@boyingliu01/xp-gate 0.5.3 → 0.7.0

package/skills/sprint-flow/SKILL.md

@@ -263,6 +263,25 @@ Phase 2 第一步必须执行 DELPHI-GATE 检查。没有 delphi-review APPROVED
 3. 验证 `verdict` 字段 == `"APPROVED"` → 不等于 → 同上 BLOCK
 4. ✅ 通过 → 进入 BUILD 编码
 
+**⚠️ Qoder Pre-Edit Gate（MANDATORY — 替代 Claude Code 的 delphi-review-guard.sh Hook）**:
+
+在 Qoder 环境中，由于没有 PreToolUse/PostToolUse 文件系统钩子，orchestrator **MUST** 在每次文件编辑/写入操作之前执行以下检查：
+
+1. 检查 `.sprint-state/` 目录是否存在 → 不存在 → 跳过检查（非 sprint 项目）
+2. 读取 `.sprint-state/delphi-reviewed.json` → 文件不存在 → **BLOCK**: 输出 `[DELPHI-GATE] delphi-review not APPROVED. 请先运行 /delphi-review`
+3. `verdict` != `"APPROVED"` → **BLOCK**
+4. `verdict` == `"APPROVED"` → 允许编辑
+
+此检查在 Phase 2 至 Phase 6 期间持续生效。orchestrator 不可绕过此检查。
+
+**Post-REQ Principles Check（替代 Claude Code 的 PostToolUse xp-gate-check Hook）**:
+
+每个 REQ 完成后（ralph-loop 三层验证 Gate 之后），orchestrator **MUST** 运行：
+```bash
+npx -y tsx src/principles/index.ts --files "<changed_files>" --format console
+```
+如果 src/principles/ 不存在（非 xp-gate 项目），则跳过此步骤。
+
 **输入**: `slices-manifest.json`（由 Phase 1 `/to-issues` 生成），按 `execution_order` 逐个执行。
 
 **默认模式**: `ralph-loop` — 逐 REQ/切片 迭代构建。每个切片（REQ）dispatch 独立 subagent，干净上下文，全量回归测试。Token 节约 40-67%。参见 `skills/ralph-loop/SKILL.md`。
@@ -425,6 +444,55 @@ Phase 2 第一步必须执行 DELPHI-GATE 检查。没有 delphi-review APPROVED
 | 7 | LAND | ✅ | `deep` | `["land-and-deploy"]` | subagent |
 | 8 | CLEANUP | ❌ | Bash（直接执行） | 无 | orchestrator |
 
+### Qoder Agent Dispatch Mapping（Qoder 平台替代方案）
+
+在 Qoder 环境中，OpenCode 的 `task()` API 和 superpowers/gstack 外部 skill 不可用。以下映射表说明每个 Phase 在 Qoder 中的执行方式：
+
+| Phase | 原 task()/skill 调用 | Qoder 替代方案 | 说明 |
+|-------|----------------------|--------------|------|
+| -1 ISOLATE | Bash 直接执行 | **Bash 直接执行**（无变化） | git worktree 操作平台无关 |
+| -0.5 AUTO-ESTIMATE | Bash 直接执行 | **Bash 直接执行**（无变化） | grep -rn 平台无关 |
+| 0 THINK | `task(deep, brainstorming)` | **plan-agent subagent** | 需求探索与设计适合 plan-agent |
+| 1 PLAN | `task(deep, autoplan+delphi+to-issues)` | **plan-agent subagent** | 规划类任务 |
+| 2 BUILD | `ralph-loop` + 外部 skill | **orchestrator 直接执行** | ralph-loop 逐 REQ 迭代，不需要独立 subagent |
+| 2 步骤 4 | `requesting-code-review` | **CodeReview subagent** | 代码盲评天然适合 CodeReview agent |
+| 2 步骤 6 | `verification-before-completion` | **orchestrator 内联** | 运行测试 + lint + coverage + principles |
+| 3 REVIEW | `task(deep, delphi+test-spec)` | **CodeReview subagent** + **browser-use MCP** | 代码走查 + 浏览器自动化 |
+| 4 ACCEPT | 强制人工 | **强制人工**（无变化） | 必须人工验收 |
+| 5 FEEDBACK | `task(quick, learn+retro+debug)` | **plan-agent** + **Memory 系统** | 回顾分析 + UpdateMemory 持久化 |
+| 6 SHIP | `task(quick, finishing-branch+ship)` | **orchestrator 直接执行** | git + gh CLI 操作平台无关 |
+| 7 LAND | `task(deep, land-and-deploy)` | **orchestrator 直接执行** | gh pr merge + CI polling |
+| 8 CLEANUP | Bash 直接执行 | **Bash 直接执行**（无变化） | git worktree remove 平台无关 |
+
+**Qoder 外部 Skill 降级表**（替代 superpowers/gstack 依赖）：
+
+| 外部 Skill | 来源 | Qoder 替代方案 |
+|-----------|------|----------------|
+| brainstorming | superpowers | orchestrator 内联需求探索对话 |
+| autoplan | gstack | plan-agent 分析代码库生成计划 |
+| freeze / unfreeze | gstack | Qoder Pre-Edit Gate 替代（见上方） |
+| requesting-code-review | superpowers | **CodeReview subagent** |
+| verification-before-completion | superpowers | orchestrator 运行测试+lint+coverage+principles |
+| learn / retro | gstack | Qoder **Memory 系统**（UpdateMemory / SearchMemory） |
+| browse | gstack | **browser-use MCP** 工具（navigate_page, click, fill, take_screenshot） |
+| ship / finishing-a-development-branch | superpowers/gstack | orchestrator 执行 git + gh CLI |
+| systematic-debugging | superpowers | orchestrator 内联分析错误日志 |
+| land-and-deploy / canary | gstack | orchestrator 执行 gh + curl/Invoke-RestMethod |
+| dispatching-parallel-agents | superpowers | orchestrator 按 dependency_graph 顺序执行 |
+| executing-plans | superpowers | orchestrator 直接执行 |
+
+**Qoder genui Widget 集成**：
+
+Phase 3 REVIEW 完成后，orchestrator **SHOULD** 使用 genui `show_widget` MCP 工具展示质量报告：
+- Widget 模板：`plugins/qoder/widgets/quality-report.html`
+- 数据源：读取项目根目录的 `quality-report.json`
+
+Sprint 执行过程中，用户可通过 `/sprint-status` 触发 genui `show_widget` 展示 Sprint 仪表板：
+- Widget 模板：`plugins/qoder/widgets/sprint-dashboard.html`
+- 数据源：`.sprint-state/sprint-state.json`
+
+详细适配规则参见 `references/qoder-adaptation.md`。
+
 **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
 - orchestrator session 仅接收 subagent 的最终结果摘要（~13,000 tokens/sprint）

