refactor: isolate Feature System input migration and compaction policy
This commit is contained in:
@@ -95,7 +95,7 @@ pub struct LoggedSessionHistoryMetadata {
|
||||
}
|
||||
|
||||
impl LoggedSessionHistoryMetadata {
|
||||
fn validate_system_input(&self) -> Result<(), crate::SystemInputError> {
|
||||
pub(crate) fn validate_system_input(&self) -> Result<(), crate::SystemInputError> {
|
||||
if matches!(self.origin, LoggedSessionHistoryOrigin::Provided { .. })
|
||||
&& self.system_input.is_none()
|
||||
{
|
||||
|
||||
@@ -1,12 +1,12 @@
|
||||
//! Versioned decoder for Session schemas that predate canonical annotated history.
|
||||
//! Versioned decoder for Session schemas v1-4, 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;
|
||||
@@ -17,6 +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::SystemInputError> {
|
||||
use crate::InputCompactionUse::{ReferenceInput, Retain};
|
||||
let item = match self {
|
||||
Self::Core(item) => item,
|
||||
Self::Feature(feature) => {
|
||||
metadata.validate_system_input()?;
|
||||
if metadata.system_input.is_some() {
|
||||
return Err(crate::SystemInputError::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.system_input = Some(input_metadata);
|
||||
SystemItem::Input { body }
|
||||
}
|
||||
};
|
||||
let entry = LoggedSystemHistoryEntry { item, metadata };
|
||||
entry.validate_system_input()?;
|
||||
Ok(entry)
|
||||
}
|
||||
}
|
||||
|
||||
fn migrated_feature_input<T: Serialize>(
|
||||
body: String,
|
||||
label: &str,
|
||||
schema: &str,
|
||||
payload: T,
|
||||
compaction: crate::InputCompactionUse,
|
||||
) -> Result<(String, crate::SystemInputMetadata), crate::SystemInputError> {
|
||||
let metadata = crate::SystemInputMetadata::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::SystemInputError> {
|
||||
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 {
|
||||
@@ -47,7 +253,9 @@ enum LegacyHistoryLogEntry {
|
||||
},
|
||||
SystemItem {
|
||||
ts: u64,
|
||||
item: SystemItem,
|
||||
item: LegacySystemItem,
|
||||
#[serde(default)]
|
||||
extensions: Vec<SessionExtension>,
|
||||
},
|
||||
}
|
||||
|
||||
@@ -57,7 +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.
|
||||
@@ -67,7 +275,7 @@ enum LegacySessionLogEntryV1 {
|
||||
#[serde(untagged)]
|
||||
enum LegacySessionLogEntryV2 {
|
||||
History(LegacyHistoryLogEntry),
|
||||
Current(LogEntry),
|
||||
Current(LegacyAnnotatedOrCurrent),
|
||||
}
|
||||
|
||||
pub(crate) fn decode_entry(
|
||||
@@ -86,15 +294,16 @@ pub(crate) fn decode_entry(
|
||||
LegacySessionLogEntryV2::History(entry) => Entry::History(entry),
|
||||
LegacySessionLogEntryV2::Current(entry) => Entry::Current(entry),
|
||||
},
|
||||
3 => Entry::Current(serde_json::from_str(line)?),
|
||||
3 | 4 => Entry::Current(serde_json::from_str(line)?),
|
||||
_ => 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)
|
||||
}
|
||||
|
||||
/// Schema 3 used DerivedSummary for Host compaction seeds. Only the trusted
|
||||
@@ -152,9 +361,75 @@ pub(crate) fn migrate_compaction_origins(
|
||||
}
|
||||
}
|
||||
|
||||
/// Explicit v1-4 -> v5 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::SystemInputError> {
|
||||
entry.validate_system_inputs()?;
|
||||
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_system_input()?,
|
||||
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_system_inputs()
|
||||
}
|
||||
|
||||
fn migration_policy(compaction: crate::InputCompactionUse) -> crate::SystemInputUsePolicy {
|
||||
crate::SystemInputUsePolicy {
|
||||
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::SystemInputError> {
|
||||
// Check before supplying legacy policy: Provided without metadata is a
|
||||
// malformed NEW record, not permission to synthesize a producer policy.
