Files
gstack/bin/gstack-review-dispatch
T
Garry Tanandcapy-ai[bot] 14d7414af3 v1.93.33.0 wave(review): #3705 #3744 #3745 #3764 #3765 #3795 (#3852)
* 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 commit b10e2db wrote 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 at ef2760f (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 main 83ae96e leaves these three files byte-identical to ef2760f, and an Arm P unit
(3593) renders byte-identical briefs at ef2760f and 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 main 3d99c22: 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(merge fc292e22f): 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(merge 68410828f): 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 minus fc292e22f); the 1,440-case plan grid still hashes to main's MAIN_PLANS. Checks: GStack Minder drive handoffs/GSTA-202/merge-6841-checks.md.

* fix(merge e85005482): targeted classes since the read accept an empty range; the wave's receipt tests pass main's targeted record

- lib/ship-receipt-depth.ts targetedClassesSince (main, GST-986) reads the range from the commit the targeted reader read to HEAD through headInputs, which since #3795 runs gstack-diff-scope's BASE_CONTAINS_HEAD check. When the reader read HEAD itself the range is empty, diff-scope reported base_contains_head, and every write with --review-targeted was refused (the product patch matched). It now passes merged=true (--merged), which skips only that check; an ancestor check already guards the range.
- test/review-exclude.test.ts and test/review-targeted.test.ts: since #3887 write refuses a money head with no targeted record and requires the record's head, so the wave's two writes that must succeed pass one, as main's own tests do (targetedAtHead in test/ship-receipt-depth.test.ts).

* test(merge e85005482): drop the wave's duplicate targeted.json KEPT entry

Main (#3887) classified .gstack/tmp/targeted.json in KEPT too; the auto-merge kept both keys, which typecheck:test rejects (TS1117). Main's entry stays.

* test(merge e85005482): ship size ledger entry for the merged tree (-232 B)

Main's ship size ledger plus the wave's entries summed to 345,334 B; the merged tree measures 345,102 B because DRIVER.md takes main's shorter Step 19 line. Recorded with scripts/size-ledger.ts record ship.

---------

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-03 01:40:07 +00:00

445 lines
37 KiB
TypeScript
Executable File

#!/usr/bin/env -S bun --no-env-file --config=/dev/null
/**
* gstack-review-dispatch — /ship's reviewers get their briefs byte for byte and the parent changes
* nothing they return (GSTA-167 no-loss gate; docs/review-policy.md#verbatim-dispatch).
*
* gstack-review-dispatch render --role <role> [--name <n>] --out <dir> [slots] write the brief, print its sha256
* gstack-review-dispatch sent --ledger <f> --role <role> [--name <n>] --sent <file> the prompt actually passed; mismatch fails
* gstack-review-dispatch collect --ledger <f> --role <role> [--name <n>] --output <file> --merged <file>
* gstack-review-dispatch judge --ledger <f> --merged <file> --judged <file> no drop, no downgrade
* gstack-review-dispatch verify --ledger <f> [--targeted-out <file>] replay every hash and the judgment
* gstack-review-dispatch pass --base <b> --out <dir> --pass <id> [-- plan flags] the pass's staged manifest
* gstack-review-dispatch show|stage|chunk|mark --manifest <f> ... one manifest step
* gstack-review-dispatch program [--ledger <f>] the checked-in Capy pass program
*
* Logic: lib/review-brief.ts (rendering from the sections), lib/review-ledger.ts (ledger, collect, judge, verify),
* lib/review-pass.ts (the staged manifest) and lib/capy-review-pass.js (the Capy program that runs it).
*/
import { spawnSync } from 'node:child_process';
import * as fs from 'node:fs';
import * as path from 'node:path';
import { EXIT, exitTableHelp } from '../lib/headless-artifacts';
import { BRIEF_ROLES, BriefError, briefFile, checkReviewedTree, checkoutRoot, checkoutTree, promptHash, renderBrief, sectionTexts, withWorkspace, type BriefRole, type Slots, type TreeCheck } from '../lib/review-brief';
import { cleanMarkers, collect, fixableRaises, mayBeUnavailable, parseFindings, readJsonl, readLedger, readerKey, recordJudgment, recordSent, appendEvent, verify, type JudgedLine, type MergedLine, type VerifyRow } from '../lib/review-ledger';
import { buildManifest, chunkCount, chunkOf, manifestPath, markReader, readManifest, renderStage, writeManifest, STAGES, type Extra, type Manifest, type PassReader, type ReaderState, type Stage } from '../lib/review-pass';
import type { Dispatch } from '../lib/review-depth';
import { runScriptSync } from '../lib/script-invocation';
import { TARGETED_RULES, parseClassList, targetedBriefSha, targetedRead } from '../lib/review-targeted';
import { resolveBaseBranch } from '../lib/ship-policy';
import { REVIEW_DIFF_MAX_BYTES, ceilingContext, disclosureDigest, disclosureLine, parseTail, readSelection, tooLargeLine, unreadableLine, type PlanExclude, type ReaderDiff } from '../lib/review-exclude';
const HELP = `gstack-review-dispatch — verbatim reviewer briefs and loss-free collection for /ship
render --role <role> [--name <n>] --out <dir> [--ledger <f>] [slots]
roles: ${BRIEF_ROLES.join(', ')}
slots: --diff-base <sha> (every role but fix-check) --exclude '<DIFF_CMD tail>' --stack <s> --test-fw <s>
--keep '<DIFF_KEEP tail after <diff-base>>' --disclosure '<the line every brief carries>' (both only under review_exclude_paths)
--learnings-file <f> --checklist <path> (default <root>/review/specialists/<name>.md; red-team.md for red-team)
--checklists <a,b> (specialist-batched: the plan's checklists= names, or paths) --findings-file <f> --specialists <n> (red-team)
--fix-list <f> --hunks <f> --tests <f> [--callers <f>] (fix-check)
--classes <money,gate,auth,secret> (targeted: the plan's TARGETED classes; the brief is review/specialists/targeted.md;
--diff-base must be the merge base with --base, default origin/HEAD's branch, on every pass)
writes <out>/<role>[-<name>].prompt.md, the brief followed by the workspace paragraph naming the toplevel of the
checkout it runs in (the one its diff and merge base come from), records it in the ledger (default <out>/review-ledger.jsonl) and prints
BRIEF: reader=<role/name> sha256=<h> bytes=<n> file=<path>. Pass that file's content as the reader's prompt, unchanged.
