mirror of
https://github.com/garrytan/gstack.git
synced 2026-11-10 18:50:18 +01:00
Merge origin/main into feat/design-lint; stamp 1.91.251.0
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
This commit is contained in:
garrytanandcapy-ai[bot] committed
commit
4b4cadcb9c
289 files changed
+16151
-2303
No files matched your search
@@ -155,7 +155,7 @@ export const CARVE_GUARDS: Record<string, CarveGuard> = {
|
||||
},
|
||||
behavioral: 'external',
|
||||
externalTest: 'test/skill-e2e-ship-section-loading.test.ts',
|
||||
maxSkeletonBytes: 81_000, // + v2.0 {{ASIDE_RESEARCH}} (Aside first, WebSearch fallback); measured 78_275. + gate integrity (HONEST_WORK_GATE_INTEGRITY W3): Step 16 stage 4 ZERO-RUN/unknown receipt rows, stage 5 honesty inventory, Step 17 open-gate ready-PR gate; measured 80,540 (2026-10-10).
|
||||
maxSkeletonBytes: 81_600, // + v2.0 {{ASIDE_RESEARCH}} (Aside first, WebSearch fallback); measured 78_275. + gate integrity (HONEST_WORK_GATE_INTEGRITY W3): Step 16 stage 4 ZERO-RUN/unknown receipt rows, stage 5 honesty inventory, Step 17 open-gate ready-PR gate; measured 80,540 (2026-10-10). + rule 22 / GBRA-108 (2026-10-25): Step 22's terminal line (gstack-ship-receipt result, the GSTACK_RESULT line a parent greps) and Step 18's unattended routing (an open PR at HEAD gets its body updated, else handoff), offset in part by tightening Steps 14, 16, 18 and 20 prose after the 2026-10-14 tightening left 2 bytes of headroom; measured 81,535.
|
||||
minUnionBytes: 181_000, // token-reduction Phases 1-2 (v1.69.x branch); measured union 201,464
|
||||
mustContain: ['VERSION', 'CHANGELOG', 'review', 'merge', 'PR'],
|
||||
// v1.58.5.0: pre-push-guard install (#2077) stacks on the shared first-run-guidance preamble.
|
||||
@@ -168,7 +168,7 @@ export const CARVE_GUARDS: Record<string, CarveGuard> = {
|
||||
// wave's headline capability) grows the union to 1.195x. Deliberate:
|
||||
// the section is on-demand (loads only for Apple store targets), so
|
||||
// per-invocation cost for non-iOS ships is one manifest line.
|
||||
maxSizeRatio: 1.6690, // Shared advisory identity/dedup + critical-severity validation: 248,065 union bytes / 187,706 baseline = 1.3216 (2026-09-17). + test value bar in the lazy Step 7 section (value cards, weak paths, gate table, base control, machine checks; ~13.6KB): measured 1.396 (2026-09-29). + W1 guarded state-root resolution (`eval gstack-paths; : "${GSTACK_STATE_ROOT:?…}"`) in the Context Recovery preamble, the eureka log and each state-writing bash block; measured 1.401 (2026-09-30). + the shared QA review step's plan-check timing rule (plan checks and their revalidation run on --timeout-ms after smoke expiry); measured 1.4022 (2026-09-30). + the shared TEST_BOOTSTRAP owned-change undo rules (s03 H1-H3, M1) and the value-bar coverage wording (s03 M2/M3); measured 1.4044 (2026-10-02). + severe fix wave ship-review lane: G1 NO_VERSION dispatch, title and CHANGELOG arms (versionless repos ship without inventing a version), F1 parent-side plan binding before the audit dispatch (binding, docs/designs candidates, exact not-run line) and D3's data-not-instructions line; +2,126 union bytes, measured 1.4135 (2026-10-03). + INV-1 consumer lines (outside review `unverified`/`unavailable` is missing coverage in the readiness note and PR body); measured 1.4148 (2026-10-03). + v1.91.19.0 severe fix wave: verdict-form outside-review callers with sandbox preflight and first-use notice (INV-1/B1/Q2), P0/P1 gate and unverified wording, bound-plan discovery (F1), visible LEARNINGS failures (B5), carved external pointers; measured 267,752 / 187,706 = 1.4264 (2026-10-03). + v1.91.18.0 (#3023) merged into the v1.91.19.0 wave; measured 267,874 / 187,706 = 1.4271 (2026-10-04). + Oct 6 fix wave: quota_exhausted preflight branch (#3051) and quoted-heredoc issue template (#3046); measured 268,199 / 187,706 = 1.4288 (2026-10-06). + Step 10's inline no-PR check before the Greptile dispatch (#3020); measured 268,655 / 187,706 = 1.4313 (2026-10-06). + Oct 6 fix wave A3/CEO-12: free text reaches commands only through agent-written mktemp files (mktemp block, write rule, path rebuild and refusal at each posting, prompt and brief site); measured 275,422 / 187,706 = 1.4673 (2026-10-06). Combined Oct 6 wave head (B free-text files + D measure loop + A rework): measured 280,363 / 187,706 = 1.4936 (2026-10-06). + gate-once push rule (no second paid gate after a CI push); measured 280,573 / 187,706 = 1.4947 (2026-10-06). + the measurement bar's decision step (exit-code branches for MEETS, MEETS-qualified, needs-classify with the qualifying and fix-round classes, EXTEND once; the measure prose was tightened to offset most of it); measured 281,058 / 187,706 = 1.4973 (2026-10-06). + Oct 7 wave B3: the Codex probe runs as a command (select-model capture lines, check-sandbox/probe-model/run-with-timeout subcommands) instead of being sourced; measured 281,438 / 187,706 = 1.4994 (2026-10-07). + Oct 7 wave CEO-28/DX-11: review prompts ask for a severity per finding and design proposals use the proposal gate; measured 281,556 / 187,706 = 1.5000 (2026-10-07). + Oct 7 wave B4: /ship publishes through gstack-post (title prepared in a file in the pr-body section, compose block plus gstack-post exit-code branches replacing the two scans); measured 281,894 / 187,706 = 1.5018 (2026-10-07). + B2 early Greptile PR (lazy Step 6.5 section: detect, public-repo consent, push, provisional title file, open; Step 10's bounded wait; the stop-leaves-the-draft rule); measured 286,626 / 187,706 = 1.5270 (2026-10-07). B3, the classifier, B4 and B2 merged: measured 287,128 / 187,706 = 1.5297 (2026-10-07). + Oct 7 wave guard (CEO-20): conditional `run_in_background` request plus the background-run recovery at each foreground dispatch site; measured 281,370 / 187,706 = 1.4990 (2026-10-07). Merged with the guard area: measured 287,440 / 187,706 = 1.5313 (2026-10-07). + Oct 8 wave: the defensive-security framing and fixture summary mode reach the security specialist and the Red Team (stated once in the dispatch, referenced by the Red Team); measured 288,783 / 187,706 = 1.5385 (2026-10-08). + gate integrity (HONEST_WORK_GATE_INTEGRITY W3): the shared GATE_SCAN_BLOCK in the core checklist (2.5) and after Step 7's child, the four-option gate question and record fields in 9.4, tests_ran states in Step 5, Gate edits and per-lane counts in the PR body with draft-while-open; measured 300,143 / 187,706 = 1.5990 (2026-10-10). + Honest Work wave merged (W2/W3 gate integrity in review/ship, W4 kernel + DONE line in every tier-2+ skill, W5/W7 in spec/ship): re-measured on the integrated tree (2026-10-10). + Oct 10 multi-agent wave PR E2 (ship/sections/handoff.md: the no-PR automation handoff, with its Section-index row and STOP pointer in the skeleton), offset by tightening Steps 1–3, 12, 14–17 and 20–21 prose so the skeleton stays under 81,000 bytes (80,997); C-pregate landed 1,123 union bytes in tests.md in between; measured 308,619 / 187,706 = 1.6442 on the integra
