Repository navigation
Explain the new failed-or-skipped and also-changed report lines in the crew manuals (GST-1455) - #4432
Conversation
…als (GST-1455) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> #4273 added these lines to the READY and lane report templates; crew/docs/captain.md, the /captain skill, the crew CREW.md template and the Capy captain page still named only Unverified:. They now list all three, and say a controller asks for a missing one in a follow-up, never refuses or stales a READY for it, as with Unverified:.
|
😎 This pull request was merged. |
Review-Finding: p1/specialist-batched#1 reader=red-team Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
…455) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
E2E Evals: ✅ PASS96 executed, 0 reused rule/judge records | 0 manual accepted (unscored; no score-cache credit) | $31.75 rule/judge cost | reconcile exit: 0 Profile: pr / mode Full gate restored by:
Rule and judge shards
Fail-closed reconciliationSliced lane: planner → duration-packed executors → fail-closed report. Behavior cases run a pre-registered 3-trial panel (PASS at 2/3 with no contract violation); a PASS 2/3 is shown with its failed trial, never as a clean pass. Reused results retain their original provenance and expiry. Dispatched narrow screen (gstack-ship-queue ready --screen) of merge commit |
- /autoplan's approval page no longer hides a reviewer's product objection behind "keep your direction". (#4431) - Every skill that loads the shared preamble, on every host, now says to ask a question once and to check a file before handing it over. (#4383) - The Captain manuals now name the `Failed or skipped:` and `Also changed:` lines that READY and lane reports carry. (#4432) - gstack's shell locks hold again on Ubuntu 26.04, where `mkdir` reports success when another process won the race (GST-2247). (#4262) - `test/gstack-lock-race.test.ts` runs the old pattern and the helper against a PATH shim that behaves like uutils 0.8.0 `mkdir`, so it runs on any runner image: the old pattern lets two of four racers win, the helper admits exactly one in each of 60 races and never overlaps across take, hold and release loops, and parallel `gstack-config` writers keep every key. (#4262) - Windows Setup E2E now runs when `bin/gstack-lock.sh` changes. (#4433) - Claude Code's skill list now says when to use each gstack skill, so Opus loads /review and /plan-eng-review when a request fits. (#4387) - A pull request's merge head can no longer keep its `/ship` receipt without a full review. (#4365) - `/ship` now counts review rounds per pull request, and the head that merges always gets a full review. (#4360) - /ship's documentation audit no longer accepts a passing result when an earlier line from the same audit said "blocked". (#4434) - /ship's documentation audit no longer spends an attempt when the audit child writes text after its result. (#4285) - The README lists the two new guides, and the install doc counts its hooks right. (#4403) - docs/releases.md now says the stable release cut treats a failed commit status as red and a pending one as still going, as it has since #4257. (#4436) - /ship's `finish --docs-requested` now accepts a docs fix when the audit named the file with a line number. (#4437) - Document the `.gstack/approval-classes.json` schema, `gstack-approval-classes` CLI commands, and owner approval citation format in `docs/ship-policy.md#approval-classes`. (#4355) - `/eval-plan` now runs four result checks instead of leaving them to judgment. (#4384) - The /review coverage-audit eval no longer fails a run that really read the source file when zsh stops a command line at an `echo ====` separator. (#4364) - Sixteen in-repo documentation links reach their section again. (#4394) - gstack agents now open every status report with what failed, what they didn't verify and what else they changed. (#4273) - Two new short guides. (#4380) - A skill you wrote whose contract still lists `check_after_last_edit` keeps the rest of its contract. (#4439) - The ship policy guide now explains how to merge any pull request with `gstack-ship-queue land`, even in a repository with one maintainer. (#4377) - /ship's test step runs a large unit suite on Linux. (#4426) - Every skill that loads the shared preamble, on every host, now says never to print a whole environment, git config or process table. (#4382) - Pull requests from /ship now open with at most three plain lines, and every merge lands as one commit titled with the PR title. (#4438) - `gstack-pr-wait`, `gstack-ci-gate` and the release cut no longer call a commit green while a check on it failed. (#4257) - `gstack-runaway` now says what a thread's cold and empty wakes cost, not just how many there were (GST-2770). (#4385) - The optional Stop hook no longer checks for a test run after the last edit, and /verify asks for it in plain words instead. (#4428) - /ship's test step says when it ran out of time, and you can set its budget. (#4429) - The remote test command no longer puts every file on one command line. (#4429) - The stable release no longer waits on the nightly Windows tests (GST-2815). (#4400) - Ubicloud fan-outs can no longer overshoot the vCPU limit, and owners no longer delete each other's VMs. (#4430) - hono is pinned to 4.13.16, which fixes five advisories the weekly OSV scan found in 4.13.13 (gstack#4406). (#4408) - `package.json` overrides (#4408) - `test/dependency-security.test.ts`: the lockfile floor check now covers `hono >= 4.13.16`. (#4408) - The nightly Windows test run finishes again. (#4409) - A short write-up checklist in ETHOS.md. (#4381) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
