@boyingliu01/xp-gate 0.10.11 → 0.10.12

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (44) hide show
  1. package/lib/__tests__/check-version.test.js +19 -5
  2. package/lib/__tests__/install-skill.test.js +1 -1
  3. package/mock-policy/AGENTS.md +3 -3
  4. package/mutation/AGENTS.md +3 -3
  5. package/package.json +1 -1
  6. package/plugins/claude-code/.claude-plugin/plugin.json +1 -1
  7. package/plugins/claude-code/skills/delphi-review/AGENTS.md +3 -3
  8. package/plugins/claude-code/skills/sprint-flow/AGENTS.md +3 -3
  9. package/plugins/claude-code/skills/sprint-flow/SKILL.md +6 -9
  10. package/plugins/claude-code/skills/sprint-flow/references/orchestration-rules.md +8 -6
  11. package/plugins/claude-code/skills/sprint-flow/references/phase-1-plan.md +2 -2
  12. package/plugins/claude-code/skills/sprint-flow/references/phase-3-review.md +3 -1
  13. package/plugins/claude-code/skills/test-specification-alignment/AGENTS.md +3 -3
  14. package/plugins/opencode/__tests__/xp-gate-e2e-upgrade.test.ts +562 -0
  15. package/plugins/opencode/package.json +1 -1
  16. package/plugins/opencode/skills/delphi-review/AGENTS.md +3 -3
  17. package/plugins/opencode/skills/sprint-flow/AGENTS.md +3 -3
  18. package/plugins/opencode/skills/sprint-flow/SKILL.md +6 -9
  19. package/plugins/opencode/skills/sprint-flow/references/orchestration-rules.md +8 -6
  20. package/plugins/opencode/skills/sprint-flow/references/phase-1-plan.md +2 -2
  21. package/plugins/opencode/skills/sprint-flow/references/phase-3-review.md +3 -1
  22. package/plugins/opencode/skills/test-specification-alignment/AGENTS.md +3 -3
  23. package/plugins/qoder/plugin.json +1 -1
  24. package/plugins/qoder/skills/delphi-review/AGENTS.md +3 -3
  25. package/plugins/qoder/skills/sprint-flow/AGENTS.md +3 -3
  26. package/plugins/qoder/skills/sprint-flow/SKILL.md +191 -1088
  27. package/plugins/qoder/skills/sprint-flow/references/orchestration-rules.md +365 -0
  28. package/plugins/qoder/skills/sprint-flow/references/phase-1-plan.md +2 -2
  29. package/plugins/qoder/skills/sprint-flow/references/phase-2-build.md +25 -180
  30. package/plugins/qoder/skills/sprint-flow/references/phase-3-review.md +3 -1
  31. package/plugins/qoder/skills/sprint-flow/references/phase-6-ship.md +4 -188
  32. package/plugins/qoder/skills/sprint-flow/references/phase-7-land.md +4 -135
  33. package/plugins/qoder/skills/sprint-flow/references/phase-8-cleanup.md +4 -187
  34. package/plugins/qoder/skills/sprint-flow/references/phase-minus-0-5-auto-estimate.md +6 -0
  35. package/plugins/qoder/skills/sprint-flow/references/phase-minus-1-isolate.md +58 -0
  36. package/plugins/qoder/skills/test-specification-alignment/AGENTS.md +3 -3
  37. package/principles/AGENTS.md +3 -3
  38. package/skills/delphi-review/AGENTS.md +3 -3
  39. package/skills/sprint-flow/AGENTS.md +3 -3
  40. package/skills/sprint-flow/SKILL.md +6 -9
  41. package/skills/sprint-flow/references/orchestration-rules.md +8 -6
  42. package/skills/sprint-flow/references/phase-1-plan.md +2 -2
  43. package/skills/sprint-flow/references/phase-3-review.md +3 -1
  44. package/skills/test-specification-alignment/AGENTS.md +3 -3
@@ -105,7 +105,7 @@ Decision 2: [决策描述]
105
105
 
