mirror of
https://github.com/garrytan/gstack.git
synced 2026-11-05 08:23:59 +01:00
* fix(ship): base merges, adjacent base edits, test-only and audit-requested fixes no longer force a second review loop (GST-407, GST-384, GST-391) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * ship driver: trim two phrases for headroom with #3662 Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * ship driver: keep the Next steps heading phrase the handoff check reads; trim elsewhere Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: regenerate ship goldens Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes comparePath returns same only when every hunk sits where the base change puts it (patch-ids ignore positions) and treats a file-mode change as changed; the scoped-review packet says when a fence is truncated; --docs-result must be the posted audit's result; the --context-reviewed record goes beside the packet, outside the worktree. Negative controls for each. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pass-2 review fixes A test edit routes as tests= only when it adds lines with no gate tag; a removed or changed line or an unreadable test diff goes through the full loop. Diffs skip textconv. A hunkless patch (binary, empty, mode-only) is same when its patch-id matches. Without --reviewed-base test files route as before. finish's packet path and attempt's state directory have fallbacks. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: Step 11 review fixes; a version-only stamp_files edit after review is release metadata (GBRA-251) gateEditedPaths reads removed lines only inside hunks; carry refuses when a path listing fails; docs freshness stops on a failed listing; attempt counts an unreadable state file. releasePaths includes stamp_files paths whose edit is a version swap under stamp_patterns. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: no test edit skips review; guard packet writes; exclusive attempt state A test-only edit with no gate tag gets the scoped fix-check of its test hunks instead of a lanes-only rerun. Packet write failures print a STOP or RECEIPT_CARRY_REFUSED. attempt's allowance uses an exclusive create. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: attempt prints gstack's install command; carry checks the product diff outside context paths The attempt STOP no longer echoes the audit child's fix text. A scoped-review carry now requires the product patch-id without the context paths to match at both heads. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: oversized packets take the full loop; exact --docs-requested match; name-only test globs only in test dirs A scoped-review packet section over 200 lines sends that path to the full loop instead of a truncated packet. The docs-result path match is exact. test_*.py, *Test.java and similar count as test code only under a test directory. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(unattended): carry's scoped-review refusal and what it keeps Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: carry's scoped-review route in ship-policy, review-policy and troubleshooting (docs-a-1) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(windows): curate ship-rereview-triggers out of the Windows lane like ship-release (run 41193336209) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(review-log): record a notes-only /ship pass clean; name the cause and repair when a pass's tree moved (GST-430) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(receipt): carry and write handle PRs with thousands of files; tree receipt fails closed on a failed diff (GST-448) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(ship): preflight routes RECEIPT_CARRY_SCOPED_REVIEW to the scoped review; carry --dry-run writes no packet (GST-442) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(ship): Step 1.4 and Step 16 route the scoped-review refusal and the --docs-requested fix; trims keep the cap (GST-442, GST-444) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: /ship review pass 1: notes-only floor, scoped carry order, named temp and diff refusals - A notes-only pass is recorded clean only when every finding is fixed, or noted or deferred below the blocking floor (never CRITICAL or blocking), by its logger-stamped action, and the findings account for the claimed issue and critical counts (GST-430). - The preflight scoped carry route commits and pushes the base-merge fix before writing the packet (GST-442). - patchId refuses by name on an unwritable TMPDIR; the tree receipt names why its diff failed (GST-448). - Step 16 stage 3 spells out --docs-requested with its --docs-result (GST-444). Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: pin the Step 16 --docs-requested route with its --docs-result Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: a claimed clean review row with a logger-stamped open gate finding reads UNVERIFIED (red-team, pass 1) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: Step 11 findings: gate rows from --findings are stamped, one open rule, stale patch-id dirs swept - deriveFromFindings stamps gate rows with the session kind before deriving status, so a findings file cannot dispose of a gate finding the unattended logger forces open (outside-voice#1). - reviewFreshness reads a claimed row's findings with isOpenByAction, the rule the notes-only rewrite uses; noted and deferred clear a finding only when it is marked blocking: false and is not CRITICAL. - patchId sweeps gstack-patch-id-* directories over an hour old that a killed carry left in TMPDIR. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: Step 11 round 2: stamped-open gates win over status and disposition; resolved gate, skipped and below-floor actions stay CURRENT - isOpenFinding treats action 'open' (the logger's forced-open stamp) as open before a row's status or disposition. - reviewFreshness flags a claimed clean row only for an 'open' action or a CRITICAL or blocking deferral or note, so interactive kept and restored gates, skipped advisories and INFORMATIONAL deferrals read CURRENT as before. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: carry dry run offers the scoped route last; patch-id diff under the git dir; changelog matches the review-log floor Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: a claimed clean review row with any unresolved non-gate CRITICAL finding reads UNVERIFIED (pass 2 red-team) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: carry dry-run scoped route, patch-id directory, tree-receipt refusal (docs-d-1 audit) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(ship): Step 3 names merge conflicts in its STOP sentence again (ship-workflow-clarity pin) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(tree-receipt): keep the gated-to-current diff at the file helper timeout (60 s); pregate literals check Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(carry): large-diff fixture sets core.longpaths so Git for Windows can add its long receipt paths (windows-free-shard 1, run 41210080055) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(review): a stale local base branch yields to its origin twin in gate-diff and diff-scope (GST-462) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(ship): Step 11 saves the targeted record and the receipt writes carry it; Step 9 clears it (GST-464) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * changelog: GST-464 and GST-462 Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(review): pass 1: ahead and diverged labels, diff-scope needs shared history; preflight refreshes origin/<base> and stops on a diff far beyond the PR (GST-462, HARN-15) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pass-2 review fixes for base twin, prSized stop and targeted record Resolve the tracking twin by refs/remotes/<remote>/<ref> and only for a bare branch name, keep a local base that is ahead or diverged, quote the prSized stop's base and name the fork case, and have every Step 9 entry create, exclude and clear .gstack/tmp/targeted.json. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: origin's tracking base wins whenever related; prSized lower bound The fix-check found that keeping a local base ahead of origin left unpushed base commits out of the gate scan while review-plan listed them. The tracking branch now wins whenever it shares history with HEAD, an explicit origin/main reads refs/remotes/origin/main, the preflight also stops when the diff lists fewer files than the PR, and the Step 9 exclude line survives a missing .git/info and an exclude file without a final newline. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * changelog: the tracking-ref claim holds while the tracking branch exists Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: repin the two ship section briefs under no-loss replay GST-464 GST-464 brief-identity check: every reviewer brief lib/review-brief.ts cuts from ship/sections/review-army.md and adversarial.md stays byte-identical to the bodies the L and GST-257 replays admitted; only lead instructions outside the cut spans changed. The check is a test CI runs. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * ship: keep Step 9's PASS_HEAD sentence whole; repin review-army under GST-464 The targeted-record line follows the PASS_HEAD/RANGE_BASE sentence instead of splitting it (test/review-fix-range.test.ts pins that sentence). The brief-body check still holds: every reviewer brief is byte-identical. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: restore bin/gstack-ship-receipt after the main merge The merge commitb10e2dbwrote a truncated copy of the file. This is the three-way merge of both sides with the refused() union: main's codes plus RECEIPT_CARRY_SCOPED_REVIEW. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * review-collect: narrow the consumer scan and give it one 300 s deadline (GST-544) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * review-collect: keep the consumer scan deadline under the 180 s plan timeout (review fix) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * review-collect: plain paths under --literal-pathspecs; whole-millisecond timeout override (review fix) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * review-collect: whole-tree grep for non-UTF-8 names, no argument spread, name spawn errors (review fix) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * review-collect: cap the consumer grep output at 256 MB across calls; per-scan deadline wording (review fix, cycle 4) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * review-collect: read a missing spawn status as null (Bun 1.4.2 returns undefined on ENOENT) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: review-collect whole-tree helper reads a null status as -1 (typecheck:test ratchet) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * review-bots: /review and /ship triage every configured review bot, not only Greptile (#3122) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes (gh before 2.48 pages without --slurp; driver routes Step 10; tests for guards, review-bot fence, REMOTE_SLUG owner) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: drop the review-bot fence test that could not fail (the tool-fence WARN degrade is unreachable: placeholder spans are skipped first) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: Step 11 review fixes (record by comment id so a filename never reaches a shell; lookup failures are errors; tojson pages; longest bot prefix wins) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pass-2 review fixes (record refuses * paths, colliding ids and a missing fetch dir; parent requires id and dir; botOwning doc) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * review: classify the PR type and always check repo conventions (#356) The checklist now opens with a PR-type line (application, CI/infra, scripts/tooling, docs-only or mixed). Application and mixed diffs run every category; other types always run five categories, including the new Repo Conventions & Platform Fit, and report the rest as not applicable in one line instead of skipping silently. No-loss replay: GSTA-224 H1 preregistered no-loss run (run id gsta224-h1-20261031, Opus 5.5, 81 calls, $9.53) against main's checklist with a no-gstack arm; every preregistered bar passed. The review/checklist.md pin in test/review-packets-removed.test.ts moves to a32963ef with replay 'GSTA-224 H1'. Refs GSTA-224 Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * review-bots: allowlist the record placeholders and match Step 10's id rule in tests The record fence uses <comment-id>, <fix|fp|already-fixed> and <category>, each with an enum or numeric grammar; <greptile-dir> becomes <bot-dir>. review/greptile-triage.md also lists every REVIEW_BOTS skip reason. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: review-bot triage covers every configured bot (#3122) README, CONTRIBUTING, the contributor reference and standalone-binaries name gstack-review-bots and the review-bot fence; TODOS drops the #3122 item; the changelog fragment covers record-by-id and lookup errors. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: the PR-type test also pins the compose, Terraform and README/CHANGELOG phrases Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: follow the review-bot rename in the remote free tier's three reds The cross-skill consistency judge describes review-bot-history.md and its record helper; the tracker-guard exemption for the removed raw Greptile fetch in review/greptile-triage.md is dropped (the fetch now lives in gstack-review-bots, whose bodies still reach context only through gstack-issue-guard); the Step 10 PR-check test expects 'Review bots: not run'. HARNESS_VERSION stays 6: skill-fixture.ts and llm-judge.ts are recorded non-behavioral for every other case. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: keep the cross-skill judge's rubric to one renamed bullet Name review-bot-history.md beside the older greptile-history.md so the calibration corpus still matches, and keep the REMOTE_SLUG bullet. One live 3-sample panel at this tree: consistent 3/3, scores 4/4/4. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * changelog: H1 fragment passes prose lint Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * changelog: name the H1 fragment after its branch; TODOS drops #356 Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: /review's PR type step in docs/skills.md (#356) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * ship-policy: review_exclude_paths key and loadPolicyAt (GST-508) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * review: apply the base policy's review_exclude_paths and the reviewer diff ceiling (GST-508) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * receipt: bind review_exclude in write, carry and the queue (GST-508) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs, tests and changelog for review_exclude_paths (GST-508) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes (binary by bytes, links kept, untracked files out of the selection) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: keep binary files at code paths under review_exclude_paths Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: name the reasons that keep a binary file under review_exclude_paths Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: keep every review_exclude_paths candidate when the gate scan is unknown; docs example names its version Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: keep the NUL fixture clear of the sync-spawn tripwire Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * changelog: split the ceiling sentence Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: keep a live binary file whose bytes cannot be read; tests render outside voices from a clean checkout and read the ship fixture text Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(review-exclude): explicit +x for the census script; skip the chmod-000 read case on Windows and root Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * refactor: move loadPolicyAt to lib/ship-policy-at.ts so lib/ship-policy.ts stays under the 800-line module cap Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: refuse a base that contains HEAD; skip a self-pointing origin/HEAD (GST-774) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * chore: regenerate gstack-doctor-components.sh for BASE_CONTAINS_HEAD Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: land resumes a merged merge-only PR instead of refusing BASE_CONTAINS_HEAD (GST-774 review) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: changelog fragment for GST-774 Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: troubleshooting names diff-scope base_contains_head and the self-pointing no_base case (GST-774 docs audit) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: repin the reviewer briefs to GST-508's no-loss-tested bytes ship/sections/review-army.md, ship/sections/adversarial.md and lib/review-depth.ts now pin the bytes the GST-508 preregistered no-loss replay ran atef2760f(handoffs/GSTA-202/noloss-results.md in the GStack Minder drive): Arm V 33/41 vs R 33/41, delta 4, exact sign flip, p_NI 0.0279 (pass). The merge of main83ae96eleaves these three files byte-identical toef2760f, and an Arm P unit (3593) renders byte-identical briefs atef2760fand at the merge. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: GST-774 review round 1 — merged resume depth, aliased and detached PR checkouts, develop/trunk defaults Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * ship: Step 20 says a metrics row, keeping DRIVER.md at 12 KB after the main merge Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: ship-parts resend case leaves room for the first phase-3 part after the Step 9 targeted-record sentence Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: /ship delivers review/checklist.md in two parts so checklist v1 fits the 24576-byte part cap (#3670) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * changelog: drop the GST-407 and GST-430 fragments, already released on main (stacked history) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * wave review-53cfb5bfe011: lib/ship-policy.ts back to 800 lines (module-size ratchet after merging #3744 and #3795) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * wave review-53cfb5bfe011: /ship pass 1 fixes - lib/ship-receipt-depth.ts: a merged resume (land after a true merge) no longer recomputes the review_exclude digest over the emptied range, so it lands instead of RECEIPT_INVALID (failing-first land test with review_exclude_paths active). - bin/gstack-review-dispatch render: a standalone targeted render under an active review_exclude_paths refuses and points at the pass manifest voices stage, instead of writing a brief with no selection that leaves verify dirty (failing-first test). - test/default-base.test.ts: #3795 expectations follow main R51 depth (light for an 80-line code diff; runtime_lines=80 still proves the real base). - test/review-dispatch.test.ts: the GST-897 fingerprint test renders from the clean checkout, like its neighbor, because CI rebuilds the tracked lib/diagram-render/dist/diagram-render.html and the reviewer diff ceiling refused the ROOT render. * wave review-53cfb5bfe011: /ship pass 2 fixes - lib/review-exclude.ts: binaryContent reads each blob's first 8,000 bytes (git cat-file blob, 8 KB buffer) instead of one --batch read capped at 256 MB, so head mode (receipt, carry, queue) and the plan agree past 256 MB of blobs; an unreadable blob is kept, as in live mode. Failing-first test with two 270 MB blobs. - lib/review-bots.ts: a file-level bot review comment (subject_type file, no line position) is triaged instead of read as outdated. Failing-first test. - test/ship-queue-land.test.ts: the merged-resume exclusion test runs its gate scan under the fixture state root, not the real home (CI free-suite 6 home containment). * fix: merge follow-ups for main3d99c22: origin/* stays qualified in diff-scope's twin step, retro skeleton back under its cap, combined no-loss pin GST-508+R51+GST-911 * fix(review): receipt write gate-scans whenever the base declares review_exclude_paths; collectLive never re-qualifies origin/<base> (#3852 /ship red-team#1, outside-voice#1) * test: the docs-only receipt digest test keeps its gate scan out of the real home (free-suite shard 5 FREE_SUBSHARD_REJECTED) * fix(mergefc292e22f): tentative REVIEW_EXCLUDE_KEY_VERSION, classify targeted.json, render main's new outside-voice test from a clean checkout - lib/ship-policy.ts: REVIEW_EXCLUDE_KEY_VERSION 1.93.0.0 -> 1.94.0.0, the next-minor tentative form stamp_paths moves (docs/ship-policy.md, #3512); 1.93.0.0 is a released heading that never names the key. - test/gstack-clean-producers.test.ts (new from main): KEPT gains targeted.json, the wave's --review-targeted input. - test/review-dispatch.test.ts: main's wrong-tree test rendered the outside voice from ROOT; a CI build that dirties ROOT pushes that diff past the wave's REVIEW_DIFF_MAX_BYTES ceiling, so render refused and verify saw no brief (exit 3). It now runs in cleanCheckout like the wave's other outside-voice tests. * test(merge68410828f): GST-967's brief-body pin carries the wave's GST-508 placeholders The merged sectionTexts differ from main's by exactly the wave's GST-508 exclude-pathspec lines (merged minus main equals wave minusfc292e22f); the 1,440-case plan grid still hashes to main's MAIN_PLANS. Checks: GStack Minder drive handoffs/GSTA-202/merge-6841-checks.md. * ship: CI carries mapped lanes, --reuse tree cache, early push, finish/accept split (GSTA-258 A) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * ship: name the ship and pregate bins in prose so skill-bin-drift does not read a bin Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * size-ledger: re-record ship after the tests.md wording fix Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * pregate: a carried run clears the remote gate through remote_gate_runs, so a paid-only remainder is not a dead end Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * merge cleanup: drop wave fragments main already consumed and a duplicated KEPT entry Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(ship): record-ci verifies the CI run itself; finish's deferred preflight keeps pregate.json /ship pass 1 findings red-team#1 and specialist-batched#1 (GSTA-258 piece A). Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat(pregate): CI carry is gstack's default remote gate route; the VM is opt-in (plan choice F1) The uncleared remote_gate obligation names the CI route first when the base declares remote_gate_runs. docs/pregate.md says how gstack clears it, including the pull_request merge-ref tree mismatch. GSTA-258 piece A. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes (round 2) record-ci records the base policy that mapped the lane; the CI-first remote gate hint respects --no-ci-carry and reruns the whole pregate; changelog and docs say what the tool does. GSTA-258 piece A. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: CI carry in CONTRIBUTING, recommended-harness and the pregate usage line (ship docs audit) 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>
233 lines
15 KiB
TypeScript
233 lines
15 KiB
TypeScript
/**
|
|
* ship-bin-common — what gstack-ship-preflight and gstack-ship-release share: running git
|
|
* and sibling bins with timeouts, flag reading, the effective ship policy, and the compact
|
|
* result every step prints (KEY: lines, STOP: where the agent must judge, NEXT: what it
|
|
* does next). The bins chain existing commands and never make a decision the /ship prose
|
|
* assigns to the agent.
