@tea-agent/loop-agent 0.43.0-next.17 → 0.43.0-next.3

package/docs/templates/frontend-implementation-dag.json

@@ -6,11 +6,10 @@
   "successCriteria": [
     "The contract covers every required user-visible behavior, state, and interaction.",
     "The implementation is admitted only after a concrete, narrow writeSet is reviewed.",
-    "Build verification are recorded before final review.",
+    "Static and behavior verification are recorded before final review.",
     "The final closeout distinguishes passed, not-run, and residual-risk evidence."
   ],
   "globalConstraints": [
-    "frontend-implementation plans and reviews requirement implementation coverage; npm run build and frozen existing tests are required. Update affected unit tests; do not add a framework when absent. Browser/visual checks may follow later; preserve production Mock isolation.",
     "This is a self-contained static template: do not generate, import, or merge a DAG from a runtime builder before execution.",
     "Replace every REPLACE/WITH/... placeholder with concrete repository paths or deterministic commands before execution.",
     "Do not commit runtime traces under .harness/dag-runs/.",
@@ -39,7 +38,7 @@
     {
       "id":"frontend-plan-pi", "depends_on":["frontend-scout-pi"], "complexity":"MED", "executor":"pi", "role":"planner", "writePolicy":"read-only", "allowedPaths":["REPLACE/WITH/FRONTEND/SOURCE/PATH/**","REPLACE/WITH/FRONTEND/TEST/PATH/**"], "forbiddenPaths":[".harness/**","artifacts/**"],
       "outputContract":"Plan record_* tools for scoped coverage, shared execution groups and UX, one mock endpoint per record, then one successful finalize_plan. Runtime derives canonical JSON and Markdown. No file writes.",
-      "subtask_prompt":"List the requirement implementation plan: what to change and in which authorized files. Map requirements to the shared static build target. Do not require test plans or behavior correctness evidence; include affected existing test files in implementation steps."
+      "subtask_prompt":"Turn the contract and reconnaissance into a minimal implementation plan. Every target file and verification step must be concrete. Preserve existing design and accessibility conventions. If any behavior lacks a verifiable target, report it as blocked instead of guessing."
     },
     {
       "id":"frontend-design-policy-shell", "depends_on":["frontend-plan-pi"], "complexity":"LOW", "executor":"shell", "role":"verifier", "writePolicy":"read-only", "allowedPaths":["REPLACE/WITH/FRONTEND/SOURCE/PATH/**","REPLACE/WITH/FRONTEND/TEST/PATH/**"], "forbiddenPaths":[".harness/**","artifacts/**"],
@@ -50,7 +49,7 @@
     {
       "id":"frontend-design-review-pi", "depends_on":["frontend-design-policy-shell"], "complexity":"MED", "executor":"pi", "role":"reviewer", "writePolicy":"read-only", "allowedPaths":["REPLACE/WITH/FRONTEND/SOURCE/PATH/**","REPLACE/WITH/FRONTEND/TEST/PATH/**"], "forbiddenPaths":[".harness/**","artifacts/**"],
       "outputContract":"record_design_finding for individual findings; approve_design or request_design_changes provides the sole committed terminal. Independently review execution-group member differences. No file writes.",
-      "subtask_prompt":"Review the approved plan against the frontend contract and design-policy result. Reject missing visible states, interaction behavior, accessibility obligations, or unsupported design claims. Do not edit files. Scope: requirement implementation coverage and authorized paths/dependencies only; no separate test plan or new framework is required. Maintain affected existing tests and require frozen tests plus build to pass; browser/visual checks may be deferred."
+      "subtask_prompt":"Review the approved plan against the frontend contract and design-policy result. Reject missing visible states, interaction behavior, accessibility obligations, or unsupported design claims. Do not edit files."
     },
     {
       "id":"frontend-writer-admission-shell", "depends_on":["frontend-design-review-pi"], "complexity":"LOW", "executor":"shell", "role":"verifier", "writePolicy":"read-only", "allowedPaths":["REPLACE/WITH/FRONTEND/TARGET/PATH/**"], "forbiddenPaths":[".harness/**","artifacts/**"],
@@ -61,13 +60,13 @@
     {
       "id":"frontend-implement-pi", "depends_on":["frontend-writer-admission-shell"], "complexity":"HIGH", "executor":"pi", "role":"implementer", "toolProfile":"write", "writePolicy":"exclusive", "writeSet":["REPLACE/WITH/FRONTEND/TARGET/PATH/**"], "allowedPaths":["REPLACE/WITH/FRONTEND/TARGET/PATH/**"], "forbiddenPaths":[".harness/**","artifacts/**"],
       "outputContract":"Implementation summary with changed files, contract coverage, focused checks run, and residual risks.",
-      "subtask_prompt":"Implement only the admitted frontend changes. Preserve established component, styling, accessibility, and state-management conventions. Cover every approved behavior, state, and interaction, then report changed files and focused verification. Do not broaden writeSet or add undeclared dependencies. Scope: requirement implementation coverage and authorized paths/dependencies only; no separate test plan or new framework is required. Maintain affected existing tests and require frozen tests plus build to pass; browser/visual checks may be deferred."
+      "subtask_prompt":"Implement only the admitted frontend changes. Preserve established component, styling, accessibility, and state-management conventions. Cover every approved behavior, state, and interaction, then report changed files and focused verification. Do not broaden writeSet or add undeclared dependencies."
     },
     {
       "id":"frontend-verify-shell", "depends_on":["frontend-implement-pi"], "complexity":"LOW", "executor":"shell", "role":"verifier", "writePolicy":"read-only", "allowedPaths":["REPLACE/WITH/FRONTEND/TARGET/PATH/**"], "forbiddenPaths":[".harness/**","artifacts/**"],
-      "outputContract":"Archived build verification output with command exit codes; no worktree writes.",
-      "subtask_prompt":"Run npm run build and record the actual exit code. Missing or failed builds must fail; never substitute a no-op.",
-      "shell":{"commands":["npm run build"],"cwd":".","timeoutMs":300000}
+      "outputContract":"Archived static and behavior verification output with command exit codes; no worktree writes.",
+      "subtask_prompt":"Run the contract-selected deterministic static and behavior verification commands. Record all exit codes. A failed required command is terminal for this DAG run; do not silently substitute a different command.",
+      "shell":{"preset":"loop-agent-standard-verify","cwd":".","timeoutMs":300000}
     },
     {
       "id":"frontend-review-context-shell", "depends_on":["frontend-verify-shell"], "complexity":"LOW", "executor":"shell", "role":"verifier", "writePolicy":"read-only", "allowedPaths":["REPLACE/WITH/FRONTEND/TARGET/PATH/**"], "forbiddenPaths":[".harness/**","artifacts/**"],
@@ -78,7 +77,7 @@
     {
       "id":"frontend-review-pi", "depends_on":["frontend-review-context-shell"], "complexity":"MED", "executor":"pi", "role":"reviewer", "writePolicy":"read-only", "allowedPaths":["REPLACE/WITH/FRONTEND/TARGET/PATH/**"], "forbiddenPaths":[".harness/**","artifacts/**"],
       "outputContract":"record_review_finding for individual findings; approve_review or request_review_changes provides the sole committed terminal. No file writes.",
-      "subtask_prompt":"Review the actual diff and archived verification evidence against the frontend contract. Do not treat missing, weak, mock-only, or not-run evidence as passed. Report explicit residual risks; do not edit files. Scope: requirement implementation coverage and authorized paths/dependencies only; no separate test plan or new framework is required. Maintain affected existing tests and require frozen tests plus build to pass; browser/visual checks may be deferred."
+      "subtask_prompt":"Review the actual diff and archived verification evidence against the frontend contract. Do not treat missing, weak, mock-only, or not-run evidence as passed. Report explicit residual risks; do not edit files."
     },
     {
       "id":"frontend-closeout-shell", "depends_on":["frontend-review-pi"], "complexity":"LOW", "executor":"shell", "role":"closeout", "writePolicy":"read-only", "allowedPaths":["REPLACE/WITH/FRONTEND/TARGET/PATH/**"], "forbiddenPaths":[".harness/**","artifacts/**"],

