@edupia-tutor/spec-driven-docs 0.14.0

package/commands/generate-bdd.tmpl

@@ -0,0 +1,534 @@
+# /generate-bdd — Generate BDD Feature Files
+
+## Gate
+{{include:steps/gate.md}}
+
+## Context
+{{include:steps/context-loader.md}}
+
+> **Tester proposals (optional input):** before generating, check `{paths.bdd_proposals_dir}/` (default `{spec_source}/feedback/bdd-proposals/`) for scenarios proposed by testers via `/propose-scenario` that map to this UC's ACs. Incorporate any the PO/Dev has accepted — then the tester's draft is removed/archived from `feedback/`. Skip if the folder is empty.
+
+---
+
+## Repo Mode Detection
+
+After loading context, determine which mode to operate in:
+
+- **Spec repo mode**: `project-context.yaml` has NO `services` section OR `setup.mode: spec`
+- **Umbrella mode**: `project-context.yaml` HAS `services` section AND `setup.mode: umbrella`
+
+→ Spec repo mode → proceed to **Platform Selection** below (skip Service Detection)
+→ Umbrella mode → proceed to **Service Detection** below (skip Platform Selection)
+
+---
+
+## Platform Selection (Spec Repo Mode Only)
+
+*Skip this section if running in umbrella mode.*
+
+Ask the user to select the target platform:
+
+```
+Which platform is this BDD for?
+  1. web    — FE/Web (React, Next.js, Angular, Vue, Nuxt)
+  2. app    — Mobile (Flutter, React Native, iOS, Android)
+  3. system — System/BE BDD (synthesized from existing web + app BDDs)
+```
+
+Wait for user selection. Set `active_platform` = chosen value.
+
+**Output path (spec repo mode):**
+`{paths.specs_dir}/{domain}/{prd-slug}/bdd/{active_platform}/{TICKET-ID}-UC{N}-{slug}.feature`
+
+**Platform vocabulary:**
+
+| Platform | "user action" | "type/input" | "observe" | "navigate" |
+|---|---|---|---|---|
+| web | "clicks" | "types into" / "enters" | "sees" / "the page shows" | "navigates to" / "goes to" |
+| app | "taps" | "enters" / "inputs" | "sees" / "the screen shows" | "navigates to" / "opens" |
+| system | N/A — use business events | — | "the system returns" / "receives response" | — |
+
+---
+
+## System BDD Synthesis (active_platform = system)
+
+*Only applies when platform = system. Skip for web and app.*
+
+### Step S0 — Brownfield Check
+
+Check the source PRD Metadata table for `| **API Source** | existing |`.
+
+**Nếu `API Source: existing`:**
+- API contract đã được PO ghi trong phần "Existing API Contract" của PRD.
+- **Skip Steps S1–S3** — không cần scan FE/App BDD, không cần conflict resolution.
+- Dùng bảng "Existing API Contract" trong PRD làm contract input cho Step S4.
+- Set `# @trace.api_source: existing` trong header của file system BDD được gen.
+
+**Nếu `API Source` không có hoặc không phải `existing`:**
+- Tiếp tục Steps S1–S3 (normal synthesis flow).
+
+---
+
+### Step S1 — Scan available FE/App BDDs
+
+Search for existing BDDs for this TICKET-ID:
+- Web BDDs: `{paths.specs_dir}/{domain}/{prd-slug}/bdd/web/{TICKET-ID}-*.feature`
+- App BDDs: `{paths.specs_dir}/{domain}/{prd-slug}/bdd/app/{TICKET-ID}-*.feature`
+
+Classify the feature:
+
+| Condition | Mode |
+|---|---|
+| Both web + app BDDs found | **Multi-platform** — synthesize from both |
+| Only web BDD found | **Web-only** — synthesize from web |
+| Only app BDD found | **App-only** — synthesize from app |
+| No FE/App BDDs found | **Backend-only** — gen directly from PRD |
+
+---
+
+### Step S2 — Extract expected contracts per platform
+
+For each found BDD file, extract:
+- **Triggers**: what user actions call the backend? (map to logical "request" events)
+- **Expected response data**: what fields/shape does each `Then` clause need from the system?
