ss-tools/specs/017-llm-analysis-plugin/tasks.md

# Tasks: LLM Analysis & Documentation Plugins v2

**Feature**: `017-llm-analysis-plugin`
**Status**: v2 Implementation — ~86% complete (86/99 tasks)  
**Spec**: [spec.md](spec.md) | **Plan**: [plan.md](plan.md) | **Data Model**: [data-model.md](data-model.md)

## User Stories & Priorities

| ID | Story | Priority | Phase |
|----|-------|----------|-------|
| US1 | Create & Schedule Validation Task | P1 | 3 |
| US2 | Validation Task List & History | P1 | 3 |
| US3 | Dual-Path Dashboard Health Analysis | P1 | 4, 5 |
| US4 | URL Parsing Integration | P1 | 6 |
| US5 | Provider/Prompt Per-Task + Settings Cleanup | P2 | 7 |
| US6 | Dashboard Hub Cleanup | P2 | 8 |
| US7 | Dataset Documentation (unchanged) | P2 | — |
| US8 | Git Commit Suggestion (unchanged) | P3 | — |

## Dependencies

```
Phase 1 (Setup)
    └─→ Phase 2 (Foundational)
            ├─→ Phase 3 (US1 + US2) — Task CRUD
            │       └─→ Phase 7 (US5) — Provider/Prompt
            ├─→ Phase 4 (US3 Path B) — Text-only execution
            ├─→ Phase 5 (US3 Path A) — Multi-chunk screenshots
            ├─→ Phase 6 (US4) — URL parsing
            └─→ Phase 8 (US6) — Hub cleanup (independent)
                    └─→ Phase 9 (Polish)
```

**Parallel**: Phase 4 + 5 + 6 can run concurrently after Phase 2. Phase 7 is tight with Phase 3. Phase 8 is independent.

---

## Phase 1: Setup — Database Migrations

**Goal**: Schema changes for v2 models. Blocks everything.

- [x] T001 [P] Add `sources` ORM relationship + `source_snapshot` JSON (audit only, nullable) to `ValidationPolicy` in `backend/src/models/llm.py`. No JSON denormalization column for authoritative state — relational `ValidationSource` table is the single source of truth.
- [x] T002 [P] Create `ValidationSource` SQLAlchemy model in `backend/src/models/llm.py` (id, policy_id FK, type, value, parsed_context JSON, status enum, resolved_dashboard_id, title, last_error, last_checked_at)
- [x] T003 [P] Add new columns to `ValidationPolicy` model: `provider_id` (String), `prompt_template` (Text, nullable), `screenshot_enabled` (Boolean, default true), `logs_enabled` (Boolean, default true), `execute_chart_data` (Boolean, default false), `llm_batch_size` (Integer, default 1 — full isolation), `policy_dashboard_concurrency_limit` (Integer, default 3) in `backend/src/models/llm.py`
- [x] T003a [P] Add `global_validation_worker_limit` config setting (default: 3) — max concurrent policy runs across all tasks. Stored in app config in `GLOBAL_VALIDATION_WORKER_LIMIT` field in `backend/src/core/config_models.py`
- [x] T004 [P] Add new columns to `ValidationRecord` model: `execution_path` (String), `source_id` (FK → ValidationSource, nullable), `dataset_health` (JSON, nullable), `chart_data_results` (JSON, nullable), `tab_screenshots` (JSON, nullable), `token_usage` (JSON, nullable), `timings` (JSON, nullable), `screenshot_paths` (JSON, nullable), `logs_sent_to_llm` (JSON, nullable), `run_id` (FK → ValidationRun) in `backend/src/models/llm.py`
- [x] T004a [P] Create `ValidationRun` SQLAlchemy model in `backend/src/models/llm.py`: id, policy_id (FK), task_id (nullable), started_at, finished_at, trigger (manual/scheduled), status (running/completed/partial/failed), dashboard_count, pass_count, warn_count, fail_count, unknown_count
- [x] T005 Create Alembic migration for all T001–T004a schema changes in `backend/alembic/versions/`
- [x] T006 Write data migration script: convert existing `dashboard_ids: list[str]` → `sources` rows in `backend/src/plugins/llm_analysis/migrations/v1_to_v2.py`
- [x] T007 [P] Add `DEFAULT_LLM_PROMPTS["dashboard_validation_prompt_multimodal"]` (Path A, image-focused) and `DEFAULT_LLM_PROMPTS["dashboard_validation_prompt_text"]` (Path B, topology-focused) to `backend/src/services/llm_prompt_templates.py`

**Verification**: `pytest backend/tests/models/test_llm_v2.py -v` — all models create/query correctly. Migration runs without data loss.

