Skip to content

v1.91.260.0 feat(design-review,plan-design-review): craft audit and Persuade plan checks; craft tells as checker-only catalog entries (GSTA-92 phase 2) - #3433

Merged
capy-ai[bot] merged 32 commits into
mainfrom
garrytan/gsta92-phase2-review
Oct 27, 2026
Merged

capy-ai[bot] merged 32 commits into
mainfrom
garrytan/gsta92-phase2-review

Conversation

@garrytan

@garrytan garrytan commented Oct 26, 2026 •

Copy link
Copy Markdown
Owner
{
  "schema_version": 1,
  "pr": 3433,
  "head": "3b6642984f74d3e4bee9682202dbcda64c7fac0b",
  "version": "1.91.256.0",
  "base": "main",
  "gate": {
    "free-remote": {
      "pass": 18804,
      "fail": 0
    }
  },
  "spend_usd": 8.53,
  "session_kind": "unattended",
  "pregate": "requires-remote cleared @acaf610c82ff (1 checks, current for 3b6642984f74)",
  "requires_remote": [
    "free-tests.yml/macos-named-regressions: https://github.com/garrytan/gstack/actions/runs/40399241446",
    "windows-free-tests.yml/windows-free-shard: https://github.com/garrytan/gstack/actions/runs/40399241547",
    "pregate.json/remote_gate: remote-gate tree=acaf610c82ff tests=18804"
  ],
  "issues": {
    "fixes": [],
    "refs": [
      3420,
      3421,
      3422,
      3459,
      3481
    ],
    "flakes": []
  },
  "review_loop": {
    "passes": 1,
    "blocking_found": 0,
    "deferred": 0,
    "noted": 0,
    "fixed": 0,
    "scope": "unknown"
  }
}

Base main. #3420 and #3422 are merged (#3422 as v1.91.230.0), origin/main 021d817 (v1.91.240.0) is merged into this branch at f6e9893, origin/main b9222a5 (v1.91.247.0, after #3421) at d2018e1, origin/main fa3a240 (v1.91.251.0, after #3459's design lint) at 2ad5798, and origin/main 576839c (v1.91.256.0, after #3481) at 3b66429, all under rule-19 grants. Phase 2 of GSTA-92: /design-review audits Persuade pages and redesigns for craft, /plan-design-review checks a landing-page plan for its conversion basics, and the craft check's ids live in the design catalog.

What changed

Before and after for the review skills

Before, on main: neither review skill checked content realism, the ship floor or a landing page's conversion basics. After: /design-review reads an on-demand craft audit when the page is a Persuade surface or a redesign, and /plan-design-review's Pass 1 runs five Persuade plan checks. The caption line gives the always-loaded cost.

  • /design-review craft audit (design-review/sections/craft-audit.md). design-review is now carved on every host (CARVED_ON_EVERY_HOST), and the audit is read in Phases 1-6 for a Persuade page or a redesign:
    • It runs gstack-design-craft on each page's served HTML, or on the repo file when no app runs, and files each CRAFT_CHECK as a category 9 finding.
    • The saved page holds session data. It is deleted in the block that checks it, whatever the exit code, and never copied to the report. Aside saves it as .{page}.html.
    • A saved page holds only inline CSS and JS, so tells in linked files are judged by eye. With no CRAFT_RESULT line, or for a mount-node shell, the check is marked unavailable and judged by eye.
    • --accepted takes that screen's finalized.json, only for a page /design-html finalized, and never covers needs-proof or lorem. A claim without proof is never marked or cut, whatever a rule or the printed fix says: it is deferred and the user is asked for the proof.
    • It covers what the check can't see, five Persuade checks, each failure filed as a deferred High, Elaya's fix order as the Phase 8 tie-break, and the installed Tailwind major version.
    • Shared rules render word for word from /design-html's craft section through scripts/resolvers/design-craft.ts.
  • /plan-design-review: for a Persuade plan, Pass 1 checks one primary action, named objections, proof beside each claim, a real risk reversal and an index/noindex decision. The runner checklist names them.
  • Catalog: the 16 craft tells are checkerOnly entries in lib/design-catalog.ts, reported only by gstack-design-craft with the catalog's fix. They stay out of every rendered skill list. transition: all reports under layout-transition.
  • Touchfiles: design resolver cases and judges also select on scripts/resolvers/design-craft.ts; design-html-slop-gate also on lib/design-catalog.ts.
  • Docs: ARCHITECTURE.md lists the two craft placeholders and every carved-on-every-host skill; docs/PROJECT_STRUCTURE.md lists the design-craft resolver.

