@llipe.com/dev-tasks 0.10.0 → 0.11.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (39) hide show
  1. package/.claude/agents/developer.md +11 -0
  2. package/.claude/agents/qa-engineer.md +31 -2
  3. package/.claude/agents/researcher.md +96 -0
  4. package/.claude/commands/planner.md +22 -7
  5. package/.claude/commands/product-engineer.md +37 -10
  6. package/.claude/commands/researcher.md +28 -0
  7. package/.claude/skills/activity-codebase-research/SKILL.md +158 -0
  8. package/.claude/skills/activity-contract-validation/SKILL.md +167 -0
  9. package/.claude/skills/activity-e2e-test-implementation/SKILL.md +156 -0
  10. package/.claude/skills/activity-integration-test-implementation/SKILL.md +156 -0
  11. package/.claude/skills/activity-test-standards/SKILL.md +41 -0
  12. package/.github/agents/developer.agent.md +11 -0
  13. package/.github/agents/planner.agent.md +22 -7
  14. package/.github/agents/product-engineer.agent.md +37 -10
  15. package/.github/agents/qa-engineer.agent.md +30 -3
  16. package/.github/agents/researcher.agent.md +96 -0
  17. package/.github/prompts/researcher.prompt.md +29 -0
  18. package/.github/skills/activity-codebase-research/SKILL.md +158 -0
  19. package/.github/skills/activity-contract-validation/SKILL.md +167 -0
  20. package/.github/skills/activity-e2e-test-implementation/SKILL.md +156 -0
  21. package/.github/skills/activity-integration-test-implementation/SKILL.md +156 -0
  22. package/.github/skills/activity-test-standards/SKILL.md +41 -0
  23. package/.kiro/agents/developer.md +11 -0
  24. package/.kiro/agents/planner.md +22 -7
  25. package/.kiro/agents/product-engineer.md +37 -10
  26. package/.kiro/agents/qa-engineer.md +30 -3
  27. package/.kiro/agents/researcher.md +99 -0
  28. package/.kiro/agents/verifier.md +1 -1
  29. package/.kiro/skills/activity-codebase-research/SKILL.md +158 -0
  30. package/.kiro/skills/activity-contract-validation/SKILL.md +167 -0
  31. package/.kiro/skills/activity-e2e-test-implementation/SKILL.md +156 -0
  32. package/.kiro/skills/activity-integration-test-implementation/SKILL.md +156 -0
  33. package/.kiro/skills/activity-test-standards/SKILL.md +41 -0
  34. package/AGENTS.md +91 -215
  35. package/CHANGELOG.md +33 -0
  36. package/CLAUDE.md +3 -2
  37. package/README.md +1 -0
  38. package/TESTING.md +19 -11
  39. package/package.json +1 -1
@@ -0,0 +1,156 @@
1
+ ---
2
+ name: activity-e2e-test-implementation
3
+ description: "Author Playwright end-to-end tests from verifier scenario tables. Covers auth, state reset, CI config, and scenario-to-spec traceability. Use when writing or backfilling E2E tests."
4
+ ---
5
+
6
+ # Activity: E2E Test Implementation (Playwright)
7
+
8
+ Convert `verifier` Design Mode scenario tables into executable Playwright specs. This skill is the execution counterpart to `activity-e2e-test-design`, which produces the scenario tables.
9
+
10
+ ---
11
+
12
+ > **RFC 2119 Notice:** The key words **MUST**, **MUST NOT**, **REQUIRED**, **SHALL**, **SHALL NOT**, **SHOULD**, **SHOULD NOT**, **RECOMMENDED**, **MAY**, and **OPTIONAL** in this document are to be interpreted as described in [RFC 2119](https://www.rfc-editor.org/rfc/rfc2119).
13
+
14
+ ## Goal
15
+
16
+ Produce Playwright E2E specs that fail when user-facing behavior is wrong. E2E tests assert on observable outcomes — never on internal state, database rows, or implementation details.
17
+
18
+ Consult `/TESTING.md` first. Its E2E layer boundary governs; this skill supplies the method.
19
+
20
+ ## E2E Layer Boundary
21
+
22
+ - **MUST** assert on user-visible behavior (page content, navigation, HTTP responses).
23
+ - **MUST NOT** assert on internal state, database contents, or implementation details.
24
+ - **MUST NOT** mock the application under test. The full stack runs.
25
+ - **MAY** seed test data via API or database before the test begins.
26
+
27
+ ## Part 1 — Playwright Prerequisite Contract
28
+
29
+ Before authoring specs, verify or establish these prerequisites:
30
+
31
+ ### Authentication strategy
32
+
33
+ | Strategy | When to Use | How |
34
+ | ---------------------------------------------- | --------------------------------------------- | ----------------------------------------------------------------------------------------------------------- |
35
+ | **`storageState` via setup project** (default) | Multi-test suites sharing a logged-in session | A `global-setup.ts` or setup project authenticates once, saves `storageState.json`, and all specs reuse it. |
36
+ | **Per-test programmatic login** | Tests that need different users or roles | Each spec calls login API directly in `beforeEach`. Slower but flexible. |
37
+ | **API-token seeding** | API-only E2E, no browser UI | Set auth headers directly via `request.newContext()`. No browser needed. |
38
+
39
+ Default to `storageState` unless the test requires a different user or role per test.
40
+
41
+ ### Seeded test users
42
+
43
+ - Create dedicated test users (not production accounts).
44
+ - Credentials reach CI via environment variables or secrets — never hardcoded in the repository.
45
+ - Use a deterministic naming convention: `e2e-user-admin@test.local`, `e2e-user-member@test.local`.
46
+ - Document how to create/reset test users in the project's test setup README.
47
+
48
+ ### Base URL and environment resolution
49
+
50
+ - Use `baseURL` in `playwright.config.ts`, resolved from `process.env.BASE_URL` or `process.env.PLAYWRIGHT_BASE_URL`.
51
+ - Never hardcode `localhost:3000` — CI and staging use different URLs.
52
+ - Provide a `.env.test.example` showing required variables.
53
+
54
+ ### Database state reset between runs
55
+
56
+ Choose one:
57
+
58
+ - **Migration + seed** (preferred): drop, migrate, seed before the test suite.
59
+ - **Transaction rollback**: wrap each test in a transaction (complex for E2E).
60
+ - **Snapshot restore**: restore a known-good database snapshot before runs.
61
+
62
+ State reset **MUST** run in `globalSetup` or a setup project, not inside individual specs.
63
+
64
+ ### Trace, screenshot, and video retention
65
+
66