---

## Phase 2: Foundational — Services & Refactored Plugin Core

**Goal**: `ValidationTaskService`, `DatasetHealthChecker`, refactored `ScreenshotService` (multi-chunk), `LLMClient` dual-mode. Blocks US1–US6.

### 2.1 ValidationTaskService

- [x] T008 [P] Implement `ValidationTaskService.create_task()` — creates `ValidationPolicy` + `ValidationSource[]` rows, validates provider_id against execution path, in `backend/src/services/validation_service.py`
- [x] T009 [P] Implement `ValidationTaskService.get_task(id)` — returns policy + sources with current status, in `backend/src/services/validation_service.py`
- [x] T010 [P] Implement `ValidationTaskService.list_tasks(env_id)` — returns all policies with aggregated last-run status, in `backend/src/services/validation_service.py`
- [x] T011 [P] Implement `ValidationTaskService.update_task(id, data)` — updates policy fields + sources, in `backend/src/services/validation_service.py`
- [x] T012 [P] Implement `ValidationTaskService.delete_task(id)` — deletes policy + cascades to sources + records, in `backend/src/services/validation_service.py`
- [x] T013 [P] Implement `ValidationTaskService.trigger_run(policy_id)` — checks FR-054 (same task not already running via ValidationRun with status=running), creates a `ValidationRun` record (FR-055d), enqueues dashboard validation tasks per FR-055, in `backend/src/services/validation_service.py`
- [x] T014 [P] Implement `ValidationTaskService.get_run_history(policy_id, page)` — paginated `ValidationRun` list with aggregate counts, in `backend/src/services/validation_service.py`
- [x] T015 [P] Implement `ValidationTaskService.get_run_detail(run_id)` — full run with all dashboard records, aggregate counts, in `backend/src/services/validation_service.py`
- [x] T015a [P] Implement `ValidationTaskService._finalize_run(run_id)` — computes aggregate counts from all `ValidationRecord`s with this `run_id`, sets finished_at and status, in `backend/src/services/validation_service.py`

### 2.2 DatasetHealthChecker (Path B)

- [x] T016 [P] Implement `DatasetHealthChecker` class in `backend/src/plugins/llm_analysis/service.py`:
  - `check_dataset_health(dataset_id)` — calls `GET /api/v1/dataset/{id}`, extracts database name, backend, kind, verifies accessibility
  - `check_chart_data(chart_id, form_data)` — optional level 3-4 checks
  - `check_dashboard_datasets(chart_list, execute_chart_data)` — batch check all unique datasets

### 2.3 ScreenshotService Refactor (multi-chunk for Path A)

- [x] T017 [P] Implement `ScreenshotService.capture_dashboard_chunks(dashboard_id, parsed_filters, output_dir) → list[{tab_name, path}]` in `backend/src/plugins/llm_analysis/service.py`:
  - Login → navigate with filters/tabs → iterate tabs → per-tab viewport (1920×1200) → CDP screenshot → collect PNG paths

### 2.3b Image Pipeline (PNG → JPEG + WebP)

- [x] T017a [P] Implement `ScreenshotService._convert_screenshots_for_llm(png_paths: list[str]) → list[str]` in `backend/src/plugins/llm_analysis/service.py`:
  - PNG → Pillow convert → JPEG quality=60, max 1024px → save as temp JPEG → return paths
  - JPEG files deleted after LLM call succeeds
- [x] T017b [P] Implement `ScreenshotService._archive_screenshots_as_webp(png_paths: list[str], output_dir: str) → list[{tab_name, webp_path}]` in `backend/src/plugins/llm_analysis/service.py`:
  - PNG → Pillow convert → WebP quality=80, lossy → save to `{output_dir}/{tab_name}_{timestamp}.webp`
  - Delete PNG after WebP saved
  - Fallback: if WebP encode fails → keep PNG, log WARN (FR-059 edge case)
- [x] T017c [P] Implement `ScreenshotService._cleanup_temp_files(paths: list[str])` in `backend/src/plugins/llm_analysis/service.py`:
  - Delete PNG and JPEG intermediates after successful archive + LLM call