package/skills/sprint-flow/references/qoder-adaptation.md

@@ -0,0 +1,173 @@
+# Qoder Platform Adaptation Guide for Sprint Flow
+
+**Version:** v0.6.0  
+**Platform:** Qoder IDE  
+**Status:** Active
+
+---
+
+## 1. Platform Differences
+
+### 1.1 No File-System Event Hooks
+
+| Capability | Claude Code | OpenCode | Qoder |
+|-----------|------------|----------|-------|
+| PreToolUse Hook | ✅ `delphi-review-guard.sh` | ❌ | ❌ |
+| PostToolUse Hook | ✅ `xp-gate-check` | ❌ | ❌ |
+| Custom Tools | ❌ | ✅ `tool()` | ❌ (MCP instead) |
+
+**Adaptation**: Gates embedded in SKILL.md as `<MANDATORY>` instructions. Orchestrator MUST execute checks before each file edit.
+
+### 1.2 No `task()` Subagent API
+
+| Capability | OpenCode | Qoder |
+|-----------|----------|-------|
+| Subagent dispatch | `task(category, load_skills)` | Agent tool (Browser/CodeReview/plan-agent) |
+| Multi-model | Agent config with different models | Qoder multi-model capability |
+| Context isolation | Automatic per-task | Automatic per-Agent |
+
+**Adaptation**: Phase→Agent mapping table in sprint-flow SKILL.md.
+
+### 1.3 No superpowers/gstack Ecosystem
+
+Qoder does not have access to the superpowers or gstack skill ecosystems. All external skill calls are replaced by:
+- **Orchestrator inline execution** (for simple tasks)
+- **Qoder native capabilities** (Memory, CodeReview, browser-use)
+- **Agent subagents** (for complex analysis/planning)
+
+---
+
+## 2. External Skill Replacement Matrix
+
+### 2.1 brainstorming (superpowers) → Orchestrator Inline
+
+**Original**: `task(category="deep", load_skills=["brainstorming"])`
+
+**Qoder Replacement**: Orchestrator conducts an interactive requirements exploration dialogue:
+1. Ask clarifying questions about the feature
+2. Analyze existing codebase for relevant modules
+3. Generate a structured design document
+4. Present to user for approval (HARD-GATE)
+
+### 2.2 autoplan (gstack) → plan-agent Subagent
+
+**Original**: `task(category="deep", load_skills=["autoplan"])`
+
+**Qoder Replacement**: Dispatch `plan-agent` subagent with:
+- Design document as input
+- Codebase structure analysis
+- Generate implementation plan with REQ/AC structure
+- Output: specification.yaml draft
+
+### 2.3 freeze/unfreeze (gstack) → Pre-Edit Gate
+
+**Original**: `freeze` locks test directories, `unfreeze` unlocks
+
+**Qoder Replacement**: Pre-Edit Gate in sprint-flow SKILL.md:
+- During Phase 2 freeze state, orchestrator MUST check target file path
+- If file is in test directory → BLOCK with message
+- This is a behavioral constraint, not a physical lock
+
+### 2.4 requesting-code-review (superpowers) → CodeReview Subagent
+
+**Original**: `task(category="unspecified-high", load_skills=["requesting-code-review"])`
+
+**Qoder Replacement**: Dispatch `CodeReview` subagent:
+- Input: changed files since last REQ commit
+- Blind review (no access to business intent, only code)
+- Output: review findings
+
+### 2.5 verification-before-completion (superpowers) → Orchestrator Inline
+
+**Original**: `task(load_skills=["verification-before-completion"])`
+
+**Qoder Replacement**: Orchestrator executes sequentially:
+1. `npm test` / `pytest` / `go test` (test runner)
+2. `npx eslint` / `ruff check` / `golangci-lint` (linter)
+3. `npx tsx src/principles/index.ts` (principles check)
+4. Coverage report check (≥80%)
+
+### 2.6 learn/retro (gstack) → Qoder Memory System
+
+**Original**: `task(load_skills=["learn", "retro"])`
+
+**Qoder Replacement**: 
+- **learn**: `UpdateMemory` with appropriate category
+  - Architecture decisions → `expert_experience`
