uctm 1.2.0 → 1.3.2

package/agents/ko/xml-schema.md

@@ -1,109 +1,109 @@
-# Agent Communication XML Schema
-
-uc-taskmanager 에이전트 간 XML 통신 포맷 정의.
-
----
-
-## 1. Dispatch Format (Dispatcher → Receiver)
-
-```xml
-<dispatch to="{receiver}" work="{WORK_ID}" task="{TASK_ID}" execution-mode="{direct|pipeline|full}">
-  <context>
-    <project>{project name}</project>
-    <language>{lang_code}</language>
-    <plan-file>works/{WORK_ID}/PLAN.md</plan-file>
-  </context>
-  <task-spec>
-    <file>works/{WORK_ID}/TASK-XX.md</file>
-    <title>{title}</title>
-    <action>{implement|verify|commit|plan|route}</action>
-    <description>{optional}</description>
-  </task-spec>
-  <previous-results>
-    <result task="{TASK_ID}" status="{PASS|FAIL|SKIP}">{summary}</result>
-  </previous-results>
-  <cache-hint sections="{section1},{section2}"/>
-</dispatch>
-```
-
-| 속성 | 값 |
-|------|----|
-| `to` | builder, verifier, committer, planner, scheduler, router |
-| `task` | `TASK-NN` — WORK prefix 포함 금지 |
-| `execution-mode` | direct / pipeline / full (생략 시 full로 간주) |
-
----
-
-## 2. Task Result Format (Receiver → Dispatcher)
-
-```xml
-<task-result work="{WORK_ID}" task="{TASK_ID}" agent="{agent}" status="{PASS|FAIL}">
-  <summary>{1-2줄 요약}</summary>
-  <files-changed>
-    <file action="{created|modified|deleted}" path="{path}">{description}</file>
-  </files-changed>
-  <verification>
-    <check name="{type}" status="{PASS|FAIL|N/A}">{output}</check>
-  </verification>
-  <notes>{참고사항}</notes>
-</task-result>
-```
-
----
-
-## 3. Dispatcher-Receiver 매핑
-
-| Dispatcher | Receiver | execution-mode | 설명 |
-|------------|----------|:--------------:|------|
-| Router | (자기 자신) | `direct` | 서브에이전트 없음. Router가 직접 구현+commit+콜백 |
-| Router | Planner | `full` | 복잡 WORK 계획 |
-| Router | Scheduler | `full` | 계획된 WORK 실행 |
-| Router | Builder | `pipeline` | TASK 1개 구현 |
-| Router | Verifier | `pipeline` | TASK 1개 검증 |
-| Router | Committer | `pipeline` | TASK 1개 커밋 |
-| Scheduler | Builder | `full` | TASK N개 구현 |
-| Scheduler | Verifier | `full` | TASK N개 검증 |
-| Scheduler | Committer | `full` | TASK N개 커밋 |
-
----
-
-## 4. Context-Handoff Element
-
-```xml
-<context-handoff from="{agent}" detail-level="{FULL|SUMMARY|DROP}">
-  <what>{변경/검증 사항}</what>
-  <why>{의사결정 근거}</why>       <!-- FULL only -->
-  <caution>{주의사항}</caution>    <!-- FULL only -->
-  <incomplete>{미완료 사항}</incomplete>  <!-- FULL only -->
-</context-handoff>
-```
-
-| detail-level | 포함 필드 |
-|:---:|---|
-| `FULL` | what, why, caution, incomplete |
-| `SUMMARY` | what만 (1-3줄) |
-| `DROP` | 요소 생략 |
-
----
-
-## 5. execution-mode별 에이전트 행동
-
-| 에이전트 | direct | pipeline | full |
-|---------|--------|----------|------|
-| Router | 구현+self-check+result.md+commit+콜백 직접 | PLAN 생성 후 B→V→C dispatch | Planner에 dispatch |
-| Planner | 호출 안 됨 | 호출 안 됨 | PLAN.md 생성 |
-| Scheduler | 호출 안 됨 | 호출 안 됨 | DAG 관리 + [B→V→C]×N |
-| Builder | 호출 안 됨 | 정상 실행 | 정상 실행 |
-| Verifier | 호출 안 됨 | 정상 실행 | 정상 실행 |
-| Committer | 호출 안 됨 | result.md+commit+콜백 | result.md+commit+콜백 |
-
-불변 항목 (모드 무관):
-
-| 항목 | direct | pipeline/full |
-|------|:---:|:---:|
-| `works/WORK-NN/` 디렉토리 | Router | Router/Planner |
-| `PLAN.md` | Router | Router/Planner |
-| `TASK-XX.md` | Router | Router/Planner |
-| `TASK-XX_result.md` | Router | Committer |
-| COMMITTER DONE 콜백 | Router | Committer |
-| `WORK-LIST.md` IN_PROGRESS | Router | Router |
+# Agent Communication XML Schema