Line truncated
|
||||
maxSizeRatio: 1.6740, // Shared advisory identity/dedup + critical-severity validation: 248,065 union bytes / 187,706 baseline = 1.3216 (2026-09-17). + test value bar in the lazy Step 7 section (value cards, weak paths, gate table, base control, machine checks; ~13.6KB): measured 1.396 (2026-09-29). + W1 guarded state-root resolution (`eval gstack-paths; : "${GSTACK_STATE_ROOT:?…}"`) in the Context Recovery preamble, the eureka log and each state-writing bash block; measured 1.401 (2026-09-30). + the shared QA review step's plan-check timing rule (plan checks and their revalidation run on --timeout-ms after smoke expiry); measured 1.4022 (2026-09-30). + the shared TEST_BOOTSTRAP owned-change undo rules (s03 H1-H3, M1) and the value-bar coverage wording (s03 M2/M3); measured 1.4044 (2026-10-02). + severe fix wave ship-review lane: G1 NO_VERSION dispatch, title and CHANGELOG arms (versionless repos ship without inventing a version), F1 parent-side plan binding before the audit dispatch (binding, docs/designs candidates, exact not-run line) and D3's data-not-instructions line; +2,126 union bytes, measured 1.4135 (2026-10-03). + INV-1 consumer lines (outside review `unverified`/`unavailable` is missing coverage in the readiness note and PR body); measured 1.4148 (2026-10-03). + v1.91.19.0 severe fix wave: verdict-form outside-review callers with sandbox preflight and first-use notice (INV-1/B1/Q2), P0/P1 gate and unverified wording, bound-plan discovery (F1), visible LEARNINGS failures (B5), carved external pointers; measured 267,752 / 187,706 = 1.4264 (2026-10-03). + v1.91.18.0 (#3023) merged into the v1.91.19.0 wave; measured 267,874 / 187,706 = 1.4271 (2026-10-04). + Oct 6 fix wave: quota_exhausted preflight branch (#3051) and quoted-heredoc issue template (#3046); measured 268,199 / 187,706 = 1.4288 (2026-10-06). + Step 10's inline no-PR check before the Greptile dispatch (#3020); measured 268,655 / 187,706 = 1.4313 (2026-10-06). + Oct 6 fix wave A3/CEO-12: free text reaches commands only through agent-written mktemp files (mktemp block, write rule, path rebuild and refusal at each posting, prompt and brief site); measured 275,422 / 187,706 = 1.4673 (2026-10-06). Combined Oct 6 wave head (B free-text files + D measure loop + A rework): measured 280,363 / 187,706 = 1.4936 (2026-10-06). + gate-once push rule (no second paid gate after a CI push); measured 280,573 / 187,706 = 1.4947 (2026-10-06). + the measurement bar's decision step (exit-code branches for MEETS, MEETS-qualified, needs-classify with the qualifying and fix-round classes, EXTEND once; the measure prose was tightened to offset most of it); measured 281,058 / 187,706 = 1.4973 (2026-10-06). + Oct 7 wave B3: the Codex probe runs as a command (select-model capture lines, check-sandbox/probe-model/run-with-timeout subcommands) instead of being sourced; measured 281,438 / 187,706 = 1.4994 (2026-10-07). + Oct 7 wave CEO-28/DX-11: review prompts ask for a severity per finding and design proposals use the proposal gate; measured 281,556 / 187,706 = 1.5000 (2026-10-07). + Oct 7 wave B4: /ship publishes through gstack-post (title prepared in a file in the pr-body section, compose block plus gstack-post exit-code branches replacing the two scans); measured 281,894 / 187,706 = 1.5018 (2026-10-07). + B2 early Greptile PR (lazy Step 6.5 section: detect, public-repo consent, push, provisional title file, open; Step 10's bounded wait; the stop-leaves-the-draft rule); measured 286,626 / 187,706 = 1.5270 (2026-10-07). B3, the classifier, B4 and B2 merged: measured 287,128 / 187,706 = 1.5297 (2026-10-07). + Oct 7 wave guard (CEO-20): conditional `run_in_background` request plus the background-run recovery at each foreground dispatch site; measured 281,370 / 187,706 = 1.4990 (2026-10-07). Merged with the guard area: measured 287,440 / 187,706 = 1.5313 (2026-10-07). + Oct 8 wave: the defensive-security framing and fixture summary mode reach the security specialist and the Red Team (stated once in the dispatch, referenced by the Red Team); measured 288,783 / 187,706 = 1.5385 (2026-10-08). + gate integrity (HONEST_WORK_GATE_INTEGRITY W3): the shared GATE_SCAN_BLOCK in the core checklist (2.5) and after Step 7's child, the four-option gate question and record fields in 9.4, tests_ran states in Step 5, Gate edits and per-lane counts in the PR body with draft-while-open; measured 300,143 / 187,706 = 1.5990 (2026-10-10). + Honest Work wave merged (W2/W3 gate integrity in review/ship, W4 kernel + DONE line in every tier-2+ skill, W5/W7 in spec/ship): re-measured on the integrated tree (2026-10-10). + Oct 10 multi-agent wave PR E2 (ship/sections/handoff.md: the no-PR automation handoff, with its Section-index row and STOP pointer in the skeleton), offset by tightening Steps 1–3, 12, 14–17 and 20–21 prose so the skeleton stays under 81,000 bytes (80,997); C-pregate landed 1,123 union bytes in tests.md in between; measured 308,619 / 187,706 = 1.6442 on the integra
Line truncated
|
||||
},
|
||||
'plan-ceo-review': {
|
||||
skill: 'plan-ceo-review',
|
||||
|
||||
@@ -21,7 +21,7 @@ export const MARKER = 'Effort-match the step';
|
||||
export function failableBun(f: Fixture) {
|
||||
put(join(f.commands, 'bun'), `#!/usr/bin/env bash
|
||||
case "$*" in
|
||||
'install --frozen-lockfile') exit 0 ;;
|
||||
'install --production --frozen-lockfile') exit 0 ;;
|
||||
'run build') echo 'Unexpected build in an install fixture' >&2; exit 90 ;;
|
||||
*gen:skill-docs*--out-dir*) if [ -f "$HOME/fail-render" ]; then echo 'render failed (fixture)' >&2; exit 7; fi ;;
|
||||
esac
|
||||
|
||||
@@ -60,9 +60,13 @@ export function fixtureDocs(scenario: DocsScenario, generatedRoot = process.env.
