@boyingliu01/xp-gate 0.12.13 → 0.13.0

package/plugins/qoder/skills/sprint-flow/templates/sprint-summary-template.md

@@ -2,7 +2,7 @@
 
 ## 使用说明
 
-此模板用于 Phase 6 (SHIP) 结束时生成 Sprint 总结。
+此模板用于 Phase 6/6 CLOSE 结束时生成 Sprint 总结。
 
 ---
 
@@ -25,13 +25,12 @@ MVP 版本: v1.0
 
 | Phase | 耗时 | 状态 | 暂停次数 | 备注 |
 |-------|------|------|---------|------|
-| Phase 0: THINK | [X min] | ✅ 完成 | 0 | [备注] |
-| Phase 1: PLAN | [X min] | ✅ 完成 | [N] | [备注] |
-| Phase 2: BUILD | [X min] | ✅ 完成 | [N] | [备注] |
-| Phase 3: REVIEW | [X min] | ✅ 完成 | [N] | [备注] |
-| Phase 4: UAT | [X min] | ✅ 完成 | 1 (必须) | [备注] |
-| Phase 5: FEEDBACK | [X min] | ✅ 完成 | 0 | [备注] |
-| Phase 6: SHIP | [X min] | ✅ 完成 | [N] | [备注] |
+| 1/6: PREP | [X min] | ✅ 完成 | 0 | worktree + 规模评估 |
+| 2/6: DESIGN | [X min] | ✅ 完成 | [N] | brainstorming + delphi-review |
+| 3/6: BUILD | [X min] | ✅ 完成 | [N] | ralph-loop + TDD |
+| 4/6: VERIFY | [X min] | ✅ 完成 | [N] | code-walkthrough + QA + feedback |
+| 5/6: SHIP | [X min] | ✅ 完成 | [N] | PR + deploy + canary |
+| 6/6: CLOSE | [X min] | ✅ 完成 | 1 (UAT 必须) | 人工验收 + cleanup |
 
 ---
 
@@ -39,16 +38,18 @@ MVP 版本: v1.0
 
 | Skill | 调用次数 | 结果 | 备注 |
 |-------|---------|------|------|
-| office-hours | 1 | ✅ | Pain Document 生成 |
+| brainstorming | 1 | ✅ | design doc |
 | autoplan | 1 | ✅/⚠️ | [taste_decisions 数量] |
-| delphi-review | [N] rounds | ✅ APPROVED | [Round 数量] |
-| specification.yaml | 1 | ✅ | specification.yaml |
-| BUILD (TDD + review) | 1 | ✅ APPROVED | [Gate 1 失败次数] |
-| test-driven-development | [N] | ✅ | [BUILD (TDD + review) 内部调用] |
-| cross-model-review | [N] rounds | ✅ APPROVED | [Round 数量] |
+| delphi-review (design) | [N] rounds | ✅ APPROVED | [Round 数量] |
+| delphi-review (code-walkthrough) | [N] rounds | ✅ APPROVED | [Round 数量] |
+| to-issues | 1 | ✅ | slices-manifest.json |
+| test-driven-development | [N] | ✅ | BUILD 内部调用 |
 | test-specification-alignment | 1 | ✅ | [覆盖率] |
 | browse | 1 | ✅ | [QA 通过] |
+| qa (web) | 1 | ✅ | [health score] |
+| benchmark (web) | 1 | ✅ | [perf baseline] |
 | learn | 1 | ✅ | [记录数量] |
+| retro | 1 | ✅ | Sprint 回顾 |
 | ship | 1 | ✅ | [PR URL] |
 | land-and-deploy | 1 | ✅ | [部署 URL] |
 | canary | 1 | ✅ | [监控正常] |
@@ -117,4 +118,4 @@ Minor Issues (可选纳入):
 ---
 
