Compare commits
99
Commits
adfa422973
...
develop
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
897c025b85 | ||
|
|
6776973e4c | ||
|
|
994e75233b | ||
|
|
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 |
Generated
+10
-2
@@ -3990,6 +3990,7 @@ dependencies = [
|
||||
"protocol",
|
||||
"serde",
|
||||
"serde_json",
|
||||
"session-store",
|
||||
"tokio",
|
||||
"workdir",
|
||||
]
|
||||
@@ -4783,12 +4784,14 @@ version = "0.1.0"
|
||||
dependencies = [
|
||||
"chrono",
|
||||
"feature-storage",
|
||||
"job",
|
||||
"manifest",
|
||||
"memory",
|
||||
"rusqlite",
|
||||
"serde",
|
||||
"serde_json",
|
||||
"server-api",
|
||||
"session-store",
|
||||
"sha2 0.11.0",
|
||||
"tempfile",
|
||||
"thiserror 2.0.18",
|
||||
@@ -5266,6 +5269,7 @@ dependencies = [
|
||||
"thiserror 2.0.18",
|
||||
"tokio",
|
||||
"tracing",
|
||||
"uuid",
|
||||
"workdir",
|
||||
]
|
||||
|
||||
@@ -6496,6 +6500,7 @@ name = "workdir"
|
||||
version = "0.1.0"
|
||||
dependencies = [
|
||||
"async-trait",
|
||||
"axum",
|
||||
"fs-operation",
|
||||
"libc",
|
||||
"manifest",
|
||||
@@ -6519,7 +6524,6 @@ dependencies = [
|
||||
"axum",
|
||||
"base64 0.22.1",
|
||||
"chrono",
|
||||
"clap",
|
||||
"client",
|
||||
"config-source",
|
||||
"dotenv",
|
||||
@@ -6557,6 +6561,7 @@ dependencies = [
|
||||
"toml",
|
||||
"tools",
|
||||
"tracing",
|
||||
"tracing-subscriber",
|
||||
"tungstenite 0.28.0",
|
||||
"uuid",
|
||||
"wip-client",
|
||||
@@ -6596,6 +6601,7 @@ dependencies = [
|
||||
"tokio",
|
||||
"tokio-tungstenite 0.29.0",
|
||||
"toml",
|
||||
"tools",
|
||||
"tower",
|
||||
"tracing",
|
||||
"tracing-subscriber",
|
||||
@@ -6683,6 +6689,7 @@ dependencies = [
|
||||
"futures",
|
||||
"manifest",
|
||||
"project-record",
|
||||
"protocol",
|
||||
"reqwest",
|
||||
"serde",
|
||||
"serde_json",
|
||||
@@ -6698,13 +6705,13 @@ dependencies = [
|
||||
"tui",
|
||||
"uuid",
|
||||
"workdir",
|
||||
"worker",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "yoi-e2e"
|
||||
version = "0.0.0"
|
||||
dependencies = [
|
||||
"chrono",
|
||||
"libc",
|
||||
"reqwest",
|
||||
"serde",
|
||||
@@ -6714,6 +6721,7 @@ dependencies = [
|
||||
"tempfile",
|
||||
"webauthn-authenticator-rs",
|
||||
"webauthn-rs-proto",
|
||||
"yoi-workspace-server",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
|
||||
@@ -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")
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
+27
-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.
|
||||
@@ -2621,6 +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,
|
||||
|
||||
@@ -17,12 +17,12 @@ use crate::{
|
||||
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,
|
||||
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,
|
||||
@@ -117,6 +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);
|
||||
|
||||
@@ -9,6 +9,7 @@ license.workspace = true
|
||||
api-macros = { workspace = true, features = ["reqwest", "axum"] }
|
||||
manifest.workspace = true
|
||||
protocol.workspace = true
|
||||
session-store.workspace = true
|
||||
serde = { workspace = true, features = ["derive"] }
|
||||
workdir.workspace = true
|
||||
|
||||
|
||||
@@ -518,9 +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>,
|
||||
}
|
||||
@@ -835,6 +836,34 @@ pub struct SessionMaterialPinResponse {
|
||||
pub pin_id: String,
|
||||
}
|
||||
|
||||
/// One body-bearing immutable slice. The byte budget includes slice metadata,
|
||||
/// but not the enclosing availability enum or the caller's durable Job envelope.
|
||||
#[derive(Clone, Debug, Serialize, Deserialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct SessionRecordingCaptureRequest {
|
||||
pub workspace_id: String,
|
||||
pub source: SessionPublicSource,
|
||||
pub expected_session_id: String,
|
||||
pub start: session_store::capture::RecordingPosition,
|
||||
pub max_entries: usize,
|
||||
pub max_serialized_bytes: usize,
|
||||
}
|
||||
|
||||
#[derive(Clone, Debug, Serialize, Deserialize)]
|
||||
#[serde(tag = "availability", rename_all = "snake_case")]
|
||||
pub enum SessionRecordingCaptureAvailability {
|
||||
NotMaterialized {
|
||||
session_id: String,
|
||||
},
|
||||
Captured {
|
||||
slice: session_store::capture::RecordingCaptureSlice,
|
||||
},
|
||||
Unavailable {
|
||||
reason: SessionPublicUnavailableReason,
|
||||
message: String,
|
||||
},
|
||||
}
|
||||
|
||||
#[derive(Clone, Debug, Serialize, Deserialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct SessionMaterialCatalogRequest {
|
||||
@@ -1140,8 +1169,36 @@ pub struct SubjectReleaseResponse {
|
||||
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,
|
||||
@@ -1217,6 +1274,16 @@ pub trait RuntimeApi {
|
||||
#[body] request: SessionMaterialPinRequest,
|
||||
) -> Result<SessionMaterialPinResponse, RuntimeApiError>;
|
||||
|
||||
#[post(
|
||||
"/v1/session-public/recording-capture",
|
||||
status = 200,
|
||||
error_status = 400
|
||||
)]
|
||||
async fn session_recording_capture(
|
||||
&self,
|
||||
#[body] request: SessionRecordingCaptureRequest,
|
||||
) -> Result<SessionRecordingCaptureAvailability, RuntimeApiError>;
|
||||
|
||||
#[post(
|
||||
"/v1/session-public/material/catalog",
|
||||
status = 200,
|
||||
@@ -1675,6 +1742,18 @@ mod tests {
|
||||
) -> 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,
|
||||
@@ -1689,6 +1768,13 @@ mod tests {
|
||||
Err(test_error(501))
|
||||
}
|
||||
|
||||
async fn session_recording_capture(
|
||||
&self,
|
||||
_request: SessionRecordingCaptureRequest,
|
||||
) -> Result<SessionRecordingCaptureAvailability, RuntimeApiError> {
|
||||
Err(test_error(501))
|
||||
}
|
||||
|
||||
async fn session_material_catalog(
|
||||
&self,
|
||||
_request: SessionMaterialCatalogRequest,
|
||||
@@ -1820,6 +1906,21 @@ 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
|
||||
|
||||
@@ -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),
|
||||
|
||||
@@ -6,6 +6,7 @@ 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::*;
|
||||
@@ -23,6 +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);
|
||||
@@ -96,6 +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.
|
||||
@@ -103,6 +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
|
||||
@@ -125,9 +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,
|
||||
}
|
||||
}
|
||||
|
||||
@@ -138,9 +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,
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -168,6 +205,11 @@ macro_rules! impl_openapi_schema {
|
||||
}
|
||||
|
||||
impl_openapi_schema!(
|
||||
SubjectPermissionsResponse,
|
||||
SubjectPermissionsMutationResponse,
|
||||
SubjectPermissionInterruption,
|
||||
authorization::SubjectPermissions,
|
||||
authorization::SubjectPermissionsUpdate,
|
||||
AuthBootstrapUserRequest,
|
||||
AuthPublicConfig,
|
||||
HostingSettings,
|
||||
@@ -1298,6 +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,
|
||||
@@ -2762,6 +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,
|
||||
@@ -4025,6 +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)]
|
||||
@@ -7410,6 +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,
|
||||
}
|
||||
|
||||
@@ -7422,7 +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))]
|
||||
@@ -10428,6 +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)]
|
||||
@@ -11533,6 +11646,7 @@ pub fn auth_api_typescript() -> String {
|
||||
ActorAuthMethod::decl(&config),
|
||||
AuthenticatedUser::decl(&config),
|
||||
RequestActor::decl(&config),
|
||||
BrowserSessionState::decl(&config),
|
||||
WhoamiResponse::decl(&config),
|
||||
AuthBootstrapUserRequest::decl(&config),
|
||||
AuthUserResponse::decl(&config),
|
||||
@@ -12929,6 +13043,7 @@ mod tests {
|
||||
workdir_attachments: Vec::new(),
|
||||
feature_connections: Default::default(),
|
||||
control_operation_id: None,
|
||||
execution_grant: None,
|
||||
})
|
||||
.unwrap();
|
||||
assert_eq!(
|
||||
@@ -12943,6 +13058,7 @@ mod tests {
|
||||
"workdir_attachments": [],
|
||||
"feature_connections": {},
|
||||
"control_operation_id": null,
|
||||
"execution_grant": null,
|
||||
})
|
||||
);
|
||||
}
|
||||
@@ -13173,6 +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();
|
||||
@@ -13961,7 +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");
|
||||
@@ -14143,11 +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 {
|
||||
@@ -14532,6 +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",
|
||||
@@ -14917,10 +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(),
|
||||
@@ -14934,10 +15080,12 @@ 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());
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -11,5 +11,7 @@ checks or Runtime catalog lifecycle management.
|
||||
- [`worker_session_store`]: storage boundary for a Session bound to a Worker
|
||||
- [`worker_metadata`]: current Worker state and active Segment switching
|
||||
- [`system_item`]: records of system input presented to the model
|
||||
- [`capture`]: Worker-independent immutable public values and bounded body transport;
|
||||
authorization, source I/O, and delivery lifecycle stay with the Host
|
||||
- [`public_snapshot`] / [`public_index`]: public projections of stored history
|
||||
- [`event_trace`]: diagnostic records independent of history replay
|
||||
|
||||
@@ -0,0 +1,967 @@
|
||||
//! Exploration domain for immutable Session captures, with no Workspace/Memory mutation capability.
|
||||
//!
|
||||
//! A capture is an ordered projection of committed entries; exploration excludes reasoning and
|
||||
//! system prompts, including Host compaction summaries and other derived context. Full inherited
|
||||
//! summary input belongs to compaction, not public observation or Memory evidence. Overview,
|
||||
//! search, bounded reads, and evidence conversion share `SessionEntryRef`.
|
||||
//! `SessionEntryRef` is a contextual UI reference. `ScopedSessionEntryRef` additionally binds
|
||||
//! the Session and exact immutable capture, and is required for portable checked operations.
|
||||
//! Appends preserve existing entry identities. Sparse real user/assistant anchors and intervening
|
||||
//! entry counts index long histories. Search with an empty filter also provides bounded range lists.
|
||||
//!
|
||||
//! Host-fixed snapshot exploration, Memory candidate evidence validation, and current Worker
|
||||
//! observation share only this domain; they do not enable or modify each other's Features.
|
||||
//! The provider owns authorization to recapture a current Worker. A capture itself proves neither
|
||||
//! completion nor approval and grants no business-mutation authority.
|
||||
//!
|
||||
//! Recording Hosts use the common committed replay through the guarded APIs below.
|
||||
//! [`recording_catalog_worker_guarded`] and [`recording_catalog_fs_guarded`] expose
|
||||
//! descriptors only to an admission callback under the caller's existing publication/
|
||||
//! erasure guard and persisted active selector, without allocating a full body DTO.
|
||||
//! [`capture_recording_slice_worker_guarded`] and [`capture_recording_slice_fs_guarded`]
|
||||
//! separately construct bounded body-bearing inputs. Admission descriptors are not
|
||||
//! sufficient Job inputs; saved recording DTOs are read/sliced without live storage.
|
||||
|
||||
use std::sync::Arc;
|
||||
|
||||
use crate::{
|
||||
LoggedSessionHistoryMetadata as SessionHistoryMetadata,
|
||||
LoggedSessionHistoryOrigin as HistoryOrigin,
|
||||
};
|
||||
mod body;
|
||||
mod recording;
|
||||
use agen::{HistoryEntry, Item, Role};
|
||||
pub use body::*;
|
||||
use protocol::{
|
||||
SessionContentPart, SessionEntryProvenance, SessionMessageRole, SessionSnapshot,
|
||||
SessionSnapshotEntryData,
|
||||
};
|
||||
pub use recording::*;
|
||||
use serde::{Deserialize, Serialize};
|
||||
|
||||
const DEFAULT_SEARCH_LIMIT: usize = 20;
|
||||
const MAX_SEARCH_LIMIT: usize = 50;
|
||||
const DEFAULT_READ_MAX_ITEMS: usize = 40;
|
||||
const MAX_READ_MAX_ITEMS: usize = 80;
|
||||
const DEFAULT_READ_MAX_BYTES: usize = 32 * 1024;
|
||||
const OVERVIEW_ANCHOR_STRIDE: usize = 8;
|
||||
|
||||
/// Append-stable contextual UI reference derived from a logical entry identity.
|
||||
/// Portable consumers must bind it with `SessionCapture::scoped_ref` before use.
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Hash, Serialize, Deserialize)]
|
||||
#[serde(transparent)]
|
||||
pub struct SessionEntryRef(String);
|
||||
|
||||
impl SessionEntryRef {
|
||||
pub fn from_history_entry_id(entry_id: &crate::LoggedSessionHistoryEntryId) -> Self {
|
||||
Self(format!("E{}", entry_id.0))
|
||||
}
|
||||
|
||||
pub fn parse(value: &str) -> Option<Self> {
|
||||
let suffix = value.strip_prefix('E')?;
|
||||
if suffix.is_empty()
|
||||
// Legacy Host boundary identities contain both Session and Segment UUIDs.
|
||||
|| suffix.len() > 256
|
||||
|| !suffix
|
||||
.bytes()
|
||||
.all(|byte| byte.is_ascii_alphanumeric() || byte == b'-')
|
||||
{
|
||||
return None;
|
||||
}
|
||||
Some(Self(value.to_string()))
|
||||
}
|
||||
|
||||
pub fn as_str(&self) -> &str {
|
||||
&self.0
|
||||
}
|
||||
}
|
||||
|
||||
impl std::fmt::Display for SessionEntryRef {
|
||||
fn fmt(&self, formatter: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
|
||||
formatter.write_str(&self.0)
|
||||
}
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
|
||||
pub enum ReferenceKind {
|
||||
User,
|
||||
Assistant,
|
||||
System,
|
||||
Tool,
|
||||
}
|
||||
|
||||
impl ReferenceKind {
|
||||
pub fn as_str(self) -> &'static str {
|
||||
match self {
|
||||
Self::User => "user",
|
||||
Self::Assistant => "assistant",
|
||||
Self::System => "system",
|
||||
Self::Tool => "tool",
|
||||
}
|
||||
}
|
||||
|
||||
pub fn parse(value: &str) -> Option<Self> {
|
||||
match value {
|
||||
"user" => Some(Self::User),
|
||||
"assistant" | "agent" => Some(Self::Assistant),
|
||||
"system" => Some(Self::System),
|
||||
"tool" => Some(Self::Tool),
|
||||
_ => None,
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
|
||||
pub enum ToolPart {
|
||||
Input,
|
||||
Output,
|
||||
Both,
|
||||
}
|
||||
|
||||
impl ToolPart {
|
||||
pub fn parse(value: &str) -> Option<Self> {
|
||||
match value {
|
||||
"input" => Some(Self::Input),
|
||||
"output" => Some(Self::Output),
|
||||
"both" => Some(Self::Both),
|
||||
_ => None,
|
||||
}
|
||||
}
|
||||
|
||||
pub fn as_str(self) -> &'static str {
|
||||
match self {
|
||||
Self::Input => "input",
|
||||
Self::Output => "output",
|
||||
Self::Both => "both",
|
||||
}
|
||||
}
|
||||
|
||||
pub fn matches(self, actual: ToolPart) -> bool {
|
||||
matches!(self, ToolPart::Both) || self == actual
|
||||
}
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone)]
|
||||
pub struct OverviewItem {
|
||||
pub id: SessionEntryRef,
|
||||
pub origin: SessionEntryProvenance,
|
||||
pub entry_range: [u64; 2],
|
||||
pub kind: ReferenceKind,
|
||||
pub label: String,
|
||||
pub text: String,
|
||||
pub intervening_entries: usize,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone)]
|
||||
pub struct ReferenceEntry {
|
||||
pub attachment_count: usize,
|
||||
use_policy: Option<protocol::SessionEntryUsePolicy>,
|
||||
pub id: SessionEntryRef,
|
||||
pub origin: SessionEntryProvenance,
|
||||
pub entry_range: [u64; 2],
|
||||
pub kind: ReferenceKind,
|
||||
pub tool_part: Option<ToolPart>,
|
||||
pub tool_name: Option<String>,
|
||||
pub label: String,
|
||||
pub summary: String,
|
||||
search_text: String,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, Default)]
|
||||
pub struct SearchOptions {
|
||||
pub query: String,
|
||||
pub kind: Option<ReferenceKind>,
|
||||
pub tool_part: Option<ToolPart>,
|
||||
pub tool_name: Option<String>,
|
||||
pub limit: Option<usize>,
|
||||
pub min_entry_index: Option<u64>,
|
||||
pub from: Option<SessionEntryRef>,
|
||||
pub through: Option<SessionEntryRef>,
|
||||
pub offset: usize,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone)]
|
||||
pub struct SearchHit {
|
||||
pub id: SessionEntryRef,
|
||||
pub origin: SessionEntryProvenance,
|
||||
pub kind: ReferenceKind,
|
||||
pub tool_part: Option<ToolPart>,
|
||||
pub tool_name: Option<String>,
|
||||
pub entry_range: [u64; 2],
|
||||
pub label: String,
|
||||
pub summary: String,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, Copy)]
|
||||
pub enum ReadSelector<'a> {
|
||||
Id(&'a str),
|
||||
EntryRange([u64; 2]),
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
|
||||
pub enum ReadDetail {
|
||||
Compact,
|
||||
Full,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone)]
|
||||
pub struct ReadOptions {
|
||||
pub include_tools: bool,
|
||||
pub tool_part: ToolPart,
|
||||
pub detail: ReadDetail,
|
||||
pub max_items: usize,
|
||||
pub max_bytes: usize,
|
||||
}
|
||||
|
||||
impl Default for ReadOptions {
|
||||
fn default() -> Self {
|
||||
Self {
|
||||
include_tools: true,
|
||||
tool_part: ToolPart::Both,
|
||||
detail: ReadDetail::Compact,
|
||||
max_items: DEFAULT_READ_MAX_ITEMS,
|
||||
max_bytes: DEFAULT_READ_MAX_BYTES,
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone)]
|
||||
pub struct ReadEntry {
|
||||
pub id: SessionEntryRef,
|
||||
pub origin: SessionEntryProvenance,
|
||||
pub kind: ReferenceKind,
|
||||
pub tool_part: Option<ToolPart>,
|
||||
pub tool_name: Option<String>,
|
||||
pub entry_range: [u64; 2],
|
||||
pub label: String,
|
||||
pub text: String,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone)]
|
||||
pub struct ReadResult {
|
||||
pub entries: Vec<ReadEntry>,
|
||||
pub truncated: bool,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone)]
|
||||
pub struct SessionEntryEvidence {
|
||||
pub segment_id: String,
|
||||
pub entry_ref: SessionEntryRef,
|
||||
pub origin: SessionEntryProvenance,
|
||||
/// Inclusive original-source positions in `segment_id`, not view/UI order.
|
||||
pub entry_range: [u64; 2],
|
||||
pub kind: ReferenceKind,
|
||||
pub tool_part: Option<ToolPart>,
|
||||
pub label: String,
|
||||
pub summary: String,
|
||||
pub excerpt: String,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone)]
|
||||
struct CapturedHistoryEntry {
|
||||
use_policy: Option<protocol::SessionEntryUsePolicy>,
|
||||
item: Item,
|
||||
entry_id: crate::LoggedSessionHistoryEntryId,
|
||||
origin: SessionEntryProvenance,
|
||||
dto: CaptureEntryDto,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone)]
|
||||
pub struct SessionCapture {
|
||||
session_id: String,
|
||||
segment_id: String,
|
||||
capture_id: String,
|
||||
view_entry_count: u64,
|
||||
entries: Arc<Vec<CapturedHistoryEntry>>,
|
||||
overview: Vec<OverviewItem>,
|
||||
index: Vec<ReferenceEntry>,
|
||||
}
|
||||
|
||||
impl SessionCapture {
|
||||
pub fn from_session_snapshot(
|
||||
session_id: impl Into<String>,
|
||||
segment_id: impl Into<String>,
|
||||
snapshot: SessionSnapshot,
|
||||
) -> Self {
|
||||
let segment_id = segment_id.into();
|
||||
let view_entry_count = snapshot.entries.len() as u64;
|
||||
let entries = snapshot
|
||||
.entries
|
||||
.into_iter()
|
||||
.enumerate()
|
||||
.filter_map(|(index, entry)| {
|
||||
let policy = CaptureUsePolicy {
|
||||
recording_material: false,
|
||||
memory_evidence: entry.use_policy.is_none_or(|p| p.memory_evidence),
|
||||
observation_readable: entry.use_policy.is_none_or(|p| p.observation_readable),
|
||||
};
|
||||
let explicit = entry.use_policy.is_some();
|
||||
let item = match entry.data {
|
||||
SessionSnapshotEntryData::UserInput { segments } => {
|
||||
Item::user_message(protocol::Segment::flatten_to_text(&segments))
|
||||
}
|
||||
SessionSnapshotEntryData::Message { role, content } => Item::Message {
|
||||
id: None,
|
||||
status: None,
|
||||
role: match role {
|
||||
SessionMessageRole::User => Role::User,
|
||||
SessionMessageRole::Assistant => Role::Assistant,
|
||||
},
|
||||
content: content
|
||||
.into_iter()
|
||||
.map(|part| match part {
|
||||
SessionContentPart::Text { text } => {
|
||||
agen::ContentPart::Text { text }
|
||||
}
|
||||
SessionContentPart::Refusal { refusal } => {
|
||||
agen::ContentPart::Refusal { refusal }
|
||||
}
|
||||
})
|
||||
.collect(),
|
||||
},
|
||||
SessionSnapshotEntryData::ToolCall {
|
||||
call_id,
|
||||
name,
|
||||
arguments,
|
||||
} => Item::tool_call(call_id, name, arguments),
|
||||
SessionSnapshotEntryData::ToolResult {
|
||||
call_id,
|
||||
summary,
|
||||
content,
|
||||
is_error,
|
||||
..
|
||||
} => Item::tool_result_item(call_id, summary, content, is_error),
|
||||
SessionSnapshotEntryData::SystemItem { content, .. } if explicit => {
|
||||
Item::system_message(content)
|
||||
}
|
||||
_ => return None,
|
||||
};
|
||||
let body = CaptureBody::project(&item, &entry.provenance, explicit)?;
|
||||
if !policy.any() {
|
||||
return None;
|
||||
}
|
||||
Some(CaptureEntryDto {
|
||||
entry_id: entry.entry_id,
|
||||
order: index as u64,
|
||||
source: CaptureSource {
|
||||
segment_id: segment_id.clone(),
|
||||
entry_index: index as u64,
|
||||
provenance: entry.provenance,
|
||||
history_origin: None,
|
||||
derived_from: entry.derived_from,
|
||||
},
|
||||
policy,
|
||||
body,
|
||||
})
|
||||
})
|
||||
.collect();
|
||||
Self::from_projected(session_id.into(), segment_id, view_entry_count, entries)
|
||||
}
|
||||
|
||||
pub fn new(
|
||||
session_id: impl Into<String>,
|
||||
segment_id: impl Into<String>,
|
||||
items: Vec<Item>,
|
||||
) -> Self {
|
||||
let segment_id = segment_id.into();
|
||||
let view_entry_count = items.len() as u64;
|
||||
let entries = items
|
||||
.into_iter()
|
||||
.enumerate()
|
||||
.filter_map(|(index, item)| {
|
||||
let origin = SessionEntryProvenance::LegacyUnknown;
|
||||
let body = CaptureBody::project(&item, &origin, false)?;
|
||||
Some(CaptureEntryDto {
|
||||
entry_id: format!("{index:08}"),
|
||||
order: index as u64,
|
||||
source: CaptureSource {
|
||||
segment_id: segment_id.clone(),
|
||||
entry_index: index as u64,
|
||||
provenance: origin,
|
||||
history_origin: None,
|
||||
derived_from: Vec::new(),
|
||||
},
|
||||
policy: CaptureUsePolicy::PUBLIC,
|
||||
body,
|
||||
})
|
||||
})
|
||||
.collect();
|
||||
Self::from_projected(session_id.into(), segment_id, view_entry_count, entries)
|
||||
}
|
||||
|
||||
/// Project a complete Host-fixed history whose source positions start at zero.
|
||||
/// Select a suffix with `select_order_range` on the resulting value instead
|
||||
/// of passing a rebased history vector: annotations do not carry source positions.
|
||||
pub fn from_complete_history(
|
||||
session_id: impl Into<String>,
|
||||
segment_id: impl Into<String>,
|
||||
entries: Vec<HistoryEntry<SessionHistoryMetadata>>,
|
||||
) -> Self {
|
||||
let segment_id = segment_id.into();
|
||||
let view_entry_count = entries.len() as u64;
|
||||
let entries = entries
|
||||
.into_iter()
|
||||
.enumerate()
|
||||
.filter_map(|(index, entry)| {
|
||||
let origin = public_provenance(&entry.annotation.origin);
|
||||
let mut item = entry.item;
|
||||
let mut explicit = false;
|
||||
let policy = if let Some(input) = entry.annotation.input_metadata {
|
||||
explicit = true;
|
||||
if matches!(
|
||||
item,
|
||||
Item::Message {
|
||||
role: Role::System,
|
||||
..
|
||||
}
|
||||
) {
|
||||
// Only the explicit public projection crosses this boundary.
|
||||
let public = input.public_item()?;
|
||||
item = Item::system_message(public.body.clone());
|
||||
} else if input.feature_payload().is_some() || input.public_item().is_some() {
|
||||
return None;
|
||||
}
|
||||
CaptureUsePolicy::from(input.usage())
|
||||
} else {
|
||||
if matches!(entry.annotation.origin, HistoryOrigin::Provided { .. }) {
|
||||
return None;
|
||||
}
|
||||
CaptureUsePolicy::PUBLIC
|
||||
};
|
||||
if !policy.any() {
|
||||
return None;
|
||||
}
|
||||
let body = CaptureBody::project(&item, &origin, explicit)?;
|
||||
Some(CaptureEntryDto {
|
||||
entry_id: entry.annotation.entry_id.0,
|
||||
order: index as u64,
|
||||
source: CaptureSource {
|
||||
segment_id: segment_id.clone(),
|
||||
entry_index: index as u64,
|
||||
provenance: origin,
|
||||
history_origin: Some(entry.annotation.origin),
|
||||
derived_from: entry
|
||||
.annotation
|
||||
.derivation
|
||||
.map(|d| d.sources.into_iter().map(|id| id.0).collect())
|
||||
.unwrap_or_default(),
|
||||
},
|
||||
policy,
|
||||
body,
|
||||
})
|
||||
})
|
||||
.collect();
|
||||
Self::from_projected(session_id.into(), segment_id, view_entry_count, entries)
|
||||
}
|
||||
|
||||
fn from_projected(
|
||||
session_id: String,
|
||||
segment_id: String,
|
||||
view_entry_count: u64,
|
||||
dtos: Vec<CaptureEntryDto>,
|
||||
) -> Self {
|
||||
let dto = CaptureDto {
|
||||
version: CAPTURE_VERSION,
|
||||
session_id: session_id.clone(),
|
||||
segment_id: segment_id.clone(),
|
||||
view_entry_count,
|
||||
entries: dtos,
|
||||
};
|
||||
let capture_id = dto.fingerprint();
|
||||
let entries: Vec<_> = dto
|
||||
.entries
|
||||
.into_iter()
|
||||
.map(|dto| CapturedHistoryEntry {
|
||||
use_policy: Some(protocol::SessionEntryUsePolicy {
|
||||
observation_readable: dto.policy.observation_readable,
|
||||
memory_evidence: dto.policy.memory_evidence,
|
||||
}),
|
||||
item: dto.body.to_item(),
|
||||
entry_id: crate::LoggedSessionHistoryEntryId(dto.entry_id.clone()),
|
||||
origin: dto.source.provenance.clone(),
|
||||
dto,
|
||||
})
|
||||
.collect();
|
||||
let mut overview = Vec::new();
|
||||
let mut index = Vec::new();
|
||||
|
||||
for entry in &entries {
|
||||
let item = &entry.item;
|
||||
let entry_range = [entry.dto.order; 2];
|
||||
let attachment_count = match entry.dto.body {
|
||||
CaptureBody::ToolResult {
|
||||
attachment_count, ..
|
||||
} => attachment_count,
|
||||
_ => 0,
|
||||
};
|
||||
match item {
|
||||
Item::Message { role, content, .. } => {
|
||||
let Some(kind) = message_reference_kind(&entry.origin, role, entry.use_policy)
|
||||
else {
|
||||
continue;
|
||||
};
|
||||
let text = content
|
||||
.iter()
|
||||
.map(|p| p.as_text())
|
||||
.collect::<Vec<_>>()
|
||||
.join("");
|
||||
let label = format!("{} message", kind.as_str());
|
||||
let summary = truncate_chars(&text, 240);
|
||||
let id = SessionEntryRef::from_history_entry_id(&entry.entry_id);
|
||||
index.push(ReferenceEntry {
|
||||
use_policy: entry.use_policy,
|
||||
attachment_count,
|
||||
id: id.clone(),
|
||||
origin: entry.origin.clone(),
|
||||
entry_range,
|
||||
kind,
|
||||
tool_part: None,
|
||||
tool_name: None,
|
||||
label: label.clone(),
|
||||
summary: summary.clone(),
|
||||
search_text: text.clone(),
|
||||
});
|
||||
if entry.use_policy.is_none_or(|p| p.observation_readable)
|
||||
&& matches!(kind, ReferenceKind::User | ReferenceKind::Assistant)
|
||||
{
|
||||
overview.push(OverviewItem {
|
||||
id: id.clone(),
|
||||
origin: entry.origin.clone(),
|
||||
entry_range,
|
||||
kind,
|
||||
label,
|
||||
text,
|
||||
intervening_entries: 0,
|
||||
});
|
||||
}
|
||||
}
|
||||
Item::ToolCall {
|
||||
name, arguments, ..
|
||||
} => {
|
||||
let text = format!("{name}\n{arguments}");
|
||||
index.push(ReferenceEntry {
|
||||
use_policy: entry.use_policy,
|
||||
attachment_count,
|
||||
id: SessionEntryRef::from_history_entry_id(&entry.entry_id),
|
||||
origin: entry.origin.clone(),
|
||||
entry_range,
|
||||
kind: ReferenceKind::Tool,
|
||||
tool_part: Some(ToolPart::Input),
|
||||
tool_name: Some(name.clone()),
|
||||
label: format!("tool input: {name}"),
|
||||
summary: format!("Tool call {name}"),
|
||||
search_text: text,
|
||||
});
|
||||
}
|
||||
Item::ToolResult {
|
||||
summary,
|
||||
content,
|
||||
attachments: _,
|
||||
..
