Files
gstack/test/fixtures/design-handoff-u-calls.json
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

235 lines
16 KiB
JSON

[
{
"sessionId": "ab2c7ff1-970e-40ec-84b1-59560fcd165a",
"toolUseId": "toolu_01MxehX219oH2HnxmXrNBL52",
"questions": [
{
"question": "D1 \u2014 Pass 2/3/5: The plan identifies that saving takes 2-5 seconds with no feedback (frozen page). DESIGN.MD fully specifies the fix: inline spinner beside \"Saving\u2026\" inside the disabled Save button, aria-busy=true, reduced-motion support. The plan names this as a gap but adds no implementation task. Should we add it? <gstack-qid:plan-design-review-save-spinner>",
"header": "Save spinner",
"multiSelect": false,
"options": [
{
"label": "Add implementation task (Recommended)",
"description": "Add a concrete task: apply DESIGN.MD pending-state pattern \u2014 spinner + 'Saving\u2026' in disabled button, aria-busy=true, prefers-reduced-motion support. Fix: ~30 min CC / ~2h human. Resolves Issues 2.1, 3 (step 6 emotional arc), and 5.5 in one task."
},
{
"label": "Leave as gap description",
"description": "Keep the gap named but untasked. Developer reads the plan gap section and decides implementation during build. Risk: the pattern is non-trivial and may ship without reduced-motion support."
}
]
}
],
"answered": true,
"failed": false,
"answers": {
"D1 \u2014 Pass 2/3/5: The plan identifies that saving takes 2-5 seconds with no feedback (frozen page). DESIGN.MD fully specifies the fix: inline spinner beside \"Saving\u2026\" inside the disabled Save button, aria-busy=true, reduced-motion support. The plan names this as a gap but adds no implementation task. Should we add it? <gstack-qid:plan-design-review-save-spinner>": "Add implementation task (Recommended)"
},
"unansweredQuestionIndices": [],
"answeredAt": "2026-09-09T07:53:07.541Z"
},
{
"sessionId": "ab2c7ff1-970e-40ec-84b1-59560fcd165a",
"toolUseId": "toolu_01AZ2KWABJtBzHYDoPAhQo14",
"questions": [
{
"question": "D2 \u2014 Pass 5: Visual Hierarchy. Save, Reset, Cancel, and Export are all rendered identically \u2014 same size, weight, and color. Nothing signals which is primary. DESIGN.MD specifies: Save is the only filled primary action (#1d4ed8 bg, white text); Reset, Cancel, Export are neutral ghost buttons. The plan names this gap but adds no implementation task. Should we add it? <gstack-qid:plan-design-review-primary-button>",
"header": "Primary button",
"multiSelect": false,
"options": [
{
"label": "Add implementation task (Recommended)",
"description": "Add task: Apply Button primary variant (#1d4ed8 fill, white text) to Save; ghost variant to Reset, Cancel, Export. Fix aligns with DESIGN.MD exactly. ~15 min CC / ~1h human. Resolves Issue 5.1."
},
{
"label": "Leave as gap description",
"description": "Keep gap named but untasked. Risk: developer ships all four buttons identical, user has no visual cue which action is primary \u2014 most critical UX gap on this page."
}
]
}
],
"answered": true,
"failed": false,
"answers": {
"D2 \u2014 Pass 5: Visual Hierarchy. Save, Reset, Cancel, and Export are all rendered identically \u2014 same size, weight, and color. Nothing signals which is primary. DESIGN.MD specifies: Save is the only filled primary action (#1d4ed8 bg, white text); Reset, Cancel, Export are neutral ghost buttons. The plan names this gap but adds no implementation task. Should we add it? <gstack-qid:plan-design-review-primary-button>": "Add implementation task (Recommended)"
},
"unansweredQuestionIndices": [],
"answeredAt": "2026-09-09T07:53:15.554Z"
},
{
"sessionId": "ab2c7ff1-970e-40ec-84b1-59560fcd165a",
"toolUseId": "toolu_01A5JA2y1jfNUU6d78Ma6G5B",
"questions": [
{
"question": "D3 \u2014 Pass 5: Spacing. The plan reports 16px spacing appearing in a third location, alongside 24px (field groups) and 32px (sections) which match DESIGN.MD. But the plan doesn't say WHERE the 16px appears. DESIGN.MD's scale has no 16px slot: sections=32px, field groups=24px, label-to-input=8px. How should we handle this? <gstack-qid:plan-design-review-spacing-16px>",
"header": "Spacing fix",
"multiSelect": false,
"options": [
{
"label": "Add task to locate and correct 16px spacing (Recommended)",
"description": "Add task: audit spacing in the header action group and between InlineStatus and first fieldset \u2014 most likely candidates for the 16px outlier. Replace with the correct DESIGN.MD value (8px, 24px, or 32px depending on context). ~20 min CC / ~30 min human."
},
{
"label": "Leave location ambiguous",
"description": "Keep gap named without specifying location. Developer hunts during implementation. Risk: they fix the wrong instance, or the 16px inconsistency survives because its location was never pinned."