 **Sprint 结束时间**: YYYY-MM-DD HH:MM:SS
-**报告生成人**: sprint-flow skill
+**报告生成人**: sprint-flow skill

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

@@ -1,9 +1,9 @@
 # SKILLS/TEST-SPECIFICATION-ALIGNMENT KNOWLEDGE BASE
 
-**Generated:** 2026-07-07
-**Commit:** 897f8eb
-**Branch:** main
-**Version:** 0.12.13.0
+**Generated:** 2026-07-08
+**Commit:** 6f868ee
+**Branch:** sprint/2026-07-07-01
+**Version:** 0.13.0.0
 
 ## OVERVIEW
 Test-Specification Alignment Engine — two-stage validation ensuring tests accurately reflect requirements and design specs.

package/principles/AGENTS.md

@@ -1,9 +1,9 @@
 # PRINCIPLES CHECKER MODULE
 
-**Generated:** 2026-07-07
-**Commit:** 897f8eb
-**Branch:** main
-**Version:** 0.12.13.0
+**Generated:** 2026-07-08
+**Commit:** 6f868ee
+**Branch:** sprint/2026-07-07-01
+**Version:** 0.13.0.0
 
 ## OVERVIEW
 Clean Code & SOLID principles checker — **Gate 4** of pre-commit. 14 rules × 9 language adapters, SARIF 2.1.0 output. Houses the **Boy Scout Rule** enforcement engine (Gate 6) and warning-baseline storage.

package/principles/lint-baseline.ts

@@ -290,58 +290,47 @@ export interface LintDeltaResult {
  * Compare current lint state against a baseline entry for a single file.
  * Used by the pre-commit hook to determine if new lint errors were introduced.
  */
+function countErrors(entry: BaselineEntry): number {
+  return (entry.eslint?.errors || 0) +
+    (entry.ruff?.errors || 0) +
+    (entry.golangci?.errors || 0) +
+    (entry.shellcheck?.errors || 0);
+}
+
+function deltaPass(reduction: number, message: string): LintDeltaResult {
+  return { enforcement: 'PASS', newWarnings: 0, newErrors: 0, reduction, message };
+}
+
+function deltaBlock(warnings: number, errors: number, message: string): LintDeltaResult {
+  return { enforcement: 'BLOCK', newWarnings: warnings, newErrors: errors, reduction: 0, message };
+}
+
 export function computeLintDelta(
   baseline: BaselineEntry | null,
   current: BaselineEntry,
 ): LintDeltaResult {
   if (!baseline) {
-    return {
-      enforcement: 'PASS',
-      newWarnings: 0,
-      newErrors: 0,
-      reduction: 0,
-      message: 'New file — baseline created. No comparison needed.',
-    };
+    return deltaPass(0, 'New file — baseline created. No comparison needed.');
   }
 
   const oldW = baseline.totalWarnings;
-  const oldE = (baseline.eslint?.errors || 0) +
-    (baseline.ruff?.errors || 0) +
-    (baseline.golangci?.errors || 0) +
-    (baseline.shellcheck?.errors || 0);
+  const oldE = countErrors(baseline);
   const newW = current.totalWarnings;
-  const newE = (current.eslint?.errors || 0) +
-    (current.ruff?.errors || 0) +
-    (current.golangci?.errors || 0) +
-    (current.shellcheck?.errors || 0);
+  const newE = countErrors(current);
 
   if (newW > oldW) {
-    return {
-      enforcement: 'BLOCK',
-      newWarnings: newW - oldW,
-      newErrors: newE > oldE ? newE - oldE : 0,
-      reduction: 0,
-      message: `Lint debt increased by ${newW - oldW} warnings (${oldW} → ${newW}). Fix new errors before committing.`,
-    };
+    const delta = newW - oldW;
+    return deltaBlock(delta, newE > oldE ? newE - oldE : 0,
+      `Lint debt increased by ${delta} warnings (${oldW} → ${newW}). Fix new errors before committing.`);
   }
 
   if (newW < oldW) {
-    return {
-      enforcement: 'PASS',
-      newWarnings: 0,
-      newErrors: 0,
-      reduction: oldW - newW,
-      message: `Lint debt reduced by ${oldW - newW} warnings (${oldW} → ${newW}). Good job!`,
-    };
+    const delta = oldW - newW;
+    return deltaPass(delta,
+      `Lint debt reduced by ${delta} warnings (${oldW} → ${newW}). Good job!`);
   }
 
