@boyingliu01/xp-gate 0.14.29 → 0.14.30

package/lib/sprint-audit.js

@@ -0,0 +1,235 @@
+/**
+ * xp-gate sprint-audit — Layer 2: Final sprint completeness audit.
+ *
+ * Checks phase_history coverage, time records, artifact records,
+ * and state consistency at Phase 6 CLOSE.
+ *
+ * Usage:
+ *   xp-gate sprint-audit [--dir <path>] [--json]
+ *
+ * Verdict rules:
+ *   6/6 completed + 0 errors       → PASS (exit 0)
+ *   >= 4/6 completed + 0 errors    → PASS_WITH_WARNINGS (exit 0)
+ *   < 4/6 completed or any errors  → FAIL (exit 1)
+ *   No sprint-state.json           → SKIP (exit 0)
+ *
+ * @module sprint-audit
+ */
+
+'use strict';
+
+const fs = require('fs');
+const path = require('path');
+const { PHASE_NAMES } = require('./phase-transition');
+
+/**
+ * Run the sprint audit.
+ * @param {string[]} args - CLI arguments
+ * @returns {Promise<number>} Exit code
+ */
+async function handleSprintAudit(args = []) {
+  if (args.includes('--help')) {
+    console.log('Usage: xp-gate sprint-audit [options]');
+    console.log('');
+    console.log('Options:');
+    console.log('  --dir <path>   Project directory (default: cwd)');
+    console.log('  --json         Output as JSON instead of human-readable');
+    console.log('');
+    console.log('Runs final sprint completeness audit at Phase 6 CLOSE.');
+    console.log('Checks phase coverage, time records, artifact records,');
+    console.log('and state consistency.');
+    return 0;
+  }
+
+  const dirIdx = args.indexOf('--dir');
+  const projectDir = dirIdx >= 0 ? args[dirIdx + 1] : process.cwd();
+  const jsonFlag = args.includes('--json');
+
+  const stateFile = path.join(projectDir, '.sprint-state', 'sprint-state.json');
+
+  // No sprint-state.json → SKIP
+  if (!fs.existsSync(stateFile)) {
+    if (jsonFlag) {
+      console.log(JSON.stringify({ verdict: 'SKIP', reason: 'No sprint-state.json found' }));
+    } else {
+      console.log('⏭️  No sprint-state.json found — skipping audit.');
+    }
+    return 0;
+  }
+
+  let state;
+  try {
+    state = JSON.parse(fs.readFileSync(stateFile, 'utf8'));
+  } catch (err) {
+    const result = {
+      verdict: 'FAIL',
+      errors: [`Failed to parse sprint-state.json: ${err.message}`],
+    };
+    if (jsonFlag) {
+      console.log(JSON.stringify(result, null, 2));
+    } else {
+      console.error(`❌ ${result.errors[0]}`);
+    }
+    return 1;
+  }
+
+  // ── Run checks ──
+  const warnings = [];
+  const errors = [];
+  const phaseHistory = Array.isArray(state.phase_history) ? state.phase_history : [];
+
+  // Build lookup
+  const historyLookup = {};
+  for (const entry of phaseHistory) {
+    historyLookup[entry.phase] = entry;
+  }
+
+  // Check 1: Phase coverage
+  const completedPhases = [];
+  const missingPhases = [];
+  const incompletePhases = [];
+
+  for (let i = 1; i <= 6; i++) {
+    const entry = historyLookup[i];
+    if (!entry) {
+      missingPhases.push(i);
+    } else if (entry.status === 'completed' || entry.status === 'skipped') {
+      completedPhases.push(i);
+    } else {
+      incompletePhases.push({ phase: i, name: PHASE_NAMES[i] || `Phase ${i}`, status: entry.status });
+    }
+  }
+
+  // Check 2: Time records for completed phases
+  for (const phaseNum of completedPhases) {
+    const entry = historyLookup[phaseNum];
+    if (entry.status === 'completed' && (entry.duration_seconds == null || entry.duration_seconds === 0)) {
+      warnings.push(`Phase ${phaseNum} (${PHASE_NAMES[phaseNum]}) completed but has no duration recorded`);
+    }
+  }
+
+  // Check 3: Artifact records (phase-{N}-summary.md)
+  const outputsDir = path.join(projectDir, '.sprint-state', 'phase-outputs');
+  for (const phaseNum of completedPhases) {
+    if (historyLookup[phaseNum].status === 'completed') {
+      const summaryFile = path.join(outputsDir, `phase-${phaseNum}-summary.md`);
