Merge remote-tracking branch 'origin/main' into capy/fixwave-D-office-hours-tier

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

# Conflicts:
#	CHANGELOG.md
#	VERSION
#	agents-digest/gstack-AGENTS.md
#	package.json

CHANGELOG.md

@@ -1,6 +1,6 @@
 # Changelog
 
-## [1.91.49.0] - 2026-10-08
+## [1.91.54.0] - 2026-10-08
 
 **Your first /office-hours session gets the first-session closing again, and you see the design doc before you approve it.**
 
@@ -25,6 +25,38 @@ Run `/gstack-upgrade`, then start `/office-hours` on a new idea. Before the doc
 
 Contributed by @kikearciniegas (#2801), @kichinosukey (#879), @RyanAlberts (#1116), @walton-chris (#1049), @aviraldua93 (#1958), @jbetala7 (#1723, #1724), @TJ-NomoAI (#1651) and @0xDevNinja (#1747).
 
+## [1.91.52.0] - 2026-10-08
+
+**`/qa` says exactly what shape `annotations.json` takes, and the `qa-quick` gate eval stops timing out at its 300 s budget.**
+
+Before writing its report, `/qa` records an `annotations.json` file and runs `gstack-qa-evidence materialize` on it. The section that describes the file listed its fields as `{evidence: [...], limits}` and told browser-only runs to put "checkpoints in limits", but it never said what type `limits` is. The validator only accepts a non-empty array of strings. In 11 of 15 recent `qa-quick` CI transcripts, the agent's first attempt wrote `limits` as an object, the call failed, and the agent had to retry. Anyone running `/qa` or `/qa-only` could hit the same retry.
+
+`qa-quick` runs on every PR that touches `browse/src`. It passed 13 of 15 recent CI runs in 206-280 s, and the other 2 hit the 300 s session timeout. Two parts of the case's own setup were adding work. Its fixture directory was not a git repository, so in all 15 runs `materialize` first failed with "revision is required when git rev-parse HEAD is unavailable". Its prompt also put the fixture's `/page1` and `/page2` links in scope. Both links return 404 on the test server, so each run spent part of its 30 s probe window, and its wrap-up, investigating and reporting them. The session budget, the thresholds and the `/qa` workflow are unchanged.
+
+### The numbers that matter
+
+Diagnostic `ship-measure` trials in the CI image (Claude Code 2.1.292, Bun 1.4.2, `--jobs 2`, `CI=true`). They never change a recorded verdict.
+
+| `qa-quick` | Before (CI, 15 runs) | After (10 trials) |
+|---|---|---|
+| Passed | 13 of 15 | 10 of 10 |
+| Pass duration, median (range) | 252 s (206-280 s) | 187 s (155-256 s) |
+| Mean cost per trial | $1.75 | $1.46 |
+| Runs with a failed `materialize` call | 15 of 15 | 0 of 10 |
+
+### What this means for you
+
+`/qa` and `/qa-only` now get `annotations.json` right on the first try, which saves a failed tool call near the end of a run. A browse PR's `qa-quick` check should no longer time out. Its slowest measured trial (256 s) sits right at the 85% headroom line (255 s), so the weekly gate's headroom alarm may still flag the case now and then.
+
+### Itemized changes
+
+#### Fixed
+- `qa/sections/exploratory.md` §4 (shared by `/qa` and `/qa-only` through the `QA_EXPLORATORY` resolver) shows `limits` as `["checkpoint 001"]` and says it is a non-empty string array, never an object. That matches what `lib/qa-evidence.ts` already enforces.
+
+#### For contributors
+- `qa-quick` commits its fixture directory to git before the session starts, as `qa-only-no-fix` already does. `/qa`'s clean-tree check and the evidence recorder's revision now work the way they do in a real repository.
+- `qa-quick` limits Quick scope to the fixture page itself: its load, console health and rendered content. The two same-origin links are listed as untested coverage. The qa-b6/b7/b8 and qa-fix-loop cases still cover link following and defect detection.
+
 ## [1.91.47.0] - 2026-10-08
 
 **`/careful` and `/guard` now check PowerShell commands, and `/freeze` now covers notebook edits.**

TODOS.md

@@ -2,7 +2,7 @@
 
 ## NEXT PRIORITY
 
-### P2/P3: office-hours and timeline follow-ups (filed 2026-10-08, v1.91.49.0)
+### P2/P3: office-hours and timeline follow-ups (filed 2026-10-08, v1.91.54.0)
 
 Left open by the office-hours tier fix (#2801, #879, #1049, #1958, #1723, #1651 part A).
 

