@tea-agent/loop-agent 0.42.0-next.9 → 0.42.1

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

@@ -14,11 +14,103 @@
 - Static targets are for project-wide commands and are traced by file and command
   only.
 
+### Behavior target shape (canonical example)
+
+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-COUNTER-LOCAL-CONSTRAINTS",
+  "file": "src/App.test.tsx",
+  "requirementIds": ["AC-FE-001", "AC-FE-005"],
+  "uiStates": ["disabled-minus", "default"]
+}
+```
+
+`stylingStrategy` describes how the frozen look is achieved; it must stay inside
+the task's declared scope. Capabilities the task source lists as non-goals (e.g.
+responsive/mobile layout, animations) must not be promised here, and themes or
+CSS conventions must not be claimed without a Scout-confirmed repository fact.
+
+### UI state declaration shape (canonical example)
+
+Use the exact state names referenced by behavior targets. Each applicable state
+carries behavior, implementation targets, and verification target ids:
+
+```json
+{
+  "uiStates": [
+    {
+      "name": "disabled-minus",
+      "applicable": true,
+      "expectedBehavior": "minus button disabled at count 0",
+      "implementationTargets": ["src/components/SmokeCounter.tsx"],
+      "verificationTargetIds": ["VT-COUNTER-LOCAL-CONSTRAINTS"]
+    }
+  ],
+  "interactions": [
+    {
+      "name": "refresh",
+      "trigger": "User clicks refresh",
+      "expectedBehavior": "reloads runs",
+      "implementationTargets": ["src/App.tsx"],
+      "verificationTargetIds": ["VT-SMOKE-COUNTER-BEHAVIOR"]
+    }
+  ]
+}
+```
+
+### Implementation target coverage (canonical example)
+
+`targets.files` is the union of every requirement's `implementationTargets`; list
+each required component, integration point, and sibling source. Admission adds
+non-static verification target files to the writer writeSet separately.
+
+```json
+{
+  "id": "AC-FE-001",
+  "implementationTargets": [
+    "src/components/SmokeCounter.tsx",
+    "src/App.tsx"
+  ],
+  "verificationTargetIds": [
+    "VT-SMOKE-COUNTER-BEHAVIOR",
+    "VT-COUNTER-LOCAL-CONSTRAINTS"
+  ]
+}
+```
+
+### Bidirectional VT cross-reference invariant
+
+Every requirement → VT citation must close in both directions: the cited VT's
+`requirementIds` must list the citing requirement back. The checker reports the
+missing direction; fix it in-node by re-submitting the corrected VT entry with
+the same id and `replace=true`. `replace` is a full replacement: the latest
+submission under an id becomes the authoritative entry (a subset re-submission
+is the new rule). A `duplicate` receipt is a correction invitation, not a
+prohibition, and a reverse-reference backfill is not "re-deriving committed
+facts".
+
+## UX vocabulary (registry first)
+
+- Record `record_state_registry` BEFORE any `record_state_flow`: one compact
+   global vocabulary of UI-state and interaction names. Details use complete execution
+   group scopes; reuse shared names across scopes, never one name per AC or a
+   rename of an already-recorded concept (kebab-case behavior-domain names, e.g.
+   `planner-task-edit`, `focus-queue-move`).
+- UI states use the contract's declared authoritative ids (`declaredUiStates`
+  in the plan input) when the source declares a state table.
+- Retry slices see `committedUx` in the plan input: reuse those exact names.
+
 ## Global decisions
 
 Keep route/component placement, Mock/data strategy, and dependency/deviation policy
-as explicit global decisions rather than duplicating them across each requirement.
-Use only frozen command labels and Scout-confirmed paths.
+global. Use only frozen command labels and Scout-confirmed paths.
+
+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 deterministic Mock-backed
@@ -32,6 +124,23 @@ widen the write set.
 ## Runtime-owned fields and terminal
 
 The runtime owns `schemaVersion`, `sourceBinding`, risk, canonical target files,
-aliases, command allowlisting, path containment, and final validation. Submit only
-editable decision facts, then call `finalize_plan` exactly once. The deterministic
-design policy materializes the canonical implementation contract.
+`requiredDeliverables`, aliases, command allowlisting, path containment, and final
+validation. Submit editable decision facts, then call `finalize_plan`; correct
+rejected facts and retry until one successful terminal commit. The deterministic design policy materializes the canonical implementation
+contract: every file in the Contract's explicit source-bound delivery inventory
+must be planned (`requiredDeliverables` gate). Permissions, prohibitions, examples
+and read-only references do not create delivery obligations. Plan receives this
+inventory as `requiredDeliverables`; it cannot add, remove or reinterpret it.
+Missing files and UX name collisions are reported by finalize_plan before commit
+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
+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.

