@anhth2/spec-driven-dev-plugin 0.6.0 → 0.8.0

package/commands/refine-prd.tmpl

@@ -58,7 +58,9 @@ summary:
 /refine-prd Complete — {PRD name}
 Findings: {total} | 🔴 Critical: {N} | 🟡 Major: {N} | 🟢 Minor: {N}
 Review: {paths.refinement_dir}/{prd-slug}-findings.yaml
-Next: Open in Review Board (right-click file) → Update PRD → /generate-bdd
+Next: Open in Review Board (right-click file) → Update PRD
+      → /review-context {prd-file}   ← verify PRD quality before generating BDD
+      → /generate-bdd {prd-file}
 ```
 
 ---
@@ -77,9 +79,16 @@ Next: Open in Review Board (right-click file) → Update PRD → /generate-bdd
 
 For each accepted finding, in order of severity (critical → major → minor):
 - Navigate to the PRD section indicated by `finding.section`.
-- Apply `finding.suggestion` (or the note from `modified` status if applicable).
+- Apply `finding.suggestion`. For `status: "modified"` findings, the human has already edited `finding.suggestion` in the Review Board — that edited value IS the fix to apply.
 - Do not alter any sections not referenced by an accepted finding.
 
+### Phase 2.5 — Update findings file
+
+For each finding that was applied (status was `accepted` or `modified`):
+- Set `status: "applied"` in `{paths.refinement_dir}/{prd-slug}-findings.yaml`.
+
+Update `summary.status: "applied"` in the findings file.
+
 ### Phase 3 — Bump version & write changelog entry
 
 1. Read current `| **Version** |` value from PRD metadata table.
@@ -107,5 +116,6 @@ Changes  :
   - {change 2}
 
 ⚠️  BDD may be outdated. Run:
-    /generate-bdd {prd-file}
+    /review-context {prd-file}   ← verify PRD quality first
+    → /generate-bdd {prd-file}
 ```