+ - **Default:** `on-first-retry` for traces, `only-on-failure` for screenshots, `off` for video.
67
+ - **CI:** retain artifacts as test attachments. Configure `outputDir` and artifact upload in CI workflow.
68
+ - Keep retention bounded — do not retain video for every passing test.
69
+
70
+ ### Browser install in CI
71
+
72
+ - CI **MUST** install browsers explicitly: `npx playwright install --with-deps chromium`.
73
+ - Locally: `npx playwright install` on first run.
74
+ - Pin Playwright version in `package.json` — do not use `latest`.
75
+
76
+ ### Sharding (large suites)
77
+
78
+ - For suites >50 specs: shard across CI workers using `--shard=1/4`, `--shard=2/4`, etc.
79
+ - Configure in CI matrix, not in `playwright.config.ts`.
80
+
81
+ ## Part 2 — Scenario-to-Spec Mapping
82
+
83
+ ### Traceability convention
84
+
85
+ Every Playwright spec **MUST** be traceable to a `verifier` Design Mode scenario.
86
+
87
+ **Annotation format:** Include `@scenario SC-{n}` in the test title or as a comment:
88
+
89
+ ```typescript
90
+ // @scenario SC-1
91
+ test("SC-1: Successful login with valid credentials", async ({ page }) => {
92
+ // ...
93
+ });
94
+ ```
95
+
96
+ Or in the test title directly:
97
+
98
+ ```typescript
99
+ test("[SC-1] User logs in with valid credentials", async ({ page }) => {
100
+ // ...
101
+ });
102
+ ```
103
+
104
+ ### Traceability chain
105
+
106
+ ```
107
+ AC-{n} → SC-{n} (test plan) → .spec.ts file / test block (@scenario SC-{n}) → Pass/Fail
108
+ ```
109
+
110
+ The `verifier` audit resolves scenario IDs to spec files by searching for `@scenario SC-{n}` or `SC-{n}:` patterns. Orphaned scenarios (in the plan but not in specs) are reported as uncovered.
111
+
112
+ ### File naming
113
+
114
+ - One spec file per feature or user journey: `login.spec.ts`, `checkout.spec.ts`.
115
+ - Group related scenarios in one file. Do not create one file per scenario unless they are independent flows.
116
+
117
+ ## Part 3 — Converting Scenario Tables to Specs
118
+
119
+ Given a scenario table from `activity-e2e-test-design`:
120
+
121
+ 1. **Read the scenario.** Extract: preconditions, steps, expected result, pass criteria.
122
+ 2. **Write the spec.** Map steps to Playwright actions. Map pass criteria to assertions.
123
+ 3. **Annotate.** Add `@scenario SC-{n}` to the test.
124
+ 4. **Handle preconditions.** Seed required state in `beforeAll`/`beforeEach` or a fixture.
125
+ 5. **Assert observable outcomes.** Use `expect(page)` or `expect(response)` — never internal state.
126
+
127
+ ### Retry and flakiness
128
+
129
+ - Use Playwright's built-in retry (`retries: 2` in config) for CI.
130
+ - Prefer explicit `await expect(locator).toBeVisible()` over arbitrary `waitForTimeout`.
131
+ - If a test is flaky, fix the root cause (race condition, state leak) rather than increasing retries.
132
+ - A flaky test that occasionally passes is worse than no test.
133
+
134
+ ### Test isolation
135
+
136
+ - Each spec **MUST** be independent — runnable in any order, in parallel.
137
+ - Never rely on state from a previous test. Use fixtures or setup projects.
138
+ - Use `test.describe.configure({ mode: 'serial' })` only when tests represent a true sequential flow.
139
+
140
+ ## Output
141
+
142
+ - Specs written or updated, by path
143
+ - Scenario-to-spec mapping table: `SC-{n}` → file path and test name
144
+ - Uncovered scenarios (in the plan but not yet implemented)
145
+ - Prerequisites missing (base URL, auth setup, browser install, etc.)
146
+ - Stated limitations (e.g., "no staging environment — E2E limited to localhost")
147
+
148
+ ## Final Instructions
149
+
150
+ 1. You **MUST** consult `/TESTING.md` and respect its E2E layer boundary.
151
+ 2. You **MUST** annotate every spec with its scenario ID (`@scenario SC-{n}`).
152
+ 3. You **MUST NOT** assert on internal state or implementation details.
153
+ 4. You **MUST** verify Playwright prerequisites before authoring specs.
154
+ 5. You **MUST** report uncovered scenarios from the test plan.
155
+ 6. You **MUST** address flakiness causes, not mask them with retries.
156
+ 7. You **MUST NOT** install dependencies — detect and recommend only.
@@ -0,0 +1,156 @@
1
+ ---
2
+ name: activity-integration-test-implementation
3
+ description: "Author integration tests (Layer 2.5) against real databases — local via testcontainers/docker-compose/Supabase CLI, remote via testing environments. Covers migrations, RLS, pgTAP, fixtures, and fallback paths. Use when writing or backfilling integration tests."
4
+ ---
5
+
6
+ # Activity: Integration Test Implementation (Layer 2.5)
7
+
8
+ Author integration tests that exercise code against a real database. Layer 2.5 exists because mocking the data layer makes SQL errors, type mismatches, NULL handling, malformed joins, and RLS policies structurally invisible.
9
+
10
+ ---
11
+
12
+ > **RFC 2119 Notice:** The key words **MUST**, **MUST NOT**, **REQUIRED**, **SHALL**, **SHALL NOT**, **SHOULD**, **SHOULD NOT**, **RECOMMENDED**, **MAY**, and **OPTIONAL** in this document are to be interpreted as described in [RFC 2119](https://www.rfc-editor.org/rfc/rfc2119).
13
+
14
+ ## Goal
15
+
16
+ Produce integration tests that fail when the data layer is wrong. If the database is mocked, the test belongs at Layer 2, not here.
17
+
18
+ Consult `/TESTING.md` first. Its Layer 2.5 boundary governs; this skill supplies the method.
19
+
20
+ ## Layer 2.5 Boundary
21
+
22
+ - **MUST** use a real database (Postgres, SQLite, etc.) — not a mock or in-memory fake.
23
+ - **MUST NOT** mock the data layer. If you mock `sql`, `prisma`, `drizzle`, or the ORM client, the test is Layer 2.
24
+ - **MUST NOT** assert on SQL text or internal query shape. Assert on persisted state or returned data.
25
+ - **MAY** mock third-party external services (payment gateways, email providers) at the HTTP boundary.
26
+
27
+ ## Part 1 — Local Integration Environment Detection
28
+
29
+ Detect the easiest applicable local option. Prefer in this order:
30
+
31
+ ### 1. Testcontainers (preferred for isolation)
32
+
33
+ - Look for `@testcontainers/postgresql` or equivalent in `package.json`/`pom.xml`/`Cargo.toml`.