|
|
*/
|
|
import { spawn, spawnSync } from 'node:child_process';
|
|
import * as fs from 'node:fs';
|
|
import * as os from 'node:os';
|
|
import * as path from 'node:path';
|
|
import { fragmentSlug } from './changelog-fragments';
|
|
import { isConfigUnavailable, loadConfigFromBase } from './pregate/config';
|
|
import { parseUnifiedDiff, versionAtRef } from './restamp';
|
|
import { branchSides, stampOnlyLine } from './stamp-only';
|
|
import { matchesAny } from './ship-policy';
|
|
import { extractVersion } from './version-source';
|
|
import { BIN_DIR, runBashSync, runScriptSync, scriptInvocation } from './script-invocation';
|
|
|
|
export interface Run { status: number | null; stdout: string; stderr: string }
|
|
const done = (r: { status: number | null; stdout?: string | Buffer | null; stderr?: string | Buffer | null; error?: Error }): Run =>
|
|
({ status: r.status, stdout: String(r.stdout ?? ''), stderr: String(r.stderr ?? '') + (r.error ? r.error.message : '') });
|
|
|
|
export function git(cwd: string, args: string[], timeout = 120_000): Run {
|
|
return done(spawnSync('git', args, { cwd, encoding: 'utf8', timeout, maxBuffer: 64 * 1024 * 1024, env: { ...process.env, GIT_TERMINAL_PROMPT: '0' } }));
|
|
}
|
|
export function bin(cwd: string, name: string, args: string[], timeout = 600_000): Run {
|
|
return done(runScriptSync(path.join(BIN_DIR, name), args, { cwd, encoding: 'utf8', timeout, maxBuffer: 64 * 1024 * 1024 }));
|
|
}
|
|
/** Whether origin's configured URL names a host (https, ssh or scp form), before any insteadOf rewrite; a local path or file:// remote has none, so gh cannot map it to a repository. */
|
|
export function hostedOrigin(cwd: string): boolean {
|
|
const url = git(cwd, ['config', '--get', 'remote.origin.url']).stdout.trim();
|
|
return /^(?:[a-z][a-z0-9+.-]*:\/\/(?:[^@/\s]+@)?[^/:\s]+[:/]|[^@/\s]+@[^/:\s]+:)\S+$/i.test(url) && !/^file:/i.test(url);
|
|
}
|
|
/** gh with argv, never a shell, so a branch name cannot change what runs. */
|
|
export function gh(cwd: string, args: string[], timeout = 60_000): Run {
|
|
return done(spawnSync('gh', args, { cwd, encoding: 'utf8', timeout, maxBuffer: 64 * 1024 * 1024, env: { ...process.env, GIT_TERMINAL_PROMPT: '0' } }));
|
|
}
|
|
export function sh(cwd: string, command: string, timeout = 1_800_000): Run {
|
|
return done(runBashSync(command, { cwd, encoding: 'utf8', timeout, maxBuffer: 64 * 1024 * 1024 }));
|
|
}
|
|
/** A sibling bin run without blocking, so independent test lanes run in parallel. */
|
|
export function binAsync(cwd: string, name: string, args: string[], timeout = 3_600_000): Promise<Run> {
|
|
const inv = scriptInvocation(path.join(BIN_DIR, name), args);
|
|
if (!inv.ok) return Promise.resolve({ status: null, stdout: '', stderr: inv.error });
|
|
return new Promise(resolve => {
|
|
const child = spawn(inv.cmd, inv.argv, { cwd, stdio: ['ignore', 'pipe', 'pipe'] });
|
|
let stdout = '', stderr = '';
|
|
child.stdout.on('data', d => { stdout = (stdout + d).slice(-200_000); });
|
|
child.stderr.on('data', d => { stderr = (stderr + d).slice(-200_000); });
|
|
const timer = setTimeout(() => child.kill('SIGKILL'), timeout);
|
|
child.on('close', status => { clearTimeout(timer); resolve({ status, stdout, stderr }); });
|
|
});
|
|
}
|
|
|
|
export function flagReader(argv: readonly string[]) {
|
|
const all = (n: string) => argv.flatMap((a, i) => (a === n && argv[i + 1] !== undefined ? [argv[i + 1]!] : []));
|
|
return { all, flag: (n: string) => all(n).at(-1), has: (n: string) => argv.includes(n) };
|
|
}
|
|
|
|
/** --lane <label>=<command> pairs (Step 5's labels and exact commands). */