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@tea-agent/loop-agent",
-  "version": "0.43.0-next.17",
+  "version": "0.43.0-next.3",
   "type": "module",
   "bin": {
     "loop-agent": "bin/loop-agent.js",
@@ -78,12 +78,9 @@
     "@deepseek-ai/dsh-invariants": "0.1.1-rc.2",
     "@earendil-works/pi-ai": "0.83.0",
     "@earendil-works/pi-coding-agent": "0.83.0",
-    "@xterm/addon-fit": "^0.11.0",
-    "@xterm/xterm": "^6.0.0",
     "commander": "^12.1.0",
     "katex": "^0.16.47",
     "mermaid": "^11.16.1",
-    "node-pty": "^1.2.0-beta.15",
     "rehype-highlight": "^7.0.2",
     "rehype-katex": "^7.0.1",
     "remark-math": "^6.0.0",
@@ -93,8 +90,8 @@
     "zod": "^3.25.76"
   },
   "optionalDependencies": {
-    "@agent-context/sift": "0.0.1-alpha.7",
-    "@cursor/sdk": "^1.0.7"
+    "@cursor/sdk": "^1.0.7",
+    "@agent-context/sift": "0.0.1-alpha.7"
   },
   "devDependencies": {
     "@remixicon/react": "^4.9.0",
@@ -102,7 +99,6 @@
     "@types/react": "^19.1.8",
     "@types/react-dom": "^19.1.6",
     "@types/semver": "^7.7.1",
-    "@vitest/coverage-v8": "^4.1.11",
     "react": "^19.1.0",
     "react-dom": "^19.1.0",
     "react-markdown": "^10.1.0",

