From cadbd0af15d5566608f621ba76fb6db7c23f077c Mon Sep 17 00:00:00 2001 From: Garry Tan Date: Fri, 16 Oct 2026 20:32:16 -0700 Subject: [PATCH] v1.91.116.0 feat: field list 2 wave B: gstack-ship-queue, approval classes, state-machine review, pregate timing check, update-check main moves (#3235) * fix(capy): the install trailer says behind= and its fix, so a stale install shows in every relayed trailer (field list 2 item 13, #2378) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(capy): a lease records its holder's start identity, so a pid reused after a wake is reclaimed; a skipped session-start upgrade ends fail behind, never ok (GBRA-105, GBRA-106) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(lease): stale needs proof (unreadable or malformed identities keep the lease), ps identity is timezone-independent, and reclaim never deletes a concurrent renewal Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat(autoplan): enforced round cap and spend budget, deferred close, public export without machine paths, opt-in durable checkpoints (field list 2 W5-W7) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(lease): one directory lock for publish, prune and reclaim; reclaim rereads the record judged stale, so a renewal is never deleted or hidden Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(lease): the directory lock names its holder; broken only when the holder is dead or its pid reused, unlock removes only its own lock, touch exits 3 under a live holder Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(lease): breakers serialize on .lock.break and reread the lock before removing it; gstack-skill-start reports a lease the held lock kept out Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(lease): name the double-crash limit of breaking a dead lock Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat(capy): --for review-voice install profile, no-Drive bootstrap command, reviewer prompt trailer (field list 2 W11) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commit 89bf556c117489205b648998bf9590f6cef99755) * test: pin review-voice row, helpers row and the no-Drive fallback in existing install tests Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commit 7f6c70459adf2ac29723b6ab8e62f0452f3fce37) * test: the DRIVER template names the reviewer trailer relay (pregate lane) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commit 2545d9a6d2ef60e0dcf48cfe7593d025736f3260) * test(context-budget): capy skill eager ceiling for the review-voice subagent paragraph (W11; ratchet protocol, capture value) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat(eval-plan): prereg diagnostics dry run (W8) and .gstack/eval-models.json lint (W9), WIP Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commit b509096218cb632ed6f5e468407a82a215deec01) * feat(eval-plan): W8/W9 tests, docs/eval-models.md, troubleshooting anchors, /eval-plan steps Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commit 9335e45de2dd0ba9432482a3d5eee069f22370b6) * test(eval-plan): eval-plan/SKILL.md names only defined codes and accepted flags Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commit a7a974d268a012f459a28213860a27f65df305bc) * test(review-voice): the launch line points at the verdict's bun-only directory (#3233's launch contract) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(third-party-actions): the Aside drive-offer detector matches the product name, not the English idiom (paid run 38988927989 tpa-absent-linux false positive) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(autoplan): export refuses artifact paths outside the run before writing; a deferred close keeps earlier undecided findings; reopening CEO grants Eng its rerun (review of #3234) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(restamp): gate-ahead keeps the lane CHANGELOG entry when both PRs took the same tentative stamp (GBRA-102 diagnosis fixture) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commit 43c75a6bb64bf67fd799cb5b8f9e0515acbf6a9b) * test(tree-receipt): a real gbrain stamp pair is same-modulo-stamps under gbrain committed policy (W1 acceptance) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commit 6cf53f9fed2ad93bda50198027776bcc2f4cc0e3) * feat(ship-policy): gate_command, full_e2e and min_gstack_version; unknown keys stay fail-closed; validate prints introducing versions Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commit 878a7123d7098d5fcc6536e13788d457ea327337) * feat(ship-queue): gstack-ship-queue ready, stamp, verify and gate-ahead (WIP, tests next) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commit 409a5957ade5f076df851f56da070d8717e6ac31) * test(ship-queue): stamp journal and resume, verify from a separate clone, gate-ahead attempts, ready Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commit ade554087b0cebacf7b5485f6360e6b904ddf061) * docs(ship-policy): Run a shared merge queue; new keys and compatibility rule; troubleshooting anchors; /ship pointer Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commit 7fc73e889244acc7ef9062e4edaaee6186ebb2c8) * fix(ship): shared-queue pointer rides the show-effective ship: line (ship skeleton has 2 bytes of parity headroom) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commit 5b33d4a01594242259abee3c8c91229c16d3f7ce) * test(windows): curate the shared-queue tests out of the Windows subset (shebang spawns) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commit 8deee147287f5b9f03e88a29b4cac98fd8f88d98) * test(fixtures): register the gbrain stamp-pair fixture as free-only Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commit 