|
||||
entry.validate_system_input()?;
|
||||
if entry.metadata.system_input.is_none()
|
||||
&& matches!(
|
||||
entry.item,
|
||||
LoggedItem::Message {
|
||||
role: crate::LoggedRole::System,
|
||||
..
|
||||
}
|
||||
)
|
||||
{
|
||||
let compaction = match entry.metadata.origin {
|
||||
LoggedSessionHistoryOrigin::JournalContext => crate::InputCompactionUse::ReferenceInput,
|
||||
LoggedSessionHistoryOrigin::CompactionSummary => {
|
||||
crate::InputCompactionUse::OpeningSummary
|
||||
}
|
||||
_ => crate::InputCompactionUse::Retain,
|
||||
};
|
||||
// No Feature payload or public projection can be recovered from text.
|
||||
entry.metadata.system_input = Some(crate::SystemInputMetadata::new(
|
||||
migration_policy(compaction),
|
||||
None,
|
||||
None,
|
||||
)?);
|
||||
}
|
||||
entry.validate_system_input()
|
||||
}
|
||||
|
||||
enum Entry {
|
||||
History(LegacyHistoryLogEntry),
|
||||
Current(LogEntry),
|
||||
Current(LegacyAnnotatedOrCurrent),
|
||||
}
|
||||
|
||||
fn legacy_metadata(
|
||||
@@ -182,8 +457,8 @@ fn canonicalize_history_entry(
|
||||
segment_id: SegmentId,
|
||||
line_index: usize,
|
||||
entry: LegacyHistoryLogEntry,
|
||||
) -> LogEntry {
|
||||
match entry {
|
||||
) -> Result<LogEntry, crate::SystemInputError> {
|
||||
Ok(match entry {
|
||||
LegacyHistoryLogEntry::SegmentStart {
|
||||
ts,
|
||||
session_id,
|
||||
@@ -237,13 +512,14 @@ 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,
|
||||
},
|
||||
}
|
||||
})
|
||||
}
|
||||
|
||||
@@ -1,5 +1,7 @@
|
||||
use super::*;
|
||||
|
||||
mod v5;
|
||||
|
||||
fn seed(
|
||||
origin: LoggedSessionHistoryOrigin,
|
||||
compacted: bool,
|
||||
|
||||
+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}}}}
|
||||
@@ -0,0 +1,596 @@
|
||||
//! 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_system_inputs().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.system_input.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.system_input.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 store = WorkerSessionStore::new(root.path()).unwrap();
|
||||
assert_marker(root.path(), 5);
|
||||
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::system_input::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::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, 6, 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_system_inputs().unwrap();
|
||||
}
|
||||
assert_eq!(
|
||||
fs::read_to_string(dir.join("session-schema.json"))
|
||||
.unwrap()
|
||||
.trim(),
|
||||
"5"
|
||||
);
|
||||
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.system_input.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(), 5, 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.system_input, v4.metadata.system_input);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[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
|
||||
.system_input
|
||||
.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_v5_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(), 5, 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(), 5);
|
||||
}
|
||||
@@ -157,8 +157,8 @@ pub enum PublicMaterialUse {
|
||||
/// A fixed material catalog. Opening a new catalog observes newly appended
|
||||
/// records; reading a body through this catalog verifies its saved digest and
|
||||
/// byte length again. Missing/corrected/deleted sources are explicit failures.
|
||||
/// Explicit evidence permission applies to model text, not the private payload;
|
||||
/// Web display and observation instead use the producer's public projection.
|
||||
/// Evidence eligibility never publishes private model text or Feature payload:
|
||||
/// System inputs also require an explicit public projection for every public use.
|
||||
pub struct SessionPublicMaterialReader {
|
||||
session_id: SessionId,
|
||||
active_segment_id: SegmentId,
|
||||
@@ -828,7 +828,7 @@ enum CanonicalBody<'a> {
|
||||
Message {
|
||||
origin: &'a LoggedSessionHistoryOrigin,
|
||||
role: LoggedRole,
|
||||
content: &'a [crate::LoggedContentPart],
|
||||
content: std::borrow::Cow<'a, [crate::LoggedContentPart]>,
|
||||
},
|
||||
ToolCall {
|
||||
origin: &'a LoggedSessionHistoryOrigin,
|
||||
@@ -904,27 +904,22 @@ fn canonical_body(
|
||||
if allowed == crate::InputEvidenceUse::Exclude {
|
||||
return None;
|
||||
}
|
||||
let public = input.public_item()?;
|
||||
if let LoggedItem::Message {
|
||||
role: LoggedRole::System,
|
||||
content,
|
||||
..