sent --ledger <f> --role <role> [--name <n>] --sent <file>
the exact prompt a dispatch passed: BRIEF_SENT: … match, or BRIEF_MISMATCH: … (exit 1; the pass is not reviewed)
collect --ledger <f> --role <role> [--name <n>] --output <file> --merged <merged.jsonl> [--manifest <f>]
the reader's raw output: hashes it and appends each finding to merged.jsonl with its label as written. A reply with
no finding must carry its brief's clean marker (NO FINDINGS; the Recommendation: line for the voices); without one it is
COLLECT_NOT_REVIEWED (exit 1): a refusal, an empty reply or a reader that never saw the diff, and verify reports NOT_COLLECTED
until the brief is re-sent and answered with a review, which voids it. A reply whose REVIEWED_TREE line is missing or names
another checkout or tree than its brief was rendered on is COLLECT_WRONG_TREE (COLLECT_TREE_MOVED when only the tree
moved; exit 1, nothing merged, verify reports NOT_COLLECTED, and with --manifest <f> the reader becomes failed); the
outside voice's, when it holds no finding, is recorded as unavailable coverage instead --unavailable '<reason>' (the outside voice only; refused when the
output holds findings) records its failure text as missing coverage: COLLECT_UNAVAILABLE, and verify prints UNAVAILABLE and unavailable=N, never a review
judge --ledger <f> --merged <merged.jsonl> --judged <judged.jsonl>
judged lines {"id","severity","reason"?,"duplicate_of"?}: every merged id kept at its severity or above (a
duplicate folds into one at least as severe); added and promoted findings need a reason. JUDGMENT: ok …, or
JUDGMENT_REJECTED: dropped=… downgraded=… (exit 1)
verify --ledger <f> [--targeted-out <file>]
BRIEF, OUTPUT and JUDGE rows from the ledger alone, then VERIFY: clean (exit 0), VERIFY: dirty (exit 1) or
VERIFY: no brief records (exit 3: this run's ledger kept no prompts). A ledger with a targeted brief also prints
TARGETED_RECORD: and --targeted-out writes it as the JSON gstack-ship-receipt write --review-targeted reads; under
review_exclude_paths prints REVIEW_EXCLUDE_RECORD: digest=<d> (the selection every reader's newest brief names: the
value gstack-ship-receipt write --review-exclude takes), and a mixed set of digests makes it dirty
pass --base <ref> --out <dir> --pass <id> [--ledger <f>] [--diff-base <sha>] [--learnings-file <f>] [--extras <json>] [--audit-only]
[--checklist-root <dir>] [--fix-list <f> --hunks <f> --tests <f> [--callers <f>]] [-- <gstack-review-plan flags>]
runs gstack-review-plan and writes <out>/pass-manifest.json: stage first (audit readers marked first in --extras),
specialists (with the other --extras readers), red-team, voices (Step 11). Renders first and specialists now; prints
the plan, MANIFEST: and one READER: line per reader. A plan whose NEXT is not full, scoped or fix-check prints PASS: none.
A fix-check reader (stage specialists) renders from decision 3.5's --fix-list, --hunks, --tests and --callers files.
--diff-base sets every reader's base, a scoped pass's Red Team included (the targeted reader keeps the merge base).
An existing manifest for the same --pass is reused (resumed). --extras: [{"name","prompt_file","first"?,"model"?}]
--audit-only skips the plan: the --extras readers are the whole pass (Step 14.5's docs audit)
Before anything is written (and again before stage renders), each reviewer's diff is read once with a
${REVIEW_DIFF_MAX_BYTES}-byte ceiling: over it prints REVIEW_DIFF_TOO_LARGE with the largest folders and the fix for where the
base policy's review_exclude_paths stands (exit 3); a git failure or timeout prints REVIEW_DIFF_UNREADABLE with the
stderr written under --out (exit 1). render applies the same ceiling to the selection --exclude and --keep name
whenever --diff-base is a commit here (always for the outside voice, whose brief embeds that selection).