package/skills/frontend-plan/references/design-decisions.md

@@ -15,3 +15,35 @@ Contract. Do not search specification roots or nearby code from Plan.
   responsive, and accessibility behavior; use not-applicable only with a reason.
 - Record styling strategy, deviations, conflicts, and unresolved gaps explicitly.
   Never silently replace a spec-defined component or claim unread evidence.
+
+### Component choice shape (canonical example)
+
+`purpose` must exactly match a declared UI state or interaction name — it is the
+coverage key the deterministic policy checks. Do not invent synonyms, and never
+swap a task-mandated component for another name without recording a deviation.
+
+```json
+[
+  {
+    "purpose": "disabled-minus",
+    "component": "SmokeCounter",
+    "decision": "new",
+    "sourceRequirementIds": ["AC-FE-001"],
+    "sourceFragmentId": "REQ-SRC-AC-FE-001",
+    "rationale": "task mandates a new SmokeCounter card on the home surface"
+  },
+  {
+    "purpose": "refresh",
+    "component": "RunFilterBar",
+    "decision": "reuse-existing",
+    "rationale": "reuses the Scout-confirmed filter bar for the refresh interaction"
+  }
+]
+```
+
+For `decision: "new"`, pass `sourceRequirementIds` + `sourceFragmentId` and let
+the runtime derive the exact task-source citation — never hand-write a
+`specReference`. A `reuse-existing` choice covers behavioural interactions
+without one row per interaction; each applicable visual UI state still needs its
+own `purpose` match (or an explicitly scoped stylingStrategy covering the visual
+dimension).

package/skills/frontend-review/SKILL.md

@@ -9,25 +9,24 @@ references:
 
 # Frontend Review
 
-Use for `frontend-review-pi`; read the findings guide and capacity diagnostic first.
-Inputs are `contracts/frontend-review-context.json`, its hash-bound contract
-reference/index and diff fragments, and only source files named by that diff. Use
-indexed contract sections when recommended. Do not reopen task sources, plans,
-design-review prose, OpenSpec, or `ai_workspace/`; the bound context is authoritative.
+Use `contracts/frontend-review-context.json`, its hash-bound contract index and diff,
+and only files named by the diff. Read the findings guide and capacity diagnostic;
+use indexed sections when advised. Do not reopen task sources, plans, OpenSpec,
+design-review prose or `ai_workspace/`.
 
 ## Authoritative Terminal
 
-Complete the review with exactly one committed typed tool call:
+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:
 
 - `approve_review` when no Critical/Important finding remains;
 - `request_review_changes` for a defect, missing required evidence, forbidden
   write, or unmet acceptance criterion. It must include a typed `issueCategory`,
-  at least one `evidenceRef`, and non-empty findings.
+  at least one `evidenceRef`, and non-empty findings (saved or supplied).
 
-The typed terminal is the only authoritative outcome. Do not require or emit a
-`VERDICT:` line or response-text JSON verdict. A request for review changes ends
-this run and is handled by the recovery controller rather than a same-run repair
-branch.
+Only the typed terminal controls the outcome; no `VERDICT:` line or JSON verdict.
+Requested changes end this run; the recovery controller owns follow-up.
 
 ## Review Scope
 

package/skills/frontend-scout/references/scout-evidence.md

@@ -21,3 +21,7 @@ the exact evidence. Do not recursively inspect unrelated directories.
 Commit `complete` only when the target surface is sufficiently proven for Plan to
 reuse without repository discovery. Otherwise commit `blocked` and list every
 unresolved path or ownership question. Do not shift discovery work into Plan.
+
+A successful typed receipt is durable. Reuse only facts bound to the same source
+and fresh file evidence; changed or missing evidence requires Scout refresh. Do
+not replay stale success or repeat complete discovery merely because a reply was lost.

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

@@ -1 +0,0 @@
-import{ag as o,ah as n}from"./mermaid.core-CWhj4JXN.js";const t=(a,r)=>o.lang.round(n.parse(a)[r]);export{t as c};

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

@@ -1 +0,0 @@
-import{s as a,c as s,a as e,C as t}from"./chunk-GF5L2VYU-CY9Xx2jV.js";import{_ as i}from"./mermaid.core-CWhj4JXN.js";import"./chunk-5VM5RSS4-BYn1Hu4R.js";import"./chunk-XXDRQBXY-Ddx1KC1l.js";import"./chunk-KBJHAD2P-DZ8AStLL.js";import"./chunk-2GRJ4B5K-B1Aq6BcK.js";import"./index-D9Sc0f0y.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-CuToPeGV.js

@@ -1 +0,0 @@
-import{s as a,c as s,a as e,C as t}from"./chunk-GF5L2VYU-CY9Xx2jV.js";import{_ as i}from"./mermaid.core-CWhj4JXN.js";import"./chunk-5VM5RSS4-BYn1Hu4R.js";import"./chunk-XXDRQBXY-Ddx1KC1l.js";import"./chunk-KBJHAD2P-DZ8AStLL.js";import"./chunk-2GRJ4B5K-B1Aq6BcK.js";import"./index-D9Sc0f0y.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};