Commit Graph
4 Commits
Author SHA1 Message Date
Garry Tanandcapy-ai[bot] 7cb151bff7 Count an outside review as clean only when it ends with a VERDICT line (#4140)
* Add failing tests: outside reviews read clean only from a last-line verdict

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

* Count an outside review as clean only from its last VERDICT line

Every outside-review prompt now asks the reviewer to end with exactly
VERDICT: CLEAN or VERDICT: FINDINGS, and the parser reads a pass only from
that line. Prose no-findings sentences are no longer evidence for clean.
Codex's structured review and /codex review run through codex exec, since
codex review --base takes no prompt and could never give the line.

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

* Repin the outside reviewer briefs and fix the tests the verdict line broke (GST-1821)

The outside brief, both adversarial sections and the review-army prompt-file line now carry the last-line VERDICT request; their pins move under the preregistered no-loss replay GST-1821. Test fakes that wrote a clean reply now end it with VERDICT: CLEAN, the review carve marker follows the codex exec sentence, size pins drop where skills shrank, and the plan-review prompt-file line is shortened so /plan-eng-review stays at its pin.

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

* Give the plan-review invocation test's fake reviewer the verdict line it now needs

CI's free-suite shard 5 failed at 1de52b0 with 18 cases in test/model-role-invocation.test.ts: the fake Codex reply had no VERDICT line, so it read unverified (exit 4), and the review-mode template now has one codex exec dispatch block instead of two. The fake reply now ends with VERDICT: FINDINGS and the block count expects one.

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

* Stop the changelog correction from claiming the verdict line closes every false-clean case

Review-Finding: p1/red-team#2 reader=red-team
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Split the changelog correction's last sentence for readability

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

* Close the review fail-opens the fix-check found (GST-1821)

A /codex review whose git diff fails now stops before Codex runs instead of sending an empty diff. The verdict is read from the raw last line, so inline code after VERDICT: CLEAN no longer reads clean, and VERDICT: CLEAN beside numbered items with no severity reads unverified. Codex structured review gets the base-branch diff appended to its prompt, the way the Claude path does, so the scope no longer depends on the prompt the host writes.

Fix round granted by the Captain (a-aec3882c9d48). Review-section pins move under replay GST-1821: the free 681-input replay and the 54 scored probe replies are unchanged through the fixed parser.

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

* Say in the changelog which numbered-list replies now read unverified, and that /codex review stops without its diff

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

* Say in the skills guide that /codex review now sends the diff through codex exec

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

* Check that the structured outside review appends the base-branch diff to its prompt

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>
2026-11-07 22:12:57 +00:00
Garry Tanandcapy-ai[bot] 6cf00aee9c Require the daemon secret and loopback Host/Origin on the design and iOS QA daemons (#4117)
* Require the daemon secret and loopback Host/Origin on the design and iOS QA daemons (GST-1747)

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

* Name the changelog fragment after the branch (GST-1747)

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

* fix: pre-landing review fixes

Review-Finding: p1/red-team#2 reader=red-team
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* fix: refuse cross-site browser requests on the iOS QA loopback, show the expired page for a stale board secret, refuse requests without a Host (GST-1747)

Review-Finding: v1/outside-voice#1 reader=outside-voice
Review-Finding: v1/adversarial-native#2 reader=adversarial-native
Review-Finding: v1/adversarial-native#5 reader=adversarial-native
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* docs: show the secret segment in the documented design board URL (GST-1747)

Review-Finding: v1/adversarial-native#1 reader=adversarial-native
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* test: keep the daemon token fixtures on one line so the credential scan reads them as code (GST-1747)

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

* docs: cover the Sec-Fetch-Site refusal, the expired board page and the no-Host 403 in the changelog fragment (GST-1747)

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>
2026-11-07 07:39:51 +00:00
Garry Tanandcapy-ai[bot] 8695938e74 v1.92.15.0 feat: plan reviews check facts and keep one task list; /office-hours hands its wireframe to design review (#340, #513, #973, #1048, #1791) (#3775)
* G1: gstack-plan-reality check opens every file:line receipt (#973)