|
||||
write('personal-note.txt', 'Unrelated user content: KEEP THIS EXACTLY.\n');
|
||||
for (const skill of ['document-release', 'ship']) {
|
||||
fs.mkdirSync(path.join(skills, skill, 'sections'), { recursive: true });
|
||||
for (const relative of skill === 'ship'
|
||||
const required = skill === 'ship'
|
||||
? ['SKILL.md', 'sections/documentation.md', 'sections/pr-body.md']
|
||||
: ['SKILL.md', 'sections/audit-scope.md', 'sections/release-body.md']) {
|
||||
: ['SKILL.md', 'sections/audit-scope.md', 'sections/release-body.md'];
|
||||
// A generated skill that loads a shared preamble names sections/preamble.md as a
|
||||
// required asset before skill start; a spawned child blocks on its absence.
|
||||
const preamble = fs.existsSync(path.join(generatedRoot, skill, 'sections/preamble.md')) ? ['sections/preamble.md'] : [];
|
||||
for (const relative of [...required, ...preamble]) {
|
||||
const source = path.join(generatedRoot, skill, relative);
|
||||
if (!fs.existsSync(source)) throw new Error(`Generate the changed skill before live evaluation: ${source}`);
|
||||
fs.copyFileSync(source, path.join(skills, skill, relative));
|
||||
|
||||
@@ -3,9 +3,10 @@ import type { fixtureDocs } from './docsync-fixture';
|
||||
import { docsConfigDir } from './docsync-repo';
|
||||
import { readOnlyInterfaceText } from './read-only-commands';
|
||||
|
||||
export function docsNativeInterface(fixture: Pick<ReturnType<typeof fixtureDocs>, 'home' | 'repo' | 'skills'>, scripts: string[] = [], transport = false, insert = false, file?: string): string {
|
||||
export function docsNativeInterface(fixture: Pick<ReturnType<typeof fixtureDocs>, 'home' | 'repo' | 'skills'> & Partial<Pick<ReturnType<typeof fixtureDocs>, 'env'>>, scripts: string[] = [], transport = false, insert = false, file?: string): string {
|
||||
const skills = fixture.skills.split(path.sep).join('/');
|
||||
return `Fixture observation interface (applies to parent and every child; ${file ? `saved at ${file}: each child prompt tells the child to Read that file first instead of copying this text` : 'include this interface in child prompts'}): Bash may execute only separate literal pwd, ls, cat, stat, sha256sum and Git read commands (status, diff, show, log, ls-files, ls-tree, check-ignore, rev-parse, merge-base, hash-object without -w, branch --show-current, describe with only --tags, --always, --abbrev=<n> or --exact-match and at most one revision). Bash may also run each of the following as its own Bash call, with nothing joined before or after it by ;, &&, || or a pipe (a --help is no exception, so never add one to a line of reads): the exact generated Preamble block with its spawned prefix, literal installed gstack-skill-start/gstack-skill-end commands for document-release (start requires GSTACK_SESSION_KIND=spawned) or their own --help, or the literal installed ${skills}/bin/gstack-docs-candidate snapshot (its --out a private .json under ${fixture.home}), compare <that .json> and --help commands. ${readOnlyInterfaceText(fixture.home)} The Git reads above may join such a line too, but not in a line with cd. A for loop over literal words (a lowercase loop variable; words without quotes, globs or $) whose body uses only such reads counts as those reads, one pass per word, wherever it sits in the line. Every read stays off actor-state.json and off ${docsConfigDir(fixture.home)} except its settings.json: that directory holds Claude's credentials and every agent's session transcript, so judge a child only by the output it returns (its echoed SESSION_KIND line included) and by the repository. The additional scripts below also run each as its own Bash call; no own-call command ever joins such a line. Otherwise no shell composition, custom interpreters, arbitrary scripts, inline eval or memory-mapped writes. The only additional scripts are ${scripts.length ? scripts.join(', ') : 'none'}.${insert ? ` To insert one saved private Markdown artifact into another (a saved section file into a report), Bash may also run the single literal command cat SOURCE.md >> TARGET.md with absolute paths under ${fixture.home}.` : ''} Read/Glob/Grep remain available; Read skill and section files with Read (offset/limit for ranges), because Bash output over 30KB becomes a truncated preview. Use Write/Edit for permitted docs and private JSON/Markdown artifacts under ${fixture.home}; do not rewrite installed skills, config, actor state or scripts. No effects outside the owned fixture. The owner preserves evidence and cleans up. Missing observer coverage blocks acceptance; the Linux kernel monitor covers syscall writes in the product tree, not hostile processes or arbitrary external destinations.