563a07aa037bc1dae6a98407981444ee4158a932) * test(ship-queue): receipt digest contract names lib/ship-queue.ts for its pregate lane Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commit 501637c2585b2903aa27b879857f3df8b69777c1) * feat(pregate): timing check flags elapsed-time bounds and sleep-then-assert in added test lines (W4) lib/pregate/checks/timing.ts prints TIMING_ASSERTION: : and a TIMING_ASSERTIONS summary; gstack-timing-ok: in any comment syntax on the line or the line above escapes one. It warns (PREGATE_TIMING_ASSERTION): measured on gstack (9 of 47 test-touching commits, 263 hits in the tree) and gbrain (37 of 95 commits; 31 of 38 sites of the five timing-flake fixes), blocking would stop a fifth to two fifths of test changes. Adds the /review checklist rule and the /investigate timing-flake playbook. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commit a3b86b10b2373af7d9eb026dabd6b38d062a9fe1) * feat(update-check): an equal VERSION with a moved main is an upgrade, via the compare API (W12) When VERSION matches but ls-remote's main SHA differs from this checkout's HEAD, bin/gstack-update-check asks the GitHub compare API (status, ahead_by) through the existing receipted curl and prints UPGRADE_AVAILABLE + ; a diverged or unreadable compare is CHECK_FAILED (unknown), and behind/identical is up to date. Never fetches. The cache gains an IDENTITY line (head, compared remote SHA, upstream): an outcome replays only for the same HEAD and upstream, a same-remote refresh reuses it without another compare, and a git checkout ignores a legacy one-line cache (non-git installs keep the one-line format). The snooze is keyed by the SHA. gstack-upgrade's question, snooze note and What's New step handle the four-field line; gstack-skill-end reports it. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commit 421e66d2a468ba88b6c5aa6083368f29069d8f02) * fix(pregate): treat planning and evidence markdown as an empty lane A docs-only diff with no .gstack/pregate.json failed lanes as PREGATE_NO_LANE. Planning and evidence Markdown is now a docs/no-tests empty lane. Unmapped source files still fail closed. Co-authored-by: Nick (cherry picked from commit e8793e59e8f41679f0d7bd121bd954853f1f2efa) * fix(pregate): keep test-read markdown on its test lane Unmarked Markdown that no test depends on is a docs/no-tests empty lane. A file a test reads, including a fixture, still selects that test through the import graph. Unmapped source and unreferenced test-tree files still fail closed. Co-authored-by: Nick (cherry picked from commit 7aabbddf3dd06c30b3407c861761d7b18bcfb284) * test(pregate): reviewer edges for the docs/no-tests empty lane (#3215) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commit 2fb3fa86130dd9d58ecef63b6695aa13e1dbd5a6) * test(pregate): requires-remote on a gbrain-shaped repo (ci:ubicloud, UBI_OWNER) (W10) A base pregate.json with gbrain's dependencies and remote_gate "bun run ci:ubicloud" (a package script whose stub needs UBICLOUD_API_KEY, names VMs from UBI_OWNER and prints PREGATE_REMOTE). Under 8 cores the test tier is one obligation naming the command; --remote passes the caller's UBI_OWNER and key through and clears it on the report; without the key the gate's own error shows and the obligation stays uncleared. #3190's path needed no change. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commit 4d69ff02dfca4e2dc352dde43745dcc53fe0a83c) * test(pregate): the ship receipt counts the timing check (7 checks) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commit cb03ef67e7b5389900e5933b84830d63a1df66b8) * test(context-budget): gstack-upgrade eager ceiling for the W12 equal-version upgrade question (ratchet protocol, capture value) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat(approval-classes): gstack-approval-classes and ship-receipt citation enforcement (W2, WIP) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commit 847c7dae3dd5e49316733497a7b607869d51c28f) * feat(approval-classes): tests, docs, /review and /ship wiring (W2) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commit 269bd5b8b5b6ed22375012a91c1e2c61aaed2ed2) * feat(review): state-machines specialist and gstack-state-matrix round-trip check with a captured #6792 regression (W3) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commit 1a634979c671159888c9ba8fd9c6383c7cbaee22) * fix(review-army): keep the --simplification force flag pinned; approval test timeouts Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commit 789d392bcefac17fef8e0199362d522c7f15b240) * test(free-fixtures): register the state-matrix-6792 fixture Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commit 1bacef296d50e128126872f98e1fe89cb0cf0cea) * test(state-matrix): cover state-machines NEVER_GATE in gstack-specialist-stats Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commit 859063d56faea814f6d15b4e0208423d9dee9d43) * test(fixtures): register the pregate-timing fixtures as free-only (W4) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(ship-queue): full_e2e needs bound gate evidence in ready and verify, CI reads every check-run page and commit status, next: quotes its paths (review #3235 P1-1, P1-5, P2-1) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(pregate): timing reads a native diff and never passes an unread one The timing check's git diff honored diff.external, textconv and diff.noprefix, so a configured driver hid every added line and the check passed. Run it with --no-ext-diff --no-textconv and explicit a/ b/ prefixes, and report a git diff that fails or does not finish as incomplete (PREGATE_INCOMPLETE), which a warn downgrade does not soften. Review of #3235, sibling of P1-4 (lib/pregate/checks/timing.ts:189). Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(approval-classes): only affirmative APPROVED evidence counts, explicit tokens are authoritative, native diffs fail closed (review #3235 P1-2, P1-3, P1-4) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(state-matrix): detect reads the native diff, ignoring diff.external and textconv (review #3235 P1-4) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(e2e): review-army-state-matrix behavior case on the #6792 fixture (field list 2, W3) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(review-army): tighten the State Machines dispatch line so /ship stays under its parity size ratio with main's #3231 review-army text Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(approval-classes): only top-level approval lines count; quoted, fenced, indented-code and commented text never does (review #3235 r2) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(approval-classes): approval evidence is the first non-blank line only, at column 0 (review #3235 r3) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(autoplan-budget): bind the reservation expectation to lib/autoplan-budget's default estimate (test-of-test ratchet) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: keep gstack-upgrade under its size budget, exempt state-matrix's fetch hint, fit the periodic plan's 37 slices Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(evals): the docs observer accepts the spawned-prefixed gstack-skill-start --help read Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(windows): curate capy-review-voice out of the Windows subset (POSIX launcher contract) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: changelog entry for field list 2 wave A Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * chore: stamp v1.91.115.0 Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: the scope-signal clarity check follows helper-printed signals; the hermetic update-check fixture writes the identity cache Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * refactor: move the release-path result codes to lib/result-codes-release.ts (module-size ratchet); fit the periodic plan's 38 slices Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: changelog entry for field list 2 wave B Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * chore: stamp v1.91.116.0 Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: copy lib/result-codes-release.ts wherever a fixture copies lib/result-codes.ts; the scope-signal check requires the helper's computed emission Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: state-matrix stats test resolves its slug under its own state root (home containment) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(windows): curate pregate-docs-lane-review out of the Windows subset (runBin shebang, like the other pregate fixtures) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(windows): curate pregate-remote-gbrain out of the Windows subset (runBin shebang, like pregate-remote) 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> Co-authored-by: Cursor Agent Co-authored-by: Nick --- .github/workflows/evals-periodic.yml | 6 +- .github/workflows/windows-pregate-e2e.yml | 1 + CHANGELOG.md | 19 + VERSION | 2 +- agents-digest/gstack-AGENTS.md | 2 +- bin/gstack-approval-classes | 84 ++++ bin/gstack-doctor-components.sh | 13 + bin/gstack-ship-policy | 11 +- bin/gstack-ship-queue | 161 +++++++ bin/gstack-ship-receipt | 35 +- bin/gstack-skill-end | 4 +- bin/gstack-specialist-stats | 4 +- bin/gstack-state-matrix | 76 ++++ bin/gstack-update-check | 149 ++++++- docs/pregate.md | 65 ++- docs/ship-policy.md | 206 ++++++++- docs/troubleshooting.md | 192 ++++++++- docs/unattended.md | 3 +- gstack-upgrade/SKILL.md | 7 +- gstack-upgrade/SKILL.md.tmpl | 7 +- investigate/sections/flake.md | 24 ++ investigate/sections/flake.md.tmpl | 24 ++ lib/approval-citations.ts | 228 ++++++++++ lib/approval-classes.ts | 262 ++++++++++++ lib/changelog-check.ts | 14 +- lib/headless-artifacts.ts | 3 + lib/pregate/checks/lanes.ts | 13 +- lib/pregate/checks/timing.ts | 227 ++++++++++ lib/pregate/config.ts | 18 +- lib/pregate/docs-lane.ts | 59 +++ lib/pregate/index.ts | 3 +- lib/pregate/lane-selection.ts | 19 +- lib/restamp.ts | 2 +- lib/result-codes-release.ts | 79 ++++ lib/result-codes.ts | 7 +- lib/ship-policy.ts | 94 ++++- lib/ship-queue-gate.ts | 232 ++++++++++ lib/ship-queue.ts | 397 ++++++++++++++++++ lib/ship-receipt.ts | 4 +- lib/state-matrix.ts | 143 +++++++ package.json | 2 +- review/checklist.md | 8 + review/sections/review-army.md | 9 +- review/specialists/state-machines.md | 62 +++ scripts/lib/windows-curation.ts | 19 + scripts/pr-dependencies.ts | 2 +- scripts/resolvers/review-army.ts | 9 +- ship/sections/review-army.md | 9 +- test/approval-classes.test.ts | 394 +++++++++++++++++ test/egress-receipt-wiring.test.ts | 2 + test/fixtures/context-budget.json | 40 +- test/fixtures/module-size-ratchet.json | 3 + .../fixtures/pregate-timing/flaky.test.ts.txt | 62 +++ .../fixtures/pregate-timing/test_flaky.py.txt | 25 ++ .../ship-queue/gbrain-stamp-pair.json | 28 ++ .../base/src/takes/proposals.ts.txt | 35 ++ .../base/test/proposals.test.ts.txt | 24 ++ test/fixtures/state-matrix-6792/capture.json | 13 + .../state-matrix-6792/captured-output.jsonl | 10 + test/fixtures/state-matrix-6792/expect.json | 30 ++ .../head/src/takes/proposals.ts.txt | 51 +++ .../head/test/proposals.test.ts.txt | 39 ++ test/gstack-ship-queue.test.ts | 390 +++++++++++++++++ test/helpers/free-fixtures-data.ts | 3 + test/helpers/ship-queue-fixture.ts | 108 +++++ test/helpers/state-matrix-fixture.ts | 55 +++ test/helpers/touchfiles-data.ts | 23 +- test/hermetic-skill-runtime.test.ts | 3 +- test/plan-tune-cathedral.test.ts | 2 +- test/pregate-docs-lane-review.test.ts | 63 +++ test/pregate-invalidation.test.ts | 2 +- test/pregate-remote-gbrain.test.ts | 91 ++++ test/pregate-selection.test.ts | 142 ++++++- test/pregate-timing.test.ts | 145 +++++++ test/restamp-gate-ahead-changelog.test.ts | 95 +++++ test/review-workflow-clarity.test.ts | 11 +- test/ship-policy-compat.test.ts | 87 ++++ test/skill-e2e-review-army.test.ts | 51 +++ test/state-matrix.test.ts | 136 ++++++ test/timeline-stop-hook-slug.test.ts | 1 + test/tree-receipt-gbrain-pair.test.ts | 64 +++ test/update-check-main-moved.test.ts | 203 +++++++++ 82 files changed, 5330 insertions(+), 120 deletions(-) create mode 100755 bin/gstack-approval-classes create mode 100755 bin/gstack-ship-queue create mode 100755 bin/gstack-state-matrix create mode 100644 lib/approval-citations.ts create mode 100644 lib/approval-classes.ts create mode 100644 lib/pregate/checks/timing.ts create mode 100644 lib/pregate/docs-lane.ts create mode 100644 lib/result-codes-release.ts create mode 100644 lib/ship-queue-gate.ts create mode 100644 lib/ship-queue.ts create mode 100644 lib/state-matrix.ts create mode 100644 review/specialists/state-machines.md create mode 100644 test/approval-classes.test.ts create mode 100644 test/fixtures/pregate-timing/flaky.test.ts.txt create mode 100644 test/fixtures/pregate-timing/test_flaky.py.txt create mode 100644 test/fixtures/ship-queue/gbrain-stamp-pair.json create mode 100644 test/fixtures/state-matrix-6792/base/src/takes/proposals.ts.txt create mode 100644 test/fixtures/state-matrix-6792/base/test/proposals.test.ts.txt create mode 100644 test/fixtures/state-matrix-6792/capture.json create mode 100644 test/fixtures/state-matrix-6792/captured-output.jsonl create mode 100644 test/fixtures/state-matrix-6792/expect.json create mode 100644 test/fixtures/state-matrix-6792/head/src/takes/proposals.ts.txt create mode 100644 test/fixtures/state-matrix-6792/head/test/proposals.test.ts.txt create mode 100644 test/gstack-ship-queue.test.ts create mode 100644 test/helpers/ship-queue-fixture.ts create mode 100644 test/helpers/state-matrix-fixture.ts create mode 100644 test/pregate-docs-lane-review.test.ts create mode 100644 test/pregate-remote-gbrain.test.ts create mode 100644 test/pregate-timing.test.ts create mode 100644 test/restamp-gate-ahead-changelog.test.ts create mode 100644 test/ship-policy-compat.test.ts create mode 100644 test/state-matrix.test.ts create mode 100644 test/tree-receipt-gbrain-pair.test.ts create mode 100644 test/update-check-main-moved.test.ts diff --git a/.github/workflows/evals-periodic.yml b/.github/workflows/evals-periodic.yml index 8abb9ba0c..45aeae1ce 100644 --- a/.github/workflows/evals-periodic.yml +++ b/.github/workflows/evals-periodic.yml @@ -150,7 +150,7 @@ jobs: - name: Emit run manifest (ALL periodic tests minus reasoned excludes) env: EVALS_ALL: "1" - run: EVALS_TIER=periodic bun --no-install run scripts/test-paid-shards.ts --tier periodic --emit-plan /tmp/paid-plan/manifest.json --slice-budget 420 --jobs 2 --max-parallel 36 + run: EVALS_TIER=periodic bun --no-install run scripts/test-paid-shards.ts --tier periodic --emit-plan /tmp/paid-plan/manifest.json --slice-budget 420 --jobs 2 --max-parallel 38 # Codex-only slices run on the host-run eval-codex-slices job; the # container executor runs every other slice. @@ -258,7 +258,7 @@ jobs: fail-fast: false # Every planned slice starts at once; test/evals-workflow-wiring.test.ts # fails when the live plan outgrows this cap. - max-parallel: 36 + max-parallel: 38 matrix: slice: ${{ fromJSON(needs.plan-slices.outputs.periodic_slices) }} steps: @@ -397,7 +397,7 @@ jobs: packages: read strategy: fail-fast: false - max-parallel: 36 + max-parallel: 38 matrix: slice: ${{ fromJSON(needs.plan-slices.outputs.periodic_codex_slices) }} steps: diff --git a/.github/workflows/windows-pregate-e2e.yml b/.github/workflows/windows-pregate-e2e.yml index 3c225d19b..96528e648 100644 --- a/.github/workflows/windows-pregate-e2e.yml +++ b/.github/workflows/windows-pregate-e2e.yml @@ -31,6 +31,7 @@ on: - 'lib/gate-diff/**' - 'lib/pregate/**' - 'lib/result-codes.ts' + - 'lib/result-codes-release.ts' - 'bin/gstack-wtree' - 'bin/gstack-slug' - 'bin/gstack-path-spelling.sh' diff --git a/CHANGELOG.md b/CHANGELOG.md index 05efb8229..8518777b9 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,5 +1,24 @@ # Changelog +## [1.91.116.0] - 2026-10-17 + +**Lanes and the coordinator now share a merge queue whose stamp claims are checked instead of trusted, risky changes need a cited owner approval before they ship, /review checks state machines cell by cell, pregate warns about timing assertions, and the update check notices when main moves without a version bump.** These are the field list 2 wave B items from the gbrain crew (W1-W4, W10, W12). + +### What this means for you + +- **`gstack-ship-queue` runs a shared merge queue.** `ready` prints one READY block and refuses when the tree differs from the pushed head. `stamp` checks every proof input, restamps through `gstack-restamp`, and resumes on an identical retry. The coordinator's `verify` reruns the tree receipt and recomputes a gate-ahead merge, so a lane's stamp claim is never taken on trust. Ship policy gains `gate_command`, `full_e2e` and `min_gstack_version`; a gstack older than a key it reads refuses with `POLICY_GSTACK_TOO_OLD`. See `docs/ship-policy.md#run-a-shared-merge-queue`. +- **Approval classes.