v1.57.10.0 feat: Codex review default-on across review/ship/plan/docs#1966
Merged
Conversation
Broaden the codex_reviews doc to describe it governing /review, /ship, /document-release, plan reviews, and /autoplan. Reject invalid values on set (preserving the existing value) so a typo can never silently flip paid Codex calls on or off. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Add a shared codexPreflight() helper (constants.ts) that, in one bash block, reads codex_reviews, sources gstack-codex-probe, checks install + auth, and echoes a single canonical mode (ready/not_installed/not_authed/ disabled). All Codex resolvers route through it. - generateCodexPlanReview: opt-in question removed; the outside voice now runs automatically (default-on), falling back to a Claude subagent when Codex is missing/unauthed. Cross-model tension still gates on user approval (sovereignty preserved). - generateAdversarialStep: probe-based availability (install AND auth), distinct not-installed vs not-authed guidance; 200-line structured-review threshold unchanged. - generateCodexDocReview (new, wired via CODEX_DOC_REVIEW): reviews the release's docs against the shipped diff range, informational + an explicit apply-fixes decision point, never auto-edits. - autoplan Phase 0.5 now honors codex_reviews=disabled so the switch is truly global. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Output of gen:skill-docs for the Codex-default-on resolver/template changes. Refreshes the factory-ship golden fixture (codex-host output unchanged — resolvers strip for the codex host). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The codexPreflight() block + CODEX_MODE branch prose (replacing the smaller opt-in question) grows plan-ceo/eng/devex-review and review by 5-7% over baseline. Each bump carries a comment justifying it as intentional capability, not slop. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
skill-validation: assert plan reviews no longer carry the opt-in question and render the default-on outside-voice, document-release carries the doc review, and the codex host strips all of it. gstack-config: codex_reviews defaults to enabled, accepts enabled/disabled, and rejects an invalid value while preserving the existing one. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Three tests (last touched v0.13.7.0) asserted get/list print empty for unset keys, but gstack-config falls back to the documented defaults table (get returns the default, list shows the active-values block). Update the assertions to the real behavior and split out an unknown-key case that does still return empty. Pre-existing red, unrelated to codex review. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Codex cross-model review now runs by default on /review, /ship, all four plan reviews, /document-release, and /autoplan, governed by one master switch (codex_reviews, default enabled). Plan-review outside voice is default-on; /document-release gets a new Codex doc-vs-diff audit; every call site detects install AND auth and falls back to a Claude subagent with a clear reason. Disable everything with: gstack-config set codex_reviews disabled Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
Merging to
After your PR is submitted to the merge queue, this comment will be automatically updated with its status. If the PR fails, failure details will also be posted here |
E2E Evals: ✅ PASS22/22 tests passed | $5.86 total cost | 12 parallel runners
12x ubicloud-standard-8 (Docker: pre-baked toolchain + deps) | wall clock ≈ slowest suite |
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.
What this ships
Makes OpenAI Codex cross-model review a default-on, opt-out standard step, governed by one master switch (
codex_reviews, defaultenabled)./plan-ceo-review,/plan-eng-review,/plan-design-review,/plan-devex-review): the Codex "outside voice" is now default-on — the opt-in "Want an outside voice?" question is gone. Falls back to a Claude subagent when Codex is missing/unauthed. Incorporating findings still requires explicit user approval (user sovereignty preserved)./document-release: newgenerateCodexDocReviewpass — reviews touched docs against the release diff for stale claims, undocumented new surface, and over/under-sold CHANGELOG entries. Informational + an explicit apply-fixes decision point; never auto-edits./review+/shipadversarial: detection upgraded from install-only (command -v codex) to install and auth, with distinct not-installed vs not-authed guidance. 200-line structured-review threshold unchanged./autoplan: Phase 0.5 preflight now honorscodex_reviews=disabled, so the switch is truly global.codex_reviewsbroadened to the master switch; invalid values onsetare rejected (existing value preserved) so a typo can't flip paid Codex calls.codexPreflight()helper centralizes the read-switch + source-probe + install/auth tri-state in one bash block.Engineering review (decisions folded in)
Plan reviewed via
/plan-eng-review. Five findings, all accepted:disabledfully skips the plan/doc outside-voice (no Claude fallback), while diff-review keeps its free Claude adversarial subagent.codexPreflight()helper (DRY).Codex outside-voice (dogfooded this branch's own feature)
Ran the Codex plan review on the plan. Refinements folded: single canonical mode var, probe-functions-only-in-preflight, review touched-docs not a fixed list, bounded Claude fallback. Four cross-model tensions resolved with the user: autoplan honors the switch (T1), kept D1 asymmetry (T2), added an apply-fixes decision point to doc review (T3), reject-on-set for invalid config (T4).
Verification
bun testexit 0, parity 13/13.codex-offered-ceo-review,codex-offered-eng-review,document-release,codex-review-findings.gstack-configtests (asserted empty for unset keys; tool falls back to documented defaults). Proven pre-existing, unrelated to this feature.Version
Requested v1.57.9.0 was already shipped to main as #1951 (gbrain source-clean render). Per the user's choice, this lands in the 1.57 line at v1.57.10.0.
🤖 Generated with Claude Code