package/commands/review-code.md

@@ -33,7 +33,7 @@ Display and wait for response:
 ```
 ⚙️  MODEL CHECK
 ──────────────────────────────────────────────────────────────────
-  Recommended  : claude-opus-4-5 (or claude-opus-4)
+  Recommended  : claude-opus-4 (or latest Opus model)
   Why needed   : Spec analysis, architecture review, code generation
                  require deep reasoning. Smaller models miss edge cases.
 
@@ -133,6 +133,7 @@ Read `.agent/project-context.yaml`. Extract and store:
 - `paths.core_entities` → path to core-entities.md
 - `paths.tech_docs_dir` → technical documentation root
 - `paths.trace_dir` → trace state directory
+- `paths.design_spec_dir` → Design Spec documents root (FE/App only)
 
 If `paths` section is absent, use these defaults:
 - `specs_dir` = `specs/bdd`
@@ -142,13 +143,46 @@ If `paths` section is absent, use these defaults:
 - `domain_knowledge_dir` = `specs/domain-knowledge`
 - `business_dictionary` = `specs/domain-knowledge/business-dictionary.md`
 - `core_entities` = `specs/domain-knowledge/core-entities.md`
-- `tech_docs_dir` = `tech-docs`
+- `tech_docs_dir` = `specs/tech-docs`
 - `trace_dir` = `.trace`
+- `design_spec_dir` = `specs/design-spec`
 
 If `tech_stack.module` is set, also load `.agent/modules/{module}/stack-profile.yaml` if it exists.
 
 ---
 
+## Step 1.5 — [SERVICE ROUTING] Resolve service paths (umbrella mode)
+
+*Skip this step entirely if `setup.mode` is not `"umbrella"` and `services` section is absent from project-context.yaml.*
+
+If `services` section is present:
+
+**1. Detect active domain** (in priority order):
+- Read `@trace.domain` from target file frontmatter (if Gate loaded a target file)
+- Extract from target file path: segment immediately after `prd_dir` base path  
+  *(e.g., `specs/prd/user/FEAT-01.md` → domain = `user`)*
+- If `$ARGUMENTS` contains a path, extract the segment after `prd_dir`
+
+**2. Route to service** — if active domain matches a key in `services`:
+- Override `paths.specs_dir` → `services.{domain}.specs_dir`
+- Override `paths.tech_docs_dir` → `services.{domain}.tech_docs_dir`
+- Store `active_service` = `services.{domain}.path`
+- Store `active_service_module` = `services.{domain}.module`
+- If service has its own `module` → use it as `active_module` (overrides `tech_stack.module`)
+
+**3. Fallback** — if domain not detected or no matching service key:
+- Keep default paths from Step 1
+- Set `active_service = unresolved`
+
+**4. Spec source auto-override** — if `setup.spec_source` is set AND the corresponding path was not already explicitly set in `paths:`:
+- Override `paths.prd_dir` → `{spec_source}/specs/prd`
+- Override `paths.design_spec_dir` → `{spec_source}/specs/design-spec`
+- Override `paths.domain_knowledge_dir` → `{spec_source}/specs/domain-knowledge`
+- Override `paths.business_dictionary` → `{spec_source}/specs/domain-knowledge/business-dictionary.md`
+- Override `paths.core_entities` → `{spec_source}/specs/domain-knowledge/core-entities.md`
+
+---
+
 ## Step 2 — [PROJECT-CONFIG] Load module stack profile (conditional)
 
 If `tech_stack.module` is set, read `.agent/modules/{module}/stack-profile.yaml`.
@@ -219,6 +253,26 @@ If the file does not exist → skip silently.
 
 ---
 
+## Step 6.5 — [PLATFORM] Derive active_module and platform_type
+
+Using `tech_stack.module` loaded in Step 1, derive and store two variables for use by all downstream commands:
+
+```
+active_module = tech_stack.module   (e.g. "java-spring", "react", "flutter")
+```
+
+| `platform_type` | Modules |
+|---|---|
+| `backend` | `java-spring`, `golang`, `dotnet`, `php-laravel`, `context-engineering` |
+| `web-frontend` | `react`, `nextjs`, `vue`, `nuxt`, `angular` |
+| `mobile` | `flutter`, `react-native`, `ios-swiftui`, `android-compose` |
+
+If `tech_stack.module` is blank or not recognized → set `platform_type = "unknown"` and flag as ⚠️ in the Step 7 recap.
+
+These two variables (`active_module`, `platform_type`) are the canonical source for all branching logic in commands that need platform-specific behavior (generate-tests, debug, fix-bug, smoke-test).
+
+---
+
 ## Step 7 — [RECAP] Working Memory Recap (anti-lost-in-middle)
 
 After loading all context, synthesize and output a compact summary block.
@@ -229,10 +283,12 @@ Output exactly this block:
 ```
 [CTX LOADED]
 Stack     : {language} / {framework} / {database}
+Platform  : {active_module} ({platform_type})
 Layers    : {layer order from CLAUDE.md §2, e.g., Controller → Facade → Service → Repository}
 Ticket    : {ticket_prefix}-
 Dict      : {loaded — N canonical terms, M banned terms | missing}
 Entities  : {loaded — EntityA, EntityB, EntityC | missing}
+Service   : {active_service} ({active_service_module}) | single-service
 Status    : {FULL | PARTIAL — missing: CLAUDE.md / business-dict / core-entities | MINIMAL}
 ```
 
@@ -254,6 +310,26 @@ After completing all steps, you have loaded:
 Proceed to the next step of the calling command.
 
 
+---
+
+## Pre-Review Scan
+
+*(Separate from the Gate CHECKPOINT — this lists the actual files and scenarios in scope.)*
+
+Scan for implementation files and scenarios, then display:
+
+```
+Review Scope — {UC-ID}
+──────────────────────────────────────
+UC        : {UC-ID}
+Files     : {list of files tagged @trace.implements={UC-ID}}
+Scenarios : {N} scenarios in .feature file
+
+Proceed with review? (Y/N)
+```
+
+Wait for explicit "Y" before proceeding.
+
 ---
 
 ## Review Dimensions
@@ -262,7 +338,7 @@ Proceed to the next step of the calling command.
 - [ ] Every controller endpoint has `@trace.implements` tag?
 - [ ] Every test file has `@trace.verifies` tag?
 - [ ] No `@trace` tags on wrong layers?
-- [ ] `{paths.trace_dir}/{UC-ID}.tsv` up to date?
+- [ ] `{paths.trace_dir}/{UC-ID}.tsv` up to date? (if stale → run `/validate-traces {UC-ID}` first, then re-run this review)
 
 ### 2. Layer Architecture (from CLAUDE.md §2)
 - [ ] Each class in the correct layer?
@@ -310,21 +386,23 @@ Suggest the logical next command based on workflow phase:
 
 | Current command         | Suggest next                                  |
 |-------------------------|-----------------------------------------------|
+| /setup-ai-first         | `/define-product` to start your first feature |
 | /define-product         | `/generate-prd {product-definition-file}`     |
 | /generate-prd           | `/refine-prd {prd-file}` then `/review-context {prd-file}` |
 | /refine-prd             | Open Review Board → update PRD → `/review-context {prd-file}` |
-| /review-context (PRD)   | `/generate-bdd {prd-file}` if APPROVED; fix PRD if NEEDS_FIX |
+| /review-context (PRD)   | FE/App: `/generate-design-spec {prd-file}` (then BDD after sign-off); BE: `/generate-bdd {prd-file}` directly; fix PRD if NEEDS_FIX |
+| /generate-design-spec   | Designer review → Figma links confirmed → PO + Designer sign-off → `/generate-bdd {prd-file}` |
 | /generate-bdd           | `/review-context {feature-file}` to verify coverage |
 | /review-context (BDD)   | `/generate-tech-docs {UC-ID}` if APPROVED; regenerate if NEEDS_FIX |
 | /generate-tech-docs     | `/review-tech-docs {tech-design-file}`        |
 | /review-tech-docs       | `/generate-code {feature-file}` if APPROVED; fix doc if NEEDS_FIX |
-| /generate-code          | `/generate-tests {UC-ID}`                     |
+| /generate-code          | First gen → `/review-code {UC-ID}`; re-gen → `/generate-tests {UC-ID}` |
 | /generate-tests         | `/run-tests {UC-ID}`                          |
 | /run-tests (passing)    | `/review-code {UC-ID}`                        |
 | /run-tests (failing)    | `/fix-bug {ticket-id}` or `/debug {error}`    |
 | /review-code            | `/smoke-test {UC-ID}` or create PR            |
 | /smoke-test             | Create PR and link to ticket                  |
-| /validate-traces        | `/generate-code {UC-ID}` for gaps             |
+| /validate-traces        | DRIFT/UNTRACKED → `/generate-code {UC-ID}`; GAP → `/generate-tests {UC-ID}`; all OK → create PR |
 | /fix-bug                | Create PR and link to ticket                  |
 | /debug                  | `/fix-bug {ticket-id}` if fix needed          |
 
@@ -350,5 +428,15 @@ Critical: {X} | Major: {Y} | Minor: {Z}
 ### Minor
 | # | File | Line | Issue | Suggested Fix |
 
+Output Artifacts: none (read-only)
+
 Verdict: APPROVED ✅ | NEEDS_FIX ❌
+
+If APPROVED ✅:
+  Next: /generate-tests {UC-ID}
+
+If NEEDS_FIX ❌:
+  - Small fix (1–3 lines, no logic change) → fix inline → re-run /review-code {UC-ID}
+  - Logic / architecture issue             → /fix-bug {TICKET_ID}
+  - Spec mismatch (code ≠ scenario)        → /generate-code {feature-file}  (re-gen affected UC)
 ```