** `.gstack/approval-classes.json` (read from the base branch) declares what needs an owner's approval. `gstack-ship-receipt write` refuses a branch that touches a class until the PR body cites `Approved by via for @`, bound to the effects being shipped. +- **/review's state-machines specialist** builds a kind × owner action matrix for diffs that change a state machine. `gstack-state-matrix check` reports every missing cell, and an untested cell is CRITICAL. +- **Pregate's `timing` check** warns on added test lines that bound wall or CPU time or sleep and then assert. Mark a deliberate bound with `gstack-timing-ok: `. /investigate gains a timing-flake playbook. +- **The update check sees a moved main.** At an equal VERSION it reports `UPGRADE_AVAILABLE + ` through the GitHub compare API (never `git fetch`). The cache is bound to HEAD and upstream, and snooze is keyed by SHA. /gstack-upgrade summarizes the commits instead of a CHANGELOG entry. +- **Pregate's docs lane** comes from #3215 by Cursor Agent: Markdown no test depends on is already a docs/no-tests empty lane. + +### For contributors + +- The release-path result codes live in `lib/result-codes-release.ts`, spread into `RESULT_CODES`, so `lib/result-codes.ts` stays inside the module-size ratchet. +- New paid case `review-army-state-matrix` (periodic, behavior). The periodic lane's `max-parallel` is 38 so every planned slice still starts at once. +- The scope-signal clarity test also accepts a signal printed by the helper its own selection line runs (SCOPE_STATE_MACHINE), and the hermetic update-check fixture writes the identity cache. + ## [1.91.115.0] - 2026-10-17 **Autoplan now enforces its round cap and spend budget and can export a public copy of a run, /eval-plan tests its preregistered diagnostics and checks every arm's model against repo rules before money moves, and a reviewer subagent can install gstack's read-only helpers in seconds.** These are the field list 2 wave A items from the gbrain crew (autoplan W5-W7, eval-plan W8/W9, reviewer install W11). diff --git a/VERSION b/VERSION index 51b1f1ca2..b7130a9f6 100644 --- a/VERSION +++ b/VERSION @@ -1 +1 @@ -1.91.115.0 +1.91.116.0 diff --git a/agents-digest/gstack-AGENTS.md b/agents-digest/gstack-AGENTS.md index f62f66dcf..e71867cf5 100644 --- a/agents-digest/gstack-AGENTS.md +++ b/agents-digest/gstack-AGENTS.md @@ -1,4 +1,4 @@ -# gstack digest v1.91.115.0 — regenerate/re-copy after upgrading gstack +# gstack digest v1.91.116.0 — regenerate/re-copy after upgrading gstack Behavioral rules from gstack (https://github.com/garrytan/gstack), compressed for agent hosts without a full skill install. The full skills add workflows, diff --git a/bin/gstack-approval-classes b/bin/gstack-approval-classes new file mode 100755 index 000000000..7d5ccee95 --- /dev/null +++ b/bin/gstack-approval-classes @@ -0,0 +1,84 @@ +#!/usr/bin/env bun +/** + * gstack-approval-classes — changes that need the owner's approval (field list 2, W2). + * + * gstack-approval-classes [check] [--base ] [--head ] [--diff-base ] [--json] + * gstack-approval-classes init [--force] + * gstack-approval-classes validate + * + * `check` reads the classes from the committed `origin/` copy of + * .gstack/approval-classes.json (never the working tree) and the migration + * rule from the base's ship policy, scans the branch's changes since the + * merge base, and prints `APPROVAL_CLASS: :` per hit, one + * `APPROVAL_SCOPE: @` per declared class with hits, and + * `APPROVAL_CLASSES: ok | found= | none` last. Built-in detectors only + * report. Exit 0 ok or none, 1 found, 3 when the base file is invalid or the + * base is unresolvable. Enforcement is gstack-ship-receipt write + * (APPROVAL_CITATION_MISSING). Logic: lib/approval-classes.ts. + */ +import { spawnSync } from 'node:child_process'; +import * as fs from 'node:fs'; +import * as path from 'node:path'; +import { APPROVAL_CLASSES_PATH, exampleApprovalClassesJson, loadWorkingApprovalClasses, renderApprovalScan, runApprovalScan } from '../lib/approval-classes'; +import { EXIT, exitTableHelp } from '../lib/headless-artifacts'; +import { resultLine } from '../lib/result-codes'; +import { resolveBaseBranch } from '../lib/ship-policy'; + +const HELP = `gstack-approval-classes — changes that need the owner's approval (docs/ship-policy.md#approval-classes) + + check [--base ] [--head ] [--diff-base ] [--json] + changes since the merge base with origin/ (default origin/HEAD's branch), at --head or the + working tree; classes come only from the committed ${APPROVAL_CLASSES_PATH} on origin/ + init [--force] write an example ${APPROVAL_CLASSES_PATH} + validate schema and containment check of the working-tree file (before you commit it) + +A declared class with hits needs a line in the PR body that gstack-ship-receipt write can resolve: + Approved by via [for @] + +${exitTableHelp()}`; + +function flag(args: string[], name: string): string | undefined { + const i = args.indexOf(name); + return i >= 0 ? args[i + 1] : undefined; +} + +function main(argv: string[]): number { + if (argv.includes('--help') || argv.includes('-h')) { process.stdout.write(HELP + '\n'); return EXIT.ok; } + const cmd = argv[0] && !argv[0].startsWith('--') ? argv[0] : 'check'; + const rest = cmd === argv[0] ? argv.slice(1) : argv; + const root = spawnSync('git', ['rev-parse', '--show-toplevel'], { encoding: 'utf8', timeout: 15_000 }); + if (root.status !