Verify review findings in the container instead of on the host - #851
Merged
Conversation
The host skill read every lens finding against the code to decide what to post, which put a judgement about code in the session that has no lens discipline and no worktree. In practice it drifted further than that: with an examine run that produced nothing, reading the diff and forming findings directly looked like the reasonable way to fill the gap. Findings now go to /crypter-devcontainer-verify, which already rules on findings from anywhere else and already rejects preferences and findings about untouched code. It grows a second input shape for this: given the lenses' own directory it assigns ids per lens rather than expecting a collected report, so the host hands over a path and reads nothing until verdicts exist. Only findings that hold reach the pull request. One that a verifier ruled against is the pipeline checking itself, and it stays in .claude/runs where a later pass can read it, rather than costing the author a read to reach a conclusion the verifier already reached. Both container calls exit 0 whichever way they go, so each step now checks what was written instead of trusting the status, and distinguishes an empty result that means success from one that means the run never happened. 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
/crypter-reviewread every lens finding against the code itself to decide what to post. That put a judgement about code in the host session, which has no lens and no worktree, and in practice it drifted further: when an examine run produced no findings, reading the diff and writing up findings directly looked like the reasonable way to fill the gap.Findings now go to
/crypter-devcontainer-verify, which already rules on findings from anywhere else and already rejects preferences and findings about code the diff did not touch. It gains a second input shape — given the lenses' findings directory rather than a collected report, it assigns ids per lens itself. The host hands over a path and reads nothing until verdicts exist.Only findings that hold are posted. One a verifier ruled against stays in
.claude/runs, where a later pass over the pipeline can read it.Both container calls exit 0 whether or not they worked, so each step now checks what was written rather than the exit status, and separates an empty result that means success from one that means the run never happened.
Documentation/Development/Agentic Development Pipeline.md is updated to match.