-  return {
-    enforcement: 'PASS',
-    newWarnings: 0,
-    newErrors: 0,
-    reduction: 0,
-    message: 'No change in lint debt.',
-  };
+  return deltaPass(0, 'No change in lint debt.');
 }
 
 // ── Formatting ────────────────────────────────────────────
@@ -370,16 +359,22 @@ export function formatBaselineSummary(baseline: Record<string, BaselineEntry>):
     if (entry.shellcheck) shellcheckFiles++;
   }
 
+  const toolLines = [
+    [eslintFiles, 'ESLint'],
+    [ruffFiles, 'Ruff'],
+    [golangciFiles, 'golangci-lint'],
+    [shellcheckFiles, 'ShellCheck'],
+  ] as const;
+
   const lines: string[] = [
     `Lint Baseline Summary:`,
     `  Files tracked: ${files.length}`,
     `  Total warnings: ${totalWarnings}`,
   ];
 
-  if (eslintFiles > 0) lines.push(`  ESLint: ${eslintFiles} files`);
-  if (ruffFiles > 0) lines.push(`  Ruff: ${ruffFiles} files`);
-  if (golangciFiles > 0) lines.push(`  golangci-lint: ${golangciFiles} files`);
-  if (shellcheckFiles > 0) lines.push(`  ShellCheck: ${shellcheckFiles} files`);
+  for (const [count, name] of toolLines) {
+    if (count > 0) lines.push(`  ${name}: ${count} files`);
+  }
 
   return lines.join('\n');
 }

package/skills/delphi-review/AGENTS.md

@@ -1,9 +1,9 @@
 # SKILLS/DELPHI-REVIEW KNOWLEDGE BASE
 
-**Generated:** 2026-07-07
-**Commit:** 897f8eb
-**Branch:** main
-**Version:** 0.12.13.0
+**Generated:** 2026-07-08
+**Commit:** 6f868ee
+**Branch:** sprint/2026-07-07-01
+**Version:** 0.13.0.0
 
 ## 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/skills/sprint-flow/AGENTS.md

@@ -1,35 +1,32 @@
 # SKILLS/SPRINT-FLOW KNOWLEDGE BASE
 
-**Generated:** 2026-07-07
-**Commit:** 897f8eb
-**Branch:** main
-**Version:** 0.12.13.0
+**Generated:** 2026-07-08
+**Commit:** 6f868ee
+**Branch:** sprint/2026-07-07-01
+**Version:** 0.13.0.0
 
 ## OVERVIEW
-**11-phase** development pipeline: ISOLATE → AUTO-ESTIMATE → THINK → PLAN → BUILD → REVIEW → SHIP → LAND → USER ACCEPTANCE → FEEDBACK → 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.
+**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.
 
-> **Doc drift**: README/CAPABILITIES still describe a "7-phase" pipeline. The canonical 11-phase model lives in `SKILL.md` and is what actually executes. See root `AGENTS.md` → "Known Drift" #4.
+> **v2.0 Compact Redesign (Issue #290)**: Merged from 11 phases to 6. PREP = old ISOLATE + AUTO-ESTIMATE. DESIGN = old THINK + PLAN. BUILD = old BUILD. VERIFY = old REVIEW + FEEDBACK. SHIP = old SHIP + LAND. CLOSE = old USER ACCEPTANCE + CLEANUP.
 