},
{
"label": "Escalate \u2014 need clarification on exact location",
"description": "Pause for the user to identify which spacing element uses 16px. Safest if you know where it is. Adds one more conversation round before work begins."
}
]
}
],
"answered": true,
"failed": false,
"answers": {
"D3 \u2014 Pass 5: Spacing. The plan reports 16px spacing appearing in a third location, alongside 24px (field groups) and 32px (sections) which match DESIGN.MD. But the plan doesn't say WHERE the 16px appears. DESIGN.MD's scale has no 16px slot: sections=32px, field groups=24px, label-to-input=8px. How should we handle this? <gstack-qid:plan-design-review-spacing-16px>": "Add task to locate and correct 16px spacing (Recommended)"
},
"unansweredQuestionIndices": [],
"answeredAt": "2026-09-09T07:53:25.574Z"
},
{
"sessionId": "ab2c7ff1-970e-40ec-84b1-59560fcd165a",
"toolUseId": "toolu_018Cx5mafCD7jxsaibDvoWa1",
"questions": [
{
"question": "D4 \u2014 Pass 5/6: Error Color \u2014 WCAG AA failure. The current error style (red text on light pink background) has ~3:1 contrast. WCAG AA requires 4.5:1 for normal-weight text. This fails both accessibility law and DESIGN.MD, which specifies: error.text #991b1b on error.surface #fef2f2, with an icon and explicit text. The plan names the gap but adds no implementation task. Should we add it? <gstack-qid:plan-design-review-error-contrast>",
"header": "Error contrast",
"multiSelect": false,
"options": [
{
"label": "Add implementation task (Recommended)",
"description": "Add task: Set error text to #991b1b on #fef2f2 background, add icon + explicit error text label. Fixes both the WCAG AA violation and DESIGN.MD alignment. ~15 min CC / ~1h human. Resolves Issues 5.3 and 6.1."
},
{
"label": "Leave as gap description",
"description": "Keep gap named but untasked. Risk: WCAG AA violation ships \u2014 legal and accessibility liability, plus poor experience for users with low vision or in challenging lighting."
}
]
}
],
"answered": true,
"failed": false,
"answers": {
"D4 \u2014 Pass 5/6: Error Color \u2014 WCAG AA failure. The current error style (red text on light pink background) has ~3:1 contrast. WCAG AA requires 4.5:1 for normal-weight text. This fails both accessibility law and DESIGN.MD, which specifies: error.text #991b1b on error.surface #fef2f2, with an icon and explicit text. The plan names the gap but adds no implementation task. Should we add it? <gstack-qid:plan-design-review-error-contrast>": "Add implementation task (Recommended)"
},
"unansweredQuestionIndices": [],
"answeredAt": "2026-09-09T07:53:35.599Z"
},
{
"sessionId": "ab2c7ff1-970e-40ec-84b1-59560fcd165a",
"toolUseId": "toolu_012vDse8oLT3o1hM7CqHd1sn",
"questions": [
{
"question": "D5 \u2014 Pass 5: Typography. Three font sizes are used (14px, 16px, 18px) across form labels. DESIGN.MD specifies two roles only: 16px body/form labels/helper text; 20px section headings. The 14px violates the Universal Rule (body text must be \u226516px) and WCAG readability. The 18px conflicts with section heading size (20px) creating a muddled hierarchy. Should we add a consolidation task? <gstack-qid:plan-design-review-typography-sizes>",
"header": "Typography",
"multiSelect": false,
"options": [
{
"label": "Add implementation task (Recommended)",
"description": "Add task: audit all form label and helper text sizes; replace 14px with 16px and 18px with 16px or 20px depending on element role. Verify no occurrence of 14px or 18px ships. ~20 min CC / ~1h human. Resolves Issue 5.4 and the <16px universal rule violation."
},
{
"label": "Leave as gap description",
"description": "Keep gap named but untasked. Risk: 14px text ships (below minimum; violates Universal Rules), and the muddled 18px/20px near-match confuses hierarchy for sighted users and may confuse screen reader users too."
}
]
}
],
"answered": true,
"failed": false,
"answers": {
"D5 \u2014 Pass 5: Typography. Three font sizes are used (14px, 16px, 18px) across form labels. DESIGN.MD specifies two roles only: 16px body/form labels/helper text; 20px section headings. The 14px violates the Universal Rule (body text must be \u226516px) and WCAG readability. The 18px conflicts with section heading size (20px) creating a muddled hierarchy. Should we add a consolidation task? <gstack-qid:plan-design-review-typography-sizes>": "Add implementation task (Recommended)"
},
"unansweredQuestionIndices": [],
"answeredAt": "2026-09-09T07:53:43.615Z"
},
{
"sessionId": "ab2c7ff1-970e-40ec-84b1-59560fcd165a",
"toolUseId": "toolu_01Mkr9iX2J2GTch2YMHxuTU7",
"questions": [
{
"question": "D6 \u2014 Pass 6: Reduced-motion save behavior. The plan says 'Respect reduced motion' and DESIGN.MD says the spinner has 'reduced-motion support' \u2014 but neither specifies what the user actually sees when prefers-reduced-motion: reduce is active. An animated spinner that ignores reduced-motion ships a broken accessibility experience. Which behavior should be specified? <gstack-qid:plan-design-review-reduced-motion>",
"header": "Reduced motion",
"multiSelect": false,
"options": [
{
"label": "Static spinner + 'Saving\u2026' text (Recommended)",
"description": "Under prefers-reduced-motion: reduce, render the spinner as a static (non-animating) icon beside 'Saving\u2026'. Users still get visual feedback but no motion. Matches what most spinner libraries produce under reduced-motion."