34
+ - Requires Docker. Check: `docker info` succeeds.
35
+ - Each test suite gets an ephemeral container — full isolation, no cleanup conflicts.
36
+
37
+ ### 2. Docker Compose
38
+
39
+ - Look for `docker-compose.yml` or `compose.yml` with a database service.
40
+ - Requires Docker. Shared instance across tests — needs explicit state reset.
41
+
42
+ ### 3. Supabase Local CLI
43
+
44
+ - Look for `supabase/config.toml` or `.supabase/` directory.
45
+ - Check: `supabase status` succeeds.
46
+ - Provides real Postgres with auth, storage, and edge functions locally.
47
+
48
+ ### 4. Fallback — No Local Environment
49
+
50
+ - If Docker is unavailable and Supabase CLI is not installed, report the limitation.
51
+ - Emit: `SKIPPED(no local database environment — Docker unavailable, Supabase CLI not installed)`.
52
+ - Recommend environment setup as a follow-up. Do not silently omit.
53
+
54
+ ## Part 2 — Fixtures, Seeding, and Lifecycle
55
+
56
+ ### Test isolation
57
+
58
+ - Each test **SHOULD** run in a transaction that rolls back on completion (preferred).
59
+ - Alternative: truncate affected tables in `beforeEach`/`afterEach`.
60
+ - Alternative for testcontainers: fresh container per suite (slower but fully isolated).
61
+
62
+ ### Seeding
63
+
64
+ - Shared seed data lives in one location per package (e.g., `test/fixtures/seed.sql` or `test/helpers/seed.ts`).
65
+ - Seeds **MUST** be idempotent — running twice produces the same state.
66
+ - Seeds **MUST NOT** depend on auto-increment IDs. Use deterministic UUIDs or named references.
67
+
68
+ ### Deterministic teardown
69
+
70
+ - Every integration test file **MUST** clean up after itself or use rollback isolation.
71
+ - Tests **MUST NOT** depend on execution order.
72
+ - Tests **MUST NOT** leave residual data that affects other test files.
73
+
74
+ ## Part 3 — Migration Clean-Apply Tests
75
+
76
+ - **MUST** test that all migrations apply cleanly from an empty database.
77
+ - **MUST** verify apply order (no duplicate prefixes, no gaps).
78
+ - **MUST** verify idempotency: running migrations twice does not error.
79
+ - For large stacks (50+ migrations): run full clean-apply on CI/scheduled; run latest N on PR.
80
+ - Report duplicate migration prefixes as a finding.
81
+
82
+ ## Part 4 — Row-Level Security (RLS) Policy Tests
83
+
84
+ RLS tests **MUST** exercise the real database policy, not application-level tenant checks in JavaScript.
85
+
86
+ ### Multi-session setup
87
+
88
+ - Create at least two database roles or authenticated sessions (Tenant A, Tenant B).
89
+ - Use `SET ROLE` or separate connections per tenant.
90
+ - For Supabase: use `supabase.auth.admin.createUser()` for test users, then authenticate with their JWTs.
91
+
92
+ ### Required assertions
93
+
94
+ | Case | Assertion |
95
+ | ---------------------------- | ----------------------------------- |
96
+ | Tenant A reads own data | Returns expected rows |
97
+ | Tenant A reads Tenant B data | Returns empty set or error |
98
+ | Tenant A writes to Tenant B | Insert/update fails or is invisible |
99
+ | Unauthenticated access | Denied by policy |
100
+ | Service role bypasses RLS | Returns all rows (when expected) |
101
+
102
+ ### Record limitations
103
+
104
+ If isolation is asserted against application-level checks rather than the real RLS policy, you **MUST** record: "Production RLS policy unverified — tested against application-layer tenant filtering only."
105
+
106
+ ## Part 5 — pgTAP / Schema Contract Tests
107
+
108
+ Use pgTAP (or equivalent: `pg_prove`, raw SQL assertions) for:
109
+
110
+ - Table and column existence.
111
+ - Constraint verification (NOT NULL, UNIQUE, CHECK, FK).
112
+ - Function and trigger existence and signatures.
113
+ - Permission grants per role.
114
+ - Index existence for query-critical paths.
115
+
116
+ When pgTAP is unavailable, use raw `SELECT` assertions against `information_schema` or `pg_catalog`.
117
+
118
+ ## Part 6 — Remote Integration Testing
119
+
120
+ ### Default: read-only
121
+
122
+ - Inspect schema, permissions, RLS policies, and data shape without mutation.
123
+ - Use `EXPLAIN` for query plan verification without executing writes.
124
+ - No approval required for read-only operations.
125
+
126
+ ### Testing environment writes
127
+
128
+ - **REQUIRE** explicit user approval before any write or migration apply.
129
+ - Connect only to a dedicated testing environment — never to production for writes.
130
+ - After writes: verify applied state, then clean up test data.
131
+ - Record: environment name, operation performed, approval evidence.
132
+
133
+ ### No testing environment available
134
+
135
+ - Report: "Remote integration limited to read-only inspection. No testing environment configured."
136
+ - Recommend environment setup. Do not fabricate a pass.
137
+
138
+ ## Output
139
+
140
+ - Tests written or updated, by path and layer
141
+ - Local environment detection result (which option selected, or fallback triggered)
142
+ - Migration clean-apply result
143
+ - RLS policy test coverage per table with RLS enabled
144
+ - Schema contract coverage (tables, constraints, functions)
145
+ - Remote integration status (read-only / testing-env / unavailable)
146
+ - Stated limitations where real-policy testing was not possible
147
+
148
+ ## Final Instructions
149
+
150
+ 1. You **MUST** consult `/TESTING.md` and respect its Layer 2.5 boundary.
151
+ 2. You **MUST NOT** mock the data layer. If the database is mocked, the test is Layer 2.
152
+ 3. You **MUST** detect the local environment and recommend the easiest applicable option.
153
+ 4. You **MUST** report a limitation when no local or remote environment is available.
154
+ 5. You **MUST** test RLS against the real policy layer, not application-level checks.
155
+ 6. You **MUST** require explicit approval before any remote write operation.
156
+ 7. You **MUST NOT** install dependencies — detect and recommend only.
@@ -92,6 +92,47 @@ A monorepo defines `test:node` as `app && scraper && db` while the `api` package
92
92
 