package/skills/frontend-bounded-implement/SKILL.md

@@ -35,16 +35,15 @@ canonical targets and do not authorize additional discovery.
 
 ## Implementation Discipline
 
-- Implement the planned requirements without a test-first stage. Update affected existing tests and preserve unrelated files; stay inside
+- Work test-first where behavior changes. Preserve unrelated files and stay inside
   `allowedPaths` and `writeSet`.
 - Implement every requirement outcome, interaction, and applicable UI state
   assigned to the writer. Keep the real request path enabled by default and use
   only the approved Mock/API strategy.
 - Do not add dependencies unless the contract approves them. Never relax lint,
   type, test, or build configuration; never add `.skip` or `.only`.
-- Run npm run build and frozen existing-test commands. Update affected unit tests
-  with changed interfaces/behavior; never delete assertions just to pass. Do not
-  install a test framework when absent. Browser/visual tests may follow later.
+- Run only the focused checks already frozen by the task. Leave full verification
+  to downstream deterministic nodes.
 
 ## Completion Summary
 

package/skills/frontend-bounded-implement/references/code-standards.md

@@ -4,16 +4,16 @@ Apply the canonical contract and the conventions visible in target files and the
 direct local dependencies. Do not reopen task sources, OpenSpec, `ai_workspace`, or
 unrelated repository areas to discover new rules or redesign approved decisions.
 
-- Implement requirement coverage and preserve existing tests and unrelated behavior.
+- Work test-first when behavior changes and preserve unrelated behavior.
 - Reuse existing public helpers, APIs, components, tokens, schemas, and test
   patterns that are directly available from the bounded target surface.
 - Keep rendering, transitions, validation, request lifecycle, errors, and side
-  effects clear; defer race and boundary tests to frontend-test.
+  effects testable; cover relevant races and boundaries.
 - Keep real API behavior enabled by default. Mock activation must follow the
   approved strategy, remain explicit and dev/test-only, and never import test mocks
   into production code.
 - Trace fixtures to the approved API/schema evidence and never store secrets.
 - Do not add unapproved dependencies, relax lint/type/test/build configuration,
   add `.skip`/`.only`, comment out real requests, or write outside `writeSet`.
-- Run build and frozen existing tests, updating affected unit tests; report real status. Downstream shell
+- Run only frozen focused checks and report their real status. Downstream shell
   verification remains authoritative.

package/skills/frontend-contract/references/contract-protocol.md

@@ -15,9 +15,7 @@
 
 - Register static, behavior, Mock, and real-integration evidence expectations as
   required, optional, or not-applicable. The classification follows the source and
-  risk; it is not selected for model convenience. These are source expectations
-  for implementation and the frontend-test handoff. Build and existing affected
-  unit tests are required here; do not invent a test framework when absent.
+  risk; it is not selected for model convenience.
 - Register a non-blocking frontend-test handoff for UI-visible or interactive work.
 - Preserve exact command labels and referenced paths. Do not invent evidence,
   connector results, APIs, or verification commands.

package/skills/frontend-design-review/SKILL.md

@@ -28,17 +28,18 @@ The typed terminal is the only authoritative outcome. Do not require or emit a
 verdict. Requested changes end this run; recovery owns the bounded follow-up.
 