+- **Error signals**: what error states must the backend signal?
+- **Business rules**: what invariants does each platform assume the system enforces?
+
+---
+
+### Step S3 — Cross-Platform Conflict Check (multi-platform mode only)
+
+*Skip if web-only, app-only, or backend-only.*
+
+Compare the extracted contracts across platforms. Flag a conflict if any of these differ:
+
+| Conflict type | Example |
+|---|---|
+| **Response shape mismatch** | Web expects `{ token, redirect_url }`, App expects `{ token, user_profile }` |
+| **Error semantics mismatch** | Web expects HTTP 423 for lock, App expects custom error code `ACC_LOCKED` |
+| **Business rule contradiction** | Web BDD says "lock after 5 attempts", App BDD says "lock after 3 attempts" |
+| **Data field conflict** | Web expects `expires_in: seconds`, App expects `expires_at: ISO timestamp` |
+
+**If conflicts detected → CHECKPOINT (mandatory, cannot skip):**
+
+```
+⚠️  CROSS-PLATFORM CONTRACT CONFLICT
+──────────────────────────────────────────────────────────────────
+Feature : {TICKET-ID} — {UC name}
+
+Conflict 1: Response shape mismatch
+  Web BDD (Then): user sees dashboard → implies { token, redirect_url }
+  App BDD (Then): app navigates to HomeScreen → implies { token, user_profile }
+
+Resolution options:
+  A — Union response
+      BE returns all fields: { token, redirect_url, user_profile }
+      Clients ignore fields they don't use. Simple, slight over-fetch.
+  B — Platform hint in request
+      Client sends X-Platform: web|app in header, BE tailors response.
+      Cleaner responses, more BE logic.
+  C — Separate endpoints
+      POST /auth/login/web  and  POST /auth/login/app
+      Maximum flexibility, more endpoints to maintain.
+  D — Custom: describe your approach
+──────────────────────────────────────────────────────────────────
+Choose resolution for each conflict (A/B/C/D):
+```
+
+Wait for PO's resolution per conflict. Record each decision as a `# @system.resolution:` annotation in the generated system BDD file.
+
+**If no conflicts → proceed to Step S4 directly.**
+
+---
+
+### Step S4 — Generate System BDD scenarios
+
+Generate scenarios based on mode and resolved conflicts:
+
+- **Multi-platform**: synthesize from both web + app contracts, applying resolved resolutions
+- **Web-only / App-only**: derive from the single platform's contracts
+- **Backend-only**: derive directly from PRD AC/BR using business event language (not HTTP)
+
+System BDD step vocabulary (always use — regardless of FE/App vocabulary):
+- Triggers: "the system receives {event}" / "a {actor} submits {action}"
+- Assertions: "the system returns {data}" / "the system signals {error}" / "the system stores {state}"
+- Do NOT use UI words (click, tap, see, navigate) in system BDD
+
+**If multi-platform with resolution A (union):**
+- System BDD shows the full response contract: all fields from all platforms
+- Add comment: `# @system.resolution: union — clients receive all fields`
+
+**If resolution B (platform hint):**
+- Write separate `Scenario Outline` using Examples table for `web` vs `app` response variants
+- Add comment: `# @system.resolution: platform-hint — X-Platform header determines response shape`
+
+**If resolution C (separate endpoints):**
+- Write separate Scenarios for each endpoint
+- Note the endpoint split explicitly in the SCOPE section
+
+---
+
+## Service Detection (Umbrella Mode Only)
+
+*Skip this section if running in spec repo mode.*
+
+Read the PRD Metadata table for `| **Service** |` and `| **Module** |` rows.