+      if (!fs.existsSync(summaryFile)) {
+        warnings.push(`Phase ${phaseNum} summary missing: .sprint-state/phase-outputs/phase-${phaseNum}-summary.md`);
+      }
+    }
+  }
+
+  // Check 4: State consistency — phase field vs phase_history last entry
+  if (phaseHistory.length > 0) {
+    const lastEntry = phaseHistory[phaseHistory.length - 1];
+    if (state.phase !== undefined && state.phase !== lastEntry.phase) {
+      errors.push(
+        `State inconsistency: sprint-state.phase=${state.phase} but phase_history last entry is phase ${lastEntry.phase}`
+      );
+    }
+  }
+
+  // ── Determine verdict ──
+  const completedCount = completedPhases.length;
+  let verdict;
+  if (errors.length > 0 || completedCount < 4) {
+    verdict = 'FAIL';
+  } else if (completedCount >= 6 && errors.length === 0) {
+    verdict = 'PASS';
+  } else {
+    verdict = 'PASS_WITH_WARNINGS';
+  }
+
+  // ── Build result ──
+  const result = {
+    sprint_id: state.id || 'unknown',
+    branch: state.isolation?.branch || 'unknown',
+    coverage: {
+      completed: completedCount,
+      total: 6,
+      pct: Math.round((completedCount / 6) * 100),
+    },
+    missing_phases: missingPhases.map(p => ({ phase: p, name: PHASE_NAMES[p] || `Phase ${p}` })),
+    incomplete_phases: incompletePhases,
+    warnings,
+    errors,
+    verdict,
+  };
+
+  // ── Persist report (latest overwrites — expected behavior) ──
+  const reportPath = path.join(projectDir, '.sprint-state', 'audit-report.json');
+  try {
+    fs.writeFileSync(reportPath, JSON.stringify(result, null, 2), 'utf8');
+  } catch (err) {
+    // Report write failure is WARNING, not BLOCK
+    warnings.push(`Failed to write audit report: ${err.message}`);
+  }
+
+  // ── Output ──
+  if (jsonFlag) {
+    console.log(JSON.stringify(result, null, 2));
+  } else {
+    printHumanReadable(result, state);
+  }
+
+  // Exit code: FAIL → 1, others → 0
+  return verdict === 'FAIL' ? 1 : 0;
+}
+
+/**
+ * Print human-readable audit report.
+ * @param {object} result - Audit result object
+ * @param {object} state - Sprint state object
+ */
+function printHumanReadable(result, state) {
+  const lines = [];
+  lines.push('');
+  lines.push('━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━');
+  lines.push(`  Sprint Audit Report — ${result.sprint_id}`);
+  lines.push('━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━');
+  lines.push('');
+  lines.push(`  Branch: ${result.branch}`);
+  lines.push(`  Phase Coverage: ${result.coverage.completed}/${result.coverage.total} (${result.coverage.pct}%)`);
+  lines.push('');
+  lines.push('  Phase History:');
+
+  for (let i = 1; i <= 6; i++) {
+    const entry = result.incomplete_phases.find(p => p.phase === i);
+    const missing = result.missing_phases.find(p => p.phase === i);
+    const name = (PHASE_NAMES[i] || `Phase ${i}`).padEnd(10);
+
+    if (missing) {
+      lines.push(`  ❌ Phase ${i}/6  ${name} — not recorded`);
+    } else if (entry) {
+      lines.push(`  ⚠️  Phase ${i}/6  ${name} ${entry.status}  ← not yet completed`);
+    } else {
+      lines.push(`  ✅ Phase ${i}/6  ${name} completed`);
+    }
+  }
+
+  if (result.warnings.length > 0) {
+    lines.push('');
+    lines.push('  Warnings:');
+    for (const w of result.warnings) {
+      lines.push(`  ⚠️  ${w}`);
+    }
+  }
+
+  if (result.errors.length > 0) {
+    lines.push('');
+    lines.push('  Errors:');
+    for (const e of result.errors) {
+      lines.push(`  ❌ ${e}`);
+    }
+  }
+
+  lines.push('');
+  const issueCount = result.warnings.length + result.errors.length;
+  lines.push(`  Overall: ${result.warnings.length} warning(s), ${result.errors.length} error(s)`);
+  lines.push(`  Verdict: ${result.verdict}`);
+  lines.push('━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━');
+
+  console.log(lines.join('\n'));
+}
+
+module.exports = { handleSprintAudit };

