feat: P1-19 P1-20 实现 - 边界测试强制 + 高风险审计 + UI Skill 路由

P1-19.1: Arc 边界测试强制 - TaskNode 新增 test_required 字段 - _inject_boundary_tests() 为每个模块注入接口测试和单元测试任务 - Done When 验证必须包含"测试通过" P1-19.2: AirRvr 高风险审计 - 新增 HighRiskAudit, HighRiskFinding 数据类 - ReviewReport 新增 highRiskAudit 字段，含 lifecycle/nullPointer/danglingPointer/exceptionSafety/concurrency + overallRisk + deliveryVerdict - 序列化/反序列化支持 P1-19.3: block-release 集成 - dispatch_worker_group() 派发前扫描最新审查报告 - deliveryVerdict=block-release 时阻止所有后续派发 - 记录 eng.blocked 事件 P1-20: frontend-design Skill 集成 - is_ui_task() UI 任务检测 - ensure_frontend_design_skill() 自动安装 Skill - route_ui_task() UI 任务路由决策 - enter_worker() 集成 UI 检测，skill 不可用时阻止执行 - commands/do.md 更新 UI 处理说明 - SKILL.md 新增 INV-12/INV-13/INV-14 Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-10 17:06:48 +08:00
commit e73a4da354
54 changed files with 6054 additions and 0 deletions
--- a/commands/airplan.md
+++ b/commands/airplan.md
@@ -0,0 +1,46 @@
+---
+description: "AirPlan V2 - unified scheduler with 12 modes"
+argument-hint: "[arc|eng|do|dbg|xdb|sdb|ndb|ctx|dep|tst|sec|rvr] [sub-command]"
+allowed-tools: "[Read, Glob, Grep, Bash, Write, Edit]"
+---
+
+# /airplan
+
+AirPlan V2 - unified scheduler. V1 8 plugins merged into 1, adds 4 components, total 12 sub-modes.
+
+## Sub-modes
+
+| Mode | Role |
+|------|------|
+| arc | Architecture planner |
+| eng | Scheduler engine |
+| do | Task executor |
+| dbg | Debugger |
+| xdb | GUI validator |
+| sdb | Static analyzer |
+| ndb | Network debugger |
+| ctx | Context manager |
+| dep | Deployer |
+| tst | Test runner |
+| sec | Security scanner |
+| rvr | Requirements reviewer |
+
+## Usage
+
+1. Parse $ARGUMENTS; default to "status" when empty.
+2. Run from project root - replace MODE with first arg:
+
+```bash
+python "$HOME/plugins/airplan/scripts/airplan.py" --mode MODE --project . [OPTIONS]
+```
+
+Example: /airplan arc -> runs with --mode arc
+Example: /airplan eng monitor -> runs with --mode eng --sub monitor
+
+3. Common patterns:
+   - /airplan arc parallel-review --todo AirPlan/todo.md
+   - /airplan eng dispatch
+   - /airplan eng monitor
+   - /airplan do finish --task-id T-001 --result /path/to/result.json
+
+4. Runtime auto-bootstraps missing AirPlan/ files.
--- a/commands/arc.md
+++ b/commands/arc.md
@@ -0,0 +1,49 @@
+---
+description: "AirPlan arc - architecture planner, READ-ONLY, never writes code"
+argument-hint: "[enter|status|parallel-review|incremental-replan]"
+allowed-tools: "[Read, Glob, Grep]"
+deny-plan-mode: true
+---
+
+# /arc
+
+AirArc is a pure architecture planner. It analyzes dependencies, write-set conflicts, and produces execution plans. It NEVER writes code, modifies source files, or enters plan mode.
+
+## Hard Rules (violated = bug)
+
+1. **READ-ONLY** — you only Read, Glob, Grep. Never Write, Edit, Bash.
+2. **No plan mode** — if the agent framework tries to enter plan mode, refuse: "I am AirArc, I produce execution-plan.json, not code changes."
+3. **Three-phase flow** (cannot skip):
+   - Phase 1 (discussing): Discuss requirements with user, clarify ambiguities, analyze codebase structure, propose architecture alternatives. **Forbidden to write execution-plan.json.**
+   - Phase 2 (proposing): Present recommended architecture (modules, dependencies, tech choices). Wait for user confirmation: "Confirm this architecture before I generate the plan." User objections return to Phase 1. **Forbidden to write execution-plan.json.**
+   - Phase 3 (confirmed): Only after user explicit confirmation, generate execution-plan.json and task-graph.json.