Why

The craft section #3420 added to /design-html only helps pages built from scratch. Existing sites and landing-page plans go through /design-review and /plan-design-review, and those skills had no check for invented content, dead links, a missing skip link, scroll-listener reveals or 100vh, nor for a plan with no primary action, unanswered objections or unsourced proof.

Approvals

Date Asked Garry's words Covers Pending
2026-10-25 Absorb the Elaya design skills "Absorb all the interesting parts of this design skill https://github.com/elayadesign/ai-design-skills" Phase 1 (#3420) none
2026-10-25 Plan ask incl. Phase 2 pin raises (via GStack Minder) "Do it" design-review and plan-design-review pins raised to measured size, plus the catalog move (autoplan gate_rev=1, rec_hash=2592f8063bfc) none
2026-10-25 Trimmed sizes: design-review +584/+614, plan-design-review +1,082, consultation 0 (GStack Minder) n/a (captain approval under Garry's "Do it") These measured sizes. /ship's review later lowered the design-review pins by 6 bytes on all 12 hosts (+578/+608) and maxSkeletonBytes 137,773 → 137,767; nothing rose none
2026-10-25 /ship cycle-cap exception 1 (lane parent) n/a (lane decision) cycle-cap exception (GSTA-92 lane, 2026-10-25): reverted 216987e's checker half to bed645a's reviewed behavior; byte-neutral prose reword; no new logic none
2026-10-25 /ship cycle-cap exception 2 (GStack Minder) under Garry's "do it" second cycle-cap exception: GStack Minder's decision under Garry's 'do it' on phase 2 (GSTA-92, 2026-10-25): one deleted word plus one test none
2026-10-25 Ship c7e0f74 as is after pass 6 (GStack Minder) n/a (captain decision) the two informational pass-6 findings below ship as documented none
2026-10-26 /ship cycle-cap exception 3 after the main merge (GStack Minder) n/a (captain decision) third cycle-cap exception (Captain, 2026-10-26): zero-byte reword closing the content-deletion path; test pin and carve-guard mustContain moved (51a117a). No carve-guard mustContain held the sentence, so only the test pin moved. Then one verification-only pass, no edits none
2026-10-26 R3 finding 2, the transition-all → layout-transition exception id (GStack Minder) n/a (captain decision) first deferred to the exception-matching follow-up; then fixed in 8cb08f2 under the rule-19 grant that reconciled the craft ids with #3459's lint: parseCraftExceptions reads a legacy transition-all id as layout-transition, with a test none