VERSION

@@ -1 +1 @@
-1.91.49.0
+1.91.54.0

agents-digest/gstack-AGENTS.md

@@ -1,4 +1,4 @@
-# gstack digest v1.91.49.0 — regenerate/re-copy after upgrading gstack
+# gstack digest v1.91.54.0 — 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,

package.json

@@ -1,6 +1,6 @@
 {
   "name": "gstack",
-  "version": "1.91.49",
+  "version": "1.91.54",
   "description": "Garry's Stack — Claude Code skills + fast headless browser. One repo, one install, entire AI engineering workflow.",
   "license": "MIT",
   "type": "module",

qa-only/sections/exploratory.md

@@ -100,7 +100,7 @@ with their failing contract and expected assertion; never create tests or freeze
 ## 4. Final report
 
 Use the surface report template; link each checkpoint. Separate browser scores, functional outcomes and proposed/executed tests.
-Write PROBE_DIR/annotations.json {evidence: [{capture, command, contract, expected, classification}], limits} (browser-only: evidence [], checkpoints in limits); before Markdown `bun EVIDENCE_TOOL materialize PROBE_DIR annotations.json` (fills observed/metadata; prints reportLinks; runs once per PROBE_DIR); you classify. Annotate every safe capture, including failures/replays: an omitted capture is withheld and keeps the verdict inconclusive. Classify a capture taken before an input change `superseded`; it closes when the same command reran on current inputs. Disclose withheld/incomplete evidence.
+Write PROBE_DIR/annotations.json {evidence: [{capture, command, contract, expected, classification}], limits: ["checkpoint 001"]} (limits: non-empty string array, not an object; browser-only: evidence []); before Markdown `bun EVIDENCE_TOOL materialize PROBE_DIR annotations.json` (fills observed/metadata; prints reportLinks; runs once per PROBE_DIR); you classify. Annotate every safe capture, including failures/replays: an omitted capture is withheld and keeps the verdict inconclusive. Classify a capture taken before an input change `superseded`; it closes when the same command reran on current inputs. Disclose withheld/incomplete evidence.
 Evidence is invocation-local.
 Missing prerequisites/expectations/observations, timeouts and refusal never pass.
 Pass requires all required current-input contracts to pass with no required remainder.

qa/sections/exploratory.md

@@ -85,7 +85,7 @@ Never freeze buggy output, weaken tests or delete valid red tests.
 ## 4. Final report
 
 Use the surface report template; link each checkpoint. Separate browser scores, functional outcomes and proposed/executed tests.
-Write PROBE_DIR/annotations.json {evidence: [{capture, command, contract, expected, classification}], limits} (browser-only: evidence [], checkpoints in limits); before Markdown `bun EVIDENCE_TOOL materialize PROBE_DIR annotations.json` (fills observed/metadata; prints reportLinks; runs once per PROBE_DIR); you classify. Annotate every safe capture, including failures/replays: an omitted capture is withheld and keeps the verdict inconclusive. Classify a capture taken before an input change `superseded`; it closes when the same command reran on current inputs. Disclose withheld/incomplete evidence.
+Write PROBE_DIR/annotations.json {evidence: [{capture, command, contract, expected, classification}], limits: ["checkpoint 001"]} (limits: non-empty string array, not an object; browser-only: evidence []); before Markdown `bun EVIDENCE_TOOL materialize PROBE_DIR annotations.json` (fills observed/metadata; prints reportLinks; runs once per PROBE_DIR); you classify. Annotate every safe capture, including failures/replays: an omitted capture is withheld and keeps the verdict inconclusive. Classify a capture taken before an input change `superseded`; it closes when the same command reran on current inputs. Disclose withheld/incomplete evidence.
 Evidence is invocation-local; /ship reruns once per invocation.
 Missing prerequisites/expectations/observations, timeouts and refusal never pass.
 Pass requires all required current-input contracts to pass with no required remainder.