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

* G1: office-hours spec reviewer checks paths and flags through a bin-enforced probe (#973)

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

* G2: plan-review reruns reconcile the last task list (gstack-tasks prior/supersede) (#1791)

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

* G2: plan reviews write task lists through gstack-tasks start/add/close

The emit block shrinks to three calls: prior (now defaulting --dir and
--branch, and printing how to reconcile), start (creates the empty
branch-named list) and add (one validated row per task). close records a
done or dropped prior task. The plan-review result codes move to
lib/result-codes-plan.ts so lib/result-codes.ts stays under the module-size
ratchet; generated plan-review sections shrink, so their size pins go down.

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

* F2: office-hours saves the sketch beside the design doc; /plan-design-review reads it

Step 5 copies sketch.png/html to <PROJECT_DIR>/{user}-{branch}-sketch-{datetime}.*
and writes a Wireframe: line (state-root relative) or Wireframe: none (<reason>).
The design review section finds the design doc before Pass 1 and opens the
wireframe, text-only when the file is missing. G4's signals line rides along
in the same generated office-hours files; tests in planning-wave-prose.

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

* G3: plan reviews tie storage to queries, not file count (#1048)

One bullet in each of plan-eng-review and plan-ceo-review: fields queried,
constrained or updated on their own get explicit columns or tables; JSON suits
a document read and written whole. Written fresh; the reporter's patch is not
ported.

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

* evals: GSTA-228 planning-wave cases with branch, main and no-gstack arms

planted facts (G1, behavior), data model (G3, behavior), task-list rerun (G2,
rule) and closing signals (G4, behavior). GSTACK_WAVE_ARM picks the arm; only
the branch arm asserts the preregistered bar, every arm writes a score row.

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

* changelog: GSTA-228 planning wave fragment

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

* G1: the probe takes subcommand words for fixed-subcommand CLIs

The planted-facts eval's one branch miss: the reviewer asked to probe
"git log", the probe refused it, and git's top-level help cannot show a log
flag, so the fabricated --since-commit stayed "unverified".
probe --help <command> [<subcommand> [<subcommand>]] now runs
<cli> <sub> --help for git, gh, docker, cargo, go, npm and uv (never node,
bun, python3, make, yarn, pnpm or a gstack bin, where the word could name a
script), in an empty temporary directory with pagers set to cat, falling back
to -h when --help has no usage line (a minimized system's missing man page).

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

* G2: task text goes through a rows file, never a command line

The free suite's generated-bash lint (INV-3) refused the add command's
<title>/<finding> placeholders: free text reaches a command only as a file the
agent writes with its file-write tool. start now also creates an empty rows
file in the repository's git-excluded .gstack/tmp and records the run; the
agent writes task and disposition rows there; add validates every row,
stamps phase, run, branch and commit, appends tasks to the list and
dispositions to task-dispositions-<phase>-<branch>.jsonl, then supersedes the
branch's earlier lists. close is gone (dispositions are rows).

The new planning-wave cases get measured periodic walls in
scripts/paid-test-durations.json so the periodic census still packs into 40
slices, the schema case declares the preamble sources its eng-template owners
need, and the paid file count is 114.

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

* G2: fold start into add so each plan review emits one bash fence

The rows file lives at .gstack/tmp/tasks-<phase>-rows.jsonl; add writes this
run's list (empty when there are no rows), appends dispositions, deletes the
rows file and supersedes the branch's earlier lists. Lowers 27 size pins.

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

* G2 tests: give gstack-tasks a private HOME and state root

CI shard 13 home containment caught gstack-slug writing ~/.gstack/slug-cache
entries from the tasks-prior fixtures.

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

* changelog: gstack-tasks has no start command

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

* G1/G2: tighten the probe and the rows file after ship review

The probe now accepts only each CLI's listed built-in subcommands (no uv run,
docker run, go test, npm exec or gh extensions), refuses gstack bins that do not
handle --help and never retries them with -h, and runs with a throwaway HOME and
an environment without keys. gstack-tasks resolves the slug through
runScriptSync (Windows) and prior deletes a rows file an unfinished run left.
Adds tests for the dropped disposition and the stale rows file.

