bin, spec: pipeline providers, SHA-bound approvals, Codex gate in review, rig-before-approval, epic merge wait - #458
Merged
Merged
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Pipeline rework from 2026-09-01..03 (22 commits) that was never opened as a PR.
mainhas been running the olderbin/scripts since: separatecodex-qa.shpasses that can't target one PR, approvals not bound to the reviewed SHA, no recovery of interrupted revisions, no provider selection. Several failures hit on 2026-09-15 are ones this branch addresses.What it changes (13 files, +838 / −398,
bin/and.agents/only)AC_PROVIDER/AC_<ROLE>_PROVIDER(claude|codex, defaultclaude) via a shared provider runner incommon.sh; QA stays model-boundbin/codex-qa.shremoved; independent Codex review moves intoreview.shand acodex_gateinmaster.sh, run before the merge gaterequires-rigstops before approval; spec routes rig-only evidence around the developerrevise.shmay hand an issue back to designAC_WAIT_MERGEwaits at a child until merged, requires an actual merge before advancing, stops on non-terminal child state; newbin/integrate.shfor conflicted epic PRsrevise.shexit, continues in the same worktree)AGENTS.md,qa.md,developer.md,codex-qa.md,architect.md: rig evidence before approval, bounded file reading, UX changes within the architect manifestChecked on 2026-09-15 against current
main(190c51b)git merge --no-commit origin/fix-qa-rig-routingintoorigin/main: exit 0, no conflicts (only.agents/qa.mdauto-merged). Main's onlybin//.agents/changes since the branch base (7511c39) are two docs commits.bash -n bin/*.shon the merged tree: clean.shellcheck -x -S warning bin/*.sh: main has 8 warnings. The merged tree has 9. The only warning this branch adds isbin/integrate.sh:29SC2164 (a barecd). The SC2209 hits inreview.sh(mode=full,mode=delta) are intentional string literals.bin/has no test harness, and no pipeline was driven with these scripts on this date.Overlap
fix-headless-agent-gates) edits the sameqa_loopneeds-work → revise block inmaster.sh. This branch rewrites therevise.shcall right above it (revise_rc, continue in same worktree). spec, master: headless roles must not background gates; tell a stalled revise from a declined one #457 also edits the same four spec files. Whichever merges second needs a rebase. spec, master: headless roles must not background gates; tell a stalled revise from a declined one #457'smaster.shpart may be partly redundant with this branch's interrupted-revision recovery; its spec rule (headless roles must not background gates) is not covered here.🤖 Generated with Claude Code
https://claude.ai/code/session_01FuCG3RuLHArnC8snRZVDYG