### 2.4 LLMClient Dual-Mode

- [x] T018 [P] Implement `LLMClient.analyze_dashboard_multimodal(screenshot_paths, logs, prompt) → dict` in `backend/src/plugins/llm_analysis/service.py`:
  - Sends all images in single `content[]` array → multimodal LLM → JSON result
- [x] T019 [P] Implement `LLMClient.analyze_dashboard_text_batch(payloads, prompt) → dict` in `backend/src/plugins/llm_analysis/service.py`:
  - Text-only LLM call with per-dashboard sections → `{dashboards: [{dashboard_id, status, summary, issues}]}`
- [x] T020 [P] Implement `LLMClient._estimate_payload_size()` and `LLMClient._reduce_image_quality()` in `backend/src/plugins/llm_analysis/service.py`:
  - FR-056: estimate → progressive reduction (JPEG quality 60→30, width 1024→800) → Path B fallback
  - **Belief-runtime**: `belief_scope("payload_reduction")` + `reason()` before each reduction + `reflect()` after outcome

### 2.5 Plugin Refactor (dispatch to Path A / Path B)

- [x] T021 Implement `DashboardValidationPlugin._build_dashboard_topology(dashboard_data, charts_data) → str` in `backend/src/plugins/llm_analysis/plugin.py`:
  - Recursive `position_json` parsing → tab → row → chart hierarchy → text description
- [x] T022 Refactor `DashboardValidationPlugin.execute()` to dispatch based on `screenshot_enabled`:
  - True → `_execute_path_a()`: call ScreenshotService → LLMClient multimodal
  - False → `_execute_path_b()`: call API chain → DatasetHealthChecker → LLMClient text
  - **Belief-runtime**: `belief_scope("execute_path_a")` / `belief_scope("execute_path_b")` + `reason()` at entry + `reflect()` at exit

### 2.7 Security & Retention (new)

- [x] T024a [P] Implement `RedactionService` in `backend/src/plugins/llm_analysis/service.py`:
  - `redact_logs(logs: list[str]) → list[str]` — strip PII, credentials, query text, tokens from URLs, native filter values
  - `redact_raw_response(raw: str) → str` — strip sensitive data before persistence
- [x] T024b [P] Add retention config to app settings: `LLM_SCREENSHOT_RETENTION_DAYS=30`, `LLM_RAW_RESPONSE_RETENTION_DAYS=30` in `backend/src/core/config_models.py`
- [x] T024c [P] Rename all «molecular-cot» references in logs to «decision audit logging»: REASON/REFLECT markers use structured JSON with deterministic metadata only per FR-029b. Updated `backend/src/core/logger.py`

- [x] T023 [P] Add `dashboard_validation_prompt_multimodal` (Path A) template to `DEFAULT_LLM_PROMPTS` in `backend/src/services/llm_prompt_templates.py`
- [x] T024 [P] Add `dashboard_validation_prompt_text` (Path B) template to `DEFAULT_LLM_PROMPTS` in `backend/src/services/llm_prompt_templates.py`

**Verification**: `pytest backend/tests/services/test_validation_task_service.py backend/tests/plugins/llm_analysis/test_service.py -v`

