_err(serde::de::Error::custom)
|
||||
}
|
||||
|
||||
// The v5 System-only metadata field was widened to role-neutral input metadata
|
||||
// in v6. Touch only known history slots, never arbitrary Feature payload objects.
|
||||
// Both keys are an ambiguous source, not permission to discard either value.
|
||||
fn migrate_legacy_metadata_field(record: &mut serde_json::Value) -> Result<(), serde_json::Error> {
|
||||
fn entry(value: &mut serde_json::Value) -> Result<(), serde_json::Error> {
|
||||
if let Some(metadata) = value
|
||||
.get_mut("metadata")
|
||||
.and_then(serde_json::Value::as_object_mut)
|
||||
{
|
||||
if let Some(old) = metadata.remove("system_input") {
|
||||
if metadata.contains_key("input_metadata") {
|
||||
return Err(serde::de::Error::custom(
|
||||
"ambiguous legacy input metadata fields",
|
||||
));
|
||||
}
|
||||
metadata.insert("input_metadata".into(), old);
|
||||
}
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
let kind = record
|
||||
.get("kind")
|
||||
.and_then(serde_json::Value::as_str)
|
||||
.unwrap_or_default()
|
||||
.to_owned();
|
||||
if matches!(
|
||||
kind.as_str(),
|
||||
"annotated_system_item"
|
||||
| "annotated_assistant_item"
|
||||
| "annotated_tool_result"
|
||||
| "tool_result_corrected"
|
||||
) {
|
||||
if let Some(value) = record.get_mut("entry") {
|
||||
entry(value)?;
|
||||
}
|
||||
}
|
||||
if let Some(history) = record
|
||||
.get_mut("history")
|
||||
.and_then(serde_json::Value::as_array_mut)
|
||||
{
|
||||
for value in history {
|
||||
entry(value)?;
|
||||
}
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Schema 3 used DerivedSummary for Host compaction seeds. Only the trusted
|
||||
/// creation boundary may identify one; arbitrary text and later seed items do not.
|
||||
/// Include already-upgraded entries so an interrupted multi-file migration resumes.
|
||||
pub(crate) fn compaction_summary_ids<'a>(
|
||||
entries: impl Iterator<Item = &'a LogEntry>,
|
||||
) -> std::collections::HashSet<LoggedSessionHistoryEntryId> {
|
||||
entries
|
||||
.filter_map(|entry| {
|
||||
let LogEntry::AnnotatedSegmentStart {
|
||||
compacted_from: Some(_),
|
||||
forked_from: None,
|
||||
history,
|
||||
..
|
||||
} = entry
|
||||
else {
|
||||
return None;
|
||||
};
|
||||
let first = history.first()?;
|
||||
(matches!(
|
||||
first.metadata.origin,
|
||||
LoggedSessionHistoryOrigin::DerivedSummary
|
||||
| LoggedSessionHistoryOrigin::CompactionSummary
|
||||
) && matches!(
|
||||
first.item,
|
||||
LoggedItem::Message {
|
||||
role: crate::LoggedRole::System,
|
||||
..
|
||||
}
|
||||
) && agen::Item::from(first.item.clone())
|
||||
.as_text()
|
||||
.is_some_and(|text| text.starts_with("[Compacted context summary]\n\n")))
|
||||
.then(|| first.metadata.entry_id.clone())
|
||||
})
|
||||
.collect()
|
||||
}
|
||||
|
||||
pub(crate) fn migrate_compaction_origins(
|
||||
entries: &mut [LogEntry],
|
||||
summaries: &std::collections::HashSet<LoggedSessionHistoryEntryId>,
|
||||
) {
|
||||
// Only inherited seed copies can share these identities. Appended input is
|
||||
// not a construction boundary and must never be reclassified from its text.
|
||||
for entry in entries {
|
||||
if let LogEntry::AnnotatedSegmentStart { history, .. } = entry {
|
||||
for entry in history {
|
||||
if summaries.contains(&entry.metadata.entry_id)
|
||||
&& entry.metadata.origin == LoggedSessionHistoryOrigin::DerivedSummary
|
||||
{
|
||||
entry.metadata.origin = LoggedSessionHistoryOrigin::CompactionSummary;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Explicit legacy-to-current boundary. No Feature inference belongs in ordinary
|
||||
/// readers/restoration. Invalid or oversized payloads fail migration; the generic
|
||||
/// payload/body/public limits are deliberately not relaxed for legacy data.
|
||||
pub(crate) fn migrate_system_inputs(entry: &mut LogEntry) -> Result<(), crate::InputMetadataError> {
|
||||
entry.validate_input_metadata()?;
|
||||
match entry {
|
||||
// Feature wire has already been converted by the explicit old-schema
|
||||
// decoder. Ordinary LogEntry can contain only generic Input/core events.
|
||||
LogEntry::AnnotatedSystemItem { entry, .. } => entry.validate_input_metadata()?,
|
||||
LogEntry::AnnotatedSegmentStart { history, .. }
|
||||
| LogEntry::AnnotatedUserInput { history, .. } => {
|
||||
for entry in history {
|
||||
migrate_flattened_system_input(entry)?;
|
||||
}
|
||||
}
|
||||
LogEntry::AnnotatedAssistantItem { entry, .. }
|
||||
| LogEntry::AnnotatedToolResult { entry, .. }
|
||||
| LogEntry::ToolResultCorrected { entry, .. } => {
|
||||
migrate_flattened_system_input(entry)?;
|
||||
}
|
||||
_ => {}
|
||||
}
|
||||
entry.validate_input_metadata()
|
||||
}
|
||||
|
||||
fn migration_policy(compaction: crate::InputCompactionUse) -> crate::HistoryInputUsePolicy {
|
||||
crate::HistoryInputUsePolicy {
|
||||
recording_material: crate::InputEvidenceUse::Exclude,
|
||||
memory_evidence: crate::InputEvidenceUse::Exclude,
|
||||
observation: crate::InputObservationUse::Hidden,
|
||||
compaction,
|
||||
}
|
||||
}
|
||||
|
||||
fn migrate_flattened_system_input(
|
||||
entry: &mut LoggedHistoryEntry,
|
||||
) -> Result<(), crate::InputMetadataError> {
|
||||
// Check before supplying legacy policy: Provided without metadata is a
|
||||
// malformed NEW record, not permission to synthesize a producer policy.
|
||||
entry.validate_input_metadata()?;
|
||||
if entry.metadata.input_metadata.is_none()
|
||||
&& (matches!(
|
||||
entry.item,
|
||||
LoggedItem::Message {
|
||||
role: crate::LoggedRole::System,
|
||||
..
|
||||
}
|
||||
) || matches!(
|
||||
entry.metadata.origin,
|
||||
LoggedSessionHistoryOrigin::DerivedSummary
|
||||
| LoggedSessionHistoryOrigin::CompactionSummary
|
||||
))
|
||||
{
|
||||
let compaction = match entry.metadata.origin {
|
||||
LoggedSessionHistoryOrigin::JournalContext => crate::InputCompactionUse::ReferenceInput,
|
||||
LoggedSessionHistoryOrigin::CompactionSummary => {
|
||||
crate::InputCompactionUse::OpeningSummary
|
||||
}
|
||||
_ => crate::InputCompactionUse::Retain,
|
||||
};
|
||||
// Legacy derived context was excluded from independent evidence. Preserve
|
||||
// that established decision explicitly, including synthetic Tool roles;
|
||||
// never guess from Tool names or body text. Payload/public stay absent.
|
||||
entry.metadata.input_metadata = Some(crate::HistoryInputMetadata::new(
|
||||
migration_policy(compaction),
|
||||
None,
|
||||
None,
|
||||
)?);
|
||||
}
|
||||
entry.validate_input_metadata()
|
||||
}
|
||||
|
||||
enum Entry {
|
||||
History(LegacyHistoryLogEntry),
|
||||
Current(LogEntry),
|
||||
Current(LegacyAnnotatedOrCurrent),
|
||||
}
|
||||
|
||||
fn legacy_metadata(
|
||||
@@ -108,6 +498,7 @@ fn legacy_metadata(
|
||||
identity.extend_from_slice(&(line_index as u64).to_be_bytes());
|
||||
identity.extend_from_slice(&(item_index as u64).to_be_bytes());
|
||||
LoggedSessionHistoryMetadata {
|
||||
input_metadata: None,
|
||||
entry_id: LoggedSessionHistoryEntryId(format!(
|
||||
"l-{}",
|
||||
base64::Engine::encode(&base64::engine::general_purpose::URL_SAFE_NO_PAD, identity)
|
||||
@@ -122,8 +513,8 @@ fn canonicalize_history_entry(
|
||||
segment_id: SegmentId,
|
||||
line_index: usize,
|
||||
entry: LegacyHistoryLogEntry,
|
||||
) -> LogEntry {
|
||||
match entry {
|
||||
) -> Result<LogEntry, crate::InputMetadataError> {
|
||||
Ok(match entry {
|
||||
LegacyHistoryLogEntry::SegmentStart {
|
||||
ts,
|
||||
session_id,
|
||||
@@ -177,13 +568,14 @@ fn canonicalize_history_entry(
|
||||
metadata: legacy_metadata(segment_id, line_index, 0),
|
||||
},
|
||||
},
|
||||
LegacyHistoryLogEntry::SystemItem { ts, item } => LogEntry::AnnotatedSystemItem {
|
||||
LegacyHistoryLogEntry::SystemItem {
|
||||
ts,
|
||||
entry: LoggedSystemHistoryEntry {
|
||||
item,
|
||||
metadata: legacy_metadata(segment_id, line_index, 0),
|
||||
},
|
||||
extensions: Vec::new(),
|
||||
item,
|
||||
extensions,
|
||||
} => LogEntry::AnnotatedSystemItem {
|
||||
ts,
|
||||
entry: item.into_entry(legacy_metadata(segment_id, line_index, 0))?,
|
||||
extensions,
|
||||
},
|
||||
}
|
||||
})
|
||||
}
|
||||
|
||||
@@ -0,0 +1,105 @@
|
||||
use super::*;
|
||||
|
||||
mod v5;
|
||||
|
||||
fn seed(
|
||||
origin: LoggedSessionHistoryOrigin,
|
||||
compacted: bool,
|
||||
role: crate::LoggedRole,
|
||||
text: &str,
|
||||
) -> LogEntry {
|
||||
LogEntry::AnnotatedSegmentStart {
|
||||
ts: 1,
|
||||
session_id: SessionId::now_v7(),
|
||||
system_prompt: None,
|
||||
config: Default::default(),
|
||||
forked_from: None,
|
||||
compacted_from: compacted.then(|| SegmentOrigin {
|
||||
segment_id: SegmentId::now_v7(),
|
||||
at_turn_index: 0,
|
||||
}),
|
||||
history: vec![LoggedHistoryEntry {
|
||||
item: LoggedItem::Message {
|
||||
role,
|
||||
content: vec![crate::LoggedContentPart::Text { text: text.into() }],
|
||||
},
|
||||
metadata: LoggedSessionHistoryMetadata {
|
||||
input_metadata: None,
|
||||
entry_id: LoggedSessionHistoryEntryId("summary".into()),
|
||||
origin,
|
||||
derivation: Some(crate::LoggedHistoryDerivation {
|
||||
sources: vec![LoggedSessionHistoryEntryId("source".into())],
|
||||
}),
|
||||
},
|
||||
}],
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn only_trusted_compaction_seed_is_migrated_and_retries_update_inherited_copies() {
|
||||
let text = "[Compacted context summary]\n\nsummary";
|
||||
for (compacted, role, text) in [
|
||||
(false, crate::LoggedRole::System, text),
|
||||
(true, crate::LoggedRole::User, text),
|
||||
(
|
||||
true,
|
||||
crate::LoggedRole::System,
|
||||
"[Session TaskStore snapshot] tasks",
|
||||
),
|
||||
] {
|
||||
let entry = seed(
|
||||
LoggedSessionHistoryOrigin::DerivedSummary,
|
||||
compacted,
|
||||
role,
|
||||
text,
|
||||
);
|
||||
assert!(compaction_summary_ids([&entry].into_iter()).is_empty());
|
||||
}
|
||||
for origin in [
|
||||
LoggedSessionHistoryOrigin::DerivedSummary,
|
||||
LoggedSessionHistoryOrigin::CompactionSummary,
|
||||
] {
|
||||
let creation = seed(origin, true, crate::LoggedRole::System, text);
|
||||
let inherited = seed(
|
||||
LoggedSessionHistoryOrigin::DerivedSummary,
|
||||
false,
|
||||
crate::LoggedRole::System,
|
||||
text,
|
||||
);
|
||||
let LogEntry::AnnotatedSegmentStart { history, .. } = &inherited else {
|
||||
panic!()
|
||||
};
|
||||
let mut pasted = history[0].clone();
|
||||
pasted.metadata.entry_id = LoggedSessionHistoryEntryId("pasted".into());
|
||||
let appended = LogEntry::AnnotatedUserInput {
|
||||
ts: 2,
|
||||
history: vec![pasted.clone()],
|
||||
segments: vec![],
|
||||
extensions: vec![],
|
||||
};
|
||||
let mut entries = vec![creation, inherited, appended];
|
||||
let ids = compaction_summary_ids(entries.iter());
|
||||
migrate_compaction_origins(&mut entries, &ids);
|
||||
for entry in &entries[..2] {
|
||||
let LogEntry::AnnotatedSegmentStart { history, .. } = entry else {
|
||||
panic!()
|
||||
};
|
||||
assert_eq!(
|
||||
history[0].metadata.origin,
|
||||
LoggedSessionHistoryOrigin::CompactionSummary
|
||||
);
|
||||
assert_eq!(history[0].metadata.entry_id.0, "summary");
|
||||
assert_eq!(
|
||||
history[0].metadata.derivation.as_ref().unwrap().sources[0].0,
|
||||
"source"
|
||||
);
|
||||
}
|
||||
let LogEntry::AnnotatedUserInput { history, .. } = &entries[2] else {
|
||||
panic!()
|
||||
};
|
||||
assert_eq!(history, &[pasted]);
|
||||
let once = serde_json::to_vec(&entries).unwrap();
|
||||
migrate_compaction_origins(&mut entries, &ids);
|
||||
assert_eq!(serde_json::to_vec(&entries).unwrap(), once);
|
||||
}
|
||||
}
|
||||
+3
@@ -0,0 +1,3 @@
|
||||
{"kind":"system_item","ts":1,"item":{"kind":"skill_activation","name":"legacy-skill","body":"legacy skill body"}}
|
||||
{"kind":"user_input","ts":2,"segments":[{"kind":"text","content":"legacy user body"}],"extensions":[{"domain":"old","payload":{"kept":true}}]}
|
||||
{"kind":"assistant_item","ts":3,"item":{"kind":"message","role":"assistant","content":[{"kind":"text","text":"legacy reply"}]}}
|
||||
+8
@@ -0,0 +1,8 @@
|
||||
{"kind":"annotated_system_item","ts":101,"entry":{"item":{"kind":"journal_startup","body":"journal body\nunchanged","snapshot":{"entries":[{"text":"private snapshot"}]},"snapshot_sha256":"snapshot-digest","prompt_provenance":{"workspace_id":"workspace","source_digest":"source","projection_digest":"projection","logical_name":"journal_startup"}},"metadata":{"entry_id":"journal-id","origin":{"kind":"legacy_unknown"},"derivation":{"sources":["source-id"]}}},"extensions":[{"domain":"migration-fixture","payload":{"kept":true}}]}
|
||||
{"kind":"annotated_system_item","ts":102,"entry":{"item":{"kind":"resident_summary_refresh","body":"resident body"},"metadata":{"entry_id":"resident-id","origin":{"kind":"derived_summary"}}}}
|
||||
{"kind":"annotated_system_item","ts":103,"entry":{"item":{"kind":"subject_behavior_refresh","body":"rendered subject body","behavior_md":"exact behavior","prompt_provenance":{"source_digest":"subject-source","projection_digest":"subject-projection","logical_name":"subject_behavior"}},"metadata":{"entry_id":"subject-id","origin":{"kind":"backend_instruction","operation_id":"op"}}}}
|
||||
{"kind":"annotated_system_item","ts":104,"entry":{"item":{"kind":"skill_activation","body":"skill body","name":"example-skill"},"metadata":{"entry_id":"skill-id","origin":{"kind":"legacy_unknown"}}}}
|
||||
{"kind":"annotated_system_item","ts":105,"entry":{"item":{"kind":"feature_invocation_result","body":"result body","result":{"invocation_id":"invoke-id","identity":"builtin:test/prepare","status":"outcome_unknown","message":"may have committed","context":null}},"metadata":{"entry_id":"result-id","origin":{"kind":"legacy_unknown"}}}}
|
||||
{"kind":"annotated_user_input","ts":106,"segments":[],"history":[{"item":{"kind":"message","role":"system","content":[{"kind":"text","text":"[Journal] prefix is not Feature evidence"}]},"metadata":{"entry_id":"flat-journal","origin":{"kind":"journal_context"},"derivation":{"sources":["journal-id"]}}},{"item":{"kind":"message","role":"system","content":[{"kind":"text","text":"summary body"}]},"metadata":{"entry_id":"flat-summary","origin":{"kind":"compaction_summary"}}},{"item":{"kind":"message","role":"system","content":[{"kind":"text","text":"[Skill: example] never infer Feature"}]},"metadata":{"entry_id":"flat-other","origin":{"kind":"legacy_unknown"}}}]}
|
||||
{"kind":"annotated_system_item","ts":107,"entry":{"item":{"kind":"notification","message":"raw message","body":"wrapped message"},"metadata":{"entry_id":"core-id","origin":{"kind":"legacy_unknown"}}}}
|
||||
{"kind":"annotated_system_item","ts":108,"entry":{"item":{"kind":"input","body":"already generic body"},"metadata":{"entry_id":"generic-id","origin":{"kind":"provided","producer":"future-owner"},"derivation":{"sources":["source-id"]},"system_input":{"usage":{"recording_material":"include","memory_evidence":"exclude","observation":"readable","compaction":"retain"},"feature_payload":{"schema":"future:unknown","version":99,"value":{"opaque":"retained"}},"public":null}}}}
|
||||
+5
@@ -0,0 +1,5 @@
|
||||
{"kind":"annotated_system_item","ts":201,"entry":{"item":{"kind":"input","body":"frozen v5 reference"},"metadata":{"entry_id":"reference-v5","origin":{"kind":"provided","producer":"owner-v5"},"system_input":{"usage":{"recording_material":"exclude","memory_evidence":"exclude","observation":"hidden","compaction":"reference_input"},"feature_payload":{"schema":"future:owner","version":8,"value":{"system_input":"opaque owner field must not be renamed"}},"public":null}}}}
|
||||
{"kind":"annotated_assistant_item","ts":202,"entry":{"item":{"kind":"tool_call","call_id":"original-call","name":"ArbitraryTool","arguments":"{}"},"metadata":{"entry_id":"original-call-entry","origin":{"kind":"model_output","worker":{"worker_id":"body"}}}}}
|
||||
{"kind":"annotated_tool_result","ts":203,"entry":{"item":{"kind":"tool_result","call_id":"original-call","summary":"original result"},"metadata":{"entry_id":"original-result-entry","origin":{"kind":"tool_output","worker":{"worker_id":"body"}}}}}
|
||||
{"kind":"annotated_assistant_item","ts":204,"entry":{"item":{"kind":"tool_call","call_id":"derived-call","name":"ArbitraryTool","arguments":"{}"},"metadata":{"entry_id":"derived-call-entry","origin":{"kind":"derived_summary"},"derivation":{"sources":["original-call-entry","original-result-entry"]}}}}
|
||||
{"kind":"annotated_tool_result","ts":205,"entry":{"item":{"kind":"tool_result","call_id":"derived-call","summary":"derived retrieval result"},"metadata":{"entry_id":"derived-result-entry","origin":{"kind":"derived_summary"},"derivation":{"sources":["original-call-entry","original-result-entry"]}}}}
|
||||
@@ -0,0 +1,709 @@
|
||||
//! Fixed old wire bytes, not fixtures generated by the current serializer.
|
||||
use super::*;
|
||||
use crate::{FsStore, InputCompactionUse, Store, WorkerSessionStore};
|
||||
use serde_json::{Value, json};
|
||||
use std::{fs, path::Path};
|
||||
|
||||
const V4: &str = include_str!("fixtures/v4-system-inputs.jsonl");
|
||||
const V1: &str = include_str!("fixtures/v1-system-inputs.jsonl");
|
||||
|
||||
fn decode_fixture(version: u32, source: &str, segment: SegmentId) -> Vec<LogEntry> {
|
||||
source
|
||||
.lines()
|
||||
.enumerate()
|
||||
.map(|(index, line)| decode_entry(version, line, SessionId::nil(), segment, index).unwrap())
|
||||
.collect()
|
||||
}
|
||||
|
||||
fn encode(entries: &[LogEntry]) -> Vec<u8> {
|
||||
let mut bytes = Vec::new();
|
||||
for entry in entries {
|
||||
serde_json::to_writer(&mut bytes, entry).unwrap();
|
||||
bytes.push(b'\n');
|
||||
}
|
||||
bytes
|
||||
}
|
||||
|
||||
fn migrate(entries: &mut [LogEntry]) {
|
||||
for entry in entries {
|
||||
migrate_system_inputs(entry).unwrap();
|
||||
entry.validate_input_metadata().unwrap();
|
||||
}
|
||||
}
|
||||
|
||||
fn write_worker(root: &Path, version: u32, source: &[u8]) -> (SessionId, SegmentId) {
|
||||
let session = SessionId::now_v7();
|
||||
let segment = SegmentId::from_u128(1);
|
||||
fs::create_dir_all(root.join("segments")).unwrap();
|
||||
fs::write(
|
||||
root.join("session.json"),
|
||||
serde_json::to_vec(&json!({
|
||||
"schema_version": version, "session_id": session,
|
||||
}))
|
||||
.unwrap(),
|
||||
)
|
||||
.unwrap();
|
||||
fs::write(
|
||||
root.join("segments").join(format!("{segment}.jsonl")),
|
||||
source,
|
||||
)
|
||||
.unwrap();
|
||||
(session, segment)
|
||||
}
|
||||
|
||||
fn assert_marker(root: &Path, version: u32) {
|
||||
let manifest: Value =
|
||||
serde_json::from_slice(&fs::read(root.join("session.json")).unwrap()).unwrap();
|
||||
assert_eq!(manifest["schema_version"], version);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn v4_fixed_wire_preserves_identity_body_payload_public_and_independent_policy() {
|
||||
let mut entries = decode_fixture(4, V4, SegmentId::nil());
|
||||
let before = entries.clone();
|
||||
migrate(&mut entries);
|
||||
let schemas = [
|
||||
"journal:startup",
|
||||
"memory:resident-summary",
|
||||
"subject:behavior",
|
||||
"skill:activation",
|
||||
"feature:invocation-result",
|
||||
];
|
||||
let old_wire: Vec<Value> = V4
|
||||
.lines()
|
||||
.map(|line| serde_json::from_str(line).unwrap())
|
||||
.collect();
|
||||
for index in 0..5 {
|
||||
let LogEntry::AnnotatedSystemItem {
|
||||
ts,
|
||||
entry,
|
||||
extensions,
|
||||
} = &entries[index]
|
||||
else {
|
||||
panic!()
|
||||
};
|
||||
let old = &old_wire[index];
|
||||
let old_item = &old["entry"]["item"];
|
||||
let old_metadata: LoggedSessionHistoryMetadata =
|
||||
serde_json::from_value(old["entry"]["metadata"].clone()).unwrap();
|
||||
let old_ext: Vec<crate::SessionExtension> = old
|
||||
.get("extensions")
|
||||
.map(|value| serde_json::from_value(value.clone()).unwrap())
|
||||
.unwrap_or_default();
|
||||
assert_eq!(*ts, old["ts"].as_u64().unwrap());
|
||||
assert_eq!(extensions, &old_ext);
|
||||
assert!(matches!(entry.item, SystemItem::Input { .. }));
|
||||
assert_eq!(
|
||||
entry.item.history_text(),
|
||||
old_item["body"].as_str().unwrap()
|
||||
);
|
||||
assert_eq!(entry.metadata.entry_id, old_metadata.entry_id);
|
||||
assert_eq!(entry.metadata.origin, old_metadata.origin);
|
||||
assert_eq!(entry.metadata.derivation, old_metadata.derivation);
|
||||
let metadata = entry.metadata.input_metadata.as_ref().unwrap();
|
||||
let public = metadata.public_item().unwrap();
|
||||
assert_eq!(public.kind, old_item["kind"].as_str().unwrap());
|
||||
assert_eq!(public.body, old_item["body"].as_str().unwrap());
|
||||
assert_eq!(
|
||||
public.presentation,
|
||||
crate::PublicSystemPresentation::Context
|
||||
);
|
||||
assert_eq!(
|
||||
metadata.usage(),
|
||||
migration_policy(if index == 0 {
|
||||
InputCompactionUse::ReferenceInput
|
||||
} else {
|
||||
InputCompactionUse::Retain
|
||||
})
|
||||
);
|
||||
let payload = metadata.feature_payload().unwrap();
|
||||
assert_eq!(payload.schema(), schemas[index]);
|
||||
assert_eq!(payload.version(), 1);
|
||||
let value: Value = payload.decode(schemas[index], 1).unwrap();
|
||||
// Independently require each frozen owner's typed v1 payload contract.
|
||||
match index {
|
||||
0 => {
|
||||
let _: JournalStartupPayload = payload.decode(schemas[index], 1).unwrap();
|
||||
}
|
||||
1 => {
|
||||
let _: ResidentSummaryPayload = payload.decode(schemas[index], 1).unwrap();
|
||||
}
|
||||
2 => {
|
||||
let _: SubjectBehaviorPayload = payload.decode(schemas[index], 1).unwrap();
|
||||
}
|
||||
3 => {
|
||||
let _: SkillActivationPayload = payload.decode(schemas[index], 1).unwrap();
|
||||
}
|
||||
4 => {
|
||||
let _: InvocationResultPayload = payload.decode(schemas[index], 1).unwrap();
|
||||
}
|
||||
_ => unreachable!(),
|
||||
}
|
||||
let mut expected = old_item.clone();
|
||||
expected.as_object_mut().unwrap().remove("kind");
|
||||
expected.as_object_mut().unwrap().remove("body");
|
||||
// Optional provenance is an explicit Option in the v1 payload contract.
|
||||
if index == 1 {
|
||||
expected["prompt_provenance"] = Value::Null;
|
||||
}
|
||||
if index == 4 {
|
||||
let result: protocol::FeatureInvocationResult =
|
||||
serde_json::from_value(old_item["result"].clone()).unwrap();
|
||||
let typed: InvocationResultPayload = payload.decode(schemas[index], 1).unwrap();
|
||||
assert_eq!(typed.result, result);
|
||||
// Preserve the protocol's typed serialization contract, including
|
||||
// its canonical representation of optional result context.
|
||||
expected["result"] = serde_json::to_value(result).unwrap();
|
||||
}
|
||||
assert_eq!(value, expected);
|
||||
assert!(value.get("body").is_none());
|
||||
}
|
||||
let LogEntry::AnnotatedUserInput { history, .. } = &entries[5] else {
|
||||
panic!()
|
||||
};
|
||||
let LogEntry::AnnotatedUserInput { history: old, .. } = &before[5] else {
|
||||
panic!()
|
||||
};
|
||||
for (index, compaction) in [
|
||||
InputCompactionUse::ReferenceInput,
|
||||
InputCompactionUse::OpeningSummary,
|
||||
InputCompactionUse::Retain,
|
||||
]
|
||||
.into_iter()
|
||||
.enumerate()
|
||||
{
|
||||
assert_eq!(history[index].item, old[index].item);
|
||||
assert_eq!(
|
||||
history[index].metadata.entry_id,
|
||||
old[index].metadata.entry_id
|
||||
);
|
||||
assert_eq!(history[index].metadata.origin, old[index].metadata.origin);
|
||||
assert_eq!(
|
||||
history[index].metadata.derivation,
|
||||
old[index].metadata.derivation
|
||||
);
|
||||
let metadata = history[index].metadata.input_metadata.as_ref().unwrap();
|
||||
assert_eq!(metadata.usage(), migration_policy(compaction));
|
||||
assert!(metadata.public_item().is_none());
|
||||
assert!(metadata.feature_payload().is_none());
|
||||
}
|
||||
// Core notification is unchanged; existing generic Input and unknown valid
|
||||
// owner payload are retained without decoding/reclassifying a Feature.
|
||||
assert_eq!(encode(&entries[6..]), encode(&before[6..]));
|
||||
let once = encode(&entries);
|
||||
migrate(&mut entries);
|
||||
assert_eq!(encode(&entries), once);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn v1_through_v4_worker_migration_reopen_and_mixed_file_retry() {
|
||||
for version in 1..=4 {
|
||||
let source = if version <= 2 { V1 } else { V4 };
|
||||
let root = tempfile::tempdir().unwrap();
|
||||
let (session, segment) = write_worker(root.path(), version, source.as_bytes());
|
||||
let path = root
|
||||
.path()
|
||||
.join("segments")
|
||||
.join(format!("{segment}.jsonl"));
|
||||
// Simulate an interrupted publication: v5 records precede legacy records
|
||||
// in one file, and a fully new file coexists with an untouched old file.
|
||||
let mut converted = decode_fixture(version, source, segment);
|
||||
migrate(&mut converted);
|
||||
let mut mixed = encode(&converted[..1]);
|
||||
mixed.extend_from_slice(source.split_once('\n').unwrap().1.as_bytes());
|
||||
fs::write(&path, &mixed).unwrap();
|
||||
let new_path = root
|
||||
.path()
|
||||
.join("segments")
|
||||
.join(format!("{}.jsonl", SegmentId::from_u128(2)));
|
||||
let new_bytes = encode(&converted);
|
||||
fs::write(&new_path, &new_bytes).unwrap();
|
||||
let old_path = root
|
||||
.path()
|
||||
.join("segments")
|
||||
.join(format!("{}.jsonl", SegmentId::from_u128(3)));
|
||||
fs::write(&old_path, source).unwrap();
|
||||
|
||||
let marker = fs::read(root.path().join("session.json")).unwrap();
|
||||
WorkerSessionStore::validate_migration(root.path()).unwrap();
|
||||
assert_eq!(fs::read(&path).unwrap(), mixed);
|
||||
assert_eq!(fs::read(&old_path).unwrap(), source.as_bytes());
|
||||
assert_eq!(fs::read(root.path().join("session.json")).unwrap(), marker);
|
||||
let store = WorkerSessionStore::new(root.path()).unwrap();
|
||||
assert_marker(root.path(), 6);
|
||||
let restored = store.read_all(session, segment).unwrap();
|
||||
assert_eq!(encode(&restored), new_bytes);
|
||||
assert_eq!(fs::read(&new_path).unwrap(), new_bytes);
|
||||
let once = fs::read(&path).unwrap();
|
||||
let old_once = fs::read(&old_path).unwrap();
|
||||
drop(store);
|
||||
let reopened = WorkerSessionStore::new(root.path()).unwrap();
|
||||
assert_eq!(encode(&reopened.read_all(session, segment).unwrap()), once);
|
||||
assert_eq!(fs::read(&path).unwrap(), once);
|
||||
assert_eq!(fs::read(&old_path).unwrap(), old_once);
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn all_segments_preflight_keeps_old_bytes_on_decode_or_conversion_failure() {
|
||||
let mut oversized: Value = serde_json::from_str(V4.lines().next().unwrap()).unwrap();
|
||||
oversized["entry"]["item"]["snapshot"] =
|
||||
json!({"large": "x".repeat(crate::input_metadata::MAX_FEATURE_PAYLOAD_BYTES + 1)});
|
||||
let mut unknown: Value = serde_json::from_str(V4.lines().next().unwrap()).unwrap();
|
||||
unknown["entry"]["item"]["kind"] = json!("unsupported_future_feature");
|
||||
let mut malformed = unknown.clone();
|
||||
malformed["entry"]["item"] = json!({"kind":"journal_startup", "body":"missing snapshot"});
|
||||
let mut missing_metadata: Value = serde_json::from_str(V4.lines().last().unwrap()).unwrap();
|
||||
missing_metadata["entry"]["metadata"]
|
||||
.as_object_mut()
|
||||
.unwrap()
|
||||
.remove("system_input");
|
||||
let mut missing_input = missing_metadata.clone();
|
||||
missing_input["entry"]["metadata"]["origin"] = json!({"kind":"legacy_unknown"});
|
||||
let mut invalid_policy: Value = serde_json::from_str(V4.lines().last().unwrap()).unwrap();
|
||||
invalid_policy["entry"]["metadata"]["system_input"]["usage"]["compaction"] = json!("unknown");
|
||||
let mut invalid_payload = invalid_policy.clone();
|
||||
invalid_payload["entry"]["metadata"]["system_input"]["usage"]["compaction"] = json!("retain");
|
||||
invalid_payload["entry"]["metadata"]["system_input"]["feature_payload"]["version"] = json!(0);
|
||||
let mut flat_provided: Value = serde_json::from_str(V4.lines().nth(5).unwrap()).unwrap();
|
||||
flat_provided["history"][0]["metadata"]["origin"] =
|
||||
json!({"kind":"provided", "producer":"owner"});
|
||||
for bad in [
|
||||
"{broken-json}\n".to_owned(),
|
||||
format!("{}\n", oversized),
|
||||
format!("{}\n", unknown),
|
||||
format!("{}\n", malformed),
|
||||
format!("{}\n", missing_metadata),
|
||||
format!("{}\n", invalid_policy),
|
||||
format!("{}\n", invalid_payload),
|
||||
format!("{}\n", flat_provided),
|
||||
format!("{}\n", missing_input),
|
||||
] {
|
||||
let root = tempfile::tempdir().unwrap();
|
||||
let (_, segment) = write_worker(root.path(), 4, V4.as_bytes());
|
||||
let first = root
|
||||
.path()
|
||||
.join("segments")
|
||||
.join(format!("{segment}.jsonl"));
|
||||
let later = root
|
||||
.path()
|
||||
.join("segments")
|
||||
.join(format!("{}.jsonl", SegmentId::from_u128(2)));
|
||||
fs::write(&later, &bad).unwrap();
|
||||
let marker = fs::read(root.path().join("session.json")).unwrap();
|
||||
assert!(WorkerSessionStore::validate_migration(root.path()).is_err());
|
||||
assert!(WorkerSessionStore::new(root.path()).is_err());
|
||||
assert_eq!(fs::read(&first).unwrap(), V4.as_bytes());
|
||||
assert_eq!(fs::read(&later).unwrap(), bad.as_bytes());
|
||||
assert_eq!(fs::read(root.path().join("session.json")).unwrap(), marker);
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn unsupported_schema_preserves_all_old_bytes() {
|
||||
for version in [0, 7, 99] {
|
||||
let root = tempfile::tempdir().unwrap();
|
||||
let (_, segment) = write_worker(root.path(), version, V4.as_bytes());
|
||||
let path = root
|
||||
.path()
|
||||
.join("segments")
|
||||
.join(format!("{segment}.jsonl"));
|
||||
let marker = fs::read(root.path().join("session.json")).unwrap();
|
||||
assert!(WorkerSessionStore::new(root.path()).is_err());
|
||||
assert_eq!(fs::read(&path).unwrap(), V4.as_bytes());
|
||||
assert_eq!(fs::read(root.path().join("session.json")).unwrap(), marker);
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn standalone_store_uses_same_v1_through_v4_migration_and_reopens() {
|
||||
// None represents the existing unmarked annotated standalone layout (v3).
|
||||
for version in [None, Some(1), Some(2), Some(3), Some(4)] {
|
||||
let root = tempfile::tempdir().unwrap();
|
||||
let session = SessionId::now_v7();
|
||||
let segment = SegmentId::from_u128(1);
|
||||
let dir = root.path().join(session.to_string());
|
||||
fs::create_dir_all(&dir).unwrap();
|
||||
let source = if version.is_some_and(|v| v <= 2) {
|
||||
V1
|
||||
} else {
|
||||
V4
|
||||
};
|
||||
let path = dir.join(format!("{segment}.jsonl"));
|
||||
fs::write(&path, source).unwrap();
|
||||
if let Some(version) = version {
|
||||
fs::write(dir.join("session-schema.json"), version.to_string()).unwrap();
|
||||
}
|
||||
let store = FsStore::new(root.path()).unwrap();
|
||||
let entries = store.read_all(session, segment).unwrap();
|
||||
for entry in entries {
|
||||
entry.validate_input_metadata().unwrap();
|
||||
}
|
||||
assert_eq!(
|
||||
fs::read_to_string(dir.join("session-schema.json"))
|
||||
.unwrap()
|
||||
.trim(),
|
||||
"6"
|
||||
);
|
||||
let once = fs::read(&path).unwrap();
|
||||
drop(store);
|
||||
FsStore::new(root.path()).unwrap();
|
||||
assert_eq!(fs::read(&path).unwrap(), once);
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn compaction_origin_upgrade_is_retained_only_for_pre_v4_sources() {
|
||||
for version in [3, 4] {
|
||||
let root = tempfile::tempdir().unwrap();
|
||||
let creation = seed(
|
||||
LoggedSessionHistoryOrigin::DerivedSummary,
|
||||
true,
|
||||
crate::LoggedRole::System,
|
||||
"[Compacted context summary]\n\nold summary",
|
||||
);
|
||||
let inherited = seed(
|
||||
LoggedSessionHistoryOrigin::DerivedSummary,
|
||||
false,
|
||||
crate::LoggedRole::System,
|
||||
"[Compacted context summary]\n\nold summary",
|
||||
);
|
||||
let (session, segment) =
|
||||
write_worker(root.path(), version, &encode(&[creation, inherited]));
|
||||
let store = WorkerSessionStore::new(root.path()).unwrap();
|
||||
for record in store.read_all(session, segment).unwrap() {
|
||||
let LogEntry::AnnotatedSegmentStart { history, .. } = record else {
|
||||
panic!()
|
||||
};
|
||||
let metadata = &history[0].metadata;
|
||||
assert_eq!(metadata.entry_id.0, "summary");
|
||||
assert_eq!(metadata.derivation.as_ref().unwrap().sources[0].0, "source");
|
||||
assert_eq!(
|
||||
metadata.origin,
|
||||
if version == 3 {
|
||||
LoggedSessionHistoryOrigin::CompactionSummary
|
||||
} else {
|
||||
LoggedSessionHistoryOrigin::DerivedSummary
|
||||
}
|
||||
);
|
||||
assert_eq!(
|
||||
metadata.input_metadata.as_ref().unwrap().usage().compaction,
|
||||
if version == 3 {
|
||||
InputCompactionUse::OpeningSummary
|
||||
} else {
|
||||
InputCompactionUse::Retain
|
||||
}
|
||||
);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn standalone_preflight_and_unsupported_marker_leave_sources_unchanged() {
|
||||
for version in [4, 99] {
|
||||
let root = tempfile::tempdir().unwrap();
|
||||
let session = SessionId::now_v7();
|
||||
let dir = root.path().join(session.to_string());
|
||||
fs::create_dir_all(&dir).unwrap();
|
||||
let first = dir.join(format!("{}.jsonl", SegmentId::from_u128(1)));
|
||||
let later = dir.join(format!("{}.jsonl", SegmentId::from_u128(2)));
|
||||
fs::write(&first, V4).unwrap();
|
||||
fs::write(&later, "{broken-json}\n").unwrap();
|
||||
let marker = version.to_string();
|
||||
fs::write(dir.join("session-schema.json"), &marker).unwrap();
|
||||
assert!(FsStore::new(root.path()).is_err());
|
||||
assert_eq!(fs::read(&first).unwrap(), V4.as_bytes());
|
||||
assert_eq!(fs::read_to_string(&later).unwrap(), "{broken-json}\n");
|
||||
assert_eq!(
|
||||
fs::read_to_string(dir.join("session-schema.json")).unwrap(),
|
||||
marker
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn current_v5_rejects_all_legacy_feature_kinds_without_rewriting_sources() {
|
||||
for line in V4.lines().take(5) {
|
||||
// Current serde, writable open and read-only restore share the same
|
||||
// current wire contract. None may dispatch to the old Feature decoder.
|
||||
assert!(serde_json::from_str::<LogEntry>(line).is_err());
|
||||
let bytes = format!("{line}\n");
|
||||
let root = tempfile::tempdir().unwrap();
|
||||
let (session, segment) = write_worker(root.path(), 6, bytes.as_bytes());
|
||||
let path = root
|
||||
.path()
|
||||
.join("segments")
|
||||
.join(format!("{segment}.jsonl"));
|
||||
let marker = fs::read(root.path().join("session.json")).unwrap();
|
||||
let readonly = WorkerSessionStore::open_read_only(root.path()).unwrap();
|
||||
assert!(readonly.read_all_read_only(session, segment).is_err());
|
||||
assert!(WorkerSessionStore::new(root.path()).is_err());
|
||||
assert_eq!(fs::read(&path).unwrap(), bytes.as_bytes());
|
||||
assert_eq!(fs::read(root.path().join("session.json")).unwrap(), marker);
|
||||
|
||||
let standalone = tempfile::tempdir().unwrap();
|
||||
let dir = standalone.path().join(session.to_string());
|
||||
fs::create_dir_all(&dir).unwrap();
|
||||
let path = dir.join(format!("{segment}.jsonl"));
|
||||
fs::write(&path, &bytes).unwrap();
|
||||
fs::write(dir.join("session-schema.json"), "5").unwrap();
|
||||
assert!(FsStore::new(standalone.path()).is_err());
|
||||
assert_eq!(fs::read(&path).unwrap(), bytes.as_bytes());
|
||||
assert_eq!(
|
||||
fs::read_to_string(dir.join("session-schema.json")).unwrap(),
|
||||
"5"
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn v1_v2_feature_wire_uses_the_same_typed_payloads_and_stable_legacy_identity() {
|
||||
let segment = SegmentId::from_u128(42);
|
||||
for version in [1, 2] {
|
||||
for (index, line) in V4.lines().take(5).enumerate() {
|
||||
let annotated: Value = serde_json::from_str(line).unwrap();
|
||||
let wire = json!({
|
||||
"kind": "system_item", "ts": annotated["ts"],
|
||||
"item": annotated["entry"]["item"],
|
||||
"extensions": [{"domain":"old-owner", "payload":{"kept":true}}],
|
||||
})
|
||||
.to_string();
|
||||
let entry = decode_entry(version, &wire, SessionId::nil(), segment, index).unwrap();
|
||||
let retry = decode_entry(version, &wire, SessionId::nil(), segment, index).unwrap();
|
||||
assert_eq!(encode(&[entry.clone()]), encode(&[retry]));
|
||||
let LogEntry::AnnotatedSystemItem {
|
||||
ts,
|
||||
entry,
|
||||
extensions,
|
||||
} = entry
|
||||
else {
|
||||
panic!()
|
||||
};
|
||||
assert_eq!(ts, annotated["ts"].as_u64().unwrap());
|
||||
assert!(matches!(entry.item, SystemItem::Input { .. }));
|
||||
assert_eq!(
|
||||
entry.item.history_text(),
|
||||
annotated["entry"]["item"]["body"].as_str().unwrap()
|
||||
);
|
||||
assert_eq!(
|
||||
entry.metadata.entry_id,
|
||||
legacy_metadata(segment, index, 0).entry_id
|
||||
);
|
||||
assert_eq!(
|
||||
entry.metadata.origin,
|
||||
LoggedSessionHistoryOrigin::LegacyUnknown
|
||||
);
|
||||
assert!(entry.metadata.derivation.is_none());
|
||||
assert_eq!(extensions[0].domain, "old-owner");
|
||||
assert_eq!(extensions[0].payload, json!({"kept":true}));
|
||||
let LogEntry::AnnotatedSystemItem { entry: v4, .. } =
|
||||
decode_entry(4, line, SessionId::nil(), segment, index).unwrap()
|
||||
else {
|
||||
panic!()
|
||||
};
|
||||
assert_eq!(entry.metadata.input_metadata, v4.metadata.input_metadata);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn migration_rejects_malformed_typed_feature_fields_instead_of_retaining_unchecked_json() {
|
||||
let mut items: Vec<Value> = V4
|
||||
.lines()
|
||||
.take(5)
|
||||
.map(|line| serde_json::from_str::<Value>(line).unwrap()["entry"]["item"].clone())
|
||||
.collect();
|
||||
items[0]["snapshot_sha256"] = json!(17);
|
||||
items[1]["prompt_provenance"] = json!({"logical_name":"missing digests"});
|
||||
items[2]["behavior_md"] = json!(["not a string"]);
|
||||
items[3]["name"] = json!({"not":"a name"});
|
||||
items[4]["result"]["status"] = json!("unsupported_status");
|
||||
for version in 1..=4 {
|
||||
for item in &items {
|
||||
let wire = if version <= 2 {
|
||||
json!({"kind":"system_item", "ts":1, "item":item})
|
||||
} else {
|
||||
json!({"kind":"annotated_system_item", "ts":1, "entry":{
|
||||
"item":item, "metadata":{
|
||||
"entry_id":"malformed-id", "origin":{"kind":"legacy_unknown"},
|
||||
},
|
||||
}})
|
||||
}
|
||||
.to_string();
|
||||
assert!(decode_entry(version, &wire, SessionId::nil(), SegmentId::nil(), 0).is_err());
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn frozen_behavior_counter_is_accepted_only_at_the_old_schema_boundary() {
|
||||
for version in 1..=4 {
|
||||
let item = json!({
|
||||
"kind":"subject_behavior_refresh", "body":"exact archived body",
|
||||
"behavior_revision":7,
|
||||
});
|
||||
let wire = if version <= 2 {
|
||||
json!({"kind":"system_item", "ts":1, "item":item})
|
||||
} else {
|
||||
json!({"kind":"annotated_system_item", "ts":1, "entry":{
|
||||
"item":item, "metadata":{
|
||||
"entry_id":"behavior-id", "origin":{"kind":"legacy_unknown"},
|
||||
},
|
||||
}})
|
||||
}
|
||||
.to_string();
|
||||
assert!(serde_json::from_str::<LogEntry>(&wire).is_err());
|
||||
let LogEntry::AnnotatedSystemItem { entry, .. } =
|
||||
decode_entry(version, &wire, SessionId::nil(), SegmentId::nil(), 0).unwrap()
|
||||
else {
|
||||
panic!()
|
||||
};
|
||||
assert_eq!(entry.item.history_text(), "exact archived body");
|
||||
let payload = entry
|
||||
.metadata
|
||||
.input_metadata
|
||||
.as_ref()
|
||||
.unwrap()
|
||||
.feature_payload()
|
||||
.unwrap();
|
||||
let typed: SubjectBehaviorPayload = payload.decode("subject:behavior", 1).unwrap();
|
||||
assert_eq!(typed.behavior_md, "");
|
||||
assert!(typed.prompt_provenance.is_none());
|
||||
assert_eq!(
|
||||
serde_json::to_value(typed).unwrap(),
|
||||
json!({
|
||||
"behavior_md":"", "prompt_provenance":null,
|
||||
})
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn current_schema_rejects_generic_input_without_metadata_instead_of_migrating_it() {
|
||||
let mut missing: Value = serde_json::from_str(V4.lines().last().unwrap()).unwrap();
|
||||
missing["entry"]["metadata"]
|
||||
.as_object_mut()
|
||||
.unwrap()
|
||||
.remove("system_input");
|
||||
let bytes = format!("{}\n", missing);
|
||||
let root = tempfile::tempdir().unwrap();
|
||||
let (_, segment) = write_worker(root.path(), 6, bytes.as_bytes());
|
||||
assert!(WorkerSessionStore::new(root.path()).is_err());
|
||||
assert_eq!(
|
||||
fs::read(
|
||||
root.path()
|
||||
.join("segments")
|
||||
.join(format!("{segment}.jsonl"))
|
||||
)
|
||||
.unwrap(),
|
||||
bytes.as_bytes()
|
||||
);
|
||||
assert_marker(root.path(), 6);
|
||||
}
|
||||
|
||||
const V5: &str = include_str!("fixtures/v5-role-metadata.jsonl");
|
||||
|
||||
#[test]
|
||||
fn v5_metadata_and_derived_tool_context_upgrade_without_changing_roles_or_original_evidence() {
|
||||
for standalone in [false, true] {
|
||||
let root = tempfile::tempdir().unwrap();
|
||||
let (session, segment) = if standalone {
|
||||
let session = SessionId::now_v7();
|
||||
let segment = SegmentId::now_v7();
|
||||
let dir = root.path().join(session.to_string());
|
||||
fs::create_dir_all(&dir).unwrap();
|
||||
fs::write(dir.join("session-schema.json"), b"5").unwrap();
|
||||
fs::write(dir.join(format!("{segment}.jsonl")), V5).unwrap();
|
||||
(session, segment)
|
||||
} else {
|
||||
write_worker(root.path(), 5, V5.as_bytes())
|
||||
};
|
||||
let entries = if standalone {
|
||||
FsStore::new(root.path())
|
||||
.unwrap()
|
||||
.read_all(session, segment)
|
||||
.unwrap()
|
||||
} else {
|
||||
WorkerSessionStore::new(root.path())
|
||||
.unwrap()
|
||||
.read_all(session, segment)
|
||||
.unwrap()
|
||||
};
|
||||
let originals: Vec<Value> = V5
|
||||
.lines()
|
||||
.map(|line| serde_json::from_str(line).unwrap())
|
||||
.collect();
|
||||
assert_eq!(entries.len(), originals.len());
|
||||
for (index, (entry, old)) in entries.iter().zip(originals).enumerate() {
|
||||
let wire = serde_json::to_value(entry).unwrap();
|
||||
assert_eq!(wire["ts"], old["ts"]);
|
||||
assert_eq!(wire["entry"]["item"], old["entry"]["item"]);
|
||||
for field in ["entry_id", "origin", "derivation"] {
|
||||
assert_eq!(
|
||||
wire["entry"]["metadata"][field],
|
||||
old["entry"]["metadata"][field]
|
||||
);
|
||||
}
|
||||
let metadata = &wire["entry"]["metadata"];
|
||||
if index == 0 {
|
||||
assert_eq!(
|
||||
metadata["input_metadata"],
|
||||
old["entry"]["metadata"]["system_input"]
|
||||
);
|
||||
assert_eq!(
|
||||
metadata["input_metadata"]["feature_payload"]["value"]["system_input"],
|
||||
"opaque owner field must not be renamed"
|
||||
);
|
||||
} else if index < 3 {
|
||||
assert!(
|
||||
metadata.get("input_metadata").is_none(),
|
||||
"ordinary model Tool originals must not acquire exclusion policy"
|
||||
);
|
||||
} else {
|
||||
assert_eq!(
|
||||
metadata["input_metadata"]["usage"],
|
||||
json!({
|
||||
"recording_material":"exclude", "memory_evidence":"exclude", "observation":"hidden", "compaction":"retain"
|
||||
})
|
||||
);
|
||||
}
|
||||
}
|
||||
let before = encode(&entries);
|
||||
let reopened = if standalone {
|
||||
FsStore::new(root.path())
|
||||
.unwrap()
|
||||
.read_all(session, segment)
|
||||
.unwrap()
|
||||
} else {
|
||||
WorkerSessionStore::new(root.path())
|
||||
.unwrap()
|
||||
.read_all(session, segment)
|
||||
.unwrap()
|
||||
};
|
||||
assert_eq!(encode(&reopened), before);
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn legacy_metadata_alias_conflict_fails_preflight_without_dropping_either_value() {
|
||||
let mut bad: Value = serde_json::from_str(V5.lines().next().unwrap()).unwrap();
|
||||
bad["entry"]["metadata"]["input_metadata"] = bad["entry"]["metadata"]["system_input"].clone();
|
||||
for version in [4, 5] {
|
||||
let root = tempfile::tempdir().unwrap();
|
||||
let (_, segment) = write_worker(root.path(), version, V5.as_bytes());
|
||||
let path = root
|
||||
.path()
|
||||
.join("segments")
|
||||
.join(format!("{segment}.jsonl"));
|
||||
let later = root
|
||||
.path()
|
||||
.join("segments")
|
||||
.join(format!("{}.jsonl", SegmentId::from_u128(2)));
|
||||
let bad_bytes = format!("{bad}\n");
|
||||
fs::write(&later, &bad_bytes).unwrap();
|
||||
assert!(WorkerSessionStore::new(root.path()).is_err());
|
||||
assert_eq!(fs::read(path).unwrap(), V5.as_bytes());
|
||||
assert_eq!(fs::read(later).unwrap(), bad_bytes.as_bytes());
|
||||
assert_marker(root.path(), version);
|
||||
}
|
||||
}
|
||||
@@ -41,11 +41,14 @@ pub(crate) fn read_without_atime_bounded(path: &Path, max_bytes: u64) -> io::Res
|
||||
pub mod event_trace;
|
||||
pub mod fs_store;
|
||||
pub mod history;
|
||||
pub mod input_metadata;
|
||||
mod legacy_session_log;
|
||||
pub mod logged_item;
|
||||
mod paste_artifact;
|
||||
pub mod public_index;
|
||||
pub mod public_material;
|
||||
pub mod public_snapshot;
|
||||
pub mod retention;
|
||||
pub mod segment;
|
||||
pub mod segment_log;
|
||||
pub mod store;
|
||||
@@ -63,6 +66,10 @@ pub use history::{
|
||||
LoggedSessionHistoryMetadata, LoggedSessionHistoryOrigin, LoggedSystemHistoryEntry,
|
||||
LoggedWorkerSubject,
|
||||
};
|
||||
pub use input_metadata::{
|
||||
FeatureInputPayload, HistoryInputMetadata, HistoryInputUsePolicy, InputCompactionUse,
|
||||
InputEvidenceUse, InputMetadataError, InputObservationUse, SystemInputEnvelope,
|
||||
};
|
||||
pub use logged_item::{LoggedContentPart, LoggedItem, LoggedRole, from_logged, to_logged};
|
||||
pub use paste_artifact::PasteArtifactLimits;
|
||||
pub use public_index::{
|
||||
@@ -96,7 +103,8 @@ pub use segment::{
|
||||
pub use segment_log::{LogEntry, RestoredState, SegmentOrigin, SessionExtension, collect_state};
|
||||
pub use store::{Store, StoreError};
|
||||
pub use system_item::{
|
||||
PromptRenderProvenance, SystemItem, SystemReminder, SystemReminderSource, render_worker_event,
|
||||
PromptRenderProvenance, PublicSystemItem, PublicSystemPresentation, SystemItem, SystemReminder,
|
||||
SystemReminderSource, render_worker_event,
|
||||
};
|
||||
pub use uploaded_file::{
|
||||
DEFAULT_MAX_FILES_PER_SUBMISSION, DEFAULT_MAX_SESSION_ARTIFACT_BYTES,
|
||||
|
||||
@@ -1296,6 +1296,7 @@ mod tests {
|
||||
LoggedHistoryEntry {
|
||||
item,
|
||||
metadata: LoggedSessionHistoryMetadata {
|
||||
input_metadata: None,
|
||||
entry_id: LoggedSessionHistoryEntryId(id.to_owned()),
|
||||
origin,
|
||||
derivation: None,
|
||||
@@ -1537,6 +1538,7 @@ mod tests {
|
||||
prompt_provenance: None,
|
||||
},
|
||||
metadata: LoggedSessionHistoryMetadata {
|
||||
input_metadata: None,
|
||||
entry_id: LoggedSessionHistoryEntryId("system-item".into()),
|
||||
origin: LoggedSessionHistoryOrigin::BackendInstruction {
|
||||
operation_id: None,
|
||||
@@ -1602,6 +1604,7 @@ mod tests {
|
||||
segment_id(20),
|
||||
"completed",
|
||||
LogEntry::RunCompleted {
|
||||
entry_id: None,
|
||||
ts: 4,
|
||||
interrupted: false,
|
||||
result: EngineResult::Finished,
|
||||
@@ -1640,7 +1643,10 @@ mod tests {
|
||||
(
|
||||
segment_id(24),
|
||||
"abandoned",
|
||||
LogEntry::PausedTurnAbandoned { ts: 4 },
|
||||
LogEntry::PausedTurnAbandoned {
|
||||
entry_id: None,
|
||||
ts: 4,
|
||||
},
|
||||
),
|
||||
];
|
||||
for (segment_id, text, outcome) in outcomes {
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@@ -27,7 +27,7 @@ use thiserror::Error;
|
||||
|
||||
use crate::{
|
||||
LogEntry, LoggedContentPart, LoggedHistoryEntry, LoggedItem, LoggedRole,
|
||||
LoggedSessionHistoryOrigin, SegmentId, SegmentOrigin, SessionId, StoreError, SystemItem,
|
||||
LoggedSessionHistoryOrigin, SegmentId, SegmentOrigin, SessionId, StoreError,
|
||||
WorkerAggregateStore, WorkerSessionStore, WorkerStoreError,
|
||||
};
|
||||
|
||||
@@ -1165,7 +1165,7 @@ fn capture_tool_correction(
|
||||
let LogEntry::ToolResultCorrected { entry, .. } = record else {
|
||||
return false;
|
||||
};
|
||||
if let Some(data) = project_item(&entry.metadata.entry_id.0, &entry.item) {
|
||||
if let Some(data) = project_history_item(entry) {
|
||||
// We read backwards: the first correction seen is the latest one.
|
||||
corrections
|
||||
.entry(entry.metadata.entry_id.0.clone())
|
||||
@@ -1600,12 +1600,12 @@ pub(crate) fn project_session_snapshot_for_segment(
|
||||
} => extend_history(&mut entries, history, Some(segments), *ts),
|
||||
LogEntry::AnnotatedAssistantItem { ts, entry }
|
||||
| LogEntry::AnnotatedToolResult { ts, entry } => {
|
||||
if let Some(data) = project_item(&entry.metadata.entry_id.0, &entry.item) {
|
||||
if let Some(data) = project_history_item(entry) {
|
||||
entries.push(history_entry(entry, *ts, data));
|
||||
}
|
||||
}
|
||||
LogEntry::ToolResultCorrected { ts, entry } => {
|
||||
if let Some(data) = project_item(&entry.metadata.entry_id.0, &entry.item) {
|
||||
if let Some(data) = project_history_item(entry) {
|
||||
if let Some(existing) = entries
|
||||
.iter_mut()
|
||||
.find(|existing| existing.entry_id == entry.metadata.entry_id.0)
|
||||
@@ -1618,11 +1618,16 @@ pub(crate) fn project_session_snapshot_for_segment(
|
||||
}
|
||||
}
|
||||
LogEntry::AnnotatedSystemItem { ts, entry, .. } => entries.push(system_entry(
|
||||
&entry.item,
|
||||
&entry.public_item(),
|
||||
entry.metadata.entry_id.0.clone(),
|
||||
*ts,
|
||||
provenance(&entry.metadata.origin),
|
||||
derivation_ids(entry),
|
||||
entry
|
||||
.metadata
|
||||
.input_metadata
|
||||
.as_ref()
|
||||
.map(crate::HistoryInputMetadata::public_system_use_policy),
|
||||
)),
|
||||
LogEntry::RunYielded {
|
||||
ts,
|
||||
@@ -1705,6 +1710,7 @@ pub(crate) fn project_session_snapshot_for_segment(
|
||||
interrupted,
|
||||
result,
|
||||
active_run_turn_count: persisted_count,
|
||||
..
|
||||
} => {
|
||||
if *interrupted && matches!(result, agen::EngineResult::Yielded) {
|
||||
let count = (*persisted_count)
|
||||
@@ -1774,7 +1780,7 @@ fn extend_history(
|
||||
segments: input_segments.cloned().unwrap_or_default(),
|
||||
}
|
||||
} else {
|
||||
let Some(data) = project_item(&entry.metadata.entry_id.0, &entry.item) else {
|
||||
let Some(data) = project_history_item(entry) else {
|
||||
continue;
|
||||
};
|
||||
data
|
||||
@@ -1789,6 +1795,19 @@ fn history_entry(
|
||||
data: SessionSnapshotEntryData,
|
||||
) -> SessionSnapshotEntry {
|
||||
SessionSnapshotEntry {
|
||||
use_policy: entry.metadata.input_metadata.as_ref().map(|input| {
|
||||
if matches!(
|
||||
entry.item,
|
||||
LoggedItem::Message {
|
||||
role: LoggedRole::System,
|
||||
..
|
||||
}
|
||||
) {
|
||||
input.public_system_use_policy()
|
||||
} else {
|
||||
input.public_use_policy()
|
||||
}
|
||||
}),
|
||||
entry_id: entry.metadata.entry_id.0.clone(),
|
||||
timestamp,
|
||||
provenance: provenance(&entry.metadata.origin),
|
||||
@@ -1832,6 +1851,7 @@ fn run_transition_entry(
|
||||
data: SessionSnapshotEntryData,
|
||||
) -> SessionSnapshotEntry {
|
||||
SessionSnapshotEntry {
|
||||
use_policy: None,
|
||||
entry_id: persisted_entry_id
|
||||
.map(|entry_id| entry_id.0.clone())
|
||||
.unwrap_or_else(|| legacy_entry_id(session_key, segment_id, log_index, 0)),
|
||||
@@ -1851,6 +1871,7 @@ fn legacy_entry(
|
||||
data: SessionSnapshotEntryData,
|
||||
) -> SessionSnapshotEntry {
|
||||
SessionSnapshotEntry {
|
||||
use_policy: None,
|
||||
entry_id: legacy_entry_id(session_key, segment_id, log_index, item_index),
|
||||
timestamp,
|
||||
provenance: SessionEntryProvenance::LegacyUnknown,
|
||||
@@ -1883,12 +1904,12 @@ fn provenance(origin: &LoggedSessionHistoryOrigin) -> SessionEntryProvenance {
|
||||
LoggedSessionHistoryOrigin::FlowInstruction { .. } => {
|
||||
SessionEntryProvenance::FlowInstruction
|
||||
}
|
||||
LoggedSessionHistoryOrigin::BackendInstruction { .. } => {
|
||||
SessionEntryProvenance::BackendInstruction
|
||||
}
|
||||
LoggedSessionHistoryOrigin::BackendInstruction { .. }
|
||||
| LoggedSessionHistoryOrigin::Provided { .. } => SessionEntryProvenance::BackendInstruction,
|
||||
LoggedSessionHistoryOrigin::ModelOutput { .. } => SessionEntryProvenance::ModelOutput,
|
||||
LoggedSessionHistoryOrigin::ToolOutput { .. } => SessionEntryProvenance::ToolOutput,
|
||||
LoggedSessionHistoryOrigin::CompactionSummary
|
||||
| LoggedSessionHistoryOrigin::JournalContext
|
||||
| LoggedSessionHistoryOrigin::DerivedSummary => SessionEntryProvenance::DerivedSummary,
|
||||
LoggedSessionHistoryOrigin::LegacyUnknown => SessionEntryProvenance::LegacyUnknown,
|
||||
}
|
||||
@@ -1912,6 +1933,35 @@ pub fn session_tool_attachment_id(
|
||||
URL_SAFE_NO_PAD.encode(hash.finalize())
|
||||
}
|
||||
|
||||
fn project_history_item(entry: &LoggedHistoryEntry) -> Option<SessionSnapshotEntryData> {
|
||||
if let Some(input) = &entry.metadata.input_metadata {
|
||||
if matches!(
|
||||
entry.item,
|
||||
LoggedItem::Message {
|
||||
role: LoggedRole::System,
|
||||
..
|
||||
}
|
||||
) {
|
||||
let public = input.public_projection();
|
||||
return Some(SessionSnapshotEntryData::SystemItem {
|
||||
item_kind: public.kind.clone(),
|
||||
content: public.body.clone(),
|
||||
data: Some(
|
||||
serde_json::to_value(public).expect("public system input is serializable"),
|
||||
),
|
||||
});
|
||||
}
|
||||
let usage = input.usage();
|
||||
if usage.recording_material == crate::InputEvidenceUse::Exclude
|
||||
&& usage.memory_evidence == crate::InputEvidenceUse::Exclude
|
||||
&& usage.observation == crate::InputObservationUse::Hidden
|
||||
{
|
||||
return None;
|
||||
}
|
||||
}
|
||||
project_item(&entry.metadata.entry_id.0, &entry.item)
|
||||
}
|
||||
|
||||
fn project_item(entry_id: &str, item: &LoggedItem) -> Option<SessionSnapshotEntryData> {
|
||||
match item {
|
||||
LoggedItem::Message { role, content } => {
|
||||
@@ -1984,30 +2034,26 @@ fn project_item(entry_id: &str, item: &LoggedItem) -> Option<SessionSnapshotEntr
|
||||
}
|
||||
|
||||
fn system_entry(
|
||||
item: &SystemItem,
|
||||
item: &crate::PublicSystemItem,
|
||||
entry_id: String,
|
||||
timestamp: u64,
|
||||
provenance: SessionEntryProvenance,
|
||||
derived_from: Vec<String>,
|
||||
use_policy: Option<protocol::SessionEntryUsePolicy>,
|
||||
) -> SessionSnapshotEntry {
|
||||
let mut data = serde_json::to_value(item).ok();
|
||||
if let Some(serde_json::Value::Object(object)) = data.as_mut() {
|
||||
object.remove("prompt_provenance");
|
||||
}
|
||||
let item_kind = data
|
||||
.as_ref()
|
||||
.and_then(|value| value.get("kind"))
|
||||
.and_then(serde_json::Value::as_str)
|
||||
.unwrap_or("system_item")
|
||||
.to_owned();
|
||||
let public = item.clone();
|
||||
let data = Some(serde_json::to_value(&public).expect("public system input is serializable"));
|
||||
let item_kind = public.kind;
|
||||
let content = public.body;
|
||||
SessionSnapshotEntry {
|
||||
use_policy,
|
||||
entry_id,
|
||||
timestamp,
|
||||
provenance,
|
||||
derived_from,
|
||||
data: SessionSnapshotEntryData::SystemItem {
|
||||
item_kind,
|
||||
content: item.history_text(),
|
||||
content,
|
||||
data,
|
||||
},
|
||||
}
|
||||
@@ -2037,6 +2083,7 @@ mod tests {
|
||||
|
||||
fn complete(ts: u64) -> LogEntry {
|
||||
LogEntry::RunCompleted {
|
||||
entry_id: None,
|
||||
ts,
|
||||
interrupted: false,
|
||||
result: agen::EngineResult::Finished,
|
||||
@@ -2288,6 +2335,7 @@ mod tests {
|
||||
content: vec![LoggedContentPart::Text { text: text.into() }],
|
||||
},
|
||||
metadata: LoggedSessionHistoryMetadata {
|
||||
input_metadata: None,
|
||||
entry_id: LoggedSessionHistoryEntryId(entry_id.into()),
|
||||
origin,
|
||||
derivation: None,
|
||||
@@ -3586,6 +3634,7 @@ mod tests {
|
||||
.map(|item| LoggedHistoryEntry {
|
||||
item,
|
||||
metadata: LoggedSessionHistoryMetadata {
|
||||
input_metadata: None,
|
||||
entry_id: LoggedSessionHistoryEntryId::new(),
|
||||
origin: LoggedSessionHistoryOrigin::LegacyUnknown,
|
||||
derivation: None,
|
||||
@@ -3640,6 +3689,7 @@ mod tests {
|
||||
}],
|
||||
},
|
||||
metadata: LoggedSessionHistoryMetadata {
|
||||
input_metadata: None,
|
||||
entry_id: user_entry_id,
|
||||
origin: LoggedSessionHistoryOrigin::HumanInput {
|
||||
account_id: "account-1".into(),
|
||||
@@ -3709,6 +3759,7 @@ mod tests {
|
||||
}],
|
||||
},
|
||||
metadata: LoggedSessionHistoryMetadata {
|
||||
input_metadata: None,
|
||||
entry_id: LoggedSessionHistoryEntryId::new(),
|
||||
origin: LoggedSessionHistoryOrigin::FlowInstruction {
|
||||
selector: "builtin:coder-review".into(),
|
||||
@@ -3728,6 +3779,7 @@ mod tests {
|
||||
}],
|
||||
},
|
||||
metadata: LoggedSessionHistoryMetadata {
|
||||
input_metadata: None,
|
||||
entry_id: user_entry_id.clone(),
|
||||
origin: origin.clone(),
|
||||
derivation: Some(LoggedHistoryDerivation {
|
||||
@@ -3758,6 +3810,7 @@ mod tests {
|
||||
fn annotated_projection_preserves_identity_and_provenance() {
|
||||
let session_id = crate::new_session_id();
|
||||
let metadata = LoggedSessionHistoryMetadata {
|
||||
input_metadata: None,
|
||||
entry_id: LoggedSessionHistoryEntryId::new(),
|
||||
origin: LoggedSessionHistoryOrigin::ModelOutput {
|
||||
worker: LoggedWorkerSubject {
|
||||
@@ -4320,6 +4373,7 @@ mod tests {
|
||||
is_error: false,
|
||||
},
|
||||
metadata: LoggedSessionHistoryMetadata {
|
||||
input_metadata: None,
|
||||
entry_id: LoggedSessionHistoryEntryId("ancestor-image".into()),
|
||||
origin: LoggedSessionHistoryOrigin::LegacyUnknown,
|
||||
derivation: None,
|
||||
@@ -4414,6 +4468,7 @@ mod tests {
|
||||
is_error: false,
|
||||
},
|
||||
metadata: LoggedSessionHistoryMetadata {
|
||||
input_metadata: None,
|
||||
entry_id: LoggedSessionHistoryEntryId("tool-images".into()),
|
||||
origin: LoggedSessionHistoryOrigin::LegacyUnknown,
|
||||
derivation: None,
|
||||
|
||||
@@ -103,6 +103,7 @@ fn finish(
|
||||
stats.insert(
|
||||
anchor.clone(),
|
||||
SessionSnapshotEntry {
|
||||
use_policy: None,
|
||||
entry_id: format!("run-stats:{anchor}"),
|
||||
timestamp: ended_at,
|
||||
provenance: SessionEntryProvenance::LegacyUnknown,
|
||||
|
||||
@@ -0,0 +1,398 @@
|
||||
//! Durable, domain-neutral Session retention pins and permanent erasure fences.
|
||||
//!
|
||||
//! Hosts choose a control root whose lifetime outlasts the physical Session.
|
||||
//! Every deletion path must execute its physical removal inside `delete`, and
|
||||
//! publishers must hold `lock_live` while creating or appending source data.
|
||||
//! A check followed by unlocked removal is not a retention guarantee.
|
||||
//!
|
||||
//! Pins have explicit owners and no timer/expiry: domain code releases its pin
|
||||
//! only after its durable consumer no longer needs originals. A permanent erase
|
||||
//! persists its fence before physical removal, invalidates pins, and rejects
|
||||
//! late pins/publication even after reopening the control store. Retrying an
|
||||
//! interrupted physical erase uses the same intent and is safe.
|
||||
|
||||
use std::collections::BTreeSet;
|
||||
use std::fs::{self, File, OpenOptions};
|
||||
use std::path::{Path, PathBuf};
|
||||
|
||||
use fs4::fs_std::FileExt;
|
||||
use serde::{Deserialize, Serialize};
|
||||
|
||||
use crate::{SessionId, StoreError};
|
||||
|
||||
#[derive(Debug, Clone, Copy, PartialEq, Eq, PartialOrd, Ord, Serialize, Deserialize)]
|
||||
#[serde(transparent)]
|
||||
pub struct SessionRetentionPin(pub uuid::Uuid);
|
||||
|
||||
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
|
||||
pub enum SessionDeletionIntent {
|
||||
Ordinary,
|
||||
ErasePermanently,
|
||||
}
|
||||
|
||||
#[derive(Debug, Default, Serialize, Deserialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
struct RetentionState {
|
||||
erased: bool,
|
||||
pins: BTreeSet<SessionRetentionPin>,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone)]
|
||||
pub struct SessionRetentionStore {
|
||||
root: PathBuf,
|
||||
}
|
||||
|
||||
/// A process-independent lock; dropping it releases the filesystem lock.
|
||||
/// Do not recursively acquire the same Session lock inside a guarded callback.
|
||||
pub struct SessionRetentionGuard {
|
||||
_file: File,
|
||||
}
|
||||
|
||||
impl SessionRetentionStore {
|
||||
pub fn new(control_root: impl Into<PathBuf>) -> Self {
|
||||
Self {
|
||||
root: control_root.into(),
|
||||
}
|
||||
}
|
||||
|
||||
fn state_path(&self, session: SessionId) -> PathBuf {
|
||||
self.root.join(format!("{session}.json"))
|
||||
}
|
||||
|
||||
fn lock(&self, session: SessionId) -> Result<SessionRetentionGuard, StoreError> {
|
||||
fs::create_dir_all(&self.root)?;
|
||||
let mut options = OpenOptions::new();
|
||||
options.read(true).write(true).create(true).truncate(false);
|
||||
#[cfg(any(target_os = "linux", target_os = "android"))]
|
||||
{
|
||||
use std::os::unix::fs::OpenOptionsExt;
|
||||
// Control roots are Host-owned; never follow a replaced lock file.
|
||||
options.custom_flags(libc::O_NOFOLLOW);
|
||||
}
|
||||
let file = options.open(self.root.join(format!("{session}.lock")))?;
|
||||
FileExt::lock_exclusive(&file)?;
|
||||
Ok(SessionRetentionGuard { _file: file })
|
||||
}
|
||||
|
||||
fn read(&self, session: SessionId) -> Result<RetentionState, StoreError> {
|
||||
match fs::read(self.state_path(session)) {
|
||||
Ok(bytes) => Ok(serde_json::from_slice(&bytes)?),
|
||||
Err(error) if error.kind() == std::io::ErrorKind::NotFound => {
|
||||
Ok(RetentionState::default())
|
||||
}
|
||||
Err(error) => Err(error.into()),
|
||||
}
|
||||
}
|
||||
|
||||
fn save(&self, session: SessionId, state: &RetentionState) -> Result<(), StoreError> {
|
||||
crate::worker_session_store::atomic_write_bytes(
|
||||
&self.state_path(session),
|
||||
&serde_json::to_vec(state)?,
|
||||
)
|
||||
}
|
||||
|
||||
/// Observational fence check; unlike `lock_live`, never creates storage.
|
||||
/// Hosts still fence result adoption in their own durable consumer: a read
|
||||
/// finishing before erasure is not authority for a delayed domain write.
|
||||
pub fn ensure_live(&self, session: SessionId) -> Result<(), StoreError> {
|
||||
if self.read(session)?.erased {
|
||||
return Err(StoreError::SessionErased(session));
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
pub fn lock_live(&self, session: SessionId) -> Result<SessionRetentionGuard, StoreError> {
|
||||
let guard = self.lock(session)?;
|
||||
if self.read(session)?.erased {
|
||||
return Err(StoreError::SessionErased(session));
|
||||
}
|
||||
Ok(guard)
|
||||
}
|
||||
|
||||
/// Protect a Host-owned Session before its first source publication. This is
|
||||
/// retention intent, not proof that any original material exists. The owner must
|
||||
/// establish it before accepting input and use the same control store for writes
|
||||
/// and deletion. Source-serving APIs must still verify actual material separately.
|
||||
pub fn retain_before_publication(
|
||||
&self,
|
||||
session: SessionId,
|
||||
pin: SessionRetentionPin,
|
||||
) -> Result<(), StoreError> {
|
||||
let _guard = self.lock_live(session)?;
|
||||
let mut state = self.read(session)?;
|
||||
if state.pins.insert(pin) {
|
||||
self.save(session, &state)?;
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Call `source_exists` under the same lock used by deletion. Replaying the
|
||||
/// same pin is idempotent; missing source never becomes a successful lease.
|
||||
pub fn pin(
|
||||
&self,
|
||||
session: SessionId,
|
||||
pin: SessionRetentionPin,
|
||||
source_exists: impl FnOnce() -> Result<bool, StoreError>,
|
||||
) -> Result<(), StoreError> {
|
||||
let _guard = self.lock_live(session)?;
|
||||
if !source_exists()? {
|
||||
return Err(StoreError::SessionSourceMissing(session));
|
||||
}
|
||||
let mut state = self.read(session)?;
|
||||
if state.pins.insert(pin) {
|
||||
self.save(session, &state)?;
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
pub fn release(&self, session: SessionId, pin: SessionRetentionPin) -> Result<(), StoreError> {
|
||||
let _guard = self.lock(session)?;
|
||||
let mut state = self.read(session)?;
|
||||
if state.pins.remove(&pin) {
|
||||
self.save(session, &state)?;
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
pub fn pins(&self, session: SessionId) -> Result<Vec<SessionRetentionPin>, StoreError> {
|
||||
let _guard = self.lock(session)?;
|
||||
Ok(self.read(session)?.pins.into_iter().collect())
|
||||
}
|
||||
|
||||
/// Execute physical removal while fencing concurrent pins and publishers.
|
||||
/// An erasure fence is retained even if removal fails or the source is
|
||||
/// already absent. Ordinary deletion after erasure is rejected: recovery
|
||||
/// must preserve the caller's explicit erase intent.
|
||||
pub fn delete<T>(
|
||||
&self,
|
||||
session: SessionId,
|
||||
intent: SessionDeletionIntent,
|
||||
remove: impl FnOnce() -> Result<T, StoreError>,
|
||||
) -> Result<T, StoreError> {
|
||||
let _guard = self.lock(session)?;
|
||||
let mut state = self.read(session)?;
|
||||
match intent {
|
||||
SessionDeletionIntent::Ordinary => {
|
||||
if state.erased {
|
||||
return Err(StoreError::SessionErased(session));
|
||||
}
|
||||
if !state.pins.is_empty() {
|
||||
return Err(StoreError::SessionPinned(session));
|
||||
}
|
||||
}
|
||||
SessionDeletionIntent::ErasePermanently => {
|
||||
if !state.erased || !state.pins.is_empty() {
|
||||
state.erased = true;
|
||||
state.pins.clear();
|
||||
self.save(session, &state)?;
|
||||
}
|
||||
}
|
||||
}
|
||||
remove()
|
||||
}
|
||||
}
|
||||
|
||||
/// FsStore's control state is outside all per-Session source directories.