== 0) { process.stderr.write('gstack-approval-classes: not inside a git repository\n'); return EXIT.usage; } + const repoRoot = root.stdout.trim(); + const file = path.join(repoRoot, APPROVAL_CLASSES_PATH); + + if (cmd === 'init') { + if (fs.existsSync(file) && !rest.includes('--force')) { process.stderr.write(`gstack-approval-classes: ${APPROVAL_CLASSES_PATH} exists (pass --force to overwrite)\n`); return EXIT.refused; } + fs.mkdirSync(path.dirname(file), { recursive: true }); + fs.writeFileSync(file, exampleApprovalClassesJson()); + process.stdout.write(`APPROVAL_CLASSES_INIT: ${APPROVAL_CLASSES_PATH} (edit, commit and merge it; check reads only the base copy)\n`); + return EXIT.ok; + } + if (cmd === 'validate') { + const load = loadWorkingApprovalClasses(repoRoot); + if ('absent' in load) { process.stdout.write(`APPROVAL_CLASSES: none (no ${APPROVAL_CLASSES_PATH})\n`); return EXIT.ok; } + if ('errors' in load) { for (const e of load.errors) process.stderr.write(resultLine('gstack-approval-classes validate', 'APPROVAL_CLASSES_INVALID', `${e.message} at ${e.path || ''}`) + '\n'); return EXIT.refused; } + if ('unavailable' in load || !load.config) return EXIT.fail; + process.stdout.write(`APPROVAL_CLASSES_VALID: ${APPROVAL_CLASSES_PATH} classes=${load.config.classes.length}\n`); + return EXIT.ok; + } + if (cmd !== 'check') { process.stderr.write(`gstack-approval-classes: unknown command ${cmd}\n${HELP}\n`); return EXIT.usage; } + + const json = rest.includes('--json'); + const base = resolveBaseBranch(repoRoot, flag(rest, '--base')); + const outcome = runApprovalScan({ repoRoot, base, head: flag(rest, '--head'), diffBase: flag(rest, '--diff-base') }); + if ('unavailable' in outcome) { process.stderr.write(resultLine('gstack-approval-classes', 'APPROVAL_SOURCE_UNAVAILABLE', `${outcome.unavailable}; classes are read only from the base, so nothing was checked`) + '\n'); return EXIT.refused; } + if ('errors' in outcome) { for (const e of outcome.errors) process.stderr.write(resultLine('gstack-approval-classes', 'APPROVAL_CLASSES_INVALID', `${e.message} at ${e.path || ''} (${outcome.source})`) + '\n'); return EXIT.refused; } + if ('error' in outcome && outcome.unreadable) { process.stderr.write(resultLine('gstack-approval-classes', 'APPROVAL_SOURCE_UNAVAILABLE', `${outcome.error}, so nothing was checked`) + '\n'); return EXIT.refused; } + if ('error' in outcome) { process.stderr.write(`gstack-approval-classes: ${outcome.error}\n`); return EXIT.usage; } + const { scan, absent } = outcome; + process.stdout.write(json ? JSON.stringify({ ...scan, absent }) + '\n' : renderApprovalScan(scan, absent)); + if (scan.hits.length) { process.stderr.write(resultLine('gstack-approval-classes', 'APPROVAL_CLASS_FOUND', `${scan.scopes.map(s => s.token).join(', ')} need an Approved by line`) + '\n'); return EXIT.fail; } + return EXIT.ok; +} + +process.exitCode = main(process.argv.slice(2)); diff --git a/bin/gstack-doctor-components.sh b/bin/gstack-doctor-components.sh index d5572418d..e0506885f 100644 --- a/bin/gstack-doctor-components.sh +++ b/bin/gstack-doctor-components.sh @@ -253,6 +253,19 @@ gstack_result_anchor() { DX_CAPTURE_INTERRUPTED) printf '%s' 'dx-capture-interrupted' ;; DX_CAPTURE_REDACTION_FAILED) printf '%s' 'dx-capture-redaction-failed' ;; DX_CAPTURE_INTERNAL) printf '%s' 'dx-capture-internal' ;; + POLICY_GSTACK_TOO_OLD) printf '%s' 'policy-gstack-too-old' ;; + QUEUE_NOT_READY) printf '%s' 'queue-not-ready' ;; + QUEUE_PROOF_MISSING) printf '%s' 'queue-proof-missing' ;; + QUEUE_STAMP_NOT_STAMP_ONLY) printf '%s' 'queue-stamp-not-stamp-only' ;; + QUEUE_VERIFY_MISMATCH) printf '%s' 'queue-verify-mismatch' ;; + QUEUE_GATE_MISSING) printf '%s' 'queue-gate-missing' ;; + GATE_AHEAD_ATTEMPT_INVALID) printf '%s' 'gate-ahead-attempt-invalid' ;; + PREGATE_TIMING_ASSERTION) printf '%s' 'pregate-timing-assertion' ;; + APPROVAL_CLASSES_INVALID) printf '%s' 'approval-classes-invalid' ;; + APPROVAL_CLASS_FOUND) printf '%s' 'approval-class-found' ;; + APPROVAL_CITATION_MISSING) printf '%s' 'approval-citation-missing' ;; + APPROVAL_SOURCE_UNAVAILABLE) printf '%s' 'approval-source-unavailable' ;; + STATE_MATRIX_INCOMPLETE) printf '%s' 'state-matrix-incomplete' ;; *) return 1 ;; esac } diff --git a/bin/gstack-ship-policy b/bin/gstack-ship-policy index 2c1d61d9b..206bd48c7 100755 --- a/bin/gstack-ship-policy +++ b/bin/gstack-ship-policy @@ -18,8 +18,8 @@ import * as path from 'node:path'; import { EXIT, exitTableHelp } from '../lib/headless-artifacts'; import { resultLine } from '../lib/result-codes'; import { - SHIP_POLICY_PATH, examplePolicyJson, explainPolicy, isUnavailable, loadPolicyFromBase, loadPolicyFromHead, - policyUnavailableLine, renderEffective, resolveBaseBranch, type LoadedPolicy, + POLICY_KEYS, POLICY_KEY_INTRODUCED, SHIP_POLICY_PATH, examplePolicyJson, explainPolicy, isUnavailable, loadPolicyFromBase, loadPolicyFromHead, + minimumReader, policyUnavailableLine, renderEffective, resolveBaseBranch, type LoadedPolicy, } from '../lib/ship-policy'; const HELP = `gstack-ship-policy — the repo ship policy (docs/ship-policy.md) @@ -86,13 +86,18 @@ function main(argv: string[]): number { if (cmd === 'validate' || cmd === 'show-effective') { const loaded = load(root, rest, cmd === 'validate' ? 'head' : 'base'); if (typeof loaded === 'number') return loaded; + const set = POLICY_KEYS.filter(k => loaded.values[k] && loaded.values[k] !