93
93
  Correct output: **defect** — `api` is unreachable from the aggregate; the CI gate and the deploy gate both let untested backend code through. Reporting "all script names conform" here is a false pass.
94
94
 
95
+ ## Part 4 — Integration, E2E, and Contract Infrastructure Detection
96
+
97
+ Detect the presence and configuration state of higher-layer test infrastructure. Report findings as **informational** — missing infrastructure is not a defect, but it informs the gap analysis.
98
+
99
+ ### Integration testing infrastructure
100
+
101
+ | Check | What to look for |
102
+ | ----------------------- | ------------------------------------------------------------- |
103
+ | **Testcontainers** | `@testcontainers/postgresql` or similar in dependencies |
104
+ | **Docker Compose** | `docker-compose.yml` or `compose.yml` with a database service |
105
+ | **Supabase local CLI** | `supabase/config.toml` or `.supabase/` directory |
106
+ | **Docker availability** | `docker info` succeeds (report if unavailable) |
107
+
108
+ ### E2E testing infrastructure
109
+
110
+ | Check | What to look for |
111
+ | ------------------------- | -------------------------------------------------------------------------------- |
112
+ | **Playwright config** | `playwright.config.ts` or `playwright.config.js` present |
113
+ | **Base URL configured** | Config references `process.env.BASE_URL` or equivalent (not hardcoded localhost) |
114
+ | **Auth setup project** | A `global-setup` or setup project defined in Playwright config |
115
+ | **Browser install in CI** | CI workflow includes `playwright install` step |
116
+ | **`test:e2e` script** | Present in `package.json` and reachable from aggregate |
117
+
118
+ ### Contract validation infrastructure
119
+
120
+ | Check | What to look for |
121
+ | -------------------------- | ------------------------------------------------------ |
122
+ | **OpenAPI spec** | `openapi.yaml`, `openapi.json`, `swagger.*` in repo |
123
+ | **AsyncAPI spec** | `asyncapi.yaml`, `asyncapi.json` in repo |
124
+ | **`dt` CLI** | `which dt` succeeds |
125
+ | **`test:contract` script** | Present in `package.json` and reachable from aggregate |
126
+
127
+ ### Reporting
128
+
129
+ Report each finding as:
130
+
131
+ - `[INFO] <infrastructure> detected: <path or status>`
132
+ - `[INFO] <infrastructure> not found — Layer {X} tests require this`
133
+
134
+ These are informational findings for the gap analysis. They do **NOT** block or fail the standards check.
135
+
95
136
  ## Failure Modes
96
137
 