|
||||
} = &entry.item
|
||||
{
|
||||
return Some(CanonicalBody::Message {
|
||||
origin: &entry.metadata.origin,
|
||||
role: LoggedRole::System,
|
||||
content,
|
||||
content: std::borrow::Cow::Owned(vec![crate::LoggedContentPart::Text {
|
||||
text: public.body.clone(),
|
||||
}]),
|
||||
});
|
||||
}
|
||||
return None;
|
||||
}
|
||||
if matches!(
|
||||
entry.metadata.origin,
|
||||
LoggedSessionHistoryOrigin::DerivedSummary
|
||||
| LoggedSessionHistoryOrigin::CompactionSummary
|
||||
| LoggedSessionHistoryOrigin::JournalContext
|
||||
) {
|
||||
return None;
|
||||
}
|
||||
match &entry.item {
|
||||
LoggedItem::Message {
|
||||
role: LoggedRole::System,
|
||||
@@ -935,7 +930,7 @@ fn canonical_body(
|
||||
LoggedItem::Message { role, content } => Some(CanonicalBody::Message {
|
||||
origin: &entry.metadata.origin,
|
||||
role: *role,
|
||||
content,
|
||||
content: std::borrow::Cow::Borrowed(content),
|
||||
}),
|
||||
LoggedItem::ToolCall {
|
||||
call_id,
|
||||
|
||||
@@ -25,6 +25,27 @@ fn message(id: &str, role: LoggedRole, text: &str) -> LoggedHistoryEntry {
|
||||
},
|
||||
)
|
||||
}
|
||||
fn system_context(
|
||||
id: &str,
|
||||
text: &str,
|
||||
compaction: crate::InputCompactionUse,
|
||||
) -> LoggedHistoryEntry {
|
||||
let mut entry = message(id, LoggedRole::System, text);
|
||||
entry.metadata.system_input = Some(
|
||||
crate::SystemInputMetadata::new(
|
||||
crate::SystemInputUsePolicy {
|
||||
recording_material: crate::InputEvidenceUse::Exclude,
|
||||
memory_evidence: crate::InputEvidenceUse::Exclude,
|
||||
observation: crate::InputObservationUse::Hidden,
|
||||
compaction,
|
||||
},
|
||||
None,
|
||||
None,
|
||||
)
|
||||
.unwrap(),
|
||||
);
|
||||
entry
|
||||
}
|
||||
fn seed(session: SessionId, history: Vec<LoggedHistoryEntry>) -> LogEntry {
|
||||
LogEntry::AnnotatedSegmentStart {
|
||||
ts: 1,
|
||||
@@ -348,7 +369,11 @@ fn yield_resume_cancel_keep_original_boundary_identity_across_compaction() {
|
||||
.descriptors()
|
||||
.cloned()
|
||||
.collect();
|
||||
let mut summary = message("summary", LoggedRole::User, "must not replace originals");
|
||||
let mut summary = system_context(
|
||||
"summary",
|
||||
"must not replace originals",
|
||||
crate::InputCompactionUse::OpeningSummary,
|
||||
);
|
||||
summary.metadata.origin = LoggedSessionHistoryOrigin::CompactionSummary;
|
||||
summary.metadata.derivation = Some(crate::LoggedHistoryDerivation {
|
||||
sources: vec![
|
||||
@@ -544,14 +569,18 @@ fn reasoning_proves_rollback_safety_but_private_and_derived_items_are_not_materi
|
||||
let store = FsStore::new(temp.path()).unwrap();
|
||||
let session = crate::new_session_id();
|
||||
let segment = crate::new_segment_id();
|
||||
let mut derived = message("derived", LoggedRole::User, "summary");
|
||||
let mut derived = system_context("derived", "summary", crate::InputCompactionUse::Retain);
|
||||