show --manifest <f> MANIFEST_JSON: <the manifest on one line>
stage --manifest <f> --stage <first|specialists|red-team|voices>
renders a stage; the Red Team only after every earlier reader is collected, its findings file being the
specialists' merged.jsonl lines byte for byte
chunk --manifest <f> --reader <r> --index <i>
BRIEF_CHUNK: reader=… index=i of=n sha256=…, then one JSON string line of at most 65,536 brief characters
mark --manifest <f> --reader <r> --state <intent|created|queued|collected|failed> [--path <p>] [--output <f>] [--error <e>]
an audit reader is collected with --output, whose REVIEWED_TREE line must match its render (else failed, COLLECT_WRONG_TREE)
mark --manifest <f> --before <tokens>,<credits> [--voices] the pass's reading at its first dispatch; --voices keeps Step 11's own
mark --manifest <f> --log-start <key> --token <t> records a review-log start token once, so a rerun starts only what is missing
reader states move forward only; intent is recorded before the subagent is created, its path right after
program [--ledger <f>]
PROGRAM: v<n> sha256=… bytes=…, then lib/capy-review-pass.js as one JSON string line (see the gstack Capy skill)
${exitTableHelp()}`;
const args = process.argv.slice(2);
const flag = (n: string) => { const i = args.indexOf(n); return i >= 0 ? args[i + 1] : undefined; };
const readFile = (f: string | undefined, what: string) => {
if (!f) return undefined;
try { return fs.readFileSync(f, 'utf8'); } catch { throw new BriefError(`cannot read ${what} file ${f}`); }
};
const ROOT = path.resolve(import.meta.dir, '..');
function render(): number {
const role = flag('--role') as BriefRole | undefined;
const out = flag('--out');
if (!role || !BRIEF_ROLES.includes(role) || !out) { process.stderr.write(`gstack-review-dispatch render: needs --role <${BRIEF_ROLES.join('|')}> and --out <dir>\n`); return EXIT.usage; }
const name = flag('--name');
const diffBase = flag('--diff-base');
const checklist = flag('--checklist') ?? (role === 'red-team' ? path.join(ROOT, 'review/specialists/red-team.md') : role === 'targeted' ? path.join(ROOT, 'review/specialists/targeted.md') : role === 'specialist' && name ? path.join(ROOT, 'review/specialists', `${name}.md`) : undefined);
if (checklist && (role === 'specialist' || role === 'red-team' || role === 'targeted') && !fs.existsSync(checklist)) throw new BriefError(`checklist not found: ${checklist}`);
const brief = role === 'targeted' ? readFile(checklist, 'targeted brief') : undefined;
if (role === 'targeted') {
const base = resolveBaseBranch(process.cwd(), flag('--base'));
const mb = mergeBaseWith(base);
const full = diffBase ? spawnSync('git', ['rev-parse', '--verify', '--quiet', `${diffBase}^{commit}`], { encoding: 'utf8', timeout: 30_000 }).stdout?.trim() : undefined;
if (!full || full !== mb) throw new BriefError(`the targeted reader reads the whole diff on every pass: --diff-base must be the merge base with ${base} (${mb ?? 'unresolved'}), got ${diffBase ?? 'none'}`);
if (!flag('--disclosure') && ceilingContext(process.cwd(), base).state === 'active') throw new BriefError(`${base}'s review_exclude_paths is active, so the targeted reader renders in the pass manifest's voices stage (gstack-review-dispatch stage --manifest <f> --stage voices), which carries the exclusion and its disclosure line`);
}
const checklists = flag('--checklists')?.split(',').map(s => s.trim()).filter(Boolean).map(c => (c.includes('/') ? c : path.join(ROOT, 'review/specialists', `${c}.md`)));
for (const c of checklists ?? []) if (!fs.existsSync(c)) throw new BriefError(`checklist not found: ${c}`);
let diff: string | undefined;
const keepItems = parseTail(flag('--keep')).filter(s => s !== '--');
const policyItems = parseTail(flag('--exclude')).filter(s => s.startsWith(':(top,exclude,glob)'));
const resolvable = !!diffBase && git(['rev-parse', '--verify', '--quiet', `${diffBase}^{commit}`]) !== null;
if (role !== 'fix-check' && diffBase && (resolvable || role === 'outside-voice')) {
const over = ceiling('gstack-review-dispatch render', resolveBaseBranch(process.cwd(), flag('--base')), out, [{ reader: readerKey(role, name), exclude: flag('--exclude'), keep: keepItems }], diffBase, undefined);
if (over) { process.stderr.write(over.line + '\n'); return over.exit; }
if (role === 'outside-voice') diff = branchDiff(diffBase, { exclude: flag('--exclude'), keep: keepItems });
}
const slots: Slots = {
name, diff_base: diffBase, exclude: flag('--exclude'), stack: flag('--stack'), test_fw: flag('--test-fw'),
learnings: readFile(flag('--learnings-file'), 'learnings'), checklist, checklists: checklists?.join(','),
findings: readFile(flag('--findings-file'), 'findings'), specialists: flag('--specialists'), diff,
classes: flag('--classes'), brief,