97
138
  | Condition | Required behavior |
@@ -138,12 +138,23 @@ Follow `.kiro/steering/implement.md`:
138
138
  | ------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
139
139
  | `product-engineer` | Produces the task lists and refined issues that `developer` executes |
140
140
  | `planner` | Orchestrates multi-story runs — delegates each story to `developer` in Execute Mode with an integration branch override |
141
+ | `researcher` | May be invoked by `developer` for troubleshooting/diagnosis when a bug or regression is unclear; conditional, never mandatory |
141
142
  | `verifier` | Invoked by `developer` in `audit` mode, post-implementation and pre-PR-ready, mandatory and non-skippable — reports fidelity/drift; findings route to `product-engineer`'s `activity-drift-reconciliation` for remediation |
142
143
  | `qa-engineer` | Invoked by `developer` at the completion gate, before the `verifier` audit — owns the testing standard, missing test harnesses, and coverage/gap reporting; `developer` still authors feature tests under rule 19 |
143
144
  | `technical-writer` | Invoked by `developer` before PR is marked ready — updates `/docs` |
144
145
  | `housekeeping` | Can be invoked during implementation for lint/type/test-wiring fixes |
145
146
  | `github-ops` | Defines conventions for all GitHub artifacts — `developer` follows these rules |
146
147
 
