Repository navigation
Codex /review with gpt-6.1-sol counts the second-model pass it already ran (GEVA-562) - #4526
Merged
Merged
Conversation
…y ran (GEVA-562) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
|
😎 This pull request was merged. |
…-562) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> # Conflicts: # docs/skill-routing-and-contracts.md
Merged
capy-ai Bot
added a commit
that referenced
this pull request
Nov 19, 2026
- `gstack-artifact validate` no longer passes a run.json that gstack-autoplan never wrote. (#4494) - /ship's changed-number check no longer stops on tests that only share a word with the change (#4478). (#4496) - On Capy, /ship no longer edits or comments on pull requests as you. (#4518) - The destructive-command check stops asking about scratch deletes and catches the real damage it used to miss. (#4513) - The destructive-command check reads commands more carefully, closing gaps found after the last release. (#4525) - The Codex readiness check and the second-model review now pick the same model for a custom Codex provider (GST-3089). (#4491) - gstack's Codex hooks work when your Codex folder's path has a `(`, `&` or other shell character in it. (#4528) - Uninstalling gstack keeps your own Codex hooks trusted. (#4528) - Codex hook setup matches Codex more closely. (#4528) - On Windows, setup copies the Claude Code hook code that gstack's Codex hooks import (#4528) - /review's checklist on Codex reads shell commands more carefully. (#4528) - On Codex, gstack now suggests the right skill for a prompt and stops destructive commands before they run. (#4512) - On Codex, /review is now held once when it tries to finish without its adversarial pass or its report, as it already is on Claude Code. (#4522) - On Codex, gstack's skill suggestion now names the skill the way Codex lists it. (#4523) - On Codex, gstack's suggested prompts and docs now name skills the way Codex lists them. (#4524) - /review on Codex with gpt-6.1-sol is no longer held back for a second-model pass it already ran. (#4526) - On Codex, office-hours, plan-design-review and gstack-upgrade work again when you name them. (#4510) - gstack knows when Codex is running unattended. (#4510) - Codex reviewers start with a clean context. (#4510) - Docs no longer say Codex has no hook support. (#4510) - A command whose output was cut off no longer counts as a finished read. (#4492) - A folder marked as published data can no longer hide source code or agent files from /ship's review. (#4516) - Correction to the on-by-default helper hooks entry: the hook still routes only to /review, /qa and /verify, so skills you've installed yourself aren't suggested yet. With gstack's skills it routes 14 of 60 real bug reports (was 17), and long prompts are no longer skipped. (#4505) - /sync-gbrain's read check now works when the first page in your code source is over 64 KB. (#4497) - Free-suite CI no longer fails before any test runs when Ubuntu's package mirror is slow. (#4530) - Syncing a second repo no longer makes the first one ask for /sync-gbrain again. (#4532) - gstack's helper hooks are now on by default in Claude Code, OpenClaw and Hermes, and the prompt-routing hook fires on real bug reports. (#4503) - `gstack-pregate clear --receipt` accepts a remote gate run from before a merged release when the release only regenerated a declared release output. (#4483) - The second-model review now keeps the reviewer's own result, and reports a used-up budget as a budget stop. (#4515) - When the reviewer wrote its review to the result file it was asked for, Codex then replaced that file with its short closing message ("Done, I wrote the review"), so the review was thrown away and reported as missing its markers. (#4515) - When the provider refuses the call with HTTP 402 Payment Required (usually a metering proxy that hit its allowance, or an account out of credits or quota), gstack used to record only "exit 1". (#4515) - The pre-commit /verify check now fails a check that times out, and its checks share one time budget (GST-3201). (#4527) - /ship's review collector no longer reads a reviewer's own scope list or list of passed checks as findings (GST-3201). (#4527) - Merge-queue stack tests fail when git cannot list a PR's added test files (GST-3201). (#4527) - /ship can now review results PRs that publish raw session data. (#4511) - /ship's review pass works when the checkout you ship isn't the project's default checkout. (#4507) - A second review round no longer reports done when nothing was reviewed. (#4520) - The prompt-routing hook now suggests skills you install yourself, and no longer sends ordinary bug reports to /qa (GST-3123). (#4506) - gstack's script runner and merge-queue checks now also refuse cut-off output. (#4502) - A failed second-model review reports the cause that actually stopped it, and the runner never deletes its own prompt. (#4519) - `gstack-ship-queue ready` now fills in the trial merges and the second-model trail read instead of printing lines to fill. (#4529) - Five small ship-tool fixes. (#4529) - A ruling the owner gives while a `/ship` run is open can be relayed. (#4529) - /ship no longer kills a working test run as stalled when the test command starts its workers in their own session. (#4533) - /ship no longer stops a review because the state-machine reader started its reply the way its instructions say. (#4504) - When Claude Code runs /verify right before a commit, it now gets a quick check instead of the full fix loop (GST-3150). (#4508) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.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
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.
