@boyingliu01/xp-gate 0.10.11 → 0.10.12

package/lib/__tests__/check-version.test.js

@@ -180,11 +180,11 @@ describe('check-version.js — REQ-001-01', () => {
     }
 
     function withMockedHttps(latestVersion, fn) {
-      const fs = require('fs');
-      const os = require('os');
-      const cpPath = require('path').join(os.homedir(), '.xp-gate', 'version-cache.json');
-      if (fs.existsSync(cpPath)) {
-        try { fs.unlinkSync(cpPath); } catch { }
+      const fsm = require('fs');
+      const osm = require('os');
+      const cpPath = require('path').join(osm.homedir(), '.xp-gate', 'version-cache.json');
+      if (fsm.existsSync(cpPath)) {
+        try { fsm.unlinkSync(cpPath); } catch { }
       }
       evictCache();
       const https = require('https');
@@ -204,11 +204,25 @@ describe('check-version.js — REQ-001-01', () => {
         callback(mockRes);
         return { on: () => undefined, destroy: () => undefined };
       };
+      // Mock getLocalVersion to return a fixed version so tests don't
+      // depend on the real package.json version (which drifts over time).
+      const savedReadFileSync = fsm.readFileSync;
+      const pkgJsonDir = require('path').join(
+        require('path').dirname(require.resolve('../check-version')),
+        '..'
+      );
+      fsm.readFileSync = (...args) => {
+        if (String(args[0]).endsWith('package.json') && String(args[0]) === require('path').join(pkgJsonDir, 'package.json')) {
+          return JSON.stringify({ name: '@boyingliu01/xp-gate', version: '0.8.21' });
+        }
+        return savedReadFileSync.apply(fsm, args);
+      };
       try {
         const m = require('../check-version');
         return fn(m);
       } finally {
         https.get = saved;
+        fsm.readFileSync = savedReadFileSync;
       }
     }
 

package/lib/__tests__/install-skill.test.js

@@ -192,7 +192,7 @@ describe('install-skill', () => {
     const result = await installSkill('sprint-flow');
 
     expect(result).toBe(1);
-    expect(console.error).toHaveBeenCalledWith('Error: sprint-flow is already installed');
+    expect(console.error).toHaveBeenCalledWith('Error: sprint-flow is already installed\nUse --force to overwrite');
   });
 
   it('backs up and replaces when target exists and force=true', async () => {

package/mock-policy/AGENTS.md

@@ -1,9 +1,9 @@
 # SRC/MOCK-POLICY KNOWLEDGE BASE
 
-**Generated:** 2026-06-23
-**Commit:** bac916f
+**Generated:** 2026-06-24
+**Commit:** f8338d6
 **Branch:** main
-**Version:** 0.10.11.0
+**Version:** 0.10.12.0
 
 ## 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:** 2026-06-23
-**Commit:** bac916f
+**Generated:** 2026-06-24
+**Commit:** f8338d6
 **Branch:** main
-**Version:** 0.10.11.0
+**Version:** 0.10.12.0
 
 ## 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": "0.10.11",
+  "version": "0.10.12",
   "description": "AI-driven development workflow: 6 quality gates + Delphi review + Sprint Flow",
   "bin": {
     "xp-gate": "./bin/xp-gate.js"

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

@@ -1,6 +1,6 @@
 {
   "name": "xp-gate",
-  "version": "0.10.11",
+  "version": "0.10.12",
   "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:** 2026-06-23
-**Commit:** bac916f
+**Generated:** 2026-06-24
+**Commit:** f8338d6
 **Branch:** main
-**Version:** 0.10.11.0
+**Version:** 0.10.12.0
 
 ## 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:** 2026-06-23
-**Commit:** bac916f
+**Generated:** 2026-06-24
+**Commit:** f8338d6
 **Branch:** main
-**Version:** 0.10.11.0
+**Version:** 0.10.12.0
 
 ## OVERVIEW
 **11-phase** development pipeline: ISOLATE → AUTO-ESTIMATE → THINK → PLAN → BUILD → REVIEW → USER ACCEPTANCE → FEEDBACK → SHIP → LAND → CLEANUP. Phase 2 default build mode is **ralph-loop** (REQ-level iteration, 40-67% token savings vs parallel). HARD-GATE in Phase 1: design must pass Delphi review (≥90% consensus) before any coding.