+
+uc-taskmanager 에이전트 간 XML 통신 포맷 정의.
+
+---
+
+## 1. Dispatch Format (Dispatcher → Receiver)
+
+```xml
+<dispatch to="{receiver}" work="{WORK_ID}" task="{TASK_ID}" execution-mode="{direct|pipeline|full}">
+  <references-dir>{참조 파일 디렉토리의 절대 경로}</references-dir>
+  <context>
+    <project>{project name}</project>
+    <language>{lang_code}</language>
+    <plan-file>works/{WORK_ID}/PLAN.md</plan-file>
+  </context>
+  <task-spec>
+    <file>works/{WORK_ID}/TASK-XX.md</file>
+    <title>{title}</title>
+    <action>{implement|verify|commit|plan|route}</action>
+    <description>{optional}</description>
+  </task-spec>
+  <previous-results>
+    <result task="{TASK_ID}" status="{PASS|FAIL|SKIP}">{summary}</result>
+  </previous-results>
+  <cache-hint sections="{section1},{section2}"/>
+</dispatch>
+```
+
+| 속성 | 값 |
+|------|----|
+| `to` | builder, verifier, committer, planner, scheduler, specifier |
+| `task` | `TASK-NN` — WORK prefix 포함 금지 |
+| `execution-mode` | direct / pipeline / full (생략 시 full로 간주) |
+
+---
+
+## 2. Task Result Format (Receiver → Dispatcher)
+
+```xml
+<task-result work="{WORK_ID}" task="{TASK_ID}" agent="{agent}" status="{PASS|FAIL}">
+  <summary>{1-2줄 요약}</summary>
+  <files-changed>
+    <file action="{created|modified|deleted}" path="{path}">{description}</file>
+  </files-changed>
+  <verification>
+    <check name="{type}" status="{PASS|FAIL|N/A}">{output}</check>
+  </verification>
+  <notes>{참고사항}</notes>
+</task-result>
+```
+
+---
+
+## 3. Dispatcher-Receiver 매핑
+
+| Dispatcher | Receiver | execution-mode | 설명 |
+|------------|----------|:--------------:|------|
+| Specifier | Builder | `direct` | 겸임: TASK 1개 구현 (Verifier 생략) |
+| Specifier | Planner | `pipeline/full` | 위임: 복잡 WORK 계획 |
+| Planner | Builder | `pipeline` | TASK 구현 |
+| Planner | Scheduler | `full` | DAG 관리 + 실행 |
+| Scheduler | Builder | `full` | TASK N개 구현 |
+| Scheduler | Verifier | `full` | TASK N개 검증 |
+| Scheduler | Committer | `full` | TASK N개 커밋 |
+
+---
+
+## 4. Context-Handoff Element
+
+```xml
+<context-handoff from="{agent}" detail-level="{FULL|SUMMARY|DROP}">
+  <what>{변경/검증 사항}</what>
+  <why>{의사결정 근거}</why>       <!-- FULL only -->
+  <caution>{주의사항}</caution>    <!-- FULL only -->
+  <incomplete>{미완료 사항}</incomplete>  <!-- FULL only -->
+</context-handoff>
+```
+
+| detail-level | 포함 필드 |
+|:---:|---|
+| `FULL` | what, why, caution, incomplete |
+| `SUMMARY` | what만 (1-3줄) |
+| `DROP` | 요소 생략 |
+
+---
+
+## 5. execution-mode별 에이전트 행동
+
+| 에이전트 | direct | pipeline | full |
+|---------|--------|----------|------|
+| Specifier | Requirement.md + PLAN.md + TASK (겸임) | Requirement.md만 → Planner 위임 | Requirement.md만 → Planner 위임 |
+| Planner | 호출 안 됨 (Specifier 겸임) | PLAN.md + TASK + execution-mode | PLAN.md + TASK + execution-mode |
+| Scheduler | 호출 안 됨 | 호출 안 됨 | DAG 관리 + [B→V→C]×N |
+| Builder | 정상 실행 (self-check) | 정상 실행 | 정상 실행 |
+| Verifier | 호출 안 됨 | 정상 실행 | 정상 실행 |
+| Committer | result.md+commit+콜백 | result.md+commit+콜백 | result.md+commit+콜백 |
+
+불변 항목 (모드 무관):
+
+| 항목 | direct | pipeline/full |
+|------|:---:|:---:|
+| `works/WORK-NN/` 디렉토리 | Specifier | Specifier |
+| `Requirement.md` | Specifier | Specifier |
+| `PLAN.md` | Specifier (겸임) | Planner |
+| `TASK-XX.md` | Specifier (겸임) | Planner |
+| `TASK-XX_result.md` | Committer | Committer |
+| COMMITTER DONE 콜백 | Committer | Committer |
+| `WORK-LIST.md` IN_PROGRESS | Specifier | Specifier |

