mirror of
https://github.com/garrytan/gstack.git
synced 2026-10-31 14:06:50 +01:00
* fix(flaky): repair the five paid gate detectors and the judged review/plan-review prose (GSTA-128)
Daily flaky pass over the 2026-10-27 Open ledger entries, paid cases first.
- ship-docsync-store (40458489644, 40477638211): docsync-observer admitted only
`git branch --show-current`; both captured parents' fourth call was a read ending
in `git branch -a`. Operand-free branch listings are now part of the read grammar.
- ship-docsync-completion (40465691803): the parent ran two /document-release
dispatches and wrote the accepted second section into the report while the case
compared the first. The contract now follows the last foreground dispatch.
- ship-local-hook-preservation (40467320097): the red reply delegated the guard to
the repo owner ("have someone wire the guard in by hand"); toUser now reads a
determiner-led phrasal object and owner/maintainer/someone + themselves.
- plan-design-finding-floor (x2): the pending menu asked to cover all 7 dimensions
without the word "focus"; the picker now reads that question shape.
- Judge cases: plan-review headers no longer offer a "(or unverified)" branch the
four-mode preflight can never print; /review's Scope Check is emitted in Step 3
after the full diff read; the small-diff rule and the specialists record agree on
State Machines; Step 5.8.2 names which post-fix rerun rule governs. Nearby prose
tightened so review, ship and plan-eng-review stay at their parity caps; shrunk
size pins lowered per the guard's own instruction.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(plan-review): expect the renamed routing row ('Any other mode') in the Eng provider case
The GSTA-128 prose repair renamed the plan-review routing row from 'other preflight mode, including harness mismatch' to 'Any other mode (not_installed, under_current_harness)'; test/plan-review-cases.test.ts:657 still asserted the old text and failed quick-bun-default on #3516 (run 40524518937).
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(eval-select): register the three new free fixtures in FREE_FIXTURES
eval: select reported docsync-branch-listing-public.json, docsync-two-attempts-public.json and design-floor-focus-cover-all.json as unknown dependencies (needs touchfile entry) and fell back to the full gate on that alone. Each is read only by a free test, so they belong in FREE_FIXTURES beside their siblings.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(review): pre-landing review fixes for the paid flaky-case repairs
Pass 1 of /ship's review loop on #3516 (core, four specialists, native and
outside adversarial, Red Team). Fixed in the diff:
- test/skill-e2e-ship-docsync.test.ts: the two-attempt retained-edit filter
dropped a path from changedPaths even when the accepted contract's
files_updated claimed it, so an honest re-audit that re-edits the same
document read as 'unreported edits'. acceptedChangedPaths() in
test/helpers/docsync-contract.ts keeps a retained path the accepted
contract claims; the free replay proves the old filter red on that shape.
- test/helpers/ship-hook-actor.ts: the owner+reflexive manual-integration arm
credited a denial ('so the owner does not have to do it themselves') or a
first-person claim. ownersOwnHand() requires a hook noun, rejects a
negation before the reflexive and a first-person subject; probes added.
- scripts/resolvers/plan-gates.ts + review/sections/manifest.json: the
no-plan path still said 'Emit Step 1.5's Scope Check once' and the STOP
trigger 'finishing Step 1.5's Scope Check', the circular prerequisite gate
40454750574 flagged, on the path most reviews take. Both now point at
Step 3 ('Step 3 emits the Scope Check once without plan fields';
'Before leaving Step 1.5').
- review/SKILL.md.tmpl: Step 3 item 5 emits the Scope Check on the first
pass only (a fix-range repeat pass reads a partial diff by construction);
two prose tightenings keep the review skeleton under its pins, which are
lowered by 3 on the eight pinned hosts.
- test/helpers/docsync-interface.ts: the declared branch-listing class now
enumerates the exact flag set DOCS_BRANCH_LIST_FLAGS accepts.
Coverage audit (Step 7) tests: plan-review and doc-review run headers admit
only the CODEX_MODE values their preflight prints
(test/outside-voice-preflight.test.ts); the final Scope Check is emitted
once in Step 3 and every owner names that point, no-plan path and STOP
trigger included (test/review-workflow-clarity.test.ts).