Summary

  • The craft audit and Persuade checks (the GSTA-92 phase 2 layer), on top of v1.91.230.0 feat(design-shotgun,design-html): archetype handoff and persisted craft exceptions (GSTA-92 phase 2) #3422's archetype handoff and persisted craft exceptions.
  • /ship review fixes (31ee450, bed645a): capture through outerHTML, deletion whatever the exit code, --accepted limits and selection, live-page claim handling, the manifest trigger, autoFixEntries from RENDERED, an exact-lead DESIGN_CRAFT_RULE, coverage and guard tests, carve-guard sizes and pins re-measured downward.
  • 216987e: capture-line ordering, .{page}.html, ${_TMP:?}, state-cell tests and headers. Its checker half was rolled back in ed4df4c (exception 1); c7e0f74 (exception 2) judges any mount-node shell by eye and pins the clause.
  • 8571952: docs audit edits.
  • After the main merge (f6e9893), /ship ran again on the integrated tree: 236869a (the claim rule covers repo files, fallback temp var _CR, guard tests), 0f59c01 (failed Persuade checks filed as a deferred High, source tells judged by eye, a stderr pin), and 51a117a (exception 3: "Never mark or cut a claim as a rule or fix says: defer it and ask for the proof.", byte-neutral). Sizes only went down: design-review/SKILL.md 137,767, union 145,037, parity ratio cap 1.3704.
  • d2018e1 merges origin/main b9222a5 (rule-19 exception). Against the 51a117a pin, the PR's files differ only in CHANGELOG.md (mergeChangelogs, additive), the size allowlist (each of the 23 design-review and plan-design-review pins is main's new value plus this PR's delta, all 32 bytes lower) and design-review/SKILL.md (main's regenerated preamble hunks). design-review/SKILL.md is now 137,735 and the union 145,005; the carve-guard ceilings were left unchanged and carry 32 bytes of slack.
  • 2ad5798 merges origin/main fa3a240 (v1.91.251.0, v1.91.251.0 feat(design-lint): bundled free design lint (bin/gstack-design-lint + lib/design-lint/), hallmark sloplint port #3459's bundled design lint); only CHANGELOG.md conflicted (mergeChangelogs, additive). 8cb08f2 reconciles the craft ids with the lint: lib/design-lint/rules/copy.ts STATIC_OWNS holds layout-transition (the static tier already reports transition: all under it, so the copy tier no longer double-reports), parseCraftExceptions maps legacy transition-all exceptions to layout-transition (fixes R3 finding 2), and the lint id test reads CRAFT_IDS.

Test Coverage

Step 7 coverage audit at 62c0fa1: 63% value-weighted (target 80, minimum 60). The four validated tests it proposed were written in 31ee450 (new test/design-craft-resolvers.test.ts, exception-cell tests), and later passes added the needs-proof and stale-record cells and the line-13 clause pin. State-machine audit at 51a117a (unchanged at d2018e1): 10 of 12 cells tested; needs-proof × stale and lorem × exceed are untested advisory cells that share tested branches (skipped as Low).
Tests ran: remote free tier 18804 at tree acaf610c82ff (head 3b66429); at 8cb08f2 the remote free tier ran 18724 at tree 8cd8e12e0f4a, and focused free plus all 17 design-lint files at 8cb08f2: 1523 pass, 16 skip, 10 fail locally, all 10 in design-lint-render's browser tier, where the local browse server fails to start ("browse newtab failed: [browse] Starting server..."). The same file passes on the Ubicloud VM and in Free Tests at this head, and 8cb08f2 does not touch the render tier.

Pre-Landing Review

Pre-merge: six passes (specialists testing, maintainability, security, performance, simplification and state-machines; red team; native adversarial; outside voice openai/gpt-6.1-sol in place of Codex, which is not installed). Passes 1-3 fixed what they found (31ee450, bed645a, 216987e) and reached /ship's three-cycle cap. Passes 4-6 were verification-only, and the edits between them ran under the two exceptions above.

Delta round at 3b66429 (rule 23, git diff 8cb08f2 3b66429 on the PR's files: the main merge only; allowlist pins are main plus this PR's delta, CHANGELOG additive, carve-guard and placeholder edits are main's own): native plus outside voice openai/gpt-6.1-sol, NO FINDINGS (VERDICT: no_findings). REVIEW_LOOP: passes=1 blocking_found=0 deferred=0 noted=0 fixed=0.

Delta round at 8cb08f2 (rule 23, git diff d2018e1 8cb08f2 only; native plus outside voice openai/gpt-6.1-sol VERDICT: no_findings): no blocking findings. Non-blocking, deferred to #3459's follow-up: the lint's static tier does not read inline style attributes, so a page whose only transition: all is inline gets no lint finding (checkCraft still reports it). This is pre-existing in #3459 under the old id, not a regression.

Merge round at d2018e1: a merge-scope review (native and outside voice openai/gpt-6.1-sol, VERDICT: no_findings) found nothing; all 23 pins match main plus the PR delta, CHANGELOG [Unreleased] is byte-identical to the pin's, and generated docs are fresh on every host. Informational: the design-review carve-guard ceiling and ratio now leave 32 bytes of slack after main's preamble shrink. Pass count: three fixing passes after the first merge (R1-R3), one verification-only pass (R4), one merge-scope pass (R5), one delta pass (R6), one delta pass (R7).