package/commands/review-code.tmpl

@@ -12,13 +12,33 @@
 
 ---
 
+## Pre-Review Scan
+
+*(Separate from the Gate CHECKPOINT — this lists the actual files and scenarios in scope.)*
+
+Scan for implementation files and scenarios, then display:
+
+```
+Review Scope — {UC-ID}
+──────────────────────────────────────
+UC        : {UC-ID}
+Files     : {list of files tagged @trace.implements={UC-ID}}
+Scenarios : {N} scenarios in .feature file
+
+Proceed with review? (Y/N)
+```
+
+Wait for explicit "Y" before proceeding.
+
+---
+
 ## Review Dimensions
 
 ### 1. Traceability
 - [ ] Every controller endpoint has `@trace.implements` tag?
 - [ ] Every test file has `@trace.verifies` tag?
 - [ ] No `@trace` tags on wrong layers?
-- [ ] `{paths.trace_dir}/{UC-ID}.tsv` up to date?
+- [ ] `{paths.trace_dir}/{UC-ID}.tsv` up to date? (if stale → run `/validate-traces {UC-ID}` first, then re-run this review)
 
 ### 2. Layer Architecture (from CLAUDE.md §2)
 - [ ] Each class in the correct layer?
@@ -53,5 +73,15 @@ Critical: {X} | Major: {Y} | Minor: {Z}
 ### Minor
 | # | File | Line | Issue | Suggested Fix |
 
+Output Artifacts: none (read-only)
+
 Verdict: APPROVED ✅ | NEEDS_FIX ❌
+
+If APPROVED ✅:
+  Next: /generate-tests {UC-ID}
+
+If NEEDS_FIX ❌:
+  - Small fix (1–3 lines, no logic change) → fix inline → re-run /review-code {UC-ID}
+  - Logic / architecture issue             → /fix-bug {TICKET_ID}
+  - Spec mismatch (code ≠ scenario)        → /generate-code {feature-file}  (re-gen affected UC)
 ```

package/commands/review-context.md

@@ -34,7 +34,7 @@ Display and wait for response:
 ```
 ⚙️  MODEL CHECK
 ──────────────────────────────────────────────────────────────────
-  Recommended  : claude-opus-4-5 (or claude-opus-4)
+  Recommended  : claude-opus-4 (or latest Opus model)
   Why needed   : Spec analysis, architecture review, code generation
                  require deep reasoning. Smaller models miss edge cases.
 