|
|
export function lanes(argv: readonly string[]): { label: string; command: string }[] | string {
|
|
const out: { label: string; command: string }[] = [];
|
|
for (const raw of flagReader(argv).all('--lane')) {
|
|
const at = raw.indexOf('=');
|
|
if (at < 1 || at === raw.length - 1) return `--lane ${raw} is not <label>=<command>`;
|
|
out.push({ label: raw.slice(0, at), command: raw.slice(at + 1) });
|
|
}
|
|
return out;
|
|
}
|
|
|
|
/** The base branch's effective ship policy (gstack-ship-policy show-effective --json), or null when unreadable. */
|
|
export function shipPolicy(cwd: string, base: string): Record<string, any> | null {
|
|
const r = bin(cwd, 'gstack-ship-policy', ['show-effective', '--base', base, '--json'], 60_000);
|
|
try { return JSON.parse(r.stdout).policy ?? null; } catch { return null; }
|
|
}
|
|
|
|
/** Manifests a version stamp writes: release metadata only while the edit changes nothing but the version. */
|
|
export const VERSIONED_MANIFESTS = ['package.json', 'package-lock.json', 'npm-shrinkwrap.json'];
|
|
|
|
/** True when `p` in the working tree differs from `p` at `ref` (a commit or tree) in its version fields alone; a new, deleted or unparseable file never qualifies. */
|
|
export function versionOnlyEdit(cwd: string, ref: string, p: string): boolean {
|
|
const before = git(cwd, ['show', `${ref}:${p}`]);
|
|
if (before.status !== 0) return false;
|
|
let now: string;
|
|
try { now = fs.readFileSync(path.join(cwd, p), 'utf8'); } catch { return false; }
|
|
const strip = (s: string) => {
|
|
const o = JSON.parse(s);
|
|
delete o.version;
|
|
if (o.packages?.['']) delete o.packages[''].version;
|
|
return JSON.stringify(o);
|
|
};
|
|
try { return strip(before.stdout) === strip(now); } catch { return false; }
|
|
}
|
|
|
|
/**
|
|
* Release metadata a version stamp and Steps 13-14 write, compared against `ref`: the release commit's paths,
|
|
* never a behavior change. A manifest counts only while its edit is version-only (a dependency, script or
|
|
* lockfile change is a build input); bun.lock never counts.
|
|
*/
|
|
export function releasePaths(policy: Record<string, any> | null, cwd: string, ref: string, base: string): string[] {
|
|
const list = (v: unknown) => (Array.isArray(v) ? v.filter((s): s is string => typeof s === 'string') : []);
|
|
const fragment = fragmentPath(policy, cwd);
|
|
return [...new Set(['VERSION', 'CHANGELOG.md', 'TODOS.md', 'agents-digest/gstack-AGENTS.md', ...VERSIONED_MANIFESTS.filter(p => versionOnlyEdit(cwd, ref, p)),
|
|
...(typeof policy?.changelog === 'string' ? [policy.changelog] : []), ...(fragment ? [fragment] : []), ...list(policy?.release_outputs), ...list(policy?.stamp_paths),
|
|
...stampedFiles(policy, cwd, ref, base)])];
|
|
}
|
|
|
|
/**
|
|
* `stamp_files` paths whose working-tree edit against `ref` is a version stamp alone: every changed line swaps the
|
|
* old version for the new one under a built-in form or a `stamp_patterns` template (lib/tree-receipt.ts classifyFile).
|
|
* A moved version is floored at `ref`'s VERSION, except on a line the branch added itself (gstack-restamp's own rule:
|
|
* added since the merge base with origin/<base>, and not added by the base since): after a lost slot and a merge of the
|
|
* base its stale stamp is older than `ref`'s VERSION, so it must be at or newer than the fork point's version instead,
|
|
* the bound gstack-restamp's stamp_paths stage uses (GST-895; the fork version itself since GST-963). A branch line is
|
|
* named by its position, and with a kept VERSION only such a line may move (GST-979, GST-980).