package/agents/{en/planner.md → planner.md}

@@ -9,7 +9,7 @@ model: opus
 
 You are the **Planner** — the WORK creation and TASK decomposition agent.
 
-Analyzes user requests to define WORK (unit of work) and decomposes them into a TASK list in dependency DAG form.
+Based on the Requirement.md created by Specifier, designs the WORK and decomposes it into TASKs, and determines the execution-mode.
 
 ```
 WORK (unit of work)    — Goal unit of the user's request
@@ -22,8 +22,9 @@ WORK (unit of work)    — Goal unit of the user's request
 
 | Duty | Description |
 |------|-------------|
-| WORK ID Determination | Scan filesystem to calculate next WORK number |
-| Project Exploration | Analyze CLAUDE.md, README, package.json, directory structure |
+| Requirement.md Analysis | Design based on requirement document created by Specifier |
+| Project Exploration | Analyze CLAUDE.md, README, package.json, directory structure, codebase |
+| Execution-Mode Determination | Determine pipeline/full based on TASK count |
 | TASK Decomposition | Decompose WORK goal into TASK list in dependency DAG form |
 | File Generation | Create PLAN.md, TASK-XX.md, TASK-XX_progress.md under `works/{WORK-ID}/` |
 | User Approval | Present plan and receive approval; generate files after approval |
@@ -35,49 +36,32 @@ WORK (unit of work)    — Goal unit of the user's request
 
 ### 3-1. STARTUP — Read Reference Files Immediately (REQUIRED)
 
+**Resolve REFERENCES_DIR**: Check your input for `REFERENCES_DIR=...` line or `<references-dir>` XML element. Use that absolute path. If not provided, default to `.claude/agents`.
+
 | File | Purpose |
 |------|---------|
-| `.claude/agents/file-content-schema.md` | File format schema (PLAN.md 7 fields, TASK format) |
-| `.claude/agents/shared-prompt-sections.md` | Common rules (TASK ID, WORK-LIST rules) |
-| `.claude/agents/work-activity-log.md` | Activity Log rules (log_work function, STAGE table) |
+| `{REFERENCES_DIR}/file-content-schema.md` | File format schema (PLAN.md 7 fields, TASK format) |
+| `{REFERENCES_DIR}/shared-prompt-sections.md` | Common rules (TASK ID, WORK-LIST rules) |
+| `{REFERENCES_DIR}/work-activity-log.md` | Activity Log rules (log_work function, STAGE table) |
 
 ### 3-2. Project Exploration (Discovery Process)
 
 ```bash
 # 1. Check existing WORKs
 ls -d works/WORK-* 2>/dev/null | sort -V | tail -1
-
-# 2. Check CLAUDE.md language setting
-grep -oP '(?<=Language:\s?)[a-z]{2}' CLAUDE.md 2>/dev/null
-
-# 3. Project information
-cat CLAUDE.md 2>/dev/null || cat README.md 2>/dev/null
-
-# 4. Tech stack
-cat package.json 2>/dev/null | head -50
-cat pyproject.toml 2>/dev/null | head -30
-cat Cargo.toml 2>/dev/null | head -20
-cat go.mod 2>/dev/null | head -10
-
-# 5. Structure
-find . -maxdepth 3 -type f \( -name "*.md" -o -name "*.json" -o -name "*.toml" \) | grep -v node_modules | head -30
 ```
 
-### 3-3. WORK ID Determination
+→ Discovery commands (steps 2–4): see `shared-prompt-sections.md` § 11
+
+### 3-3. Requirement.md Analysis + WORK Directory Check
 
-Filesystem scan result is the sole source. MEMORY.md reference prohibited.
+Specifier has already created the WORK directory and written Requirement.md.
+Check the WORK ID from the dispatch XML's `work` attribute, and read Requirement.md from that directory.
 
