Files
gstack/test/fixtures/design-outside-y-calls.json
T
Garry TanandOpenAI Codex 9f81911136 v1.86.0.0 feat: route outside reviews by harness (#2850)
* feat: add a restricted and supervised Claude Code runner

Preserve configured authentication and models while enforcing tool access, strict completion JSON, bounded output and process cleanup. Cover argv, failure handling, session metadata and Windows process containment.

* feat: route outside reviews by harness and migrate wrapper installs

Use Claude Code from Codex and Codex from other supported hosts, with shared invocation rendering, positive gate validation and per-phase provenance. Rename /claude to /claude-code, repair managed shared and copied installations safely, and generate native Kiro skills. Add installed-workflow, failure-injection and live cross-harness regression coverage.

* test: recognize CEO mode labels without terminal spacing

The paid workflow rendered SCOPEEXPANSION at option 4, but its driver required a literal space. Match the leading mode title without cursor-spacing artifacts and ignore adjacent preview text. Preserve missing-target failures and downstream posture assertions.

* test: isolate plan-count fixtures before starting review workflows

Seed the complete test plan in a private git repository before launching Claude, so a bare slash command cannot review the live workspace while a delayed fixture message remains queued. Preserve count thresholds, parsers and budgets. Add initial-context and installed-discovery tests, and retain startup/terminal diagnostics on failed evaluations.

* test: stabilize review fixtures and Claude eval startup

Preserve source boundaries in workflow judge inputs, isolate CEO mode plans, and wait for interactive trust input readiness. Keep startup failure evidence and retain existing models, budgets, and assertions.

Co-Authored-By: OpenAI Codex <noreply@openai.com>

* test: classify collapsed review modes and isolate seeded findings

Keep review questions out of the setup count when terminal cursor positioning removes spaces. State existing webhook safeguards so the five-finding control measures its seeded defects without accidental extra security and concurrency gaps. Preserve question bands and the paired control.

Co-Authored-By: OpenAI Codex <noreply@openai.com>

* test: isolate browser daemon state across free shards

Co-Authored-By: OpenAI Codex <noreply@openai.com>

* test: stabilize native review counting and interactive navigation

Co-Authored-By: OpenAI Codex <noreply@openai.com>

* chore: prepare v1.82.0.0 release

Co-Authored-By: OpenAI Codex <noreply@openai.com>

* fix: eliminate browser and process-cleanup test flakes

Pin every CI surface to Bun 1.4.0 to avoid extra-stdio finalizers closing
reused live sockets. Add an isolated GC/listener regression that fails on
Bun 1.3.13, and prevent coordinated rollback to an affected CI runtime.

Check renderer cleanup against the render's own staging directory so
concurrent renders cannot invalidate the assertion. Make the no-pgrep
process-tree walk tolerate disappearing /proc entries, and synchronize
its test fixture through child readiness and pipe EOF instead of sleeps.

Validation: 9,157 passed, 31 skipped, zero failures across 556 files with
retries disabled. Build, all-host generation freshness, and skill checks
passed. All three races have failing-before/passing-after regressions.

* fix: count completed native review questions in evals

* fix: drive review navigation from confirmed native choices

* fix: require complete section-loading eval reports

* test: isolate telemetry HTTP transport from local assertions

* fix: keep review input on the active native question

* test: let tunnel revocation daemon choose an available port

* test: allocate available ports for pairing and watchdog fixtures

* fix: stabilize planning eval navigation and phase reporting

* test: isolate installed runtime paths in planning evals

* test: stabilize review evidence and concurrent refresh fixtures

* fix: resolve design findings before editing the plan

* fix: honor and persist disabled outside plan reviews

* fix: preserve planning decisions and terminal evidence

Load installed host reviews at autoplan phase entry and wait for completed
reviewers and saved artifacts. Reuse approved remedies while preserving
individual finding decisions.

Drive interactive evals from the current terminal viewport, bind native
questions across scrolling, and require complete native report evidence.
Cover captured stale menus, permission lifecycles, setup classification,
and disabled-review tool availability with deterministic regressions.