The crew manuals now explain the
Failed or skipped:andAlso changed:lines that agents' ready-to-merge messages and work reports carry since #4273. A controller asks for a missing one in a follow-up and never refuses a READY over it, so the manuals match the templates agents copy.What changed
crew/docs/captain.md: the READY contract and the drive and rules tables name all three report lines, and the follow-up exception that coversUnverified:now covers the two new lines too.captain/SKILL.md.tmpl(and its generatedcaptain/SKILL.md): the READY field table gains rows for the two lines, marked "never refused or staled; ask for it".captain/templates/CREW.mdandcapy/skill/gstack/captain.md: the lane steps and the evidence item name the three lines.changelog.d/captain-docs-report-lines.md: the release-note entry.Why
After #4273 the READY and report templates asked for three lines while four manuals still described only
Unverified:, so a controller following a manual could treat the new lines as unknown or refuse a READY that lacked them. The docs audit on #4273 found this drift, and the owner accepted it there on the promise of this follow-up.Blast radius
Only Markdown changes, and agents load it, so CI keeps its full run. That is safe because no code parses these lines, and
test/captain-skill.test.tsstill finds every sentence it pins (73 focused tests pass at the fixed tree).Pre-Landing Review
One review round ran on the plan gstack printed: a batched specialist and an adversarial reviewer, with a coverage audit. One fix round followed, and its fix-check found nothing. Nothing reached the blocking floor.
crew/docs/captain.md:438called the two new lines "optional the same way" right after "the one exception". It now says the same exception covers a missingFailed or skipped:orAlso changed:line.Review notes
Below the blocking floor. These are recorded here and not fixed in this PR.
test/captain-skill.test.ts:35: no test pins the two new READY rows or their asked-for status, so a later edit could drop them without a red test.crew/docs/captain.md:440: the word "optional" clashed with READY.md's own "optional lines". The fix above removed it.captain/SKILL.md.tmpl:349andcaptain/templates/CREW.md:72: these list the lines in report.md's order, while factory.md point 10 and the shared closer use another order. Make gstack agents lead every report with what failed, what's unverified and what else changed (GST-1455) #4273 disclosed the same split.captain/templates/CREW.md:64: only the template new crews copy changes, so running crews keep their old wording until their controller syncs it.Issues
Refs #4273
Documentation
Status: current. The 6 selected files (3 commits, base 76fad3e..head 7e3fd2f, with no staged, unstaged or new files) are consistent with each other and with the existing READY and report templates. No edits were made (read-only audit).
Scope: Captain manuals and templates that name the READY and lane-report lines, plus the changelog fragment. The related templates captain/templates/READY.md and captain/templates/report.md were cross-checked.
Coverage debt: the two new lines have reference coverage in every Captain manual and template. One explanation gap remains: the paragraph in READY.md that justifies the ask-don't-refuse rule names only
Unverified:. Diagram drift: none, since no diagrams touch this surface.Test plan
bun run test: carried from CI Free Tests run 44068318074 at this tree, exit 0.bun test test/captain-skill.test.ts test/capy-skill-wrapper.test.ts, 73 pass, 0 fail.gstack-ship-queue ready --screen(eval:select keeps 145 behaviors scheduled, over the $10 cap).Agent notes
fc, one test-gap note, same as specialist refactor: reorganize codebase into modular structure #2); the counted fix-check is runfc2.Approvals
No approvals recorded for branch captain-docs-report-lines.
Plan: exempt: audited-list (docs audit docs-4273-1, Captain ruling A3, approval a-e2439cc50776)
Plan check: exempt audited-list
REVIEW_LOOP: passes=1 blocking_found=0 deferred=0 noted=4 fixed=1 scope=frozen ledgers_read=4 fix_checks=1 dispatches=1
Gate edits: none detected (0 listed, 0 read; patterns: RH-1,RH-3,RH-4,RH-12,RH-13,RH-14,RH-15,RH-16; unlisted idioms: none)
Refs GST-1455