|
||||
pub(crate) fn fs_retention(root: &Path) -> SessionRetentionStore {
|
||||
SessionRetentionStore::new(root.join(".retention"))
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
#[test]
|
||||
fn publication_intent_survives_reopen_without_attesting_missing_originals() {
|
||||
let temp = tempfile::tempdir().unwrap();
|
||||
let source = temp.path().join("source");
|
||||
let controls = temp.path().join("controls");
|
||||
let session = crate::new_session_id();
|
||||
let pin = SessionRetentionPin(uuid::Uuid::now_v7());
|
||||
let retention = SessionRetentionStore::new(&controls);
|
||||
retention.retain_before_publication(session, pin).unwrap();
|
||||
let reopened = SessionRetentionStore::new(&controls);
|
||||
assert_eq!(reopened.pins(session).unwrap(), [pin]);
|
||||
// An early owner is not a successful source-availability receipt.
|
||||
assert!(
|
||||
matches!(reopened.pin(session, pin, || Ok(source.is_file())), Err(StoreError::SessionSourceMissing(id)) if id == session)
|
||||
);
|
||||
{
|
||||
let _publication = reopened.lock_live(session).unwrap();
|
||||
fs::write(&source, "committed before notification").unwrap();
|
||||
}
|
||||
assert!(
|
||||
matches!(reopened.delete(session, SessionDeletionIntent::Ordinary, || { fs::remove_file(&source)?; Ok(()) }), Err(StoreError::SessionPinned(id)) if id == session)
|
||||
);
|
||||
assert_eq!(
|
||||
fs::read_to_string(&source).unwrap(),
|
||||
"committed before notification"
|
||||
);
|
||||
reopened
|
||||
.delete(session, SessionDeletionIntent::ErasePermanently, || {
|
||||
fs::remove_file(&source)?;
|
||||
Ok(())
|
||||
})
|
||||
.unwrap();
|
||||
assert!(
|
||||
matches!(retention.retain_before_publication(session, pin), Err(StoreError::SessionErased(id)) if id == session)
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn pin_survives_reopen_blocks_delete_and_releases_idempotently() {
|
||||
let temp = tempfile::tempdir().unwrap();
|
||||
let id = crate::new_session_id();
|
||||
let pin = SessionRetentionPin(uuid::Uuid::now_v7());
|
||||
let store = SessionRetentionStore::new(temp.path());
|
||||
store.pin(id, pin, || Ok(true)).unwrap();
|
||||
store.pin(id, pin, || Ok(true)).unwrap();
|
||||
let reopened = SessionRetentionStore::new(temp.path());
|
||||
assert_eq!(reopened.pins(id).unwrap(), [pin]);
|
||||
assert!(matches!(
|
||||
reopened.delete(id, SessionDeletionIntent::Ordinary, || Ok(())),
|
||||
Err(StoreError::SessionPinned(_))
|
||||
));
|
||||
reopened.release(id, pin).unwrap();
|
||||
reopened.release(id, pin).unwrap();
|
||||
assert_eq!(
|
||||
reopened
|
||||
.delete(id, SessionDeletionIntent::Ordinary, || Ok(7))
|
||||
.unwrap(),
|
||||
7
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn erase_failure_persists_fence_invalidates_pin_and_rejects_late_publication() {
|
||||
let temp = tempfile::tempdir().unwrap();
|
||||
let id = crate::new_session_id();
|
||||
let pin = SessionRetentionPin(uuid::Uuid::now_v7());
|
||||
let store = SessionRetentionStore::new(temp.path());
|
||||
store.pin(id, pin, || Ok(true)).unwrap();
|
||||
assert!(
|
||||
store
|
||||
.delete(
|
||||
id,
|
||||
SessionDeletionIntent::ErasePermanently,
|
||||
|| Err::<(), _>(std::io::Error::other("injected removal failure").into())
|
||||
)
|
||||
.is_err()
|
||||
);
|
||||
let reopened = SessionRetentionStore::new(temp.path());
|
||||
assert!(reopened.pins(id).unwrap().is_empty());
|
||||
assert!(matches!(
|
||||
reopened.pin(id, pin, || Ok(true)),
|
||||
Err(StoreError::SessionErased(_))
|
||||
));
|
||||
assert!(matches!(
|
||||
reopened.lock_live(id),
|
||||
Err(StoreError::SessionErased(_))
|
||||
));
|
||||
reopened
|
||||
.delete(id, SessionDeletionIntent::ErasePermanently, || Ok(()))
|
||||
.unwrap();
|
||||
reopened.release(id, pin).unwrap();
|
||||
assert!(matches!(
|
||||
reopened.lock_live(id),
|
||||
Err(StoreError::SessionErased(_))
|
||||
));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn fs_normal_delete_obeys_pin_and_permanent_erase_fences_all_source_writes() {
|
||||
use crate::{FsStore, LogEntry, Store};
|
||||
let temp = tempfile::tempdir().unwrap();
|
||||
let store = FsStore::new(temp.path()).unwrap();
|
||||
let session = crate::new_session_id();
|
||||
let segment = crate::new_segment_id();
|
||||
let entry = LogEntry::TurnEnd {
|
||||
ts: 1,
|
||||
turn_count: 1,
|
||||
};
|
||||
store
|
||||
.create_segment(session, segment, &[entry.clone()])
|
||||
.unwrap();
|
||||
let pin = SessionRetentionPin(uuid::Uuid::now_v7());
|
||||
store.pin_session(session, pin).unwrap();
|
||||
assert!(matches!(
|
||||
store.delete_session(session),
|
||||
Err(StoreError::SessionPinned(_))
|
||||
));
|
||||
assert!(store.exists(session, segment).unwrap());
|
||||
store
|
||||
.delete_session_with_intent(session, SessionDeletionIntent::ErasePermanently)
|
||||
.unwrap();
|
||||
let reopened = FsStore::new(temp.path()).unwrap();
|
||||
assert!(!reopened.exists(session, segment).unwrap());
|
||||
assert!(matches!(
|
||||
reopened.pin_session(session, pin),
|
||||
Err(StoreError::SessionErased(_))
|
||||
));
|
||||
assert!(matches!(
|
||||
reopened.append(session, segment, &entry),
|
||||
Err(StoreError::SessionErased(_))
|
||||
));
|
||||
assert!(matches!(
|
||||
reopened.create_segment(session, segment, &[entry]),
|
||||
Err(StoreError::SessionErased(_))
|
||||
));
|
||||
assert!(
|
||||
!reopened
|
||||
.delete_session_with_intent(session, SessionDeletionIntent::ErasePermanently)
|
||||
.unwrap()
|
||||
);
|
||||
assert!(!reopened.exists(session, segment).unwrap());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn independent_handles_serialize_delete_with_late_pin() {
|
||||
let temp = tempfile::tempdir().unwrap();
|
||||
let source = temp.path().join("source");
|
||||
fs::create_dir(&source).unwrap();
|
||||
let control = temp.path().join("control");
|
||||
let session = crate::new_session_id();
|
||||
let pin = SessionRetentionPin(uuid::Uuid::now_v7());
|
||||
let (entered_tx, entered_rx) = std::sync::mpsc::channel();
|
||||
let (release_tx, release_rx) = std::sync::mpsc::channel();
|
||||
let control2 = control.clone();
|
||||
let source2 = source.clone();
|
||||
let delete = std::thread::spawn(move || {
|
||||
SessionRetentionStore::new(control2).delete(
|
||||
session,
|
||||
SessionDeletionIntent::Ordinary,
|
||||
|| {
|
||||
entered_tx.send(()).unwrap();
|
||||
release_rx
|
||||
.recv_timeout(std::time::Duration::from_secs(10))
|
||||
.unwrap();
|
||||
fs::remove_dir(&source2)?;
|
||||
Ok(())
|
||||
},
|
||||
)
|
||||
});
|
||||
entered_rx
|
||||
.recv_timeout(std::time::Duration::from_secs(10))
|
||||
.unwrap();
|
||||
let late = std::thread::spawn(move || {
|
||||
SessionRetentionStore::new(control).pin(session, pin, || Ok(source.is_dir()))
|
||||
});
|
||||
release_tx.send(()).unwrap();
|
||||
delete.join().unwrap().unwrap();
|
||||
assert!(matches!(
|
||||
late.join().unwrap(),
|
||||
Err(StoreError::SessionSourceMissing(_))
|
||||
));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn missing_source_cannot_acquire_pin() {
|
||||
let temp = tempfile::tempdir().unwrap();
|
||||
let id = crate::new_session_id();
|
||||
let store = SessionRetentionStore::new(temp.path());
|
||||
assert!(matches!(
|
||||
store.pin(id, SessionRetentionPin(uuid::Uuid::now_v7()), || Ok(false)),
|
||||
Err(StoreError::SessionSourceMissing(_))
|
||||
));
|
||||
assert!(store.pins(id).unwrap().is_empty());
|
||||
}
|
||||
}
|
||||
@@ -329,6 +329,7 @@ pub fn save_run_completed(
|
||||
session_id,
|
||||
segment_id,
|
||||
LogEntry::RunCompleted {
|
||||
entry_id: None,
|
||||
ts: segment_log::now_millis(),
|
||||
interrupted,
|
||||
result,
|
||||
|
||||
@@ -122,6 +122,8 @@ pub enum LogEntry {
|
||||
/// Replay restores both interruption state and any resumable logical-run
|
||||
/// turn budget.
|
||||
RunCompleted {
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
entry_id: Option<crate::LoggedSessionHistoryEntryId>,
|
||||
ts: u64,
|
||||
interrupted: bool,
|
||||
result: EngineResult,
|
||||
@@ -194,7 +196,11 @@ pub enum LogEntry {
|
||||
/// A paused interrupted turn was explicitly abandoned without calling
|
||||
/// `run()` or `resume()` again. Replay clears the interrupted marker so
|
||||
/// the restored Worker is idle and future user input starts a normal new turn.
|
||||
PausedTurnAbandoned { ts: u64 },
|
||||
PausedTurnAbandoned {
|
||||
ts: u64,
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
entry_id: Option<crate::LoggedSessionHistoryEntryId>,
|
||||
},
|
||||
|
||||
/// `RequestConfig` changed.
|
||||
ConfigChanged { ts: u64, config: RequestConfig },
|
||||
@@ -248,12 +254,31 @@ pub struct SegmentOrigin {
|
||||
}
|
||||
|
||||
impl LogEntry {
|
||||
/// Validate generic System records before a Store publishes any bytes.
|
||||
pub fn validate_input_metadata(&self) -> Result<(), crate::InputMetadataError> {
|
||||
match self {
|
||||
Self::AnnotatedSegmentStart { history, .. }
|
||||
| Self::AnnotatedUserInput { history, .. } => {
|
||||
for entry in history {
|
||||
entry.validate_input_metadata()?;
|
||||
}
|
||||
}
|
||||
Self::AnnotatedAssistantItem { entry, .. }
|
||||
| Self::AnnotatedToolResult { entry, .. }
|
||||
| Self::ToolResultCorrected { entry, .. } => entry.validate_input_metadata()?,
|
||||
Self::AnnotatedSystemItem { entry, .. } => entry.validate_input_metadata()?,
|
||||
_ => {}
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
/// Allocate the durable public identity for a newly committed Run
|
||||
/// transition. Calling this repeatedly is idempotent so the exact value
|
||||
/// written to storage is also the value published to live subscribers.
|
||||
pub fn ensure_session_entry_id(&mut self) {
|
||||
let entry_id = match self {
|
||||
Self::RunYielded { entry_id, .. }
|
||||
Self::RunCompleted { entry_id, .. }
|
||||
| Self::PausedTurnAbandoned { entry_id, .. }
|
||||
| Self::RunYielded { entry_id, .. }
|
||||
| Self::RunResumed { entry_id, .. }
|
||||
| Self::RunCancelled { entry_id, .. }
|
||||
| Self::RunErrored { entry_id, .. } => entry_id,
|
||||
@@ -275,7 +300,9 @@ impl LogEntry {
|
||||
record_start: u64,
|
||||
) {
|
||||
let entry_id = match self {
|
||||
Self::RunYielded { entry_id, .. }
|
||||
Self::RunCompleted { entry_id, .. }
|
||||
| Self::PausedTurnAbandoned { entry_id, .. }
|
||||
| Self::RunYielded { entry_id, .. }
|
||||
| Self::RunResumed { entry_id, .. }
|
||||
| Self::RunCancelled { entry_id, .. }
|
||||
| Self::RunErrored { entry_id, .. } => entry_id,
|
||||
@@ -527,6 +554,7 @@ mod tests {
|
||||
LoggedHistoryEntry {
|
||||
item: LoggedItem::from(item),
|
||||
metadata: LoggedSessionHistoryMetadata {
|
||||
input_metadata: None,
|
||||
entry_id: LoggedSessionHistoryEntryId::new(),
|
||||
origin: LoggedSessionHistoryOrigin::LegacyUnknown,
|
||||
derivation: None,
|
||||
@@ -586,6 +614,7 @@ mod tests {
|
||||
turn_count: 1,
|
||||
},
|
||||
LogEntry::RunCompleted {
|
||||
entry_id: None,
|
||||
ts: 3200,
|
||||
interrupted: false,
|
||||
result: EngineResult::Finished,
|
||||
@@ -893,12 +922,16 @@ mod tests {
|
||||
compacted_from: None,
|
||||
},
|
||||
LogEntry::RunCompleted {
|
||||
entry_id: None,
|
||||
ts: 100,
|
||||
interrupted: true,
|
||||
result: EngineResult::Paused,
|
||||
active_run_turn_count: Some(1),
|
||||
},
|
||||
LogEntry::PausedTurnAbandoned { ts: 200 },
|
||||
LogEntry::PausedTurnAbandoned {
|
||||
entry_id: None,
|
||||
ts: 200,
|
||||
},
|
||||
]);
|
||||
assert!(!state.last_run_interrupted);
|
||||
assert_eq!(state.active_run_turn_count, None);
|
||||
@@ -1056,6 +1089,7 @@ mod tests {
|
||||
turn_count: 2,
|
||||
},
|
||||
LogEntry::RunCompleted {
|
||||
entry_id: None,
|
||||
ts: 300,
|
||||
interrupted: true,
|
||||
result: EngineResult::LimitReached,
|
||||
@@ -1069,13 +1103,16 @@ mod tests {
|
||||
|
||||
#[test]
|
||||
fn paused_turn_abandoned_entry_round_trip_via_json() {
|
||||
let entry = LogEntry::PausedTurnAbandoned { ts: 12345 };
|
||||
let entry = LogEntry::PausedTurnAbandoned {
|
||||
entry_id: None,
|
||||
ts: 12345,
|
||||
};
|
||||
let json = serde_json::to_string(&entry).unwrap();
|
||||
let parsed: serde_json::Value = serde_json::from_str(&json).unwrap();
|
||||
assert_eq!(parsed["kind"], "paused_turn_abandoned");
|
||||
let decoded: LogEntry = serde_json::from_str(&json).unwrap();
|
||||
match decoded {
|
||||
LogEntry::PausedTurnAbandoned { ts } => assert_eq!(ts, 12345),
|
||||
LogEntry::PausedTurnAbandoned { ts, .. } => assert_eq!(ts, 12345),
|
||||
other => panic!("expected PausedTurnAbandoned, got {other:?}"),
|
||||
}
|
||||
}
|
||||
|
||||
@@ -27,12 +27,27 @@ pub enum StoreError {
|
||||
#[error("serialization error: {0}")]
|
||||
Serde(#[from] serde_json::Error),
|
||||
|
||||
#[error("invalid history input metadata: {0}")]
|
||||
InvalidInputMetadata(#[from] crate::InputMetadataError),
|
||||
|
||||
#[error("segment not found: {0}")]
|
||||
NotFound(SegmentId),
|
||||
|
||||
#[error("log corrupted at line {line}: {message}")]
|
||||
Corrupt { line: usize, message: String },
|
||||
|
||||
#[error("session source is missing: {0}")]
|
||||
SessionSourceMissing(SessionId),
|
||||
|
||||
#[error("session original material is retained by a durable consumer: {0}")]
|
||||
SessionPinned(SessionId),
|
||||
|
||||
#[error("session was permanently erased: {0}")]
|
||||
SessionErased(SessionId),
|
||||
|
||||
#[error("session source retention is unsupported by this store")]
|
||||
SessionRetentionUnsupported,
|
||||
|
||||
#[error("retained observation read limit exceeded")]
|
||||
ReadLimitExceeded,
|
||||
|
||||
@@ -80,6 +95,17 @@ pub enum StoreError {
|
||||
/// take `(SessionId, SegmentId)` so segments can be physically grouped
|
||||
/// per Session on disk (or per session_id in a DB).
|
||||
pub trait Store: Send + Sync {
|
||||
/// Establish durable retention intent before the Host accepts public input.
|
||||
/// This does not attest source availability; it must use the same control store
|
||||
/// as publishers and physical deletion. Unsupported stores fail closed.
|
||||
fn retain_session_before_publication(
|
||||
&self,
|
||||
_session_id: SessionId,
|
||||
_pin: crate::retention::SessionRetentionPin,
|
||||
) -> Result<(), StoreError> {
|
||||
Err(StoreError::SessionRetentionUnsupported)
|
||||
}
|
||||
|
||||
/// Append a single log entry to the segment log.
|
||||
///
|
||||
/// One committed line per successful call. Implementations must not expose
|
||||
|
||||
@@ -86,12 +86,16 @@ pub struct PromptRenderProvenance {
|
||||
/// `notify_wrapper` template) re-shape the live rendering on a later
|
||||
/// resume.
|
||||
///
|
||||
/// New variants get added here as fresh injection kinds come online
|
||||
/// (e.g. `TaskReminder`). The `kind` JSON tag is the snake_case form of
|
||||
/// the variant name.
|
||||
/// Feature-owned inputs use `Input` plus explicit annotated metadata; adding a
|
||||
/// Feature must not extend this enum or ordinary replay. Only core events have
|
||||
/// dedicated variants. Pre-v5 Feature kinds exist exclusively in the migration
|
||||
/// decoder, not in this current wire contract.
|
||||
#[derive(Debug, Clone, Serialize, Deserialize)]
|
||||
#[serde(tag = "kind", rename_all = "snake_case")]
|
||||
pub enum SystemItem {
|
||||
/// Generic System body; private metadata and public presentation are supplied
|
||||
/// independently by the producer in the same annotated history record.
|
||||
Input { body: String },
|
||||
/// Free-form notification sent in by an external caller via
|
||||
/// `Method::Notify`. `message` is the raw caller-supplied text;
|
||||
/// `body` is the wrapped LLM-context form (Worker renders it via
|
||||
@@ -114,14 +118,6 @@ pub enum SystemItem {
|
||||
prompt_provenance: Option<PromptRenderProvenance>,
|
||||
},
|
||||
|
||||
/// Result of an explicitly selected chat Feature invocation. The typed
|
||||
/// result is retained for clients; `body` is the exact bounded context made
|
||||
/// visible to the Worker model.
|
||||
FeatureInvocationResult {
|
||||
result: protocol::FeatureInvocationResult,
|
||||
body: String,
|
||||
},
|
||||
|
||||
/// `@<path>` file reference resolution. `body` is the rendered
|
||||
/// LLM-context text (`[File: <path>]\n…` for regular files,
|
||||
/// `[Dir: <path>]\n…` for directory listings, possibly with a
|
||||
@@ -129,10 +125,6 @@ pub enum SystemItem {
|
||||
/// byte-identical to what was sent.
|
||||
FileAttachment { path: String, body: String },
|
||||
|
||||
/// Explicit Agent Skill activation. `body` is the exact LLM-facing
|
||||
/// Skill text committed before any subsequent LLM request can use it.
|
||||
SkillActivation { name: String, body: String },
|
||||
|
||||
/// Historical persisted Knowledge reference resolution. Knowledge is no
|
||||
/// longer active, so restored sessions ignore this item instead of replaying
|
||||
/// archived record text into model context.
|
||||
@@ -156,29 +148,6 @@ pub enum SystemItem {
|
||||
prompt_provenance: Option<PromptRenderProvenance>,
|
||||
},
|
||||
|
||||
/// Restore-boundary refresh of the current resident Memory projection.
|
||||
/// The exact rendered body is retained so replay is byte-identical; a
|
||||
/// refresh with no ready summary explicitly supersedes older resident
|
||||
/// context without deleting or rewriting history.
|
||||
ResidentSummaryRefresh {
|
||||
body: String,
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
prompt_provenance: Option<PromptRenderProvenance>,
|
||||
},
|
||||
|
||||
/// A Host-fetched change to user-managed Subject behavior. Each changed
|
||||
/// body is appended rather than rewriting prior prompt/session content.
|
||||
SubjectBehaviorRefresh {
|
||||
body: String,
|
||||
/// Exact user-managed behavior acknowledged after durable commit. Old
|
||||
/// logs omit this value; an empty value is not an acknowledgement of a
|
||||
/// nonempty behavior and does not replace their stored rendered body.
|
||||
#[serde(default)]
|
||||
behavior_md: String,
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
prompt_provenance: Option<PromptRenderProvenance>,
|
||||
},
|
||||
|
||||
/// Synthetic note inserted after an interrupted turn before the next
|
||||
/// user input. `body` is the exact LLM-context text explaining that the
|
||||
/// previous turn was cut short.
|
||||
@@ -189,23 +158,67 @@ pub enum SystemItem {
|
||||
},
|
||||
}
|
||||
|
||||
/// Allowlisted presentation data shared by live events and retained snapshots.
|
||||
/// Private Feature payloads and render provenance never cross this boundary.
|
||||
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct PublicSystemItem {
|
||||
pub kind: String,
|
||||
pub body: String,
|
||||
pub presentation: PublicSystemPresentation,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq)]
|
||||
#[serde(tag = "kind", rename_all = "snake_case", deny_unknown_fields)]
|
||||
pub enum PublicSystemPresentation {
|
||||
Notification { message: String },
|
||||
WorkerEvent { event: WorkerEvent },
|
||||
Context,
|
||||
TaskReminder,
|
||||
Ignored,
|
||||
}
|
||||
|
||||
impl SystemItem {
|
||||
pub fn public_item(&self) -> PublicSystemItem {
|
||||
let presentation = match self {
|
||||
Self::Notification { message, .. } => PublicSystemPresentation::Notification {
|
||||
message: message.clone(),
|
||||
},
|
||||
Self::WorkerEvent { event, .. } => PublicSystemPresentation::WorkerEvent {
|
||||
event: event.clone(),
|
||||
},
|
||||
Self::TaskReminder { .. } => PublicSystemPresentation::TaskReminder,
|
||||
Self::Input { .. }
|
||||
| Self::LegacyKnowledgeIgnored { .. }
|
||||
| Self::LegacyIgnored { .. } => PublicSystemPresentation::Ignored,
|
||||
Self::FileAttachment { .. } | Self::Interrupt { .. } => {
|
||||
PublicSystemPresentation::Context
|
||||
}
|
||||
};
|
||||
PublicSystemItem {
|
||||
kind: self.kind_label().to_owned(),
|
||||
body: if matches!(presentation, PublicSystemPresentation::Ignored) {
|
||||
String::new()
|
||||
} else {
|
||||
self.history_text()
|
||||
},
|
||||
presentation,
|
||||
}
|
||||
}
|
||||
|
||||
/// Free-text body the LLM sees inside its `role:system` message
|
||||
/// for this item. Returns the variant's stored `body` verbatim.
|
||||
pub fn history_text(&self) -> String {
|
||||
match self {
|
||||
SystemItem::Input { body } => body.clone(),
|
||||
SystemItem::Notification { body, .. } => body.clone(),
|
||||
SystemItem::WorkerEvent { body, .. } => body.clone(),
|
||||
SystemItem::FeatureInvocationResult { body, .. } => body.clone(),
|
||||
SystemItem::FileAttachment { body, .. } => body.clone(),
|
||||
SystemItem::SkillActivation { body, .. } => body.clone(),
|
||||
SystemItem::LegacyKnowledgeIgnored { .. } => String::new(),
|
||||
SystemItem::LegacyIgnored { slug } => {
|
||||
format!("Ignored legacy procedure item: /{slug}")
|
||||
}
|
||||
SystemItem::TaskReminder { body, .. } => body.clone(),
|
||||
SystemItem::ResidentSummaryRefresh { body, .. } => body.clone(),
|
||||
SystemItem::SubjectBehaviorRefresh { body, .. } => body.clone(),
|
||||
SystemItem::Interrupt { body, .. } => body.clone(),
|
||||
}
|
||||
}
|
||||
@@ -220,16 +233,13 @@ impl SystemItem {
|
||||
/// wire — keep flexible.
|
||||
pub fn kind_label(&self) -> &'static str {
|
||||
match self {
|
||||
SystemItem::Input { .. } => "input",
|
||||
SystemItem::Notification { .. } => "notification",
|
||||
SystemItem::WorkerEvent { .. } => "worker_event",
|
||||
SystemItem::FeatureInvocationResult { .. } => "feature_invocation_result",
|
||||
SystemItem::FileAttachment { .. } => "file_attachment",
|
||||
SystemItem::SkillActivation { .. } => "skill_activation",
|
||||
SystemItem::LegacyKnowledgeIgnored { .. } => "legacy_knowledge_ignored",
|
||||
SystemItem::LegacyIgnored { .. } => "legacy_ignored",
|
||||
SystemItem::TaskReminder { .. } => "task_reminder",
|
||||
SystemItem::ResidentSummaryRefresh { .. } => "resident_summary_refresh",
|
||||
SystemItem::SubjectBehaviorRefresh { .. } => "subject_behavior_refresh",
|
||||
SystemItem::Interrupt { .. } => "interrupt",
|
||||
}
|
||||
}
|
||||
@@ -287,33 +297,45 @@ mod tests {
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn subject_behavior_refresh_round_trips_with_exact_body() {
|
||||
let item = SystemItem::SubjectBehaviorRefresh {
|
||||
body: "current Subject context".to_string(),
|
||||
behavior_md: "exact behavior".to_string(),
|
||||
prompt_provenance: None,
|
||||
};
|
||||
let raw = serde_json::to_string(&item).unwrap();
|
||||
let parsed: SystemItem = serde_json::from_str(&raw).unwrap();
|
||||
assert_eq!(parsed.history_text(), "current Subject context");
|
||||
assert!(
|
||||
matches!(parsed, SystemItem::SubjectBehaviorRefresh { behavior_md, .. } if behavior_md == "exact behavior")
|
||||
);
|
||||
fn current_system_item_rejects_frozen_feature_kinds() {
|
||||
// Even well-formed old payloads cannot enter normal v5 decode/replay.
|
||||
for line in include_str!("legacy_session_log/tests/fixtures/v4-system-inputs.jsonl")
|
||||
.lines()
|
||||
.take(5)
|
||||
{
|
||||
let record: serde_json::Value = serde_json::from_str(line).unwrap();
|
||||
assert!(serde_json::from_value::<SystemItem>(record["entry"]["item"].clone()).is_err());
|
||||
assert!(
|
||||
serde_json::from_value::<crate::LoggedSystemHistoryEntry>(record["entry"].clone())
|
||||
.is_err()
|
||||
);
|
||||
assert!(serde_json::from_str::<crate::LogEntry>(line).is_err());
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn frozen_subject_behavior_log_reads_old_counter_without_republishing_it() {
|
||||
let old = r#"{"kind":"subject_behavior_refresh","body":"exact archived body","behavior_revision":7}"#;
|
||||
let item: SystemItem = serde_json::from_str(old).unwrap();
|
||||
assert_eq!(item.history_text(), "exact archived body");
|
||||
assert_eq!(
|
||||
serde_json::to_value(item).unwrap(),
|
||||
serde_json::json!({
|
||||
"kind": "subject_behavior_refresh",
|
||||
"body": "exact archived body",
|
||||
"behavior_md": ""
|
||||
})
|
||||
);
|
||||
fn public_system_input_decoder_rejects_private_fields_and_unknown_presentations() {
|
||||
let valid = serde_json::json!({
|
||||
"kind": "new-feature-label",
|
||||
"body": "explicit public content",
|
||||
"presentation": { "kind": "context" },
|
||||
});
|
||||
let public: PublicSystemItem = serde_json::from_value(valid.clone()).unwrap();
|
||||
assert_eq!(public.body, "explicit public content");
|
||||
for private_field in [
|
||||
"payload",
|
||||
"prompt_provenance",
|
||||
"policy",
|
||||
"snapshot",
|
||||
"behavior_md",
|
||||
] {
|
||||
let mut malformed = valid.clone();
|
||||
malformed[private_field] = serde_json::json!({ "private": true });
|
||||
assert!(serde_json::from_value::<PublicSystemItem>(malformed).is_err());
|
||||
}
|
||||
let mut unknown = valid;
|
||||
unknown["presentation"] = serde_json::json!({ "kind": "execute_feature_payload" });
|
||||
assert!(serde_json::from_value::<PublicSystemItem>(unknown).is_err());
|
||||
}
|
||||
|
||||
#[test]
|
||||
@@ -409,29 +431,6 @@ mod tests {
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn invocation_result_retains_typed_outcome_and_exact_context() {
|
||||
let result = protocol::FeatureInvocationResult {
|
||||
invocation_id: "stable-invoke".into(),
|
||||
identity: protocol::FeatureInvocationIdentity("builtin:test/prepare".into()),
|
||||
status: protocol::FeatureInvocationStatus::OutcomeUnknown,
|
||||
message: "operation may have committed".into(),
|
||||
context: None,
|
||||
};
|
||||
let body = "Outcome unknown; do not retry automatically";
|
||||
let item = SystemItem::FeatureInvocationResult {
|
||||
result: result.clone(),
|
||||
body: body.into(),
|
||||
};
|
||||
let restored: SystemItem =
|
||||
serde_json::from_str(&serde_json::to_string(&item).unwrap()).unwrap();
|
||||
assert_eq!(restored.history_text(), body);
|
||||
assert_eq!(restored.kind_label(), "feature_invocation_result");
|
||||
assert!(
|
||||
matches!(restored, SystemItem::FeatureInvocationResult { result: saved, .. } if saved == result)
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn round_trip_worker_event() {
|
||||
let item = SystemItem::WorkerEvent {
|
||||
|
||||
@@ -210,18 +210,6 @@ impl WorkerMetadata {
|
||||
}
|
||||
}
|
||||
|
||||
fn replace_active_session(metadata: &mut WorkerMetadata, active: Option<WorkerActiveSegmentRef>) {
|
||||
if let Some(session_id) = active.as_ref().map(|active| active.session_id)
|
||||
&& metadata
|
||||
.subjektiv_session_attribution
|
||||
.as_ref()
|
||||
.is_some_and(|state| state.session_id() != session_id)
|
||||
{
|
||||
metadata.subjektiv_session_attribution = None;
|
||||
}
|
||||
metadata.active = active;
|
||||
}
|
||||
|
||||
/// Sync persistence backend for Worker metadata.
|
||||
pub trait WorkerMetadataStore: Send + Sync {
|
||||
/// Create or replace metadata for its `worker_name` key.
|
||||
@@ -297,7 +285,7 @@ pub trait WorkerMetadataStore: Send + Sync {
|
||||
workspace_root: Option<PathBuf>,
|
||||
) -> Result<WorkerMetadata, WorkerStoreError> {
|
||||
self.update_by_name(worker_name, |metadata| {
|
||||
replace_active_session(metadata, active);
|
||||
metadata.active = active;
|
||||
metadata.resolved_manifest_snapshot = resolved_manifest_snapshot;
|
||||
if let Some(workspace_id) = workspace_id {
|
||||
metadata.workspace_id = Some(workspace_id);
|
||||
@@ -317,7 +305,7 @@ pub trait WorkerMetadataStore: Send + Sync {
|
||||
workspace_id: Option<String>,
|
||||
) -> Result<WorkerMetadata, WorkerStoreError> {
|
||||
self.update_by_name(worker_name, |metadata| {
|
||||
replace_active_session(metadata, active);
|
||||
metadata.active = active;
|
||||
metadata.resolved_manifest_snapshot = resolved_manifest_snapshot;
|
||||
if let Some(workspace_id) = workspace_id {
|
||||
metadata.workspace_id = Some(workspace_id);
|
||||
@@ -334,7 +322,7 @@ pub trait WorkerMetadataStore: Send + Sync {
|
||||
workspace_root: Option<PathBuf>,
|
||||
) -> Result<WorkerMetadata, WorkerStoreError> {
|
||||
self.update_by_name(worker_name, |metadata| {
|
||||
replace_active_session(metadata, active);
|
||||
metadata.active = active;
|
||||
metadata.resolved_manifest_snapshot = resolved_manifest_snapshot;
|
||||
if let Some(workspace_root) = workspace_root {
|
||||
metadata.workspace_root = Some(workspace_root);
|
||||
@@ -342,18 +330,6 @@ pub trait WorkerMetadataStore: Send + Sync {
|
||||
})
|
||||
}
|
||||
|
||||
/// Set the Host-owned Subjektiv Session attribution lifecycle state while
|
||||
/// preserving the active Session pointer and every unrelated field.
|
||||
fn set_subjektiv_session_attribution(
|
||||
&self,
|
||||
worker_name: &str,
|
||||
state: SubjektivSessionAttributionState,
|
||||
) -> Result<WorkerMetadata, WorkerStoreError> {
|
||||
self.update_by_name(worker_name, |metadata| {
|
||||
metadata.subjektiv_session_attribution = Some(state);
|
||||
})
|
||||
}
|
||||
|
||||
/// Set spawned-child registry state while preserving active pointer and manifest snapshot.
|
||||
fn set_spawned_children(
|
||||
&self,
|
||||
@@ -806,6 +782,15 @@ where
|
||||
S: crate::Store,
|
||||
W: Send + Sync,
|
||||
{
|
||||
fn retain_session_before_publication(
|
||||
&self,
|
||||
session_id: SessionId,
|
||||
pin: crate::retention::SessionRetentionPin,
|
||||
) -> Result<(), crate::StoreError> {
|
||||
self.session_store
|
||||
.retain_session_before_publication(session_id, pin)
|
||||
}
|
||||
|
||||
fn append(
|
||||
&self,
|
||||
session_id: SessionId,
|
||||
@@ -1078,13 +1063,13 @@ mod tests {
|
||||
))
|
||||
.unwrap();
|
||||
store
|
||||
.set_subjektiv_session_attribution(
|
||||
"subject-worker",
|
||||
SubjektivSessionAttributionState::OutcomeUnknown {
|
||||
session_id,
|
||||
diagnostic: "request interrupted".to_string(),
|
||||
},
|
||||
)
|
||||
.update_by_name("subject-worker", |metadata| {
|
||||
metadata.subjektiv_session_attribution =
|
||||
Some(SubjektivSessionAttributionState::OutcomeUnknown {
|
||||
session_id,
|
||||
diagnostic: "request interrupted".to_string(),
|
||||
});
|
||||
})
|
||||
.unwrap();
|
||||
store
|
||||
.set_active(
|
||||
@@ -1108,7 +1093,7 @@ mod tests {
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn new_active_session_clears_prior_session_attribution_state() {
|
||||
fn generic_active_update_does_not_interpret_host_attribution() {
|
||||
let tmp = tempfile::TempDir::new().unwrap();
|
||||
let store = FsWorkerStore::new(tmp.path()).unwrap();
|
||||
let old_session_id = crate::new_session_id();
|
||||
@@ -1120,13 +1105,13 @@ mod tests {
|
||||
))
|
||||
.unwrap();
|
||||
store
|
||||
.set_subjektiv_session_attribution(
|
||||
"subject-worker",
|
||||
SubjektivSessionAttributionState::Confirmed {
|
||||
session_id: old_session_id,
|
||||
subject_id: "subject-1".to_string(),
|
||||
},
|
||||
)
|
||||
.update_by_name("subject-worker", |metadata| {
|
||||
metadata.subjektiv_session_attribution =
|
||||
Some(SubjektivSessionAttributionState::Confirmed {
|
||||
session_id: old_session_id,
|
||||
subject_id: "subject-1".to_string(),
|
||||
});
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
store
|
||||
@@ -1142,7 +1127,9 @@ mod tests {
|
||||
restored.active,
|
||||
Some(WorkerActiveSegmentRef::pending_segment(new_session_id))
|
||||
);
|
||||
assert!(restored.subjektiv_session_attribution.is_none());
|
||||
assert!(
|
||||
matches!(restored.subjektiv_session_attribution, Some(SubjektivSessionAttributionState::Confirmed { session_id, .. }) if session_id == old_session_id)
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
|
||||
@@ -36,7 +36,10 @@ use std::path::{Path, PathBuf};
|
||||
use std::sync::{Arc, Mutex};
|
||||
use std::time::SystemTime;
|
||||
|
||||
const SESSION_SCHEMA_VERSION: u32 = 3;
|
||||
const SESSION_SCHEMA_VERSION: u32 = 6;
|
||||
const SYSTEM_INPUT_SESSION_SCHEMA_VERSION: u32 = 5;
|
||||
const COMPACTION_SESSION_SCHEMA_VERSION: u32 = 4;
|
||||
const ANNOTATED_SESSION_SCHEMA_VERSION: u32 = 3;
|
||||
const PREVIOUS_SESSION_SCHEMA_VERSION: u32 = 2;
|
||||
const LEGACY_SESSION_SCHEMA_VERSION: u32 = 1;
|
||||
const SESSION_FILE: &str = "session.json";
|
||||
@@ -48,6 +51,7 @@ pub struct WorkerSessionStore {
|
||||
root: PathBuf,
|
||||
session_id: Arc<Mutex<Option<SessionId>>>,
|
||||
append_lock: Arc<Mutex<()>>,
|
||||
retention: Option<crate::retention::SessionRetentionStore>,
|
||||
}
|
||||
|
||||
#[derive(Debug, Serialize, Deserialize)]
|
||||
@@ -72,6 +76,9 @@ pub(crate) struct RetainedSegmentReader {
|
||||
read_end: u64,
|
||||
buffer_start: u64,
|
||||
buffer: Vec<u8>,
|
||||
// Newest-to-oldest fragments of a record spanning multiple read chunks.
|
||||
// Keep them separate until its boundary is found to avoid repeated prepend copies.
|
||||
record_suffix: Vec<Vec<u8>>,
|
||||
}
|
||||
|
||||
impl RetainedSegmentReader {
|
||||
@@ -82,13 +89,19 @@ impl RetainedSegmentReader {
|
||||
let mut read_bytes = 0_u64;
|
||||
loop {
|
||||
if !self.buffer.is_empty() {
|
||||
if self.buffer.last() != Some(&b'\n') {
|
||||
return Err(StoreError::Corrupt {
|
||||
line: 0,
|
||||
message: "retained Segment cursor is not at a record boundary".to_string(),
|
||||
});
|
||||
}
|
||||
let prior_newline = self.buffer[..self.buffer.len() - 1]
|
||||
let search_end = if self.record_suffix.is_empty() {
|
||||
if self.buffer.last() != Some(&b'\n') {
|
||||
return Err(StoreError::Corrupt {
|
||||
line: 0,
|
||||
message: "retained Segment cursor is not at a record boundary"
|
||||
.to_string(),
|
||||
});
|
||||
}
|
||||
self.buffer.len() - 1
|
||||
} else {
|
||||
self.buffer.len()
|
||||
};
|
||||
let prior_newline = self.buffer[..search_end]
|
||||
.iter()
|
||||
.rposition(|byte| *byte == b'\n');
|
||||
if let Some(newline) =
|
||||
@@ -100,9 +113,13 @@ impl RetainedSegmentReader {
|
||||
newline + 1
|
||||
};
|
||||
let record_start = self.buffer_start + record_start_in_buffer as u64;
|
||||
let record_end = self.buffer_start + self.buffer.len() as u64;
|
||||
let record =
|
||||
self.buffer[record_start_in_buffer..self.buffer.len() - 1].to_vec();
|
||||
let record_end = self.read_end;
|
||||
let mut record = Vec::with_capacity((record_end - record_start) as usize);
|
||||
record.extend_from_slice(&self.buffer[record_start_in_buffer..]);
|
||||
for fragment in self.record_suffix.drain(..).rev() {
|
||||
record.extend_from_slice(&fragment);
|
||||
}
|
||||
record.pop(); // The final newline was checked before collecting fragments.
|
||||
self.buffer.truncate(record_start_in_buffer);
|
||||
self.read_end = record_start;
|
||||
if record.is_empty() {
|
||||
@@ -126,24 +143,17 @@ impl RetainedSegmentReader {
|
||||
read_bytes,
|
||||
));
|
||||
}
|
||||
// This chunk has no earlier boundary. Never scan or copy it again
|
||||
// until the complete record can be assembled once.
|
||||
self.record_suffix.push(std::mem::take(&mut self.buffer));
|
||||
} else if self.read_end == 0 {
|
||||
return Ok((None, read_bytes));
|
||||
}
|
||||
|
||||
if self.buffer_start == 0 && !self.buffer.is_empty() {
|
||||
return Err(StoreError::Corrupt {
|
||||
line: 0,
|
||||
message: "retained Segment log does not end at a record boundary".to_string(),
|
||||
});
|
||||
}
|
||||
if read_bytes >= max_additional_bytes {
|
||||
return Err(StoreError::ReadLimitExceeded);
|
||||
}
|
||||
let end = if self.buffer.is_empty() {
|
||||
self.read_end
|
||||
} else {
|
||||
self.buffer_start
|
||||
};
|
||||
let end = self.buffer_start;
|
||||
let available = max_additional_bytes - read_bytes;
|
||||
let chunk_len = end
|
||||
.min(RETAINED_BACKWARD_READ_CHUNK_BYTES as u64)
|
||||
@@ -156,7 +166,6 @@ impl RetainedSegmentReader {
|
||||
let mut chunk = vec![0_u8; chunk_len as usize];
|
||||
self.file.read_exact(&mut chunk)?;
|
||||
read_bytes += chunk_len;
|
||||
chunk.extend_from_slice(&self.buffer);
|
||||
self.buffer = chunk;
|
||||
self.buffer_start = start;
|
||||
}
|
||||
@@ -164,9 +173,48 @@ impl RetainedSegmentReader {
|
||||
}
|
||||
|
||||
impl WorkerSessionStore {
|
||||
/// Publishes through the same external control store used by Runtime retention.
|
||||
/// Existing manifest migration is fenced too; future writes keep the guard until their
|
||||
/// physical publication finishes. The control root must outlive this aggregate.
|
||||
pub fn new_with_retention(
|
||||
root: impl Into<PathBuf>,
|
||||
retention: crate::retention::SessionRetentionStore,
|
||||
) -> Result<Self, StoreError> {
|
||||
let root = root.into();
|
||||
let existing = match fs::read(root.join(SESSION_FILE)) {
|
||||
Ok(bytes) => Some(serde_json::from_slice::<SessionManifest>(&bytes)?.session_id),
|
||||
Err(error) if error.kind() == std::io::ErrorKind::NotFound => None,
|
||||
Err(error) => return Err(error.into()),
|
||||
};
|
||||
let _guard = existing
|
||||
.map(|session| retention.lock_live(session))
|
||||
.transpose()?;
|
||||
let mut store = Self::new(root)?;
|
||||
store.retention = Some(retention);
|
||||
Ok(store)
|
||||
}
|
||||
|
||||
fn lock_publication(
|
||||
&self,
|
||||
session: SessionId,
|
||||
) -> Result<Option<crate::retention::SessionRetentionGuard>, StoreError> {
|
||||
self.retention
|
||||
.as_ref()
|
||||
.map(|store| store.lock_live(session))
|
||||
.transpose()
|
||||
}
|
||||
|
||||
/// Open the Session store rooted at `<worker-aggregate>/session`.
|
||||
pub fn new(root: impl Into<PathBuf>) -> Result<Self, StoreError> {
|
||||
let root = root.into();
|
||||
Self::new_with_migration_writer(root.into(), atomic_write_bytes)
|
||||
}
|
||||
|
||||
// Keep fault injection at the storage publication boundary, without global
|
||||
// flags or a public alternate restore API. Production always uses atomic writes.
|
||||
fn new_with_migration_writer(
|
||||
root: PathBuf,
|
||||
write_segment: impl FnMut(&Path, &[u8]) -> Result<(), StoreError>,
|
||||
) -> Result<Self, StoreError> {
|
||||
fs::create_dir_all(root.join(SEGMENTS_DIR))?;
|
||||
let session_id = match fs::read(root.join(SESSION_FILE)) {
|
||||
Ok(bytes) => {
|
||||
@@ -175,11 +223,16 @@ impl WorkerSessionStore {
|
||||
SESSION_SCHEMA_VERSION => {
|
||||
validate_canonical_segment_logs(&root)?;
|
||||
}
|
||||
PREVIOUS_SESSION_SCHEMA_VERSION | LEGACY_SESSION_SCHEMA_VERSION => {
|
||||
migrate_segment_logs_to_v3(
|
||||
&root,
|
||||
LEGACY_SESSION_SCHEMA_VERSION
|
||||
| PREVIOUS_SESSION_SCHEMA_VERSION
|
||||
| ANNOTATED_SESSION_SCHEMA_VERSION
|
||||
| COMPACTION_SESSION_SCHEMA_VERSION
|
||||
| SYSTEM_INPUT_SESSION_SCHEMA_VERSION => {
|
||||
migrate_segment_logs_to_current(
|
||||
segment_log_paths(&root)?,
|
||||
manifest.session_id,
|
||||
manifest.schema_version,
|
||||
write_segment,
|
||||
)?;
|
||||
manifest.schema_version = SESSION_SCHEMA_VERSION;
|
||||
atomic_write_json(&root.join(SESSION_FILE), &manifest)?;
|
||||
@@ -202,9 +255,37 @@ impl WorkerSessionStore {
|
||||
root,
|
||||
session_id: Arc::new(Mutex::new(session_id)),
|
||||
append_lock: Arc::new(Mutex::new(())),
|
||||
retention: None,
|
||||
})
|
||||
}
|
||||
|
||||
/// Validate an existing Session's conversion without publishing any bytes.
|
||||
/// Hosts can isolate unreadable archives before admitting a staged migration;
|
||||
/// the versioned decoder and conversion checks remain owned by this store.
|
||||
pub fn validate_migration(root: &Path) -> Result<(), StoreError> {
|
||||
let manifest: SessionManifest =
|
||||
serde_json::from_slice(&fs::read(root.join(SESSION_FILE))?)?;
|
||||
match manifest.schema_version {
|
||||
SESSION_SCHEMA_VERSION => validate_canonical_segment_logs(root),
|
||||
LEGACY_SESSION_SCHEMA_VERSION
|
||||
| PREVIOUS_SESSION_SCHEMA_VERSION
|
||||
| ANNOTATED_SESSION_SCHEMA_VERSION
|
||||
| COMPACTION_SESSION_SCHEMA_VERSION
|
||||
| SYSTEM_INPUT_SESSION_SCHEMA_VERSION => migrate_segment_logs_to_current(
|
||||
segment_log_paths(root)?,
|
||||
manifest.session_id,
|
||||
manifest.schema_version,
|
||||
|_, _| Ok(()),
|
||||
),
|
||||
version => Err(StoreError::Corrupt {
|
||||
line: 0,
|
||||
message: format!(
|
||||
"unsupported Worker Session schema version {version}, expected {SESSION_SCHEMA_VERSION}"
|
||||
),
|
||||
}),
|
||||
}
|
||||
}
|
||||
|
||||
/// Open an already-retained Session without creating directories or migrating
|
||||
/// persisted data. Observation paths must never mutate retained state.
|
||||
pub fn open_read_only(root: impl Into<PathBuf>) -> Result<Self, StoreError> {
|
||||
@@ -224,6 +305,7 @@ impl WorkerSessionStore {
|
||||
root,
|
||||
session_id: Arc::new(Mutex::new(Some(manifest.session_id))),
|
||||
append_lock: Arc::new(Mutex::new(())),
|
||||
retention: None,
|
||||
})
|
||||
}
|
||||
|
||||
@@ -456,6 +538,7 @@ impl WorkerSessionStore {
|
||||
read_end: before_offset,
|
||||
buffer_start: before_offset,
|
||||
buffer: Vec::new(),
|
||||
record_suffix: Vec::new(),
|
||||
})
|
||||
}
|
||||
|
||||
@@ -682,12 +765,25 @@ impl WorkerSessionStore {
|
||||
}
|
||||
|
||||
impl Store for WorkerSessionStore {
|
||||
fn retain_session_before_publication(
|
||||
&self,
|
||||
session_id: SessionId,
|
||||
pin: crate::retention::SessionRetentionPin,
|
||||
) -> Result<(), StoreError> {
|
||||
self.retention
|
||||
.as_ref()
|
||||
.ok_or(StoreError::SessionRetentionUnsupported)?
|
||||
.retain_before_publication(session_id, pin)
|
||||
}
|
||||
|
||||
fn append(
|
||||
&self,
|
||||
session_id: SessionId,
|
||||
segment_id: SegmentId,
|
||||
entry: &LogEntry,
|
||||
) -> Result<(), StoreError> {
|
||||
entry.validate_input_metadata()?;
|
||||
let _retention = self.lock_publication(session_id)?;
|
||||
self.ensure_session(session_id, true)?;
|
||||
self.append_log_entry(&self.log_path(segment_id), entry)
|
||||
}
|
||||
@@ -710,6 +806,11 @@ impl Store for WorkerSessionStore {
|
||||
}
|
||||
|
||||
fn list_segments(&self, session_id: SessionId) -> Result<Vec<SegmentId>, StoreError> {
|
||||
// A pending Worker can have metadata before its atomic initial seed.
|
||||
// Absence is queryable without materializing or binding this store.
|
||||
if self.session_id()?.is_none() {
|
||||
return Ok(Vec::new());
|
||||
}
|
||||
self.ensure_session(session_id, false)?;
|
||||
let mut segments: Vec<SegmentId> = Vec::new();
|
||||
for entry in fs::read_dir(self.root.join(SEGMENTS_DIR))? {
|
||||
@@ -740,6 +841,10 @@ impl Store for WorkerSessionStore {
|
||||
segment_id: SegmentId,
|
||||
entries: &[LogEntry],
|
||||
) -> Result<(), StoreError> {
|
||||
for entry in entries {
|
||||
entry.validate_input_metadata()?;
|
||||
}
|
||||
let _retention = self.lock_publication(session_id)?;
|
||||
self.ensure_session(session_id, true)?;
|
||||
let mut content = Vec::new();
|
||||
for entry in entries {
|
||||
@@ -751,6 +856,9 @@ impl Store for WorkerSessionStore {
|
||||
}
|
||||
|
||||
fn exists(&self, session_id: SessionId, segment_id: SegmentId) -> Result<bool, StoreError> {
|
||||
if self.session_id()?.is_none() {
|
||||
return Ok(false);
|
||||
}
|
||||
self.ensure_session(session_id, false)?;
|
||||
Ok(self.log_path(segment_id).exists())
|
||||
}
|
||||
@@ -788,6 +896,7 @@ impl Store for WorkerSessionStore {
|
||||
content: &str,
|
||||
limits: PasteArtifactLimits,
|
||||
) -> Result<PasteArtifactRef, StoreError> {
|
||||
let _retention = self.lock_publication(session_id)?;
|
||||
self.ensure_session(session_id, true)?;
|
||||
let _guard = self
|
||||
.append_lock
|
||||
@@ -818,6 +927,7 @@ impl Store for WorkerSessionStore {
|
||||
content: &[u8],
|
||||
limits: UploadedFileLimits,
|
||||
) -> Result<UploadedFileRef, StoreError> {
|
||||
let _retention = self.lock_publication(session_id)?;
|
||||
self.ensure_session(session_id, true)?;
|
||||
let _guard = self
|
||||
.append_lock
|
||||
@@ -842,6 +952,7 @@ impl Store for WorkerSessionStore {
|
||||
context: &UploadedFileUploadContext,
|
||||
limits: UploadedFileLimits,
|
||||
) -> Result<UploadedFileRef, StoreError> {
|
||||
let _retention = self.lock_publication(session_id)?;
|
||||
self.ensure_session(session_id, true)?;
|
||||
let _guard = self
|
||||
.append_lock
|
||||
@@ -881,6 +992,7 @@ impl Store for WorkerSessionStore {
|
||||
reference: &UploadedFileRef,
|
||||
source_entry_id: &str,
|
||||
) -> Result<UploadedFileRef, StoreError> {
|
||||
let _retention = self.lock_publication(session_id)?;
|
||||
self.ensure_session(session_id, false)?;
|
||||
let _guard = self
|
||||
.append_lock
|
||||
@@ -909,6 +1021,7 @@ impl Store for WorkerSessionStore {
|
||||
reference: &UploadedFileRef,
|
||||
owner_id: &str,
|
||||
) -> Result<(), StoreError> {
|
||||
let _retention = self.lock_publication(session_id)?;
|
||||
self.ensure_session(session_id, false)?;
|
||||
let _guard = self
|
||||
.append_lock
|
||||
@@ -923,6 +1036,7 @@ impl Store for WorkerSessionStore {
|
||||
artifact_id: &str,
|
||||
owner_id: &str,
|
||||
) -> Result<(), StoreError> {
|
||||
let _retention = self.lock_publication(session_id)?;
|
||||
self.ensure_session(session_id, false)?;
|
||||
let _guard = self
|
||||
.append_lock
|
||||
@@ -937,6 +1051,7 @@ impl Store for WorkerSessionStore {
|
||||
artifact_id: &str,
|
||||
source_entry_id: &str,
|
||||
) -> Result<(), StoreError> {
|
||||
let _retention = self.lock_publication(session_id)?;
|
||||
self.ensure_session(session_id, false)?;
|
||||
let _guard = self
|
||||
.append_lock
|
||||
@@ -954,6 +1069,7 @@ impl Store for WorkerSessionStore {
|
||||
session_id: SessionId,
|
||||
live_owner_ids: &[String],
|
||||
) -> Result<u64, StoreError> {
|
||||
let _retention = self.lock_publication(session_id)?;
|
||||
self.ensure_session(session_id, false)?;
|
||||
let _guard = self
|
||||
.append_lock
|
||||
@@ -967,6 +1083,7 @@ impl Store for WorkerSessionStore {
|
||||
session_id: SessionId,
|
||||
artifact_id: &str,
|
||||
) -> Result<bool, StoreError> {
|
||||
let _retention = self.lock_publication(session_id)?;
|
||||
self.ensure_session(session_id, false)?;
|
||||
let _guard = self
|
||||
.append_lock
|
||||
@@ -976,6 +1093,7 @@ impl Store for WorkerSessionStore {
|
||||
}
|
||||
|
||||
fn delete_uncommitted_uploaded_files(&self, session_id: SessionId) -> Result<u64, StoreError> {
|
||||
let _retention = self.lock_publication(session_id)?;
|
||||
self.ensure_session(session_id, false)?;
|
||||
let _guard = self
|
||||
.append_lock
|
||||
@@ -1010,6 +1128,7 @@ impl Store for WorkerSessionStore {
|
||||
segment_id: SegmentId,
|
||||
entry: &TraceEntry,
|
||||
) -> Result<(), StoreError> {
|
||||
let _retention = self.lock_publication(session_id)?;
|
||||
self.ensure_session(session_id, true)?;
|
||||
self.append_line(&self.trace_path(segment_id), &serde_json::to_string(entry)?)
|
||||
}
|
||||
@@ -1035,7 +1154,12 @@ fn open_retained_file(path: &Path) -> std::io::Result<File> {
|
||||
}
|
||||
|
||||
fn segment_log_paths(root: &Path) -> Result<Vec<(SegmentId, PathBuf)>, StoreError> {
|
||||
let segments = root.join(SEGMENTS_DIR);
|
||||
segment_log_paths_in_directory(&root.join(SEGMENTS_DIR))
|
||||
}
|
||||
|
||||
fn segment_log_paths_in_directory(
|
||||
segments: &Path,
|
||||
) -> Result<Vec<(SegmentId, PathBuf)>, StoreError> {
|
||||
if !segments.exists() {
|
||||
return Ok(Vec::new());
|
||||
}
|
||||
@@ -1078,21 +1202,23 @@ fn segment_log_paths(root: &Path) -> Result<Vec<(SegmentId, PathBuf)>, StoreErro
|
||||
Ok(paths)
|
||||
}
|
||||
|
||||
fn migrate_segment_logs_to_v3(
|
||||
root: &Path,
|
||||
fn migrate_segment_logs_to_current(
|
||||
paths: Vec<(SegmentId, PathBuf)>,
|
||||
session_id: SessionId,
|
||||
source_schema_version: u32,
|
||||
mut write_segment: impl FnMut(&Path, &[u8]) -> Result<(), StoreError>,
|
||||
) -> Result<(), StoreError> {
|
||||
struct MigrationPlan {
|
||||
path: PathBuf,
|
||||
source: Vec<u8>,
|
||||
entries: Vec<LogEntry>,
|
||||
output: Vec<u8>,
|
||||
}
|
||||
|
||||
// Phase 1 is strictly read-only. Every segment must parse and canonicalize
|
||||
// successfully before the first authoritative byte is replaced.
|
||||
let mut plans = Vec::new();
|
||||
for (segment_id, path) in segment_log_paths(root)? {
|
||||
for (segment_id, path) in paths {
|
||||
let source = fs::read(&path)?;
|
||||
let canonical = parse_legacy_jsonl(source_schema_version, session_id, segment_id, &source)
|
||||
.map_err(|error| StoreError::Corrupt {
|
||||
@@ -1102,17 +1228,32 @@ fn migrate_segment_logs_to_v3(
|
||||
path.display()
|
||||
),
|
||||
})?;
|
||||
let mut output = Vec::new();
|
||||
for entry in canonical {
|
||||
serde_json::to_writer(&mut output, &entry)?;
|
||||
output.push(b'\n');
|
||||
}
|
||||
plans.push(MigrationPlan {
|
||||
path,
|
||||
source,
|
||||
output,
|
||||
entries: canonical,
|
||||
output: Vec::new(),
|
||||
});
|
||||
}
|
||||
// Resolve trusted creation boundaries first, then update inherited copies by
|
||||
// logical identity too (fork/rewind seeds retain the same entry id).
|
||||
let summaries = if source_schema_version < COMPACTION_SESSION_SCHEMA_VERSION {
|
||||
crate::legacy_session_log::compaction_summary_ids(
|
||||
plans.iter().flat_map(|plan| plan.entries.iter()),
|
||||
)
|
||||
} else {
|
||||
// v4 already made the explicit origin migration. Preserve its origins.
|
||||
Default::default()
|
||||
};
|
||||
for plan in &mut plans {
|
||||
crate::legacy_session_log::migrate_compaction_origins(&mut plan.entries, &summaries);
|
||||
for mut entry in std::mem::take(&mut plan.entries) {
|
||||
crate::legacy_session_log::migrate_system_inputs(&mut entry)?;
|
||||
entry.validate_input_metadata()?;
|
||||
serde_json::to_writer(&mut plan.output, &entry)?;
|
||||
plan.output.push(b'\n');
|
||||
}
|
||||
}
|
||||
|
||||
// Fence the complete preflight snapshot before starting phase 2. Session
|
||||
// open is the exclusive restore boundary; this additionally fails closed
|
||||
@@ -1130,14 +1271,56 @@ fn migrate_segment_logs_to_v3(
|
||||
}
|
||||
|
||||
for plan in plans {
|
||||
atomic_write_bytes(&plan.path, &plan.output)?;
|
||||
write_segment(&plan.path, &plan.output)?;
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Upgrade the standalone per-Session layout using the same persisted format
|
||||
/// migration as Worker aggregates. Called only at writable Host store startup.
|
||||
pub(crate) fn migrate_fs_session(root: &Path, session_id: SessionId) -> Result<(), StoreError> {
|
||||
let marker = root.join("session-schema.json");
|
||||
let version: u32 = match fs::read(&marker) {
|
||||
Ok(bytes) => serde_json::from_slice(&bytes)?,
|
||||
Err(error) if error.kind() == std::io::ErrorKind::NotFound => {
|
||||
ANNOTATED_SESSION_SCHEMA_VERSION
|
||||
}
|
||||
Err(error) => return Err(error.into()),
|
||||
};
|
||||
match version {
|
||||
SESSION_SCHEMA_VERSION => {
|
||||
validate_canonical_segment_paths(segment_log_paths_in_directory(root)?)
|
||||
}
|
||||
LEGACY_SESSION_SCHEMA_VERSION
|
||||
| PREVIOUS_SESSION_SCHEMA_VERSION
|
||||
| ANNOTATED_SESSION_SCHEMA_VERSION
|
||||
| COMPACTION_SESSION_SCHEMA_VERSION
|
||||
| SYSTEM_INPUT_SESSION_SCHEMA_VERSION => {
|
||||
migrate_segment_logs_to_current(
|
||||
segment_log_paths_in_directory(root)?,
|
||||
session_id,
|
||||
version,
|
||||
atomic_write_bytes,
|
||||
)?;
|
||||
atomic_write_json(&marker, &SESSION_SCHEMA_VERSION)
|
||||
}
|
||||
_ => Err(StoreError::Corrupt {
|
||||
line: 0,
|
||||
message: format!("unsupported standalone Session schema {version}"),
|
||||
}),
|
||||
}
|
||||
}
|
||||
|
||||
fn validate_canonical_segment_logs(root: &Path) -> Result<(), StoreError> {
|
||||
for (_, path) in segment_log_paths(root)? {
|
||||
let _: Vec<LogEntry> = parse_jsonl(&fs::read(&path)?)?;
|
||||
validate_canonical_segment_paths(segment_log_paths(root)?)
|
||||
}
|
||||
|
||||
fn validate_canonical_segment_paths(paths: Vec<(SegmentId, PathBuf)>) -> Result<(), StoreError> {
|
||||
for (_, path) in paths {
|
||||
let entries: Vec<LogEntry> = parse_jsonl(&fs::read(&path)?)?;
|
||||
for entry in entries {
|
||||
entry.validate_input_metadata()?;
|
||||
}
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
@@ -1151,17 +1334,26 @@ fn parse_legacy_jsonl(
|
||||
let text = std::str::from_utf8(bytes).map_err(|error| {
|
||||
serde_json::Error::io(std::io::Error::new(std::io::ErrorKind::InvalidData, error))
|
||||
})?;
|
||||
text.lines()
|
||||
let mut offset = 0_u64;
|
||||
text.split_inclusive('\n')
|
||||
.enumerate()
|
||||
.filter(|(_, line)| !line.trim().is_empty())
|
||||
.map(|(line_index, line)| {
|
||||
crate::legacy_session_log::decode_entry(
|
||||
.filter_map(|(line_index, line)| {
|
||||
let start = offset;
|
||||
offset += line.len() as u64;
|
||||
(!line.trim().is_empty()).then_some((line_index, line, start))
|
||||
})
|
||||
.map(|(line_index, line, start)| {
|
||||
let mut entry = crate::legacy_session_log::decode_entry(
|
||||
schema_version,
|
||||
line,
|
||||
session_id,
|
||||
segment_id,
|
||||
line_index,
|
||||
)
|
||||
)?;
|
||||
// Byte offsets change during migration. Persist identities previously
|
||||
// synthesized from the OLD offsets before rewriting any record.
|
||||
entry.ensure_legacy_session_entry_id(session_id, segment_id, start);
|
||||
Ok(entry)
|
||||
})
|
||||
.collect()
|
||||
}
|
||||
@@ -1308,6 +1500,7 @@ mod tests {
|
||||
LoggedHistoryEntry {
|
||||
item: LoggedItem::from(item),
|
||||
metadata: LoggedSessionHistoryMetadata {
|
||||
input_metadata: None,
|
||||
entry_id: LoggedSessionHistoryEntryId::new(),
|
||||
origin: LoggedSessionHistoryOrigin::LegacyUnknown,
|
||||
derivation: None,
|
||||
@@ -1315,6 +1508,139 @@ mod tests {
|
||||
}
|
||||
}
|
||||
|
||||
fn retained_reader(bytes: &[u8]) -> RetainedSegmentReader {
|
||||
let mut file = tempfile::tempfile().unwrap();
|
||||
file.write_all(bytes).unwrap();
|
||||
RetainedSegmentReader {
|
||||
file,
|
||||
session_id: new_session_id(),
|
||||
segment_id: new_segment_id(),
|
||||
read_end: bytes.len() as u64,
|
||||
buffer_start: bytes.len() as u64,
|
||||
buffer: Vec::new(),
|
||||
record_suffix: Vec::new(),
|
||||
}
|
||||
}
|
||||
|
||||
fn checkpoint_line(text: String) -> Vec<u8> {
|
||||
let mut bytes = serde_json::to_vec(&LogEntry::InputSegmentsCheckpoint {
|
||||
ts: 1,
|
||||
user_segments: vec![vec![protocol::Segment::Text { content: text }]],
|
||||
})
|
||||
.unwrap();
|
||||
bytes.push(b'\n');
|
||||
bytes
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn retained_reader_preserves_records_and_offsets_across_chunk_boundaries() {
|
||||
let chunk = RETAINED_BACKWARD_READ_CHUNK_BYTES;
|
||||
let overhead = checkpoint_line(String::new()).len();
|
||||
for line_size in [chunk - 1, chunk, chunk + 1, chunk * 3] {
|
||||
let lines = [
|
||||
checkpoint_line("最初\nの行".into()),
|
||||
checkpoint_line("x".repeat(line_size - overhead)),
|
||||
checkpoint_line("最後".into()),
|
||||
];
|
||||
let bytes = lines.concat();
|
||||
let mut reader = retained_reader(&bytes);
|
||||
let mut end = bytes.len() as u64;
|
||||
let mut total_read = 0;
|
||||
for line in lines.iter().rev() {
|
||||
let (record, read) = reader.previous_record(u64::MAX).unwrap();
|
||||
total_read += read;
|
||||
let record = record.unwrap();
|
||||
assert_eq!(record.end_offset, end);
|
||||
end -= line.len() as u64;
|
||||
assert_eq!(record.start_offset, end);
|
||||
assert_eq!(
|
||||
serde_json::to_vec(&record.entry).unwrap(),
|
||||
line[..line.len() - 1]
|
||||
);
|
||||
}
|
||||
assert_eq!(total_read, bytes.len() as u64);
|
||||
let (record, read) = reader.previous_record(0).unwrap();
|
||||
assert!(record.is_none());
|
||||
assert_eq!(read, 0);
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn retained_reader_resumes_after_budget_exhaustion_and_serves_buffered_records() {
|
||||
let first = checkpoint_line("first".into());
|
||||
let last = checkpoint_line("大きな行".repeat(RETAINED_BACKWARD_READ_CHUNK_BYTES));
|
||||
let mut reader = retained_reader(&[first.clone(), last.clone()].concat());
|
||||
let budget = RETAINED_BACKWARD_READ_CHUNK_BYTES as u64;
|
||||
assert!(matches!(
|
||||
reader.previous_record(budget),
|
||||
Err(StoreError::ReadLimitExceeded)
|
||||
));
|
||||
assert!(matches!(
|
||||
reader.previous_record(0),
|
||||
Err(StoreError::ReadLimitExceeded)
|
||||
));
|
||||
let (record, read) = reader.previous_record(u64::MAX).unwrap();
|
||||
let record = record.unwrap();
|
||||
assert_eq!(record.start_offset, first.len() as u64);
|
||||
assert_eq!(record.end_offset, (first.len() + last.len()) as u64);
|
||||
assert_eq!(read + budget, record.end_offset);
|
||||
assert_eq!(
|
||||
serde_json::to_vec(&record.entry).unwrap(),
|
||||
last[..last.len() - 1]
|
||||
);
|
||||
let (record, read) = reader.previous_record(0).unwrap();
|
||||
assert_eq!(record.unwrap().start_offset, 0);
|
||||
assert_eq!(read, 0);
|
||||
assert!(reader.previous_record(0).unwrap().0.is_none());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn retained_reader_requires_the_prior_boundary_byte_at_exact_chunk_edges() {
|
||||
let chunk = RETAINED_BACKWARD_READ_CHUNK_BYTES;
|
||||
let overhead = checkpoint_line(String::new()).len();
|
||||
for size in [chunk - 1, chunk, chunk + 1] {
|
||||
let first = checkpoint_line("first".into());
|
||||
let last = checkpoint_line("x".repeat(size - overhead));
|
||||
let bytes = [first.clone(), last.clone()].concat();
|
||||
let mut reader = retained_reader(&bytes);
|
||||
// The final record alone is insufficient: its preceding newline
|
||||
// must also be read before its start can be established.
|
||||
assert!(matches!(
|
||||
reader.previous_record(size as u64),
|
||||
Err(StoreError::ReadLimitExceeded)
|
||||
));
|
||||
let (record, read) = reader.previous_record(1).unwrap();
|
||||
let record = record.unwrap();
|
||||
assert_eq!(read, 1);
|
||||
assert_eq!(record.start_offset, first.len() as u64);
|
||||
assert_eq!(record.end_offset, bytes.len() as u64);
|
||||
assert_eq!(
|
||||
serde_json::to_vec(&record.entry).unwrap(),
|
||||
last[..last.len() - 1]
|
||||
);
|
||||
let (record, read) = reader.previous_record(u64::MAX).unwrap();
|
||||
assert_eq!(record.unwrap().start_offset, 0);
|
||||
assert_eq!(read, (first.len() - 1) as u64);
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn retained_reader_rejects_empty_malformed_and_unterminated_records() {
|
||||
for bytes in [
|
||||
b"\n".as_slice(),
|
||||
b"{bad json}\n",
|
||||
b"{\"kind\":\"input_segments_checkpoint\"}",
|
||||
] {
|
||||
assert!(retained_reader(bytes).previous_record(u64::MAX).is_err());
|
||||
}
|
||||
let mut bytes = checkpoint_line("valid".into());
|
||||
bytes.push(b'\n');
|
||||
assert!(matches!(
|
||||
retained_reader(&bytes).previous_record(u64::MAX),
|
||||
Err(StoreError::Corrupt { .. })
|
||||
));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn canonical_combined_store_supports_attachment_uploads() {
|
||||
let root = tempfile::tempdir().unwrap();
|
||||
@@ -1762,6 +2088,146 @@ mod tests {
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn v5_migration_retries_after_second_file_publication_fails() {
|
||||
fn identity_and_body(entries: &[LogEntry]) -> Vec<serde_json::Value> {
|
||||
entries
|
||||
.iter()
|
||||
.flat_map(|record| match record {
|
||||
LogEntry::AnnotatedSystemItem { entry, .. } => vec![entry.to_history_entry()],
|
||||
LogEntry::AnnotatedUserInput { history, .. } => history.clone(),
|
||||
_ => panic!("unexpected record in fixed migration fixture"),
|
||||
})
|
||||
.map(|entry| {
|
||||
serde_json::json!({
|
||||
"entry_id": entry.metadata.entry_id,
|
||||
"origin": entry.metadata.origin,
|
||||
"derivation": entry.metadata.derivation,
|
||||
"item": entry.item,
|
||||
})
|
||||
})
|
||||
.collect()
|
||||
}
|
||||
|
||||
const SOURCE: &str =
|
||||
include_str!("legacy_session_log/tests/fixtures/v4-system-inputs.jsonl");
|
||||
let root = tempfile::tempdir().unwrap();
|
||||
let session_id = new_session_id();
|
||||
let first_id = SegmentId::from_u128(1);
|
||||
let second_id = SegmentId::from_u128(2);
|
||||
fs::create_dir_all(root.path().join(SEGMENTS_DIR)).unwrap();
|
||||
let marker_path = root.path().join(SESSION_FILE);
|
||||
atomic_write_json(
|
||||
&marker_path,
|
||||
&SessionManifest {
|
||||
schema_version: COMPACTION_SESSION_SCHEMA_VERSION,
|
||||
session_id,
|
||||
},
|
||||
)
|
||||
.unwrap();
|
||||
let old_marker = fs::read(&marker_path).unwrap();
|
||||
let first_path = root
|
||||
.path()
|
||||
.join(SEGMENTS_DIR)
|
||||
.join(format!("{first_id}.jsonl"));
|
||||
let second_path = root
|
||||
.path()
|
||||
.join(SEGMENTS_DIR)
|
||||
.join(format!("{second_id}.jsonl"));
|
||||
let second_source = SOURCE.replace("-id", "-second-id");
|
||||
fs::write(&first_path, SOURCE).unwrap();
|
||||
fs::write(&second_path, &second_source).unwrap();
|
||||
let old_first = fs::read(&first_path).unwrap();
|
||||
let old_second = fs::read(&second_path).unwrap();
|
||||
let first_identity =
|
||||
identity_and_body(&parse_legacy_jsonl(4, session_id, first_id, &old_first).unwrap());
|
||||
let second_identity =
|
||||
identity_and_body(&parse_legacy_jsonl(4, session_id, second_id, &old_second).unwrap());
|
||||
|
||||
let mut writes = 0;
|
||||
let mut first_published = None;
|
||||
let failure = WorkerSessionStore::new_with_migration_writer(
|
||||
root.path().to_path_buf(),
|
||||
|path, bytes| {
|
||||
writes += 1;
|
||||
match writes {
|
||||
1 => {
|
||||
assert_eq!(path, first_path.as_path());
|
||||
// Both files are still old when the first publication starts.
|
||||
assert_eq!(fs::read(&first_path).unwrap(), old_first);
|
||||
assert_eq!(fs::read(&second_path).unwrap(), old_second);
|
||||
atomic_write_bytes(path, bytes)?;
|
||||
first_published = Some(bytes.to_vec());
|
||||
Ok(())
|
||||
}
|
||||
2 => {
|
||||
assert_eq!(path, second_path.as_path());
|
||||
assert_eq!(
|
||||
fs::read(&first_path).unwrap(),
|
||||
*first_published.as_ref().unwrap()
|
||||
);
|
||||
assert_eq!(fs::read(&second_path).unwrap(), old_second);
|
||||
// Fail only this atomic-write boundary, after complete
|
||||
// preflight and a real successful first-file publication.
|
||||
Err(std::io::Error::other("injected second migration write failure").into())
|
||||
}
|
||||
_ => panic!("publication continued after its write failure"),
|
||||
}
|
||||
},
|
||||
);
|
||||
let error = match failure {
|
||||
Ok(_) => panic!("the injected publication failure must reject store open"),
|
||||
Err(error) => error,
|
||||
};
|
||||
assert!(
|
||||
error
|
||||
.to_string()
|
||||
.contains("injected second migration write failure")
|
||||
);
|
||||
assert_eq!(writes, 2);
|
||||
let first_published = first_published.unwrap();
|
||||
assert_ne!(first_published, old_first);
|
||||
assert_eq!(fs::read(&first_path).unwrap(), first_published);
|
||||
assert_eq!(fs::read(&second_path).unwrap(), old_second);
|
||||
assert_eq!(fs::read(&marker_path).unwrap(), old_marker);
|
||||
let updated_first: Vec<LogEntry> = parse_jsonl(&first_published).unwrap();
|
||||
for entry in &updated_first {
|
||||
entry.validate_input_metadata().unwrap();
|
||||
}
|
||||
assert!(matches!(
|
||||
&updated_first[0],
|
||||
LogEntry::AnnotatedSystemItem {
|
||||
entry: crate::LoggedSystemHistoryEntry {
|
||||
item: crate::SystemItem::Input { .. },
|
||||
..
|
||||
},
|
||||
..
|
||||
}
|
||||
));
|
||||
assert_eq!(identity_and_body(&updated_first), first_identity);
|
||||
|
||||
// Retry via the public production constructor, without any injection or
|
||||
// hand-built mixed fixture. The old marker drives the same migration.
|
||||
let store = WorkerSessionStore::new(root.path()).unwrap();
|
||||
let first = store.read_all(session_id, first_id).unwrap();
|
||||
let second = store.read_all(session_id, second_id).unwrap();
|
||||
assert_eq!(identity_and_body(&first), first_identity);
|
||||
assert_eq!(identity_and_body(&second), second_identity);
|
||||
for entry in first.iter().chain(second.iter()) {
|
||||
entry.validate_input_metadata().unwrap();
|
||||
}
|
||||
assert_eq!(fs::read(&first_path).unwrap(), first_published);
|
||||
let second_published = fs::read(&second_path).unwrap();
|
||||
assert_ne!(second_published, old_second);
|
||||
let manifest: SessionManifest =
|
||||
serde_json::from_slice(&fs::read(&marker_path).unwrap()).unwrap();
|
||||
assert_eq!(manifest.schema_version, SESSION_SCHEMA_VERSION);
|
||||
drop(store);
|
||||
WorkerSessionStore::new(root.path()).unwrap();
|
||||
assert_eq!(fs::read(&first_path).unwrap(), first_published);
|
||||
assert_eq!(fs::read(&second_path).unwrap(), second_published);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn current_jsonl_requires_annotations_across_append_rewrite_and_reopen() {
|
||||
let root = tempfile::tempdir().unwrap();
|
||||
@@ -1906,6 +2372,24 @@ mod tests {
|
||||
assert!(matches!(error, StoreError::Corrupt { .. }));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn pending_session_probes_are_empty_without_binding_and_foreign_materialized_session_is_rejected()
|
||||
{
|
||||
let root = tempfile::tempdir().unwrap();
|
||||
let session_id = new_session_id();
|
||||
let segment_id = new_segment_id();
|
||||
let store = WorkerSessionStore::new(root.path()).unwrap();
|
||||
assert!(!store.exists(session_id, segment_id).unwrap());
|
||||
assert!(store.list_segments(session_id).unwrap().is_empty());
|
||||
assert_eq!(store.session_id().unwrap(), None);
|
||||
let reopened = WorkerSessionStore::new(root.path()).unwrap();
|
||||
assert_eq!(reopened.session_id().unwrap(), None);
|
||||
store.create_segment(session_id, segment_id, &[]).unwrap();
|
||||
let foreign = new_session_id();
|
||||
assert!(store.exists(foreign, segment_id).is_err());
|
||||
assert!(store.list_segments(foreign).is_err());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn reopen_preserves_session_and_segment_ids() {
|
||||
let root = tempfile::tempdir().unwrap();
|
||||
|
||||
@@ -11,6 +11,7 @@ fn annotated(item: Item) -> LoggedHistoryEntry {
|
||||
LoggedHistoryEntry {
|
||||
item: LoggedItem::from(item),
|
||||
metadata: LoggedSessionHistoryMetadata {
|
||||
input_metadata: None,
|
||||
entry_id: LoggedSessionHistoryEntryId::new(),
|
||||
origin: LoggedSessionHistoryOrigin::LegacyUnknown,
|
||||
derivation: None,
|
||||
@@ -62,6 +63,7 @@ fn round_trip_write_and_read() {
|
||||
turn_count: 1,
|
||||
},
|
||||
LogEntry::RunCompleted {
|
||||
entry_id: None,
|
||||
ts: 3200,
|
||||
interrupted: false,
|
||||
result: EngineResult::Finished,
|
||||
@@ -157,9 +159,10 @@ fn create_segment_replacement_keeps_open_old_log_and_commits_complete_new_log()
|
||||
assert_eq!(reopened.read_entry_count(sid, segid).unwrap(), new.len());
|
||||
assert_eq!(
|
||||
std::fs::read_dir(path.parent().unwrap()).unwrap().count(),
|
||||
1,
|
||||
"successful replacement must not leave temporary files"
|
||||
2,
|
||||
"successful replacement leaves only the segment and Session schema marker"
|
||||
);
|
||||
assert!(path.parent().unwrap().join("session-schema.json").is_file());
|
||||
}
|
||||
|
||||
#[test]
|
||||
@@ -419,3 +422,177 @@ fn lookup_session_of_finds_owning_session() {
|
||||
|
||||
assert_eq!(store.lookup_session_of(segid).unwrap(), Some(sid));
|
||||
}
|
||||
|
||||
// Storage/projection component test: both production layouts, temporary originals,
|
||||
// no Feature, model, runtime or Host authority is substituted into this boundary.