derived.metadata.origin = LoggedSessionHistoryOrigin::DerivedSummary;
|
||||
let mut journal = message("journal", LoggedRole::User, "frozen Journal reference");
|
||||
let mut journal = system_context(
|
||||
"journal",
|
||||
"frozen Journal reference",
|
||||
crate::InputCompactionUse::ReferenceInput,
|
||||
);
|
||||
journal.metadata.origin = LoggedSessionHistoryOrigin::JournalContext;
|
||||
let mut summary = message(
|
||||
let mut summary = system_context(
|
||||
"compaction-summary",
|
||||
LoggedRole::User,
|
||||
"complementary summary",
|
||||
crate::InputCompactionUse::OpeningSummary,
|
||||
);
|
||||
summary.metadata.origin = LoggedSessionHistoryOrigin::CompactionSummary;
|
||||
let reasoning = entry(
|
||||
@@ -580,19 +609,23 @@ fn reasoning_proves_rollback_safety_but_private_and_derived_items_are_not_materi
|
||||
LogEntry::AnnotatedSystemItem {
|
||||
ts: 1,
|
||||
entry: crate::LoggedSystemHistoryEntry {
|
||||
item: crate::SystemItem::JournalStartup {
|
||||
item: crate::SystemItem::Input {
|
||||
body: "previous Journal must not become new recording material".into(),
|
||||
snapshot: serde_json::json!({"journals": []}),
|
||||
snapshot_sha256: "retained-digest".into(),
|
||||
prompt_provenance: crate::PromptRenderProvenance {
|
||||
workspace_id: None,
|
||||
source_digest: "source".into(),
|
||||
projection_digest: "projection".into(),
|
||||
logical_name: "internal.subjektiv_journal_startup".into(),
|
||||
},
|
||||
},
|
||||
metadata: LoggedSessionHistoryMetadata {
|
||||
system_input: None,
|
||||
system_input: Some(
|
||||
crate::SystemInputMetadata::new(
|
||||
crate::SystemInputUsePolicy {
|
||||
recording_material: crate::InputEvidenceUse::Exclude,
|
||||
memory_evidence: crate::InputEvidenceUse::Exclude,
|
||||
observation: crate::InputObservationUse::Hidden,
|
||||
compaction: crate::InputCompactionUse::ReferenceInput,
|
||||
},
|
||||
None,
|
||||
None,
|
||||
)
|
||||
.unwrap(),
|
||||
),
|
||||
entry_id: LoggedSessionHistoryEntryId("startup-journal".into()),
|
||||
origin: LoggedSessionHistoryOrigin::DerivedSummary,
|
||||
derivation: None,
|
||||
@@ -779,6 +812,19 @@ fn schema_v3_compaction_migrates_persistently_and_strict_reader_keeps_original_i
|
||||
panic!()
|
||||
};
|
||||
summary.metadata.origin = LoggedSessionHistoryOrigin::CompactionSummary;
|
||||
summary.metadata.system_input = Some(
|
||||
crate::SystemInputMetadata::new(
|
||||
crate::SystemInputUsePolicy {
|
||||
recording_material: crate::InputEvidenceUse::Exclude,
|
||||
memory_evidence: crate::InputEvidenceUse::Exclude,
|
||||
observation: crate::InputObservationUse::Hidden,
|
||||
compaction: crate::InputCompactionUse::OpeningSummary,
|
||||
},
|
||||
None,
|
||||
None,
|
||||
)
|
||||
.unwrap(),
|
||||
);
|
||||
assert_eq!(history, &[summary]);
|
||||
// Run-transition ids synthesized from byte offsets must be frozen before
|
||||
// the changed summary record shifts every subsequent record offset.
