fix(runner): always emit MESSAGES_SNAPSHOT to prevent compaction failures#1693
Merged
Conversation
…ures Three fixes to ensure MESSAGES_SNAPSHOT is always emitted, which is required for compactFinishedRun to succeed. Without it, sessions are marked corrupted and chat history is lost after the JSONL tail-read optimization (ffe4a21). - adapter.py: Remove `if run_messages:` guard around MESSAGES_SNAPSHOT emission. Runs that produce no assistant output (interrupted, halted on frontend tool, state-tool-only) still need a snapshot so compaction can succeed. When run_messages is empty the snapshot is the stamped input history, which is sufficient for compaction to find MESSAGES_SNAPSHOT and atomically replace the JSONL. - grpc_transport.py: Skip empty-payload gRPC messages instead of building a message with empty content. An empty-content message causes process_messages to return "" which triggers an early RunFinishedEvent before _stream_claude_sdk runs, so run_messages stays empty and MESSAGES_SNAPSHOT is never emitted. Affects both Operator-managed and control-plane-reconciled runner sessions. - run.py: Assign UUIDs to message dicts that lack an id in to_run_agent_input. Without ids, upsert_message falls back to append for every message, creating duplicates in the MESSAGES_SNAPSHOT for multi-turn sessions going through the gRPC dict message path. Co-Authored-By: Claude <noreply@anthropic.com>
✅ Deploy Preview for cheerful-kitten-f556a0 canceled.
|
Contributor
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: CHILL Plan: Enterprise Run ID: 📒 Files selected for processing (3)
📝 WalkthroughWalkthroughThree defensive fixes in the ambient runner message pipeline: incoming messages are normalized with injected UUIDs when ChangesAmbient Runner Message Pipeline Robustness
🚥 Pre-merge checks | ✅ 7 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (7 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches📝 Generate docstrings
🧪 Generate unit tests (beta)
✨ Simplify code
Comment |
Contributor
Merge Queue Status
This pull request spent 12 seconds in the queue, including 2 seconds running CI. Required conditions to merge |
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.
Summary
C1 —
grpc_transport.py: Skip gRPC messages with empty payloads instead of building an empty-content message. An empty-content message causesprocess_messagesto return"", which triggers an earlyRunFinishedEventbefore_stream_claude_sdkever runs — sorun_messagesstays empty andMESSAGES_SNAPSHOTis never emitted. Affects both Operator-managed and control-plane-reconciled runner sessions.C2 —
run.py: Assign UUIDs to message dicts missing anidinto_run_agent_input. Without ids,upsert_messagefalls back to append on every call, creating duplicates in the snapshot for multi-turn sessions going through the gRPC dict message path.C3 —
adapter.py: Remove theif run_messages:guard aroundMESSAGES_SNAPSHOTemission. Runs that produce no assistant output (interrupted, halted on frontend tool, state-management-tool-only turns) still need a snapshot socompactFinishedRuncan succeed. Whenrun_messagesis empty the snapshot contains the stamped input history, which is sufficient. Without a snapshot, compaction logs "session corrupted, keeping raw events" and chat history is lost after the tail-read optimization (ffe4a21).Root cause
compactFinishedRun(backendagui_store.go) requiresMESSAGES_SNAPSHOTto be present in the JSONL to perform compaction. If absent, it aborts and leaves raw streaming delta events in the file. On the next large-session tail-read (8e3bac3), those deltas may be missing from the head scan and the user sees blank chat history on reconnect.The
MESSAGES_SNAPSHOTgap was introduced whenambient-control-planeadded a second reconciled runner path: control-plane sessions reach the runner via gRPC (GRPCSessionListener) rather than HTTP, and the gRPC path has different message-shape guarantees that exposed all three gaps simultaneously.Test plan
MESSAGES_SNAPSHOTlog line should appear for everyRUN_FINISHED/RUN_ERRORturncompactionlog should showX raw events → Y snapshot events(not "session corrupted")🤖 Generated with Claude Code
Summary by CodeRabbit
Release Notes