 ## STRUCTURE
 ```
 skills/sprint-flow/
-├── SKILL.md              # 11-phase pipeline definition (canonical)
+├── SKILL.md              # 6-phase pipeline definition (canonical, v2.0)
 ├── AGENTS.md             # This file (mirrored to 7 other locations — DO NOT edit mirrors)
 ├── evals/                # Evaluation test cases
 ├── evolution-history.json
 ├── evolution-log.md
 ├── references/
-│   ├── phase-minus-0-5-auto-estimate.md  # Phase -0.5: AUTO-ESTIMATE
-│   ├── phase-0-think.md                   # Phase 0: brainstorming → CONTEXT.md + ADR
-│   ├── phase-1-plan.md                    # Phase 1: autoplan + delphi-review (HARD-GATE)
-│   ├── phase-2-build.md                   # Phase 2: ralph-loop default + TDD + test-align
-│   ├── phase-3-review.md                  # Phase 3: code-walkthrough + QA + benchmark
-│   ├── phase-4-uat.md                     # Phase 4: USER ACCEPTANCE
-│   ├── phase-5-feedback.md                # Phase 5: retro + debugging + learn
-│   ├── phase-6-ship.md                    # Phase 6: finishing-dev-branch + PR
-│   ├── phase-7-land.md                    # Phase 7: land + deploy
-│   ├── phase-8-cleanup.md                 # Phase 8: sprint branch cleanup
+│   ├── phase-1-prep.md                    # Phase 1/6: PREP (worktree isolation + sizing)
+│   ├── phase-2-design.md                  # Phase 2/6: DESIGN (brainstorming + delphi-review HARD-GATE)
+│   ├── phase-3-build.md                   # Phase 3/6: BUILD (ralph-loop default + TDD + test-align)
+│   ├── phase-4-verify.md                  # Phase 4/6: VERIFY (code-walkthrough + QA + feedback)
+│   ├── phase-5-ship.md                    # Phase 5/6: SHIP (PR + merge + deploy + canary)
+│   ├── phase-6-close.md                   # Phase 6/6: CLOSE (UAT + cleanup)
 │   ├── force-levels.md                    # Phase forcing rules
+│   ├── orchestration-rules.md             # Agent dispatch, context inheritance, transition rules
 │   └── components/                        # Reusable phase building blocks
 └── templates/
     ├── auto-estimate-output-template.md
@@ -43,73 +40,64 @@ skills/sprint-flow/
 ## WHERE TO LOOK
 | Task | Location | Notes |
 |------|----------|-------|
-| Pipeline definition | SKILL.md | 11 phases with HARD-GATE between Phase 1 and Phase 2 |
-| Auto-estimate phase | references/phase-minus-0-5-auto-estimate.md | Sizing pass before THINK |
-| THINK phase | references/phase-0-think.md | brainstorming → CONTEXT.md + ADR |
-| PLAN phase + HARD-GATE | references/phase-1-plan.md | autoplan → delphi-review → specification.yaml |
-| BUILD phase | references/phase-2-build.md | ralph-loop (default) vs parallel |
+| Pipeline definition | SKILL.md | 6 phases with HARD-GATE between DESIGN (2/6) and BUILD (3/6) |
+| PREP phase | references/phase-1-prep.md | worktree isolation + sizing pass |
+| DESIGN phase + HARD-GATE | references/phase-2-design.md | brainstorming + autoplan + delphi-review → specification.yaml |
+| BUILD phase | references/phase-3-build.md | ralph-loop (default) vs parallel |
+| VERIFY phase | references/phase-4-verify.md | code-walkthrough + QA + retro + learn |
+| SHIP phase | references/phase-5-ship.md | PR + merge + deploy + canary |
+| CLOSE phase | references/phase-6-close.md | UAT + cleanup |
 | Force-level rules | references/force-levels.md | Defines when each phase becomes mandatory |
+| Orchestration rules | references/orchestration-rules.md | Agent dispatch, context inheritance, transition gates |
 | Templates | templates/ | Auto-estimate, sprint progress/summary, pain doc, emergent issues |
 
-## THE 11 PHASES
