thanhnvandClaude Opus 4.8
36a4812ef3
Standard production layout: the OKR app (was nested under AINative_OKR_CASAN5/) is now
the repository root. No more wrapper directory.
- Promote AINative_OKR_CASAN5/* -> repo root (backend/ frontend/ packages/ apps/
.specify/ docs/ infra/ nginx/ scripts/ + configs). Merge tool dirs: .gitea (kept the
active deploy ci.yml, added harness-ci.yml + runbooks), .claude (agents/commands +
launch.json), .github moved up.
- Remove redundant: 00_SUBMISSION_PACKAGE, scattered root notes (FPT_CASAN_Full.md,
tu-tuong-casan.md, casan-tu-sinh..., casan_harness_assessment.md, source-review...,
README_CASAN5_REFINED.md), casan-next-plans/ and optimize-docs/ (competition/planning
artifacts — roadmap + design history preserved in git log / commit messages).
- Update all references to the old layout:
- .gitea/workflows/{ci,harness-ci}.yml, .github/workflows/{ci,deploy}.yml:
working-directory .; drop AINative_OKR_CASAN5/ prefix; .specify/{tests,scripts}
-> packages/casan-harness/... (.specify/logs state kept)
- .claude/launch.json, .gitea/*-runbook.md: path prefixes
- CLAUDE.md, README.md: docs/input -> apps/okr/domain/input
- policy-bundle.yaml: 8 policy paths -> packages/casan-harness/...; manifest re-signed
- secrets-scan.sh: fixture excludes -> new package/domain paths.
Full gate from the new root: PASS=64 FAIL=0 SKIP=3.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
140 lines
6.1 KiB
Markdown
140 lines
6.1 KiB
Markdown
# Steps 10–12: Implementation & QA Phase
|
||
|
||
> Boss MUST read this file before executing Steps 10–12.
|
||
> Protocols referenced: `protocols/gate-retry-protocol.md`, `protocols/report-gate-protocol.md`, `protocols/implement-delegation.md`
|
||
|
||
---
|
||
|
||
## STEP 10 — Implementation + Build & Fix (Auto-Retry)
|
||
|
||
| Key | Value |
|
||
|-----|-------|
|
||
| Agent | `speckit.implement` |
|
||
| Model | `gpt-5-3-codex` |
|
||
| Input | `tasks.md`, `plan.md`, `data-model.md`, `contracts/`, `docs/output/ipa-docs/testcase/testcase-<mod-id>-<short-name>.md` |
|
||
| Report | `reports/10-implement-report.md` (NN=10, phase=implement) |
|
||
| Gate | BUILD GATE (Auto-Retry) + REPORT HARD GATE (+ "Test Results" + "Screen Verification" sections required) |
|
||
| Max retries | 5 |
|
||
|
||
**Delegation:** Per `protocols/implement-delegation.md` § STEP 10.
|
||
|
||
**Additional context:**
|
||
```yaml
|
||
feature-id: <feature-id>
|
||
module-id: <mod-id>
|
||
report-nn: 10
|
||
report-phase: implement
|
||
pipeline-context: docs/output/output_logs/<feature-id>/pipeline-context.yaml
|
||
```
|
||
|
||
**Phase 1 — Gen test:**
|
||
- Every source file under `src/` must have a dedicated test file under `test/` or co-located (following standard TypeScript/Jest testing conventions)
|
||
- All checklist items in `specs/<feature-id>/checklists/` must be resolved before proceeding
|
||
- Auto-resolve any checklist ambiguities per `protocols/auto-resolve-protocol.md`
|
||
|
||
**⛔ Test Quality Mandate (Post-Mortem P-08):**
|
||
- Integration tests MUST use real database (SQLite for local, Docker DB for CI) — **in-memory mocks are PROHIBITED**
|
||
- Every endpoint test MUST verify: HTTP status, response shape, actual DB state change (read-back after write)
|
||
- Authorization tests MUST verify: unauthenticated → 401, wrong role → 403, ownership violation → 403
|
||
- Pseudo-tests (tests that always pass, mock everything, or have no assertions) are treated as CRITICAL review failure
|
||
|
||
**Phase 2 — Implement:**
|
||
- Execute all tasks in `specs/<feature-id>/tasks.md` phase by phase
|
||
- All checklist items in `specs/<feature-id>/checklists/` must be resolved before proceeding
|
||
- Auto-resolve any checklist ambiguities per `protocols/auto-resolve-protocol.md`
|
||
|
||
**Phase 3 — Build & Fix:**
|
||
1. Fix all compile/lint errors (`get_errors` → fix → repeat until zero)
|
||
2. Build frontend: `cd frontend && npm install && npm run build`
|
||
3. Start Docker (if `docker-compose.dev.yml` exists): `docker compose -f docker/docker-compose.dev.yml up -d`