== 'default'); + const introduced = Object.fromEntries(set.map(k => [k, POLICY_KEY_INTRODUCED[k]])); + const minReader = set.length ? minimumReader(introduced) : null; if (json) { - process.stdout.write(JSON.stringify({ valid: loaded.errors.length === 0, present: loaded.present, source: loaded.source, policy: loaded.policy, values: loaded.values, errors: loaded.errors }) + '\n'); + process.stdout.write(JSON.stringify({ valid: loaded.errors.length === 0, present: loaded.present, source: loaded.source, policy: loaded.policy, values: loaded.values, introduced, min_reader: minReader, errors: loaded.errors }) + '\n'); return loaded.errors.length ? EXIT.fail : EXIT.ok; } printErrors(loaded); if (cmd === 'validate') { process.stdout.write(loaded.errors.length ? `POLICY_INVALID: ${loaded.errors.length} error(s) in ${loaded.source.label}\n` : `POLICY_VALID: ${loaded.present ? loaded.source.label : `no ${SHIP_POLICY_PATH} (defaults apply)`}\n`); + for (const k of set) process.stdout.write(`KEY: ${k} introduced=${introduced[k]}\n`); + if (minReader) process.stdout.write(`MIN_READER: gstack ${minReader} (every lane that reads this policy needs at least this version)\n`); return loaded.errors.length ? EXIT.fail : EXIT.ok; } process.stdout.write(renderEffective(loaded, { base: flag(rest, '--base') ?? resolveBaseBranch(root) })); diff --git a/bin/gstack-ship-queue b/bin/gstack-ship-queue new file mode 100755 index 000000000..6135827bb --- /dev/null +++ b/bin/gstack-ship-queue @@ -0,0 +1,161 @@ +#!/usr/bin/env bun +/** + * gstack-ship-queue — the shared merge queue, one subcommand per protocol + * step (field list 2, W1; docs/ship-policy.md#run-a-shared-merge-queue). + * + * gstack-ship-queue ready --pr [--pregate ] [--gate-exit --gate-log ] + * gstack-ship-queue stamp --pr --version --expect-gated --expect-base + * [--expect-order ] [--allow-repo-commands] [--gate-exit --gate-log ] + * gstack-ship-queue verify --pr (--gated | --record ) [--receipt ] + * [--expect-head ] [--ref ] [--no-fetch] [--gate-exit --gate-log ] + * gstack-ship-queue gate-ahead --after --pr [--predecessor-ref ] [--allow-repo-commands] + * gstack-ship-queue gate-ahead --record --pr --attempt --exit --log + * gstack-ship-queue gate-ahead --list --pr + * + * Every subcommand takes --base (default origin/HEAD, else main) and + * ends with GSTACK_RESULT: skill=ship-queue status=complete|refused run=. + * gstack-restamp stays the primitive. Nothing here pushes. Logic: + * lib/ship-queue.ts, lib/ship-queue-gate.ts. + */ +import { spawnSync } from 'node:child_process'; +import * as path from 'node:path'; +import { EXIT, exitTableHelp, formatResult } from '../lib/headless-artifacts'; +import { versionAtRef } from '../lib/restamp'; +import { RESULT_CODES } from '../lib/result-codes'; +import { resolveBaseBranch } from '../lib/ship-policy'; +import { loadBasePolicy, ready, stamp, verify, type QueueContext, type StepOutput } from '../lib/ship-queue'; +import { attemptFile, listAttempts, prepareGateAhead, recordGateAhead, type QueueFailure } from '../lib/ship-queue-gate'; + +const HELP = `gstack-ship-queue — the shared merge queue's protocol steps (docs/ship-policy.md#run-a-shared-merge-queue) + + ready --pr [--pregate ] [--gate-exit --gate-log ] + READY # STAMP_VERSION=, CI at that head, PREGATE, gate state + stamp --pr --version --expect-gated --expect-base [--expect-order ] [--allow-repo-commands] + [--gate-exit --gate-log ] + restamp, commit and prove: QUEUE_STAMP: head= gated= tree= receipt= + verify --pr --gated | --record [--receipt ] [--expect-head ] [--ref ] [--no-fetch] + [--gate-exit --gate-log ] (full_e2e: --gated needs the lane's passing gate run on that head) + the coordinator's check from the PR's pushed head: VERIFY: ... and MERGE_CONDITION + gate-ahead --after --pr [--predecessor-ref ] [--allow-repo-commands] + prepare an attempt: merged, stamped worktree, gated sha and the gate command + gate-ahead --record --pr --attempt --exit --log + bind the gate result to that attempt's gated tree; removes its worktree + gate-ahead --list --pr attempts for a PR, newest last (the current one) + +--base : base branch (default: origin/HEAD, else main). Nothing here pushes. +${exitTableHelp()}`; + +function flag(args: string[], name: string): string | undefined { + const i = args.indexOf(name); + return i >= 0 ? args[i + 1] : undefined; +} + +function finish(cmd: string, out: StepOutput): number { + for (const line of out.lines) process.stdout.write(line + '\n'); + if (out.failure) { + const f = out.failure; + process.stderr.write(`gstack-ship-queue ${cmd}: ${f.message}; fix: ${f.fix ?? RESULT_CODES[f.code].fix} (${f.code})\n`); + } + process.stdout.write(formatResult('ship-queue', out.ok ? 'complete' : 'refused', out.run) + '\n'); + if (out.ok) return EXIT.ok; + return out.failure && ['QUEUE_VERIFY_MISMATCH', 'QUEUE_STAMP_NOT_STAMP_ONLY'].includes(out.failure.code) ? EXIT.fail : EXIT.refused; +} + +const shq = (s: string) => `'${s.replace(/'/g, `'\\''`)}'`; + +function usage(message: string): number { + process.stderr.write(`gstack-ship-queue: ${message}\n${HELP}\n`); + return EXIT.usage; +} + +function gateAhead(ctx: QueueContext, args: string[]): number { + const pr = flag(args, '--pr'); + if (!pr) return usage('gate-ahead needs --pr (records are keyed by PR)'); + if (args.includes('--list')) { + const all = listAttempts(ctx.repoRoot, pr); + for (const a of all) process.stdout.write(`ATTEMPT: ${a.attempt} state=${a.state} gated_tree=${a.gated_tree} predecessor=#${a.predecessor_pr}@${a.predecessor_head.slice(0, 12)}${a.result ? ` exit=${a.result.exit}` : ''}${a === all.at(-1) ? ' current' : ''}\n`); + if (!all.length) process.stdout.write(`ATTEMPT: none for #${pr}\n`); + return EXIT.ok; + } + if (args.includes('--record')) { + const attempt = flag(args, '--attempt'); + const exit = flag(args, '--exit'); + const log = flag(args, '--log'); + if (!attempt || exit === undefined || !