@@ -138,6 +138,7 @@ Read `.agent/project-context.yaml`. Extract and store:
 - `paths.core_entities` → path to core-entities.md
 - `paths.tech_docs_dir` → technical documentation root
 - `paths.trace_dir` → trace state directory
+- `paths.design_spec_dir` → Design Spec documents root (FE/App only)
 
 If `paths` section is absent, use these defaults:
 - `specs_dir` = `specs/bdd`
@@ -147,13 +148,46 @@ If `paths` section is absent, use these defaults:
 - `domain_knowledge_dir` = `specs/domain-knowledge`
 - `business_dictionary` = `specs/domain-knowledge/business-dictionary.md`
 - `core_entities` = `specs/domain-knowledge/core-entities.md`
-- `tech_docs_dir` = `tech-docs`
+- `tech_docs_dir` = `specs/tech-docs`
 - `trace_dir` = `.trace`
+- `design_spec_dir` = `specs/design-spec`
 
 If `tech_stack.module` is set, also load `.agent/modules/{module}/stack-profile.yaml` if it exists.
 
 ---
 
+## Step 1.5 — [SERVICE ROUTING] Resolve service paths (umbrella mode)
+
+*Skip this step entirely if `setup.mode` is not `"umbrella"` and `services` section is absent from project-context.yaml.*
+
+If `services` section is present:
+
+**1. Detect active domain** (in priority order):
+- Read `@trace.domain` from target file frontmatter (if Gate loaded a target file)
+- Extract from target file path: segment immediately after `prd_dir` base path  
+  *(e.g., `specs/prd/user/FEAT-01.md` → domain = `user`)*
+- If `$ARGUMENTS` contains a path, extract the segment after `prd_dir`
+
+**2. Route to service** — if active domain matches a key in `services`:
+- Override `paths.specs_dir` → `services.{domain}.specs_dir`
+- Override `paths.tech_docs_dir` → `services.{domain}.tech_docs_dir`
+- Store `active_service` = `services.{domain}.path`
+- Store `active_service_module` = `services.{domain}.module`
+- If service has its own `module` → use it as `active_module` (overrides `tech_stack.module`)
+
+**3. Fallback** — if domain not detected or no matching service key:
+- Keep default paths from Step 1
+- Set `active_service = unresolved`
+
+**4. Spec source auto-override** — if `setup.spec_source` is set AND the corresponding path was not already explicitly set in `paths:`:
+- Override `paths.prd_dir` → `{spec_source}/specs/prd`
+- Override `paths.design_spec_dir` → `{spec_source}/specs/design-spec`
+- Override `paths.domain_knowledge_dir` → `{spec_source}/specs/domain-knowledge`
+- Override `paths.business_dictionary` → `{spec_source}/specs/domain-knowledge/business-dictionary.md`
+- Override `paths.core_entities` → `{spec_source}/specs/domain-knowledge/core-entities.md`
+
+---
+
 ## Step 2 — [PROJECT-CONFIG] Load module stack profile (conditional)
 
 If `tech_stack.module` is set, read `.agent/modules/{module}/stack-profile.yaml`.
@@ -224,6 +258,26 @@ If the file does not exist → skip silently.
 
 ---
 
+## Step 6.5 — [PLATFORM] Derive active_module and platform_type
+
+Using `tech_stack.module` loaded in Step 1, derive and store two variables for use by all downstream commands:
+
+```
+active_module = tech_stack.module   (e.g. "java-spring", "react", "flutter")
+```
+
+| `platform_type` | Modules |
+|---|---|
+| `backend` | `java-spring`, `golang`, `dotnet`, `php-laravel`, `context-engineering` |
+| `web-frontend` | `react`, `nextjs`, `vue`, `nuxt`, `angular` |
+| `mobile` | `flutter`, `react-native`, `ios-swiftui`, `android-compose` |
+
+If `tech_stack.module` is blank or not recognized → set `platform_type = "unknown"` and flag as ⚠️ in the Step 7 recap.
+
+These two variables (`active_module`, `platform_type`) are the canonical source for all branching logic in commands that need platform-specific behavior (generate-tests, debug, fix-bug, smoke-test).
+
+---
+
 ## Step 7 — [RECAP] Working Memory Recap (anti-lost-in-middle)
 
 After loading all context, synthesize and output a compact summary block.
@@ -234,10 +288,12 @@ Output exactly this block:
 ```
 [CTX LOADED]
 Stack     : {language} / {framework} / {database}
+Platform  : {active_module} ({platform_type})
 Layers    : {layer order from CLAUDE.md §2, e.g., Controller → Facade → Service → Repository}
 Ticket    : {ticket_prefix}-
 Dict      : {loaded — N canonical terms, M banned terms | missing}
 Entities  : {loaded — EntityA, EntityB, EntityC | missing}
+Service   : {active_service} ({active_service_module}) | single-service
 Status    : {FULL | PARTIAL — missing: CLAUDE.md / business-dict / core-entities | MINIMAL}
 ```
 
@@ -280,6 +336,44 @@ Derive the output findings filename:
 