|
||||
#[test]
|
||||
fn generic_system_append_and_fork_preserve_metadata_without_public_payload_leak() {
|
||||
use session_store::{
|
||||
FeatureInputPayload, HistoryInputMetadata, HistoryInputUsePolicy, InputCompactionUse,
|
||||
InputEvidenceUse, InputObservationUse, LoggedHistoryDerivation, LoggedSystemHistoryEntry,
|
||||
PublicSystemItem, PublicSystemPresentation, SystemInputEnvelope, WorkerSessionStore,
|
||||
};
|
||||
for worker_layout in [false, true] {
|
||||
let dir = tempfile::tempdir().unwrap();
|
||||
let sid = new_session_id();
|
||||
let segment = new_segment_id();
|
||||
let fork = new_segment_id();
|
||||
let store: Box<dyn Store> = if worker_layout {
|
||||
Box::new(WorkerSessionStore::new(dir.path()).unwrap())
|
||||
} else {
|
||||
Box::new(FsStore::new(dir.path()).unwrap())
|
||||
};
|
||||
store
|
||||
.create_segment(sid, segment, &[nil_session_start(1, sid)])
|
||||
.unwrap();
|
||||
let entry = LoggedSystemHistoryEntry::from_input(
|
||||
LoggedSessionHistoryOrigin::Provided {
|
||||
producer: "new-feature".into(),
|
||||
},
|
||||
Some(LoggedHistoryDerivation {
|
||||
sources: vec![LoggedSessionHistoryEntryId("source-entry".into())],
|
||||
}),
|
||||
SystemInputEnvelope::new(
|
||||
"private model body",
|
||||
HistoryInputMetadata::new(
|
||||
HistoryInputUsePolicy {
|
||||
recording_material: InputEvidenceUse::Exclude,
|
||||
memory_evidence: InputEvidenceUse::Exclude,
|
||||
observation: InputObservationUse::Hidden,
|
||||
compaction: InputCompactionUse::ReferenceInput,
|
||||
},
|
||||
Some(
|
||||
FeatureInputPayload::encode(
|
||||
"new-feature:context",
|
||||
101,
|
||||
&serde_json::json!({"private": "secret-detail"}),
|
||||
)
|
||||
.unwrap(),
|
||||
),
|
||||
Some(PublicSystemItem {
|
||||
kind: "context".into(),
|
||||
body: "explicit public body".into(),
|
||||
presentation: PublicSystemPresentation::Context,
|
||||
}),
|
||||
)
|
||||
.unwrap(),
|
||||
)
|
||||
.unwrap(),
|
||||
);
|
||||
store
|
||||
.append(
|
||||
sid,
|
||||
segment,
|
||||
&LogEntry::AnnotatedSystemItem {
|
||||
ts: 2,
|
||||
entry: entry.clone(),
|
||||
extensions: vec![],
|
||||
},
|
||||
)
|
||||
.unwrap();
|
||||
let saved = store.read_all(sid, segment).unwrap();
|
||||
let LogEntry::AnnotatedSystemItem {
|
||||
entry: restored, ..
|
||||
} = &saved[1]
|
||||
else {
|
||||
panic!("missing system input")
|
||||
};
|
||||
assert_eq!(restored.to_history_entry(), entry.to_history_entry());
|
||||
assert_eq!(
|
||||
collect_state(&saved).history[0].as_text(),
|
||||
Some("private model body")
|
||||
);
|
||||
let mut fork_seed = nil_session_start(3, sid);
|
||||
if let LogEntry::AnnotatedSegmentStart {
|
||||
history,
|
||||
forked_from,
|
||||
..
|
||||
} = &mut fork_seed
|
||||
{
|
||||
history.push(restored.to_history_entry());
|
||||
*forked_from = Some(session_store::SegmentOrigin {
|
||||
segment_id: segment,
|
||||
at_turn_index: 0,
|
||||
});
|
||||
}
|
||||
store.create_segment(sid, fork, &[fork_seed]).unwrap();
|
||||
let fork_saved = store.read_all(sid, fork).unwrap();
|
||||
let LogEntry::AnnotatedSegmentStart { history, .. } = &fork_saved[0] else {
|
||||
unreachable!()
|
||||
};
|
||||
assert_eq!(history, &[entry.to_history_entry()]);
|
||||
let original = session_store::public_snapshot::project_session_snapshot(sid, &saved);
|
||||
let inherited = session_store::public_snapshot::project_session_snapshot(sid, &fork_saved);
|
||||
let public = serde_json::to_string(&original.entries).unwrap();
|
||||
assert!(public.contains("explicit public body"));
|
||||
for private in ["private model body", "secret-detail", "new-feature:context"] {
|
||||
assert!(!public.contains(private), "private field leaked: {private}");
|
||||
}
|
||||
assert_eq!(original.entries.len(), 1);
|
||||
assert_eq!(inherited.entries.len(), 1);
|
||||
assert_eq!(original.entries[0].entry_id, inherited.entries[0].entry_id);
|
||||
assert_eq!(
|
||||
original.entries[0].derived_from,
|
||||
inherited.entries[0].derived_from
|
||||
);
|
||||
assert_eq!(
|
||||
original.entries[0].provenance,
|
||||
inherited.entries[0].provenance
|
||||
);
|
||||
assert_eq!(
|
||||
serde_json::to_value(&original.entries[0].data).unwrap(),
|
||||
serde_json::to_value(&inherited.entries[0].data).unwrap()
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn invalid_generic_system_input_rejects_append_create_and_external_json_without_changing_originals()
|
||||
{
|
||||
use session_store::{StoreError, SystemItem, WorkerSessionStore};
|
||||
for worker_layout in [false, true] {
|
||||
let dir = tempfile::tempdir().unwrap();
|
||||
let sid = new_session_id();
|
||||
let segment = new_segment_id();
|
||||
let store: Box<dyn Store> = if worker_layout {
|
||||
Box::new(WorkerSessionStore::new(dir.path()).unwrap())
|
||||
} else {
|
||||
Box::new(FsStore::new(dir.path()).unwrap())
|
||||
};
|
||||
let seed = nil_session_start(1, sid);
|
||||
store
|
||||
.create_segment(sid, segment, std::slice::from_ref(&seed))
|
||||
.unwrap();
|
||||
let path = if worker_layout {
|
||||
dir.path().join("segments").join(format!("{segment}.jsonl"))
|
||||
} else {
|
||||
dir.path()
|
||||
.join(sid.to_string())
|
||||
.join(format!("{segment}.jsonl"))
|
||||
};
|
||||
let before = std::fs::read(&path).unwrap();
|
||||
let invalid = LogEntry::AnnotatedSystemItem {
|
||||
ts: 2,
|
||||
extensions: vec![],
|
||||
entry: session_store::LoggedSystemHistoryEntry {
|
||||
item: SystemItem::Input {
|
||||
body: "no policy".into(),
|
||||
},
|
||||
metadata: LoggedSessionHistoryMetadata::legacy_unknown(),
|
||||
},
|
||||
};
|
||||
assert!(matches!(
|
||||
store.append(sid, segment, &invalid),
|
||||
Err(StoreError::InvalidInputMetadata(_))
|
||||
));
|
||||
assert!(matches!(
|
||||
store.create_segment(sid, segment, &[seed, invalid.clone()]),
|
||||
Err(StoreError::InvalidInputMetadata(_))
|
||||
));
|
||||
assert!(
|
||||
serde_json::from_value::<LogEntry>(serde_json::to_value(invalid).unwrap()).is_err()
|
||||
);
|
||||
assert_eq!(std::fs::read(path).unwrap(), before);
|
||||
assert_eq!(store.read_all(sid, segment).unwrap().len(), 1);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -24,6 +24,7 @@ fn annotated(items: &[Item]) -> Vec<session_store::LoggedHistoryEntry> {
|
||||
.map(|item| session_store::LoggedHistoryEntry {
|
||||
item: session_store::LoggedItem::from(item),
|
||||
metadata: session_store::LoggedSessionHistoryMetadata {
|
||||
input_metadata: None,
|
||||
entry_id: session_store::LoggedSessionHistoryEntryId::new(),
|
||||
origin: session_store::LoggedSessionHistoryOrigin::LegacyUnknown,
|
||||
derivation: None,
|
||||
|
||||
@@ -23,7 +23,7 @@ serde.workspace = true
|
||||
serde_json.workspace = true
|
||||
session-store.workspace = true
|
||||
thiserror.workspace = true
|
||||
tokio = { workspace = true, features = ["rt", "sync", "time"] }
|
||||
tokio = { workspace = true, features = ["rt", "sync", "time", "net", "io-util", "io-std", "signal"] }
|
||||
uuid = { workspace = true, features = ["v7"] }
|
||||
worker.workspace = true
|
||||
|
||||
|
||||
@@ -4,7 +4,8 @@ A Host that starts existing Workers in the same process. Assembles interactive W
|
||||
|
||||
## Reference index
|
||||
|
||||
- [`host`] — bootstrap and confirmed shutdown.
|
||||
- [`host`] — bootstrap and confirmed shutdown, with or without a TUI.
|
||||
- [`unix`] — optional operator transport; disconnect does not release execution ownership.
|
||||
- [`launch`] — Profile, cwd, and Subject validation before launch.
|
||||
- [`store`] — Worker records and leases.
|
||||
- [`jobs`] — Job execution and independent result and cleanup lifetimes.
|
||||
|
||||
+250
-40
@@ -23,10 +23,7 @@ use session_store::{
|
||||
CombinedStore, FsStore, FsWorkerStore, WorkerActiveSegmentRef, WorkerMetadataStore,
|
||||
};
|
||||
use thiserror::Error;
|
||||
use worker::bootstrap::{
|
||||
WorkerBootstrap, WorkerBootstrapError, WorkerBootstrapLayout, bash_output_dir_for_worker_id,
|
||||
};
|
||||
use worker::controller::WorkerControllerTransport;
|
||||
use worker::bootstrap::{WorkerBootstrap, WorkerBootstrapError, WorkerBootstrapLayout};
|
||||
use worker::ipc::protocol_session::{
|
||||
WorkerProtocolSessionStreams, dispatch_worker_protocol_method, live_log_entry_event,
|
||||
subscribe_worker_protocol_session,
|
||||
@@ -57,6 +54,15 @@ pub struct StandaloneHost {
|
||||
lease: Option<StandaloneWorkerLease>,
|
||||
jobs: crate::jobs::StandaloneJobs,
|
||||
subject: Option<crate::subjektiv::SubjectConnection>,
|
||||
subject_release: Option<worker::SubjectReleaseReservation>,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Error)]
|
||||
pub enum StandaloneSubjectDisconnectError {
|
||||
#[error("Subject release requires an actual Idle Controller without pending work: {0}")]
|
||||
Controller(String),
|
||||
#[error("Subject release remains incomplete; retained binding/lease must be reconciled: {0}")]
|
||||
Incomplete(String),
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Error)]
|
||||
@@ -89,6 +95,10 @@ pub enum StandaloneStartupError {
|
||||
FeatureComposition,
|
||||
#[error("the in-process Worker controller could not start")]
|
||||
Controller,
|
||||
#[error(
|
||||
"mandatory initial context remains unconfirmed; restore retained Worker {worker_id} to retry this Session"
|
||||
)]
|
||||
InitialContextPending { worker_id: WorkerId },
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, Copy, PartialEq, Eq, Error)]
|
||||
@@ -171,7 +181,7 @@ impl StandaloneHost {
|
||||
let jobs = match crate::jobs::StandaloneJobs::open(&jobs_path, launch.cwd.clone()) {
|
||||
Ok(jobs) => jobs,
|
||||
Err(_) => {
|
||||
let _ = store.abandon_allocation(allocation);
|
||||
cancel_unpublished_start(&store, &mut subject, allocation)?;
|
||||
return Err(StandaloneStartupError::StateStore);
|
||||
}
|
||||
};
|
||||
@@ -179,8 +189,11 @@ impl StandaloneHost {
|
||||
if let Some(client) = &model_client {
|
||||
jobs.bind_model_client(client.clone_boxed());
|
||||
}
|
||||
if let Some(subject) = &subject {
|
||||
subject.host.bind_jobs(jobs.clone())?;
|
||||
if let Some(connection) = &subject
|
||||
&& let Err(error) = connection.host.bind_jobs(jobs.clone())
|
||||
{
|
||||
cancel_unpublished_start(&store, &mut subject, allocation)?;
|
||||
return Err(error);
|
||||
}
|
||||
// WorkerId is the stable identity. The current Worker store remains
|
||||
// name-keyed, so keep its derived storage key separate from the
|
||||
@@ -192,7 +205,7 @@ impl StandaloneHost {
|
||||
let (backing_store, worker_store) = match backing_store(&store, worker_id) {
|
||||
Ok(stores) => stores,
|
||||
Err(error) => {
|
||||
let _ = store.abandon_allocation(allocation);
|
||||
cancel_unpublished_start(&store, &mut subject, allocation)?;
|
||||
return Err(error);
|
||||
}
|
||||
};
|
||||
@@ -200,7 +213,6 @@ impl StandaloneHost {
|
||||
WorkerFilesystemAuthority::local(launch.cwd.clone(), launch.cwd.clone());
|
||||
let workspace_context = WorkerWorkspaceContext::local_filesystem(None);
|
||||
let runtime_base = store.runtime_dir(worker_id);
|
||||
let bash_output_dir = bash_output_dir_for_worker_id(worker_id);
|
||||
|
||||
let mut bootstrap = WorkerBootstrap::new(
|
||||
bootstrap_manifest,
|
||||
@@ -208,11 +220,7 @@ impl StandaloneHost {
|
||||
launch.prompt_catalog,
|
||||
workspace_context,
|
||||
filesystem_authority,
|
||||
WorkerBootstrapLayout::Direct {
|
||||
runtime_base,
|
||||
bash_output_dir,
|
||||
},
|
||||
WorkerControllerTransport::InProcess,
|
||||
WorkerBootstrapLayout::Direct { runtime_base },
|
||||
);
|
||||
if let Some(subject) = &subject {
|
||||
bootstrap = bootstrap.with_subjektiv_host(subject.host.clone());
|
||||
@@ -220,12 +228,61 @@ impl StandaloneHost {
|
||||
if let Some(model_client) = model_client {
|
||||
bootstrap = bootstrap.with_model_client(model_client);
|
||||
}
|
||||
let prepared = match bootstrap.prepare().await {
|
||||
Ok(prepared) => prepared,
|
||||
Err(error) => {
|
||||
cancel_unpublished_start(&store, &mut subject, allocation)?;
|
||||
return Err(classify_startup_error(error));
|
||||
}
|
||||
};
|
||||
// Reserve a recoverable identity before mandatory initial-context persistence.
|
||||
// A failed/unknown seed must be reopened as this Session, never abandoned and
|
||||
// replaced by a newly fetched context under an invisible ghost binding.
|
||||
let pending_record = if subject.is_some() {
|
||||
match store.commit_created_connected(
|
||||
&allocation,
|
||||
manifest.clone(),
|
||||
storage_key.clone(),
|
||||
prepared.worker().session_id(),
|
||||
None,
|
||||
subject.as_ref().map(|s| s.binding.clone()),
|
||||
) {
|
||||
Ok(record) => Some(record),
|
||||
Err(_) => {
|
||||
if let Some(subject) = &mut subject {
|
||||
subject.retain();
|
||||
}
|
||||
allocation.into_lease().retain();
|
||||
return Err(StandaloneStartupError::StateStore);
|
||||
}
|
||||
}
|
||||
} else {
|
||||
None
|
||||
};
|
||||
if let Some(subject) = &mut subject {
|
||||
subject.arm();
|
||||
}
|
||||
let started = match bootstrap.start().await {
|
||||
let started = match prepared.start().await {
|
||||
Ok(started) => started,
|
||||
Err(error) => {
|
||||
if let Some(record) = &pending_record {
|
||||
let cleanup = jobs.shutdown().await;
|
||||
let saved = store.mark_stopped(
|
||||
record,
|
||||
record.active_session_id,
|
||||
record.active_segment_id,
|
||||
StandaloneShutdownReason::StartupFailed,
|
||||
);
|
||||
let closed = cleanup.is_ok()
|
||||
&& saved.is_ok()
|
||||
&& subject.as_mut().is_some_and(|s| s.close().is_ok());
|
||||
if closed {
|
||||
let _ = allocation.into_lease().release();
|
||||
} else {
|
||||
allocation.into_lease().retain();
|
||||
}
|
||||
return Err(StandaloneStartupError::InitialContextPending { worker_id });
|
||||
}
|
||||
let _ = store.abandon_allocation(allocation);
|
||||
return Err(classify_startup_error(error));
|
||||
}
|
||||
@@ -234,22 +291,35 @@ impl StandaloneHost {
|
||||
Ok(active) => active,
|
||||
Err(error) => {
|
||||
stop_started_worker(started).await;
|
||||
let _ = store.abandon_allocation(allocation);
|
||||
if pending_record.is_some() {
|
||||
allocation.into_lease().retain();
|
||||
} else {
|
||||
let _ = store.abandon_allocation(allocation);
|
||||
}
|
||||
return Err(error);
|
||||
}
|
||||
};
|
||||
let record = match store.commit_created_connected(
|
||||
&allocation,
|
||||
manifest,
|
||||
storage_key,
|
||||
active.session_id,
|
||||
active.segment_id,
|
||||
subject.as_ref().map(|s| s.binding.clone()),
|
||||
) {
|
||||
let committed = if let Some(record) = &pending_record {
|
||||
store.update_active_pointer(record, active.session_id, active.segment_id)
|
||||
} else {
|
||||
store.commit_created_connected(
|
||||
&allocation,
|
||||
manifest,
|
||||
storage_key,
|
||||
active.session_id,
|
||||
active.segment_id,
|
||||
None,
|
||||
)
|
||||
};
|
||||
let record = match committed {
|
||||
Ok(record) => record,
|
||||
Err(_) => {
|
||||
stop_started_worker(started).await;
|
||||
let _ = store.abandon_allocation(allocation);
|
||||
if pending_record.is_some() {
|
||||
allocation.into_lease().retain();
|
||||
} else {
|
||||
let _ = store.abandon_allocation(allocation);
|
||||
}
|
||||
return Err(StandaloneStartupError::StateStore);
|
||||
}
|
||||
};
|
||||
@@ -350,7 +420,6 @@ impl StandaloneHost {
|
||||
);
|
||||
let workspace_context = WorkerWorkspaceContext::local_filesystem(None);
|
||||
let runtime_base = store.runtime_dir(worker_id);
|
||||
let bash_output_dir = bash_output_dir_for_worker_id(worker_id);
|
||||
|
||||
let mut bootstrap = WorkerBootstrap::new(
|
||||
manifest,
|
||||
@@ -358,11 +427,7 @@ impl StandaloneHost {
|
||||
worker::PromptCatalogSource::builtins_only(),
|
||||
workspace_context,
|
||||
filesystem_authority,
|
||||
WorkerBootstrapLayout::Direct {
|
||||
runtime_base,
|
||||
bash_output_dir,
|
||||
},
|
||||
WorkerControllerTransport::InProcess,
|
||||
WorkerBootstrapLayout::Direct { runtime_base },
|
||||
);
|
||||
if let Some(subject) = &subject {
|
||||
bootstrap = bootstrap.with_subjektiv_host(subject.host.clone());
|
||||
@@ -427,6 +492,7 @@ impl StandaloneHost {
|
||||
lease: Some(lease),
|
||||
jobs,
|
||||
subject,
|
||||
subject_release: None,
|
||||
}
|
||||
}
|
||||
|
||||
@@ -451,10 +517,75 @@ impl StandaloneHost {
|
||||
/// Working events, committed session entries, alert snapshots, and the
|
||||
/// initial history snapshot are merged behind the client boundary.
|
||||
pub fn connect(&self) -> Client<InProcessSocket> {
|
||||
let streams = subscribe_worker_protocol_session(&self.handle);
|
||||
let (socket, peer) = InProcessSocket::pair();
|
||||
tokio::spawn(run_protocol_session(self.handle.clone(), streams, peer));
|
||||
Client::new(socket)
|
||||
Client::new(connect_protocol(self.handle.clone()))
|
||||
}
|
||||
|
||||
/// Logical Subject disconnection, not Worker shutdown or completion of its represented work.
|
||||
/// A successful release keeps the old Controller fenced; a fresh Worker/Session may then
|
||||
/// acquire the Subject. Failures before durable revocation allow normal recovery and retry.
|
||||
pub async fn disconnect_subject(&mut self) -> Result<(), StandaloneSubjectDisconnectError> {
|
||||
let Some(subject) = &mut self.subject else {
|
||||
return Ok(());
|
||||
};
|
||||
let mut reservation = match self.subject_release.take() {
|
||||
Some(reservation) => reservation,
|
||||
None => self
|
||||
.handle
|
||||
.reserve_subject_release()
|
||||
.await
|
||||
.map_err(StandaloneSubjectDisconnectError::Controller)?,
|
||||
};
|
||||
let release = match subject.release_for_handoff(&self.record, &mut reservation) {
|
||||
Ok(()) => match self.jobs.shutdown().await {
|
||||
Ok(()) => subject.close().map_err(|error| error.to_string()),
|
||||
Err(error) => Err(error.to_string()),
|
||||
},
|
||||
Err(error) => Err(error),
|
||||
};
|
||||
match release {
|
||||
Ok(()) => {
|
||||
self.subject_release = Some(reservation);
|
||||
self.subject = None;
|
||||
Ok(())
|
||||
}
|
||||
Err(error) => {
|
||||
// If revocation committed, keep the actual Controller reserved even if closing
|
||||
// storage/unlocking failed. Dropping a reservation must not undo revocation.
|
||||
if subject.writer_released_or_unknown() {
|
||||
self.subject_release = Some(reservation);
|
||||
}
|
||||
Err(StandaloneSubjectDisconnectError::Incomplete(error))
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Run without a TUI until an admitted protocol Shutdown, controller exit, or process signal.
|
||||
/// Client EOF only disconnects that client. All exits confirm the same production shutdown
|
||||
/// and lease release as the in-process UI; an unconfirmed shutdown retains the lease.
|
||||
pub async fn serve_unix(
|
||||
self,
|
||||
endpoint: crate::unix::UnixEndpoint,
|
||||
) -> Result<(), crate::HeadlessError> {
|
||||
let mut adapter = crate::unix::UnixAdapter::start(endpoint, self.handle.clone());
|
||||
let signal = async {
|
||||
let mut terminate =
|
||||
tokio::signal::unix::signal(tokio::signal::unix::SignalKind::terminate())?;
|
||||
tokio::select! {
|
||||
result = tokio::signal::ctrl_c() => result,
|
||||
_ = terminate.recv() => Ok(()),
|
||||
}
|
||||
};
|
||||
let result = tokio::select! {
|
||||
_ = self.handle.protocol_closed() => Ok(()),
|
||||
result = signal => result,
|
||||
result = adapter.ended() => result,
|
||||
};
|
||||
// Reclaim the public entry and every connection before releasing execution ownership.
|
||||
let transport = adapter.shutdown().await;
|
||||
self.shutdown().await?;
|
||||
result?;
|
||||
transport?;
|
||||
Ok(())
|
||||
}
|
||||
|
||||
pub fn with_shutdown_timeout(mut self, shutdown_timeout: Duration) -> Self {
|
||||
@@ -539,9 +670,8 @@ impl Drop for StandaloneHost {
|
||||
}
|
||||
}
|
||||
|
||||
// The in-process channel is owned by the local operator's Host, not an
|
||||
// arbitrary socket or Backend account. decode_method discards wire provenance;
|
||||
// only this boundary can stamp accepted local human input.
|
||||
// Both in-process views and credential-checked Unix clients are admitted by this operator's
|
||||
// Host. decode_method discards wire provenance; only this boundary stamps local human input.
|
||||
fn authorize_local_input(method: protocol::Method) -> protocol::Method {
|
||||
use protocol::{AuthenticatedInputSource, Method};
|
||||
match method {
|
||||
@@ -584,6 +714,13 @@ fn authorize_local_input(method: protocol::Method) -> protocol::Method {
|
||||
}
|
||||
}
|
||||
|
||||
pub(crate) fn connect_protocol(handle: worker::WorkerHandle) -> InProcessSocket {
|
||||
let streams = subscribe_worker_protocol_session(&handle);
|
||||
let (socket, peer) = InProcessSocket::pair();
|
||||
tokio::spawn(run_protocol_session(handle, streams, peer));
|
||||
socket
|
||||
}
|
||||
|
||||
async fn run_protocol_session(
|
||||
handle: worker::WorkerHandle,
|
||||
streams: WorkerProtocolSessionStreams,
|
||||
@@ -619,6 +756,11 @@ async fn run_protocol_session(
|
||||
event = events.recv() => {
|
||||
match event {
|
||||
Ok(event) => {
|
||||
let Ok(event) = handle.alerter.freshen_event(event) else {
|
||||
// The retained anchor was evicted; reconnect must obtain
|
||||
// a paired session/Alert snapshot rather than a stale row.
|
||||
return;
|
||||
};
|
||||
if !send_protocol_event(&peer, event).await {
|
||||
return;
|
||||
}
|
||||
@@ -690,12 +832,32 @@ async fn send_protocol_event(peer: &InProcessPeer, event: Event) -> bool {
|
||||
peer.send(message).await.is_ok()
|
||||
}
|
||||
|
||||
fn cancel_unpublished_start(
|
||||
store: &StandaloneWorkerStore,
|
||||
subject: &mut Option<crate::subjektiv::SubjectConnection>,
|
||||
allocation: crate::store::StandaloneWorkerAllocation,
|
||||
) -> Result<(), StandaloneStartupError> {
|
||||
if let Some(connection) = subject {
|
||||
if connection.abort_unpublished_start().is_err() {
|
||||
connection.retain();
|
||||
allocation.into_lease().retain();
|
||||
return Err(StandaloneStartupError::StateStore);
|
||||
}
|
||||
}
|
||||
store
|
||||
.abandon_allocation(allocation)
|
||||
.map_err(classify_store_startup_error)
|
||||
}
|
||||
|
||||
fn backing_store(
|
||||
store: &StandaloneWorkerStore,
|
||||
worker_id: WorkerId,
|
||||
) -> Result<(StandaloneBackingStore, FsWorkerStore), StandaloneStartupError> {
|
||||
let session_store = FsStore::new(store.sessions_dir(worker_id))
|
||||
.map_err(|_| StandaloneStartupError::StateStore)?;
|
||||
let session_store = FsStore::new_with_retention(
|
||||
store.sessions_dir(worker_id),
|
||||
crate::store::session_retention(store.root()),
|
||||
)
|
||||
.map_err(|_| StandaloneStartupError::StateStore)?;
|
||||
let worker_store = FsWorkerStore::new(store.worker_metadata_dir(worker_id))
|
||||
.map_err(|_| StandaloneStartupError::StateStore)?;
|
||||
Ok((
|
||||
@@ -808,3 +970,51 @@ mod local_input_tests {
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod source_retention_tests {
|
||||
//! Host backing-store assembly uses the production publisher and an isolated external
|
||||
//! erasure fence. No controller/model is substituted for the source authority under test.
|
||||
use super::*;
|
||||
use session_store::{LogEntry, Store, StoreError};
|
||||
|
||||
#[test]
|
||||
fn backing_publisher_and_reopen_use_the_host_wide_erasure_fence() {
|
||||
let temp = tempfile::tempdir().unwrap();
|
||||
let workers = StandaloneWorkerStore::open(temp.path().join("state")).unwrap();
|
||||
let allocation = workers
|
||||
.allocate(temp.path(), StaleLeasePolicy::Reject)
|
||||
.unwrap();
|
||||
let worker = allocation.worker_id();
|
||||
let (backing, _) = backing_store(&workers, worker).unwrap();
|
||||
let session = session_store::SessionId::now_v7();
|
||||
let segment = uuid::Uuid::now_v7();
|
||||
let entry = LogEntry::TurnEnd {
|
||||
ts: 1,
|
||||
turn_count: 1,
|
||||
};
|
||||
backing
|
||||
.create_segment(session, segment, &[entry.clone()])
|
||||
.unwrap();
|
||||
let retention = crate::store::session_retention(workers.root());
|
||||
assert!(
|
||||
retention
|
||||
.delete(
|
||||
session,
|
||||
session_store::retention::SessionDeletionIntent::ErasePermanently,
|
||||
|| Err::<(), StoreError>(
|
||||
std::io::Error::other("injected physical erase failure").into()
|
||||
)
|
||||
)
|
||||
.is_err()
|
||||
);
|
||||
assert!(
|
||||
matches!(backing.append(session, segment, &entry), Err(StoreError::SessionErased(id)) if id == session)
|
||||
);
|
||||
let (reopened, _) = backing_store(&workers, worker).unwrap();
|
||||
assert!(
|
||||
matches!(reopened.append(session, segment, &entry), Err(StoreError::SessionErased(id)) if id == session)
|
||||
);
|
||||
assert!(!workers.sessions_dir(worker).join(".retention").exists());
|
||||
}
|
||||
}
|
||||
|
||||
@@ -25,7 +25,7 @@ use thiserror::Error;
|
||||
#[path = "job_store/legacy_migrations.rs"]
|
||||
mod legacy_migrations;
|
||||
|
||||
const SCHEMA_VERSION: i64 = 3;
|
||||
const SCHEMA_VERSION: i64 = 4;
|
||||
|
||||
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(rename_all = "snake_case")]
|
||||
@@ -189,6 +189,7 @@ impl JobStore {
|
||||
0 => {
|
||||
tx.execute_batch(SCHEMA)?;
|
||||
tx.execute_batch(GRANT_SCHEMA)?;
|
||||
tx.execute_batch(RECONCILIATION_SCHEMA)?;
|
||||
tx.pragma_update(None, "user_version", SCHEMA_VERSION)?;
|
||||
}
|
||||
1 | 2 => {
|
||||
@@ -196,6 +197,11 @@ impl JobStore {
|
||||
tx.execute_batch(GRANT_SCHEMA)?;
|
||||
}
|
||||
legacy_migrations::migrate_legacy_jobs(&tx)?;
|
||||
tx.execute_batch(RECONCILIATION_SCHEMA)?;
|
||||
tx.pragma_update(None, "user_version", SCHEMA_VERSION)?;
|
||||
}
|
||||
3 => {
|
||||
tx.execute_batch(RECONCILIATION_SCHEMA)?;
|
||||
tx.pragma_update(None, "user_version", SCHEMA_VERSION)?;
|
||||
}
|
||||
SCHEMA_VERSION => {}
|
||||
@@ -278,6 +284,49 @@ impl JobStore {
|
||||
Ok(snapshot)
|
||||
}
|
||||
|
||||
/// Domain Host attests that this fenced attempt's only effects are reconciled in its
|
||||
/// authoritative durable consumer. This releases serialization, not the original Unknown
|
||||
/// history, and cannot authorize retry or change its result. The service checks cleanup.
|
||||
pub(crate) fn reconcile_granted_attempt(
|
||||
&mut self,
|
||||
job_id: &str,
|
||||
attempt_id: &str,
|
||||
domain_receipt: &str,
|
||||
) -> Result<(), JobStoreError> {
|
||||
if domain_receipt.is_empty()
|
||||
|| domain_receipt.len() > 256
|
||||
|| domain_receipt.chars().any(char::is_control)
|
||||
{
|
||||
return Err(JobStoreError::InvalidTransition(
|
||||
"invalid domain reconciliation receipt",
|
||||
));
|
||||
}
|
||||
let tx = self
|
||||
.conn
|
||||
.transaction_with_behavior(TransactionBehavior::Immediate)?;
|
||||
let snapshot = require_snapshot(&tx, job_id)?;
|
||||
check_attempt(&snapshot, attempt_id)?;
|
||||
if snapshot.domain_grant.is_none()
|
||||
|| snapshot.attempt.state != JobAttemptState::Unknown
|
||||
|| !matches!(snapshot.state, JobState::Unknown | JobState::Cancelled)
|
||||
{
|
||||
return Err(JobStoreError::InvalidTransition(
|
||||
"domain reconciliation requires a fenced unknown granted attempt",
|
||||
));
|
||||
}
|
||||
let old: Option<String> = tx.query_row("SELECT domain_receipt FROM job_domain_reconciliations WHERE job_id=?1 AND attempt_id=?2",
|
||||
params![job_id,attempt_id], |row| row.get(0)).optional()?;
|
||||
if old.as_deref().is_some_and(|old| old != domain_receipt) {
|
||||
return Err(JobStoreError::InvalidTransition(
|
||||
"domain reconciliation receipt changed",
|
||||
));
|
||||
}
|
||||
tx.execute("INSERT OR IGNORE INTO job_domain_reconciliations(job_id,attempt_id,domain_receipt) VALUES(?1,?2,?3)",
|
||||
params![job_id,attempt_id,domain_receipt])?;
|
||||
tx.commit()?;
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Only definitive failure can create a new immutable attempt. Unknown
|
||||
/// outcomes require caller reconciliation, never an automatic replay.
|
||||
pub(crate) fn retry(&mut self, job_id: &str) -> Result<JobSnapshot, JobStoreError> {
|
||||
@@ -319,6 +368,16 @@ impl JobStore {
|
||||
.collect()
|
||||
}
|
||||
|
||||
pub(crate) fn unknown_granted(&self) -> Result<Vec<JobSnapshot>, JobStoreError> {
|
||||
let mut statement = self.conn.prepare("SELECT i.job_id FROM job_intents i JOIN job_attempts a ON a.job_id=i.job_id AND a.number=i.current_attempt JOIN job_domain_grants g ON g.job_id=i.job_id WHERE a.state='unknown' AND NOT EXISTS (SELECT 1 FROM job_domain_reconciliations r WHERE r.job_id=a.job_id AND r.attempt_id=a.attempt_id) ORDER BY i.rowid")?;
|
||||
let ids = statement
|
||||
.query_map([], |row| row.get::<_, String>(0))?
|
||||
.collect::<rusqlite::Result<Vec<_>>>()?;
|
||||
ids.into_iter()
|
||||
.map(|id| require_snapshot(&self.conn, &id))
|
||||
.collect()
|
||||
}
|
||||
|
||||
/// Only unstarted current attempts are eligible for service startup/resume.
|
||||
pub(crate) fn pending(&self) -> Result<Vec<JobSnapshot>, JobStoreError> {
|
||||
let mut statement = self.conn.prepare(
|
||||
@@ -527,8 +586,10 @@ fn check_serialization(
|
||||
if let Some(key) = key {
|
||||
let conflicting: bool = conn.query_row(
|
||||
"SELECT EXISTS(SELECT 1 FROM job_intents i WHERE serialization_key = ?1
|
||||
AND job_id <> ?2 AND (state IN ('pending', 'unknown') OR EXISTS
|
||||
(SELECT 1 FROM job_attempts a WHERE a.job_id = i.job_id AND a.state = 'unknown')))",
|
||||
AND job_id <> ?2 AND (state = 'pending' OR EXISTS
|
||||
(SELECT 1 FROM job_attempts a WHERE a.job_id = i.job_id AND a.state = 'unknown'
|
||||
AND NOT EXISTS (SELECT 1 FROM job_domain_reconciliations r
|
||||
WHERE r.job_id=a.job_id AND r.attempt_id=a.attempt_id))))",
|
||||
params![key, job_id],
|
||||
|row| row.get(0),
|
||||
)?;
|
||||
@@ -658,6 +719,22 @@ fn read_snapshot(conn: &Connection, job_id: &str) -> Result<Option<JobSnapshot>,
|
||||
.transpose()
|
||||
}
|
||||
|
||||
const RECONCILIATION_SCHEMA: &str = "
|
||||
DROP INDEX job_serialization_singleflight;
|
||||
CREATE UNIQUE INDEX job_serialization_singleflight ON job_intents(serialization_key)
|
||||
WHERE serialization_key IS NOT NULL AND state = 'pending';
|
||||
CREATE TABLE job_domain_reconciliations (
|
||||
job_id TEXT NOT NULL REFERENCES job_intents(job_id),
|
||||
attempt_id TEXT NOT NULL,
|
||||
domain_receipt TEXT NOT NULL,
|
||||
PRIMARY KEY (job_id, attempt_id)
|
||||
);
|
||||
CREATE TRIGGER job_reconciliation_immutable BEFORE UPDATE ON job_domain_reconciliations
|
||||
BEGIN SELECT RAISE(ABORT, 'immutable domain reconciliation'); END;
|
||||
CREATE TRIGGER job_reconciliation_retained BEFORE DELETE ON job_domain_reconciliations
|
||||
BEGIN SELECT RAISE(ABORT, 'retained domain reconciliation'); END;
|
||||
";
|
||||
|
||||
const GRANT_SCHEMA: &str = "
|
||||
CREATE TABLE job_domain_grants (
|
||||
job_id TEXT PRIMARY KEY NOT NULL REFERENCES job_intents(job_id),
|
||||
@@ -732,6 +809,98 @@ mod tests {
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn granted_unknown_reconciliation_releases_serialization_but_preserves_history() {
|
||||
let (dir, mut store) = fixture();
|
||||
let mut first = request("first");
|
||||
first.serialization_key = Some("journal".into());
|
||||
let reserved = store
|
||||
.reserve_granted(first, Some(json!({"domain":"journal"})))
|
||||
.unwrap();
|
||||
store
|
||||
.dispatch("first", &reserved.attempt.attempt_id, 8)
|
||||
.unwrap();
|
||||
let unknown = store
|
||||
.finish(
|
||||
"first",
|
||||
&reserved.attempt.attempt_id,
|
||||
JobAttemptState::Unknown,
|
||||
Some("response lost"),
|
||||
)
|
||||
.unwrap();
|
||||
let mut second = request("second");
|
||||
second.serialization_key = Some("journal".into());
|
||||
assert!(matches!(
|
||||
store.reserve(second.clone()),
|
||||
Err(JobStoreError::SerializationConflict(_))
|
||||
));
|
||||
assert!(
|
||||
store
|
||||
.reconcile_granted_attempt("first", "foreign-attempt", "domain-fenced")
|
||||
.is_err()
|
||||
);
|
||||
store
|
||||
.reconcile_granted_attempt("first", &unknown.attempt.attempt_id, "domain-fenced")
|
||||
.unwrap();
|
||||
store
|
||||
.reconcile_granted_attempt("first", &unknown.attempt.attempt_id, "domain-fenced")
|
||||
.unwrap();
|
||||
assert!(
|
||||
store
|
||||
.reconcile_granted_attempt("first", &unknown.attempt.attempt_id, "different-proof")
|
||||
.is_err()
|
||||
);
|
||||
assert_eq!(store.get("first").unwrap(), unknown);
|
||||
store.reserve(second).unwrap();
|
||||
assert!(store.retry("first").is_err());
|
||||
drop(store);
|
||||
let mut reopened = JobStore::open(&dir.path().join("jobs.sqlite3")).unwrap();
|
||||
assert_eq!(reopened.get("first").unwrap(), unknown);
|
||||
assert!(reopened.unknown_granted().unwrap().is_empty());
|
||||
assert!(
|
||||
reopened
|
||||
.conn
|
||||
.execute("DELETE FROM job_domain_reconciliations", [])
|
||||
.is_err()
|
||||
);
|
||||
assert!(reopened.retry("first").is_err());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn schema_three_migration_preserves_unknown_grant_and_its_serialization_fence() {
|
||||
let (dir, mut store) = fixture();
|
||||
let mut first = request("first");
|
||||
first.serialization_key = Some("journal".into());
|
||||
let reserved = store
|
||||
.reserve_granted(first, Some(json!({"domain":"journal"})))
|
||||
.unwrap();
|
||||
store
|
||||
.dispatch("first", &reserved.attempt.attempt_id, 8)
|
||||
.unwrap();
|
||||
let unknown = store
|
||||
.finish(
|
||||
"first",
|
||||
&reserved.attempt.attempt_id,
|
||||
JobAttemptState::Unknown,
|
||||
Some("unconfirmed"),
|
||||
)
|
||||
.unwrap();
|
||||
store.conn.execute_batch("DROP TRIGGER job_reconciliation_immutable; DROP TRIGGER job_reconciliation_retained; DROP TABLE job_domain_reconciliations; DROP INDEX job_serialization_singleflight; CREATE UNIQUE INDEX job_serialization_singleflight ON job_intents(serialization_key) WHERE serialization_key IS NOT NULL AND state IN ('pending','unknown'); PRAGMA user_version=3;").unwrap();
|
||||
drop(store);
|
||||
let mut reopened = JobStore::open(&dir.path().join("jobs.sqlite3")).unwrap();
|
||||
assert_eq!(reopened.get("first").unwrap(), unknown);
|
||||
let mut next = request("next");
|
||||
next.serialization_key = Some("journal".into());
|
||||
assert!(matches!(
|
||||
reopened.reserve(next.clone()),
|
||||
Err(JobStoreError::SerializationConflict(_))
|
||||
));
|
||||
reopened
|
||||
.reconcile_granted_attempt("first", &unknown.attempt.attempt_id, "domain-fenced")
|
||||
.unwrap();
|
||||
reopened.reserve(next).unwrap();
|
||||
}
|
||||
|
||||
fn fixture() -> (TempDir, JobStore) {
|
||||
let dir = tempfile::tempdir().unwrap();
|
||||
let store = JobStore::open(&dir.path().join("jobs.sqlite3")).unwrap();
|
||||
|
||||
@@ -66,6 +66,15 @@ struct Executions {
|
||||
jobs: HashMap<String, Execution>,
|
||||
}
|
||||
|
||||
pub(crate) struct QuiescentJobClosure<'a> {
|
||||
executions: std::sync::MutexGuard<'a, Executions>,
|
||||
}
|
||||
impl QuiescentJobClosure<'_> {
|
||||
pub(crate) fn commit(&mut self) {
|
||||
self.executions.closed = true;
|
||||
}
|
||||
}
|
||||
|
||||
/// Cloneable Feature-facing access to a Host-owned service. Cloning this handle
|
||||
/// neither extends the Host's authority nor permits opening/recovering its store.
|
||||
#[derive(Clone)]
|
||||
@@ -79,6 +88,27 @@ pub struct StandaloneJobs {
|
||||
}
|
||||
|
||||
impl StandaloneJobs {
|
||||
/// Excludes request/start/result acknowledgement while a Subject Host checks its final
|
||||
/// saved obligations and releases ownership. Accepted results alone are insufficient:
|
||||
/// every spawned execution must have actually finished successful cleanup.
|
||||
pub(crate) fn reserve_quiescent_closure(
|
||||
&self,
|
||||
) -> Result<QuiescentJobClosure<'_>, JobServiceError> {
|
||||
let executions = self.executions.lock().expect("Job executions poisoned");
|
||||
if executions.closed {
|
||||
return Err(JobServiceError::Closed);
|
||||
}
|
||||
if executions.jobs.values().any(|execution| {
|
||||
!execution.task.is_finished()
|
||||
|| !matches!(execution.complete.borrow().as_ref(), Some(Ok(())))
|
||||
}) {
|
||||
return Err(JobServiceError::Cleanup(
|
||||
"delegated Job execution/cleanup remains running or unconfirmed".into(),
|
||||
));
|
||||
}
|
||||
Ok(QuiescentJobClosure { executions })
|
||||
}
|
||||
|
||||
pub(crate) fn open(path: &Path, cwd: PathBuf) -> Result<Self, JobServiceError> {
|
||||
Ok(Self {
|
||||
store: Arc::new(Mutex::new(Some(JobStore::open(path)?))),
|
||||
@@ -157,6 +187,30 @@ impl StandaloneJobs {
|
||||
self.with_store(|store| store.unacknowledged())
|
||||
}
|
||||
|
||||
pub(crate) fn unknown_granted(&self) -> Result<Vec<JobSnapshot>, JobServiceError> {
|
||||
self.with_store(|store| store.unknown_granted())
|
||||
}
|
||||
|
||||
/// Release only an Unknown attempt's serialization reservation after the bound domain
|
||||
/// has reconciled its receipts and durably fenced further effects. Never a generic retry.
|
||||
pub(crate) fn reconcile_granted_attempt(
|
||||
&self,
|
||||
job_id: &str,
|
||||
attempt_id: &str,
|
||||
domain_receipt: &str,
|
||||
) -> Result<(), JobServiceError> {
|
||||
let executions = self.executions.lock().expect("Job executions poisoned");
|
||||
if executions.closed {
|
||||
return Err(JobServiceError::Closed);
|
||||
}
|
||||
if executions.jobs.contains_key(job_id) {
|
||||
return Err(JobServiceError::Cleanup(
|
||||
"domain reconciliation requires observed execution cleanup".into(),
|
||||
));
|
||||
}
|
||||
self.with_store(|store| store.reconcile_granted_attempt(job_id, attempt_id, domain_receipt))
|
||||
}
|
||||
|
||||
/// Explicit new attempt, bounded by immutable intent limits. Unknown
|
||||
/// outcomes cannot be retried without domain reconciliation/new intent.
|
||||
pub fn retry(&self, job_id: &str) -> Result<JobSnapshot, JobServiceError> {
|
||||
|
||||
@@ -7,8 +7,49 @@ pub mod launch;
|
||||
pub mod store;
|
||||
pub mod subjektiv;
|
||||
mod subjektiv_sessions;
|
||||
pub mod unix;
|
||||
|
||||
pub use host::{StandaloneHost, StandaloneShutdownError, StandaloneStartupError};
|
||||
pub use unix::{UnixEndpoint, relay_unix_client, run_unix_client};
|
||||
|
||||
/// Restore reads the saved cwd and Profile, not a newly resolved launch recipe.
|
||||
pub enum HeadlessLaunch {
|
||||
Fresh(ResolvedStandaloneLaunch),
|
||||
Restore {
|
||||
state_dir: std::path::PathBuf,
|
||||
worker_id: WorkerId,
|
||||
},
|
||||
}
|
||||
|
||||
#[derive(Debug, thiserror::Error)]
|
||||
pub enum HeadlessError {
|
||||
#[error(transparent)]
|
||||
Transport(#[from] std::io::Error),
|
||||
#[error(transparent)]
|
||||
Startup(#[from] StandaloneStartupError),
|
||||
#[error(transparent)]
|
||||
Shutdown(#[from] StandaloneShutdownError),
|
||||
}
|
||||
|
||||
/// Reserve the optional public transport before creating or restoring execution state.
|
||||
pub async fn run_headless(
|
||||
launch: HeadlessLaunch,
|
||||
endpoint: std::path::PathBuf,
|
||||
) -> Result<(), HeadlessError> {
|
||||
let endpoint = UnixEndpoint::bind(endpoint)?;
|
||||
let host = match launch {
|
||||
HeadlessLaunch::Fresh(launch) => StandaloneHost::start(launch).await?,
|
||||
HeadlessLaunch::Restore {
|
||||
state_dir,
|
||||
worker_id,
|
||||
} => StandaloneHost::restore(state_dir, worker_id).await?,
|
||||
};
|
||||
host.serve_unix(endpoint).await
|
||||
}
|
||||
|
||||
pub use host::{
|
||||
StandaloneHost, StandaloneShutdownError, StandaloneStartupError,
|
||||
StandaloneSubjectDisconnectError,
|
||||
};
|
||||
pub use launch::{ResolvedStandaloneLaunch, StandaloneLaunchConfig, StandaloneLaunchError};
|
||||
pub use protocol::WorkerId;
|
||||
pub use store::{
|
||||
|
||||
@@ -119,6 +119,16 @@ pub enum StaleLeasePolicy {
|
||||
Recover,
|
||||
}
|
||||
|
||||
/// Source control outlives Worker relocation and physical Session pruning. Always derive this
|
||||
/// from the Host state root, never from an individual live or retained Worker directory.
|
||||
pub(crate) fn session_retention(
|
||||
state_root: &Path,
|
||||
) -> session_store::retention::SessionRetentionStore {
|
||||
session_store::retention::SessionRetentionStore::new(
|
||||
state_root.join("retention/session-sources"),
|
||||
)
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone)]
|
||||
pub struct StandaloneWorkerStore {
|
||||
root: PathBuf,
|
||||
@@ -359,7 +369,19 @@ impl StandaloneWorkerStore {
|
||||
}
|
||||
|
||||
pub fn delete(&self, id: WorkerId) -> Result<(), StandaloneStoreError> {
|
||||
let record = self.load(id)?;
|
||||
let record = match self.load(id) {
|
||||
Err(StandaloneStoreError::WorkerNotFound(_)) => {
|
||||
let retained_root = self.root.join("subjektiv").join("retained-workers");
|
||||
let retained =
|
||||
Self::open_existing(retained_root).and_then(|store| store.load(id))?;
|
||||
if retained.status == StandaloneWorkerStatus::Stopped && retained.subject.is_some()
|
||||
{
|
||||
return Ok(());
|
||||
}
|
||||
return Err(StandaloneStoreError::InvalidRecord(id));
|
||||
}
|
||||
result => result?,
|
||||
};
|
||||
if record.status != StandaloneWorkerStatus::Stopped {
|
||||
return Err(StandaloneStoreError::DeleteActive(id));
|
||||
}
|
||||
@@ -374,6 +396,7 @@ impl StandaloneWorkerStore {
|
||||
LeaseLiveness::Unknown => StandaloneStoreError::LeaseLivenessUnknown(id),
|
||||
});
|
||||
}
|
||||
crate::subjektiv::prepare_worker_deletion(&self.root, &record)?;
|
||||
fs::remove_dir_all(self.worker_dir(id)).map_err(StandaloneStoreError::Io)?;
|
||||
sync_directory(&self.root)
|
||||
}
|
||||
@@ -793,6 +816,8 @@ pub enum StandaloneStoreError {
|
||||
LeaseOwnershipLost,
|
||||
#[error("standalone Worker {0} must be stopped before deletion")]
|
||||
DeleteActive(WorkerId),
|
||||
#[error("Journal deletion handoff/retention is unconfirmed: {0}")]
|
||||
JournalRetention(String),
|
||||
#[error("standalone Worker {0} metadata changed since it was read")]
|
||||
MetadataChanged(WorkerId),
|
||||
#[error("system clock is before the Unix epoch or out of range")]
|
||||
|
||||
@@ -5,9 +5,11 @@
|
||||
//! non-private nodes; delegates schema/migration to `subjektiv` and connection policy to `feature-storage`.
|
||||
//!
|
||||
//! The Host holds each selected Subject's exclusive kernel lease through body execution and
|
||||
//! confirmed delegated Job cleanup. Process death releases kernel locks; uncertain in-process
|
||||
//! cleanup retains leases. Restore validates saved Subject/storage bindings and reacquires the
|
||||
//! same Subject. Launches without a selected Subject do not implicitly connect this store.
|
||||
//! confirmed delegated Job cleanup. Kernel lock release never clears durable body ownership:
|
||||
//! shutdown/process death permits only the same body to restore, not a replacement to start.
|
||||
//! Explicit disconnection requires actual Controller quiescence and final Journal completion;
|
||||
//! storage then revokes that writer lifetime before the lease is released. Uncertain cleanup
|
||||
//! retains leases. Launches without a selected Subject do not implicitly connect this store.
|
||||
//!
|
||||
//! The selected Subject's Job store is shared across Workers; the generic Jobs service owns execution
|
||||
//! and cleanup. Consolidation grants allow only immutable candidate batches and limited operations,
|
||||
@@ -15,6 +17,9 @@
|
||||
//! Unknown attempts are not rerun; delivery failures for accepted results do not trigger model
|
||||
//! reexecution. Memory application and surface repair use shared-domain CAS/receipts.
|
||||
|
||||
mod journal;
|
||||
pub(crate) use journal::prepare_worker_deletion;
|
||||
|
||||
use std::fs::{self, File, OpenOptions};
|
||||
use std::io::Write;
|
||||
use std::path::{Path, PathBuf};
|
||||
@@ -46,6 +51,8 @@ pub enum SubjectError {
|
||||
#[error(transparent)]
|
||||
Domain(#[from] subjektiv::SubjektivError),
|
||||
#[error(transparent)]
|
||||
Journal(#[from] subjektiv::journal::JournalError),
|
||||
#[error(transparent)]
|
||||
Storage(#[from] feature_storage::FeatureStorageError),
|
||||
#[error("local Subject storage metadata: {0}")]
|
||||
Json(#[from] serde_json::Error),
|
||||
@@ -220,7 +227,51 @@ impl StandaloneSubjects {
|
||||
scope_id: self.scope_id.clone(),
|
||||
subject_id: subject_id.to_string(),
|
||||
};
|
||||
let host = Arc::new(LocalSubjectHost {
|
||||
if self.store.journal_worker_was_released(
|
||||
subject_id,
|
||||
&self.scope_id,
|
||||
&worker_id.to_string(),
|
||||
)? {
|
||||
return Err(SubjectError::InvalidScope("this body's Subject binding was released; start a new Worker/Session rather than restore its old authority".into()));
|
||||
}
|
||||
// Before writer lifetimes existed, a saved body record was the only durable
|
||||
// attachment evidence. Never interpret its stopped status as a release on upgrade.
|
||||
let workers = crate::store::StandaloneWorkerStore::open_existing(&self.state_root)
|
||||
.map_err(|error| SubjectError::InvalidScope(error.to_string()))?;
|
||||
for entry in fs::read_dir(&self.state_root)? {
|
||||
let entry = entry?;
|
||||
let Ok(prior_id) = entry
|
||||
.file_name()
|
||||
.to_string_lossy()
|
||||
.parse::<protocol::WorkerId>()
|
||||
else {
|
||||
continue;
|
||||
};
|
||||
if prior_id == worker_id {
|
||||
continue;
|
||||
}
|
||||
let prior = match workers.load(prior_id) {
|
||||
Ok(prior) => prior,
|
||||
Err(crate::store::StandaloneStoreError::WorkerNotFound(_)) => continue,
|
||||
Err(error) => return Err(SubjectError::InvalidScope(error.to_string())),
|
||||
};
|
||||
if prior.subject.as_ref() == Some(&binding)
|
||||
&& !self.store.journal_worker_was_released(
|
||||
subject_id,
|
||||
&self.scope_id,
|
||||
&prior_id.to_string(),
|
||||
)?
|
||||
{
|
||||
return Err(SubjectError::InvalidScope("saved Subject body has no explicit release; restore it and complete the Idle/Journal handoff, rather than treating inactive storage as unoccupied".into()));
|
||||
}
|
||||
}
|
||||
let writer =
|
||||
self.store
|
||||
.claim_journal_writer(subject_id, &self.scope_id, &worker_id.to_string())?;
|
||||
let host = Arc::new_cyclic(|weak| LocalSubjectHost {
|
||||
writer,
|
||||
self_weak: weak.clone(),
|
||||
journal_dispatch: Mutex::new(false),
|
||||
language: self.memory_language.clone(),
|
||||
catalog: self,
|
||||
binding: binding.clone(),
|
||||
@@ -247,6 +298,37 @@ pub(crate) struct SubjectConnection {
|
||||
armed: bool,
|
||||
}
|
||||
impl SubjectConnection {
|
||||
/// Construction failed before any Controller or mandatory startup context was published.
|
||||
/// This is cancellation of an unpublished reservation, not Idle inferred from a stopped body.
|
||||
pub(crate) fn abort_unpublished_start(&mut self) -> Result<(), SubjectError> {
|
||||
self.host
|
||||
.catalog
|
||||
.store
|
||||
.release_journal_writer(&self.host.writer)?;
|
||||
self.close()
|
||||
}
|
||||
|
||||
pub(crate) fn writer_released_or_unknown(&self) -> bool {
|
||||
self.host
|
||||
.catalog
|
||||
.store
|
||||
.journal_writer_active(&self.host.writer)
|
||||
.map(|active| !active)
|
||||
.unwrap_or(true)
|
||||
}
|
||||
|
||||
pub(crate) fn release_for_handoff(
|
||||
&mut self,
|
||||
record: &crate::store::StandaloneWorkerRecord,
|
||||
reservation: &mut worker::SubjectReleaseReservation,
|
||||
) -> Result<(), String> {
|
||||
if let Err(error) = self.host.release_for_handoff(record, reservation) {
|
||||
self.host.wake_journals();
|
||||
return Err(error.to_string());
|
||||
}
|
||||
reservation.commit_disconnect()
|
||||
}
|
||||
|
||||
pub fn arm(&mut self) {
|
||||
self.armed = true;
|
||||
}
|
||||
@@ -277,6 +359,9 @@ impl Drop for SubjectConnection {
|
||||
}
|
||||
|
||||
pub(crate) struct LocalSubjectHost {
|
||||
writer: subjektiv::journal::JournalWriterBinding,
|
||||
self_weak: std::sync::Weak<Self>,
|
||||
journal_dispatch: Mutex<bool>,
|
||||
catalog: StandaloneSubjects,
|
||||
binding: StandaloneSubjectBinding,
|
||||
worker_id: protocol::WorkerId,
|
||||
@@ -293,6 +378,16 @@ impl LocalSubjectHost {
|
||||
"local Subject Host is closed".into(),
|
||||
));
|
||||
}
|
||||
if !self
|
||||
.catalog
|
||||
.store
|
||||
.journal_writer_active(&self.writer)
|
||||
.map_err(journal::journal_error)?
|
||||
{
|
||||
return Err(SubjektivHostError::Unavailable(
|
||||
"Subject writer binding was released".into(),
|
||||
));
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
fn body(&self, context: &SubjektivHostContext) -> Result<(), SubjektivHostError> {
|
||||
@@ -332,6 +427,9 @@ impl LocalSubjectHost {
|
||||
"Session does not belong to this local Subject/Worker scope".into(),
|
||||
));
|
||||
}
|
||||
store
|
||||
.bind_journal_session(&self.writer, record.clone())
|
||||
.map_err(journal::journal_error)?;
|
||||
return Ok(record);
|
||||
}
|
||||
if !create {
|
||||
@@ -348,9 +446,13 @@ impl LocalSubjectHost {
|
||||
&context.session_id,
|
||||
)
|
||||
.map_err(domain_error)?;
|
||||
store
|
||||
let record = store
|
||||
.record_session_attribution(record)
|
||||
.map_err(domain_error)
|
||||
.map_err(domain_error)?;
|
||||
store
|
||||
.bind_journal_session(&self.writer, record.clone())
|
||||
.map_err(journal::journal_error)?;
|
||||
Ok(record)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -551,10 +653,11 @@ impl LocalSubjectHost {
|
||||
.and_then(|v| serde_json::from_value::<LocalConsolidationGrant>(v.clone()).ok())
|
||||
.is_some_and(|g| g.binding == self.binding)
|
||||
{
|
||||
schedule_job(jobs.clone(), job.request.job_id);
|
||||
schedule_job(jobs.clone(), job.request.job_id, self.self_weak.clone());
|
||||
}
|
||||
}
|
||||
}
|
||||
self.recover_journals();
|
||||
}
|
||||
fn validate_evidence(
|
||||
&self,
|
||||
@@ -690,6 +793,107 @@ impl LocalSubjectHost {
|
||||
}
|
||||
}
|
||||
impl SubjektivHost for LocalSubjectHost {
|
||||
fn memory_journal(
|
||||
&self,
|
||||
context: &SubjektivHostContext,
|
||||
request: subjektiv::journal::memory_links::MemoryJournalRequest,
|
||||
) -> Result<subjektiv::journal::memory_links::MemoryJournalResponse, SubjektivHostError> {
|
||||
self.body(context)?;
|
||||
let reader = subjektiv::journal::JournalHostContext::validated_reader(
|
||||
&self.catalog.store,
|
||||
&self.binding.subject_id,
|
||||
)
|
||||
.map_err(journal::journal_error)?;
|
||||
self.catalog
|
||||
.store
|
||||
.execute_memory_journal_with_source_presence(&reader, request, |session| {
|
||||
crate::subjektiv_sessions::original_session_presence(
|
||||
&self.catalog.state_root,
|
||||
&self.binding.scope_id,
|
||||
&self.binding.subject_id,
|
||||
&self.catalog.store,
|
||||
session,
|
||||
)
|
||||
})
|
||||
.map_err(journal::journal_error)
|
||||
}
|
||||
fn journal_startup_granted(&self) -> bool {
|
||||
self.live.load(Ordering::Acquire)
|
||||
}
|
||||
fn journal_startup_context(
|
||||
&self,
|
||||
context: &SubjektivHostContext,
|
||||
) -> Result<subjektiv::journal::startup::JournalStartupSnapshot, SubjektivHostError> {
|
||||
self.body(context)?;
|
||||
let reader = subjektiv::journal::JournalHostContext::validated_reader(
|
||||
&self.catalog.store,
|
||||
&self.binding.subject_id,
|
||||
)
|
||||
.map_err(journal::journal_error)?;
|
||||
let predecessor = self
|
||||
.catalog
|
||||
.store
|
||||
.journal_predecessor_session(&self.writer)
|
||||
.map_err(journal::journal_error)?;
|
||||
self.catalog
|
||||
.store
|
||||
.journal_startup_snapshot(&reader, predecessor.as_deref())
|
||||
.map_err(journal::journal_error)
|
||||
}
|
||||
fn journal_compaction_granted(&self) -> bool {
|
||||
self.live.load(Ordering::Acquire)
|
||||
}
|
||||
fn journal_compaction_context(
|
||||
&self,
|
||||
context: &SubjektivHostContext,
|
||||
) -> Result<subjektiv::journal::startup::JournalStartupSnapshot, SubjektivHostError> {
|
||||
self.body(context)?;
|
||||
let attribution = self
|
||||
.catalog
|
||||
.store
|
||||
.session_attribution(&context.session_id)
|
||||
.map_err(domain_error)?
|
||||
.filter(|attr| {
|
||||
attr.subject_id == self.binding.subject_id
|
||||
&& attr.runtime_id == self.binding.scope_id
|
||||
&& attr.worker_id == self.worker_id.to_string()
|
||||
})
|
||||
.ok_or_else(|| {
|
||||
SubjektivHostError::InvalidArgument(
|
||||
"foreign or unattributed compaction Session".into(),
|
||||
)
|
||||
})?;
|
||||
let host = subjektiv::journal::JournalHostContext::validated_session(
|
||||
&self.catalog.store,
|
||||
attribution,
|
||||
)
|
||||
.map_err(journal::journal_error)?;
|
||||
if host.writer_binding_id() != Some(self.writer.binding_id.as_str()) {
|
||||
return Err(SubjektivHostError::InvalidArgument(
|
||||
"compaction writer lifetime mismatch".into(),
|
||||
));
|
||||
}
|
||||
self.catalog
|
||||
.store
|
||||
.journal_compaction_snapshot(&host)
|
||||
.map_err(journal::journal_error)
|
||||
}
|
||||
fn journal_recording_granted(&self) -> bool {
|
||||
self.live.load(Ordering::Acquire)
|
||||
}
|
||||
fn request_journal_recording(
|
||||
&self,
|
||||
context: &SubjektivHostContext,
|
||||
_reason: subjektiv::journal::transport::JournalRecordingReason,
|
||||
) -> Result<subjektiv::journal::transport::JournalRecordingResponse, SubjektivHostError> {
|
||||
let admitted = self.admit_journal(context)?;
|
||||
self.wake_journals();
|
||||
Ok(if admitted {
|
||||
subjektiv::journal::transport::JournalRecordingResponse::Accepted
|
||||
} else {
|
||||
subjektiv::journal::transport::JournalRecordingResponse::NoNewSources
|
||||
})
|
||||
}
|
||||
fn settings(&self) -> SubjektivHostSettings {
|
||||
SubjektivHostSettings {
|
||||
language: self.language.clone(),
|
||||
@@ -788,6 +992,7 @@ impl SubjektivHost for LocalSubjectHost {
|
||||
create_if_missing: bool,
|
||||
) -> Result<SubjektivRecordSessionResponse, SubjektivHostError> {
|
||||
let attribution = self.attribution(context, create_if_missing)?;
|
||||
self.reserve_journal_session(context)?;
|
||||
Ok(SubjektivRecordSessionResponse {
|
||||
subject_id: attribution.subject_id,
|
||||
session_id: attribution.session_id,
|
||||
@@ -811,7 +1016,7 @@ impl SubjektivHost for LocalSubjectHost {
|
||||
.is_some_and(|g| g.binding == self.binding)
|
||||
})
|
||||
{
|
||||
schedule_job(jobs, pending.request.job_id);
|
||||
schedule_job(jobs, pending.request.job_id, self.self_weak.clone());
|
||||
let (count, bytes) = self
|
||||
.catalog
|
||||
.store
|
||||
@@ -874,7 +1079,7 @@ impl SubjektivHost for LocalSubjectHost {
|
||||
.map_err(|e| SubjektivHostError::Unavailable(e.to_string()))?,
|
||||
)
|
||||
.map_err(|e| SubjektivHostError::Unavailable(e.to_string()))?;
|
||||
schedule_job(jobs, snapshot.request.job_id);
|
||||
schedule_job(jobs, snapshot.request.job_id, self.self_weak.clone());
|
||||
Ok(memory::backend::MemoryConsolidationOutput { status:"started".into(),summary:"Requested a durable generic standalone consolidation Job; processing stops on Host shutdown".into(),candidate_count:count,total_bytes:bytes })
|
||||
}
|
||||
}
|
||||
@@ -894,6 +1099,9 @@ impl crate::jobs::JobDomainProvider for LocalDomainProvider {
|
||||
) -> Result<worker::job::JobFeatureGrant, String> {
|
||||
let host = self.0.upgrade().ok_or("Subject Host unavailable")?;
|
||||
host.ensure_live().map_err(|e| e.to_string())?;
|
||||
if snapshot.request.purpose == journal::PURPOSE {
|
||||
return journal::grant(host, snapshot, fence);
|
||||
}
|
||||
let grant: LocalConsolidationGrant = serde_json::from_value(
|
||||
snapshot
|
||||
.domain_grant
|
||||
@@ -1097,7 +1305,11 @@ impl worker::job::JobResultFinalizer for LocalConsolidationFinalizer {
|
||||
}
|
||||
}
|
||||
|
||||
fn schedule_job(jobs: crate::jobs::StandaloneJobs, id: String) {
|
||||
fn schedule_job(
|
||||
jobs: crate::jobs::StandaloneJobs,
|
||||
id: String,
|
||||
host: std::sync::Weak<LocalSubjectHost>,
|
||||
) {
|
||||
// Scheduling/consumer acknowledgement has no Internal Worker ownership.
|
||||
// The generic service fences and retains every execution until cleanup.
|
||||
tokio::spawn(async move {
|
||||
@@ -1114,6 +1326,9 @@ fn schedule_job(jobs: crate::jobs::StandaloneJobs, id: String) {
|
||||
"standalone Subject Job {id} cleanup/acknowledgement is unconfirmed: {error}"
|
||||
),
|
||||
}
|
||||
if let Some(host) = host.upgrade() {
|
||||
host.wake_journals();
|
||||
}
|
||||
});
|
||||
}
|
||||
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,463 @@
|
||||
//! Public standalone protocol through real mid-turn compaction and Journal Jobs.
|
||||
//! Only external model streams are scripted. No history, attribution, hook or Job
|
||||
//! result is injected; cancellation and rollback use the controller's public commands.
|
||||
//! Reported model usage and a low configured request threshold force two rewrites.
|
||||
//! The test attests durable public originals, not unfinished display deltas or meaning.
|
||||
|
||||
use super::*;
|
||||
use agen::llm_client::{
|
||||
ClientError, LlmClient, Request,
|
||||
event::{Event, ResponseStatus, StatusEvent, StopReason, UsageEvent},
|
||||
types::Item,
|
||||
};
|
||||
use futures::{Stream, StreamExt};
|
||||
use std::pin::Pin;
|
||||
use std::sync::atomic::AtomicUsize;
|
||||
|
||||
type ResponseStream = Pin<Box<dyn Stream<Item = Result<Event, ClientError>> + Send>>;
|
||||
const SUMMARY: &str = "DERIVED_COMPACTION_SENTINEL_NOT_AN_ORIGINAL";
|
||||
const ROLLED_BACK: &str = "ROLLED_BACK_INPUT_MUST_NOT_REACH_JOURNAL";
|
||||
const PARTIAL: &str = "public partial answer before cancellation";
|
||||
|
||||
#[derive(Clone, Default)]
|
||||
struct CompactingDialog {
|
||||
shared: DialogAndJournal,
|
||||
dialog_calls: Arc<AtomicUsize>,
|
||||
compactions: Arc<AtomicUsize>,
|
||||
rollback_entered: Arc<tokio::sync::Notify>,
|
||||
partial_stream_paused: Arc<tokio::sync::Notify>,
|
||||
}
|
||||
|
||||
fn events(events: Vec<Event>) -> ResponseStream {
|
||||
Box::pin(futures::stream::iter(events.into_iter().map(Ok)))
|
||||
}
|
||||
fn done() -> ResponseStream {
|
||||
events(vec![
|
||||
Event::text_block_start(0),
|
||||
Event::text_delta(0, "done"),
|
||||
Event::text_block_stop(0, Some(StopReason::EndTurn)),
|
||||
])
|
||||
}
|
||||
|
||||
#[async_trait::async_trait]
|
||||
impl LlmClient for CompactingDialog {
|
||||
async fn stream(&self, request: Request) -> Result<ResponseStream, ClientError> {
|
||||
if request
|
||||
.tools
|
||||
.iter()
|
||||
.any(|tool| tool.name == "write_summary")
|
||||
{
|
||||
if request.items.iter().any(|item| matches!(item, Item::ToolResult { call_id, .. } if call_id == "compact-summary")) {
|
||||
return Ok(done());
|
||||
}
|
||||
let count = self.compactions.fetch_add(1, Ordering::SeqCst);
|
||||
assert!(count < 2, "unexpected additional compaction");
|
||||
return Ok(events(vec![
|
||||
Event::tool_use_start(0, "compact-summary", "write_summary"),
|
||||
Event::tool_input_delta(0, serde_json::json!({"text": SUMMARY}).to_string()),
|
||||
Event::tool_use_stop(0),
|
||||
Event::Status(StatusEvent {
|
||||
status: ResponseStatus::Completed,
|
||||
}),
|
||||
]));
|
||||
}
|
||||
if request.tools.iter().any(|tool| {
|
||||
matches!(
|
||||
tool.name.as_str(),
|
||||
"ReadJournalState" | "SubmitMemorySurface" | "SubmitJobResult"
|
||||
)
|
||||
}) {
|
||||
return self.shared.stream(request).await;
|
||||
}
|
||||
match self.dialog_calls.fetch_add(1, Ordering::SeqCst) {
|
||||
step @ (0 | 1) => {
|
||||
assert!(request.tools.iter().any(|tool| tool.name == "TaskCreate"));
|
||||
Ok(events(vec![
|
||||
Event::tool_use_start(0, format!("public-task-{step}"), "TaskCreate"),
|
||||
Event::tool_input_delta(
|
||||
0,
|
||||
serde_json::json!({
|
||||
"subject": format!("original activity {step}"),
|
||||
"description": format!("original task result before compaction {step}")
|
||||
})
|
||||
.to_string(),
|
||||
),
|
||||
Event::tool_use_stop(0),
|
||||
Event::Usage(UsageEvent {
|
||||
input_tokens: Some(100_000),
|
||||
output_tokens: Some(10),
|
||||
total_tokens: Some(100_010),
|
||||
..Default::default()
|
||||
}),
|
||||
Event::Status(StatusEvent {
|
||||
status: ResponseStatus::Completed,
|
||||
}),
|
||||
]))
|
||||
}
|
||||
2 => {
|
||||
let paused = self.partial_stream_paused.clone();
|
||||
Ok(Box::pin(
|
||||
events(vec![
|
||||
Event::text_block_start(0),
|
||||
Event::text_delta(0, PARTIAL),
|
||||
Event::text_block_stop(0, None),
|
||||
])
|
||||
.chain(futures::stream::once(async move {
|
||||
paused.notify_one();
|
||||
std::future::pending::<Result<Event, ClientError>>().await
|
||||
})),
|
||||
))
|
||||
}
|
||||
3 => {
|
||||
// No AI event: cancelling this request must roll back the submitted input.
|
||||
self.rollback_entered.notify_one();
|
||||
std::future::pending::<()>().await;
|
||||
unreachable!()
|
||||
}
|
||||
other => panic!("unexpected dialog request {other}"),
|
||||
}
|
||||
}
|
||||
fn clone_boxed(&self) -> Box<dyn LlmClient> {
|
||||
Box::new(self.clone())
|
||||
}
|
||||
}
|
||||
|
||||
async fn cancel_and_wait(
|
||||
client: &mut client::Client<client::transport::in_process::Socket>,
|
||||
sequence: u64,
|
||||
) {
|
||||
client
|
||||
.send(&protocol::Method::Cancel {
|
||||
command: protocol::WorkerCommandEnvelope::new(sequence),
|
||||
})
|
||||
.await
|
||||
.unwrap();
|
||||
tokio::time::timeout(std::time::Duration::from_secs(20), async {
|
||||
loop {
|
||||
match client.next_event().await.unwrap().unwrap() {
|
||||
protocol::Event::RunEnd { result } => {
|
||||
assert_ne!(result, protocol::RunResult::Finished);
|
||||
return;
|
||||
}
|
||||
protocol::Event::Error { code, message } => panic!("{code:?}: {message}"),
|
||||
_ => {}
|
||||
}
|
||||
}
|
||||
})
|
||||
.await
|
||||
.unwrap();
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn public_mid_turn_compactions_preserve_originals_and_drain_after_cancel_and_rollback() {
|
||||
tokio::time::timeout(std::time::Duration::from_secs(60), async {
|
||||
let temp = tempfile::tempdir().unwrap();
|
||||
let state = temp.path().join("state");
|
||||
let catalog = StandaloneSubjects::open(&state).unwrap();
|
||||
let subject = catalog.create("compaction-journal", None).unwrap();
|
||||
let model = CompactingDialog {
|
||||
shared: DialogAndJournal {
|
||||
journal: JournalScript {
|
||||
gate_first: true,
|
||||
..Default::default()
|
||||
},
|
||||
..Default::default()
|
||||
},
|
||||
..Default::default()
|
||||
};
|
||||
let mut launch = crate::StandaloneLaunchConfig::new(
|
||||
temp.path(),
|
||||
&state,
|
||||
manifest::ProfileSelector::source_named(
|
||||
manifest::ProfileRegistrySource::Builtin,
|
||||
"standalone-subjektiv",
|
||||
),
|
||||
"public-compaction-journal",
|
||||
)
|
||||
.with_subject(subject.id.clone())
|
||||
.resolve()
|
||||
.unwrap();
|
||||
launch.profile.manifest.compaction = Some(manifest::CompactionConfig {
|
||||
threshold: None,
|
||||
request_threshold: Some(50_000),
|
||||
retained_tokens: 0,
|
||||
..Default::default()
|
||||
});
|
||||
let mut host = crate::StandaloneHost::start_with_model_client(launch, model.clone())
|
||||
.await
|
||||
.unwrap();
|
||||
let session = host.record().active_session_id;
|
||||
let workers = StandaloneWorkerStore::open_existing(&state).unwrap();
|
||||
let source_store = session_store::FsStore::new_with_retention(
|
||||
workers.sessions_dir(host.record().worker_id),
|
||||
crate::store::session_retention(&state),
|
||||
)
|
||||
.unwrap();
|
||||
let mut client = host.connect();
|
||||
client
|
||||
.send(&protocol::Method::submit_text(
|
||||
protocol::new_submission_request_id(),
|
||||
"original long turn survives compaction",
|
||||
))
|
||||
.await
|
||||
.unwrap();
|
||||
let mut completed_compactions = 0;
|
||||
loop {
|
||||
match client.next_event().await.unwrap().unwrap() {
|
||||
protocol::Event::CompactionProgress {
|
||||
compaction: Some(progress),
|
||||
} if progress.phase == protocol::CompactionPhase::Committing => {
|
||||
assert_eq!(
|
||||
progress.trigger,
|
||||
protocol::CompactionTrigger::RequestThreshold
|
||||
);
|
||||
completed_compactions += 1;
|
||||
}
|
||||
protocol::Event::TextDelta { text } if text.contains(PARTIAL) => break,
|
||||
protocol::Event::RunEnd { .. } => panic!("dialog ended before cancellation"),
|
||||
protocol::Event::SessionEntryCommitted { entry } if matches!(entry.data, protocol::SessionSnapshotEntryData::RunError { .. }) => panic!("dialog failed before cancellation: {entry:?}"),
|
||||
protocol::Event::Error { code, message } => panic!("{code:?}: {message}"),
|
||||
_ => {}
|
||||
}
|
||||
}
|
||||
assert_eq!(model.compactions.load(Ordering::SeqCst), 2);
|
||||
assert_eq!(completed_compactions, 2);
|
||||
model.shared.journal.entered.notified().await;
|
||||
let context = JournalHostContext::validated_session(
|
||||
&catalog.store,
|
||||
catalog
|
||||
.store
|
||||
.session_attribution(&session.to_string())
|
||||
.unwrap()
|
||||
.unwrap(),
|
||||
)
|
||||
.unwrap();
|
||||
let reader = JournalHostContext::validated_reader(&catalog.store, &subject.id).unwrap();
|
||||
let journal = catalog
|
||||
.store
|
||||
.list_journals(&reader, None, 1)
|
||||
.unwrap()
|
||||
.items
|
||||
.pop()
|
||||
.unwrap();
|
||||
let first = catalog
|
||||
.store
|
||||
.active_journal_generation(&context, &journal.id)
|
||||
.unwrap()
|
||||
.unwrap();
|
||||
assert!(
|
||||
catalog
|
||||
.store
|
||||
.list_journal_entries(&reader, &journal.id, None, 10)
|
||||
.unwrap()
|
||||
.items
|
||||
.is_empty(),
|
||||
"compaction must finish before generation is released"
|
||||
);
|
||||
model.partial_stream_paused.notified().await;
|
||||
cancel_and_wait(&mut client, 1).await;
|
||||
client
|
||||
.send(&protocol::Method::submit_text(
|
||||
protocol::new_submission_request_id(),
|
||||
ROLLED_BACK,
|
||||
))
|
||||
.await
|
||||
.unwrap();
|
||||
model.rollback_entered.notified().await;
|
||||
let before_rollback: Vec<_> = source_store
|
||||
.list_segments(session)
|
||||
.unwrap()
|
||||
.iter()
|
||||
.flat_map(|segment| source_store.read_all(session, *segment).unwrap())
|
||||
.collect();
|
||||
assert!(
|
||||
serde_json::to_string(&before_rollback)
|
||||
.unwrap()
|
||||
.contains(ROLLED_BACK),
|
||||
"the submitted input must reach the actual durable rollback boundary"
|
||||
);
|
||||
cancel_and_wait(&mut client, 2).await;
|
||||
assert_eq!(
|
||||
catalog
|
||||
.store
|
||||
.active_journal_generation(&context, &journal.id)
|
||||
.unwrap()
|
||||
.unwrap(),
|
||||
first,
|
||||
"compaction/cancellation must not alter the running generation's frozen input"
|
||||
);
|
||||
|
||||
assert!(matches!(source_store.delete_session(session),
|
||||
Err(session_store::StoreError::SessionPinned(id)) if id == session));
|
||||
let segments = source_store.list_segments(session).unwrap();
|
||||
assert_eq!(segments.len(), 3);
|
||||
let raw: Vec<_> = segments
|
||||
.iter()
|
||||
.flat_map(|segment| source_store.read_all(session, *segment).unwrap())
|
||||
.collect();
|
||||
for history in raw.iter().filter_map(|record| match record {
|
||||
session_store::LogEntry::AnnotatedSegmentStart { history, compacted_from: Some(_), .. } => Some(history),
|
||||
_ => None,
|
||||
}) {
|
||||
let mut calls = std::collections::HashSet::new();
|
||||
let mut results = 0;
|
||||
for entry in history {
|
||||
let is_tool = matches!(entry.item, session_store::LoggedItem::ToolCall { .. } | session_store::LoggedItem::ToolResult { .. });
|
||||
let Some(metadata) = entry.metadata.input_metadata.as_ref().filter(|_| is_tool) else { continue; };
|
||||
assert_eq!(metadata.usage().recording_material, session_store::InputEvidenceUse::Exclude);
|
||||
assert_eq!(metadata.usage().memory_evidence, session_store::InputEvidenceUse::Exclude);
|
||||
assert_eq!(metadata.usage().observation, session_store::InputObservationUse::Hidden);
|
||||
assert!(metadata.public_item().is_none());
|
||||
assert!(entry.metadata.derivation.is_some());
|
||||
match &entry.item {
|
||||
session_store::LoggedItem::ToolCall { call_id, .. } => { calls.insert(call_id.clone()); }
|
||||
session_store::LoggedItem::ToolResult { call_id, .. } => {
|
||||
assert!(calls.contains(call_id), "derived Tool result must follow its real logical call");
|
||||
results += 1;
|
||||
}
|
||||
_ => unreachable!(),
|
||||
}
|
||||
}
|
||||
assert!(!calls.is_empty());
|
||||
assert!(results >= calls.len());
|
||||
}
|
||||
assert_eq!(
|
||||
raw.iter()
|
||||
.filter(|entry| matches!(
|
||||
entry,
|
||||
session_store::LogEntry::AnnotatedSegmentStart {
|
||||
compacted_from: Some(_),
|
||||
..