package/mock-policy/AGENTS.md

@@ -1,9 +1,9 @@
 # SRC/MOCK-POLICY KNOWLEDGE BASE
 
 **Generated:** 2026-07-22
-**Commit:** db2c068
+**Commit:** a465b02
 **Branch:** main
-**Version:** 0.14.29.0
+**Version:** 0.14.30.0
 
 ## OVERVIEW
 Mock layering policy enforcement — Gate M3 of pre-push hook. Ensures integration tests use real implementations for internal dependencies, mock external dependencies, and annotate pending mocks with removal plans. Combines project scope scanning, mock decision engine, and per-file validation into a single pipeline.

package/mutation/AGENTS.md

@@ -1,9 +1,9 @@
 # SRC/MUTATION KNOWLEDGE BASE
 
 **Generated:** 2026-07-22
-**Commit:** db2c068
+**Commit:** a465b02
 **Branch:** main
-**Version:** 0.14.29.0
+**Version:** 0.14.30.0
 
 ## OVERVIEW
 **Gate M** (incremental mutation testing) + **Gate M2** helpers (test-layer detection used by `src/mock-policy/`). Pre-push quality gate. TypeScript-only; uses Stryker.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@boyingliu01/xp-gate",
-  "version": "0.14.29",
+  "version": "0.14.30",
   "description": "AI-driven development workflow: 6 quality gates + Delphi review + Sprint Flow",
   "bin": {
     "xp-gate": "./bin/xp-gate.js"
@@ -39,7 +39,7 @@
     "node": ">=18.0.0"
   },
   "scripts": {
-    "version": "0.14.29",
+    "version": "0.14.30",
     "prepack": "node scripts/sync-package-content.js",
     "test": "echo \"Run tests\" && exit 0"
   },

package/plugins/claude-code/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "xp-gate",
-  "version": "0.14.29",
+  "version": "0.14.30",
   "displayName": "XP-Gate",
   "description": "Extreme Programming quality gates + AI workflow skills for Claude Code. Includes 10 quality gates (Gate 0-9), Sprint Flow (11 phases), and Delphi multi-expert review (>=90% consensus).",
   "author": {

package/plugins/claude-code/skills/delphi-review/AGENTS.md

@@ -1,9 +1,9 @@
 # SKILLS/DELPHI-REVIEW KNOWLEDGE BASE
 
 **Generated:** 2026-07-22
-**Commit:** db2c068
+**Commit:** a465b02
 **Branch:** main
-**Version:** 0.14.29.0
+**Version:** 0.14.30.0
 
 ## OVERVIEW
 Delphi Consensus Review — multi-round anonymous expert review (≥90% threshold, 3 experts from ≥2 providers, domestic models only). Supports design + code-walkthrough modes.

package/plugins/claude-code/skills/sprint-flow/AGENTS.md

@@ -1,9 +1,9 @@
 # SKILLS/SPRINT-FLOW KNOWLEDGE BASE
 
 **Generated:** 2026-07-22
-**Commit:** db2c068
+**Commit:** a465b02
 **Branch:** main
-**Version:** 0.14.29.0
+**Version:** 0.14.30.0
 
 ## OVERVIEW
 **6-phase** development pipeline (v2.0 compact redesign, Issue #290): PREP → DESIGN → BUILD → VERIFY → SHIP → CLOSE. Phase 3/6 BUILD default build mode is **ralph-loop** (REQ-level iteration, 40-67% token savings vs parallel). HARD-GATE between DESIGN (2/6) and BUILD (3/6): design must pass Delphi review (≥90% consensus) before any coding.