|
||||
} => {
|
||||
let attachment_marker = if attachment_count == 0 {
|
||||
String::new()
|
||||
} else {
|
||||
format!("\n[{} image attachment(s)]", attachment_count)
|
||||
};
|
||||
let text = format!(
|
||||
"{summary}\n{}{attachment_marker}",
|
||||
content.as_deref().unwrap_or_default(),
|
||||
);
|
||||
index.push(ReferenceEntry {
|
||||
use_policy: entry.use_policy,
|
||||
attachment_count,
|
||||
id: SessionEntryRef::from_history_entry_id(&entry.entry_id),
|
||||
origin: entry.origin.clone(),
|
||||
entry_range,
|
||||
kind: ReferenceKind::Tool,
|
||||
tool_part: Some(ToolPart::Output),
|
||||
tool_name: None,
|
||||
label: "tool output".to_string(),
|
||||
summary: truncate_chars(summary, 240),
|
||||
search_text: text,
|
||||
});
|
||||
}
|
||||
Item::AssistantResponseBoundary { .. } | Item::Reasoning { .. } => {}
|
||||
}
|
||||
}
|
||||
|
||||
if overview.len() > 2 {
|
||||
let last = overview.len() - 1;
|
||||
overview = overview
|
||||
.into_iter()
|
||||
.enumerate()
|
||||
.filter_map(|(index, entry)| {
|
||||
(index == 0 || index == last || index % OVERVIEW_ANCHOR_STRIDE == 0)
|
||||
.then_some(entry)
|
||||
})
|
||||
.collect();
|
||||
}
|
||||
|
||||
for overview_index in 0..overview.len().saturating_sub(1) {
|
||||
let current_entry = overview[overview_index].entry_range[0];
|
||||
let next_entry = overview[overview_index + 1].entry_range[0];
|
||||
overview[overview_index].intervening_entries = index
|
||||
.iter()
|
||||
.filter(|entry| {
|
||||
let entry_index = entry.entry_range[0];
|
||||
entry_index > current_entry && entry_index < next_entry
|
||||
})
|
||||
.count();
|
||||
}
|
||||
|
||||
Self {
|
||||
session_id,
|
||||
segment_id,
|
||||
capture_id,
|
||||
view_entry_count,
|
||||
entries: Arc::new(entries),
|
||||
overview,
|
||||
index,
|
||||
}
|
||||
}
|
||||
|
||||
/// Public source entries are immutable; callers retain their own business decisions.
|
||||
pub fn entries(&self) -> impl ExactSizeIterator<Item = &CaptureEntryDto> {
|
||||
self.entries.iter().map(|entry| &entry.dto)
|
||||
}
|
||||
|
||||
pub fn overview(&self) -> &[OverviewItem] {
|
||||
&self.overview
|
||||
}
|
||||
|
||||
/// Capture-local UI position, not the original source position used by evidence.
|
||||
pub fn view_order_for_ref(&self, reference: &SessionEntryRef) -> Option<u64> {
|
||||
self.index
|
||||
.iter()
|
||||
.find(|entry| entry.id == *reference)
|
||||
.map(|entry| entry.entry_range[0])
|
||||
}
|
||||
|
||||
pub fn search(&self, options: &SearchOptions) -> Vec<SearchHit> {
|
||||
if self.validate_search(options).is_err() {
|
||||
return Vec::new();
|
||||
}
|
||||
let query = options.query.trim().to_lowercase();
|
||||
let limit = options
|
||||
.limit
|
||||
.unwrap_or(DEFAULT_SEARCH_LIMIT)
|
||||
.clamp(1, MAX_SEARCH_LIMIT);
|
||||
let tool_name = options.tool_name.as_deref();
|
||||
let min_entry_index = options
|
||||
.from
|
||||
.as_ref()
|
||||
.and_then(|reference| self.view_order_for_ref(reference))
|
||||
.unwrap_or_else(|| options.min_entry_index.unwrap_or(0));
|
||||
let max_entry_index = options
|
||||
.through
|
||||
.as_ref()
|
||||
.and_then(|reference| self.view_order_for_ref(reference))
|
||||
.unwrap_or(u64::MAX);
|
||||
let mut skipped = 0usize;
|
||||
let mut hits = Vec::new();
|
||||
|
||||
for entry in &self.index {
|
||||
if entry.use_policy.is_some_and(|p| !p.observation_readable) {
|
||||
continue;
|
||||
}
|
||||
if entry.entry_range[0] < min_entry_index || entry.entry_range[0] > max_entry_index {
|
||||
continue;
|
||||
}
|
||||
if let Some(kind) = options.kind {
|
||||
if entry.kind != kind {
|
||||
continue;
|
||||
}
|
||||
}
|
||||
if let Some(part) = options.tool_part {
|
||||
if entry.kind != ReferenceKind::Tool {
|
||||
continue;
|
||||
}
|
||||
let Some(actual) = entry.tool_part else {
|
||||
continue;
|
||||
};
|
||||
if !part.matches(actual) {
|
||||
continue;
|
||||
}
|
||||
}
|
||||
if let Some(name) = tool_name {
|
||||
if entry.tool_name.as_deref() != Some(name) {
|
||||
continue;
|
||||
}
|
||||
}
|
||||
if !query.is_empty() && !entry.search_text.to_lowercase().contains(&query) {
|
||||
continue;
|
||||
}
|
||||
if skipped < options.offset {
|
||||
skipped += 1;
|
||||
continue;
|
||||
}
|
||||
hits.push(SearchHit {
|
||||
id: entry.id.clone(),
|
||||
origin: entry.origin.clone(),
|
||||
kind: entry.kind,
|
||||
tool_part: entry.tool_part,
|
||||
tool_name: entry.tool_name.clone(),
|
||||
entry_range: entry.entry_range,
|
||||
label: entry.label.clone(),
|
||||
summary: entry.summary.clone(),
|
||||
});
|
||||
if hits.len() >= limit {
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
hits
|
||||
}
|
||||
|
||||
pub fn read(&self, selector: ReadSelector<'_>, options: ReadOptions) -> ReadResult {
|
||||
let max_items = options.max_items.clamp(1, MAX_READ_MAX_ITEMS);
|
||||
let max_bytes = options.max_bytes.max(1);
|
||||
let mut entries = Vec::new();
|
||||
let mut bytes = 0usize;
|
||||
let mut truncated = false;
|
||||
|
||||
let selected: Vec<&ReferenceEntry> = match selector {
|
||||
ReadSelector::Id(id) => self
|
||||
.index
|
||||
.iter()
|
||||
.filter(|entry| entry.id.as_str() == id)
|
||||
.collect(),
|
||||
ReadSelector::EntryRange([start, end]) => self
|
||||
.index
|
||||
.iter()
|
||||
.filter(|entry| entry.entry_range[0] >= start && entry.entry_range[0] <= end)
|
||||
.collect(),
|
||||
};
|
||||
|
||||
for entry in selected {
|
||||
if entry.use_policy.is_some_and(|p| !p.observation_readable) {
|
||||
continue;
|
||||
}
|
||||
if entries.len() >= max_items {
|
||||
truncated = true;
|
||||
break;
|
||||
}
|
||||
if entry.kind == ReferenceKind::Tool {
|
||||
if !options.include_tools {
|
||||
continue;
|
||||
}
|
||||
if let Some(actual) = entry.tool_part {
|
||||
if !options.tool_part.matches(actual) {
|
||||
continue;
|
||||
}
|
||||
}
|
||||
}
|
||||
let Some(item) = self
|
||||
.entries
|
||||
.iter()
|
||||
.find(|captured| captured.dto.order == entry.entry_range[0])
|
||||
.map(|entry| &entry.item)
|
||||
else {
|
||||
continue;
|
||||
};
|
||||
let remaining = max_bytes.saturating_sub(bytes);
|
||||
if remaining == 0 {
|
||||
truncated = true;
|
||||
break;
|
||||
}
|
||||
let rendered = render_item(item, entry, options.detail, usize::MAX);
|
||||
truncated |= rendered.len() > remaining;
|
||||
let text = truncate_bytes(&rendered, remaining);
|
||||
bytes = bytes.saturating_add(text.len());
|
||||
entries.push(ReadEntry {
|
||||
id: entry.id.clone(),
|
||||
origin: entry.origin.clone(),
|
||||
kind: entry.kind,
|
||||
tool_part: entry.tool_part,
|
||||
tool_name: entry.tool_name.clone(),
|
||||
entry_range: entry.entry_range,
|
||||
label: entry.label.clone(),
|
||||
text,
|
||||
});
|
||||
if truncated {
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
ReadResult { entries, truncated }
|
||||
}
|
||||
|
||||
/// Resolves the committed tool-call input for a provider call id. This is
|
||||
/// used by explicit-memory receipts only after the containing run is durable,
|
||||
/// so a model-authored claim can cite its own committed tool invocation
|
||||
/// without inventing a SessionEntryRef.
|
||||
pub fn evidence_for_tool_call(&self, call_id: &str) -> Option<SessionEntryEvidence> {
|
||||
let captured = self.entries.iter().find(|entry| {
|
||||
matches!(
|
||||
&entry.item,
|
||||
Item::ToolCall {
|
||||
call_id: stored_call_id,
|
||||
..
|
||||
} if stored_call_id == call_id
|
||||
)
|
||||
})?;
|
||||
let reference = self.index.iter().find(|entry| {
|
||||
entry.entry_range[0] == captured.dto.order
|
||||
&& entry.kind == ReferenceKind::Tool
|
||||
&& entry.tool_part == Some(ToolPart::Input)
|
||||
})?;
|
||||
self.evidence_for(reference.id.as_str())
|
||||
}
|
||||
|
||||
pub fn evidence_for(&self, id: &str) -> Option<SessionEntryEvidence> {
|
||||
let entry = self.index.iter().find(|entry| entry.id.as_str() == id)?;
|
||||
if entry.use_policy.is_some_and(|p| !p.memory_evidence) {
|
||||
return None;
|
||||
}
|
||||
let captured = self
|
||||
.entries
|
||||
.iter()
|
||||
.find(|captured| captured.dto.order == entry.entry_range[0])?;
|
||||
let excerpt = render_item(&captured.item, entry, ReadDetail::Compact, 2 * 1024);
|
||||
Some(SessionEntryEvidence {
|
||||
segment_id: captured.dto.source.segment_id.clone(),
|
||||
entry_ref: entry.id.clone(),
|
||||
origin: entry.origin.clone(),
|
||||
entry_range: [captured.dto.source.entry_index; 2],
|
||||
kind: entry.kind,
|
||||
tool_part: entry.tool_part,
|
||||
label: entry.label.clone(),
|
||||
summary: entry.summary.clone(),
|
||||
excerpt,
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
pub(crate) fn public_provenance(origin: &HistoryOrigin) -> SessionEntryProvenance {
|
||||
match origin {
|
||||
HistoryOrigin::HumanInput { .. } | HistoryOrigin::LocalHumanInput => {
|
||||
SessionEntryProvenance::HumanInput
|
||||
}
|
||||
HistoryOrigin::WorkerInput { .. } => SessionEntryProvenance::WorkerInput,
|
||||
HistoryOrigin::FlowInstruction { .. } => SessionEntryProvenance::FlowInstruction,
|
||||
HistoryOrigin::BackendInstruction { .. } | HistoryOrigin::Provided { .. } => {
|
||||
SessionEntryProvenance::BackendInstruction
|
||||
}
|
||||
HistoryOrigin::ModelOutput { .. } => SessionEntryProvenance::ModelOutput,
|
||||
HistoryOrigin::ToolOutput { .. } => SessionEntryProvenance::ToolOutput,
|
||||
HistoryOrigin::CompactionSummary
|
||||
| HistoryOrigin::DerivedSummary
|
||||
| HistoryOrigin::JournalContext => SessionEntryProvenance::DerivedSummary,
|
||||
HistoryOrigin::LegacyUnknown => SessionEntryProvenance::LegacyUnknown,
|
||||
}
|
||||
}
|
||||
|
||||
fn message_reference_kind(
|
||||
origin: &SessionEntryProvenance,
|
||||
provider_role: &Role,
|
||||
use_policy: Option<protocol::SessionEntryUsePolicy>,
|
||||
) -> Option<ReferenceKind> {
|
||||
if use_policy.is_some() {
|
||||
return match provider_role {
|
||||
Role::System => Some(ReferenceKind::System),
|
||||
Role::User => Some(ReferenceKind::User),
|
||||
Role::Assistant => Some(ReferenceKind::Assistant),
|
||||
};
|
||||
}
|
||||
match origin {
|
||||
SessionEntryProvenance::HumanInput | SessionEntryProvenance::WorkerInput => {
|
||||
Some(ReferenceKind::User)
|
||||
}
|
||||
SessionEntryProvenance::ModelOutput => Some(ReferenceKind::Assistant),
|
||||
SessionEntryProvenance::ToolOutput => Some(ReferenceKind::Tool),
|
||||
SessionEntryProvenance::LegacyUnknown => match provider_role {
|
||||
Role::User => Some(ReferenceKind::User),
|
||||
Role::Assistant => Some(ReferenceKind::Assistant),
|
||||
Role::System => None,
|
||||
},
|
||||
// Flow/backend/system content remains out of the observation surface
|
||||
// even when represented with a provider user/system role.
|
||||
SessionEntryProvenance::FlowInstruction
|
||||
| SessionEntryProvenance::BackendInstruction
|
||||
| SessionEntryProvenance::DerivedSummary => None,
|
||||
}
|
||||
}
|
||||
|
||||
fn render_item(
|
||||
item: &Item,
|
||||
entry: &ReferenceEntry,
|
||||
detail: ReadDetail,
|
||||
max_bytes: usize,
|
||||
) -> String {
|
||||
let text = match item {
|
||||
Item::Message { role, content, .. } => {
|
||||
let text = content
|
||||
.iter()
|
||||
.map(|p| p.as_text())
|
||||
.collect::<Vec<_>>()
|
||||
.join("");
|
||||
format!("[{} {:?}] {text}", entry.id, role)
|
||||
}
|
||||
Item::ToolCall {
|
||||
name, arguments, ..
|
||||
} => match detail {
|
||||
ReadDetail::Compact => format!("[{} ToolInput {name}] (arguments omitted)", entry.id),
|
||||
ReadDetail::Full => format!("[{} ToolInput {name}]\narguments: {arguments}", entry.id),
|
||||
},
|
||||
Item::ToolResult {
|
||||
summary,
|
||||
content,
|
||||
attachments: _,
|
||||
is_error,
|
||||
..
|
||||
} => {
|
||||
let attachment_line = if entry.attachment_count == 0 {
|
||||
String::new()
|
||||
} else {
|
||||
format!("\nattachments: {} image(s)", entry.attachment_count)
|
||||
};
|
||||
match detail {
|
||||
ReadDetail::Compact => format!(
|
||||
"[{} ToolOutput{}]\nsummary: {summary}\ncontent: (omitted){attachment_line}",
|
||||
entry.id,
|
||||
if *is_error { " error" } else { "" },
|
||||
),
|
||||
ReadDetail::Full => format!(
|
||||
"[{} ToolOutput{}]\nsummary: {summary}\ncontent: {}{attachment_line}",
|
||||
entry.id,
|
||||
if *is_error { " error" } else { "" },
|
||||
content.as_deref().unwrap_or_default(),
|
||||
),
|
||||
}
|
||||
}
|
||||
Item::AssistantResponseBoundary { .. } => {
|
||||
format!("[{} Assistant response boundary omitted]", entry.id)
|
||||
}
|
||||
Item::Reasoning { .. } => format!("[{} Reasoning omitted]", entry.id),
|
||||
};
|
||||
truncate_bytes(&text, max_bytes)
|
||||
}
|
||||
|
||||
fn truncate_chars(text: &str, max_chars: usize) -> String {
|
||||
if max_chars == 0 {
|
||||
return "… [truncated]".to_string();
|
||||
}
|
||||
if text.chars().count() <= max_chars {
|
||||
return text.to_string();
|
||||
}
|
||||
let mut out = text.chars().take(max_chars).collect::<String>();
|
||||
out.push_str("… [truncated]");
|
||||
out
|
||||
}
|
||||
|
||||
fn truncate_bytes(text: &str, max_bytes: usize) -> String {
|
||||
if text.len() <= max_bytes {
|
||||
return text.to_owned();
|
||||
}
|
||||
let marker = "… [truncated]";
|
||||
let mut end = max_bytes.saturating_sub(marker.len());
|
||||
while !text.is_char_boundary(end) {
|
||||
end -= 1;
|
||||
}
|
||||
let mut out = text[..end].to_owned();
|
||||
if max_bytes >= marker.len() {
|
||||
out.push_str(marker);
|
||||
}
|
||||
out
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,425 @@
|
||||
//! Host capture and pure canonical slicing. No Job state or live-reader fallback lives here.
|
||||
|
||||
use super::*;
|
||||
use crate::committed_replay::CommittedPublicReplay;
|
||||
use crate::public_material::{
|
||||
PublicMaterialDescriptor, PublicMaterialError, PublicMaterialLimits, PublicMaterialUse,
|
||||
};
|
||||
use crate::retention::SessionRetentionStore;
|
||||
use crate::{SegmentId, SessionId};
|
||||
use std::path::Path;
|
||||
|
||||
/// Continuation in canonical Journal order, not an observation/Memory view cursor.
|
||||
/// A Host must reconcile the descriptor at this position with its saved checkpoint.
|
||||
#[derive(Debug, Clone, Copy, Default, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct RecordingPosition {
|
||||
pub canonical_order: u64,
|
||||
pub byte_offset: u64,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct RecordingCaptureSlice {
|
||||
pub capture: CaptureDto,
|
||||
pub next: Option<RecordingPosition>,
|
||||
}
|
||||
|
||||
/// Inspect recording admission descriptors without constructing a body-bearing DTO.
|
||||
///
|
||||
/// The Host must authorize the source and hold the **same** Session publication/erasure
|
||||
/// guard from before reading its persisted active pointer until this function returns
|
||||
/// (including the callback). Pass that pointer's Segment, not a filename/mtime-derived
|
||||
/// selector. This function verifies the guard and stored Session identities but does
|
||||
/// not authorize the caller or establish that the supplied guard fences this root.
|
||||
/// No lock is recursively acquired, no active pointer is reread, and no replay handle
|
||||
/// or body-read capability is exposed to `inspect`.
|
||||
///
|
||||
/// The common committed recording replay fixes per-file ends before decoding. It
|
||||
/// retains only descriptors/locations, decoding one record at a time and streaming
|
||||
/// canonical bodies into their digests. `replay_limits` bound record allocation,
|
||||
/// aggregate storage extent, entries and Segments; there is no full-capture text/JSON
|
||||
/// allocation or `CaptureLimits` ceiling. The callback receives only descriptors in
|
||||
/// canonical order and may return a Host-specific mapping (including a `Result`). It
|
||||
/// runs once on success and not at all on replay/identity/resource errors.
|
||||
///
|
||||
/// This catalog is for Host admission, **not** a descriptor-only Job input. Construct
|
||||
/// the Job's bounded body input with the guarded slice API at its own authorized
|
||||
/// boundary; after saving it, execute only that immutable value. Neither descriptors
|
||||
/// nor a completed callback authorize delayed adoption after erasure.
|
||||
///
|
||||
/// ```no_run
|
||||
/// # use std::path::Path;
|
||||
/// # use session_store::{SessionId, SegmentId};
|
||||
/// # use session_store::retention::SessionRetentionGuard;
|
||||
/// # use session_store::public_material::PublicMaterialError;
|
||||
/// # fn admit(root: &Path, session: SessionId, active: SegmentId,
|
||||
/// # guard: &SessionRetentionGuard) -> Result<Vec<u64>, PublicMaterialError> {
|
||||
/// // `active` was resolved from persisted Host metadata while holding `guard`.
|
||||
/// session_store::capture::recording_catalog_worker_guarded(
|
||||
/// root, session, active, Default::default(), guard,
|
||||
/// |descriptors| descriptors.iter().map(|d| d.total_bytes).collect(),
|
||||
/// )
|
||||
/// # }
|
||||
/// ```
|
||||
pub fn recording_catalog_worker_guarded<T>(
|
||||
session_root: &Path,
|
||||
expected_session: SessionId,
|
||||
active_segment: SegmentId,
|
||||
replay_limits: PublicMaterialLimits,
|
||||
guard: &crate::retention::SessionRetentionGuard,
|
||||
inspect: impl FnOnce(&[PublicMaterialDescriptor]) -> T,
|
||||
) -> Result<T, PublicMaterialError> {
|
||||
if guard.session_id() != expected_session {
|
||||
return Err(PublicMaterialError::Inconsistent);
|
||||
}
|
||||
let replay = CommittedPublicReplay::open_worker_guarded(
|
||||
session_root,
|
||||
active_segment,
|
||||
replay_limits,
|
||||
None,
|
||||
PublicMaterialUse::Recording,
|
||||
)?;
|
||||
if replay.session_id() != expected_session {
|
||||
return Err(PublicMaterialError::Inconsistent);
|
||||
}
|
||||
Ok(inspect(&replay.into_recording_descriptors()))
|
||||
}
|
||||
|
||||
/// FsStore-layout counterpart of [`recording_catalog_worker_guarded`].
|
||||
///
|
||||
/// `sessions_root` is the directory containing per-Session directories. Invoke this
|
||||
/// inside the Host's `with_recording_boundary` callback, passing **its existing guard
|
||||
/// and persisted active Segment**. That same external retention control store must
|
||||
/// fence publishers, pointer changes, archive moves and erasure. Do not reacquire the
|
||||
/// guard or use a separately opened legacy public reader inside the boundary.
|
||||
/// All descriptor-only, allocation and callback guarantees of the Worker variant
|
||||
/// apply; this function does not construct an unbounded transient `CaptureDto`.
|
||||
pub fn recording_catalog_fs_guarded<T>(
|
||||
sessions_root: &Path,
|
||||
session: SessionId,
|
||||
active_segment: SegmentId,
|
||||
replay_limits: PublicMaterialLimits,
|
||||
guard: &crate::retention::SessionRetentionGuard,
|
||||
inspect: impl FnOnce(&[PublicMaterialDescriptor]) -> T,
|
||||
) -> Result<T, PublicMaterialError> {
|
||||
if guard.session_id() != session {
|
||||
return Err(PublicMaterialError::Inconsistent);
|
||||
}
|
||||
let replay = CommittedPublicReplay::open_fs_guarded(
|
||||
sessions_root,
|
||||
session,
|
||||
active_segment,
|
||||
replay_limits,
|
||||
)?;
|
||||
Ok(inspect(&replay.into_recording_descriptors()))
|
||||
}
|
||||
|
||||
/// Capture the selected original lineage, including typed Host run boundaries.
|
||||
/// The caller must hold the Session publication/erasure guard while selecting the
|
||||
/// active pointer and through this call. Runtime publishers use this same lock
|
||||
/// for appends and Segment creation. No lock is recursively acquired here.
|
||||
pub fn capture_recording_worker_guarded(
|
||||
session_root: &Path,
|
||||
expected_session: SessionId,
|
||||
active_segment: SegmentId,
|
||||
replay_limits: PublicMaterialLimits,
|
||||
capture_limits: CaptureLimits,
|
||||
guard: &crate::retention::SessionRetentionGuard,
|
||||
) -> Result<CaptureDto, PublicMaterialError> {
|
||||
if guard.session_id() != expected_session {
|
||||
return Err(PublicMaterialError::Inconsistent);
|
||||
}
|
||||
let replay = CommittedPublicReplay::open_worker_guarded(
|
||||
session_root,
|
||||
active_segment,
|
||||
replay_limits,
|
||||
None,
|
||||
PublicMaterialUse::Recording,
|
||||
)?;
|
||||
if replay.session_id() != expected_session {
|
||||
return Err(PublicMaterialError::Inconsistent);
|
||||
}
|
||||
replay.into_recording_dto(capture_limits)
|
||||
}
|
||||
|
||||
/// Standalone convenience entry; Hosts resolving a mutable active pointer should
|
||||
/// instead hold the fence while resolving it and call the guarded entry.
|
||||
pub fn capture_recording_worker(
|
||||
session_root: &Path,
|
||||
expected_session: SessionId,
|
||||
active_segment: SegmentId,
|
||||
retention: &SessionRetentionStore,
|
||||
replay_limits: PublicMaterialLimits,
|
||||
capture_limits: CaptureLimits,
|
||||
) -> Result<CaptureDto, PublicMaterialError> {
|
||||
let guard = retention
|
||||
.lock_live(expected_session)
|
||||
.map_err(|error| match error {
|
||||
crate::StoreError::SessionErased(_) => PublicMaterialError::Erased,
|
||||
_ => PublicMaterialError::Unavailable,
|
||||
})?;
|
||||
capture_recording_worker_guarded(
|
||||
session_root,
|
||||
expected_session,
|
||||
active_segment,
|
||||
replay_limits,
|
||||
capture_limits,
|
||||
&guard,
|
||||
)
|
||||
}
|
||||
|
||||
/// Bounded construction for one Job input: descriptor replay is bounded separately;
|
||||
/// only at most the requested body budget is materialized from the fixed files.
|
||||
pub fn capture_recording_slice_worker_guarded(
|
||||
session_root: &Path,
|
||||
expected_session: SessionId,
|
||||
active_segment: SegmentId,
|
||||
replay_limits: PublicMaterialLimits,
|
||||
start: RecordingPosition,
|
||||
max_entries: usize,
|
||||
max_serialized_bytes: usize,
|
||||
guard: &crate::retention::SessionRetentionGuard,
|
||||
) -> Result<RecordingCaptureSlice, PublicMaterialError> {
|
||||
if guard.session_id() != expected_session {
|
||||
return Err(PublicMaterialError::Inconsistent);
|
||||
}
|
||||
let replay = CommittedPublicReplay::open_worker_guarded(
|
||||
session_root,
|
||||
active_segment,
|
||||
replay_limits,
|
||||
None,
|
||||
PublicMaterialUse::Recording,
|
||||
)?;
|
||||
if replay.session_id() != expected_session {
|
||||
return Err(PublicMaterialError::Inconsistent);
|
||||
}
|
||||
replay.recording_slice(start, max_entries, max_serialized_bytes)
|
||||
}
|
||||
|
||||
/// The standalone FsStore layout uses the same committed replay and fixed values.
|
||||
pub fn capture_recording_fs_guarded(
|
||||
sessions_root: &Path,
|
||||
session: SessionId,
|
||||
active_segment: SegmentId,
|
||||
replay_limits: PublicMaterialLimits,
|
||||
capture_limits: CaptureLimits,
|
||||
guard: &crate::retention::SessionRetentionGuard,
|
||||
) -> Result<CaptureDto, PublicMaterialError> {
|
||||
if guard.session_id() != session {
|
||||
return Err(PublicMaterialError::Inconsistent);
|
||||
}
|
||||
CommittedPublicReplay::open_fs_guarded(sessions_root, session, active_segment, replay_limits)?
|
||||
.into_recording_dto(capture_limits)
|
||||
}
|
||||
|
||||
/// Bounded standalone capture; the caller holds its FsStore retention fence.
|
||||
pub fn capture_recording_slice_fs_guarded(
|
||||
sessions_root: &Path,
|
||||
session: SessionId,
|
||||
active_segment: SegmentId,
|
||||
replay_limits: PublicMaterialLimits,
|
||||
start: RecordingPosition,
|
||||
max_entries: usize,
|
||||
max_serialized_bytes: usize,
|
||||
guard: &crate::retention::SessionRetentionGuard,
|
||||
) -> Result<RecordingCaptureSlice, PublicMaterialError> {
|
||||
if guard.session_id() != session {
|
||||
return Err(PublicMaterialError::Inconsistent);
|
||||
}
|
||||
CommittedPublicReplay::open_fs_guarded(sessions_root, session, active_segment, replay_limits)?
|
||||
.recording_slice(start, max_entries, max_serialized_bytes)
|
||||
}
|
||||
|
||||
impl CaptureDto {
|
||||
/// Select the oldest canonical prefix fitting both budgets, including JSON
|
||||
/// escaping, metadata and continuation. Only immutable owned bytes are read.
|
||||
/// A later Job can recapture at `next`; never combine live pages into this value.
|
||||
pub fn recording_slice(
|
||||
&self,
|
||||
start: RecordingPosition,
|
||||
max_entries: usize,
|
||||
max_serialized_bytes: usize,
|
||||
) -> Result<RecordingCaptureSlice, CaptureError> {
|
||||
if max_entries == 0 {
|
||||
return Err(CaptureError::BudgetTooSmall);
|
||||
}
|
||||
if start.canonical_order > self.view_entry_count {
|
||||
return Err(CaptureError::InvalidRange);
|
||||
}
|
||||
let mut result = RecordingCaptureSlice {
|
||||
capture: CaptureDto {
|
||||
version: self.version,
|
||||
session_id: self.session_id.clone(),
|
||||
segment_id: self.segment_id.clone(),
|
||||
view_entry_count: self.view_entry_count,
|
||||
entries: Vec::new(),
|
||||
},
|
||||
next: (start.canonical_order < self.view_entry_count).then_some(start),
|
||||
};
|
||||
if body::json_size(&result, max_serialized_bytes).is_err() {
|
||||
return Err(CaptureError::BudgetTooSmall);
|
||||
}
|
||||
if start.canonical_order == self.view_entry_count {
|
||||
if start.byte_offset != 0 {
|
||||
return Err(CaptureError::InvalidRange);
|
||||
}
|
||||
result.capture.validate(CaptureLimits {
|
||||
max_bytes: max_serialized_bytes,
|
||||
max_text_bytes: max_serialized_bytes,
|
||||
max_entries,
|
||||
..Default::default()
|
||||
})?;
|
||||
return Ok(result);
|
||||
}
|
||||
let first = self
|
||||
.entries
|
||||
.iter()
|
||||
.position(|entry| entry.order == start.canonical_order)
|
||||
.ok_or(CaptureError::InvalidRange)?;
|
||||
let mut expected_order = start.canonical_order;
|
||||
for entry in self.entries.iter().skip(first).take(max_entries) {
|
||||
if entry.order != expected_order {
|
||||
return Err(CaptureError::InvalidRange);
|
||||
}
|
||||
let CaptureBody::CanonicalPublic {
|
||||
descriptor,
|
||||
byte_offset,
|
||||
text,
|
||||
boundary,
|
||||
} = &entry.body
|
||||
else {
|
||||
return Err(CaptureError::Invalid("not a recording capture"));
|
||||
};
|
||||
if !entry.policy.recording_material {
|
||||
return Err(CaptureError::PolicyDenied);
|
||||
}
|
||||
let offset = if entry.order == start.canonical_order {
|
||||
start.byte_offset
|
||||
} else {
|
||||
*byte_offset
|
||||
};
|
||||
let local = offset
|
||||
.checked_sub(*byte_offset)
|
||||
.and_then(|o| usize::try_from(o).ok())
|
||||
.ok_or(CaptureError::InvalidRange)?;
|
||||
if local > text.len()
|
||||
|| !text.is_char_boundary(local)
|
||||
|| offset >= descriptor.total_bytes
|
||||
{
|
||||
return Err(CaptureError::InvalidRange);
|
||||
}
|
||||
let item = CaptureEntryDto {
|
||||
entry_id: entry.entry_id.clone(),
|
||||
order: entry.order,
|
||||
source: entry.source.clone(),
|
||||
policy: entry.policy,
|
||||
body: CaptureBody::CanonicalPublic {
|
||||
descriptor: descriptor.clone(),
|
||||
byte_offset: offset,
|
||||
text: String::new(),
|
||||
boundary: *boundary,
|
||||
},
|
||||
};
|
||||
result.capture.entries.push(item);
|
||||
// At most budget bytes are considered before allocating a trial fragment.