|
||||
}
|
||||
))
|
||||
.count(),
|
||||
2
|
||||
);
|
||||
assert!(
|
||||
!serde_json::to_string(&raw).unwrap().contains(ROLLED_BACK),
|
||||
"pre-AI cancellation must roll back the speculative input"
|
||||
);
|
||||
assert!(
|
||||
serde_json::to_string(&raw).unwrap().contains(SUMMARY),
|
||||
"real rewrite did not persist its summary"
|
||||
);
|
||||
let metadata =
|
||||
session_store::FsWorkerStore::new(workers.worker_metadata_dir(host.record().worker_id))
|
||||
.unwrap()
|
||||
.read_by_name(&host.record().storage_key)
|
||||
.unwrap()
|
||||
.unwrap();
|
||||
let originals =
|
||||
session_store::public_material::SessionPublicMaterialReader::open_fs_with_retention(
|
||||
&workers.sessions_dir(host.record().worker_id),
|
||||
session,
|
||||
metadata.active.unwrap().segment_id.unwrap(),
|
||||
session_store::public_material::PublicMaterialLimits::default(),
|
||||
crate::store::session_retention(&state),
|
||||
)
|
||||
.unwrap();
|
||||
let final_original = originals.descriptors().last().unwrap();
|
||||
let expected_cursor = (final_original.canonical_order + 1, 0);
|
||||
let canonical: Vec<_> = originals
|
||||
.descriptors()
|
||||
.map(|descriptor| {
|
||||
let page = originals
|
||||
.read_content(descriptor, 0, MAX_JOURNAL_READ_BYTES)
|
||||
.unwrap();
|
||||
assert_eq!(page.next_offset, descriptor.total_bytes);
|
||||
page.content
|
||||
})
|
||||
.collect();
|
||||
assert!(!canonical.join("\n").contains(ROLLED_BACK));
|
||||
assert!(!canonical.join("\n").contains(SUMMARY));
|
||||
|
||||
// Resume the existing runner, then its one durable successor, with no more input.
|
||||
let jobs = host.jobs();
|
||||
model.shared.journal.release.notify_one();
|
||||
jobs.wait(&first.job.job_id).await.unwrap();
|
||||
model.shared.journal.entered.notified().await;
|
||||
let second = catalog
|
||||
.store
|
||||
.active_journal_generation(&context, &journal.id)
|
||||
.unwrap()
|
||||
.unwrap();
|
||||
assert_ne!(first.id, second.id);
|
||||
model.shared.journal.release.notify_one();
|
||||
jobs.wait(&second.job.job_id).await.unwrap();
|
||||
assert!(!catalog.store.journal_retention_required(&context).unwrap());
|
||||
let (saved, open) = catalog
|
||||
.store
|
||||
.journal_resume_state(&context, &journal.id)
|
||||
.unwrap();
|
||||
let open = open.unwrap();
|
||||
assert!(!open.ongoing.is_empty());
|
||||
let entries = catalog
|
||||
.store
|
||||
.list_journal_entries(&reader, &journal.id, None, 10)
|
||||
.unwrap();
|
||||
assert_eq!(
|
||||
entries.items.len(),
|
||||
1,
|
||||
"compaction/turn boundaries must not fix or duplicate the open entry"
|
||||
);
|
||||
assert_eq!(entries.items[0].id, open.id);
|
||||
let supplied = model
|
||||
.shared
|
||||
.journal
|
||||
.source_reads
|
||||
.lock()
|
||||
.unwrap()
|
||||
.values()
|
||||
.cloned()
|
||||
.collect::<Vec<_>>()
|
||||
.join("\n");
|
||||
for original in [
|
||||
"original long turn survives compaction",
|
||||
"original activity 0",
|
||||
"original activity 1",
|
||||
] {
|
||||
assert!(
|
||||
supplied.contains(original),
|
||||
"Journal did not receive {original}"
|
||||
);
|
||||
}
|
||||
for original in canonical {
|
||||
assert!(
|
||||
supplied.contains(&original),
|
||||
"a durable public original was skipped"
|
||||
);
|
||||
}
|
||||
assert!(
|
||||
!supplied.contains(SUMMARY),
|
||||
"derived summary substituted for original input"
|
||||
);
|
||||
assert!(
|
||||
!supplied.contains(ROLLED_BACK),
|
||||
"cancelled input was admitted after rollback"
|
||||
);
|
||||
assert_eq!((saved.process_order, saved.process_byte), expected_cursor);
|
||||
let position = catalog
|
||||
.store
|
||||
.read_journal_text(
|
||||
&reader,
|
||||
&journal.id,
|
||||
None,
|
||||
JournalTextField::CurrentPosition,
|
||||
None,
|
||||
0,
|
||||
MAX_JOURNAL_READ_BYTES,
|
||||
)
|
||||
.unwrap();
|
||||
assert!(!position.text.is_empty());
|
||||
loop {
|
||||
match host.disconnect_subject().await {
|
||||
Ok(()) => break,
|
||||
Err(crate::StandaloneSubjectDisconnectError::Incomplete(message)) if message.contains("dispatcher") || message.contains("cleanup") => tokio::task::yield_now().await,
|
||||
Err(error) => panic!("recorded compaction/cancellation lineage must remain releasable while work is unfinished: {error}"),
|
||||
}
|
||||
}
|
||||
host.shutdown().await.unwrap();
|
||||
})
|
||||
.await
|
||||
.expect("bounded public compaction/Journal integration");
|
||||
}
|
||||
@@ -0,0 +1,170 @@
|
||||
//! Real LocalSubjectHost/Journal storage -> PreparedWorker -> compactor Request -> durable seed.
|
||||
//! Only external LLM responses and the fixture's Job execution fence are substituted. The
|
||||
//! in-flight generation is retained while its real adapter updates storage during generation.
|
||||
//! Temporary storage and the parent fixture own cleanup; ordinary standalone lib tests select
|
||||
//! this suite. Predetermined summaries attest transport and persistence, not model understanding.
|
||||
|
||||
use super::*;
|
||||
use agen::llm_client::{
|
||||
ClientError, LlmClient, Request,
|
||||
event::{Event, ResponseStatus, StatusEvent},
|
||||
types::Item,
|
||||
};
|
||||
use futures::Stream;
|
||||
use session_store::{CombinedStore, FsWorkerStore, LogEntry};
|
||||
use std::pin::Pin;
|
||||
|
||||
const BEFORE: &str = "FROZEN_POSITION: B partially implemented; tests not run; result unconfirmed";
|
||||
const AFTER: &str = "NEXT_POSITION: background Journal changed during compactor generation";
|
||||
const COMPLEMENT: &str =
|
||||
"Unrecorded request: keep the user's constraint and finish the remaining checks.";
|
||||
|
||||
#[derive(Clone)]
|
||||
struct MockClient {
|
||||
adapter: Arc<LocalJournalHost>,
|
||||
requests: Arc<Mutex<Vec<Request>>>,
|
||||
updated: Arc<AtomicBool>,
|
||||
}
|
||||
|
||||
#[async_trait::async_trait]
|
||||
impl LlmClient for MockClient {
|
||||
fn clone_boxed(&self) -> Box<dyn LlmClient> {
|
||||
Box::new(self.clone())
|
||||
}
|
||||
|
||||
async fn stream(
|
||||
&self,
|
||||
request: Request,
|
||||
) -> Result<Pin<Box<dyn Stream<Item = Result<Event, ClientError>> + Send>>, ClientError> {
|
||||
assert!(
|
||||
request
|
||||
.tools
|
||||
.iter()
|
||||
.any(|tool| tool.name == "write_summary")
|
||||
);
|
||||
let first = self.requests.lock().unwrap().is_empty();
|
||||
self.requests.lock().unwrap().push(request);
|
||||
let events = if first {
|
||||
assert!(!self.updated.swap(true, Ordering::SeqCst));
|
||||
let state = self.adapter.state().unwrap();
|
||||
save(
|
||||
&self.adapter,
|
||||
"position-during-compaction",
|
||||
&state.current_journal.state_token,
|
||||
JournalAction::UpdatePosition {
|
||||
current_position: AFTER.into(),
|
||||
},
|
||||
vec![],
|
||||
);
|
||||
vec![
|
||||
Event::tool_use_start(0, "summary", "write_summary"),
|
||||
Event::tool_input_delta(0, serde_json::json!({ "text": COMPLEMENT }).to_string()),
|
||||
Event::tool_use_stop(0),
|
||||
Event::Status(StatusEvent {
|
||||
status: ResponseStatus::Completed,
|
||||
}),
|
||||
]
|
||||
} else {
|
||||
vec![
|
||||
Event::text_block_start(0),
|
||||
Event::text_delta(0, "summary saved"),
|
||||
Event::text_block_stop(0, None),
|
||||
Event::Status(StatusEvent {
|
||||
status: ResponseStatus::Completed,
|
||||
}),
|
||||
]
|
||||
};
|
||||
Ok(Box::pin(futures::stream::iter(events.into_iter().map(Ok))))
|
||||
}
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn local_host_compaction_freezes_pending_journal_through_request_and_durable_seed_during_update()
|
||||
{
|
||||
tokio::time::timeout(std::time::Duration::from_secs(30), async {
|
||||
let fixture = Fixture::new("Keep the user's constraint; work remains unfinished and unconfirmed.");
|
||||
let (adapter, _, job) = fixture.adapter();
|
||||
let created = save(
|
||||
&adapter,
|
||||
"record-partial-work",
|
||||
&adapter.generation.initial_journal.state_token,
|
||||
JournalAction::Create {
|
||||
title: "A corrected to B".into(),
|
||||
body: "B partially implemented; tests not run; result unconfirmed".into(),
|
||||
ongoing: "Finish remaining checks".into(),
|
||||
state: JournalEntryState::Open,
|
||||
source_end: None,
|
||||
correction_refs: vec![],
|
||||
},
|
||||
adapter.generation.selected_ranges.clone(),
|
||||
);
|
||||
save(&adapter, "position-before-compaction", &created.state_token,
|
||||
JournalAction::UpdatePosition { current_position: BEFORE.into() }, vec![]);
|
||||
let before = adapter.state().unwrap();
|
||||
let expected = fixture.host().journal_compaction_context(&fixture.context).unwrap();
|
||||
let journal = &expected.journals[0];
|
||||
assert_eq!(journal.source_session_id, fixture.context.session_id);
|
||||
assert_eq!(journal.current_position, BEFORE);
|
||||
assert_eq!(journal.entries[0].state, JournalEntryState::Open);
|
||||
assert!(!before.selected_ranges.is_empty());
|
||||
assert_eq!(journal.process_order, before.current_journal.process_order);
|
||||
assert_eq!(journal.process_byte, before.current_journal.process_byte);
|
||||
assert_eq!(journal.process_order, 0);
|
||||
assert_eq!(journal.process_byte, 0, "saved open records do not advance processing checkpoint");
|
||||
let expected_json = serde_json::to_string(&expected).unwrap();
|
||||
let adapter = Arc::new(adapter);
|
||||
let model = MockClient { adapter: adapter.clone(), requests: Arc::default(), updated: Arc::new(AtomicBool::new(false)) };
|
||||
let workers = StandaloneWorkerStore::open_existing(&fixture.host().catalog.state_root).unwrap();
|
||||
let worker_id = fixture._allocation.as_ref().unwrap().worker_id();
|
||||
let store = CombinedStore::new(fixture.sessions.clone(), FsWorkerStore::new(workers.worker_metadata_dir(worker_id)).unwrap());
|
||||
let mut manifest = manifest::WorkerManifest::from_toml(&format!("[worker]\nname='{}'\n[model]\nscheme='anthropic'\nmodel_id='scripted'\n[engine]\n[scope]\nallow=[]", fixture.context.worker_id)).unwrap();
|
||||
manifest.feature.subjektiv.profile.enabled = true;
|
||||
manifest.feature.subjektiv.profile.extraction.enabled = false;
|
||||
let mut prepared = worker::WorkerBootstrap::new(
|
||||
manifest,
|
||||
store,
|
||||
worker::PromptCatalogSource::builtins_only(),
|
||||
worker::WorkerWorkspaceContext::no_workspace(),
|
||||
worker::WorkerFilesystemAuthority::None,
|
||||
worker::WorkerBootstrapLayout::Direct { runtime_base: fixture._temp.path().join("runtime") },
|
||||
).with_model_client(model.clone()).with_subjektiv_host(fixture.host().clone()).prepare_restored("journal-test").await.unwrap();
|
||||
assert_eq!(prepared.worker().session_id().to_string(), fixture.context.session_id);
|
||||
let source_segment = prepared.worker().segment_id();
|
||||
let original = fixture.sessions.read_all(prepared.worker().session_id(), source_segment).unwrap();
|
||||
let generation = fixture.host().catalog.store.active_journal_generation(&adapter.context, &adapter.grant.journal_id).unwrap().unwrap();
|
||||
assert!(!fixture.host().session_fully_reflected(&fixture.context.session_id).unwrap());
|
||||
prepared.worker_mut().compact(0).await.unwrap();
|
||||
assert!(model.updated.load(Ordering::SeqCst));
|
||||
let worker = prepared.worker();
|
||||
assert_ne!(worker.segment_id(), source_segment);
|
||||
let seed = worker.store().read_all(worker.session_id(), worker.segment_id()).unwrap().into_iter().find_map(|entry| match entry { LogEntry::AnnotatedSegmentStart { history, .. } => Some(history), _ => None }).expect("durable compacted seed");
|
||||
let journal_items: Vec<_> = seed.iter().filter(|entry| entry.metadata.input_metadata.as_ref().is_some_and(|input| input.usage().compaction == session_store::InputCompactionUse::ReferenceInput)).collect();
|
||||
assert_eq!(journal_items.len(), 1);
|
||||
let journal_item = Item::from(journal_items[0].item.clone());
|
||||
let body = journal_item.as_text().unwrap();
|
||||
assert!(body.contains(&expected_json), "durable seed contains the full selected JSON and processing checkpoint");
|
||||
assert!(body.contains(BEFORE));
|
||||
assert!(!body.contains(AFTER));
|
||||
assert!(seed.iter().any(|entry| entry.metadata.input_metadata.as_ref().is_some_and(|input| input.usage().compaction == session_store::InputCompactionUse::OpeningSummary) && Item::from(entry.item.clone()).as_text().is_some_and(|text| text.contains(COMPLEMENT))));
|
||||
let requests = model.requests.lock().unwrap();
|
||||
let input = requests[0].items.iter().find_map(|item| match item {
|
||||
Item::Message { role: agen::llm_client::types::Role::User, .. } => item.as_text().filter(|text| text.contains("## Conversation overview/index")),
|
||||
_ => None,
|
||||
}).expect("actual compactor user request");
|
||||
assert!(input.ends_with(body), "exact same frozen reference goes to actual compactor and seed");
|
||||
assert_eq!(input.matches(&expected_json).count(), 1);
|
||||
assert!(!input.contains(AFTER));
|
||||
drop(requests);
|
||||
let latest = fixture.host().journal_compaction_context(&fixture.context).unwrap();
|
||||
assert_eq!(latest.journals[0].current_position, AFTER);
|
||||
assert_ne!(latest.journals[0].state_token, expected.journals[0].state_token);
|
||||
assert_eq!(latest.journals[0].process_order, expected.journals[0].process_order);
|
||||
assert_eq!(latest.journals[0].process_byte, expected.journals[0].process_byte);
|
||||
assert_eq!(latest.journals[0].entries, expected.journals[0].entries);
|
||||
assert_eq!(fixture.host().catalog.store.active_journal_generation(&adapter.context, &adapter.grant.journal_id).unwrap(), Some(generation));
|
||||
assert_eq!(fixture.host().jobs().unwrap().get(&job.request.job_id).unwrap().state, job.state);
|
||||
let unchanged: Vec<_> = fixture.sessions.read_all(worker.session_id(), source_segment).unwrap().into_iter().filter(|entry| !matches!(entry, LogEntry::Extension { domain, .. } if domain == "metrics")).collect();
|
||||
assert_eq!(serde_json::to_value(unchanged).unwrap(), serde_json::to_value(original).unwrap());
|
||||
assert!(!fixture.host().session_fully_reflected(&fixture.context.session_id).unwrap());
|
||||
}).await.expect("compaction must finish without recording Job completion");
|
||||
}
|
||||
@@ -0,0 +1,228 @@
|
||||
//! Real standalone Subject/Controller/Journal Job/initial input connection. Only external
|
||||
//! model streams are scripted. The scenario checks persisted data and ordering, not whether
|
||||
//! a real model understands the correction or can autonomously continue the work.
|
||||
|
||||
use super::*;
|
||||
use crate::{StandaloneHost, StandaloneLaunchConfig, StandaloneSubjectDisconnectError};
|
||||
use agen::llm_client::types::Item;
|
||||
|
||||
fn launch(root: &Path, state: &Path, subject: &str, name: &str) -> crate::ResolvedStandaloneLaunch {
|
||||
StandaloneLaunchConfig::new(
|
||||
root,
|
||||
state,
|
||||
manifest::ProfileSelector::source_named(
|
||||
manifest::ProfileRegistrySource::Builtin,
|
||||
"standalone-subjektiv",
|
||||
),
|
||||
name,
|
||||
)
|
||||
.with_subject(subject.into())
|
||||
.resolve()
|
||||
.unwrap()
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn recorded_idle_body_handoff_preserves_open_after_source_deletion_and_seeds_next_body_once()
|
||||
{
|
||||
tokio::time::timeout(std::time::Duration::from_secs(60), async {
|
||||
let temp = tempfile::tempdir().unwrap();
|
||||
let state = temp.path().join("state");
|
||||
let catalog = StandaloneSubjects::open(&state).unwrap();
|
||||
let subject = catalog.create("continuity", Some("BEHAVIOR_ORIGINAL_UNCHANGED")).unwrap();
|
||||
let model = DialogAndJournal { journal: JournalScript { gate_first: true, ..Default::default() }, ..Default::default() };
|
||||
let mut first = StandaloneHost::start_with_model_client(launch(temp.path(), &state, &subject.id, "first"), model.clone()).await.unwrap();
|
||||
let old_worker = first.worker_id();
|
||||
let old_session = first.record().active_session_id;
|
||||
let old_writer = catalog.store.claim_journal_writer(&subject.id, &catalog.scope_id, &old_worker.to_string()).unwrap();
|
||||
submit_dialog(&first, "A was proposed, user corrected its constraint; B selected because A is unusable. One step performed; tests not performed; external outcome Unknown. Work is unfinished.").await;
|
||||
model.journal.entered.notified().await;
|
||||
assert!(matches!(first.disconnect_subject().await, Err(StandaloneSubjectDisconnectError::Incomplete(_))));
|
||||
assert!(catalog.store.journal_writer_active(&old_writer).unwrap());
|
||||
assert!(StandaloneHost::start_with_model_client(launch(temp.path(), &state, &subject.id, "premature"), DialogAndJournal::default()).await.is_err());
|
||||
let context = JournalHostContext::validated_session(&catalog.store, catalog.store.session_attribution(&old_session.to_string()).unwrap().unwrap()).unwrap();
|
||||
let id = catalog.store.journal_for_session(&context).unwrap().unwrap();
|
||||
let generation = catalog.store.active_journal_generation(&context, &id).unwrap().unwrap();
|
||||
model.journal.release.notify_one();
|
||||
first.jobs().wait(&generation.job.job_id).await.unwrap();
|
||||
// Observe the authoritative gate after cleanup; yielding is cooperative scheduling,
|
||||
// never elapsed time used as proof of recording completion.
|
||||
loop {
|
||||
match first.disconnect_subject().await {
|
||||
Ok(()) => break,
|
||||
Err(StandaloneSubjectDisconnectError::Incomplete(message)) if message.contains("dispatcher") || message.contains("cleanup") => tokio::task::yield_now().await,
|
||||
Err(error) => panic!("unexpected handoff blocker: {error}"),
|
||||
}
|
||||
}
|
||||
assert!(!catalog.store.journal_writer_active(&old_writer).unwrap());
|
||||
assert!(catalog.store.accept_journal_sources(&context, "late old activity", &[generation.selected_ranges[0].clone()]).is_err());
|
||||
first.shutdown().await.unwrap();
|
||||
let workers = StandaloneWorkerStore::open_existing(&state).unwrap();
|
||||
workers.delete(old_worker).unwrap();
|
||||
assert!(!workers.sessions_dir(old_worker).exists());
|
||||
let reader = JournalHostContext::validated_reader(&catalog.store, &subject.id).unwrap();
|
||||
let historical = catalog.store.journal_startup_snapshot(&reader, Some(&old_session.to_string())).unwrap();
|
||||
assert_eq!(historical.journals[0].entries[0].state, JournalEntryState::Open);
|
||||
assert!(historical.journals[0].entries[0].ongoing.contains("unknown"));
|
||||
assert!(catalog.store.list_memories(&subject.id).unwrap().is_empty());
|
||||
|
||||
let second_model = DialogAndJournal::default();
|
||||
let second = StandaloneHost::start_with_model_client(launch(temp.path(), &state, &subject.id, "second"), second_model.clone()).await.unwrap();
|
||||
submit_dialog(&second, "Continue B; describe what is still unperformed and unconfirmed.").await;
|
||||
let requests = second_model.dialog_requests.lock().unwrap();
|
||||
let initial = &requests[0];
|
||||
let context_index = initial.items.iter().position(|item| item.as_text().is_some_and(|text| text.contains("Proposed A; user corrected it to B"))).expect("saved Journal visible to first model request");
|
||||
let user_index = initial.items.iter().position(|item| matches!(item, Item::Message { role: agen::llm_client::types::Role::User, .. })).unwrap();
|
||||
assert!(context_index < user_index);
|
||||
assert_eq!(initial.items.iter().filter(|item| item.as_text().is_some_and(|text| text.contains("Proposed A; user corrected it to B"))).count(), 1);
|
||||
drop(requests);
|
||||
let session = second.record().active_session_id;
|
||||
let sessions = session_store::FsStore::new_with_retention(workers.sessions_dir(second.worker_id()), crate::store::session_retention(&state)).unwrap();
|
||||
let pointer = session_store::FsWorkerStore::new(workers.worker_metadata_dir(second.worker_id())).unwrap().read_by_name(&second.record().storage_key).unwrap().unwrap().active.unwrap();
|
||||
let entries = sessions.read_all(session, pointer.segment_id.unwrap()).unwrap();
|
||||
let journal_items = entries.iter().filter(|entry| matches!(entry, session_store::LogEntry::AnnotatedSystemItem { entry, .. } if entry.metadata.input_metadata.as_ref().and_then(|input| input.feature_payload()).is_some_and(|payload| payload.schema() == "journal:startup"))).count();
|
||||
assert_eq!(journal_items, 1);
|
||||
assert_eq!(catalog.store.subject(&subject.id).unwrap().unwrap().behavior_md, "BEHAVIOR_ORIGINAL_UNCHANGED");
|
||||
second.shutdown().await.unwrap();
|
||||
}).await.expect("bounded complete Subject handoff connection");
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn saved_public_history_without_admission_notification_blocks_release_until_actual_recording()
|
||||
{
|
||||
tokio::time::timeout(std::time::Duration::from_secs(60), async {
|
||||
let temp = tempfile::tempdir().unwrap();
|
||||
let state = temp.path().join("state");
|
||||
let catalog = StandaloneSubjects::open(&state).unwrap();
|
||||
let subject = catalog.create("saved-before-notified", None).unwrap();
|
||||
let model = DialogAndJournal {
|
||||
journal: JournalScript {
|
||||
gate_first: true,
|
||||
..Default::default()
|
||||
},
|
||||
..Default::default()
|
||||
};
|
||||
let mut host = StandaloneHost::start_with_model_client(
|
||||
launch(temp.path(), &state, &subject.id, "gap"),
|
||||
model.clone(),
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
let workers = StandaloneWorkerStore::open_existing(&state).unwrap();
|
||||
let record = host.record().clone();
|
||||
let writer = catalog
|
||||
.store
|
||||
.claim_journal_writer(
|
||||
&subject.id,
|
||||
&catalog.scope_id,
|
||||
&host.worker_id().to_string(),
|
||||
)
|
||||
.unwrap();
|
||||
let sessions = session_store::FsStore::new_with_retention(
|
||||
workers.sessions_dir(host.worker_id()),
|
||||
crate::store::session_retention(&state),
|
||||
)
|
||||
.unwrap();
|
||||
// The production saved-history boundary, with its admission callback deliberately
|
||||
// omitted. The real Host release must discover these bytes, not trust Job status.
|
||||
sessions
|
||||
.append(
|
||||
record.active_session_id,
|
||||
record.active_segment_id.unwrap(),
|
||||
&session_store::LogEntry::AnnotatedUserInput {
|
||||
ts: 3,
|
||||
segments: vec![],
|
||||
extensions: vec![],
|
||||
history: vec![message(
|
||||
"missed-admission",
|
||||
"A corrected to B, partially performed, outcome Unknown",
|
||||
)],
|
||||
},
|
||||
)
|
||||
.unwrap();
|
||||
assert!(host.disconnect_subject().await.is_err());
|
||||
assert!(catalog.store.journal_writer_active(&writer).unwrap());
|
||||
model.journal.entered.notified().await;
|
||||
let context = JournalHostContext::validated_session(
|
||||
&catalog.store,
|
||||
catalog
|
||||
.store
|
||||
.session_attribution(&record.active_session_id.to_string())
|
||||
.unwrap()
|
||||
.unwrap(),
|
||||
)
|
||||
.unwrap();
|
||||
let id = catalog
|
||||
.store
|
||||
.journal_for_session(&context)
|
||||
.unwrap()
|
||||
.unwrap();
|
||||
let generation = catalog
|
||||
.store
|
||||
.active_journal_generation(&context, &id)
|
||||
.unwrap()
|
||||
.unwrap();
|
||||
model.journal.release.notify_one();
|
||||
host.jobs().wait(&generation.job.job_id).await.unwrap();
|
||||
loop {
|
||||
match host.disconnect_subject().await {
|
||||
Ok(()) => break,
|
||||
Err(StandaloneSubjectDisconnectError::Incomplete(message))
|
||||
if message.contains("dispatcher") || message.contains("cleanup") =>
|
||||
{
|
||||
tokio::task::yield_now().await
|
||||
}
|
||||
Err(error) => {
|
||||
panic!("unexpected release blocker after saved-history recording: {error}")
|
||||
}
|
||||
}
|
||||
}
|
||||
assert!(!catalog.store.journal_writer_active(&writer).unwrap());
|
||||
let snapshot = catalog
|
||||
.store
|
||||
.journal_startup_snapshot(
|
||||
&JournalHostContext::validated_reader(&catalog.store, &subject.id).unwrap(),
|
||||
None,
|
||||
)
|
||||
.unwrap();
|
||||
assert!(!snapshot.journals[0].current_position.is_empty());
|
||||
assert_eq!(
|
||||
snapshot.journals[0].entries[0].state,
|
||||
JournalEntryState::Open
|
||||
);
|
||||
host.shutdown().await.unwrap();
|
||||
})
|
||||
.await
|
||||
.expect("saved-history/notification-gap handoff is bounded");
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn shutdown_and_normal_deletion_cannot_release_subject_occupancy() {
|
||||
let temp = tempfile::tempdir().unwrap();
|
||||
let state = temp.path().join("state");
|
||||
let catalog = StandaloneSubjects::open(&state).unwrap();
|
||||
let subject = catalog.create("retained-owner", None).unwrap();
|
||||
let host = StandaloneHost::start_with_model_client(
|
||||
launch(temp.path(), &state, &subject.id, "retained"),
|
||||
DialogAndJournal::default(),
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
let worker = host.worker_id();
|
||||
host.shutdown().await.unwrap();
|
||||
let workers = StandaloneWorkerStore::open_existing(&state).unwrap();
|
||||
assert!(workers.delete(worker).is_err());
|
||||
assert!(
|
||||
StandaloneHost::start_with_model_client(
|
||||
launch(temp.path(), &state, &subject.id, "not-an-owner"),
|
||||
DialogAndJournal::default()
|
||||
)
|
||||
.await
|
||||
.is_err()
|
||||
);
|
||||
let mut restored =
|
||||
StandaloneHost::restore_with_model_client(state, worker, DialogAndJournal::default())
|
||||
.await
|
||||
.unwrap();
|
||||
restored.disconnect_subject().await.unwrap();
|
||||
restored.shutdown().await.unwrap();
|
||||
}
|
||||
@@ -0,0 +1,596 @@
|
||||
//! Connected standalone Host -> Subjektiv Memory/Journal -> real FsStore coverage.
|
||||
//! Candidate and Journal decisions are explicit test inputs; no model, Runtime or live DB
|
||||
//! is used. The parent Journal fixture owns isolated temporary storage and binding cleanup.
|
||||
//! Selected by the ordinary standalone lib tests, with no additional feature or service.
|
||||
|
||||
use super::*;
|
||||
use memory::{
|
||||
backend::MemoryStageCandidateOperation,
|
||||
extract::{CandidateKind, ExtractedCandidate, StagingEvidence},
|
||||
schema::{EvidenceKind, EvidenceOriginKind, SourceEvidenceRef, SourceRef},
|
||||
};
|
||||
use subjektiv::{
|
||||
CandidateDecision, CandidateDecisionRequest, MemoryChangeTarget, MemoryDraft, MemoryRecord,
|
||||
StagingResolution, SubjectStagingRecord,
|
||||
journal::memory_links::{
|
||||
JournalTargetAvailability, MemoryJournalLinks, MemoryJournalRequest, MemoryJournalResponse,
|
||||
MemoryJournalSelector, SourceConnection, UnconnectedReason,
|
||||
},
|
||||
};
|
||||
|
||||
fn adopt_original(fixture: &Fixture) -> (MemoryRecord, SubjectStagingRecord, StagingResolution) {
|
||||
let evidence_index = session_store::public_index::read_fs_session_evidence_index(
|
||||
fixture.sessions.root_dir(),
|
||||
fixture.context.session_id.parse().unwrap(),
|
||||
session_store::SessionPublicIndexLimits {
|
||||
max_bytes: 8 * 1024 * 1024,
|
||||
max_entries: 20_000,
|
||||
max_segments: 64,
|
||||
},
|
||||
)
|
||||
.unwrap();
|
||||
let range = *evidence_index
|
||||
.ranges
|
||||
.get(&(fixture.segment.to_string(), "Efirst".into()))
|
||||
.unwrap()
|
||||
.first()
|
||||
.unwrap();
|
||||
let staged = fixture
|
||||
.host()
|
||||
.stage_candidate(
|
||||
&fixture.context,
|
||||
MemoryStageCandidateOperation {
|
||||
source: SourceRef {
|
||||
segment_id: fixture.segment.to_string(),
|
||||
range,
|
||||
},
|
||||
extract_run_id: "explicit-test-extraction-input".into(),
|
||||
candidate: ExtractedCandidate {
|
||||
kind: CandidateKind::Preference,
|
||||
claim: "Keep correction history".into(),
|
||||
why_useful: "Preserves the reason for later decisions".into(),
|
||||
staleness: None,
|
||||
evidence_ids: vec!["Efirst".into()],
|
||||
},
|
||||
evidence: vec![StagingEvidence {
|
||||
id: "Efirst".into(),
|
||||
kind: EvidenceKind::new(EvidenceKind::MESSAGE),
|
||||
entry_range: Some(range),
|
||||
origin: None,
|
||||
excerpt: None,
|
||||
summary: None,
|
||||
}],
|
||||
source_refs: vec![SourceEvidenceRef {
|
||||
session_id: Some(fixture.context.session_id.clone()),
|
||||
segment_id: Some(fixture.segment.to_string()),
|
||||
entry_range: Some(range),
|
||||
evidence_id: Some("Efirst".into()),
|
||||
..Default::default()
|
||||
}],
|
||||
},
|
||||
)
|
||||
.unwrap();
|
||||
let store = &fixture.host().catalog.store;
|
||||
let subject = &fixture.connection.binding.subject_id;
|
||||
let candidate = store
|
||||
.staging_candidate(subject, &staged.staging_id)
|
||||
.unwrap()
|
||||
.unwrap();
|
||||
let receipt = store
|
||||
.decide_candidate(
|
||||
subject,
|
||||
CandidateDecisionRequest {
|
||||
request_id: "explicit-test-adoption-input".into(),
|
||||
candidate_id: staged.staging_id,
|
||||
reason: "Adopt the committed original evidence, not the Journal summary".into(),
|
||||
decision: CandidateDecision::Apply {
|
||||
target: MemoryChangeTarget::Create,
|
||||
draft: MemoryDraft::active(
|
||||
CandidateKind::Preference,
|
||||
"Keep correction history",
|
||||
"Preserve earlier decisions and their corrections",
|
||||
"Preserves the reason for later decisions",
|
||||
"Adopt original HumanInput",
|
||||
),
|
||||
},
|
||||
},
|
||||
)
|
||||
.unwrap();
|
||||
(receipt.memory.unwrap(), candidate, receipt.resolution)
|
||||
}
|
||||
|
||||
fn create_entry(adapter: &LocalJournalHost, state: JournalEntryState) -> JournalReceipt {
|
||||
save(
|
||||
adapter,
|
||||
"record-original-context",
|
||||
&adapter.generation.initial_journal.state_token,
|
||||
JournalAction::Create {
|
||||
title: "A proposal was corrected".into(),
|
||||
body: "Proposal A changed to B; only part was performed, outcome unconfirmed.".into(),
|
||||
ongoing: if state == JournalEntryState::Open {
|
||||
"Remaining work is not complete".into()
|
||||
} else {
|
||||
String::new()
|
||||
},
|
||||
state,
|
||||
source_end: (state == JournalEntryState::Fixed).then(|| {
|
||||
adapter
|
||||
.generation
|
||||
.selected_ranges
|
||||
.last()
|
||||
.unwrap()
|
||||
.source
|
||||
.pointer
|
||||
.clone()
|
||||
}),
|
||||
correction_refs: vec![],
|
||||
},
|
||||
adapter.generation.selected_ranges.clone(),
|
||||
)
|
||||
}
|
||||
|
||||
fn assert_originals_unchanged(
|
||||
fixture: &Fixture,
|
||||
memory: &MemoryRecord,
|
||||
candidate: &SubjectStagingRecord,
|
||||
resolution: &StagingResolution,
|
||||
) {
|
||||
let catalog = StandaloneSubjects::open_existing(&fixture.host().catalog.state_root).unwrap();
|
||||
let store = &catalog.store;
|
||||
let subject = &fixture.connection.binding.subject_id;
|
||||
assert_eq!(
|
||||
serde_json::to_value(store.memory(subject, &memory.id).unwrap().unwrap()).unwrap(),
|
||||
serde_json::to_value(memory).unwrap(),
|
||||
);
|
||||
assert_eq!(
|
||||
serde_json::to_value(
|
||||
store
|
||||
.staging_candidate(subject, &candidate.id)
|
||||
.unwrap()
|
||||
.unwrap()
|
||||
)
|
||||
.unwrap(),
|
||||
serde_json::to_value(candidate).unwrap(),
|
||||
);
|
||||
assert_eq!(
|
||||
serde_json::to_value(
|
||||
store
|
||||
.staging_resolution(subject, &candidate.id)
|
||||
.unwrap()
|
||||
.unwrap()
|
||||
)
|
||||
.unwrap(),
|
||||
serde_json::to_value(resolution).unwrap(),
|
||||
);
|
||||
assert_eq!(store.list_memories(subject).unwrap().len(), 1);
|
||||
}
|
||||
|
||||
fn selector(memory: &MemoryRecord, candidate: &SubjectStagingRecord) -> MemoryJournalSelector {
|
||||
MemoryJournalSelector {
|
||||
memory_id: memory.id.clone(),
|
||||
change_id: memory.change_id.clone(),
|
||||
candidate_id: candidate.id.clone(),
|
||||
}
|
||||
}
|
||||
|
||||
fn links(
|
||||
fixture: &Fixture,
|
||||
selector: &MemoryJournalSelector,
|
||||
reconcile: bool,
|
||||
) -> MemoryJournalLinks {
|
||||
let request = if reconcile {
|
||||
MemoryJournalRequest::Reconcile {
|
||||
selector: selector.clone(),
|
||||
}
|
||||
} else {
|
||||
MemoryJournalRequest::Links {
|
||||
selector: selector.clone(),
|
||||
}
|
||||
};
|
||||
let MemoryJournalResponse::Links(links) = fixture
|
||||
.host()
|
||||
.memory_journal(&fixture.context, request)
|
||||
.unwrap()
|
||||
else {
|
||||
panic!("expected Memory Journal links")
|
||||
};
|
||||
links
|
||||
}
|
||||
|
||||
fn read_request(
|
||||
selector: &MemoryJournalSelector,
|
||||
journal: &str,
|
||||
entry: &str,
|
||||
) -> MemoryJournalRequest {
|
||||
MemoryJournalRequest::Read {
|
||||
selector: selector.clone(),
|
||||
source_index: 0,
|
||||
journal_id: journal.into(),
|
||||
entry_id: entry.into(),
|
||||
expected_token: None,
|
||||
byte_offset: 0,
|
||||
max_bytes: MAX_JOURNAL_READ_BYTES,
|
||||
}
|
||||
}
|
||||
|
||||
fn assert_link(links: &MemoryJournalLinks, journal: &str, entry: &str, reconsideration: bool) {
|
||||
assert_eq!(links.sources.len(), 1);
|
||||
assert_eq!(links.sources[0].source_index, 0);
|
||||
assert_eq!(
|
||||
links.sources[0].connection,
|
||||
SourceConnection::Linked {
|
||||
journal_id: journal.into(),
|
||||
entry_id: entry.into(),
|
||||
target: JournalTargetAvailability::Available,
|
||||
reconsideration,
|
||||
},
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn saved_link_reads_after_original_worker_and_session_deletion_from_replacement_host() {
|
||||
let mut fixture = Fixture::new("Please preserve the reasons for my corrected decisions");
|
||||
let (memory, candidate, resolution) = adopt_original(&fixture);
|
||||
let selector = selector(&memory, &candidate);
|
||||
assert_eq!(
|
||||
candidate.evidence[0].origin.as_ref().unwrap().kind,
|
||||
EvidenceOriginKind::HumanInput
|
||||
);
|
||||
assert_eq!(
|
||||
candidate.source_refs[0].origin,
|
||||
candidate.evidence[0].origin
|
||||
);
|
||||
assert!(
|
||||
candidate.evidence[0]
|
||||
.excerpt
|
||||
.as_ref()
|
||||
.unwrap()
|
||||
.contains("corrected decisions")
|
||||
);
|
||||
let (adapter, _, _) = fixture.adapter();
|
||||
let recorded = create_entry(&adapter, JournalEntryState::Fixed);
|
||||
let entry = recorded.entry_id.clone().unwrap();
|
||||
let journal = adapter.grant.journal_id.clone();
|
||||
let connected = links(&fixture, &selector, true);
|
||||
assert_link(&connected, &journal, &entry, false);
|
||||
let request = read_request(&selector, &journal, &entry);
|
||||
let before = fixture
|
||||
.host()
|
||||
.memory_journal(&fixture.context, request.clone())
|
||||
.unwrap();
|
||||
let positioned = save(
|
||||
&adapter,
|
||||
"position-original",
|
||||
&recorded.state_token,
|
||||
JournalAction::UpdatePosition {
|
||||
current_position: "Recorded correction; remaining outcome unconfirmed".into(),
|
||||
},
|
||||
vec![],
|
||||
);
|
||||
save(
|
||||
&adapter,
|
||||
"checkpoint-original",
|
||||
&positioned.state_token,
|
||||
JournalAction::Checkpoint {
|
||||
record_operation_ids: vec![recorded.request_id],
|
||||
},
|
||||
adapter.generation.selected_ranges.clone(),
|
||||
);
|
||||
adapter.finish().unwrap();
|
||||
fixture
|
||||
.host()
|
||||
.catalog
|
||||
.store
|
||||
.close_journal_generation(
|
||||
&adapter.context,
|
||||
&adapter.generation.id,
|
||||
&adapter.generation.job,
|
||||
)
|
||||
.unwrap();
|
||||
let state = fixture.host().catalog.state_root.clone();
|
||||
let subject = fixture.connection.binding.subject_id.clone();
|
||||
let original_session = fixture.context.session_id.clone();
|
||||
// This Host/storage suite has no Controller. Complete the explicit persisted
|
||||
// writer-release boundary before deletion; the sibling handoff suite exercises
|
||||
// the production Idle reservation + Host lifecycle that authorizes that release.
|
||||
fixture
|
||||
.host()
|
||||
.catalog
|
||||
.store
|
||||
.release_journal_writer(&fixture.host().writer)
|
||||
.unwrap();
|
||||
let (worker, workers) = fixture.stop_worker();
|
||||
workers.delete(worker).unwrap();
|
||||
assert!(matches!(
|
||||
workers.load(worker),
|
||||
Err(crate::store::StandaloneStoreError::WorkerNotFound(_))
|
||||
));
|
||||
assert!(!fixture.sessions.root_dir().join(&original_session).exists());
|
||||
assert!(
|
||||
!retained_workers_root(&state)
|
||||
.join(worker.to_string())
|
||||
.exists()
|
||||
);
|
||||
|
||||
let replacement_worker = protocol::WorkerId::now_v7();
|
||||
let mut replacement = StandaloneSubjects::open_existing(&state)
|
||||
.unwrap()
|
||||
.connect(&subject, replacement_worker)
|
||||
.unwrap();
|
||||
let replacement_context = SubjektivHostContext {
|
||||
worker_id: replacement_worker.to_string(),
|
||||
session_id: session_store::SessionId::now_v7().to_string(),
|
||||
};
|
||||
let MemoryJournalResponse::Links(saved) = replacement
|
||||
.host
|
||||
.memory_journal(
|
||||
&replacement_context,
|
||||
MemoryJournalRequest::Links {
|
||||
selector: selector.clone(),
|
||||
},
|
||||
)
|
||||
.unwrap()
|
||||
else {
|
||||
panic!("expected saved links")
|
||||
};
|
||||
assert_link(&saved, &journal, &entry, false);
|
||||
let after = replacement
|
||||
.host
|
||||
.memory_journal(&replacement_context, request)
|
||||
.unwrap();
|
||||
let MemoryJournalResponse::Read(read) = &after else {
|
||||
panic!("expected saved Journal text")
|
||||
};
|
||||
assert!(
|
||||
read.page
|
||||
.as_ref()
|
||||
.unwrap()
|
||||
.text
|
||||
.contains("outcome unconfirmed")
|
||||
);
|
||||
assert_eq!(
|
||||
read.source.original_source,
|
||||
subjektiv::journal::memory_links::OriginalSourceAvailability::Missing
|
||||
);
|
||||
// Reading the saved edge does not depend on a live Session fetch or a replacement Job.
|
||||
let MemoryJournalResponse::Read(before) = before else {
|
||||
panic!("expected Journal text")
|
||||
};
|
||||
assert_eq!(before.page, read.page);
|
||||
assert!(
|
||||
replacement.host.jobs().is_err(),
|
||||
"the reader has no model/Job executor"
|
||||
);
|
||||
assert_originals_unchanged(&fixture, &memory, &candidate, &resolution);
|
||||
replacement.close().unwrap();
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn late_journal_fix_connects_existing_memory_without_using_checkpoint_as_event_end() {
|
||||
let fixture = Fixture::new("Keep the reasons behind corrected decisions");
|
||||
let (memory, candidate, resolution) = adopt_original(&fixture);
|
||||
let selector = selector(&memory, &candidate);
|
||||
assert_eq!(
|
||||
links(&fixture, &selector, false).sources[0].connection,
|
||||
SourceConnection::Unconnected {
|
||||
reason: UnconnectedReason::NotReconciled
|
||||
}
|
||||
);
|
||||
assert_eq!(
|
||||
links(&fixture, &selector, true).sources[0].connection,
|
||||
SourceConnection::Unconnected {
|
||||
reason: UnconnectedReason::SourceNotAdmitted
|
||||
}
|
||||
);
|
||||
let (adapter, _, _) = fixture.adapter();
|
||||
let recorded = create_entry(&adapter, JournalEntryState::Open);
|
||||
let entry = recorded.entry_id.clone().unwrap();
|
||||
let positioned = save(
|
||||
&adapter,
|
||||
"position-open",
|
||||
&recorded.state_token,
|
||||
JournalAction::UpdatePosition {
|
||||
current_position: "Work remains open; no fixed endpoint yet".into(),
|
||||
},
|
||||
vec![],
|
||||
);
|
||||
// Checkpoint a proper prefix, leaving source bytes for the later Fix.
|
||||
// A fully checkpointed generation cannot admit another activity write.
|
||||
let mut reflected = adapter.generation.selected_ranges.clone();
|
||||
reflected.last_mut().unwrap().bytes.end -= 1;
|
||||
let checkpoint = save(
|
||||
&adapter,
|
||||
"checkpoint-open",
|
||||
&positioned.state_token,
|
||||
JournalAction::Checkpoint {
|
||||
record_operation_ids: vec![recorded.request_id],
|
||||
},
|
||||
reflected.clone(),
|
||||
);
|
||||
let unconnected = links(&fixture, &selector, true);
|
||||
assert_eq!(
|
||||
unconnected.sources[0].connection,
|
||||
SourceConnection::Unconnected {
|
||||
reason: UnconnectedReason::JournalNotFixed
|
||||
}
|
||||
);
|
||||
assert_eq!(links(&fixture, &selector, true), unconnected);
|
||||
let state = adapter.state().unwrap();
|
||||
let open = state.current_open.unwrap();
|
||||
assert_eq!(open.id, entry);
|
||||
assert_eq!(open.state, JournalEntryState::Open);
|
||||
assert!(open.source_end.is_none());
|
||||
let last = reflected.last().unwrap();
|
||||
assert_eq!(state.current_journal.process_order, last.source.order);
|
||||
assert_eq!(state.current_journal.process_byte, last.bytes.end);
|
||||
save(
|
||||
&adapter,
|
||||
"fix-later",
|
||||
&checkpoint.state_token,
|
||||
JournalAction::Fix {
|
||||
entry_id: entry.clone(),
|
||||
source_end: adapter
|
||||
.generation
|
||||
.selected_ranges
|
||||
.last()
|
||||
.unwrap()
|
||||
.source
|
||||
.pointer
|
||||
.clone(),
|
||||
},
|
||||
adapter.generation.selected_ranges.clone(),
|
||||
);
|
||||
// A plain saved-state read must not silently perform reconciliation.
|
||||
assert_eq!(links(&fixture, &selector, false), unconnected);
|
||||
let connected = links(&fixture, &selector, true);
|
||||
assert_link(&connected, &adapter.grant.journal_id, &entry, false);
|
||||
assert_eq!(links(&fixture, &selector, true), connected);
|
||||
assert_eq!(links(&fixture, &selector, false), connected);
|
||||
assert_originals_unchanged(&fixture, &memory, &candidate, &resolution);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn host_rejects_foreign_subject_worker_context_and_closed_connection_for_all_link_operations() {
|
||||
let mut fixture = Fixture::new("Keep correction history");
|
||||
let (memory, candidate, resolution) = adopt_original(&fixture);
|
||||
let selector = selector(&memory, &candidate);
|
||||
let (adapter, _, _) = fixture.adapter();
|
||||
let recorded = create_entry(&adapter, JournalEntryState::Fixed);
|
||||
let journal = adapter.grant.journal_id.clone();
|
||||
let entry = recorded.entry_id.unwrap();
|
||||
assert_link(&links(&fixture, &selector, true), &journal, &entry, false);
|
||||
let requests = [
|
||||
MemoryJournalRequest::Reconcile {
|
||||
selector: selector.clone(),
|
||||
},
|
||||
MemoryJournalRequest::Links {
|
||||
selector: selector.clone(),
|
||||
},
|
||||
read_request(&selector, &journal, &entry),
|
||||
MemoryJournalRequest::Related {
|
||||
journal_id: journal,
|
||||
entry_id: entry,
|
||||
after: None,
|
||||
limit: 32,
|
||||
},
|
||||
];
|
||||
let catalog = StandaloneSubjects::open_existing(&fixture.host().catalog.state_root).unwrap();
|
||||
let foreign_subject = catalog.create("different-reader", None).unwrap();
|
||||
let foreign_worker = protocol::WorkerId::now_v7();
|
||||
let mut foreign = catalog
|
||||
.connect(&foreign_subject.id, foreign_worker)
|
||||
.unwrap();
|
||||
let foreign_context = SubjektivHostContext {
|
||||
worker_id: foreign_worker.to_string(),
|
||||
session_id: session_store::SessionId::now_v7().to_string(),
|
||||
};
|
||||
let wrong_worker = SubjektivHostContext {
|
||||
worker_id: foreign_worker.to_string(),
|
||||
..fixture.context.clone()
|
||||
};
|
||||
for request in &requests {
|
||||
assert!(
|
||||
foreign
|
||||
.host
|
||||
.memory_journal(&foreign_context, request.clone())
|
||||
.is_err()
|
||||
);
|
||||
assert!(
|
||||
fixture
|
||||
.host()
|
||||
.memory_journal(&wrong_worker, request.clone())
|
||||
.is_err()
|
||||
);
|
||||
}
|
||||
foreign.close().unwrap();
|
||||
fixture.connection.close().unwrap();
|
||||
for request in requests {
|
||||
assert!(
|
||||
fixture
|
||||
.host()
|
||||
.memory_journal(&fixture.context, request)
|
||||
.is_err()
|
||||
);
|
||||
}
|
||||
assert_originals_unchanged(&fixture, &memory, &candidate, &resolution);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn journal_correction_finds_related_memory_without_revising_or_retargeting_its_evidence() {
|
||||
let fixture = Fixture::new("Keep correction history");
|
||||
let (memory, candidate, resolution) = adopt_original(&fixture);
|
||||
let selector = selector(&memory, &candidate);
|
||||
fixture.append("correction", "The earlier result was not confirmed");
|
||||
let (adapter, _, _) = fixture.adapter();
|
||||
let ranges = &adapter.generation.selected_ranges;
|
||||
assert_eq!(ranges.len(), 2);
|
||||
let original = save(
|
||||
&adapter,
|
||||
"original-event",
|
||||
&adapter.generation.initial_journal.state_token,
|
||||
JournalAction::Create {
|
||||
title: "Original context".into(),
|
||||
body: "A change was proposed; execution remained uncertain".into(),
|
||||
ongoing: String::new(),
|
||||
state: JournalEntryState::Fixed,
|
||||
source_end: Some(ranges[0].source.pointer.clone()),
|
||||
correction_refs: vec![],
|
||||
},
|
||||
vec![ranges[0].clone()],
|
||||
);
|
||||
let entry = original.entry_id.unwrap();
|
||||
let journal = &adapter.grant.journal_id;
|
||||
assert_link(&links(&fixture, &selector, true), journal, &entry, false);
|
||||
let corrected = save(
|
||||
&adapter,
|
||||
"correction-event",
|
||||
&original.state_token,
|
||||
JournalAction::Create {
|
||||
title: "Correction".into(),
|
||||
body: "The earlier result was unconfirmed; reconsider its associated Memory".into(),
|
||||
ongoing: String::new(),
|
||||
state: JournalEntryState::Fixed,
|
||||
source_end: Some(ranges[1].source.pointer.clone()),
|
||||
correction_refs: vec![entry.clone()],
|
||||
},
|
||||
vec![ranges[1].clone()],
|
||||
);
|
||||
assert_link(&links(&fixture, &selector, false), journal, &entry, true);
|
||||
let correction_entry = corrected.entry_id.unwrap();
|
||||
for target in [&entry, &correction_entry] {
|
||||
let MemoryJournalResponse::Related(related) = fixture
|
||||
.host()
|
||||
.memory_journal(
|
||||
&fixture.context,
|
||||
MemoryJournalRequest::Related {
|
||||
journal_id: journal.clone(),
|
||||
entry_id: target.clone(),
|
||||
after: None,
|
||||
limit: 32,
|
||||
},
|
||||
)
|
||||
.unwrap()
|
||||
else {
|
||||
panic!("expected related Memory")
|
||||
};
|
||||
assert_eq!(related.items.len(), 1);
|
||||
assert_eq!(related.items[0].selector, selector);
|
||||
assert_eq!(related.items[0].source_index, 0);
|
||||
assert!(related.items[0].reconsideration);
|
||||
assert!(related.next.is_none());
|
||||
}
|
||||
let MemoryJournalResponse::Read(read) = fixture
|
||||
.host()
|
||||
.memory_journal(&fixture.context, read_request(&selector, journal, &entry))
|
||||
.unwrap()
|
||||
else {
|
||||
panic!("expected original context")
|
||||
};
|
||||
assert!(
|
||||
read.page
|
||||
.unwrap()
|
||||
.text
|
||||
.contains("execution remained uncertain")
|
||||
);
|
||||
assert_originals_unchanged(&fixture, &memory, &candidate, &resolution);
|
||||
}
|
||||
@@ -37,9 +37,8 @@ fn subject_kernel_lease_is_not_worker_or_profile_scoped() {
|
||||
let catalog = StandaloneSubjects::open(temp.path().join("state")).unwrap();
|
||||
let a = catalog.create("a", None).unwrap();
|
||||
let b = catalog.create("b", None).unwrap();
|
||||
let mut first = catalog
|
||||
.connect(&a.id, protocol::WorkerId::now_v7())
|
||||
.unwrap();
|
||||
let first_id = protocol::WorkerId::now_v7();
|
||||
let mut first = catalog.connect(&a.id, first_id).unwrap();
|
||||
assert!(matches!(
|
||||
StandaloneSubjects::open_existing(&temp.path().join("state"))
|
||||
.unwrap()
|
||||
@@ -51,11 +50,18 @@ fn subject_kernel_lease_is_not_worker_or_profile_scoped() {
|
||||
.connect(&b.id, protocol::WorkerId::now_v7())
|
||||
.unwrap();
|
||||
first.close().unwrap();
|
||||
let mut replacement = StandaloneSubjects::open_existing(&temp.path().join("state"))
|
||||
assert!(
|
||||
StandaloneSubjects::open_existing(&temp.path().join("state"))
|
||||
.unwrap()
|
||||
.connect(&a.id, protocol::WorkerId::now_v7())
|
||||
.is_err(),
|
||||
"kernel lease release is not durable body release"
|
||||
);
|
||||
let mut resumed = StandaloneSubjects::open_existing(&temp.path().join("state"))
|
||||
.unwrap()
|
||||
.connect(&a.id, protocol::WorkerId::now_v7())
|
||||
.connect(&a.id, first_id)
|
||||
.unwrap();
|
||||
replacement.close().unwrap();
|
||||
resumed.close().unwrap();
|
||||
second.close().unwrap();
|
||||
}
|
||||
|
||||
|
||||
@@ -155,6 +155,81 @@ pub(crate) fn authorized_index(
|
||||
)
|
||||
}
|
||||
|
||||
pub(crate) fn authorized_sessions_path(
|
||||
state_root: &Path,
|
||||
scope_id: &str,
|
||||
subject_id: &str,
|
||||
store: &SubjektivStore,
|
||||
session_id: &str,
|
||||
) -> Result<PathBuf, SubjektivHostError> {
|
||||
let backend = Backend {
|
||||
state_root,
|
||||
scope_id,
|
||||
subject_id,
|
||||
store,
|
||||
reader: session_store::public_index::read_fs_session_public_index,
|
||||
};
|
||||
(|| {
|
||||
backend.check_scope()?;
|
||||
required_selector(session_id)?;
|
||||
let attribution = backend.attribution(session_id)?;
|
||||
Ok(backend.authorize(attribution)?.sessions_path)
|
||||
})()
|
||||
.map_err(|error: Failure| SubjektivHostError::Unavailable(error.message))
|
||||
}
|
||||
|
||||
/// Checks only saved ownership and filesystem metadata, never Session bytes or a Worker restore.
|
||||
/// Inaccessible/corrupt storage stays unknown rather than being reported as absent.
|
||||
pub(crate) fn original_session_presence(
|
||||
state_root: &Path,
|
||||
scope_id: &str,
|
||||
subject_id: &str,
|
||||
store: &SubjektivStore,
|
||||
session_id: &str,
|
||||
) -> Option<bool> {
|
||||
let attribution = store.session_attribution(session_id).ok()??;
|
||||
if store.scope_id() != scope_id
|
||||
|| attribution.subject_id != subject_id
|
||||
|| attribution.runtime_id != scope_id
|
||||
{
|
||||
return None;
|
||||
}
|
||||
let worker: WorkerId = attribution.worker_id.parse().ok()?;
|
||||
let session: SessionId = session_id.parse().ok()?;
|
||||
let active = StandaloneWorkerStore::open_existing(state_root).ok()?;
|
||||
let (workers, record) = match active.load(worker) {
|
||||
Ok(record) => (active, record),
|
||||
Err(StandaloneStoreError::WorkerNotFound(_)) => {
|
||||
let root = state_root.join("subjektiv").join("retained-workers");
|
||||
match std::fs::metadata(&root) {
|
||||
Err(error) if error.kind() == std::io::ErrorKind::NotFound => return Some(false),
|
||||
Err(_) => return None,
|
||||
Ok(_) => {}
|
||||
}
|
||||
let retained = StandaloneWorkerStore::open_existing(root).ok()?;
|
||||
match retained.load(worker) {
|
||||
Ok(record) => (retained, record),
|
||||
Err(StandaloneStoreError::WorkerNotFound(_)) => return Some(false),
|
||||
Err(_) => return None,
|
||||
}
|
||||
}
|
||||
Err(_) => return None,
|
||||
};
|
||||
if record.worker_id != worker
|
||||
|| !record
|
||||
.subject
|
||||
.as_ref()
|
||||
.is_some_and(|binding| binding.scope_id == scope_id && binding.subject_id == subject_id)
|
||||
{
|
||||
return None;
|
||||
}
|
||||
match std::fs::metadata(workers.sessions_dir(worker).join(session.to_string())) {
|
||||
Ok(metadata) if metadata.is_dir() => Some(true),
|
||||
Err(error) if error.kind() == std::io::ErrorKind::NotFound => Some(false),
|
||||
_ => None,
|
||||
}
|
||||
}
|
||||
|
||||
fn authorized_index_with_reader(
|
||||
state_root: &Path,
|
||||
scope_id: &str,
|
||||
@@ -221,13 +296,28 @@ impl Backend<'_> {
|
||||
"Attributed standalone Worker state is missing",
|
||||
));
|
||||
}
|
||||
let workers = StandaloneWorkerStore::open_existing(self.state_root).map_err(|_| {
|
||||
let mut workers = StandaloneWorkerStore::open_existing(self.state_root).map_err(|_| {
|
||||
failure(
|
||||
SubjektivSessionDiagnosticCode::RuntimeUnavailable,
|
||||
"Standalone Worker storage is inaccessible",
|
||||
)
|
||||
})?;
|
||||
let record = workers.load(id).map_err(|error| match error {
|
||||
let record = match workers.load(id) {
|
||||
Err(StandaloneStoreError::WorkerNotFound(_)) => {
|
||||
workers = StandaloneWorkerStore::open_existing(
|
||||
self.state_root.join("subjektiv").join("retained-workers"),
|
||||
)
|
||||
.map_err(|_| {
|
||||
failure(
|
||||
SubjektivSessionDiagnosticCode::RetentionMissing,
|
||||
"Original Session is not retained",
|
||||
)
|
||||
})?;
|
||||
workers.load(id)
|
||||
}
|
||||
result => result,
|
||||
}
|
||||
.map_err(|error| match error {
|
||||
StandaloneStoreError::WorkerNotFound(_) => failure(
|
||||
SubjektivSessionDiagnosticCode::RetentionMissing,
|
||||
"Attributed standalone Worker record is missing",
|
||||
@@ -262,6 +352,13 @@ impl Backend<'_> {
|
||||
"Attributed Session identity is invalid",
|
||||
)
|
||||
})?;
|
||||
let retention = crate::store::session_retention(self.state_root);
|
||||
let _guard = retention.lock_live(id).map_err(|_| {
|
||||
failure(
|
||||
SubjektivSessionDiagnosticCode::RetentionMissing,
|
||||
"Original Session is erased or its retention fence is unavailable",
|
||||
)
|
||||
})?;
|
||||
let index = (self.reader)(&source.sessions_path, id, limits).map_err(index_failure)?;
|
||||
if index.session_id != source.attribution.session_id {
|
||||
return Err(failure(
|
||||
@@ -1524,6 +1621,7 @@ allow = []
|
||||
let history = |id: &str, item: LoggedItem| LoggedHistoryEntry {
|
||||
item,
|
||||
metadata: LoggedSessionHistoryMetadata {
|
||||
input_metadata: None,
|
||||
entry_id: LoggedSessionHistoryEntryId(id.into()),
|
||||
origin: LoggedSessionHistoryOrigin::BackendInstruction { operation_id: None },
|
||||
derivation: None,
|
||||
@@ -1539,7 +1637,11 @@ allow = []
|
||||
)
|
||||
};
|
||||
let sessions = f.index_path.parent().unwrap();
|
||||
let fs_store = session_store::FsStore::new(sessions).unwrap();
|
||||
let fs_store = session_store::FsStore::new_with_retention(
|
||||
sessions,
|
||||
crate::store::session_retention(&f.temp.path().join("workers")),
|
||||
)
|
||||
.unwrap();
|
||||
let segment: SessionId = f.segment.parse().unwrap();
|
||||
fs_store
|
||||
.create_segment(
|
||||
@@ -1592,6 +1694,7 @@ allow = []
|
||||
// A valid JSON record without its final newline is not committed.
|
||||
log.write_all(
|
||||
&serde_json::to_vec(&LogEntry::RunCompleted {
|
||||
entry_id: None,
|
||||
ts: 4,
|
||||
interrupted: false,
|
||||
result: agen::EngineResult::Finished,
|
||||
|
||||
@@ -0,0 +1,296 @@
|
||||
//! Optional operator transport owned by the Standalone Host, never by a Worker.
|
||||
//!
|
||||
//! The endpoint's existing parent must be private to the current Unix user. Binding never
|
||||
//! removes an existing entry, including stale sockets. Recovery is an explicit operator action.
|
||||
//! Peers must have that same uid; admitted methods still cross the normal local protocol
|
||||
//! authorization boundary. Disconnect only drops a view, not the Host or its execution lease.
|
||||
|
||||
use std::io;
|
||||
use std::os::unix::fs::{FileTypeExt, MetadataExt, PermissionsExt};
|
||||
use std::path::{Path, PathBuf};
|
||||
|
||||
use client::transport::Socket;
|
||||
use protocol::stream::{JsonLineWriter, decode_event, decode_method};
|
||||
use tokio::io::{AsyncBufReadExt, BufReader};
|
||||
use tokio::net::{UnixListener, UnixStream};
|
||||
use tokio::sync::oneshot;
|
||||
use tokio::task::{JoinHandle, JoinSet};
|
||||
|
||||
/// A bound endpoint reservation. Drop removes only the exact socket created by this bind.
|
||||
/// It can be reserved before starting a Host, so bind failures do not allocate Workers.
|
||||
pub struct UnixEndpoint {
|
||||
listener: UnixListener,
|
||||
path: PathBuf,
|
||||
device: u64,
|
||||
inode: u64,
|
||||
}
|
||||
|
||||
impl UnixEndpoint {
|
||||
pub fn bind(path: impl AsRef<Path>) -> io::Result<Self> {
|
||||
let path = path.as_ref();
|
||||
let name = path.file_name().ok_or_else(|| {
|
||||
io::Error::new(io::ErrorKind::InvalidInput, "endpoint requires a filename")
|
||||
})?;
|
||||
let parent = std::fs::canonicalize(
|
||||
path.parent()
|
||||
.filter(|p| !p.as_os_str().is_empty())
|
||||
.unwrap_or(Path::new(".")),
|
||||
)?;
|
||||
let metadata = std::fs::metadata(&parent)?;
|
||||
// SAFETY: geteuid has no preconditions and does not mutate process identity.
|
||||
let uid = unsafe { libc::geteuid() };
|
||||
if !metadata.is_dir() || metadata.uid() != uid || metadata.mode() & 0o077 != 0 {
|
||||
return Err(io::Error::new(
|
||||
io::ErrorKind::PermissionDenied,
|
||||
"endpoint parent must be a current-user-owned private directory (mode 0700)",
|
||||
));
|
||||
}
|
||||
let path = parent.join(name);
|
||||
let listener = UnixListener::bind(&path)?;
|
||||
let metadata = std::fs::symlink_metadata(&path)?;
|
||||
let endpoint = Self {
|
||||
listener,
|
||||
path,
|
||||
device: metadata.dev(),
|
||||
inode: metadata.ino(),
|
||||
};
|
||||
std::fs::set_permissions(&endpoint.path, std::fs::Permissions::from_mode(0o600))?;
|
||||
Ok(endpoint)
|
||||
}
|
||||
|
||||
pub fn path(&self) -> &Path {
|
||||
&self.path
|
||||
}
|
||||
}
|
||||
|
||||
impl Drop for UnixEndpoint {
|
||||
fn drop(&mut self) {
|
||||
if let Ok(current) = std::fs::symlink_metadata(&self.path)
|
||||
&& current.file_type().is_socket()
|
||||
&& current.dev() == self.device
|
||||
&& current.ino() == self.inode
|
||||
{
|
||||
let _ = std::fs::remove_file(&self.path);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
pub(crate) struct UnixAdapter {
|
||||
task: Option<JoinHandle<io::Result<()>>>,
|
||||
stop: Option<oneshot::Sender<()>>,
|
||||
}
|
||||
|
||||
impl UnixAdapter {
|
||||
pub(crate) fn start(endpoint: UnixEndpoint, handle: worker::WorkerHandle) -> Self {
|
||||
let (stop, mut stopped) = oneshot::channel();
|
||||
let task = tokio::spawn(async move {
|
||||
let mut connections = JoinSet::new();
|
||||
let result = loop {
|
||||
tokio::select! {
|
||||
_ = &mut stopped => break Ok(()),
|
||||
accepted = endpoint.listener.accept(), if connections.len() < 64 => {
|
||||
match accepted {
|
||||
Ok((stream, _)) => {
|
||||
// The filesystem gate protects connection establishment; credentials
|
||||
// also fence open connections to the Host's operator identity.
|
||||
let allowed = stream.peer_cred().is_ok_and(|cred| {
|
||||
// SAFETY: geteuid has no preconditions.
|
||||
cred.uid() == unsafe { libc::geteuid() }
|
||||
});
|
||||
if allowed {
|
||||
let socket = crate::host::connect_protocol(handle.clone());
|
||||
connections.spawn(bridge(stream, socket));
|
||||
}
|
||||
}
|
||||
Err(error) => break Err(error),
|
||||
}
|
||||
}
|
||||
_ = connections.join_next(), if !connections.is_empty() => {}
|
||||
}
|
||||
};
|
||||
connections.shutdown().await;
|
||||
// Keep the bound endpoint alive until every connection has been reclaimed.
|
||||
drop(endpoint);
|
||||
result
|
||||
});
|
||||
Self {
|
||||
task: Some(task),
|
||||
stop: Some(stop),
|
||||
}
|
||||
}
|
||||
|
||||
pub(crate) async fn ended(&mut self) -> io::Result<()> {
|
||||
let result = self.task.as_mut().expect("adapter task").await;
|
||||
self.task.take();
|
||||
result.map_err(io::Error::other)?
|
||||
}
|
||||
|
||||
pub(crate) async fn shutdown(mut self) -> io::Result<()> {
|
||||
if let Some(stop) = self.stop.take() {
|
||||
let _ = stop.send(());
|
||||
}
|
||||
if self.task.is_some() {
|
||||
self.ended().await?;
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
}
|
||||
|
||||
impl Drop for UnixAdapter {
|
||||
fn drop(&mut self) {
|
||||
if let Some(stop) = self.stop.take() {
|
||||
let _ = stop.send(());
|
||||
}
|
||||
// Sending stop lets the task join its connection set and drop its endpoint.
|
||||
// A Host dropped without confirmed shutdown keeps the production execution lease.
|
||||
}
|
||||
}
|
||||
|
||||
async fn bridge(
|
||||
stream: UnixStream,
|
||||
mut socket: client::transport::in_process::Socket,
|
||||
) -> io::Result<()> {
|
||||
let (reader, writer) = stream.into_split();
|
||||
let mut reader = BufReader::new(reader).lines();
|
||||
let mut writer = JsonLineWriter::new(writer);
|
||||
loop {
|
||||
tokio::select! {
|
||||
line = reader.next_line() => {
|
||||
let Some(message) = line? else { return Ok(()); };
|
||||
if message.trim().is_empty() { continue; }
|
||||
socket.send(message).await.map_err(io::Error::other)?;
|
||||
}
|
||||
event = socket.next() => {
|
||||
let Some(message) = event.map_err(io::Error::other)? else { return Ok(()); };
|
||||
let event = decode_event(&message).map_err(io::Error::other)?;
|
||||
writer.write_event(&event).await?;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Connect a JSONL operator client. EOF disconnects without issuing Shutdown.
|
||||
/// Input is decoded as Worker Methods and output contains Worker Events only.
|
||||
pub async fn run_unix_client(endpoint: PathBuf) -> io::Result<()> {
|
||||
relay_unix_client(endpoint, tokio::io::stdin(), tokio::io::stdout()).await
|
||||
}
|
||||
|
||||
/// The CLI's stream relay, also usable by embedders that own their input/output streams.
|
||||
pub async fn relay_unix_client<R, W>(endpoint: PathBuf, input: R, output: W) -> io::Result<()>
|
||||
where
|
||||
R: tokio::io::AsyncRead + Unpin,
|
||||
W: tokio::io::AsyncWrite + Unpin,
|
||||
{
|
||||
let stream = UnixStream::connect(endpoint).await?;
|
||||
let (reader, writer) = stream.into_split();
|
||||
let mut input = BufReader::new(input).lines();
|
||||
let mut to_host = JsonLineWriter::new(writer);
|
||||
let mut from_host = BufReader::new(reader).lines();
|
||||
let mut output = JsonLineWriter::new(output);
|
||||
loop {
|
||||
tokio::select! {
|
||||
line = input.next_line() => {
|
||||
let Some(line) = line? else { return Ok(()); };
|
||||
if line.trim().is_empty() { continue; }
|
||||
let method = decode_method(&line).map_err(io::Error::other)?;
|
||||
to_host.write(&method).await?;
|
||||
}
|
||||
line = from_host.next_line() => {
|
||||
let Some(line) = line? else { return Ok(()); };
|
||||
let event = decode_event(&line).map_err(io::Error::other)?;
|
||||
output.write_event(&event).await?;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
#[tokio::test]
|
||||
async fn endpoint_requires_private_parent_and_is_owner_only() {
|
||||
let directory = tempfile::tempdir().unwrap();
|
||||
let path = directory.path().join("host.sock");
|
||||
std::fs::set_permissions(directory.path(), std::fs::Permissions::from_mode(0o755)).unwrap();
|
||||
let error = UnixEndpoint::bind(&path)
|
||||
.err()
|
||||
.expect("public parent rejected");
|
||||
assert_eq!(error.kind(), io::ErrorKind::PermissionDenied);
|
||||
assert!(!path.exists());
|
||||
std::fs::set_permissions(directory.path(), std::fs::Permissions::from_mode(0o700)).unwrap();
|
||||
let endpoint = UnixEndpoint::bind(&path).unwrap();
|
||||
assert_eq!(
|
||||
std::fs::metadata(&path).unwrap().permissions().mode() & 0o777,
|
||||
0o600
|
||||
);
|
||||
let client = UnixStream::connect(&path).await.unwrap();
|
||||
let (server, _) = endpoint.listener.accept().await.unwrap();
|
||||
assert_eq!(
|
||||
client.peer_cred().unwrap().uid(),
|
||||
server.peer_cred().unwrap().uid()
|
||||
);
|
||||
drop(endpoint);
|
||||
assert!(!path.exists());
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn bind_failure_precedes_worker_state_and_startup_failure_releases_only_its_endpoint() {
|
||||
let directory = tempfile::tempdir().unwrap();
|
||||
std::fs::set_permissions(directory.path(), std::fs::Permissions::from_mode(0o700)).unwrap();
|
||||
let path = directory.path().join("host.sock");
|
||||
let owner = UnixEndpoint::bind(&path).unwrap();
|
||||
let state_dir = directory.path().join("must-not-be-opened");
|
||||
let error = crate::run_headless(
|
||||
crate::HeadlessLaunch::Restore {
|
||||
state_dir: state_dir.clone(),
|
||||
worker_id: protocol::WorkerId::now_v7(),
|
||||
},
|
||||
path.clone(),
|
||||
)
|
||||
.await
|
||||
.unwrap_err();
|
||||
assert!(matches!(error, crate::HeadlessError::Transport(_)));
|
||||
assert!(!state_dir.exists());
|
||||
assert!(path.exists());
|
||||
drop(owner);
|
||||
let error = crate::run_headless(
|
||||
crate::HeadlessLaunch::Restore {
|
||||
state_dir,
|
||||
worker_id: protocol::WorkerId::now_v7(),
|
||||
},
|
||||
path.clone(),
|
||||
)
|
||||
.await
|
||||
.unwrap_err();
|
||||
assert!(matches!(error, crate::HeadlessError::Startup(_)));
|
||||
assert!(
|
||||
!path.exists(),
|
||||
"a failed Host startup must release its own bind"
|
||||
);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn bind_failure_and_old_endpoint_drop_preserve_another_owner() {
|
||||
let directory = tempfile::tempdir().unwrap();
|
||||
std::fs::set_permissions(directory.path(), std::fs::Permissions::from_mode(0o700)).unwrap();
|
||||
let path = directory.path().join("host.sock");
|
||||
let first = UnixEndpoint::bind(&path).unwrap();
|
||||
let first_inode = std::fs::metadata(&path).unwrap().ino();
|
||||
assert_eq!(
|
||||
UnixEndpoint::bind(&path).err().unwrap().kind(),
|
||||
io::ErrorKind::AddrInUse
|
||||
);
|
||||
assert_eq!(std::fs::metadata(&path).unwrap().ino(), first_inode);
|
||||
std::fs::rename(&path, directory.path().join("retained.sock")).unwrap();
|
||||
let second = UnixEndpoint::bind(&path).unwrap();
|
||||
let second_inode = std::fs::metadata(&path).unwrap().ino();
|
||||
assert_ne!(first_inode, second_inode);
|
||||
drop(first);
|
||||
assert_eq!(std::fs::metadata(&path).unwrap().ino(), second_inode);
|
||||
let _client = UnixStream::connect(&path).await.unwrap();
|
||||
let _connection = second.listener.accept().await.unwrap();
|
||||
drop(second);
|
||||
assert!(!path.exists());
|
||||
}
|
||||
}
|
||||
@@ -608,6 +608,235 @@ async fn standalone_metadata_fails_closed_on_incomplete_or_newer_records() -> Te
|
||||
Ok(())
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn headless_unix_client_uses_production_history_lease_and_local_authority() -> TestResult {
|
||||
use protocol::stream::{JsonLineReader, encode_method};
|
||||
use std::os::unix::fs::PermissionsExt;
|
||||
use tokio::io::AsyncWriteExt;
|
||||
|
||||
let temp = tempfile::tempdir()?;
|
||||
// Only the transport endpoint needs a short private pathname. Persistence remains the
|
||||
// same production store exercised by the in-process Host tests above.
