feat(ce-review): add headless mode for programmatic callers#430
Merged
Conversation
Add mode:headless as a fourth explicit mode for skill-to-skill invocation. Headless applies safe_auto fixes in a single pass, returns structured text output with the full findings envelope, writes run artifacts, and emits "Review complete" as a terminal signal. No interactive prompts, no todos, no checkout switching. Follows the pattern established by document-review's headless mode (#425), adapted for ce:review's richer findings schema (autofix_class, owner, requires_verification, evidence[], pre_existing). 🤖 Generated with Claude Opus 4.6 via [Claude Code](https://claude.com/claude-code) + Compound Engineering v2.58.1 Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>
Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>
- Add "Review complete" terminal signal to headless output template - Add cross-platform question tool names to headless rules - Add CE agent sections to headless envelope (Learnings, Agent-Native, Schema Drift, Deployment Notes) - Generalize conflicting mode flags error for all mode combinations - Add contract test assertions for no-commit/push/PR and single-pass Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: d66799a99e
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
Add severity and why_it_matters to pre-existing findings in the headless output so programmatic callers can parse them consistently. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>
Advertise headless mode in the argument-hint frontmatter for both skills so humans reading the skill definition know the mode exists and can think about utility-skill usage patterns. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>
…onsistency Both ce-review and document-review now use modes-first ordering in argument-hint, matching the standard [flags] [target] convention. Updated the two example invocations in Phase 0 to match. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: cd847abbbb
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
- Use headless error envelope when mode:headless is a conflicting flag - Add Coverage section to headless output envelope (suppressed counts, untracked file exclusions, failed reviewers) - Add routing metadata to pre-existing findings in headless envelope Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>
Merged
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
mode:headlessas a fourth explicit mode to ce:review for skill-to-skill invocationsafe_autofixes in a single pass, returns structured text output with findings envelope, writes run artifacts, and emits "Review complete" signalChanges
Also: added
mode:headlesstoargument-hintin both ce-review and document-review for human discoverability, and reordered document-review's argument-hint to modes-first ([mode:headless] [path]) for consistency with ce-review's[flags] [target]convention.Test plan
bun test tests/review-skill-contract.test.ts— 9 tests, 112 assertions passbun test— 498 pass, 0 failmode:headlessfrom another skill and verify structured output🤖 Generated with Claude Opus 4.6 via Claude Code + Compound Engineering v2.58.1