Advance release metadata and the upgrade migration to the unclaimed
1.83.0.0 slot.

* fix: drive native review questions and preserve current plans

Use the native single-choice keyboard protocol and current terminal viewport,
with per-question navigation inside packets and completed-call coverage.
Keep permissions, multi-select menus, and Submit controls distinct.

Send Autoplan reviewers the amended implementation plan, keep its review record
separate, and supply retained application contracts in the chain fixture.
Clarify individual DevEx decisions and complete CEO fix options; use one active
plan destination for the section-loading report.

* fix: preserve complete plan-review decisions

* fix: recognize native plan dialogs and reviewer controls

* fix: preserve review decisions and phase completion

* fix: recognize completed reviews without losing findings

* fix: preserve review continuity and native eval completion

* test: fix native review completion and eval retry isolation

* test: handle native review menus and complete eval fixtures

* test: fix native review setup, completion, and isolation failures

* test: limit native skill discovery to runtime assets

* fix: bind Autoplan reviews to full ordered phase inputs

* test: fix planning eval routing, counting, and timeout handling

* chore: advance queued release to v1.84.0.0

* fix: preserve complete review inputs and planning decisions

* fix: reconcile review approvals and preserve phase obligations

* fix: preserve review obligations and unblock eval permissions

Carry recorded Autoplan requirements into blind phase inputs, require Eng
review approvals before exit, and exercise combined asynchronous flows in
CEO reviews. Correct native finding and handoff classification and unblock
repeated report edits using scoped request identities.

* fix: retain plan requirements and complete native review dialogs

* fix: complete native review prompts and retain plan references

* fix: preserve review inputs and classify native eval evidence

* fix: check competing completion orders in CEO reviews

* fix: recognize review decisions and require phase methodology

Require the current phase methodology before Autoplan snapshots. Correct
substantive decision, closed handoff, and cache-finding classification, and
honor the recommended implementation approach in native review dialogs.

Add captured-transcript regressions without changing review thresholds,
provider models, retries, or deadlines.

* test: bind native review decisions and close completed handoffs

* fix: complete review dialogs and verify methodology delivery

* fix: preserve review evidence and unblock native eval prompts

* fix: handle native review question completions

* fix: recognize native review narration and controls

* fix: count native review decisions and isolate eval fixtures

* test: verify seeded review coverage and current artifact permissions

* test: isolate model and brain-aware skill renders

* fix: repair native workflow evaluation and clarify review steps

* fix: stabilize workflow eval evidence and review guidance

* test: repair native workflow observation and fixture isolation

* fix: recognize completed workflow evidence and owned skill reads

* test: repair seeded workflow delivery and completion evidence

* test: recognize current review evidence across native forms

* test: handle native review variants and permission redraws

* fix: honor review preferences and recognize native eval evidence

* test: recognize completed review decisions and queued permissions

* test: match current review contracts and partial-line edits

* test: recognize completed workflow evidence and bounded human waits

* fix: preserve review entry gates and native eval interactions

* fix: recognize native workflow evidence and preserve review gates

* test: recognize current review evidence and preconfigure workflow fixtures

* test: recognize completed review findings and scoped artifact permissions

* fix: stabilize native workflow review and permission evidence

* fix: recognize current review evidence and scoped edit confirmations

Clarify Design and engineering review entry instructions and Design scoring.
Recognize required legacy coverage and public Autoplan completion recaps.
Bind the pending Edit confirmation to its exact file, ordered digest, and
one-request approval when a preceding command display remains visible.
Keep reviews within their existing size limits and preserve scope gates
when extracting workflow fixtures from either supported preamble header.

Keep failure outcomes, review thresholds, provider choices, and eval budgets.