|
||||
let mut low = 0;
|
||||
let mut high = text.len().saturating_sub(local).min(max_serialized_bytes);
|
||||
let prior_next = result.next;
|
||||
while low < high {
|
||||
let mid = low + (high - low).div_ceil(2);
|
||||
let mut end = local + mid;
|
||||
while !text.is_char_boundary(end) {
|
||||
end -= 1;
|
||||
}
|
||||
if let CaptureBody::CanonicalPublic { text: fragment, .. } =
|
||||
&mut result.capture.entries.last_mut().unwrap().body
|
||||
{
|
||||
*fragment = text[local..end].to_owned();
|
||||
}
|
||||
let next_offset = offset + (end - local) as u64;
|
||||
result.next = if next_offset < descriptor.total_bytes {
|
||||
Some(RecordingPosition {
|
||||
canonical_order: entry.order,
|
||||
byte_offset: next_offset,
|
||||
})
|
||||
} else {
|
||||
(entry.order + 1 < self.view_entry_count).then_some(RecordingPosition {
|
||||
canonical_order: entry.order + 1,
|
||||
byte_offset: 0,
|
||||
})
|
||||
};
|
||||
if body::json_size(&result, max_serialized_bytes).is_ok() {
|
||||
low = mid;
|
||||
} else {
|
||||
high = mid - 1;
|
||||
}
|
||||
}
|
||||
let mut end = local + low;
|
||||
while !text.is_char_boundary(end) {
|
||||
end -= 1;
|
||||
}
|
||||
if end == local {
|
||||
result.capture.entries.pop();
|
||||
result.next = prior_next;
|
||||
if result.capture.entries.is_empty() {
|
||||
return Err(CaptureError::BudgetTooSmall);
|
||||
}
|
||||
break;
|
||||
}
|
||||
if let CaptureBody::CanonicalPublic { text: fragment, .. } =
|
||||
&mut result.capture.entries.last_mut().unwrap().body
|
||||
{
|
||||
*fragment = text[local..end].to_owned();
|
||||
}
|
||||
let next_offset = offset + (end - local) as u64;
|
||||
result.next = if next_offset < descriptor.total_bytes {
|
||||
Some(RecordingPosition {
|
||||
canonical_order: entry.order,
|
||||
byte_offset: next_offset,
|
||||
})
|
||||
} else {
|
||||
(entry.order + 1 < self.view_entry_count).then_some(RecordingPosition {
|
||||
canonical_order: entry.order + 1,
|
||||
byte_offset: 0,
|
||||
})
|
||||
};
|
||||
if next_offset < descriptor.total_bytes {
|
||||
break;
|
||||
}
|
||||
expected_order = entry.order + 1;
|
||||
}
|
||||
body::json_size(&result, max_serialized_bytes).map_err(|_| CaptureError::BudgetTooSmall)?;
|
||||
result.capture.validate(CaptureLimits {
|
||||
max_bytes: max_serialized_bytes,
|
||||
max_text_bytes: max_serialized_bytes,
|
||||
max_entries,
|
||||
..Default::default()
|
||||
})?;
|
||||
Ok(result)
|
||||
}
|
||||
|
||||
/// Resolve canonical text already in the value. No original storage is consulted.
|
||||
pub fn recording_text(
|
||||
&self,
|
||||
order: u64,
|
||||
) -> Result<(&crate::public_material::PublicMaterialDescriptor, u64, &str), CaptureError> {
|
||||
let entry = self
|
||||
.entries
|
||||
.iter()
|
||||
.find(|entry| entry.order == order)
|
||||
.ok_or(CaptureError::UnknownReference)?;
|
||||
if !entry.policy.recording_material {
|
||||
return Err(CaptureError::PolicyDenied);
|
||||
}
|
||||
match &entry.body {
|
||||
CaptureBody::CanonicalPublic {
|
||||
descriptor,
|
||||
byte_offset,
|
||||
text,
|
||||
..
|
||||
} => Ok((descriptor, *byte_offset, text)),
|
||||
_ => Err(CaptureError::Invalid("not canonical recording text")),
|
||||
}
|
||||
}
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
@@ -68,6 +68,24 @@ impl FsStore {
|
||||
) -> 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(())),
|
||||
@@ -343,6 +361,7 @@ impl Store for FsStore {
|
||||
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)
|
||||
@@ -430,10 +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 {
|
||||
|
||||
@@ -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);
|
||||
}
|
||||
}
|
||||
@@ -38,9 +38,12 @@ pub(crate) fn read_without_atime_bounded(path: &Path, max_bytes: u64) -> io::Res
|
||||
}
|
||||
}
|
||||
|
||||
pub mod capture;
|
||||
mod committed_replay;
|
||||
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;
|
||||
@@ -65,6 +68,10 @@ 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::{
|
||||
@@ -98,7 +105,8 @@ 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,
|
||||
|
||||
@@ -46,6 +46,13 @@ pub struct SessionRetentionStore {
|
||||
/// Do not recursively acquire the same Session lock inside a guarded callback.
|
||||
pub struct SessionRetentionGuard {
|
||||
_file: File,
|
||||
session_id: SessionId,
|
||||
}
|
||||
|
||||
impl SessionRetentionGuard {
|
||||
pub fn session_id(&self) -> SessionId {
|
||||
self.session_id
|
||||
}
|
||||
}
|
||||
|
||||
impl SessionRetentionStore {
|
||||
@@ -71,7 +78,10 @@ impl SessionRetentionStore {
|
||||
}
|
||||
let file = options.open(self.root.join(format!("{session}.lock")))?;
|
||||
FileExt::lock_exclusive(&file)?;
|
||||
Ok(SessionRetentionGuard { _file: file })
|
||||
Ok(SessionRetentionGuard {
|
||||
_file: file,
|
||||
session_id: session,
|
||||
})
|
||||
}
|
||||
|
||||
fn read(&self, session: SessionId) -> Result<RetentionState, StoreError> {
|
||||
|
||||
@@ -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:?}"),
|
||||
}
|
||||
}
|
||||
|
||||
@@ -27,6 +27,9 @@ 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),
|
||||
|
||||
|
||||
@@ -86,20 +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 {
|
||||
/// One-time derived Journal reference context. The bounded Host snapshot is
|
||||
/// retained as JSON independently of its rendered body and prompt projection.
|
||||
JournalStartup {
|
||||
body: String,
|
||||
snapshot: serde_json::Value,
|
||||
snapshot_sha256: String,
|
||||
prompt_provenance: PromptRenderProvenance,
|
||||
},
|
||||
/// 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
|
||||
@@ -122,14 +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
|
||||
@@ -137,10 +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.
|
||||
@@ -164,29 +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.
|
||||
@@ -197,24 +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::JournalStartup { body, .. } => body.clone(),
|
||||
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(),
|
||||
}
|
||||
}
|
||||
@@ -229,17 +233,13 @@ impl SystemItem {
|
||||
/// wire — keep flexible.
|
||||
pub fn kind_label(&self) -> &'static str {
|
||||
match self {
|
||||
SystemItem::JournalStartup { .. } => "journal_startup",
|
||||
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",
|
||||
}
|
||||
}
|
||||
@@ -297,33 +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]
|
||||
@@ -419,29 +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,
|
||||
@@ -1087,13 +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(
|
||||
@@ -1117,7 +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();
|
||||
@@ -1129,13 +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
|
||||
@@ -1151,7 +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";
|
||||
@@ -203,7 +206,15 @@ impl WorkerSessionStore {
|
||||
|
||||
/// 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) => {
|
||||
@@ -212,11 +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)?;
|
||||
@@ -243,6 +259,33 @@ impl WorkerSessionStore {
|
||||
})
|
||||
}
|
||||
|
||||
/// 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> {
|
||||
@@ -739,6 +782,7 @@ impl Store for WorkerSessionStore {
|
||||
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)
|
||||
@@ -797,6 +841,9 @@ 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();
|
||||
@@ -1107,7 +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());
|
||||
}
|
||||
@@ -1150,21 +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 {
|
||||
@@ -1174,17 +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
|
||||
@@ -1202,14 +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(())
|
||||
}
|
||||
@@ -1223,17 +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()
|
||||
}
|
||||
@@ -1380,6 +1500,7 @@ mod tests {
|
||||
LoggedHistoryEntry {
|
||||
item: LoggedItem::from(item),
|
||||
metadata: LoggedSessionHistoryMetadata {
|
||||
input_metadata: None,
|
||||
entry_id: LoggedSessionHistoryEntryId::new(),
|
||||
origin: LoggedSessionHistoryOrigin::LegacyUnknown,
|
||||
derivation: None,
|
||||
@@ -1967,6 +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();
|
||||
|
||||
@@ -0,0 +1,711 @@
|
||||
//! Public consumer boundary: real capture adapters, checked DTO codec and pure readers.
|
||||
//! No Worker, persistence, live Session provider, or substituted capture implementation.
|
||||
|
||||
use agen::{HistoryEntry, Item};
|
||||
use protocol::{
|
||||
SessionEntryProvenance, SessionSnapshot, SessionSnapshotEntry, SessionSnapshotEntryData,
|
||||
};
|
||||
use session_store::capture::*;
|
||||
use session_store::{
|
||||
FeatureInputPayload, HistoryInputMetadata, HistoryInputUsePolicy, InputCompactionUse,
|
||||
InputEvidenceUse, InputObservationUse, LoggedHistoryDerivation, LoggedSessionHistoryEntryId,
|
||||
LoggedSessionHistoryMetadata, LoggedSessionHistoryOrigin, PublicSystemItem,
|
||||
PublicSystemPresentation,
|
||||
};
|
||||
|
||||
fn history(
|
||||
id: &str,
|
||||
item: Item,
|
||||
input_metadata: Option<HistoryInputMetadata>,
|
||||
) -> HistoryEntry<LoggedSessionHistoryMetadata> {
|
||||
HistoryEntry::new(
|
||||
item,
|
||||
LoggedSessionHistoryMetadata {
|
||||
entry_id: LoggedSessionHistoryEntryId(id.into()),
|
||||
origin: LoggedSessionHistoryOrigin::LocalHumanInput,
|
||||
derivation: Some(LoggedHistoryDerivation {
|
||||
sources: vec![LoggedSessionHistoryEntryId("earlier-entry".into())],
|
||||
}),
|
||||
input_metadata,
|
||||
},
|
||||
)
|
||||
}
|
||||
|
||||
fn usage(recording: bool, memory: bool, observation: bool) -> HistoryInputUsePolicy {
|
||||
HistoryInputUsePolicy {
|
||||
recording_material: if recording {
|
||||
InputEvidenceUse::Include
|
||||
} else {
|
||||
InputEvidenceUse::Exclude
|
||||
},
|
||||
memory_evidence: if memory {
|
||||
InputEvidenceUse::Include
|
||||
} else {
|
||||
InputEvidenceUse::Exclude
|
||||
},
|
||||
observation: if observation {
|
||||
InputObservationUse::Readable
|
||||
} else {
|
||||
InputObservationUse::Hidden
|
||||
},
|
||||
compaction: InputCompactionUse::Retain,
|
||||
}
|
||||
}
|
||||
|
||||
fn reference(capture: &SessionCapture, id: &str) -> ScopedSessionEntryRef {
|
||||
capture
|
||||
.scoped_ref(&SessionEntryRef::parse(id).unwrap())
|
||||
.unwrap()
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn public_consumer_roundtrip_retains_body_original_source_order_origin_and_independent_policy() {
|
||||
let entries = vec![
|
||||
history(
|
||||
"recording",
|
||||
Item::user_message("record-only"),
|
||||
Some(HistoryInputMetadata::new(usage(true, false, false), None, None).unwrap()),
|
||||
),
|
||||
history(
|
||||
"memory",
|
||||
Item::user_message("memory-only"),
|
||||
Some(HistoryInputMetadata::new(usage(false, true, false), None, None).unwrap()),
|
||||
),
|
||||
history(
|
||||
"observation",
|
||||
Item::user_message("observation-only"),
|
||||
Some(HistoryInputMetadata::new(usage(false, false, true), None, None).unwrap()),
|
||||
),
|
||||
];
|
||||
let capture = SessionCapture::from_complete_history("synthetic-session", "selected", entries);
|
||||
let mut dto = capture.to_dto();
|
||||
// The checked boundary also accepts entries retained from different original segments.
|
||||
dto.entries[0].source.segment_id = "original-a".into();
|
||||
dto.entries[0].source.entry_index = 80;
|
||||
dto.entries[1].source.segment_id = "original-b".into();
|
||||
dto.entries[1].source.entry_index = 3;
|
||||
let capture = SessionCapture::try_from_dto(dto.clone(), CaptureLimits::default()).unwrap();
|
||||
let encoded = capture.encode(CaptureLimits::default()).unwrap();
|
||||
let restored = SessionCapture::decode(&encoded, CaptureLimits::default()).unwrap();
|
||||
assert_eq!(restored.to_dto(), dto);
|
||||
assert_eq!(restored.capture_id(), capture.capture_id());
|
||||
for (id, allowed) in [
|
||||
("Erecording", CapturePurpose::Recording),
|
||||
("Ememory", CapturePurpose::MemoryEvidence),
|
||||
("Eobservation", CapturePurpose::Observation),
|
||||
] {
|
||||
let reference = reference(&capture, id);
|
||||
assert_eq!(
|
||||
restored.resolve_ref(&reference, allowed).unwrap(),
|
||||
capture.resolve_ref(&reference, allowed).unwrap()
|
||||
);
|
||||
for purpose in [
|
||||
CapturePurpose::Recording,
|
||||
CapturePurpose::MemoryEvidence,
|
||||
CapturePurpose::Observation,
|
||||
] {
|
||||
assert_eq!(
|
||||
restored.resolve_ref(&reference, purpose).is_ok(),
|
||||
purpose == allowed
|
||||
);
|
||||
}
|
||||
}
|
||||
assert_eq!(restored.overview().len(), 1);
|
||||
assert_eq!(restored.search(&SearchOptions::default()).len(), 1);
|
||||
assert!(restored.evidence_for("Erecording").is_none());
|
||||
let evidence = restored.evidence_for("Ememory").unwrap();
|
||||
assert_eq!(evidence.segment_id, "original-b");
|
||||
assert_eq!(evidence.entry_range, [3, 3]);
|
||||
assert!(evidence.excerpt.contains("memory-only"));
|
||||
let recorded = restored
|
||||
.slice(CapturePurpose::Recording, None, 10, 16_000)
|
||||
.unwrap();
|
||||
assert_eq!(recorded.slice().items.len(), 1);
|
||||
assert_eq!(recorded.slice().items[0].text, "record-only");
|
||||
for (purpose, expected) in [
|
||||
(CapturePurpose::MemoryEvidence, "memory-only"),
|
||||
(CapturePurpose::Observation, "observation-only"),
|
||||
] {
|
||||
let slice = restored.slice(purpose, None, 10, 16_000).unwrap();
|
||||
assert_eq!(slice.slice().items.len(), 1);
|
||||
assert_eq!(slice.slice().items[0].text, expected);
|
||||
assert!(
|
||||
restored
|
||||
.read_raw(
|
||||
&reference(&restored, "Erecording"),
|
||||
purpose,
|
||||
RawField::MessagePart(0),
|
||||
0,
|
||||
100
|
||||
)
|
||||
.is_err()
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn common_data_drops_reasoning_raw_system_and_private_payload_even_when_unindexed() {
|
||||
let payload = FeatureInputPayload::encode(
|
||||
"capture-test",
|
||||
1,
|
||||
&serde_json::json!({"secret": "PRIVATE-PAYLOAD"}),
|
||||
)
|
||||
.unwrap();
|
||||
let public = PublicSystemItem {
|
||||
kind: "notice".into(),
|
||||
body: "public notice".into(),
|
||||
presentation: PublicSystemPresentation::Ignored,
|
||||
};
|
||||
let system =
|
||||
HistoryInputMetadata::new(usage(true, true, true), Some(payload.clone()), Some(public))
|
||||
.unwrap();
|
||||
let private = HistoryInputMetadata::new(usage(true, true, true), Some(payload), None).unwrap();
|
||||
let capture = SessionCapture::from_complete_history(
|
||||
"s",
|
||||
"segment",
|
||||
vec![
|
||||
history("raw", Item::system_message("RAW-SYSTEM-PROMPT"), None),
|
||||
history("reasoning", Item::reasoning("HIDDEN-REASONING"), None),
|
||||
history(
|
||||
"private",
|
||||
Item::system_message("PRIVATE-SYSTEM-BODY"),
|
||||
Some(private),
|
||||
),
|
||||
history(
|
||||
"public",
|
||||
Item::system_message("MODEL-SYSTEM-BODY"),
|
||||
Some(system),
|
||||
),
|
||||
history("ordinary", Item::user_message("ordinary"), None),
|
||||
],
|
||||
);
|
||||
let encoded = String::from_utf8(capture.encode(CaptureLimits::default()).unwrap()).unwrap();
|
||||
let retained_debug = format!("{capture:?}");
|
||||
for secret in [
|
||||
"RAW-SYSTEM-PROMPT",
|
||||
"HIDDEN-REASONING",
|
||||
"PRIVATE-SYSTEM-BODY",
|
||||
"MODEL-SYSTEM-BODY",
|
||||
"PRIVATE-PAYLOAD",
|
||||
] {
|
||||
assert!(!encoded.contains(secret));
|
||||
assert!(!retained_debug.contains(secret));
|
||||
}
|
||||
assert_eq!(capture.to_dto().entries.len(), 2);
|
||||
assert!(encoded.contains("public notice"));
|
||||
// Filtered entries do not renumber the public source positions.
|
||||
assert_eq!(capture.to_dto().entries[0].order, 3);
|
||||
assert_eq!(
|
||||
capture.view_order_for_ref(&SessionEntryRef::parse("Eordinary").unwrap()),
|
||||
Some(4)
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn protocol_projection_does_not_invent_recording_permission() {
|
||||
let capture = SessionCapture::from_session_snapshot(
|
||||
"s",
|
||||
"seg",
|
||||
SessionSnapshot {
|
||||
pending_submissions: Default::default(),
|
||||
entries: vec![SessionSnapshotEntry {
|
||||
entry_id: "projected".into(),
|
||||
timestamp: 0,
|
||||
provenance: SessionEntryProvenance::HumanInput,
|
||||
derived_from: vec!["source".into()],
|
||||
use_policy: Some(protocol::SessionEntryUsePolicy {
|
||||
observation_readable: true,
|
||||
memory_evidence: false,
|
||||
}),
|
||||
data: SessionSnapshotEntryData::Message {
|
||||
role: protocol::SessionMessageRole::User,
|
||||
content: vec![protocol::SessionContentPart::Text {
|
||||
text: "projected".into(),
|
||||
}],
|
||||
},
|
||||
}],
|
||||
},
|
||||
);
|
||||
let reference = reference(&capture, "Eprojected");
|
||||
assert!(matches!(
|
||||
capture.resolve_ref(&reference, CapturePurpose::Recording),
|
||||
Err(CaptureError::PolicyDenied)
|
||||
));
|
||||
assert!(
|
||||
capture
|
||||
.resolve_ref(&reference, CapturePurpose::Observation)
|
||||
.is_ok()
|
||||
);
|
||||
assert!(capture.evidence_for("Eprojected").is_none());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn malformed_dtos_and_oversized_representations_are_rejected() {
|
||||
let capture = SessionCapture::new("s", "seg", vec![Item::user_message("body")]);
|
||||
let original = serde_json::to_value(capture.to_dto()).unwrap();
|
||||
let mut invalids = Vec::new();
|
||||
let mut value = original.clone();
|
||||
value["version"] = 999.into();
|
||||
invalids.push(value);
|
||||
let mut value = original.clone();
|
||||
value["unexpected"] = true.into();
|
||||
invalids.push(value);
|
||||
let mut value = original.clone();
|
||||
value["entries"][0]["policy"]["recording_material"] = "include".into();
|
||||
invalids.push(value);
|
||||
let mut value = original.clone();
|
||||
value["entries"][0]["policy"]
|
||||
.as_object_mut()
|
||||
.unwrap()
|
||||
.remove("memory_evidence");
|
||||
invalids.push(value);
|
||||
let mut value = original.clone();
|
||||
value["entries"][0]["body"] = serde_json::json!({"kind":"reasoning","text":"secret"});
|
||||
invalids.push(value);
|
||||
let mut value = original.clone();
|
||||
value["entries"][0]["body"]["feature_payload"] = serde_json::json!({"private":true});
|
||||
invalids.push(value);
|
||||
let mut value = original.clone();
|
||||
value["entries"][0]["body"]["role"] = "system".into();
|
||||
invalids.push(value);
|
||||
let mut value = original.clone();
|
||||
value["entries"][0]["source"]["unknown"] = true.into();
|
||||
invalids.push(value);
|
||||
let mut value = original.clone();
|
||||
value["entries"][0]["source"]["history_origin"] =
|
||||
serde_json::json!({"kind":"legacy_unknown","unknown":true});
|
||||
invalids.push(value);
|
||||
let mut value = original.clone();
|
||||
value["entries"][0]["entry_id"] = "bad/id".into();
|
||||
invalids.push(value);
|
||||
let mut value = original.clone();
|
||||
value["entries"]
|
||||
.as_array_mut()
|
||||
.unwrap()
|
||||
.push(original["entries"][0].clone());
|
||||
invalids.push(value);
|
||||
for invalid in invalids {
|
||||
let bytes = serde_json::to_vec(&invalid).unwrap();
|
||||
assert!(
|
||||
SessionCapture::decode(&bytes, CaptureLimits::default()).is_err(),
|
||||
"accepted {invalid}"
|
||||
);
|
||||
}
|
||||
let bytes = capture.encode(CaptureLimits::default()).unwrap();
|
||||
assert!(
|
||||
SessionCapture::decode(
|
||||
&bytes,
|
||||
CaptureLimits {
|
||||
max_bytes: bytes.len() - 1,
|
||||
..CaptureLimits::default()
|
||||
}
|
||||
)
|
||||
.is_err()
|
||||
);
|
||||
assert!(
|
||||
capture
|
||||
.encode(CaptureLimits {
|
||||
max_entries: 0,
|
||||
..CaptureLimits::default()
|
||||
})
|
||||
.is_err()
|
||||
);
|
||||
assert!(
|
||||
capture
|
||||
.encode(CaptureLimits {
|
||||
max_text_bytes: 3,
|
||||
..CaptureLimits::default()
|
||||
})
|
||||
.is_err()
|
||||
);
|
||||
let mut reversed = capture.to_dto();
|
||||
reversed.view_entry_count = 2;
|
||||
let mut second = reversed.entries[0].clone();
|
||||
second.entry_id = "second".into();
|
||||
second.source.entry_index = 4;
|
||||
second.order = 0;
|
||||
reversed.entries[0].order = 1;
|
||||
reversed.entries.push(second);
|
||||
assert!(SessionCapture::try_from_dto(reversed, CaptureLimits::default()).is_err());
|
||||
let mut duplicate_source = capture.to_dto();
|
||||
duplicate_source.view_entry_count = 2;
|
||||
let mut second = duplicate_source.entries[0].clone();
|
||||
second.entry_id = "distinct-id".into();
|
||||
second.order = 1;
|
||||
duplicate_source.entries.push(second);
|
||||
assert!(matches!(
|
||||
SessionCapture::try_from_dto(duplicate_source, CaptureLimits::default()),
|
||||
Err(CaptureError::Invalid("duplicate source position"))
|
||||
));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn raw_utf8_tool_input_and_result_are_lossless_without_preview_markers() {
|
||||
let arguments = "\"quoted\"\\path\n日本語🙂".repeat(300);
|
||||
let result = "result\n\t\\\"λ🙂".repeat(400);
|
||||
let capture = SessionCapture::new(
|
||||
"s",
|
||||
"seg",
|
||||
vec![
|
||||
Item::tool_call("call", "tool", arguments.clone()),
|
||||
Item::tool_result_item("call", "summary", Some(result.clone()), false),
|
||||
],
|
||||
);
|
||||
for (id, field, expected) in [
|
||||
("E00000000", RawField::ToolArguments, arguments),
|
||||
("E00000001", RawField::ToolContent, result),
|
||||
] {
|
||||
let reference = reference(&capture, id);
|
||||
let mut offset = 0;
|
||||
let mut actual = String::new();
|
||||
loop {
|
||||
let part = capture
|
||||
.read_raw(&reference, CapturePurpose::Observation, field, offset, 17)
|
||||
.unwrap();
|
||||
assert!(part.text.len() <= 17);
|
||||
assert_eq!(part.offset, offset);
|
||||
actual.push_str(&part.text);
|
||||
match part.next_offset {
|
||||
Some(next) => {
|
||||
assert!(next > offset);
|
||||
offset = next;
|
||||
}
|
||||
None => break,
|
||||
}
|
||||
}
|
||||
assert_eq!(actual, expected);
|
||||
}
|
||||
let unicode = SessionCapture::new("s", "seg", vec![Item::tool_call("call", "tool", "🙂")]);
|
||||
let reference = reference(&unicode, "E00000000");
|
||||
assert!(matches!(
|
||||
unicode.read_raw(
|
||||
&reference,
|
||||
CapturePurpose::Observation,
|
||||
RawField::ToolArguments,
|
||||
1,
|
||||
8
|
||||
),
|
||||
Err(CaptureError::InvalidRange)
|
||||
));
|
||||
assert!(matches!(
|
||||
unicode.read_raw(
|
||||
&reference,
|
||||
CapturePurpose::Observation,
|
||||
RawField::ToolArguments,
|
||||
0,
|
||||
3
|
||||
),
|
||||
Err(CaptureError::BudgetTooSmall)
|
||||
));
|
||||
assert!(matches!(
|
||||
unicode.read_raw(
|
||||
&reference,
|
||||
CapturePurpose::Observation,
|
||||
RawField::ToolArguments,
|
||||
5,
|
||||
8
|
||||
),
|
||||
Err(CaptureError::InvalidRange)
|
||||
));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn escaped_json_slice_budget_includes_metadata_and_bound_continuation() {
|
||||
let body = "\"\\\n\t🙂日本語".repeat(500);
|
||||
let capture = SessionCapture::new(
|
||||
"synthetic-session",
|
||||
"segment",
|
||||
vec![Item::tool_call("call", "tool", body.clone())],
|
||||
);
|
||||
let other_session = SessionCapture::new(
|
||||
"other-session",
|
||||
"segment",
|
||||
vec![Item::tool_call("call", "tool", body.clone())],
|
||||
);
|
||||
let changed = SessionCapture::new(
|
||||
"synthetic-session",
|
||||
"segment",
|
||||
vec![Item::tool_call("call", "tool", "changed")],
|
||||
);
|
||||
let mut cursor = None;
|
||||
let mut actual = String::new();
|
||||
let budget = 1400;
|
||||
loop {
|
||||
let part = capture
|
||||
.slice(CapturePurpose::Recording, cursor.as_ref(), 1, budget)
|
||||
.unwrap();
|
||||
assert!(part.encoded_len() <= budget);
|
||||
assert_eq!(part.encoded_len(), part.as_json().len());
|
||||
assert_eq!(serde_json::to_vec(part.slice()).unwrap(), part.as_json());
|
||||
assert_eq!(part.slice().items.len(), 1);
|
||||
let item = &part.slice().items[0];
|
||||
assert_eq!(item.offset, actual.len());
|
||||
actual.push_str(&item.text);
|
||||
cursor = part.slice().next_cursor.clone();
|
||||
if let Some(cursor) = &cursor {
|
||||
assert!(matches!(
|
||||
other_session.slice(CapturePurpose::Recording, Some(cursor), 1, budget),
|
||||
Err(CaptureError::ForeignReference)
|
||||
));
|
||||
assert!(matches!(
|
||||
changed.slice(CapturePurpose::Recording, Some(cursor), 1, budget),
|
||||
Err(CaptureError::ForeignReference)
|
||||
));
|
||||
assert!(matches!(
|
||||
capture.slice(CapturePurpose::Observation, Some(cursor), 1, budget),
|
||||
Err(CaptureError::ForeignReference)
|
||||
));
|
||||
} else {
|
||||
break;
|
||||
}
|
||||
}
|
||||
assert_eq!(actual, body);
|
||||
assert!(matches!(
|
||||
capture.slice(CapturePurpose::Recording, None, 1, 8),
|
||||
Err(CaptureError::BudgetTooSmall)
|
||||
));
|
||||
assert!(matches!(
|
||||
capture.slice(CapturePurpose::Recording, None, 0, budget),
|
||||
Err(CaptureError::BudgetTooSmall)
|
||||
));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn snapshot_immutability_and_scoped_operations_reject_foreign_or_unknown_refs_and_bad_ranges() {
|
||||
let mut source = vec![
|
||||
Item::user_message("before"),
|
||||
Item::assistant_message("answer"),
|
||||
];
|
||||
let capture = SessionCapture::new("s", "seg", source.clone());
|
||||
let fixed_bytes = capture.encode(CaptureLimits::default()).unwrap();
|
||||
let first = reference(&capture, "E00000000");
|
||||
let second = reference(&capture, "E00000001");
|
||||
source.push(Item::user_message("appended"));
|
||||
source[0] = Item::user_message("compacted");
|
||||
source.clear();
|
||||
assert_eq!(
|
||||
capture.encode(CaptureLimits::default()).unwrap(),
|
||||
fixed_bytes
|
||||
);
|
||||
assert_eq!(
|
||||
capture.clone().encode(CaptureLimits::default()).unwrap(),
|
||||
fixed_bytes
|
||||
);
|
||||
let foreign = SessionCapture::new(
|
||||
"different",
|
||||
"seg",
|
||||
vec![
|
||||
Item::user_message("before"),
|
||||
Item::assistant_message("answer"),
|
||||
],
|
||||
);
|
||||
assert!(matches!(
|
||||
foreign.resolve_ref(&first, CapturePurpose::Observation),
|
||||
Err(CaptureError::ForeignReference)
|
||||
));
|
||||
assert!(matches!(
|
||||
capture.checked_range(&second, &first, CapturePurpose::Observation),
|
||||
Err(CaptureError::InvalidRange)
|
||||
));
|
||||
assert_eq!(
|
||||
capture
|
||||
.checked_range(&first, &second, CapturePurpose::Observation)
|
||||
.unwrap()
|
||||
.len(),
|
||||
2
|
||||
);
|
||||
let unknown = SessionEntryRef::parse("E99999999").unwrap();
|
||||
assert_eq!(capture.view_order_for_ref(&unknown), None);
|
||||
assert!(matches!(
|
||||
capture.scoped_ref(&unknown),
|
||||
Err(CaptureError::UnknownReference)
|
||||
));
|
||||
assert!(
|
||||
capture
|
||||
.search_checked(&SearchOptions {
|
||||
from: Some(unknown.clone()),
|
||||
..Default::default()
|
||||
})
|
||||
.is_err()
|
||||
);
|
||||
assert!(
|
||||
capture
|
||||
.search(&SearchOptions {
|
||||
through: Some(unknown),
|
||||
..Default::default()
|
||||
})
|
||||
.is_empty()
|
||||
);
|
||||
assert!(
|
||||
capture
|
||||
.read_checked(ReadSelector::EntryRange([1, 0]), ReadOptions::default())
|
||||
.is_err()
|
||||
);
|
||||
assert!(
|
||||
capture
|
||||
.read_checked(ReadSelector::EntryRange([0, 99]), ReadOptions::default())
|
||||
.is_err()
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn slices_preserve_empty_and_long_result_fields_under_item_and_metadata_budgets() {
|
||||
let summary = "summary\n\"🙂".repeat(100);
|
||||
let content = "content\t\\日本語".repeat(200);
|
||||
let capture = SessionCapture::new(
|
||||
"s",
|
||||
"seg",
|
||||
vec![
|
||||
Item::tool_result_item("first", summary.clone(), Some(content.clone()), true),
|
||||
Item::tool_result_item("empty", "", Some(String::new()), false),
|
||||
],
|
||||
);
|
||||
let mut cursor = None;
|
||||
let mut fields: Vec<(String, RawField, String)> = Vec::new();
|
||||
loop {
|
||||
let part = capture
|
||||
.slice(CapturePurpose::Recording, cursor.as_ref(), 2, 1500)
|
||||
.unwrap();
|
||||
assert!(part.slice().items.len() <= 2);
|
||||
assert!(serde_json::to_vec(part.slice()).unwrap().len() <= 1500);
|
||||
for item in &part.slice().items {
|
||||
let id = item.reference.entry_ref.to_string();
|
||||
if let Some((last_id, last_field, text)) = fields.last_mut() {
|
||||
if *last_id == id && *last_field == item.field {
|
||||
assert_eq!(text.len(), item.offset);
|
||||
text.push_str(&item.text);
|
||||
continue;
|
||||
}
|
||||
}
|
||||
assert_eq!(item.offset, 0);
|
||||
fields.push((id, item.field, item.text.clone()));
|
||||
}
|
||||
cursor = part.slice().next_cursor.clone();
|
||||
if cursor.is_none() {
|
||||
break;
|
||||
}
|
||||
}
|
||||
assert_eq!(
|
||||
fields,
|
||||
vec![
|
||||
("E00000000".into(), RawField::ToolSummary, summary),
|
||||
("E00000000".into(), RawField::ToolContent, content),
|
||||
("E00000001".into(), RawField::ToolSummary, String::new()),
|
||||
("E00000001".into(), RawField::ToolContent, String::new()),
|
||||
]
|
||||
);
|
||||
let metadata_heavy = SessionCapture::new(
|
||||
"s",
|
||||
"seg",
|
||||
vec![Item::tool_call("call", "name".repeat(200), "x")],
|
||||
);
|
||||
assert!(matches!(
|
||||
metadata_heavy.slice(CapturePurpose::Recording, None, 1, 700),
|
||||
Err(CaptureError::BudgetTooSmall)
|
||||
));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn evidence_uses_original_segment_positions_after_roundtrip_and_view_selection() {
|
||||
let full = SessionCapture::new(
|
||||
"s",
|
||||
"selected",
|
||||
vec![
|
||||
Item::user_message("first"),
|
||||
Item::assistant_message("second"),
|
||||
],
|
||||
);
|
||||
let mut dto = full.to_dto();
|
||||
dto.entries[0].source.segment_id = "original-a".into();
|
||||
dto.entries[0].source.entry_index = 80;
|
||||
dto.entries[1].source.segment_id = "original-b".into();
|
||||
dto.entries[1].source.entry_index = 3;
|
||||
let encoded = dto.encode(CaptureLimits::default()).unwrap();
|
||||
let restored = SessionCapture::decode(&encoded, CaptureLimits::default()).unwrap();
|
||||
for (id, segment, index, order) in [
|
||||
("E00000000", "original-a", 80, 0),
|
||||
("E00000001", "original-b", 3, 1),
|
||||
] {
|
||||
let evidence = restored.evidence_for(id).unwrap();
|
||||
assert_eq!(evidence.segment_id, segment);
|
||||
assert_eq!(evidence.entry_range, [index; 2]);
|
||||
let read = restored.read(ReadSelector::Id(id), ReadOptions::default());
|
||||
assert_eq!(read.entries[0].entry_range, [order; 2]);
|
||||
}
|
||||
let selected = restored.select_order_range(1..2).unwrap();
|
||||
assert_eq!(selected.overview()[0].entry_range, [0, 0]);
|
||||
let evidence = selected.evidence_for("E00000001").unwrap();
|
||||
assert_eq!(evidence.segment_id, "original-b");
|
||||
assert_eq!(evidence.entry_range, [3, 3]);
|
||||
let roundtrip = SessionCapture::decode(
|
||||
&selected.encode(CaptureLimits::default()).unwrap(),
|
||||
CaptureLimits::default(),
|
||||
)
|
||||
.unwrap();
|
||||
assert_eq!(roundtrip.to_dto(), selected.to_dto());
|
||||
assert_eq!(
|
||||
roundtrip.evidence_for("E00000001").unwrap().entry_range,
|
||||
[3, 3]
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn fixed_history_selection_preserves_original_coordinates_and_checks_private_position_bounds() {
|
||||
let history = vec![
|
||||
history("old", Item::user_message("old"), None),
|
||||
history("hidden", Item::reasoning("PRIVATE"), None),
|
||||
history("selected", Item::user_message("selected"), None),
|
||||
history("private-tail", Item::system_message("PRIVATE"), None),
|
||||
];
|
||||
let full = SessionCapture::from_complete_history("s", "seg", history);
|
||||
let suffix = full.select_order_range(1..4).unwrap();
|
||||
let original = full
|
||||
.entries()
|
||||
.find(|entry| entry.entry_id == "selected")
|
||||
.unwrap();
|
||||
let selected = suffix.entries().next().unwrap();
|
||||
assert_eq!(selected.entry_id, original.entry_id);
|
||||
assert_eq!(selected.source, original.source);
|
||||
assert_eq!(selected.body, original.body);
|
||||
assert_eq!(selected.policy, original.policy);
|
||||
assert!(suffix.evidence_for("Eold").is_none());
|
||||
assert_eq!(suffix.search(&SearchOptions::default()).len(), 1);
|
||||
assert_eq!(
|
||||
suffix.view_order_for_ref(&SessionEntryRef::parse("Eselected").unwrap()),
|
||||
Some(1)
|
||||
);
|
||||
assert_eq!(selected.source.entry_index, 2);
|
||||
assert_eq!(selected.order, 1);
|
||||
assert_eq!(suffix.to_dto().view_entry_count, 3);
|
||||
assert_eq!(
|
||||
suffix.evidence_for("Eselected").unwrap().entry_range,
|
||||
[2, 2]
|
||||
);
|
||||
let nested = suffix.select_order_range(1..2).unwrap();
|
||||
assert_eq!(nested.entries().next().unwrap().order, 0);
|
||||
assert_eq!(nested.entries().next().unwrap().source, original.source);
|
||||
let restored = SessionCapture::decode(
|
||||
&suffix.encode(CaptureLimits::default()).unwrap(),
|
||||
CaptureLimits::default(),
|
||||
)
|
||||
.unwrap();
|
||||
assert_eq!(restored.to_dto(), suffix.to_dto());
|
||||
assert!(full.select_order_range(4..5).is_err());
|
||||
let reversed = std::ops::Range { start: 3, end: 2 };
|
||||
assert!(full.select_order_range(reversed).is_err());
|
||||
let hidden_only = full.select_order_range(3..4).unwrap();
|
||||
assert_eq!(hidden_only.entries().len(), 0);
|
||||
assert_eq!(hidden_only.to_dto().view_entry_count, 1);
|
||||
let mut invalid = full.to_dto();
|
||||
invalid.view_entry_count = 2; // the selected entry's view order is outside this extent
|
||||
assert!(SessionCapture::try_from_dto(invalid, CaptureLimits::default()).is_err());
|
||||
assert_eq!(
|
||||
full.retain_entries(|entry| entry.entry_id == "selected")
|
||||
.entries()
|
||||
.next()
|
||||
.unwrap()
|
||||
.source,
|
||||
original.source
|
||||
);
|
||||
assert_eq!(full.to_dto().view_entry_count, 4);
|
||||
}
|
||||
@@ -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.