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

@@ -237,11 +237,11 @@ Sprint Flow: ISOLATE → AUTO-ESTIMATE → THINK → PLAN → BUILD → REVIEW
 - **HARD-GATE**: 设计未批准 → 不可进入实现
 
 ### Phase 1: PLAN（共识评审）
-- **注意**: `autoplan` 和 `to-issues` 是交互式 skill，**必须由 orchestrator 直接执行**（Issue #225, #248）
-- **执行模式（三阶段）**:
+- **注意**: `autoplan`、`delphi-review` 和 `to-issues` 均为交互式 skill，**必须由 orchestrator 直接执行**（Issue #225, #248, #249）
+- **执行模式（三阶段，全部 orchestrator 直接执行）**:
   1. **Orchestrator 直接执行 autoplan**: `skill(name="autoplan")` → 用户确认 taste_decisions
-  2. **Orchestrator 直接执行 to-issues**: `skill(name="to-issues")` → 用户确认 Issue 拆分方案
-  3. **Subagent 执行 delphi-review**: `task(category="deep", load_skills=["delphi-review"])` — 非交互式，可自动运行至 APPROVED
+  2. **Orchestrator 直接执行 delphi-review**: `skill(name="delphi-review")` — 等待 APPROVED（非 APPROVED 时需等待用户确认/处理）
+  3. **Orchestrator 直接执行 to-issues**: `skill(name="to-issues")` → 用户确认 Issue 拆分方案
 - 输入: phase-0-summary.md + 设计文档
 - 输出: `specification.yaml`（含 user_stories[]）+ `slices-manifest.json`
 
@@ -276,13 +276,10 @@ Sprint Flow: ISOLATE → AUTO-ESTIMATE → THINK → PLAN → BUILD → REVIEW
 5. **Mock Minimization**: integration-first, mock 仅限 external services, 密度 > 30% 需 `@mock-justified`
 
 ### Phase 3: REVIEW + TEST（验证）
-- **Subagent dispatch**: orchestrator 通过 `task(category="deep", load_skills=["delphi-review", "test-specification-alignment"])` 启动独立 session
+- **Orchestrator 直接执行**: delphi-review code-walkthrough 需要用户确认 verdict（Issue #249），**必须由 orchestrator 直接调用** `skill(name="delphi-review")`
+- **Orchestrator 按序执行**: `delphi-review --mode code-walkthrough` → 等待 APPROVED → `test-specification-alignment` → `browse` (gstack) → 可选 `qa`/`design-review`/`benchmark` (gstack)
 - 输入: phase-2-summary.md + MVP 代码
 - 输出: 评审报告 + 测试对齐结果
-- `delphi-review --mode code-walkthrough` — 多专家匿名代码走查
-- `test-specification-alignment` — 测试与 Spec 对齐验证
-- `browse` (gstack) — 浏览器自动化测试
-- `k6` / `locust` / `gatling` — 负载/压力测试（可选，后端项目）
 
 ### 负载/压力测试（可选）
 - **适用项目**：主要用于后端服务的压力测试 (k6/Locust/Gatling)，Web 前端已有 `benchmark` 技能覆盖 Core Web Vitals、加载时间和资源大小等性能指标

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

@@ -31,9 +31,9 @@
 | -1 | ISOLATE | ❌ | Bash（直接执行） | 无 | orchestrator |
 | -0.5 | AUTO-ESTIMATE | ❌ | Bash（直接执行） | 无 | orchestrator |
 | 0 | THINK | ❌ | orchestrator（直接执行） | `["brainstorming"]` | orchestrator |
-| 1 | PLAN | ⚠️ | orchestrator 执行 autoplan + to-issues（交互）→ subagent 执行 delphi-review | 见下方说明 | orchestrator + subagent |
+| 1 | PLAN | ❌ | orchestrator（直接执行） | `["autoplan", "delphi-review", "to-issues"]` | orchestrator |
 | 2 | BUILD | ✅ | ralph-loop | `["test-driven-development"]` | subagent |
-| 3 | REVIEW | ✅ | `deep` | `["delphi-review", "test-specification-alignment"]` | subagent |
+| 3 | REVIEW | ❌ | orchestrator（直接执行） | `["delphi-review", "test-specification-alignment"]` | orchestrator |
 | 4 | USER ACCEPT | ❌ | **强制人工** | 无 | 用户 |
 | 5 | FEEDBACK | ✅ | `quick` | `["learn", "retro", "systematic-debugging"]` | subagent |
 | 6 | SHIP | ❌ | orchestrator（直接执行） | `["finishing-a-development-branch", "ship"]` | orchestrator |
@@ -46,15 +46,17 @@
 |-------|-------|---------------------------|
 | 0 | `brainstorming` | 需要与用户对话确认需求、提出澄清问题。Subagent 是 fire-and-forget 模式，无法暂停等待用户输入（Issue #217） |
 | 1 | `autoplan` | taste_decisions 节点暂停等待用户确认。必须由 orchestrator 直接执行（Issue #225） |
+| 1 | `delphi-review` | design 模式需等待 verdict APPROVED；非 APPROVED 时需用户确认是否接受分歧方案（Issue #249） |
 | 1 | `to-issues` | Step 6 "向用户确认" — 展示拆分结果，等待用户批准后才生成 slices-manifest.json |
+| 3 | `delphi-review --mode code-walkthrough` | Code walkthrough 非 APPROVED 时需暂停等待用户处理 Critical Issues（Issue #249） |
 | 6 | `finishing-a-development-branch` | 4 选项菜单 (merge/PR/keep/discard) 需要用户选择；Option 4 (discard) 要求 typed confirmation |
 | 6 | `ship` | PR 创建前需要用户确认；包含 AskUserQuestion STOP 点 |
 | 7 | `land-and-deploy` | Merge 确认、rollback 决策 — 均为用户交互点 |
 