Post-merge on the integrated tree: R1 (f6e9893) and R2 (236869a) fixed what they found; R3 (0f59c01) reached the cycle cap with one Medium finding (the checker's printed fix text, "drop the claim" / "remove the claim before publishing", could lead Phase 8 to delete a real claim), closed by exception 3 in 51a117a. The R4 verification-only pass at 51a117a ran all nine reviewers with no edits: outside voice VERDICT: no_findings, red team, security, performance, simplification and testing clean. It found nothing beyond wording, and these Low wording-only notes ship as is:

  • CHANGELOG.md:13: "skeleton, union and parity ratio at their measured sizes" overstates the union guard, which is a floor (maintainability).
  • design-review/sections/craft-audit.md.tmpl:35: Phase 8 has no pointer back to the craft audit's fix-order section, so after compaction the tie-break and Tailwind check rely on memory; a pointer does not fit the byte cap (native adversarial, confidence 6).
  • craft-audit.md.tmpl:7,13: the repo-file path judges framework source by eye inside Phases 1-6, against "Never read source code" (native adversarial, confidence 5).

Shipping with these informational findings from the pre-merge passes (GStack Minder's decision):

  • design-review/sections/craft-audit.md.tmpl:13: "mount-node shell" is undefined, so an agent could read a hydrated SPA as a shell (red team and native adversarial, confidence 4). The "an empty mount node" wording goes to the follow-up PR with shell detection.
  • CHANGELOG.md: the Tests bullet's last sentence names the stale-record cell twice (maintainability).
  • FAQPage JSON-LD as a High Persuade check, and the Pass 1 vs Pass 4 Persuade lists in /plan-design-review: informational.

Deferred to #3422's follow-up PR (exception matching, provenance and shell detection):

  • acceptFindings accepts needs-proof and lorem in code; the craft audit files them anyway.
  • Agent-accepted craft exceptions persist without user confirmation (design-html/sections/craft.md.tmpl:66; the hand-off still lists every one). The follow-up adds who accepted each exception and user confirmation before it persists.
  • Documented checker limitations: it counts script bodies, so a hydration payload that repeats the markup double-counts code rules; it gives a CRAFT_RESULT for mount-node shells (CRA/Vue <noscript> shells included); single-quoted inline handlers are not read for alert(); presence rules can match text inside scripts; commented-out markup is scanned; a body with only images or web components is checked as is.

Gate edits: none detected (18 listed, 11 eligible, 11 read, unread=0 at 8cb08f2 (21 listed, 12 eligible, 12 read); patterns: RH-1,RH-3,RH-4,RH-12,RH-13,RH-14,RH-15,RH-16; unlisted idioms: none)
Outside review: R7 VERDICT: no_findings at 3b66429, R6 at 8cb08f2, R5 at d2018e1 and R4 at 51a117a (openai/gpt-6.1-sol); Codex unavailable (not installed).

Exploratory QA

The craft checker was exercised by reviewers on scratch HTML (Vite, CRA, Vue CLI and Next shells, hydration payloads, commented scripts, image-only bodies). Results are in the findings above.

Design Review

No frontend files changed — design review skipped.

Eval Results

Focused paid case at the final head 3b66429: touchfiles selects no gate-tier case for the 8cb08f2..3b66429 delta. It selects 18 periodic or marathon cases (carve-section-loading for 16 skills, office-hours-section-loading, office-hours-design-draft), all through main's own edits to the ship and review entries in test/helpers/carve-guards.ts. This PR's skill among them ran: carve-section-loading-plan-design-review PASS 1/1 (no cost reported). The rest were not run, to stay under the $10 per-PR lane cap.