|
||||
@@ -827,7 +873,11 @@ fn midturn_compaction_uses_exact_source_ids_and_preserves_discarded_originals()
|
||||
],
|
||||
)
|
||||
.unwrap();
|
||||
let mut summary = message("summary", LoggedRole::User, "never use as original");
|
||||
let mut summary = system_context(
|
||||
"summary",
|
||||
"never use as original",
|
||||
crate::InputCompactionUse::OpeningSummary,
|
||||
);
|
||||
summary.metadata.origin = LoggedSessionHistoryOrigin::CompactionSummary;
|
||||
summary.metadata.derivation = Some(crate::LoggedHistoryDerivation {
|
||||
sources: vec![
|
||||
@@ -1032,7 +1082,11 @@ fn zero_turn_fork_from_seed_and_consecutive_compactions_preserve_original_identi
|
||||
for index in 0..3 {
|
||||
let compact = crate::new_segment_id();
|
||||
let summary_id = format!("summary-{index}");
|
||||
let mut summary = message(&summary_id, LoggedRole::User, "not original");
|
||||
let mut summary = system_context(
|
||||
&summary_id,
|
||||
"not original",
|
||||
crate::InputCompactionUse::OpeningSummary,
|
||||
);
|
||||
summary.metadata.origin = LoggedSessionHistoryOrigin::CompactionSummary;
|
||||
summary.metadata.derivation = Some(crate::LoggedHistoryDerivation {
|
||||
sources: source_ids
|
||||
@@ -1180,7 +1234,11 @@ fn correction_preserves_original_identity_across_compaction_without_summary_fall
|
||||
],
|
||||
)
|
||||
.unwrap();
|
||||
let mut summary = message("summary", LoggedRole::User, "not original");
|
||||
let mut summary = system_context(
|
||||
"summary",
|
||||
"not original",
|
||||
crate::InputCompactionUse::OpeningSummary,
|
||||
);
|
||||
summary.metadata.origin = LoggedSessionHistoryOrigin::CompactionSummary;
|
||||
summary.metadata.derivation = Some(crate::LoggedHistoryDerivation {
|
||||
sources: vec![LoggedSessionHistoryEntryId("result".into())],
|
||||
@@ -1228,7 +1286,11 @@ fn compaction_without_exact_derivation_or_with_invalid_turn_is_rejected() {
|
||||
),
|
||||
] {
|
||||
let segment = crate::new_segment_id();
|
||||
let mut summary = message("summary", LoggedRole::User, "not original");
|
||||
let mut summary = system_context(
|
||||
"summary",
|
||||
"not original",
|
||||
crate::InputCompactionUse::OpeningSummary,
|
||||
);
|
||||
summary.metadata.origin = LoggedSessionHistoryOrigin::CompactionSummary;
|
||||
summary.metadata.derivation = derivation;
|
||||
let mut start = seed(session, vec![summary]);
|
||||
@@ -1257,54 +1319,69 @@ fn generic_system_material_uses_explicit_evidence_purpose_not_producer_or_body()
|
||||
let session = crate::new_session_id();
|
||||
let segment = crate::new_segment_id();
|
||||
let fork = crate::new_segment_id();
|
||||
let make = |producer: &str, recording_material, memory_evidence, body: &str| {
|
||||
LoggedSystemHistoryEntry::from_input(
|
||||
LoggedSessionHistoryOrigin::Provided {
|
||||
producer: producer.into(),
|
||||
},
|
||||
None,
|
||||
SystemInputEnvelope::new(
|
||||
body,
|
||||
SystemInputMetadata::new(
|
||||
SystemInputUsePolicy {
|
||||
recording_material,
|
||||
memory_evidence,
|
||||
observation: InputObservationUse::Hidden,
|
||||
compaction: InputCompactionUse::Retain,
|
||||
},
|
||||
Some(
|
||||
FeatureInputPayload::encode(
|
||||
"unknown:future",
|
||||
99,
|
||||
&serde_json::json!({"private": "not-public"}),
|
||||
)
|
||||
.unwrap(),
|
||||
),
|
||||
None,
|
||||
let make =
|
||||
|producer: &str, recording_material, memory_evidence, body: &str, public: bool| {
|
||||
LoggedSystemHistoryEntry::from_input(
|
||||
LoggedSessionHistoryOrigin::Provided {
|
||||
producer: producer.into(),
|
||||
},
|
||||
None,
|
||||
SystemInputEnvelope::new(
|
||||
format!("private model text: {body}"),
|
||||
SystemInputMetadata::new(
|
||||
SystemInputUsePolicy {
|
||||
recording_material,
|
||||
memory_evidence,
|
||||
observation: InputObservationUse::Hidden,
|
||||
compaction: InputCompactionUse::Retain,
|
||||
},
|
||||
Some(
|
||||
FeatureInputPayload::encode(
|
||||
"unknown:future",
|