---

## Phase 3: US1 + US2 — Task CRUD API + Task List Page

**Goal**: REST API for validation tasks + frontend task list and create/edit form.

### 3.1 API Routes

- [x] T025 [US1] Implement `POST /api/validation-tasks` — creates `ValidationPolicy` + `ValidationSource[]` in `backend/src/api/routes/validation_tasks.py`
- [x] T026 [US1] Implement `GET /api/validation-tasks` — list all tasks with aggregated last-run status in `backend/src/api/routes/validation_tasks.py`
- [x] T027 [US2] Implement `GET /api/validation-tasks/{policy_id}` — task detail + per-source status in `backend/src/api/routes/validation_tasks.py`
- [x] T028 [US1] Implement `PUT /api/validation-tasks/{policy_id}` — update task in `backend/src/api/routes/validation_tasks.py`
- [x] T029 [US1] Implement `DELETE /api/validation-tasks/{policy_id}` — delete task (cascade sources + records), in `backend/src/api/routes/validation_tasks.py`
- [x] T030 [US1] Implement `POST /api/validation-tasks/{policy_id}/run` — manual trigger (checks FR-054 + FR-055) in `backend/src/api/routes/validation_tasks.py`
- [x] T031 [US2] Implement `GET /api/validation-tasks/{policy_id}/runs` — paginated run history (ValidationRun list, not individual records) in `backend/src/api/routes/validation_tasks.py`
- [x] T032 [US2] Implement `GET /api/validation-tasks/{policy_id}/runs/{run_id}` — full run detail: run metadata + all per-dashboard ValidationRecords with dataset_health, screenshots, logs, timings, in `backend/src/api/routes/validation_tasks.py`
- [x] T032b Implement legacy redirect: `GET /reports/llm/{taskId}` → 302 to `/validation-tasks/{policy_id}/runs/{run_id}` when `taskId` maps to `ValidationRun.task_id`, in `backend/src/api/routes/validation_tasks.py`

### 3.2 Task List Page

- [x] T035 [US2] Create `frontend/src/routes/validation-tasks/+page.svelte` — task list page with columns: name, schedule, last run status (PASS/WARN/FAIL/UNKNOWN), dashboard count, status (active/inactive), actions (edit/delete/run now)
- [x] T036 [US2] Create `frontend/src/routes/validation-tasks/+page.js` — load function calling `GET /api/validation-tasks`

### 3.3 Task Create/Edit Form

- [x] T037 [US1] Create `frontend/src/routes/validation-tasks/new/+page.svelte` — task creation page
- [x] T038 [US1] Create `frontend/src/components/llm/ValidationTaskForm.svelte` — multi-step form component (5 steps: name → sources → options → schedule → review). Includes provider filter per FR-050, path-specific prompt defaults per FR-048, screenshot toggle per FR-053
- [x] T039 [US1] Create `frontend/src/routes/validation-tasks/[policyId]/edit/+page.svelte` — task edit page (reuses `ValidationTaskForm`)

### 3.5 Task Detail Page + Report Page

- [x] T040 [US2] Create `frontend/src/routes/validation-tasks/[policyId]/+page.svelte` — task detail page with run history table, per-source breakdown, actions
- [x] T041 [US2] Create `frontend/src/routes/validation-tasks/[policyId]/+page.js` — load function calling `GET /api/validation-tasks/{id}` + `GET /api/validation-tasks/{id}/runs`
- [x] T041a [US2] Create `frontend/src/routes/validation-tasks/[policyId]/runs/[runId]/+page.svelte` — multi-dashboard run report page with collapsible dashboard list, Path A/B sections, screenshots, dataset health, logs, timings
- [x] T041b Implement `GET /api/validation-tasks/{policy_id}/runs/{run_id}` — API endpoint returning full run with all records

### 3.6 Shared Report Component

- [x] T042 [US1] Create `frontend/src/lib/components/llm/ValidationTaskReport.svelte` — shared report component with status badge, summary, issues table, execution path indicator