 ```bash
-LATEST=$(ls -d works/WORK-* 2>/dev/null | sort -V | tail -1)
-if [ -z "$LATEST" ]; then
-  NEXT_ID="WORK-01"
-else
-  LATEST_NUM=$(basename $LATEST | sed 's/WORK-//')
-  NEXT_ID="WORK-$((LATEST_NUM + 1))"
-fi
-
-# Safety check
-[ -d "works/$NEXT_ID" ] && echo "ERROR: $NEXT_ID already exists. Aborting." && exit 1
+# Check WORK ID from dispatch XML
+WORK_ID="WORK-NN"  # work attribute from dispatch XML
+cat "works/${WORK_ID}/Requirement.md"
 ```
 
 ### 3-4. TASK Decomposition
@@ -92,6 +76,19 @@ Use `mcp__sequential-thinking__sequentialthinking` when TASK count is 4+ or depe
 - When tech stack is unfamiliar and decomposition strategy is unclear
 - When parallel/sequential structure judgment is ambiguous
 
+### 3-4-1. Execution-Mode Determination
+
+Determine execution mode based on TASK decomposition results.
+
+| Mode | Condition | Example |
+|------|-----------|---------|
+| **pipeline** | 1 TASK + significant implementation | Single feature, game creation |
+| **full** | Multiple TASKs or dependencies exist | Auth system, large refactoring |
+
+> Planner determines pipeline or full only. direct is already decided when Specifier assumes Planner role.
+
+Record the determined mode in PLAN.md's `> Execution-Mode:` field.
+
 ### 3-5. User Approval and File Generation
 
 ```
@@ -103,7 +100,7 @@ Use `mcp__sequential-thinking__sequentialthinking` when TASK count is 4+ or depe
 
 ### 3-6. Output Structure
 
-→ see `.claude/agents/file-content-schema.md` § 7
+→ see `{REFERENCES_DIR}/file-content-schema.md` § 7
 
 Creation responsibilities:
 - `PLAN.md`, `TASK-XX.md`, `TASK-XX_progress.md` (initial template) → Planner
@@ -113,7 +110,7 @@ Creation responsibilities:
 
 When creating TASK files, always create `TASK-XX_progress.md` template in the same directory.
 
-File formats: → `.claude/agents/file-content-schema.md` § 1 (PLAN.md), § 2 (TASK), § 3 (progress initial value)
+File formats: → `{REFERENCES_DIR}/file-content-schema.md` § 1 (PLAN.md), § 2 (TASK), § 3 (progress initial value)
 
 ### 3-7. MCP Tool Usage (Serena)
 
@@ -127,23 +124,14 @@ File formats: → `.claude/agents/file-content-schema.md` § 1 (PLAN.md), § 2 (
 ### 3-8. Output Language Rule
 
 → Priority rules: see `shared-prompt-sections.md` § 1
-
-Planner-specific locale detection:
-```
-1. CLAUDE.md → check "Language: xx"
-2. If not found, ask user for language
-3. If not found, auto-detect system locale
-   - Windows: powershell -c "[CultureInfo]::CurrentCulture.TwoLetterISOLanguageName"
-   - Linux/Mac: locale | grep LANG | grep -oP '[a-z]{2}' | head -1
-   - Fallback: "en"
-```
+→ Locale detection: see `shared-prompt-sections.md` § 9
 
 Record resolved language in PLAN.md `> Language:` field. Write all outputs in that language.
 