|
||
4. Build backend: `cd backend && npm install && npm run build`
|
||
5. Verify startup (if Docker available): `cd backend && npm run start:dev`
|
||
|
||
**Gate logic:**
|
||
- ✅ Build succeeds + app starts → proceed to Step 11
|
||
- ❌ Build/startup fails → **Auto-Retry Loop:**
|
||
1. Capture error log
|
||
2. Write `[ISSUE]` in boss log
|
||
3. Invoke `speckit.implement`: *"Fix build/startup errors: <error log>. Minimal fix."*
|
||
4. Retry build sequence
|
||
5. If retry > 5: `[ESCALATION]`, mark PARTIAL COMPLETE
|
||
|
||
> ⛔ **[REPORT GATE]** per `protocols/report-gate-protocol.md`
|
||
|
||
---
|
||
|
||
## STEP 11 — Code Review (Auto-Retry)
|
||
|
||
| Key | Value |
|
||
|-----|-------|
|
||
| Agent | `okr.reviewcode` |
|
||
| Model | `claude-sonnet-4-6` |
|
||
| Input | Implemented source code, spec, tasks, constitution |
|
||
| Report | `reports/11-review-code-report.md` |
|
||
| Gate | REVIEW GATE (Auto-Retry) + REPORT HARD GATE |
|
||
| Fix agent | `speckit.implement` |
|
||
| Max retries | 5 |
|
||
|
||
**Gate logic:**
|
||
- ✅/⚠️ → proceed to Step 12
|
||
- ❌ REJECTED → invoke `speckit.implement` to fix CRITICAL issues → re-invoke `okr.reviewcode`
|
||
- Escalation after 5 retries → continue to Step 12
|
||
|
||
**Additional DB Data Check:**
|
||
Code review MUST also verify:
|
||
- All screen data is fetched from the database (via Prisma Client / API endpoints), NOT from mock/hardcoded data
|
||
- Prisma seed script (`backend/prisma/seed.ts`) includes necessary seed data for the screens to display real content
|
||
- Frontend components call real API endpoints (not mock adapters or static JSON)
|
||
- If mock data is detected, mark as ❌ CRITICAL and instruct fix agent to replace with DB-backed data
|
||
|
||
> ⛔ **[REPORT GATE]** per `protocols/report-gate-protocol.md`
|
||
|
||
---
|
||
|
||
## STEP 12 — Final QA Audit: Test Execution (Independent QA)
|
||
|
||
| Key | Value |
|
||
|-----|-------|
|
||
| Agent | `okr.testkit` |
|
||
| Model | `claude-sonnet-4-6` |
|
||
| Mode | `run-tests` |
|
||
| Prerequisite | Step 10 PASSED |
|
||
| Report (Phase C) | `reports/12-testkit-report.md` |
|
||
| Report (Phase D) | `docs/output/ipa-docs/testreport/testreport-<MOD-ID>-<short-name>.md` |
|
||
| Gate | TEST GATE (BACK-TO-PLAN on FAIL) |
|
||
|
||
> ⚠ This is the **FINAL quality gate** before launch. No screen shown until ALL tests pass.
|
||
|
||
**Delegation `$ARGUMENTS`:**
|
||
```
|
||
run-tests <feature-id>
|
||
```
|
||
|
||
**Additional delegation context (mandatory):**
|
||
|
||
Pipeline report (Phase C) MUST include:
|
||
1. `## Test Execution Summary` — Category | Total | Passed | Failed | Skipped | Pass Rate
|
||
2. `## Failed Test Details` — every failed test with TC-ID, failure reason, design reference
|
||
3. `## Retry Log` — Retry Count | Target | Fix Applied | Result
|
||
4. `## Screen Verification Results (E2E)` — per-screen accessibility
|
||
5. `## Coverage` — Istanbul/c8 metrics
|
||
6. `## Overall Verdict` — PASS / FAIL
|
||
|
||
IPA detail report (Phase D) generation rules:
|
||
- Take `docs/output/ipa-docs/testcase/testcase-<MOD-ID>-<short-name>.md` as BASE
|
||
- Rename title to `Test Execution Result Report`
|
||
- Keep ALL test case rows intact — fill `Execution Result`, `Verdict`, `Notes` columns only
|
||
- Add `## Test Execution Summary`, `## Coverage Results` at top
|
||
- Append `## Screen Verification Results`, `## SRS/BD/DD Compliance Check`, `## Overall Verdict` at bottom
|
||
|
||
**GATE — FAIL ← BACK TO PLAN (Full Fix Cycle):**
|
||
|
||
Per `protocols/gate-retry-protocol.md` § BACK-TO-PLAN Fix Cycle:
|
||
- ✅ ALL tests PASS + coverage ≥ 80% → proceed to Step 13
|
||
- ❌ Tests FAIL → re-invoke pipeline from STEP 6 (max 3 full cycles)
|
||
- If 3 cycles exhausted → `[ESCALATION]`, proceed to Step 13 with failure report
|
||
|
||
> ⛔ **[REPORT GATE]** — **Both files required:**
|
||
> 1. `reports/12-testkit-report.md` (Phase C)
|
||
> 2. `docs/output/ipa-docs/testreport/testreport-<MOD-ID>-<short-name>.md` (Phase D)
|