/^-?\d+$/.test(exit) || !log) return usage('gate-ahead --record needs --attempt --exit --log '); + const r = recordGateAhead({ repoRoot: ctx.repoRoot, pr, attempt, exit: Number(exit), log: path.resolve(log) }); + if ('code' in r) return finish('gate-ahead', { ok: false, lines: [], failure: r, run: attemptFile(ctx.repoRoot, pr, attempt) }); + const cur = r.current && r.current.attempt !== attempt ? `no (superseded by ${r.current.attempt})` : 'yes'; + return finish('gate-ahead', { + ok: true, run: path.relative(ctx.repoRoot, r.file), + lines: [ + `GATE_RECORD: pr=${pr} attempt=${attempt} exit=${r.record.result!.exit} gated_tree=${r.record.gated_tree} log_sha256=${r.record.result!.log_sha256} current=${cur}`, + ...(r.repeated ? ['note: identical retry; the stored result is returned'] : []), + `record: ${r.file}`, + `next: send the record file with the READY report; the coordinator runs gstack-ship-queue verify --pr ${pr} --record once this PR is stamped`, + ], + }); + } + const after = flag(args, '--after'); + if (!after) return usage('gate-ahead needs --after , --record or --list'); + const policy = loadBasePolicy(ctx); + if ('message' in policy) return finish('gate-ahead', { ok: false, lines: [], failure: policy, run: 'none' }); + const at = versionAtRef(ctx.repoRoot, 'HEAD'); + const r = prepareGateAhead({ + repoRoot: ctx.repoRoot, base: ctx.base, pr, after, predecessorRef: flag(args, '--predecessor-ref'), allowRepoCommands: args.includes('--allow-repo-commands'), + policy: policy.policy, versionRel: 'rel' in at ? at.rel : 'VERSION', + }); + if ('code' in r) return finish('gate-ahead', { ok: false, lines: [], failure: r as QueueFailure, run: 'none' }); + const rec = r.record; + const log = path.join(path.dirname(rec.worktree), 'gate.log'); + const cmd = rec.gate_command ?? ''; + const superseded = listAttempts(ctx.repoRoot, pr).filter(a => a.attempt !== rec.attempt && a.state === 'prepared').map(a => a.attempt); + return finish('gate-ahead', { + ok: true, run: path.relative(ctx.repoRoot, r.file), + lines: [ + `GATE_AHEAD: pr=${pr} attempt=${rec.attempt} gated=${rec.gated_head} tree=${rec.gated_tree} merge_tree=${rec.merge_tree} predecessor=#${rec.predecessor_pr}@${rec.predecessor_head.slice(0, 12)} version=${rec.version}`, + `worktree: ${rec.worktree}`, + `record: ${r.file}`, + `GATE_COMMAND: ${rec.gate_command ?? 'none (the policy sets no gate_command; run the repo gate you would run on a PR head)'}`, + ...(superseded.length ? [`note: this attempt is now current; earlier unrecorded attempts (${superseded.join(', ')}) keep their worktrees until recorded`] : []), + `next: (cd ${shq(rec.worktree)} && ${cmd}) > ${shq(log)} 2>&1; gstack-ship-queue gate-ahead --record --pr ${pr} --attempt ${rec.attempt} --exit $? --log ${shq(log)}`, + ], + }); +} + +function main(argv: string[]): number { + const [cmd, ...args] = argv; + if (!cmd || cmd === '--help' || cmd === '-h' || cmd === 'help') { process.stdout.write(HELP + '\n'); return cmd ? EXIT.ok : EXIT.usage; } + const probe = spawnSync('git', ['rev-parse', '--show-toplevel'], { encoding: 'utf8', timeout: 15_000 }); + if (probe.status !== 0) return usage('not inside a git repository'); + const repoRoot = probe.stdout.trim(); + const gh = (a: string[]) => { const r = spawnSync('gh', a, { cwd: repoRoot, encoding: 'utf8', timeout: 60_000 }); return { ok: r.status === 0, out: r.stdout ?? '', err: r.stderr ?? (r.error ? String(r.error.message) : '') }; }; + const ctx: QueueContext = { repoRoot, base: resolveBaseBranch(repoRoot, flag(args, '--base')), gh }; + const pr = flag(args, '--pr'); + if (cmd === 'gate-ahead') return gateAhead(ctx, args); + if (!pr || !/^\d+$/.test(pr)) return usage(`${cmd} needs --pr `); + const gateExit = flag(args, '--gate-exit'); + if (gateExit !== undefined && !/^-?\d+$/.test(gateExit)) return usage('--gate-exit needs an exit code'); + const gate = { gateExit: gateExit === undefined ? undefined : Number(gateExit), gateLog: flag(args, '--gate-log') }; + if (cmd === 'ready') return finish('ready', ready(ctx, { pr, pregate: flag(args, '--pregate'), ...gate })); + if (cmd === 'stamp') { + const version = flag(args, '--version'); + const expectGated = flag(args, '--expect-gated'); + const expectBase = flag(args, '--expect-base'); + if (!version || !expectGated || !expectBase) return usage('stamp needs --version --expect-gated --expect-base '); + return finish('stamp', stamp(ctx, { + pr, version, expectGated, expectBase, expectOrder: flag(args, '--expect-order')?.split(',').map(s => s.trim()).filter(Boolean), + allowRepoCommands: args.includes('--allow-repo-commands'), ...gate, + failAfter: process.env.GSTACK_SHIP_QUEUE_FAIL_AFTER, + })); + } + if (cmd === 'verify') { + const record = flag(args, '--record'); + return finish('verify', verify(ctx, { + pr, gated: flag(args, '--gated'), record: record ? path.resolve(record) : undefined, receipt: flag(args, '--receipt'), + expectHead: flag(args, '--expect-head'), ref: flag(args, '--ref'), noFetch: args.includes('--no-fetch'), ...gate, + })); + } + return usage(`unknown subcommand ${cmd}`); +} + +process.exitCode = main(process.argv.slice(2)); diff --git a/bin/gstack-ship-receipt b/bin/gstack-ship-receipt index f8441f1a7..bd3baa6aa 100755 --- a/bin/gstack-ship-receipt +++ b/bin/gstack-ship-receipt @@ -6,7 +6,8 @@ * [--predecessor ] [--gate ] [--ci ] [--spend-usd ] * [--session-kind ] [--artifacts-consumed /] [--run ] [--thread ] * [--receipt ] [--policy