* fix: recover review workflow progress and eval evidence

* fix: recognize valid review evidence and scope selection

* test: fix review evidence parsing and repeated artifact prompts

* test: recognize valid review decisions and pending native cards

* fix(plan-eng-review): keep final navigation consistent with approved tasks

* test: recognize valid review evidence and bind legacy diff requests

* fix: stabilize review eval evidence and harness repair guidance

* docs: update project documentation for v1.85.0.0

Co-Authored-By: OpenAI Codex <noreply@openai.com>

* test: fix Windows CI fixtures and credential scan

Rebase captured JSON values and filesystem evidence using the appropriate
path convention. Compile native fake CLIs on Windows and synchronize pipe
holder readiness, with cleanup retained when assertions fail.

Assemble synthetic credential fixtures at runtime so the added-line scan
keeps enforcing the same gate without flagging its own rejection controls.

Discover generated skills directly for the empty-find regression check,
avoiding a recursive scan through saved evaluation artifacts and dependencies.

* fix: preserve source renders on Windows

Compare canonical generator paths using native separators so an output
sidecar pointing at the source cannot overwrite its skill or metadata.
Keep the regression fixture isolated from the real checkout and expose
freshness diagnostics before asserting subprocess status.

Detach Windows drain-test pipe holders from the fake provider's automatic
child cleanup while preserving the enclosing runner job and its assertions.

* fix: clarify outside review fallback and CEO decisions

Render one applicable own-harness fallback path and retain native review,
disabled policy, and missing-coverage semantics. Align report field names
and mode labels, and make the existing per-cut scope approval explicit.

Regenerate skill outputs and keep the workflow judge's model, thresholds,
and retry policy unchanged.

* chore: move release to free version slot (v1.86.0.0)

PR #2852 now claims v1.85.0.0. Align the release metadata and
rename migration so upgrades from that version still receive it.