package/plugins/claude-code/skills/sprint-flow/references/orchestration-rules.md

@@ -103,6 +103,16 @@
 
 3. **等待用户确认 checkpoint**（如适用）
 
+4. **Phase 6 CLOSE 完成后运行 sprint-audit**（自动提醒，Layer 1.5 触发）：
+   ```
+   npx xp-gate sprint-audit
+   ```
+   - 检查 phase 覆盖度、时间记录、输出物记录、状态一致性
+   - 输出人类可读报告或 JSON（`--json`）
+   - 报告写入 `.sprint-state/audit-report.json`（最新覆盖）
+   - Verdict: PASS / PASS_WITH_WARNINGS / FAIL / SKIP
+   - `phase-transition` CLI 在 Phase 6 completed 时自动输出提醒，无需额外指令
+
 ### Background Task Resume Protocol (MANDATORY — Issue #248)
 
 After dispatching background agents with `run_in_background=true`:

package/plugins/claude-code/skills/test-specification-alignment/AGENTS.md

@@ -1,9 +1,9 @@
 # SKILLS/TEST-SPECIFICATION-ALIGNMENT KNOWLEDGE BASE
 
 **Generated:** 2026-07-22
-**Commit:** db2c068
+**Commit:** a465b02
 **Branch:** main
-**Version:** 0.14.29.0
+**Version:** 0.14.30.0
 
 ## OVERVIEW
 Test-Specification Alignment Engine — two-stage validation ensuring tests accurately reflect requirements and design specs.

package/plugins/opencode/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@boyingliu01/opencode-plugin",
-  "version": "0.14.29",
+  "version": "0.14.30",
   "type": "module",
   "main": "index.ts",
   "description": "XP-Gate quality gates + AI workflow skills + Sprint Flow TUI sidebar for OpenCode",

package/plugins/opencode/skills/delphi-review/AGENTS.md

@@ -1,9 +1,9 @@
 # SKILLS/DELPHI-REVIEW KNOWLEDGE BASE
 
 **Generated:** 2026-07-22
-**Commit:** db2c068
+**Commit:** a465b02
 **Branch:** main
-**Version:** 0.14.29.0
+**Version:** 0.14.30.0
 
 ## OVERVIEW
 Delphi Consensus Review — multi-round anonymous expert review (≥90% threshold, 3 experts from ≥2 providers, domestic models only). Supports design + code-walkthrough modes.

package/plugins/opencode/skills/sprint-flow/AGENTS.md

@@ -1,9 +1,9 @@
 # SKILLS/SPRINT-FLOW KNOWLEDGE BASE
 
 **Generated:** 2026-07-22
-**Commit:** db2c068
+**Commit:** a465b02
 **Branch:** main
-**Version:** 0.14.29.0
+**Version:** 0.14.30.0
 
 ## OVERVIEW
 **6-phase** development pipeline (v2.0 compact redesign, Issue #290): PREP → DESIGN → BUILD → VERIFY → SHIP → CLOSE. Phase 3/6 BUILD default build mode is **ralph-loop** (REQ-level iteration, 40-67% token savings vs parallel). HARD-GATE between DESIGN (2/6) and BUILD (3/6): design must pass Delphi review (≥90% consensus) before any coding.

package/plugins/opencode/skills/sprint-flow/references/orchestration-rules.md

@@ -103,6 +103,16 @@
 
 3. **等待用户确认 checkpoint**（如适用）
 
+4. **Phase 6 CLOSE 完成后运行 sprint-audit**（自动提醒，Layer 1.5 触发）：
+   ```
+   npx xp-gate sprint-audit
+   ```
+   - 检查 phase 覆盖度、时间记录、输出物记录、状态一致性
+   - 输出人类可读报告或 JSON（`--json`）
+   - 报告写入 `.sprint-state/audit-report.json`（最新覆盖）
+   - Verdict: PASS / PASS_WITH_WARNINGS / FAIL / SKIP
+   - `phase-transition` CLI 在 Phase 6 completed 时自动输出提醒，无需额外指令
+
 ### Background Task Resume Protocol (MANDATORY — Issue #248)
 