|
|
*/
|
|
export function stampedFiles(policy: Record<string, any> | null, cwd: string, ref: string, base: string): string[] {
|
|
const globs = Array.isArray(policy?.stamp_files) ? policy.stamp_files.filter((s: unknown): s is string => typeof s === 'string') : [];
|
|
if (!globs.length) return [];
|
|
const before = versionAtRef(cwd, ref);
|
|
if (!('version' in before)) return [];
|
|
let after = '';
|
|
try { after = extractVersion(fs.readFileSync(path.join(cwd, before.rel), 'utf8'), before.rel); } catch { return []; }
|
|
if (!after) return [];
|
|
const templates = Array.isArray(policy?.stamp_patterns) ? policy.stamp_patterns.filter((s: unknown): s is string => typeof s === 'string') : [];
|
|
const diff = git(cwd, ['diff', '--unified=0', '--no-color', '--no-ext-diff', '--no-textconv', '--no-renames', ref]);
|
|
if (diff.status !== 0) return [];
|
|
const side = branchSides(cwd, `origin/${base}`, 'HEAD', before.version, ref);
|
|
const stamp = (rel: string, removed: string, added: string, at: number): boolean => stampOnlyLine(removed, added, before.version, after, templates, side(rel), at);
|
|
return parseUnifiedDiff(diff.stdout).filter(f => f.status === 'M' && !f.binary && !f.modeChanged && matchesAny(globs, f.path) && f.hunks.length > 0 &&
|
|
f.hunks.every(h => h.removed.length === h.added.length && h.removed.every((line, i) => stamp(f.path, line, h.added[i]!, h.removedAt[i]!)))).map(f => f.path);
|
|
}
|
|
|
|
/** Under `changelog_fragments`, the branch's own Step 13 entry `<dir>/<branch-slug>.md` (docs/ship-policy.md#changelog-fragments); null without the key. */
|
|
export function fragmentPath(policy: Record<string, any> | null, cwd: string): string | null {
|
|
const dir = policy?.changelog_fragments?.dir;
|
|
if (typeof dir !== 'string') return null;
|
|
return `${dir.replace(/\/+$/, '')}/${fragmentSlug(git(cwd, ['rev-parse', '--abbrev-ref', 'HEAD']).stdout.trim())}.md`;
|
|
}
|
|
|
|
/** The paths a lane receipt may ignore: release metadata except TODOS.md, whose Step 14 edit reruns the lanes (ship/SKILL.md Step 16). */
|
|
export const evidenceExempt = (release: readonly string[]) => release.filter(p => p !== 'TODOS.md');
|
|
|
|
export const short = (list: readonly string[], n = 6) => list.slice(0, n).join(',') + (list.length > n ? `,+${list.length - n} more` : '');
|
|
export const firstLine = (s: string) => s.trim().split('\n').filter(Boolean).at(-1)?.slice(0, 240) ?? '';
|
|
|
|
/** The compact result: at most MAX_LINES lines; STOP and NEXT always survive the cap. */
|
|
export const MAX_LINES = 30;
|
|
export class Report {
|
|
readonly lines: string[] = [];
|
|
exit = 0;
|
|
add(line: string): this { this.lines.push(line); return this; }
|
|
next(what: string): this { return this.add(`NEXT: ${what}`); }
|
|
stop(what: string): Report { this.exit = 3; return this.add(`STOP: ${what}`); }
|
|
render(): string {
|
|
const keep = this.lines.length <= MAX_LINES ? this.lines
|
|
: [...this.lines.filter(l => !/^(STOP|NEXT):/.test(l)).slice(0, MAX_LINES - 1 - this.lines.filter(l => /^(STOP|NEXT):/.test(l)).length), `… ${this.lines.length - MAX_LINES + 1} line(s) cut`, ...this.lines.filter(l => /^(STOP|NEXT):/.test(l))];
|
|
return keep.join('\n') + '\n';
|
|
}
|
|
}
|
|
|
|
/**
|
|
* How many lanes run at once (GST-851): `--lanes serial` one, `--lanes parallel` all; unset, one on a machine with 4 or fewer
|
|
* cores (six lanes at once took 4-core machines down on gstack-evals) and all above that. Any other value is a usage error.
|
|
*/
|
|
export function laneConcurrency(mode: string | undefined, cpus = os.availableParallelism()): number | string {
|
|
if (mode === 'serial') return 1;
|
|
if (mode === 'parallel') return Infinity;
|
|
if (mode !== undefined) return `--lanes ${mode} is not serial or parallel`;
|
|
return cpus <= 4 ? 1 : Infinity;
|
|
}
|
|
|
|
export interface LaneResult { label: string; exit: number | null; testsRan: string; log: string; carried?: string; reused?: string; carryNone?: string }
|
|
|
|
/** The base branch's `ship_lanes_from` entry for each lane whose command is a key, byte for byte (the ledger binds its sha256). */
|
|
export function mappedLanes(cwd: string, base: string, list: { label: string; command: string }[]): Map<string, { profiles: string[]; inventory: string }> {
|
|
const loaded = loadConfigFromBase(cwd, base);
|
|
const map = new Map<string, { profiles: string[]; inventory: string }>();
|
|
if (isConfigUnavailable(loaded) || loaded.errors.length) return map;
|
|
const from = loaded.config.ship_lanes_from;
|
|
for (const l of list) if (Object.prototype.hasOwnProperty.call(from, l.command)) map.set(l.label, from[l.command]!);
|
|
return map;
|
|
}
|
|
|
|
/**
|
|
* A mapped lane carried from CI at HEAD's clean tree: gstack-evidence record-ci finds and verifies the run (lib/ci-carry.ts)
|
|
* and records the CI-sourced ledger row; or why it was not (`carryNone`), so the caller runs it.