106
106
  ---
107
107
 
108
- ### Step 2b: 调用 delphi-review(强制)
108
+ ### Step 2b: 调用 delphi-review(强制,orchestrator 直接执行)
109
109
 
110
110
  ```bash
111
111
  skill(name="delphi-review", user_message="[设计文档 + taste_decisions 确认结果]")
@@ -117,7 +117,7 @@ delphi-review 执行:
117
117
  - 输出: APPROVED / REQUEST_CHANGES
118
118
 
119
119
  **如果 REQUEST_CHANGES**:
120
- - ⚠️ 暂停等待用户修复
120
+ - ⚠️ 暂停等待用户处理(orchestrator 直接执行,可交互确认)
121
121
  - 修复后重新评审(从 Round 2 起步)
122
122
  - 直到 APPROVED
123
123
 
@@ -4,6 +4,8 @@
4
4
 
5
5
  多专家代码走查、测试对齐、浏览器测试。确保 MVP 符合 specification。
6
6
 
7
+ **执行者**: orchestrator 直接执行全部步骤(非 subagent dispatch)— Issue #249。
8
+
7
9
  Web 前端项目额外增加:系统化 QA、视觉审计、性能基线。
8
10
 
9
11
  ---
@@ -46,7 +48,7 @@ delphi code-walkthrough 执行:
46
48
  - ≥90% 共识 + APPROVED 才通过
47
49
 
48
50
  **如果 REQUEST_CHANGES**:
49
- - ⚠️ 暂停等待用户修复 Critical Issues + 处理 Major Concerns
51
+ - ⚠️ 暂停等待用户处理 Critical Issues + Major Concerns(orchestrator 直接执行,可交互)
50
52
  - 修复后回到 Round 2 重新评审
51
53
 
52
54
  **如果 APPROVED**:
@@ -1,9 +1,9 @@
1
1
  # SKILLS/TEST-SPECIFICATION-ALIGNMENT KNOWLEDGE BASE
2
2
 
3
- **Generated:** 2026-06-23
4
- **Commit:** bac916f
3
+ **Generated:** 2026-06-24
4
+ **Commit:** f8338d6
5
5
  **Branch:** main
6
- **Version:** 0.10.11.0
6
+ **Version:** 0.10.12.0
7
7
 
8
8
  ## OVERVIEW
9
9
  Test-Specification Alignment Engine — two-stage validation ensuring tests accurately reflect requirements and design specs.
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "xp-gate",
3
- "version": "0.10.11",
3
+ "version": "0.10.12",
4
4
  "displayName": "XP-Gate",
5
5
  "description": "Extreme Programming quality gates + AI workflow skills for Qoder. Includes 10 quality gates (Gate 0-9), Sprint Flow (11 phases), and Delphi multi-expert review (>=90% consensus).",
6
6
  "author": {
@@ -1,9 +1,9 @@
1
1
  # SKILLS/DELPHI-REVIEW KNOWLEDGE BASE
2
2
 
3
- **Generated:** 2026-06-23
4
- **Commit:** bac916f
3
+ **Generated:** 2026-06-24
4
+ **Commit:** f8338d6
5
5
  **Branch:** main
6
- **Version:** 0.10.11.0
6
+ **Version:** 0.10.12.0
7
7
 
8
8
  ## OVERVIEW
9
9
  Delphi Consensus Review — multi-round anonymous expert review (≥90% threshold, 3 experts from ≥2 providers, domestic models only). Supports design + code-walkthrough modes.
@@ -1,9 +1,9 @@
1
1
  # SKILLS/SPRINT-FLOW KNOWLEDGE BASE
2
2
 
3
- **Generated:** 2026-06-23
4
- **Commit:** bac916f
3
+ **Generated:** 2026-06-24
4
+ **Commit:** f8338d6
5
5
  **Branch:** main
6
- **Version:** 0.10.11.0
6
+ **Version:** 0.10.12.0
7
7
 
8
8
  ## OVERVIEW
9
9
  **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.