|
||||
const state = fixture.env?.GSTACK_HOME ?? path.join(fixture.home, 'state');
|
||||
return `Fixture observation interface (applies to parent and every child; ${file ? `saved at ${file}: each child prompt tells the child to Read that file first instead of copying this text` : 'include this interface in child prompts'}): Bash may execute only separate literal pwd, ls, cat, stat, sha256sum and Git read commands (status, diff, show, log, ls-files, ls-tree, check-ignore, rev-parse, merge-base, hash-object without -w, branch --show-current, describe with only --tags, --always, --abbrev=<n> or --exact-match and at most one revision). Bash may also run each of the following as its own Bash call, with nothing joined before or after it by ;, &&, || or a pipe (a --help is no exception, so never add one to a line of reads): the exact generated Preamble block with its spawned prefix, literal installed gstack-skill-start/gstack-skill-end commands for document-release (start requires GSTACK_SESSION_KIND=spawned) or their own --help, or the literal installed ${skills}/bin/gstack-docs-candidate snapshot (its --out a private .json under ${fixture.home}), compare <that .json> and --help commands. ${readOnlyInterfaceText(fixture.home)} The Git reads above may join such a line too, but not in a line with cd. A for loop over literal words (a lowercase loop variable; words without quotes, globs or $) whose body uses only such reads counts as those reads, one pass per word, wherever it sits in the line. Every read stays off actor-state.json and off ${docsConfigDir(fixture.home)} except its settings.json: that directory holds Claude's credentials and every agent's session transcript, so judge a child only by the output it returns (its echoed SESSION_KIND line included) and by the repository. The additional scripts below also run each as its own Bash call; no own-call command ever joins such a line. Otherwise no shell composition, custom interpreters, arbitrary scripts, inline eval or memory-mapped writes. The only additional scripts are ${scripts.length ? scripts.join(', ') : 'none'}.${insert ? ` To insert one saved private Markdown artifact into another (a saved section file into a report), Bash may also run the single literal command cat SOURCE.md >> TARGET.md with absolute paths under ${fixture.home}.` : ''} Read/Glob/Grep remain available; Read skill and section files with Read (offset/limit for ranges), because Bash output over 30KB becomes a truncated preview. A private JSON/Markdown artifact (the snapshot --out file, saved child output, a section or report file) lives directly under ${fixture.home} or in a new directory you create there, never inside the repository, ${skills}, ${docsConfigDir(fixture.home)}, ${state} (gstack's own state directory, not a place for your files) or ${fixture.home}/remote.git. Use Write/Edit for permitted docs and those private artifacts; do not rewrite installed skills, config, actor state or scripts. No effects outside the owned fixture. The owner preserves evidence and cleans up. Missing observer coverage blocks acceptance; the Linux kernel monitor covers syscall writes in the product tree, not hostile processes or arbitrary external destinations.
|
||||
|
||||
The working directory for parent and child Bash calls is already ${fixture.repo}. Run Git reads directly, for example: git status, git diff --cached, git merge-base main HEAD, git rev-parse HEAD. Do not use Git global options such as -C, -c, --git-dir or --work-tree, and do not prepend cd or another shell wrapper. The literal git subcommand must immediately follow git; an absolute owned repository path does not make git -C an allowed command.
|
||||
|
||||
|
||||
@@ -422,7 +422,12 @@ function docsPrivateArtifact(file: string, fixture: ReturnType<typeof fixtureDoc
|
||||
path.basename(file) !== 'actor-state.json' && path.basename(actual) !== 'actor-state.json';
|
||||
}
|
||||
|
||||
/** A candidate call at a wrong binary path that does not exist exited 127 before anything ran; it is ignored only when the same command at the declared path follows and runs. */
|
||||
/**
|
||||
* A candidate call at a wrong binary path that does not exist exited 127 before anything ran; it is ignored only when
|
||||
* the same command at the declared path runs: after the slip for snapshot and compare, whose recovery the lifecycle
|
||||
* needs, and anywhere in the transcript for --help, which reads nothing the agent still has to recover (gate
|
||||
* 40323989742: the parent read the usage at the declared path, mistyped the path on a second --help, then went on).
|
||||
*/
|
||||
function candidateNotFound(calls: SkillTestResult['toolCalls'], index: number, fixture: ReturnType<typeof fixtureDocs>, scripts: string[]): boolean {
|
||||
const command = String(calls[index].input?.command ?? '').trim();
|
||||
const binary = command.split(' ')[0]!;
|
||||
@@ -436,7 +441,8 @@ function candidateNotFound(calls: SkillTestResult['toolCalls'], index: number, f
|
||||
if (!['ENOENT', 'ENOTDIR'].includes((error as NodeJS.ErrnoException).code ?? '')) return false;
|
||||
}
|
||||
const retry = candidate + command.slice(binary.length);
|
||||
return docsCommandAllowed(retry, fixture, scripts) && calls.slice(index + 1).some(call =>
|
||||
const candidates = retry === `${candidate} --help` ? calls.filter((_, position) => position !== index) : calls.slice(index + 1);
|
||||
return docsCommandAllowed(retry, fixture, scripts) && candidates.some(call =>
|
||||
call.tool === 'Bash' && String(call.input?.command ?? '').trim() === retry && !call.output.startsWith('Exit code'));
|
||||
}
|
||||
|
||||
|
||||
@@ -128,6 +128,9 @@ export const FREE_FIXTURES: Readonly<Record<string, readonly string[]>> = {
|
||||
'test/fixtures/eng-test-plan-edit-cli.js': ['test/eng-test-plan-edit-approval.test.ts'],
|
||||
'test/fixtures/eng-test-plan-edit-dacc.json': ['test/eng-test-plan-edit-approval.test.ts'],
|
||||
'test/fixtures/eval-history/wave-reds-8-censuses.json': ['test/eval-history.test.ts'],
|
||||
'test/fixtures/evidence/pregate-remote-cleared.out': ['test/evidence.test.ts'],
|
||||
'test/fixtures/evidence/pregate-remote-failed.out': ['test/evidence.test.ts'],
|
||||
'test/fixtures/evidence/shard-runner-files-from.out': ['test/evidence.test.ts'],
|
||||
'test/fixtures/exercised-map-replay.json': ['scripts/exercised-map.ts'],
|
||||
'test/fixtures/exit-propagation/**': ['test/exit-propagation.test.ts'],
|
||||
'test/fixtures/free-shard-capture.ts': ['test/test-free-shards-capture.test.ts'],
|
||||
@@ -140,6 +143,7 @@ export const FREE_FIXTURES: Readonly<Record<string, readonly string[]>> = {
|
||||
'test/fixtures/investigate-owned-question-39195396438.json': ['test/workflow-boundaries-fixture.test.ts'],
|
||||
'test/fixtures/judge-calibration/**': ['scripts/judge-calibration.ts', 'test/judge-calibration.test.ts'],
|
||||
'test/fixtures/judge-panel-replay-2026-10-05.json': ['test/judge-panel-median.test.ts'],
|
||||
'test/fixtures/launch-env-echo/**': ['test/launch-env-echo-ratchet.test.ts'],
|
||||
'test/fixtures/merge-train-3345/**': ['test/changelog-merge-damage.test.ts', 'test/compare-pr-version.test.ts'],
|
||||
'test/fixtures/module-size-ratchet.json': ['test/helpers/module-size.ts', 'test/module-size-ratchet.test.ts'],
|
||||
'test/fixtures/module-size/**': ['test/helpers/module-size.ts', 'test/module-size-ratchet.test.ts'],
|
||||
|
||||
@@ -172,7 +172,7 @@ export function makeFixture(): Fixture {
|
||||
mkdirSync(home, { recursive: true });
|
||||
put(join(commands, 'bun'), `#!/usr/bin/env bash
|
||||
case "$*" in
|
||||
'install --frozen-lockfile') exit 0 ;;
|
||||
'install --production --frozen-lockfile') exit 0 ;;
|
||||
'run build') echo 'Unexpected build in an install fixture' >&2; exit 90 ;;
|
||||
*) exec ${quote(process.execPath)} "$@" ;;
|
||||
esac
|
||||
@@ -248,7 +248,7 @@ export function fixture(layout: string) {
|
||||
};
|
||||
write(join(commands, 'bun'), `#!/usr/bin/env bash
|
||||
case "$*" in
|
||||
'install --frozen-lockfile') exit 0 ;;
|
||||
'install --production --frozen-lockfile') exit 0 ;;
|
||||
'build --help') echo 'Fixture Bun has no CSO compile flags'; exit 0 ;;
|
||||
'run build') echo 'Unexpected build in registration fixture' >&2; exit 90 ;;
|
||||
*) exec ${quote(process.execPath)} "$@" ;;
|
||||
|
||||
@@ -54,7 +54,7 @@ Fixture execution boundary:
|
||||
- Reports belong only in existing qa-reports. Retain fixture state; the owner cleans it after preserving evidence. Authorized source/test edits use Write/Edit. Every Write/Edit targets an owned path inside this working directory; a write anywhere else, including its parent directory, fails acceptance. Read/Glob/Grep support arbitrary read-only discovery, including directory/path inventory.