 Check every execution group against its members' complete outcomes. Permissions,
-thresholds and error paths remain independent ACs with corresponding planned implementation.
-The shared static build target checks buildability only.
+thresholds and error paths remain independent ACs; a shared VT must prove them all.
+Constraint/exclusion labels never waive source-required behavior evidence.
 
 ## Blocking Conditions
 
-- Any criterion lacks planned implementation; UI states lack reasons; a
+- Any criterion lacks implementation/verification; UI states lack reasons; a
   dependency lacks permission; confirmed primitives/rules are ignored; design claims
   lack knowledge-base or required openspec specification evidence; paths cross
-  write bounds; the frozen npm run build command is missing.
+  write bounds; commands are missing/non-deterministic; or
+  interaction, responsive, accessibility, data, or failure behavior requires guessing.
 - `MOCK_STRATEGY: blocked`; missing permitted target paths, endpoint/schema-to-fixture
-  mapping or dev/test-only activation; a second Mock framework;
+  mapping, fixed verification, or dev/test-only activation; a second Mock framework;
   inline fake data; commented real requests; Mock-on production defaults; test-only
   production imports; or Mock evidence reported as real integration.
 
@@ -48,7 +49,7 @@ conflict, or unresolved UI decisions.
 
 ## Method And Human-readable Output
 
-Map criteria to planned steps/files/states, audit paths/evidence, classify Blocking
+Map criteria to steps/files/states/checks, audit paths/evidence, classify Blocking
 or Advisory, and never edit files.
 
 ### Spec Evidence Rules
@@ -58,9 +59,3 @@ evidence paths bound in its upstream context. Successful paired reads are the on
 summaries do not substitute for them. A concise human-readable summary may list
 checked items and findings, but it is never a control protocol. Each requested
 change names its criterion/section, gap, and required plan change.
-
-## Implementation workflow boundary
-
-Plan implementation files and affected existing unit tests; require frozen tests
-and build to pass. No new framework or separate test plan is required. Additional
-browser/visual checks may follow later in frontend-test.

package/skills/frontend-design-review/references/review-checklist.md

@@ -3,7 +3,7 @@
 ## Coverage
 
 - Route/component, non-goals, assumptions, and unresolved ambiguity are explicit.
-- Each acceptance criterion maps to planned steps, files, UI behavior, and states.
+- Each acceptance criterion maps to steps, files, UI behavior, states, and verification.
 - Success/error/loading/empty/disabled/permission/retry/stale/boundary states are handled or N/A.
 
 ## Project Fit
@@ -20,9 +20,9 @@
 
 ## Verification
 
-- Require npm run build and the frozen existing-test commands.
-- Plan must include affected existing tests; no separate test plan or new framework.
-- Existing test failures block completion; browser/visual checks may be deferred.
+- Static/behavior commands are exact, frozen, discoverable, and deterministic.
+- Tests prove changed state and flows at supported levels; browser/visual only when task/gate requires.
+- Missing required verification is a blocker; optional gaps are disclosed risks.
 
 ## Mock Safety
 
@@ -31,13 +31,13 @@
 - Prefer native mock; browser intercept only for existing e2e; request adapter only for reversible local preview.
 - Real request stays default; activation is explicit, reversible, local/test-only, and production-off.
 - Plans use only DAG-frozen shell entrypoints.
-- Mock strategies keep production defaults off; Mock behavior tests are deferred.
-- `not-needed` records its rationale and preserves any Real Integration Gap.
+- Mock strategies need default-real-path build with Mock off plus Mock-backed behavior evidence.
+- `not-needed` needs real/no-remote evidence, or default-auto skipped-Mock rationale with Real Integration Gap preserved when no project Mock capability exists.
 - Mock-backed checks prove frontend states only; real integration remains pending until actual backend evidence exists.
 