+
+| Condition | Action |
+|---|---|
+| PRD has `Service` row AND value is not "default" | Use it as `active_service` + `active_module`. Load catalog for that module. |
+| PRD has no `Service` row AND `services` defined in project-context.yaml | Ask: "Which service is this BDD for?" (list services, wait for selection) |
+| Single-service project (no `services` array) | `active_service = "default"`, `active_module = tech_stack.module` |
+
+**Output path (umbrella mode):**
+- `active_service = "default"` → `{paths.specs_dir}/{domain}/{prd-slug}/bdd/{TICKET-ID}-UC{N}-{slug}.feature`
+- `active_service ≠ "default"` → `{paths.specs_dir}/{domain}/{prd-slug}/bdd/{active_service}/{TICKET-ID}-UC{N}-{slug}.feature`
+
+**Platform vocabulary** — adapt BDD step wording based on `active_module`:
+
+| Platform type | Modules | "click" | "type" | "see" | "navigate" |
+|---|---|---|---|---|---|
+| Web | react, nextjs, vue, nuxt, angular | "clicks" | "types into" / "enters" | "sees" / "the page shows" | "navigates to" / "goes to" |
+| Mobile | flutter, react-native, ios-swiftui, android-compose | "taps" | "enters" / "inputs" | "sees" / "the screen shows" | "navigates to" / "opens" |
+| Backend / API | java-spring, golang, dotnet, php-laravel | *(no UI steps — use)* "submits a request" / "calls the API" | — | "receives response" / "the system returns" | — |
+
+Apply this vocabulary silently when writing Gherkin steps. Do NOT mix web and mobile terms in the same feature file.
+
+---
+
+## Orchestration Check
+
+*Skip this section if already in sub-agent mode (Step 0 of Gate was triggered).*
+
+After loading context, check if the target PRD is large enough to warrant sub-agents:
+
+1. Count `#### {TICKET-ID}-UC` headings in the PRD → **UC count**.
+2. Count total lines in the PRD → **line count**.
+3. If **UC count > 3** OR **line count > 300**:
+   - Switch to orchestration mode — follow `steps/spawn-agent.md`.
+   - The main session becomes the orchestrator: spawn 1 sub-agent per UC.
+   - Each sub-agent runs `/generate-bdd` with `_agent_mode: true` payload.
+   - Collect results and show merged report.
+   - **Do NOT continue with the steps below.**
+4. If UC count ≤ 3 AND line count ≤ 300 → continue with Version Check below (single-session mode).
+
+---
+
+## Sub-Agent Return Format
+
+*This section applies when running as a sub-agent (Gate Step 0 detected `_agent_mode: true`).*
+
+After generating all `.feature` and `.tsv` files for the assigned UC, return the structured result JSON (as specified in `steps/spawn-agent.md` Step E):
+
+```json
+{ "uc_id": "{TICKET-ID}-UC{N}", "files_created": ["path/to/file1", "path/to/file2"], "status": "success | error", "errors": [] }
+```
+
+---
+
+## Version Check
+
+Before generating, check for existing `.feature` files for this PRD:
+
+1. Resolve the search path based on mode:
+   - **Spec repo mode**: `{paths.specs_dir}/{domain}/{prd-slug}/bdd/{active_platform}/{TICKET-ID}-UC*.feature`
+   - **Umbrella mode**: `{paths.specs_dir}/{domain}/{prd-slug}/bdd/{TICKET-ID}-UC*.feature` (or with `{active_service}/` if multi-service)
+2. Read current PRD `| **Version** |` from metadata (e.g., `1.2`).
+
+**If no existing feature files** → fresh generation, proceed normally. Use PRD version as `@trace.prd_version`.
+
+**If existing feature files found**:
+- Read `# @trace.prd_version:` from the existing feature file header.
+- Compare with current PRD version.
+- If **same** → ask: "BDD already generated from PRD v{version}. Regenerate? (Y/N)"
+- If **different** (PRD was updated):
+  1. Read `## Changelog` from the PRD — extract all rows newer than the existing BDD's `@trace.prd_version`.