148
+ ### Codebase Research for Troubleshooting (Conditional)
149
+
150
+ When diagnosing a bug, regression, or unclear failure during implementation, you **SHOULD** invoke `researcher` if:
151
+
152
+ - The failure spans multiple modules and the root cause is not immediately apparent.
153
+ - The area is unfamiliar or lacks documentation.
154
+ - Multiple hypotheses need codebase evidence to disambiguate.
155
+
156
+ **Skip when:** the failure is localized to a single file or function, or the root cause is already identified. This is a recommended diagnostic tool, not a mandatory gate.
157
+
147
158
  ---
148
159
 
149
160
  ## Autonomous Behavior Contract
@@ -84,6 +84,20 @@ If any required input is missing, ask one focused question with a default option
84
84
 
85
85
  ---
86
86
 
87
+ ## Codebase Research for Pre-Orchestration (Conditional)
88
+
89
+ Before parsing stories and building the dependency graph, you **SHOULD** invoke `researcher` if:
90
+
91
+ - The stories span multiple modules or packages whose dependencies are not yet established.
92
+ - The orchestration involves unfamiliar areas of the codebase.
93
+ - Story ordering requires understanding cross-module data flow or contract boundaries.
94
+
95
+ **Skip when:** story dependencies are already explicit in the task file, the codebase is small and well-understood, or a non-stale research artifact already covers the scope.
96
+
97
+ When triggered, delegate to `researcher` with the orchestration question (e.g., "What are the dependency relationships between modules X, Y, and Z?"). Consume the resulting `/workstream/research-*.md` artifact to inform dependency ordering in Phase 1.
98
+
99
+ ---
100
+
87
101
  ## Phase 0 - Discover Task Source
88
102
 
89
103
  ### Option A - File in /workstream
@@ -456,15 +470,16 @@ Planner **MUST NOT** allow multiple open story PRs to merge concurrently.
456
470
  After all stories are merged into integration:
457
471
 
458
472
  1. Run full integration test suite on integration branch.
459
- 2. Invoke `verifier` in `audit` mode for a **PRD-level rollup audit** against the full integrated scope (all merged stories on the integration branch, cross-checked against the source PRD/spec/milestone). This is mandatory and non-skippable — it runs whether or not any story-level drift was previously reported. Post the resulting human-readable summary to the plan/milestone issue via `github-ops` comment conventions. Rollup drift findings **MUST NOT** block the consolidated PR handoff; Unintended/Intended drift routes to `product-engineer`'s `activity-drift-reconciliation` flow.
460
- 3. Invoke `technical-writer` for a planner-level drift/stale-doc validation pass against integrated changes; unresolved drift **MUST** block handoff.
461
- 4. Open one consolidated PR from integration branch to `main`.
462
- 5. **Do NOT merge.** Notify the user that the consolidated PR is ready for their review.
463
- 6. Wait for the user to approve and merge the PR into `main`.
464
- 7. Before final handoff, **MUST** ensure the local working branch is the integration branch used for this run:
473
+ 2. Invoke `qa-engineer` at **PRD scope** (all packages affected by the merged stories, all layers) for a coverage and gap rollup. Report a PRD-level `coverage_gate` that aggregates per-story gates. Scope to packages affected by the merged stories, not the entire workspace.
474
+ 3. Invoke `verifier` in `audit` mode for a **PRD-level rollup audit** against the full integrated scope (all merged stories on the integration branch, cross-checked against the source PRD/spec/milestone). This is mandatory and non-skippable — it runs whether or not any story-level drift was previously reported. Post the resulting human-readable summary to the plan/milestone issue via `github-ops` comment conventions. Rollup drift findings **MUST NOT** block the consolidated PR handoff; Unintended/Intended drift routes to `product-engineer`'s `activity-drift-reconciliation` flow.
475
+ 4. Invoke `technical-writer` for a planner-level drift/stale-doc validation pass against integrated changes; unresolved drift **MUST** block handoff.
476
+ 5. Open one consolidated PR from integration branch to `main`.
477
+ 6. **Do NOT merge.** Notify the user that the consolidated PR is ready for their review.
478
+ 7. Wait for the user to approve and merge the PR into `main`.
479
+ 8. Before final handoff, **MUST** ensure the local working branch is the integration branch used for this run:
465
480
  - Preferred: run `git checkout integration/<plan-id>-<short-description>`.
466
481
  - Alternative (if checkout is not possible in the current runtime): explicitly verify and report current branch, and provide the exact checkout command the user can run.
467
- 8. Final user response **MUST** include a `PR Directives (User Action Required)` section with:
482
+ 9. Final user response **MUST** include a `PR Directives (User Action Required)` section with:
468
483
  - consolidated PR URL
469
484
  - current CI/check status
470
485
  - exact required user actions: review, approve, and merge
@@ -69,11 +69,13 @@ Chains: `refine` → `plan`. Produces a lightweight refinement doc under `/works
69
69
 