...(flag('--disclosure') ? { disclosure: flag('--disclosure'), policy_exclude: policyItems.map(quote).join(' ') || undefined, keep: keepItems.map(quote).join(' ') || undefined } : {}),
fix_list: readFile(flag('--fix-list'), 'fix list'), hunks: readFile(flag('--hunks'), 'hunks'), tests: readFile(flag('--tests'), 'tests'), callers: readFile(flag('--callers'), 'callers'),
};
const workdir = checkoutRoot();
const tree = checkoutTree(workdir);
if (!tree) throw new BriefError(`cannot read HEAD^{tree} and the toplevel of ${workdir}; a brief names the checkout its reply must prove`);
const text = withWorkspace(renderBrief(role, slots, sectionTexts(ROOT)), workdir);
fs.mkdirSync(out, { recursive: true, mode: 0o700 });
const file = path.join(path.resolve(out), briefFile(role, name));
fs.writeFileSync(file, text, { mode: 0o600 });
const ledger = flag('--ledger') ?? path.join(out, 'review-ledger.jsonl');
const sha = promptHash(text);
const targeted = brief === undefined ? {} : { classes: parseClassList(flag('--classes')!), rules: TARGETED_RULES, brief_sha: targetedBriefSha(checklist), diff_base: diffBase ?? null, ...(diffBase ? targetedRead(process.cwd(), diffBase) : { patch_id: 'none', head: null }) };
appendEvent(ledger, { event: 'rendered', reader: readerKey(role, name), role, name: name ?? null, file, sha256: sha, bytes: Buffer.byteLength(text), workdir, tree, ...targeted, ...(disclosureDigest(flag('--disclosure')) ? { exclude: disclosureDigest(flag('--disclosure')) } : {}) });
process.stdout.write(`BRIEF: reader=${readerKey(role, name)} sha256=${sha} bytes=${Buffer.byteLength(text)} file=${file}\n`);
return EXIT.ok;
}
const quote = (s: string) => `'${s.replace(/'/g, "'\\''")}'`;
const wrongTree = (reader: string, t: TreeCheck) => `${t.moved ? 'COLLECT_TREE_MOVED' : 'COLLECT_WRONG_TREE'}: reader=${reader} reported=${JSON.stringify(t.reported)} expected=${JSON.stringify(t.expected)} (${t.moved ? 'the checkout moved after this brief was rendered' : 'the reply did not review the checkout its brief named'}; nothing merged; restore it with a fresh pass under a new --pass and --out)\n`;
const PROGRAM_FILE = path.join(ROOT, 'lib', 'capy-review-pass.js');
const PROGRAM_VERSION = 1;
const git = (a: string[]) => { const r = spawnSync('git', a, { encoding: 'utf8', timeout: 60_000, maxBuffer: 256 * 1024 * 1024 }); return r.status === 0 ? r.stdout : null; };
const mergeBaseWith = (base: string) => [`origin/${base}`, base].map(ref => git(['merge-base', ref, 'HEAD'])?.trim()).find(Boolean);
const readerLine = (m: Manifest, r: PassReader) => `READER: ${r.reader} stage=${r.stage} state=${r.state} title="${r.title}"${r.sha256 ? ` sha256=${r.sha256} bytes=${r.bytes} chunks=${r.chunks}` : ''}${r.path ? ` path=${r.path}` : ''}`;
/** Each selection is read once per process: the ceiling check and the outside voice's embedded diff share it. */
const selections = new Map<string, ReaderDiff>();
const selectionOf = (base: string, exclude: string | undefined, keep: readonly string[] = []) => {
const key = JSON.stringify([base, exclude ?? '', keep]);
if (!selections.has(key)) selections.set(key, readSelection(process.cwd(), base, parseTail(exclude), keep));
return selections.get(key)!;
};
const branchDiff = (base: string, r?: Pick<PassReader, 'exclude' | 'keep'>) => {
const d = selectionOf(base, r?.exclude, r?.keep);
if (!d.ok) throw new BriefError(`git diff ${base} failed`);
return d.text;
};
/** The ceiling over every reader about to render: the first one over or unreadable stops the step before it writes anything else. */
function ceiling(context: string, base: string, outDir: string, readers: ReadonlyArray<Pick<PassReader, 'reader' | 'exclude' | 'keep' | 'diff_base' | 'prompt_file'> & { diff_base?: string }>, diffBase: string, known: PlanExclude | undefined): { exit: number; line: string } | null {
for (const r of readers) {
if (r.prompt_file) continue;
const at = r.diff_base ?? diffBase;
const d = selectionOf(at, r.exclude, r.keep);
if (!d.ok) return { exit: EXIT.fail, line: unreadableLine(context, r.reader, d, at, base, outDir) };
if (d.bytes > REVIEW_DIFF_MAX_BYTES) return { exit: EXIT.refused, line: tooLargeLine(context, r.reader, d, ceilingContext(process.cwd(), base, known)).line };
}
return null;
}
function pass(): number {
const base = flag('--base'), out = flag('--out'), id = flag('--pass');
if (!base || !out || !id || !/^[a-z0-9-]+$/.test(id)) { process.stderr.write('gstack-review-dispatch pass: needs --base <ref>, --out <dir> and --pass <id> (lowercase letters, digits, dashes)\n'); return EXIT.usage; }
const file = manifestPath(out);
if (fs.existsSync(file)) {
const m = readManifest(file);
if (m.pass !== id) throw new BriefError(`${file} belongs to pass ${m.pass}, not ${id}`);
process.stdout.write([...m.plan_lines, `MANIFEST: file=${file} pass=${m.pass} readers=${m.readers.length} resumed`, ...m.readers.map(r => readerLine(m, r))].join('\n') + '\n');
return EXIT.ok;
}