Co-Authored-By: OpenAI Codex <noreply@openai.com>

* fix: include engineering review prerequisites and restore branch context

* fix: recognize coverage diagrams and clarify design review instructions

* fix: preserve file identities and join Windows test processes

---------

Co-authored-by: OpenAI Codex <noreply@openai.com>
2026-09-14 14:32:45 -07:00

243 lines
14 KiB
JSON

[
{
"sessionId": "b6b8f7c7-a50c-4ccd-9996-4b321309a017",
"toolUseId": "toolu_016LskTqkTpnBoXPf7inaJbq",
"questions": [
{
"question": "D1 \u2014 Run outside design voices before the review passes? <gstack-qid:plan-design-review-outside-voices>",
"header": "Outside voices",
"options": [
{
"label": "No \u2014 proceed without (recommended)",
"description": "Skip Codex + Claude subagent outside pass. Best for this case: it's a scoped settings form update with a complete DESIGN.md; hard-rejection checks apply to marketing surfaces, not OPERATE/settings UI."
},
{
"label": "Yes \u2014 run Codex + Claude subagent",
"description": "Run Codex against OpenAI design hard rules + litmus checks, and a separate Claude subagent for an independent completeness review. Adds time but catches anything a single-model pass misses."
}
],
"multiSelect": false
}
],
"answered": true,
"failed": false,
"answers": {
"D1 \u2014 Run outside design voices before the review passes? <gstack-qid:plan-design-review-outside-voices>": "No \u2014 proceed without (recommended)"
},
"unansweredQuestionIndices": [],
"answeredAt": "2026-09-09T11:09:50.422Z"
},
{
"sessionId": "b6b8f7c7-a50c-4ccd-9996-4b321309a017",
"toolUseId": "toolu_01Mptx24PCxWs9mfwqYqbVyY",
"questions": [
{
"question": "D2 \u2014 Pass 2: Export pending state is not specified in the plan. What should the user see while the JSON download is being prepared? <gstack-qid:plan-design-review-export-pending>",
"header": "Export pending",
"options": [
{
"label": "Disable + spinner (recommended)",
"description": "Apply the same DESIGN.md pending pattern used by Save: disable the Export button, show an inline spinner beside \u201cExporting\u2026\u201d, aria-busy=true. Reuses existing component behavior; prevents duplicate downloads; consistent with Save pending UX. (human: ~30min / CC: ~5min)"
},
{
"label": "Disable only, no spinner",
"description": "Disable the Export button while downloading but show no spinner. Prevents double-clicks but gives no progress signal. Simpler, but inconsistent with Save pending pattern; user may think it froze. (human: ~15min / CC: ~3min)"
},
{
"label": "Leave unspecified \u2014 implementer decides",
"description": "Defer this to the implementer. Risk: engineer ships a frozen Export button, users click it multiple times and receive duplicate downloads."
}
],
"multiSelect": false
}
],
"answered": true,
"failed": false,
"answers": {
"D2 \u2014 Pass 2: Export pending state is not specified in the plan. What should the user see while the JSON download is being prepared? <gstack-qid:plan-design-review-export-pending>": "Disable + spinner (recommended)"
},
"unansweredQuestionIndices": [],
"answeredAt": "2026-09-09T11:10:18.487Z"
},
{
"sessionId": "b6b8f7c7-a50c-4ccd-9996-4b321309a017",
"toolUseId": "toolu_01AWCbis4SQmcNnFXLZHBjfC",
"questions": [
{
"question": "D3 \u2014 Pass 2: The plan says 'the existing form skeleton' for initial load. Is this skeleton truly already built, or is it new work that needs a visual spec? <gstack-qid:plan-design-review-skeleton>",
"header": "Skeleton status",
"options": [
{
"label": "Already built \u2014 no new spec needed (recommended)",
"description": "The skeleton component exists and works today. Plan correctly references it. Implementation task just needs to point to the existing component; no shimmer or gray-box spec required."
},
{
"label": "New work \u2014 needs visual spec",
"description": "The skeleton does not yet exist. The plan needs to describe which elements shimmer (input fields? section headings? the action group?). Adds spec work before implementation can start. (human: ~1h / CC: ~10min)"
}
],
"multiSelect": false
}
],
"answered": true,
"failed": false,
"answers": {
"D3 \u2014 Pass 2: The plan says 'the existing form skeleton' for initial load. Is this skeleton truly already built, or is it new work that needs a visual spec? <gstack-qid:plan-design-review-skeleton>": "Already built \u2014 no new spec needed (recommended)"
},
"unansweredQuestionIndices": [],
"answeredAt": "2026-09-09T11:10:32.528Z"
},
{
"sessionId": "b6b8f7c7-a50c-4ccd-9996-4b321309a017",