Earlier evidence at 8cb08f2. design-html-slop-gate runs because lib/design-craft.ts changed. Touchfiles selected four of the six design cases for the d2018e1..8cb08f2 delta on the PR's files: design-review-detector-shim, design-review-detector-shim-dom, design-review-plugin-handoff and plan-design-with-ui-scope. It did not select plan-design-review-no-ui-scope or plan-mode-no-op. For 8cb08f2's own files alone it selects only design-html-slop-gate.

  • design-html-slop-gate (behavior): PASS 3/3 ($0.30, $0.33, $0.29)
  • design-review-detector-shim: PASS ($0.13)
  • design-review-detector-shim-dom: PASS ($0.26)
  • design-review-plugin-handoff: PASS ($0.13)
  • plan-design-with-ui-scope: PASS 1/1 (PTY case; no cost reported)

Earlier evidence at d2018e1:

  • design-review-detector-shim: PASS ($0.13)
  • design-review-detector-shim-dom: PASS ($0.25)
  • design-review-plugin-handoff: PASS ($0.14)
  • plan-design-review-no-ui-scope: PASS ($0.06)
  • plan-design-with-ui-scope: PASS 1/1 (PTY case; no cost reported)
  • plan-mode-no-op: PASS, 6/6 subtests (PTY case; no cost reported). The first attempt was cut off by a machine restart after 4 passing subtests and rerun once at the same head (launch interruption, not a flake).
  • judge "design-review/SKILL.md fix loop": PASS, 4/4/4 ($0.06)

Earlier evidence at 51a117a:

  • design-review-detector-shim: PASS ($0.14)
  • design-review-detector-shim-dom: PASS ($0.24)
  • design-review-plugin-handoff: PASS ($0.14)
  • plan-design-review-no-ui-scope: PASS ($0.11)
  • plan-design-with-ui-scope: PASS 1/1 (PTY case; the runner reports no cost)
  • plan-mode-no-op: PASS, 6/6 subtests (PTY case; no cost reported). The first attempt was cut off by a machine restart after 4 passing subtests and rerun once at the same head; that is a launch interruption, not a flake.
  • judge "design-review/SKILL.md fix loop": PASS, 4/4/4 ($0.06)

Earlier evidence at 0f59c01 (all PASS: the six cases and the judge) and a cancelled partial run at 236869a.

Pre-merge, at c7e0f74 (the docs-only commit after it selects no case):

  • design-review-detector-shim: PASS ($0.13)
  • design-review-detector-shim-dom: PASS ($0.28), a real DOM-mode run with the browse binary built
  • design-review-plugin-handoff: PASS ($0.14)
  • judge "design-review/SKILL.md fix loop": PASS, 4/3/4 ($0.06)

At 62c0fa1: plan-design-review-no-ui-scope, plan-design-with-ui-scope, carve-section-loading-plan-design-review, plan-design-review-plan-mode, plan-design-review-plan-mode-smoke, review-design-lite (3/3 trials) and design-consultation-core all PASS. plan-design-finding-floor timed out once, then passed its rerun, and is logged in the flaky ledger. The "plan-design-review/SKILL.md passes" judge passes. design-review-fix needs Aside on macOS and was not run. The design-consultation research judge was deselected by touchfiles, since design-consultation is unchanged.

Greptile Review

No Greptile comments.

Plan Completion

No plan file found — plan completion not run.

Issues

Refs #3420
Refs #3421
Refs #3422
Refs #3459
Refs #3481

Verification Results

No Step 8.1 obligations (no plan file).

TODOS

No TODO items completed in this PR.

Documentation

Status: current at 51a117a. Since the last audit, only craft-audit prose, tests and carve guards changed; the ARCHITECTURE.md and docs/PROJECT_STRUCTURE.md lines still match (they name files and placeholders, not wording). The audit below is from the pre-merge round.

Pre-merge status: updated. Three factual doc edits; no blockers.