|
||||
- Bash accepts separate literal commands only: no shell composition, scripts or added path operands. Read-only forms are pwd, ls, ls -la, git status --short, git status --porcelain, git branch --show-current, git diff, git diff --stat, git rev-parse HEAD, bun --version, and exactly date -u +%Y-%m-%dT%H:%M:%SZ. Native tests use bun test with optional named test/*.test.ts selectors.
|
||||
- These are complete command forms, not general shell examples. For inventory inside a named directory, use Read/Glob/Grep; the listed ls forms inspect only the working directory. Do not add operands or flags beyond the declared forms, even for read-only discovery.
|
||||
- The installed production helper is bin/gstack-qa-evidence (absolute owned path also accepted); \`bun bin/gstack-qa-evidence --help\` prints its usage, and the helper source is not part of the task. Probe outputs are declared public/synthetic, so capture with: bun bin/gstack-qa-evidence capture qa-reports NNN --public --timeout-ms 10000 -- NATIVE_PROBE. The child must be one of the observation forms below. Each execution/replay gets a fresh three-digit ID. The helper does not authorize another command, interpreter, path, pipeline or redirect.
|
||||
- The installed production helper is bin/gstack-qa-evidence (absolute owned path also accepted); \`bun bin/gstack-qa-evidence --help\` prints its usage, and the helper source is not part of the task. That is the only --help here: the probe's contract is README.md, so a bare bun run probe (with --help or any argument) outside a capture is a bypass, not a read. Probe outputs are declared public/synthetic, so capture with: bun bin/gstack-qa-evidence capture qa-reports NNN --public --timeout-ms 10000 -- NATIVE_PROBE. The child must be one of the observation forms below. Each execution/replay gets a fresh three-digit ID. The helper does not authorize another command, interpreter, path, pipeline or redirect.
|
||||
- After the first capture, put causal intent in the next capture itself: bun bin/gstack-qa-evidence capture qa-reports NNN --public --timeout-ms 10000 --after PREV --hypothesis 'causal hypothesis' -- NATIVE_PROBE, where PREV is the capture ID of the most recent completed native probe. Before running the probe, the helper publishes qa-reports/exploration-NNN.json linking capture PREV's observation to it, so one call is both checkpoint and probe. The separate form stays valid: bun bin/gstack-qa-evidence checkpoint qa-reports NNN CAPTURE_ID 'full prior capture command' 'causal hypothesis' 'full next capture command' (or an intent.json with only capture, observationCommand, hypothesis and nextCommand), then the exact next command after successful publication. Quote arguments literally. Only the helper writes observed fields.
|
||||
- Write annotations.json inside qa-reports, then run bun bin/gstack-qa-evidence materialize qa-reports annotations.json to produce evidence.json before writing Markdown. Annotations have revision, runtime, cwd, evidence rows {capture,command,contract,expected,classification}, learning (selected checkpoint IDs) and limits; omit observed, which the helper supplies from captures. In each evidence row, capture is the three-digit capture ID and command is the exact full outer capture invocation, including that ID and all wrapper options, not just the native child command after --. This same full-command definition applies to observationCommand and nextCommand. Select a checkpoint whose next native command differs, not a same-command replay with a new capture ID. Retain all required safe observations and every executed probe.