scripts/resolvers/qa.ts

@@ -147,7 +147,7 @@ Never freeze buggy output, weaken tests or delete valid red tests.`}
 ## 4. Final report
 
 Use the surface report template; link each checkpoint. Separate browser scores, functional outcomes and proposed/executed tests.
-Write PROBE_DIR/annotations.json {evidence: [{capture, command, contract, expected, classification}], limits} (browser-only: evidence [], checkpoints in limits); before Markdown \`bun EVIDENCE_TOOL materialize PROBE_DIR annotations.json\` (fills observed/metadata; prints reportLinks; runs once per PROBE_DIR); you classify. Annotate every safe capture, including failures/replays: an omitted capture is withheld and keeps the verdict inconclusive. Classify a capture taken before an input change \`superseded\`; it closes when the same command reran on current inputs. Disclose withheld/incomplete evidence.
+Write PROBE_DIR/annotations.json {evidence: [{capture, command, contract, expected, classification}], limits: ["checkpoint 001"]} (limits: non-empty string array, not an object; browser-only: evidence []); before Markdown \`bun EVIDENCE_TOOL materialize PROBE_DIR annotations.json\` (fills observed/metadata; prints reportLinks; runs once per PROBE_DIR); you classify. Annotate every safe capture, including failures/replays: an omitted capture is withheld and keeps the verdict inconclusive. Classify a capture taken before an input change \`superseded\`; it closes when the same command reran on current inputs. Disclose withheld/incomplete evidence.
 Evidence is invocation-local${reportOnly ? '.' : '; /ship reruns once per invocation.'}
 Missing prerequisites/expectations/observations, timeouts and refusal never pass.
 Pass requires all required current-input contracts to pass with no required remainder.

test/skill-e2e-qa-workflow.test.ts

@@ -49,6 +49,13 @@ describeIfSelected('QA skill E2E', ['qa-quick'], () => {
 
     // Create report directory
     fs.mkdirSync(path.join(qaDir, 'qa-reports'), { recursive: true });
+
+    for (const args of [['init', '-b', 'main'], ['config', 'user.email', 'test@test.com'], ['config', 'user.name', 'Test'],
+      ['add', '.'], ['commit', '-m', 'initial']]) {
+      const git = spawnSync('git', args, { cwd: qaDir, stdio: 'pipe', timeout: 5000 });
+      if (git.error) throw git.error;
+      if (git.status !== 0) throw new Error(`git ${args.join(' ')} failed: ${git.stderr}`);
+    }
   });
 
   afterAll(() => {
@@ -68,7 +75,7 @@ qa is a carved skill: when SKILL.md tells you to Read ~/.claude/skills/gstack/qa
 Skip the preamble bash block, lake intro, telemetry, and contributor mode sections — go straight to the QA workflow.
 
 Run a Quick-depth QA test on ${testServer.url}/basic.html
-This fixture is one static page with two same-origin navigation links (/page1, /page2) and one external link; Quick scope is that page and its two same-origin links.
+This fixture is one static page with two same-origin navigation links (/page1, /page2) and one external link. Quick scope is that page only: its load, console health and rendered content. Do not follow or probe its links; list them as untested coverage.
 As the caller, I set a 30-second total probe limit for this run (shorter than Browser Quick's own budget), so start the deadline with SECONDS=30.
 Write concise checkpoints and a concise report, retaining required evidence, scores and untested-coverage fields; cite evidence IDs instead of repeating commands.
 Do NOT use AskUserQuestion — run Quick tier directly.