 ## PRD Review Mode
 
+### P0 — Umbrella Routing Check (umbrella mode only)
+
+*Skip this check entirely if `setup.mode` is not `"umbrella"` (i.e., `services` section absent from project-context.yaml).*
+
+When `setup.mode = umbrella`, the PRD must have correct routing metadata so context-loader Step 1.5 can direct generated output to the right service submodule. Run these checks **before P1–P5**:
+
+**P0.1 — `@trace.domain` presence**
+- Read the PRD frontmatter block (lines starting with `@trace.` at top of file)
+- If `@trace.domain` is **absent** → **critical** finding:
+  - `finding`: "`@trace.domain` is missing. Dev team's umbrella routing depends on this field to route BDD and code output to the correct service submodule."
+  - `suggestion`: "Add `@trace.domain: {domain}` to the PRD frontmatter. Use one of the domain keys defined in the umbrella's `project-context.yaml` services section."
+  - `auto_fixable: false` — PO must confirm the correct domain name
+
+**P0.2 — `@trace.domain` matches a service key**
+- If `@trace.domain` is present, check if its value matches any key in the `services` section of project-context.yaml
+- If **no match found** → **critical** finding:
+  - `finding`: "`@trace.domain: {value}` does not match any key in the umbrella's `services` config. Routing will fall back to default paths and BDD may be generated to the wrong location."
+  - `suggestion`: "Either update `@trace.domain` to match an existing service key ({list known keys}), or add a new entry to `services` in project-context.yaml for domain `{value}`."
+  - `auto_fixable: false`
+- If `services` section is not yet configured (empty/placeholder) → **major** finding:
+  - `finding`: "Umbrella `services` section is not yet configured. Cannot verify domain routing."
+  - `suggestion`: "Update `.agent/project-context.yaml` services section with domain-to-submodule mapping before generating BDD."
+  - `auto_fixable: false`
+
+**P0.3 — `@trace.status` check**
+- If `@trace.status` is absent → **minor**, `auto_fixable: true` (add `@trace.status: draft`)
+- If `@trace.status: draft` → **major**, `auto_fixable: false`:
+  - `finding`: "PRD status is `draft`. Dev team should not generate BDD from an unapproved PRD."
+  - `suggestion`: "PO/SA should review and update status to `approved` before dev team proceeds."
+
+> **P0 is a gate check:** If P0.1 or P0.2 yields a critical finding, display a warning before proceeding:
+> ```
+> ⚠️  ROUTING WARNING: @trace.domain issue detected.
+>    BDD/code generated from this PRD may land in the wrong service submodule.
+>    Resolve P0 findings before running /generate-bdd.
+> ```
+> Then continue with P1–P5 (do not abort — PO may be reviewing early-stage PRDs).
+
 ### P1 — Terminology Check (Business Dictionary)
 
 Load `{paths.business_dictionary}`.
@@ -379,14 +473,15 @@ Using `{paths.business_dictionary}` and `{paths.core_entities}`:
 ### B4 — Compliance Checks (C.1–C.5)
 
 - [ ] C.1 Wireframe Coverage: every screen component/action has ≥1 SC → finding per missing item
-- [ ] C.2 PRD Traceability: same as B1 (deduplicate)
+- [ ] C.2 PRD Traceability: covered fully by B1 — do NOT create new findings here; deduplicate against B1 findings
 - [ ] C.3 Business Dictionary terms used → same as B2
 - [ ] C.4 Banned Terms: 0 banned terms → **critical**, auto-fixable
 - [ ] C.5 NHÓM Grouping: if ≥3 SCs, grouped by business theme → **major**, auto-fixable
 
 ### B5 — Metadata & Structural Check
 
-- [ ] File header has all `@trace.*` fields → **minor**, auto-fixable
+- [ ] File header has all required `@trace.*` fields — check each explicitly: `@trace.id`, `@trace.title`, `@trace.revision`, `@trace.domain`, `@trace.service`, `@trace.module`, `@trace.status`, `@trace.author`, `@trace.created_at`, `@trace.prd`, `@trace.prd_version`, `@trace.bdd_version`, `@trace.business_rules`, `@trace.dataset` → **minor** per missing field, auto-fixable
+  - Note: `@trace.revision` is always `1` (static field — see generate-bdd.tmpl). Only check for presence; do NOT flag value as stale.
 - [ ] Every scenario has `# @trace.scenario`, `# @trace.sc_version`, `# @trace.business_rules`, `# Side-effects:` → **minor**, auto-fixable
 - [ ] Coverage Matrix at end of file → **major**, auto-fixable (AI regenerates)
 - [ ] Pre-merge Checklist at end of file → **minor**, auto-fixable
@@ -467,21 +562,23 @@ Suggest the logical next command based on workflow phase:
 
