chore(ship): fix stale workflow test, document ad hoc ChatGPT consultation - #655
Merged
BorisTyshkevich merged 1 commit intoAug 9, 2026
Merged
Conversation
…on procedure skills/ship/tests/workflow-contract.test.mjs asserted against the OLD flat for-loop shape of decompose-and-implement-loop.workflow.mjs (pre-PR #651) -- PR #651's wave-based rewrite (sequential waves, parallel() only within an explicitly-independent multi-sub-task wave) broke 3 of its regex assertions and left a 4th (bare `model: 'sonnet'`) only coincidentally passing. Rewrote the assertions to pin the current structure and intent: wave-ordered iteration, the solo-vs-parallel branch, a fresh Sonnet agent on both paths, and a dead-agent halt at all three call sites (solo, parallel wave, integration). Confirmed pre-existing on origin/main via git stash before this fix. Also documented a third ChatGPT touchpoint for /ship, alongside the two formal pass-counted loops: an ad hoc, coordinator-only consultation for a genuinely hard judgment call internal review can't resolve, using the same manual Chrome-driving technique already sanctioned for stalled-generation recovery and post-pass-cap continuation (review-loops.md) -- no new script/plumbing. Cross-referenced from per-issue-cycle.md's root-cause circuit breaker and internal review budget sections, and from SKILL.md's ChatGPT review loops operating rules. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01LwFPT465eDJqYcRa8HGNLz
BorisTyshkevich
deleted the
chore/ship-skill-workflow-test-and-adhoc-consult
branch
August 9, 2026 08:08
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
skills/ship/tests/workflow-contract.test.mjs's pre-existing failure (confirmed viagit stashto fail identically onorigin/mainbefore any of this): its drift-bind assertions pinned the OLD flat sequential-loop shape ofdecompose-and-implement-loop.workflow.mjs, never updated when PR feat(ship): run independent decompose-and-implement sub-tasks concurrently #651 rewrote it into dependency-ordered "waves" with within-wave concurrency. Rewrote the assertions to pin the current wave-ordered structure and its real invariants (solo-vs-parallel branching, a fresh Sonnet agent on both paths, a dead-agent halt at all 3 call sites), and renamed the test to match./shipChatGPT touchpoint — an ad hoc, coordinator-only consultation for a genuinely hard judgment call internal review can't resolve — using the same manual Chrome-driving technique already sanctioned in PR chore(ship): default to chatgpt planner, fix #630 tooling friction #654 for stalled-generation recovery. No new script/plumbing; cross-referenced fromper-issue-cycle.mdandSKILL.md.Test plan
node --test skills/ship/tests/*.test.mjs— 8/8 pass (was 7/8 before this change)origin/main, unrelated to any recent change🤖 Generated with Claude Code
https://claude.ai/code/session_01LwFPT465eDJqYcRa8HGNLz