**Verification**: Create task via UI → list shows task → detail shows sources → run now → report renders.

---

## Phase 4: US3 — Path B Execution (Text-Only + Batching)

**Goal**: Text-only validation with dataset health checking, optional chart data execution, and LLM batching.

- [x] T043 [US3] Implement `DashboardValidationPlugin._execute_path_b(run_id, dashboard_sources, params, context)` in `backend/src/plugins/llm_analysis/plugin.py`:
  1. For each dashboard: collect topology via `_build_dashboard_topology()` + dataset health via `DatasetHealthChecker` + logs
  2. Default: `llm_batch_size=1` — one LLM call per dashboard (full isolation). Values >1 group dashboards into batches per FR-045a
  3. For each batch: build structured prompt with per-dashboard labeled sections + strict JSON response schema `{dashboards: [{dashboard_id, status, summary, issues}]}`
  4. Call `LLMClient.analyze_dashboard_text_batch(dashboard_payloads, prompt)` → parse response
  5. Missing/parse-error dashboards → mark UNKNOWN individually, preserve other dashboards in batch
  6. Persist individual `ValidationRecord` per dashboard, linked to `run_id`
  - **Belief-runtime**: `belief_scope("execute_path_b_batch")` + `reason(f"batch {i}/{total}: {n} dashboards")` + `reflect()` with token_usage per batch
- [x] T043a [US3] Implement `LLMClient.analyze_dashboard_text_batch(payloads: list[dict], prompt: str) → dict` in `backend/src/plugins/llm_analysis/service.py`:
  - Builds prompt: per-dashboard labeled sections, enforced `{dashboards: [{dashboard_id, ...}]}` JSON schema
  - Validates response completeness: missing dashboard_id → UNKNOWN fallback per-dashboard
- [x] T044 [US3] Create DatasetHealth display in run detail page — table: dataset name, database, backend, status icon (✓/✗), error message, affected charts count
- [x] T045 [US3] Create ChartDataResults display in run detail page — table: chart name, viz_type, executed (✓/skipped), duration, row count, error

**Rejected-path regression test**:
- [x] T047 [US3] Add test: Path B batch of 5 dashboards, 1 with KXD error → only that dashboard UNKNOWN, other 4 preserved with valid results — in `backend/tests/services/test_path_b_batch.py`
- [x] T047a [US3] Add test: batch_size=1 (full isolation) → each dashboard gets individual LLM call with no cross-contamination — in `backend/tests/services/test_path_b_isolated.py`

**Verification**: Create task with 5 Path B dashboards, `llm_batch_size=1` (default) → 5 individual LLM calls, full isolation. Opt-in `llm_batch_size=3` → 2 LLM calls, structured prompt with per-dashboard isolation. Dashboard with broken dataset → only its record UNKNOWN, others preserved.

**Verification**: Create task with 5 Path B dashboards, `llm_batch_size=1` (default) → 5 individual LLM calls, full isolation. Opt-in `llm_batch_size=3` → 2 LLM calls, structured prompt with per-dashboard isolation. Dashboard with broken dataset → only its record UNKNOWN, others preserved.

---

## Phase 5: US3 — Path A Execution (Multi-Chunk Screenshots)

**Goal**: Per-tab screenshots + multimodal LLM + payload estimation.

- [x] T048 [US3] Implement `DashboardValidationPlugin._execute_path_a(params, context)` in `backend/src/plugins/llm_analysis/plugin.py`:
  1. Parse URL filters if source is URL type (re-parse per FR-057)
  2. `ScreenshotService.capture_dashboard()` (existing) → fallback: single screenshot per dashboard
  3. Log fetch via `_fetch_dashboard_logs()`
  4. `LLMClient._estimate_payload_size()` → check token budget per FR-056
  5. Quality reduction loop if needed (FR-056)
  6. `LLMClient.analyze_dashboard_multimodal()` → JSON result
  7. Fallback to `_execute_path_b()` if payload still exceeds limit
  8. Persist `ValidationRecord` with `execution_path="screenshot"`, `tab_screenshots`, `token_usage`
  - **Belief-runtime**: `belief_scope("execute_path_a")` + `reason()` before payload reduction + `reflect()` after each reduction + `reason()` on Path B fallback
- [x] T049 [US3] Update `frontend/src/routes/validation-tasks/[policyId]/runs/[runId]/+page.svelte` — add Path A sections: tab selector (from `tab_screenshots`), per-tab image viewer with zoom, issues table with tab/chart location

**Rejected-path regression test**:
- [x] T050 [US3] Add test: multi-chunk screenshots exceed token limit → quality reduction triggered → Path B fallback when still exceeded — in `backend/tests/services/test_payload_reduction.py`

**Verification**: Create task with `screenshot_enabled=true`, 5-tab dashboard → report shows per-tab screenshots + issues.