 | Current command         | Suggest next                                  |
 |-------------------------|-----------------------------------------------|
+| /setup-ai-first         | `/define-product` to start your first feature |
 | /define-product         | `/generate-prd {product-definition-file}`     |
 | /generate-prd           | `/refine-prd {prd-file}` then `/review-context {prd-file}` |
 | /refine-prd             | Open Review Board → update PRD → `/review-context {prd-file}` |
-| /review-context (PRD)   | `/generate-bdd {prd-file}` if APPROVED; fix PRD if NEEDS_FIX |
+| /review-context (PRD)   | FE/App: `/generate-design-spec {prd-file}` (then BDD after sign-off); BE: `/generate-bdd {prd-file}` directly; fix PRD if NEEDS_FIX |
+| /generate-design-spec   | Designer review → Figma links confirmed → PO + Designer sign-off → `/generate-bdd {prd-file}` |
 | /generate-bdd           | `/review-context {feature-file}` to verify coverage |
 | /review-context (BDD)   | `/generate-tech-docs {UC-ID}` if APPROVED; regenerate if NEEDS_FIX |
 | /generate-tech-docs     | `/review-tech-docs {tech-design-file}`        |
 | /review-tech-docs       | `/generate-code {feature-file}` if APPROVED; fix doc if NEEDS_FIX |
-| /generate-code          | `/generate-tests {UC-ID}`                     |
+| /generate-code          | First gen → `/review-code {UC-ID}`; re-gen → `/generate-tests {UC-ID}` |
 | /generate-tests         | `/run-tests {UC-ID}`                          |
 | /run-tests (passing)    | `/review-code {UC-ID}`                        |
 | /run-tests (failing)    | `/fix-bug {ticket-id}` or `/debug {error}`    |
 | /review-code            | `/smoke-test {UC-ID}` or create PR            |
 | /smoke-test             | Create PR and link to ticket                  |
-| /validate-traces        | `/generate-code {UC-ID}` for gaps             |
+| /validate-traces        | DRIFT/UNTRACKED → `/generate-code {UC-ID}`; GAP → `/generate-tests {UC-ID}`; all OK → create PR |
 | /fix-bug                | Create PR and link to ticket                  |
 | /debug                  | `/fix-bug {ticket-id}` if fix needed          |
 
@@ -500,7 +597,9 @@ Mode: {PRD | BDD}
 Findings: {total} | 🔴 Critical: {N} | 🟡 Major: {N} | 🟢 Minor: {N}
 Auto-fixable: {N} | Needs human decision: {N}
 
-Findings file: {paths.refinement_dir}/{slug}-findings.yaml
+Findings file:
+  {If PRD}: {paths.refinement_dir}/{prd-slug}-review-context-findings.yaml
+  {If BDD}: {paths.refinement_dir}/{uc-id}-review-bdd-findings.yaml
 
 Next options:
   A) Quick fix  : /review-context --fix {target-file}
@@ -536,6 +635,7 @@ For each finding where `auto_fixable: true`, in order (critical → major → mi
 
 | check_id | What to apply |
 |----------|--------------|
+| P0.3 (Missing status) | Add `@trace.status: draft` to frontmatter |
 | P1 (Banned term) | Replace every banned term occurrence with canonical term |
 | P4 (Structure) | Add missing section/metadata skeleton |
 
@@ -557,7 +657,7 @@ After applying each finding, mark it `status: "applied_automatically"` in the fi
 
 ### Phase 3 — Version bump
 
-- **PRD**: if ≥1 finding applied → bump minor version, add Changelog entry:
+- **PRD**: if ≥1 finding applied → bump **minor** version (auto-fix only applies P1 banned-term replacements and P4 skeleton additions — never alters UC structure or BR content, so minor bump is always correct), add Changelog entry:
   `Auto-fix: applied {N} auto-fixable review-context findings`
 - **BDD**: if ≥1 finding applied → increment `@trace.bdd_version` by 0.1
 
@@ -577,7 +677,9 @@ Still pending (needs human decision): {N}
 {If PRD}: Version bumped: {old} → {new}
 {If BDD}: bdd_version: {old} → {new}
 
