mirror of
https://github.com/garrytan/gstack.git
synced 2026-09-16 01:45:29 +02:00
* 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>
251 lines
13 KiB
JSON
251 lines
13 KiB
JSON
[
|
|
{
|
|
"sessionId": "ce4def56-9180-4e1e-ba55-859036af9758",
|
|
"toolUseId": "toolu_01X8ZMvTZ76gAdUBVcBgRjNi",
|
|
"questions": [
|
|
{
|
|
"question": "D1 \u2014 Convert the Save button visual hierarchy gap into an implementation task? <gstack-qid:plan-design-review-ia-1>",
|
|
"header": "D1 Hierarchy",
|
|
"multiSelect": false,
|
|
"options": [
|
|
{
|
|
"label": "A) Add as implementation task (Recommended)",
|
|
"description": "Convert the gap into a concrete task: 'Apply filled primary styling (#1d4ed8, white text) to Save; ghost styling to Reset, Cancel, Export per DESIGN.md.' Completeness: 10/10 \u2014 implementer has a specific, verifiable task with exact tokens."
|
|
},
|
|
{
|
|
"label": "B) Add token reference only",
|
|
"description": "Add a note in the gap section pointing to the DESIGN.md spec, but don't create a formal task. Completeness: 7/10 \u2014 the fix is findable but not surfaced for sprint planning or checklist use."
|
|
},
|
|
{
|
|
"label": "C) Leave as described gap",
|
|
"description": "Keep the gap as prose only. Completeness: 3/10 \u2014 the problem is named but implementers must cross-reference DESIGN.md to find the fix, risking it being missed or done wrong."
|
|
}
|
|
]
|
|
}
|
|
],
|
|
"answered": true,
|
|
"failed": false,
|
|
"answers": {
|
|
"D1 \u2014 Convert the Save button visual hierarchy gap into an implementation task? <gstack-qid:plan-design-review-ia-1>": "A) Add as implementation task (Recommended)"
|
|
},
|
|
"unansweredQuestionIndices": [],
|
|
"answeredAt": "2026-09-09T09:50:51.334Z"
|
|
},
|
|
{
|
|
"sessionId": "ce4def56-9180-4e1e-ba55-859036af9758",
|
|
"toolUseId": "toolu_01CXhjZH4WEWPRGdmNTuAehf",
|
|
"questions": [
|
|
{
|
|
"question": "D2 \u2014 Add the pending-save state spec as an implementation task? <gstack-qid:plan-design-review-states-1>",
|
|
"header": "D2 PendingSave",
|
|
"multiSelect": false,
|
|
"options": [
|
|
{
|
|
"label": "A) Add as implementation task (Recommended)",
|
|
"description": "Task: 'Render an inline spinner beside the text \u201cSaving\u2026\u201d inside the disabled Save button; set aria-busy=true on the button; under prefers-reduced-motion, remove the spinner but preserve disabled state and text.' Completeness: 10/10 \u2014 implementer has the full DESIGN.md spec with the a11y attribute and the motion variant."
|
|
},
|
|
{
|
|
"label": "B) Add note in Motion gap only",
|
|
"description": "Reference the DESIGN.md spinner pattern in the Motion gap section without a formal task. Completeness: 7/10 \u2014 the fix is documented but not actionable as a discrete work item."
|
|
},
|
|
{
|
|
"label": "C) Leave Motion gap as-is",
|
|
"description": "Keep the gap description as a known issue without specifying the fix. Completeness: 3/10 \u2014 ships a frozen page during 2-5s saves; users may try clicking Save again (duplicate submit)."
|
|
}
|
|
]
|
|
}
|
|
],
|
|
"answered": true,
|
|
"failed": false,
|
|
"answers": {
|
|
"D2 \u2014 Add the pending-save state spec as an implementation task? <gstack-qid:plan-design-review-states-1>": "A) Add as implementation task (Recommended)"
|
|
},
|
|
"unansweredQuestionIndices": [],
|
|
"answeredAt": "2026-09-09T09:51:05.384Z"
|
|
},
|
|
{
|
|
"sessionId": "ce4def56-9180-4e1e-ba55-859036af9758",
|
|
"toolUseId": "toolu_01CbscyDZBegLpC9mhQdEtm4",
|
|
"questions": [
|
|
{
|
|
"question": "D3 \u2014 Add a state coverage table to the plan body for implementer reference? <gstack-qid:plan-design-review-states-2>",
|
|
"header": "D3 StateTable",
|
|
"multiSelect": false,
|
|
"options": [
|
|
{
|
|
"label": "A) Add state table (Recommended)",
|
|
"description": "Insert a feature \u00d7 state table (Form load / Save / Export / Dirty state \u00d7 Loading / Empty / Error / Success / Pending). No new design decisions \u2014 all cells derive from existing specs. Completeness: 10/10 \u2014 implementers can verify each state against a single reference."
|
|
},
|
|
{
|
|
"label": "B) Leave states in prose only",
|
|
"description": "Keep the existing prose descriptions without a structured table. Completeness: 7/10 \u2014 specs are all there but scattered across paragraphs; edge cases like Export error during dirty-edit are harder to spot."