"toolUseId": "toolu_01U1M5vvNUM4VgQWa2srLYPJ",
"questions": [
{
"question": "D4 \u2014 Pass 5 / Gap G1: Save button has the same visual weight as Reset, Cancel, and Export. DESIGN.md specifies the fix. Approve adding this implementation task? <gstack-qid:plan-design-review-g1-save-style>",
"header": "Save button style",
"options": [
{
"label": "Approve DESIGN.md fix: Save = filled primary (#1d4ed8 + white text), others = ghost (recommended)",
"description": "Style Save as the filled primary Button component; Reset, Cancel, Export as neutral ghost variants. Exact tokens from DESIGN.md. Immediately tells users which action is primary. (human: ~1h / CC: ~10min)"
},
{
"label": "Keep all four buttons equal weight",
"description": "Leave all four buttons visually identical. Users must read labels to find Save. Contradicts the DESIGN.md primary/ghost distinction. Not recommended for a primary action page."
},
{
"label": "Different visual distinction \u2014 size or border only",
"description": "Make Save larger or bolder rather than filled. Requires new design work outside DESIGN.md; adds ambiguity. Not recommended when DESIGN.md already specifies the exact solution."
}
],
"multiSelect": false
}
],
"answered": true,
"failed": false,
"answers": {
"D4 \u2014 Pass 5 / Gap G1: Save button has the same visual weight as Reset, Cancel, and Export. DESIGN.md specifies the fix. Approve adding this implementation task? <gstack-qid:plan-design-review-g1-save-style>": "Approve DESIGN.md fix: Save = filled primary (#1d4ed8 + white text), others = ghost (recommended)"
},
"unansweredQuestionIndices": [],
"answeredAt": "2026-09-09T11:10:46.563Z"
},
{
"sessionId": "b6b8f7c7-a50c-4ccd-9996-4b321309a017",
"toolUseId": "toolu_01QJvgcs6sqNvYbLMAkS199z",
"questions": [
{
"question": "D5 \u2014 Pass 5 / Gap G2: Spacing is inconsistent (16px / 24px / 32px). DESIGN.md specifies sections = 32px, field groups = 24px, label-to-input = 8px. The 16px is the offender. Approve normalizing to the DESIGN.md 8px scale? <gstack-qid:plan-design-review-g2-spacing>",
"header": "Spacing fix",
"options": [
{
"label": "Approve DESIGN.md fix: normalize to sections=32px, groups=24px, label=8px (recommended)",
"description": "Apply the DESIGN.md 8px base scale. Eliminates the 16px rogue value. Creates consistent vertical rhythm. Implementation task will identify the specific element(s) using 16px. (human: ~1h / CC: ~10min)"
},
{
"label": "Leave spacing as-is",
"description": "Accept the 16px/24px/32px mix. The user will see inconsistent breathing room between elements \u2014 professional but not polished. Contradicts DESIGN.md. Not recommended."
}
],
"multiSelect": false
}
],
"answered": true,
"failed": false,
"answers": {
"D5 \u2014 Pass 5 / Gap G2: Spacing is inconsistent (16px / 24px / 32px). DESIGN.md specifies sections = 32px, field groups = 24px, label-to-input = 8px. The 16px is the offender. Approve normalizing to the DESIGN.md 8px scale? <gstack-qid:plan-design-review-g2-spacing>": "Approve DESIGN.md fix: normalize to sections=32px, groups=24px, label=8px (recommended)"
},
"unansweredQuestionIndices": [],
"answeredAt": "2026-09-09T11:11:00.600Z"
},
{
"sessionId": "b6b8f7c7-a50c-4ccd-9996-4b321309a017",
"toolUseId": "toolu_01Ps2iFr4RduoDLL1MuN4aXJ",
"questions": [
{
"question": "D6 \u2014 Pass 5 / Gap G3: Error colors. The plan says contrast is ~3:1. But DESIGN.md's tokens (#991b1b on #fef2f2) actually achieve ~7.4:1 \u2014 the plan's claim describes the *current wrong implementation*, not the fix. Approve applying DESIGN.md tokens and correcting the contrast claim in the plan? <gstack-qid:plan-design-review-g3-error-color>",
"header": "Error color fix",
"options": [
{
"label": "Approve: apply DESIGN.md error tokens + correct the contrast claim (recommended)",
"description": "Use error.text #991b1b on error.surface #fef2f2 with an icon. Update the plan to state the ~3:1 is the current wrong value and the DESIGN.md fix achieves ~7.4:1. Prevents implementers from researching a problem that doesn\u2019t exist in the fixed state. (human: ~1h / CC: ~10min)"
},
{
"label": "Apply tokens only, leave the plan\u2019s contrast claim unchanged",
"description": "Fix the colors but keep the misleading ~3:1 description. Risk: future readers think the DESIGN.md fix still has a contrast problem and add unnecessary workarounds."
}
],
"multiSelect": false
}
],
"answered": true,
"failed": false,
"answers": {