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(ship-hook-actor): read the owner's denial in the owner's own clause
Review pass 2 on #3516 (State Machines, with the same site flagged by every
other reviewer): the pass-1 negation guard in ownersOwnHand() scanned the
whole sentence prefix before the reflexive, so an honest request after a
negated subordinate clause ("Since the installer did not run, the repo owner
needs to add the guard to the existing hooks themselves") was refused, a
recall regression against ee73419 that would red the paid
ship-local-hook-preservation case. The guard now reads the clause from the
last owner noun to the reflexive, and its contraction alternative matches
"doesn't"/"won't" (the pass-1 form sat behind a word boundary and never
matched). Three credited and two refused probes added; the credited ones
fail on the pass-1 helper.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs(changelog): [Unreleased] entry for the GSTA-128 paid flaky-case repairs
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs(changelog): count the four repaired gate detectors, not five
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(parity): re-pin ship maxSizeRatio 1.7524 -> 1.7525 on the main-merged tree
The review-army small-diff clause (+5 union bytes) lands on a main that
sat 4 bytes under the ship cap after #3515 and #3517: 328,932 -> 328,937
/ 187,706 = 1.7524 both ways at four places, so the pin moves one in the
last place. GStack Minder's rule 19 grant for #3516 after train 26 free
run 40556676971 failed test/parity-suite.test.ts. Before/after and the
reason are in the CHANGELOG entry.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* RESTAMP: 1.91.280.0 -> 1.91.281.0 (stamped; queue_mode=stamp-at-merge base=origin/main@703b0049ebbe policy=base origin/main@703b0049ebbe:.gstack/ship-policy.json)
ship, next in queue at 1.91.281.0
STAMP_VERSION: 1.91.281.0
claims: ignored (stamp-at-merge)
stage version: done (wrote 1.91.281.0)
stage release_tool: done (bun scripts/gen-agents-digest.ts)
stage changelog: done (Unreleased -> 1.91.281.0)
stage stamp_paths: skipped (no tentative mention newer than the fork version 1.91.276.0 and none of base 1.91.280.0 on a line this branch added)
stage mirror: skipped (no mirror in policy)
stage apply: done (4 file(s))
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 5d8184d56..4363f3d7b 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,6 +1,6 @@
# Changelog
-## [Unreleased]
+## [1.91.281.0] - 2026-10-27
**Four paid gate detectors stop judging honest transcripts red, and /review's Scope Check has one emission point.** The 2026-10-27 flaky pass (GSTA-128) read each red transcript and repaired the detector or the prose it judged, never the threshold.
diff --git a/VERSION b/VERSION
index 3d95d3946..12d5f1cc7 100644
--- a/VERSION
+++ b/VERSION
@@ -1 +1 @@
-1.91.280.0
+1.91.281.0
diff --git a/agents-digest/gstack-AGENTS.md b/agents-digest/gstack-AGENTS.md
index 15ac5e105..2b8121978 100644
--- a/agents-digest/gstack-AGENTS.md
+++ b/agents-digest/gstack-AGENTS.md
@@ -1,4 +1,4 @@
-# gstack digest v1.91.280.0 — regenerate/re-copy after upgrading gstack
+# gstack digest v1.91.281.0 — regenerate/re-copy after upgrading gstack
Behavioral rules from gstack (https://github.com/garrytan/gstack), compressed
for agent hosts without a full skill install. The full skills add workflows,
diff --git a/node_modules b/node_modules
new file mode 120000
index 000000000..858ae29ce
--- /dev/null
+++ b/node_modules
@@ -0,0 +1 @@
+/workspace/gstack/node_modules
\ No newline at end of file
diff --git a/package.json b/package.json
index d0c1012d7..4a7a5d6cb 100644
--- a/package.json
+++ b/package.json
@@ -1,6 +1,6 @@
{
"name": "gstack",
- "version": "1.91.280",
+ "version": "1.91.281",
"description": "Garry's Stack — Claude Code skills + fast headless browser. One repo, one install, entire AI engineering workflow.",
"license": "MIT",
"type": "module",
FILES: CHANGELOG.md VERSION agents-digest/gstack-AGENTS.md package.json
MERGE_CONDITION: sha=d0ed2d938ef4c98352a53ea27ce3596824068568
next: NEW_VERSION=1.91.281.0; commit and push only the stamp diff above (FILES), with no edit of your own: the train's verify accepts the CHANGELOG only as the base's plus this PR's entry re-headed; merge with the expected head d0ed2d938e and recompute on a stale queue.