|
||||
- ${entry.family === 'cli' ? 'CLI observation forms: bun run probe -- balance; bun run probe -- export; bun run probe -- apply with zero to three literal arguments; bun cancel.ts. The equivalent bun run cli commands may be diagnostic but do not emit probe JSON. Arguments use ASCII letters/digits/._+- or quoted forms including spaces. The generic wrapper does NOT support wait: the only bounded wait/cancellation interface is bun cancel.ts.' : `Webhook observation form: bun run probe -- followed by one of happy, reject, duplicate, partial, concurrent-ab, concurrent-ba, cancel, dependency. ${entry.mode === 'qa-only' ? 'All eight scenarios are required coverage; a replay does not replace another scenario. ' : ''}Choose their order from observations after the happy path. bun cancel.ts is a CLI-only entrypoint, not part of this fixture.`}
|
||||
|
||||
@@ -13,7 +13,9 @@ import { spawnSync } from 'node:child_process';
|
||||
import { createHash } from 'node:crypto';
|
||||
import * as fs from 'node:fs';
|
||||
import * as path from 'node:path';
|
||||
import type { ShipReceipt } from '../../lib/headless-artifacts';
|
||||
import { TRAIN_KEYS_VERSION } from '../../lib/ship-policy';
|
||||
import { orderReceipt, renderReceiptBlock } from '../../lib/ship-receipt';
|
||||
import { BASE_POLICY, makeFixtureRepo, runBin, type FixtureRepo } from './restamp-fixture';
|
||||
|
||||
export const TRAIN_BLOCK = {
|
||||
@@ -25,6 +27,10 @@ export const TRAIN_POLICY = { ...BASE_POLICY, train: TRAIN_BLOCK, min_gstack_ver
|
||||
export interface Rule {
|
||||
fail?: boolean; silent?: boolean; failButCreate?: boolean; status?: string; conclusion?: string | null; event?: string; headSha?: string;
|
||||
record?: { panels: unknown[]; census?: unknown; verdict?: 'GREEN' | 'RED'; nonce?: string };
|
||||
/** The run's paid-plan manifest: planned entries (default 1), or a raw manifest object; null uploads no paid-plan artifact, as a superseded screen does. */
|
||||
plan?: { planned: number } | { manifest: unknown } | null;
|
||||
/** Marks every artifact of runs dispatched under this rule expired in the artifacts listing. */
|
||||
expired?: boolean;
|
||||
check?: string | null;
|
||||
bisect?: { prefixes: string[]; patterns: Record<string, string>; costUsd?: number };
|
||||
}
|
||||
@@ -58,8 +64,24 @@ export function repoKey(fx: TrainFixture): string {
|
||||
return createHash('sha256').update(norm).digest('hex').slice(0, 16);
|
||||
}
|
||||
|
||||
/** A same-repo PR: a branch from origin/main touching `file`, published as refs/pull/<n>/head (and /merge), known to the gh shim. */
|
||||
export function openPr(fx: TrainFixture, pr: string, opts: { file?: string; text?: string; changelog?: boolean | ((text: string) => string); cross?: boolean; from?: string } = {}): string {
|
||||
/** The PR body /ship leaves behind: the receipt block first (lib/ship-receipt.ts), bound to `head`, then prose. */
|
||||
export function shippedBody(pr: string, head: string, extra: Partial<ShipReceipt> = {}): string {
|
||||
return renderReceiptBlock(orderReceipt({ schema_version: 1, pr: Number(pr), head, base: 'main', queue_mode: 'stamp-at-merge', ...extra })) + `\n## What changed\n\n#${pr} change\n`;
|
||||
}
|
||||
|
||||
/** Set a shimmed PR's body (`shippedBody` for a receipt bound to another head, '' for none). */
|
||||
export function setPrBody(fx: TrainFixture, pr: string, body: string): void {
|
||||
fx.write(d => { d.prs[pr] = { ...(d.prs[pr] as Record<string, unknown>), body }; });
|
||||
}
|
||||
|
||||
/** What GitHub keeps at refs/pull/<n>/merge: a merge commit whose first parent is the base and whose second parent is the PR head. */
|
||||
export function mergeRefCommit(fx: TrainFixture, head: string): string {
|
||||
const { repo } = fx;
|
||||
return repo.git('commit-tree', `${head}^{tree}`, '-p', 'origin/main', '-p', head, '-m', `Merge ${head.slice(0, 12)} into main`);
|
||||
}
|
||||
|
||||
/** A same-repo PR: a branch from origin/main touching `file`, published as refs/pull/<n>/head (and /merge, as GitHub's merge commit), known to the gh shim with a /ship receipt for its head (`shipped: false` leaves the body empty). */
|
||||
export function openPr(fx: TrainFixture, pr: string, opts: { file?: string; text?: string; changelog?: boolean | ((text: string) => string); cross?: boolean; from?: string; shipped?: boolean } = {}): string {
|
||||
const { repo } = fx;
|
||||
repo.git('checkout', '-q', opts.from ?? 'origin/main', '-B', `pr-${pr}`);
|
||||
const file = opts.file ?? `pr-${pr}.txt`;
|
||||
@@ -72,8 +94,8 @@ export function openPr(fx: TrainFixture, pr: string, opts: { file?: string; text
|
||||
repo.git('add', '-A');
|
||||
repo.git('commit', '-q', '-m', `feat #${pr}`);
|
||||
const head = repo.git('rev-parse', 'HEAD');
|
||||
repo.git('push', '-q', '-f', 'origin', `HEAD:refs/pull/${pr}/head`, `HEAD:refs/pull/${pr}/merge`);
|
||||
fx.write(d => { d.prs[pr] = { headRefOid: head, isCrossRepository: !!opts.cross, state: 'OPEN', headRefName: `pr-${pr}`, url: `https://github.com/fixture/repo/pull/${pr}`, body: '' }; });
|
||||
repo.git('push', '-q', '-f', 'origin', `HEAD:refs/pull/${pr}/head`, `${mergeRefCommit(fx, head)}:refs/pull/${pr}/merge`);
|
||||
fx.write(d => { d.prs[pr] = { headRefOid: head, isCrossRepository: !!opts.cross, state: 'OPEN', headRefName: `pr-${pr}`, url: `https://github.com/fixture/repo/pull/${pr}`, body: opts.shipped === false ? '' : shippedBody(pr, head) }; });
|
||||
return head;
|
||||
}
|
||||
|
||||
@@ -136,7 +158,8 @@ function shimSource(): string {
|
||||
" const id = d.nextId++; const head = rule.headSha || inputs.expected_sha || rev('refs/heads/' + ref) || rev(ref);",
|
||||
" const run = { databaseId: id, workflow: w, headBranch: ref, headSha: head, status: rule.status || 'completed', conclusion: rule.conclusion === undefined ? 'success' : rule.conclusion,",
|
||||
" url: 'https://example.invalid/runs/' + id, event: rule.event || 'workflow_dispatch', displayTitle: inputs.nonce ? 'E2E Evals [eval-bg ' + inputs.nonce + ']' : w, inputs };",
|
||||
" d.runs.push(run); d.artifacts[id] = {};",
|
||||
" d.runs.push(run); d.artifacts[id] = {}; if (rule.expired) (d.expired = d.expired || {})[id] = true;",