||||
99,
|
||||
&serde_json::json!({"private": "not-public"}),
|
||||
)
|
||||
.unwrap(),
|
||||
),
|
||||
public.then(|| crate::PublicSystemItem {
|
||||
kind: "context".into(),
|
||||
body: body.into(),
|
||||
presentation: crate::PublicSystemPresentation::Context,
|
||||
}),
|
||||
)
|
||||
.unwrap(),
|
||||
)
|
||||
.unwrap(),
|
||||
)
|
||||
.unwrap(),
|
||||
)
|
||||
};
|
||||
};
|
||||
let inputs = [
|
||||
make(
|
||||
"same-owner",
|
||||
InputEvidenceUse::Include,
|
||||
InputEvidenceUse::Exclude,
|
||||
"do not extract this; original material",
|
||||
true,
|
||||
),
|
||||
make(
|
||||
"same-owner",
|
||||
InputEvidenceUse::Exclude,
|
||||
InputEvidenceUse::Include,
|
||||
"memory-only original",
|
||||
true,
|
||||
),
|
||||
make(
|
||||
"renamed-owner",
|
||||
InputEvidenceUse::Exclude,
|
||||
InputEvidenceUse::Exclude,
|
||||
"reference without warning text",
|
||||
true,
|
||||
),
|
||||
make(
|
||||
"private-only",
|
||||
InputEvidenceUse::Include,
|
||||
InputEvidenceUse::Include,
|
||||
"must not publish without projection",
|
||||
false,
|
||||
),
|
||||
];
|
||||
let root = if worker_layout {
|
||||
@@ -1403,6 +1480,7 @@ fn generic_system_material_uses_explicit_evidence_purpose_not_producer_or_body()
|
||||
assert_eq!(value["role"], "system");
|
||||
assert_eq!(value["content"][0]["text"], expected_text);
|
||||
assert!(!body.contains("not-public"));
|
||||
assert!(!body.contains("private model text"));
|
||||
assert!(!body.contains("unknown:future"));
|
||||
}
|
||||
}
|
||||
|
||||
@@ -86,23 +86,16 @@ pub struct PromptRenderProvenance {
|
||||
/// `notify_wrapper` template) re-shape the live rendering on a later
|
||||
/// resume.
|
||||
///
|
||||
/// New variants get added here as fresh injection kinds come online
|
||||
/// (e.g. `TaskReminder`). The `kind` JSON tag is the snake_case form of
|
||||
/// the variant name.
|
||||
/// Feature-owned inputs use `Input` plus explicit annotated metadata; adding a
|
||||
/// Feature must not extend this enum or ordinary replay. Only core events have
|
||||
/// dedicated variants. Pre-v5 Feature kinds exist exclusively in the migration
|
||||
/// decoder, not in this current wire contract.
|
||||
#[derive(Debug, Clone, Serialize, Deserialize)]
|
||||
#[serde(tag = "kind", rename_all = "snake_case")]
|
||||
pub enum SystemItem {
|
||||
/// Generic System body; private metadata and public presentation are supplied
|
||||
/// independently by the producer in the same annotated history record.
|
||||
Input { body: String },
|
||||
/// 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,
|
||||
},
|
||||
/// 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
|
||||
@@ -125,14 +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
|
||||
@@ -140,10 +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.
|
||||
@@ -167,29 +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.
|
||||
@@ -233,13 +191,9 @@ impl SystemItem {
|
||||
Self::Input { .. }
|
||||
| Self::LegacyKnowledgeIgnored { .. }
|
||||
| Self::LegacyIgnored { .. } => PublicSystemPresentation::Ignored,
|
||||
Self::JournalStartup { .. }
|
||||
| Self::ResidentSummaryRefresh { .. }
|
||||
| Self::SubjectBehaviorRefresh { .. }
|
||||
| Self::SkillActivation { .. }
|
||||
| Self::FeatureInvocationResult { .. }
|
||||
| Self::FileAttachment { .. }
|
||||
| Self::Interrupt { .. } => PublicSystemPresentation::Context,
|
||||
Self::FileAttachment { .. } | Self::Interrupt { .. } => {
|
||||
PublicSystemPresentation::Context
|
||||
}
|
||||
};
|
||||
PublicSystemItem {
|
||||
kind: self.kind_label().to_owned(),
|
||||
@@ -257,19 +211,14 @@ impl SystemItem {
|
||||
pub fn history_text(&self) -> String {
|
||||
match self {
|
||||
SystemItem::Input { body } => body.clone(),
|
||||
SystemItem::JournalStartup { 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(),
|
||||
}
|
||||
}
|
||||
@@ -285,17 +234,12 @@ impl SystemItem {
|
||||