-**Phase 1 执行模式（两阶段）**：
+**Phase 1 执行模式（全部 orchestrator 直接执行）**：
 1. **Orchestrator 直接执行 autoplan**：`skill(name="autoplan")` → 等待用户确认 taste_decisions
-2. **Orchestrator 直接执行 to-issues**：`skill(name="to-issues")` → 等待用户确认 Issue 拆分
-3. **Subagent 执行 delphi-review**：`task(category="deep", load_skills=["delphi-review"])` — 非交互式，可自动运行至 APPROVED
+2. **Orchestrator 直接执行 delphi-review**：`skill(name="delphi-review")` → 等待 APPROVED（非 APPROVED 时暂停等待用户确认）
+3. **Orchestrator 直接执行 to-issues**：`skill(name="to-issues")` → 等待用户确认 Issue 拆分
 
 **上下文隔离原则**：
 - 每个 Subagent 在**独立 session** 中启动，不继承 orchestrator 的对话历史
@@ -71,7 +73,7 @@
 | Phase 0 | phase--1-summary（仅路径） | 隔离环境信息（worktree 路径） |
 | Phase 1 | phase-0-summary.md + design-doc | 设计决策 + 结构化规格 |
 | Phase 2 | phase-1-summary.md + specification.yaml | 评审结论 + REQ 列表 |
-| Phase 3 | phase-2-summary.md + MVP 代码 | 构建结果 |
+| Phase 3 | phase-2-summary.md + MVP 代码 | 构建结果（orchestrator 直接执行，无 subagent 上下文继承） |
 | Phase 4 | — | **人工验收**。Phase 4 不产生 subagent summary，但用户验收结果记录在 `.sprint-state/phase-outputs/emergent-issues.md`（如有 emergent issues）。Phase 5 加载此文件。 |
 | Phase 5 | phase-4-summary.md + emergent-issues.md | 验收结论 |
 | Phase 6 | phase-5-summary.md + feedback-log.md | 复盘结论 |

package/plugins/claude-code/skills/sprint-flow/references/phase-1-plan.md

@@ -105,7 +105,7 @@ Decision 2: [决策描述]
 
 ---
 
-### Step 2b: 调用 delphi-review（强制）
+### Step 2b: 调用 delphi-review（强制，orchestrator 直接执行）
 
 ```bash
 skill(name="delphi-review", user_message="[设计文档 + taste_decisions 确认结果]")
@@ -117,7 +117,7 @@ delphi-review 执行：
 - 输出: APPROVED / REQUEST_CHANGES
 
 **如果 REQUEST_CHANGES**:
-- ⚠️ 暂停等待用户修复
+- ⚠️ 暂停等待用户处理（orchestrator 直接执行，可交互确认）
 - 修复后重新评审（从 Round 2 起步）
 - 直到 APPROVED
 

package/plugins/claude-code/skills/sprint-flow/references/phase-3-review.md

@@ -4,6 +4,8 @@
 
 多专家代码走查、测试对齐、浏览器测试。确保 MVP 符合 specification。
 
+**执行者**: orchestrator 直接执行全部步骤（非 subagent dispatch）— Issue #249。
+
 Web 前端项目额外增加：系统化 QA、视觉审计、性能基线。
 
 ---
@@ -46,7 +48,7 @@ delphi code-walkthrough 执行：
 - ≥90% 共识 + APPROVED 才通过
 
 **如果 REQUEST_CHANGES**:
-- ⚠️ 暂停等待用户修复 Critical Issues + 处理 Major Concerns
+- ⚠️ 暂停等待用户处理 Critical Issues + Major Concerns（orchestrator 直接执行，可交互）
 - 修复后回到 Round 2 重新评审
 
 **如果 APPROVED**:

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

@@ -1,9 +1,9 @@
 # SKILLS/TEST-SPECIFICATION-ALIGNMENT KNOWLEDGE BASE
 
-**Generated:** 2026-06-23
-**Commit:** bac916f
+**Generated:** 2026-06-24
+**Commit:** f8338d6
 **Branch:** main
-**Version:** 0.10.11.0
+**Version:** 0.10.12.0
 
 ## OVERVIEW
 Test-Specification Alignment Engine — two-stage validation ensuring tests accurately reflect requirements and design specs.