|
||||
" if (rule.plan !== null) d.artifacts[id]['paid-plan'] = rule.plan && rule.plan.manifest ? rule.plan.manifest : { tier: 'gate', sliceCount: 1, entries: Array.from({ length: rule.plan ? rule.plan.planned : 1 }, (_, i) => ({ file: 'test/case-' + i + '.test.ts', status: 'planned' })) };",
|
||||
" if (rule.record && !inputs.prefix_shas) d.artifacts[id][d.artifact] = { schema: 1, kind: 'train-gate', nonce: rule.record.nonce || inputs.nonce, head_sha: head, tree: rev(head + '^{tree}'),",
|
||||
" verdict: rule.record.verdict || 'GREEN', census: rule.record.census, panels: rule.record.panels };",
|
||||
" if (rule.check && !inputs.prefix_shas) (d.checks[head] = d.checks[head] || []).push({ name: 'gstack/full-gate', status: 'completed', conclusion: rule.check });",
|
||||
@@ -155,9 +178,12 @@ function shimSource(): string {
|
||||
"if (a[0] === 'run' && a[1] === 'view') { const r = d.runs.find(x => String(x.databaseId) === a[2]); if (!r) fail('run not found'); out(r); }",
|
||||
"if (a[0] === 'run' && a[1] === 'download') {",
|
||||
" const art = (d.artifacts[a[2]] || {})[opt('-n')]; if (!art) fail('no artifact matches');",
|
||||
" fs.mkdirSync(opt('-D'), { recursive: true }); fs.writeFileSync(path.join(opt('-D'), 'record.json'), JSON.stringify(art)); save(); process.exit(0);",
|
||||
" fs.mkdirSync(opt('-D'), { recursive: true }); fs.writeFileSync(path.join(opt('-D'), opt('-n') === 'paid-plan' ? 'manifest.json' : 'record.json'), JSON.stringify(art));",
|
||||
" if (opt('-n') === 'paid-plan') fs.writeFileSync(path.join(opt('-D'), 'gate-reuse.json'), '{\"reuse\":\"confirmed\"}'); save(); process.exit(0);",
|
||||
"}",
|
||||
"if (a[0] === 'api') {",
|
||||
" const arts = /actions\\/runs\\/(\\d+)\\/artifacts(?:\\?name=([^&]+))?/.exec(a[1] || '');",
|
||||
" if (arts) { const names = Object.keys(d.artifacts[arts[1]] || {}).filter(n => !arts[2] || n === decodeURIComponent(arts[2])); out({ total_count: names.length, artifacts: names.map(name => ({ name, expired: !!(d.expired || {})[arts[1]] })) }); }",
|
||||
" const named = /commits\\/([0-9a-f]+)\\/check-runs\\?check_name=([^&]+)/.exec(a[1] || '');",
|
||||
" if (named) { const list = (d.checks[named[1]] || []).filter(c => c.name === decodeURIComponent(named[2])); out({ total_count: list.length, check_runs: list }); }",
|
||||
" const paged = /commits\\/([0-9a-f]+)\\/(check-runs|status)\\?.*page=(\\d+)/.exec(a[1] || '');",
|
||||
|
||||
@@ -46,9 +46,17 @@ export function asideDriveOptions(text: string): string[] {
|
||||
/** Any lettered option offering a browser drive, for flows where no drive may be offered. */
|
||||
export const offersDriveOption = (text: string): boolean => letteredOptions(text).some(option => /drive|browse|Aside/i.test(option));
|
||||
|
||||
/** The defer option: a lettered option that defers, postpones or sets the step aside for now. */
|
||||
/**
|
||||
* The defer option: a lettered option that defers, postpones or sets the step aside for now. "Wait for now" and
|
||||
* "hold off for now" count only as the option's own opening or sentence (gate 40290033102: "D) Wait for now. I'll
|
||||
* mark this step as blocked on you."), never as a drive option's "I wait while you sign in": the phrase must open the
|
||||
* option or a sentence and end it, and the option must not be a browser drive, so "I wait for now while you sign in",
|
||||
* "wait for now and do it yourself" and "I drive it in Aside. I wait for now." do not count.
|
||||
*/
|
||||
export const offersDefer = (text: string): boolean => letteredOptions(text).some(option =>
|
||||
/\b(?:defer\w*|postpone\w*|put (?:this|it)(?: step)? off|skip (?:this|it)(?: step)? for now|come back to (?:this|it)(?: step)? later|leave (?:this|it)(?: step)? for (?:now|later))\b/i.test(option));
|
||||
/\b(?:defer\w*|postpone\w*|put (?:this|it)(?: step)? off|skip (?:this|it)(?: step)? for now|come back to (?:this|it)(?: step)? later|leave (?:this|it)(?: step)? for (?:now|later))\b/i.test(option)
|
||||
|| !/drive|browse|Aside/i.test(option)
|
||||
&& /(?:^|[.!?;:]\s+)(?:(?:we|I|let['\u2019]s) )?(?:wait|hold off)(?: on (?:this|it)(?: step)?)? for now\b(?=\s*(?:[.!?;:]|[-\u2013\u2014]|$))/i.test(option));
|
||||
|
||||
/** The manual option: "manual", or one sentence offering instructions or steps the user follows themselves. */
|
||||
export function offersManualSteps(text: string): boolean {
|
||||
|
||||
@@ -814,10 +814,10 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
|
||||
'ship-triage': ['bin/gstack-state-root.sh', 'lib/state-root.ts', 'ship/**', 'bin/gstack-repo-mode', 'test/skill-e2e-triage.test.ts', 'test/helpers/ship-triage-labels.ts',
|
||||
'scripts/resolvers/testing.ts'
|
||||
],
|
||||
'ship-docsync-completion': ['bin/gstack-docs-candidate', 'bin/gstack-state-root.sh', 'lib/state-root.ts', 'ship/**', 'document-release/**', 'test/skill-e2e-ship-docsync.test.ts', 'test/helpers/docsync-*.ts', 'test/helpers/read-only-commands.ts', 'test/helpers/session-runner.ts', 'test/helpers/hermetic-env.ts', 'bin/gstack-skill-start', 'bin/gstack-session-kind', 'scripts/resolvers/sections.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/gen-skill-docs.ts', 'scripts/resolvers/testing.ts', 'test/helpers/qa-checkpoint-evidence.ts', 'test/helpers/qa-functional-observer.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/qa-evidence-producer.ts', 'test/helpers/qa-functional-fixture.ts', 'bin/gstack-context-recovery'],
|
||||
'ship-docsync-completion': ['bin/gstack-docs-candidate', 'bin/gstack-state-root.sh', 'lib/state-root.ts', 'ship/**', 'document-release/**', 'test/skill-e2e-ship-docsync.test.ts', 'test/helpers/docsync-*.ts', 'test/helpers/read-only-commands.ts', 'test/helpers/session-runner.ts', 'test/helpers/hermetic-env.ts', 'bin/gstack-skill-start', 'bin/gstack-session-kind', 'scripts/resolvers/sections.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/gen-skill-docs.ts', 'scripts/resolvers/testing.ts', 'test/helpers/qa-checkpoint-evidence.ts', 'test/helpers/qa-functional-observer.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/qa-evidence-producer.ts', 'test/helpers/qa-functional-fixture.ts', 'bin/gstack-context-recovery', 'test/fixtures/docsync-state-dir-artifacts-public.json'],