+## THE 6 PHASES (v2.0)
 
-| Phase | Name | Key Action | Hard Gate |
-|-------|------|-----------|-----------|
-| -1 | ISOLATE | Isolate working tree / worktree creation | — |
-| -0.5 | AUTO-ESTIMATE | Sizing pass; emits estimate template | — |
-| 0 | THINK | brainstorming → CONTEXT.md + ADR | — |
-| 1 | PLAN | autoplan → delphi-review → specification.yaml | **HARD-GATE**: design must reach ≥90% Delphi consensus |
-| 2 | BUILD | ralph-loop (REQ-level, default) + TDD + test-spec-alignment | — |
-| 3 | REVIEW | code-walkthrough + QA + benchmark | — |
-| 4 | SHIP | finishing-a-development-branch → PR | — |
-| 5 | LAND | land + deploy staging + canary | — |
-| 6 | USER ACCEPTANCE | Manual verification on staging | — |
-| 7 | FEEDBACK | retro + debugging + `learn` (Sprint-level) | — |
-| 8 | CLEANUP | Sprint branch cleanup (per `docs/plans/2026-06-06-sprint-branch-cleanup-design.md`) | — |
+| Phase | Name | Maps From (old 11) | Key Action | Hard Gate |
+|-------|------|-------------------|------------|-----------|
+| 1/6 | PREP | ISOLATE + AUTO-ESTIMATE | Worktree isolation + sizing | — |
+| 2/6 | DESIGN | THINK + PLAN | brainstorming → autoplan → Delphi consensus | **HARD-GATE**: design must reach ≥90% Delphi consensus |
+| 3/6 | BUILD | BUILD | ralph-loop (default) + TDD + test-spec-alignment | — |
+| 4/6 | VERIFY | REVIEW + FEEDBACK | code-walkthrough + QA + retro + learn | HARD-GATE: feedback-log.md must exist |
+| 5/6 | SHIP | SHIP + LAND | PR → squash-merge → deploy → canary | — |
+| 6/6 | CLOSE | USER ACCEPT + CLEANUP | Manual UAT → emergent issues → cleanup | HARD-GATE: UAT mandatory manual |
 
 ## CONVENTIONS
-- **ralph-loop is Phase 2 default**. Each REQ runs in a clean context (no linear accumulation), saving 40-67% tokens vs parallel mode.
-- **delphi-review HARD-GATE in Phase 1**: design must reach ≥90% consensus across ≥2 model providers, domestic models only. Unapproved → BLOCK coding.
-- **`learn` is called twice**: once per REQ in Phase 2 (ralph-loop internal, `progress.log` permanent/contextual classification) and once in Phase 5 (Sprint-level retro).
+- **ralph-loop is Phase 3/6 BUILD default**. Each REQ runs in a clean context, saving 40-67% tokens.
+- **delphi-review HARD-GATE in Phase 2/6 DESIGN**: design must reach ≥90% consensus across ≥2 model providers, domestic models only. Unapproved → BLOCK coding.
+- **`learn` is called twice**: once per REQ in Phase 3/6 (ralph-loop internal) and once in Phase 4/6 VERIFY (Sprint-level retro).
 - **Phase isolation**: each phase has explicit entry/exit criteria documented in its `references/phase-*.md` file.
-- **Emergent Requirements** discovered in Phase 6 (USER ACCEPTANCE) are explicitly captured via `templates/emergent-issues-template.md` — never silently merged.
-- **Auto-detection**: Phase 0 uses `src/npm-package/lib/ui-detector.ts` to pick the right tech-stack templates.
+- **Emergent Requirements** discovered in Phase 6/6 CLOSE (USER ACCEPTANCE) are explicitly captured via `templates/emergent-issues-template.md` — never silently merged.
+- **Auto-detection**: Phase 2/6 DESIGN uses `src/npm-package/lib/ui-detector.ts` to pick the right tech-stack templates.
 
 ## ANTI-PATTERNS (THIS PROJECT)
-- Do NOT skip `delphi-review` in Phase 1 — HARD-GATE blocks implementation.
+- Do NOT skip `delphi-review` in Phase 2/6 DESIGN — HARD-GATE blocks implementation.
 - Do NOT use parallel build mode unless explicitly requested. Ralph-loop is the default for a reason.
-- Do NOT enter Phase 1 (PLAN) without completing Phase 0 (THINK).