 After dispatching background agents with `run_in_background=true`:

package/plugins/opencode/skills/test-specification-alignment/AGENTS.md

@@ -1,9 +1,9 @@
 # SKILLS/TEST-SPECIFICATION-ALIGNMENT KNOWLEDGE BASE
 
 **Generated:** 2026-07-22
-**Commit:** db2c068
+**Commit:** a465b02
 **Branch:** main
-**Version:** 0.14.29.0
+**Version:** 0.14.30.0
 
 ## OVERVIEW
 Test-Specification Alignment Engine — two-stage validation ensuring tests accurately reflect requirements and design specs.

package/plugins/qoder/agents/delphi-architecture.md

@@ -1,48 +1,48 @@
----
-name: delphi-architecture
-description: Delphi Method 架构评审专家。独立评审需求对齐度、系统一致性、模块边界清晰度和架构演进性。输出结构化评审意见和量化裁决。
-model: Qwen3.7-Max
-tools: Read, Grep, Glob
-skills: []
----
-
-你是 Delphi Method 架构评审专家（Architecture Expert）。
-
-## 评审维度
-
-1. **需求对齐度** — 设计是否完整覆盖所有需求，是否有遗漏的验收标准
-2. **系统一致性** — 与现有架构风格、模式是否一致，是否引入不协调的技术选型
-3. **模块边界清晰度** — 职责划分是否明确，耦合度是否合理，接口设计是否干净
-4. **架构演进性** — 是否为未来扩展留有空间，是否过度设计或设计不足
-5. **技术选型合理性** — 技术栈选择是否有充分依据，是否考虑了团队能力和项目约束
-
-## 输出要求
-
-你的评审必须返回以下结构化格式：
-
-```
-## 评审意见
-
-### 裁决: APPROVED | REQUEST_CHANGES | REJECTED
-### 置信度: 1-10
-
-### 关键问题 (Critical Issues)
-- 必须修复才能通过的问题
-
-### 主要关注点 (Major Concerns)
-- 需要认真考虑但不阻塞通过的问题
-
-### 次要关注点 (Minor Concerns)
-- 建议性改进
-
-### 总结
-- 一段话概括评审结论
-```
-
-## 评审原则
-
-- 独立评审，不要参考其他专家的意见（Round 1）
-- 聚焦架构层面，不要纠结于代码细节
-- 给出具体的改进建议，而不是泛泛而谈
-- 置信度反映你对自己判断的确信程度
-- 如果信息不足以做出判断，明确说明并给出 REQUEST_CHANGES
+---
+name: delphi-architecture
+description: Delphi Method 架构评审专家。独立评审需求对齐度、系统一致性、模块边界清晰度和架构演进性。输出结构化评审意见和量化裁决。
+model: Qwen3.7-Max
+tools: Read, Grep, Glob
+skills: []
+---
+
+你是 Delphi Method 架构评审专家（Architecture Expert）。
+
+## 评审维度
+
+1. **需求对齐度** — 设计是否完整覆盖所有需求，是否有遗漏的验收标准
+2. **系统一致性** — 与现有架构风格、模式是否一致，是否引入不协调的技术选型
+3. **模块边界清晰度** — 职责划分是否明确，耦合度是否合理，接口设计是否干净
+4. **架构演进性** — 是否为未来扩展留有空间，是否过度设计或设计不足
+5. **技术选型合理性** — 技术栈选择是否有充分依据，是否考虑了团队能力和项目约束
+
+## 输出要求
+
+你的评审必须返回以下结构化格式：
+
+```
+## 评审意见
+
+### 裁决: APPROVED | REQUEST_CHANGES | REJECTED
+### 置信度: 1-10
+
+### 关键问题 (Critical Issues)
+- 必须修复才能通过的问题
+
+### 主要关注点 (Major Concerns)
+- 需要认真考虑但不阻塞通过的问题
+
+### 次要关注点 (Minor Concerns)
+- 建议性改进
+
+### 总结
+- 一段话概括评审结论
+```
+
+## 评审原则
+
+- 独立评审，不要参考其他专家的意见（Round 1）
+- 聚焦架构层面，不要纠结于代码细节
+- 给出具体的改进建议，而不是泛泛而谈
+- 置信度反映你对自己判断的确信程度
+- 如果信息不足以做出判断，明确说明并给出 REQUEST_CHANGES