 ## Verdict Matrix
 
-- Request revision for coverage gaps, unsafe scope, unauthorized deps, unresolved required interaction, missing build entrypoint, skipped local specification fallback (`openspec/schemas/`, `openspec/project-specs/`, or `ai_workspace/`), unsafe/missing Mock strategy, or Mock evidence presented as real integration.
+- Request revision for coverage gaps, unsafe scope, unauthorized deps, unresolved required interaction, missing required verification, skipped local specification fallback (`openspec/schemas/`, `openspec/project-specs/`, or `ai_workspace/`), unsafe/missing Mock strategy, or Mock evidence presented as real integration.
 - Request revision for component selection non-conformance: spec-defined components silently replaced or self-invented without a declared deviation, `uiComponentChoices` missing for UI-visible work, or a `uiComponentChoices` `specReference.path` not cited in the `openspec-citations` block / not actually read.
 - Knowledge-base unavailable but relevant OpenSpec or `ai_workspace/` rules applied is advisory only.
 - Optional cleanup that cannot affect acceptance is advisory.

package/skills/frontend-plan/SKILL.md

@@ -29,13 +29,6 @@ cite `evidencePath` of an existing file; greenfield is `decision=new`.
 Bind every file in the Contract-owned `requiredDeliverables` inventory. It records
 explicit source obligations, not every path mentioned by a requirement.
 
-Large UX work runs in bounded scopes against that shared registry. Complete every
-assigned requirement; preserve earlier scopes' shared bindings when correcting an
-entry. Ledger previews are incomplete. Use `read_plan_facts` to retrieve full
-fields, following `nextOffset` with `expectedRevision` pinned. For oversized
-strings use `stringOffset` and follow `nextStringOffset`; restart pagination when
-the revision changes. Never submit a truncated preview as a replacement payload.
-
 Cross-slice citations must close in the same session: when a requirement cites a
 verification target committed in another slice's session, re-commit that target
 here with the same id and `replace=true` (union backfill) before finalize. A
@@ -44,15 +37,3 @@ here with the same id and `replace=true` (union backfill) before finalize. A
 The runtime owns protected skeleton fields, path/command validation, materialization,
 and final schema checks. Finish with one successful `finalize_plan` (correct rejected facts and retry); return no Markdown
 narrative. Record a genuine evidence gap when frozen facts are insufficient.
-
-## Implementation boundary
-
-Plan actions and files, including affected existing unit tests. Build and frozen
-existing tests must pass. No separate test plan or new framework is required.
-Browser/visual testing may follow in frontend-test.
-
-Submit `finalize_plan({implementationSteps: [{requirementIds, action}]})`.
-Cover every frozen ID, including constraints/exclusions (what to preserve/avoid).
-An action may cover related IDs and must describe changes within approved paths,
-not just repeat filenames or AC titles. Fix rejected missing/unknown/blank steps
-and retry. Runtime renders AC-linked canonical steps; no test plan is required.

package/skills/frontend-plan/references/decision-contract.md

@@ -6,22 +6,24 @@
   implementation paths and verification target IDs.
 - Record observable state and interaction behavior, including trigger and expected
   behavior. IDs and paths alone are not behavioral coverage.
-- Use a shared static build target for requirement coverage; build does not prove behavior.
-- List affected existing tests in implementation steps and update their assertions.
-  No separate test plan or per-AC test titles are required; frozen test commands must pass.
+- One behavior target may cover multiple related requirements when one observable
+  test behavior proves them together.
+- Every non-static verification target `id` is the stable machine trace token and
+  must later appear in a real `describe` / `it` / `test` title. There is no free-form
+  `symbol` field.
 - Static targets are for project-wide commands and are traced by file and command
   only.
 
-### Build target mapping
+### Behavior target shape (canonical example)
 
-Static build targets map requirements to files using the frozen commandId; they
-do not prove tested behavior.
+Each behavior target names the requirements it proves and declared UI states it
+exercises. Empty `requirementIds`, or empty `uiStates` when any state/interaction
+is declared, is rejected. Copy state names verbatim; never invent synonyms.
 
 ```json
 {
-  "id": "VT-BUILD",
-  "commandId": "<frozen-build-commandId>",
-  "file": "src/App.tsx",
+  "id": "VT-COUNTER-LOCAL-CONSTRAINTS",
+  "file": "src/App.test.tsx",
   "requirementIds": ["AC-FE-001", "AC-FE-005"],
   "uiStates": ["disabled-minus", "default"]
 }
@@ -45,7 +47,7 @@ carries behavior, implementation targets, and verification target ids:
       "applicable": true,
       "expectedBehavior": "minus button disabled at count 0",
       "implementationTargets": ["src/components/SmokeCounter.tsx"],
-      "verificationTargetIds": ["VT-BUILD"]
+      "verificationTargetIds": ["VT-COUNTER-LOCAL-CONSTRAINTS"]
     }
   ],
   "interactions": [
@@ -54,7 +56,7 @@ carries behavior, implementation targets, and verification target ids:
       "trigger": "User clicks refresh",
       "expectedBehavior": "reloads runs",
       "implementationTargets": ["src/App.tsx"],
-      "verificationTargetIds": ["VT-BUILD"]
+      "verificationTargetIds": ["VT-SMOKE-COUNTER-BEHAVIOR"]
     }
   ]
 }
@@ -74,7 +76,8 @@ non-static verification target files to the writer writeSet separately.
     "src/App.tsx"
   ],
   "verificationTargetIds": [
-    "VT-BUILD"
+    "VT-SMOKE-COUNTER-BEHAVIOR",
+    "VT-COUNTER-LOCAL-CONSTRAINTS"
   ]
 }
 ```
@@ -110,8 +113,9 @@ One component choice may cover many states/interactions via `covers`.
 `reuse-existing` requires an existing-file `evidencePath`; greenfield uses `new`.
 