---

## Phase 6: US4 — URL Parsing Integration

**Goal**: Paste Superset URL → parse → use in task creation + execution.

- [x] T051 [US4] Implement `POST /api/validation-tasks/parse-url` in `backend/src/api/routes/validation_tasks.py`
- [x] T052 [US4] Create `frontend/src/lib/components/llm/UrlParser.svelte` — URL paste input with parse, success green banner, error red banner, partial recovery amber banner
- [x] T053 [US4] Integrate `UrlParser` into `ValidationTaskForm.svelte` — «Paste URL» tab in source selector (Step 2)
- [x] T054 [US4] Implement URL re-parse on execution per FR-057 in `DashboardValidationPlugin`:
  - For URL-type sources: call `SupersetContextExtractor.parse_superset_link()` on every run
  - If fails → mark source invalid, set last_error, log WARN
  - If dashboard_id changed → log WARN, use new ID

**Rejected-path regression test**:
- [x] T055 [US4] Add test: URL source with deleted dashboard → re-parse fails → source marked invalid, error logged, task skips source — in `backend/tests/services/test_url_reparse.py`

**Verification**: Paste Superset URL with filters → form shows dashboard title + 3 native filters + 2 active tabs → create task → execution re-parses URL successfully.

---

## Phase 7: US5 — Provider/Prompt Per-Task + Settings Cleanup

**Goal**: Remove `dashboard_validation` binding from LLM settings. Provider + prompt configured per-task.

- [x] T056 [US5] Remove `"dashboard_validation": ""` from `DEFAULT_LLM_PROVIDER_BINDINGS` in `backend/src/services/llm_prompt_templates.py`
- [ ] T057 [US5] Remove dashboard_validation binding UI row from `frontend/src/routes/admin/settings/llm/+page.svelte`
- [ ] T058 [US5] Update LLM settings API schema to exclude `dashboard_validation` from provider_bindings payload in `backend/src/schemas/llm.py`
- [x] T059 [US5] Implement provider selector filter logic in `ValidationTaskForm.svelte` (Step 3) — `screenshot_enabled=true` shows only multimodal providers; `screenshot_enabled=false` shows all active providers
- [x] T060 [US5] Add `ValidationTaskService.create_task()` validation: reject if `screenshot_enabled=true` but provider `is_multimodal=false` — implemented via `_validate_provider(provider_id, require_multimodal=screenshot_enabled)` in `backend/src/services/validation_service.py`
- [x] T061 [US5] Add test: create task with `screenshot_enabled=true` and non-multimodal provider → HTTP 400, in `backend/tests/api/test_validation_tasks_api.py`
- [x] T061a [US5] Implement `DELETE /api/llm/providers/{id}` enforcement: query active ValidationPolicy references, return 409 with `{error, blocking_tasks: [{id, name}]}` (FR-058), in `backend/src/api/routes/llm.py`
- [x] T062 [US5] Add test: delete provider with active tasks → HTTP 409 with blocking task list (FR-058), in `backend/tests/api/test_llm_provider_delete.py`
- [x] T063 [US5] Add test: POST /api/tasks with `plugin_id=llm_dashboard_validation` → HTTP 400 with migration message (FR hard cut), in `backend/tests/api/test_tasks_deprecated_llm.py`

**Verification**: LLM settings page shows only 3 bindings. Create task with multimodal provider → works. Create with non-multimodal + screenshot → rejected.

---

## Phase 8: US6 — Dashboard Hub Cleanup + Validation Indicator

**Goal**: Remove Validate button + LLM status column. Add lightweight validation indicator per dashboard row + detail page history.