70
70
  Detect mode from user input:
71
71
 
72
- | Input | Mode | Activity Chain |
73
- | --------------------------------- | ---------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------- |
74
- | "init" or foundation request | **Init Mode** | `activity-init` |
75
- | Feature description / PRD request | **Feature Mode** | `activity-refine` → `activity-generate-spec` → `activity-generate-stories` → `activity-publish-github` → `plan` → `verifier` (Design Mode) recommendation |
76
- | GitHub Issue number + repo | **Issue Mode** | `activity-refine` → `plan` → `verifier` (Design Mode) recommendation |
72
+ | Input | Mode | Activity Chain |
73
+ | --------------------------------- | ---------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
74
+ | "init" or foundation request | **Init Mode** | `activity-init` |
75
+ | Feature description / PRD request | **Feature Mode** | `activity-refine` → [`researcher`] → `activity-generate-spec` → `activity-generate-stories` → `activity-publish-github` → `plan` → `verifier` (Design Mode) recommendation |
76
+ | GitHub Issue number + repo | **Issue Mode** | [`researcher`] → `activity-refine` → `plan` → `verifier` (Design Mode) recommendation |
77
+
78
+ > **Note:** `[researcher]` steps are conditional — recommended when trigger heuristics are met, skipped for trivial or single-file changes. See "Codebase Research (Conditional)" below.
77
79
 
78
80
  If the user explicitly asks to start from a later activity (e.g., "generate stories from this spec"), you **MAY** skip earlier steps when the required input artifacts already exist and are approved.
79
81
 
@@ -165,6 +167,7 @@ This agent invokes the following **skills** for each activity. You **MUST** load
165
167
  | -------------------------------- | ------------------------------------------ |
166
168
  | Initialize foundation | `activity-init` |
167
169
  | Refine scope / create PRD | `activity-refine` |
170
+ | Codebase research (conditional) | `activity-codebase-research` |
168
171
  | Generate technical specification | `activity-generate-spec` |
169
172
  | Generate user stories | `activity-generate-stories` |
170
173
  | Publish stories to GitHub | `activity-publish-github` |
@@ -219,7 +222,19 @@ Follow the `activity-refine` skill (PRD mode):
219
222
  4. Produce PRD: `/docs/requirements/prd-[feature-name].md`
220
223
  5. Present for user review and iterate.
221
224
 
222
- #### Phase 2 — Generate Specification
225
+ #### Phase 2 — Codebase Research (Conditional)
226
+
227
+ After refining and before generating the specification, evaluate whether `researcher` SHOULD be invoked. Trigger heuristics:
228
+
229
+ - A spec is about to be written for an area with existing implementation.
230
+ - The change plausibly spans more than one module, package, or repository.
231
+ - The target area is unfamiliar or undocumented in `/workstream`.
232
+
233
+ **Skip when:** the feature is entirely greenfield with no existing code to map, or a non-stale research artifact already covers the scope.
234
+
235
+ When triggered, delegate to `researcher` with the PRD scope as the research question. Consume the resulting `/workstream/research-*.md` artifact as input to Phase 3 (Generate Specification).
236
+
237
+ #### Phase 3 — Generate Specification
223
238
 
224
239
  Follow the `activity-generate-spec` skill:
225
240
 
@@ -228,7 +243,7 @@ Follow the `activity-generate-spec` skill:
228
243
  3. Produce specification: `/workstream/specification-[prd-name].md`
229
244
  4. Present for user review and iterate.
230
245
 
231
- #### Phase 3 — Generate Stories
246
+ #### Phase 4 — Generate Stories
232
247
 
233
248
  Follow the `activity-generate-stories` skill:
234
249
 
@@ -237,7 +252,7 @@ Follow the `activity-generate-stories` skill:
237
252
  3. Produce stories: `/workstream/user-stories-[prd-name].md`
238
253
  4. Present for user review and iterate.
239
254
 
240
- #### Phase 4 — Publish to GitHub
255
+ #### Phase 5 — Publish to GitHub
241
256
 
242
257
  Follow the `activity-publish-github` skill:
243
258
 
@@ -245,7 +260,7 @@ Follow the `activity-publish-github` skill:
245
260
  2. Publish each story as a GitHub Issue (delegate to `github-ops`).
246
261
  3. Produce publication report: `/workstream/github-publication-[prd-name].md`
247
262
 
248
- #### Phase 5 — Plan
263
+ #### Phase 6 — Plan
249
264
 
250
265
  Follow the `plan` steering document:
251
266
 
@@ -253,7 +268,7 @@ Follow the `plan` steering document:
253
268
  2. Generate task list: `/workstream/tasks-[prd-name]-plan.md`
254
269
  3. Update GitHub Issues with checklists.
255
270
 
256
- #### Phase 6 — Verifier Design Recommendation (Test-First)
271
+ #### Phase 7 — Verifier Design Recommendation (Test-First)
257
272
 