const planArgs = args.includes('--') ? args.slice(args.indexOf('--') + 1) : [];
if (args.includes('--audit-only')) {
const extrasFile = flag('--extras');
if (!extrasFile) { process.stderr.write('gstack-review-dispatch pass --audit-only: needs --extras (the audit readers, e.g. Step 14.5\'s docs reader)\n'); return EXIT.usage; }
const extras = JSON.parse(readFile(extrasFile, 'extras')!) as Extra[];
const m = buildManifest({ pass: id, out, ledger: flag('--ledger') ?? path.join(out, 'review-ledger.jsonl'), base, diffBase: mergeBaseWith(base) ?? 'HEAD', root: git(['rev-parse', '--show-toplevel'])?.trim() ?? process.cwd(),
checklistRoot: flag('--checklist-root') ?? ROOT, dispatches: [], next: 'audit', planLines: ['PASS: audit-only (no reviewer plan; its extras run as one batch)'], extras });
fs.mkdirSync(m.out, { recursive: true, mode: 0o700 });
const t = sectionTexts(ROOT);
renderStage(m, 'first', t, branchDiff);
renderStage(m, 'specialists', t, branchDiff);
writeManifest(file, m);
process.stdout.write([...m.plan_lines, `MANIFEST: file=${file} pass=${id} readers=${m.readers.length} audit-only`, ...m.readers.map(r => readerLine(m, r))].join('\n') + '\n');
return EXIT.ok;
}
const plan = (json: boolean) => runScriptSync(path.join(ROOT, 'bin', 'gstack-review-plan'), ['--base', base, ...planArgs, ...(json ? ['--json'] : [])], { encoding: 'utf8', timeout: 180_000, maxBuffer: 64 * 1024 * 1024 });
const text = plan(false);
if (text.status !== 0) { process.stdout.write(text.stdout ?? ''); process.stderr.write(text.stderr ?? ''); return EXIT.fail; }
const j = plan(true);
if (j.status !== 0) { process.stderr.write(j.stderr ?? ''); return EXIT.fail; }
const p = JSON.parse(j.stdout) as { next: { step: string }; dispatches: Dispatch[]; targeted?: { classes: string[] }; fix_range?: { base: string } | null; review_exclude?: Record<string, unknown> & { state: string; excluded?: number; kept_files?: unknown; references?: unknown } };
const step = p.next.step;
const fixChecks = step === 'fix-check' ? [] : p.dispatches.filter(d => d.role === 'fix-check');
const planLines = [...text.stdout.trimEnd().split('\n'), ...fixChecks.map(d => `FIX_CHECK: planned effort=${d.effort} (Step 3.5 runs it on its own; not in this manifest)`)];
if (step !== 'full' && step !== 'scoped' && step !== 'fix-check') { process.stdout.write([...planLines, `PASS: none next=${step} (no reviewer pass; follow NEXT)`].join('\n') + '\n'); return EXIT.ok; }
const rangeBase = step === 'scoped' ? git(['rev-parse', '--verify', '--quiet', `${p.fix_range?.base ?? ''}^{commit}`])?.trim() : undefined;
if (step === 'scoped' && !rangeBase) throw new BriefError('a scoped plan names no readable fix range base');
const mergeBase = mergeBaseWith(base);
const diffBase = flag('--diff-base') ?? (planArgs.includes('--adversarial-ran') ? rangeBase : undefined) ?? mergeBase;
if (!diffBase) throw new BriefError(`no merge base between ${base} and HEAD`);
const root = git(['rev-parse', '--show-toplevel'])?.trim() ?? process.cwd();
const extrasFile = flag('--extras');
const extras = extrasFile ? JSON.parse(readFile(extrasFile, 'extras')!) as Extra[] : [];
const m = buildManifest({ pass: id, out, ledger: flag('--ledger') ?? path.join(out, 'review-ledger.jsonl'), base, diffBase, root, checklistRoot: flag('--checklist-root') ?? ROOT,
dispatches: step === 'fix-check' ? p.dispatches : p.dispatches.filter(d => d.role !== 'fix-check'), next: step, planLines, learnings: readFile(flag('--learnings-file'), 'learnings') ?? null, extras,
targetedClasses: p.targeted?.classes, mergeBase, rangeBase: flag('--diff-base') ? undefined : rangeBase,
fixCheck: step === 'fix-check' && (flag('--fix-list') || flag('--hunks') || flag('--tests')) ? { fix_list: flag('--fix-list')!, hunks: flag('--hunks')!, tests: flag('--tests')!, callers: flag('--callers') } : undefined,
...planExclude(p.review_exclude) });
const over = ceiling('gstack-review-dispatch pass', base, m.out, m.readers, m.diff_base, (m.review_exclude as PlanExclude) ?? null);
if (over) { process.stdout.write(planLines.join('\n') + '\n'); process.stderr.write(over.line + '\n'); return over.exit; }
fs.mkdirSync(m.out, { recursive: true, mode: 0o700 });
const t = sectionTexts(ROOT);
renderStage(m, 'first', t, branchDiff);
renderStage(m, 'specialists', t, branchDiff);
writeManifest(file, m);
const count = (s: string) => m.readers.filter(r => r.stage === s).length;
process.stdout.write([...planLines, `MANIFEST: file=${file} pass=${id} readers=${m.readers.length} first=${count('first')} specialists=${count('specialists')} red-team=${count('red-team')} voices=${count('voices')}`, ...m.readers.map(r => readerLine(m, r))].join('\n') + '\n');
return EXIT.ok;
}
/** The manifest's copy of the plan's review_exclude (no file lists) and the brief's disclosure line, when the plan had one. */