- [x] T064 [US6] Remove `handleValidate()` function from `frontend/src/routes/dashboards/+page.svelte`
- [x] T065 [US6] Remove LLM validation status column from dashboard hub grid (column header + `getLlmSummaryLabel()` + `getValidationBadgeClass()` rendering) in `frontend/src/routes/dashboards/+page.svelte`
- [x] T065a [US6] Add `getValidationStatusBatch()` API method in `frontend/src/lib/api.js` — calls `GET /api/dashboards/{env_id}/validation-status?dashboard_ids=...` with graceful 404 fallback
- [x] T065b [US6] Add validation indicator dot (PASS/WARN/FAIL/UNKNOWN) next to dashboard title in hub rows. Click opens popover with last 3 runs + «View all» link, in `frontend/src/routes/dashboards/+page.svelte`
- [x] T066 [US6] Remove «Validate» action from action dropdown menu in `frontend/src/routes/dashboards/+page.svelte`
- [x] T067 [US6] Deprecate old `normalizeValidationStatus()` + `getLlmSummaryLabel()` — replaced by indicator + batch endpoint, in `frontend/src/routes/dashboards/+page.svelte`
- [x] T068 [US6] Remove LLM validation status loading from `frontend/src/routes/dashboards/[id]/+page.svelte` (old `runLlmValidationTask()` + `openLlmReport()`)
- [x] T068a [US6] Add «Validation History» section to `frontend/src/routes/dashboards/[id]/+page.svelte` — last 10 runs for this dashboard, links to canonical run detail pages
- [x] T069 [US6] Add «Create Validation Task» button to dashboard hub toolbar that navigates to `/validation-tasks/new?ids=1,2,3` (pre-fills selected dashboard IDs) in `frontend/src/routes/dashboards/+page.svelte`
- [x] T070 [US6] Update `frontend/src/lib/components/layout/TaskDrawer.svelte` — updated `resolveLlmValidationStatus()` to use ValidationRun aggregate counts; updated `handleOpenLlmReport()` to navigate to canonical `/validation-tasks/{policyId}/runs/{runId}`

**Verification**: Dashboard hub has no Validate button, no LLM column. Colored dot indicator per row with dropdown. Detail page has Validation History section. «Create Validation Task» button pre-fills IDs.

---

## Phase 9: Polish & Cross-Cutting Verification

**Goal**: Migration testing, backward compat, ADR updates, final verification.

### 9.1 Migration & Backward Compat

- [ ] T071 Run data migration on test DB: verify all existing `dashboard_ids` → `sources[]` conversion in `backend/tests/migrations/test_v2_data_migration.py`
- [x] T072 Update assistant tool `_tool_llm_validation.py` — replaced ad-hoc `run_llm_validation` dispatch with task creation via `ValidationTaskService.create_task()` + `trigger_run()`, in `backend/src/api/routes/assistant/_tool_llm_validation.py`

### 9.2 ADR Updates

- [x] T073 Update `docs/adr/ADR-0008-assistant-tool-registry.md` — noted that `_tool_llm_validation.py` now creates tasks instead of ad-hoc validation; added positive consequence for task-based validation
- [x] T074 Update `docs/adr/ADR-0004-plugin-architecture.md` — updated description to note v2 dual-path execution + ValidationTaskService persistent policies

### 9.3 Final Verification

- [ ] T075 Run full end-to-end: create task → URL source (with filters) → Path A run → view report with per-tab screenshots
- [ ] T076 Run full end-to-end: create task → dashboard ID sources → Path B run (execute_chart_data=true) → view report with dataset health + chart data
- [ ] T077 Run full end-to-end: create task → Path B run against dashboard with broken dataset → verify LLM reports UNHEALTHY
- [ ] T078 Run full end-to-end: delete provider used by active task → verify HTTP 409 with blocking task names
- [ ] T079 Run full test suite: `cd backend && source .venv/bin/activate && python -m pytest -v`
- [ ] T080 Run frontend tests: `cd frontend && npm run test`
- [ ] T081 Run backend lint: `cd backend && python -m ruff check .`
- [ ] T082 Run frontend lint: `cd frontend && npm run lint`
- [ ] T083 Run semantic audit: `axiom_semantic_validation audit_belief_protocol` on all new C4/C5 contracts
- [ ] T084 Run semantic audit: `axiom_semantic_validation audit_contracts` on `backend/src/plugins/llm_analysis/` and `backend/src/services/validation_service.py`