Scope: base 8d95013..c7e0f74 on garrytan/gsta92-phase2-review: 33 committed files, with no staged, unstaged or new files. The change is GSTA-92 phase 2: the /design-review craft audit section (design-review is now carved on every host), the /plan-design-review Persuade checks, gstack-design-craft --accepted with craft_exceptions in finalized.json, the /design-shotgun archetype handoff to /design-html, and the craft tells moved into catalog checkerOnly entries. Read in full: ARCHITECTURE.md, docs/PROJECT_STRUCTURE.md, NOTICE.md, AGENTS.md and the new craft-audit template. Read by relevant section or diff hunk: CLAUDE.md, README.md, docs/skills.md, CONTRIBUTING.md, docs/TESTING_INTERNALS.md and the changed design templates.

Doc diff preview:

  • ARCHITECTURE.md: added {{DESIGN_CRAFT_RULE:<lead>}} and {{DESIGN_PERSUADE_CHECKS}} rows to the placeholder table. The runGeneration() paragraph now names CARVED_ON_EVERY_HOST (qa, qa-only, ship, plan-ceo-review, office-hours, design-review) instead of only QA/qa-only.
  • docs/PROJECT_STRUCTURE.md: added design-craft to the resolver-module list.

Documentation health:

  • ARCHITECTURE.md: Updated (placeholder rows, carved-on-every-host list)
  • docs/PROJECT_STRUCTURE.md: Updated (design-craft resolver)
  • docs/skills.md: Current (this branch's archetype handoff lines are accurate)
  • NOTICE.md: Current (the new Elaya-derived files are attributed)
  • README.md: Current
  • AGENTS.md: Current
  • CLAUDE.md: Current
  • CONTRIBUTING.md: Current
  • CHANGELOG.md: not voice-audited (Step 5 is outside ship-owned scope)
  • TODOS.md: not touched (Step 7 is outside ship-owned scope)

Documentation Debt

  • ⚠️ /design-review craft audit (sections/craft-audit.md): reference only in skill prose. The docs/skills.md deep dive and the README row have no how-to.
  • ⚠️ /plan-design-review Persuade checks: skill prose only. docs/skills.md describes the seven passes and does not mention the Persuade plan checks (how-to).
  • ⚠️ gstack-design-craft --accepted and finalized.json craft_exceptions: reference only in the design-html craft section and the bin header. There is no user-facing how-to.
  • ⚠️ checkerOnly catalog entries: code and CHANGELOG only. docs/designs/IMPECCABLE_INTEROP.md does not explain checker-only entries.
  • Older debt: the craft check (bin/gstack-design-craft, lib/design-craft.ts) is missing from the docs/PROJECT_STRUCTURE.md bin/lib lists and from the CONTRIBUTING.md test families.

Diagram drift: none. No diagram entity changed. Suggest a docs-debt label and a /document-generate pass for the gaps.

Test plan

Open in Capy

garrytan and others added 12 commits October 25, 2026 21:03
…laya design skills (GSTA-92)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
…drop a $-digit literal from craft.md; count only craft-check executions in design-html-slop-gate

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

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

# Conflicts:
#	CHANGELOG.md
…roved.json; persist accepted craft exceptions in finalized.json (GSTA-92 phase 2)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
…ost, Persuade plan checks, craft tells as catalog entries (GSTA-92 phase 2)

Size pins and caps raised to measured sizes only: design-review (13 hosts), plan-design-review (12), design-consultation (9), design-consultation maxSizeRatio, and the new design-review parity guard. Garry 2026-10-25 "Do it" (GSTA-92).

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
…design-review and plan-design-review growth to the planned size (GSTA-92)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
… runs (GSTA-92)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
…n the craft resolver; slop gate on the catalog (GSTA-92)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
…-92)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
…3420)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
…/gsta92-phase2-review (retarget after #3420)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
@capy-ai
capy-ai Bot changed the base branch from garrytan/gsta92-phase2-handoff to main October 26, 2026 00:36
@trunk-io

trunk-io Bot commented Oct 26, 2026 •

Copy link
Copy Markdown

😎 This pull request was merged.