function planExclude(x: (Record<string, unknown> & { state: string; excluded?: number }) | undefined): { reviewExclude?: Record<string, unknown>; disclosure?: string } {
if (!x) return {};
const { kept_files: _k, references: _r, ...rest } = x;
return { reviewExclude: rest, ...(x.state === 'active' ? { disclosure: disclosureLine(x as unknown as Parameters<typeof disclosureLine>[0]) } : {}) };
}
function passStep(cmd: string): number {
const file = flag('--manifest');
if (!file) { process.stderr.write(`gstack-review-dispatch ${cmd}: --manifest <file> is required\n`); return EXIT.usage; }
const m = readManifest(file);
if (cmd === 'show') { process.stdout.write(`MANIFEST_JSON: ${JSON.stringify(m)}\n`); return EXIT.ok; }
if (cmd === 'stage') {
const stage = flag('--stage') as Stage | undefined;
if (!stage || !STAGES.includes(stage)) { process.stderr.write(`gstack-review-dispatch stage: --stage ${STAGES.join('|')}\n`); return EXIT.usage; }
const pending = m.readers.filter(r => r.stage === stage && r.state === 'planned');
const over = ceiling('gstack-review-dispatch stage', m.base, m.out, pending, m.diff_base, (m.review_exclude as PlanExclude) ?? null);
if (over) { process.stderr.write(over.line + '\n'); return over.exit; }
const done = renderStage(m, stage, sectionTexts(ROOT), branchDiff);
writeManifest(file, m);
process.stdout.write([`STAGE: ${stage} rendered=${done.length}`, ...done.map(r => readerLine(m, r))].join('\n') + '\n');
return EXIT.ok;
}
if (cmd === 'chunk') {
const r = m.readers.find(x => x.reader === flag('--reader'));
if (!r?.file || !r.sha256) { process.stderr.write(`gstack-review-dispatch chunk: no rendered reader ${flag('--reader')}\n`); return EXIT.usage; }
const text = readFile(r.file, 'brief')!;
if (promptHash(text) !== r.sha256) throw new BriefError(`${r.reader}'s brief ${r.file} changed since it was rendered`);
const index = Number(flag('--index') ?? '0');
process.stdout.write(`BRIEF_CHUNK: reader=${r.reader} index=${index} of=${chunkCount(text)} sha256=${r.sha256}\n${JSON.stringify(chunkOf(text, index))}\n`);
return EXIT.ok;
}
if (cmd === 'mark') {
const logStart = flag('--log-start');
if (logStart) {
const token = flag('--token');
if (!token) { process.stderr.write('gstack-review-dispatch mark: --log-start <key> --token <t>\n'); return EXIT.usage; }
m.log_starts ??= {};
m.log_starts[logStart] ??= token;
writeManifest(file, m);
process.stdout.write(`LOG_START: ${logStart} token=${m.log_starts[logStart]}\n`);
return EXIT.ok;
}
const before = flag('--before');
if (before) {
const [tokens, credits] = before.split(',').map(Number);
if (!Number.isFinite(tokens) || !Number.isFinite(credits)) { process.stderr.write('gstack-review-dispatch mark: --before <tokens>,<credits> [--voices]\n'); return EXIT.usage; }
const key = args.includes('--voices') ? 'before_voices' : 'before';
m[key] ??= { tokens: tokens!, credits: credits! };
writeManifest(file, m);
process.stdout.write(`BEFORE: ${key === 'before_voices' ? 'stage=voices ' : ''}tokens=${m[key]!.tokens} credits=${m[key]!.credits}\n`);
return EXIT.ok;
}
const audit = m.readers.find(x => x.reader === flag('--reader'));
if (flag('--state') === 'collected' && audit?.prompt_file && audit.tree !== undefined) {
if (!flag('--output')) { process.stderr.write(`gstack-review-dispatch mark: ${audit.reader} is collected with --output <its reply>, which must prove the checkout it reviewed\n`); return EXIT.usage; }
const tree = checkReviewedTree(readFile(flag('--output'), 'reader output')!, audit.tree);
if (!tree.ok) {
markReader(m, audit.reader, 'failed', { output: flag('--output'), error: `reviewed another tree: ${tree.reported}` });
writeManifest(file, m);
process.stdout.write(wrongTree(audit.reader, tree));
return EXIT.fail;
}
}
const r = markReader(m, flag('--reader') ?? '', flag('--state') as ReaderState, { path: flag('--path'), output: flag('--output'), error: flag('--error') });
writeManifest(file, m);
process.stdout.write(readerLine(m, r) + '\n');
return EXIT.ok;
}
return EXIT.usage;
}
function program(): number {
const text = readFile(PROGRAM_FILE, 'pass program')!;
const sha = promptHash(text);
const ledger = flag('--ledger');
if (ledger) appendEvent(ledger, { event: 'program', version: PROGRAM_VERSION, sha256: sha });
process.stdout.write(`PROGRAM: v${PROGRAM_VERSION} sha256=${sha} bytes=${Buffer.byteLength(text)}\n${JSON.stringify(text)}\n`);
return EXIT.ok;
}
/**
* The receipt's review_targeted record from the newest targeted dispatch: done only when its brief was sent verbatim, its output
* collected, and it was rendered on a committed diff (uncommitted never proves what was read). `head` names the commit it read:
* a later commit does not undo the read, and gstack-ship-receipt write binds the record only while that commit's product patch is
* the receipt's (GST-986: Step 11 fixes after the read printed status=failed findings=0 for a completed reader).