---

## Verification Criteria per User Story

| Story | Independent Verification |
|-------|-------------------------|
| **US1** | Create task with 2 dashboards (ID + URL), Path A, cron `0 8 * * *` → task appears in list → scheduled execution succeeds → report shows per-tab screenshots |
| **US2** | Task list shows 3 tasks with different statuses → click task → detail shows per-dashboard breakdown → click dashboard → full report renders |
| **US3** | Path B against broken dataset → report shows dataset UNHEALTHY + affected charts. Path A against dashboard with visual error → report shows issue with tab/chart location |
| **US4** | Paste Superset URL with native_filters → parse returns dashboard title + 3 filters + 2 tabs → saved in ValidationSource → re-parsed on execution |
| **US5** | LLM settings shows 3 bindings (no dashboard_validation). Create task with multimodal provider → works. Create with non-multimodal + screenshot → rejected |
| **US6** | Dashboard hub: no Validate button, no LLM column. «Create Validation Task» toolbar button pre-fills selected IDs |

## Rejected-Path Regression Coverage

| Rejected Path | Test Task | Expected Behavior |
|---------------|-----------|-------------------|
| Old `POST /api/tasks` with `llm_dashboard_validation` | T063 | HTTP 400: «deprecated, use /api/validation-tasks» |
| Provider deletion when used by active tasks | T062 | HTTP 409: returns blocking task names |
| Duplicate manual trigger of same task | T013 (FR-054 check) | Toast «Already running», no queue |
| Non-multimodal provider + screenshot task | T061 | HTTP 400: «provider must be multimodal» |
| URL re-parse fails (dashboard deleted) | T055 | Source marked invalid, task skips, continues with other sources |
| Multi-chunk token limit exceeded | T050 | Quality reduction → Path B fallback, logged via molecular-cot |
| Path B dataset health check fails | T047 | LLM report flags dataset UNHEALTHY + affected charts |

## Belief-Runtime Instrumentation Tasks

| Contract | Tier | Task | Instrumentation |
|----------|------|------|-----------------|
| `LLMClient._estimate_payload_size` + `_reduce_image_quality` | C4 | T020 | `belief_scope("payload_reduction")` + `reason()` per reduction + `reflect()` on outcome |
| `DashboardValidationPlugin._execute_path_a` | C4 | T048 | `belief_scope("execute_path_a")` + `reason()` at navigation/tab/resize + `reflect()` with timings |
| `DashboardValidationPlugin._execute_path_b` | C4 | T043 | `belief_scope("execute_path_b")` + `reason()` at each API call + `reflect()` with token_usage |
| `ValidationTaskService.trigger_run` | C4 | T013 | `belief_scope("trigger_run")` + `reason()` on queue decision + `reflect()` after enqueue |
| `ScreenshotService.capture_dashboard_chunks` | C4 | T017 | `belief_scope("capture_chunks")` + `reason()` per tab switch + `reflect()` with screenshot count |

## Parallel Execution Opportunities

| Group | Tasks | Dependencies |
|-------|-------|--------------|
| **Phase 1** | T001–T007 | None (all parallel) |
| **Phase 2** | T008–T015 (service), T016 (health checker), T017 (screenshot), T018–T020 (LLM client) | After Phase 1 |
| **Phase 3** | T025–T034 (API), T035–T042 (frontend) | After Phase 2 |
| **Phase 4+5+6** | T043–T047 (Path B), T048–T050 (Path A), T051–T055 (URL) | After Phase 2, all three parallel |
| **Phase 7+8** | T056–T063 (provider/prompt), T064–T070 (hub) | After Phase 3, both parallel |
| **Phase 9** | T071–T084 | After all phases |

## Total: 99 tasks across 9 phases — 86% complete

| Phase | Tasks | Status |
|-------|-------|--------|
| 1 — Setup | 8 | ✅ 8/8 |
| 2 — Foundational | 23 | ✅ 23/23 |
| 3 — Task CRUD + Reports | 22 | ✅ 22/22 |
| 4 — Path B | 5 | ✅ 5/5 |
| 5 — Path A | 3 | ✅ 3/3 |
| 6 — URL Parsing | 5 | ✅ 5/5 |
| 7 — Provider/Prompt | 8 | ✅ 8/8 |
| 8 — Hub Cleanup | 10 | ✅ 9/10 (T070 done) |
| 9 — Polish | 14 | ⬜ 14/14 pending (T071, T075-T084 — e2e tests, semantic audit, full test suite)