fix(telemetry): join overlapping flush hints; contain adoption replay per event

Second review round, both pinned red-first:

- Overlapping turn-boundary flush hints now JOIN the outstanding flush
  promise (Promise.all) instead of displacing it: the SDK's
  concurrent-flush guard resolves an overlapping forceFlush()
  immediately, so retaining only the latest promise let shutdown()
  proceed while the first export was still in flight — the same silent
  drop the single-flush fix closed.
- Adoption replay contains failures per event, matching the firehose:
  one rejected record is withheld fail-closed while the rest of the
  historical log still hands off. Wrapping the whole loop let a single
  failure silently skip the remainder on an already-adopted session.
This commit is contained in:
kingwl
2026-07-25 03:48:32 +08:00
parent e6a8ff2621
commit d398eda432
4 changed files with 77 additions and 12 deletions

View File

@@ -113,15 +113,19 @@ export class TelemetryCoordinator {
* @param session - the live session to adopt; a second adoption is a no-op.
*/
private adopt(session: Session): void {
this.contain(() => {
if (this.adopted.has(session)) return
this.adopted.add(session)
const cursor = handoffCursor.get(session) ?? -1
for (const event of session.events) {
if (this.adopted.has(session)) return
this.adopted.add(session)
const cursor = handoffCursor.get(session) ?? -1
// Containment is PER EVENT, matching the firehose: one rejected record
// is withheld fail-closed while the rest of the historical replay
// proceeds — wrapping the whole loop would let a single failure silently
// skip the remainder of the log on an already-adopted session.
for (const event of session.events) {
this.contain(() => {
if (event.seq <= cursor) this.track(session, event)
else this.capture(session, event)
}
})
})
}
}
/** Feed the chunk projection without handing off — the ≤cursor half of re-adoption. */

View File

@@ -26,11 +26,15 @@ class FakeBackend implements TelemetryBackend {
records: TelemetryRecord[] = []
calls: string[] = []
emitError: Error | undefined
rejectSeq: number | undefined
shutdownError: Error | undefined
shutdownResolved = false
emit(record: TelemetryRecord): void {
if (this.emitError) throw this.emitError
if (this.rejectSeq !== undefined && record.attributes['event.seq'] === this.rejectSeq) {
throw new Error(`backend rejected seq ${this.rejectSeq}`)
}
this.records.push(record)
this.calls.push(`emit:${String(record.attributes['event.seq'] ?? record.attributes['telemetry.op'])}`)
}
@@ -213,6 +217,28 @@ describe('TelemetryCoordinator adoption', () => {
expect(second.ledger().map(r => r.attributes['event.type'])).toEqual(['turn/end'])
})
it('replays past a record the backend rejects: one event withheld, the rest adopted', async () => {
const backend = new FakeBackend()
const ctx = new Context()
await ctx.plugin(SessionStore)
const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => {})
const session = liveSession(ctx, 'partial')
appendTurn(session)
session.append('turn/end', { turn: 1, reason: { kind: 'completed' } })
// The backend rejects exactly the middle historical event: fail-closed
// must withhold THAT record only — an adoption replay that dies on the
// first contained failure would silently skip the rest of the log while
// the session stays marked adopted.
backend.rejectSeq = 1
await ctx.plugin({
name: 'fake-telemetry',
inject: ['sessions'],
apply: (inner: Context) => void new TelemetryCoordinator(inner, backend),
})
expect(backend.ledger().map(r => r.attributes['event.seq'])).toEqual([0, 2])
expect(warn).toHaveBeenCalled()
})
it('re-hands the full log when no cursor survived (fresh session object)', async () => {
const backend = new FakeBackend()
const ctx = new Context()