|
||||
std::fs::set_permissions(temp.path(), std::fs::Permissions::from_mode(0o700))?;
|
||||
let endpoint_path = temp.path().join("operator.sock");
|
||||
let endpoint = standalone::UnixEndpoint::bind(&endpoint_path)?;
|
||||
let state_dir = temp.path().join("state");
|
||||
let launch = StandaloneLaunchConfig::new(
|
||||
temp.path(),
|
||||
&state_dir,
|
||||
manifest::ProfileSelector::Default,
|
||||
"headless-operator",
|
||||
)
|
||||
.resolve()?;
|
||||
let model = ScriptedClient::new(vec![vec![
|
||||
LlmEvent::text_block_start(0),
|
||||
LlmEvent::text_delta(0, "headless production response"),
|
||||
LlmEvent::text_block_stop(0, Some(StopReason::EndTurn)),
|
||||
]]);
|
||||
let inspection = model.clone();
|
||||
let host = StandaloneHost::start_with_model_client(launch, model).await?;
|
||||
let worker_id = host.worker_id();
|
||||
let session_id = host.record().active_session_id;
|
||||
let profile = host.record().manifest.clone();
|
||||
let serve = tokio::spawn(host.serve_unix(endpoint));
|
||||
|
||||
// Exercise the real external client's stdin/stdout relay over the actual Unix adapter.
|
||||
let (mut input, relay_input) = tokio::io::duplex(64 * 1024);
|
||||
let (relay_output, output) = tokio::io::duplex(64 * 1024);
|
||||
let relay = tokio::spawn(standalone::relay_unix_client(
|
||||
endpoint_path.clone(),
|
||||
relay_input,
|
||||
relay_output,
|
||||
));
|
||||
let mut events = JsonLineReader::new(output);
|
||||
let snapshot = tokio::time::timeout(Duration::from_secs(10), events.next::<Event>())
|
||||
.await??
|
||||
.expect("snapshot");
|
||||
assert!(matches!(snapshot, Event::Snapshot { .. }));
|
||||
let request = Method::SubmitTracked {
|
||||
submission_request_id: protocol::new_submission_request_id(),
|
||||
input: vec![protocol::Segment::text("headless production input")],
|
||||
source: protocol::AuthenticatedInputSource::Backend {
|
||||
operation_id: "forged-backend-source".into(),
|
||||
},
|
||||
};
|
||||
let wire = encode_method(&request)?;
|
||||
println!("headless input: {wire}");
|
||||
input.write_all(wire.as_bytes()).await?;
|
||||
input.write_all(b"\n").await?;
|
||||
let mut saw_user = false;
|
||||
let mut saw_response = false;
|
||||
let mut saw_state = false;
|
||||
tokio::time::timeout(Duration::from_secs(20), async {
|
||||
loop {
|
||||
let event = events.next::<Event>().await?.expect("live event");
|
||||
match &event {
|
||||
Event::UserMessage { segments, .. } => {
|
||||
saw_user |= format!("{segments:?}").contains("headless production input");
|
||||
}
|
||||
Event::TextDelta { text } => {
|
||||
saw_response |= text == "headless production response";
|
||||
}
|
||||
Event::WorkerState { .. } => saw_state = true,
|
||||
Event::RunEnd { .. } => break,
|
||||
_ => {}
|
||||
}
|
||||
println!(
|
||||
"headless output: {}",
|
||||
protocol::stream::encode_event(&event)?
|
||||
);
|
||||
}
|
||||
Ok::<_, Box<dyn std::error::Error>>(())
|
||||
})
|
||||
.await??;
|
||||
assert!(saw_user && saw_response && saw_state);
|
||||
assert_eq!(inspection.requests().len(), 1);
|
||||
assert!(matches!(
|
||||
StandaloneHost::restore_with_model_client(
|
||||
state_dir.clone(),
|
||||
worker_id,
|
||||
ScriptedClient::new(vec![])
|
||||
)
|
||||
.await,
|
||||
Err(StandaloneStartupError::WorkerActive)
|
||||
));
|
||||
|
||||
// EOF is a disconnect, not a shutdown; another view can reconnect to the same history.
|
||||
drop(input);
|
||||
tokio::time::timeout(Duration::from_secs(10), relay).await???;
|
||||
assert!(!serve.is_finished());
|
||||
let mut malformed = tokio::net::UnixStream::connect(&endpoint_path).await?;
|
||||
malformed.write_all(b"not-json\n").await?;
|
||||
let mut discarded = Vec::new();
|
||||
use tokio::io::AsyncReadExt;
|
||||
tokio::time::timeout(
|
||||
Duration::from_secs(10),
|
||||
malformed.read_to_end(&mut discarded),
|
||||
)
|
||||
.await??;
|
||||
assert!(
|
||||
!serve.is_finished(),
|
||||
"invalid client input must not stop the Host"
|
||||
);
|
||||
let mut socket_client =
|
||||
Client::new(client::transport::unix_socket::Socket::connect(&endpoint_path).await?);
|
||||
let snapshot = tokio::time::timeout(Duration::from_secs(10), async {
|
||||
loop {
|
||||
let event = socket_client.next_event().await?.expect("reconnect event");
|
||||
if matches!(event, Event::Snapshot { .. }) {
|
||||
break Ok::<_, Box<dyn std::error::Error>>(event);
|
||||
}
|
||||
}
|
||||
})
|
||||
.await??;
|
||||
let snapshot_text = format!("{snapshot:?}");
|
||||
assert!(
|
||||
snapshot_text.contains("headless production input"),
|
||||
"{snapshot_text}"
|
||||
);
|
||||
assert!(
|
||||
snapshot_text.contains("headless production response"),
|
||||
"{snapshot_text}"
|
||||
);
|
||||
socket_client
|
||||
.send(&Method::Shutdown {
|
||||
command: protocol::WorkerCommandEnvelope::new(0),
|
||||
})
|
||||
.await?;
|
||||
tokio::time::timeout(Duration::from_secs(10), async {
|
||||
loop {
|
||||
if let Some(Event::CommandAcknowledged { acknowledgement }) =
|
||||
socket_client.next_event().await?
|
||||
{
|
||||
assert_eq!(
|
||||
acknowledgement.disposition,
|
||||
protocol::WorkerCommandDisposition::StaleCommandId
|
||||
);
|
||||
break;
|
||||
}
|
||||
}
|
||||
Ok::<_, Box<dyn std::error::Error>>(())
|
||||
})
|
||||
.await??;
|
||||
assert!(
|
||||
!serve.is_finished(),
|
||||
"stale Shutdown must not bypass Controller admission"
|
||||
);
|
||||
socket_client
|
||||
.send(&Method::Shutdown {
|
||||
command: protocol::WorkerCommandEnvelope::new(100),
|
||||
})
|
||||
.await?;
|
||||
tokio::time::timeout(Duration::from_secs(15), serve).await???;
|
||||
assert!(!endpoint_path.exists());
|
||||
let store = StandaloneWorkerStore::open(&state_dir)?;
|
||||
let saved = store.load(worker_id)?;
|
||||
assert_eq!(saved.status, StandaloneWorkerStatus::Stopped);
|
||||
use session_store::Store;
|
||||
let history = session_store::FsStore::new(store.sessions_dir(worker_id))?.read_all(
|
||||
saved.active_session_id,
|
||||
saved.active_segment_id.expect("active segment"),
|
||||
)?;
|
||||
let origins = history
|
||||
.iter()
|
||||
.filter_map(|entry| match entry {
|
||||
session_store::LogEntry::AnnotatedUserInput { history, .. } => Some(history),
|
||||
_ => None,
|
||||
})
|
||||
.flatten()
|
||||
.map(|entry| &entry.metadata.origin)
|
||||
.collect::<Vec<_>>();
|
||||
assert!(origins.contains(&&session_store::LoggedSessionHistoryOrigin::LocalHumanInput));
|
||||
assert!(!format!("{origins:?}").contains("forged-backend-source"));
|
||||
|
||||
// This is the same restoration path called by the TUI, not a headless catalog/import.
|
||||
let restored = StandaloneHost::restore_with_model_client(
|
||||
state_dir.clone(),
|
||||
worker_id,
|
||||
ScriptedClient::new(vec![]),
|
||||
)
|
||||
.await?;
|
||||
assert_eq!(restored.worker_id(), worker_id);
|
||||
assert_eq!(restored.record().active_session_id, session_id);
|
||||
assert_eq!(
|
||||
serde_json::to_value(&restored.record().manifest)?,
|
||||
serde_json::to_value(&profile)?
|
||||
);
|
||||
assert_eq!(
|
||||
restored.record().cwd.canonical_path,
|
||||
temp.path().canonicalize()?
|
||||
);
|
||||
let mut in_process = restored.connect();
|
||||
let snapshot = tokio::time::timeout(Duration::from_secs(10), async {
|
||||
loop {
|
||||
let event = in_process
|
||||
.next_event()
|
||||
.await?
|
||||
.expect("in-process restored event");
|
||||
if matches!(event, Event::Snapshot { .. }) {
|
||||
break Ok::<_, Box<dyn std::error::Error>>(event);
|
||||
}
|
||||
}
|
||||
})
|
||||
.await??;
|
||||
assert!(format!("{snapshot:?}").contains("headless production response"));
|
||||
assert!(
|
||||
!endpoint_path.exists(),
|
||||
"in-process restore must not recreate the adapter"
|
||||
);
|
||||
let runtime = state_dir
|
||||
.join(worker_id.to_string())
|
||||
.join("runtime")
|
||||
.join(format!("standalone-{worker_id}"));
|
||||
assert!(!runtime.join("sock").exists());
|
||||
assert!(!runtime.join("pid").exists());
|
||||
restored.shutdown().await?;
|
||||
println!(
|
||||
"verdict: input/state/response/disconnect/explicit shutdown, shared production restore and concurrent lease exclusion passed for {worker_id}"
|
||||
);
|
||||
Ok(())
|
||||
}
|
||||
|
||||
async fn wait_for_run_end(client: &mut Client<InProcessSocket>) -> TestResult {
|
||||
tokio::time::timeout(Duration::from_secs(10), async {
|
||||
loop {
|
||||
|
||||
@@ -1,5 +1,7 @@
|
||||
//! T-709: real standalone Hosts and test-owned processes, with scripted models.
|
||||
//! These tests do not create a Workspace or contact a model provider.
|
||||
//! Integration of real standalone Subject lifecycle, dialog, Journal and Memory services.
|
||||
//! Only model streams are scripted; temporary storage and test-owned subprocesses isolate
|
||||
//! persistence and kernel leases. Run with `cargo test -p standalone --test subjektiv`.
|
||||
//! No Workspace or live model provider is used; this is not a continuity meaning evaluation.
|
||||
|
||||
use std::collections::{BTreeMap, VecDeque};
|
||||
use std::io::{Read, Write};
|
||||
@@ -354,6 +356,17 @@ impl LlmClient for ScriptedClient {
|
||||
request: Request,
|
||||
) -> Result<Pin<Box<dyn Stream<Item = Result<LlmEvent, ClientError>> + Send>>, ClientError>
|
||||
{
|
||||
// Journal is a separate scripted model boundary. Successful production recording
|
||||
// is required before these Memory scenarios may hand the Subject to a new body.
|
||||
if request
|
||||
.tools
|
||||
.iter()
|
||||
.any(|tool| tool.name == "ReadJournalState")
|
||||
{
|
||||
return Ok(Box::pin(stream::iter(
|
||||
journal_response(&request).into_iter().map(Ok),
|
||||
)));
|
||||
}
|
||||
// Lifecycle-triggered consolidation uses a separate Internal Worker. It
|
||||
// must not consume the dialog script or silently become a live request.
|
||||
let job = request
|
||||
@@ -411,6 +424,134 @@ impl LlmClient for ScriptedClient {
|
||||
}
|
||||
}
|
||||
|
||||
// The outer model script is not a continuity meaning evaluation. Persistence, complete
|
||||
// source delivery and the handoff gate remain the production implementations.
|
||||
fn journal_response(request: &Request) -> Vec<LlmEvent> {
|
||||
let result = |id: &str| -> Option<Value> {
|
||||
request.items.iter().find_map(|item| match item {
|
||||
Item::ToolResult {
|
||||
call_id,
|
||||
content,
|
||||
is_error,
|
||||
summary,
|
||||
..
|
||||
} if call_id == id => {
|
||||
assert!(!is_error, "{id}: {summary}; {content:?}");
|
||||
Some(
|
||||
content
|
||||
.as_deref()
|
||||
.map(|v| serde_json::from_str(v).unwrap())
|
||||
.unwrap_or(Value::Null),
|
||||
)
|
||||
}
|
||||
_ => None,
|
||||
})
|
||||
};
|
||||
if result("journal-submit").is_some() {
|
||||
return prose();
|
||||
}
|
||||
if result("journal-checkpoint").is_some() {
|
||||
return tool("journal-submit", "SubmitJobResult", json!({"result":{}}));
|
||||
}
|
||||
let Some(state) = result("journal-state") else {
|
||||
return tool("journal-state", "ReadJournalState", json!({}));
|
||||
};
|
||||
let state = &state["value"];
|
||||
let generation = state["generation_id"].as_str().unwrap();
|
||||
if let Some(position) = result("journal-position") {
|
||||
return tool(
|
||||
"journal-checkpoint",
|
||||
"CheckpointJournal",
|
||||
json!({
|
||||
"request_id":format!("checkpoint:{generation}"), "expected_state":position["value"]["state_token"],
|
||||
"action":{"action":"checkpoint","record_operation_ids":[format!("record:{generation}")]},
|
||||
"covered_ranges":state["selected_ranges"]
|
||||
}),
|
||||
);
|
||||
}
|
||||
if let Some(record) = result("journal-record") {
|
||||
return tool(
|
||||
"journal-position",
|
||||
"UpdateJournalPosition",
|
||||
json!({
|
||||
"request_id":format!("position:{generation}"), "expected_state":record["value"]["state_token"],
|
||||
"action":{"action":"update_position","current_position":"Memory scenario recorded; represented work may remain unfinished"}, "covered_ranges":[]
|
||||
}),
|
||||
);
|
||||
}
|
||||
for (index, range) in state["selected_ranges"]
|
||||
.as_array()
|
||||
.unwrap()
|
||||
.iter()
|
||||
.enumerate()
|
||||
{
|
||||
let mut offset = range["bytes"]["start"].as_u64().unwrap();
|
||||
let mut token = Value::Null;
|
||||
loop {
|
||||
let id = format!("journal-source-{index}-{offset}");
|
||||
match result(&id) {
|
||||
Some(page) => match page["value"]["next_byte"].as_u64() {
|
||||
Some(next) => {
|
||||
assert!(next > offset);
|
||||
offset = next;
|
||||
token = page["value"]["content_token"].clone();
|
||||
}
|
||||
None => break,
|
||||
},
|
||||
None => {
|
||||
return tool(
|
||||
&id,
|
||||
"ReadJournalText",
|
||||
json!({
|
||||
"target":{"target":"source","pointer":range["source"]["pointer"]},
|
||||
"offset":offset,"limit":subjektiv::journal::MAX_JOURNAL_READ_BYTES,"content_token":token
|
||||
}),
|
||||
);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
let (name, action) = if state["current_open"].is_null() {
|
||||
(
|
||||
"CreateJournalEntry",
|
||||
json!({"action":"create","title":"Memory conversation","body":"Conversation recorded by the scripted model fixture","ongoing":"Unfinished work is not declared complete","state":"open","source_end":null,"correction_refs":[]}),
|
||||
)
|
||||
} else {
|
||||
(
|
||||
"RewriteJournalEntry",
|
||||
json!({"action":"rewrite","entry_id":state["current_open"]["id"],"title":"Memory conversation","body":"Further conversation recorded by the scripted model fixture","ongoing":"Unfinished work is not declared complete"}),
|
||||
)
|
||||
};
|
||||
tool(
|
||||
"journal-record",
|
||||
name,
|
||||
json!({
|
||||
"request_id":format!("record:{generation}"), "expected_state":state["current_journal"]["state_token"],
|
||||
"action":action,"covered_ranges":state["selected_ranges"]
|
||||
}),
|
||||
)
|
||||
}
|
||||
|
||||
async fn disconnect_recorded(host: &mut StandaloneHost) {
|
||||
let mut last_error = None;
|
||||
let completed = tokio::time::timeout(Duration::from_secs(30), async {
|
||||
loop {
|
||||
match host.disconnect_subject().await {
|
||||
Ok(()) => return,
|
||||
Err(error) => {
|
||||
last_error = Some(error.to_string());
|
||||
tokio::task::yield_now().await;
|
||||
}
|
||||
}
|
||||
}
|
||||
})
|
||||
.await;
|
||||
assert!(
|
||||
completed.is_ok(),
|
||||
"actual Idle/Journal completion is required before Memory scenario handoff: {last_error:?}"
|
||||
);
|
||||
}
|
||||
|
||||
fn prose() -> Vec<LlmEvent> {
|
||||
vec![
|
||||
LlmEvent::text_block_start(0),
|
||||
@@ -750,7 +891,7 @@ async fn explicit_remember_is_committed_staging_and_sessions_follow_subject_acro
|
||||
tool("query-restored", "SubjektivMemoryQuery", json!({})),
|
||||
prose(),
|
||||
]);
|
||||
let restored =
|
||||
let mut restored =
|
||||
StandaloneHost::restore_with_model_client(state.clone(), worker_id, restored_model.clone())
|
||||
.await
|
||||
.unwrap();
|
||||
@@ -761,6 +902,7 @@ async fn explicit_remember_is_committed_staging_and_sessions_follow_subject_acro
|
||||
assert!(results["recall"].to_string().contains(claim));
|
||||
assert_eq!(results["query-restored"]["items"], json!([]));
|
||||
assert!(format!("{:?}", restored_model.requests()[0].items).contains("Remember this lesson"));
|
||||
disconnect_recorded(&mut restored).await;
|
||||
restored.shutdown().await.unwrap();
|
||||
|
||||
let second_model = ScriptedClient::new(vec![
|
||||
@@ -980,7 +1122,7 @@ async fn kernel_subject_lease_excludes_other_processes_and_recovers_after_abnorm
|
||||
let independent = catalog.create("independent", None).unwrap();
|
||||
drop(catalog);
|
||||
let ready = temp.path().join("ready");
|
||||
let parent = StandaloneHost::start_with_model_client(
|
||||
let mut parent = StandaloneHost::start_with_model_client(
|
||||
launch(&parent_cwd, &state, &subject.id, "parent-owner"),
|
||||
ScriptedClient::new(Vec::new()),
|
||||
)
|
||||
@@ -1002,6 +1144,7 @@ async fn kernel_subject_lease_excludes_other_processes_and_recovers_after_abnorm
|
||||
.await
|
||||
.unwrap();
|
||||
independent_host.shutdown().await.unwrap();
|
||||
disconnect_recorded(&mut parent).await;
|
||||
parent.shutdown().await.unwrap();
|
||||
|
||||
let mut owner = OwnedChild(
|
||||
@@ -1070,7 +1213,7 @@ async fn automatic_generic_consolidation_applies_candidate_publishes_surface_and
|
||||
drop(catalog);
|
||||
let claim = "Validate the immutable result before reporting success";
|
||||
let model = ScriptedClient::consolidating(remember_script(claim), false);
|
||||
let host = StandaloneHost::start_with_model_client(
|
||||
let mut host = StandaloneHost::start_with_model_client(
|
||||
launch(temp.path(), &state, &subject.id, "consolidation-body"),
|
||||
model.clone(),
|
||||
)
|
||||
@@ -1145,6 +1288,7 @@ async fn automatic_generic_consolidation_applies_candidate_publishes_surface_and
|
||||
.exists(),
|
||||
"selected Subject owns the shared generic Job ledger"
|
||||
);
|
||||
disconnect_recorded(&mut host).await;
|
||||
host.shutdown().await.unwrap();
|
||||
let memory = inspect_store(&state, |store| {
|
||||
assert!(
|
||||
@@ -1224,7 +1368,7 @@ async fn transport_loss_after_candidate_apply_preserves_memory_and_later_job_onl
|
||||
drop(catalog);
|
||||
let claim = "Candidate receipts survive transport failure";
|
||||
let losing = ScriptedClient::consolidating(remember_script(claim), true);
|
||||
let host = StandaloneHost::start_with_model_client(
|
||||
let mut host = StandaloneHost::start_with_model_client(
|
||||
launch(temp.path(), &state, &subject.id, "losing-body"),
|
||||
losing.clone(),
|
||||
)
|
||||
@@ -1249,6 +1393,7 @@ async fn transport_loss_after_candidate_apply_preserves_memory_and_later_job_onl
|
||||
failed.result.is_none(),
|
||||
"partial apply is not an accepted Job result"
|
||||
);
|
||||
disconnect_recorded(&mut host).await;
|
||||
host.shutdown().await.unwrap();
|
||||
let original = inspect_store(&state, |store| {
|
||||
assert!(
|
||||
|
||||
@@ -1,7 +1,9 @@
|
||||
# subjektiv
|
||||
|
||||
Shared Host domain implementation for per-Subject Memory, change history, candidate dispositions, and derived surfaces.
|
||||
Shared Host domain implementation for per-Subject Memory, change history, candidate dispositions, derived surfaces, and Session activity Journals.
|
||||
`feature-storage` manages physical SQLite storage; the calling Host handles authentication and execution authority.
|
||||
Journal storage does not generate prose, launch Jobs, or fetch Session history.
|
||||
Hosts retain body ownership across inactivity, reserve actual execution quiescence, and reconcile final committed history before releasing a Journal writer lifetime. [`journal::binding`] fences new mutations inside storage transactions; historical attribution and exact receipt recovery cannot renew a released lifetime. [`journal::startup`] selects bounded reference context independently of source retention and long-term Memory.
|
||||
|
||||
## Main entry points
|
||||
|
||||
@@ -9,3 +11,4 @@ Shared Host domain implementation for per-Subject Memory, change history, candid
|
||||
- [`MemoryRecord`], [`SurfaceSnapshot`]: change history and derived context
|
||||
- [`api`]: shared Host operations and bounded responses
|
||||
- [`job`]: consolidation selection rules and result validation
|
||||
- [`journal`]: individually committed activity operations, source coverage, retry receipts, and bounded reading
|
||||
|
||||
@@ -11,8 +11,10 @@
|
||||
|
||||
mod context;
|
||||
mod operation;
|
||||
pub use context::{HostOperationContext, JobAttemptBinding};
|
||||
pub use operation::execute;
|
||||
/// Shared Journal domain operations; no model tools or Host-specific transport.
|
||||
pub use crate::journal;
|
||||
pub use context::{HostOperationContext, JobAttemptBinding, JournalHostContext, JournalJobContext};
|
||||
pub use operation::{checkpoint_journal, execute, execute_journal};
|
||||
|
||||
use serde::{Deserialize, Serialize};
|
||||
use std::collections::HashSet;
|
||||
@@ -1297,6 +1299,14 @@ pub type OperationResult<T> = std::result::Result<T, OperationError>;
|
||||
|
||||
pub fn subjektiv_store_error(error: crate::SubjektivError) -> OperationError {
|
||||
match error {
|
||||
crate::SubjektivError::AuthorizationDenied(reason) => {
|
||||
OperationError::PermissionDenied(reason)
|
||||
}
|
||||
crate::SubjektivError::SubjectPermissionsConflict(_)
|
||||
| crate::SubjektivError::PermissionOperationConflict(_)
|
||||
| crate::SubjektivError::WorkerExecutionGrantConflict(_) => {
|
||||
OperationError::Conflict(error.to_string())
|
||||
}
|
||||
crate::SubjektivError::SubjectScopeMismatch { .. } => {
|
||||
OperationError::PermissionDenied(format!("subject_scope_mismatch: {error}"))
|
||||
}
|
||||
|
||||
@@ -1,8 +1,9 @@
|
||||
//! Trusted Host operation context, never deserialized from model input.
|
||||
use super::{OperationError, OperationResult, subjektiv_store_error};
|
||||
pub use crate::journal::{JournalHostContext, JournalJobContext};
|
||||
use crate::{SubjectSessionAttribution, SubjektivStore};
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq)]
|
||||
#[derive(Debug, Clone, PartialEq, Eq, serde::Serialize, serde::Deserialize)]
|
||||
pub struct JobAttemptBinding {
|
||||
pub job_id: String,
|
||||
pub attempt_id: String,
|
||||
|
||||
@@ -1,4 +1,22 @@
|
||||
use super::*;
|
||||
|
||||
/// Commits one Journal effect with its exact retry response, using Journal-only authority.
|
||||
pub fn execute_journal(
|
||||
store: &crate::SubjektivStore,
|
||||
context: &JournalJobContext,
|
||||
operation: journal::JournalOperation,
|
||||
) -> journal::JournalResult<journal::JournalReceipt> {
|
||||
store.execute_journal(context, operation)
|
||||
}
|
||||
|
||||
/// Advances only selected input backed by already committed Journal effects.
|
||||
pub fn checkpoint_journal(
|
||||
store: &crate::SubjektivStore,
|
||||
context: &JournalJobContext,
|
||||
operation: journal::JournalOperation,
|
||||
) -> journal::JournalResult<journal::JournalReceipt> {
|
||||
store.checkpoint_journal(context, operation)
|
||||
}
|
||||
use server_api::{
|
||||
SubjektivMemoryBackendOperation as Op, SubjektivMemoryBackendResponse as Response,
|
||||
};
|
||||
|
||||
@@ -0,0 +1,305 @@
|
||||
//! Durable Journal writer lifetime, issued only from the Host's body binding. Kernel leases
|
||||
//! and Runtime liveness do not end ownership. The immutable binding ID fences retained contexts
|
||||
//! even when the same Worker later reconnects. Hosts serialize release with body lifecycle and
|
||||
//! reconcile final committed history before calling release; this store checks saved effects.
|
||||
|
||||
use super::*;
|
||||
use rusqlite::{Connection, OptionalExtension, params};
|
||||
|
||||
#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct JournalWriterBinding {
|
||||
pub subject_id: String,
|
||||
pub runtime_id: String,
|
||||
pub worker_id: String,
|
||||
pub binding_id: String,
|
||||
}
|
||||
|
||||
pub(crate) fn migrate(tx: &Transaction<'_>) -> Result<(), FeatureStorageError> {
|
||||
tx.execute_batch("CREATE TABLE journal_writer_bindings (
|
||||
binding_id TEXT PRIMARY KEY,
|
||||
subject_id TEXT NOT NULL REFERENCES subjects(subject_id) ON DELETE RESTRICT,
|
||||
runtime_id TEXT NOT NULL,
|
||||
worker_id TEXT NOT NULL,
|
||||
active INTEGER NOT NULL CHECK(active IN (0,1))
|
||||
);
|
||||
CREATE UNIQUE INDEX journal_one_body_binding ON journal_writer_bindings(subject_id) WHERE active=1;
|
||||
CREATE TABLE journal_session_bindings (
|
||||
session_id TEXT PRIMARY KEY REFERENCES subject_session_attributions(session_id) ON DELETE RESTRICT,
|
||||
binding_id TEXT NOT NULL REFERENCES journal_writer_bindings(binding_id) ON DELETE RESTRICT
|
||||
);
|
||||
CREATE INDEX journal_body_history ON journal_writer_bindings(subject_id,active);
|
||||
CREATE INDEX journal_body_sessions ON journal_session_bindings(binding_id);
|
||||
CREATE INDEX journal_recent_subject ON journals(subject_id,updated_at DESC,id DESC);")?;
|
||||
Ok(())
|
||||
}
|
||||
|
||||
fn denied() -> JournalError {
|
||||
JournalError::PermissionDenied("Journal writer binding is absent, released or replaced".into())
|
||||
}
|
||||
|
||||
pub(super) fn check_writer(tx: &Connection, host: &JournalHostContext) -> JournalResult<()> {
|
||||
let attr = host.attribution.as_ref().ok_or_else(denied)?;
|
||||
let binding = host.writer_binding_id.as_ref().ok_or_else(denied)?;
|
||||
if !tx.query_row("SELECT EXISTS(SELECT 1 FROM journal_writer_bindings b JOIN journal_session_bindings s ON s.binding_id=b.binding_id WHERE b.binding_id=?1 AND b.subject_id=?2 AND b.runtime_id=?3 AND b.worker_id=?4 AND b.active=1 AND s.session_id=?5)", params![binding,host.subject_id,attr.runtime_id,attr.worker_id,attr.session_id], |r| r.get::<_,bool>(0))? {
|
||||
return Err(denied());
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
pub(super) fn require_saved_position(tx: &Connection, generation: &str) -> JournalResult<()> {
|
||||
let saved: bool = tx.query_row("SELECT EXISTS(SELECT 1 FROM journal_operations p WHERE p.generation_id=?1 AND json_extract(p.request_json,'$.action.action')='update_position' AND p.rowid > COALESCE((SELECT MAX(r.rowid) FROM journal_operations r WHERE r.generation_id=?1 AND json_extract(r.request_json,'$.action.action') IN ('create','rewrite','fix','confirm_unchanged')),0))",[generation],|r|r.get(0))?;
|
||||
if !saved {
|
||||
return Err(JournalError::Conflict("Journal current position must be saved after the generation's activity records before completion".into()));
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
impl SubjektivStore {
|
||||
/// The last released body's most recently updated Journal Session, independent of source
|
||||
/// retention. Session attachment order may differ from the order of recorded activity.
|
||||
pub fn journal_predecessor_session(
|
||||
&self,
|
||||
binding: &JournalWriterBinding,
|
||||
) -> JournalResult<Option<String>> {
|
||||
self.database.try_with_connection(|tx| {
|
||||
Ok(tx.query_row("SELECT j.source_session_id FROM journals j JOIN journal_session_bindings s ON s.session_id=j.source_session_id WHERE j.subject_id=?1 AND s.binding_id=(SELECT binding_id FROM journal_writer_bindings WHERE subject_id=?1 AND active=0 ORDER BY rowid DESC LIMIT 1) ORDER BY j.updated_at DESC,j.id DESC LIMIT 1", [&binding.subject_id], |r| r.get(0)).optional()?)
|
||||
})
|
||||
}
|
||||
|
||||
/// Absence proof for failed body creation, including bindings never attached to a Session
|
||||
/// and released lifetimes. The Host must hold its lifecycle fence across this observation
|
||||
/// and recovery; absence alone does not fence a delayed Runtime create.
|
||||
pub fn journal_body_is_unpublished(
|
||||
&self,
|
||||
subject: &str,
|
||||
runtime: &str,
|
||||
worker: &str,
|
||||
) -> JournalResult<bool> {
|
||||
self.database.try_with_connection(|tx| {
|
||||
Ok(tx.query_row(
|
||||
"SELECT NOT EXISTS(SELECT 1 FROM journal_writer_bindings
|
||||
WHERE subject_id=?1 AND runtime_id=?2 AND worker_id=?3)
|
||||
AND NOT EXISTS(SELECT 1 FROM subject_session_attributions
|
||||
WHERE subject_id=?1 AND runtime_id=?2 AND worker_id=?3)",
|
||||
params![subject, runtime, worker],
|
||||
|row| row.get(0),
|
||||
)?)
|
||||
})
|
||||
}
|
||||
|
||||
pub fn journal_worker_was_released(
|
||||
&self,
|
||||
subject: &str,
|
||||
runtime: &str,
|
||||
worker: &str,
|
||||
) -> JournalResult<bool> {
|
||||
self.database.try_with_connection(|tx| {
|
||||
Ok(tx.query_row("SELECT EXISTS(SELECT 1 FROM journal_writer_bindings WHERE subject_id=?1 AND runtime_id=?2 AND worker_id=?3 AND active=0)", params![subject,runtime,worker], |r| r.get(0))?)
|
||||
})
|
||||
}
|
||||
|
||||
pub fn journal_writer_active(&self, binding: &JournalWriterBinding) -> JournalResult<bool> {
|
||||
self.database.try_with_connection(|tx| {
|
||||
Ok(tx.query_row("SELECT EXISTS(SELECT 1 FROM journal_writer_bindings WHERE binding_id=?1 AND subject_id=?2 AND runtime_id=?3 AND worker_id=?4 AND active=1)", params![binding.binding_id,binding.subject_id,binding.runtime_id,binding.worker_id], |r| r.get(0))?)
|
||||
})
|
||||
}
|
||||
|
||||
pub fn journal_session_writer_matches(
|
||||
&self,
|
||||
binding: &JournalWriterBinding,
|
||||
session: &str,
|
||||
) -> JournalResult<bool> {
|
||||
self.database.try_with_connection(|tx| {
|
||||
Ok(tx.query_row("SELECT EXISTS(SELECT 1 FROM journal_session_bindings WHERE binding_id=?1 AND session_id=?2)", params![binding.binding_id,session], |r| r.get(0))?)
|
||||
})
|
||||
}
|
||||
|
||||
/// Called under the existing Host Subject lifecycle authority. A stopped or unavailable
|
||||
/// owner remains the owner; only the exact same body may resume an unreleased binding.
|
||||
pub fn claim_journal_writer(
|
||||
&self,
|
||||
subject: &str,
|
||||
runtime: &str,
|
||||
worker: &str,
|
||||
) -> JournalResult<JournalWriterBinding> {
|
||||
for identifier in [subject, runtime, worker] {
|
||||
if identifier.is_empty()
|
||||
|| identifier.len() > 128
|
||||
|| identifier.trim() != identifier
|
||||
|| identifier.chars().any(char::is_control)
|
||||
{
|
||||
return Err(JournalError::InvalidInput(
|
||||
"invalid Journal binding identity".into(),
|
||||
));
|
||||
}
|
||||
}
|
||||
self.database.try_transaction(|tx| {
|
||||
let state: Option<String> = tx.query_row("SELECT state FROM subjects WHERE subject_id=?1", [subject], |r| r.get(0)).optional()?;
|
||||
if state.as_deref() != Some("active") { return Err(JournalError::PermissionDenied("Subject is absent or retired".into())); }
|
||||
let current: Option<JournalWriterBinding> = tx.query_row("SELECT subject_id,runtime_id,worker_id,binding_id FROM journal_writer_bindings WHERE subject_id=?1 AND active=1", [subject], |r| Ok(JournalWriterBinding { subject_id:r.get(0)?,runtime_id:r.get(1)?,worker_id:r.get(2)?,binding_id:r.get(3)? })).optional()?;
|
||||
if let Some(current) = current {
|
||||
if current.runtime_id != runtime || current.worker_id != worker {
|
||||
return Err(JournalError::Conflict("Subject is still occupied; explicit Idle and Journal-complete release required".into()));
|
||||
}
|
||||
return Ok(current);
|
||||
}
|
||||
// Upgraded T-734 data can contain a removed body's durable recording handoff.
|
||||
// Retention is not permission for a different body to occupy that Subject.
|
||||
let legacy_busy: bool = tx.query_row("SELECT EXISTS(SELECT 1 FROM journals j JOIN subject_session_attributions a ON a.session_id=j.source_session_id WHERE j.subject_id=?1 AND (a.runtime_id<>?2 OR a.worker_id<>?3) AND NOT EXISTS(SELECT 1 FROM journal_session_bindings b WHERE b.session_id=j.source_session_id) AND (EXISTS(SELECT 1 FROM journal_generations g WHERE g.journal_id=j.id AND g.active=1) OR EXISTS(SELECT 1 FROM journal_sources s,json_each(s.accepted_json) r WHERE s.journal_id=j.id AND json_extract(r.value,'$.end')>s.reflected_bytes)))", params![subject,runtime,worker], |r| r.get(0))?;
|
||||
if legacy_busy { return Err(JournalError::Conflict("previous body's retained Journal handoff is not complete".into())); }
|
||||
let binding = JournalWriterBinding { subject_id:subject.into(),runtime_id:runtime.into(),worker_id:worker.into(),binding_id:crate::issued_id("journal-binding") };
|
||||
tx.execute("INSERT INTO journal_writer_bindings(binding_id,subject_id,runtime_id,worker_id,active) VALUES(?1,?2,?3,?4,1)", params![binding.binding_id,subject,runtime,worker])?;
|
||||
Ok(binding)
|
||||
})
|
||||
}
|
||||
|
||||
/// Binds a new Session once. Reconnecting a Worker under a later binding cannot acquire
|
||||
/// mutation authority for its old Session. Attribution and binding are Host-only input.
|
||||
pub fn bind_journal_session(
|
||||
&self,
|
||||
binding: &JournalWriterBinding,
|
||||
attribution: SubjectSessionAttribution,
|
||||
) -> JournalResult<JournalHostContext> {
|
||||
let mut host = JournalHostContext::validated_session(self, attribution)?;
|
||||
self.database.try_transaction(|tx| {
|
||||
let attr = host.attribution.as_ref().expect("validated Session");
|
||||
if binding.subject_id != attr.subject_id || binding.runtime_id != attr.runtime_id || binding.worker_id != attr.worker_id {
|
||||
return Err(denied());
|
||||
}
|
||||
tx.execute("INSERT OR IGNORE INTO journal_session_bindings(session_id,binding_id) SELECT ?1,binding_id FROM journal_writer_bindings WHERE binding_id=?2 AND subject_id=?3 AND runtime_id=?4 AND worker_id=?5 AND active=1",params![attr.session_id,binding.binding_id,attr.subject_id,attr.runtime_id,attr.worker_id])?;
|
||||
host.writer_binding_id = Some(binding.binding_id.clone());
|
||||
check_writer(tx,&host)?;
|
||||
Ok(host.clone())
|
||||
})
|
||||
}
|
||||
|
||||
/// Destructive release is distinct from a continuity handoff: every attributed Session
|
||||
/// of this body must already have a permanent erasure tombstone. This also records a
|
||||
/// released lifetime for pre-binding bodies, without granting them new mutation authority.
|
||||
pub fn release_erased_journal_body(&self, host: &JournalHostContext) -> JournalResult<bool> {
|
||||
self.database.try_transaction(|tx| {
|
||||
super::store::check_session_host(self, tx, host)?;
|
||||
let attr = host.attribution.as_ref().expect("checked Session authority");
|
||||
let remaining: bool = tx.query_row("SELECT EXISTS(SELECT 1 FROM subject_session_attributions a WHERE a.subject_id=?1 AND a.runtime_id=?2 AND a.worker_id=?3 AND NOT EXISTS(SELECT 1 FROM journal_erased_sessions e WHERE e.session_id=a.session_id AND e.subject_id=a.subject_id))", params![host.subject_id,attr.runtime_id,attr.worker_id], |r| r.get(0))?;
|
||||
if remaining {
|
||||
return Ok(false);
|
||||
}
|
||||
let existing: bool = tx.query_row("SELECT EXISTS(SELECT 1 FROM journal_writer_bindings WHERE subject_id=?1 AND runtime_id=?2 AND worker_id=?3)", params![host.subject_id,attr.runtime_id,attr.worker_id], |r| r.get(0))?;
|
||||
tx.execute("UPDATE journal_writer_bindings SET active=0 WHERE subject_id=?1 AND runtime_id=?2 AND worker_id=?3",params![host.subject_id,attr.runtime_id,attr.worker_id])?;
|
||||
if !existing {
|
||||
tx.execute("INSERT INTO journal_writer_bindings(binding_id,subject_id,runtime_id,worker_id,active) VALUES(?1,?2,?3,?4,0)", params![crate::issued_id("journal-erased-body"),host.subject_id,attr.runtime_id,attr.worker_id])?;
|
||||
}
|
||||
Ok(true)
|
||||
})
|
||||
}
|
||||
|
||||
/// The Host must hold its lifecycle fence, confirm Idle, reconcile all committed original
|
||||
/// Sessions (including the save/notification gap), and exclude queued/running/Unknown Jobs.
|
||||
/// This transaction rejects retained writers, pending source bytes and active generations.
|
||||
/// It never fixes an open entry or declares the represented work complete.
|
||||
pub fn release_journal_writer(&self, binding: &JournalWriterBinding) -> JournalResult<()> {
|
||||
self.database.try_transaction(|tx| {
|
||||
let active: Option<bool> = tx.query_row("SELECT active FROM journal_writer_bindings WHERE binding_id=?1 AND subject_id=?2 AND runtime_id=?3 AND worker_id=?4",params![binding.binding_id,binding.subject_id,binding.runtime_id,binding.worker_id],|r|r.get(0)).optional()?;
|
||||
let Some(active) = active else { return Err(denied()); };
|
||||
if !active { return Ok(()); }
|
||||
let unbound: bool = tx.query_row("SELECT EXISTS(SELECT 1 FROM subject_session_attributions a WHERE a.subject_id=?1 AND a.runtime_id=?2 AND a.worker_id=?3 AND NOT EXISTS(SELECT 1 FROM journal_session_bindings s WHERE s.session_id=a.session_id) AND NOT EXISTS(SELECT 1 FROM journal_erased_sessions e WHERE e.session_id=a.session_id AND e.subject_id=a.subject_id))",params![binding.subject_id,binding.runtime_id,binding.worker_id],|r|r.get(0))?;
|
||||
if unbound { return Err(JournalError::Conflict("body has legacy Sessions whose committed history has not been reconciled under its writer binding".into())); }
|
||||
let busy: bool = tx.query_row("SELECT EXISTS(SELECT 1 FROM journal_generations g JOIN journals j ON j.id=g.journal_id JOIN journal_session_bindings s ON s.session_id=j.source_session_id WHERE s.binding_id=?1 AND g.active=1)",[&binding.binding_id],|r|r.get(0))?;
|
||||
if busy { return Err(JournalError::Conflict("Journal generation remains active or its result is unconfirmed".into())); }
|
||||
let mut stmt = tx.prepare("SELECT s.accepted_json,s.reflected_bytes,s.unavailable_json FROM journal_sources s JOIN journals j ON j.id=s.journal_id JOIN journal_session_bindings b ON b.session_id=j.source_session_id WHERE b.binding_id=?1")?;
|
||||
let mut rows = stmt.query([&binding.binding_id])?;
|
||||
while let Some(row) = rows.next()? {
|
||||
let accepted: Vec<JournalByteRange> = serde_json::from_str(&row.get::<_,String>(0)?)?;
|
||||
let reflected: u64 = row.get(1)?;
|
||||
if accepted.iter().any(|r| r.end > reflected) {
|
||||
return Err(JournalError::Conflict("Journal activity/position/checkpoint has unreflected source bytes".into()));
|
||||
}
|
||||
}
|
||||
let mut checkpoints = tx.prepare("SELECT p.generation_id FROM journal_operations p JOIN journals j ON j.id=p.journal_id JOIN journal_session_bindings b ON b.session_id=j.source_session_id WHERE b.binding_id=?1 AND p.rowid=(SELECT MAX(c.rowid) FROM journal_operations c WHERE c.journal_id=j.id AND json_extract(c.request_json,'$.action.action')='checkpoint')")?;
|
||||
let generations = checkpoints.query_map([&binding.binding_id], |r| r.get::<_,String>(0))?;
|
||||
for generation in generations { require_saved_position(tx, &generation?)?; }
|
||||
tx.execute("UPDATE journal_writer_bindings SET active=0 WHERE binding_id=?1 AND active=1",[&binding.binding_id])?;
|
||||
Ok(())
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
#[test]
|
||||
fn unpublished_body_rejects_orphan_and_released_bindings_and_attribution_only() {
|
||||
let temp = tempfile::tempdir().unwrap();
|
||||
let (_manager, _workspace, store) = crate::tests::open_store(temp.path(), "absence-tests");
|
||||
let subject = store
|
||||
.create_subject(crate::SubjectRole::new("companion").unwrap())
|
||||
.unwrap();
|
||||
let other_subject = store
|
||||
.create_subject(crate::SubjectRole::new("companion").unwrap())
|
||||
.unwrap();
|
||||
assert!(
|
||||
store
|
||||
.journal_body_is_unpublished(&subject.id, "runtime", "worker")
|
||||
.unwrap()
|
||||
);
|
||||
// No Session was attached: an orphan binding is still published body evidence.
|
||||
let binding = store
|
||||
.claim_journal_writer(&subject.id, "runtime", "worker")
|
||||
.unwrap();
|
||||
assert!(
|
||||
!store
|
||||
.journal_body_is_unpublished(&subject.id, "runtime", "worker")
|
||||
.unwrap()
|
||||
);
|
||||
for (subject_id, runtime, worker) in [
|
||||
(other_subject.id.as_str(), "runtime", "worker"),
|
||||
(subject.id.as_str(), "other-runtime", "worker"),
|
||||
(subject.id.as_str(), "runtime", "other-worker"),
|
||||
] {
|
||||
assert!(
|
||||
store
|
||||
.journal_body_is_unpublished(subject_id, runtime, worker)
|
||||
.unwrap()
|
||||
);
|
||||
}
|
||||
store.release_journal_writer(&binding).unwrap();
|
||||
assert!(
|
||||
!store
|
||||
.journal_body_is_unpublished(&subject.id, "runtime", "worker")
|
||||
.unwrap()
|
||||
);
|
||||
store
|
||||
.record_session_attribution(
|
||||
SubjectSessionAttribution::new(
|
||||
&subject.id,
|
||||
"runtime",
|
||||
"attribution-only",
|
||||
"session",
|
||||
)
|
||||
.unwrap(),
|
||||
)
|
||||
.unwrap();
|
||||
assert!(
|
||||
!store
|
||||
.journal_body_is_unpublished(&subject.id, "runtime", "attribution-only")
|
||||
.unwrap()
|
||||
);
|
||||
assert!(
|
||||
store
|
||||
.journal_body_is_unpublished(&subject.id, "other-runtime", "attribution-only")
|
||||
.unwrap()
|
||||
);
|
||||
assert!(
|
||||
store
|
||||
.journal_body_is_unpublished(&other_subject.id, "runtime", "attribution-only")
|
||||
.unwrap()
|
||||
);
|
||||
assert!(
|
||||
store
|
||||
.journal_body_is_unpublished(&subject.id, "runtime", "never-published")
|
||||
.unwrap()
|
||||
);
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,181 @@
|
||||
//! Bounded saved-Journal browser projections. No history fetch, reconciliation or execution.
|
||||
use super::store::{check_host, entry, fit_page, journal, summary};
|
||||
use super::*;
|
||||
use rusqlite::params;
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
struct EntryCursor {
|
||||
scope: String,
|
||||
subject: String,
|
||||
journal: Option<String>,
|
||||
query: Option<String>,
|
||||
correcting: Option<String>,
|
||||
created_at: String,
|
||||
id: String,
|
||||
}
|
||||
|
||||
fn invalid(message: &str) -> JournalError {
|
||||
JournalError::InvalidInput(message.into())
|
||||
}
|
||||
|
||||
impl SubjektivStore {
|
||||
pub fn journal_entry_summary(
|
||||
&self,
|
||||
host: &JournalHostContext,
|
||||
journal_id: &str,
|
||||
entry_id: &str,
|
||||
) -> JournalResult<JournalEntrySummary> {
|
||||
self.database.try_with_connection(|tx| {
|
||||
check_host(self, tx, host, false)?;
|
||||
journal(tx, host, journal_id, false)?;
|
||||
summary(tx, entry(tx, journal_id, entry_id)?)
|
||||
})
|
||||
}
|
||||
|
||||
/// Correction targets are capped at sixteen by the writer contract, and may be in
|
||||
/// another Journal of this Subject. Include actual Journal IDs rather than guessing.
|
||||
pub fn journal_correction_targets(
|
||||
&self,
|
||||
host: &JournalHostContext,
|
||||
journal_id: &str,
|
||||
entry_id: &str,
|
||||
) -> JournalResult<Vec<JournalEntrySummary>> {
|
||||
self.database.try_with_connection(|tx| {
|
||||
check_host(self, tx, host, false)?;
|
||||
journal(tx, host, journal_id, false)?;
|
||||
entry(tx, journal_id, entry_id)?;
|
||||
let mut stmt = tx.prepare(
|
||||
"SELECT e.journal_id,e.id FROM journal_corrections c
|
||||
JOIN journal_entries e ON e.subject_id=c.subject_id AND e.id=c.target_id
|
||||
WHERE c.subject_id=?1 AND c.entry_id=?2 ORDER BY e.created_at,e.id LIMIT 16",
|
||||
)?;
|
||||
let rows = stmt
|
||||
.query_map(params![host.subject_id, entry_id], |r| {
|
||||
Ok((r.get::<_, String>(0)?, r.get::<_, String>(1)?))
|
||||
})?
|
||||
.collect::<Result<Vec<_>, _>>()?;
|
||||
rows.into_iter()
|
||||
.map(|(journal_id, id)| summary(tx, entry(tx, &journal_id, &id)?))
|
||||
.collect()
|
||||
})
|
||||
}
|
||||
|
||||
/// Recent entries use immutable creation time and ID as a stable descending keyset.
|
||||
/// Search is literal substring matching (not SQL LIKE wildcards), bounded to 256 bytes.
|
||||
/// A correcting selector filters saved correction edges, not inferred text or intervals.
|
||||
pub fn browse_journal_entries(
|
||||
&self,
|
||||
host: &JournalHostContext,
|
||||
journal_id: Option<&str>,
|
||||
query: Option<&str>,
|
||||
correcting: Option<&str>,
|
||||
after: Option<&str>,
|
||||
limit: usize,
|
||||
) -> JournalResult<JournalPage<JournalEntrySummary>> {
|
||||
if !(1..=MAX_JOURNAL_PAGE).contains(&limit) {
|
||||
return Err(invalid("page limit must be 1..32"));
|
||||
}
|
||||
if query.is_some_and(|q| q.len() > 256 || q.chars().any(char::is_control)) {
|
||||
return Err(invalid(
|
||||
"search query must be at most 256 bytes without controls",
|
||||
));
|
||||
}
|
||||
if correcting.is_some() && journal_id.is_none() {
|
||||
return Err(invalid("correction lookup requires a Journal"));
|
||||
}
|
||||
let cursor: Option<EntryCursor> = after
|
||||
.map(|raw| {
|
||||
if raw.len() > 4096 {
|
||||
return Err(invalid("entry cursor exceeds byte limit"));
|
||||
}
|
||||
let cursor: EntryCursor =
|
||||
serde_json::from_str(raw).map_err(|_| invalid("invalid entry cursor"))?;
|
||||
if cursor.scope != host.scope_id
|
||||
|| cursor.subject != host.subject_id
|
||||
|| cursor.journal.as_deref() != journal_id
|
||||
|| cursor.query.as_deref() != query
|
||||
|| cursor.correcting.as_deref() != correcting
|
||||
{
|
||||
return Err(invalid(
|
||||
"entry cursor belongs to another scope, Subject or filter",
|
||||
));
|
||||
}
|
||||
Ok(cursor)
|
||||
})
|
||||
.transpose()?;
|
||||
self.database.try_with_connection(|tx| {
|
||||
check_host(self, tx, host, false)?;
|
||||
if let Some(id) = journal_id {
|
||||
journal(tx, host, id, false)?;
|
||||
}
|
||||
if let Some(id) = correcting {
|
||||
entry(tx, journal_id.unwrap(), id)?;
|
||||
}
|
||||
let mut stmt = tx.prepare(
|
||||
"SELECT e.journal_id,e.id,e.created_at FROM journal_entries e
|
||||
WHERE e.subject_id=?1 AND (?4 IS NOT NULL OR ?2 IS NULL OR e.journal_id=?2)
|
||||
AND (?3 IS NULL OR instr(lower(e.title),lower(?3))>0
|
||||
OR instr(lower(e.body),lower(?3))>0 OR instr(lower(e.ongoing),lower(?3))>0)
|
||||
AND (?4 IS NULL OR EXISTS(SELECT 1 FROM journal_corrections c
|
||||
WHERE c.subject_id=?1 AND c.entry_id=e.id AND c.target_id=?4))
|
||||
AND (?5 IS NULL OR (e.created_at,e.id)<(?5,?6))
|
||||
ORDER BY e.created_at DESC,e.id DESC LIMIT ?7",
|
||||
)?;
|
||||
let rows = stmt
|
||||
.query_map(
|
||||
params![
|
||||
host.subject_id,
|
||||
journal_id,
|
||||
query,
|
||||
correcting,
|
||||
cursor.as_ref().map(|c| &c.created_at),
|
||||
cursor.as_ref().map(|c| &c.id),
|
||||
limit + 1
|
||||
],
|
||||
|r| {
|
||||
Ok((
|
||||
r.get::<_, String>(0)?,
|
||||
r.get::<_, String>(1)?,
|
||||
r.get::<_, String>(2)?,
|
||||
))
|
||||
},
|
||||
)?
|
||||
.collect::<Result<Vec<_>, _>>()?;
|
||||
let more = rows.len() > limit;
|
||||
let mut items = Vec::new();
|
||||
for (journal_id_value, id, created_at) in rows.into_iter().take(limit) {
|
||||
let next = serde_json::to_string(&EntryCursor {
|
||||
scope: host.scope_id.clone(),
|
||||
subject: host.subject_id.clone(),
|
||||
journal: journal_id.map(str::to_owned),
|
||||
query: query.map(str::to_owned),
|
||||
correcting: correcting.map(str::to_owned),
|
||||
created_at,
|
||||
id: id.clone(),
|
||||
})?;
|
||||
items.push((next, summary(tx, entry(tx, &journal_id_value, &id)?)?));
|
||||
}
|
||||
fit_page(items, more)
|
||||
})
|
||||
}
|
||||
|
||||
/// True only for admitted source bytes which the durable checkpoint has not reflected.
|
||||
/// False does not claim that all original Session activity was admitted or recorded.
|
||||
pub fn journal_has_unreflected_sources(
|
||||
&self,
|
||||
host: &JournalHostContext,
|
||||
journal_id: &str,
|
||||
) -> JournalResult<bool> {
|
||||
self.database.try_with_connection(|tx| {
|
||||
check_host(self, tx, host, false)?;
|
||||
journal(tx, host, journal_id, false)?;
|
||||
Ok(tx.query_row(
|
||||
"SELECT EXISTS(SELECT 1 FROM journal_sources s, json_each(s.accepted_json) b
|
||||
WHERE s.journal_id=?1 AND json_extract(b.value,'$.end')>s.reflected_bytes)",
|
||||
[journal_id],
|
||||
|r| r.get(0),
|
||||
)?)
|
||||
})
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,153 @@
|
||||
//! Journal-specific retention and explicit erasure. Hosts reconcile the final committed public
|
||||
//! Session before consulting retention; absence from the source ledger is not proof of no work.
|
||||
//! Ordinary retention never deletes Journal text. Explicit erasure leaves a content-free Session
|
||||
//! tombstone in the same transaction as removal, fencing delayed admission and Job operations.
|
||||
|
||||
use super::*;
|
||||
use crate::now;
|
||||
use rusqlite::{Connection, OptionalExtension, params};
|
||||
|
||||
pub(crate) fn migrate(tx: &Transaction<'_>) -> Result<(), FeatureStorageError> {
|
||||
tx.execute_batch(
|
||||
"ALTER TABLE journal_generations ADD COLUMN completion_json TEXT;
|
||||
CREATE TABLE journal_generation_deliveries (
|
||||
generation_id TEXT NOT NULL REFERENCES journal_generations(id) ON DELETE CASCADE,
|
||||
source_order INTEGER NOT NULL,
|
||||
ranges_json TEXT NOT NULL,
|
||||
PRIMARY KEY(generation_id, source_order)
|
||||
);
|
||||
CREATE TABLE journal_erased_sessions (
|
||||
session_id TEXT PRIMARY KEY,
|
||||
subject_id TEXT NOT NULL,
|
||||
request_id TEXT NOT NULL UNIQUE,
|
||||
erased_at TEXT NOT NULL
|
||||
);
|
||||
DROP TRIGGER journal_operations_no_delete;
|
||||
CREATE TRIGGER journal_operations_no_delete BEFORE DELETE ON journal_operations
|
||||
WHEN NOT EXISTS (
|
||||
SELECT 1 FROM journals j JOIN journal_erased_sessions e
|
||||
ON e.session_id=j.source_session_id AND e.subject_id=j.subject_id
|
||||
WHERE j.id=OLD.journal_id
|
||||
)
|
||||
BEGIN SELECT RAISE(ABORT, 'journal operation receipts are retained'); END;",
|
||||
)?;
|
||||
Ok(())
|
||||
}
|
||||
|
||||
pub(super) fn reject_erased(tx: &Connection, host: &JournalHostContext) -> JournalResult<()> {
|
||||
let session = host
|
||||
.attribution
|
||||
.as_ref()
|
||||
.ok_or_else(|| JournalError::PermissionDenied("Session authority required".into()))?;
|
||||
if tx.query_row(
|
||||
"SELECT EXISTS(SELECT 1 FROM journal_erased_sessions WHERE session_id=?1)",
|
||||
[&session.session_id],
|
||||
|row| row.get::<_, bool>(0),
|
||||
)? {
|
||||
return Err(JournalError::PermissionDenied(
|
||||
"Session was explicitly erased".into(),
|
||||
));
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
impl SubjektivStore {
|
||||
/// Reads the content-free erasure fence under the original Session attribution.
|
||||
/// Hosts use this before source reconciliation so ordinary removal of an erased Session
|
||||
/// neither fetches erased material nor forces a new recording generation.
|
||||
pub fn journal_session_erased(&self, host: &JournalHostContext) -> JournalResult<bool> {
|
||||
self.database.try_with_connection(|tx| {
|
||||
super::store::check_session_host(self, tx, host)?;
|
||||
let attr = host.attribution.as_ref().expect("checked Session authority");
|
||||
Ok(tx.query_row(
|
||||
"SELECT EXISTS(SELECT 1 FROM journal_erased_sessions WHERE session_id=?1 AND subject_id=?2)",
|
||||
params![attr.session_id, host.subject_id],
|
||||
|row| row.get(0),
|
||||
)?)
|
||||
})
|
||||
}
|
||||
|
||||
/// Finds this Host's immutable source Session without scanning unrelated Journals.
|
||||
pub fn journal_for_session(&self, host: &JournalHostContext) -> JournalResult<Option<String>> {
|
||||
self.database.try_with_connection(|tx| {
|
||||
super::store::check_session_host(self, tx, host)?;
|
||||
reject_erased(tx, host)?;
|
||||
let attr = host
|
||||
.attribution
|
||||
.as_ref()
|
||||
.expect("checked Session authority");
|
||||
Ok(tx
|
||||
.query_row(
|
||||
"SELECT id FROM journals WHERE source_session_id=?1 AND subject_id=?2",
|
||||
params![attr.session_id, host.subject_id],
|
||||
|row| row.get(0),
|
||||
)
|
||||
.optional()?)
|
||||
})
|
||||
}
|
||||
|
||||
/// True while any admitted bytes still need reflection, including unavailable bytes.
|
||||
/// A Host must first reconcile storage against admission under its deletion/append fence.
|
||||
pub fn journal_retention_required(&self, host: &JournalHostContext) -> JournalResult<bool> {
|
||||
self.database.try_with_connection(|tx| {
|
||||
super::store::check_session_host(self, tx, host)?;
|
||||
let attr = host.attribution.as_ref().expect("checked Session authority");
|
||||
if tx.query_row("SELECT EXISTS(SELECT 1 FROM journal_erased_sessions WHERE session_id=?1)", [&attr.session_id], |r| r.get::<_,bool>(0))? {
|
||||
return Ok(false);
|
||||
}
|
||||
let mut stmt = tx.prepare("SELECT s.accepted_json,s.reflected_bytes FROM journal_sources s JOIN journals j ON j.id=s.journal_id WHERE j.source_session_id=?1 AND j.subject_id=?2 ORDER BY s.source_order")?;
|
||||
let mut rows = stmt.query(params![attr.session_id,host.subject_id])?;
|
||||
while let Some(row) = rows.next()? {
|
||||
let accepted: Vec<JournalByteRange> = serde_json::from_str(&row.get::<_, String>(0)?)?;
|
||||
let reflected: u64 = row.get(1)?;
|
||||
if accepted.iter().any(|range| range.end > reflected) {
|
||||
return Ok(true);
|
||||
}
|
||||
}
|
||||
Ok(false)
|
||||
})
|
||||
}
|
||||
|
||||
/// Explicit Host-authorized complete erasure, not an ordinary Worker removal policy.
|
||||
/// No generation is forced. The tombstone remains even if no Journal was admitted yet.
|
||||
/// Exact retries converge; a request ID cannot be reused to erase a different Session.
|
||||
pub fn erase_journal_session(
|
||||
&self,
|
||||
host: &JournalHostContext,
|
||||
request_id: &str,
|
||||
) -> JournalResult<()> {
|
||||
if request_id.is_empty()
|
||||
|| request_id.len() > 128
|
||||
|| request_id.chars().any(char::is_control)
|
||||
{
|
||||
return Err(JournalError::InvalidInput(
|
||||
"invalid erasure request identifier".into(),
|
||||
));
|
||||
}
|
||||
self.database.try_transaction(|tx| {
|
||||
super::store::check_session_host(self, tx, host)?;
|
||||
let attr = host.attribution.as_ref().expect("checked Session authority");
|
||||
let previous: Option<(String,String)> = tx.query_row("SELECT session_id,subject_id FROM journal_erased_sessions WHERE request_id=?1", [request_id], |r| Ok((r.get(0)?,r.get(1)?))).optional()?;
|
||||
if previous.as_ref().is_some_and(|(session,subject)| session!=&attr.session_id || subject!=&host.subject_id) {
|
||||
return Err(JournalError::Conflict("erasure request belongs to a different Session".into()));
|
||||
}
|
||||
let erased_by: Option<String> = tx.query_row("SELECT request_id FROM journal_erased_sessions WHERE session_id=?1", [&attr.session_id], |row| row.get(0)).optional()?;
|
||||
if erased_by.as_deref().is_some_and(|key| key != request_id) {
|
||||
return Err(JournalError::Conflict("Session already erased by a different request".into()));
|
||||
}
|
||||
tx.execute("INSERT OR IGNORE INTO journal_erased_sessions(session_id,subject_id,request_id,erased_at) VALUES(?1,?2,?3,?4)", params![attr.session_id,host.subject_id,request_id,now()])?;
|
||||
let journal: Option<String> = tx.query_row("SELECT id FROM journals WHERE source_session_id=?1 AND subject_id=?2",params![attr.session_id,host.subject_id],|r|r.get(0)).optional()?;
|
||||
if let Some(id) = journal {
|
||||
// The erasure marker is the only condition permitting receipt deletion. Normal
|
||||
// record/checkpoint/retention paths retain their immutable receipts.
|
||||
tx.execute("DELETE FROM journal_operations WHERE journal_id=?1",[&id])?;
|
||||
tx.execute("DELETE FROM journal_generations WHERE journal_id=?1",[&id])?;
|
||||
tx.execute("DELETE FROM journal_corrections WHERE entry_id IN (SELECT id FROM journal_entries WHERE journal_id=?1) OR target_id IN (SELECT id FROM journal_entries WHERE journal_id=?1)",[&id])?;
|
||||
tx.execute("DELETE FROM journal_entries WHERE journal_id=?1",[&id])?;
|
||||
tx.execute("DELETE FROM journal_sources WHERE journal_id=?1",[&id])?;
|
||||
tx.execute("DELETE FROM journals WHERE id=?1",[&id])?;
|
||||
}
|
||||
Ok(())
|
||||
})
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,668 @@
|
||||
//! Additive, immutable provenance-to-context links, not additional evidence for a Memory claim.
|
||||
//!
|
||||
//! Reconciliation reads only saved candidate anchors and the Host-attested Journal source ledger.
|
||||
//! It never fetches history, starts Workers, changes extraction/consolidation, fixes an open event,
|
||||
//! or mutates Memory. A stable evidence reference identifies a public entry, not its legacy numeric
|
||||
//! display range. Missing stable identity stays unconnected; numeric ranges are not guessed to be
|
||||
//! canonical order. Saved edges remain usable without the original runtime and cannot be retargeted.
|
||||
//! Journal content is never copied here. Explicit erasure retains edges and exposes the tombstone.
|
||||
|
||||
use super::{
|
||||
JournalError, JournalHostContext, JournalResult, JournalSourcePointer, JournalTextField,
|
||||
JournalTextPage, MAX_JOURNAL_PAGE, MAX_JOURNAL_RESPONSE_BYTES,
|
||||
};
|
||||
use crate::{MAX_STAGING_ANCHORS, SubjectStagingRecord, SubjektivStore};
|
||||
use memory::schema::SourceEvidenceRef;
|
||||
use rusqlite::{Connection, OptionalExtension, Transaction, params};
|
||||
use serde::{Deserialize, Serialize};
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests;
|
||||
|
||||
pub(crate) fn migrate(tx: &Transaction<'_>) -> feature_storage::Result<()> {
|
||||
tx.execute_batch(include_str!("schema.sql"))?;
|
||||
Ok(())
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct MemoryJournalSelector {
|
||||
pub memory_id: String,
|
||||
pub change_id: String,
|
||||
pub candidate_id: String,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(tag = "action", rename_all = "snake_case", deny_unknown_fields)]
|
||||
pub enum MemoryJournalRequest {
|
||||
Reconcile {
|
||||
selector: MemoryJournalSelector,
|
||||
},
|
||||
/// Reads saved link state only; does not implicitly retry reconciliation.
|
||||
Links {
|
||||
selector: MemoryJournalSelector,
|
||||
},
|
||||
/// Continues reconciliation over immutable source indices, at most MAX_STAGING_ANCHORS per call.
|
||||
ReconcilePage {
|
||||
selector: MemoryJournalSelector,
|
||||
source_offset: usize,
|
||||
limit: usize,
|
||||
},
|
||||
/// Reads another saved source page without reconciliation.
|
||||
LinksPage {
|
||||
selector: MemoryJournalSelector,
|
||||
source_offset: usize,
|
||||
limit: usize,
|
||||
},
|
||||
Read {
|
||||
selector: MemoryJournalSelector,
|
||||
source_index: usize,
|
||||
journal_id: String,
|
||||
entry_id: String,
|
||||
expected_token: Option<String>,
|
||||
byte_offset: usize,
|
||||
max_bytes: usize,
|
||||
},
|
||||
Related {
|
||||
journal_id: String,
|
||||
entry_id: String,
|
||||
after: Option<RelatedMemoryCursor>,
|
||||
limit: usize,
|
||||
},
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(
|
||||
tag = "kind",
|
||||
content = "value",
|
||||
rename_all = "snake_case",
|
||||
deny_unknown_fields
|
||||
)]
|
||||
pub enum MemoryJournalResponse {
|
||||
Links(MemoryJournalLinks),
|
||||
Read(MemoryJournalRead),
|
||||
Related(RelatedMemories),
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(rename_all = "snake_case")]
|
||||
pub enum OriginalSourceAvailability {
|
||||
/// No saved Host attestation. None of these values imply a live history fetch.
|
||||
Unknown,
|
||||
Missing,
|
||||
Available,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(rename_all = "snake_case")]
|
||||
pub enum JournalTargetAvailability {
|
||||
Available,
|
||||
Unavailable,
|
||||
Erased,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(rename_all = "snake_case")]
|
||||
pub enum UnconnectedReason {
|
||||
NotReconciled,
|
||||
InsufficientSource,
|
||||
SourceNotAdmitted,
|
||||
AmbiguousSource,
|
||||
JournalNotFixed,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(tag = "state", rename_all = "snake_case", deny_unknown_fields)]
|
||||
pub enum SourceConnection {
|
||||
Unconnected {
|
||||
reason: UnconnectedReason,
|
||||
},
|
||||
Linked {
|
||||
journal_id: String,
|
||||
entry_id: String,
|
||||
target: JournalTargetAvailability,
|
||||
/// A saved correction invites reconsideration, never an automatic Memory edit.
|
||||
reconsideration: bool,
|
||||
},
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct MemoryJournalSourceLink {
|
||||
pub source_index: usize,
|
||||
pub original_source: OriginalSourceAvailability,
|
||||
pub connection: SourceConnection,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct MemoryJournalLinks {
|
||||
pub selector: MemoryJournalSelector,
|
||||
pub sources: Vec<MemoryJournalSourceLink>,
|
||||
pub total_sources: usize,
|
||||
pub next_source_index: Option<usize>,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct MemoryJournalRead {
|
||||
pub source: MemoryJournalSourceLink,
|
||||
/// Absent for an unavailable or explicitly erased target; never falls back to another entry.
|
||||
pub page: Option<JournalTextPage>,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct RelatedMemoryCursor {
|
||||
pub memory_id: String,
|
||||
pub change_id: String,
|
||||
pub candidate_id: String,
|
||||
pub source_index: usize,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct RelatedMemory {
|
||||
pub selector: MemoryJournalSelector,
|
||||
pub source_index: usize,
|
||||
pub reconsideration: bool,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct RelatedMemories {
|
||||
pub items: Vec<RelatedMemory>,
|
||||
pub next: Option<RelatedMemoryCursor>,
|
||||
}
|
||||
|
||||
fn invalid(message: &str) -> JournalError {
|
||||
JournalError::InvalidInput(message.into())
|
||||
}
|
||||
|
||||
fn identifier(value: &str) -> JournalResult<()> {
|
||||
if value.is_empty() || value.len() > 256 || value.chars().any(char::is_control) {
|
||||
return Err(invalid("invalid Memory/Journal selector identifier"));
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
fn selector_valid(selector: &MemoryJournalSelector) -> JournalResult<()> {
|
||||
identifier(&selector.memory_id)?;
|
||||
identifier(&selector.change_id)?;
|
||||
identifier(&selector.candidate_id)
|
||||
}
|
||||
|
||||
fn candidate(
|
||||
store: &SubjektivStore,
|
||||
tx: &Connection,
|
||||
host: &JournalHostContext,
|
||||
selector: &MemoryJournalSelector,
|
||||
) -> JournalResult<SubjectStagingRecord> {
|
||||
super::store::check_host(store, tx, host, false)?;
|
||||
selector_valid(selector)?;
|
||||
// The immutable change-candidate edge, not the current Memory projection or a supplied
|
||||
// candidate ID alone, authorizes this provenance selector.
|
||||
let raw: Option<String> = tx
|
||||
.query_row(
|
||||
"SELECT s.record_json FROM staging_records s JOIN memory_change_candidates c
|
||||
ON c.subject_id=s.subject_id AND c.candidate_id=s.candidate_id
|
||||
WHERE c.subject_id=?1 AND c.memory_id=?2 AND c.change_id=?3 AND c.candidate_id=?4",
|
||||
params![
|
||||
host.subject_id,
|
||||
selector.memory_id,
|
||||
selector.change_id,
|
||||
selector.candidate_id
|
||||
],
|
||||
|r| r.get(0),
|
||||
)
|
||||
.optional()?;
|
||||
let record: SubjectStagingRecord = serde_json::from_str(
|
||||
&raw.ok_or_else(|| JournalError::NotFound("Memory change candidate membership".into()))?,
|
||||
)?;
|
||||
Ok(record)
|
||||
}
|
||||
|
||||
#[derive(Debug)]
|
||||
struct SavedLink {
|
||||
reason: String,
|
||||
journal_id: Option<String>,
|
||||
entry_id: Option<String>,
|
||||
session_id: Option<String>,
|
||||
order: Option<u64>,
|
||||
}
|
||||
|
||||
fn saved(
|
||||
tx: &Connection,
|
||||
host: &JournalHostContext,
|
||||
candidate_id: &str,
|
||||
index: usize,
|
||||
) -> JournalResult<Option<SavedLink>> {
|
||||
Ok(tx.query_row(
|
||||
"SELECT reason,journal_id,entry_id,source_session_id,source_order FROM memory_journal_links
|
||||
WHERE subject_id=?1 AND candidate_id=?2 AND source_index=?3",
|
||||
params![host.subject_id, candidate_id, index],
|
||||
|r| Ok(SavedLink { reason:r.get(0)?,journal_id:r.get(1)?,entry_id:r.get(2)?,session_id:r.get(3)?,order:r.get(4)? }),
|
||||
).optional()?)
|
||||
}
|
||||
|
||||
fn original_availability(
|
||||
tx: &Connection,
|
||||
journal: &str,
|
||||
order: u64,
|
||||
) -> JournalResult<OriginalSourceAvailability> {
|
||||
let unavailable: Option<String> = tx
|
||||
.query_row(
|
||||
"SELECT unavailable_json FROM journal_sources WHERE journal_id=?1 AND source_order=?2",
|
||||
params![journal, order],
|
||||
|r| r.get(0),
|
||||
)
|
||||
.optional()?;
|
||||
Ok(match unavailable {
|
||||
None => OriginalSourceAvailability::Unknown,
|
||||
Some(raw) => {
|
||||
let ranges: Vec<super::JournalByteRange> = serde_json::from_str(&raw)?;
|
||||
if ranges.is_empty() {
|
||||
OriginalSourceAvailability::Available
|
||||
} else {
|
||||
OriginalSourceAvailability::Missing
|
||||
}
|
||||
}
|
||||
})
|
||||
}
|
||||
|
||||
fn project(
|
||||
tx: &Connection,
|
||||
host: &JournalHostContext,
|
||||
candidate_id: &str,
|
||||
index: usize,
|
||||
) -> JournalResult<MemoryJournalSourceLink> {
|
||||
let Some(link) = saved(tx, host, candidate_id, index)? else {
|
||||
return Ok(MemoryJournalSourceLink {
|
||||
source_index: index,
|
||||
original_source: OriginalSourceAvailability::Unknown,
|
||||
connection: SourceConnection::Unconnected {
|
||||
reason: UnconnectedReason::NotReconciled,
|
||||
},
|
||||
});
|
||||
};
|
||||
if link.reason != "linked" {
|
||||
let reason = match link.reason.as_str() {
|
||||
"insufficient_source" => UnconnectedReason::InsufficientSource,
|
||||
"source_not_admitted" => UnconnectedReason::SourceNotAdmitted,
|
||||
"ambiguous_source" => UnconnectedReason::AmbiguousSource,
|
||||
"journal_not_fixed" => UnconnectedReason::JournalNotFixed,
|
||||
_ => return Err(invalid("invalid saved connection reason")),
|
||||
};
|
||||
return Ok(MemoryJournalSourceLink {
|
||||
source_index: index,
|
||||
original_source: OriginalSourceAvailability::Unknown,
|
||||
connection: SourceConnection::Unconnected { reason },
|
||||
});
|
||||
}
|
||||
let journal_id = link
|
||||
.journal_id
|
||||
.ok_or_else(|| invalid("saved link lacks Journal"))?;
|
||||
let entry_id = link
|
||||
.entry_id
|
||||
.ok_or_else(|| invalid("saved link lacks entry"))?;
|
||||
let session = link
|
||||
.session_id
|
||||
.ok_or_else(|| invalid("saved link lacks Session"))?;
|
||||
let order = link
|
||||
.order
|
||||
.ok_or_else(|| invalid("saved link lacks source order"))?;
|
||||
let erased: bool = tx.query_row(
|
||||
"SELECT EXISTS(SELECT 1 FROM journal_erased_sessions WHERE subject_id=?1 AND session_id=?2)",
|
||||
params![host.subject_id, session], |r| r.get(0),
|
||||
)?;
|
||||
let exists: bool = tx.query_row(
|
||||
"SELECT EXISTS(SELECT 1 FROM journal_entries e JOIN journals j ON j.id=e.journal_id
|
||||
WHERE e.subject_id=?1 AND e.journal_id=?2 AND e.id=?3 AND j.source_session_id=?4)",
|
||||
params![host.subject_id, journal_id, entry_id, session],
|
||||
|r| r.get(0),
|
||||
)?;
|
||||
let reconsideration = tx.query_row(
|
||||
"SELECT EXISTS(SELECT 1 FROM journal_corrections WHERE subject_id=?1 AND target_id=?2)",
|
||||
params![host.subject_id, entry_id],
|
||||
|r| r.get(0),
|
||||
)?;
|
||||
Ok(MemoryJournalSourceLink {
|
||||
source_index: index,
|
||||
original_source: original_availability(tx, &journal_id, order)?,
|
||||
connection: SourceConnection::Linked {
|
||||
journal_id,
|
||||
entry_id,
|
||||
target: if erased {
|
||||
JournalTargetAvailability::Erased
|
||||
} else if exists {
|
||||
JournalTargetAvailability::Available
|
||||
} else {
|
||||
JournalTargetAvailability::Unavailable
|
||||
},
|
||||
reconsideration,
|
||||
},
|
||||
})
|
||||
}
|
||||
|
||||
struct Resolved {
|
||||
journal: String,
|
||||
entry: String,
|
||||
session: String,
|
||||
order: u64,
|
||||
}
|
||||
|
||||
fn resolve(
|
||||
tx: &Connection,
|
||||
host: &JournalHostContext,
|
||||
source: &SourceEvidenceRef,
|
||||
) -> JournalResult<Result<Resolved, &'static str>> {
|
||||
let Some(evidence) = source.evidence_id.as_deref() else {
|
||||
return Ok(Err("insufficient_source"));
|
||||
};
|
||||
if !evidence.starts_with('E')
|
||||
|| evidence.len() < 2
|
||||
|| evidence.len() > 129
|
||||
|| !evidence[1..]
