tasks ready

.opencode/command/speckit.tasks.md

@@ -1,13 +1,13 @@
 ---
-description: Generate an actionable, dependency-ordered tasks.md for the active Rust MCP feature.
+description: Generate an actionable, dependency-ordered tasks.md for the active Python/Svelte feature.
 handoffs:
   - label: Analyze For Consistency
     agent: speckit.analyze
-    prompt: Run a cross-artifact consistency analysis for the Rust MCP feature
+    prompt: Run a cross-artifact consistency analysis for the Python/Svelte feature
     send: true
   - label: Implement Project
     agent: speckit.implement
-    prompt: Start implementation in phases for the Rust MCP feature
+    prompt: Start implementation in phases for the Python/Svelte feature
     send: true
 ---
 
@@ -31,9 +31,9 @@ You **MUST** consider the user input before proceeding (if not empty).
 
 3. **Build the task model**:
    - Extract user stories and priorities from `spec.md`
-   - Extract repository structure, tool/resource scope, verification stack, and semantic constraints from `plan.md`
+   - Extract repository structure, backend/frontend scope, verification stack, and semantic constraints from `plan.md`
    - Extract accepted-path and rejected-path memory from ADRs and `contracts/modules.md`
-   - Map entities, tool payloads, runtime evidence, and verification scenarios to stories
+   - Map entities, API payloads, UI components, and verification scenarios to stories
    - Generate tasks grouped by story and ordered by dependency
    - Validate that no task schedules an ADR-rejected path
 
@@ -41,9 +41,9 @@ You **MUST** consider the user input before proceeding (if not empty).
    - Phase 1: Setup
    - Phase 2: Foundational work
    - Phase 3+: one phase per user story in priority order
-    - Final phase: polish and cross-cutting verification
-    - Every task must use the strict checklist format and include exact file paths
-    - Write the final document to `FEATURE_DIR/tasks.md`, never to `.kilo/plans/` or other side folders
+   - Final phase: polish and cross-cutting verification
+   - Every task must use the strict checklist format and include exact file paths
+   - Write the final document to `FEATURE_DIR/tasks.md`, never to `.kilo/plans/` or other side folders
 
 5. **Report** the generated path and summarize:
    - total task count
@@ -74,38 +74,52 @@ Rules:
 4. `[USx]` required only for user-story phases
 5. exact file paths required in the description
 
-### Rust / MCP Pathing
+### Python / Svelte Pathing
 
 Prefer real repository paths such as:
 
-- `src/server/*.rs`
-- `src/services/**/*.rs`
-- `src/models/*.rs`
-- `src/semantics/*.rs`
-- `tests/*.rs`
+**Backend (Python):**
+- `backend/src/api/*.py` (FastAPI routes)
+- `backend/src/core/**/*.py` (core services, task manager, auth, migration, plugins)
+- `backend/src/models/*.py` (SQLAlchemy models)
+- `backend/src/services/*.py` (business logic)
+- `backend/src/schemas/*.py` (Pydantic schemas)
+- `backend/tests/*.py` (pytest tests)
+
+**Frontend (Svelte):**
+- `frontend/src/routes/**/*.svelte` (SvelteKit pages)
+- `frontend/src/lib/components/**/*.svelte` (reusable Svelte 5 components)
+- `frontend/src/lib/stores/*.svelte.js` (Svelte rune stores)
+- `frontend/src/lib/api/*.js` (API client modules)
+- `frontend/tests/**/*.test.js` (vitest tests)
+
+**Shared/Infrastructure:**
 - `docs/adr/*.md`
+- `docker/*`
 - `specs/<feature>/contracts/*.md`
 
 Do **not** generate default tasks for:
 
-- `backend/` or `frontend/`
-- `*.py`
-- `.svelte`
-- `__tests__/`
+- `src/**/*.rs` or `tests/*.rs`
+- `Cargo.toml`
+- `cargo` commands
+- MCP server/tool/resource syntax unless the feature actually introduces them
 
 ### Verification Discipline
 
 Each story phase must end with:
 
-- a verification task against `ux_reference.md` interpreted as the caller/operator interaction contract
+- a verification task against `ux_reference.md` interpreted as the API caller, CLI operator, or Svelte UX interaction contract
 - a semantic audit / verification task tied to repository validators and touched contracts
 
 Typical verification tasks may include:
 
-- focused `cargo test` commands
-- `cargo test --all-targets --all-features -- --nocapture`
-- `cargo clippy --all-targets --all-features -- -D warnings`
-- `python3 scripts/static_verify.py`
+- focused `pytest backend/tests/test_<module>.py` commands
+- `cd backend && pytest` (full backend suite)
+- `cd frontend && npm run test` (vitest suite)
+- `ruff check backend/` (Python lint)
+- `cd frontend && npm run build` (Svelte build validation)
+- `python3 scripts/static_verify.py` (semantic static verification)
 
 Only include the commands that are truly required by the feature scope.
 
@@ -115,8 +129,9 @@ If a task implements or depends on a guarded contract, append a concise guardrai
 
 Examples:
 
-- `- [ ] T021 [US1] Implement deterministic tool envelope mapping in src/server/tools.rs (RATIONALE: preserve task-shaped MCP parity; REJECTED: ad-hoc per-tool response shapes)`
-- `- [ ] T033 [US2] Add runtime evidence verification in tests/server_protocol.rs (RATIONALE: C4/C5 flows must expose belief markers; REJECTED: relying on manual log inspection only)`
+- `- [ ] T021 [US1] Implement report generation endpoint in backend/src/api/reports.py (RATIONALE: unified report envelope preserves task-shaped parity; REJECTED: ad-hoc per-endpoint response shapes)`
+- `- [ ] T033 [US2] Add WebSocket logging handler in backend/src/core/task_manager/ws_handler.py (RATIONALE: C4/C5 flows must expose real-time log streaming; REJECTED: polling-based log retrieval)`
+- `- [ ] T040 [US3] Create DashboardCard component in frontend/src/lib/components/DashboardCard.svelte (RATIONALE: @UX_STATE must cover Idle/Loading/Error/Empty; REJECTED: single-state inline rendering without recovery)`
 
 If no safe executable task wording exists because the accepted path is still unclear, stop and emit `[NEED_CONTEXT: target]`.
 
@@ -124,8 +139,9 @@ If no safe executable task wording exists because the accepted path is still unc
 
 Tests are optional only when the feature truly has no new verification surface. In this repository, test tasks are usually expected for:
 
-- new MCP tools/resources
-- new query/mutation flows
+- new FastAPI endpoints / WebSocket handlers
+- new plugin or service modules
+- new Svelte components with `@UX_STATE` contracts
 - C4/C5 semantic contracts
 - runtime evidence / belief-state behavior
 - rejected-path regression coverage
@@ -136,5 +152,5 @@ Before finalizing `tasks.md`, verify that:
 
 - blocking ADRs are inherited into setup/foundational or downstream story tasks
 - no task text schedules a rejected path
-- story tasks remain executable within the actual Rust crate structure
+- story tasks remain executable within the actual Python/Svelte repository structure
 - at least one explicit verification task protects against rejected-path regression