+  2. Show CHECKPOINT:
+     ```
+     ⚠️  PRD version drift detected
+     BDD was generated from PRD v{old}
+     PRD is now at v{new}
+
+     Changes since v{old}:
+       {changelog rows}
+
+     Options:
+       Y — update only affected scenarios
+       F — full regeneration of all scenarios
+       N — cancel
+     ```
+  3. Proceed based on user choice.
+
+---
+
+## BDD Writing Rules (R1-R10 — enforce strictly)
+
+| Rule | Name | Requirement |
+|------|------|-------------|
+| R1 | Given/When/Then Semantics | Given=state, When=action, Then=outcome. Every SC needs full G/W/T. |
+| R2 | One Behavior Per Scenario | 1 SC = 1 behavior. Do NOT chain When→Then→When→Then. |
+| R3 | Ubiquitous Language | Do NOT use UI selectors / API names / tech terms in steps. |
+| R4 | Outside-in Naming | SC name describes business outcome. No "click" / "(Case X)" / component names. |
+| R5 | Declarative over Imperative | Describe WHAT (business intent), NOT HOW (UI mechanic). |
+| R6 | Observable Outcomes Only | Then asserts observable outcome. Not UI intermediate state / internal state. |
+| R7 | Key Examples / Concrete | Use concrete values. Not vague "valid data". |
+| R8 | Independence | SC runs independently. Does not depend on state from another SC. |
+| R9 | Test Data Completeness | Data table has enough fields to derive expected Then. |
+| R10 | Scope Boundary Explicit | Cross-UC reference uses navigation wording + Note comment. |
+
+## Project Compliance (fail review if missing — C.1-C.5)
+
+| Check | Rule |
+|-------|------|
+| C.1 Wireframe Coverage | Every component/action in Wireframe has ≥1 SC. |
+| C.2 PRD Traceability | Every AC and every BR (including each logic bullet) maps to ≥1 SC. |
+| C.3 Business Dictionary | Use correct canonical terms from business-dictionary.md. |
+| C.4 Banned Terms | 0 banned terms in file — grep before generating. |
+| C.5 NHÓM Grouping | Feature ≥3 SCs → MUST have NHÓM grouping by business theme. |
+
+---
+
+## NHÓM Grouping Convention (C.5 — mandatory for ≥3 scenarios)
+
+Group by business theme, NOT by happy/negative/edge.
+
+Format header (indent 2 spaces, same level as Background):
+```
+  # ==========================================================
+  # NHÓM N: <Business theme> (<BR refs if applicable>)
+  # ==========================================================
+```
+
+Rules:
+- Number sequentially NHÓM 1 → N. SC IDs sequential across lifecycle (do not reset per NHÓM).
+- Each NHÓM can contain @happy + @edge + @negative of the same theme.
+- SCs in NHÓM do not need to be in ID order (NHÓM 2 can contain SC4, SC8, SC11 if same theme).
+
+Suggested patterns (adjust per UC):
+- `Init / Save success — valid data combinations`
+- `Validation / Block when invalid`
+- `Error handling — API fail / system error`
+- `Cancel changes / Close modal without saving`
+- `Cross-system / Downstream effects`
+- `Idempotency & Concurrency`
+
+---
+
+## UC Decomposition
+
+For each UC in the PRD, present the SC outline **before generating**:
+```
+{TICKET-ID}-UC1: {Use Case Name}
+  NHÓM 1: {Theme} (BR1, BR2)
+    SC1 [@happy]:              {business outcome}
+    SC2 [@happy @alternative]: {variant outcome}
+  NHÓM 2: {Theme} (BR2, BR3)
+    SC3 [@edge]:               {edge case}
+    SC4 [@negative]:           {error handling}
+  ACs covered: AC1, AC2
+  BRs covered: {TICKET-ID}-UC1-BR1, BR2, BR3
+```
+
+CHECKPOINT: "Does this outline look correct? Do you want to add or remove any SCs?" → **Wait for confirm before generating.**
+
+---
+
+## Generate
+
+**Output path by mode:**
+- **Spec repo mode**: `{paths.specs_dir}/{domain}/{prd-slug}/bdd/{active_platform}/{TICKET-ID}-UC{N}-{slug}.feature`
+- **Umbrella mode (single-service)**: `{paths.specs_dir}/{domain}/{prd-slug}/bdd/{TICKET-ID}-UC{N}-{slug}.feature`
+- **Umbrella mode (multi-service)**: `{paths.specs_dir}/{domain}/{prd-slug}/bdd/{active_service}/{TICKET-ID}-UC{N}-{slug}.feature`
+
+For each UC, write to the resolved path above. Use vocabulary for the active platform (from Platform Selection or Service Detection).