|
||||
.bytes()
|
||||
.all(|c| c.is_ascii_alphanumeric() || c == b'-')
|
||||
|| (source.session_id.is_none() && source.segment_id.is_none())
|
||||
{
|
||||
return Ok(Err("insufficient_source"));
|
||||
}
|
||||
// Segment identity may be omitted only when an immutable Session attribution disambiguates it.
|
||||
// A candidate's primary legacy source range is not substituted for an individual anchor.
|
||||
let segment = match source.segment_id.as_deref() {
|
||||
Some(raw) => match uuid::Uuid::parse_str(raw) {
|
||||
Ok(id) => Some(id),
|
||||
Err(_) => return Ok(Err("insufficient_source")),
|
||||
},
|
||||
None => None,
|
||||
};
|
||||
let mut stmt = tx.prepare(
|
||||
"SELECT j.id,j.source_session_id,s.source_order,s.pointer_json FROM journal_sources s
|
||||
JOIN journals j ON j.id=s.journal_id
|
||||
JOIN subject_session_attributions a ON a.subject_id=j.subject_id AND a.session_id=j.source_session_id
|
||||
WHERE j.subject_id=?1 AND s.entry_ref=?2
|
||||
AND (?3 IS NULL OR j.source_session_id=?3)
|
||||
AND (?4 IS NULL OR json_extract(s.pointer_json,'$.segment_id')=?4)
|
||||
LIMIT 2",
|
||||
)?;
|
||||
let found = stmt
|
||||
.query_map(
|
||||
params![
|
||||
host.subject_id,
|
||||
evidence,
|
||||
source.session_id,
|
||||
segment.map(|s| s.to_string())
|
||||
],
|
||||
|r| {
|
||||
Ok((
|
||||
r.get::<_, String>(0)?,
|
||||
r.get::<_, String>(1)?,
|
||||
r.get::<_, u64>(2)?,
|
||||
r.get::<_, String>(3)?,
|
||||
))
|
||||
},
|
||||
)?
|
||||
.collect::<Result<Vec<_>, _>>()?;
|
||||
if found.is_empty() {
|
||||
return Ok(Err("source_not_admitted"));
|
||||
}
|
||||
if found.len() != 1 {
|
||||
return Ok(Err("ambiguous_source"));
|
||||
}
|
||||
let (journal, session, order, pointer) = &found[0];
|
||||
let pointer: JournalSourcePointer = serde_json::from_str(pointer)?;
|
||||
if pointer.entry_ref != evidence || segment.is_some_and(|s| s != pointer.segment_id) {
|
||||
return Ok(Err("ambiguous_source"));
|
||||
}
|
||||
// A fixed endpoint covers (previous_fixed_end, source_end]. The Session start is the first
|
||||
// interval's lower boundary. Processing checkpoints and open entries cannot supply an end.
|
||||
let mut stmt = tx.prepare(
|
||||
"SELECT e.id FROM journal_entries e WHERE e.subject_id=?1 AND e.journal_id=?2
|
||||
AND e.state='fixed' AND e.source_order>=?3
|
||||
AND NOT EXISTS(SELECT 1 FROM journal_entries p WHERE p.journal_id=e.journal_id
|
||||
AND p.position<e.position AND p.state='fixed' AND p.source_order>=?3)
|
||||
ORDER BY e.position LIMIT 2",
|
||||
)?;
|
||||
let entries = stmt
|
||||
.query_map(params![host.subject_id, journal, order], |r| {
|
||||
r.get::<_, String>(0)
|
||||
})?
|
||||
.collect::<Result<Vec<_>, _>>()?;
|
||||
match entries.as_slice() {
|
||||
[entry] => Ok(Ok(Resolved {
|
||||
journal: journal.clone(),
|
||||
entry: entry.clone(),
|
||||
session: session.clone(),
|
||||
order: *order,
|
||||
})),
|
||||
[] => Ok(Err("journal_not_fixed")),
|
||||
_ => Ok(Err("ambiguous_source")),
|
||||
}
|
||||
}
|
||||
|
||||
fn reconcile(
|
||||
tx: &Connection,
|
||||
host: &JournalHostContext,
|
||||
record: &SubjectStagingRecord,
|
||||
indices: std::ops::Range<usize>,
|
||||
) -> JournalResult<()> {
|
||||
for index in indices {
|
||||
let source = &record.source_refs[index];
|
||||
if saved(tx, host, &record.id, index)?.is_some_and(|s| s.reason == "linked") {
|
||||
continue;
|
||||
}
|
||||
let (reason, resolved) = match resolve(tx, host, source)? {
|
||||
Ok(link) => ("linked", Some(link)),
|
||||
Err(reason) => (reason, None),
|
||||
};
|
||||
tx.execute(
|
||||
"INSERT INTO memory_journal_links(subject_id,candidate_id,source_index,reason,
|
||||
journal_id,entry_id,source_session_id,source_order) VALUES(?1,?2,?3,?4,?5,?6,?7,?8)
|
||||
ON CONFLICT(subject_id,candidate_id,source_index) DO UPDATE SET
|
||||
reason=excluded.reason,journal_id=excluded.journal_id,entry_id=excluded.entry_id,
|
||||
source_session_id=excluded.source_session_id,source_order=excluded.source_order",
|
||||
params![
|
||||
host.subject_id,
|
||||
record.id,
|
||||
index,
|
||||
reason,
|
||||
resolved.as_ref().map(|r| r.journal.as_str()),
|
||||
resolved.as_ref().map(|r| r.entry.as_str()),
|
||||
resolved.as_ref().map(|r| r.session.as_str()),
|
||||
resolved.as_ref().map(|r| r.order)
|
||||
],
|
||||
)?;
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
impl SubjektivStore {
|
||||
/// Scoped Memory provenance bridge. Reconcile is additive and idempotent, so a lost response
|
||||
/// needs no operation ledger: retry the same selector and reread saved edges. Reads never reconcile.
|
||||
pub fn execute_memory_journal(
|
||||
&self,
|
||||
host: &JournalHostContext,
|
||||
request: MemoryJournalRequest,
|
||||
) -> JournalResult<MemoryJournalResponse> {
|
||||
let response = match request {
|
||||
MemoryJournalRequest::Reconcile { selector } => {
|
||||
self.memory_journal_links(host, selector, true, 0, MAX_STAGING_ANCHORS)?
|
||||
}
|
||||
MemoryJournalRequest::Links { selector } => {
|
||||
self.memory_journal_links(host, selector, false, 0, MAX_STAGING_ANCHORS)?
|
||||
}
|
||||
MemoryJournalRequest::ReconcilePage {
|
||||
selector,
|
||||
source_offset,
|
||||
limit,
|
||||
} => self.memory_journal_links(host, selector, true, source_offset, limit)?,
|
||||
MemoryJournalRequest::LinksPage {
|
||||
selector,
|
||||
source_offset,
|
||||
limit,
|
||||
} => self.memory_journal_links(host, selector, false, source_offset, limit)?,
|
||||
MemoryJournalRequest::Read {
|
||||
selector,
|
||||
source_index,
|
||||
journal_id,
|
||||
entry_id,
|
||||
expected_token,
|
||||
byte_offset,
|
||||
max_bytes,
|
||||
} => {
|
||||
identifier(&journal_id)?;
|
||||
identifier(&entry_id)?;
|
||||
if !(4..=super::MAX_JOURNAL_READ_BYTES).contains(&max_bytes) {
|
||||
return Err(invalid("text page must be 4..16384 bytes"));
|
||||
}
|
||||
if let Some(token) = expected_token.as_deref() {
|
||||
identifier(token)?;
|
||||
}
|
||||
let mut source = self.database.try_with_connection(|tx| {
|
||||
let record = candidate(self, tx, host, &selector)?;
|
||||
if source_index >= record.source_refs.len() {
|
||||
return Err(invalid("source index outside candidate anchors"));
|
||||
}
|
||||
let link = project(tx, host, &selector.candidate_id, source_index)?;
|
||||
match &link.connection {
|
||||
SourceConnection::Linked {
|
||||
journal_id: saved_journal,
|
||||
entry_id: saved_entry,
|
||||
..
|
||||
} if saved_journal == &journal_id && saved_entry == &entry_id => Ok(link),
|
||||
_ => Err(JournalError::PermissionDenied(
|
||||
"read requires the exact saved Journal link".into(),
|
||||
)),
|
||||
}
|
||||
})?;
|
||||
let page = match &source.connection {
|
||||
SourceConnection::Linked {
|
||||
target: JournalTargetAvailability::Available,
|
||||
..
|
||||
} => {
|
||||
match self.read_journal_text(
|
||||
host,
|
||||
&journal_id,
|
||||
Some(&entry_id),
|
||||
JournalTextField::Body,
|
||||
expected_token.as_deref(),
|
||||
byte_offset,
|
||||
max_bytes,
|
||||
) {
|
||||
Ok(page) => Some(page),
|
||||
// Erasure between the saved-edge check and shared text read must not
|
||||
// fall back, expose cached text, or pretend the link never existed.
|
||||
Err(JournalError::NotFound(_)) => {
|
||||
source = self.database.try_with_connection(|tx| {
|
||||
project(tx, host, &selector.candidate_id, source_index)
|
||||
})?;
|
||||
None
|
||||
}
|
||||
Err(error) => return Err(error),
|
||||
}
|
||||
}
|
||||
_ => None,
|
||||
};
|
||||
MemoryJournalResponse::Read(MemoryJournalRead { source, page })
|
||||
}
|
||||
MemoryJournalRequest::Related {
|
||||
journal_id,
|
||||
entry_id,
|
||||
after,
|
||||
limit,
|
||||
} => self.related_memories(host, &journal_id, &entry_id, after.as_ref(), limit)?,
|
||||
};
|
||||
if serde_json::to_string_pretty(&response)?.len() > MAX_JOURNAL_RESPONSE_BYTES {
|
||||
return Err(invalid("Memory Journal response exceeds byte budget"));
|
||||
}
|
||||
Ok(response)
|
||||
}
|
||||
|
||||
fn memory_journal_links(
|
||||
&self,
|
||||
host: &JournalHostContext,
|
||||
selector: MemoryJournalSelector,
|
||||
do_reconcile: bool,
|
||||
source_offset: usize,
|
||||
limit: usize,
|
||||
) -> JournalResult<MemoryJournalResponse> {
|
||||
if !(1..=MAX_STAGING_ANCHORS).contains(&limit) {
|
||||
return Err(invalid("source page exceeds staging anchor bound"));
|
||||
}
|
||||
self.database.try_transaction(|tx| {
|
||||
let record = candidate(self, tx, host, &selector)?;
|
||||
let total_sources = record.source_refs.len();
|
||||
if source_offset > total_sources {
|
||||
return Err(invalid("source offset outside immutable candidate anchors"));
|
||||
}
|
||||
let end = source_offset.saturating_add(limit).min(total_sources);
|
||||
if do_reconcile {
|
||||
reconcile(tx, host, &record, source_offset..end)?;
|
||||
}
|
||||
let sources = (source_offset..end)
|
||||
.map(|index| project(tx, host, &selector.candidate_id, index))
|
||||
.collect::<JournalResult<Vec<_>>>()?;
|
||||
Ok(MemoryJournalResponse::Links(MemoryJournalLinks {
|
||||
selector,
|
||||
sources,
|
||||
total_sources,
|
||||
next_source_index: (end < total_sources).then_some(end),
|
||||
}))
|
||||
})
|
||||
}
|
||||
|
||||
fn related_memories(
|
||||
&self,
|
||||
host: &JournalHostContext,
|
||||
journal_id: &str,
|
||||
entry_id: &str,
|
||||
after: Option<&RelatedMemoryCursor>,
|
||||
limit: usize,
|
||||
) -> JournalResult<MemoryJournalResponse> {
|
||||
identifier(journal_id)?;
|
||||
identifier(entry_id)?;
|
||||
if !(1..=MAX_JOURNAL_PAGE).contains(&limit) {
|
||||
return Err(invalid("related page must be 1..32"));
|
||||
}
|
||||
if let Some(cursor) = after {
|
||||
identifier(&cursor.memory_id)?;
|
||||
identifier(&cursor.change_id)?;
|
||||
identifier(&cursor.candidate_id)?;
|
||||
if i64::try_from(cursor.source_index).is_err() {
|
||||
return Err(invalid("invalid related source index"));
|
||||
}
|
||||
}
|
||||
self.database.try_with_connection(|tx| {
|
||||
super::store::check_host(self,tx,host,false)?;
|
||||
// Saved target identity authorizes reverse lookup after erasure as well as before it.
|
||||
let known:bool=tx.query_row(
|
||||
"SELECT EXISTS(SELECT 1 FROM journal_entries WHERE subject_id=?1 AND journal_id=?2 AND id=?3)
|
||||
OR EXISTS(SELECT 1 FROM memory_journal_links WHERE subject_id=?1 AND journal_id=?2 AND entry_id=?3)",
|
||||
params![host.subject_id,journal_id,entry_id],|r|r.get(0))?;
|
||||
if !known { return Err(JournalError::NotFound("Journal entry".into())); }
|
||||
let mut stmt=tx.prepare(
|
||||
"SELECT m.memory_id,m.change_id,l.candidate_id,l.source_index,
|
||||
EXISTS(SELECT 1 FROM journal_corrections c WHERE c.subject_id=l.subject_id AND c.target_id=l.entry_id)
|
||||
FROM memory_journal_links l JOIN memory_change_candidates m
|
||||
ON m.subject_id=l.subject_id AND m.candidate_id=l.candidate_id
|
||||
WHERE l.subject_id=?1 AND l.reason='linked'
|
||||
AND ((l.journal_id=?2 AND l.entry_id=?3)
|
||||
OR EXISTS(SELECT 1 FROM journal_corrections c WHERE c.subject_id=?1 AND c.entry_id=?3 AND c.target_id=l.entry_id))
|
||||
AND (?4 IS NULL OR (m.memory_id,m.change_id,l.candidate_id,l.source_index)>(?4,?5,?6,?7))
|
||||
ORDER BY m.memory_id,m.change_id,l.candidate_id,l.source_index LIMIT ?8")?;
|
||||
let mut items=stmt.query_map(params![host.subject_id,journal_id,entry_id,
|
||||
after.map(|c|c.memory_id.as_str()),after.map(|c|c.change_id.as_str()),
|
||||
after.map(|c|c.candidate_id.as_str()),after.map(|c|c.source_index),limit+1],
|
||||
|r|Ok(RelatedMemory {selector:MemoryJournalSelector {memory_id:r.get(0)?,change_id:r.get(1)?,candidate_id:r.get(2)?},
|
||||
source_index:r.get(3)?,reconsideration:r.get(4)?}))?.collect::<Result<Vec<_>,_>>()?;
|
||||
let more=items.len()>limit;
|
||||
items.truncate(limit);
|
||||
let next=if more {items.last().map(|last|RelatedMemoryCursor {
|
||||
memory_id:last.selector.memory_id.clone(),change_id:last.selector.change_id.clone(),
|
||||
candidate_id:last.selector.candidate_id.clone(),source_index:last.source_index })} else {None};
|
||||
Ok(MemoryJournalResponse::Related(RelatedMemories {items,next}))
|
||||
})
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,33 @@
|
||||
-- References outlive explicit Journal erasure. Do not add target-row foreign keys:
|
||||
-- lifecycle erasure deletes Journal content but retains its Session tombstone.
|
||||
CREATE TABLE memory_journal_links (
|
||||
subject_id TEXT NOT NULL,
|
||||
candidate_id TEXT NOT NULL,
|
||||
source_index INTEGER NOT NULL CHECK(source_index >= 0),
|
||||
reason TEXT NOT NULL CHECK(reason IN (
|
||||
'insufficient_source', 'source_not_admitted', 'ambiguous_source',
|
||||
'journal_not_fixed', 'linked'
|
||||
)),
|
||||
journal_id TEXT,
|
||||
entry_id TEXT,
|
||||
source_session_id TEXT,
|
||||
source_order INTEGER,
|
||||
PRIMARY KEY(subject_id, candidate_id, source_index),
|
||||
FOREIGN KEY(subject_id, candidate_id)
|
||||
REFERENCES staging_records(subject_id, candidate_id) ON DELETE RESTRICT,
|
||||
CHECK((reason = 'linked' AND journal_id IS NOT NULL AND entry_id IS NOT NULL
|
||||
AND source_session_id IS NOT NULL AND source_order IS NOT NULL AND source_order >= 0)
|
||||
OR (reason <> 'linked' AND journal_id IS NULL AND entry_id IS NULL
|
||||
AND source_session_id IS NULL AND source_order IS NULL))
|
||||
);
|
||||
CREATE INDEX memory_journal_links_reverse
|
||||
ON memory_journal_links(subject_id, journal_id, entry_id, candidate_id, source_index);
|
||||
CREATE TRIGGER memory_journal_links_identity BEFORE UPDATE ON memory_journal_links
|
||||
WHEN OLD.subject_id <> NEW.subject_id OR OLD.candidate_id <> NEW.candidate_id
|
||||
OR OLD.source_index <> NEW.source_index
|
||||
BEGIN SELECT RAISE(ABORT, 'Journal source reference identity is immutable'); END;
|
||||
CREATE TRIGGER memory_journal_links_connected_immutable BEFORE UPDATE ON memory_journal_links
|
||||
WHEN OLD.reason = 'linked'
|
||||
BEGIN SELECT RAISE(ABORT, 'connected Journal references are immutable'); END;
|
||||
CREATE TRIGGER memory_journal_links_retained BEFORE DELETE ON memory_journal_links
|
||||
BEGIN SELECT RAISE(ABORT, 'Journal references are retained'); END;
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,415 @@
|
||||
//! Durable activity records owned by Subjektiv, independent of Session retention.
|
||||
//!
|
||||
//! Hosts attest committed public source identity and canonical Session order, not models. Byte
|
||||
//! ranges are half-open in the Host's canonical UTF-8 public-entry serialization (including
|
||||
//! framing, so even an empty message has a nonzero length). Compaction copies must retain the
|
||||
//! original pointer/order/digest; derived summaries are not new sources. Rewind replacement is
|
||||
//! an identity conflict, never an implicit reset. This module does not fetch or retain history.
|
||||
//!
|
||||
//! Each record operation and its exact retry receipt commit together. A separate checkpoint
|
||||
//! advances only a contiguous, selected prefix backed by saved record/explicit no-change
|
||||
//! receipts. It cannot use a position update as evidence. Stopping between these boundaries
|
||||
//! leaves saved records and unreflected input; read receipts before retrying, even across reopen
|
||||
//! or replacement Jobs. No whole-Job result submission is required. The Host checks live Job
|
||||
//! execution leases before issuing contexts, and durably closes a generation on cancellation.
|
||||
//!
|
||||
//! Selected ranges describe concrete public bytes supplied to generation, not a preview's
|
||||
//! enclosing history range or a permission to claim unobserved bytes. The Host verifies canonical
|
||||
//! serialization, SHA-256 identity and UTF-8 slice boundaries before admission/selection. This
|
||||
//! store validates identities, byte bounds and coverage but cannot attest text it does not fetch.
|
||||
//! Availability is the latest Host attestation; readers must not equate it with a live fetch.
|
||||
//! Public text and metadata reads are paged. Full generation/resume snapshots are Host-only
|
||||
//! construction material bounded by per-field storage caps (three text fields plus current position),
|
||||
//! not model-facing reads. A restored snapshot never restores an external Job lease.
|
||||
//!
|
||||
//! A T-734 caller saves `Create`/`Rewrite`/`Fix` under stable request IDs, carries each returned
|
||||
//! `state_token` into the next operation, optionally saves `UpdatePosition`, then submits
|
||||
//! `Checkpoint { record_operation_ids }` for just the reflected prefix. After a lost response it
|
||||
//! queries the original receipt, status and coverage pages before submitting any new create.
|
||||
//! On restart it reads the active generation and current resume state, verifies the external Job
|
||||
//! binding, and continues missing operations; cancellation closes the generation before replacement.
|
||||
//! A replacement may checkpoint old saved record receipts only for identical selected source bytes.
|
||||
//! Tokens incorporate prior saved content conditions as well as current content, preventing A→B→A
|
||||
//! edits from resurrecting an old operation premise after intervening saved effects.
|
||||
//! Source-ledger pagination uses an opaque, scope/Subject/Journal-bound content cursor: late gap
|
||||
//! admission, accepted-fragment extension, reflection, or availability changes reject continuation.
|
||||
//! The fingerprint and bounded projection share one transaction; hashing streams bounded rows.
|
||||
//! Hosts resuming at the processing cursor can use a bounded source point lookup instead of
|
||||
//! traversing already reflected pages. Receipt/entry keysets remain append-stable.
|
||||
|
||||
pub mod binding;
|
||||
pub use binding::JournalWriterBinding;
|
||||
pub(crate) use binding::migrate as migrate_binding;
|
||||
pub mod browser;
|
||||
mod lifecycle;
|
||||
pub mod memory_links;
|
||||
pub(crate) use lifecycle::migrate as migrate_lifecycle;
|
||||
pub mod recording;
|
||||
pub mod service;
|
||||
mod source_status;
|
||||
pub mod startup;
|
||||
mod store;
|
||||
#[cfg(test)]
|
||||
mod tests;
|
||||
pub mod transport;
|
||||
|
||||
use crate::{SubjectSessionAttribution, SubjektivStore, api::JobAttemptBinding};
|
||||
use feature_storage::FeatureStorageError;
|
||||
use rusqlite::Transaction;
|
||||
use serde::{Deserialize, Serialize};
|
||||
use uuid::Uuid;
|
||||
|
||||
pub type JournalId = String;
|
||||
pub type JournalEntryId = String;
|
||||
pub type JournalResult<T> = Result<T, JournalError>;
|
||||
pub const MAX_JOURNAL_TEXT_BYTES: usize = 1024 * 1024;
|
||||
pub const MAX_JOURNAL_RANGES: usize = 64;
|
||||
pub const MAX_JOURNAL_PAGE: usize = 32;
|
||||
pub const MAX_JOURNAL_READ_BYTES: usize = 16 * 1024;
|
||||
/// Whole pretty-serialized public page budget, including escaped text and metadata.
|
||||
pub const MAX_JOURNAL_RESPONSE_BYTES: usize = 64 * 1024;
|
||||
|
||||
/// Stable owner of Backend source retention, shared by attribution-time protection
|
||||
/// and later source admission/release. This identifier confers no read authority.
|
||||
/// Local standalone storage uses its scope-exclusive Session UUID as the owner.
|
||||
pub fn source_retention_pin(workspace: &str, subject: &str, session: &str) -> Uuid {
|
||||
use sha2::{Digest, Sha256};
|
||||
let digest = Sha256::digest(
|
||||
serde_json::to_vec(&(
|
||||
"subjektiv-journal-retention-v1",
|
||||
workspace,
|
||||
subject,
|
||||
session,
|
||||
))
|
||||
.expect("string tuple serialization"),
|
||||
);
|
||||
let mut bytes = [0; 16];
|
||||
bytes.copy_from_slice(&digest[..16]);
|
||||
Uuid::from_bytes(bytes)
|
||||
}
|
||||
|
||||
#[derive(Debug, thiserror::Error)]
|
||||
pub enum JournalError {
|
||||
#[error("journal permission denied: {0}")]
|
||||
PermissionDenied(String),
|
||||
#[error("journal conflict: {0}")]
|
||||
Conflict(String),
|
||||
#[error("invalid journal input: {0}")]
|
||||
InvalidInput(String),
|
||||
#[error("journal record not found: {0}")]
|
||||
NotFound(String),
|
||||
#[error(transparent)]
|
||||
Storage(#[from] FeatureStorageError),
|
||||
#[error(transparent)]
|
||||
Json(#[from] serde_json::Error),
|
||||
#[error(transparent)]
|
||||
Subject(#[from] crate::SubjektivError),
|
||||
}
|
||||
impl From<rusqlite::Error> for JournalError {
|
||||
fn from(e: rusqlite::Error) -> Self {
|
||||
Self::Storage(e.into())
|
||||
}
|
||||
}
|
||||
|
||||
/// Host-issued in-process authority, never a model request DTO. Reader contexts need no live Session.
|
||||
#[derive(Debug, Clone)]
|
||||
pub struct JournalHostContext {
|
||||
scope_id: String,
|
||||
subject_id: String,
|
||||
attribution: Option<SubjectSessionAttribution>,
|
||||
writer_binding_id: Option<String>,
|
||||
}
|
||||
impl JournalHostContext {
|
||||
/// Evidence for a retained Job grant, not permission to mint or renew a binding.
|
||||
pub fn writer_binding_id(&self) -> Option<&str> {
|
||||
self.writer_binding_id.as_deref()
|
||||
}
|
||||
|
||||
pub fn validated_reader(store: &SubjektivStore, subject_id: &str) -> JournalResult<Self> {
|
||||
store
|
||||
.subject(subject_id)?
|
||||
.ok_or_else(|| JournalError::NotFound(subject_id.into()))?;
|
||||
Ok(Self {
|
||||
scope_id: store.scope_id().into(),
|
||||
subject_id: subject_id.into(),
|
||||
attribution: None,
|
||||
writer_binding_id: None,
|
||||
})
|
||||
}
|
||||
/// External authentication, public-history validation and execution authority are Host duties.
|
||||
pub fn validated_session(
|
||||
store: &SubjektivStore,
|
||||
attribution: SubjectSessionAttribution,
|
||||
) -> JournalResult<Self> {
|
||||
if store.session_attribution(&attribution.session_id)?.as_ref() != Some(&attribution) {
|
||||
return Err(JournalError::PermissionDenied(
|
||||
"immutable Session attribution mismatch".into(),
|
||||
));
|
||||
}
|
||||
let mut context = Self::validated_reader(store, &attribution.subject_id)?;
|
||||
use rusqlite::OptionalExtension;
|
||||
context.writer_binding_id = store.database.try_with_connection(|tx| {
|
||||
Ok::<_, JournalError>(
|
||||
tx.query_row(
|
||||
"SELECT binding_id FROM journal_session_bindings WHERE session_id=?1",
|
||||
[&attribution.session_id],
|
||||
|r| r.get(0),
|
||||
)
|
||||
.optional()?,
|
||||
)
|
||||
})?;
|
||||
context.attribution = Some(attribution);
|
||||
Ok(context)
|
||||
}
|
||||
}
|
||||
|
||||
/// A restricted Journal generation, not Memory consolidation authority.
|
||||
#[derive(Debug, Clone)]
|
||||
pub struct JournalJobContext {
|
||||
host: JournalHostContext,
|
||||
generation_id: String,
|
||||
binding: JobAttemptBinding,
|
||||
}
|
||||
impl JournalJobContext {
|
||||
pub fn validated(
|
||||
store: &SubjektivStore,
|
||||
host: &JournalHostContext,
|
||||
generation_id: &str,
|
||||
binding: JobAttemptBinding,
|
||||
) -> JournalResult<Self> {
|
||||
let context = Self {
|
||||
host: host.clone(),
|
||||
generation_id: generation_id.into(),
|
||||
binding,
|
||||
};
|
||||
store.validate_journal_job(&context)?;
|
||||
Ok(context)
|
||||
}
|
||||
|
||||
/// Reconstructs a retained binding for exact completion/receipt recovery. Hosts still check
|
||||
/// the external attempt lease. New record/checkpoint operations independently require an
|
||||
/// active generation inside their transaction, so this never revives cancelled authority.
|
||||
pub fn validated_recovery(
|
||||
store: &SubjektivStore,
|
||||
host: &JournalHostContext,
|
||||
generation_id: &str,
|
||||
binding: JobAttemptBinding,
|
||||
) -> JournalResult<Self> {
|
||||
let context = Self {
|
||||
host: host.clone(),
|
||||
generation_id: generation_id.into(),
|
||||
binding,
|
||||
};
|
||||
store.database.try_with_connection(|tx| {
|
||||
self::store::job(store, tx, &context, false)?;
|
||||
Ok::<_, JournalError>(())
|
||||
})?;
|
||||
Ok(context)
|
||||
}
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct JournalSourcePointer {
|
||||
pub segment_id: Uuid,
|
||||
/// Serialized public SessionEntryRef, including its `E` prefix.
|
||||
pub entry_ref: String,
|
||||
}
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct JournalSource {
|
||||
pub session_id: String,
|
||||
pub pointer: JournalSourcePointer,
|
||||
/// Host-attested canonical public entry order across Segments, starting at zero.
|
||||
pub order: u64,
|
||||
pub content_sha256: String,
|
||||
pub total_bytes: u64,
|
||||
}
|
||||
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct JournalByteRange {
|
||||
pub start: u64,
|
||||
pub end: u64,
|
||||
}
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct JournalSourceRange {
|
||||
pub source: JournalSource,
|
||||
pub bytes: JournalByteRange,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(rename_all = "snake_case")]
|
||||
pub enum JournalEntryState {
|
||||
Open,
|
||||
Fixed,
|
||||
}
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
|
||||
pub struct Journal {
|
||||
pub id: JournalId,
|
||||
pub subject_id: String,
|
||||
pub source_session_id: String,
|
||||
pub title: String,
|
||||
pub current_position: String,
|
||||
/// Processing cursor is independent of every fixed event endpoint.
|
||||
pub process_order: u64,
|
||||
pub process_byte: u64,
|
||||
/// Content condition advanced by committed operations, never by acceptance notifications.
|
||||
pub state_token: String,
|
||||
pub created_at: String,
|
||||
pub updated_at: String,
|
||||
}
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
|
||||
pub struct JournalMetadata {
|
||||
pub id: JournalId,
|
||||
pub subject_id: String,
|
||||
pub source_session_id: String,
|
||||
pub title: String,
|
||||
pub current_position_bytes: usize,
|
||||
pub process_order: u64,
|
||||
pub process_byte: u64,
|
||||
pub state_token: String,
|
||||
pub created_at: String,
|
||||
pub updated_at: String,
|
||||
}
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
|
||||
pub struct JournalEntry {
|
||||
pub id: JournalEntryId,
|
||||
pub journal_id: JournalId,
|
||||
pub position: u64,
|
||||
pub state: JournalEntryState,
|
||||
pub title: String,
|
||||
pub body: String,
|
||||
pub ongoing: String,
|
||||
pub source_end: Option<JournalSourcePointer>,
|
||||
pub created_at: String,
|
||||
pub updated_at: String,
|
||||
pub fixed_at: Option<String>,
|
||||
pub correction_refs: Vec<JournalEntryId>,
|
||||
}
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
|
||||
pub struct JournalGeneration {
|
||||
pub id: String,
|
||||
pub journal_id: JournalId,
|
||||
pub job: JobAttemptBinding,
|
||||
pub selected_ranges: Vec<JournalSourceRange>,
|
||||
pub initial_journal: Journal,
|
||||
pub initial_open: Option<JournalEntry>,
|
||||
pub previous_fixed_end: Option<JournalSourcePointer>,
|
||||
}
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(tag = "action", rename_all = "snake_case", deny_unknown_fields)]
|
||||
pub enum JournalAction {
|
||||
Create {
|
||||
title: String,
|
||||
body: String,
|
||||
ongoing: String,
|
||||
state: JournalEntryState,
|
||||
source_end: Option<JournalSourcePointer>,
|
||||
correction_refs: Vec<JournalEntryId>,
|
||||
},
|
||||
Rewrite {
|
||||
entry_id: JournalEntryId,
|
||||
title: String,
|
||||
body: String,
|
||||
ongoing: String,
|
||||
},
|
||||
Fix {
|
||||
entry_id: JournalEntryId,
|
||||
source_end: JournalSourcePointer,
|
||||
},
|
||||
UpdatePosition {
|
||||
current_position: String,
|
||||
},
|
||||
/// Explicitly records the caller's checked conclusion that no entry change is needed.
|
||||
ConfirmUnchanged,
|
||||
/// Links durable record/no-change receipts to actual reflected input; IDs are Journal scoped.
|
||||
Checkpoint {
|
||||
record_operation_ids: Vec<String>,
|
||||
},
|
||||
}
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct JournalOperation {
|
||||
pub request_id: String,
|
||||
pub expected_state: String,
|
||||
pub action: JournalAction,
|
||||
pub covered_ranges: Vec<JournalSourceRange>,
|
||||
}
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
|
||||
pub struct JournalReceipt {
|
||||
pub request_id: String,
|
||||
pub generation_id: String,
|
||||
pub entry_id: Option<JournalEntryId>,
|
||||
pub state_token: String,
|
||||
pub process_order: u64,
|
||||
pub process_byte: u64,
|
||||
}
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
|
||||
pub struct JournalSavedOperation {
|
||||
pub operation: JournalOperation,
|
||||
pub receipt: JournalReceipt,
|
||||
}
|
||||
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(rename_all = "snake_case")]
|
||||
pub enum JournalOperationKind {
|
||||
Create,
|
||||
Rewrite,
|
||||
Fix,
|
||||
UpdatePosition,
|
||||
ConfirmUnchanged,
|
||||
Checkpoint,
|
||||
}
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
|
||||
pub struct JournalOperationStatus {
|
||||
pub receipt: JournalReceipt,
|
||||
pub kind: JournalOperationKind,
|
||||
pub covered_range_count: usize,
|
||||
}
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
|
||||
pub struct JournalSourceStatus {
|
||||
pub source: JournalSource,
|
||||
pub accepted: Vec<JournalByteRange>,
|
||||
pub unavailable: Vec<JournalByteRange>,
|
||||
pub reflected_bytes: u64,
|
||||
}
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
|
||||
pub struct JournalPage<T> {
|
||||
pub items: Vec<T>,
|
||||
pub next: Option<String>,
|
||||
}
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
|
||||
pub struct JournalEntrySummary {
|
||||
pub id: JournalEntryId,
|
||||
pub journal_id: JournalId,
|
||||
pub position: u64,
|
||||
pub state: JournalEntryState,
|
||||
pub title: String,
|
||||
pub source_end: Option<JournalSourcePointer>,
|
||||
/// Exclusive start; None means Session start. The end is inclusive.
|
||||
pub previous_fixed_end: Option<JournalSourcePointer>,
|
||||
pub source_available: bool,
|
||||
pub correction_refs: Vec<JournalEntryId>,
|
||||
pub content_token: String,
|
||||
pub created_at: String,
|
||||
pub updated_at: String,
|
||||
pub fixed_at: Option<String>,
|
||||
}
|
||||
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(rename_all = "snake_case")]
|
||||
pub enum JournalTextField {
|
||||
Body,
|
||||
Ongoing,
|
||||
CurrentPosition,
|
||||
}
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
|
||||
pub struct JournalTextPage {
|
||||
pub text: String,
|
||||
pub next_byte: Option<usize>,
|
||||
pub content_token: String,
|
||||
}
|
||||
|
||||
pub(super) fn migrate(tx: &Transaction<'_>) -> feature_storage::Result<()> {
|
||||
tx.execute_batch(include_str!("schema.sql"))?;
|
||||
Ok(())
|
||||
}
|
||||
@@ -0,0 +1,194 @@
|
||||
//! Host-side construction of bounded Journal generation input.
|
||||
//!
|
||||
//! Admission and byte identity belong to the Session Host. Selection neither starts Jobs nor
|
||||
//! treats previews, failed fetches, or missing bytes as reflected. Production readers verify
|
||||
//! original canonical identity while streaming and return only the requested bounded fragment.
|
||||
|
||||
use super::*;
|
||||
use sha2::{Digest, Sha256};
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct JournalMaterial {
|
||||
pub range: JournalSourceRange,
|
||||
pub text: String,
|
||||
}
|
||||
|
||||
/// Adapter for Host captures already bounded by their storage read contract. Filesystem/Runtime
|
||||
/// callers should use [`select_materials_bounded`] rather than allocating a whole large entry.
|
||||
pub fn select_materials(
|
||||
store: &SubjektivStore,
|
||||
host: &JournalHostContext,
|
||||
journal_id: &str,
|
||||
max_bytes: usize,
|
||||
mut read: impl FnMut(&JournalSource) -> JournalResult<String>,
|
||||
) -> JournalResult<Vec<JournalMaterial>> {
|
||||
select_materials_bounded(
|
||||
store,
|
||||
host,
|
||||
journal_id,
|
||||
max_bytes,
|
||||
|source, start, limit| {
|
||||
let text = read(source)?;
|
||||
verify_canonical_text(source, &text)?;
|
||||
let start = usize::try_from(start).map_err(|_| invalid("source offset overflow"))?;
|
||||
if !text.is_char_boundary(start) {
|
||||
return Err(conflict("source offset is not UTF-8 aligned"));
|
||||
}
|
||||
let mut end = start.saturating_add(limit).min(text.len());
|
||||
while !text.is_char_boundary(end) {
|
||||
end -= 1;
|
||||
}
|
||||
Ok(JournalMaterial {
|
||||
range: JournalSourceRange {
|
||||
source: source.clone(),
|
||||
bytes: JournalByteRange {
|
||||
start: start as u64,
|
||||
end: end as u64,
|
||||
},
|
||||
},
|
||||
text: text[start..end].into(),
|
||||
})
|
||||
},
|
||||
)
|
||||
}
|
||||
|
||||
fn invalid(message: &str) -> JournalError {
|
||||
JournalError::InvalidInput(message.into())
|
||||
}
|
||||
fn conflict(message: &str) -> JournalError {
|
||||
JournalError::Conflict(message.into())
|
||||
}
|
||||
|
||||
/// Selects the oldest contiguous input under a whole serialized materials-array budget.
|
||||
/// The Host callback verifies original public provenance/digest/length while streaming, and
|
||||
/// returns at most `limit` canonical UTF-8 bytes at exactly `start`. Its descriptor must equal
|
||||
/// the admitted source. This in-process attestation must never be deserialized from model input.
|
||||
pub fn select_materials_bounded(
|
||||
store: &SubjektivStore,
|
||||
host: &JournalHostContext,
|
||||
journal_id: &str,
|
||||
max_bytes: usize,
|
||||
mut read: impl FnMut(&JournalSource, u64, usize) -> JournalResult<JournalMaterial>,
|
||||
) -> JournalResult<Vec<JournalMaterial>> {
|
||||
let journal = store.read_journal(host, journal_id)?;
|
||||
let mut order = journal.process_order;
|
||||
let mut offset = journal.process_byte;
|
||||
let mut materials = Vec::new();
|
||||
let mut remaining = max_bytes.saturating_sub(2);
|
||||
while materials.len() < MAX_JOURNAL_RANGES {
|
||||
let status = match store.read_journal_source(host, journal_id, order) {
|
||||
Ok(status) => status,
|
||||
Err(JournalError::NotFound(_)) => break,
|
||||
Err(error) => return Err(error),
|
||||
};
|
||||
if offset == status.source.total_bytes {
|
||||
order = order
|
||||
.checked_add(1)
|
||||
.ok_or_else(|| invalid("source order exhausted"))?;
|
||||
offset = 0;
|
||||
continue;
|
||||
}
|
||||
let Some(accepted) = status
|
||||
.accepted
|
||||
.iter()
|
||||
.find(|r| r.start <= offset && offset < r.end)
|
||||
else {
|
||||
break;
|
||||
};
|
||||
let mut end = accepted.end;
|
||||
for unavailable in &status.unavailable {
|
||||
if unavailable.start <= offset && offset < unavailable.end {
|
||||
end = offset;
|
||||
break;
|
||||
}
|
||||
if offset < unavailable.start {
|
||||
end = end.min(unavailable.start);
|
||||
}
|
||||
}
|
||||
if end == offset {
|
||||
break;
|
||||
}
|
||||
let empty = JournalMaterial {
|
||||
range: JournalSourceRange {
|
||||
source: status.source.clone(),
|
||||
bytes: JournalByteRange {
|
||||
start: offset,
|
||||
end: offset,
|
||||
},
|
||||
},
|
||||
text: String::new(),
|
||||
};
|
||||
let envelope = serde_json::to_vec(&empty)?.len() + usize::from(!materials.is_empty());
|
||||
// Reserve decimal endpoint growth and enough room for one UTF-8 scalar.
|
||||
let allowance = remaining.saturating_sub(envelope.saturating_add(20));
|
||||
if allowance < 4 {
|
||||
if materials.is_empty() {
|
||||
return Err(invalid(
|
||||
"input budget cannot fit source metadata and a UTF-8 scalar",
|
||||
));
|
||||
}
|
||||
break;
|
||||
}
|
||||
let limit = allowance.min((end - offset).min(usize::MAX as u64) as usize);
|
||||
let mut material = read(&status.source, offset, limit)?;
|
||||
if material.range.source != status.source
|
||||
|| material.range.bytes.start != offset
|
||||
|| material.range.bytes.end != offset.saturating_add(material.text.len() as u64)
|
||||
|| material.range.bytes.end > end
|
||||
|| material.text.is_empty()
|
||||
|| material.text.len() > limit
|
||||
{
|
||||
return Err(conflict(
|
||||
"Host source chunk does not match the requested canonical byte range",
|
||||
));
|
||||
}
|
||||
let mut allowance = remaining - envelope;
|
||||
let mut selected_bytes = 0;
|
||||
for ch in material.text.chars() {
|
||||
let cost = match ch {
|
||||
'"' | '\\' | '\u{8}' | '\u{c}' | '\n' | '\r' | '\t' => 2,
|
||||
ch if ch < '\u{20}' => 6,
|
||||
ch => ch.len_utf8(),
|
||||
};
|
||||
if cost.saturating_add(20) > allowance {
|
||||
break;
|
||||
}
|
||||
allowance -= cost;
|
||||
selected_bytes += ch.len_utf8();
|
||||
}
|
||||
if selected_bytes == 0 {
|
||||
if materials.is_empty() {
|
||||
return Err(invalid("input budget cannot fit one escaped UTF-8 scalar"));
|
||||
}
|
||||
break;
|
||||
}
|
||||
material.text.truncate(selected_bytes);
|
||||
material.range.bytes.end = offset + selected_bytes as u64;
|
||||
let cost = serde_json::to_vec(&material)?.len() + usize::from(!materials.is_empty());
|
||||
if cost > remaining {
|
||||
return Err(invalid("generation input budget accounting failed"));
|
||||
}
|
||||
remaining -= cost;
|
||||
offset = material.range.bytes.end;
|
||||
materials.push(material);
|
||||
if offset < end {
|
||||
break;
|
||||
}
|
||||
}
|
||||
Ok(materials)
|
||||
}
|
||||
|
||||
/// Verifies the full canonical public role/tool framing of an already bounded Host capture.
|
||||
pub fn verify_canonical_text(source: &JournalSource, text: &str) -> JournalResult<()> {
|
||||
if text.len() as u64 != source.total_bytes
|
||||
|| Sha256::digest(text.as_bytes())
|
||||
.iter()
|
||||
.map(|byte| format!("{byte:02x}"))
|
||||
.collect::<String>()
|
||||
!= source.content_sha256
|
||||
{
|
||||
return Err(conflict("canonical public source bytes changed"));
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
@@ -0,0 +1,88 @@
|
||||
CREATE TABLE journals (
|
||||
id TEXT PRIMARY KEY,
|
||||
subject_id TEXT NOT NULL REFERENCES subjects(subject_id) ON DELETE RESTRICT,
|
||||
source_session_id TEXT NOT NULL UNIQUE,
|
||||
title TEXT NOT NULL,
|
||||
current_position TEXT NOT NULL,
|
||||
process_order INTEGER NOT NULL DEFAULT 0 CHECK (process_order >= 0),
|
||||
process_byte INTEGER NOT NULL DEFAULT 0 CHECK (process_byte >= 0),
|
||||
state_token TEXT NOT NULL,
|
||||
created_at TEXT NOT NULL,
|
||||
updated_at TEXT NOT NULL,
|
||||
UNIQUE(subject_id, id)
|
||||
);
|
||||
CREATE TABLE journal_entries (
|
||||
id TEXT PRIMARY KEY,
|
||||
subject_id TEXT NOT NULL,
|
||||
journal_id TEXT NOT NULL,
|
||||
position INTEGER NOT NULL CHECK (position >= 0),
|
||||
state TEXT NOT NULL CHECK (state IN ('open', 'fixed')),
|
||||
title TEXT NOT NULL,
|
||||
body TEXT NOT NULL,
|
||||
ongoing TEXT NOT NULL,
|
||||
source_end_json TEXT,
|
||||
source_order INTEGER,
|
||||
created_at TEXT NOT NULL,
|
||||
updated_at TEXT NOT NULL,
|
||||
fixed_at TEXT,
|
||||
UNIQUE(journal_id, position),
|
||||
UNIQUE(subject_id, id),
|
||||
FOREIGN KEY(subject_id, journal_id) REFERENCES journals(subject_id, id) ON DELETE RESTRICT,
|
||||
CHECK ((state = 'open' AND source_end_json IS NULL AND source_order IS NULL AND fixed_at IS NULL)
|
||||
OR (state = 'fixed' AND source_end_json IS NOT NULL AND source_order IS NOT NULL AND source_order >= 0 AND fixed_at IS NOT NULL AND ongoing = ''))
|
||||
);
|
||||
CREATE UNIQUE INDEX journal_one_open ON journal_entries(journal_id) WHERE state = 'open';
|
||||
CREATE TRIGGER journal_append_after_open BEFORE INSERT ON journal_entries
|
||||
WHEN EXISTS (SELECT 1 FROM journal_entries WHERE journal_id = NEW.journal_id AND state = 'open')
|
||||
BEGIN SELECT RAISE(ABORT, 'journal open must be the tail'); END;
|
||||
CREATE TRIGGER journal_fixed_immutable BEFORE UPDATE ON journal_entries WHEN OLD.state = 'fixed'
|
||||
BEGIN SELECT RAISE(ABORT, 'journal fixed entries are immutable'); END;
|
||||
CREATE TRIGGER journal_entry_identity BEFORE UPDATE ON journal_entries
|
||||
WHEN OLD.id <> NEW.id OR OLD.subject_id <> NEW.subject_id OR OLD.journal_id <> NEW.journal_id
|
||||
OR OLD.position <> NEW.position OR OLD.created_at <> NEW.created_at
|
||||
BEGIN SELECT RAISE(ABORT, 'journal entry identity is immutable'); END;
|
||||
CREATE TABLE journal_corrections (
|
||||
subject_id TEXT NOT NULL,
|
||||
entry_id TEXT NOT NULL,
|
||||
target_id TEXT NOT NULL,
|
||||
PRIMARY KEY(entry_id, target_id),
|
||||
FOREIGN KEY(subject_id, entry_id) REFERENCES journal_entries(subject_id, id) ON DELETE RESTRICT,
|
||||
FOREIGN KEY(subject_id, target_id) REFERENCES journal_entries(subject_id, id) ON DELETE RESTRICT,
|
||||
CHECK(entry_id <> target_id)
|
||||
);
|
||||
CREATE TABLE journal_sources (
|
||||
journal_id TEXT NOT NULL REFERENCES journals(id) ON DELETE RESTRICT,
|
||||
source_order INTEGER NOT NULL CHECK(source_order >= 0),
|
||||
pointer_json TEXT NOT NULL,
|
||||
entry_ref TEXT NOT NULL,
|
||||
source_json TEXT NOT NULL,
|
||||
accepted_json TEXT NOT NULL,
|
||||
unavailable_json TEXT NOT NULL,
|
||||
reflected_bytes INTEGER NOT NULL DEFAULT 0 CHECK(reflected_bytes >= 0),
|
||||
PRIMARY KEY(journal_id, source_order),
|
||||
UNIQUE(journal_id, pointer_json),
|
||||
UNIQUE(journal_id, entry_ref)
|
||||
);
|
||||
CREATE TABLE journal_generations (
|
||||
id TEXT PRIMARY KEY,
|
||||
journal_id TEXT NOT NULL REFERENCES journals(id) ON DELETE RESTRICT,
|
||||
job_id TEXT NOT NULL,
|
||||
attempt_id TEXT NOT NULL,
|
||||
request_json TEXT NOT NULL,
|
||||
snapshot_json TEXT NOT NULL,
|
||||
active INTEGER NOT NULL CHECK(active IN (0, 1)),
|
||||
UNIQUE(journal_id, job_id, attempt_id)
|
||||
);
|
||||
CREATE UNIQUE INDEX journal_one_generation ON journal_generations(journal_id) WHERE active = 1;
|
||||
CREATE TABLE journal_operations (
|
||||
journal_id TEXT NOT NULL REFERENCES journals(id) ON DELETE RESTRICT,
|
||||
request_id TEXT NOT NULL,
|
||||
generation_id TEXT NOT NULL REFERENCES journal_generations(id) ON DELETE RESTRICT,
|
||||
request_json TEXT NOT NULL,
|
||||
receipt_json TEXT NOT NULL,
|
||||
PRIMARY KEY(journal_id, request_id)
|
||||
);
|
||||
CREATE TRIGGER journal_operations_no_update BEFORE UPDATE ON journal_operations
|
||||
BEGIN SELECT RAISE(ABORT, 'journal operation receipts are immutable'); END;
|
||||
CREATE TRIGGER journal_operations_no_delete BEFORE DELETE ON journal_operations
|
||||
BEGIN SELECT RAISE(ABORT, 'journal operation receipts are retained'); END;
|
||||
@@ -0,0 +1,424 @@
|
||||
//! Shared sequential Job service. Backend and standalone authenticate and check the live attempt
|
||||
//! before each call; the store additionally fences closed generations inside mutation transactions.
|
||||
//! Job completion attests a saved processing checkpoint, not model prose or fixed event state.
|
||||
|
||||
use super::transport::*;
|
||||
use super::*;
|
||||
use rusqlite::{OptionalExtension, params};
|
||||
use sha2::{Digest, Sha256};
|
||||
|
||||
fn metadata(j: &Journal) -> JournalMetadata {
|
||||
JournalMetadata {
|
||||
id: j.id.clone(),
|
||||
subject_id: j.subject_id.clone(),
|
||||
source_session_id: j.source_session_id.clone(),
|
||||
title: j.title.clone(),
|
||||
current_position_bytes: j.current_position.len(),
|
||||
process_order: j.process_order,
|
||||
process_byte: j.process_byte,
|
||||
state_token: j.state_token.clone(),
|
||||
created_at: j.created_at.clone(),
|
||||
updated_at: j.updated_at.clone(),
|
||||
}
|
||||
}
|
||||
|
||||
fn text_page(
|
||||
text: &str,
|
||||
read: &JournalTextRead,
|
||||
condition: &[u8],
|
||||
maximum_end: usize,
|
||||
) -> JournalResult<JournalTextPage> {
|
||||
if !(1..=MAX_JOURNAL_READ_BYTES).contains(&read.limit)
|
||||
|| read.offset > maximum_end
|
||||
|| !text.is_char_boundary(read.offset)
|
||||
{
|
||||
return Err(JournalError::InvalidInput(
|
||||
"invalid Journal UTF-8 read range".into(),
|
||||
));
|
||||
}
|
||||
let token: String = Sha256::digest(condition)
|
||||
.iter()
|
||||
.map(|b| format!("{b:02x}"))
|
||||
.collect();
|
||||
if read
|
||||
.content_token
|
||||
.as_deref()
|
||||
.is_some_and(|expected| expected != token)
|
||||
|| (read.offset > 0 && read.content_token.is_none())
|
||||
{
|
||||
return Err(JournalError::Conflict(
|
||||
"Journal text changed or continuation condition missing".into(),
|
||||
));
|
||||
}
|
||||
let mut end = read.offset.saturating_add(read.limit).min(maximum_end);
|
||||
while !text.is_char_boundary(end) {
|
||||
end -= 1;
|
||||
}
|
||||
if end == read.offset && end < maximum_end {
|
||||
return Err(JournalError::InvalidInput(
|
||||
"read limit cannot fit one UTF-8 scalar".into(),
|
||||
));
|
||||
}
|
||||
Ok(JournalTextPage {
|
||||
text: text[read.offset..end].into(),
|
||||
next_byte: (end < maximum_end).then_some(end),
|
||||
content_token: token,
|
||||
})
|
||||
}
|
||||
|
||||
/// Adapter for Host captures bounded by their storage contract. Production source reads should
|
||||
/// use [`execute_bounded`] to avoid allocating an entire source for one small read.
|
||||
pub fn execute(
|
||||
store: &SubjektivStore,
|
||||
context: &JournalJobContext,
|
||||
request: JournalJobRequest,
|
||||
mut read_source: impl FnMut(&JournalSource) -> JournalResult<String>,
|
||||
) -> JournalResult<JournalJobResponse> {
|
||||
execute_bounded(store, context, request, |source, start, limit| {
|
||||
let text = read_source(source)?;
|
||||
super::recording::verify_canonical_text(source, &text)?;
|
||||
let start = usize::try_from(start)
|
||||
.map_err(|_| JournalError::InvalidInput("source offset overflow".into()))?;
|
||||
if !text.is_char_boundary(start) {
|
||||
return Err(JournalError::InvalidInput(
|
||||
"source offset is not UTF-8 aligned".into(),
|
||||
));
|
||||
}
|
||||
let mut end = start.saturating_add(limit).min(text.len());
|
||||
while !text.is_char_boundary(end) {
|
||||
end -= 1;
|
||||
}
|
||||
Ok(recording::JournalMaterial {
|
||||
range: JournalSourceRange {
|
||||
source: source.clone(),
|
||||
bytes: JournalByteRange {
|
||||
start: start as u64,
|
||||
end: end as u64,
|
||||
},
|
||||
},
|
||||
text: text[start..end].into(),
|
||||
})
|
||||
})
|
||||
}
|
||||
|
||||
/// Reads are delivered through this service before mutation authority is enabled. The durable
|
||||
/// delivery ledger stores byte ranges only: Jobs may retain immutable descriptors without
|
||||
/// accumulating a permanent second copy of the original Session in their request ledgers.
|
||||
/// The Host verifies original provenance/digest/length and returns a bounded UTF-8 fragment.
|
||||
pub fn execute_bounded(
|
||||
store: &SubjektivStore,
|
||||
context: &JournalJobContext,
|
||||
request: JournalJobRequest,
|
||||
mut read_source: impl FnMut(&JournalSource, u64, usize) -> JournalResult<recording::JournalMaterial>,
|
||||
) -> JournalResult<JournalJobResponse> {
|
||||
let generation = store
|
||||
.database
|
||||
.try_with_connection(|tx| super::store::job(store, tx, context, true))?;
|
||||
let mut delivered = None;
|
||||
let response = match request {
|
||||
JournalJobRequest::Execute { operation } => {
|
||||
require_delivery(store, context, &generation.selected_ranges)?;
|
||||
let receipt = if matches!(operation.action, JournalAction::Checkpoint { .. }) {
|
||||
crate::api::checkpoint_journal(store, context, operation)?
|
||||
} else {
|
||||
crate::api::execute_journal(store, context, operation)?
|
||||
};
|
||||
JournalJobResponse::Saved(receipt)
|
||||
}
|
||||
JournalJobRequest::ReadState => {
|
||||
let state = store.database.try_with_connection(|tx| {
|
||||
let generation = super::store::job(store, tx, context, true)?;
|
||||
let current =
|
||||
super::store::journal(tx, &context.host, &generation.journal_id, true)?;
|
||||
let current_open = super::store::open(tx, &generation.journal_id)?;
|
||||
Ok::<_, JournalError>(JournalJobState {
|
||||
generation_id: generation.id,
|
||||
initial_journal: metadata(&generation.initial_journal),
|
||||
initial_open: generation
|
||||
.initial_open
|
||||
.map(|e| super::store::summary(tx, e))
|
||||
.transpose()?,
|
||||
current_journal: metadata(¤t),
|
||||
current_open: current_open
|
||||
.map(|e| super::store::summary(tx, e))
|
||||
.transpose()?,
|
||||
previous_fixed_end: generation.previous_fixed_end,
|
||||
selected_ranges: generation.selected_ranges,
|
||||
})
|
||||
})?;
|
||||
JournalJobResponse::State(state)
|
||||
}
|
||||
JournalJobRequest::QueryOperation { request_id } => {
|
||||
let status = match store.read_journal_operation_status(
|
||||
&context.host,
|
||||
&generation.journal_id,
|
||||
&request_id,
|
||||
) {
|
||||
Ok(status) => Some(status),
|
||||
Err(JournalError::NotFound(_)) => None,
|
||||
Err(error) => return Err(error),
|
||||
};
|
||||
JournalJobResponse::Operation(status)
|
||||
}
|
||||
JournalJobRequest::ReadOperationCoverage {
|
||||
request_id,
|
||||
offset,
|
||||
limit,
|
||||
} => JournalJobResponse::Coverage(store.read_journal_operation_coverage(
|
||||
&context.host,
|
||||
&generation.journal_id,
|
||||
&request_id,
|
||||
offset,
|
||||
limit,
|
||||
)?),
|
||||
JournalJobRequest::ListOperations { after, limit } => {
|
||||
let receipts = store.list_journal_operations(
|
||||
&context.host,
|
||||
&generation.journal_id,
|
||||
after.as_deref(),
|
||||
limit,
|
||||
)?;
|
||||
let items = receipts
|
||||
.items
|
||||
.iter()
|
||||
.map(|r| {
|
||||
store.read_journal_operation_status(
|
||||
&context.host,
|
||||
&generation.journal_id,
|
||||
&r.request_id,
|
||||
)
|
||||
})
|
||||
.collect::<JournalResult<Vec<_>>>()?;
|
||||
JournalJobResponse::Operations(JournalPage {
|
||||
items,
|
||||
next: receipts.next,
|
||||
})
|
||||
}
|
||||
JournalJobRequest::ReadText { read } => {
|
||||
let text = match &read.target {
|
||||
JournalTextTarget::Source { pointer } => {
|
||||
let range = generation
|
||||
.selected_ranges
|
||||
.iter()
|
||||
.find(|r| {
|
||||
&r.source.pointer == pointer
|
||||
&& r.bytes.start <= read.offset as u64
|
||||
&& read.offset as u64 <= r.bytes.end
|
||||
})
|
||||
.ok_or_else(|| {
|
||||
JournalError::PermissionDenied(
|
||||
"source bytes are outside this generation".into(),
|
||||
)
|
||||
})?;
|
||||
if !(1..=MAX_JOURNAL_READ_BYTES).contains(&read.limit) {
|
||||
return Err(JournalError::InvalidInput(
|
||||
"invalid source read limit".into(),
|
||||
));
|
||||
}
|
||||
let condition =
|
||||
serde_json::to_vec(&(&generation.id, &range.source, range.bytes))?;
|
||||
let token: String = Sha256::digest(&condition)
|
||||
.iter()
|
||||
.map(|b| format!("{b:02x}"))
|
||||
.collect();
|
||||
if read
|
||||
.content_token
|
||||
.as_deref()
|
||||
.is_some_and(|expected| expected != token)
|
||||
|| (read.offset as u64 != range.bytes.start && read.content_token.is_none())
|
||||
{
|
||||
return Err(JournalError::Conflict(
|
||||
"source continuation condition missing or changed".into(),
|
||||
));
|
||||
}
|
||||
let mut material =
|
||||
read_source(&range.source, read.offset as u64, read.limit.max(4))?;
|
||||
if material.range.source != range.source
|
||||
|| material.range.bytes.start != read.offset as u64
|
||||
|| material.range.bytes.end
|
||||
!= (read.offset as u64).saturating_add(material.text.len() as u64)
|
||||
|| material.range.bytes.end > range.source.total_bytes
|
||||
|| material.text.len() > read.limit.max(4)
|
||||
{
|
||||
return Err(JournalError::Conflict(
|
||||
"source fragment identity or byte range changed".into(),
|
||||
));
|
||||
}
|
||||
let mut length = material
|
||||
.text
|
||||
.len()
|
||||
.min(read.limit)
|
||||
.min((range.bytes.end - read.offset as u64) as usize);
|
||||
while !material.text.is_char_boundary(length) {
|
||||
length -= 1;
|
||||
}
|
||||
if length == 0 && (read.offset as u64) < range.bytes.end {
|
||||
return Err(JournalError::InvalidInput(
|
||||
"read limit cannot fit a source UTF-8 scalar".into(),
|
||||
));
|
||||
}
|
||||
material.text.truncate(length);
|
||||
let end = read.offset + length;
|
||||
if length > 0 {
|
||||
delivered = Some((
|
||||
range.source.order,
|
||||
JournalByteRange {
|
||||
start: read.offset as u64,
|
||||
end: end as u64,
|
||||
},
|
||||
));
|
||||
}
|
||||
JournalTextPage {
|
||||
text: material.text,
|
||||
next_byte: ((end as u64) < range.bytes.end).then_some(end),
|
||||
content_token: token,
|
||||
}
|
||||
}
|
||||
target => {
|
||||
let (journal, open) = match target {
|
||||
JournalTextTarget::Position { snapshot }
|
||||
| JournalTextTarget::OpenBody { snapshot }
|
||||
| JournalTextTarget::OpenOngoing { snapshot } => match snapshot {
|
||||
JournalSnapshot::Initial => (
|
||||
generation.initial_journal.clone(),
|
||||
generation.initial_open.clone(),
|
||||
),
|
||||
JournalSnapshot::Current => {
|
||||
store.journal_resume_state(&context.host, &generation.journal_id)?
|
||||
}
|
||||
},
|
||||
JournalTextTarget::Source { .. } => unreachable!(),
|
||||
};
|
||||
let text = match target {
|
||||
JournalTextTarget::Position { .. } => journal.current_position.clone(),
|
||||
JournalTextTarget::OpenBody { .. } => open
|
||||
.as_ref()
|
||||
.ok_or_else(|| JournalError::NotFound("no open entry".into()))?
|
||||
.body
|
||||
.clone(),
|
||||
JournalTextTarget::OpenOngoing { .. } => open
|
||||
.as_ref()
|
||||
.ok_or_else(|| JournalError::NotFound("no open entry".into()))?
|
||||
.ongoing
|
||||
.clone(),
|
||||
JournalTextTarget::Source { .. } => unreachable!(),
|
||||
};
|
||||
let condition = serde_json::to_vec(&(
|
||||
&generation.id,
|
||||
&read.target,
|
||||
&journal.state_token,
|
||||
&text,
|
||||
))?;
|
||||
text_page(&text, &read, &condition, text.len())?
|
||||
}
|
||||
};
|
||||
JournalJobResponse::Text(text)
|
||||
}
|
||||
};
|
||||
if serde_json::to_vec(&response)?.len() > MAX_JOURNAL_RESPONSE_BYTES {
|
||||
return Err(JournalError::InvalidInput(
|
||||
"Journal response exceeds bounded tool budget".into(),
|
||||
));
|
||||
}
|
||||
if let Some((order, range)) = delivered {
|
||||
store.database.try_transaction(|tx| {
|
||||
// A response that cannot fit the tool budget or loses its live generation must
|
||||
// not attest bytes. Lost responses can safely reread the identical source page.
|
||||
super::store::job(store, tx, context, true)?;
|
||||
let saved: Option<String> = tx.query_row(
|
||||
"SELECT ranges_json FROM journal_generation_deliveries WHERE generation_id=?1 AND source_order=?2",
|
||||
params![context.generation_id, order], |row| row.get(0),
|
||||
).optional()?;
|
||||
let mut ranges: Vec<JournalByteRange> = saved.map(|raw| serde_json::from_str(&raw)).transpose()?.unwrap_or_default();
|
||||
ranges.push(range);
|
||||
tx.execute(
|
||||
"INSERT INTO journal_generation_deliveries(generation_id,source_order,ranges_json) VALUES(?1,?2,?3) ON CONFLICT(generation_id,source_order) DO UPDATE SET ranges_json=excluded.ranges_json",
|
||||
params![context.generation_id, order, serde_json::to_string(&super::store::merge(ranges)?)?],
|
||||
)?;
|
||||
Ok::<_, JournalError>(())
|
||||
})?;
|
||||
}
|
||||
Ok(response)
|
||||
}
|
||||
|
||||
fn require_delivery(
|
||||
store: &SubjektivStore,
|
||||
context: &JournalJobContext,
|
||||
selected: &[JournalSourceRange],
|
||||
) -> JournalResult<()> {
|
||||
store.database.try_with_connection(|tx| {
|
||||
super::store::job(store, tx, context, true)?;
|
||||
for range in selected {
|
||||
let saved: Option<String> = tx.query_row(
|
||||
"SELECT ranges_json FROM journal_generation_deliveries WHERE generation_id=?1 AND source_order=?2",
|
||||
params![context.generation_id, range.source.order], |row| row.get(0),
|
||||
).optional()?;
|
||||
let delivered: Vec<JournalByteRange> = saved.map(|raw| serde_json::from_str(&raw)).transpose()?.unwrap_or_default();
|
||||
if !delivered.iter().any(|bytes| bytes.start <= range.bytes.start && range.bytes.end <= bytes.end) {
|
||||
return Err(JournalError::Conflict(
|
||||
"read every selected source byte with ReadJournalText before recording or checkpointing".into(),
|
||||
));
|
||||
}
|
||||
}
|
||||
Ok(())
|
||||
})
|
||||
}
|
||||
|
||||
/// Atomically saves completion and fences new operations. Exact replay returns the same saved
|
||||
/// completion even after later generations advance the Journal. Cancelled incomplete generations
|
||||
/// cannot manufacture completion, and neither fixing an entry nor updating position can substitute
|
||||
/// for the receipt-backed processing cursor.
|
||||
pub fn finish(
|
||||
store: &SubjektivStore,
|
||||
context: &JournalJobContext,
|
||||
) -> JournalResult<JournalJobCompletion> {
|
||||
store.database.try_transaction(|tx| {
|
||||
let generation = super::store::job(store, tx, context, false)?;
|
||||
let saved: Option<String> = tx
|
||||
.query_row(
|
||||
"SELECT completion_json FROM journal_generations WHERE id=?1",
|
||||
[&generation.id],
|
||||
|row| row.get(0),
|
||||
)
|
||||
.optional()?
|
||||
.flatten();
|
||||
if let Some(saved) = saved {
|
||||
return Ok(serde_json::from_str(&saved)?);
|
||||
}
|
||||
super::store::job(store, tx, context, true)?;
|
||||
super::binding::require_saved_position(tx, &generation.id)?;
|
||||
let last = generation
|
||||
.selected_ranges
|
||||
.last()
|
||||
.ok_or_else(|| JournalError::InvalidInput("empty generation selection".into()))?;
|
||||
let end = if last.bytes.end == last.source.total_bytes {
|
||||
(
|
||||
last.source
|
||||
.order
|
||||
.checked_add(1)
|
||||
.ok_or_else(|| JournalError::InvalidInput("source order exhausted".into()))?,
|
||||
0,
|
||||
)
|
||||
} else {
|
||||
(last.source.order, last.bytes.end)
|
||||
};
|
||||
let journal = super::store::journal(tx, &context.host, &generation.journal_id, true)?;
|
||||
if (journal.process_order, journal.process_byte) != end {
|
||||
return Err(JournalError::Conflict(
|
||||
"generation has unreflected selected bytes; save a receipt-backed checkpoint first"
|
||||
.into(),
|
||||
));
|
||||
}
|
||||
let completion = JournalJobCompletion {
|
||||
generation_id: generation.id.clone(),
|
||||
state_token: journal.state_token,
|
||||
process_order: journal.process_order,
|
||||
process_byte: journal.process_byte,
|
||||
};
|
||||
tx.execute(
|
||||
"UPDATE journal_generations SET active=0,completion_json=?2 WHERE id=?1",
|
||||
params![generation.id, serde_json::to_string(&completion)?],
|
||||
)?;
|
||||
Ok(completion)
|
||||
})
|
||||
}
|
||||
@@ -0,0 +1,93 @@
|
||||
//! Optional Host metadata observations for original material, independent of saved Journal reading.
|
||||
//!
|
||||
//! Presence checks must not fetch original history or restore a Worker. A failed/unauthorized
|
||||
//! metadata lookup is unknown, not missing, and cannot prevent a saved Journal body from being read.
|
||||
|
||||
use super::memory_links::{
|
||||
MemoryJournalRequest, MemoryJournalResponse, OriginalSourceAvailability,
|
||||
};
|
||||
use super::{JournalHostContext, JournalResult, SubjektivStore};
|
||||
use rusqlite::{OptionalExtension, params};
|
||||
|
||||
impl SubjektivStore {
|
||||
/// Executes the saved-reference operation first, then annotates original-source absence using
|
||||
/// Host-owned metadata only. `Some(false)` is confirmed absence; `None` is an unavailable lookup.
|
||||
/// Presence alone cannot attest that a particular historical entry is still readable.
|
||||
pub fn execute_memory_journal_with_source_presence(
|
||||
&self,
|
||||
host: &JournalHostContext,
|
||||
request: MemoryJournalRequest,
|
||||
mut presence: impl FnMut(&str) -> Option<bool>,
|
||||
) -> JournalResult<MemoryJournalResponse> {
|
||||
let selector = match &request {
|
||||
MemoryJournalRequest::Reconcile { selector }
|
||||
| MemoryJournalRequest::Links { selector }
|
||||
| MemoryJournalRequest::ReconcilePage { selector, .. }
|
||||
| MemoryJournalRequest::LinksPage { selector, .. }
|
||||
| MemoryJournalRequest::Read { selector, .. } => Some(selector.clone()),
|
||||
MemoryJournalRequest::Related { .. } => None,
|
||||
};
|
||||
let mut response = self.execute_memory_journal(host, request)?;
|
||||
let Some(selector) = selector else {
|
||||
return Ok(response);
|
||||
};
|
||||
// Membership and scoped reader authority were checked by the operation. Candidate JSON is
|
||||
// immutable; never infer source ownership from its presence without checking attribution.
|
||||
let candidate = self.staging_candidate(&host.subject_id, &selector.candidate_id)?;
|
||||
let mut observations = std::collections::HashMap::new();
|
||||
let mut annotate =
|
||||
|link: &mut super::memory_links::MemoryJournalSourceLink| -> JournalResult<()> {
|
||||
let source = candidate
|
||||
.as_ref()
|
||||
.and_then(|c| c.source_refs.get(link.source_index));
|
||||
// Legacy anchors may lack a Session ID. A connected edge already resolved it
|
||||
// from immutable attribution and stable Segment/entry identity; reuse that saved
|
||||
// identity rather than fetching history or modifying the original candidate.
|
||||
let saved_session: Option<String> = self.database.try_with_connection(|tx| {
|
||||
Ok::<_, super::JournalError>(tx.query_row(
|
||||
"SELECT source_session_id FROM memory_journal_links
|
||||
WHERE subject_id=?1 AND candidate_id=?2 AND source_index=?3 AND reason='linked'",
|
||||
params![host.subject_id, selector.candidate_id, link.source_index],
|
||||
|row| row.get(0),
|
||||
).optional()?)
|
||||
})?;
|
||||
let session = saved_session
|
||||
.as_deref()
|
||||
.or_else(|| source.and_then(|s| s.session_id.as_deref()));
|
||||
let observed = if let Some(session) = session {
|
||||
if let Some(value) = observations.get(session) {
|
||||
*value
|
||||
} else {
|
||||
let owned = self
|
||||
.session_attribution(session)?
|
||||
.is_some_and(|a| a.subject_id == host.subject_id);
|
||||
let value = if owned { presence(session) } else { None };
|
||||
observations.insert(session.to_owned(), value);
|
||||
value
|
||||
}
|
||||
} else {
|
||||
None
|
||||
};
|
||||
link.original_source = match observed {
|
||||
Some(false) => OriginalSourceAvailability::Missing,
|
||||
// Preserve explicit saved missing-byte attestations. Directory/registry presence
|
||||
// does not prove the referenced entry survived rewind or storage corruption.
|
||||
_ if link.original_source == OriginalSourceAvailability::Missing => {
|
||||
OriginalSourceAvailability::Missing
|
||||
}
|
||||
_ => OriginalSourceAvailability::Unknown,
|
||||
};
|
||||
Ok(())
|
||||
};
|
||||
match &mut response {
|
||||
MemoryJournalResponse::Links(page) => {
|
||||
for source in &mut page.sources {
|
||||
annotate(source)?;
|
||||
}
|
||||
}
|
||||
MemoryJournalResponse::Read(read) => annotate(&mut read.source)?,
|
||||
MemoryJournalResponse::Related(_) => {}
|
||||
}
|
||||
Ok(response)
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,151 @@
|
||||
//! Read-only, bounded Journal context at body startup and compaction boundaries.
|
||||
//! Selection, text projection, references and processing checkpoints share one storage
|
||||
//! transaction. Reads neither consult source history/Job liveness nor mutate recording.
|
||||
//! Startup prefers the Host-retained predecessor; compaction requires a live body writer
|
||||
//! and prefers its current Session, without waiting for Idle or recording completion.
|
||||
//! Both supplement only from the same Subject under the same independent budgets.
|
||||
//! This is derived reference material, never a new observation or an execution capability.
|
||||
|
||||
use super::*;
|
||||
use rusqlite::{Connection, OptionalExtension, params};
|
||||
|
||||
pub const STARTUP_MAX_BYTES: usize = 32 * 1024;
|
||||
const JOURNALS: usize = 3;
|
||||
const ENTRIES: usize = 3;
|
||||
const TEXT_BYTES: usize = 2048;
|
||||
|
||||
#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct JournalStartupSnapshot {
|
||||
pub subject_id: String,
|
||||
pub journals: Vec<StartupJournal>,
|
||||
pub omitted: bool,
|
||||
}
|
||||
#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct StartupJournal {
|
||||
pub journal_id: String,
|
||||
pub source_session_id: String,
|
||||
pub state_token: String,
|
||||
pub process_order: u64,
|
||||
pub process_byte: u64,
|
||||
pub current_position: String,
|
||||
pub entries: Vec<StartupEntry>,
|
||||
pub omitted: bool,
|
||||
}
|
||||
#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct StartupEntry {
|
||||
pub entry_id: String,
|
||||
pub position: u64,
|
||||
pub state: JournalEntryState,
|
||||
pub title: String,
|
||||
pub body: String,
|
||||
pub ongoing: String,
|
||||
pub source_end: Option<JournalSourcePointer>,
|
||||
pub correction_refs: Vec<String>,
|
||||
pub omitted: bool,
|
||||
}
|
||||
|
||||
// Read a bounded UTF-8 prefix at SQLite, not a full megabyte field followed by truncation.
|
||||
fn text(tx: &Connection, table: &str, id: &str, field: &str) -> JournalResult<(String, bool)> {
|
||||
let (mut bytes, length): (Vec<u8>, usize) = tx.query_row(
|
||||
&format!("SELECT COALESCE(substr(CAST({field} AS BLOB),1,?2),X''),length(CAST({field} AS BLOB)) FROM {table} WHERE id=?1"),
|
||||
params![id, TEXT_BYTES],
|
||||
|r| Ok((r.get(0)?, r.get(1)?)),
|
||||
)?;
|
||||
let length_read = bytes.len();
|
||||
match std::str::from_utf8(&bytes) {
|
||||
Ok(_) => {}
|
||||
Err(error) if error.error_len().is_none() => bytes.truncate(error.valid_up_to()),
|
||||
Err(_) => {
|
||||
return Err(JournalError::Conflict(
|
||||
"stored Journal text is not UTF-8".into(),
|
||||
));
|
||||
}
|
||||
}
|
||||
let omitted = bytes.len() < length || length_read < length;
|
||||
Ok((String::from_utf8(bytes).expect("validated UTF-8"), omitted))
|
||||
}
|
||||
|
||||
impl SubjektivStore {
|
||||
/// `previous_session` comes from the Host's retained predecessor binding, not model input.
|
||||
/// Recent Subject-local Journals supplement that predecessor under independent fixed budgets.
|
||||
pub fn journal_startup_snapshot(
|
||||
&self,
|
||||
host: &JournalHostContext,
|
||||
previous_session: Option<&str>,
|
||||
) -> JournalResult<JournalStartupSnapshot> {
|
||||
self.context_snapshot(host, previous_session, false)
|
||||
}
|
||||
|
||||
/// Read the saved current-Session Journal without reconciling or advancing it.
|
||||
/// The active writer check fences released body lifetimes, not non-Idle execution.
|
||||
pub fn journal_compaction_snapshot(
|
||||
&self,
|
||||
host: &JournalHostContext,
|
||||
) -> JournalResult<JournalStartupSnapshot> {
|
||||
let session = host.attribution.as_ref().ok_or_else(|| {
|
||||
JournalError::PermissionDenied("compaction requires a Host-bound body Session".into())
|
||||
})?;
|
||||
self.context_snapshot(host, Some(&session.session_id), true)
|
||||
}
|
||||
|
||||
fn context_snapshot(
|
||||
&self,
|
||||
host: &JournalHostContext,
|
||||
preferred_session: Option<&str>,
|
||||
require_current_writer: bool,
|
||||
) -> JournalResult<JournalStartupSnapshot> {
|
||||
self.database.try_transaction(|tx| {
|
||||
super::store::check_host(self, tx, host, require_current_writer)?;
|
||||
let mut ids = Vec::new();
|
||||
if let Some(session) = preferred_session {
|
||||
let previous: Option<(String, String)> = tx.query_row(
|
||||
"SELECT id,subject_id FROM journals WHERE source_session_id=?1",
|
||||
[session], |r| Ok((r.get(0)?, r.get(1)?)),
|
||||
).optional()?;
|
||||
if let Some((id, subject)) = previous {
|
||||
if subject != host.subject_id { return Err(JournalError::PermissionDenied("predecessor Journal belongs to another Subject".into())); }
|
||||
ids.push(id);
|
||||
}
|
||||
}
|
||||
let mut query = tx.prepare("SELECT id FROM journals WHERE subject_id=?1 ORDER BY updated_at DESC,id DESC LIMIT ?2")?;
|
||||
let recent = query.query_map(params![host.subject_id, JOURNALS + 1], |r| r.get::<_, String>(0))?;
|
||||
for id in recent { let id = id?; if !ids.contains(&id) { ids.push(id); } }
|
||||
let omitted = ids.len() > JOURNALS;
|
||||
ids.truncate(JOURNALS);
|
||||
let mut snapshot = JournalStartupSnapshot { subject_id: host.subject_id.clone(), journals: Vec::new(), omitted };
|
||||
for id in ids {
|
||||
let (session, token, order, byte) = tx.query_row(
|
||||
"SELECT source_session_id,state_token,process_order,process_byte FROM journals WHERE id=?1 AND subject_id=?2",
|
||||
params![id, host.subject_id], |r| Ok((r.get(0)?,r.get(1)?,r.get(2)?,r.get(3)?)),
|
||||
)?;
|
||||
let (current_position, mut omitted) = text(tx, "journals", &id, "current_position")?;
|
||||
let mut stmt = tx.prepare("SELECT id,position,state,source_end_json FROM journal_entries WHERE journal_id=?1 ORDER BY position DESC LIMIT ?2")?;
|
||||
let rows = stmt.query_map(params![id, ENTRIES + 1], |r| Ok((r.get::<_,String>(0)?,r.get::<_,u64>(1)?,r.get::<_,String>(2)?,r.get::<_,Option<String>>(3)?)))?.collect::<Result<Vec<_>,_>>()?;
|
||||
omitted |= rows.len() > ENTRIES;
|
||||
let mut entries = Vec::new();
|
||||
for (entry_id, position, state, source_end) in rows.into_iter().take(ENTRIES) {
|
||||
let (title, title_cut) = text(tx, "journal_entries", &entry_id, "title")?;
|
||||
let (body, body_cut) = text(tx, "journal_entries", &entry_id, "body")?;
|
||||
let (ongoing, ongoing_cut) = text(tx, "journal_entries", &entry_id, "ongoing")?;
|
||||
let mut refs = tx.prepare("SELECT target_id FROM journal_corrections WHERE entry_id=?1 ORDER BY target_id LIMIT 17")?;
|
||||
let mut correction_refs = refs.query_map([&entry_id], |r| r.get::<_,String>(0))?.collect::<Result<Vec<_>,_>>()?;
|
||||
let omitted = title_cut || body_cut || ongoing_cut || correction_refs.len() > 16;
|
||||
correction_refs.truncate(16);
|
||||
entries.push(StartupEntry { entry_id, position, state: match state.as_str() { "open" => JournalEntryState::Open, "fixed" => JournalEntryState::Fixed, _ => return Err(JournalError::Conflict("invalid stored Journal entry state".into())) }, title, body, ongoing, source_end: source_end.map(|s| serde_json::from_str(&s)).transpose()?, correction_refs, omitted });
|
||||
}
|
||||
snapshot.journals.push(StartupJournal { journal_id: id, source_session_id: session, state_token: token, process_order: order, process_byte: byte, current_position, entries, omitted });
|
||||
}
|
||||
// JSON escaping also consumes the independent output budget. Drop least-priority
|
||||
// entries/Journals rather than returning an over-budget or silently partial document.
|
||||
while serde_json::to_vec(&snapshot)?.len() > STARTUP_MAX_BYTES {
|
||||
snapshot.omitted = true;
|
||||
let journal = snapshot.journals.last_mut().ok_or_else(|| JournalError::InvalidInput("startup metadata exceeds budget".into()))?;
|
||||
if journal.entries.pop().is_some() { journal.omitted = true; } else { snapshot.journals.pop(); }
|
||||
}
|
||||
Ok(snapshot)
|
||||
})
|
||||
}
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,135 @@
|
||||
//! Bounded, Host-bound Journal recording and sequential Job transport.
|
||||
//!
|
||||
//! Subject, Journal and generation authority never come from these model inputs.
|
||||
//! Hosts validate live execution and public source bytes before selection; reading a
|
||||
//! preview must not select the enclosing entry. Operation retries retain the entire
|
||||
//! JournalOperation, including its original expected_state and covered_ranges.
|
||||
|
||||
use serde::{Deserialize, Serialize};
|
||||
|
||||
use super::{
|
||||
JournalEntrySummary, JournalMetadata, JournalOperation, JournalOperationStatus, JournalPage,
|
||||
JournalReceipt, JournalSourcePointer, JournalSourceRange, JournalTextPage,
|
||||
};
|
||||
|
||||
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(rename_all = "snake_case")]
|
||||
pub enum JournalRecordingReason {
|
||||
RunCommitted,
|
||||
TaskCompleted,
|
||||
BeforeCompact,
|
||||
WorkerRestored,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct JournalCompactionRequest {
|
||||
pub session_id: String,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct JournalRecordingRequest {
|
||||
pub reason: JournalRecordingReason,
|
||||
}
|
||||
|
||||
/// Admission is durable Host evidence, not proof that generation finished.