-Findings file: {paths.refinement_dir}/{slug}-findings.yaml
+Findings file:
+  {If PRD}: {paths.refinement_dir}/{prd-slug}-review-context-findings.yaml
+  {If BDD}: {paths.refinement_dir}/{uc-id}-review-bdd-findings.yaml
 Re-run /review-context {file} to confirm 0 remaining critical findings.
 ```
 
@@ -596,8 +698,10 @@ Open findings file in Review Board → then run: /review-context --resume {file}
 
 ### Phase 1 — Read accepted findings
 
-1. Derive findings filename from target file (same rule as above).
-2. Read `{paths.refinement_dir}/{slug}-findings.yaml`.
+1. Derive findings filename from target file using the same rule as Detect Review Mode:
+   - PRD: `{paths.refinement_dir}/{prd-slug}-review-context-findings.yaml`
+   - BDD: `{paths.refinement_dir}/{uc-id}-review-bdd-findings.yaml`
+2. Read the findings file.
 3. Collect findings where `status: "accepted"` or `status: "modified"`.
 4. If none → report "No accepted findings. File unchanged." and stop.
 
@@ -608,6 +712,7 @@ Apply in order: critical → major → minor.
 **For PRD findings:**
 | check_id | What to do |
 |----------|-----------|
+| P0.3 (Missing status) | Add `@trace.status: draft` to frontmatter |
 | P1 (Banned term) | Replace every occurrence of banned term with canonical term |
 | P2 (Ambiguity) | Apply the fix stated in `suggestion` or `modified` note |
 | P3 (Conflict) | Apply the resolution stated in the modified note |
@@ -627,6 +732,7 @@ Apply in order: critical → major → minor.
 | B6 (Side effects) | Add missing `And <side-effect>` to Then block |
 
 → After applying, increment `@trace.bdd_version` in file header by 0.1.
+→ Also update `{paths.trace_dir}/{UC-ID}.tsv`: set `bdd_version` column to the new `@trace.bdd_version` value for all rows, and set `last_updated` to today's date.
 
 ### Phase 3 — Report
 

package/commands/review-context.tmpl

@@ -36,6 +36,44 @@ Derive the output findings filename:
 
 ## PRD Review Mode
 
+### P0 — Umbrella Routing Check (umbrella mode only)
+
+*Skip this check entirely if `setup.mode` is not `"umbrella"` (i.e., `services` section absent from project-context.yaml).*
+
+When `setup.mode = umbrella`, the PRD must have correct routing metadata so context-loader Step 1.5 can direct generated output to the right service submodule. Run these checks **before P1–P5**:
+
+**P0.1 — `@trace.domain` presence**
+- Read the PRD frontmatter block (lines starting with `@trace.` at top of file)
+- If `@trace.domain` is **absent** → **critical** finding:
+  - `finding`: "`@trace.domain` is missing. Dev team's umbrella routing depends on this field to route BDD and code output to the correct service submodule."
+  - `suggestion`: "Add `@trace.domain: {domain}` to the PRD frontmatter. Use one of the domain keys defined in the umbrella's `project-context.yaml` services section."
+  - `auto_fixable: false` — PO must confirm the correct domain name
+
+**P0.2 — `@trace.domain` matches a service key**
+- If `@trace.domain` is present, check if its value matches any key in the `services` section of project-context.yaml
+- If **no match found** → **critical** finding:
+  - `finding`: "`@trace.domain: {value}` does not match any key in the umbrella's `services` config. Routing will fall back to default paths and BDD may be generated to the wrong location."
+  - `suggestion`: "Either update `@trace.domain` to match an existing service key ({list known keys}), or add a new entry to `services` in project-context.yaml for domain `{value}`."
+  - `auto_fixable: false`
+- If `services` section is not yet configured (empty/placeholder) → **major** finding:
+  - `finding`: "Umbrella `services` section is not yet configured. Cannot verify domain routing."
+  - `suggestion`: "Update `.agent/project-context.yaml` services section with domain-to-submodule mapping before generating BDD."
+  - `auto_fixable: false`
+
+**P0.3 — `@trace.status` check**
+- If `@trace.status` is absent → **minor**, `auto_fixable: true` (add `@trace.status: draft`)
+- If `@trace.status: draft` → **major**, `auto_fixable: false`:
+  - `finding`: "PRD status is `draft`. Dev team should not generate BDD from an unapproved PRD."
+  - `suggestion`: "PO/SA should review and update status to `approved` before dev team proceeds."
+
+> **P0 is a gate check:** If P0.1 or P0.2 yields a critical finding, display a warning before proceeding:
+> ```
+> ⚠️  ROUTING WARNING: @trace.domain issue detected.
+>    BDD/code generated from this PRD may land in the wrong service submodule.
+>    Resolve P0 findings before running /generate-bdd.
+> ```
+> Then continue with P1–P5 (do not abort — PO may be reviewing early-stage PRDs).
+
 ### P1 — Terminology Check (Business Dictionary)
 
 Load `{paths.business_dictionary}`.
@@ -135,14 +173,15 @@ Using `{paths.business_dictionary}` and `{paths.core_entities}`:
 ### B4 — Compliance Checks (C.1–C.5)
 
 - [ ] C.1 Wireframe Coverage: every screen component/action has ≥1 SC → finding per missing item
-- [ ] C.2 PRD Traceability: same as B1 (deduplicate)
+- [ ] C.2 PRD Traceability: covered fully by B1 — do NOT create new findings here; deduplicate against B1 findings
 - [ ] C.3 Business Dictionary terms used → same as B2
 - [ ] C.4 Banned Terms: 0 banned terms → **critical**, auto-fixable
 - [ ] C.5 NHÓM Grouping: if ≥3 SCs, grouped by business theme → **major**, auto-fixable
 
 ### B5 — Metadata & Structural Check
 
-- [ ] File header has all `@trace.*` fields → **minor**, auto-fixable
+- [ ] File header has all required `@trace.*` fields — check each explicitly: `@trace.id`, `@trace.title`, `@trace.revision`, `@trace.domain`, `@trace.service`, `@trace.module`, `@trace.status`, `@trace.author`, `@trace.created_at`, `@trace.prd`, `@trace.prd_version`, `@trace.bdd_version`, `@trace.business_rules`, `@trace.dataset` → **minor** per missing field, auto-fixable
+  - Note: `@trace.revision` is always `1` (static field — see generate-bdd.tmpl). Only check for presence; do NOT flag value as stale.
 - [ ] Every scenario has `# @trace.scenario`, `# @trace.sc_version`, `# @trace.business_rules`, `# Side-effects:` → **minor**, auto-fixable
 - [ ] Coverage Matrix at end of file → **major**, auto-fixable (AI regenerates)
 - [ ] Pre-merge Checklist at end of file → **minor**, auto-fixable
@@ -203,7 +242,9 @@ Mode: {PRD | BDD}
 Findings: {total} | 🔴 Critical: {N} | 🟡 Major: {N} | 🟢 Minor: {N}
 Auto-fixable: {N} | Needs human decision: {N}
 
-Findings file: {paths.refinement_dir}/{slug}-findings.yaml
+Findings file:
+  {If PRD}: {paths.refinement_dir}/{prd-slug}-review-context-findings.yaml
+  {If BDD}: {paths.refinement_dir}/{uc-id}-review-bdd-findings.yaml
 
 Next options:
   A) Quick fix  : /review-context --fix {target-file}
@@ -239,6 +280,7 @@ For each finding where `auto_fixable: true`, in order (critical → major → mi
 
 | check_id | What to apply |
 |----------|--------------|
+| P0.3 (Missing status) | Add `@trace.status: draft` to frontmatter |
 | P1 (Banned term) | Replace every banned term occurrence with canonical term |
 | P4 (Structure) | Add missing section/metadata skeleton |
 
@@ -260,7 +302,7 @@ After applying each finding, mark it `status: "applied_automatically"` in the fi
 
 ### Phase 3 — Version bump
 
-- **PRD**: if ≥1 finding applied → bump minor version, add Changelog entry:
+- **PRD**: if ≥1 finding applied → bump **minor** version (auto-fix only applies P1 banned-term replacements and P4 skeleton additions — never alters UC structure or BR content, so minor bump is always correct), add Changelog entry:
   `Auto-fix: applied {N} auto-fixable review-context findings`
 - **BDD**: if ≥1 finding applied → increment `@trace.bdd_version` by 0.1
 
@@ -280,7 +322,9 @@ Still pending (needs human decision): {N}
 {If PRD}: Version bumped: {old} → {new}
 {If BDD}: bdd_version: {old} → {new}
 
-Findings file: {paths.refinement_dir}/{slug}-findings.yaml
+Findings file:
+  {If PRD}: {paths.refinement_dir}/{prd-slug}-review-context-findings.yaml
+  {If BDD}: {paths.refinement_dir}/{uc-id}-review-bdd-findings.yaml
 Re-run /review-context {file} to confirm 0 remaining critical findings.
 ```
 