|
||||
|
||||
@@ -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,
|
||||
@@ -216,7 +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,
|
||||
@@ -224,11 +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());
|
||||
@@ -428,7 +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,
|
||||
@@ -436,11 +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());
|
||||
@@ -530,10 +517,7 @@ 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.
|
||||
@@ -575,6 +559,35 @@ impl StandaloneHost {
|
||||
}
|
||||
}
|
||||
|
||||
/// 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 {
|
||||
self.shutdown_timeout = shutdown_timeout;
|
||||
self
|
||||
@@ -657,9 +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 {
|
||||
@@ -702,6 +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,
|
||||
|
||||
@@ -25,7 +25,46 @@ use thiserror::Error;
|
||||
#[path = "job_store/legacy_migrations.rs"]
|
||||
mod legacy_migrations;
|
||||
|
||||
const SCHEMA_VERSION: i64 = 4;
|
||||
const SCHEMA_VERSION: i64 = 5;
|
||||
|
||||
/// Availability of the immutable input body, independent of execution outcome.
|
||||
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(rename_all = "snake_case")]
|
||||
pub enum JobInputDisposition {
|
||||
Available,
|
||||
Reclaimed,
|
||||
Erased,
|
||||
Invalidated,
|
||||
}
|
||||
|
||||
impl JobInputDisposition {
|
||||
pub fn as_str(self) -> &'static str {
|
||||
match self {
|
||||
Self::Available => "available",
|
||||
Self::Reclaimed => "reclaimed",
|
||||
Self::Erased => "erased",
|
||||
Self::Invalidated => "invalidated",
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Host-authorized retirement; erasure and legacy invalidation do not change outcomes.
|
||||
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
|
||||
pub enum JobInputRetirementReason {
|
||||
Completed,
|
||||
ExplicitErasure,
|
||||
LegacyInvalidation,
|
||||
}
|
||||
|
||||
impl JobInputRetirementReason {
|
||||
pub fn disposition(self) -> JobInputDisposition {
|
||||
match self {
|
||||
Self::Completed => JobInputDisposition::Reclaimed,
|
||||
Self::ExplicitErasure => JobInputDisposition::Erased,
|
||||
Self::LegacyInvalidation => JobInputDisposition::Invalidated,
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(rename_all = "snake_case")]
|
||||
@@ -67,7 +106,11 @@ impl JobAttemptState {
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
|
||||
pub struct JobSnapshot {
|
||||
/// Receipt metadata. After retirement `input` is null; use the verified loader to execute.
|
||||
pub request: JobRequest,
|
||||
pub input_digest: String,
|
||||
pub intent_fingerprint: String,
|
||||
pub input_disposition: JobInputDisposition,
|
||||
/// Durable Host-issued domain delegation, not model input or Profile identity.
|
||||
pub domain_grant: Option<Value>,
|
||||
pub state: JobState,
|
||||
@@ -77,14 +120,27 @@ pub struct JobSnapshot {
|
||||
}
|
||||
|
||||
impl JobSnapshot {
|
||||
/// Load only the original available body, checking both content and immutable intent.
|
||||
pub fn load_executable_request(&self) -> Result<&JobRequest, JobStoreError> {
|
||||
if self.input_disposition != JobInputDisposition::Available {
|
||||
return Err(JobStoreError::InvalidTransition("Job input is retired"));
|
||||
}
|
||||
self.request.validate()?;
|
||||
if self.request.input_digest()? != self.input_digest
|
||||
|| self.request.fingerprint()? != self.intent_fingerprint
|
||||
{
|
||||
return Err(JobStoreError::Corrupt(
|
||||
"immutable input or intent fingerprint mismatch".into(),
|
||||
));
|
||||
}
|
||||
Ok(&self.request)
|
||||
}
|
||||
|
||||
/// Shared Feature-facing read contract; no Workspace or execution identity leaks.
|
||||
pub fn outcome(&self) -> job::JobOutcome {
|
||||
job::JobOutcome {
|
||||
job_id: self.request.job_id.clone(),
|
||||
input_digest: self
|
||||
.request
|
||||
.input_digest()
|
||||
.expect("validated immutable Job input"),
|
||||
input_digest: self.input_digest.clone(),
|
||||
attempt_id: self.attempt.attempt_id.clone(),
|
||||
attempt: self.attempt.number,
|
||||
state: match self.state {
|
||||
@@ -204,9 +260,23 @@ impl JobStore {
|
||||
tx.execute_batch(RECONCILIATION_SCHEMA)?;
|
||||
tx.pragma_update(None, "user_version", SCHEMA_VERSION)?;
|
||||
}
|
||||
SCHEMA_VERSION => {}
|
||||
4 | SCHEMA_VERSION => {}
|
||||
other => return Err(JobStoreError::UnsupportedSchema(other)),
|
||||
}
|
||||
if version < 5 {
|
||||
tx.execute_batch(INPUT_RETENTION_SCHEMA)?;
|
||||
let has_legacy_archive: bool = tx.query_row("SELECT EXISTS(SELECT 1 FROM sqlite_schema WHERE type='table' AND name='legacy_job_archive')", [], |r| r.get(0))?;
|
||||
if has_legacy_archive {
|
||||
tx.execute_batch("DROP TRIGGER legacy_job_archive_immutable;
|
||||
CREATE TRIGGER legacy_job_archive_immutable BEFORE UPDATE OF job_id,fingerprint,attempts_json ON legacy_job_archive
|
||||
BEGIN SELECT RAISE(ABORT, 'immutable legacy Job archive'); END;
|
||||
CREATE TRIGGER legacy_job_archive_input_retirement BEFORE UPDATE OF request_json ON legacy_job_archive
|
||||
WHEN NOT EXISTS (SELECT 1 FROM job_intents WHERE job_id=OLD.job_id AND input_disposition<>'available')
|
||||
OR (json_remove(NEW.request_json,'$.input') = json_remove(OLD.request_json,'$.input') AND json_type(NEW.request_json,'$.input')='null') IS NOT TRUE
|
||||
BEGIN SELECT RAISE(ABORT, 'immutable legacy Job input'); END;")?;
|
||||
}
|
||||
tx.pragma_update(None, "user_version", SCHEMA_VERSION)?;
|
||||
}
|
||||
// An accepted result is the only evidence of success. Reserved attempts
|
||||
// were never started and remain pending; cancelled attempts never resume.
|
||||
tx.execute_batch(
|
||||
@@ -249,10 +319,7 @@ impl JobStore {
|
||||
[&request.job_id],
|
||||
|row| row.get(0),
|
||||
)?;
|
||||
if stored != fingerprint
|
||||
|| snapshot.request != request
|
||||
|| snapshot.domain_grant != grant
|
||||
{
|
||||
if stored != fingerprint || snapshot.domain_grant != grant {
|
||||
return Err(JobStoreError::IntentConflict(request.job_id));
|
||||
}
|
||||
tx.commit()?;
|
||||
@@ -334,6 +401,7 @@ impl JobStore {
|
||||
.conn
|
||||
.transaction_with_behavior(TransactionBehavior::Immediate)?;
|
||||
let previous = require_snapshot(&tx, job_id)?;
|
||||
previous.load_executable_request()?;
|
||||
if previous.state != JobState::Failed || previous.attempt.state != JobAttemptState::Failed {
|
||||
return Err(JobStoreError::InvalidTransition(
|
||||
"retry requires known failure",
|
||||
@@ -354,6 +422,81 @@ impl JobStore {
|
||||
Ok(snapshot)
|
||||
}
|
||||
|
||||
/// Historical snapshots for one domain Session, including terminal and retired Jobs.
|
||||
pub(crate) fn list_session_snapshots(
|
||||
&self,
|
||||
session_id: &str,
|
||||
after: Option<&str>,
|
||||
limit: usize,
|
||||
) -> Result<Vec<JobSnapshot>, JobStoreError> {
|
||||
let mut stmt = self.conn.prepare("SELECT i.job_id FROM job_intents i JOIN job_domain_grants g ON g.job_id=i.job_id WHERE json_extract(g.grant_json,'$.session_id')=?1 AND (?2 IS NULL OR i.job_id>?2) ORDER BY i.job_id LIMIT ?3")?;
|
||||
let ids = stmt
|
||||
.query_map(
|
||||
params![session_id, after, limit.clamp(1, 100) as i64],
|
||||
|r| r.get::<_, String>(0),
|
||||
)?
|
||||
.collect::<rusqlite::Result<Vec<_>>>()?;
|
||||
ids.into_iter()
|
||||
.map(|id| require_snapshot(&self.conn, &id))
|
||||
.collect()
|
||||
}
|
||||
|
||||
/// The Host must fence domain mutation and delivery before erasure/invalidation.
|
||||
/// This atomically prevents dispatch/retry/result acceptance, without rewriting outcome.
|
||||
pub(crate) fn reclaim_input(
|
||||
&mut self,
|
||||
job_id: &str,
|
||||
expected_input_digest: &str,
|
||||
reason: JobInputRetirementReason,
|
||||
) -> Result<JobSnapshot, JobStoreError> {
|
||||
let tx = self
|
||||
.conn
|
||||
.transaction_with_behavior(TransactionBehavior::Immediate)?;
|
||||
let snapshot = require_snapshot(&tx, job_id)?;
|
||||
if snapshot.input_digest != expected_input_digest {
|
||||
return Err(JobStoreError::DigestMismatch);
|
||||
}
|
||||
let desired = reason.disposition();
|
||||
if snapshot.input_disposition == desired {
|
||||
tx.commit()?;
|
||||
reclaim_retired_input_storage(&self.conn)?;
|
||||
return Ok(snapshot);
|
||||
}
|
||||
if reason == JobInputRetirementReason::Completed
|
||||
&& (snapshot.state != JobState::Completed
|
||||
|| snapshot.attempt.state != JobAttemptState::Completed
|
||||
|| snapshot.result.is_none())
|
||||
{
|
||||
return Err(JobStoreError::InvalidTransition(
|
||||
"reclaim requires known completed result",
|
||||
));
|
||||
}
|
||||
if snapshot.input_disposition != JobInputDisposition::Available
|
||||
&& reason != JobInputRetirementReason::ExplicitErasure
|
||||
{
|
||||
return Err(JobStoreError::InvalidTransition(
|
||||
"retired input cannot be restored or reclassified",
|
||||
));
|
||||
}
|
||||
if reason == JobInputRetirementReason::Completed {
|
||||
snapshot.load_executable_request()?;
|
||||
}
|
||||
let mut metadata = snapshot.request.clone();
|
||||
metadata.input = Value::Null;
|
||||
tx.execute(
|
||||
"UPDATE job_intents SET request_json=?2, input_disposition=?3 WHERE job_id=?1",
|
||||
params![job_id, serde_json::to_string(&metadata)?, desired.as_str()],
|
||||
)?;
|
||||
let has_legacy_archive: bool = tx.query_row("SELECT EXISTS(SELECT 1 FROM sqlite_schema WHERE type='table' AND name='legacy_job_archive')", [], |r| r.get(0))?;
|
||||
if has_legacy_archive {
|
||||
tx.execute("UPDATE legacy_job_archive SET request_json=json_set(request_json,'$.input',json('null')) WHERE job_id=?1", [job_id])?;
|
||||
}
|
||||
let snapshot = require_snapshot(&tx, job_id)?;
|
||||
tx.commit()?;
|
||||
reclaim_retired_input_storage(&self.conn)?;
|
||||
Ok(snapshot)
|
||||
}
|
||||
|
||||
pub(crate) fn get(&self, job_id: &str) -> Result<JobSnapshot, JobStoreError> {
|
||||
require_snapshot(&self.conn, job_id)
|
||||
}
|
||||
@@ -383,7 +526,7 @@ impl JobStore {
|
||||
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
|
||||
WHERE i.state = 'pending' AND a.state = 'reserved' ORDER BY i.rowid",
|
||||
WHERE i.state = 'pending' AND i.input_disposition='available' AND a.state = 'reserved' ORDER BY i.rowid",
|
||||
)?;
|
||||
let ids = statement
|
||||
.query_map([], |row| row.get::<_, String>(0))?
|
||||
@@ -406,6 +549,7 @@ impl JobStore {
|
||||
.transaction_with_behavior(TransactionBehavior::Immediate)?;
|
||||
let snapshot = require_snapshot(&tx, job_id)?;
|
||||
check_attempt(&snapshot, attempt_id)?;
|
||||
snapshot.load_executable_request()?;
|
||||
if snapshot.state != JobState::Pending
|
||||
|| snapshot.attempt.state != JobAttemptState::Reserved
|
||||
{
|
||||
@@ -447,7 +591,7 @@ impl JobStore {
|
||||
.transaction_with_behavior(TransactionBehavior::Immediate)?;
|
||||
let snapshot = require_snapshot(&tx, &bound.job_id)?;
|
||||
check_attempt(&snapshot, &bound.attempt_id)?;
|
||||
if snapshot.request.input_digest()? != bound.input_digest {
|
||||
if snapshot.input_digest != bound.input_digest {
|
||||
return Err(JobStoreError::DigestMismatch);
|
||||
}
|
||||
let (digest, encoded) =
|
||||
@@ -466,6 +610,7 @@ impl JobStore {
|
||||
tx.commit()?;
|
||||
return Ok(snapshot);
|
||||
}
|
||||
snapshot.load_executable_request()?;
|
||||
if snapshot.state != JobState::Pending
|
||||
|| snapshot.attempt.state != JobAttemptState::Dispatched
|
||||
{
|
||||
@@ -649,7 +794,7 @@ fn read_snapshot(conn: &Connection, job_id: &str) -> Result<Option<JobSnapshot>,
|
||||
let row = conn
|
||||
.query_row(
|
||||
"SELECT i.request_json, i.state, i.acknowledged, a.attempt_id, a.number,
|
||||
a.state, a.failure, a.result_json FROM job_intents i JOIN job_attempts a
|
||||
a.state, a.failure, a.result_json, a.input_digest, i.fingerprint, i.input_disposition FROM job_intents i JOIN job_attempts a
|
||||
ON a.job_id = i.job_id AND a.number = i.current_attempt WHERE i.job_id = ?1",
|
||||
[job_id],
|
||||
|row| {
|
||||
@@ -662,12 +807,27 @@ fn read_snapshot(conn: &Connection, job_id: &str) -> Result<Option<JobSnapshot>,
|
||||
row.get::<_, String>(5)?,
|
||||
row.get::<_, Option<String>>(6)?,
|
||||
row.get::<_, Option<String>>(7)?,
|
||||
row.get::<_, String>(8)?,
|
||||
row.get::<_, String>(9)?,
|
||||
row.get::<_, String>(10)?,
|
||||
))
|
||||
},
|
||||
)
|
||||
.optional()?;
|
||||
row.map(
|
||||
|(request, state, acknowledged, attempt_id, number, attempt_state, failure, result)| {
|
||||
|(
|
||||
request,
|
||||
state,
|
||||
acknowledged,
|
||||
attempt_id,
|
||||
number,
|
||||
attempt_state,
|
||||
failure,
|
||||
result,
|
||||
input_digest,
|
||||
intent_fingerprint,
|
||||
disposition,
|
||||
)| {
|
||||
let state = match state.as_str() {
|
||||
"pending" => JobState::Pending,
|
||||
"completed" => JobState::Completed,
|
||||
@@ -693,8 +853,17 @@ fn read_snapshot(conn: &Connection, job_id: &str) -> Result<Option<JobSnapshot>,
|
||||
)));
|
||||
}
|
||||
};
|
||||
let request_value: Value = serde_json::from_str(&request)?;
|
||||
if request_value.get("input").is_none() {
|
||||
return Err(JobStoreError::Corrupt(
|
||||
"stored Job input field is missing".into(),
|
||||
));
|
||||
}
|
||||
Ok(JobSnapshot {
|
||||
request: serde_json::from_str(&request)?,
|
||||
request: serde_json::from_value(request_value)?,
|
||||
input_digest,
|
||||
intent_fingerprint,
|
||||
input_disposition: serde_json::from_value(Value::String(disposition))?,
|
||||
domain_grant: conn
|
||||
.query_row(
|
||||
"SELECT grant_json FROM job_domain_grants WHERE job_id = ?1",
|
||||
@@ -719,6 +888,37 @@ fn read_snapshot(conn: &Connection, job_id: &str) -> Result<Option<JobSnapshot>,
|
||||
.transpose()
|
||||
}
|
||||
|
||||
// Retirement is already durable before this maintenance step. Failure must be
|
||||
// retried with the same Job/digest/reason; it must never restore input. VACUUM
|
||||
// removes historical free-page copies, including stores written before secure_delete.
|
||||
fn reclaim_retired_input_storage(conn: &Connection) -> Result<(), JobStoreError> {
|
||||
conn.execute_batch("PRAGMA secure_delete=ON; VACUUM;")?;
|
||||
let busy: i64 = conn.query_row("PRAGMA wal_checkpoint(TRUNCATE)", [], |r| r.get(0))?;
|
||||
if busy != 0 {
|
||||
return Err(JobStoreError::InvalidTransition(
|
||||
"input retired; SQLite body cleanup blocked by a reader, retry retirement",
|
||||
));
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
const INPUT_RETENTION_SCHEMA: &str = "
|
||||
ALTER TABLE job_intents ADD COLUMN input_disposition TEXT NOT NULL DEFAULT 'available'
|
||||
CHECK (input_disposition IN ('available','reclaimed','erased','invalidated'));
|
||||
DROP TRIGGER job_intent_immutable;
|
||||
CREATE TRIGGER job_intent_immutable BEFORE UPDATE OF
|
||||
job_id, fingerprint, serialization_key, max_concurrent ON job_intents
|
||||
BEGIN SELECT RAISE(ABORT, 'immutable Job intent'); END;
|
||||
CREATE TRIGGER job_input_retirement BEFORE UPDATE OF request_json, input_disposition ON job_intents
|
||||
WHEN (
|
||||
((OLD.input_disposition = 'available' AND NEW.input_disposition IN ('reclaimed','erased','invalidated'))
|
||||
OR (OLD.input_disposition IN ('reclaimed','invalidated') AND NEW.input_disposition = 'erased'))
|
||||
AND json_remove(NEW.request_json,'$.input') = json_remove(OLD.request_json,'$.input')
|
||||
AND json_type(NEW.request_json,'$.input') = 'null'
|
||||
) IS NOT TRUE
|
||||
BEGIN SELECT RAISE(ABORT, 'immutable Job input retirement'); END;
|
||||
";
|
||||
|
||||
const RECONCILIATION_SCHEMA: &str = "
|
||||
DROP INDEX job_serialization_singleflight;
|
||||
CREATE UNIQUE INDEX job_serialization_singleflight ON job_intents(serialization_key)
|
||||
@@ -885,7 +1085,11 @@ mod tests {
|
||||
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();
|
||||
store.conn.execute_batch("DROP TRIGGER job_input_retirement; DROP TRIGGER job_intent_immutable;
|
||||
ALTER TABLE job_intents DROP COLUMN input_disposition;
|
||||
CREATE TRIGGER job_intent_immutable BEFORE UPDATE OF job_id,request_json,fingerprint,serialization_key,max_concurrent ON job_intents
|
||||
BEGIN SELECT RAISE(ABORT, 'immutable Job intent'); END;
|
||||
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);
|
||||
@@ -911,10 +1115,7 @@ mod tests {
|
||||
JobResultSubmission {
|
||||
job_id: snapshot.request.job_id.clone(),
|
||||
attempt_id: snapshot.attempt.attempt_id.clone(),
|
||||
input_digest: snapshot
|
||||
.request
|
||||
.input_digest()
|
||||
.expect("validated immutable Job input"),
|
||||
input_digest: snapshot.input_digest.clone(),
|
||||
result,
|
||||
}
|
||||
}
|
||||
@@ -926,6 +1127,314 @@ mod tests {
|
||||
.unwrap()
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn input_reclaim_reopens_as_receipt_and_exact_replay_never_rehydrates() {
|
||||
let (dir, mut store) = fixture();
|
||||
let original = request("retained");
|
||||
let grant = Some(json!({"session_id":"session-a", "consumer":"fixture"}));
|
||||
let reserved = store
|
||||
.reserve_granted(original.clone(), grant.clone())
|
||||
.unwrap();
|
||||
let running = store
|
||||
.dispatch("retained", &reserved.attempt.attempt_id, 8)
|
||||
.unwrap();
|
||||
let result = submission(&running, json!({"saved":true}));
|
||||
let completed = store.accept(&result).unwrap();
|
||||
store.ack("retained").unwrap();
|
||||
let retired = store
|
||||
.reclaim_input(
|
||||
"retained",
|
||||
&completed.input_digest,
|
||||
JobInputRetirementReason::Completed,
|
||||
)
|
||||
.unwrap();
|
||||
assert_eq!(retired.input_disposition, JobInputDisposition::Reclaimed);
|
||||
assert!(retired.request.input.is_null());
|
||||
assert!(retired.load_executable_request().is_err());
|
||||
assert_eq!(
|
||||
retired.outcome().input_digest,
|
||||
original.input_digest().unwrap()
|
||||
);
|
||||
assert_eq!(retired.result, completed.result);
|
||||
drop(store);
|
||||
let mut reopened = JobStore::open(&dir.path().join("jobs.sqlite3")).unwrap();
|
||||
assert_eq!(
|
||||
reopened
|
||||
.reserve_granted(original.clone(), grant.clone())
|
||||
.unwrap(),
|
||||
retired
|
||||
);
|
||||
assert_eq!(reopened.accept(&result).unwrap(), retired);
|
||||
assert_eq!(
|
||||
reopened
|
||||
.list_session_snapshots("session-a", None, 1)
|
||||
.unwrap(),
|
||||
vec![retired.clone()]
|
||||
);
|
||||
assert!(
|
||||
reopened
|
||||
.list_session_snapshots("session-b", None, 100)
|
||||
.unwrap()
|
||||
.is_empty()
|
||||
);
|
||||
assert!(
|
||||
reopened
|
||||
.list_session_snapshots("session-a", Some("retained"), 100)
|
||||
.unwrap()
|
||||
.is_empty()
|
||||
);
|
||||
let mut changed = original.clone();
|
||||
changed.input = json!({"changed":true});
|
||||
assert!(matches!(
|
||||
reopened.reserve_granted(changed, grant),
|
||||
Err(JobStoreError::IntentConflict(_))
|
||||
));
|
||||
assert!(reopened.retry("retained").is_err());
|
||||
assert!(
|
||||
reopened
|
||||
.dispatch("retained", &retired.attempt.attempt_id, 8)
|
||||
.is_err()
|
||||
);
|
||||
assert!(reopened.conn.execute("UPDATE job_intents SET request_json=?1,input_disposition='available' WHERE job_id='retained'", [serde_json::to_string(&original).unwrap()]).is_err());
|
||||
let erased = reopened
|
||||
.reclaim_input(
|
||||
"retained",
|
||||
&retired.input_digest,
|
||||
JobInputRetirementReason::ExplicitErasure,
|
||||
)
|
||||
.unwrap();
|
||||
assert_eq!(erased.input_disposition, JobInputDisposition::Erased);
|
||||
assert_eq!(erased.state, JobState::Completed);
|
||||
assert!(erased.acknowledged);
|
||||
assert_eq!(
|
||||
reopened
|
||||
.reserve_granted(original, erased.domain_grant.clone())
|
||||
.unwrap(),
|
||||
erased
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn unfinished_unknown_and_failed_inputs_are_kept_until_explicit_invalidation() {
|
||||
let (_dir, mut store) = fixture();
|
||||
for (id, state) in [
|
||||
("pending", None),
|
||||
("unknown", Some(JobAttemptState::Unknown)),
|
||||
("failed", Some(JobAttemptState::Failed)),
|
||||
] {
|
||||
let original = request(id);
|
||||
let snapshot = store.reserve(original.clone()).unwrap();
|
||||
if let Some(state) = state {
|
||||
store.dispatch(id, &snapshot.attempt.attempt_id, 8).unwrap();
|
||||
store
|
||||
.finish(
|
||||
id,
|
||||
&snapshot.attempt.attempt_id,
|
||||
state,
|
||||
Some("not complete"),
|
||||
)
|
||||
.unwrap();
|
||||
}
|
||||
let before = store.get(id).unwrap();
|
||||
assert!(
|
||||
store
|
||||
.reclaim_input(
|
||||
id,
|
||||
&before.input_digest,
|
||||
JobInputRetirementReason::Completed
|
||||
)
|
||||
.is_err()
|
||||
);
|
||||
assert_eq!(store.get(id).unwrap(), before);
|
||||
assert_eq!(before.load_executable_request().unwrap(), &original);
|
||||
assert!(
|
||||
store
|
||||
.reclaim_input(id, "wrong", JobInputRetirementReason::ExplicitErasure)
|
||||
.is_err()
|
||||
);
|
||||
let retired = store
|
||||
.reclaim_input(
|
||||
id,
|
||||
&before.input_digest,
|
||||
JobInputRetirementReason::LegacyInvalidation,
|
||||
)
|
||||
.unwrap();
|
||||
assert_eq!(retired.state, before.state);
|
||||
assert_eq!(retired.attempt, before.attempt);
|
||||
assert_eq!(retired.input_disposition, JobInputDisposition::Invalidated);
|
||||
assert!(store.retry(id).is_err());
|
||||
assert!(store.dispatch(id, &before.attempt.attempt_id, 8).is_err());
|
||||
assert_eq!(store.reserve(original).unwrap(), retired);
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn erased_dispatched_input_refuses_delayed_result_without_rewriting_unknown() {
|
||||
let (dir, mut store) = fixture();
|
||||
let running = dispatched(&mut store, request("erase-running"));
|
||||
let result = submission(&running, json!({"late":true}));
|
||||
let erased = store
|
||||
.reclaim_input(
|
||||
"erase-running",
|
||||
&running.input_digest,
|
||||
JobInputRetirementReason::ExplicitErasure,
|
||||
)
|
||||
.unwrap();
|
||||
assert!(store.accept(&result).is_err());
|
||||
assert_eq!(erased.state, JobState::Pending);
|
||||
drop(store);
|
||||
let mut reopened = JobStore::open(&dir.path().join("jobs.sqlite3")).unwrap();
|
||||
let recovered = reopened.get("erase-running").unwrap();
|
||||
assert_eq!(recovered.state, JobState::Unknown);
|
||||
assert_eq!(recovered.input_disposition, JobInputDisposition::Erased);
|
||||
assert_eq!(recovered.input_digest, running.input_digest);
|
||||
assert!(reopened.accept(&result).is_err());
|
||||
assert!(reopened.retry("erase-running").is_err());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn available_input_loader_refuses_tamper_missing_body_and_envelope_changes() {
|
||||
for mutation in [
|
||||
"json_set(request_json,'$.input',json('{\"tampered\":true}'))",
|
||||
"json_remove(request_json,'$.input')",
|
||||
"json_set(request_json,'$.instruction','changed')",
|
||||
] {
|
||||
let (_dir, mut store) = fixture();
|
||||
store.reserve(request("tamper")).unwrap();
|
||||
// Simulate external corruption bypassing SQLite's normal write guard.