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(tag = "status", rename_all = "snake_case", deny_unknown_fields)]
|
||||
pub enum JournalRecordingResponse {
|
||||
NoNewSources,
|
||||
Accepted,
|
||||
}
|
||||
|
||||
/// No unbounded initial/current body or position is included in model state.
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
|
||||
pub struct JournalJobState {
|
||||
pub generation_id: String,
|
||||
pub initial_journal: JournalMetadata,
|
||||
pub initial_open: Option<JournalEntrySummary>,
|
||||
pub current_journal: JournalMetadata,
|
||||
pub current_open: Option<JournalEntrySummary>,
|
||||
pub previous_fixed_end: Option<JournalSourcePointer>,
|
||||
/// Frozen permission to fetch this prefix, not evidence of delivery or reflection.
|
||||
/// The sequential service gates mutations on its durable Source-read delivery ledger.
|
||||
pub selected_ranges: Vec<JournalSourceRange>,
|
||||
}
|
||||
|
||||
/// Host-verified saved progress only; not an aggregate record submission.
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
|
||||
pub struct JournalJobCompletion {
|
||||
pub generation_id: String,
|
||||
pub state_token: String,
|
||||
pub process_order: u64,
|
||||
pub process_byte: u64,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(rename_all = "snake_case")]
|
||||
pub enum JournalSnapshot {
|
||||
Initial,
|
||||
Current,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(tag = "target", rename_all = "snake_case", deny_unknown_fields)]
|
||||
pub enum JournalTextTarget {
|
||||
Position {
|
||||
snapshot: JournalSnapshot,
|
||||
},
|
||||
OpenBody {
|
||||
snapshot: JournalSnapshot,
|
||||
},
|
||||
OpenOngoing {
|
||||
snapshot: JournalSnapshot,
|
||||
},
|
||||
/// The Host restricts this pointer to this Job's frozen public source input.
|
||||
Source {
|
||||
pointer: JournalSourcePointer,
|
||||
},
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct JournalTextRead {
|
||||
pub target: JournalTextTarget,
|
||||
pub offset: usize,
|
||||
pub limit: usize,
|
||||
/// Required continuation condition; None only for the first chunk.
|
||||
pub content_token: Option<String>,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(tag = "kind", rename_all = "snake_case", deny_unknown_fields)]
|
||||
pub enum JournalJobRequest {
|
||||
Execute {
|
||||
operation: JournalOperation,
|
||||
},
|
||||
ReadState,
|
||||
QueryOperation {
|
||||
request_id: String,
|
||||
},
|
||||
ReadOperationCoverage {
|
||||
request_id: String,
|
||||
offset: usize,
|
||||
limit: usize,
|
||||
},
|
||||
ListOperations {
|
||||
after: Option<String>,
|
||||
limit: usize,
|
||||
},
|
||||
ReadText {
|
||||
read: JournalTextRead,
|
||||
},
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(tag = "result", content = "value", rename_all = "snake_case")]
|
||||
pub enum JournalJobResponse {
|
||||
Saved(JournalReceipt),
|
||||
State(JournalJobState),
|
||||
Operation(Option<JournalOperationStatus>),
|
||||
Coverage(JournalPage<JournalSourceRange>),
|
||||
Operations(JournalPage<JournalOperationStatus>),
|
||||
Text(JournalTextPage),
|
||||
}
|
||||
@@ -929,7 +929,7 @@ mod tests {
|
||||
let (_manager, _workspace, store) = open_store(&root, "workspace-a");
|
||||
let migrated_subject = store.subject(&subject_id).unwrap().unwrap();
|
||||
assert!(migrated_subject.behavior_md.is_empty());
|
||||
assert!(migrated_subject.behavior_md.is_empty());
|
||||
assert!(store.subject_permissions(&subject_id).unwrap().is_none());
|
||||
let lifecycle_attribution = attribution(
|
||||
&subject_id,
|
||||
"runtime-1",
|
||||
@@ -953,6 +953,32 @@ mod tests {
|
||||
store.session_attribution("session-1").unwrap().unwrap(),
|
||||
stored_attribution
|
||||
);
|
||||
let binding = store
|
||||
.claim_journal_writer(&subject_id, "runtime-1", "worker-1")
|
||||
.unwrap();
|
||||
let host = store
|
||||
.bind_journal_session(&binding, stored_attribution.clone())
|
||||
.unwrap();
|
||||
let range = crate::journal::JournalSourceRange {
|
||||
source: crate::journal::JournalSource {
|
||||
session_id: stored_attribution.session_id.clone(),
|
||||
pointer: crate::journal::JournalSourcePointer {
|
||||
segment_id: Uuid::now_v7(),
|
||||
entry_ref: "Eafter-v1-migration".into(),
|
||||
},
|
||||
order: 0,
|
||||
content_sha256: "ab".repeat(32),
|
||||
total_bytes: 8,
|
||||
},
|
||||
bytes: crate::journal::JournalByteRange { start: 0, end: 8 },
|
||||
};
|
||||
let journal_id = store
|
||||
.accept_journal_sources(&host, "After oldest supported migration", &[range])
|
||||
.unwrap();
|
||||
assert_eq!(
|
||||
store.read_journal(&host, &journal_id).unwrap().subject_id,
|
||||
subject_id
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
|
||||
@@ -2,7 +2,9 @@
|
||||
|
||||
pub mod api;
|
||||
pub mod job;
|
||||
pub mod journal;
|
||||
mod legacy_migrations;
|
||||
pub mod permissions;
|
||||
mod schema;
|
||||
use legacy_migrations::{
|
||||
add_candidate_decision_receipts, add_subject_behavior, add_subject_session_attribution,
|
||||
@@ -81,6 +83,16 @@ pub enum SubjektivError {
|
||||
},
|
||||
#[error("subject `{subject_id}` behavior content changed")]
|
||||
SubjectBehaviorConflict { subject_id: String },
|
||||
#[error("subject `{0}` permission source changed")]
|
||||
SubjectPermissionsConflict(String),
|
||||
#[error("permission operation `{0}` was reused with different input")]
|
||||
PermissionOperationConflict(String),
|
||||
#[error("authorization denied: {0}")]
|
||||
AuthorizationDenied(String),
|
||||
#[error("Worker execution grant binding conflicts for `{0}`")]
|
||||
WorkerExecutionGrantConflict(String),
|
||||
#[error("Subject `{subject_id}` has more than {limit} retained Worker execution grants")]
|
||||
WorkerExecutionGrantListOverflow { subject_id: String, limit: usize },
|
||||
#[error("surface generation conflict: {0}")]
|
||||
SurfaceGenerationConflict(String),
|
||||
#[error("memory `{memory_id}` cannot transition from {from:?} to {to:?}")]
|
||||
@@ -602,6 +614,31 @@ static MIGRATIONS: &[FeatureMigration] = &[
|
||||
"replace counters with immutable changes and content conditions",
|
||||
schema::migrate,
|
||||
),
|
||||
FeatureMigration::new(
|
||||
8,
|
||||
"add durable journal operations and processing ranges",
|
||||
journal::migrate,
|
||||
),
|
||||
FeatureMigration::new(
|
||||
9,
|
||||
"fence erased journal Sessions and permit explicit content erasure",
|
||||
journal::migrate_lifecycle,
|
||||
),
|
||||
FeatureMigration::new(
|
||||
10,
|
||||
"fence journal writers by explicit body binding lifetime",
|
||||
journal::migrate_binding,
|
||||
),
|
||||
FeatureMigration::new(
|
||||
11,
|
||||
"add immutable candidate Journal context links",
|
||||
journal::memory_links::migrate,
|
||||
),
|
||||
FeatureMigration::new(
|
||||
12,
|
||||
"add explicit Subject permission sources and immutable child execution grants",
|
||||
permissions::migrate,
|
||||
),
|
||||
];
|
||||
|
||||
pub const REGISTRATION: FeatureRegistration =
|
||||
|
||||
@@ -0,0 +1,288 @@
|
||||
//! Host-administered permission sources and immutable child grants, separate from behavior.
|
||||
//!
|
||||
//! The Host authenticates administrators before source writes and binds verified Worker/Profile
|
||||
//! identities before grant writes. These records are not a Worker registry. The Host alone
|
||||
//! authenticates root execution ownership against its canonical Backend singleton and checks
|
||||
//! every live lineage edge; Journal bindings and retained grants cannot establish ownership.
|
||||
//! Replays return historical evidence without restoring a source or granting current authority.
|
||||
use super::*;
|
||||
use server_api::authorization::{
|
||||
PermissionResource, ScopedPermission, SubjectPermissions, SubjectPermissionsUpdate,
|
||||
WorkerExecutionGrant, validate_authorization_identifier, validate_scoped_permissions,
|
||||
};
|
||||
use sha2::{Digest, Sha256};
|
||||
|
||||
pub const MAX_SUBJECT_WORKER_EXECUTION_GRANTS: usize = 1_000;
|
||||
|
||||
pub(super) fn migrate(tx: &Transaction<'_>) -> feature_storage::Result<()> {
|
||||
tx.execute_batch(include_str!("permissions.sql"))?;
|
||||
Ok(())
|
||||
}
|
||||
|
||||
impl SubjektivStore {
|
||||
/// Unset sources are `None` (deny), including migrated Subjects. This is an admin read,
|
||||
/// not an effective-authorization decision; retired Subjects retain their source evidence.
|
||||
pub fn subject_permissions(&self, subject_id: &str) -> Result<Option<SubjectPermissions>> {
|
||||
self.database.try_with_connection(|connection| {
|
||||
require_subject_in_connection(connection, subject_id)?;
|
||||
source_in_connection(connection, subject_id)
|
||||
})
|
||||
}
|
||||
|
||||
/// Host-admin-only replacement. Every replacement issues a fresh change ID, including
|
||||
/// identical contents. Revocation is an explicit empty replacement. A scope-wide operation
|
||||
/// ID binds Subject, CAS input, and both permission vectors; result and receipt commit together.
|
||||
pub fn set_subject_permissions(
|
||||
&self,
|
||||
subject_id: &str,
|
||||
update: &SubjectPermissionsUpdate,
|
||||
) -> Result<SubjectPermissions> {
|
||||
validate_authorization_identifier(subject_id).map_err(SubjektivError::InvalidRecord)?;
|
||||
validate_authorization_identifier(&update.operation_id)
|
||||
.map_err(SubjektivError::InvalidRecord)?;
|
||||
if let Some(change) = &update.expected_change_id {
|
||||
validate_authorization_identifier(change).map_err(SubjektivError::InvalidRecord)?;
|
||||
}
|
||||
validate_scope(self.scope_id(), &update.execution)?;
|
||||
validate_scope(self.scope_id(), &update.delegation)?;
|
||||
let fingerprint: String = Sha256::digest(serde_json::to_vec(&(subject_id, update))?)
|
||||
.iter()
|
||||
.map(|byte| format!("{byte:02x}"))
|
||||
.collect();
|
||||
self.database.try_transaction(|tx| {
|
||||
require_subject(tx, subject_id)?;
|
||||
let receipt: Option<(String, String)> = tx.query_row(
|
||||
"SELECT request_fingerprint, change_id FROM subject_permission_receipts WHERE operation_id=?1",
|
||||
[&update.operation_id], |row| Ok((row.get(0)?, row.get(1)?)),
|
||||
).optional()?;
|
||||
if let Some((saved, change_id)) = receipt {
|
||||
if saved != fingerprint {
|
||||
return Err(SubjektivError::PermissionOperationConflict(update.operation_id.clone()));
|
||||
}
|
||||
let raw: String = tx.query_row(
|
||||
"SELECT record_json FROM subject_permission_changes WHERE subject_id=?1 AND change_id=?2",
|
||||
params![subject_id, change_id], |row| row.get(0),
|
||||
)?;
|
||||
return Ok(serde_json::from_str(&raw)?);
|
||||
}
|
||||
require_active_subject(tx, subject_id)?;
|
||||
let current = source_in_connection(tx, subject_id)?;
|
||||
if current.as_ref().map(|source| &source.change_id) != update.expected_change_id.as_ref() {
|
||||
return Err(SubjektivError::SubjectPermissionsConflict(subject_id.into()));
|
||||
}
|
||||
let source = SubjectPermissions {
|
||||
change_id: issued_id("permissions"),
|
||||
execution: update.execution.clone(),
|
||||
delegation: update.delegation.clone(),
|
||||
};
|
||||
tx.execute("INSERT INTO subject_permission_changes(subject_id,change_id,record_json) VALUES(?1,?2,?3)",
|
||||
params![subject_id, source.change_id, serde_json::to_string(&source)?])?;
|
||||
tx.execute("INSERT INTO subject_permissions(subject_id,change_id) VALUES(?1,?2) ON CONFLICT(subject_id) DO UPDATE SET change_id=excluded.change_id",
|
||||
params![subject_id, source.change_id])?;
|
||||
tx.execute("INSERT INTO subject_permission_receipts(operation_id,subject_id,request_fingerprint,change_id) VALUES(?1,?2,?3,?4)",
|
||||
params![update.operation_id, subject_id, fingerprint, source.change_id])?;
|
||||
Ok(source)
|
||||
})
|
||||
}
|
||||
|
||||
/// Binds child grants only. Exact retries recover an immutable binding even after revocation;
|
||||
/// that success is not authorization to execute or redelegate. New bindings require the
|
||||
/// current source, an active Subject and explicit delegation containment. The Host must
|
||||
/// authenticate root singleton ownership and every live lineage edge before calling;
|
||||
/// a missing retained parent is not ownership evidence. Profile resolution, provider scope,
|
||||
/// Worker creation and caller authentication also remain Host duties.
|
||||
pub fn bind_worker_execution_grant(&self, grant: &WorkerExecutionGrant) -> Result<()> {
|
||||
validate_grant(self.scope_id(), grant)?;
|
||||
self.database.try_transaction(|tx| {
|
||||
if let Some(existing) = grant_in_connection(tx, &grant.runtime_id, &grant.worker_id)? {
|
||||
return if existing == *grant { Ok(()) } else {
|
||||
Err(SubjektivError::WorkerExecutionGrantConflict(format!("{}/{}", grant.runtime_id, grant.worker_id)))
|
||||
};
|
||||
}
|
||||
require_active_subject(tx, &grant.subject_id)?;
|
||||
let source = source_in_connection(tx, &grant.subject_id)?
|
||||
.ok_or_else(|| denied("Subject permissions are unset"))?;
|
||||
if source.change_id != grant.source_change_id {
|
||||
return Err(denied("Subject permission source is no longer current"));
|
||||
}
|
||||
require_covered(&source.delegation, &grant.permissions)?;
|
||||
require_covered(&source.delegation, &grant.redelegation)?;
|
||||
// A child grant cannot turn a body (including a released historical body) into a
|
||||
// delegated child or attach a Worker historically attributed to a different Subject.
|
||||
let invalid_target: bool = tx.query_row(
|
||||
"SELECT EXISTS(SELECT 1 FROM journal_writer_bindings WHERE runtime_id=?1 AND worker_id=?2) OR EXISTS(SELECT 1 FROM subject_session_attributions WHERE runtime_id=?1 AND worker_id=?2 AND subject_id<>?3)",
|
||||
params![grant.runtime_id, grant.worker_id, grant.subject_id], |row| row.get(0),
|
||||
)?;
|
||||
if invalid_target { return Err(denied("target is a body or belongs to another Subject")); }
|
||||
let origin = require_retained_origin(tx, grant)?;
|
||||
if let Some(origin) = origin {
|
||||
require_covered(&origin.redelegation, &grant.permissions)?;
|
||||
require_covered(&origin.redelegation, &grant.redelegation)?;
|
||||
}
|
||||
tx.execute("INSERT INTO worker_execution_grants(runtime_id,worker_id,subject_id,source_change_id,record_json) VALUES(?1,?2,?3,?4,?5)",
|
||||
params![grant.runtime_id, grant.worker_id, grant.subject_id, grant.source_change_id, serde_json::to_string(grant)?])?;
|
||||
Ok(())
|
||||
})
|
||||
}
|
||||
|
||||
/// Returns this Subject's retained grants, including stale grants needed for cancellation
|
||||
/// and reporting. Never an ownership list or effective-authorization decision. Overflow is
|
||||
/// explicit rather than silently omitting Workers from a cancellation/reporting pass.
|
||||
pub fn list_subject_worker_execution_grants(
|
||||
&self,
|
||||
subject_id: &str,
|
||||
) -> Result<Vec<WorkerExecutionGrant>> {
|
||||
validate_authorization_identifier(subject_id).map_err(SubjektivError::InvalidRecord)?;
|
||||
self.database.try_with_connection(|connection| {
|
||||
require_subject_in_connection(connection, subject_id)?;
|
||||
let mut statement = connection.prepare(
|
||||
"SELECT record_json FROM worker_execution_grants WHERE subject_id=?1 ORDER BY runtime_id,worker_id LIMIT ?2",
|
||||
)?;
|
||||
let mut rows = statement.query(params![subject_id, MAX_SUBJECT_WORKER_EXECUTION_GRANTS + 1])?;
|
||||
let mut grants = Vec::new();
|
||||
while let Some(row) = rows.next()? {
|
||||
if grants.len() == MAX_SUBJECT_WORKER_EXECUTION_GRANTS {
|
||||
return Err(SubjektivError::WorkerExecutionGrantListOverflow {
|
||||
subject_id: subject_id.into(),
|
||||
limit: MAX_SUBJECT_WORKER_EXECUTION_GRANTS,
|
||||
});
|
||||
}
|
||||
grants.push(serde_json::from_str(&row.get::<_, String>(0)?)?);
|
||||
}
|
||||
Ok(grants)
|
||||
})
|
||||
}
|
||||
|
||||
/// Returns retained binding evidence, not current authorization. The Host must compare the
|
||||
/// active Subject, source change, current origin ownership, Profile and provider constraints.
|
||||
pub fn worker_execution_grant(
|
||||
&self,
|
||||
runtime: &str,
|
||||
worker: &str,
|
||||
) -> Result<Option<WorkerExecutionGrant>> {
|
||||
validate_authorization_identifier(runtime).map_err(SubjektivError::InvalidRecord)?;
|
||||
validate_authorization_identifier(worker).map_err(SubjektivError::InvalidRecord)?;
|
||||
self.database
|
||||
.try_with_connection(|connection| grant_in_connection(connection, runtime, worker))
|
||||
}
|
||||
}
|
||||
|
||||
fn source_in_connection(
|
||||
connection: &Connection,
|
||||
subject: &str,
|
||||
) -> Result<Option<SubjectPermissions>> {
|
||||
let raw: Option<String> = connection.query_row(
|
||||
"SELECT c.record_json FROM subject_permissions p JOIN subject_permission_changes c ON c.subject_id=p.subject_id AND c.change_id=p.change_id WHERE p.subject_id=?1",
|
||||
[subject], |row| row.get(0),
|
||||
).optional()?;
|
||||
raw.map(|raw| serde_json::from_str(&raw).map_err(Into::into))
|
||||
.transpose()
|
||||
}
|
||||
|
||||
fn grant_in_connection(
|
||||
connection: &Connection,
|
||||
runtime: &str,
|
||||
worker: &str,
|
||||
) -> Result<Option<WorkerExecutionGrant>> {
|
||||
let raw: Option<String> = connection
|
||||
.query_row(
|
||||
"SELECT record_json FROM worker_execution_grants WHERE runtime_id=?1 AND worker_id=?2",
|
||||
params![runtime, worker],
|
||||
|row| row.get(0),
|
||||
)
|
||||
.optional()?;
|
||||
raw.map(|raw| serde_json::from_str(&raw).map_err(Into::into))
|
||||
.transpose()
|
||||
}
|
||||
|
||||
fn validate_scope(scope: &str, permissions: &[ScopedPermission]) -> Result<()> {
|
||||
validate_scoped_permissions(permissions).map_err(SubjektivError::InvalidRecord)?;
|
||||
for permission in permissions {
|
||||
if let PermissionResource::Workspace { workspace_id } = &permission.resource
|
||||
&& workspace_id != scope
|
||||
{
|
||||
return Err(denied("Workspace permission is outside this store scope"));
|
||||
}
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
fn validate_grant(scope: &str, grant: &WorkerExecutionGrant) -> Result<()> {
|
||||
for value in [
|
||||
&grant.subject_id,
|
||||
&grant.origin_runtime_id,
|
||||
&grant.origin_worker_id,
|
||||
&grant.source_change_id,
|
||||
&grant.runtime_id,
|
||||
&grant.worker_id,
|
||||
&grant.profile,
|
||||
&grant.profile_digest,
|
||||
] {
|
||||
validate_authorization_identifier(value).map_err(SubjektivError::InvalidRecord)?;
|
||||
}
|
||||
if grant.origin_runtime_id == grant.runtime_id && grant.origin_worker_id == grant.worker_id {
|
||||
return Err(denied("a child grant cannot originate from itself"));
|
||||
}
|
||||
validate_scope(scope, &grant.permissions)?;
|
||||
validate_scope(scope, &grant.redelegation)
|
||||
}
|
||||
|
||||
fn require_covered(ceiling: &[ScopedPermission], requested: &[ScopedPermission]) -> Result<()> {
|
||||
if requested
|
||||
.iter()
|
||||
.all(|permission| ceiling.iter().any(|allowed| allowed.covers(permission)))
|
||||
{
|
||||
Ok(())
|
||||
} else {
|
||||
Err(denied(
|
||||
"requested permission or redelegation exceeds its explicit ceiling",
|
||||
))
|
||||
}
|
||||
}
|
||||
|
||||
fn require_retained_origin(
|
||||
tx: &Transaction<'_>,
|
||||
grant: &WorkerExecutionGrant,
|
||||
) -> Result<Option<WorkerExecutionGrant>> {
|
||||
let mut runtime = grant.origin_runtime_id.clone();
|
||||
let mut worker = grant.origin_worker_id.clone();
|
||||
let mut direct_origin = None;
|
||||
let mut visited = HashSet::from([(grant.runtime_id.clone(), grant.worker_id.clone())]);
|
||||
// Validate retained lineage only. Absence terminates at a Host-authenticated root;
|
||||
// neither Journal active state nor absence of a grant proves current singleton ownership.
|
||||
for _ in 0..64 {
|
||||
if !visited.insert((runtime.clone(), worker.clone())) {
|
||||
return Err(denied("cyclic grant origin"));
|
||||
}
|
||||
let foreign_attribution: bool = tx.query_row(
|
||||
"SELECT EXISTS(SELECT 1 FROM journal_writer_bindings WHERE runtime_id=?1 AND worker_id=?2 AND subject_id<>?3) OR EXISTS(SELECT 1 FROM subject_session_attributions WHERE runtime_id=?1 AND worker_id=?2 AND subject_id<>?3)",
|
||||
params![runtime, worker, grant.subject_id], |row| row.get(0),
|
||||
)?;
|
||||
if foreign_attribution {
|
||||
return Err(denied("grant origin is attributed to another Subject"));
|
||||
}
|
||||
let Some(origin) = grant_in_connection(tx, &runtime, &worker)? else {
|
||||
return Ok(direct_origin);
|
||||
};
|
||||
if origin.subject_id != grant.subject_id
|
||||
|| origin.source_change_id != grant.source_change_id
|
||||
{
|
||||
return Err(denied(
|
||||
"grant origin belongs to another Subject or permission source",
|
||||
));
|
||||
}
|
||||
if direct_origin.is_none() {
|
||||
direct_origin = Some(origin.clone());
|
||||
}
|
||||
runtime = origin.origin_runtime_id;
|
||||
worker = origin.origin_worker_id;
|
||||
}
|
||||
Err(denied("grant origin exceeds maximum delegation depth"))
|
||||
}
|
||||
|
||||
fn denied(reason: &str) -> SubjektivError {
|
||||
SubjektivError::AuthorizationDenied(reason.into())
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests;
|
||||
@@ -0,0 +1,45 @@
|
||||
CREATE TABLE subject_permission_changes (
|
||||
subject_id TEXT NOT NULL REFERENCES subjects(subject_id) ON DELETE RESTRICT,
|
||||
change_id TEXT NOT NULL CHECK (length(change_id) > 0),
|
||||
record_json TEXT NOT NULL,
|
||||
PRIMARY KEY (subject_id, change_id)
|
||||
);
|
||||
CREATE TABLE subject_permissions (
|
||||
subject_id TEXT PRIMARY KEY REFERENCES subjects(subject_id) ON DELETE RESTRICT,
|
||||
change_id TEXT NOT NULL,
|
||||
FOREIGN KEY (subject_id, change_id) REFERENCES subject_permission_changes(subject_id, change_id) ON DELETE RESTRICT
|
||||
);
|
||||
CREATE TABLE subject_permission_receipts (
|
||||
operation_id TEXT PRIMARY KEY CHECK (length(operation_id) > 0),
|
||||
subject_id TEXT NOT NULL,
|
||||
request_fingerprint TEXT NOT NULL,
|
||||
change_id TEXT NOT NULL,
|
||||
FOREIGN KEY (subject_id, change_id) REFERENCES subject_permission_changes(subject_id, change_id) ON DELETE RESTRICT
|
||||
);
|
||||
CREATE TABLE worker_execution_grants (
|
||||
runtime_id TEXT NOT NULL,
|
||||
worker_id TEXT NOT NULL,
|
||||
subject_id TEXT NOT NULL,
|
||||
source_change_id TEXT NOT NULL,
|
||||
record_json TEXT NOT NULL,
|
||||
PRIMARY KEY (runtime_id, worker_id),
|
||||
FOREIGN KEY (subject_id, source_change_id) REFERENCES subject_permission_changes(subject_id, change_id) ON DELETE RESTRICT
|
||||
);
|
||||
CREATE TRIGGER subject_permission_changes_no_update BEFORE UPDATE ON subject_permission_changes BEGIN
|
||||
SELECT RAISE(ABORT, 'Subject permission changes are immutable');
|
||||
END;
|
||||
CREATE TRIGGER subject_permission_changes_no_delete BEFORE DELETE ON subject_permission_changes BEGIN
|
||||
SELECT RAISE(ABORT, 'Subject permission changes are retained');
|
||||
END;
|
||||
CREATE TRIGGER subject_permission_receipts_no_update BEFORE UPDATE ON subject_permission_receipts BEGIN
|
||||
SELECT RAISE(ABORT, 'Subject permission receipts are immutable');
|
||||
END;
|
||||
CREATE TRIGGER subject_permission_receipts_no_delete BEFORE DELETE ON subject_permission_receipts BEGIN
|
||||
SELECT RAISE(ABORT, 'Subject permission receipts are retained');
|
||||
END;
|
||||
CREATE TRIGGER worker_execution_grants_no_update BEFORE UPDATE ON worker_execution_grants BEGIN
|
||||
SELECT RAISE(ABORT, 'Worker execution grants are immutable');
|
||||
END;
|
||||
CREATE TRIGGER worker_execution_grants_no_delete BEFORE DELETE ON worker_execution_grants BEGIN
|
||||
SELECT RAISE(ABORT, 'Worker execution grants are retained');
|
||||
END;
|
||||
@@ -0,0 +1,656 @@
|
||||
//! Real SQLite component tests through store APIs; Host authentication, canonical singleton
|
||||
//! ownership and live lineage checks are outside this suite. Root origins are Host-attested inputs;
|
||||
//! Journal fixtures exercise defensive attribution only, never execution authority.
|
||||
use super::*;
|
||||
use crate::tests::{open_store, role};
|
||||
use feature_storage::FeatureStorage;
|
||||
use std::path::Path;
|
||||
|
||||
fn permission(operation: &str, path: &str, recursive: bool) -> ScopedPermission {
|
||||
ScopedPermission {
|
||||
operation: operation.into(),
|
||||
resource: PermissionResource::Workdir {
|
||||
working_directory_id: "wd".into(),
|
||||
path: path.into(),
|
||||
recursive,
|
||||
},
|
||||
}
|
||||
}
|
||||
|
||||
fn update(
|
||||
operation: &str,
|
||||
expected: Option<&str>,
|
||||
delegation: Vec<ScopedPermission>,
|
||||
) -> SubjectPermissionsUpdate {
|
||||
SubjectPermissionsUpdate {
|
||||
operation_id: operation.into(),
|
||||
expected_change_id: expected.map(Into::into),
|
||||
execution: Vec::new(),
|
||||
delegation,
|
||||
}
|
||||
}
|
||||
|
||||
fn grant(subject: &str, source: &str, worker: &str) -> WorkerExecutionGrant {
|
||||
WorkerExecutionGrant {
|
||||
subject_id: subject.into(),
|
||||
origin_runtime_id: "runtime".into(),
|
||||
origin_worker_id: "body".into(),
|
||||
source_change_id: source.into(),
|
||||
runtime_id: "runtime".into(),
|
||||
worker_id: worker.into(),
|
||||
profile: "builtin:coder".into(),
|
||||
profile_digest: "resolved-profile-sha256".into(),
|
||||
permissions: vec![permission("file.read", "src", false)],
|
||||
redelegation: Vec::new(),
|
||||
}
|
||||
}
|
||||
|
||||
fn schema(store: &SubjektivStore) -> Vec<(String, String)> {
|
||||
store.database.try_with_connection::<_, SubjektivError>(|connection| {
|
||||
let mut statement = connection.prepare("SELECT name,sql FROM sqlite_master WHERE name NOT LIKE 'sqlite_%' AND sql IS NOT NULL ORDER BY name")?;
|
||||
Ok(statement.query_map([], |row| Ok((row.get(0)?, row.get(1)?)))?.collect::<std::result::Result<_, _>>()?)
|
||||
}).unwrap()
|
||||
}
|
||||
|
||||
fn open_version(
|
||||
root: &Path,
|
||||
version: usize,
|
||||
) -> (FeatureStorage, ScopedFeatureStorage, SubjektivStore) {
|
||||
let manager = FeatureStorage::new(root);
|
||||
let scope = manager.scope("workspace-a").unwrap();
|
||||
let registration = scope
|
||||
.register(FeatureRegistration::new(
|
||||
SUBJEKTIV_FEATURE_ID,
|
||||
&MIGRATIONS[..version],
|
||||
))
|
||||
.unwrap();
|
||||
let store = SubjektivStore::open(&scope, ®istration).unwrap();
|
||||
(manager, scope, store)
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn replacements_are_cas_fenced_replayable_and_never_restore_old_permissions() {
|
||||
let temp = tempfile::tempdir().unwrap();
|
||||
let subject;
|
||||
let first;
|
||||
let first_update = update("allow", None, vec![permission("file.read", ".", true)]);
|
||||
{
|
||||
let (_manager, _scope, store) = open_store(temp.path(), "workspace-a");
|
||||
subject = store.create_subject(role()).unwrap().id;
|
||||
assert!(store.subject_permissions(&subject).unwrap().is_none());
|
||||
first = store
|
||||
.set_subject_permissions(&subject, &first_update)
|
||||
.unwrap();
|
||||
assert_eq!(
|
||||
store
|
||||
.set_subject_permissions(&subject, &first_update)
|
||||
.unwrap(),
|
||||
first
|
||||
);
|
||||
assert!(matches!(
|
||||
store.set_subject_permissions(&subject, &update("stale", None, Vec::new())),
|
||||
Err(SubjektivError::SubjectPermissionsConflict(_))
|
||||
));
|
||||
assert!(matches!(
|
||||
store.set_subject_permissions(&subject, &update("allow", None, Vec::new())),
|
||||
Err(SubjektivError::PermissionOperationConflict(_))
|
||||
));
|
||||
let other = store.create_subject(role()).unwrap();
|
||||
assert!(matches!(
|
||||
store.set_subject_permissions(&other.id, &first_update),
|
||||
Err(SubjektivError::PermissionOperationConflict(_))
|
||||
));
|
||||
let same = store
|
||||
.set_subject_permissions(
|
||||
&subject,
|
||||
&update("same", Some(&first.change_id), first.delegation.clone()),
|
||||
)
|
||||
.unwrap();
|
||||
assert_ne!(same.change_id, first.change_id);
|
||||
let revoked = store
|
||||
.set_subject_permissions(
|
||||
&subject,
|
||||
&update("revoke", Some(&same.change_id), Vec::new()),
|
||||
)
|
||||
.unwrap();
|
||||
assert!(revoked.delegation.is_empty());
|
||||
assert_eq!(
|
||||
store
|
||||
.set_subject_permissions(&subject, &first_update)
|
||||
.unwrap(),
|
||||
first
|
||||
);
|
||||
assert_eq!(store.subject_permissions(&subject).unwrap(), Some(revoked));
|
||||
}
|
||||
let (_reopened_manager, _reopened_scope, reopened) = open_store(temp.path(), "workspace-a");
|
||||
assert!(
|
||||
reopened
|
||||
.subject_permissions(&subject)
|
||||
.unwrap()
|
||||
.unwrap()
|
||||
.delegation
|
||||
.is_empty()
|
||||
);
|
||||
assert_eq!(
|
||||
reopened
|
||||
.set_subject_permissions(&subject, &first_update)
|
||||
.unwrap(),
|
||||
first
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn failed_receipt_insert_rolls_back_source_history_and_projection() {
|
||||
let temp = tempfile::tempdir().unwrap();
|
||||
let (_manager, _scope, store) = open_store(temp.path(), "workspace-a");
|
||||
let subject = store.create_subject(role()).unwrap().id;
|
||||
let first = store
|
||||
.set_subject_permissions(&subject, &update("first", None, Vec::new()))
|
||||
.unwrap();
|
||||
store.database.try_transaction::<_, SubjektivError>(|tx| {
|
||||
tx.execute_batch("CREATE TRIGGER fail_permission_receipt BEFORE INSERT ON subject_permission_receipts BEGIN SELECT RAISE(ABORT,'injected receipt failure'); END;")?;
|
||||
Ok(())
|
||||
}).unwrap();
|
||||
let replacement = update(
|
||||
"second",
|
||||
Some(&first.change_id),
|
||||
vec![permission("file.read", ".", true)],
|
||||
);
|
||||
assert!(
|
||||
store
|
||||
.set_subject_permissions(&subject, &replacement)
|
||||
.is_err()
|
||||
);
|
||||
assert_eq!(store.subject_permissions(&subject).unwrap(), Some(first));
|
||||
store.database.try_transaction::<_, SubjektivError>(|tx| {
|
||||
let counts: (u32, u32) = tx.query_row("SELECT (SELECT count(*) FROM subject_permission_changes),(SELECT count(*) FROM subject_permission_receipts)", [], |r| Ok((r.get(0)?, r.get(1)?)))?;
|
||||
assert_eq!(counts, (1, 1));
|
||||
tx.execute_batch("DROP TRIGGER fail_permission_receipt")?;
|
||||
Ok(())
|
||||
}).unwrap();
|
||||
assert!(
|
||||
store
|
||||
.set_subject_permissions(&subject, &replacement)
|
||||
.is_ok()
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn scope_and_validation_rejections_do_not_issue_permission_sources() {
|
||||
let temp = tempfile::tempdir().unwrap();
|
||||
let (_a_manager, _a_scope, a) = open_store(&temp.path().join("a"), "workspace-a");
|
||||
let (_b_manager, _b_scope, b) = open_store(&temp.path().join("b"), "workspace-b");
|
||||
let subject = a.create_subject(role()).unwrap().id;
|
||||
assert!(
|
||||
b.set_subject_permissions(&subject, &update("cross-subject", None, Vec::new()))
|
||||
.is_err()
|
||||
);
|
||||
let cross_workspace = ScopedPermission {
|
||||
operation: "ticket.create".into(),
|
||||
resource: PermissionResource::Workspace {
|
||||
workspace_id: "workspace-b".into(),
|
||||
},
|
||||
};
|
||||
assert!(
|
||||
a.set_subject_permissions(
|
||||
&subject,
|
||||
&update("cross-workspace", None, vec![cross_workspace])
|
||||
)
|
||||
.is_err()
|
||||
);
|
||||
for (operation, path) in [
|
||||
("file.*", "src"),
|
||||
("file..read", "src"),
|
||||
("file.read", "../src"),
|
||||
("file.read", "src/../escape"),
|
||||
] {
|
||||
assert!(
|
||||
a.set_subject_permissions(
|
||||
&subject,
|
||||
&update("invalid", None, vec![permission(operation, path, true)])
|
||||
)
|
||||
.is_err()
|
||||
);
|
||||
}
|
||||
assert!(a.subject_permissions(&subject).unwrap().is_none());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn child_grants_are_immutable_bounded_and_do_not_create_subject_ownership() {
|
||||
let temp = tempfile::tempdir().unwrap();
|
||||
let (_manager, _scope, store) = open_store(temp.path(), "workspace-a");
|
||||
let subject = store.create_subject(role()).unwrap().id;
|
||||
let source = store
|
||||
.set_subject_permissions(
|
||||
&subject,
|
||||
&update("allow", None, vec![permission("file.read", "src", true)]),
|
||||
)
|
||||
.unwrap();
|
||||
let child = grant(&subject, &source.change_id, "child");
|
||||
store.bind_worker_execution_grant(&child).unwrap();
|
||||
store.bind_worker_execution_grant(&child).unwrap();
|
||||
assert_eq!(
|
||||
store.worker_execution_grant("runtime", "child").unwrap(),
|
||||
Some(child.clone())
|
||||
);
|
||||
assert!(
|
||||
store
|
||||
.journal_body_is_unpublished(&subject, "runtime", "child")
|
||||
.unwrap()
|
||||
);
|
||||
let mut changed = child.clone();
|
||||
changed.profile_digest = "changed-profile".into();
|
||||
assert!(matches!(
|
||||
store.bind_worker_execution_grant(&changed),
|
||||
Err(SubjektivError::WorkerExecutionGrantConflict(_))
|
||||
));
|
||||
for (worker, requested) in [
|
||||
("write", permission("file.write", "src", false)),
|
||||
("escape", permission("file.read", ".", true)),
|
||||
("prefix", permission("file.read", "src-other", false)),
|
||||
] {
|
||||
let mut candidate = grant(&subject, &source.change_id, worker);
|
||||
candidate.permissions = vec![requested];
|
||||
assert!(store.bind_worker_execution_grant(&candidate).is_err());
|
||||
assert!(
|
||||
store
|
||||
.worker_execution_grant("runtime", worker)
|
||||
.unwrap()
|
||||
.is_none()
|
||||
);
|
||||
}
|
||||
let mut self_origin = child.clone();
|
||||
self_origin.worker_id = "body".into();
|
||||
assert!(store.bind_worker_execution_grant(&self_origin).is_err());
|
||||
let other = store.create_subject(role()).unwrap();
|
||||
store
|
||||
.claim_journal_writer(&other.id, "runtime", "other-body")
|
||||
.unwrap();
|
||||
let mut invalid = grant(&subject, &source.change_id, "other-body");
|
||||
assert!(store.bind_worker_execution_grant(&invalid).is_err());
|
||||
invalid.worker_id = "forged-child".into();
|
||||
invalid.origin_worker_id = "other-body".into();
|
||||
assert!(store.bind_worker_execution_grant(&invalid).is_err());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn redelegation_requires_current_source_and_explicit_retained_parent_ceiling() {
|
||||
let temp = tempfile::tempdir().unwrap();
|
||||
let (_manager, _scope, store) = open_store(temp.path(), "workspace-a");
|
||||
let subject = store.create_subject(role()).unwrap().id;
|
||||
let source = store
|
||||
.set_subject_permissions(
|
||||
&subject,
|
||||
&update("allow", None, vec![permission("file.read", ".", true)]),
|
||||
)
|
||||
.unwrap();
|
||||
let mut child = grant(&subject, &source.change_id, "child");
|
||||
child.redelegation = vec![permission("file.read", "src", true)];
|
||||
store.bind_worker_execution_grant(&child).unwrap();
|
||||
let mut descendant = grant(&subject, &source.change_id, "grandchild");
|
||||
descendant.origin_worker_id = "child".into();
|
||||
store.bind_worker_execution_grant(&descendant).unwrap();
|
||||
let mut excessive = descendant.clone();
|
||||
excessive.worker_id = "excessive".into();
|
||||
excessive.redelegation = vec![permission("file.read", ".", true)];
|
||||
assert!(store.bind_worker_execution_grant(&excessive).is_err());
|
||||
let mut nondelegator = descendant.clone();
|
||||
nondelegator.origin_worker_id = "grandchild".into();
|
||||
nondelegator.worker_id = "great-grandchild".into();
|
||||
assert!(store.bind_worker_execution_grant(&nondelegator).is_err());
|
||||
let mut stale = descendant.clone();
|
||||
stale.worker_id = "after-source-replacement".into();
|
||||
let revoked = store
|
||||
.set_subject_permissions(
|
||||
&subject,
|
||||
&update("revoke", Some(&source.change_id), Vec::new()),
|
||||
)
|
||||
.unwrap();
|
||||
assert_ne!(revoked.change_id, source.change_id);
|
||||
stale.origin_worker_id = "new-body".into();
|
||||
assert!(store.bind_worker_execution_grant(&stale).is_err());
|
||||
// Exact retries/readback recover evidence but cannot revive the source or origin.
|
||||
store.bind_worker_execution_grant(&child).unwrap();
|
||||
assert_eq!(
|
||||
store.worker_execution_grant("runtime", "child").unwrap(),
|
||||
Some(child)
|
||||
);
|
||||
store.retire_subject(&subject).unwrap();
|
||||
stale.source_change_id = revoked.change_id;
|
||||
assert!(store.bind_worker_execution_grant(&stale).is_err());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn journal_state_neither_authenticates_roots_nor_bypasses_retained_child_ceilings() {
|
||||
let temp = tempfile::tempdir().unwrap();
|
||||
let (_manager, _scope, store) = open_store(temp.path(), "workspace-a");
|
||||
let subject = store.create_subject(role()).unwrap().id;
|
||||
let source = store
|
||||
.set_subject_permissions(
|
||||
&subject,
|
||||
&update("allow", None, vec![permission("file.read", ".", true)]),
|
||||
)
|
||||
.unwrap();
|
||||
// The Host has authenticated root ownership outside this store. No Journal record is
|
||||
// required; changing Journal writer state cannot supply or invalidate that authentication.
|
||||
store
|
||||
.bind_worker_execution_grant(&grant(&subject, &source.change_id, "without-journal"))
|
||||
.unwrap();
|
||||
let journal = store
|
||||
.claim_journal_writer(&subject, "runtime", "body")
|
||||
.unwrap();
|
||||
store
|
||||
.bind_worker_execution_grant(&grant(&subject, &source.change_id, "with-active-journal"))
|
||||
.unwrap();
|
||||
store.release_journal_writer(&journal).unwrap();
|
||||
store
|
||||
.bind_worker_execution_grant(&grant(&subject, &source.change_id, "with-released-journal"))
|
||||
.unwrap();
|
||||
// An active Journal binding must never upgrade a child's empty redelegation ceiling.
|
||||
store
|
||||
.claim_journal_writer(&subject, "runtime", "without-journal")
|
||||
.unwrap();
|
||||
let mut descendant = grant(&subject, &source.change_id, "descendant");
|
||||
descendant.origin_worker_id = "without-journal".into();
|
||||
assert!(matches!(
|
||||
store.bind_worker_execution_grant(&descendant),
|
||||
Err(SubjektivError::AuthorizationDenied(_))
|
||||
));
|
||||
assert!(
|
||||
store
|
||||
.worker_execution_grant("runtime", "descendant")
|
||||
.unwrap()
|
||||
.is_none()
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn retained_origins_reject_cycles_foreign_subjects_and_stale_parent_sources() {
|
||||
let temp = tempfile::tempdir().unwrap();
|
||||
let (_manager, _scope, store) = open_store(temp.path(), "workspace-a");
|
||||
let subject = store.create_subject(role()).unwrap().id;
|
||||
let source = store
|
||||
.set_subject_permissions(
|
||||
&subject,
|
||||
&update("allow", None, vec![permission("file.read", ".", true)]),
|
||||
)
|
||||
.unwrap();
|
||||
let mut child = grant(&subject, &source.change_id, "child");
|
||||
child.redelegation = source.delegation.clone();
|
||||
store.bind_worker_execution_grant(&child).unwrap();
|
||||
// Closing a retained chain back through its previously unbound root must not create a cycle.
|
||||
let mut cycle = grant(&subject, &source.change_id, "body");
|
||||
cycle.origin_worker_id = "child".into();
|
||||
assert!(matches!(
|
||||
store.bind_worker_execution_grant(&cycle),
|
||||
Err(SubjektivError::AuthorizationDenied(_))
|
||||
));
|
||||
let other = store.create_subject(role()).unwrap().id;
|
||||
let other_source = store
|
||||
.set_subject_permissions(&other, &update("other", None, source.delegation.clone()))
|
||||
.unwrap();
|
||||
let mut foreign = grant(&other, &other_source.change_id, "foreign-child");
|
||||
foreign.origin_worker_id = "child".into();
|
||||
assert!(matches!(
|
||||
store.bind_worker_execution_grant(&foreign),
|
||||
Err(SubjektivError::AuthorizationDenied(_))
|
||||
));
|
||||
let current = store
|
||||
.set_subject_permissions(
|
||||
&subject,
|
||||
&update("replace", Some(&source.change_id), source.delegation),
|
||||
)
|
||||
.unwrap();
|
||||
let mut stale_parent = grant(&subject, ¤t.change_id, "stale-parent-child");
|
||||
stale_parent.origin_worker_id = "child".into();
|
||||
assert!(matches!(
|
||||
store.bind_worker_execution_grant(&stale_parent),
|
||||
Err(SubjektivError::AuthorizationDenied(_))
|
||||
));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn failed_grant_insert_leaves_no_binding_and_can_retry_same_grant() {
|
||||
let temp = tempfile::tempdir().unwrap();
|
||||
let (_manager, _scope, store) = open_store(temp.path(), "workspace-a");
|
||||
let subject = store.create_subject(role()).unwrap().id;
|
||||
let source = store
|
||||
.set_subject_permissions(
|
||||
&subject,
|
||||
&update("allow", None, vec![permission("file.read", ".", true)]),
|
||||
)
|
||||
.unwrap();
|
||||
let child = grant(&subject, &source.change_id, "child");
|
||||
store.database.try_transaction::<_, SubjektivError>(|tx| {
|
||||
tx.execute_batch("CREATE TRIGGER fail_grant BEFORE INSERT ON worker_execution_grants BEGIN SELECT RAISE(ABORT,'injected grant failure'); END;")?;
|
||||
Ok(())
|
||||
}).unwrap();
|
||||
assert!(store.bind_worker_execution_grant(&child).is_err());
|
||||
assert!(
|
||||
store
|
||||
.worker_execution_grant("runtime", "child")
|
||||
.unwrap()
|
||||
.is_none()
|
||||
);
|
||||
store
|
||||
.database
|
||||
.try_transaction::<_, SubjektivError>(|tx| {
|
||||
tx.execute_batch("DROP TRIGGER fail_grant")?;
|
||||
Ok(())
|
||||
})
|
||||
.unwrap();
|
||||
store.bind_worker_execution_grant(&child).unwrap();
|
||||
for sql in [
|
||||
"UPDATE worker_execution_grants SET source_change_id='forged'",
|
||||
"DELETE FROM worker_execution_grants",
|
||||
"UPDATE subject_permission_changes SET record_json='{}'",
|
||||
"DELETE FROM subject_permission_receipts",
|
||||
] {
|
||||
assert!(
|
||||
store
|
||||
.database
|
||||
.try_transaction::<_, SubjektivError>(|tx| {
|
||||
tx.execute_batch(sql)?;
|
||||
Ok(())
|
||||
})
|
||||
.is_err(),
|
||||
"{sql}"
|
||||
);
|
||||
}
|
||||
assert_eq!(
|
||||
store.worker_execution_grant("runtime", "child").unwrap(),
|
||||
Some(child)
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn current_schema_migration_preserves_subject_and_matches_new_database() {
|
||||
let temp = tempfile::tempdir().unwrap();
|
||||
let root = temp.path().join("migrated");
|
||||
let original;
|
||||
{
|
||||
let (_old_manager, _old_scope, old) = open_version(&root, 11);
|
||||
original = old
|
||||
.create_subject_with_behavior(role(), "Keep behavior separate".into())
|
||||
.unwrap();
|
||||
}
|
||||
let (_migrated_manager, _migrated_scope, migrated) = open_store(&root, "workspace-a");
|
||||
assert_eq!(
|
||||
migrated.subject(&original.id).unwrap(),
|
||||
Some(original.clone())
|
||||
);
|
||||
assert!(
|
||||
migrated
|
||||
.subject_permissions(&original.id)
|
||||
.unwrap()
|
||||
.is_none()
|
||||
);
|
||||
let (_fresh_manager, _fresh_scope, fresh) =
|
||||
open_store(&temp.path().join("fresh"), "workspace-a");
|
||||
assert_eq!(schema(&migrated), schema(&fresh));
|
||||
let source = migrated
|
||||
.set_subject_permissions(&original.id, &update("new-source", None, Vec::new()))
|
||||
.unwrap();
|
||||
assert!(!source.change_id.is_empty());
|
||||
assert_eq!(migrated.subject(&original.id).unwrap(), Some(original));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn unset_or_execution_only_source_cannot_issue_child_grants_and_saved_grants_survive_reopen() {
|
||||
let temp = tempfile::tempdir().unwrap();
|
||||
let saved;
|
||||
{
|
||||
let (_manager, _scope, store) = open_store(temp.path(), "workspace-a");
|
||||
let subject = store.create_subject(role()).unwrap().id;
|
||||
assert!(
|
||||
store
|
||||
.bind_worker_execution_grant(&grant(&subject, "unset", "child"))
|
||||
.is_err()
|
||||
);
|
||||
let mut execution_only = update("execution", None, Vec::new());
|
||||
execution_only.execution = vec![permission("file.read", ".", true)];
|
||||
let source = store
|
||||
.set_subject_permissions(&subject, &execution_only)
|
||||
.unwrap();
|
||||
assert!(
|
||||
store
|
||||
.bind_worker_execution_grant(&grant(&subject, &source.change_id, "child"))
|
||||
.is_err()
|
||||
);
|
||||
let source = store
|
||||
.set_subject_permissions(
|
||||
&subject,
|
||||
&update(
|
||||
"delegation",
|
||||
Some(&source.change_id),
|
||||
execution_only.execution,
|
||||
),
|
||||
)
|
||||
.unwrap();
|
||||
saved = grant(&subject, &source.change_id, "child");
|
||||
store.bind_worker_execution_grant(&saved).unwrap();
|
||||
}
|
||||
let (_manager, _scope, store) = open_store(temp.path(), "workspace-a");
|
||||
assert_eq!(
|
||||
store.worker_execution_grant("runtime", "child").unwrap(),
|
||||
Some(saved.clone())
|
||||
);
|
||||
store.bind_worker_execution_grant(&saved).unwrap();
|
||||
let mut conflicting = saved;
|
||||
conflicting.profile = "builtin:default".into();
|
||||
assert!(matches!(
|
||||
store.bind_worker_execution_grant(&conflicting),
|
||||
Err(SubjektivError::WorkerExecutionGrantConflict(_))
|
||||
));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn subject_grant_listing_is_scoped_retained_ordered_and_fails_on_overflow() {
|
||||
let temp = tempfile::tempdir().unwrap();
|
||||
let (_manager, _scope, store) = open_store(temp.path(), "workspace-a");
|
||||
let subject = store.create_subject(role()).unwrap().id;
|
||||
let other = store.create_subject(role()).unwrap().id;
|
||||
assert!(
|
||||
store
|
||||
.list_subject_worker_execution_grants(&subject)
|
||||
.unwrap()
|
||||
.is_empty()
|
||||
);
|
||||
let source = store
|
||||
.set_subject_permissions(
|
||||
&subject,
|
||||
&update("allow", None, vec![permission("file.read", ".", true)]),
|
||||
)
|
||||
.unwrap();
|
||||
let other_source = store
|
||||
.set_subject_permissions(&other, &update("other", None, source.delegation.clone()))
|
||||
.unwrap();
|
||||
let other_grant = grant(&other, &other_source.change_id, "other-child");
|
||||
store.bind_worker_execution_grant(&other_grant).unwrap();
|
||||
for index in (0..MAX_SUBJECT_WORKER_EXECUTION_GRANTS).rev() {
|
||||
store
|
||||
.bind_worker_execution_grant(&grant(
|
||||
&subject,
|
||||
&source.change_id,
|
||||
&format!("child-{index:04}"),
|
||||
))
|
||||
.unwrap();
|
||||
}
|
||||
store
|
||||
.set_subject_permissions(
|
||||
&subject,
|
||||
&update("revoke", Some(&source.change_id), Vec::new()),
|
||||
)
|
||||
.unwrap();
|
||||
store.retire_subject(&subject).unwrap();
|
||||
let listed = store
|
||||
.list_subject_worker_execution_grants(&subject)
|
||||
.unwrap();
|
||||
assert_eq!(listed.len(), MAX_SUBJECT_WORKER_EXECUTION_GRANTS);
|
||||
assert!(
|
||||
listed
|
||||
.iter()
|
||||
.all(|grant| grant.subject_id == subject && grant.source_change_id == source.change_id)
|
||||
);
|
||||
assert!(
|
||||
listed
|
||||
.windows(2)
|
||||
.all(|pair| (&pair[0].runtime_id, &pair[0].worker_id)
|
||||
< (&pair[1].runtime_id, &pair[1].worker_id))
|
||||
);
|
||||
assert_eq!(
|
||||
store.list_subject_worker_execution_grants(&other).unwrap(),
|
||||
vec![other_grant.clone()]
|
||||
);
|
||||
// Seed one more retained row directly: the retired Subject cannot issue new grants.
|
||||
// Listing must report overflow rather than returning a seemingly complete cancellation set.
|
||||
let overflow = grant(&subject, &source.change_id, "overflow");
|
||||
store.database.try_transaction::<_, SubjektivError>(|tx| {
|
||||
tx.execute("INSERT INTO worker_execution_grants(runtime_id,worker_id,subject_id,source_change_id,record_json) VALUES(?1,?2,?3,?4,?5)",
|
||||
params![overflow.runtime_id, overflow.worker_id, overflow.subject_id, overflow.source_change_id, serde_json::to_string(&overflow)?])?;
|
||||
Ok(())
|
||||
}).unwrap();
|
||||
assert!(
|
||||
matches!(store.list_subject_worker_execution_grants(&subject), Err(SubjektivError::WorkerExecutionGrantListOverflow { subject_id, limit: MAX_SUBJECT_WORKER_EXECUTION_GRANTS }) if subject_id == subject)
|
||||
);
|
||||
assert_eq!(
|
||||
store.list_subject_worker_execution_grants(&other).unwrap(),
|
||||
vec![other_grant]
|
||||
);
|
||||
let (_foreign_manager, _foreign_scope, foreign) =
|
||||
open_store(&temp.path().join("foreign"), "workspace-b");
|
||||
assert!(matches!(
|
||||
foreign.list_subject_worker_execution_grants(&subject),
|
||||
Err(SubjektivError::SubjectNotFound(_))
|
||||
));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn failed_schema_migration_rolls_back_new_tables_and_preserves_old_data() {
|
||||
let temp = tempfile::tempdir().unwrap();
|
||||
let original;
|
||||
{
|
||||
let (_old_manager, _old_scope, old) = open_version(temp.path(), 11);
|
||||
original = old.create_subject(role()).unwrap();
|
||||
old.database
|
||||
.try_transaction::<_, SubjektivError>(|tx| {
|
||||
tx.execute_batch("CREATE TABLE subject_permissions (collision TEXT)")?;
|
||||
Ok(())
|
||||
})
|
||||
.unwrap();
|
||||
}
|
||||
{
|
||||
let manager = FeatureStorage::new(temp.path());
|
||||
let scope = manager.scope("workspace-a").unwrap();
|
||||
let registration = SubjektivStore::register(&scope).unwrap();
|
||||
assert!(SubjektivStore::open(&scope, ®istration).is_err());
|
||||
}
|
||||
let (_old_manager, _old_scope, old) = open_version(temp.path(), 11);
|
||||
assert_eq!(old.database.schema_version().unwrap(), 11);
|
||||
assert_eq!(old.subject(&original.id).unwrap(), Some(original));
|
||||
old.database.try_with_connection::<_, SubjektivError>(|connection| {
|
||||
let created: bool = connection.query_row("SELECT EXISTS(SELECT 1 FROM sqlite_master WHERE name='subject_permission_changes')", [], |row| row.get(0))?;
|
||||
assert!(!created);
|
||||
Ok(())
|
||||
}).unwrap();
|
||||
}
|
||||
@@ -23,7 +23,8 @@ thiserror = { workspace = true }
|
||||
tokio = { workspace = true, features = ["process", "rt", "sync", "time"] }
|
||||
tracing = { workspace = true }
|
||||
workdir = { workspace = true }
|
||||
uuid = { workspace = true, features = ["v7"] }
|
||||
|
||||
[dev-dependencies]
|
||||
filetime = "0.2.27"
|
||||
tokio = { workspace = true, features = ["macros", "rt-multi-thread"] }
|
||||
tokio = { workspace = true, features = ["macros", "rt-multi-thread", "test-util"] }
|
||||
|
||||
+246
-232
@@ -1,24 +1,26 @@
|
||||
//! Bash Tool using WorkdirSession command capability.
|
||||
//!
|
||||
//! The selected session owns cwd, process launch, bounded output, timeout, and cancellation.
|
||||
//! Workdir owns launch and byte transport; Bash owns bounded preview and retained evidence.
|
||||
//! Bash is not a sandbox; the Runtime process and OS user define the execution boundary.
|
||||
//! Per-execution handles and nonces prevent cancellation of another command. Dropping a future
|
||||
//! does not confirm termination; active registrations remain until cleanup requests cancellation
|
||||
//! and observes terminal output.
|
||||
//! does not confirm termination. Registrations remain during bounded cancellation/drain cleanup;
|
||||
//! an unconfirmed provider outcome leaves partial evidence, never a fabricated terminal fence.
|
||||
|
||||
use std::collections::{HashMap, HashSet};
|
||||
use std::path::PathBuf;
|
||||
use std::sync::{Arc, Mutex};
|
||||
|
||||
use crate::bash_output::{BashOutputMetadata, BashOutputView, BashOutputWriter};
|
||||
use agen::tool::{Tool, ToolDefinition, ToolError, ToolMeta, ToolOutput};
|
||||
use async_trait::async_trait;
|
||||
use schemars::JsonSchema;
|
||||
use serde::Deserialize;
|
||||
use serde::{Deserialize, Serialize};
|
||||
use workdir::{
|
||||
CommandHandle, CommandOutputRequest, CommandRequest, WorkdirPath, WorkdirSessionHandle,
|
||||
WorkdirSessionRouter,
|
||||
};
|
||||
|
||||
mod cleanup;
|
||||
|
||||
const DEFAULT_TIMEOUT_SECS: u64 = 120;
|
||||
const MAX_TIMEOUT_SECS: u64 = 600;
|
||||
const INLINE_BYTE_BUDGET: usize = 12 * 1024;
|
||||
@@ -28,16 +30,18 @@ struct BashParams {
|
||||
/// Worker-local alias of the Workdir attachment to use.
|
||||
#[serde(default)]
|
||||
target_workdir: Option<String>,
|
||||
/// Workdir-relative directory in which to execute the command.
|
||||
/// Directory in which to execute the command.
|
||||
// Keep provider path-coordinate documentation out of the model-facing schema.
|
||||
#[schemars(with = "String")]
|
||||
cwd: WorkdirPath,
|
||||
command: String,
|
||||
#[serde(default)]
|
||||
timeout: Option<u64>,
|
||||
}
|
||||
|
||||
pub(crate) struct BashTool {
|
||||
pub struct BashTool {
|
||||
router: Arc<WorkdirSessionRouter>,
|
||||
output_dir: PathBuf,
|
||||
output: BashOutputView,
|
||||
state: Arc<Mutex<BashExecutionState>>,
|
||||
}
|
||||
|
||||
@@ -63,6 +67,8 @@ struct CommandGuard {
|
||||
execution_id: String,
|
||||
execution_nonce: u64,
|
||||
handle: Option<CommandHandle>,
|
||||
cursor: u64,
|
||||
retained: Option<BashOutputWriter>,
|
||||
}
|
||||
|
||||
impl Drop for CommandGuard {
|
||||
@@ -70,46 +76,69 @@ impl Drop for CommandGuard {
|
||||
let Some(handle) = self.handle.take() else {
|
||||
return;
|
||||
};
|
||||
let workdir = self.session.clone();
|
||||
let state = Arc::clone(&self.state);
|
||||
let execution_id = self.execution_id.clone();
|
||||
let execution_nonce = self.execution_nonce;
|
||||
// A dropped provider future is not terminal confirmation. Keep the live
|
||||
// execution registered until cleanup has both requested cancellation and
|
||||
// observed terminal command output, so cancellation/session teardown
|
||||
// cannot race with an apparently empty registry.
|
||||
tokio::spawn(async move {
|
||||
let _ = workdir.cancel_command(handle.clone()).await;
|
||||
let _ = workdir
|
||||
.command_output(CommandOutputRequest {
|
||||
handle,
|
||||
cursor: 0,
|
||||
limit: INLINE_BYTE_BUDGET,
|
||||
wait: true,
|
||||
})
|
||||
.await;
|
||||
let mut state = state.lock().unwrap();
|
||||
if state
|
||||
.active
|
||||
.get(&execution_id)
|
||||
.is_some_and(|active| active.execution_nonce == execution_nonce)
|
||||
{
|
||||
state.active.remove(&execution_id);
|
||||
state.cancellation_requested.remove(&execution_id);
|
||||
}
|
||||
});
|
||||
let cleanup = cleanup::Cleanup {
|
||||
session: self.session.clone(),
|
||||
state: Arc::clone(&self.state),
|
||||
execution_id: self.execution_id.clone(),
|
||||
execution_nonce: self.execution_nonce,
|
||||
handle,
|
||||
cursor: self.cursor,
|
||||
retained: self
|
||||
.retained
|
||||
.take()
|
||||
.expect("started command owns output writer"),
|
||||
};
|
||||
tokio::spawn(cleanup.run());
|
||||
}
|
||||
}
|
||||
|
||||
#[async_trait]
|
||||
impl Tool for BashTool {
|
||||
async fn execute(
|
||||
// Output pages are replayable only with the exact same command/cursor/limit.
|
||||
// Retry read transport failures, never command start, and cap both attempts and
|
||||
// backoff. The caller's deadline bounds a disconnected or unresponsive provider.
|
||||
async fn command_page(
|
||||
session: &workdir::WorkdirSessionHandle,
|
||||
request: CommandOutputRequest,
|
||||
) -> Result<workdir::CommandOutput, workdir::WorkdirError> {
|
||||
for attempt in 0..3 {
|
||||
match session.command_output(request.clone()).await {
|
||||
Err(error)
|
||||
if attempt < 2
|
||||
&& matches!(
|
||||
error.classification_source(),
|
||||
workdir::WorkdirError::Transport(_)
|
||||
| workdir::WorkdirError::Unavailable(_)
|
||||
| workdir::WorkdirError::OutcomeUnknown(_)
|
||||
) =>
|
||||
{
|
||||
tokio::time::sleep(std::time::Duration::from_millis(100 << attempt)).await;
|
||||
}
|
||||
result => return result,
|
||||
}
|
||||
}
|
||||
unreachable!("bounded retry loop returns its last result")
|
||||
}
|
||||
|
||||
impl BashTool {
|
||||
pub fn input_schema() -> serde_json::Value {
|
||||
serde_json::to_value(schemars::schema_for!(BashParams)).expect("Bash schema serialization")
|
||||
}
|
||||
|
||||
pub fn new(router: Arc<WorkdirSessionRouter>, output: BashOutputView) -> Self {
|
||||
Self {
|
||||
router,
|
||||
output,
|
||||
state: Arc::new(Mutex::new(BashExecutionState::default())),
|
||||
}
|
||||
}
|
||||
|
||||
pub async fn execute_result(
|
||||
&self,
|
||||
input_json: &str,
|
||||
ctx: agen::tool::ToolExecutionContext,
|
||||
) -> Result<ToolOutput, ToolError> {
|
||||
) -> Result<BashResult, ToolError> {
|
||||
let params: BashParams = serde_json::from_str(input_json)
|
||||
.map_err(|error| ToolError::InvalidArgument(format!("invalid Bash input: {error}")))?;
|
||||
let retained = self.output.begin().map_err(ToolError::ExecutionFailed)?;
|
||||
let selected = crate::routing::resolve_session(
|
||||
&self.router,
|
||||
params.target_workdir.as_deref(),
|
||||
@@ -134,14 +163,15 @@ impl Tool for BashTool {
|
||||
execution_id: execution_id.clone(),
|
||||
execution_nonce,
|
||||
handle: None,
|
||||
cursor: 0,
|
||||
retained: Some(retained),
|
||||
};
|
||||
let handle = session
|
||||
.start_command(CommandRequest {
|
||||
command: params.command,
|
||||
timeout_secs,
|
||||
output_limit: INLINE_BYTE_BUDGET,
|
||||
transport_byte_budget: self.output.byte_budget(),
|
||||
cwd: params.cwd,
|
||||
spill_dir: Some(self.output_dir.clone()),
|
||||
tool_call_id: Some(call_id.clone()),
|
||||
})
|
||||
.await
|
||||
@@ -167,15 +197,101 @@ impl Tool for BashTool {
|
||||
.await
|
||||
.map_err(crate::ToolsError::from)?;
|
||||
}
|
||||
let output = session
|
||||
.command_output(CommandOutputRequest {
|
||||
handle,
|
||||
cursor: 0,
|
||||
limit: INLINE_BYTE_BUDGET,
|
||||
wait: true,
|
||||
})
|
||||
let mut cursor = 0;
|
||||
let mut stdout_preview = Vec::new();
|
||||
let mut stderr_preview = Vec::new();
|
||||
let mut seen = [0_u64; 2];
|
||||
let mut empty_polls = 0;
|
||||
let deadline =
|
||||
tokio::time::Instant::now() + std::time::Duration::from_secs(timeout_secs + 30);
|
||||
let terminal = loop {
|
||||
let page = tokio::time::timeout_at(
|
||||
deadline,
|
||||
command_page(
|
||||
&session,
|
||||
CommandOutputRequest {
|
||||
handle: handle.clone(),
|
||||
cursor,
|
||||
limit: workdir::MAX_COMMAND_READ_BYTES,
|
||||
wait: true,
|
||||
},
|
||||
),
|
||||
)
|
||||
.await
|
||||
.map_err(|_| {
|
||||
ToolError::ExecutionFailed(
|
||||
"command byte transport deadline exceeded; terminal outcome unknown".into(),
|
||||
)
|
||||
})?
|
||||
.map_err(crate::ToolsError::from)?;
|
||||
let mut next = cursor;
|
||||
for chunk in &page.chunks {
|
||||
if chunk.sequence != next || chunk.bytes.is_empty() {
|
||||
return Err(ToolError::ExecutionFailed(
|
||||
"command byte transport sequence gap".into(),
|
||||
));
|
||||
}
|
||||
next = next
|
||||
.checked_add(chunk.bytes.len() as u64)
|
||||
.filter(|n| *n <= self.output.byte_budget())
|
||||
.ok_or_else(|| {
|
||||
ToolError::ExecutionFailed(
|
||||
"command byte transport exceeds delivery budget".into(),
|
||||
)
|
||||
})?;
|
||||
let index = if chunk.stream == workdir::CommandStream::Stdout {
|
||||
0
|
||||
} else {
|
||||
1
|
||||
};
|
||||
if chunk.offset != seen[index] {
|
||||
return Err(ToolError::ExecutionFailed(
|
||||
"command byte transport offset gap".into(),
|
||||
));
|
||||
}
|
||||
seen[index] += chunk.bytes.len() as u64;
|
||||
guard
|
||||
.retained
|
||||
.as_mut()
|
||||
.unwrap()
|
||||
.append_chunk(chunk)
|
||||
.map_err(ToolError::ExecutionFailed)?;
|
||||
let available =
|
||||
INLINE_BYTE_BUDGET.saturating_sub(stdout_preview.len() + stderr_preview.len());
|
||||
let preview = if index == 0 {
|
||||
&mut stdout_preview
|
||||
} else {
|
||||
&mut stderr_preview
|
||||
};
|
||||
preview.extend_from_slice(&chunk.bytes[..available.min(chunk.bytes.len())]);
|
||||
}
|
||||
if page.next_cursor != next {
|
||||
return Err(ToolError::ExecutionFailed(
|
||||
"command byte transport cursor does not fence the page".into(),
|
||||
));
|
||||
}
|
||||
if page.chunks.is_empty() && page.terminal.is_none() {
|
||||
empty_polls += 1;
|
||||
if empty_polls > 32 {
|
||||
return Err(ToolError::ExecutionFailed(
|
||||
"command byte transport made no progress after bounded polls".into(),
|
||||
));
|
||||
}
|
||||
} else {
|
||||
empty_polls = 0;
|
||||
}
|
||||
cursor = page.next_cursor;
|
||||
guard.cursor = cursor;
|
||||
if let Some(terminal) = page.terminal {
|
||||
break terminal;
|
||||
}
|
||||
};
|
||||
let metadata = guard
|
||||
.retained
|
||||
.as_mut()
|
||||
.unwrap()
|
||||
.finish_transport(&terminal)
|
||||
.map_err(ToolError::ExecutionFailed)?;
|
||||
let cancellation_requested = {
|
||||
let mut state = self.state.lock().unwrap();
|
||||
let owns_registration = state
|
||||
@@ -193,41 +309,84 @@ impl Tool for BashTool {
|
||||
};
|
||||
guard.handle = None;
|
||||
|
||||
let timed_out = output.timed_out;
|
||||
let summary = if cancellation_requested {
|
||||
format!("$ {cmd_summary} (cancelled)")
|
||||
} else if output.timed_out {
|
||||
format!("$ {cmd_summary} (timed out after {timeout_secs}s)")
|
||||
} else {
|
||||
match output.exit_code {
|
||||
Some(0) => format!("$ {cmd_summary}"),
|
||||
Some(code) => format!("$ {cmd_summary} (exit {code})"),
|
||||
None => format!("$ {cmd_summary} (terminated)"),
|
||||
}
|
||||
};
|
||||
let content = if output.content.is_empty() {
|
||||
None
|
||||
} else if output.truncated {
|
||||
let notice = match output.output_path {
|
||||
Some(path) => format!(
|
||||
"[showing bounded WorkdirSession command output; full output saved to {}]",
|
||||
path.display()
|
||||
),
|
||||
None => "[showing bounded WorkdirSession command output; additional output was truncated]"
|
||||
.to_owned(),
|
||||
let timed_out = terminal.status == workdir::CommandStatus::TimedOut;
|
||||
let mut summary =
|
||||
if cancellation_requested || terminal.status == workdir::CommandStatus::Cancelled {
|
||||
format!("$ {cmd_summary} (cancelled)")
|
||||
} else if timed_out {
|
||||
format!("$ {cmd_summary} (timed out after {timeout_secs}s)")
|
||||
} else {
|
||||
match terminal.exit_code {
|
||||
Some(0) => format!("$ {cmd_summary}"),
|
||||
Some(code) => format!("$ {cmd_summary} (exit {code})"),
|
||||
None => format!("$ {cmd_summary} (terminated)"),
|
||||
}
|
||||
};
|
||||
Some(format!("{notice}\n{}", output.content))
|
||||
} else {
|
||||
Some(output.content)
|
||||
};
|
||||
let output = ToolOutput {
|
||||
if matches!(
|
||||
terminal.output_collection,
|
||||
workdir::CommandOutputCollection::Incomplete { .. }
|
||||
) {
|
||||
summary.push_str(" (output incomplete)");
|
||||
}
|
||||
Ok(BashResult {
|
||||
summary,
|
||||
content,
|
||||
attachments: Vec::new(),
|
||||
};
|
||||
if cancellation_requested {
|
||||
stdout_preview: String::from_utf8_lossy(&stdout_preview).into_owned(),
|
||||
stderr_preview: String::from_utf8_lossy(&stderr_preview).into_owned(),
|
||||
preview_omitted: terminal.stdout_bytes.saturating_add(terminal.stderr_bytes)
|
||||
> (stdout_preview.len() + stderr_preview.len()) as u64,
|
||||
metadata,
|
||||
cancelled: cancellation_requested
|
||||
|| terminal.status == workdir::CommandStatus::Cancelled,
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
#[derive(Debug, Serialize)]
|
||||
pub struct BashResult {
|
||||
pub summary: String,
|
||||
pub stdout_preview: String,
|
||||
pub stderr_preview: String,
|
||||
pub preview_omitted: bool,
|
||||
pub metadata: BashOutputMetadata,
|
||||
pub cancelled: bool,
|
||||
}
|
||||
|
||||
impl BashResult {
|
||||
pub fn stdout_entry(&self) -> String {
|
||||
format!("/bash-output/{}/stdout", self.metadata.id)
|
||||
}
|
||||
pub fn stderr_entry(&self) -> String {
|
||||
format!("/bash-output/{}/stderr", self.metadata.id)
|
||||
}
|
||||
pub fn order_entry(&self) -> String {
|
||||
format!("/bash-output/{}/order", self.metadata.id)
|
||||
}
|
||||
pub fn tool_output(&self) -> ToolOutput {
|
||||
let content = serde_json::json!({
|
||||
"stdout_preview": self.stdout_preview, "stderr_preview": self.stderr_preview,
|
||||
"preview_omitted": self.preview_omitted, "output": self.metadata,
|
||||
"stdout_entry": self.stdout_entry(), "stderr_entry": self.stderr_entry(), "order_entry": self.order_entry(),
|
||||
});
|
||||
ToolOutput {
|
||||
summary: self.summary.clone(),
|
||||
content: Some(content.to_string()),
|
||||
attachments: vec![],
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[async_trait]
|
||||
impl Tool for BashTool {
|
||||
async fn execute(
|
||||
&self,
|
||||
input: &str,
|
||||
ctx: agen::tool::ToolExecutionContext,
|
||||
) -> Result<ToolOutput, ToolError> {
|
||||
let result = self.execute_result(input, ctx).await?;
|
||||
let output = result.tool_output();
|
||||
if result.cancelled {
|
||||
Err(ToolError::Cancelled(output))
|
||||
} else if timed_out {
|
||||
} else if result.metadata.terminal.status == Some(workdir::CommandStatus::TimedOut) {
|
||||
Err(ToolError::Interrupted(output))
|
||||
} else {
|
||||
Ok(output)
|
||||
@@ -288,164 +447,19 @@ fn truncate_for_summary(command: &str) -> String {
|
||||
summary
|
||||
}
|
||||
|
||||
pub fn bash_tool(session: WorkdirSessionHandle, output_dir: PathBuf) -> ToolDefinition {
|
||||
routed_bash_tool(crate::routing::singleton_router(session), output_dir)
|
||||
pub fn bash_tool(session: WorkdirSessionHandle, output: BashOutputView) -> ToolDefinition {
|
||||
routed_bash_tool(crate::routing::singleton_router(session), output)
|
||||
}
|
||||
|
||||
pub(crate) fn routed_bash_tool(
|
||||
router: Arc<WorkdirSessionRouter>,
|
||||
output_dir: PathBuf,
|
||||
output: BashOutputView,
|
||||
) -> ToolDefinition {
|
||||
Arc::new(move || {
|
||||
let schema = schemars::schema_for!(BashParams);
|
||||
let meta = ToolMeta::new("Bash")
|
||||
.description("Execute a shell command in one selected Workdir. Process start, bounded inline output, full-output spill, timeout and cancellation are owned by that WorkdirSession provider. This is not a sandbox.")