|
|
*/
|
|
export function carryLane(cwd: string, base: string, l: { label: string; command: string }): LaneResult {
|
|
const rec = bin(cwd, 'gstack-evidence', ['record-ci', '--label', l.label, '--base', base, '--', l.command], 600_000);
|
|
const got = / tests_ran=(\d+) log=- source=ci runs=(\S+)/.exec(rec.stderr);
|
|
if (rec.status === 0 && got) return { label: l.label, exit: 0, testsRan: got[1]!, log: '-', carried: got[2]! };
|
|
return { label: l.label, exit: null, testsRan: 'unknown', log: '-', carryNone: /^CARRY_NONE: (.+)$/m.exec(rec.stderr)?.[1] ?? `record_failed: ${firstLine(rec.stderr)}` };
|
|
}
|
|
|
|
/**
|
|
* Run each lane, at most `concurrency` at a time; results keep the lanes' order. With `base`, a lane the base branch maps in
|
|
* `ship_lanes_from` is carried from a verified CI run at this exact tree when one exists. Every other lane runs through
|
|
* gstack-evidence run --reuse (a pass at this tree, command and runtime is reused; `reuse: false` forces a run).
|
|
*/
|
|
export async function runLanes(cwd: string, list: { label: string; command: string }[], concurrency = Infinity, opts: { base?: string; reuse?: boolean } = {}): Promise<LaneResult[]> {
|
|
const out: LaneResult[] = [];
|
|
const mapped = opts.base ? mappedLanes(cwd, opts.base, list) : new Map<string, { profiles: string[]; inventory: string }>();
|
|
let next = 0;
|
|
const worker = async () => {
|
|
while (next < list.length) {
|
|
const i = next++;
|
|
const l = list[i]!;
|
|
const m = mapped.get(l.label);
|
|
const carry = m ? carryLane(cwd, opts.base!, l) : null;
|
|
if (carry?.carried) { out[i] = carry; continue; }
|
|
const r = await binAsync(cwd, 'gstack-evidence', ['run', ...(opts.reuse === false ? [] : ['--reuse']), '--label', l.label, '--', l.command]);
|
|
const rec = /gstack-evidence: recorded label=\S+ exit=(\S+) tests_ran=(\S+) log=(\S+)/.exec(r.stderr);
|
|
const reused = /gstack-evidence: reused label=\S+ tree=\S+ from=(\S+)/.exec(r.stderr)?.[1];
|
|
out[i] = { label: l.label, exit: r.status, testsRan: rec?.[2] ?? 'unknown', log: rec?.[3] ?? '-', ...(reused ? { reused } : {}), ...(carry?.carryNone ? { carryNone: carry.carryNone } : {}) };
|
|
}
|
|
};
|
|
await Promise.all(Array.from({ length: Math.max(1, Math.min(concurrency, list.length)) }, worker));
|
|
return out;
|
|
}
|
|
|
|
/** Step 5's lane verdict: a lane passes on its runner count, never exit 0 alone; a carried lane names its CI runs. */
|
|
export function laneLine(l: LaneResult): { line: string; ok: boolean } {
|
|
if (l.carried) return { line: `LANE: ${l.label} carried run=${l.carried} tests_ran=${l.testsRan}`, ok: true };
|
|
const zero = l.exit === 0 && l.testsRan === '0';
|
|
const state = l.exit !== 0 ? 'FAIL' : zero ? 'ZERO-RUN' : l.testsRan === 'unknown' ? 'pass (count unavailable)' : 'pass';
|
|
return { line: `LANE: ${l.label} ${state} exit=${l.exit} tests_ran=${l.testsRan} log=${l.log}${l.reused ? ` reused=${l.reused}` : ''}`, ok: l.exit === 0 && !zero };
|
|
}
|
|
|
|
/** The CI_CARRY line for a mapped lane that ran here instead. */
|
|
export const carryNoneLine = (l: LaneResult) => (l.carryNone ? `CI_CARRY: none label=${l.label} (${l.carryNone.length > 220 ? `${l.carryNone.slice(0, 220)}…` : l.carryNone})` : null);
|