|
||||
store
|
||||
.conn
|
||||
.execute_batch("DROP TRIGGER job_input_retirement")
|
||||
.unwrap();
|
||||
store
|
||||
.conn
|
||||
.execute_batch(&format!("UPDATE job_intents SET request_json={mutation}"))
|
||||
.unwrap();
|
||||
match store.get("tamper") {
|
||||
Ok(snapshot) => {
|
||||
assert!(snapshot.load_executable_request().is_err());
|
||||
assert!(
|
||||
store
|
||||
.dispatch("tamper", &snapshot.attempt.attempt_id, 8)
|
||||
.is_err()
|
||||
);
|
||||
}
|
||||
Err(JobStoreError::Json(_) | JobStoreError::Corrupt(_)) => {}
|
||||
other => panic!("unexpected corrupt input read: {other:?}"),
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn input_retirement_cleanup_failure_is_durable_and_exact_retry_finishes_without_rehydration() {
|
||||
let (dir, mut store) = fixture();
|
||||
let mut original = request("physical-erasure");
|
||||
let private_body = "private-input-retirement-original-bytes".repeat(1000);
|
||||
original.input = json!({"body":private_body});
|
||||
let reserved = store.reserve(original.clone()).unwrap();
|
||||
// A reader retaining the old SQLite snapshot prevents truncation of the old WAL.
|
||||
let reader = Connection::open(dir.path().join("jobs.sqlite3")).unwrap();
|
||||
reader
|
||||
.execute_batch("BEGIN; SELECT request_json FROM job_intents;")
|
||||
.unwrap();
|
||||
store.conn.busy_timeout(std::time::Duration::ZERO).unwrap();
|
||||
assert!(
|
||||
store
|
||||
.reclaim_input(
|
||||
"physical-erasure",
|
||||
&reserved.input_digest,
|
||||
JobInputRetirementReason::ExplicitErasure
|
||||
)
|
||||
.is_err()
|
||||
);
|
||||
let retired = store.get("physical-erasure").unwrap();
|
||||
assert_eq!(retired.input_disposition, JobInputDisposition::Erased);
|
||||
assert!(retired.load_executable_request().is_err());
|
||||
reader.execute_batch("ROLLBACK").unwrap();
|
||||
drop(reader);
|
||||
let replay = store
|
||||
.reclaim_input(
|
||||
"physical-erasure",
|
||||
&reserved.input_digest,
|
||||
JobInputRetirementReason::ExplicitErasure,
|
||||
)
|
||||
.unwrap();
|
||||
assert_eq!(replay, retired);
|
||||
assert_eq!(store.reserve(original).unwrap(), retired);
|
||||
let needle = b"private-input-retirement-original-bytes";
|
||||
for entry in std::fs::read_dir(dir.path()).unwrap() {
|
||||
let path = entry.unwrap().path();
|
||||
if path.is_file() {
|
||||
let bytes = std::fs::read(&path).unwrap();
|
||||
assert!(
|
||||
!bytes.windows(needle.len()).any(|bytes| bytes == needle),
|
||||
"retired body remained in {}",
|
||||
path.display()
|
||||
);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn missing_original_null_input_is_not_treated_as_available_null() {
|
||||
let (_dir, mut store) = fixture();
|
||||
let mut original = request("null-original");
|
||||
original.input = Value::Null;
|
||||
let reserved = store.reserve(original).unwrap();
|
||||
assert!(reserved.load_executable_request().is_ok());
|
||||
store.conn.execute_batch("DROP TRIGGER job_input_retirement; UPDATE job_intents SET request_json=json_remove(request_json,'$.input')").unwrap();
|
||||
assert!(store.get("null-original").is_err());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn input_retirement_migration_preserves_receipts_and_rolls_back_failed_ddl() {
|
||||
let (dir, mut store) = fixture();
|
||||
let original = store.reserve(request("upgrade")).unwrap();
|
||||
store.conn.execute_batch("DROP TRIGGER job_input_retirement; DROP TRIGGER job_intent_immutable;
|
||||
ALTER TABLE job_intents DROP COLUMN input_disposition;
|
||||
CREATE TRIGGER job_intent_immutable BEFORE UPDATE OF job_id,request_json,fingerprint,serialization_key,max_concurrent ON job_intents
|
||||
BEGIN SELECT RAISE(ABORT, 'immutable Job intent'); END;
|
||||
PRAGMA user_version=4;
|
||||
CREATE TRIGGER job_input_retirement BEFORE UPDATE ON job_attempts BEGIN SELECT RAISE(ABORT,'collision'); END;").unwrap();
|
||||
drop(store);
|
||||
let path = dir.path().join("jobs.sqlite3");
|
||||
assert!(JobStore::open(&path).is_err());
|
||||
let conn = Connection::open(&path).unwrap();
|
||||
let version: i64 = conn
|
||||
.pragma_query_value(None, "user_version", |r| r.get(0))
|
||||
.unwrap();
|
||||
assert_eq!(version, 4);
|
||||
let present: bool = conn.query_row("SELECT EXISTS(SELECT 1 FROM pragma_table_info('job_intents') WHERE name='input_disposition')",[],|r|r.get(0)).unwrap();
|
||||
assert!(!present);
|
||||
conn.execute_batch("DROP TRIGGER job_input_retirement")
|
||||
.unwrap();
|
||||
drop(conn);
|
||||
let mut reopened = JobStore::open(&path).unwrap();
|
||||
assert_eq!(reopened.get("upgrade").unwrap(), original);
|
||||
assert_eq!(
|
||||
reopened
|
||||
.get("upgrade")
|
||||
.unwrap()
|
||||
.load_executable_request()
|
||||
.unwrap(),
|
||||
&request("upgrade")
|
||||
);
|
||||
let retired = reopened
|
||||
.reclaim_input(
|
||||
"upgrade",
|
||||
&original.input_digest,
|
||||
JobInputRetirementReason::ExplicitErasure,
|
||||
)
|
||||
.unwrap();
|
||||
assert_eq!(retired.state, JobState::Pending);
|
||||
assert!(
|
||||
reopened
|
||||
.conn
|
||||
.execute_batch("UPDATE job_intents SET input_disposition='available'")
|
||||
.is_err()
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn database_configuration_schema_and_identity_constraints() {
|
||||
let (_dir, mut store) = fixture();
|
||||
|
||||
@@ -143,6 +143,42 @@ mod tests {
|
||||
(original, receipt, grant)
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn legacy_archive_input_erasure_preserves_fingerprints_and_attempt_receipts() {
|
||||
let dir = tempfile::tempdir().unwrap();
|
||||
let path = dir.path().join("jobs.sqlite3");
|
||||
seed(&path, 2);
|
||||
let mut store = JobStore::open(&path).unwrap();
|
||||
let before: (String, String) = store
|
||||
.conn
|
||||
.query_row(
|
||||
"SELECT fingerprint,attempts_json FROM legacy_job_archive WHERE job_id='done'",
|
||||
[],
|
||||
|r| Ok((r.get(0)?, r.get(1)?)),
|
||||
)
|
||||
.unwrap();
|
||||
let snapshot = store.get("done").unwrap();
|
||||
store
|
||||
.reclaim_input(
|
||||
"done",
|
||||
&snapshot.input_digest,
|
||||
JobInputRetirementReason::ExplicitErasure,
|
||||
)
|
||||
.unwrap();
|
||||
let (body, fingerprint, attempts): (String,String,String) = store.conn.query_row("SELECT request_json,fingerprint,attempts_json FROM legacy_job_archive WHERE job_id='done'",[],|r|Ok((r.get(0)?,r.get(1)?,r.get(2)?))).unwrap();
|
||||
assert!(serde_json::from_str::<Value>(&body).unwrap()["input"].is_null());
|
||||
assert_eq!((fingerprint, attempts), before);
|
||||
assert!(store.conn.execute_batch("UPDATE legacy_job_archive SET request_json=json_set(request_json,'$.input','restored') WHERE job_id='done'").is_err());
|
||||
drop(store);
|
||||
let mut reopened = JobStore::open(&path).unwrap();
|
||||
let receipt = reopened
|
||||
.reserve_granted(request("done"), snapshot.domain_grant)
|
||||
.unwrap();
|
||||
assert_eq!(receipt.state, JobState::Completed);
|
||||
assert_eq!(receipt.input_disposition, JobInputDisposition::Erased);
|
||||
assert!(receipt.load_executable_request().is_err());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn legacy_versions_preserve_intent_receipts_attempts_grants_and_replay() {
|
||||
for version in [1, 2] {
|
||||
|
||||
+113
-48
@@ -26,7 +26,10 @@ use job::{JobRequest, JobResultSubmission};
|
||||
use tokio::sync::watch;
|
||||
|
||||
use crate::job_store::JobStore;
|
||||
pub use crate::job_store::{JobAttempt, JobAttemptState, JobSnapshot, JobState, JobStoreError};
|
||||
pub use crate::job_store::{
|
||||
JobAttempt, JobAttemptState, JobInputDisposition, JobInputRetirementReason, JobSnapshot,
|
||||
JobState, JobStoreError,
|
||||
};
|
||||
|
||||
#[derive(Debug, thiserror::Error)]
|
||||
pub enum JobServiceError {
|
||||
@@ -40,6 +43,8 @@ pub enum JobServiceError {
|
||||
Capacity,
|
||||
#[error("standalone Job cleanup failed: {0}")]
|
||||
Cleanup(String),
|
||||
#[error("standalone Job shutdown is incomplete; execution resources are still owned")]
|
||||
ShutdownIncomplete,
|
||||
}
|
||||
|
||||
pub(crate) trait JobAttemptFence: Send + Sync {
|
||||
@@ -173,6 +178,36 @@ impl StandaloneJobs {
|
||||
Ok(self.with_store(|store| store.reserve(request))?)
|
||||
}
|
||||
|
||||
/// Enumerate historical domain snapshots for a Session, including retired input receipts.
|
||||
pub fn list_session_snapshots(
|
||||
&self,
|
||||
session_id: &str,
|
||||
after: Option<&str>,
|
||||
limit: usize,
|
||||
) -> Result<Vec<JobSnapshot>, JobServiceError> {
|
||||
self.with_store(|store| store.list_session_snapshots(session_id, after, limit))
|
||||
}
|
||||
|
||||
/// Retire body only. The caller fences domain effects/delivered snapshots before erasure.
|
||||
/// Normal reclamation also requires that execution cleanup has finished.
|
||||
pub fn reclaim_input(
|
||||
&self,
|
||||
job_id: &str,
|
||||
expected_input_digest: &str,
|
||||
reason: JobInputRetirementReason,
|
||||
) -> Result<JobSnapshot, JobServiceError> {
|
||||
let executions = self.executions.lock().expect("Job executions poisoned");
|
||||
if reason == JobInputRetirementReason::Completed
|
||||
&& executions
|
||||
.jobs
|
||||
.get(job_id)
|
||||
.is_some_and(|execution| !execution.task.is_finished())
|
||||
{
|
||||
return Err(JobServiceError::Capacity);
|
||||
}
|
||||
self.with_store(|store| store.reclaim_input(job_id, expected_input_digest, reason))
|
||||
}
|
||||
|
||||
pub fn get(&self, job_id: &str) -> Result<JobSnapshot, JobServiceError> {
|
||||
Ok(self.with_store(|store| store.get(job_id))?)
|
||||
}
|
||||
@@ -274,6 +309,12 @@ impl StandaloneJobs {
|
||||
job_id: &str,
|
||||
client: Option<Box<dyn LlmClient>>,
|
||||
) -> Result<(), JobServiceError> {
|
||||
// Preparation owns copies of the immutable input and domain adapter too. Exclude
|
||||
// owner shutdown before creating them, not only before publishing the task.
|
||||
let mut executions = self.executions.lock().expect("Job executions poisoned");
|
||||
if executions.closed {
|
||||
return Err(JobServiceError::Closed);
|
||||
}
|
||||
let client = client.or_else(|| {
|
||||
self.model_client
|
||||
.lock()
|
||||
@@ -282,16 +323,14 @@ impl StandaloneJobs {
|
||||
.map(|c| c.clone_boxed())
|
||||
});
|
||||
let snapshot = self.get(job_id)?;
|
||||
snapshot.load_executable_request()?;
|
||||
let timeout = Duration::from_secs(u64::from(snapshot.request.limits.timeout_seconds));
|
||||
let deadline = tokio::time::Instant::now() + timeout;
|
||||
let fence: Arc<dyn JobAttemptFence> = Arc::new(BoundAttemptFence {
|
||||
store: self.store.clone(),
|
||||
job_id: job_id.into(),
|
||||
attempt_id: snapshot.attempt.attempt_id.clone(),
|
||||
input_digest: snapshot
|
||||
.request
|
||||
.input_digest()
|
||||
.map_err(JobStoreError::from)?,
|
||||
input_digest: snapshot.input_digest.clone(),
|
||||
deadline,
|
||||
});
|
||||
let grant = match (
|
||||
@@ -311,10 +350,6 @@ impl StandaloneJobs {
|
||||
let prepared =
|
||||
worker::job::prepare_job_with_grant(&snapshot.request, &self.cwd, client, grant)
|
||||
.map_err(|error| JobServiceError::Configuration(error.to_string()))?;
|
||||
let mut executions = self.executions.lock().expect("Job executions poisoned");
|
||||
if executions.closed {
|
||||
return Err(JobServiceError::Closed);
|
||||
}
|
||||
executions.jobs.retain(|_, run| {
|
||||
!(run.task.is_finished() && matches!(run.complete.borrow().as_ref(), Some(Ok(()))))
|
||||
});
|
||||
@@ -367,10 +402,7 @@ impl StandaloneJobs {
|
||||
store: store.clone(),
|
||||
job_id: id.clone(),
|
||||
attempt_id: attempt_id.clone(),
|
||||
input_digest: snapshot
|
||||
.request
|
||||
.input_digest()
|
||||
.map_err(JobStoreError::from)?,
|
||||
input_digest: snapshot.input_digest.clone(),
|
||||
deadline,
|
||||
});
|
||||
let (cancel, mut cancellation) = watch::channel(false);
|
||||
@@ -446,23 +478,25 @@ impl StandaloneJobs {
|
||||
.clone()
|
||||
.expect("completion");
|
||||
result.map_err(JobServiceError::Cleanup)?;
|
||||
let task = {
|
||||
let mut executions = self.executions.lock().expect("Job executions poisoned");
|
||||
if executions
|
||||
.jobs
|
||||
.get(job_id)
|
||||
.is_some_and(|run| run.attempt_id == attempt)
|
||||
{
|
||||
executions.jobs.remove(job_id)
|
||||
} else {
|
||||
None
|
||||
}
|
||||
};
|
||||
if let Some(execution) = task {
|
||||
execution
|
||||
.task
|
||||
.await
|
||||
.map_err(|error| JobServiceError::Cleanup(error.to_string()))??;
|
||||
// Completion is published immediately before the task returns. Do not remove
|
||||
// its ownership record until the runtime confirms that return (and future drop).
|
||||
while self
|
||||
.executions
|
||||
.lock()
|
||||
.expect("Job executions poisoned")
|
||||
.jobs
|
||||
.get(job_id)
|
||||
.is_some_and(|run| run.attempt_id == attempt && !run.task.is_finished())
|
||||
{
|
||||
tokio::task::yield_now().await;
|
||||
}
|
||||
let mut executions = self.executions.lock().expect("Job executions poisoned");
|
||||
if executions
|
||||
.jobs
|
||||
.get(job_id)
|
||||
.is_some_and(|run| run.attempt_id == attempt)
|
||||
{
|
||||
executions.jobs.remove(job_id);
|
||||
}
|
||||
}
|
||||
self.get(job_id)
|
||||
@@ -476,33 +510,63 @@ impl StandaloneJobs {
|
||||
}
|
||||
}
|
||||
|
||||
pub(crate) async fn shutdown(&self) -> Result<(), JobServiceError> {
|
||||
/// Initiate owner shutdown without blocking a synchronous caller. Success confirms all
|
||||
/// local executions have returned, including request/history and Feature cleanup. An
|
||||
/// incomplete/error result retains the service resources and must retain the Host lease.
|
||||
pub(crate) fn try_shutdown(&self) -> Result<(), JobServiceError> {
|
||||
self.close();
|
||||
let tasks = {
|
||||
let mut executions = self.executions.lock().expect("Job executions poisoned");
|
||||
std::mem::take(&mut executions.jobs)
|
||||
};
|
||||
let mut error = None;
|
||||
for execution in tasks.into_values() {
|
||||
match execution.task.await {
|
||||
Ok(Ok(())) => {}
|
||||
Ok(Err(failure)) => {
|
||||
error = Some(failure);
|
||||
}
|
||||
Err(failure) => {
|
||||
error = Some(JobServiceError::Cleanup(failure.to_string()));
|
||||
let mut executions = self.executions.lock().expect("Job executions poisoned");
|
||||
for execution in executions.jobs.values() {
|
||||
if !execution.task.is_finished() {
|
||||
return Err(JobServiceError::ShutdownIncomplete);
|
||||
}
|
||||
match execution.complete.borrow().as_ref() {
|
||||
Some(Ok(())) => {}
|
||||
Some(Err(error)) => return Err(JobServiceError::Cleanup(error.clone())),
|
||||
None => {
|
||||
return Err(JobServiceError::Cleanup(
|
||||
"Internal Worker ended without cleanup confirmation".into(),
|
||||
));
|
||||
}
|
||||
}
|
||||
}
|
||||
// Close SQLite before the Host releases its lease. Cloned handles may
|
||||
// outlive the Host but cannot mutate or retain the live connection.
|
||||
executions.jobs.clear();
|
||||
// Retained external handles share these slots; they cannot retain a live store,
|
||||
// provider or model client after successful owner shutdown.
|
||||
self.store.lock().expect("Job store poisoned").take();
|
||||
self.domain.lock().expect("Job domain poisoned").take();
|
||||
self.model_client
|
||||
.lock()
|
||||
.expect("Job model transport poisoned")
|
||||
.take();
|
||||
error.map_or(Ok(()), Err)
|
||||
Ok(())
|
||||
}
|
||||
|
||||
pub(crate) async fn shutdown(&self) -> Result<(), JobServiceError> {
|
||||
self.close();
|
||||
let completions: Vec<_> = self
|
||||
.executions
|
||||
.lock()
|
||||
.expect("Job executions poisoned")
|
||||
.jobs
|
||||
.values()
|
||||
.map(|execution| execution.complete.clone())
|
||||
.collect();
|
||||
// Never take execution ownership out of the shared service across an await: a
|
||||
// cancelled shutdown future or a concurrent close must still see the barrier.
|
||||
for mut completion in completions {
|
||||
completion
|
||||
.wait_for(Option::is_some)
|
||||
.await
|
||||
.map_err(|error| JobServiceError::Cleanup(error.to_string()))?;
|
||||
}
|
||||
loop {
|
||||
match self.try_shutdown() {
|
||||
// Only the task's final return follows its completion notification.
|
||||
Err(JobServiceError::ShutdownIncomplete) => tokio::task::yield_now().await,
|
||||
result => return result,
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -574,7 +638,8 @@ impl JobAttemptFence for BoundAttemptFence {
|
||||
if snapshot.state != JobState::Pending
|
||||
|| snapshot.attempt.state != JobAttemptState::Dispatched
|
||||
|| snapshot.attempt.attempt_id != self.attempt_id
|
||||
|| snapshot.request.input_digest().map_err(|e| e.to_string())? != self.input_digest
|
||||
|| snapshot.input_digest != self.input_digest
|
||||
|| snapshot.input_disposition != JobInputDisposition::Available
|
||||
{
|
||||
return Err("Job domain grant is not bound to the current live attempt".into());
|
||||
}
|
||||
|
||||
@@ -468,3 +468,104 @@ async fn cleanup_cannot_reclassify_success_or_durable_cancellation_and_stale_han
|
||||
assert!(matches!(operation, Err(JobServiceError::Closed)));
|
||||
}
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn cancelled_shutdown_future_keeps_execution_barrier_and_unknown_input() {
|
||||
// Actual generic runner + SQLite; only the provider stream is scripted/blocked.
|
||||
let temp = tempfile::tempdir().unwrap();
|
||||
let path = temp.path().join("jobs.sqlite3");
|
||||
let jobs = StandaloneJobs::open(&path, temp.path().into()).unwrap();
|
||||
let reserved = jobs.request(request("cancel-shutdown-wait")).unwrap();
|
||||
let model = DomainTestClient {
|
||||
stall: true,
|
||||
..Default::default()
|
||||
};
|
||||
jobs.start_with_model_client(&reserved.request.job_id, model.clone())
|
||||
.await
|
||||
.unwrap();
|
||||
await_model(&model).await;
|
||||
{
|
||||
let shutdown = jobs.shutdown();
|
||||
tokio::pin!(shutdown);
|
||||
assert!(futures::poll!(shutdown.as_mut()).is_pending());
|
||||
// Drop the caller's waiter while cancellation/cleanup is still pending.
|
||||
}
|
||||
assert!(matches!(
|
||||
jobs.try_shutdown(),
|
||||
Err(JobServiceError::ShutdownIncomplete)
|
||||
));
|
||||
assert!(jobs.store.lock().unwrap().is_some());
|
||||
assert!(matches!(
|
||||
jobs.request(request("after-shutdown")),
|
||||
Err(JobServiceError::Closed)
|
||||
));
|
||||
tokio::time::timeout(Duration::from_secs(5), jobs.shutdown())
|
||||
.await
|
||||
.unwrap()
|
||||
.unwrap();
|
||||
assert!(jobs.store.lock().unwrap().is_none());
|
||||
let reopened = StandaloneJobs::open(&path, temp.path().into()).unwrap();
|
||||
let unknown = reopened.get(&reserved.request.job_id).unwrap();
|
||||
assert_eq!(unknown.attempt.state, JobAttemptState::Unknown);
|
||||
assert_eq!(unknown.input_disposition, JobInputDisposition::Available);
|
||||
assert_eq!(unknown.request, reserved.request);
|
||||
assert_eq!(unknown.input_digest, reserved.input_digest);
|
||||
assert!(reopened.retry(&unknown.request.job_id).is_err());
|
||||
reopened.shutdown().await.unwrap();
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn input_retirement_service_fences_live_attempt_and_preserves_session_receipts() {
|
||||
// Production service + SQLite + attempt/result fences, without a model or Worker fixture.
|
||||
let temp = tempfile::tempdir().unwrap();
|
||||
let path = temp.path().join("jobs.sqlite3");
|
||||
let jobs = StandaloneJobs::open(&path, temp.path().to_path_buf()).unwrap();
|
||||
let original = request("input-retirement");
|
||||
let grant = json!({"session_id":"session-a"});
|
||||
let reserved = jobs
|
||||
.request_granted(original.clone(), grant.clone())
|
||||
.unwrap();
|
||||
jobs.with_store(|store| store.dispatch("input-retirement", &reserved.attempt.attempt_id, 8))
|
||||
.unwrap();
|
||||
let fence = BoundAttemptFence {
|
||||
store: jobs.store.clone(),
|
||||
job_id: "input-retirement".into(),
|
||||
attempt_id: reserved.attempt.attempt_id.clone(),
|
||||
input_digest: reserved.input_digest.clone(),
|
||||
deadline: tokio::time::Instant::now() + Duration::from_secs(10),
|
||||
};
|
||||
assert!(fence.ensure_live().is_ok());
|
||||
assert!(
|
||||
jobs.reclaim_input(
|
||||
"input-retirement",
|
||||
&reserved.input_digest,
|
||||
JobInputRetirementReason::Completed
|
||||
)
|
||||
.is_err()
|
||||
);
|
||||
let erased = jobs
|
||||
.reclaim_input(
|
||||
"input-retirement",
|
||||
&reserved.input_digest,
|
||||
JobInputRetirementReason::ExplicitErasure,
|
||||
)
|
||||
.unwrap();
|
||||
assert!(fence.ensure_live().is_err());
|
||||
assert!(
|
||||
sink(&jobs, "input-retirement", &reserved.attempt.attempt_id)
|
||||
.submit(result("input-retirement", &reserved.attempt.attempt_id))
|
||||
.is_err()
|
||||
);
|
||||
assert!(jobs.start("input-retirement").await.is_err());
|
||||
assert_eq!(
|
||||
jobs.list_session_snapshots("session-a", None, 100).unwrap(),
|
||||
vec![erased.clone()]
|
||||
);
|
||||
assert!(
|
||||
jobs.list_session_snapshots("session-b", None, 100)
|
||||
.unwrap()
|
||||
.is_empty()
|
||||
);
|
||||
assert_eq!(jobs.request_granted(original, grant).unwrap(), erased);
|
||||
jobs.shutdown().await.unwrap();
|
||||
}
|
||||
|
||||
@@ -7,6 +7,44 @@ pub mod launch;
|
||||
pub mod store;
|
||||
pub mod subjektiv;
|
||||
mod subjektiv_sessions;
|
||||
pub mod unix;
|
||||
|
||||
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,
|
||||
|
||||
@@ -54,6 +54,8 @@ pub enum SubjectError {
|
||||
Journal(#[from] subjektiv::journal::JournalError),
|
||||
#[error(transparent)]
|
||||
Storage(#[from] feature_storage::FeatureStorageError),
|
||||
#[error("local Subject Job shutdown: {0}")]
|
||||
JobShutdown(#[from] crate::jobs::JobServiceError),
|
||||
#[error("local Subject storage metadata: {0}")]
|
||||
Json(#[from] serde_json::Error),
|
||||
#[error("local Subject storage permission or identity is invalid: {0}")]
|
||||
@@ -338,8 +340,16 @@ impl SubjectConnection {
|
||||
}
|
||||
}
|
||||
pub fn close(&mut self) -> Result<(), SubjectError> {
|
||||
self.host.jobs.lock().expect("Subject Jobs poisoned").take();
|
||||
self.host.live.store(false, Ordering::Release);
|
||||
{
|
||||
let mut jobs = self.host.jobs.lock().expect("Subject Jobs poisoned");
|
||||
if let Some(service) = jobs.as_ref() {
|
||||
// Signal cancellation, but retain the handle and exclusive lease until
|
||||
// the generic owner confirms local request/history/resource teardown.
|
||||
service.try_shutdown()?;
|
||||
}
|
||||
jobs.take();
|
||||
}
|
||||
self.host.catalog.manager.shutdown()?;
|
||||
if let Some(file) = &self.lease {
|
||||
file.unlock()?;
|
||||
@@ -840,6 +850,44 @@ impl SubjektivHost for LocalSubjectHost {
|
||||
.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)
|
||||
}
|
||||
|
||||
@@ -5,9 +5,12 @@
|
||||
//! recovery authority; shutdown does not delete either original Sessions or pending requests.
|
||||
|
||||
use super::*;
|
||||
use crate::jobs::{JobAttemptState, JobSnapshot, JobState};
|
||||
use crate::jobs::{
|
||||
JobAttemptState, JobInputDisposition, JobInputRetirementReason, JobSnapshot, JobState,
|
||||
};
|
||||
use session_store::capture::{CaptureDto, CaptureLimits, RecordingPosition};
|
||||
use subjektiv::api::JobAttemptBinding;
|
||||
use subjektiv::journal::recording::JournalMaterial;
|
||||
use subjektiv::journal::recording::JournalInput;
|
||||
use subjektiv::journal::transport::*;
|
||||
use subjektiv::journal::*;
|
||||
use worker::subjektiv::{JournalJobFinalizer, JournalJobHost, JournalJobToolsFeature};
|
||||
@@ -16,7 +19,6 @@ use worker::subjektiv::{JournalJobFinalizer, JournalJobHost, JournalJobToolsFeat
|
||||
mod tests;
|
||||
|
||||
pub(super) const PURPOSE: &str = "subjektiv_journal";
|
||||
const INPUT_BUDGET: usize = 48 * 1024;
|
||||
|
||||
#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
@@ -27,6 +29,7 @@ struct LocalJournalGrant {
|
||||
session_id: String,
|
||||
journal_id: String,
|
||||
ranges: Vec<JournalSourceRange>,
|
||||
#[serde(default, skip_serializing_if = "Vec::is_empty")]
|
||||
origins: Vec<SourceOrigin>,
|
||||
}
|
||||
#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize)]
|
||||
@@ -35,11 +38,6 @@ struct SourceOrigin {
|
||||
pointer: JournalSourcePointer,
|
||||
origin: session_store::public_material::PublicMaterialOrigin,
|
||||
}
|
||||
impl LocalJournalGrant {
|
||||
fn input(&self) -> serde_json::Value {
|
||||
serde_json::json!({"selected_ranges": self.ranges, "origins": self.origins})
|
||||
}
|
||||
}
|
||||
|
||||
impl StandaloneSubjects {
|
||||
/// Explicit operator erasure, separate from ordinary Worker removal. Requires the
|
||||
@@ -84,32 +82,29 @@ impl StandaloneSubjects {
|
||||
self.state_root.clone(),
|
||||
)
|
||||
.map_err(|error| SubjectError::InvalidScope(error.to_string()))?;
|
||||
for snapshot in jobs
|
||||
.pending()
|
||||
.map_err(|e| SubjectError::InvalidScope(e.to_string()))?
|
||||
.into_iter()
|
||||
.chain(
|
||||
jobs.unknown_granted()
|
||||
.map_err(|e| SubjectError::InvalidScope(e.to_string()))?,
|
||||
)
|
||||
{
|
||||
if snapshot.domain_grant.as_ref().is_some_and(|grant| {
|
||||
grant.get("session_id").and_then(|v| v.as_str()) == Some(session_id)
|
||||
}) {
|
||||
let mut after = None;
|
||||
loop {
|
||||
let page = jobs
|
||||
.list_session_snapshots(session_id, after.as_deref(), 100)
|
||||
.map_err(|e| SubjectError::InvalidScope(e.to_string()))?;
|
||||
if page.is_empty() {
|
||||
break;
|
||||
}
|
||||
for snapshot in &page {
|
||||
jobs.cancel(&snapshot.request.job_id)
|
||||
.map_err(|e| SubjectError::InvalidScope(e.to_string()))?;
|
||||
jobs.reclaim_input(
|
||||
&snapshot.request.job_id,
|
||||
&snapshot.input_digest,
|
||||
JobInputRetirementReason::ExplicitErasure,
|
||||
)
|
||||
.map_err(|e| SubjectError::InvalidScope(e.to_string()))?;
|
||||
if snapshot.state == JobState::Completed && !snapshot.acknowledged {
|
||||
jobs.acknowledge(&snapshot.request.job_id)
|
||||
.map_err(|e| SubjectError::InvalidScope(e.to_string()))?;
|
||||
}
|
||||
}
|
||||
}
|
||||
for snapshot in jobs
|
||||
.unacknowledged_results()
|
||||
.map_err(|e| SubjectError::InvalidScope(e.to_string()))?