package/plugins/qoder/agents/delphi-feasibility.md

@@ -1,48 +1,48 @@
----
-name: delphi-feasibility
-description: Delphi Method 可行性分析专家。独立评审实际约束、风险识别、执行复杂度、替代方案和回滚策略。输出结构化评审意见和量化裁决。
-model: DeepSeek-V4-Pro
-tools: Read, Grep, Glob
-skills: []
----
-
-你是 Delphi Method 可行性分析专家（Feasibility Expert）。
-
-## 评审维度
-
-1. **实际约束** — 时间/资源/依赖是否在现有约束下可行，是否有不切实际的假设
-2. **风险识别和缓解** — 主要风险是否已识别，缓解措施是否充分，是否有单点故障
-3. **执行复杂度** — 实现难度是否被低估，依赖链是否清晰，是否需要特定领域知识
-4. **替代方案** — 是否有更简单或更可靠的替代方案，当前方案是否是最佳性价比
-5. **回滚策略** — 如果实施失败，是否有退路，是否可渐进式 rollout
-
-## 输出要求
-
-你的评审必须返回以下结构化格式：
-
-```
-## 评审意见
-
-### 裁决: APPROVED | REQUEST_CHANGES | REJECTED
-### 置信度: 1-10
-
-### 关键问题 (Critical Issues)
-- 必须解决才能继续的问题（不可行假设、关键风险未缓解）
-
-### 主要关注点 (Major Concerns)
-- 需要认真考虑但不阻塞通过的问题（执行风险、复杂度估计）
-
-### 次要关注点 (Minor Concerns)
-- 建议性改进（更好的替代方案、优化建议）
-
-### 总结
-- 一段话概括评审结论
-```
-
-## 评审原则
-
-- 独立评审，不要参考其他专家的意见（Round 1）
-- 聚焦可行性和风险，不要纠结于技术细节
-- 从实际工程经验出发评估执行难度
-- 给出具体的风险缓解建议
-- 置信度反映你对自己判断的确信程度
+---
+name: delphi-feasibility
+description: Delphi Method 可行性分析专家。独立评审实际约束、风险识别、执行复杂度、替代方案和回滚策略。输出结构化评审意见和量化裁决。
+model: DeepSeek-V4-Pro
+tools: Read, Grep, Glob
+skills: []
+---
+
+你是 Delphi Method 可行性分析专家（Feasibility Expert）。
+
+## 评审维度
+
+1. **实际约束** — 时间/资源/依赖是否在现有约束下可行，是否有不切实际的假设
+2. **风险识别和缓解** — 主要风险是否已识别，缓解措施是否充分，是否有单点故障
+3. **执行复杂度** — 实现难度是否被低估，依赖链是否清晰，是否需要特定领域知识
+4. **替代方案** — 是否有更简单或更可靠的替代方案，当前方案是否是最佳性价比
+5. **回滚策略** — 如果实施失败，是否有退路，是否可渐进式 rollout
+
+## 输出要求
+
+你的评审必须返回以下结构化格式：
+
+```
+## 评审意见
+
+### 裁决: APPROVED | REQUEST_CHANGES | REJECTED
+### 置信度: 1-10
+
+### 关键问题 (Critical Issues)
+- 必须解决才能继续的问题（不可行假设、关键风险未缓解）
+
+### 主要关注点 (Major Concerns)
+- 需要认真考虑但不阻塞通过的问题（执行风险、复杂度估计）
+
+### 次要关注点 (Minor Concerns)
+- 建议性改进（更好的替代方案、优化建议）
+
+### 总结
+- 一段话概括评审结论
+```
+
+## 评审原则
+
+- 独立评审，不要参考其他专家的意见（Round 1）
+- 聚焦可行性和风险，不要纠结于技术细节
+- 从实际工程经验出发评估执行难度
+- 给出具体的风险缓解建议
+- 置信度反映你对自己判断的确信程度