 For Mock/API, keep the real request path enabled by default. Select only a strategy
-allowed by the frozen task capability. Active Mock requires production-default-off activation; Mock tests are deferred. `not-needed` records the reason Mock is unnecessary or skipped and any real-integration gap;
-no behavior test evidence is required here.
+allowed by the frozen task capability. Active Mock requires deterministic Mock-backed
+verification and production-default-off activation. `not-needed` requires positive
+real/no-remote evidence or records a real-integration gap.
 
 Add dependencies only when authorized. Record unsupported dependency, path, API,
 design, or verification needs as blocking evidence gaps; never invent a command or
@@ -134,20 +138,9 @@ and checked again by the policy shell.
 Use `record_plan_group_coverage` for a complete declared execution group with shared
 targets/VTs; runtime expands to all canonical members. Submit individual coverage
 for differences. Constraints/exclusions create no invented UI or tests; keep genuine
-source expectations and affected existing tests; no new framework is required.
+evidence gaps, and never weaken behavior evidence required by the source.
 
 Submit Mock policy with `record_mock_api` and empty endpoints, then one endpoint per
 `record_mock_endpoint`. Use `replace:true` for revisions, plus `remove:true` to
 withdraw an endpoint. Use stable finding/fact identities; successful receipts mean
 durable commits. Resume missing work instead of regenerating full JSON or history.
-
-## Implementation steps submission
-
-Submit `finalize_plan` with `implementationSteps: [{requirementIds, action}]`.
-Each action says what to change and where within the approved implementation
-paths. Cover every frozen requirement ID, including constraints and exclusions
-(state what to preserve or avoid). One action may cover several related IDs.
-Do not merely repeat file names or AC titles. Missing, unknown or blank steps
-return a correctable receipt; fix the steps and call finalize_plan again.
-The runtime renders these into canonical `implementationSteps` strings with AC
-references. No test plan or new tests are required by this protocol.

package/skills/frontend-review/SKILL.md

@@ -30,18 +30,24 @@ Requested changes end this run; the recovery controller owns follow-up.
 
 ## Review Scope
 
-- Map every requirement to corresponding implementation in the cumulative diff
-  and bound target files. Report missing implementation or altered requirements.
-- Check allowed paths, forbidden paths, approved dependencies and source-bound
-  design constraints. Preserve production Mock isolation and real-request defaults.
-- Inspect build and frozen existing-test results; required commands must pass.
-- Check affected existing tests were maintained with changed behavior/interfaces.
-  Do not require a new framework or separate test plan when absent.
-- Broader browser/visual checks may use the frontend-test handoff. Do not defer
-  failing existing unit tests or weaken assertions to permit approval.
-- Build success proves buildability only. Do not report tested behavior or real
-  integration without actual evidence. Treat shell exit status as authoritative.
-- Do not edit files or perform repository-wide rediscovery.
+- Compare intent, contract, plan, diff, and evidence; report altered requirements.
+- Inspect every changed file against allowed, forbidden, and approved write scope.
+- Map criteria to behavior, applicable UI states, tests, and shell evidence.
+- Review state/data flow, validation, async/error behavior, design, responsive/a11y,
+  dependencies, and regression risk when applicable.
+- Inspect static, behavior, and available Mock-specific artifacts directly. For Mock
+  strategies, compare the endpoint matrix, handler/fixture/adapter and consumer diff;
+  require the real request as default, contract-aligned fixtures, production isolation,
+  and no false real-integration claim. `not-needed` needs applicable real/no-remote
+  evidence, or an explicit default-auto skipped-Mock rationale with the Real
+  Integration Gap preserved when no project Mock capability is confirmed.
+- Inspect lint assessment directly. `baseline-debt` requires intact evidence, only
+  baseline-matched diagnostics on unchanged files, and none on writer-changed files.
+  Report debt, never `lint passed`; `failed`/`unavailable` blocks. Typecheck, build,
+  and test still require successful final exits.
+- Evaluate component/design claims against bound evidence; do not replace it with a
+  repository-wide search or connector query.
+- Treat shell exit status as authoritative. Do not edit files.
 