},
{
"label": "'Saving\u2026' text only, no spinner",
"description": "Hide the spinner entirely under reduced-motion; show 'Saving\u2026' text alone inside the disabled button. Simpler, zero animation artifacts, but removes the visual progress indicator entirely."
}
]
}
],
"answered": true,
"failed": false,
"answers": {
"D6 \u2014 Pass 6: Reduced-motion save behavior. The plan says 'Respect reduced motion' and DESIGN.MD says the spinner has 'reduced-motion support' \u2014 but neither specifies what the user actually sees when prefers-reduced-motion: reduce is active. An animated spinner that ignores reduced-motion ships a broken accessibility experience. Which behavior should be specified? <gstack-qid:plan-design-review-reduced-motion>": "Static spinner + 'Saving\u2026' text (Recommended)"
},
"unansweredQuestionIndices": [],
"answeredAt": "2026-09-09T07:53:51.630Z"
},
{
"sessionId": "ab2c7ff1-970e-40ec-84b1-59560fcd165a",
"toolUseId": "toolu_01KkdZitbTn6SvNCpZpKA2rq",
"questions": [
{
"question": "D7 \u2014 Pass 7: InlineStatus layout stability. The persistent status area transitions between three states: blank (before first save), 'Unsaved changes', and 'Saved at HH:mm'. If no minimum height is reserved, the content below it (Profile fieldset) will shift up/down each time the text appears or disappears. Neither the plan nor DESIGN.MD specifies whether a min-height should hold the space. What should the plan specify? <gstack-qid:plan-design-review-inline-status-height>",
"header": "Status height",
"multiSelect": false,
"options": [
{
"label": "Reserve min-height equal to one text line (Recommended)",
"description": "Add spec: InlineStatus container has min-height: 1 line-height (approximately 24px). Blank state renders empty space; text transitions without layout shift. Matches the 'Unsaved changes' line height as the stable baseline."
},
{
"label": "Allow layout shift (no min-height)",
"description": "No min-height; content shifts when status text appears. Simpler CSS. Risk: noticeable layout jump on first edit or save \u2014 may feel broken, especially combined with the focus ring on the Save button."
},
{
"label": "Defer \u2014 decide during implementation",
"description": "Leave this unspecified; let the developer decide during build. Risk: inconsistent between future form pages if not codified."
}
]
}
],
"answered": true,
"failed": false,
"answers": {
"D7 \u2014 Pass 7: InlineStatus layout stability. The persistent status area transitions between three states: blank (before first save), 'Unsaved changes', and 'Saved at HH:mm'. If no minimum height is reserved, the content below it (Profile fieldset) will shift up/down each time the text appears or disappears. Neither the plan nor DESIGN.MD specifies whether a min-height should hold the space. What should the plan specify? <gstack-qid:plan-design-review-inline-status-height>": "Reserve min-height equal to one text line (Recommended)"
},
"unansweredQuestionIndices": [],
"answeredAt": "2026-09-09T07:54:07.678Z"
},
{
"sessionId": "ab2c7ff1-970e-40ec-84b1-59560fcd165a",
"toolUseId": "toolu_01QeeStZr3jXcFNm2spvvn3S",
"questions": [
{
"question": "Design review complete (6/10 \u2192 9/10). 7 decisions resolved, 6 implementation tasks added, 0 deferred. The design review added significant interaction specs (spinner pending-state, reduced-motion behavior, layout stability) that have architectural implications. Eng review is the required shipping gate. What next? <gstack-qid:plan-design-review-next-step>",
"header": "Next step",
"multiSelect": false,
"options": [
{
"label": "Run /plan-eng-review next (Recommended)",
"description": "Eng review is the required gate before shipping. This design review added spinner behavior, reduced-motion spec, and InlineStatus layout constraints \u2014 architectural implications worth validating before implementation starts."
},
{
"label": "Skip \u2014 handle next steps manually",
"description": "Exit plan mode and proceed on your own. You have 6 concrete implementation tasks ready to build from."
}
]
}
],
"answered": true,
"failed": false,
"answers": {
"Design review complete (6/10 \u2192 9/10). 7 decisions resolved, 6 implementation tasks added, 0 deferred. The design review added significant interaction specs (spinner pending-state, reduced-motion behavior, layout stability) that have architectural implications. Eng review is the required shipping gate. What next? <gstack-qid:plan-design-review-next-step>": "Run /plan-eng-review next (Recommended)"
},
"unansweredQuestionIndices": [],
"answeredAt": "2026-09-09T07:57:37.838Z"
}
]