|
||||
.input_schema(serde_json::to_value(schema).expect("Bash schema serialization"));
|
||||
let tool: Arc<dyn Tool> = Arc::new(BashTool {
|
||||
router: router.clone(),
|
||||
output_dir: output_dir.clone(),
|
||||
state: Arc::new(Mutex::new(BashExecutionState::default())),
|
||||
});
|
||||
.description("Execute a shell command in one selected Workdir. Workdir owns launch, lossless bounded byte transport, timeout and cancel; Bash owns preview, quota-limited ephemeral output and read-only virtual references. This is not a sandbox.")
|
||||
.input_schema(BashTool::input_schema());
|
||||
let tool: Arc<dyn Tool> = Arc::new(BashTool::new(router.clone(), output.clone()));
|
||||
(meta, tool)
|
||||
})
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use std::sync::Arc;
|
||||
|
||||
use manifest::{Permission, Scope, ScopeConfig, ScopeRule};
|
||||
use tempfile::TempDir;
|
||||
use workdir::{LocalWorkdirSession, WorkdirSessionHandle};
|
||||
|
||||
use super::bash_tool;
|
||||
use crate::{grep::grep_tool, read::read_tool, tracker::Tracker};
|
||||
|
||||
fn session_with_output_scope(root: &TempDir, output: &TempDir) -> WorkdirSessionHandle {
|
||||
let scope = Scope::from_config(&ScopeConfig {
|
||||
allow: vec![
|
||||
ScopeRule {
|
||||
target: root.path().to_path_buf(),
|
||||
permission: Permission::Write,
|
||||
recursive: true,
|
||||
symlink_policy: Default::default(),
|
||||
},
|
||||
ScopeRule {
|
||||
target: output.path().to_path_buf(),
|
||||
permission: Permission::Read,
|
||||
recursive: true,
|
||||
symlink_policy: Default::default(),
|
||||
},
|
||||
],
|
||||
deny: Vec::new(),
|
||||
})
|
||||
.unwrap();
|
||||
Arc::new(LocalWorkdirSession::new(scope, root.path().to_path_buf()))
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn long_output_is_spilled_and_available_to_read_and_grep() {
|
||||
let root = TempDir::new().unwrap();
|
||||
let output = TempDir::new().unwrap();
|
||||
let session = session_with_output_scope(&root, &output);
|
||||
let (_, bash) = bash_tool(session.clone(), output.path().to_path_buf())();
|
||||
let command = "i=0; while [ $i -lt 2000 ]; do printf 'line-%04d\\n' \"$i\"; i=$((i+1)); done; printf 'FINAL-NEEDLE\\n'";
|
||||
let result = bash
|
||||
.execute(
|
||||
&serde_json::json!({ "command": command, "cwd": "." }).to_string(),
|
||||
Default::default(),
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
let rendered = result.content.expect("bounded Bash output");
|
||||
let artifact = std::fs::read_dir(output.path())
|
||||
.unwrap()
|
||||
.next()
|
||||
.expect("artifact entry")
|
||||
.unwrap()
|
||||
.path();
|
||||
|
||||
assert!(rendered.contains("full output saved to"));
|
||||
assert!(rendered.contains(&artifact.display().to_string()));
|
||||
let retained = std::fs::read_to_string(&artifact).unwrap();
|
||||
assert!(retained.starts_with("line-0000\n"));
|
||||
assert!(retained.ends_with("FINAL-NEEDLE\n"));
|
||||
assert_eq!(retained.lines().count(), 2001);
|
||||
|
||||
let (_, read) = read_tool(session.clone(), Tracker::new())();
|
||||
let read_result = read
|
||||
.execute(
|
||||
&serde_json::json!({
|
||||
"file_path": artifact,
|
||||
"offset": 2000,
|
||||
"limit": 1,
|
||||
})
|
||||
.to_string(),
|
||||
Default::default(),
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
assert!(
|
||||
read_result
|
||||
.content
|
||||
.expect("Read content")
|
||||
.contains("FINAL-NEEDLE")
|
||||
);
|
||||
|
||||
let (_, grep) = grep_tool(session)();
|
||||
let grep_result = grep
|
||||
.execute(
|
||||
&serde_json::json!({
|
||||
"pattern": "FINAL-NEEDLE",
|
||||
"path": artifact,
|
||||
"output_mode": "content",
|
||||
})
|
||||
.to_string(),
|
||||
Default::default(),
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
let grep_content = grep_result.content.expect("Grep content");
|
||||
assert!(
|
||||
grep_content.contains("FINAL-NEEDLE"),
|
||||
"unexpected Grep content: {grep_content:?}"
|
||||
);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn missing_cwd_is_rejected_before_command_start() {
|
||||
let root = TempDir::new().unwrap();
|
||||
let output = TempDir::new().unwrap();
|
||||
let session = session_with_output_scope(&root, &output);
|
||||
let (_, bash) = bash_tool(session, output.path().to_path_buf())();
|
||||
|
||||
let error = bash
|
||||
.execute(
|
||||
&serde_json::json!({ "command": "printf hidden" }).to_string(),
|
||||
Default::default(),
|
||||
)
|
||||
.await
|
||||
.unwrap_err();
|
||||
|
||||
assert!(error.to_string().contains("missing field `cwd`"));
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn short_output_does_not_leave_a_spill_artifact() {
|
||||
let root = TempDir::new().unwrap();
|
||||
let output = TempDir::new().unwrap();
|
||||
let session = session_with_output_scope(&root, &output);
|
||||
let (_, bash) = bash_tool(session, output.path().to_path_buf())();
|
||||
|
||||
let result = bash
|
||||
.execute(
|
||||
&serde_json::json!({ "command": "printf short", "cwd": "." }).to_string(),
|
||||
Default::default(),
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
assert_eq!(result.content.as_deref(), Some("short"));
|
||||
assert_eq!(std::fs::read_dir(output.path()).unwrap().count(), 0);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -0,0 +1,121 @@
|
||||
//! Finite Drop cleanup. A cancel acknowledgement is not termination evidence; only a
|
||||
//! validated terminal fence confirms the process result. No provider text is logged.
|
||||
|
||||
use super::*;
|
||||
use crate::bash_output::{
|
||||
CleanupCancel, CleanupDiagnostics, CleanupDrain, CleanupFailure, CleanupProviderFailure,
|
||||
CleanupRegistration,
|
||||
};
|
||||
use std::time::Duration;
|
||||
|
||||
const CLEANUP_TIMEOUT: Duration = Duration::from_secs(10);
|
||||
// Reserve time for independent terminal observation even if cancel never responds.
|
||||
const CANCEL_TIMEOUT: Duration = Duration::from_secs(2);
|
||||
|
||||
pub(super) struct Cleanup {
|
||||
pub session: WorkdirSessionHandle,
|
||||
pub state: Arc<Mutex<BashExecutionState>>,
|
||||
pub execution_id: String,
|
||||
pub execution_nonce: u64,
|
||||
pub handle: CommandHandle,
|
||||
pub cursor: u64,
|
||||
pub retained: BashOutputWriter,
|
||||
}
|
||||
|
||||
impl Cleanup {
|
||||
pub async fn run(mut self) {
|
||||
let deadline = tokio::time::Instant::now() + CLEANUP_TIMEOUT;
|
||||
let cancel = match tokio::time::timeout(
|
||||
CANCEL_TIMEOUT,
|
||||
self.session.cancel_command(self.handle.clone()),
|
||||
)
|
||||
.await
|
||||
{
|
||||
Ok(Ok(())) => CleanupCancel::Acknowledged,
|
||||
Ok(Err(error)) => CleanupCancel::Failed {
|
||||
reason: CleanupProviderFailure::from(&error),
|
||||
},
|
||||
Err(_) => CleanupCancel::DeadlineExceeded,
|
||||
};
|
||||
let drain = match tokio::time::timeout_at(deadline, self.drain()).await {
|
||||
Ok(Ok(())) => CleanupDrain::TerminalConfirmed,
|
||||
Ok(Err(reason)) => CleanupDrain::Failed { reason },
|
||||
Err(_) => CleanupDrain::DeadlineExceeded,
|
||||
};
|
||||
let deadline_expired = matches!(drain, CleanupDrain::DeadlineExceeded);
|
||||
// Finalize evidence before exposing an empty registry. Keep the lock through
|
||||
// publication so an older cleanup can never remove a newer generation.
|
||||
let mut state = self.state.lock().unwrap();
|
||||
let registration = if state
|
||||
.active
|
||||
.get(&self.execution_id)
|
||||
.is_some_and(|active| active.execution_nonce == self.execution_nonce)
|
||||
{
|
||||
state.active.remove(&self.execution_id);
|
||||
state.cancellation_requested.remove(&self.execution_id);
|
||||
CleanupRegistration::Released
|
||||
} else {
|
||||
CleanupRegistration::Superseded
|
||||
};
|
||||
let diagnostics = CleanupDiagnostics {
|
||||
execution_nonce: self.execution_nonce,
|
||||
cancel,
|
||||
drain,
|
||||
deadline_expired,
|
||||
registration,
|
||||
};
|
||||
tracing::info!(
|
||||
output_id = %self.retained.id(),
|
||||
cleanup = ?diagnostics,
|
||||
"Bash Drop cleanup finished; cancellation and terminal observation are independent"
|
||||
);
|
||||
self.retained.finish_cleanup(diagnostics);
|
||||
drop(self.retained);
|
||||
}
|
||||
|
||||
async fn drain(&mut self) -> Result<(), CleanupFailure> {
|
||||
loop {
|
||||
let page = command_page(
|
||||
&self.session,
|
||||
CommandOutputRequest {
|
||||
handle: self.handle.clone(),
|
||||
cursor: self.cursor,
|
||||
limit: workdir::MAX_COMMAND_READ_BYTES,
|
||||
wait: true,
|
||||
},
|
||||
)
|
||||
.await
|
||||
.map_err(|error| CleanupFailure::Provider {
|
||||
reason: CleanupProviderFailure::from(&error),
|
||||
})?;
|
||||
let mut next = self.cursor;
|
||||
for chunk in &page.chunks {
|
||||
if chunk.sequence != next {
|
||||
return Err(CleanupFailure::SequenceGap);
|
||||
}
|
||||
next = next
|
||||
.checked_add(chunk.bytes.len() as u64)
|
||||
.filter(|next| *next <= crate::bash_output::COMMAND_BYTES as u64)
|
||||
.ok_or(CleanupFailure::DeliveryBudgetExceeded)?;
|
||||
self.retained
|
||||
.append_chunk(chunk)
|
||||
.map_err(|_| CleanupFailure::RetainedChunkInvalid)?;
|
||||
}
|
||||
if page.next_cursor != next {
|
||||
return Err(CleanupFailure::CursorGap);
|
||||
}
|
||||
self.cursor = next;
|
||||
if let Some(terminal) = page.terminal {
|
||||
self.retained
|
||||
.finish_transport(&terminal)
|
||||
.map_err(|_| CleanupFailure::TerminalMetadataInvalid)?;
|
||||
return Ok(());
|
||||
}
|
||||
// An immediately-ready provider must not starve the cleanup deadline.
|
||||
tokio::task::yield_now().await;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests;
|
||||
@@ -0,0 +1,397 @@
|
||||
//! Component tests enter through the production CommandGuard Drop, cleanup, page
|
||||
//! validation and retained store. Only the Workdir provider is replaced; paused time
|
||||
//! and a cancel barrier make faults/deadlines deterministic without OS timing.
|
||||
|
||||
use super::*;
|
||||
use std::sync::atomic::{AtomicBool, Ordering};
|
||||
use workdir::*;
|
||||
|
||||
const PRIVATE: &str = "SECRET command /private/host/path output password=poison";
|
||||
|
||||
#[derive(Clone, Copy, Debug)]
|
||||
enum Fault {
|
||||
Cancel,
|
||||
CancelHang,
|
||||
Drain,
|
||||
TerminalTimeout,
|
||||
Sequence,
|
||||
Cursor,
|
||||
RetainedChunk,
|
||||
TerminalMetadata,
|
||||
CollectionIncomplete,
|
||||
Complete,
|
||||
}
|
||||
|
||||
#[derive(Debug)]
|
||||
struct Provider {
|
||||
local: LocalWorkdirSession,
|
||||
fault: Fault,
|
||||
cancelling: tokio::sync::Notify,
|
||||
allow_drain: AtomicBool,
|
||||
}
|
||||
|
||||
#[async_trait]
|
||||
impl WorkdirSession for Provider {
|
||||
fn workdir(&self) -> &Workdir {
|
||||
self.local.workdir()
|
||||
}
|
||||
fn capabilities(&self) -> WorkdirSessionCapabilities {
|
||||
WorkdirSessionCapabilities::ALL
|
||||
}
|
||||
async fn stat(&self, _: StatRequest) -> Result<StatResult, WorkdirError> {
|
||||
Err(WorkdirError::OperationFailed)
|
||||
}
|
||||
async fn read(&self, _: ReadRequest) -> Result<ReadResult, WorkdirError> {
|
||||
Err(WorkdirError::OperationFailed)
|
||||
}
|
||||
async fn write(&self, _: WriteRequest) -> Result<WriteResult, WorkdirError> {
|
||||
Err(WorkdirError::OperationFailed)
|
||||
}
|
||||
async fn edit(&self, _: EditRequest) -> Result<EditResult, WorkdirError> {
|
||||
Err(WorkdirError::OperationFailed)
|
||||
}
|
||||
async fn list(&self, _: ListRequest) -> Result<ListResult, WorkdirError> {
|
||||
Err(WorkdirError::OperationFailed)
|
||||
}
|
||||
async fn glob(&self, _: GlobRequest) -> Result<GlobResult, WorkdirError> {
|
||||
Err(WorkdirError::OperationFailed)
|
||||
}
|
||||
async fn grep(&self, _: GrepRequest) -> Result<GrepResult, WorkdirError> {
|
||||
Err(WorkdirError::OperationFailed)
|
||||
}
|
||||
async fn start_command(&self, _: CommandRequest) -> Result<CommandHandle, WorkdirError> {
|
||||
Err(WorkdirError::OperationFailed)
|
||||
}
|
||||
async fn command_status(&self, _: CommandHandle) -> Result<CommandStatus, WorkdirError> {
|
||||
Err(WorkdirError::OperationFailed)
|
||||
}
|
||||
|
||||
async fn command_output(
|
||||
&self,
|
||||
request: CommandOutputRequest,
|
||||
) -> Result<CommandOutput, WorkdirError> {
|
||||
assert_eq!(request.cursor, 3);
|
||||
while !self.allow_drain.load(Ordering::Acquire) {
|
||||
tokio::task::yield_now().await;
|
||||
}
|
||||
match self.fault {
|
||||
Fault::Drain => {
|
||||
return Err(WorkdirError::Transport(PRIVATE.into())
|
||||
.with_failure_reason(WorkdirFailureReason::HttpTransfer));
|
||||
}
|
||||
Fault::TerminalTimeout => return std::future::pending().await,
|
||||
_ => {}
|
||||
}
|
||||
let mut chunk = CommandByteChunk {
|
||||
sequence: 3,
|
||||
offset: 3,
|
||||
stream: CommandStream::Stdout,
|
||||
bytes: b"tail".to_vec(),
|
||||
};
|
||||
if matches!(self.fault, Fault::Sequence) {
|
||||
chunk.sequence = 4;
|
||||
}
|
||||
if matches!(self.fault, Fault::RetainedChunk) {
|
||||
chunk.offset = 42;
|
||||
}
|
||||
let mut terminal = terminal();
|
||||
if matches!(self.fault, Fault::TerminalMetadata) {
|
||||
terminal.stdout_delivered_bytes = 6;
|
||||
}
|
||||
if matches!(self.fault, Fault::CollectionIncomplete) {
|
||||
terminal.output_collection = CommandOutputCollection::Incomplete {
|
||||
failure: CommandFailure {
|
||||
stage: CommandFailureStage::StdoutDrain,
|
||||
reason: CommandIoErrorKind::Other,
|
||||
os_code: None,
|
||||
},
|
||||
};
|
||||
}
|
||||
Ok(CommandOutput {
|
||||
chunks: vec![chunk],
|
||||
next_cursor: if matches!(self.fault, Fault::Cursor) {
|
||||
8
|
||||
} else {
|
||||
7
|
||||
},
|
||||
terminal: Some(terminal),
|
||||
})
|
||||
}
|
||||
|
||||
async fn cancel_command(&self, _: CommandHandle) -> Result<(), WorkdirError> {
|
||||
self.cancelling.notify_one();
|
||||
match self.fault {
|
||||
Fault::Cancel => Err(WorkdirError::Unavailable(PRIVATE.into())),
|
||||
Fault::CancelHang => std::future::pending().await,
|
||||
_ => Ok(()),
|
||||
}
|
||||
}
|
||||
async fn close(&self) -> Result<(), WorkdirError> {
|
||||
Ok(())
|
||||
}
|
||||
}
|
||||
|
||||
fn terminal() -> CommandTerminal {
|
||||
CommandTerminal {
|
||||
status: CommandStatus::Completed,
|
||||
exit_code: Some(0),
|
||||
process_failure: None,
|
||||
output_collection: CommandOutputCollection::Complete,
|
||||
stdout_bytes: 7,
|
||||
stderr_bytes: 0,
|
||||
stdout_delivered_bytes: 7,
|
||||
stderr_delivered_bytes: 0,
|
||||
truncation_reason: None,
|
||||
}
|
||||
}
|
||||
|
||||
struct Fixture {
|
||||
_root: tempfile::TempDir,
|
||||
provider: Arc<Provider>,
|
||||
state: Arc<Mutex<BashExecutionState>>,
|
||||
view: BashOutputView,
|
||||
id: String,
|
||||
}
|
||||
|
||||
impl Fixture {
|
||||
fn start(fault: Fault) -> (Self, CommandGuard) {
|
||||
let base =
|
||||
std::path::Path::new(env!("CARGO_MANIFEST_DIR")).join("../../target/cleanup-fixtures");
|
||||
std::fs::create_dir_all(&base).unwrap();
|
||||
let root = tempfile::tempdir_in(base).unwrap();
|
||||
let provider = Arc::new(Provider {
|
||||
local: LocalWorkdirSession::new(
|
||||
manifest::Scope::writable(root.path()).unwrap(),
|
||||
root.path().into(),
|
||||
),
|
||||
fault,
|
||||
cancelling: Default::default(),
|
||||
allow_drain: AtomicBool::new(false),
|
||||
});
|
||||
let view = BashOutputView::new();
|
||||
let mut retained = view.begin().unwrap();
|
||||
retained.append(CommandStream::Stdout, b"pre");
|
||||
let id = retained.id();
|
||||
let state = Arc::new(Mutex::new(BashExecutionState::default()));
|
||||
let handle = CommandHandle(PRIVATE.into());
|
||||
state.lock().unwrap().active.insert(
|
||||
PRIVATE.into(),
|
||||
ActiveCommand {
|
||||
call_id: PRIVATE.into(),
|
||||
execution_nonce: 1,
|
||||
session: provider.clone(),
|
||||
handle: handle.clone(),
|
||||
},
|
||||
);
|
||||
state
|
||||
.lock()
|
||||
.unwrap()
|
||||
.cancellation_requested
|
||||
.insert(PRIVATE.into());
|
||||
let guard = CommandGuard {
|
||||
session: provider.clone(),
|
||||
state: state.clone(),
|
||||
execution_id: PRIVATE.into(),
|
||||
execution_nonce: 1,
|
||||
handle: Some(handle),
|
||||
cursor: 3,
|
||||
retained: Some(retained),
|
||||
};
|
||||
(
|
||||
Self {
|
||||
_root: root,
|
||||
provider,
|
||||
state,
|
||||
view,
|
||||
id,
|
||||
},
|
||||
guard,
|
||||
)
|
||||
}
|
||||
|
||||
async fn finish(&self) -> BashOutputMetadata {
|
||||
self.provider.allow_drain.store(true, Ordering::Release);
|
||||
// The provider's read retry backoff and cleanup deadlines are virtual time.
|
||||
for _ in 0..4 {
|
||||
tokio::task::yield_now().await;
|
||||
tokio::time::advance(Duration::from_secs(3)).await;
|
||||
}
|
||||
for _ in 0..1000 {
|
||||
if let Some(metadata) = self.view.metadata(&self.id) {
|
||||
return metadata;
|
||||
}
|
||||
tokio::task::yield_now().await;
|
||||
}
|
||||
panic!("finite cleanup did not publish partial evidence");
|
||||
}
|
||||
|
||||
fn assert_evidence(&self, m: &BashOutputMetadata, terminal: bool, bytes: &[u8]) {
|
||||
assert_eq!(
|
||||
self.view
|
||||
.read(&self.id, CommandStream::Stdout, 0, 64)
|
||||
.unwrap(),
|
||||
bytes
|
||||
);
|
||||
assert_eq!(m.stdout_saved, bytes.len());
|
||||
assert_eq!(m.stdout_delivered, bytes.len() as u64);
|
||||
assert_eq!(m.stdout_seen, bytes.len() as u64);
|
||||
assert_eq!(
|
||||
m.terminal.status,
|
||||
terminal.then_some(CommandStatus::Completed)
|
||||
);
|
||||
assert_eq!(m.terminal.exit_code, terminal.then_some(0));
|
||||
if !terminal {
|
||||
assert!(m.terminal.output_collection.is_none());
|
||||
assert!(m.terminal.process_failure.is_none());
|
||||
assert!(!m.terminal.transport_complete);
|
||||
}
|
||||
let diagnostics = m.cleanup.as_ref().unwrap();
|
||||
assert_eq!(diagnostics.execution_nonce, 1);
|
||||
let json = serde_json::to_string(diagnostics).unwrap();
|
||||
let debug = format!("{diagnostics:?}");
|
||||
for forbidden in [
|
||||
PRIVATE, "SECRET", "/private", "password", "poison", "tail", "pre",
|
||||
] {
|
||||
assert!(!json.contains(forbidden), "diagnostics leaked data: {json}");
|
||||
assert!(
|
||||
!debug.contains(forbidden),
|
||||
"tracing payload leaked data: {debug}"
|
||||
);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[tokio::test(start_paused = true)]
|
||||
async fn cancel_failure_does_not_preclude_confirmed_terminal() {
|
||||
let (f, guard) = Fixture::start(Fault::Cancel);
|
||||
drop(guard);
|
||||
f.provider.cancelling.notified().await;
|
||||
assert!(f.state.lock().unwrap().active.contains_key(PRIVATE));
|
||||
let m = f.finish().await;
|
||||
f.assert_evidence(&m, true, b"pretail");
|
||||
assert!(m.terminal.transport_complete);
|
||||
assert!(matches!(
|
||||
m.cleanup.as_ref().unwrap().cancel,
|
||||
CleanupCancel::Failed { .. }
|
||||
));
|
||||
assert!(matches!(
|
||||
m.cleanup.as_ref().unwrap().drain,
|
||||
CleanupDrain::TerminalConfirmed
|
||||
));
|
||||
assert!(!m.cleanup.as_ref().unwrap().deadline_expired);
|
||||
assert!(f.state.lock().unwrap().active.is_empty());
|
||||
assert!(f.state.lock().unwrap().cancellation_requested.is_empty());
|
||||
}
|
||||
|
||||
#[tokio::test(start_paused = true)]
|
||||
async fn acknowledged_cancel_drain_faults_keep_distinct_reasons_and_partial_bytes() {
|
||||
for (fault, reason, bytes) in [
|
||||
(Fault::Drain, "provider", b"pre".as_slice()),
|
||||
(Fault::Sequence, "sequence_gap", b"pre"),
|
||||
(Fault::Cursor, "cursor_gap", b"pretail"),
|
||||
(Fault::RetainedChunk, "retained_chunk_invalid", b"pre"),
|
||||
(
|
||||
Fault::TerminalMetadata,
|
||||
"terminal_metadata_invalid",
|
||||
b"pretail",
|
||||
),
|
||||
] {
|
||||
let (f, guard) = Fixture::start(fault);
|
||||
drop(guard);
|
||||
f.provider.cancelling.notified().await;
|
||||
let m = f.finish().await;
|
||||
f.assert_evidence(&m, false, bytes);
|
||||
let diagnostic = serde_json::to_value(m.cleanup.as_ref().unwrap()).unwrap();
|
||||
assert_eq!(diagnostic["cancel"]["outcome"], "acknowledged");
|
||||
assert_eq!(diagnostic["drain"]["outcome"], "failed");
|
||||
assert_eq!(diagnostic["drain"]["reason"]["kind"], reason);
|
||||
assert_eq!(diagnostic["registration"], "released");
|
||||
assert_eq!(diagnostic["deadline_expired"], false);
|
||||
assert!(f.state.lock().unwrap().active.is_empty());
|
||||
}
|
||||
}
|
||||
|
||||
#[tokio::test(start_paused = true)]
|
||||
async fn terminal_deadline_never_claims_stop_or_leaves_active_collector() {
|
||||
let (f, guard) = Fixture::start(Fault::TerminalTimeout);
|
||||
drop(guard);
|
||||
f.provider.cancelling.notified().await;
|
||||
let m = f.finish().await;
|
||||
f.assert_evidence(&m, false, b"pre");
|
||||
assert!(matches!(
|
||||
m.cleanup.as_ref().unwrap().cancel,
|
||||
CleanupCancel::Acknowledged
|
||||
));
|
||||
assert!(matches!(
|
||||
m.cleanup.as_ref().unwrap().drain,
|
||||
CleanupDrain::DeadlineExceeded
|
||||
));
|
||||
assert!(m.cleanup.as_ref().unwrap().deadline_expired);
|
||||
assert!(f.state.lock().unwrap().active.is_empty());
|
||||
}
|
||||
|
||||
#[tokio::test(start_paused = true)]
|
||||
async fn cancel_deadline_still_attempts_independent_terminal_observation() {
|
||||
let (f, guard) = Fixture::start(Fault::CancelHang);
|
||||
drop(guard);
|
||||
f.provider.cancelling.notified().await;
|
||||
let m = f.finish().await;
|
||||
f.assert_evidence(&m, true, b"pretail");
|
||||
assert!(matches!(
|
||||
m.cleanup.as_ref().unwrap().cancel,
|
||||
CleanupCancel::DeadlineExceeded
|
||||
));
|
||||
assert!(matches!(
|
||||
m.cleanup.as_ref().unwrap().drain,
|
||||
CleanupDrain::TerminalConfirmed
|
||||
));
|
||||
assert!(!m.cleanup.as_ref().unwrap().deadline_expired);
|
||||
assert!(f.state.lock().unwrap().active.is_empty());
|
||||
}
|
||||
|
||||
#[tokio::test(start_paused = true)]
|
||||
async fn old_cleanup_preserves_new_execution_and_cancellation_registration() {
|
||||
let (f, guard) = Fixture::start(Fault::Complete);
|
||||
drop(guard);
|
||||
f.provider.cancelling.notified().await;
|
||||
f.state
|
||||
.lock()
|
||||
.unwrap()
|
||||
.active
|
||||
.get_mut(PRIVATE)
|
||||
.unwrap()
|
||||
.execution_nonce = 2;
|
||||
let m = f.finish().await;
|
||||
f.assert_evidence(&m, true, b"pretail");
|
||||
assert!(matches!(
|
||||
m.cleanup.as_ref().unwrap().registration,
|
||||
CleanupRegistration::Superseded
|
||||
));
|
||||
assert_eq!(f.state.lock().unwrap().active[PRIVATE].execution_nonce, 2);
|
||||
assert!(
|
||||
f.state
|
||||
.lock()
|
||||
.unwrap()
|
||||
.cancellation_requested
|
||||
.contains(PRIVATE)
|
||||
);
|
||||
}
|
||||
|
||||
#[tokio::test(start_paused = true)]
|
||||
async fn terminal_confirmation_is_independent_of_output_collection_completeness() {
|
||||
let (f, guard) = Fixture::start(Fault::CollectionIncomplete);
|
||||
drop(guard);
|
||||
f.provider.cancelling.notified().await;
|
||||
let m = f.finish().await;
|
||||
f.assert_evidence(&m, true, b"pretail");
|
||||
assert!(!m.terminal.transport_complete);
|
||||
assert!(matches!(
|
||||
m.terminal.output_collection,
|
||||
Some(CommandOutputCollection::Incomplete { .. })
|
||||
));
|
||||
assert!(matches!(
|
||||
m.cleanup.as_ref().unwrap().drain,
|
||||
CleanupDrain::TerminalConfirmed
|
||||
));
|
||||
assert!(f.state.lock().unwrap().active.is_empty());
|
||||
}
|
||||
@@ -0,0 +1,725 @@
|
||||
//! Bash-owned bounded output, independent of Workdir transport and Console subscribers.
|
||||
//!
|
||||
//! Output is ephemeral evidence, not a filesystem grant. Every lookup checks the live view;
|
||||
//! children can see their own subtree and ancestors can retain evidence after child revocation.
|
||||
//! Root teardown clears all bytes. A new root (including restore) has a new incarnation and
|
||||
//! never reconstructs grants from history. Expiry is measured from admission, enforced on
|
||||
//! lookup and by a weak reaper once commands run in Tokio. Parent and all descendants share
|
||||
//! one pool: admission reserves a whole command budget, evicts the oldest terminal evidence
|
||||
//! first, and refuses rather than evicting a live collector. Revoking a child denies access
|
||||
//! but leaves ancestor evidence until pool eviction/expiry; root teardown clears the pool.
|
||||
|
||||
use std::collections::VecDeque;
|
||||
use std::sync::{
|
||||
Arc, Mutex, Weak,
|
||||
atomic::{AtomicBool, Ordering},
|
||||
};
|
||||
use std::time::{Duration, Instant};
|
||||
|
||||
use serde::Serialize;
|
||||
use workdir::{CommandStatus, CommandStream};
|
||||
|
||||
pub(crate) const COMMAND_BYTES: usize = 4 * 1024 * 1024;
|
||||
const STORE_BYTES: usize = 32 * 1024 * 1024;
|
||||
const STORE_COUNT: usize = 64;
|
||||
const ORDER_COUNT: usize = 4096;
|
||||
const RETENTION: Duration = Duration::from_secs(3600);
|
||||
|
||||
#[derive(Clone)]
|
||||
pub struct BashOutputView {
|
||||
store: Arc<Mutex<Store>>,
|
||||
lineage: Vec<String>,
|
||||
active: Arc<AtomicBool>,
|
||||
authority: Arc<dyn Fn() -> bool + Send + Sync>,
|
||||
}
|
||||
|
||||
struct Store {
|
||||
records: VecDeque<Arc<Mutex<Record>>>,
|
||||
reserved: usize,
|
||||
retention: Duration,
|
||||
reaper_started: bool,
|
||||
_shutdown: tokio::sync::watch::Sender<()>,
|
||||
}
|
||||
|
||||
struct Record {
|
||||
id: String,
|
||||
owner: Vec<String>,
|
||||
created: Instant,
|
||||
stdout: Vec<u8>,
|
||||
stderr: Vec<u8>,
|
||||
order: Vec<OutputRange>,
|
||||
stdout_seen: u64,
|
||||
stderr_seen: u64,
|
||||
truncated: bool,
|
||||
limit: Option<RetentionLimit>,
|
||||
transport_counts: Option<(u64, u64)>,
|
||||
transport_truncation: Option<workdir::CommandOutputTruncation>,
|
||||
terminal: Option<OutputTerminal>,
|
||||
cleanup: Option<CleanupDiagnostics>,
|
||||
}
|
||||
|
||||
#[derive(Clone, Debug, Serialize)]
|
||||
pub struct OutputRange {
|
||||
pub stream: CommandStream,
|
||||
pub start: u64,
|
||||
pub end: u64,
|
||||
}
|
||||
|
||||
#[derive(Clone, Debug, Serialize)]
|
||||
pub struct OutputTerminal {
|
||||
pub status: Option<CommandStatus>,
|
||||
pub exit_code: Option<i32>,
|
||||
pub process_failure: Option<workdir::CommandFailure>,
|
||||
pub output_collection: Option<workdir::CommandOutputCollection>,
|
||||
/// True only for confirmed EOF collection (quota is reported separately). A terminal
|
||||
/// fence or exit zero alone does not confirm the unobserved process tail.
|
||||
pub transport_complete: bool,
|
||||
}
|
||||
|
||||
#[derive(Clone, Copy, Debug, Serialize)]
|
||||
#[serde(rename_all = "snake_case")]
|
||||
pub enum RetentionLimit {
|
||||
ByteQuota,
|
||||
OrderQuota,
|
||||
}
|
||||
|
||||
#[derive(Clone, Debug, Serialize)]
|
||||
pub struct BashOutputMetadata {
|
||||
pub id: String,
|
||||
pub stdout_saved: usize,
|
||||
pub stderr_saved: usize,
|
||||
pub stdout_seen: u64,
|
||||
pub stderr_seen: u64,
|
||||
pub stdout_delivered: u64,
|
||||
pub stderr_delivered: u64,
|
||||
pub retention_limit: Option<RetentionLimit>,
|
||||
pub transport_truncation: Option<workdir::CommandOutputTruncation>,
|
||||
pub storage_truncated: bool,
|
||||
pub terminal: OutputTerminal,
|
||||
pub cleanup: Option<CleanupDiagnostics>,
|
||||
pub text_encoding: &'static str,
|
||||
pub ordering: &'static str,
|
||||
}
|
||||
|
||||
/// Drop cleanup observations, not assertions that cancellation stopped a process.
|
||||
/// Correlate with the enclosing output UUID and this host-assigned execution generation;
|
||||
/// caller identifiers, provider handles, commands and error text are deliberately excluded.
|
||||
#[derive(Clone, Debug, Serialize)]
|
||||
pub struct CleanupDiagnostics {
|
||||
pub execution_nonce: u64,
|
||||
pub cancel: CleanupCancel,
|
||||
pub drain: CleanupDrain,
|
||||
pub deadline_expired: bool,
|
||||
pub registration: CleanupRegistration,
|
||||
}
|
||||
|
||||
#[derive(Clone, Debug, Serialize)]
|
||||
#[serde(tag = "outcome", rename_all = "snake_case")]
|
||||
pub enum CleanupCancel {
|
||||
Acknowledged,
|
||||
Failed { reason: CleanupProviderFailure },
|
||||
DeadlineExceeded,
|
||||
}
|
||||
|
||||
#[derive(Clone, Debug, Serialize)]
|
||||
#[serde(tag = "outcome", rename_all = "snake_case")]
|
||||
pub enum CleanupDrain {
|
||||
TerminalConfirmed,
|
||||
Failed { reason: CleanupFailure },
|
||||
DeadlineExceeded,
|
||||
}
|
||||
|
||||
#[derive(Clone, Debug, Serialize)]
|
||||
#[serde(tag = "kind", rename_all = "snake_case")]
|
||||
pub enum CleanupFailure {
|
||||
Provider { reason: CleanupProviderFailure },
|
||||
SequenceGap,
|
||||
CursorGap,
|
||||
DeliveryBudgetExceeded,
|
||||
RetainedChunkInvalid,
|
||||
TerminalMetadataInvalid,
|
||||
}
|
||||
|
||||
#[derive(Clone, Debug, Serialize)]
|
||||
pub struct CleanupProviderFailure {
|
||||
pub failure_reason: Option<workdir::WorkdirFailureReason>,
|
||||
pub denial_reason: Option<workdir::WorkdirDenialReason>,
|
||||
}
|
||||
|
||||
impl From<&workdir::WorkdirError> for CleanupProviderFailure {
|
||||
fn from(error: &workdir::WorkdirError) -> Self {
|
||||
Self {
|
||||
failure_reason: error.failure_reason(),
|
||||
denial_reason: error.denial_reason(),
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[derive(Clone, Copy, Debug, Serialize)]
|
||||
#[serde(rename_all = "snake_case")]
|
||||
pub enum CleanupRegistration {
|
||||
Released,
|
||||
Superseded,
|
||||
}
|
||||
|
||||
/// A bounded reservation acquired before command start. Drop terminalizes partial evidence.
|
||||
pub struct BashOutputWriter {
|
||||
record: Arc<Mutex<Record>>,
|
||||
}
|
||||
|
||||
impl Default for BashOutputView {
|
||||
fn default() -> Self {
|
||||
Self::new()
|
||||
}
|
||||
}
|
||||
|
||||
impl BashOutputView {
|
||||
pub fn new() -> Self {
|
||||
let (shutdown, _) = tokio::sync::watch::channel(());
|
||||
let store = Arc::new(Mutex::new(Store {
|
||||
records: VecDeque::new(),
|
||||
reserved: 0,
|
||||
retention: RETENTION,
|
||||
reaper_started: false,
|
||||
_shutdown: shutdown,
|
||||
}));
|
||||
let view = Self {
|
||||
store,
|
||||
lineage: vec![uuid::Uuid::now_v7().to_string()],
|
||||
active: Arc::new(AtomicBool::new(true)),
|
||||
authority: Arc::new(|| true),
|
||||
};
|
||||
view.start_reaper();
|
||||
view
|
||||
}
|
||||
|
||||
fn start_reaper(&self) {
|
||||
let Ok(runtime) = tokio::runtime::Handle::try_current() else {
|
||||
return;
|
||||
};
|
||||
let mut store = self.store.lock().unwrap();
|
||||
if store.reaper_started {
|
||||
return;
|
||||
}
|
||||
let receiver = store._shutdown.subscribe();
|
||||
store.reaper_started = true;
|
||||
let weak = Arc::downgrade(&self.store);
|
||||
runtime.spawn(reap(weak, receiver));
|
||||
}
|
||||
|
||||
pub fn byte_budget(&self) -> u64 {
|
||||
COMMAND_BYTES as u64
|
||||
}
|
||||
|
||||
pub fn child(&self, authority: Arc<dyn Fn() -> bool + Send + Sync>) -> Self {
|
||||
let parent = self.clone();
|
||||
let mut lineage = self.lineage.clone();
|
||||
lineage.push(uuid::Uuid::now_v7().to_string());
|
||||
Self {
|
||||
store: self.store.clone(),
|
||||
lineage,
|
||||
active: Arc::new(AtomicBool::new(true)),
|
||||
authority: Arc::new(move || parent.is_active() && authority()),
|
||||
}
|
||||
}
|
||||
|
||||
pub fn is_active(&self) -> bool {
|
||||
self.active.load(Ordering::Acquire) && (self.authority)()
|
||||
}
|
||||
|
||||
pub fn is_root(&self) -> bool {
|
||||
self.lineage.len() == 1
|
||||
}
|
||||
|
||||
pub fn revoke(&self) {
|
||||
self.active.store(false, Ordering::Release);
|
||||
if self.lineage.len() == 1 {
|
||||
let mut store = self.store.lock().unwrap();
|
||||
store.records.clear();
|
||||
store.reserved = 0;
|
||||
}
|
||||
}
|
||||
|
||||
pub fn begin(&self) -> Result<BashOutputWriter, String> {
|
||||
if !self.is_active() {
|
||||
return Err("Bash output authority revoked".into());
|
||||
}
|
||||
// A host may construct the Feature before entering Tokio. Command admission
|
||||
// happens inside the runtime, so idle expiry must start here as well.
|
||||
self.start_reaper();
|
||||
let mut store = self.store.lock().unwrap();
|
||||
if !self.is_active() {
|
||||
return Err("Bash output authority revoked".into());
|
||||
}
|
||||
store.expire(Instant::now());
|
||||
while store.records.len() >= STORE_COUNT || store.reserved + COMMAND_BYTES > STORE_BYTES {
|
||||
let Some(index) = store
|
||||
.records
|
||||
.iter()
|
||||
.position(|r| r.lock().unwrap().terminal.is_some())
|
||||
else {
|
||||
return Err("Bash output capacity is occupied by live commands".into());
|
||||
};
|
||||
store.records.remove(index);
|
||||
store.reserved -= COMMAND_BYTES;
|
||||
}
|
||||
let record = Arc::new(Mutex::new(Record {
|
||||
id: uuid::Uuid::now_v7().to_string(),
|
||||
owner: self.lineage.clone(),
|
||||
created: Instant::now(),
|
||||
stdout: Vec::new(),
|
||||
stderr: Vec::new(),
|
||||
order: Vec::new(),
|
||||
stdout_seen: 0,
|
||||
stderr_seen: 0,
|
||||
truncated: false,
|
||||
limit: None,
|
||||
transport_counts: None,
|
||||
transport_truncation: None,
|
||||
terminal: None,
|
||||
cleanup: None,
|
||||
}));
|
||||
store.records.push_back(record.clone());
|
||||
store.reserved += COMMAND_BYTES;
|
||||
Ok(BashOutputWriter { record })
|
||||
}
|
||||
|
||||
fn record(&self, id: &str) -> Option<Arc<Mutex<Record>>> {
|
||||
if !self.is_active() {
|
||||
return None;
|
||||
}
|
||||
let mut store = self.store.lock().unwrap();
|
||||
if !self.is_active() {
|
||||
return None;
|
||||
}
|
||||
store.expire(Instant::now());
|
||||
store
|
||||
.records
|
||||
.iter()
|
||||
.find(|r| {
|
||||
let r = r.lock().unwrap();
|
||||
r.id == id && r.owner.starts_with(&self.lineage) && r.terminal.is_some()
|
||||
})
|
||||
.cloned()
|
||||
}
|
||||
|
||||
pub fn metadata(&self, id: &str) -> Option<BashOutputMetadata> {
|
||||
let record = self.record(id)?;
|
||||
let r = record.lock().unwrap();
|
||||
Some(r.metadata())
|
||||
}
|
||||
|
||||
/// Copies at most the caller's bounded range; never publishes output bodies in descriptors.
|
||||
pub fn read(
|
||||
&self,
|
||||
id: &str,
|
||||
stream: CommandStream,
|
||||
offset: usize,
|
||||
limit: usize,
|
||||
) -> Option<Vec<u8>> {
|
||||
let record = self.record(id)?;
|
||||
let r = record.lock().unwrap();
|
||||
let bytes = match stream {
|
||||
CommandStream::Stdout => &r.stdout,
|
||||
CommandStream::Stderr => &r.stderr,
|
||||
};
|
||||
let start = offset.min(bytes.len());
|
||||
Some(bytes[start..start.saturating_add(limit.min(64 * 1024)).min(bytes.len())].to_vec())
|
||||
}
|
||||
|
||||
/// Scan the bounded raw source without cloning it, decoding only the requested line window.
|
||||
/// A long single line uses the common byte reader instead of allocating an oversized text page.
|
||||
pub fn line_window(
|
||||
&self,
|
||||
id: &str,
|
||||
stream: CommandStream,
|
||||
offset: usize,
|
||||
limit: usize,
|
||||
) -> Option<Result<(String, bool), String>> {
|
||||
let record = self.record(id)?;
|
||||
let r = record.lock().unwrap();
|
||||
let bytes = match stream {
|
||||
CommandStream::Stdout => &r.stdout,
|
||||
CommandStream::Stderr => &r.stderr,
|
||||
};
|
||||
let mut lines = bytes.split_inclusive(|b| *b == b'\n').skip(offset);
|
||||
let mut window = Vec::new();
|
||||
for line in lines.by_ref().take(limit.min(2000)) {
|
||||
if window.len() + line.len() > 64 * 1024 {
|
||||
return Some(Err(
|
||||
"text source window exceeds 64 KiB; use the common byte reader".into(),
|
||||
));
|
||||
}
|
||||
window.extend_from_slice(line);
|
||||
}
|
||||
let more = lines.next().is_some();
|
||||
Some(Ok((String::from_utf8_lossy(&window).into_owned(), more)))
|
||||
}
|
||||
|
||||
pub fn order(&self, id: &str) -> Option<Vec<OutputRange>> {
|
||||
let record = self.record(id)?;
|
||||
let r = record.lock().unwrap();
|
||||
Some(r.order.clone())
|
||||
}
|
||||
}
|
||||
|
||||
impl Record {
|
||||
fn metadata(&self) -> BashOutputMetadata {
|
||||
BashOutputMetadata {
|
||||
id: self.id.clone(),
|
||||
stdout_saved: self.stdout.len(),
|
||||
stderr_saved: self.stderr.len(),
|
||||
stdout_seen: self.transport_counts.map_or(self.stdout_seen, |c| c.0),
|
||||
stderr_seen: self.transport_counts.map_or(self.stderr_seen, |c| c.1),
|
||||
stdout_delivered: self.stdout_seen,
|
||||
stderr_delivered: self.stderr_seen,
|
||||
retention_limit: self.limit,
|
||||
transport_truncation: self.transport_truncation.clone(),
|
||||
storage_truncated: self.truncated || self.transport_truncation.is_some(),
|
||||
terminal: self.terminal.clone().expect("finalized record"),
|
||||
cleanup: self.cleanup.clone(),
|
||||
text_encoding: "utf8_lossy",
|
||||
ordering: "provider_read_observation",
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
impl Store {
|
||||
fn expire(&mut self, now: Instant) {
|
||||
let before = self.records.len();
|
||||
self.records
|
||||
.retain(|r| now.duration_since(r.lock().unwrap().created) < self.retention);
|
||||
self.reserved -= (before - self.records.len()) * COMMAND_BYTES;
|
||||
}
|
||||
}
|
||||
|
||||
async fn reap(weak: Weak<Mutex<Store>>, mut shutdown: tokio::sync::watch::Receiver<()>) {
|
||||
loop {
|
||||
tokio::select! {
|
||||
_ = tokio::time::sleep(Duration::from_secs(30)) => {},
|
||||
_ = shutdown.changed() => return,
|
||||
}
|
||||
let Some(store) = weak.upgrade() else {
|
||||
return;
|
||||
};
|
||||
store.lock().unwrap().expire(Instant::now());
|
||||
}
|
||||
}
|
||||
|
||||
impl BashOutputWriter {
|
||||
pub(crate) fn id(&self) -> String {
|
||||
self.record.lock().unwrap().id.clone()
|
||||
}
|
||||
|
||||
pub(crate) fn finish_cleanup(&mut self, diagnostics: CleanupDiagnostics) {
|
||||
self.record.lock().unwrap().cleanup = Some(diagnostics);
|
||||
}
|
||||
|
||||
pub fn append_chunk(&mut self, chunk: &workdir::CommandByteChunk) -> Result<(), String> {
|
||||
let expected = {
|
||||
let r = self.record.lock().unwrap();
|
||||
match chunk.stream {
|
||||
CommandStream::Stdout => r.stdout_seen,
|
||||
CommandStream::Stderr => r.stderr_seen,
|
||||
}
|
||||
};
|
||||
if chunk.offset != expected || chunk.bytes.is_empty() {
|
||||
return Err("command byte transport stream gap or empty chunk".into());
|
||||
}
|
||||
self.append(chunk.stream, &chunk.bytes);
|
||||
Ok(())
|
||||
}
|
||||
|
||||
pub fn append(&mut self, stream: CommandStream, bytes: &[u8]) {
|
||||
let mut r = self.record.lock().unwrap();
|
||||
let seen = match stream {
|
||||
CommandStream::Stdout => &mut r.stdout_seen,
|
||||
CommandStream::Stderr => &mut r.stderr_seen,
|
||||
};
|
||||
let start = *seen;
|
||||
*seen = seen.saturating_add(bytes.len() as u64);
|
||||
let available = COMMAND_BYTES.saturating_sub(r.stdout.len() + r.stderr.len());
|
||||
let n = if r.truncated || r.order.len() >= ORDER_COUNT {
|
||||
0
|
||||
} else {
|
||||
available.min(bytes.len())
|
||||
};
|
||||
if n < bytes.len() {
|
||||
r.truncated = true;
|
||||
if r.limit.is_none() {
|
||||
r.limit = Some(if r.order.len() >= ORDER_COUNT {
|
||||
RetentionLimit::OrderQuota
|
||||
} else {
|
||||
RetentionLimit::ByteQuota
|
||||
});
|
||||
}
|
||||
}
|
||||
if n > 0 {
|
||||
match stream {
|
||||
CommandStream::Stdout => r.stdout.extend_from_slice(&bytes[..n]),
|
||||
CommandStream::Stderr => r.stderr.extend_from_slice(&bytes[..n]),
|
||||
}
|
||||
if let Some(last) = r
|
||||
.order
|
||||
.last_mut()
|
||||
.filter(|last| last.stream == stream && last.end == start)
|
||||
{
|
||||
last.end += n as u64;
|
||||
} else {
|
||||
r.order.push(OutputRange {
|
||||
stream,
|
||||
start,
|
||||
end: start + n as u64,
|
||||
});
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
pub fn finish_transport(
|
||||
&mut self,
|
||||
terminal: &workdir::CommandTerminal,
|
||||
) -> Result<BashOutputMetadata, String> {
|
||||
let mut r = self.record.lock().unwrap();
|
||||
if !terminal.metadata_valid()
|
||||
|| terminal.stdout_delivered_bytes != r.stdout_seen
|
||||
|| terminal.stderr_delivered_bytes != r.stderr_seen
|
||||
{
|
||||
return Err("command terminal counts do not fence delivered bytes".into());
|
||||
}
|
||||
r.transport_counts = Some((terminal.stdout_bytes, terminal.stderr_bytes));
|
||||
r.transport_truncation = terminal.truncation_reason.clone();
|
||||
r.terminal = Some(OutputTerminal {
|
||||
status: Some(terminal.status),
|
||||
exit_code: terminal.exit_code,
|
||||
transport_complete: matches!(
|
||||
terminal.output_collection,
|
||||
workdir::CommandOutputCollection::Complete
|
||||
),
|
||||
process_failure: terminal.process_failure,
|
||||
output_collection: Some(terminal.output_collection),
|
||||
});
|
||||
Ok(r.metadata())
|
||||
}
|
||||
|
||||
pub fn finish(&mut self, terminal: OutputTerminal) -> BashOutputMetadata {
|
||||
let mut r = self.record.lock().unwrap();
|
||||
r.terminal = Some(terminal);
|
||||
r.metadata()
|
||||
}
|
||||
}
|
||||
|
||||
impl Drop for BashOutputWriter {
|
||||
fn drop(&mut self) {
|
||||
let mut r = self.record.lock().unwrap();
|
||||
if r.terminal.is_none() {
|
||||
r.terminal = Some(OutputTerminal {
|
||||
status: None,
|
||||
exit_code: None,
|
||||
transport_complete: false,
|
||||
process_failure: None,
|
||||
output_collection: None,
|
||||
});
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
fn finish(view: &BashOutputView, text: &[u8]) -> String {
|
||||
let mut writer = view.begin().unwrap();
|
||||
writer.append(CommandStream::Stdout, text);
|
||||
writer
|
||||
.finish(OutputTerminal {
|
||||
status: Some(CommandStatus::Completed),
|
||||
exit_code: Some(0),
|
||||
transport_complete: true,
|
||||
process_failure: None,
|
||||
output_collection: Some(workdir::CommandOutputCollection::Complete),
|
||||
})
|
||||
.id
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn revoked_child_is_denied_while_parent_keeps_evidence_and_sibling_is_denied() {
|
||||
let root = BashOutputView::new();
|
||||
let lease = Arc::new(AtomicBool::new(true));
|
||||
let child = root.child({
|
||||
let lease = lease.clone();
|
||||
Arc::new(move || lease.load(Ordering::Acquire))
|
||||
});
|
||||
let sibling = root.child(Arc::new(|| true));
|
||||
let id = finish(&child, b"child");
|
||||
assert_eq!(
|
||||
child.read(&id, CommandStream::Stdout, 0, 20).unwrap(),
|
||||
b"child"
|
||||
);
|
||||
assert!(sibling.metadata(&id).is_none());
|
||||
assert!(BashOutputView::new().metadata(&id).is_none());
|
||||
lease.store(false, Ordering::Release);
|
||||
assert!(child.metadata(&id).is_none());
|
||||
assert_eq!(
|
||||
root.read(&id, CommandStream::Stdout, 0, 20).unwrap(),
|
||||
b"child"
|
||||
);
|
||||
root.revoke();
|
||||
let restored = BashOutputView::new();
|
||||
assert!(root.metadata(&id).is_none());
|
||||
assert!(restored.metadata(&id).is_none());
|
||||
let new_id = finish(&restored, b"new incarnation");
|
||||
assert_ne!(new_id, id);
|
||||
assert!(child.metadata(&new_id).is_none());
|
||||
assert!(root.begin().is_err());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn parent_and_descendants_share_admission_without_evicting_live_evidence() {
|
||||
let root = BashOutputView::new();
|
||||
let child = root.child(Arc::new(|| true));
|
||||
let sibling = root.child(Arc::new(|| true));
|
||||
let mut writers = (0..STORE_BYTES / COMMAND_BYTES)
|
||||
.map(|index| {
|
||||
if index % 2 == 0 {
|
||||
root.begin()
|
||||
} else {
|
||||
child.begin()
|
||||
}
|
||||
.unwrap()
|
||||
})
|
||||
.collect::<Vec<_>>();
|
||||
assert!(sibling.begin().is_err());
|
||||
let mut first = writers.remove(0);
|
||||
first.append(CommandStream::Stdout, b"finished");
|
||||
let metadata = first.finish(OutputTerminal {
|
||||
status: Some(CommandStatus::Completed),
|
||||
exit_code: Some(0),
|
||||
transport_complete: true,
|
||||
process_failure: None,
|
||||
output_collection: Some(workdir::CommandOutputCollection::Complete),
|
||||
});
|
||||
assert!(root.metadata(&metadata.id).is_some());
|
||||
let _replacement = sibling.begin().unwrap();
|
||||
assert!(root.metadata(&metadata.id).is_none());
|
||||
assert!(root.begin().is_err());
|
||||
assert_eq!(writers.len(), STORE_BYTES / COMMAND_BYTES - 1);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn quota_and_forced_drop_are_distinct_from_preview_omission() {
|
||||
let root = BashOutputView::new();
|
||||
let mut writer = root.begin().unwrap();
|
||||
writer.append(CommandStream::Stdout, &vec![b'x'; COMMAND_BYTES + 1]);
|
||||
writer.append(CommandStream::Stderr, b"tail");
|
||||
let id = writer.record.lock().unwrap().id.clone();
|
||||
drop(writer);
|
||||
let m = root.metadata(&id).unwrap();
|
||||
assert_eq!(m.stdout_saved, COMMAND_BYTES);
|
||||
assert_eq!(m.stdout_seen, COMMAND_BYTES as u64 + 1);
|
||||
assert_eq!(m.stderr_seen, 4);
|
||||
assert!(m.storage_truncated);
|
||||
assert!(!m.terminal.transport_complete);
|
||||
assert_eq!(
|
||||
root.read(&id, CommandStream::Stdout, 0, usize::MAX)
|
||||
.unwrap()
|
||||
.len(),
|
||||
64 * 1024
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn expiry_and_count_eviction_never_reuse_old_references() {
|
||||
let root = BashOutputView::new();
|
||||
let id = finish(&root, b"old");
|
||||
root.store.lock().unwrap().retention = Duration::ZERO;
|
||||
assert!(root.metadata(&id).is_none());
|
||||
root.store.lock().unwrap().retention = RETENTION;
|
||||
let first = finish(&root, b"first");
|
||||
for _ in 0..STORE_COUNT {
|
||||
finish(&root, b"later");
|
||||
}
|
||||
assert!(root.metadata(&first).is_none());
|
||||
assert!(root.store.lock().unwrap().reserved <= STORE_BYTES);
|
||||
}
|
||||
#[tokio::test(start_paused = true)]
|
||||
async fn expiry_reclaims_bytes_without_another_read_and_reaper_ends_with_owner() {
|
||||
// Exercise host construction outside a runtime, followed by real async admission.
|
||||
let root = std::thread::spawn(BashOutputView::new).join().unwrap();
|
||||
finish(&root, b"expires without lookup");
|
||||
let mut closed = root.store.lock().unwrap()._shutdown.subscribe();
|
||||
tokio::task::yield_now().await;
|
||||
// The store uses monotonic wall time for publication and Tokio time only for scheduling.
|
||||
// Age the record deterministically rather than delaying this test in real time.
|
||||
root.store.lock().unwrap().records[0]
|
||||
.lock()
|
||||
.unwrap()
|
||||
.created = Instant::now() - RETENTION;
|
||||
tokio::time::advance(Duration::from_secs(31)).await;
|
||||
tokio::task::yield_now().await;
|
||||
assert_eq!(root.store.lock().unwrap().reserved, 0);
|
||||
drop(root);
|
||||
assert!(closed.changed().await.is_err());
|
||||
}
|
||||
#[test]
|
||||
fn terminal_counts_must_fence_the_received_prefix_before_marking_evidence_complete() {
|
||||
let root = BashOutputView::new();
|
||||
let mut writer = root.begin().unwrap();
|
||||
writer.append(CommandStream::Stdout, b"abc");
|
||||
let mut terminal = serde_json::json!({"status":"completed","exit_code":0,"process_failure":null,"output_collection":{"state":"complete"},"stdout_bytes":9,"stderr_bytes":0,"stdout_delivered_bytes":4,"stderr_delivered_bytes":0,"truncation_reason":"byte_budget"});
|
||||
assert!(
|
||||
writer
|
||||
.finish_transport(&serde_json::from_value(terminal.clone()).unwrap())
|
||||
.is_err()
|
||||
);
|
||||
terminal["stdout_delivered_bytes"] = serde_json::json!(3);
|
||||
let metadata = writer
|
||||
.finish_transport(&serde_json::from_value(terminal).unwrap())
|
||||
.unwrap();
|
||||
assert_eq!(metadata.stdout_saved, 3);
|
||||
assert_eq!(metadata.stdout_delivered, 3);
|
||||
assert_eq!(metadata.stdout_seen, 9);
|
||||
assert!(metadata.storage_truncated);
|
||||
assert!(metadata.retention_limit.is_none());
|
||||
assert_eq!(
|
||||
metadata.transport_truncation,
|
||||
Some(workdir::CommandOutputTruncation::ByteBudget)
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn incomplete_collection_with_quota_retains_both_causes_without_claiming_complete_output() {
|
||||
let root = BashOutputView::new();
|
||||
let mut writer = root.begin().unwrap();
|
||||
writer.append(CommandStream::Stdout, b"abc");
|
||||
let terminal: workdir::CommandTerminal = serde_json::from_value(serde_json::json!({
|
||||
"status":"completed", "exit_code":0, "process_failure":null,
|
||||
"output_collection":{"state":"incomplete","failure":{"stage":"stdout_drain","reason":"other","os_code":null}},
|
||||
"stdout_bytes":9, "stderr_bytes":0, "stdout_delivered_bytes":3, "stderr_delivered_bytes":0,
|
||||
"truncation_reason":"byte_budget"
|
||||
})).unwrap();
|
||||
let metadata = writer.finish_transport(&terminal).unwrap();
|
||||
assert!(!metadata.terminal.transport_complete);
|
||||
assert_eq!(metadata.terminal.exit_code, Some(0));
|
||||
assert_eq!(
|
||||
metadata.terminal.output_collection,
|
||||
Some(terminal.output_collection)
|
||||
);
|
||||
assert_eq!(
|
||||
metadata.transport_truncation,
|
||||
Some(workdir::CommandOutputTruncation::ByteBudget)
|
||||
);
|
||||
assert_eq!(metadata.stdout_seen, 9);
|
||||
assert_eq!(metadata.stdout_saved, 3);
|
||||
assert!(metadata.storage_truncated);
|
||||
assert!(metadata.retention_limit.is_none());
|
||||
assert_eq!(
|
||||
root.read(&metadata.id, CommandStream::Stdout, 0, 100)
|
||||
.unwrap(),
|
||||
b"abc"
|
||||
);
|
||||
assert_eq!(
|
||||
serde_json::to_value(root.metadata(&metadata.id).unwrap()).unwrap(),
|
||||
serde_json::to_value(metadata).unwrap()
|
||||
);
|
||||
}
|
||||
}
|
||||
@@ -403,3 +403,71 @@ fn check_pattern(pattern: &str) -> Result<(), ToolError> {
|
||||
#[cfg(test)]
|
||||
#[path = "checkout_tests.rs"]
|
||||
mod tests;
|
||||
|
||||
/// Read a bounded native text window through the same checked target.
|
||||
/// The returned one-shot action records prior-Read only after the caller's presentation succeeds.
|
||||
#[allow(clippy::too_many_arguments)]
|
||||
pub async fn read_checkout_text(
|
||||
router: Arc<WorkdirSessionRouter>,
|
||||
tracker: Tracker,
|
||||
alias: &str,
|
||||
generation: u64,
|
||||
path: WorkdirPath,
|
||||
validator: Vec<u8>,
|
||||
offset: usize,
|
||||
limit: usize,
|
||||
max_bytes: usize,
|
||||
) -> Result<(workdir::ReadResult, Option<Vec<u8>>, impl FnOnce()), ToolError> {
|
||||
let selected =
|
||||
crate::routing::resolve_session(&router, Some(alias), WorkdirSessionCapability::Read)?;
|
||||
if selected.generation != generation {
|
||||
return Err(stale_checkout("checkout connection changed"));
|
||||
}
|
||||
let tracker = tracker.scoped_attachment(&selected.alias, selected.generation);
|
||||
let target = FileTarget {
|
||||
session: selected.session.clone(),
|
||||
path: path.clone(),
|
||||
validator: Some(validator),
|
||||
};
|
||||
let (result, validator) = target.read(offset, limit, max_bytes).await?;
|
||||
let hash = result.content_hash.clone();
|
||||
let total_lines = result.total_lines;
|
||||
Ok((result, validator, move || {
|
||||
tracker.record_workdir_observation(&path, hash, total_lines);
|
||||
}))
|
||||
}
|
||||
|
||||
/// Binary-safe checked byte window. This does not establish a text prior-Read observation.
|
||||
#[allow(clippy::too_many_arguments)]
|
||||
pub async fn read_checkout_bytes(
|
||||
router: Arc<WorkdirSessionRouter>,
|
||||
alias: &str,
|
||||
generation: u64,
|
||||
path: WorkdirPath,
|
||||
validator: Vec<u8>,
|
||||
offset: u64,
|
||||
max_bytes: usize,
|
||||
) -> Result<(workdir::ReadBytesResult, Vec<u8>), ToolError> {
|
||||
let selected =
|
||||
crate::routing::resolve_session(&router, Some(alias), WorkdirSessionCapability::Read)?;
|
||||
if selected.generation != generation {
|
||||
return Err(stale_checkout("checkout connection changed"));
|
||||
}
|
||||
let result = selected
|
||||
.session
|
||||
.checkout_execute(workdir::CheckoutRequest {
|
||||
target: path.clone(),
|
||||
validator,
|
||||
operation: workdir::CheckoutOperation::ReadBytes { offset, max_bytes },
|
||||
})
|
||||
.await
|
||||
.map_err(crate::file_target::checked_error)?;
|
||||
match result.output {
|
||||
workdir::CheckoutOutput::ReadBytes(read)
|
||||
if read.path == path && read.offset == offset && read.bytes.len() <= max_bytes =>
|
||||
{
|
||||
Ok((read, result.observation.validator))
|
||||
}
|
||||
_ => Err(crate::file_target::readonly_result_error("ReadBytes")),
|
||||
}
|
||||
}
|
||||
|
||||
@@ -21,7 +21,7 @@ pub(crate) struct EditParams {
|
||||
/// Worker-local alias of the Workdir attachment to use.
|
||||
#[serde(default)]
|
||||
pub target_workdir: Option<String>,
|
||||
/// Logical path relative to the bound Workdir root.
|
||||
/// Existing file in which to replace text.
|
||||
pub file_path: String,
|
||||
#[serde(flatten)]
|
||||
pub edit: fs_operation::text::EditArgs,
|
||||
|
||||
@@ -147,7 +147,9 @@ impl FileTarget {
|
||||
pub(crate) fn checked_error(error: workdir::WorkdirError) -> ToolError {
|
||||
use workdir::WorkdirError;
|
||||
let code = match error.classification_source() {
|
||||
WorkdirError::DenialContext { .. } => unreachable!("diagnostic context unwrapped"),
|
||||
WorkdirError::DenialContext { .. } | WorkdirError::FailureContext { .. } => {
|
||||
unreachable!("diagnostic context unwrapped")
|
||||
}
|
||||
WorkdirError::Conflict(_) | WorkdirError::NotFound(_) => "checkout_stale",
|
||||
WorkdirError::Denied { .. }
|
||||
| WorkdirError::OutOfScope { .. }
|
||||
@@ -165,6 +167,7 @@ pub(crate) fn checked_error(error: workdir::WorkdirError) -> ToolError {
|
||||
| WorkdirError::IsDirectory { .. }
|
||||
| WorkdirError::InvalidGlob { .. }
|
||||
| WorkdirError::InvalidRegex { .. } => "checkout_invalid",
|
||||
WorkdirError::NotDispatched => "checkout_not_dispatched",
|
||||
WorkdirError::Unavailable { .. } | WorkdirError::SessionClosed => "checkout_unavailable",
|
||||
// IO/transport failures may arrive after effects have begun. Do not infer
|
||||
// no-effects from their text or strip explicit OutcomeUnknown evidence.
|
||||
|
||||
@@ -17,7 +17,7 @@ pub(crate) struct GlobParams {
|
||||
pub target_workdir: Option<String>,
|
||||
/// Glob pattern, for example `**/*.rs` or `src/**/test_*.py`.
|
||||
pub pattern: String,
|
||||
/// Logical Workdir-relative directory. Defaults to the Workdir root.
|
||||
/// Directory to search. Defaults to `.`.
|
||||
#[serde(default)]
|
||||
pub path: Option<String>,
|
||||
}
|
||||
@@ -106,7 +106,7 @@ pub(crate) fn routed_glob_tool(router: Arc<WorkdirSessionRouter>) -> ToolDefinit
|
||||
Arc::new(move || {
|
||||
let schema = schemars::schema_for!(GlobParams);
|
||||
let meta = ToolMeta::new("Glob")
|
||||
.description("Find files matching a glob pattern inside the selected Workdir. Results are sorted and capped at 1000 entries. Paths are Workdir-relative.")
|
||||
.description("Find files matching a glob pattern inside the selected Workdir. Results are sorted and capped at 1000 entries.")
|
||||
.input_schema(serde_json::to_value(schema).expect("Glob schema serialization"));
|
||||
let tool: Arc<dyn Tool> = Arc::new(GlobTool {
|
||||
router: router.clone(),
|
||||
|
||||
@@ -27,7 +27,7 @@ pub(crate) struct GrepParams {
|
||||
#[serde(default)]
|
||||
target_workdir: Option<String>,
|
||||
pattern: String,
|
||||
/// Workdir-relative path, or an absolute path covered by readable scope. Defaults to the Workdir root.
|
||||
/// File or directory to search. Defaults to `.`.
|
||||
#[serde(default)]
|
||||
pub path: Option<String>,
|
||||
#[serde(default)]
|
||||
@@ -160,7 +160,7 @@ pub(crate) fn routed_grep_tool(router: Arc<WorkdirSessionRouter>) -> ToolDefinit
|
||||
Arc::new(move || {
|
||||
let schema = schemars::schema_for!(GrepParams);
|
||||
let meta = ToolMeta::new("Grep")
|
||||
.description("Search a file or directory in the selected Workdir with a regex. Content results group lines by file; `>` marks matching lines and unmarked lines are context. Directory traversal executes inside the WorkdirSession provider. Results are bounded and Workdir-relative.")
|
||||
.description("Search a file or directory in the selected Workdir with a regex. Content results group lines by file; `>` marks matching lines and unmarked lines are context. Directory traversal executes inside the WorkdirSession provider. Results are bounded.")
|
||||
.input_schema(serde_json::to_value(schema).expect("Grep schema serialization"));
|
||||
let tool: Arc<dyn Tool> = Arc::new(GrepTool {
|
||||
router: router.clone(),
|
||||
|
||||
+10
-9
@@ -5,6 +5,7 @@ pub mod error;
|
||||
pub mod tracker;
|
||||
|
||||
mod bash;
|
||||
pub mod bash_output;
|
||||
mod edit;
|
||||
mod file_target;
|
||||
mod glob;
|
||||
@@ -16,7 +17,7 @@ pub mod view_image;
|
||||
mod web;
|
||||
mod write;
|
||||
|
||||
pub use bash::bash_tool;
|
||||
pub use bash::{BashResult, BashTool, bash_tool};
|
||||
pub use checkout::{CheckoutToolOutput, execute_checkout_tool};
|
||||
pub use edit::edit_tool;
|
||||
pub use error::ToolsError;
|
||||
@@ -35,7 +36,7 @@ pub use write::write_tool;
|
||||
pub fn core_builtin_tools(
|
||||
session: workdir::WorkdirSessionHandle,
|
||||
tracker: Tracker,
|
||||
bash_output_dir: std::path::PathBuf,
|
||||
bash_output: bash_output::BashOutputView,
|
||||
) -> Vec<agen::tool::ToolDefinition> {
|
||||
use workdir::WorkdirSessionCapability;
|
||||
|
||||
@@ -58,7 +59,7 @@ pub fn core_builtin_tools(
|
||||
tools.push(grep::routed_grep_tool(router.clone()));
|
||||
}
|
||||
if capabilities.supports(WorkdirSessionCapability::Command) {
|
||||
tools.push(bash::routed_bash_tool(router, bash_output_dir));
|
||||
tools.push(bash::routed_bash_tool(router, bash_output));
|
||||
}
|
||||
tools
|
||||
}
|
||||
@@ -71,7 +72,7 @@ pub fn core_builtin_tools(
|
||||
pub fn routed_builtin_tools(
|
||||
router: std::sync::Arc<workdir::WorkdirSessionRouter>,
|
||||
tracker: Tracker,
|
||||
bash_output_dir: std::path::PathBuf,
|
||||
bash_output: bash_output::BashOutputView,
|
||||
) -> Vec<agen::tool::ToolDefinition> {
|
||||
vec![
|
||||
read::routed_read_tool(router.clone(), tracker.clone()),
|
||||
@@ -79,14 +80,14 @@ pub fn routed_builtin_tools(
|
||||
edit::routed_edit_tool(router.clone(), tracker),
|
||||
glob::routed_glob_tool(router.clone()),
|
||||
grep::routed_grep_tool(router.clone()),
|
||||
bash::routed_bash_tool(router, bash_output_dir),
|
||||
bash::routed_bash_tool(router, bash_output),
|
||||
]
|
||||
}
|
||||
|
||||
pub fn routed_builtin_tools_for_current_capabilities(
|
||||
router: std::sync::Arc<workdir::WorkdirSessionRouter>,
|
||||
tracker: Tracker,
|
||||
bash_output_dir: std::path::PathBuf,
|
||||
bash_output: bash_output::BashOutputView,
|
||||
) -> Vec<agen::tool::ToolDefinition> {
|
||||
use workdir::WorkdirSessionCapability;
|
||||
|
||||
@@ -108,7 +109,7 @@ pub fn routed_builtin_tools_for_current_capabilities(
|
||||
tools.push(grep::routed_grep_tool(router.clone()));
|
||||
}
|
||||
if capabilities.supports(WorkdirSessionCapability::Command) {
|
||||
tools.push(bash::routed_bash_tool(router, bash_output_dir));
|
||||
tools.push(bash::routed_bash_tool(router, bash_output));
|
||||
}
|
||||
tools
|
||||
}
|
||||
@@ -121,7 +122,7 @@ pub fn read_only_builtin_tools(
|
||||
workdir::WorkdirSessionCapabilities::READ_ONLY,
|
||||
"read-only tool projection requires a read-only Workdir session"
|
||||
);
|
||||
core_builtin_tools(session, Tracker::new(), std::path::PathBuf::new())
|
||||
core_builtin_tools(session, Tracker::new(), bash_output::BashOutputView::new())
|
||||
}
|
||||
|
||||
pub fn read_only_routed_builtin_tools(
|
||||
@@ -173,7 +174,7 @@ mod workdir_tool_tests {
|
||||
SharedScope::new(Scope::writable(dir.path()).unwrap()),
|
||||
WorkdirSessionCapabilities::READ_ONLY,
|
||||
));
|
||||
let names = core_builtin_tools(session, Tracker::new(), dir.path().join("output"))
|
||||
let names = core_builtin_tools(session, Tracker::new(), bash_output::BashOutputView::new())
|
||||
.into_iter()
|
||||
.map(|definition| definition().0.name)
|
||||
.collect::<Vec<_>>();
|
||||
|
||||
@@ -13,7 +13,7 @@ use workdir::{WorkdirPath, WorkdirSessionHandle, WorkdirSessionRouter};
|
||||
const DESCRIPTION: &str = "Read a text file from a Workdir attachment selected by its Worker-local alias. \
|
||||
Supports offset/limit for large files. Returns line-numbered output (1-based). \
|
||||
Directories cannot be read. The file must be read before Write or Edit can \
|
||||
modify it. Paths are Workdir-relative unless an absolute path is explicitly readable. \
|
||||
modify it. \
|
||||
When exactly one Workdir is attached, target_workdir may be omitted.";
|
||||
|
||||
const DEFAULT_LIMIT: usize = 2000;
|
||||
@@ -24,7 +24,7 @@ pub(crate) struct ReadParams {
|
||||
/// Worker-local alias of the Workdir attachment to use.
|
||||
#[serde(default)]
|
||||
pub target_workdir: Option<String>,
|
||||
/// Workdir-relative path, or an absolute path covered by readable scope.
|
||||
/// Text file to read; directories are not supported.
|
||||
pub file_path: String,
|
||||
#[serde(flatten)]
|
||||
pub read: fs_operation::text::LineReadArgs,
|
||||
|
||||
@@ -20,7 +20,7 @@ pub const MAX_IMAGE_BYTES: usize = 10 * 1024 * 1024;
|
||||
const IMAGE_READ_CHUNK_BYTES: usize = 1024 * 1024;
|
||||
|
||||
const DESCRIPTION: &str = "Attach an image from the selected Workdir attachment to the next model request. \
|
||||
The path must be logical and Workdir-relative. Supported formats: PNG, JPEG, GIF, and WebP. \
|
||||
Supported formats: PNG, JPEG, GIF, and WebP. \
|
||||
When exactly one Workdir is attached, target_workdir may be omitted.";
|
||||
|
||||
#[derive(Debug, Deserialize, schemars::JsonSchema)]
|
||||
@@ -28,7 +28,7 @@ struct ViewImageParams {
|
||||
/// Worker-local alias of the Workdir attachment to use.
|
||||
#[serde(default)]
|
||||
target_workdir: Option<String>,
|
||||
/// Logical path relative to the bound Workdir root.
|
||||
/// Image file to attach to the next model request.
|
||||
path: String,
|
||||
}
|
||||
|
||||
@@ -360,10 +360,52 @@ mod tests {
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn bounded_binary_read_accepts_arbitrary_bytes_at_caller_limit_and_rejects_larger_files()
|
||||
{
|
||||
async fn bounded_binary_read_accepts_caller_limits_above_the_image_tool_limit() {
|
||||
// The caller's limit is a reader policy, not a LocalWorkdir storage contract.
|
||||
// Supply immutable chunks here; the separate component case exercises the
|
||||
// real provider across a chunk boundary without repeatedly hashing 16 MiB.
|
||||
let dir = TempDir::new().unwrap();
|
||||
let bytes = vec![0xff; 16 * 1024 * 1024];
|
||||
let hash = Sha256::digest(&bytes).into();
|
||||
let responses = bytes
|
||||
.chunks(IMAGE_READ_CHUNK_BYTES)
|
||||
.enumerate()
|
||||
.map(|(index, bytes)| {
|
||||
chunk(
|
||||
bytes,
|
||||
(index * IMAGE_READ_CHUNK_BYTES) as u64,
|
||||
16 * 1024 * 1024,
|
||||
hash,
|
||||
)
|
||||
})
|
||||
.collect();
|
||||
let session = binary_session(&dir, responses);
|
||||
let path = WorkdirPath::new("artifact.bin").unwrap();
|
||||
assert_eq!(
|
||||
read_workdir_bytes(&session, path.clone(), bytes.len())
|
||||
.await
|
||||
.unwrap(),
|
||||
bytes
|
||||
);
|
||||
let session = binary_session(
|
||||
&dir,
|
||||
vec![chunk(
|
||||
&bytes[..IMAGE_READ_CHUNK_BYTES],
|
||||
0,
|
||||
bytes.len() as u64,
|
||||
hash,
|
||||
)],
|
||||
);
|
||||
assert!(matches!(
|
||||
read_workdir_bytes(&session, path, bytes.len() - 1).await,
|
||||
Err(WorkdirError::InvalidArgument(_))
|
||||
));
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn bounded_binary_read_reassembles_provider_chunks_and_enforces_the_caller_limit() {
|
||||
let dir = TempDir::new().unwrap();
|
||||
let bytes = vec![0xff; IMAGE_READ_CHUNK_BYTES + 1];
|
||||
std::fs::write(dir.path().join("artifact.bin"), &bytes).unwrap();
|
||||
let session =
|
||||
LocalWorkdirSession::new(Scope::writable(dir.path()).unwrap(), dir.path().into());
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user