|
|
}
|
|
]
|
|
}
|
|
],
|
|
"answered": true,
|
|
"failed": false,
|
|
"answers": {
|
|
"D3 \u2014 Add a state coverage table to the plan body for implementer reference? <gstack-qid:plan-design-review-states-2>": "A) Add state table (Recommended)"
|
|
},
|
|
"unansweredQuestionIndices": [],
|
|
"answeredAt": "2026-09-09T09:51:13.416Z"
|
|
},
|
|
{
|
|
"sessionId": "ce4def56-9180-4e1e-ba55-859036af9758",
|
|
"toolUseId": "toolu_01BwktmsUeBQpaEobh9sZdvN",
|
|
"questions": [
|
|
{
|
|
"question": "D4 \u2014 Add a user journey storyboard to the plan? <gstack-qid:plan-design-review-journey-1>",
|
|
"header": "D4 Storyboard",
|
|
"multiSelect": false,
|
|
"options": [
|
|
{
|
|
"label": "A) Add storyboard (Recommended)",
|
|
"description": "Render the accepted journey as a step/user-does/user-feels/plan-specifies table (8 rows covering happy path, save failure, cancel with dirty state, first-time new account). No new design decisions \u2014 pure rendering of existing specs. Completeness: 10/10 \u2014 implementers understand the emotional arc and can verify the spec covers each moment."
|
|
},
|
|
{
|
|
"label": "B) Keep one-sentence journey description",
|
|
"description": "Leave the current one-sentence happy-path description. Completeness: 5/10 \u2014 the journey exists but reads like a state machine; error recovery arcs and first-time experience aren't visible without cross-referencing multiple paragraphs."
|
|
}
|
|
]
|
|
}
|
|
],
|
|
"answered": true,
|
|
"failed": false,
|
|
"answers": {
|
|
"D4 \u2014 Add a user journey storyboard to the plan? <gstack-qid:plan-design-review-journey-1>": "A) Add storyboard (Recommended)"
|
|
},
|
|
"unansweredQuestionIndices": [],
|
|
"answeredAt": "2026-09-09T09:51:21.443Z"
|
|
},
|
|
{
|
|
"sessionId": "ce4def56-9180-4e1e-ba55-859036af9758",
|
|
"toolUseId": "toolu_01LLaQKbCpHmntdB1qWG3x38",
|
|
"questions": [
|
|
{
|
|
"question": "D5 \u2014 Convert the spacing gap into an implementation task with explicit DESIGN.md scale? <gstack-qid:plan-design-review-ds-2>",
|
|
"header": "D5 Spacing",
|
|
"multiSelect": false,
|
|
"options": [
|
|
{
|
|
"label": "A) Add as implementation task (Recommended)",
|
|
"description": "Task: 'Apply the 8px spacing scale: between-section gaps 32px, between-field-group gaps 24px, label-to-input gaps 8px. Remove any 16px gap \u2014 no context in DESIGN.md uses 16px here.' Completeness: 10/10 \u2014 implementer has exact values and knows which to remove."
|
|
},
|
|
{
|
|
"label": "B) Reference DESIGN.md scale without a task",
|
|
"description": "Add a note pointing to the 8px base system in DESIGN.md. Completeness: 7/10 \u2014 the scale is accessible but the erroneous 16px value isn't explicitly called out for removal, risking it staying in the implementation."
|
|
},
|
|
{
|
|
"label": "C) Leave as gap description",
|
|
"description": "Keep the spacing gap as a prose description only. Completeness: 3/10 \u2014 ships inconsistent vertical rhythm; the UI will have a subtle broken-grid feel that erodes trust without an obvious cause."
|
|
}
|
|
]
|
|
}
|
|
],
|
|
"answered": true,
|
|
"failed": false,
|
|
"answers": {
|
|
"D5 \u2014 Convert the spacing gap into an implementation task with explicit DESIGN.md scale? <gstack-qid:plan-design-review-ds-2>": "A) Add as implementation task (Recommended)"
|
|
},
|
|
"unansweredQuestionIndices": [],
|
|
"answeredAt": "2026-09-09T09:51:31.485Z"
|
|
},
|
|
{
|
|
"sessionId": "ce4def56-9180-4e1e-ba55-859036af9758",
|
|
"toolUseId": "toolu_01LUq6SetnpMxG9CuiYaogRN",
|
|
"questions": [
|
|
{
|
|
"question": "D6 \u2014 Convert the error color gap into an implementation task with WCAG-compliant tokens? <gstack-qid:plan-design-review-ds-3>",
|
|
"header": "D6 ErrorColor",
|
|
"multiSelect": false,
|
|
"options": [
|
|
{
|
|
"label": "A) Add as implementation task (Recommended)",
|
|
"description": "Task: 'Apply error.text #991b1b on error.surface #fef2f2, plus an error icon and explicit text label. Measured contrast 5.9:1 \u2014 passes WCAG AA (4.5:1 required for normal text).' Completeness: 10/10 \u2014 implementer has exact hex values, knows the icon requirement, and can verify with a contrast checker."