 ## Evidence And Output
 

package/skills/frontend-review/references/review-findings.md

@@ -1,30 +1,49 @@
 # Frontend Review Findings Guide
 
-## Scope and severity
+## Severity
 
-- **Critical/Important**: missing requirement implementation, unauthorized writes
-  or dependencies, production Mock isolation violation, altered source requirements,
-  failed/missing npm run build, or a false verification/integration claim.
-- **Advisory**: behavior correctness, edge cases, regression concerns and missing
-  tests. Record these for later frontend-test work; they do not block implementation.
+- **Critical**: blocks primary flow, corrupts data, violates security/privacy, writes forbidden paths, bypasses required verification.
+- **Important**: acceptance/state/validation gap, material convention drift, missing behavior tests, unauthorized dependency, unsafe mock activation/import, mock-contract drift, misleading real-integration claim, or failed/missing required verification.
+- **Minor**: non-blocking maintainability, copy, layout, or cleanup issue.
 
 ## Evidence
 
-Cite the bound contract, actual cumulative diff, tight file locations and archived
-build result. Never substitute an implementation summary for the diff or invent
-verification results. Use only evidence supplied in the canonical review context.
-
-## Review sequence
-
-1. Establish changed files and authorized write boundaries.
-2. Map each requirement to corresponding implementation.
-3. Check source-bound design constraints, dependency permission and production Mock isolation.
-4. Confirm build and frozen existing tests passed and classify findings within this scope.
-
-## Pass rules
-
-All requirements have corresponding implementation, changes stay authorized,
-production Mock safety is preserved, and build plus frozen existing tests passed.
-Affected unit tests must reflect changed behavior; do not remove assertions to pass.
-No new framework or separate test plan is required when absent.
-Behavior and real integration remain unverified unless separate evidence exists.
+- Cite tight file locations, exact commands/results, or named DAG artifacts.
+- Never invent evidence; name the missing check. An implementation summary is not the actual diff.
+- Failed required static/behavior verification is at least Important. Lint may be
+  `baseline-debt` only with a valid `frontend-lint-assessment-v1`; this is not a
+  passed lint result. A changed-file lint diagnostic, new unmatched diagnostic,
+  command drift, missing baseline, timeout, or unparseable output is Important.
+- Treat the design evidence already bound in the canonical review context as the
+  source of truth. Do not launch a connector query or repository-wide OpenSpec/
+  `ai_workspace` search to replace frozen evidence; label a missing bound evidence
+  reference accurately instead.
+
+## Review Sequence
+
+1. Establish changed-file inventory and write boundaries.
+2. Compare the bound contract with the approved constraints and cumulative diff.
+3. Map each criterion to code, states, tests, and evidence.
+4. Inspect interactions, state/data/API behavior, failure paths, and regressions.
+5. Check mock selection, contract-to-fixture mapping, activation/default path,
+   handler/fixture/adapter and consumer diff, verification, production imports, and
+   the real-integration gap.
+6. Check bound design evidence, responsive/a11y behavior, dependencies, and maintenance.
+7. Classify findings and derive the verdict mechanically.
+
+```text
+- [Critical|Important|Minor] path:line — Problem; impact; required correction; evidence.
+```
+
+## Pass Rules
+
+- No Critical or Important findings remain.
+- Required static and behavior nodes ran and passed.
+- Lint is `passed` or evidence-backed `baseline-debt`; typecheck, build, and test are
+  passed. Any debt count and affected unchanged files remain disclosed.
+- Changed files are authorized.
+- Criteria and applicable states have implementation and evidence.
+- Required Mock-backed behavior passed; any generated Mock-specific verification also
+  passed; Mock is not enabled by default in production. For default-auto skipped
+  Mock, the real request remains default and the Real Integration Gap is preserved.
+- Optional unavailable knowledge/browser/visual/manual checks remain explicit risks.