+
+```gherkin
+# ============================================================
+# @trace.id: {TICKET-ID}-UC{N}
+# @trace.title: <Feature name>
+# @trace.revision: 1  ← static field; use @trace.bdd_version for version tracking (incremented by /review-context --fix or --resume)
+# @trace.domain: <domain>
+# @trace.platform: {active_platform — web | app | system | (omit in umbrella mode)}
+# @trace.service: {active_service — omit in spec repo mode}
+# @trace.module: {active_module in umbrella mode; "unknown" in spec repo mode}
+# @trace.status: draft
+# @trace.author: AI-generated
+# @trace.created_at: {YYYY-MM-DD}
+# @trace.prd: {TICKET-ID}
+# @trace.prd_version: {read from PRD metadata "| **Version** |"}
+# @trace.bdd_version: {1.0 if fresh generation; increment by 0.1 on re-generation — e.g. 1.0 → 1.1}
+# @trace.business_rules: {TICKET-ID}-UC{N}-BR1, {TICKET-ID}-UC{N}-BR2
+# @trace.dataset: {domain}.testdata.yaml
+# ============================================================
+
+# === CONTEXT ===
+# Actor:     <role performing the action, e.g., Consumer, Staff, System>
+# Screens:   <related screens, e.g., Cart → Confirm Order → Order Detail>
+# Entities:  <business entities, e.g., Order, OrderItem, Consumer>
+# Pre-state: <shared state before entering scenarios>
+
+# === SCOPE ===
+# In:  <what this UC covers>
+# Out: <what is NOT in this UC — link to other UC/feature (R10)>
+
+# === BUSINESS DEFINITION ===
+# Quick reference for terms used in this feature. SoT details: business-dictionary.md
+# <Term 1>: <short definition>
+# <Term 2>: <short definition>
+
+Feature: <Feature name>
+  As a <role>
+  I want to <action>
+  So that <business value>
+
+  Background:
+    Given <shared precondition — use aliases from dataset, not technical IDs>
+
+  # ==========================================================
+  # NHÓM 1: <Business theme> (<BR refs>)
+  # ==========================================================
+
+  # Side-effects: <list brief Then side-effects to verify>
+  # @trace.scenario: {TICKET-ID}-UC{N}-SC1
+  # @trace.sc_version: 1.0
+  # @trace.business_rules: {TICKET-ID}-UC{N}-BR1
+  @happy
+  Scenario: <describe business outcome — use precise verb: create/receive/assign/block>
+    Given <input state — alias from dataset>
+    When <single action>
+    Then <main observable outcome>
+      And <side-effect 1 declared in header>
+
+  # Side-effects: <...>
+  # @trace.scenario: {TICKET-ID}-UC{N}-SC2
+  # @trace.sc_version: 1.0
+  # @trace.business_rules: {TICKET-ID}-UC{N}-BR1
+  @happy @alternative
+  Scenario: <same NHÓM 1 theme but different path — e.g., different enum value>
+    Given <state>
+    When <action>
+    Then <outcome>
+
+  # ==========================================================
+  # NHÓM 2: <Business theme 2> (<BR refs>)
+  # ==========================================================
+
+  # Side-effects: <...>
+  # @trace.scenario: {TICKET-ID}-UC{N}-SC3