|
||||
{
|
||||
if snapshot.domain_grant.as_ref().is_some_and(|grant| {
|
||||
grant.get("session_id").and_then(|v| v.as_str()) == Some(session_id)
|
||||
}) {
|
||||
jobs.acknowledge(&snapshot.request.job_id)
|
||||
.map_err(|e| SubjectError::InvalidScope(e.to_string()))?;
|
||||
}
|
||||
after = page.last().map(|job| job.request.job_id.clone());
|
||||
}
|
||||
session_store::FsStore::new_with_retention(
|
||||
path,
|
||||
@@ -590,17 +585,28 @@ impl LocalSubjectHost {
|
||||
self.ensure_live()?;
|
||||
let jobs = self.jobs()?;
|
||||
for saved in jobs.unacknowledged_results().map_err(service_error)? {
|
||||
if self.journal_grant(&saved).is_ok() {
|
||||
if self.journal_grant_scope(&saved).is_ok() {
|
||||
self.complete_journal_job(&jobs, &saved)?;
|
||||
}
|
||||
}
|
||||
for pending in jobs.pending().map_err(service_error)? {
|
||||
if self.journal_grant(&pending).is_ok() {
|
||||
if pending.request.purpose != PURPOSE {
|
||||
continue;
|
||||
}
|
||||
self.journal_grant_scope(&pending)?;
|
||||
if pending.request.input.get("capture").is_some() {
|
||||
self.journal_grant(&pending)?;
|
||||
return Ok(Some((jobs, pending.request.job_id)));
|
||||
}
|
||||
// Old descriptor jobs never acquire new execution authority. Their immutable
|
||||
// identity/input is retired, not upgraded in place; saved checkpoint wins.
|
||||
let replacement = self.replace_legacy_journal_job(&jobs, &pending)?;
|
||||
if let Some(id) = replacement {
|
||||
return Ok(Some((jobs, id)));
|
||||
}
|
||||
}
|
||||
for unknown in jobs.unknown_granted().map_err(service_error)? {
|
||||
let Ok(grant) = self.journal_grant(&unknown) else {
|
||||
let Ok(grant) = self.journal_grant_scope(&unknown) else {
|
||||
continue;
|
||||
};
|
||||
let context = authority(self, &grant.session_id)?;
|
||||
@@ -685,32 +691,96 @@ impl LocalSubjectHost {
|
||||
}
|
||||
}
|
||||
}
|
||||
let materials = self.select_journal_materials(&context, &journal.id)?;
|
||||
if materials.is_empty() {
|
||||
let mut retained = None;
|
||||
// Saved body snapshots always win over descriptor migration. In particular,
|
||||
// a failed continuation must not recapture its original text even if an
|
||||
// invalidated legacy grant still bounds a larger unprocessed suffix.
|
||||
for legacy_pass in [false, true] {
|
||||
let mut after_job = None;
|
||||
loop {
|
||||
let page = jobs
|
||||
.list_session_snapshots(
|
||||
&journal.source_session_id,
|
||||
after_job.as_deref(),
|
||||
100,
|
||||
)
|
||||
.map_err(service_error)?;
|
||||
if page.is_empty() {
|
||||
break;
|
||||
}
|
||||
for saved in &page {
|
||||
if saved.request.purpose != PURPOSE {
|
||||
continue;
|
||||
}
|
||||
let legacy = saved.input_disposition
|
||||
== JobInputDisposition::Invalidated
|
||||
|| (saved.input_disposition == JobInputDisposition::Available
|
||||
&& saved.request.input.get("capture").is_none());
|
||||
if legacy != legacy_pass
|
||||
|| (!legacy
|
||||
&& saved.input_disposition != JobInputDisposition::Available)
|
||||
{
|
||||
continue;
|
||||
}
|
||||
let saved_grant = self.journal_grant_scope(saved)?;
|
||||
if saved_grant.journal_id != journal.id {
|
||||
continue;
|
||||
}
|
||||
if legacy {
|
||||
if let Some(id) = self.replace_legacy_journal_job(&jobs, saved)? {
|
||||
return Ok(Some((jobs, id)));
|
||||
}
|
||||
continue;
|
||||
}
|
||||
self.journal_grant(saved)?;
|
||||
let original = JournalInput::decode(&saved.request.input)
|
||||
.map_err(journal_error)?;
|
||||
let continuation = self.build_journal_input(
|
||||
&context,
|
||||
&journal.id,
|
||||
Some(&original.capture),
|
||||
)?;
|
||||
if !continuation.selected_ranges.is_empty() {
|
||||
retained = Some(continuation);
|
||||
break;
|
||||
}
|
||||
if saved.state == JobState::Completed && saved.acknowledged {
|
||||
// Recover the acknowledgement-before-reclamation gap without
|
||||
// turning a retained receipt into an executable empty input.
|
||||
jobs.reclaim_input(
|
||||
&saved.request.job_id,
|
||||
&saved.input_digest,
|
||||
JobInputRetirementReason::Completed,
|
||||
)
|
||||
.map_err(service_error)?;
|
||||
}
|
||||
}
|
||||
if retained.is_some() {
|
||||
break;
|
||||
}
|
||||
after_job = page.last().map(|job| job.request.job_id.clone());
|
||||
}
|
||||
if retained.is_some() {
|
||||
break;
|
||||
}
|
||||
}
|
||||
let input = match retained {
|
||||
Some(input) => input,
|
||||
None => self.build_journal_input(&context, &journal.id, None)?,
|
||||
};
|
||||
|
||||
if input.selected_ranges.is_empty() {
|
||||
continue;
|
||||
}
|
||||
let ranges = materials
|
||||
.into_iter()
|
||||
.map(|material| material.range)
|
||||
.collect::<Vec<_>>();
|
||||
let origins = self.journal_origins(&ranges)?;
|
||||
let grant = LocalJournalGrant {
|
||||
writer_binding_id: Some(self.writer.binding_id.clone()),
|
||||
binding: self.binding.clone(),
|
||||
session_id: journal.source_session_id,
|
||||
journal_id: journal.id.clone(),
|
||||
ranges,
|
||||
origins,
|
||||
};
|
||||
let request = job::JobRequest {
|
||||
job_id: format!("subjektiv-journal:{}", uuid::Uuid::now_v7()),
|
||||
purpose: PURPOSE.into(), input_ref: format!("subjektiv://{}/journal/{}", self.binding.subject_id, journal.id),
|
||||
input: grant.input(),
|
||||
instruction: "ReadJournalState first. Input descriptors are the frozen canonical public ranges authorized for this Job, not already read material. Read every selected source byte with bounded ReadJournalText before recording; then read initial/current position and open text in bounded pages. Reconcile saved operation receipts before new creates. Save sequential Create/Rewrite/Fix and UpdateJournalPosition operations, then CheckpointJournal backed by saved record/no-change receipts for all selected input. Do not fix an ongoing event just because this Job/turn ended. SubmitJobResult with result: {} only after the entire selected prefix is reflected. Never infer tool success or user intent not evidenced by public input.".into(),
|
||||
profile: "builtin:subjektiv-journal-recording".into(),
|
||||
serialization_key: Some(format!("subjektiv-journal:{}", journal.id)),
|
||||
limits: job::JobLimits { timeout_seconds: 600, ..Default::default() },
|
||||
ranges: input.selected_ranges.clone(),
|
||||
origins: vec![],
|
||||
};
|
||||
let request = self.journal_request(&journal.id, &input)?;
|
||||
let saved = jobs
|
||||
.request_granted(
|
||||
request,
|
||||
@@ -727,6 +797,138 @@ impl LocalSubjectHost {
|
||||
}
|
||||
}
|
||||
|
||||
fn replace_legacy_journal_job(
|
||||
&self,
|
||||
jobs: &crate::jobs::StandaloneJobs,
|
||||
old: &JobSnapshot,
|
||||
) -> Result<Option<String>, SubjektivHostError> {
|
||||
let grant = self.journal_grant_scope(old)?;
|
||||
if old.input_disposition == JobInputDisposition::Available {
|
||||
old.load_executable_request()
|
||||
.map_err(|e| SubjektivHostError::InvalidArgument(e.to_string()))?;
|
||||
if old.request.input
|
||||
!= serde_json::json!({"selected_ranges":grant.ranges,"origins":grant.origins})
|
||||
{
|
||||
return Err(SubjektivHostError::InvalidArgument(
|
||||
"invalid legacy Journal descriptor input".into(),
|
||||
));
|
||||
}
|
||||
} else if old.input_disposition != JobInputDisposition::Invalidated {
|
||||
return Err(SubjektivHostError::InvalidArgument(
|
||||
"legacy Journal input is unavailable".into(),
|
||||
));
|
||||
}
|
||||
let context = authority(self, &grant.session_id)?;
|
||||
if let Some(active) = self
|
||||
.catalog
|
||||
.store
|
||||
.active_journal_generation(&context, &grant.journal_id)
|
||||
.map_err(journal_error)?
|
||||
{
|
||||
if active.job.job_id != old.request.job_id {
|
||||
return Err(SubjektivHostError::InvalidArgument(
|
||||
"another generation owns legacy migration".into(),
|
||||
));
|
||||
}
|
||||
self.catalog
|
||||
.store
|
||||
.close_journal_generation(&context, &active.id, &active.job)
|
||||
.map_err(journal_error)?;
|
||||
}
|
||||
jobs.cancel(&old.request.job_id).map_err(service_error)?;
|
||||
let current = self
|
||||
.catalog
|
||||
.store
|
||||
.read_journal(&context, &grant.journal_id)
|
||||
.map_err(journal_error)?;
|
||||
let end = grant
|
||||
.ranges
|
||||
.last()
|
||||
.ok_or_else(|| SubjektivHostError::InvalidArgument("empty legacy selection".into()))?;
|
||||
let end_position = if end.bytes.end == end.source.total_bytes {
|
||||
(end.source.order + 1, 0)
|
||||
} else {
|
||||
(end.source.order, end.bytes.end)
|
||||
};
|
||||
let replacement = if (current.process_order, current.process_byte) >= end_position {
|
||||
None
|
||||
} else {
|
||||
let mut capture = self.recording_capture(&grant.session_id)?;
|
||||
capture
|
||||
.entries
|
||||
.retain(|entry| grant.ranges.iter().any(|r| r.source.order == entry.order));
|
||||
for entry in &mut capture.entries {
|
||||
let range = grant
|
||||
.ranges
|
||||
.iter()
|
||||
.find(|r| r.source.order == entry.order)
|
||||
.unwrap();
|
||||
let session_store::capture::CaptureBody::CanonicalPublic {
|
||||
descriptor,
|
||||
byte_offset,
|
||||
text,
|
||||
..
|
||||
} = &mut entry.body
|
||||
else {
|
||||
unreachable!()
|
||||
};
|
||||
if source_descriptor(&grant.session_id, descriptor) != range.source
|
||||
|| !grant.origins.iter().any(|origin| {
|
||||
origin.pointer == range.source.pointer && origin.origin == descriptor.origin
|
||||
})
|
||||
|| !text.is_char_boundary(range.bytes.start as usize)
|
||||
|| !text.is_char_boundary(range.bytes.end as usize)
|
||||
{
|
||||
return Err(SubjektivHostError::InvalidArgument(
|
||||
"legacy original source identity/range changed".into(),
|
||||
));
|
||||
}
|
||||
*text = text[range.bytes.start as usize..range.bytes.end as usize].to_owned();
|
||||
*byte_offset = range.bytes.start;
|
||||
}
|
||||
let input = self.build_journal_input(&context, &grant.journal_id, Some(&capture))?;
|
||||
let request = self.journal_request(&grant.journal_id, &input)?;
|
||||
let next_grant = LocalJournalGrant {
|
||||
ranges: input.selected_ranges.clone(),
|
||||
origins: vec![],
|
||||
..grant
|
||||
};
|
||||
Some(
|
||||
jobs.request_granted(
|
||||
request,
|
||||
serde_json::to_value(next_grant)
|
||||
.map_err(|e| SubjektivHostError::Unavailable(e.to_string()))?,
|
||||
)
|
||||
.map_err(service_error)?
|
||||
.request
|
||||
.job_id,
|
||||
)
|
||||
};
|
||||
jobs.reclaim_input(
|
||||
&old.request.job_id,
|
||||
&old.input_digest,
|
||||
JobInputRetirementReason::LegacyInvalidation,
|
||||
)
|
||||
.map_err(service_error)?;
|
||||
Ok(replacement)
|
||||
}
|
||||
|
||||
fn journal_request(
|
||||
&self,
|
||||
journal_id: &str,
|
||||
input: &JournalInput,
|
||||
) -> Result<job::JobRequest, SubjektivHostError> {
|
||||
Ok(job::JobRequest {
|
||||
job_id: format!("subjektiv-journal:{}", uuid::Uuid::now_v7()), purpose: PURPOSE.into(),
|
||||
input_ref: format!("subjektiv://{}/journal/{journal_id}", self.binding.subject_id),
|
||||
input: serde_json::to_value(input).map_err(|e| SubjektivHostError::Unavailable(e.to_string()))?,
|
||||
instruction: "Input contains the frozen canonical public source bodies, provenance and byte ranges. Use only this saved input, never re-fetch Source. ReadJournalState first and read initial/current Journal position/open text in bounded pages if needed. Reconcile saved operation receipts before new creates. Save sequential Create/Rewrite/Fix and UpdateJournalPosition operations, then CheckpointJournal backed by saved record/no-change receipts for all selected input. Do not fix an ongoing event just because this Job/turn ended. SubmitJobResult with result: {} only after the entire selected prefix is reflected. Never infer tool success or user intent not evidenced by public input.".into(),
|
||||
profile: "builtin:subjektiv-journal-recording".into(),
|
||||
serialization_key: Some(format!("subjektiv-journal:{journal_id}")),
|
||||
limits: job::JobLimits { timeout_seconds: 600, ..Default::default() },
|
||||
})
|
||||
}
|
||||
|
||||
fn pin_journal_session(&self, session: &str) -> Result<(), SubjektivHostError> {
|
||||
let path = crate::subjektiv_sessions::authorized_sessions_path(
|
||||
&self.catalog.state_root,
|
||||
@@ -869,11 +1071,16 @@ impl LocalSubjectHost {
|
||||
Ok(())
|
||||
}
|
||||
|
||||
fn material_reader(
|
||||
fn with_recording_boundary<T>(
|
||||
&self,
|
||||
session: &str,
|
||||
) -> Result<session_store::public_material::SessionPublicMaterialReader, SubjektivHostError>
|
||||
{
|
||||
read: impl FnOnce(
|
||||
&Path,
|
||||
session_store::SessionId,
|
||||
session_store::SegmentId,
|
||||
&session_store::retention::SessionRetentionGuard,
|
||||
) -> Result<T, SubjektivHostError>,
|
||||
) -> Result<T, SubjektivHostError> {
|
||||
let sessions = crate::subjektiv_sessions::authorized_sessions_path(
|
||||
&self.catalog.state_root,
|
||||
&self.binding.scope_id,
|
||||
@@ -906,6 +1113,11 @@ impl LocalSubjectHost {
|
||||
.ok_or_else(|| SubjektivHostError::InvalidArgument("invalid Session storage".into()))?
|
||||
.join("worker")
|
||||
.join(&record.storage_key);
|
||||
let session_id = session
|
||||
.parse()
|
||||
.map_err(|_| SubjektivHostError::InvalidArgument("invalid Session".into()))?;
|
||||
let retention = crate::store::session_retention(&self.catalog.state_root);
|
||||
let guard = retention.lock_live(session_id).map_err(source_error)?;
|
||||
// This is the persisted active selector, not the newest filename/mtime or a model claim.
|
||||
let metadata =
|
||||
session_store::WorkerAggregateStore::open_read_only(metadata_root, &record.storage_key)
|
||||
@@ -933,154 +1145,203 @@ impl LocalSubjectHost {
|
||||
"no attested active lineage for the retained Session".into(),
|
||||
)
|
||||
})?;
|
||||
session_store::public_material::SessionPublicMaterialReader::open_fs_with_retention(
|
||||
&sessions,
|
||||
session
|
||||
.parse()
|
||||
.map_err(|_| SubjektivHostError::InvalidArgument("invalid Session".into()))?,
|
||||
active,
|
||||
session_store::public_material::PublicMaterialLimits {
|
||||
max_segments: 256,
|
||||
max_entries: 100_000,
|
||||
max_record_bytes: 64 * 1024 * 1024,
|
||||
},
|
||||
crate::store::session_retention(&self.catalog.state_root),
|
||||
)
|
||||
.map_err(|error| SubjektivHostError::Unavailable(error.to_string()))
|
||||
read(&sessions, session_id, active, &guard)
|
||||
}
|
||||
|
||||
fn recording_capture(&self, session: &str) -> Result<CaptureDto, SubjektivHostError> {
|
||||
self.with_recording_boundary(session, |sessions, session_id, active, guard| {
|
||||
session_store::capture::capture_recording_fs_guarded(
|
||||
sessions,
|
||||
session_id,
|
||||
active,
|
||||
session_store::public_material::PublicMaterialLimits::default(),
|
||||
CaptureLimits {
|
||||
max_bytes: 128 * 1024 * 1024,
|
||||
max_entries: 100_000,
|
||||
max_text_bytes: 64 * 1024 * 1024,
|
||||
..Default::default()
|
||||
},
|
||||
guard,
|
||||
)
|
||||
.map_err(|e| SubjektivHostError::Unavailable(e.to_string()))
|
||||
})
|
||||
}
|
||||
|
||||
fn journal_sources(
|
||||
&self,
|
||||
session: &str,
|
||||
) -> Result<Vec<JournalSourceRange>, SubjektivHostError> {
|
||||
let reader = self.material_reader(session)?;
|
||||
Ok(reader
|
||||
.descriptors()
|
||||
.map(|descriptor| JournalSourceRange {
|
||||
source: source_descriptor(session, descriptor),
|
||||
bytes: JournalByteRange {
|
||||
start: 0,
|
||||
end: descriptor.total_bytes,
|
||||
self.with_recording_boundary(session, |sessions, session_id, active, guard| {
|
||||
session_store::capture::recording_catalog_fs_guarded(
|
||||
sessions,
|
||||
session_id,
|
||||
active,
|
||||
session_store::public_material::PublicMaterialLimits::default(),
|
||||
guard,
|
||||
|descriptors| {
|
||||
descriptors
|
||||
.iter()
|
||||
.map(|descriptor| JournalSourceRange {
|
||||
source: source_descriptor(session, descriptor),
|
||||
bytes: JournalByteRange {
|
||||
start: 0,
|
||||
end: descriptor.total_bytes,
|
||||
},
|
||||
})
|
||||
.collect()
|
||||
},
|
||||
})
|
||||
.collect())
|
||||
}
|
||||
|
||||
fn source_reader(
|
||||
&self,
|
||||
source: &JournalSource,
|
||||
) -> Result<session_store::public_material::SessionPublicMaterialReader, SubjektivHostError>
|
||||
{
|
||||
let sessions = crate::subjektiv_sessions::authorized_sessions_path(
|
||||
&self.catalog.state_root,
|
||||
&self.binding.scope_id,
|
||||
&self.binding.subject_id,
|
||||
&self.catalog.store,
|
||||
&source.session_id,
|
||||
)?;
|
||||
// Frozen, already admitted original pointers do not follow the Worker's later active
|
||||
// Session/Segment. This reads that original lineage and still checks descriptor identity,
|
||||
// canonical order and digest below; the shared service enforces the frozen byte range.
|
||||
session_store::public_material::SessionPublicMaterialReader::open_fs_with_retention(
|
||||
&sessions,
|
||||
source
|
||||
.session_id
|
||||
.parse()
|
||||
.map_err(|_| SubjektivHostError::InvalidArgument("invalid Session".into()))?,
|
||||
source.pointer.segment_id,
|
||||
session_store::public_material::PublicMaterialLimits {
|
||||
max_segments: 256,
|
||||
max_entries: 100_000,
|
||||
max_record_bytes: 64 * 1024 * 1024,
|
||||
},
|
||||
crate::store::session_retention(&self.catalog.state_root),
|
||||
)
|
||||
.map_err(|error| SubjektivHostError::Unavailable(error.to_string()))
|
||||
}
|
||||
|
||||
fn journal_origins(
|
||||
&self,
|
||||
ranges: &[JournalSourceRange],
|
||||
) -> Result<Vec<SourceOrigin>, SubjektivHostError> {
|
||||
if ranges.is_empty() {
|
||||
return Err(SubjektivHostError::InvalidArgument(
|
||||
"empty material selection".into(),
|
||||
));
|
||||
}
|
||||
ranges
|
||||
.iter()
|
||||
.map(|range| {
|
||||
let reader = self.source_reader(&range.source)?;
|
||||
reader
|
||||
.descriptors()
|
||||
.find(|descriptor| {
|
||||
source_descriptor(&range.source.session_id, descriptor) == range.source
|
||||
})
|
||||
.map(|descriptor| SourceOrigin {
|
||||
pointer: range.source.pointer.clone(),
|
||||
origin: descriptor.origin.clone(),
|
||||
})
|
||||
.ok_or_else(|| {
|
||||
SubjektivHostError::InvalidArgument(
|
||||
"source provenance/identity changed".into(),
|
||||
)
|
||||
})
|
||||
})
|
||||
.collect()
|
||||
}
|
||||
|
||||
fn journal_source_window(
|
||||
&self,
|
||||
source: &JournalSource,
|
||||
offset: u64,
|
||||
max_bytes: usize,
|
||||
) -> Result<String, SubjektivHostError> {
|
||||
let reader = self.source_reader(source)?;
|
||||
let descriptor = reader.descriptors().find(|descriptor| source_descriptor(&source.session_id, descriptor) == *source)
|
||||
.ok_or_else(|| SubjektivHostError::InvalidArgument("canonical source identity/order/digest changed or is outside the authorized Session".into()))?;
|
||||
reader
|
||||
.read_content(descriptor, offset, max_bytes)
|
||||
.map(|window| window.content)
|
||||
.map_err(|error| SubjektivHostError::Unavailable(error.to_string()))
|
||||
}
|
||||
|
||||
fn journal_source_material(
|
||||
&self,
|
||||
source: &JournalSource,
|
||||
start: u64,
|
||||
limit: usize,
|
||||
) -> JournalResult<JournalMaterial> {
|
||||
let text = self
|
||||
.journal_source_window(source, start, limit.max(4))
|
||||
.map_err(|error| JournalError::Conflict(error.to_string()))?;
|
||||
Ok(JournalMaterial {
|
||||
range: JournalSourceRange {
|
||||
source: source.clone(),
|
||||
bytes: JournalByteRange {
|
||||
start,
|
||||
end: start + text.len() as u64,
|
||||
},
|
||||
},
|
||||
text,
|
||||
)
|
||||
.map_err(|e| SubjektivHostError::Unavailable(e.to_string()))
|
||||
})
|
||||
}
|
||||
|
||||
fn select_journal_materials(
|
||||
fn build_journal_input(
|
||||
&self,
|
||||
context: &JournalHostContext,
|
||||
id: &str,
|
||||
) -> Result<Vec<JournalMaterial>, SubjektivHostError> {
|
||||
subjektiv::journal::recording::select_materials_bounded(
|
||||
&self.catalog.store,
|
||||
context,
|
||||
id,
|
||||
INPUT_BUDGET,
|
||||
|source, start, limit| self.journal_source_material(source, start, limit),
|
||||
)
|
||||
saved: Option<&CaptureDto>,
|
||||
) -> Result<JournalInput, SubjektivHostError> {
|
||||
let session = self
|
||||
.catalog
|
||||
.store
|
||||
.read_journal(context, id)
|
||||
.map_err(journal_error)?
|
||||
.source_session_id;
|
||||
JournalInput::build(&self.catalog.store, context, id, |order, offset, budget| {
|
||||
let capture = match saved {
|
||||
Some(capture) => capture.clone(),
|
||||
None => {
|
||||
let capture = self
|
||||
.with_recording_boundary(&session, |sessions, session_id, active, guard| {
|
||||
session_store::capture::capture_recording_slice_fs_guarded(
|
||||
sessions,
|
||||
session_id,
|
||||
active,
|
||||
session_store::public_material::PublicMaterialLimits::default(),
|
||||
RecordingPosition {
|
||||
canonical_order: order,
|
||||
byte_offset: offset,
|
||||
},
|
||||
MAX_JOURNAL_RANGES,
|
||||
budget,
|
||||
guard,
|
||||
)
|
||||
.map(|slice| slice.capture)
|
||||
.map_err(|e| SubjektivHostError::Unavailable(e.to_string()))
|
||||
})
|
||||
.map_err(|e| JournalError::Conflict(e.to_string()))?;
|
||||
// Admission and capture are separate saves. An append between them
|
||||
// may be in replay but has not yet been accepted for this Journal.
|
||||
return self.accepted_capture_prefix(context, id, capture);
|
||||
}
|
||||
};
|
||||
let end = capture
|
||||
.entries
|
||||
.last()
|
||||
.map(|entry| {
|
||||
capture
|
||||
.recording_text(entry.order)
|
||||
.map(|(descriptor, start, text)| {
|
||||
if start + text.len() as u64 == descriptor.total_bytes {
|
||||
RecordingPosition {
|
||||
canonical_order: entry.order + 1,
|
||||
byte_offset: 0,
|
||||
}
|
||||
} else {
|
||||
RecordingPosition {
|
||||
canonical_order: entry.order,
|
||||
byte_offset: start + text.len() as u64,
|
||||
}
|
||||
}
|
||||
})
|
||||
})
|
||||
.transpose()
|
||||
.map_err(|e| JournalError::Conflict(e.to_string()))?;
|
||||
if end.is_none_or(|end| (order, offset) >= (end.canonical_order, end.byte_offset)) {
|
||||
return Ok(CaptureDto {
|
||||
entries: vec![],
|
||||
..capture
|
||||
});
|
||||
}
|
||||
capture
|
||||
.recording_slice(
|
||||
RecordingPosition {
|
||||
canonical_order: order,
|
||||
byte_offset: offset,
|
||||
},
|
||||
MAX_JOURNAL_RANGES,
|
||||
budget,
|
||||
)
|
||||
.map(|slice| slice.capture)
|
||||
.map_err(|e| JournalError::Conflict(e.to_string()))
|
||||
})
|
||||
.map_err(journal_error)
|
||||
}
|
||||
|
||||
fn journal_grant(
|
||||
fn accepted_capture_prefix(
|
||||
&self,
|
||||
context: &JournalHostContext,
|
||||
id: &str,
|
||||
mut capture: CaptureDto,
|
||||
) -> JournalResult<CaptureDto> {
|
||||
let mut selected = Vec::new();
|
||||
for mut entry in capture.entries {
|
||||
let status = match self
|
||||
.catalog
|
||||
.store
|
||||
.read_journal_source(context, id, entry.order)
|
||||
{
|
||||
Ok(status) => status,
|
||||
Err(JournalError::NotFound(_)) => break,
|
||||
Err(error) => return Err(error),
|
||||
};
|
||||
let session_store::capture::CaptureBody::CanonicalPublic {
|
||||
descriptor,
|
||||
byte_offset,
|
||||
text,
|
||||
..
|
||||
} = &mut entry.body
|
||||
else {
|
||||
return Err(JournalError::InvalidInput("non-recording capture".into()));
|
||||
};
|
||||
if source_descriptor(&capture.session_id, descriptor) != status.source {
|
||||
return Err(JournalError::Conflict(
|
||||
"captured source differs from admitted identity".into(),
|
||||
));
|
||||
}
|
||||
let Some(accepted) = status
|
||||
.accepted
|
||||
.iter()
|
||||
.find(|range| range.start <= *byte_offset && *byte_offset < range.end)
|
||||
else {
|
||||
break;
|
||||
};
|
||||
let end = status
|
||||
.unavailable
|
||||
.iter()
|
||||
.filter(|range| range.end > *byte_offset)
|
||||
.fold(accepted.end, |end, range| {
|
||||
end.min(range.start.max(*byte_offset))
|
||||
});
|
||||
let mut length = text.len().min(end.saturating_sub(*byte_offset) as usize);
|
||||
while !text.is_char_boundary(length) {
|
||||
length -= 1;
|
||||
}
|
||||
if length == 0 {
|
||||
break;
|
||||
}
|
||||
text.truncate(length);
|
||||
let partial = *byte_offset + (text.len() as u64) < descriptor.total_bytes;
|
||||
selected.push(entry);
|
||||
if partial {
|
||||
break;
|
||||
}
|
||||
}
|
||||
capture.entries = selected;
|
||||
Ok(capture)
|
||||
}
|
||||
|
||||
fn journal_grant_scope(
|
||||
&self,
|
||||
snapshot: &JobSnapshot,
|
||||
) -> Result<LocalJournalGrant, SubjektivHostError> {
|
||||
@@ -1097,7 +1358,6 @@ impl LocalSubjectHost {
|
||||
|| snapshot.request.purpose != PURPOSE
|
||||
|| snapshot.request.serialization_key.as_deref()
|
||||
!= Some(&format!("subjektiv-journal:{}", grant.journal_id))
|
||||
|| snapshot.request.input != grant.input()
|
||||
{
|
||||
return Err(SubjektivHostError::InvalidArgument(
|
||||
"Job input/grant does not match this Journal capability".into(),
|
||||
@@ -1135,12 +1395,33 @@ impl LocalSubjectHost {
|
||||
Ok(grant)
|
||||
}
|
||||
|
||||
fn journal_grant(
|
||||
&self,
|
||||
snapshot: &JobSnapshot,
|
||||
) -> Result<LocalJournalGrant, SubjektivHostError> {
|
||||
snapshot
|
||||
.load_executable_request()
|
||||
.map_err(|e| SubjektivHostError::InvalidArgument(e.to_string()))?;
|
||||
let grant = self.journal_grant_scope(snapshot)?;
|
||||
let input = JournalInput::decode(&snapshot.request.input).map_err(journal_error)?;
|
||||
if input.subject_id != self.binding.subject_id
|
||||
|| input.journal_id != grant.journal_id
|
||||
|| input.capture.session_id != grant.session_id
|
||||
|| input.selected_ranges != grant.ranges
|
||||
{
|
||||
return Err(SubjektivHostError::InvalidArgument(
|
||||
"saved Journal body identity/ranges differ from grant".into(),
|
||||
));
|
||||
}
|
||||
Ok(grant)
|
||||
}
|
||||
|
||||
fn complete_journal_job(
|
||||
&self,
|
||||
jobs: &crate::jobs::StandaloneJobs,
|
||||
snapshot: &JobSnapshot,
|
||||
) -> Result<(), SubjektivHostError> {
|
||||
let grant = self.journal_grant(snapshot)?;
|
||||
let grant = self.journal_grant_scope(snapshot)?;
|
||||
let context = authority(self, &grant.session_id)?;
|
||||
let completion: JournalJobCompletion =
|
||||
serde_json::from_value(snapshot.result.clone().ok_or_else(|| {
|
||||
@@ -1174,6 +1455,12 @@ impl LocalSubjectHost {
|
||||
}
|
||||
jobs.acknowledge(&snapshot.request.job_id)
|
||||
.map_err(service_error)?;
|
||||
jobs.reclaim_input(
|
||||
&snapshot.request.job_id,
|
||||
&snapshot.input_digest,
|
||||
JobInputRetirementReason::Completed,
|
||||
)
|
||||
.map_err(service_error)?;
|
||||
if let Err(error) = self.prune_retained_workers() {
|
||||
// Pruning is independent of a successful checkpoint/result. Keep the originals
|
||||
// and continue draining other saved prefixes; a retention error is not model failure.
