[agent] sprint-executor: task-d98bb271 - #695
Open
sunholo-voight-kampff wants to merge 2 commits into
Open
Conversation
…ing (M2+M3) Completes M-MISSION-LOOP-UNIFIED-TELEMETRY. M1 (session-keyed chain linkage) landed in 56b449d; this is M2 and M3. M2 — a mission iteration reported $0.0000 while holding $0.1077. Two defects with DIFFERENT owners, which is why they are separate changes: * writer-side: PostIteration created stages and never transitioned them, so every stage kept CreateStage's pending default. IterationStage now carries a per-stage `status`. * caller-side: IterationStage already carried TokensIn/TokensOut and already passed them to UpdateStageMetrics — the zeros came from the poster. The mission-control skill now supplies the real counts. Stage cost/tokens are also aggregated into the chain total, which nothing credited before. `status` is per stage on purpose: a stage that failed reads back `failed`, and StagesCompleted excludes it. Blanket-completing an iteration's stages would satisfy "nothing left pending" while hiding the failure, so that is tested against rather than merely avoided. An omitted status stays valid and leaves the stage pending (the skill and the CLI ship independently); an unrecognised value is rejected loudly rather than coerced. M3 — PostIteration now writes through a narrow IterationSink, a strict subset of observatory.Backend, so the Firestore store satisfies it (compile-time assertion added there). UpdateStageEvalAssessment is SQLite-only, so it is an optional IterationModelSink upgrade whose absence is reported, never silent. PostToLegs/FlushLegs write to every destination this NODE has configured: local always, cloud when AILANG_STORAGE=gcp. Nothing is rig-specific. hybrid is deliberately not a cloud leg — it resolves the observatory to local SQLite, so treating it as one would dual-write the same database twice. Each leg spools SEPARATELY. A shared spool would replay a post the local leg already stored, duplicating that chain on every flush. This extends the existing bounded+loud spool rather than inventing a fail-soft policy: the 100-entry / 1 MiB caps hold, every buffering event warns, and the command still exits 0. `ailang chains list|view --remote` reads the configured cloud observatory. Local stays the default; --remote with no cloud configured is an error, because a remote query silently answered from SQLite would report a cloud-side record as absent when it was never queried. Not done: the live cloud read-back, which needs credentials the sprint sandbox does not have. Recorded in the design doc and the handover. Tests: the SQLite read-back tests run in CI; every accounting rule is ALSO covered by cgo-free fake-sink tests, because this sandbox has no C toolchain. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Matches the surrounding style in iteration_post.go; no behaviour change. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Autonomous task
task-d98bb271completed and pushed by agentsprint-executor.This PR was opened deterministically by the AILANG coordinator wrapper.
View execution chain:
ailang chains view task-d98bb271