On Codex with gpt-6.1-sol, /review is no longer blocked at session end for a missing second-model pass that it ran.
Why: with Sol, Codex starts subagents through its
collaborationtools and names a started agent bytask_name, notagent_id, so the checklist reader missed it; this blocks gstack-evals' Codex pin.Nothing to do: the fix ships with the next gstack release.
What changed
lib/codex-rollout.tscounts a started call to Codex's ownspawn_agent: anagent_idresult from themulti_agent_v1namespace, or atask_nameresult from thecollaborationnamespace (multi_agents_v2). A call with no namespace may hold either. A failed spawn still doesn't count, and a same-named tool from any other namespace never counts.test/fixtures/skill-contract/codex/exec-sol-spawn-met.jsonl: a keyless Codex 0.170 run with-m gpt-6.1-solagainst a local stub endpoint, trimmed like the other fixtures.docs/skill-routing-and-contracts.md, and a changelog fragment.Tests
test/skill-contract-codex.test.ts: the Sol run's adversarial pass is met at the first stop (fails at b0f865c); a collaboration spawn whose result has notask_name(empty, error text, nickname only) is not a dispatch, and neither is aspawn_agentfrom another namespace.Why
The end-of-session contract check reads the Codex rollout to see whether /review ran its adversarial pass. Its fixtures came from gpt-5.4-mini, where a started agent answers with
agent_id. Sol answers withtask_name, so a session that did the work was held once for a pass it had already run.Blast radius
Only the Codex rollout reader behind the skill contract check changes. Claude Code sessions and other hosts are untouched. A Codex release that renames the namespace would make the check hold a session once, which is the same failure this fixes, not data loss.
Documentation
Status: current. The docs already match the change, so nothing was edited.
Scope: the diff from base b0f865c to head e006027 on codex-sol-spawn-dispatch, which counts a Codex
spawn_agentcall in thecollaborationnamespace as started when its result names atask_name. The diff touches lib/codex-rollout.ts, a new Sol fixture and its test, the codex fixture README, docs/skill-routing-and-contracts.md and a changelog.d fragment. There were no staged, unstaged or untracked changes.Documentation health:
agent_idandtask_name, failed spawns and tools of the same name from other namespaces.Coverage debt: none. Diagram drift: none.
Agent notes
Bug fix (no plan review). Reported by GEVA-562 via GEVA-2 on 2026-11-19, reproduced on b0f865c with
gstack-skill-contract checkon the run's rollout (missing adversarial-pass). Decision trail: reports/GSTA-651-decisions.tsv in the controller drive.Approvals
No approvals recorded for branch codex-sol-spawn-dispatch.
Plan: exempt: bug fix (failing-first test in test/skill-contract-codex.test.ts fails at b0f865c)
Pre-Landing Review
Pre-Landing Review: 2 issues — 0 auto-fixed, 0 asked, 0 deferred, 2 noted
REVIEW_LOOP: passes=1 blocking_found=0 deferred=0 noted=2 fixed=0 scope=frozen dispatches=1
Gate edits: none detected (GATE_SCAN tagged=0 at e006027)
agent_idused to count; (2)task_nameis chosen by the model, so a structured error that echoed it back would count; unconfirmed, since the fixture came from a stub.lib/codex-rollout.ts, over this PR's $10 paid cap; they ride the scheduled gate on main.