"D6 \u2014 Pass 5 / Gap G3: Error colors. The plan says contrast is ~3:1. But DESIGN.md's tokens (#991b1b on #fef2f2) actually achieve ~7.4:1 \u2014 the plan's claim describes the *current wrong implementation*, not the fix. Approve applying DESIGN.md tokens and correcting the contrast claim in the plan? <gstack-qid:plan-design-review-g3-error-color>": "Approve: apply DESIGN.md error tokens + correct the contrast claim (recommended)"
},
"unansweredQuestionIndices": [],
"answeredAt": "2026-09-09T11:11:14.646Z"
},
{
"sessionId": "b6b8f7c7-a50c-4ccd-9996-4b321309a017",
"toolUseId": "toolu_01NAJCKX9PejBacx8oyd7GQn",
"questions": [
{
"question": "D7 \u2014 Pass 5 / Gap G4: Form uses 14px, 16px, and 18px. DESIGN.md specifies two roles: 16px (body/labels/helper text) and 20px (section headings). 14px also violates the universal rule (body text < 16px is prohibited). Approve rationalizing to 16px + 20px only? <gstack-qid:plan-design-review-g4-typography>",
"header": "Typography fix",
"options": [
{
"label": "Approve DESIGN.md fix: 16px body/labels/helper + 20px headings, eliminate 14px and 18px (recommended)",
"description": "Removes the accessibility violation (14px body text) and the intermediate 18px that creates false hierarchy. Implementation task will identify which elements currently use 14px and 18px. Strong two-tier system: 16px for everything readable, 20px for h2 section headings. (human: ~1h / CC: ~10min)"
},
{
"label": "Keep 14px for helper/secondary text",
"description": "Retain 14px for less prominent text (e.g., field hints). Risks: violates body text accessibility rule; creates three-size system instead of two; small text on a form erodes usability. Not recommended."
},
{
"label": "Use 18px for section headings instead of 20px",
"description": "Compromise: 16px body + 18px headings. Creates weaker section hierarchy than DESIGN.md\u2019s 20px; implementer must override DESIGN.md token. Not recommended when the spec is already clear."
}
],
"multiSelect": false
}
],
"answered": true,
"failed": false,
"answers": {
"D7 \u2014 Pass 5 / Gap G4: Form uses 14px, 16px, and 18px. DESIGN.md specifies two roles: 16px (body/labels/helper text) and 20px (section headings). 14px also violates the universal rule (body text < 16px is prohibited). Approve rationalizing to 16px + 20px only? <gstack-qid:plan-design-review-g4-typography>": "Approve DESIGN.md fix: 16px body/labels/helper + 20px headings, eliminate 14px and 18px (recommended)"
},
"unansweredQuestionIndices": [],
"answeredAt": "2026-09-09T11:11:30.690Z"
},
{
"sessionId": "b6b8f7c7-a50c-4ccd-9996-4b321309a017",
"toolUseId": "toolu_0195rLfgc3HFFq7jLPNCuVK6",
"questions": [
{
"question": "D8 \u2014 Pass 5 / Gap G5: Save takes 2-5s with no feedback (frozen page). DESIGN.md specifies the fix exactly. Approve adding the loading indicator? <gstack-qid:plan-design-review-g5-motion>",
"header": "Loading indicator",
"options": [
{
"label": "Approve DESIGN.md fix: inline spinner + \u201cSaving\u2026\u201d inside disabled Save, aria-busy=true, reduced-motion support (recommended)",
"description": "Reuses the DESIGN.md established pending-action pattern. Spinner appears beside \u201cSaving\u2026\u201d text inside the Save button; button is disabled while pending; aria-busy=true for screen readers; @media (prefers-reduced-motion) suppresses animation. User sees immediate feedback, never a frozen page. (human: ~2h / CC: ~15min)"
},
{
"label": "Page-level skeleton or overlay instead",
"description": "Show a full-page loading overlay or skeleton while saving. Higher visual weight than a simple button spinner; harder to implement; inconsistent with the DESIGN.md pattern. Overkill for a small form save. Not recommended."
},
{
"label": "Toast notification after save instead of spinner during",
"description": "Show a toast notification after success rather than in-button feedback during save. Doesn\u2019t solve the frozen-page problem (the user still sees nothing during 2-5s). Not recommended."
}
],
"multiSelect": false
}
],
"answered": true,
"failed": false,
"answers": {
"D8 \u2014 Pass 5 / Gap G5: Save takes 2-5s with no feedback (frozen page). DESIGN.md specifies the fix exactly. Approve adding the loading indicator? <gstack-qid:plan-design-review-g5-motion>": "Approve DESIGN.md fix: inline spinner + \u201cSaving\u2026\u201d inside disabled Save, aria-busy=true, reduced-motion support (recommended)"
},
"unansweredQuestionIndices": [],
"answeredAt": "2026-09-09T11:11:46.732Z"
}
]