Repository navigation
Let the /ship conductor trial resolve case revert conflicts by hand (GST-3003) - #4460
Merged
Merged
Conversation
…GST-3003) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
|
😎 This pull request was merged. |
capy-ai Bot
added a commit
that referenced
this pull request
Nov 18, 2026
- A test, or a scratch repository in the temp directory, can no longer write approval rows into your real Capy Drive (GST-3027). (#4466) - An unattended /autoplan run on Claude Code no longer says the publication guard is off while it is on. (#4481) - A phase report written only in reasoning now gets a denial that says so and names the fix. (#4481) - `gstack-autoplan revise` no longer refuses a plan that the first `next` accepted. (#4470) - `revise --plan` with a different file now says the run follows that file. (#4470) - A second-model plan review in `/autoplan` is no longer reported as unavailable when it actually ran (GST-3051). (#4471) - The /ship conductor trial plan now lets case reverts that conflict with later code be resolved by hand in docs, tests and the planted file, so large pull requests can be cases (GST-3003). (#4460) - A locked plan for a trial of /ship without its separate conductor subagent (GST-3003). (#4456) - A driven /ship now runs each phase as one command, counts its calls, and stops itself at 100 minutes. (#4451) - /ship stops asking owners to clear two kinds of bookkeeping noise: base-side merge text and a reviewer's confirmation prose. (#4458) - A base merge that only touched base-side text no longer stops `/ship` finish for an owner's grant. (#4458) - A reviewer's confirmation prose no longer becomes a Critical finding that only an owner can clear. (#4458) - A CI run that passed only after its failed jobs were re-run is now marked wherever gstack reuses it. (#4473) - /ship reuses CI's passing test run when merging the base changed no file, and stops instead of quietly starting hour-long test runs or reviewing an empty diff (GST-3019). (#4461) - /ship on Codex no longer stops at the test coverage audit. (#4489) - A cold first-use check before an app build reaches its owner (GST-3025). (#4465) - `skill_prefix=true` now survives updates when gbrain is installed. (#4454) - The OpenClaw docs no longer send you to ClawHub, which held only April 2026 builds of office-hours, ceo-review and retro and no longer has gstack skills (the docs also said four skills while listing three). (#4454) - `gstack-issue-links` no longer reads other repositories' issues as gstack's. (#4454) - /ship's pre-gate finds the tests of a monorepo app that imports through its own `@/` alias. (#4464) - /office-hours explains why it recommends a mode. (#4450) - /office-hours keeps its 34 founder videos and essays out of the skill file. (#4463) - Two `gstack-owner-answers add` runs for the same answer no longer collide. (#4490) - A Captain can check an ask against the owner's earlier answers before sending it. (#4467) - `gstack-post` stops reading /ship's own receipt identifiers as phone numbers, so posting a /ship PR body no longer needs a confirm. (#4488) - GitHub release notes now list every change in plain words, with a link to its pull request. (#4390) - gstack's router no longer gives bug reports a special rule, so the model fixes a bug the way it would without gstack. (#4442) - /ship's review plan now sorts Swift and Xcode files by risk instead of sending every iOS PR to the full review panel (GST-3041). (#4469) - /ship's review plan now sends Swift code that touches private user data to the full review panel (GST-3052). (#4472) - A round grant at /ship's review round cap now buys the fix round it names, in the same run or the next (GST-2968). (#4479) - The secrets check stops flagging three kinds of ordinary code as a secret, and catches two misses. (#4457) - A security finding's location and reason no longer go into a PR body. (#4486) - The token-capped /ship child on Claude Code now starts its prompt with the typed `/ship` command, so the skill actually loads. (#4487) - A /ship receipt now counts the second-model review's blocking findings, and refuses to be written while one is still open. (#4485) - A `/ship` with a token cap on Claude Code no longer stops at its first handoff. (#4452) - /ship's push step now always ends with one line that says whether it pushed (GST-3053). (#4474) - A PR's review-round count can no longer be overwritten by the body `/ship` posts. (#4440) - One queued record with a malformed path no longer stops artifacts sync for every project. (#4455) - A failed artifacts push stays reported until a push succeeds. (#4455) - The /sync-gbrain memory row no longer says OK when pages failed to import. (#4455) - ### Tests (#4495) - A policy-floor test no longer fails once gstack's own version reaches the minor after the newest policy key; it now checks a floor above both, so the v1.101.0.0 release can pass CI. (#4495) - CI now uploads free-suite test results to Trunk with analytics-uploader v2.1.8 and analytics-cli 0.17.0, up from v2.1.6 and 0.16.2. (#4453) - Packing a checkout for a Ubicloud run no longer fails when git beside it is rewriting a ref. (#4447) - The /plan-ceo-review HOLD SCOPE eval no longer fails a review because its follow-up question didn't repeat the mode name. (#4447) - Unattended /autoplan now records the owner's relayed gate reply instead of refusing it. (#4484) - Unattended /autoplan now runs the second-model review you turned on, and waits for it instead of ending the session. (#4459) - Two /autoplan runs started in the same second no longer share a run id. (#4459) 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.
Lets the /ship conductor trial use pull requests whose revert conflicts with later code, by resolving those conflicts by hand in docs, tests and the planted file only.
Why: only 5 of the 10 needed cases (and no large one) reverted cleanly, so the trial could not start as planned.
Nothing to do: no bar, arm, decision, scoring rule or stop rule changes; no paid call has run.
What changed
Cases rule 1 now lets a conflicting host revert be resolved by hand in docs, tests and the planted file.
Before/after as text: Cases rule 1 now lets a conflicting host revert be resolved by hand in docs, tests and the planted file
The trial plan asked for host pull requests whose revert applied cleanly to one frozen main commit. Most hosts conflict with later code, so the rule now allows a hand resolution limited to docs, test files and the file that will hold the planted bug. A conflict in any other code file still disqualifies the host, and every resolution is written into the private label file. A dated amendment line under the frozen date says why and on whose grant.
Why
The sealing step found that only 5 of the 10 hosts the plan needs reverted cleanly onto the frozen commit, and none of the large ones did, so the trial could not pick its cases. The amendment lands before any paid call, so no result can have shaped it.
Blast radius
Only the trial plan's case-selection rule and one changelog fragment change. No code reads the rule's text. The preregistration check still passes (
PREREG: ok present=8/8, script ran), and the docs-only classifier still refuses this file, so CI runs the full suite on it (script ran).Pre-Landing Review
No blocking issues. The review read the whole diff and recorded two notes below the blocking floor. One is a wording ambiguity in the amended rule (which side wins a VERSION, CHANGELOG.md or package.json conflict that is "ignored"); it was left unchanged because the rule text is fixed by the owner's grant, and every resolution is recorded in the label file anyway. The other is listed under Review notes.
Review notes
Below the blocking floor (advisory, informational, test-gap or wording items); recorded here and not fixed in this PR.
docs/evals/ship-conductor-fold-prereg.md:97completenessNote on the noted finding: rule 4 builds each trial as "the base plus the host's commit with the plant folded in". With a hand-resolved revert, that commit is in effect the inverse of the recorded resolution; the sealer should apply it that way.
Exploratory QA
Functional smoke, 2 probes, both passed on the current tree: the preregistration check on the amended file (exit 0,
PREREG: ok present=8/8 stack=loaded no_gstack_arm=ok), and the docs-only classifier on this diff (docsOnly: false, the plan file refused as pinned results, so CI keeps the full suite). The sealing procedure the rule governs is not exercised here.Eval Results
No prompt-related files changed, so evals were skipped (the eval selector chose no probes and no judges).
Review bot comments
No review bot comments.
Scope Drift
Scope Check: CLEAN. Intent: amend Cases rule 1 of the G1 preregistration with a dated line. Delivered: that rule change, the amendment line and a changelog fragment.
Plan Completion
Plan completion audit: not run (no plan is bound to this branch and no docs/designs/ file matches).
Verification Results
No plan-specific checks (no plan file); automatic QA above.
TODOS
No TODO items completed in this PR.
Documentation
Status: current. No documentation edits were needed.
Scope: the diff from e1cfcea to the branch head (committed, staged, unstaged and new files), which changes
docs/evals/ship-conductor-fold-prereg.md(an amendment to Cases rule 1 allowing revert conflicts to be resolved by hand) and addschangelog.d/capy-g1-cases-amend.md. I searched the repository for docs that mention the plan, and the only other one ischangelog.d/capy-plan-a-trial-of.md.Documentation health:
docs/evals/ship-conductor-fold-prereg.md: current. The amendment note, frozen commit 88da124 and label-file recording agree with the Branches, Labels and anti-leak sections.changelog.d/capy-g1-cases-amend.md: current, and accurate.changelog.d/capy-plan-a-trial-of.md: current, with no contradiction.Debt: no coverage gaps and no diagram drift.
Tests
bun --no-env-file test --timeout=30000 test/eval-plan-no-gstack-arm.test.ts test/eval-plan-result-checks.test.ts test/docs-only.test.ts: 86 tests ran, exit 0bin/gstack-eval-plan prereg --check docs/evals/ship-conductor-fold-prereg.md: PREREG: okAgent notes
Refs GST-3003
Approvals
No approvals recorded for branch capy/g1-cases-amend.
Plan: exempt: crew:eval-prereg-amendment (owner grant GSTA-36)
REVIEW_LOOP: passes=1 blocking_found=0 deferred=0 noted=1 fixed=0 scope=frozen
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)
Review plan: class=docs depth=light pass=1 dispatches=0 (specialists, red-team, adversarial-native and outside-voice skipped by plan)
🤖 Generated with Claude Code