Repository navigation
fix(review): parse fenced findings, run the metered model, ship the review image - #762
Merged
Merged
Conversation
The review script hardcoded z-ai/glm-5.2 and ignored the MODEL the Lambda passes, so reviews were reserved at Haiku's 4 credits but ran on glm-5.2. Read MODEL, keeping glm-5.2 as the fallback when it is absent. The Lambda's default anthropic/claude-haiku-4-5 is not an OpenRouter model ID (OpenRouter uses dotted IDs). Use anthropic/claude-haiku-5.5, whose 1M context matches the model_context_window in the shared Codex config. deploy.yml never built Dockerfile.review, so the github-agent-review:latest image has been frozen since 2026-08-29 (#707). Build and push it on every deploy alongside the agent image. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Every automated review since 2026-09-10 ended in review:error with exit code 4. Codex completed and the model wrote a decision, but glm-5.2 does not honor --output-schema through OpenRouter and fenced its JSON in ```json. jq rejected the fenced file and set -e aborted the review (CloudWatch, task_mvkh3yby_ah82dd on #760). Strip a leading/trailing fence when the findings are not already JSON, and fail with an explicit message when they still are not. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Contributor
|
🛡️ Protected files detected This PR modifies files that require human review:
This PR will not be auto-merged and needs manual review. |
This was referenced Oct 25, 2026
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Every automated review since 2026-09-10 ended in
review:errorwith exit code 4. CloudWatch fortask_mvkh3yby_ah82dd(#760) shows Codex completed and the model approved the PR, but glm-5.2 does not honor--output-schemathrough OpenRouter and wrapped its JSON in a```jsonfence.jqrejected the file andset -eaborted the review.review-entrypoint.shhardcodedz-ai/glm-5.2and ignoredMODEL, so reviews were reserved at Haiku's 4 credits but ran on glm-5.2. It now readsMODEL(fallback glm-5.2).anthropic/claude-haiku-4-5is not an OpenRouter ID (OpenRouter uses dots). Default is nowanthropic/claude-haiku-5.5, whose 1M context matches the shared Codexmodel_context_window.deploy.ymlnever builtDockerfile.review, sogithub-agent-review:latesthas been frozen since 2026-08-29. Closes adr: deploy.yml does not build review agent image — known gap, not a conscious decision #707.The main task default stays
z-ai/glm-5.2, perAGENTS.md.Test plan
cd infra && npm run build && npx jest: 23 suites, 347 tests pass, including new assertions for each change.approved), plain JSON, and non-JSON (explicit error).🤖 Generated with Claude Code