+  - Coding patterns → `development_practice_specification`
+  - Project structure → `project_introduction`
+- **retro**: `plan-agent` subagent analyzes git log + code quality trends
+  - Output stored via `UpdateMemory` as `task_summary_experience`
+
+### 2.7 browse (gstack) → browser-use MCP
+
+**Original**: `browse` navigates to localhost, interacts with UI
+
+**Qoder Replacement**: Use `browser-use` MCP tools:
+- `navigate_page` → navigate to localhost:3000
+- `click` / `fill` → interact with UI elements
+- `take_screenshot` → capture visual verification
+- `take_snapshot` → get accessibility tree for validation
+
+### 2.8 ship/finishing-branch → Orchestrator Git/GH CLI
+
+**Original**: External skill calls
+
+**Qoder Replacement**: Orchestrator executes:
+- `git add` + `git commit` + `git push`
+- `gh pr create` + `gh pr merge`
+- Standard git workflow (platform-independent)
+
+---
+
+## 3. genui Widget Integration
+
+### 3.1 Quality Report Widget
+
+**Trigger**: After Phase 3 REVIEW completes
+
+**Execution**:
+```
+show_widget(widget_path="plugins/qoder/widgets/quality-report.html", data={...quality-report.json contents...})
+```
+
+### 3.2 Sprint Dashboard Widget
+
+**Trigger**: User requests `/sprint-status` or Phase transition
+
+**Execution**:
+```
+show_widget(widget_path="plugins/qoder/widgets/sprint-dashboard.html", data={...sprint-state.json contents...})
+```
+
+---
+
+## 4. Memory System Integration
+
+### 4.1 Learnings Categories
+
+| ralph-loop Category | Qoder Memory Category | Scope |
+|--------------------|-----------------------|-------|
+| permanent (architecture) | `expert_experience` | workspace |
+| permanent (convention) | `development_practice_specification` | workspace |
+| permanent (structure) | `project_introduction` | workspace |
+| contextual | Not persisted | session only |
+| sprint retro | `task_summary_experience` | workspace |
+
+### 4.2 Memory Lifecycle
+
+1. **REQ complete** → `UpdateMemory` for permanent learnings
+2. **Sprint Phase 5** → `UpdateMemory` for sprint-level retro
+3. **Next sprint** → `SearchMemory` to recall relevant learnings
+4. **Stale learnings** → User can request memory cleanup
+
+---
+
+## 5. Known Limitations
+
+| Limitation | Impact | Mitigation |
+|-----------|--------|-----------|
+| Skill-embedded gates less reliable than hooks | Agent may ignore constraints | `<MANDATORY>` tags + Terminal State Checklist |
+| No physical file-system lock for freeze | Test files could be modified | Pre-Edit Gate + Terminal State verification |
+| Single model for all experts (degraded mode) | Loses cross-provider anonymity | Clearly label degraded reviews |
+| No `k6`/`locust` integration | Load testing limited | Future: MCP server for load testing |

package/skills/test-specification-alignment/SKILL.md

@@ -569,6 +569,29 @@ legacy_mode:
 
 ---
 
+## Qoder 平台适配
+
+### freeze 机制替代（替代 gstack/freeze skill）
+
+在 Qoder 环境中，freeze/unfreeze 通过 sprint-flow 的 **Pre-Edit Gate** 替代：
+- Phase 2 执行期间，orchestrator 禁止修改测试目录下的文件
+- 此约束通过 SKILL.md 指令强制执行（非物理阻断）
+- orchestrator 在每次文件编辑前检查：如果目标文件位于测试目录且当前处于 Phase 2 freeze 状态，则 **BLOCK**
+
+### Agent 配置适配
+
+| 原配置 | Qoder 替代 | 说明 |
+|---------|------------|------|
+| Phase 1 Agent (Qwen3.5-Plus) | **orchestrator 直接执行** | YAML 解析 + AST 解析由 orchestrator 内联完成 |
+| Phase 2 Agent (GLM-5) | **orchestrator 直接执行** | 测试执行由 orchestrator 通过 Bash 工具完成 |
+
+### Qoder 集成点
+
+- Phase 3 REVIEW 完成后，使用 genui `show_widget` 展示对齐报告摘要
+- 对齐分数记录通过 `UpdateMemory` 持久化（development_test_specification 类型）
+
+---
+
 ## Anti-Patterns
 
 | 错误 | 正确 |