garrytan and others added 4 commits October 26, 2026 00:49
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
A malformed or missing --accepted exceptions file now gets the full craft
check with nothing accepted, after a warning, still exiting 2. Before, it
printed nothing, and the craft section treats a missing CRAFT_RESULT as
'check unavailable', so one bad finalized.json switched the gate off
(found by both adversarial passes). The header comment and the craft
section now document the accepted-count suffix on CRAFT_RESULT. Tests
cover duplicate carried-forward exception ids and the slop-gate touchfiles
selection.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
The craft section passed --accepted whenever a finalized.json sat beside
the page, so a same-day Start fresh build inherited the old page's
exceptions. It now passes them only when evolving or rerunning a page it
finalized, records the count the check reports now, and writes [] when
nothing was accepted instead of the template's placeholder entry. A test
pins exit 2 for a clean page with a broken exceptions file.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
… (GSTA-92)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
garrytan and others added 7 commits October 26, 2026 01:31
…n/gsta92-phase2-review

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
…STA-92)

- craft-audit: no CRAFT_RESULT line means unavailable (exit 2 after a
  malformed --accepted record still printed findings); --accepted only for a
  /design-html finalized page, never for needs-proof or lorem; never add
  [Needs proof] markers to a live page; Aside capture via pg.evaluate; the
  saved raw DOM is deleted in the checking block and never reported
- manifest trigger covers an explicit craft audit (skeleton -6 bytes; pins
  lowered to measured size, union ratio back under its cap)
- autoFixEntries reads RENDERED; DESIGN_CRAFT_RULE needs exactly one lead
- tests: checkerOnly contract, resolver throw paths, Persuade checks in both
  skills, resolver touchfile selection, exception state cells
- CHANGELOG: host counts and the audit's new rules

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
- craft-audit: linked CSS/JS is unchecked on a saved page (judge by eye);
  a mount-node shell is framework source; --accepted takes that screen's
  finalized.json or none; on a live page a claim without proof is filed and
  asked about, never marked or cut; the saved page is removed whatever the
  exit code; shorter fix-order and Tailwind prose keeps the union under cap
- tests: exact-lead red cases, autoFixEntries in the checkerOnly union, the
  audit's outcome/exception/session-data clauses; carve guard checks the
  session-data rule and records measured sizes (skeleton cap 137_767)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
…ture order (GSTA-92)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
…ount-node shell judged by eye (GSTA-92)

cycle-cap exception (GSTA-92 lane, 2026-10-25): reverted 216987e's checker half to bed645a's reviewed behavior; byte-neutral prose reword; no new logic

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
…GSTA-92)

second cycle-cap exception: GStack Minder's decision under Garry's 'do it' on phase 2 (GSTA-92, 2026-10-25): one deleted word plus one test

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
…craft resolver (GSTA-92 /ship docs audit)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
garrytan and others added 3 commits October 26, 2026 10:10
…ded)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
…o files, craft temp var, guard tests (GSTA-92)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
…s source tells by eye; stderr pin (GSTA-92)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
garrytan and others added 5 commits October 26, 2026 10:40
Pass R3 (native adversarial, Medium): the CRAFT_CHECK fix text for
round-number and needs-proof says to drop or remove the claim, which
could lead Phase 8 to delete a real claim. The audit sentence now
covers both a rule and the printed fix: defer the claim and ask for
the proof. Byte-neutral (80 -> 80); design-review/SKILL.md 137,767,
union 145,037, unchanged. The test pin moves with the sentence; no
carve-guard mustContain held this sentence.

third cycle-cap exception (Captain, 2026-10-26): zero-byte reword closing the content-deletion path; test pin and carve-guard mustContain moved

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

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

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
…s static-tier; legacy transition-all exceptions map to it)

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

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
….0 (train slot 1)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
@github-actions github-actions Bot changed the title feat(design-review,plan-design-review): craft audit and Persuade plan checks; craft tells as checker-only catalog entries (GSTA-92 phase 2) v1.91.260.0 feat(design-review,plan-design-review): craft audit and Persuade plan checks; craft tells as checker-only catalog entries (GSTA-92 phase 2) Oct 27, 2026
@capy-ai
capy-ai Bot merged commit 6c5b2d4 into main Oct 27, 2026
62 checks passed
garrytan added a commit that referenced this pull request Oct 27, 2026
…ded); catalog budget re-measured for design-motion

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant