Repository navigation
fix(spec): let claude reviews finish and name failure evidence - #13
Merged
Merged
Conversation
`allstack spec review --host claude` timed out at its 240-second deadline on a 217-line production plan, and the failure message ended with an empty path because a timed-out host has empty stderr. Raise the review deadline to 280 seconds, below the 290-second limit on the enclosing operation, and limit the reviewer to 12 code locations so it reports before the deadline. Record the process evidence directory on `Outcome` and include exit state and that directory in the error. Verified: the same plan now completes on the Claude host in 203s with a receipt. Full test suite and clippy pass.
decebal
marked this pull request as ready for review
November 9, 2026 11:35
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
allstack spec review --host claudetimed out at 240s on a 217-line production plan (all-sourcedocs/plans/2026-11-08-fly-cost-reduction.md). Deadline is now 280s, below the 290s limit on the enclosing operation.Trade-off
The 12-location limit applies to both hosts, so a review of a code-heavy plan can leave claims unchecked. The report must list them. In the verification run, Claude checked 7 locations and listed 6 unchecked items.
Test plan
cargo fmt --checkcargo clippy --all-targets -- -D warningscargo test: all pass, 2 ignored because they require real Chronistests/spec.rsasserts exit state, a realresult.jsonunder the named evidence path, and the prompt limit--host claude: 203s, receipt written, verdictfindings🤖 Generated with Claude Code