|
||||
@@ -1192,47 +1479,18 @@ pub(super) fn grant(
|
||||
.journal_grant(snapshot)
|
||||
.map_err(|error| error.to_string())?;
|
||||
let context = authority(&host, &grant.session_id).map_err(|error| error.to_string())?;
|
||||
// Re-fetch selected identities before opening mutation authority. Only descriptors are
|
||||
// retained in Job storage; the model must fetch actual source bytes with bounded tools.
|
||||
for range in &grant.ranges {
|
||||
let length = usize::try_from(
|
||||
range
|
||||
.bytes
|
||||
.end
|
||||
.checked_sub(range.bytes.start)
|
||||
.ok_or("invalid source range")?,
|
||||
)
|
||||
.map_err(|_| "source range overflow")?;
|
||||
if length > INPUT_BUDGET {
|
||||
return Err("source range exceeds frozen input budget".into());
|
||||
}
|
||||
let text = host
|
||||
.journal_source_window(&range.source, range.bytes.start, length.max(4))
|
||||
.map_err(|error| error.to_string())?;
|
||||
if text.len() != length {
|
||||
return Err("frozen Journal source byte range changed".into());
|
||||
}
|
||||
}
|
||||
if host
|
||||
.journal_origins(&grant.ranges)
|
||||
.map_err(|error| error.to_string())?
|
||||
!= grant.origins
|
||||
{
|
||||
return Err(
|
||||
"frozen Journal provenance does not match the authorized original Session".into(),
|
||||
);
|
||||
}
|
||||
let input = JournalInput::decode(&snapshot.request.input).map_err(|e| e.to_string())?;
|
||||
let input_digest = snapshot.input_digest.clone();
|
||||
let generation = host
|
||||
.catalog
|
||||
.store
|
||||
.prepare_journal_generation(
|
||||
.prepare_journal_input(
|
||||
&context,
|
||||
&grant.journal_id,
|
||||
&input,
|
||||
JobAttemptBinding {
|
||||
job_id: snapshot.request.job_id.clone(),
|
||||
attempt_id: snapshot.attempt.attempt_id.clone(),
|
||||
},
|
||||
grant.ranges.clone(),
|
||||
)
|
||||
.map_err(|error| error.to_string())?;
|
||||
let job_context = JournalJobContext::validated(
|
||||
@@ -1242,12 +1500,17 @@ pub(super) fn grant(
|
||||
generation.job.clone(),
|
||||
)
|
||||
.map_err(|error| error.to_string())?;
|
||||
input
|
||||
.validate_generation(&generation)
|
||||
.map_err(|e| e.to_string())?;
|
||||
let adapter = Arc::new(LocalJournalHost {
|
||||
host,
|
||||
grant,
|
||||
context,
|
||||
job_context,
|
||||
#[cfg(test)]
|
||||
generation,
|
||||
input_digest,
|
||||
fence,
|
||||
});
|
||||
Ok(worker::job::JobFeatureGrant {
|
||||
@@ -1263,7 +1526,9 @@ struct LocalJournalHost {
|
||||
grant: LocalJournalGrant,
|
||||
context: JournalHostContext,
|
||||
job_context: JournalJobContext,
|
||||
#[cfg(test)]
|
||||
generation: JournalGeneration,
|
||||
input_digest: String,
|
||||
fence: Arc<dyn crate::jobs::JobAttemptFence>,
|
||||
}
|
||||
impl LocalJournalHost {
|
||||
@@ -1296,18 +1561,20 @@ impl JournalJobHost for LocalJournalHost {
|
||||
request: JournalJobRequest,
|
||||
) -> Result<JournalJobResponse, SubjektivHostError> {
|
||||
let context = self.live()?;
|
||||
subjektiv::journal::service::execute_bounded(
|
||||
// The generic runner has supplied this exact immutable input before it can
|
||||
// invoke this bound tool. Preparation alone is not evidence of delivery.
|
||||
subjektiv::journal::service::attest_input_delivery(
|
||||
&self.host.catalog.store,
|
||||
&context,
|
||||
&self.input_digest,
|
||||
&self.grant.ranges,
|
||||
)
|
||||
.map_err(journal_error)?;
|
||||
subjektiv::journal::service::execute_snapshot(
|
||||
&self.host.catalog.store,
|
||||
&context,
|
||||
&self.input_digest,
|
||||
request,
|
||||
|source, start, limit| {
|
||||
if source.session_id != self.generation.initial_journal.source_session_id {
|
||||
return Err(JournalError::PermissionDenied(
|
||||
"foreign original Session".into(),
|
||||
));
|
||||
}
|
||||
self.host.journal_source_material(source, start, limit)
|
||||
},
|
||||
)
|
||||
.map_err(journal_error)
|
||||
}
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -215,6 +215,7 @@ async fn public_mid_turn_compactions_preserve_originals_and_drain_after_cancel_a
|
||||
}
|
||||
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}"),
|
||||
_ => {}
|
||||
}
|
||||
@@ -294,6 +295,32 @@ async fn public_mid_turn_compactions_preserve_originals_and_drain_after_cancel_a
|
||||
.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!(
|
||||
|
||||
@@ -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");
|
||||
}
|
||||
@@ -79,7 +79,7 @@ async fn recorded_idle_body_handoff_preserves_open_after_source_deletion_and_see
|
||||
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 matches!(entry.item, session_store::SystemItem::JournalStartup { .. }))).count();
|
||||
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();
|
||||
|
||||
@@ -1621,6 +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,
|
||||
@@ -1693,6 +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 +608,239 @@ 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()?;
|
||||
// Shorten only the owned endpoint's components, preserving the harness TMPDIR
|
||||
// even when it is checkout-local. No process-global cwd or external /tmp fallback.
|
||||
let socket_dir = tempfile::Builder::new()
|
||||
.prefix("")
|
||||
.rand_bytes(4)
|
||||
.tempdir()?;
|
||||
std::fs::set_permissions(socket_dir.path(), std::fs::Permissions::from_mode(0o700))?;
|
||||
let endpoint_path = socket_dir.path().join("s");
|
||||
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 {
|
||||
|
||||
@@ -479,38 +479,28 @@ fn journal_response(request: &Request) -> Vec<LlmEvent> {
|
||||
}),
|
||||
);
|
||||
}
|
||||
for (index, range) in state["selected_ranges"]
|
||||
.as_array()
|
||||
.unwrap()
|
||||
let input: Value = request
|
||||
.items
|
||||
.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
|
||||
}),
|
||||
);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
.filter_map(Item::as_text)
|
||||
.find_map(|text| {
|
||||
text.lines()
|
||||
.find_map(|line| line.strip_prefix("input_json: "))
|
||||
})
|
||||
.map(|json| serde_json::from_str(json).unwrap())
|
||||
.expect("saved direct Journal input");
|
||||
let input = subjektiv::journal::recording::JournalInput::decode(&input).unwrap();
|
||||
assert_eq!(
|
||||
serde_json::to_value(&input.selected_ranges).unwrap(),
|
||||
state["selected_ranges"]
|
||||
);
|
||||
assert!(
|
||||
input
|
||||
.capture
|
||||
.entries
|
||||
.iter()
|
||||
.all(|entry| input.capture.recording_text(entry.order).is_ok())
|
||||
);
|
||||
let (name, action) = if state["current_open"].is_null() {
|
||||
(
|
||||
"CreateJournalEntry",
|
||||
|
||||
@@ -15,6 +15,8 @@ serde = { workspace = true, features = ["derive"] }
|
||||
serde_json.workspace = true
|
||||
sha2.workspace = true
|
||||
server-api.workspace = true
|
||||
session-store.workspace = true
|
||||
job.workspace = true
|
||||
thiserror.workspace = true
|
||||
uuid = { workspace = true, features = ["v7"] }
|
||||
|
||||
|
||||
@@ -1299,6 +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}"))
|
||||
}
|
||||
|
||||
@@ -67,6 +67,27 @@ impl SubjektivStore {
|
||||
})
|
||||
}
|
||||
|
||||
/// 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,
|
||||
@@ -203,3 +224,82 @@ impl SubjektivStore {
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
#[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),
|
||||
)?)
|
||||
})
|
||||
}
|
||||
}
|
||||
@@ -40,6 +40,7 @@
|
||||
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;
|
||||
|
||||
@@ -5,8 +5,221 @@
|
||||
//! original canonical identity while streaming and return only the requested bounded fragment.
|
||||
|
||||
use super::*;
|
||||
use session_store::capture::{CaptureDto, CaptureLimits};
|
||||
use sha2::{Digest, Sha256};
|
||||
|
||||
/// A Job owns only this bounded original-body prefix. The initial content condition binds
|
||||
/// the separate generation snapshot (whose potentially large Journal text remains paged).
|
||||
/// Neither possessing these bytes nor delivering them is a processing checkpoint.
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct JournalInput {
|
||||
pub version: u32,
|
||||
pub subject_id: String,
|
||||
pub journal_id: String,
|
||||
pub initial_state_token: String,
|
||||
pub initial_open_id: Option<String>,
|
||||
pub previous_fixed_end: Option<JournalSourcePointer>,
|
||||
pub selected_ranges: Vec<JournalSourceRange>,
|
||||
pub capture: CaptureDto,
|
||||
}
|
||||
|
||||
impl JournalInput {
|
||||
/// Capture callback runs once for this immutable Job, never once per page. Fitting uses
|
||||
/// only that captured value and measures the complete serialized input, including the
|
||||
/// initial Journal condition and ranges duplicated beside the capture's descriptors.
|
||||
pub fn build(
|
||||
store: &SubjektivStore,
|
||||
host: &JournalHostContext,
|
||||
journal_id: &str,
|
||||
capture_once: impl FnOnce(u64, u64, usize) -> JournalResult<CaptureDto>,
|
||||
) -> JournalResult<Self> {
|
||||
let (journal, open, previous_fixed_end) = store.database.try_with_connection(|tx| {
|
||||
super::store::check_host(store, tx, host, true)?;
|
||||
Ok::<_, JournalError>((
|
||||
super::store::journal(tx, host, journal_id, true)?,
|
||||
super::store::open(tx, journal_id)?,
|
||||
super::store::previous_fixed(tx, journal_id)?.map(|p| p.0),
|
||||
))
|
||||
})?;
|
||||
let mut input = Self {
|
||||
version: 1,
|
||||
subject_id: journal.subject_id.clone(),
|
||||
journal_id: journal_id.into(),
|
||||
initial_state_token: journal.state_token,
|
||||
initial_open_id: open.map(|e| e.id),
|
||||
previous_fixed_end,
|
||||
selected_ranges: Vec::new(),
|
||||
capture: CaptureDto {
|
||||
version: 1,
|
||||
session_id: journal.source_session_id,
|
||||
segment_id: "pending".into(),
|
||||
view_entry_count: 0,
|
||||
entries: Vec::new(),
|
||||
},
|
||||
};
|
||||
let envelope = serde_json::to_vec(&input)?.len();
|
||||
// Capture once at a fixed storage boundary. Any adjustment for the Journal envelope
|
||||
// below operates on this value only, never by making another live capture request.
|
||||
let budget = job::MAX_JOB_INPUT_BYTES.saturating_sub(envelope);
|
||||
input.capture = capture_once(journal.process_order, journal.process_byte, budget)?;
|
||||
input.selected_ranges = capture_ranges(&input.capture)?;
|
||||
if input.selected_ranges.is_empty() {
|
||||
return Ok(input);
|
||||
}
|
||||
input.fit()?;
|
||||
let value = serde_json::to_value(&input)?;
|
||||
Self::decode(&value)
|
||||
}
|
||||
|
||||
fn fit(&mut self) -> JournalResult<()> {
|
||||
let original = self.capture.clone();
|
||||
let first = self
|
||||
.selected_ranges
|
||||
.first()
|
||||
.ok_or_else(|| invalid("empty recording selection"))?;
|
||||
let start = session_store::capture::RecordingPosition {
|
||||
canonical_order: first.source.order,
|
||||
byte_offset: first.bytes.start,
|
||||
};
|
||||
let mut budget = serde_json::to_vec(&original)?.len();
|
||||
loop {
|
||||
let bytes = serde_json::to_vec(self)?.len();
|
||||
if bytes <= job::MAX_JOB_INPUT_BYTES {
|
||||
return Ok(());
|
||||
}
|
||||
budget = budget
|
||||
.checked_sub(bytes - job::MAX_JOB_INPUT_BYTES)
|
||||
.ok_or_else(|| invalid("Journal envelope cannot fit source bytes"))?;
|
||||
self.capture = original
|
||||
.recording_slice(start, MAX_JOURNAL_RANGES, budget)
|
||||
.map_err(|e| invalid(&e.to_string()))?
|
||||
.capture;
|
||||
self.selected_ranges = capture_ranges(&self.capture)?;
|
||||
if self.selected_ranges.is_empty() {
|
||||
return Err(invalid("Journal envelope cannot fit one source scalar"));
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
pub fn decode(value: &serde_json::Value) -> JournalResult<Self> {
|
||||
if serde_json::to_vec(value)?.len() > job::MAX_JOB_INPUT_BYTES {
|
||||
return Err(invalid(
|
||||
"Journal input exceeds whole serialized Job input limit",
|
||||
));
|
||||
}
|
||||
let input: Self = serde_json::from_value(value.clone())?;
|
||||
input
|
||||
.capture
|
||||
.validate(CaptureLimits {
|
||||
max_bytes: job::MAX_JOB_INPUT_BYTES,
|
||||
max_entries: MAX_JOURNAL_RANGES,
|
||||
max_text_bytes: job::MAX_JOB_INPUT_BYTES,
|
||||
..CaptureLimits::default()
|
||||
})
|
||||
.map_err(|e| invalid(&e.to_string()))?;
|
||||
if input.version != 1
|
||||
|| input.subject_id.is_empty()
|
||||
|| input.journal_id.is_empty()
|
||||
|| input.initial_state_token.is_empty()
|
||||
|| input.selected_ranges.is_empty()
|
||||
|| input.selected_ranges.len() > MAX_JOURNAL_RANGES
|
||||
|| input
|
||||
.selected_ranges
|
||||
.iter()
|
||||
.any(|r| r.source.session_id != input.capture.session_id)
|
||||
{
|
||||
return Err(invalid("invalid Journal input identity or selection"));
|
||||
}
|
||||
if capture_ranges(&input.capture)? != input.selected_ranges {
|
||||
return Err(conflict(
|
||||
"Journal body snapshot does not match selected canonical ranges",
|
||||
));
|
||||
}
|
||||
Ok(input)
|
||||
}
|
||||
|
||||
pub fn validate_generation(&self, generation: &JournalGeneration) -> JournalResult<()> {
|
||||
if generation.journal_id != self.journal_id
|
||||
|| generation.initial_journal.subject_id != self.subject_id
|
||||
|| generation.initial_journal.source_session_id != self.capture.session_id
|
||||
|| generation.initial_journal.state_token != self.initial_state_token
|
||||
|| generation.initial_open.as_ref().map(|e| &e.id) != self.initial_open_id.as_ref()
|
||||
|| generation.previous_fixed_end != self.previous_fixed_end
|
||||
|| generation.selected_ranges != self.selected_ranges
|
||||
{
|
||||
return Err(conflict(
|
||||
"saved Journal input differs from its initial generation snapshot",
|
||||
));
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
}
|
||||
|
||||
/// Converts the shared recording projection into Journal's coverage language without
|
||||
/// interpreting model text or constructing a second capture representation.
|
||||
pub fn capture_ranges(capture: &CaptureDto) -> JournalResult<Vec<JournalSourceRange>> {
|
||||
use session_store::capture::CaptureBody;
|
||||
let mut ranges = Vec::new();
|
||||
for entry in &capture.entries {
|
||||
let CaptureBody::CanonicalPublic {
|
||||
descriptor,
|
||||
byte_offset,
|
||||
text,
|
||||
..
|
||||
} = &entry.body
|
||||
else {
|
||||
return Err(invalid(
|
||||
"Journal requires canonical original recording capture",
|
||||
));
|
||||
};
|
||||
if !entry.policy.recording_material
|
||||
|| text.is_empty()
|
||||
|| descriptor.identity.segment_id.to_string() != entry.source.segment_id
|
||||
|| descriptor.identity.entry_ref != format!("E{}", entry.entry_id)
|
||||
|| descriptor.canonical_order != entry.order
|
||||
|| byte_offset
|
||||
.checked_add(text.len() as u64)
|
||||
.is_none_or(|end| end > descriptor.total_bytes)
|
||||
{
|
||||
return Err(conflict(
|
||||
"recording body identity, policy or range mismatch",
|
||||
));
|
||||
}
|
||||
let source = JournalSource {
|
||||
session_id: capture.session_id.clone(),
|
||||
pointer: JournalSourcePointer {
|
||||
segment_id: descriptor.identity.segment_id,
|
||||
entry_ref: descriptor.identity.entry_ref.clone(),
|
||||
},
|
||||
order: descriptor.canonical_order,
|
||||
content_sha256: descriptor.sha256.clone(),
|
||||
total_bytes: descriptor.total_bytes,
|
||||
};
|
||||
if *byte_offset == 0 && text.len() as u64 == descriptor.total_bytes {
|
||||
verify_canonical_text(&source, text)?;
|
||||
}
|
||||
ranges.push(JournalSourceRange {
|
||||
source,
|
||||
bytes: JournalByteRange {
|
||||
start: *byte_offset,
|
||||
end: *byte_offset + text.len() as u64,
|
||||
},
|
||||
});
|
||||
}
|
||||
for pair in ranges.windows(2) {
|
||||
if pair[0].source.order.checked_add(1) != Some(pair[1].source.order)
|
||||
|| pair[0].bytes.end != pair[0].source.total_bytes
|
||||
|| pair[1].bytes.start != 0
|
||||
{
|
||||
return Err(conflict(
|
||||
"recording capture is not an oldest contiguous prefix",
|
||||
));
|
||||
}
|
||||
}
|
||||
Ok(ranges)
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct JournalMaterial {
|
||||
|
||||
@@ -66,8 +66,8 @@ fn text_page(
|
||||
})
|
||||
}
|
||||
|
||||
/// 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.
|
||||
/// Legacy adapter for Host captures bounded by their storage contract.
|
||||
/// Production Hosts use [`attest_input_delivery`] and [`execute_snapshot`] instead.
|
||||
pub fn execute(
|
||||
store: &SubjektivStore,
|
||||
context: &JournalJobContext,
|
||||
@@ -101,23 +101,149 @@ pub fn execute(
|
||||
})
|
||||
}
|
||||
|
||||
/// 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(crate) fn migrate_input_delivery(
|
||||
tx: &rusqlite::Transaction<'_>,
|
||||
) -> feature_storage::Result<()> {
|
||||
tx.execute_batch(
|
||||
"CREATE TABLE journal_generation_input_deliveries (
|
||||
generation_id TEXT PRIMARY KEY NOT NULL REFERENCES journal_generations(id) ON DELETE CASCADE,
|
||||
input_digest TEXT NOT NULL CHECK(length(input_digest)=71 AND substr(input_digest,1,7)='sha256:' AND substr(input_digest,8) NOT GLOB '*[^0-9a-f]*')
|
||||
);
|
||||
CREATE TRIGGER journal_generation_input_delivery_no_update
|
||||
BEFORE UPDATE ON journal_generation_input_deliveries
|
||||
BEGIN SELECT RAISE(ABORT, 'Journal input delivery bindings are immutable'); END;",
|
||||
)?;
|
||||
Ok(())
|
||||
}
|
||||
|
||||
fn validate_input_digest(input_digest: &str) -> JournalResult<()> {
|
||||
// Preserve JobRequest::input_digest() verbatim, including its algorithm prefix.
|
||||
if input_digest.strip_prefix("sha256:").is_none_or(|hex| {
|
||||
hex.len() != 64
|
||||
|| !hex
|
||||
.bytes()
|
||||
.all(|b| b.is_ascii_digit() || (b'a'..=b'f').contains(&b))
|
||||
}) {
|
||||
return Err(JournalError::InvalidInput(
|
||||
"immutable Job input digest must be sha256: followed by 64 lowercase hex digits".into(),
|
||||
));
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Trusted Host-only delivery evidence, never a model tool or a claim of understanding.
|
||||
/// Before calling, the Host must validate the saved, immutable body-bearing input against the
|
||||
/// bound Job's input digest, its Session/provenance/ranges, and the actual dispatch plan that
|
||||
/// supplies that exact input. The service cannot verify bytes it does not own. This transaction
|
||||
/// stores only the digest bound to the generation's immutable selection; it neither copies the
|
||||
/// body nor changes records, position, reflection or checkpoint. Exact replay is allowed only
|
||||
/// while the same generation and writer binding remain active; changed digests/ranges conflict.
|
||||
pub fn attest_input_delivery(
|
||||
store: &SubjektivStore,
|
||||
context: &JournalJobContext,
|
||||
input_digest: &str,
|
||||
selected_ranges: &[JournalSourceRange],
|
||||
) -> JournalResult<()> {
|
||||
validate_input_digest(input_digest)?;
|
||||
store.database.try_transaction(|tx| {
|
||||
super::lifecycle::reject_erased(tx, &context.host)?;
|
||||
let generation = super::store::job(store, tx, context, true)?;
|
||||
if generation.selected_ranges != selected_ranges {
|
||||
return Err(JournalError::Conflict(
|
||||
"immutable Job input selection differs from generation".into(),
|
||||
));
|
||||
}
|
||||
let saved: Option<String> = tx.query_row(
|
||||
"SELECT input_digest FROM journal_generation_input_deliveries WHERE generation_id=?1",
|
||||
[&generation.id], |row| row.get(0),
|
||||
).optional()?;
|
||||
if let Some(saved) = saved {
|
||||
if saved != input_digest {
|
||||
return Err(JournalError::Conflict(
|
||||
"generation is bound to a different immutable Job input digest".into(),
|
||||
));
|
||||
}
|
||||
} else {
|
||||
tx.execute(
|
||||
"INSERT INTO journal_generation_input_deliveries(generation_id,input_digest) VALUES(?1,?2)",
|
||||
params![generation.id, input_digest],
|
||||
)?;
|
||||
}
|
||||
Ok(())
|
||||
})
|
||||
}
|
||||
|
||||
fn require_input_delivery(
|
||||
tx: &rusqlite::Connection,
|
||||
context: &JournalJobContext,
|
||||
input_digest: &str,
|
||||
) -> JournalResult<()> {
|
||||
validate_input_digest(input_digest)?;
|
||||
let saved: Option<String> = tx
|
||||
.query_row(
|
||||
"SELECT input_digest FROM journal_generation_input_deliveries WHERE generation_id=?1",
|
||||
[&context.generation_id],
|
||||
|row| row.get(0),
|
||||
)
|
||||
.optional()?;
|
||||
if saved.as_deref() != Some(input_digest) {
|
||||
return Err(JournalError::Conflict(
|
||||
"trusted Host delivery of this immutable Job input is required".into(),
|
||||
));
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Production sequential execution over Journal state and the Host-attested immutable input.
|
||||
/// The digest is taken from the bound saved Job by the Host, not from model arguments. Every
|
||||
/// request requires the matching delivery binding and an active generation/writer. Source text
|
||||
/// is already in immutable input: Source targets fail explicitly, with no Session reader or
|
||||
/// fallback. Receipt-backed record, position and checkpoint constraints remain unchanged.
|
||||
pub fn execute_snapshot(
|
||||
store: &SubjektivStore,
|
||||
context: &JournalJobContext,
|
||||
input_digest: &str,
|
||||
request: JournalJobRequest,
|
||||
) -> JournalResult<JournalJobResponse> {
|
||||
execute_inner(store, context, request, Some(input_digest), |_, _, _| {
|
||||
Err(JournalError::PermissionDenied(
|
||||
"Source reads are unavailable for immutable Journal input".into(),
|
||||
))
|
||||
})
|
||||
}
|
||||
|
||||
/// Legacy/test source-read adapter. Production Hosts must use [`execute_snapshot`].
|
||||
/// This ledger attests bounded Source responses only and cannot satisfy the input-digest gate.
|
||||
pub fn execute_bounded(
|
||||
store: &SubjektivStore,
|
||||
context: &JournalJobContext,
|
||||
request: JournalJobRequest,
|
||||
read_source: impl FnMut(&JournalSource, u64, usize) -> JournalResult<recording::JournalMaterial>,
|
||||
) -> JournalResult<JournalJobResponse> {
|
||||
execute_inner(store, context, request, None, read_source)
|
||||
}
|
||||
|
||||
fn execute_inner(
|
||||
store: &SubjektivStore,
|
||||
context: &JournalJobContext,
|
||||
request: JournalJobRequest,
|
||||
input_digest: Option<&str>,
|
||||
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 generation = store.database.try_with_connection(|tx| {
|
||||
super::lifecycle::reject_erased(tx, &context.host)?;
|
||||
let generation = super::store::job(store, tx, context, true)?;
|
||||
if let Some(input_digest) = input_digest {
|
||||
require_input_delivery(tx, context, input_digest)?;
|
||||
}
|
||||
Ok::<_, JournalError>(generation)
|
||||
})?;
|
||||
let mut delivered = None;
|
||||
let response = match request {
|
||||
JournalJobRequest::Execute { operation } => {
|
||||
require_delivery(store, context, &generation.selected_ranges)?;
|
||||
if input_digest.is_none() {
|
||||
require_delivery(store, context, &generation.selected_ranges)?;
|
||||
}
|
||||
let receipt = if matches!(operation.action, JournalAction::Checkpoint { .. }) {
|
||||
crate::api::checkpoint_journal(store, context, operation)?
|
||||
} else {
|
||||
@@ -197,6 +323,11 @@ pub fn execute_bounded(
|
||||
JournalJobRequest::ReadText { read } => {
|
||||
let text = match &read.target {
|
||||
JournalTextTarget::Source { pointer } => {
|
||||
if input_digest.is_some() {
|
||||
return Err(JournalError::PermissionDenied(
|
||||
"Source target is unavailable: raw source bodies are in immutable Job input".into(),
|
||||
));
|
||||
}
|
||||
let range = generation
|
||||
.selected_ranges
|
||||
.iter()
|
||||
|
||||
@@ -1,5 +1,9 @@
|
||||
//! Read-only, bounded Journal context for a new body Session. Selection and text projection
|
||||
//! share one storage transaction; no source history, Job, admission or checkpoint is consulted.
|
||||
//! 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::*;
|
||||
@@ -71,11 +75,32 @@ impl SubjektivStore {
|
||||
&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, false)?;
|
||||
super::store::check_host(self, tx, host, require_current_writer)?;
|
||||
let mut ids = Vec::new();
|
||||
if let Some(session) = previous_session {
|
||||
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)?)),
|
||||
|
||||
@@ -70,7 +70,10 @@ fn page_limit(limit: usize) -> JournalResult<usize> {
|
||||
}
|
||||
Ok(limit)
|
||||
}
|
||||
fn fit_page<T: Serialize>(rows: Vec<(String, T)>, mut more: bool) -> JournalResult<JournalPage<T>> {
|
||||
pub(super) fn fit_page<T: Serialize>(
|
||||
rows: Vec<(String, T)>,
|
||||
mut more: bool,
|
||||
) -> JournalResult<JournalPage<T>> {
|
||||
let mut page = JournalPage {
|
||||
items: Vec::new(),
|
||||
next: None,
|
||||
@@ -162,7 +165,7 @@ pub(super) fn journal(
|
||||
}
|
||||
Ok(j)
|
||||
}
|
||||
fn entry(tx: &Connection, journal_id: &str, id: &str) -> JournalResult<JournalEntry> {
|
||||
pub(super) fn entry(tx: &Connection, journal_id: &str, id: &str) -> JournalResult<JournalEntry> {
|
||||
let row = tx.query_row("SELECT id, journal_id, position, state, title, body, ongoing, source_end_json, created_at, updated_at, fixed_at FROM journal_entries WHERE journal_id=?1 AND id=?2", params![journal_id, id], |r| Ok((r.get::<_,String>(0)?,r.get::<_,String>(1)?,r.get::<_,u64>(2)?,r.get::<_,String>(3)?,r.get::<_,String>(4)?,r.get::<_,String>(5)?,r.get::<_,String>(6)?,r.get::<_,Option<String>>(7)?,r.get::<_,String>(8)?,r.get::<_,String>(9)?,r.get::<_,Option<String>>(10)?))).optional()?.ok_or_else(|| JournalError::NotFound(id.into()))?;
|
||||
let mut stmt = tx.prepare(
|
||||
"SELECT target_id FROM journal_corrections WHERE entry_id=?1 ORDER BY target_id",
|
||||
@@ -199,7 +202,7 @@ pub(super) fn open(tx: &Connection, journal_id: &str) -> JournalResult<Option<Jo
|
||||
.optional()?;
|
||||
id.map(|id| entry(tx, journal_id, &id)).transpose()
|
||||
}
|
||||
fn previous_fixed(
|
||||
pub(super) fn previous_fixed(
|
||||
tx: &Connection,
|
||||
journal_id: &str,
|
||||
) -> JournalResult<Option<(JournalSourcePointer, u64)>> {
|
||||
@@ -566,6 +569,60 @@ impl SubjektivStore {
|
||||
Ok(snapshot)
|
||||
})
|
||||
}
|
||||
/// Rebind a saved body input to a new attempt without resampling its initial state.
|
||||
/// The first binding freezes the full initial Journal snapshot; retries reuse it and
|
||||
/// retain operation receipts. Different Jobs cannot borrow that snapshot as authority.
|
||||
pub fn prepare_journal_input(
|
||||
&self,
|
||||
host: &JournalHostContext,
|
||||
input: &super::recording::JournalInput,
|
||||
binding: JobAttemptBinding,
|
||||
) -> JournalResult<JournalGeneration> {
|
||||
label(&binding.job_id)?;
|
||||
label(&binding.attempt_id)?;
|
||||
self.database.try_transaction(|tx| {
|
||||
check_host(self, tx, host, false)?;
|
||||
check_session_host(self, tx, host)?;
|
||||
let current = journal(tx, host, &input.journal_id, true)?;
|
||||
let existing: Option<String> = tx.query_row(
|
||||
"SELECT snapshot_json FROM journal_generations WHERE journal_id=?1 AND job_id=?2 AND attempt_id=?3",
|
||||
params![input.journal_id, binding.job_id, binding.attempt_id], |r| r.get(0)).optional()?;
|
||||
if let Some(raw) = existing {
|
||||
let g = serde_json::from_str(&raw)?;
|
||||
input.validate_generation(&g)?;
|
||||
return Ok(g);
|
||||
}
|
||||
// Retained receipt lookup does not reacquire writer authority. Only a new
|
||||
// generation requires the current active Subject/Session writer lifetime.
|
||||
check_host(self, tx, host, true)?;
|
||||
if tx.query_row("SELECT EXISTS(SELECT 1 FROM journal_generations WHERE journal_id=?1 AND active=1)", [&input.journal_id], |r| r.get::<_, bool>(0))? {
|
||||
return Err(conflict("another active generation owns this Journal"));
|
||||
}
|
||||
let prior: Option<String> = tx.query_row(
|
||||
"SELECT snapshot_json FROM journal_generations WHERE journal_id=?1 AND job_id=?2 ORDER BY rowid LIMIT 1",
|
||||
params![input.journal_id, binding.job_id], |r| r.get(0)).optional()?;
|
||||
let mut g = if let Some(raw) = prior {
|
||||
serde_json::from_str::<JournalGeneration>(&raw)?