-### 3-9. Requirement Code (REQ) Recording
+### 3-9. Requirement Recording
 
-- `REQ-XXX` pattern exists: `> Requirement: REQ-XXX`
-- If absent: `> Requirement: {user request text}` — record the user's request text as-is
+Record Requirement.md path in PLAN.md `> Requirement:` field:
+- `> Requirement: works/WORK-NN/Requirement.md`
 
 ---
 
@@ -154,5 +142,6 @@ Record resolved language in PLAN.md `> Language:` field. Write all outputs in th
 - NEVER create cross-WORK dependencies — only intra-WORK dependencies allowed
 - ALWAYS create `works/{WORK-ID}/` directory structure
 - TASK filenames: `TASK-XX.md` format only (runner.ts `parseTaskFilename()` recognition criteria)
-- WORK ID determination: filesystem scan only, MEMORY.md reference prohibited
+- WORK directory is already created by Specifier — Planner does not create WORKs
+- WORK-LIST.md is managed by Specifier — Planner does not modify it
 - File generation without user approval prohibited — always present plan and receive approval first

package/agents/{en/scheduler.md → scheduler.md}

@@ -36,13 +36,15 @@ You are the **Scheduler** — the WORK pipeline execution agent.
 
 ### 3-1. STARTUP — Read Reference Files Immediately (REQUIRED)
 
+**Resolve REFERENCES_DIR**: Check your input for `REFERENCES_DIR=...` line or `<references-dir>` XML element. Use that absolute path. If not provided, default to `.claude/agents`.
+
 | File | Purpose |
 |------|---------|
-| `.claude/agents/file-content-schema.md` | File format schema |
-| `.claude/agents/shared-prompt-sections.md` | Common rules |
-| `.claude/agents/xml-schema.md` | XML communication format |
-| `.claude/agents/context-policy.md` | Sliding Window rules |
-| `.claude/agents/work-activity-log.md` | Activity Log rules (log_work function, STAGE table) |
+| `{REFERENCES_DIR}/file-content-schema.md` | File format schema |
+| `{REFERENCES_DIR}/shared-prompt-sections.md` | Common rules |
+| `{REFERENCES_DIR}/xml-schema.md` | XML communication format |
+| `{REFERENCES_DIR}/context-policy.md` | Sliding Window rules |
+| `{REFERENCES_DIR}/work-activity-log.md` | Activity Log rules (log_work function, STAGE table) |
 
 ### 3-2. WORK Identification and Initial Load
 
@@ -132,7 +134,7 @@ Committer FAIL retry:
 
 ### 3-9. Progress Report
 
-Update PROGRESS.md after TASK completion (→ see `.claude/agents/file-content-schema.md` § 6) and output status:
+Update PROGRESS.md after TASK completion (→ see `{REFERENCES_DIR}/file-content-schema.md` § 6) and output status:
 
 ```
 ✅ TASK-XX completed — commit: {hash}
@@ -163,8 +165,8 @@ Multi-WORK status check:
 - Bypassing pipeline results in missing result.md → WORK completion recognition failure
 
 ### WORK-LIST.md Rules
-- Do not change WORK-LIST.md to COMPLETED — changed only at git push time
-- → see `.claude/agents/shared-prompt-sections.md` § 8
+- Do not modify WORK-LIST.md — archival is handled by committer
+- → see `{REFERENCES_DIR}/shared-prompt-sections.md` § 8
 
 ### Output Language Rule
 → see `shared-prompt-sections.md` § 1

package/agents/{en/shared-prompt-sections.md → shared-prompt-sections.md}

@@ -52,6 +52,7 @@ fi
 
 ```
 works/{WORK_ID}/
+  ├─ Requirement.md                 # Created by Specifier (mandatory)
   ├─ PLAN.md
   ├─ PROGRESS.md
   ├─ TASK-00.md               # No WORK prefix
@@ -106,7 +107,7 @@ echo "$DONE / $TOTAL"
 
 ## § 7. PLAN.md Required Meta-Information — 7 Fields
 
-→ `.claude/agents/file-content-schema.md` § 1 reference
+→ `{REFERENCES_DIR}/file-content-schema.md` § 1 reference
 
 | Field | Required | Description |
 |-------|----------|-------------|
@@ -124,17 +125,105 @@ echo "$DONE / $TOTAL"
 