258
273
  After the task list is finalized:
259
274
 
@@ -265,6 +280,18 @@ This enforces the repository's **test-first design** default: tests and acceptan
265
280
 
266
281
  ### Issue Mode
267
282
 
283
+ #### Codebase Research (Conditional)
284
+
285
+ Before refining, evaluate whether `researcher` SHOULD be invoked. Trigger heuristics:
286
+
287
+ - The target area is unfamiliar or undocumented in `/workstream`.
288
+ - The change plausibly spans more than one module, package, or repository.
289
+ - The task is diagnostic (bug, regression, "why does X happen").
290
+
291
+ **Skip when:** the issue is a trivial single-file change, a typo/copy fix, or a non-stale research artifact already covers the same scope.
292
+
293
+ When triggered, delegate to `researcher` with the issue title/description as the research question. Consume the resulting `/workstream/research-*.md` artifact as input to Phase A.
294
+
268
295
  #### Phase A — Refine Issue
269
296
 
270
297
  Follow the `activity-refine` skill (Issue Refinement mode):
@@ -40,7 +40,7 @@ Invoke `activity-test-standards`. It establishes or refreshes `/TESTING.md` for
40
40
  - Verify script reachability: every package containing tests **MUST** be reachable from the aggregate test command, and the CI and deploy gates **MUST** invoke that aggregate. A correct script name that omits a package is a defect.
41
41
  - Preserve consumer-authored content. Additions are additive.
42
42
 
43
- ### 2. Author or fill missing tests
43
+ ### 2. Author or fill missing tests (Layers 1-2)
44
44
 
45
45
  Invoke `activity-test-implementation` for the requested scope.
46
46
 
@@ -49,7 +49,34 @@ Invoke `activity-test-implementation` for the requested scope.
49
49
  - Security-negative tests are **mandatory** for every authentication and authorization path: invalid signature, expired credential, wrong issuer or audience, tampered claims.
50
50
  - A passing suite over a permissive implementation is a finding, not a pass.
51
51
 
52
- ### 3. Coverage and gap report
52
+ ### 2.5. Integration tests (Layer 2.5) — conditional
53
+
54
+ Invoke `activity-integration-test-implementation` for the requested scope.
55
+
56
+ - **Condition:** Run only when Layer 2.5 is configured in `/TESTING.md` (not `<!-- unfilled -->`). If Layer 2.5 is not configured, emit `SKIPPED(Layer 2.5 not configured in TESTING.md)` and proceed to the next step.
57
+ - Detect the local environment (testcontainers, docker-compose, Supabase local CLI) and recommend the easiest option.
58
+ - Write integration tests: migration clean-apply, RLS policy assertions, schema contracts.
59
+ - Report limitations when no local or remote environment is available.
60
+
61
+ ### 3. E2E tests — conditional
62
+
63
+ Invoke `activity-e2e-test-implementation` for the requested scope.
64
+
65
+ - **Condition:** Run only when the E2E layer is configured in `/TESTING.md` (not `<!-- unfilled -->`). If E2E is not configured, emit `SKIPPED(E2E layer not configured in TESTING.md)` and proceed to the next step.
66
+ - Convert verifier scenario tables into Playwright specs with `@scenario SC-{n}` traceability.
67
+ - Verify Playwright prerequisites (auth, base URL, state reset, browser install).
68
+ - Report uncovered scenarios from the test plan.
69
+
70
+ ### 4. Contract validation — conditional
71
+
72
+ Invoke `activity-contract-validation` for the requested scope.
73
+
74
+ - **Condition:** Run only when the Contract Validation layer is configured in `/TESTING.md` (not `<!-- unfilled -->`) or when OpenAPI/AsyncAPI specs are detected in the repository. If neither condition is met, emit `SKIPPED(no contract validation layer configured and no API specs found)` and proceed to the next step.
75
+ - Detect `dt` availability. If unavailable, emit `SKIPPED(dt not installed)` with manual instructions.
76
+ - Run `dt verify contract-diff`, `impact`, and `drift`.
77
+ - Report breaking changes as critical findings. Report drift as non-blocking.
78
+
79
+ ### 5. Coverage and gap report
53
80
 
54
81
  Invoke `activity-coverage-gap-analysis`.
55
82
 
@@ -74,7 +101,7 @@ You **MUST NOT** edit:
74
101
 
75
102
  ## Non-Negotiable Rules
76
103
 
77
- 1. You **MUST** run all three steps in order, every invocation.
104
+ 1. You **MUST** run all steps in order, every invocation. Steps 2.5, 3, and 4 are conditional — skip with a reason when the layer is not configured.
78
105
  2. You **MUST NOT** report a pass for anything you could not measure.
79
106
  3. You **MUST** report an unfilled `/TESTING.md` placeholder as unfilled.
80
107
  4. You **MUST** treat a green suite over an insecure or permissive implementation as a finding.