-- Do NOT implement before design is APPROVED — Phase 1 must reach Delphi consensus first.
-- Do NOT merge an Emergent Requirement into the original Sprint silently — capture it via the template.
+- Do NOT enter Phase 2/6 DESIGN (PLAN) without completing DESIGN (brainstorming).
+- Do NOT implement before design is APPROVED — Phase 2/6 DESIGN must reach Delphi consensus first.
+- Do NOT merge an Emergent Requirement into the original Sprint silently — capture it via the template in Phase 6/6 CLOSE.
 - Do NOT terminate Delphi review before ≥90% consensus or 5 rounds, whichever first.
 
 ## UNIQUE STYLES
-- **11 phases** including negative-numbered pre-phases (-1, -0.5) — intentional, captures the work that happens before "real" coding starts.
-- **HARD-GATE** between PLAN and BUILD is enforced both in the SKILL.md instructions and in the Claude Code plugin's PreToolUse hook (`plugins/claude-code/bin/delphi-review-guard.sh`).
-- **Per-REQ clean context in ralph-loop** = the core efficiency mechanism. Sprint-flow specifically chooses this over parallel mode.
+- **6 phases** (v2.0 Issue #290) — compact design with merged phases (1-6 numbering)
+- **HARD-GATE** between DESIGN and BUILD enforced both in SKILL.md and Claude Code plugin's PreToolUse hook.
+- **Per-REQ clean context in ralph-loop** = the core efficiency mechanism.
 - **Tech-stack auto-detection** via `--type` and `--lang` flags or `ui-detector.ts`.
 
 ## COMMANDS
 ```bash
-/sprint-flow "开发用户登录"                                     # Full 11-phase pipeline
+/sprint-flow "开发用户登录"                                     # Full 6-phase pipeline
 /sprint-flow "开发用户登录" --type web-nextjs --lang typescript # Pin tech stack
-/sprint-flow "开发用户登录" --phase build-only                  # Skip planning (advanced)
+/sprint-flow "开发用户登录" --phase build-only                  # Skip design (advanced)
 /sprint-flow "开发用户登录" --mode parallel                     # Legacy all-at-once (NOT default)
+/sprint-flow "开发用户登录" --stop-at design                    # Stop after DESIGN phase
 /delphi-review "开发用户登录" --type web-nextjs --lang typescript
 ```
 
 ## NOTES
-- Integrates: brainstorming, autoplan, delphi-review, TDD, test-specification-alignment, qa, design-review, benchmark, systematic-debugging, retro, learn, finishing-a-development-branch.
+- Integrates: brainstorming, autoplan, delphi-review, TDD, test-specification-alignment, qa, design-review, benchmark, systematic-debugging, retro, learn, finishing-a-development-branch, land-and-deploy.
 - ralph-loop's internal learnings are persisted via `progress.log` (permanent vs contextual classification).
-- Phase 5 calls `gstack/learn` for Sprint-level retrospective.
-- Phase 8 cleanup behavior is governed by `docs/plans/2026-06-06-sprint-branch-cleanup-design.md`.
-- This `AGENTS.md` is the canonical version. **7 byte-identical mirrors** exist at:
-  - `plugins/claude-code/skills/sprint-flow/AGENTS.md`
-  - `plugins/opencode/skills/sprint-flow/AGENTS.md`
-  - `plugins/qoder/skills/sprint-flow/AGENTS.md`
-  - `src/npm-package/skills/sprint-flow/AGENTS.md`
-  - `src/npm-package/plugins/claude-code/skills/sprint-flow/AGENTS.md`
-  - `src/npm-package/plugins/opencode/skills/sprint-flow/AGENTS.md`
-  - `src/npm-package/plugins/qoder/skills/sprint-flow/AGENTS.md`
+- Phase 4/6 VERIFY calls `gstack/learn` for Sprint-level retrospective.
+- Phase 6/6 CLOSE cleanup behavior is governed by `docs/plans/2026-06-06-sprint-branch-cleanup-design.md`.
+- This `AGENTS.md` is the canonical version. **7 byte-identical mirrors** exist.
   Mirrors are updated by `scripts/copy-skills.sh`. Do NOT edit them by hand.
-