 File: `works/WORK-LIST.md`
 
-| Status | Timing |
-|--------|--------|
-| `IN_PROGRESS` | Added when WORK directory is created |
-| `COMPLETED` | Automatically changed by committer when last TASK is completed |
+**Format:**
+```
+LAST_WORK_ID: WORK-XX
+
+| WORK | 제목 | 상태 | 생성일 | 완료일 |
+|------|------|------|--------|--------|
+| WORK-NN | ... | IN_PROGRESS | YYYY-MM-DD | |
+| WORK-MM | ... | DONE | YYYY-MM-DD | YYYY-MM-DD |
+```
+
+| Status | Meaning | Trigger |
+|--------|---------|---------|
+| `IN_PROGRESS` | WORK is being executed | specifier creates WORK |
+| `DONE` | All TASKs completed, awaiting review/push | committer completes last TASK |
+| `COMPLETED` | Archived to _COMPLETED/ | push merge (Main Claude batch processes all DONE) |
+
+Rules:
+- `LAST_WORK_ID` header tracks the highest WORK ID ever created
+- **specifier**: on WORK creation, add IN_PROGRESS row + update `LAST_WORK_ID`
+- **committer**: when last TASK is completed, change `IN_PROGRESS` → `DONE` and fill completion date (do NOT move folder or remove row)
+- **Main Claude** (push procedure): move all DONE WORKs to `works/_COMPLETED/`, remove their rows from WORK-LIST.md
+
+---
+
+## § 9. Locale Detection
+
+```
+1. CLAUDE.md → check "Language: xx"
+2. If not found, ask user for language
+3. If not found, auto-detect system locale
+   - Windows: powershell -c "[CultureInfo]::CurrentCulture.TwoLetterISOLanguageName"
+   - Linux/Mac: locale | grep LANG | grep -oP '[a-z]{2}' | head -1
+   - Fallback: "en"
+```
+
+---
+
+## § 10. Callback Transmission Template
+
+Replace `{CallbackType}` with the actual key name (e.g., `ProgressCallback`, `TaskCallback`).
+
+```bash
+CALLBACK_URL=$(grep "^{CallbackType}:" CLAUDE.md 2>/dev/null | sed 's/^{CallbackType}: //' | tr -d '\r')
+CALLBACK_TOKEN=$(grep "^CallbackToken:" CLAUDE.md 2>/dev/null | sed 's/^CallbackToken: //' | tr -d '\r')
+
+if [ -n "$CALLBACK_URL" ] && [ "$CALLBACK_URL" != "{CallbackType}:" ]; then
+  PAYLOAD=$(cat <<EOF
+{
+  "workId": "${WORK_ID}",
+  "taskId": "${TASK_ID}",
+  ... agent-specific fields ...
+}
+EOF
+  )
+  AUTH_HEADER=""
+  [ -n "$CALLBACK_TOKEN" ] && AUTH_HEADER="-H \"X-Runner-Api-Key: ${CALLBACK_TOKEN}\""
+  curl -s -X POST "$CALLBACK_URL" \
+    -H "Content-Type: application/json" \
+    $AUTH_HEADER \
+    -d "$PAYLOAD" > /dev/null 2>&1
+fi
+```
+
+Agent-specific payload fields:
+- **ProgressCallback** (builder): `"status": "IN_PROGRESS"`, `"currentReasoning": "..."`
+- **TaskCallback** (committer): `"status": "SUCCESS"`, `"commitHash": "${COMMIT_HASH}"`
+
+---
+
+## § 11. Project Discovery
+
+```bash
+# 1. Check CLAUDE.md language setting
+grep -oP '(?<=Language:\s?)[a-z]{2}' CLAUDE.md 2>/dev/null
+
+# 2. Tech stack
+cat package.json 2>/dev/null | head -50
+cat pyproject.toml 2>/dev/null | head -30
+cat Cargo.toml 2>/dev/null | head -20
+cat go.mod 2>/dev/null | head -10
+
+# 3. Structure (when needed)
+find . -maxdepth 3 -type f \( -name "*.md" -o -name "*.json" -o -name "*.toml" \) | grep -v node_modules | head -30
+```
+
+---
+
+## § 12. Progress File Gate Check
+
+Gate conditions for `works/WORK-NN/TASK-XX_progress.md`:
+- File exists at the expected path
+- `Status: COMPLETED` line is present
+- `## Files Changed` section is present and non-empty
 
-- Must add IN_PROGRESS when WORK directory is created
-- committer: after committing the last TASK, change WORK-LIST.md from `IN_PROGRESS` to `COMPLETED`
+On gate failure → return FAIL task-result immediately. Do not proceed to subsequent steps.
 
 ---
 
 ## Version
 
 - Created: 2026-03-10
-- Updated: 2026-03-15
+- Updated: 2026-03-21