@@ -299,8 +343,10 @@ Open findings file in Review Board → then run: /review-context --resume {file}
 
 ### Phase 1 — Read accepted findings
 
-1. Derive findings filename from target file (same rule as above).
-2. Read `{paths.refinement_dir}/{slug}-findings.yaml`.
+1. Derive findings filename from target file using the same rule as Detect Review Mode:
+   - PRD: `{paths.refinement_dir}/{prd-slug}-review-context-findings.yaml`
+   - BDD: `{paths.refinement_dir}/{uc-id}-review-bdd-findings.yaml`
+2. Read the findings file.
 3. Collect findings where `status: "accepted"` or `status: "modified"`.
 4. If none → report "No accepted findings. File unchanged." and stop.
 
@@ -311,6 +357,7 @@ Apply in order: critical → major → minor.
 **For PRD findings:**
 | check_id | What to do |
 |----------|-----------|
+| P0.3 (Missing status) | Add `@trace.status: draft` to frontmatter |
 | P1 (Banned term) | Replace every occurrence of banned term with canonical term |
 | P2 (Ambiguity) | Apply the fix stated in `suggestion` or `modified` note |
 | P3 (Conflict) | Apply the resolution stated in the modified note |
@@ -330,6 +377,7 @@ Apply in order: critical → major → minor.
 | B6 (Side effects) | Add missing `And <side-effect>` to Then block |
 
 → After applying, increment `@trace.bdd_version` in file header by 0.1.
+→ Also update `{paths.trace_dir}/{UC-ID}.tsv`: set `bdd_version` column to the new `@trace.bdd_version` value for all rows, and set `last_updated` to today's date.
 
 ### Phase 3 — Report