|
|
},
|
|
{
|
|
"label": "B) Note the DESIGN.md tokens only",
|
|
"description": "Add a note pointing to the DESIGN.md error color pair without a formal task. Completeness: 7/10 \u2014 the fix is findable but ships as a follow-up item rather than a merge requirement."
|
|
},
|
|
{
|
|
"label": "C) Leave as gap description",
|
|
"description": "Keep the ~3:1 contrast gap as prose only. Completeness: 3/10 \u2014 ships a WCAG AA violation; users with low vision miss error messages; legal and audit risk."
|
|
}
|
|
]
|
|
}
|
|
],
|
|
"answered": true,
|
|
"failed": false,
|
|
"answers": {
|
|
"D6 \u2014 Convert the error color gap into an implementation task with WCAG-compliant tokens? <gstack-qid:plan-design-review-ds-3>": "A) Add as implementation task (Recommended)"
|
|
},
|
|
"unansweredQuestionIndices": [],
|
|
"answeredAt": "2026-09-09T09:51:39.521Z"
|
|
},
|
|
{
|
|
"sessionId": "ce4def56-9180-4e1e-ba55-859036af9758",
|
|
"toolUseId": "toolu_01TZCPbE7Yf39r5abjL8QRiV",
|
|
"questions": [
|
|
{
|
|
"question": "D7 \u2014 Convert the typography gap into an implementation task with the two-role system? <gstack-qid:plan-design-review-ds-4>",
|
|
"header": "D7 Typography",
|
|
"multiSelect": false,
|
|
"options": [
|
|
{
|
|
"label": "A) Add as implementation task (Recommended)",
|
|
"description": "Task: 'Apply two font-size roles: 16px for body text, form labels, and helper text; 20px for the h2 section headings (Profile, Notifications). Remove 14px (below universal-rule minimum) and 18px (no role in the design system).' Completeness: 10/10 \u2014 implementer has both the target values and the values to remove, with the WCAG rationale for the 14px removal."
|
|
},
|
|
{
|
|
"label": "B) Reference two-role system only",
|
|
"description": "Add a note pointing to the DESIGN.md two-role spec without listing which sizes to remove. Completeness: 7/10 \u2014 the target is clear but 14px and 18px may linger without an explicit removal instruction."
|
|
},
|
|
{
|
|
"label": "C) Leave as gap description",
|
|
"description": "Keep the 3-size description as a known gap. Completeness: 3/10 \u2014 ships 14px text that violates the universal-rule body minimum; flat hierarchy where headings don't distinguish themselves from body."
|
|
}
|
|
]
|
|
}
|
|
],
|
|
"answered": true,
|
|
"failed": false,
|
|
"answers": {
|
|
"D7 \u2014 Convert the typography gap into an implementation task with the two-role system? <gstack-qid:plan-design-review-ds-4>": "A) Add as implementation task (Recommended)"
|
|
},
|
|
"unansweredQuestionIndices": [],
|
|
"answeredAt": "2026-09-09T09:51:49.561Z"
|
|
},
|
|
{
|
|
"sessionId": "ce4def56-9180-4e1e-ba55-859036af9758",
|
|
"toolUseId": "toolu_01EAbwBxUqkGimEBVbC9iFMm",
|
|
"questions": [
|
|
{
|
|
"question": "D8 \u2014 Address the skip navigation link gap? <gstack-qid:plan-design-review-a11y-1>",
|
|
"header": "D8 SkipNav",
|
|
"multiSelect": false,
|
|
"options": [
|
|
{
|
|
"label": "A) Add verification task: confirm skip link exists in app shell (Recommended)",
|
|
"description": "Task: 'Verify that the persistent app navigation includes a skip-to-main-content link (WCAG 2.1 SC 2.4.1 Bypass Blocks). If absent, add <a href=\"#main-content\" class=\"sr-only focus:not-sr-only\">Skip to content</a> before the nav.' Completeness: 10/10 \u2014 WCAG 2.4.1 compliance confirmed or addressed; keyboard users can bypass nav on every page load."
|
|
},
|
|
{
|
|
"label": "B) Note it as a known gap, defer to app shell audit",
|
|
"description": "Add a note that skip nav is out of this form's scope and should be verified at app shell level. Completeness: 7/10 \u2014 the question is raised but the settings page may ship with a WCAG 2.4.1 gap if the shell audit doesn't happen alongside this PR."
|
|
},
|
|
{
|
|
"label": "C) Out of scope \u2014 leave unaddressed",
|
|
"description": "The plan covers only the settings form; skip nav is a shell concern. No action. Completeness: 5/10 \u2014 risk: if no skip link exists, keyboard users must tab through all nav items on every form interaction cycle."
|
|
}
|
|
]
|
|
}
|
|
],
|
|
"answered": true,
|
|
"failed": false,
|
|
"answers": {
|
|
"D8 \u2014 Address the skip navigation link gap? <gstack-qid:plan-design-review-a11y-1>": "A) Add verification task: confirm skip link exists in app shell (Recommended)"
|
|
},
|
|
"unansweredQuestionIndices": [],
|
|
"answeredAt": "2026-09-09T09:51:59.598Z"
|
|
}
|
|
]
|