*/
function targetedRecord(ledger: string, rows: VerifyRow[]): { classes: string[]; rules: string; brief_sha: string; status: 'done' | 'failed'; findings: number; raised_by: string; head: string | null } | null {
const events = readLedger(ledger);
const render = events.filter(e => e.event === 'rendered' && e.reader === 'targeted').at(-1);
if (!render) return null;
const label = rows.filter(r => r.kind === 'BRIEF' && r.reader.split('@')[0] === 'targeted').at(-1)?.reader;
const brief = rows.filter(r => r.kind === 'BRIEF' && r.reader === label).at(-1);
const output = rows.filter(r => r.kind === 'OUTPUT' && r.reader === label).at(-1);
const head = typeof render.head === 'string' && /^[0-9a-f]{40,64}$/.test(render.head) ? render.head : null;
const committed = typeof render.patch_id === 'string' && !['uncommitted', 'none'].includes(render.patch_id) && head !== null;
const done = brief?.status === 'MATCH' && output?.status === 'MATCH' && committed;
const ids = events.filter(e => e.event === 'output' && e.reader === 'targeted').at(-1)?.ids;
return { classes: (render.classes as string[]) ?? [], rules: String(render.rules), brief_sha: String(render.brief_sha), status: done ? 'done' : 'failed', findings: Array.isArray(ids) ? ids.length : 0, raised_by: 'targeted', head };
}
/**
* The selection the verified briefs read under review_exclude_paths: the digest every reader's newest brief names (fix-check reads
* named hunks, not the selection); null when no brief names one, so a repository without the key verifies as before.
*/
function excludeRecord(ledger: string): { digest: string } | { mixed: string[] } | null {
const newest = new Map<string, Record<string, unknown>>();
for (const e of readLedger(ledger)) if (e.event === 'rendered' && e.role && e.role !== 'fix-check') newest.set(String(e.reader), e);
const named = [...newest.values()].map(e => (typeof e.exclude === 'string' ? e.exclude : 'none'));
if (!named.some(d => d !== 'none')) return null;
const digests = [...new Set(named)];
return digests.length === 1 ? { digest: digests[0]! } : { mixed: digests };
}
function main(): number {
const cmd = args[0];
if (!cmd || cmd === '--help' || cmd === '-h') { process.stdout.write(HELP + '\n'); return cmd ? EXIT.ok : EXIT.usage; }
if (cmd === 'render') return render();
if (cmd === 'pass') return pass();
if (cmd === 'program') return program();
if (['show', 'stage', 'chunk', 'mark'].includes(cmd)) return passStep(cmd);
const ledger = flag('--ledger');
if (!ledger) { process.stderr.write(`gstack-review-dispatch ${cmd}: --ledger <file> is required\n`); return EXIT.usage; }
const reader = flag('--role') ? readerKey(flag('--role')!, flag('--name')) : '';
if (cmd === 'sent') {
const sent = readFile(flag('--sent'), 'sent prompt');
if (!reader || sent === undefined) { process.stderr.write('gstack-review-dispatch sent: needs --role and --sent <file>\n'); return EXIT.usage; }
const r = recordSent(ledger, reader, sent);
process.stdout.write(r.ok ? `BRIEF_SENT: reader=${reader} sha256=${r.sent} match\n`
: `BRIEF_MISMATCH: reader=${reader} rendered=${r.rendered ?? 'none'} sent=${r.sent} (dispatch the rendered file unchanged; this reader's review does not count)\n`);
return r.ok ? EXIT.ok : EXIT.fail;
}
if (cmd === 'collect') {
const outFile = flag('--output');
const output = readFile(outFile, 'reader output');
const merged = flag('--merged');
if (!reader || output === undefined || !merged) { process.stderr.write('gstack-review-dispatch collect: needs --role, --output <file> and --merged <file>\n'); return EXIT.usage; }
const unavailable = flag('--unavailable');
if (unavailable !== undefined && !mayBeUnavailable(reader)) { process.stderr.write(`gstack-review-dispatch collect: --unavailable is for the outside voice only; ${reader}'s missing coverage leaves the review incomplete, never clean\n`); return EXIT.usage; }
if (unavailable !== undefined && !unavailable.trim()) { process.stderr.write('gstack-review-dispatch collect: --unavailable needs a reason\n'); return EXIT.usage; }
if (unavailable !== undefined && parseFindings(reader, output).length) { process.stderr.write(`gstack-review-dispatch collect: ${reader}'s output holds findings; collect it without --unavailable so none is lost\n`); return EXIT.usage; }
const rendered = readLedger(ledger).filter(e => e.event === 'rendered' && e.reader === reader).at(-1);
const tree = unavailable === undefined && rendered && 'tree' in rendered ? checkReviewedTree(output, typeof rendered.tree === 'string' ? rendered.tree : null) : undefined;