+  # @trace.sc_version: 1.0
+  # @trace.business_rules: {TICKET-ID}-UC{N}-BR2
+  @edge
+  Scenario: <boundary / error scenario>
+    Given <state>
+    When <action>
+    Then <expected error handling>
+```
+
+### Coverage Matrix & Pre-merge Checklist *(appended to end of each file)*
+
+```gherkin
+# === PRD COVERAGE (C.1 + C.2) ===
+# AC mapping:
+#   AC1 (...) → SC1, SC2
+#   AC2 (...) → SC3
+# BR mapping (each bullet MUST have ≥1 SC — C.2):
+#   {TICKET-ID}-UC{N}-BR1 (...) → SC1, SC2
+#   {TICKET-ID}-UC{N}-BR2 (...) → SC3
+# Wireframe mapping (every component/action ≥1 SC — C.1):
+#   Screen "<screen name>":
+#     [x] <action 1>  → SC1
+#     [x] <action 2>  → SC2
+#     [ ] <action 3>  → MISSING ← BLOCK MERGE
+
+# === PRE-MERGE CHECKLIST ===
+# - [ ] Every SC has Side-effects + @trace.scenario + @trace.sc_version + @trace.business_rules
+# - [ ] Coverage Matrix: 0 MISSING lines (C.1)
+# - [ ] Every AC/BR maps to ≥1 SC (C.2)
+# - [ ] 0 banned terms (C.4) — grep file before merging
+# - [ ] Feature ≥3 SCs has NHÓM grouping by business theme (C.5)
+# - [ ] If popup/modal: Popup/Modal Lifecycle declared in BUSINESS DEFINITION
+# - [ ] If display logic ≥2 dimensions: Display Logic Matrix in BUSINESS DEFINITION
+```
+
+---
+
+## Write Trace State
+
+After generating all `.feature` files, create or update `{paths.trace_dir}/{domain}/{prd-slug}/{UC-ID}.tsv` for each UC.
+
+> **Umbrella + `spec_source`:** both the `.feature` files **and** the trace `.tsv` write to the **spec repo** (`{spec_source}/specs/{domain}/{prd-slug}/bdd/…` and `{spec_source}/.trace/{domain}/{prd-slug}/…`, resolved by context-loader) — a **single-repo** write, committed/pushed to the spec submodule. (Trace is consolidated in the spec repo so the PM manages all status in one place; code-side commands update it cross-repo later.)
+
+**TSV columns (tab-separated, one header row + one data row per scenario):**
+```
+sc_id\tsc_title\tspec_ver\tgen_ver\timplemented_by\ttest_count\ttest_classes\tdev_selftest\tdev_selftest_at\tqc_status\tqc_run_at\tqc_owner\tqc_blocked_by\tprd_version\tbdd_version\ttech_doc_revision\tfe_tech_doc_revision\tprd_status\tuc_status\tfe_phase\tstatus\tlast_updated
+```
+
+**Rules:**
+- If file does not exist → create with header row + all scenario rows.
+- If file exists (re-generation) → for each SC in the new `.feature`:
+  - SC already in `.tsv` AND `spec_ver` is unchanged → update only: `sc_title`, `prd_version`, `bdd_version`, `prd_status`, `uc_status`, `last_updated`. Leave all other columns unchanged.
+  - SC already in `.tsv` AND `spec_ver` changed (scenario was modified) → update: `sc_title`, `spec_ver`, `prd_version`, `bdd_version`, `prd_status`, `uc_status`, `last_updated` AND set `status = DRIFT` immediately (so the TSV reflects drift without waiting for `/validate-traces`). Leave `gen_ver`, `implemented_by`, `test_count`, `test_classes`, `tech_doc_revision`, `fe_tech_doc_revision` unchanged.
