@tea-agent/loop-agent 0.43.0-next.17 → 0.43.0-next.19

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 identifier of that
+  contract entry only; it never needs to appear in test titles. Do not add tests
+  or rename titles to carry generated ids.
 - 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

@@ -4,7 +4,7 @@ description: Use to review completed frontend code and verification before close
 references:
   - path: references/review-findings.md
     required: true
-    maxChars: 2800
+    maxChars: 3200
 ---
 
 # Frontend Review
@@ -16,9 +16,9 @@ design-review prose or `ai_workspace/`.
 
 ## Authoritative Terminal
 
-Submit findings one at a time with `record_review_finding` using stable IDs.
-Use `replace:true` for revisions. The terminal automatically includes saved findings;
-do not repeat their array. Correct rejected calls, then commit one successful terminal:
+Submit findings one at a time with `record_review_finding` (stable IDs,
+`replace:true` for revisions). The terminal auto-includes saved findings; correct
+rejected calls, then commit one successful terminal:
 
 - `approve_review` when no Critical/Important finding remains;
 - `request_review_changes` for a defect, missing required evidence, forbidden
@@ -30,24 +30,20 @@ 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.
-
-## Evidence And Output
-
-Findings cite a tight file location, exact command/result, or named DAG artifact.
-Separate confirmed defects, missing evidence, and residual risks using Findings,
-Verification Assessment, UX Assessment, and Residual Risks headings.
-
-A pass requires no Critical/Important findings and all required shell checks passed.
-Still report knowledge-source status and optional browser/manual gaps.
+Follow the findings guide's review sequence and pass rules. In addition:
+
+- Compare intent, contract, plan, diff, and evidence; report altered requirements.
+  Check every changed file against allowed/forbidden/approved write scope, and map
+  criteria to behavior, applicable UI states, tests, and shell evidence.
+- Mock strategies need the real request as default, contract-aligned fixtures,
+  production isolation, and no false real-integration claim; `not-needed` needs
+  real/no-remote evidence, or a default-auto skipped-Mock rationale with the Real
+  Integration Gap preserved when no project Mock capability is confirmed.
+- Inspect lint only when `lintConfigured: true`; with `lintConfigured: false` there
+  is no lint surface — report no lint finding. Typecheck, build, and test still
+  require successful exits.
+- Read shell exit status from `verificationEvidence.commands`, not prose or the
+  trace: the trace proves binding only, never that a command succeeded. Judge
+  whether the tests are sufficient; do not guess whether the commands ran.
+- Evaluate component/design claims against bound evidence; do not replace it with a
+  repository-wide search or connector query. Do not edit files.

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

@@ -1,30 +1,54 @@
 # 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: verify each frozen command through
+  `verificationEvidence.commands` (per-command `exitCode`/`ok`) instead of inferring from
+  the trace, which only proves binding.
+- When the task declares lint commands (`lintConfigured: true`), lint is `passed` or
+  evidence-backed `baseline-debt`; typecheck, build, and test are passed. Any debt count
+  and affected unchanged files remain disclosed. A task that declares no lint commands
+  reports `lintConfigured: false`: lint is not part of its verification surface, so
+  report no lint finding either way.
+- 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.

package/dist/worker/console/static/assets/channel-BxdTlb_5.js

@@ -1 +0,0 @@
-import{ag as o,ah as n}from"./mermaid.core-CQA4Nzmo.js";const t=(a,r)=>o.lang.round(n.parse(a)[r]);export{t as c};

package/dist/worker/console/static/assets/classDiagram-JCYQIIEL-_ByA1Nf8.js

@@ -1 +0,0 @@
-import{s as a,c as s,a as e,C as t}from"./chunk-GF5L2VYU-D9UA7hUb.js";import{_ as i}from"./mermaid.core-CQA4Nzmo.js";import"./chunk-5VM5RSS4-DGdvrNm8.js";import"./chunk-XXDRQBXY-CScR6mDD.js";import"./chunk-KBJHAD2P-BmuEOIh7.js";import"./chunk-2GRJ4B5K-CoviemSL.js";import"./index-wXlQohNs.js";var n={parser:e,get db(){return new t},renderer:s,styles:a,init:i(r=>{r.class||(r.class={}),r.class.arrowMarkerAbsolute=r.arrowMarkerAbsolute},"init")};export{n as diagram};

package/dist/worker/console/static/assets/classDiagram-v2-OCEON4UE-_ByA1Nf8.js

@@ -1 +0,0 @@
-import{s as a,c as s,a as e,C as t}from"./chunk-GF5L2VYU-D9UA7hUb.js";import{_ as i}from"./mermaid.core-CQA4Nzmo.js";import"./chunk-5VM5RSS4-DGdvrNm8.js";import"./chunk-XXDRQBXY-CScR6mDD.js";import"./chunk-KBJHAD2P-BmuEOIh7.js";import"./chunk-2GRJ4B5K-CoviemSL.js";import"./index-wXlQohNs.js";var n={parser:e,get db(){return new t},renderer:s,styles:a,init:i(r=>{r.class||(r.class={}),r.class.arrowMarkerAbsolute=r.arrowMarkerAbsolute},"init")};export{n as diagram};