pub fn kind_label(&self) -> &'static str {
|
||||
match self {
|
||||
SystemItem::Input { .. } => "input",
|
||||
SystemItem::JournalStartup { .. } => "journal_startup",
|
||||
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",
|
||||
}
|
||||
}
|
||||
@@ -353,18 +297,20 @@ 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]
|
||||
@@ -392,21 +338,6 @@ mod tests {
|
||||
assert!(serde_json::from_value::<PublicSystemItem>(unknown).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": ""
|
||||
})
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn notification_history_text_returns_stored_body() {
|
||||
let item = SystemItem::Notification {
|
||||
@@ -500,29 +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 {
|
||||
|
||||
@@ -36,7 +36,8 @@ use std::path::{Path, PathBuf};
|
||||
use std::sync::{Arc, Mutex};
|
||||
use std::time::SystemTime;
|
||||
|
||||
const SESSION_SCHEMA_VERSION: u32 = 4;
|
||||
const 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;
|
||||
@@ -204,7 +205,15 @@ 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) => {
|
||||
@@ -215,11 +224,13 @@ impl WorkerSessionStore {
|
||||
}
|
||||
LEGACY_SESSION_SCHEMA_VERSION
|
||||
| PREVIOUS_SESSION_SCHEMA_VERSION
|
||||
| ANNOTATED_SESSION_SCHEMA_VERSION => {
|
||||
migrate_segment_logs_to_v4(
|
||||
| ANNOTATED_SESSION_SCHEMA_VERSION
|
||||
| COMPACTION_SESSION_SCHEMA_VERSION => {
|
||||
migrate_segment_logs_to_v5(
|
||||
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)?;
|
||||
@@ -1162,10 +1173,11 @@ fn segment_log_paths_in_directory(
|
||||
Ok(paths)
|
||||
}
|
||||
|
||||
fn migrate_segment_logs_to_v4(
|
||||
fn migrate_segment_logs_to_v5(
|
||||
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,
|
||||
@@ -1196,12 +1208,19 @@ fn migrate_segment_logs_to_v4(
|
||||
}
|
||||
// Resolve trusted creation boundaries first, then update inherited copies by
|
||||
// logical identity too (fork/rewind seeds retain the same entry id).
|
||||
let summaries = crate::legacy_session_log::compaction_summary_ids(
|
||||
plans.iter().flat_map(|plan| plan.entries.iter()),
|
||||
);
|
||||
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 entry in std::mem::take(&mut plan.entries) {
|
||||
for mut entry in std::mem::take(&mut plan.entries) {
|
||||
crate::legacy_session_log::migrate_system_inputs(&mut entry)?;
|
||||
entry.validate_system_inputs()?;
|
||||
serde_json::to_writer(&mut plan.output, &entry)?;
|
||||
plan.output.push(b'\n');
|
||||
}
|
||||
@@ -1223,7 +1242,7 @@ fn migrate_segment_logs_to_v4(
|
||||
}
|
||||
|
||||
for plan in plans {
|
||||
atomic_write_bytes(&plan.path, &plan.output)?;
|
||||
write_segment(&plan.path, &plan.output)?;
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
@@ -1240,9 +1259,19 @@ pub(crate) fn migrate_fs_session(root: &Path, session_id: SessionId) -> Result<(
|
||||
Err(error) => return Err(error.into()),
|
||||
};
|
||||
match version {
|
||||
SESSION_SCHEMA_VERSION => Ok(()),
|
||||
ANNOTATED_SESSION_SCHEMA_VERSION => {
|
||||
migrate_segment_logs_to_v4(segment_log_paths_in_directory(root)?, session_id, 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 => {
|
||||
migrate_segment_logs_to_v5(
|
||||
segment_log_paths_in_directory(root)?,
|
||||
session_id,
|
||||
version,
|
||||
atomic_write_bytes,
|
||||
)?;
|
||||
atomic_write_json(&marker, &SESSION_SCHEMA_VERSION)
|
||||
}
|
||||
_ => Err(StoreError::Corrupt {
|
||||
@@ -1253,8 +1282,15 @@ pub(crate) fn migrate_fs_session(root: &Path, session_id: SessionId) -> Result<(
|
||||
}
|
||||
|
||||
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_system_inputs()?;
|
||||
}
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
@@ -2022,6 +2058,146 @@ 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_system_inputs().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_system_inputs().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();
|
||||
|
||||
Reference in New Issue
Block a user