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

* G2: add refuses while an earlier task is neither carried nor closed

Ship review (state matrix): a rerun that skipped RECONCILE silently retired
open tasks. add now names each undecided <run_id>/<id> and writes nothing.

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

* G1/G2: fixes from the ship fix-check and Step 11 voices

Probe: find the repository root without running git, drop relative and
in-repository PATH entries for lookup and for the child, keep HOME and
toolchain locations (rustup, mise, asdf) but no keys, drop cargo fmt/clippy
(external cargo-* programs), restore planted env in the test.
gstack-tasks: resolve the exclude path against the cwd (subdirectories),
resolve --dir, stamp an empty branch on a detached HEAD like the aggregator,
name the file from --branch, and refuse a same-second second list instead of
appending. Receipts: line 0, reversed ranges, dangling links and paths
through files are unresolved instead of crashing.

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

* changelog: probe limits and the reconcile refusal

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

* docs: probe subcommand counts per CLI (ship docs audit)

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

---------

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-11-01 06:11:17 +00:00
Garry Tanandcapy-ai[bot] a14c28aca7 v1.91.289.0 feat: skill diet pilots for plan-design-review, office-hours and design-review (GSTA-134) (#3525)
* feat(plan-design-review): skill diet (GSTA-134 pilot 1)

SKILL.md 66,063 -> 56,209 B (claude host); review-sections.md 52,243 -> 50,183 B.
Cut model-known prose (cognitive patterns, verbose designer prose, duplicated
formatting rules); UX principles kept as a five-line Krug summary after the
blind judge showed wayfinding loss without it. Section layout unchanged:
autoplan's methodology snapshot requires review-sections.md as the only indexed
section.

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

* feat(office-hours): skill diet (GSTA-134 pilot 2)

Moves the Phase 3.5 Codex second opinion and the Phase 4.25 visual design
(designer mockups / HTML sketch) out of the eager SKILL.md into on-demand
sections behind STOP pointers; the CODEX_SECOND_OPINION, DESIGN_MOCKUP and
DESIGN_SKETCH resolvers are untouched. Claude-host SKILL.md 73,248 -> 43,885
bytes. skill-diet before/after (Opus, 9 tasks x 3): success 26/27 -> 27/27,
median tokens per successful run 170,197 -> 124,941; blind judge after 10,
before 5 of 15. YC pitch, flattery and promo text unchanged (sections
byte-identical to main).

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

* feat(design-review): skill diet (GSTA-134 pilot 3)

Moves the outside voices and the test-framework bootstrap into on-demand
sections (the bootstrap now loads at Phase 8e.5, its only consumer: a
JS-behavior fix that needs a regression test with no known test command),
replaces the UX principles block with a Krug summary, and tightens the
DESIGN_METHODOLOGY prose (design-review is its only consumer). Shared
resolvers TEST_BOOTSTRAP and DESIGN_OUTSIDE_VOICES are untouched.
Claude-host SKILL.md 115,947 -> 84,869 bytes. skill-diet before/after
(Opus, 12 tasks x 3): success 32/36 -> 34/36, median tokens per successful
run 326,662 -> 257,819; blind judge after 9, before 5, tie 1.

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

* test: re-pin size, context and carve guards for the GSTA-134 skill diets

Every pin moves down except office-hours' parity maxSizeRatio (1.1796 ->
1.1921, GStack Minder's call as merge-queue owner): its union grew 1,662 B
because the second-opinion question now sits in the skeleton while the
untouched CODEX_SECOND_OPINION resolver keeps its own copy. design-review
leaves the size allowlist on every host.

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

* fix: drop the stale <affected-url> placeholder after the design-review Phase 8d diet

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

* fix: design-review checklist headers count the items they list after the diet

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

* docs: design-review report path and UX_PRINCIPLES consumers after the skill diets

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

* chore: CHANGELOG [Unreleased] for the GSTA-134 skill diets

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>
2026-10-28 04:17:22 +00:00