|
||||
'ship-docsync-current': ['bin/gstack-docs-candidate', 'bin/gstack-state-root.sh', 'lib/state-root.ts', 'ship/**', 'document-release/**', 'test/skill-e2e-ship-docsync.test.ts', 'test/helpers/docsync-*.ts', 'test/helpers/read-only-commands.ts', 'test/helpers/session-runner.ts', 'test/helpers/hermetic-env.ts', 'bin/gstack-skill-start', 'bin/gstack-session-kind', 'scripts/resolvers/sections.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/gen-skill-docs.ts', 'scripts/resolvers/testing.ts', 'test/helpers/qa-checkpoint-evidence.ts', 'test/helpers/qa-functional-observer.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/qa-evidence-producer.ts', 'test/helpers/qa-functional-fixture.ts', 'bin/gstack-context-recovery', 'test/fixtures/docsync-candidate-not-found-public.json'],
|
||||
'ship-docsync-failure': ['bin/gstack-docs-candidate', 'bin/gstack-state-root.sh', 'lib/state-root.ts', 'ship/**', 'document-release/**', 'test/skill-e2e-ship-docsync.test.ts', 'test/helpers/docsync-*.ts', 'test/helpers/read-only-commands.ts', 'test/helpers/session-runner.ts', 'test/helpers/hermetic-env.ts', 'bin/gstack-skill-start', 'bin/gstack-session-kind', 'scripts/resolvers/sections.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/gen-skill-docs.ts', 'scripts/resolvers/testing.ts', 'test/helpers/qa-checkpoint-evidence.ts', 'test/helpers/qa-functional-observer.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/qa-evidence-producer.ts', 'test/helpers/qa-functional-fixture.ts', 'bin/gstack-context-recovery'],
|
||||
'ship-docsync-store': ['bin/gstack-docs-candidate', 'bin/gstack-state-root.sh', 'lib/state-root.ts', 'ship/**', 'document-release/**', 'test/skill-e2e-ship-docsync.test.ts', 'test/helpers/docsync-*.ts', 'test/helpers/read-only-commands.ts', 'test/helpers/session-runner.ts', 'test/helpers/hermetic-env.ts', 'bin/gstack-skill-start', 'bin/gstack-session-kind', 'scripts/resolvers/sections.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/gen-skill-docs.ts', 'scripts/resolvers/testing.ts', 'test/helpers/qa-checkpoint-evidence.ts', 'test/helpers/qa-functional-observer.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/qa-evidence-producer.ts', 'test/helpers/qa-functional-fixture.ts', 'bin/gstack-context-recovery'],
|
||||
'ship-docsync-store': ['bin/gstack-docs-candidate', 'bin/gstack-state-root.sh', 'lib/state-root.ts', 'ship/**', 'document-release/**', 'test/skill-e2e-ship-docsync.test.ts', 'test/helpers/docsync-*.ts', 'test/helpers/read-only-commands.ts', 'test/helpers/session-runner.ts', 'test/helpers/hermetic-env.ts', 'bin/gstack-skill-start', 'bin/gstack-session-kind', 'scripts/resolvers/sections.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/gen-skill-docs.ts', 'scripts/resolvers/testing.ts', 'test/helpers/qa-checkpoint-evidence.ts', 'test/helpers/qa-functional-observer.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/qa-evidence-producer.ts', 'test/helpers/qa-functional-fixture.ts', 'bin/gstack-context-recovery', 'test/fixtures/docsync-help-not-found-public.json'],
|
||||
// #2733 behavioral proof: the JSON contract survives a firing gate inside a
|
||||
// spawned-marked subagent. Deps name every behavior under test — the
|
||||
// session-kind override, the skill-start gates, both hooks + the shared
|
||||
@@ -856,7 +856,7 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
|
||||
'design-review-detector-shim-dom': ['bin/gstack-state-root.sh', 'lib/state-root.ts', 'design-review/**', 'scripts/resolvers/design.ts', 'scripts/resolvers/outside-voice.ts', 'lib/design-detect-contract.ts', 'lib/dom-dump-script.ts', 'lib/dom-dump.js', 'bin/gstack-design-detect.ts', 'browse/src/**', 'test/helpers/fake-impeccable.ts', 'test/fixtures/fake-impeccable.ts', 'test/fixtures/impeccable-detect-sample.json', 'test/fixtures/review-eval-design-slop.*', 'test/skill-e2e-design.test.ts',
|
||||
'scripts/resolvers/testing.ts', 'test/helpers/aside-available.ts', 'test/helpers/llm-judge.ts', 'test/helpers/office-hours-attempt.ts'],
|
||||
'design-review-plugin-handoff': ['bin/gstack-state-root.sh', 'lib/state-root.ts', 'design-review/**', 'scripts/resolvers/design.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/testing.ts', 'lib/design-catalog.ts', 'lib/design-detect-contract.ts', 'bin/gstack-design-detect.ts', 'test/helpers/hermetic-env.ts', 'test/helpers/fake-impeccable.ts', 'test/fixtures/fake-impeccable.ts', 'test/fixtures/impeccable-detect-sample.json', 'test/fixtures/review-eval-design-slop.html', 'test/fixtures/review-eval-design-slop.css', 'test/skill-e2e-design.test.ts', 'test/helpers/aside-available.ts', 'test/helpers/llm-judge.ts', 'test/helpers/office-hours-attempt.ts'],
|
||||
'design-html-slop-gate': ['bin/gstack-state-root.sh', 'lib/state-root.ts', 'design-html/**', 'scripts/resolvers/design.ts', 'scripts/resolvers/outside-voice.ts', 'lib/design-detect-contract.ts', 'bin/gstack-design-detect.ts', 'test/helpers/fake-impeccable.ts', 'test/fixtures/fake-impeccable.ts', 'test/fixtures/impeccable-detect-sample.json', 'test/skill-e2e-design.test.ts', 'test/fixtures/review-eval-design-slop.html', 'test/fixtures/review-eval-design-slop.css', 'test/helpers/aside-available.ts', 'test/helpers/llm-judge.ts', 'test/helpers/office-hours-attempt.ts'],
|
||||
'design-html-slop-gate': ['bin/gstack-state-root.sh', 'lib/state-root.ts', 'design-html/**', 'scripts/resolvers/design.ts', 'scripts/resolvers/outside-voice.ts', 'lib/design-detect-contract.ts', 'bin/gstack-design-detect.ts', 'lib/design-craft.ts', 'bin/gstack-design-craft', 'test/helpers/fake-impeccable.ts', 'test/fixtures/fake-impeccable.ts', 'test/fixtures/impeccable-detect-sample.json', 'test/skill-e2e-design.test.ts', 'test/fixtures/review-eval-design-slop.html', 'test/fixtures/review-eval-design-slop.css', 'test/helpers/aside-available.ts', 'test/helpers/llm-judge.ts', 'test/helpers/office-hours-attempt.ts'],
|
||||
|
||||
// /diagram (diagram-render bundle consumers). Triplet = deterministic
|
||||
// functional (gate); authoring quality = LLM-judged benchmark (periodic).
|
||||
|
||||
Reference in new issue
Block a user