|
||||
} else {
|
||||
JournalGeneration { id: String::new(), journal_id: input.journal_id.clone(), job: binding.clone(),
|
||||
selected_ranges: input.selected_ranges.clone(), initial_journal: current.clone(),
|
||||
initial_open: open(tx, &input.journal_id)?, previous_fixed_end: previous_fixed(tx, &input.journal_id)?.map(|p| p.0) }
|
||||
};
|
||||
input.validate_generation(&g)?;
|
||||
check_ranges(tx, ¤t, &input.selected_ranges, true)?;
|
||||
let end = prefix(&g.initial_journal, &input.selected_ranges)?;
|
||||
let cursor = (current.process_order, current.process_byte);
|
||||
if cursor < (g.initial_journal.process_order, g.initial_journal.process_byte) || cursor > end {
|
||||
return Err(conflict("saved input no longer owns the current processing cursor"));
|
||||
}
|
||||
g.id = issued_id("journal-generation");
|
||||
g.job = binding;
|
||||
tx.execute("INSERT INTO journal_generations(id,journal_id,job_id,attempt_id,request_json,snapshot_json,active) VALUES(?1,?2,?3,?4,?5,?6,1)",
|
||||
params![g.id,g.journal_id,g.job.job_id,g.job.attempt_id,serde_json::to_string(&g.selected_ranges)?,serde_json::to_string(&g)?])?;
|
||||
Ok(g)
|
||||
})
|
||||
}
|
||||
|
||||
pub(super) fn validate_journal_job(&self, ctx: &JournalJobContext) -> JournalResult<()> {
|
||||
self.database.try_with_connection(|tx| {
|
||||
job(self, tx, ctx, true)?;
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,8 +1,10 @@
|
||||
//! 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
|
||||
//! Hosts validate live execution and public source bytes before selection, save body-bearing
|
||||
//! immutable Job input, and attest its exact digest and dispatch plan through the service.
|
||||
//! Model requests cannot attest input delivery; Source targets are rejected by snapshot execution.
|
||||
//! Initial/current Journal reads remain separate from input delivery. Operation retries retain the entire
|
||||
//! JournalOperation, including its original expected_state and covered_ranges.
|
||||
|
||||
use serde::{Deserialize, Serialize};
|
||||
@@ -21,6 +23,12 @@ pub enum JournalRecordingReason {
|
||||
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 {
|
||||
@@ -44,8 +52,8 @@ pub struct JournalJobState {
|
||||
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.
|
||||
/// Frozen source selection delivered in immutable Job input, not evidence of reflection.
|
||||
/// Production execution requires the trusted Host's matching input-digest attestation.
|
||||
pub selected_ranges: Vec<JournalSourceRange>,
|
||||
}
|
||||
|
||||
@@ -77,7 +85,8 @@ pub enum JournalTextTarget {
|
||||
OpenOngoing {
|
||||
snapshot: JournalSnapshot,
|
||||
},
|
||||
/// The Host restricts this pointer to this Job's frozen public source input.
|
||||
/// Legacy source-read adapter only. Production snapshot execution rejects this target;
|
||||
/// raw source bodies must already be present in the immutable Job input.
|
||||
Source {
|
||||
pointer: JournalSourcePointer,
|
||||
},
|
||||
|
||||
@@ -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",
|
||||
|
||||
@@ -4,6 +4,7 @@ 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,
|
||||
@@ -82,6 +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:?}")]
|
||||
@@ -623,6 +634,16 @@ static MIGRATIONS: &[FeatureMigration] = &[
|
||||
"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,
|
||||
),
|
||||
FeatureMigration::new(
|
||||
13,
|
||||
"bind Journal generation delivery to immutable Job input digest",
|
||||
journal::service::migrate_input_delivery,
|
||||
),
|
||||
];
|
||||
|
||||
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,
|
||||
}
|
||||
|
||||
|
||||
@@ -20,7 +20,7 @@ pub(crate) struct WriteParams {
|
||||
/// Worker-local alias of the Workdir attachment to use.
|
||||
#[serde(default)]
|
||||
pub target_workdir: Option<String>,
|
||||
/// Logical path relative to the bound Workdir root.
|
||||
/// File to create or overwrite.
|
||||
pub file_path: String,
|
||||
#[serde(flatten)]
|
||||
pub write: fs_operation::text::WriteArgs,
|
||||
|
||||
@@ -3,7 +3,7 @@
|
||||
use std::sync::Arc;
|
||||
|
||||
use agen::tool::{Tool, ToolDefinition};
|
||||
use manifest::{Permission, Scope, ScopeConfig, ScopeRule};
|
||||
use manifest::Scope;
|
||||
use serde_json::json;
|
||||
use tempfile::TempDir;
|
||||
use tools::{Tracker, core_builtin_tools};
|
||||
@@ -28,31 +28,23 @@ impl Registry {
|
||||
}
|
||||
}
|
||||
|
||||
fn setup() -> (TempDir, TempDir, Registry) {
|
||||
fn setup() -> (TempDir, Registry) {
|
||||
let dir = TempDir::new().unwrap();
|
||||
let spill = TempDir::new().unwrap();
|
||||
let base = Scope::writable(dir.path()).unwrap();
|
||||
let mut config = ScopeConfig {
|
||||
allow: base.allow_rules(),
|
||||
deny: base.deny_rules(),
|
||||
};
|
||||
config.allow.push(ScopeRule {
|
||||
target: spill.path().to_path_buf(),
|
||||
permission: Permission::Read,
|
||||
recursive: true,
|
||||
symlink_policy: Default::default(),
|
||||
});
|
||||
let scope = Scope::from_config(&config).unwrap();
|
||||
let scope = Scope::writable(dir.path()).unwrap();
|
||||
let fs: WorkdirSessionHandle =
|
||||
std::sync::Arc::new(LocalWorkdirSession::new(scope, dir.path().to_path_buf()));
|
||||
let tracker = Tracker::new();
|
||||
let reg = Registry::new(core_builtin_tools(fs, tracker, spill.path().to_path_buf()));
|
||||
(dir, spill, reg)
|
||||
let reg = Registry::new(core_builtin_tools(
|
||||
fs,
|
||||
tracker,
|
||||
tools::bash_output::BashOutputView::new(),
|
||||
));
|
||||
(dir, reg)
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn unicode_path_and_content() {
|
||||
let (dir, _spill, reg) = setup();
|
||||
let (dir, reg) = setup();
|
||||
let file = dir.path().join("日本語ファイル.txt");
|
||||
let content = "こんにちは 🦀 世界\nabc\n";
|
||||
|
||||
@@ -87,7 +79,7 @@ async fn unicode_path_and_content() {
|
||||
async fn symlink_to_outside_scope_is_rejected_for_write() {
|
||||
use std::os::unix::fs::symlink;
|
||||
|
||||
let (dir, _spill, reg) = setup();
|
||||
let (dir, reg) = setup();
|
||||
let outside = TempDir::new().unwrap();
|
||||
let outside_target = outside.path().join("secret.txt");
|
||||
std::fs::write(&outside_target, "secret").unwrap();
|
||||
@@ -151,7 +143,7 @@ async fn symlink_to_outside_scope_is_rejected_for_write() {
|
||||
async fn broken_symlink_reports_target_and_repair_hint() {
|
||||
use std::os::unix::fs::symlink;
|
||||
|
||||
let (dir, _spill, reg) = setup();
|
||||
let (dir, reg) = setup();
|
||||
let link = dir.path().join("external-project");
|
||||
let target = dir.path().join("missing-target");
|
||||
symlink(&target, &link).unwrap();
|
||||
@@ -173,7 +165,7 @@ async fn broken_symlink_reports_target_and_repair_hint() {
|
||||
|
||||
#[tokio::test]
|
||||
async fn empty_file_read_and_edit() {
|
||||
let (dir, _spill, reg) = setup();
|
||||
let (dir, reg) = setup();
|
||||
let file = dir.path().join("empty.txt");
|
||||
std::fs::write(&file, "").unwrap();
|
||||
|
||||
@@ -207,7 +199,7 @@ async fn empty_file_read_and_edit() {
|
||||
|
||||
#[tokio::test]
|
||||
async fn very_long_single_line() {
|
||||
let (dir, _spill, reg) = setup();
|
||||
let (dir, reg) = setup();
|
||||
let file = dir.path().join("long.txt");
|
||||
let big: String = "x".repeat(1024 * 1024); // 1 MiB, no newlines
|
||||
std::fs::write(&file, &big).unwrap();
|
||||
@@ -226,7 +218,7 @@ async fn very_long_single_line() {
|
||||
|
||||
#[tokio::test]
|
||||
async fn absolute_path_requires_matching_read_scope() {
|
||||
let (_dir, _spill, reg) = setup();
|
||||
let (_dir, reg) = setup();
|
||||
let outside = tempfile::tempdir().unwrap();
|
||||
let outside_file = outside.path().join("outside.txt");
|
||||
std::fs::write(&outside_file, "secret").unwrap();
|
||||
@@ -247,7 +239,7 @@ async fn absolute_path_requires_matching_read_scope() {
|
||||
|
||||
#[tokio::test]
|
||||
async fn directory_target_is_rejected_for_read() {
|
||||
let (_dir, _spill, reg) = setup();
|
||||
let (_dir, reg) = setup();
|
||||
let read = reg.get("Read");
|
||||
let err = read
|
||||
.execute(&json!({ "file_path": "." }).to_string(), Default::default())
|
||||
@@ -258,7 +250,7 @@ async fn directory_target_is_rejected_for_read() {
|
||||
|
||||
#[tokio::test]
|
||||
async fn deeply_nested_new_file_is_created() {
|
||||
let (dir, _spill, reg) = setup();
|
||||
let (dir, reg) = setup();
|
||||
let deep = dir.path().join("a/b/c/d/e/deep.txt");
|
||||
let write = reg.get("Write");
|
||||
write
|
||||
@@ -277,7 +269,7 @@ async fn deeply_nested_new_file_is_created() {
|
||||
|
||||
#[tokio::test]
|
||||
async fn replace_preserves_unicode() {
|
||||
let (dir, _spill, reg) = setup();
|
||||
let (dir, reg) = setup();
|
||||
let file = dir.path().join("u.txt");
|
||||
std::fs::write(&file, "🦀 rust 🦀\n").unwrap();
|
||||
|
||||
@@ -306,7 +298,7 @@ async fn replace_preserves_unicode() {
|
||||
|
||||
#[tokio::test]
|
||||
async fn grep_handles_unicode_pattern() {
|
||||
let (dir, _spill, reg) = setup();
|
||||
let (dir, reg) = setup();
|
||||
let file = dir.path().join("u.txt");
|
||||
std::fs::write(&file, "English\n日本語\nрусский\n").unwrap();
|
||||
|
||||
|
||||
+1035
-153
File diff suppressed because it is too large
Load Diff
+36
-20
@@ -3013,7 +3013,8 @@ impl App {
|
||||
/// `[File: …]` parsing path: each kind maps directly to a typed
|
||||
/// block (`Block::Notify`, `Block::WorkerEvent`, …).
|
||||
fn apply_system_item(&mut self, value: &serde_json::Value) {
|
||||
let Ok(item) = serde_json::from_value::<session_store::SystemItem>(value.clone()) else {
|
||||
let Ok(item) = serde_json::from_value::<session_store::PublicSystemItem>(value.clone())
|
||||
else {
|
||||
// Unknown / forward-compat shape: fall back to rendering the
|
||||
// raw text payload (if any) as a generic system message.
|
||||
if let Some(text) = value.get("body").and_then(|b| b.as_str()) {
|
||||
@@ -3024,29 +3025,23 @@ impl App {
|
||||
}
|
||||
return;
|
||||
};
|
||||
match item {
|
||||
session_store::SystemItem::Notification { message, .. } => {
|
||||
let body = item.body;
|
||||
match item.presentation {
|
||||
session_store::PublicSystemPresentation::Notification { message } => {
|
||||
self.blocks.push(Block::Notify { message });
|
||||
}
|
||||
session_store::SystemItem::WorkerEvent { event, .. } => {
|
||||
session_store::PublicSystemPresentation::WorkerEvent { event } => {
|
||||
self.blocks.push(Block::WorkerEvent { event });
|
||||
}
|
||||
session_store::SystemItem::FeatureInvocationResult { body, .. }
|
||||
| session_store::SystemItem::FileAttachment { body, .. }
|
||||
| session_store::SystemItem::SkillActivation { body, .. }
|
||||
| session_store::SystemItem::JournalStartup { body, .. }
|
||||
| session_store::SystemItem::ResidentSummaryRefresh { body, .. }
|
||||
| session_store::SystemItem::SubjectBehaviorRefresh { body, .. }
|
||||
| session_store::SystemItem::Interrupt { body, .. } => {
|
||||
session_store::PublicSystemPresentation::Context => {
|
||||
self.task_store.apply_system_message_text(&body);
|
||||
self.blocks.push(Block::SystemMessage { text: body });
|
||||
}
|
||||
session_store::SystemItem::TaskReminder { body, .. } => {
|
||||
session_store::PublicSystemPresentation::TaskReminder => {
|
||||
self.task_store.apply_system_message_text(&body);
|
||||
self.blocks.push(Block::TaskReminder { text: body });
|
||||
}
|
||||
session_store::SystemItem::LegacyIgnored { .. } => {}
|
||||
session_store::SystemItem::LegacyKnowledgeIgnored { .. } => {}
|
||||
session_store::PublicSystemPresentation::Ignored => {}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -3572,6 +3567,7 @@ mod completion_flow_tests {
|
||||
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,
|
||||
@@ -4329,6 +4325,7 @@ mod completion_flow_tests {
|
||||
}));
|
||||
app.handle_worker_event(Event::SessionEntryCommitted {
|
||||
entry: protocol::SessionSnapshotEntry {
|
||||
use_policy: None,
|
||||
entry_id: "run-failure".into(),
|
||||
timestamp: 2,
|
||||
provenance: protocol::SessionEntryProvenance::LegacyUnknown,
|
||||
@@ -4450,12 +4447,12 @@ mod completion_flow_tests {
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn live_legacy_workflow_system_item_is_ignored() {
|
||||
fn retired_system_input_is_ignored() {
|
||||
let mut app = App::new("test".into());
|
||||
let item = serde_json::json!({
|
||||
"kind": "workflow",
|
||||
"slug": "build",
|
||||
"body": "[Workflow /build]\nRun the build",
|
||||
"kind": "retired_input",
|
||||
"body": "",
|
||||
"presentation": { "kind": "ignored" },
|
||||
});
|
||||
app.handle_worker_event(Event::SystemItem {
|
||||
entry_id: None,
|
||||
@@ -4861,12 +4858,30 @@ mod completion_flow_tests {
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn feature_label_does_not_select_system_input_presentation() {
|
||||
for label in ["journal_startup", "new-unregistered-feature"] {
|
||||
let mut app = App::new("test".into());
|
||||
app.handle_worker_event(Event::SystemItem {
|
||||
entry_id: None,
|
||||
item: serde_json::json!({
|
||||
"kind": label,
|
||||
"body": "explicit public content",
|
||||
"presentation": { "kind": "context" },
|
||||
}),
|
||||
});
|
||||
assert!(
|
||||
matches!(app.blocks.as_slice(), [Block::SystemMessage { text }] if text == "explicit public content")
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn live_system_item_notification_appends_notify_block() {
|
||||
let mut app = App::new("test".into());
|
||||
let item = serde_json::json!({
|
||||
"kind": "notification",
|
||||
"message": "hi",
|
||||
"presentation": { "kind": "notification", "message": "hi" },
|
||||
"body": "[Notification] hi",
|
||||
});
|
||||
app.handle_worker_event(Event::SystemItem {
|
||||
@@ -4884,7 +4899,7 @@ mod completion_flow_tests {
|
||||
let mut app = App::new("test".into());
|
||||
let item = serde_json::json!({
|
||||
"kind": "worker_event",
|
||||
"event": { "kind": "turn_ended", "worker_name": "child" },
|
||||
"presentation": { "kind": "worker_event", "event": { "kind": "turn_ended", "worker_name": "child" } },
|
||||
"body": "[Notification] worker `child` finished a turn",
|
||||
});
|
||||
app.handle_worker_event(Event::SystemItem {
|
||||
@@ -5285,6 +5300,7 @@ mod completion_flow_tests {
|
||||
item: serde_json::json!({
|
||||
"kind": "task_reminder",
|
||||
"body": snapshot,
|
||||
"presentation": { "kind": "task_reminder" },
|
||||
}),
|
||||
});
|
||||
|
||||
|
||||
@@ -162,6 +162,7 @@ fn request_from_selection(selection: Selection) -> BackendCreateWorkerRequest {
|
||||
ticket_assignment: None,
|
||||
feature_connections: Default::default(),
|
||||
control_operation_id: None,
|
||||
execution_grant: None,
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -20,8 +20,9 @@ serde_json.workspace = true
|
||||
sha2.workspace = true
|
||||
tempfile.workspace = true
|
||||
thiserror.workspace = true
|
||||
tokio = { workspace = true, features = ["process", "rt", "sync", "time"] }
|
||||
tokio = { workspace = true, features = ["io-util", "process", "rt", "sync", "time"] }
|
||||
|
||||
[dev-dependencies]
|
||||
axum.workspace = true
|
||||
serde_json.workspace = true
|
||||
tempfile.workspace = true
|
||||
|
||||
@@ -6,7 +6,7 @@
|
||||
//! hashes alone do not accept same-content inode replacements. Callers own Read line numbering
|
||||
//! and per-attachment read history.
|
||||
//!
|
||||
//! Create paths are checkout-root-relative and must be strict descendants of the observed target
|
||||
//! Create paths use the target's session coordinates and must be strict descendants of the observed target
|
||||
//! directory. Existing destinations are never overwritten; results return the updated observation
|
||||
//! of the retained target directory, not the created file. Read results also return the validator
|
||||
//! of the state actually read, never a replacement from a later independent stat.
|
||||
@@ -18,7 +18,8 @@
|
||||
//!
|
||||
//! Search delegates to shared List/Glob/Grep engines. Scope rules form unions within layers and
|
||||
//! intersections across layers, provider authority, and output roots. Wrappers transform coordinates
|
||||
//! once; returned paths and Grep content are relative to the final session's logical root.
|
||||
//! once; returned paths and Grep content are relative to the composed output root (the caller's
|
||||
//! cwd by default).
|
||||
//! Paths are not reverse-parsed from rendered filenames; non-UTF-8 names are not lossily aliased.
|
||||
//! Unsupported providers reject search rather than fall back to broader trait searches. Search is
|
||||
//! live traversal, not an atomic snapshot of all descendants or exclusion of external editors.
|
||||
@@ -48,6 +49,10 @@ pub struct CheckoutRequest {
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize, JsonSchema)]
|
||||
#[serde(tag = "operation", rename_all = "snake_case", deny_unknown_fields)]
|
||||
pub enum CheckoutOperation {
|
||||
ReadBytes {
|
||||
offset: u64,
|
||||
max_bytes: usize,
|
||||
},
|
||||
Read {
|
||||
offset: usize,
|
||||
limit: usize,
|
||||
@@ -71,7 +76,7 @@ pub enum CheckoutOperation {
|
||||
impl CheckoutOperation {
|
||||
pub fn capability(&self) -> WorkdirSessionCapability {
|
||||
match self {
|
||||
Self::Read { .. } => WorkdirSessionCapability::Read,
|
||||
Self::Read { .. } | Self::ReadBytes { .. } => WorkdirSessionCapability::Read,
|
||||
Self::Edit { .. } => WorkdirSessionCapability::Edit,
|
||||
Self::Write { .. } | Self::Create { .. } => WorkdirSessionCapability::Write,
|
||||
}
|
||||
@@ -86,6 +91,7 @@ impl CheckoutOperation {
|
||||
)]
|
||||
pub enum CheckoutOutput {
|
||||
Read(ReadResult),
|
||||
ReadBytes(crate::ReadBytesResult),
|
||||
Write(WriteResult),
|
||||
Edit(EditResult),
|
||||
}
|
||||
@@ -551,15 +557,13 @@ mod tests {
|
||||
));
|
||||
}
|
||||
#[tokio::test]
|
||||
async fn checkout_hardlink_save_isolates_alias_and_rejects_symlinks_special_files() {
|
||||
async fn checkout_hardlink_save_isolates_alias_and_rejects_symlinks() {
|
||||
let root = tempfile::tempdir().unwrap();
|
||||
std::fs::write(root.path().join("a"), "original").unwrap();
|
||||
std::fs::hard_link(root.path().join("a"), root.path().join("alias")).unwrap();
|
||||
std::os::unix::fs::symlink("a", root.path().join("link")).unwrap();
|
||||
let _socket = std::os::unix::net::UnixListener::bind(root.path().join("socket")).unwrap();
|
||||
let session = session(root.path());
|
||||
assert!(session.checkout_observe(path("link")).await.is_err());
|
||||
assert!(session.checkout_observe(path("socket")).await.is_err());
|
||||
let read = checked_read(&session, session.checkout_observe(path("a")).await.unwrap()).await;
|
||||
session
|
||||
.checkout_execute(CheckoutRequest {
|
||||
|
||||
@@ -0,0 +1,43 @@
|
||||
//! Bounded collection for tests whose subject is command routing/lifecycle,
|
||||
//! rather than the byte-page protocol itself.
|
||||
|
||||
use crate::*;
|
||||
|
||||
#[derive(Debug)]
|
||||
pub(crate) struct CollectedCommand {
|
||||
pub content: String,
|
||||
pub status: CommandStatus,
|
||||
pub exit_code: Option<i32>,
|
||||
pub timed_out: bool,
|
||||
}
|
||||
|
||||
#[async_trait::async_trait]
|
||||
pub(crate) trait CollectCommand: WorkdirSession {
|
||||
async fn collect_command_output(
|
||||
&self,
|
||||
mut request: CommandOutputRequest,
|
||||
) -> Result<CollectedCommand, WorkdirError> {
|
||||
let mut bytes = Vec::new();
|
||||
request.wait = true;
|
||||
loop {
|
||||
let page = self.command_output(request.clone()).await?;
|
||||
for chunk in page.chunks {
|
||||
bytes.extend(chunk.bytes);
|
||||
assert!(
|
||||
bytes.len() <= 16 * 1024 * 1024,
|
||||
"fixture output exceeded bounded test collection"
|
||||
);
|
||||
}
|
||||
request.cursor = page.next_cursor;
|
||||
if let Some(terminal) = page.terminal {
|
||||
return Ok(CollectedCommand {
|
||||
content: String::from_utf8_lossy(&bytes).into_owned(),
|
||||
status: terminal.status,
|
||||
exit_code: terminal.exit_code,
|
||||
timed_out: terminal.status == CommandStatus::TimedOut,
|
||||
});
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
impl<T: WorkdirSession + ?Sized> CollectCommand for T {}
|
||||
@@ -0,0 +1,68 @@
|
||||
//! Model-facing session coordinates, separate from provider paths and authority.
|
||||
|
||||
use crate::{WorkdirPath, WorkdirSessionCapabilities, WorkdirToolScopeRule};
|
||||
use schemars::JsonSchema;
|
||||
use serde::{Deserialize, Serialize};
|
||||
|
||||
/// A snapshot of the environment actually used by a session's operations.
|
||||
///
|
||||
/// Cwd is a logical Workdir-root coordinate. Scope targets use that root or
|
||||
/// explicit absolute provider paths. Scope is an additional allow ceiling, not
|
||||
/// a replacement for provider checks. Providers
|
||||
/// may retain further restrictions (including deny rules); this projection
|
||||
/// never authorizes an operation.
|
||||
#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize, JsonSchema)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct WorkdirSessionEnvironment {
|
||||
#[serde(deserialize_with = "deserialize_cwd")]
|
||||
pub cwd: WorkdirPath,
|
||||
pub scope: Option<Vec<WorkdirToolScopeRule>>,
|
||||
pub capabilities: WorkdirSessionCapabilities,
|
||||
pub restrictions: Vec<String>,
|
||||
}
|
||||
|
||||
fn deserialize_cwd<'de, D: serde::Deserializer<'de>>(
|
||||
deserializer: D,
|
||||
) -> Result<WorkdirPath, D::Error> {
|
||||
let path = String::deserialize(deserializer)?;
|
||||
WorkdirPath::new(path).map_err(serde::de::Error::custom)
|
||||
}
|
||||
|
||||
impl WorkdirSessionEnvironment {
|
||||
pub fn root(capabilities: WorkdirSessionCapabilities) -> Self {
|
||||
Self {
|
||||
cwd: WorkdirPath::root(),
|
||||
scope: None,
|
||||
capabilities,
|
||||
restrictions: Vec::new(),
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
#[test]
|
||||
fn wire_cwd_is_normalized_and_cannot_claim_an_absolute_or_parent_base() {
|
||||
let mut wire = serde_json::to_value(WorkdirSessionEnvironment::root(
|
||||
WorkdirSessionCapabilities::READ_ONLY,
|
||||
))
|
||||
.unwrap();
|
||||
for invalid in [
|
||||
"/absolute",
|
||||
"../parent",
|
||||
"nested/../parent",
|
||||
"nested\\other",
|
||||
] {
|
||||
wire["cwd"] = invalid.into();
|
||||
assert!(
|
||||
serde_json::from_value::<WorkdirSessionEnvironment>(wire.clone()).is_err(),
|
||||
"{invalid}"
|
||||
);
|
||||
}
|
||||
wire["cwd"] = "./nested//child".into();
|
||||
let decoded: WorkdirSessionEnvironment = serde_json::from_value(wire).unwrap();
|
||||
assert_eq!(decoded.cwd.as_str(), "nested/child");
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,175 @@
|
||||
//! Real Local/scoped/read-only/router sessions across loopback HTTP. Only the
|
||||
//! HTTP authentication boundary is a fixture; coordinate and scope checks are
|
||||
//! production implementations. Runs in the normal http-client library suite.
|
||||
#![cfg(all(feature = "http-client", target_os = "linux"))]
|
||||
|
||||
use crate::http::*;
|
||||
use crate::*;
|
||||
use axum::{
|
||||
Json, Router,
|
||||
extract::State,
|
||||
routing::{delete, post},
|
||||
};
|
||||
use std::sync::Arc;
|
||||
|
||||
struct Server(tokio::task::JoinHandle<()>);
|
||||
impl Drop for Server {
|
||||
fn drop(&mut self) {
|
||||
self.0.abort();
|
||||
}
|
||||
}
|
||||
|
||||
async fn open(State(session): State<WorkdirSessionHandle>) -> Json<OpenWorkdirSessionResponse> {
|
||||
Json(OpenWorkdirSessionResponse {
|
||||
session_id: WorkdirSessionId::new("environment-session").unwrap(),
|
||||
workdir_id: session.workdir().id().clone(),
|
||||
capabilities: session.capabilities(),
|
||||
environment: session.environment(),
|
||||
})
|
||||
}
|
||||
async fn operation(
|
||||
State(session): State<WorkdirSessionHandle>,
|
||||
Json(request): Json<WorkdirSessionOperationRequest>,
|
||||
) -> Result<
|
||||
Json<WorkdirSessionOperationResult>,
|
||||
(axum::http::StatusCode, Json<WorkdirTransportError>),
|
||||
> {
|
||||
dispatch_workdir_session_operation(session.as_ref(), request.operation)
|
||||
.await
|
||||
.map(Json)
|
||||
.map_err(|error| {
|
||||
(
|
||||
axum::http::StatusCode::FORBIDDEN,
|
||||
Json(WorkdirTransportError::from_workdir_error(&error)),
|
||||
)
|
||||
})
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn remote_environment_matches_scoped_readonly_operations_without_rebasing_twice() {
|
||||
let root = tempfile::tempdir().unwrap();
|
||||
std::fs::create_dir(root.path().join("nested")).unwrap();
|
||||
std::fs::write(root.path().join("nested/file.txt"), "nested marker").unwrap();
|
||||
std::fs::write(root.path().join("file.txt"), "root decoy").unwrap();
|
||||
let broker = WorkdirToolBroker::new(Arc::new(LocalWorkdirSession::new(
|
||||
manifest::Scope::writable(root.path()).unwrap(),
|
||||
root.path().to_path_buf(),
|
||||
)));
|
||||
let lease = broker
|
||||
.scope(WorkdirToolScope {
|
||||
cwd: WorkdirPath::new("nested").unwrap(),
|
||||
rules: vec![WorkdirToolScopeRule {
|
||||
target: WorkdirPath::new("nested").unwrap(),
|
||||
permission: WorkdirToolScopePermission::Write,
|
||||
recursive: true,
|
||||
symlink_policy: Default::default(),
|
||||
}],
|
||||
command: true,
|
||||
})
|
||||
.await
|
||||
.unwrap();
|
||||
let session: WorkdirSessionHandle = Arc::new(ReadOnlyWorkdirSession::new(lease.tool_session()));
|
||||
let expected = session.environment();
|
||||
let app = Router::new()
|
||||
.route("/v1/working-directories/{id}/sessions", post(open))
|
||||
.route("/v1/workdir-sessions/{id}/operations", post(operation))
|
||||
.route(
|
||||
"/v1/workdir-sessions/{id}",
|
||||
delete(|| async { axum::http::StatusCode::NO_CONTENT }),
|
||||
)
|
||||
.with_state(session.clone());
|
||||
let listener = tokio::net::TcpListener::bind("127.0.0.1:0").await.unwrap();
|
||||
let address = listener.local_addr().unwrap();
|
||||
let _server = Server(tokio::spawn(async move {
|
||||
axum::serve(listener, app).await.unwrap();
|
||||
}));
|
||||
let remote: WorkdirSessionHandle = Arc::new(
|
||||
RemoteWorkdirSession::open(
|
||||
reqwest::Client::builder().no_proxy().build().unwrap(),
|
||||
format!("http://{address}").parse().unwrap(),
|
||||
"fixture",
|
||||
session.workdir().id().clone(),
|
||||
OpenWorkdirSessionRequest::default(),
|
||||
)
|
||||
.await
|
||||
.unwrap(),
|
||||
);
|
||||
let router = WorkdirSessionRouter::new();
|
||||
router
|
||||
.attach(WorkdirAttachmentAlias::new("remote").unwrap(), remote)
|
||||
.unwrap();
|
||||
let selected = router.resolve(Some("remote")).unwrap().session;
|
||||
assert_eq!(selected.environment(), expected);
|
||||
assert_eq!(expected.cwd, WorkdirPath::new("nested").unwrap());
|
||||
assert!(
|
||||
!expected
|
||||
.capabilities
|
||||
.supports(WorkdirSessionCapability::Command)
|
||||
);
|
||||
assert!(
|
||||
expected
|
||||
.scope
|
||||
.unwrap()
|
||||
.iter()
|
||||
.all(|rule| rule.permission == WorkdirToolScopePermission::Read)
|
||||
);
|
||||
let found = selected
|
||||
.glob(GlobRequest {
|
||||
path: WorkdirPath::root(),
|
||||
pattern: "*.txt".into(),
|
||||
limit: 10,
|
||||
})
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(found.paths, vec![WorkdirPath::new("file.txt").unwrap()]);
|
||||
let path = found.paths[0].clone();
|
||||
let read = selected
|
||||
.read(ReadRequest {
|
||||
path: path.clone(),
|
||||
offset: 0,
|
||||
limit: 10,
|
||||
max_bytes: 100,
|
||||
})
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(read.path, path);
|
||||
assert_eq!(read.bytes, b"nested marker");
|
||||
assert!(
|
||||
selected
|
||||
.write(WriteRequest {
|
||||
path,
|
||||
content: b"denied".to_vec(),
|
||||
expected_hash: Some(read.content_hash)
|
||||
})
|
||||
.await
|
||||
.is_err()
|
||||
);
|
||||
assert!(
|
||||
selected
|
||||
.read(ReadRequest {
|
||||
path: WorkdirPath::new_scoped(root.path().join("file.txt").to_str().unwrap())
|
||||
.unwrap(),
|
||||
offset: 0,
|
||||
limit: 10,
|
||||
max_bytes: 100
|
||||
})
|
||||
.await
|
||||
.is_err()
|
||||
);
|
||||
assert!(
|
||||
selected
|
||||
.start_command(CommandRequest {
|
||||
command: "touch escaped".into(),
|
||||
cwd: WorkdirPath::root(),
|
||||
timeout_secs: 5,
|
||||
transport_byte_budget: 100,
|
||||
tool_call_id: None
|
||||
})
|
||||
.await
|
||||
.is_err()
|
||||
);
|
||||
assert!(!root.path().join("nested/escaped").exists());
|
||||
router.close_all().await.unwrap();
|
||||
lease.close().await.unwrap();
|
||||
broker.close().await.unwrap();
|
||||
}
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user