+  - SC is new (added in this re-gen) → append new row with `gen_ver`, `implemented_by`, `test_count`, `test_classes`, `dev_selftest`, `dev_selftest_at`, `qc_status`, `qc_run_at`, `qc_owner`, `qc_blocked_by`, `tech_doc_revision`, `fe_tech_doc_revision` all set to `—`.
+  - SC no longer in `.feature` (removed) → delete its row.
+
+**Values to write for each scenario:**
+
+| Column | Value |
+|--------|-------|
+| `sc_id` | `{UC-ID}-SC{N}` |
+| `sc_title` | scenario title text |
+| `spec_ver` | `@trace.sc_version` of this scenario |
+| `gen_ver` | `—` (not yet generated) |
+| `implemented_by` | `—` |
+| `test_count` | `—` |
+| `test_classes` | `—` |
+| `dev_selftest` | `—` (no tests run yet) |
+| `dev_selftest_at` | `—` |
+| `qc_status` | `—` (official QC automation result — set by `/qc-run-test`) |
+| `qc_run_at` | `—` |
+| `qc_owner` | `—` (who a non-passing SC waits on: `dev` / `po` — set by `/qc-run-test` + `/report-bug`) |
+| `qc_blocked_by` | `—` (linked `BUG-{id}` / `GAP-{id}` — set by `/qc-run-test` + `/report-bug`) |
+| `prd_version` | `@trace.prd_version` from `.feature` header |
+| `bdd_version` | `@trace.bdd_version` from `.feature` header |
+| `tech_doc_revision` | `—` (BE API contract revision — set by `/generate-code` + `/review-tech-docs`) |
+| `fe_tech_doc_revision` | `—` (FE client tech-design revision `{UC-ID}-tech-design-{platform}.md` — set by `/generate-code --phase=integration` + `/review-tech-docs` on an FE doc) |
+| `prd_status` | read `\| **Status** \|` from PRD metadata |
+| `uc_status` | `draft` for new UCs; keep existing value for re-gen |
+| `fe_phase` | `—` (set by `/generate-code --phase` when FE implements) |
+| `status` | `UNTRACKED` |
+| `last_updated` | today `YYYY-MM-DD` |
+
+## Refresh Panel Mirror
+{{include:steps/trace-mirror.md}}
+
+## Output
+
+{{include:steps/report-footer.md}}
+
+```
+/generate-bdd Complete
+
+[Spec repo mode — platform: {active_platform}]
+Files:
+  {paths.specs_dir}/{domain}/{prd-slug}/bdd/{active_platform}/{TICKET-ID}-UC1-{slug}.feature ({N} scenarios)
+  {paths.specs_dir}/{domain}/{prd-slug}/bdd/{active_platform}/{TICKET-ID}-UC2-{slug}.feature ({N} scenarios)
+Trace:
+  {paths.trace_dir}/{domain}/{prd-slug}/{TICKET-ID}-UC1.tsv ({N} rows)
+  {paths.trace_dir}/{domain}/{prd-slug}/{TICKET-ID}-UC2.tsv ({N} rows)
+Next (spec repo):
+  → Run /generate-bdd again for other platforms (web → app → system)
+  → After all platforms generated: commit + push + notify dev team
+  → Dev team reads BDD from spec submodule — no /generate-bdd on their side
+
+[Umbrella mode — service: {active_service}]
+Files:
+  {paths.specs_dir}/{domain}/{prd-slug}/bdd/{TICKET-ID}-UC1-{slug}.feature ({N} scenarios)
+Trace:
+  {paths.trace_dir}/{domain}/{prd-slug}/{TICKET-ID}-UC1.tsv ({N} rows)
+Next (umbrella):
+  → /review-context {feature-file} to verify coverage
+  → /generate-tech-docs {feature-file}
+  → /generate-code {feature-file}
+
+📊 Living Docs: run /validate-traces (or /sync) to push this trace to the spec-module dashboard.
+```