GSTACK_RESULT: skill=restamp status=complete run=/workspace/gstack/.gstack/tmp/restamp-journal.json
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>
91 lines
5.0 KiB
TypeScript
91 lines
5.0 KiB
TypeScript
import * as path from 'node:path';
|
|
|
|
export interface DocsCompletion {
|
|
schema_version: 1;
|
|
audit_id: string;
|
|
status: 'updated' | 'current' | 'blocked';
|
|
files_updated: string[];
|
|
files_reviewed: string[];
|
|
documentation_section: string;
|
|
blockers: string[];
|
|
decisions: string[];
|
|
}
|
|
|
|
const keys = ['schema_version', 'audit_id', 'status', 'files_updated', 'files_reviewed', 'documentation_section', 'blockers', 'decisions'];
|
|
|
|
export function parseDocsCompletion(output: string, auditId: string): DocsCompletion {
|
|
const result = JSON.parse(output.trimEnd().split('\n').at(-1)!);
|
|
if (!result || Array.isArray(result) || typeof result !== 'object' ||
|
|
Object.keys(result).sort().join() !== [...keys].sort().join()) throw new Error('completion fields');
|
|
if (result.schema_version !== 1 || result.audit_id !== auditId) throw new Error('completion identity');
|
|
if (!['updated', 'current', 'blocked'].includes(result.status)) throw new Error('completion status');
|
|
for (const field of ['files_updated', 'files_reviewed', 'blockers', 'decisions']) {
|
|
if (!Array.isArray(result[field]) || result[field].some((v: unknown) => typeof v !== 'string' || !v.trim())) {
|
|
throw new Error(`completion ${field}`);
|
|
}
|
|
}
|
|
if (typeof result.documentation_section !== 'string' || !result.documentation_section.trim()) throw new Error('completion markdown');
|
|
for (const field of ['files_updated', 'files_reviewed']) {
|
|
const paths: string[] = result[field];
|
|
if (new Set(paths).size !== paths.length || paths.some(p => path.posix.isAbsolute(p) || p.includes('\\') ||
|
|
p.split('/').some(part => !part || part === '.' || part === '..') || /[*?\[\]]/.test(p))) throw new Error('completion paths');
|
|
}
|
|
if (result.status === 'blocked' ? result.blockers.length === 0 : result.blockers.length !== 0) throw new Error('completion blockers');
|
|
if (result.status === 'current' && result.files_updated.length !== 0 ||
|
|
result.status === 'updated' && result.files_updated.length === 0) throw new Error('completion edits');
|
|
return result;
|
|
}
|
|
|
|
export function vetDocsCompletion(result: DocsCompletion, evidence: {
|
|
settled: boolean;
|
|
markerSeen: boolean;
|
|
headUnchanged: boolean;
|
|
indexUnchanged: boolean;
|
|
candidateUnchanged: boolean;
|
|
readOnly: boolean;
|
|
changedPaths: string[];
|
|
allowedDocs: string[];
|
|
}): void {
|
|
if (!evidence.settled || !evidence.markerSeen) throw new Error('unsettled or unmarked child');
|
|
if (!evidence.headUnchanged || !evidence.indexUnchanged) throw new Error('Git ownership violation');
|
|
if (!evidence.candidateUnchanged) throw new Error('stale candidate');
|
|
if (evidence.readOnly && evidence.changedPaths.length) throw new Error('read-only mutation');
|
|
if ([...evidence.changedPaths].sort().join('\0') !== [...result.files_updated].sort().join('\0')) throw new Error('unreported edits');
|
|
const forbidden = /(?:^|\/)(?:VERSION|CHANGELOG(?:\.[^/]*)?|TODOS(?:\.[^/]*)?|package(?:-lock)?\.json|[^/]*lock[^/]*|manifest\.json)$/i;
|
|
if (evidence.changedPaths.some(p => forbidden.test(p) || !evidence.allowedDocs.includes(p))) throw new Error('non-doc mutation');
|
|
}
|
|
|
|
/**
|
|
* The changed paths the accepted (last) attempt answers for. A rejected earlier attempt's reported edit stays in the tree
|
|
* (Blocked recovery preserves partial content), so it is not the accepted attempt's unreported edit; the accepted attempt
|
|
* answers for it again only when its own `files_updated` claims it (an honest re-audit that re-edited the same document).
|
|
*/
|
|
export function acceptedChangedPaths(changed: string[], contracts: DocsCompletion[]): string[] {
|
|
const accepted = contracts.at(-1)!;
|
|
const retained = contracts.slice(0, -1).flatMap(earlier => earlier.files_updated);
|
|
return changed.filter(p => !retained.includes(p) || accepted.files_updated.includes(p));
|
|
}
|
|
|
|
export function extractDocsDispatch(section: string): string {
|
|
const begin = section.indexOf('**Subagent prompt:**');
|
|
const end = section.indexOf('**Parent processing:**');
|
|
if (begin < 0 || end <= begin) throw new Error('documentation dispatch markers moved');
|
|
return section.slice(begin + '**Subagent prompt:**'.length, end)
|
|
.split('\n').map(line => line.replace(/^> ?/, '')).join('\n').trim();
|
|
}
|
|
|
|
export function docsDispatchIndex(calls: Array<{ tool: string; input: unknown }>): number {
|
|
return docsDispatchIndices(calls)[0] ?? -1;
|
|
}
|
|
|
|
/**
|
|
* Every /document-release dispatch, in order. The audit gate's attempt budget is an initial audit plus one repair/re-audit, so a
|
|
* run has one or two; the parent's accepted contract is the last (gate 40465691803: the parent rejected attempt 1 for a false
|
|
* claim in its section, re-audited over its retained edit, and reported attempt 2's section).
|
|
*/
|
|
export function docsDispatchIndices(calls: Array<{ tool: string; input: unknown }>): number[] {
|
|
return calls.flatMap((call, index) => ['Agent', 'Task'].includes(call.tool) &&
|
|
/document-release\/SKILL\.md|executing the \/document-release workflow/i.test(JSON.stringify(call.input)) &&
|
|
!/Parent processing:|## Step 19: Create PR\/MR/.test(JSON.stringify(call.input)) ? [index] : []);
|
|
}
|