if (tree && !tree.ok && mayBeUnavailable(reader) && !parseFindings(reader, output).length) {
const why = `reviewed another tree: reported ${tree.reported}, expected ${tree.expected}`;
const r = collect(ledger, reader, output, merged, path.resolve(outFile!), why);
process.stdout.write(`COLLECT_UNAVAILABLE: reader=${reader} sha256=${r.sha} reason=${JSON.stringify(why)} (missing outside coverage: unavailable, never clean)\n`);
return EXIT.ok;
}
const mf = flag('--manifest');
let plan: ReturnType<typeof readManifest> | undefined;
try { plan = mf ? readManifest(mf) : undefined; } catch (e) { process.stderr.write(`gstack-review-dispatch collect: ${(e as Error).message}; native FIXABLE collects as CRITICAL\n`); }
const r = collect(ledger, reader, output, merged, path.resolve(outFile!), unavailable, tree, fixableRaises(plan && path.resolve(plan.ledger) === path.resolve(ledger) ? plan.plan_lines : undefined));
if (tree && !tree.ok) {
if (mf && plan) { markReader(plan, reader, 'failed', { output: outFile, error: `reviewed another tree: ${tree.reported}` }); writeManifest(mf, plan); }
process.stdout.write(wrongTree(reader, tree));
return EXIT.fail;
}
if (unavailable !== undefined) { process.stdout.write(`COLLECT_UNAVAILABLE: reader=${reader} sha256=${r.sha} reason=${JSON.stringify(unavailable)} (missing outside coverage: unavailable, never clean)\n`); return EXIT.ok; }
if (!r.review) {
process.stdout.write(`COLLECT_NOT_REVIEWED: reader=${reader} findings=0 sha256=${r.sha} (no finding and no ${cleanMarkers(reader).map(([m]) => m).join(' or ')} line: a refusal, an empty reply or a reader that never saw the diff is not a review; verify reports this brief NOT_COLLECTED)\n`);
return EXIT.fail;
}
process.stdout.write(`COLLECT: reader=${reader} findings=${r.lines.length} sha256=${r.sha} merged=${merged}\n`);
return EXIT.ok;
}
if (cmd === 'judge') {
const merged = flag('--merged');
const judged = flag('--judged');
if (!merged || !judged) { process.stderr.write('gstack-review-dispatch judge: needs --merged <file> and --judged <file>\n'); return EXIT.usage; }
const r = recordJudgment(ledger, readJsonl<MergedLine>(merged), readJsonl<JudgedLine>(judged), judged, merged);
process.stdout.write(r.ok ? `JUDGMENT: ok added=${r.added.length} promoted=${r.promoted.length} folded=${r.folded.length}\n`
: `JUDGMENT_REJECTED: dropped=${JSON.stringify(r.dropped)} downgraded=${JSON.stringify(r.downgraded)} unexplained=${JSON.stringify(r.unexplained)} invalid=${JSON.stringify(r.invalid)} (lead judgment may add or promote a finding, never drop or downgrade one)\n`);
return r.ok ? EXIT.ok : EXIT.fail;
}
if (cmd === 'verify') {
if (flag('--targeted-out')) fs.rmSync(flag('--targeted-out')!, { force: true });
const v = verify(ledger);
for (const r of v.rows) process.stdout.write(`${r.kind} ${r.reader} ${r.status} ${r.detail}\n`);
if (!v.briefs) { process.stdout.write('VERIFY: no brief records (this run\'s ledger kept no prompts; dispatched-vs-rendered cannot be checked)\n'); return EXIT.refused; }
const record = targetedRecord(ledger, v.rows);
if (record) {
process.stdout.write(`TARGETED_RECORD: classes=${record.classes.join(',')} status=${record.status} findings=${record.findings} brief=${record.brief_sha.slice(0, 12)} rules=${record.rules} read=${record.head?.slice(0, 12) ?? 'none'}\n`);
if (flag('--targeted-out')) fs.writeFileSync(flag('--targeted-out')!, JSON.stringify(record) + '\n');
}
const sel = excludeRecord(ledger);
if (sel && 'digest' in sel) process.stdout.write(`REVIEW_EXCLUDE_RECORD: digest=${sel.digest} (gstack-ship-receipt write --review-exclude ${sel.digest})\n`);
if (sel && 'mixed' in sel) process.stdout.write(`REVIEW_EXCLUDE_RECORD: mixed digests=${sel.mixed.join(',')} (readers read different review_exclude_paths selections; rerun the review so every reader reads HEAD's)\n`);
const clean = v.clean && !(sel && 'mixed' in sel);
process.stdout.write(`VERIFY: ${clean ? 'clean' : 'dirty'} briefs=${v.briefs} outputs=${v.rows.filter(r => r.kind === 'OUTPUT').length} voided=${v.voided}${v.unavailable ? ` unavailable=${v.unavailable}` : ''}\n`);
return clean ? EXIT.ok : EXIT.fail;
}
process.stderr.write(`gstack-review-dispatch: unknown command ${cmd}\n${HELP}\n`);
return EXIT.usage;
}
try { process.exitCode = main(); } catch (e) {
if (e instanceof BriefError) { process.stderr.write(`BRIEF_RENDER_FAILED: ${e.message}\n`); process.exitCode = EXIT.fail; } else throw e;
}