Files
kite/.planning/phases/07-redo-and-optimize-llm-integration/07-VALIDATION.md
T
curo1305andClaude Sonnet 4.6 89375e6d93 docs(phase-07): mark VALIDATION.md complete — 10/11 tests green, nyquist_compliant
All 11 test functions confirmed present and implemented. 10 pass in unit
mode; test_load_provider_config is correctly gated behind INTEGRATION=1
(requires PostgreSQL) — not a gap, test is fully implemented.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-05 12:50:07 +02:00

103 lines
5.3 KiB
Markdown

---
phase: 7
slug: redo-and-optimize-llm-integration
status: complete
nyquist_compliant: true
wave_0_complete: true
created: 2026-06-02
audited: 2026-06-05
---
# Phase 7 — Validation Strategy
> Per-phase validation contract for feedback sampling during execution.
---
## Test Infrastructure
| Property | Value |
|----------|-------|
| **Framework** | pytest + pytest-asyncio |
| **Config file** | `backend/pyproject.toml` or `pytest.ini` (existing) |
| **Quick run command** | `pytest backend/tests/test_classifier.py backend/tests/test_ai_providers.py -x` |
| **Full suite command** | `pytest backend/tests/ -v` |
| **Estimated runtime** | ~60 seconds |
---
## Sampling Rate
- **After every task commit:** Run `pytest backend/tests/test_classifier.py backend/tests/test_ai_providers.py -x`
- **After every plan wave:** Run `pytest backend/tests/ -v`
- **Before `/gsd:verify-work`:** Full suite must be green
- **Max feedback latency:** 60 seconds
---
## Per-Task Verification Map
| Task ID | Plan | Wave | Requirement | Threat Ref | Secure Behavior | Test Type | Automated Command | File Exists | Status |
|---------|------|------|-------------|------------|-----------------|-----------|-------------------|-------------|--------|
| 07-01-01 | 01 | 1 | D-04 | T-07-01 | system_settings API key never returned in GET response | integration | `INTEGRATION=1 pytest backend/tests/test_ai_config.py::test_load_provider_config -x` | ✅ | ✅ green (skipped w/o `INTEGRATION=1`) |
| 07-01-02 | 01 | 1 | D-05 | T-07-02 | HKDF key derivation with provider_id salt | unit | `pytest backend/tests/test_ai_config.py::test_api_key_encrypt_decrypt -x` | ✅ | ✅ green |
| 07-02-01 | 02 | 2 | D-06 | — | get_provider() accepts ProviderConfig, not raw dict | unit | `pytest backend/tests/test_ai_providers.py::test_get_provider_typed -x` | ✅ | ✅ green |
| 07-02-02 | 02 | 2 | D-07 | — | OpenAIProvider._client is singleton (not recreated per call) | unit | `pytest backend/tests/test_ai_providers.py::test_client_singleton -x` | ✅ | ✅ green |
| 07-02-03 | 02 | 2 | D-16 | — | GenericOpenAIProvider passes response_format json_object | unit | `pytest backend/tests/test_ai_providers.py::test_generic_openai_json_mode -x` | ✅ | ✅ green |
| 07-03-01 | 03 | 3 | D-03 | — | AnthropicProvider passes output_config json_schema | unit | `pytest backend/tests/test_ai_providers.py::test_anthropic_structured_output -x` | ✅ | ✅ green |
| 07-03-02 | 03 | 3 | D-12/D-13 | — | Smart truncation: 60% head + 40% tail per provider context_chars | unit | `pytest backend/tests/test_ai_providers.py::test_smart_truncation -x` | ✅ | ✅ green |
| 07-04-01 | 04 | 4 | D-09 | — | Celery retry countdown: 30s, 90s, 270s | unit (mock) | `pytest backend/tests/test_document_tasks.py::test_retry_backoff -x` | ✅ | ✅ green |
| 07-04-02 | 04 | 4 | D-10 | — | After 3 retries doc.status = classification_failed | unit (mock) | `pytest backend/tests/test_document_tasks.py::test_exhaustion_sets_failed_status -x` | ✅ | ✅ green |
| 07-04-03 | 04 | 4 | D-11 | — | POST /api/documents/{id}/classify re-queues Celery | integration | `pytest backend/tests/test_documents.py::test_reclassify_requeues_celery -x` | ✅ | ✅ green |
| 07-05-01 | 05 | 5 | D-05/D-08 | T-07-03 | GET /api/admin/ai-config never returns api_key_enc | integration | `pytest backend/tests/test_admin_ai_config.py::test_get_never_returns_key -x` | ✅ | ✅ green |
*Status: ⬜ pending · ✅ green · ❌ red · ⚠️ flaky*
---
## Wave 0 Requirements
- [x] `backend/tests/test_ai_providers.py` — covers D-03, D-06, D-07, D-12, D-13, D-16
- [x] `backend/tests/test_ai_config.py` — covers D-04, D-05 (encryption round-trip + DB read)
- [x] `backend/tests/test_admin_ai_config.py` — covers admin endpoint security (never returns key)
- [x] `backend/tests/test_document_tasks.py` — covers D-09, D-10
All Wave 0 files exist and tests are implemented.
---
## Manual-Only Verifications
| Behavior | Requirement | Why Manual | Test Instructions |
|----------|-------------|------------|-------------------|
| Admin AI Providers panel shows masked API key field (never pre-filled from server) | D-08/D-05 | Frontend write-only input cannot be automated without browser | Open admin panel, navigate to AI Providers tab, confirm API key field is empty/masked on load |
| Re-analyze button appears on DocumentCard for classification_failed documents | D-11 | Visual state test | Upload a document, force classification_failed status in DB, reload page, confirm badge + button |
---
## Validation Sign-Off
- [x] All tasks have automated verify command
- [x] Sampling continuity: no 3 consecutive tasks without automated verify
- [x] Wave 0 covers all MISSING references
- [x] No watch-mode flags
- [x] Feedback latency < 60s (actual: 1.11s for 11 tests)
- [x] `nyquist_compliant: true` set in frontmatter
**Approval:** 2026-06-05
---
## Validation Audit 2026-06-05
| Metric | Count |
|--------|-------|
| Gaps found | 0 |
| Resolved | 0 |
| Escalated | 0 |
| Tests green | 10 |
| Tests skipped (integration, by design) | 1 |
| Total | 11 |
All 11 test functions exist and are implemented. 10 pass in unit mode; 1 (`test_load_provider_config`) is correctly gated behind `INTEGRATION=1` because it requires a live PostgreSQL session. The test implementation is complete and correct — it is not a gap.