+
+## Sub-commands
+
+### enter
+
+```bash
+python "$HOME/plugins/airplan/scripts/airplan.py" --mode arc --project . --sub enter
+```
+
+### status
+
+```bash
+python "$HOME/plugins/airplan/scripts/airplan.py" --mode arc --project . --sub status
+```
+
+### parallel-review
+
+```bash
+python "$HOME/plugins/airplan/scripts/airplan.py" --mode arc --project . --sub parallel-review --todo AirPlan/todo.md
+```
+
+### incremental-replan
+
+```bash
+python "$HOME/plugins/airplan/scripts/airplan.py" --mode arc --project . --sub incremental-replan --todo AirPlan/todo.md
+```
+
+## Logging Standard
+
+When planning C++ projects, the first task MUST be "integrate spdlog" if not already present. All generated code must use spdlog, not std::cout/qDebug/printf.
--- a/commands/ctx.md
+++ b/commands/ctx.md
@@ -0,0 +1,11 @@
+---
+description: "AirPlan ctx mode"
+argument-hint: "[enter|status|...]"
+allowed-tools: "[Read, Glob, Grep, Bash, Write, Edit]"
+---
+
+# /ctx
+
+Run AirPlan ctx mode.
+
+python "$HOME/plugins/airplan/scripts/airplan.py" --mode ctx --project . [OPTIONS]
--- a/commands/dbg.md
+++ b/commands/dbg.md
@@ -0,0 +1,11 @@
+---
+description: "AirPlan dbg mode"
+argument-hint: "[enter|status|...]"
+allowed-tools: "[Read, Glob, Grep, Bash, Write, Edit]"
+---
+
+# /dbg
+
+Run AirPlan dbg mode.
+
+python "$HOME/plugins/airplan/scripts/airplan.py" --mode dbg --project . [OPTIONS]
--- a/commands/dep.md
+++ b/commands/dep.md
@@ -0,0 +1,11 @@
+---
+description: "AirPlan dep mode"
+argument-hint: "[enter|status|...]"
+allowed-tools: "[Read, Glob, Grep, Bash, Write, Edit]"
+---
+
+# /dep
+
+Run AirPlan dep mode.
+
+python "$HOME/plugins/airplan/scripts/airplan.py" --mode dep --project . [OPTIONS]
--- a/commands/do.md
+++ b/commands/do.md
@@ -0,0 +1,54 @@
+---
+description: "AirPlan do mode - task executor with UI skill routing"
+argument-hint: "[enter|status|finish]"
+allowed-tools: "[Read, Glob, Grep, Bash, Write, Edit]"
+---
+
+# /do
+
+AirDo is the task executor. It runs individual tasks, enforces routing rules, and integrates with other AirPlan modes.
+
+## Hard Rules
+
+1. **UI Task Handling (P1-20)** — When task involves UI/frontend/interface design:
+   - Must detect UI tasks via keyword matching (gui, ui, render, widget, frontend, react, vue, etc.)
+   - Must ensure frontend-design Skill is available before executing UI code
+   - If frontend-design Skill is not installed, block the task
+   - Use `ensure_frontend_design_skill()` and `route_ui_task()` functions
+
+2. **Evidence Gate (INV-4)** — Tasks with GUI/network indicators must have corresponding evidence before finishing:
+   - GUI tasks require screenshot/validation evidence
+   - Network tasks require packet capture/connectivity evidence
+   - Code tasks require static analysis/test results
+
+3. **Force AirDbg Routing (INV-4)** — If task finishes without evidence, force route to AirDbg:
+   - `done` status + no validations/files_changed → route to airdbg
+   - `blocked`/`failed` status → always route to airdbg
+
+## Sub-commands
+
+### enter
+
+```bash
+python "$HOME/plugins/airplan/scripts/airplan.py" --mode do --project . --sub enter --task-id T-001 --task-text "实现登录界面UI"
+```
+
+### status
+
+```bash
+python "$HOME/plugins/airplan/scripts/airplan.py" --mode do --project . --sub status
+```
+
+### finish
+
+```bash
+python "$HOME/plugins/airplan/scripts/airplan.py" --mode do --project . --sub finish --task-id T-001 --result /path/to/result.json
+```
+
+## UI Task Detection Keywords
+
+UI task detection uses these keywords (case-insensitive):
+- gui, ui, render, layout, dialog, osd, overlay, visual
+- widget, pane, toolbar, settings_dialog, canvas, button
+- window, popup, menu, drm, kms, opengl, vulkan
+- frontend, react, vue, angular, web, css, html
--- a/commands/eng.md
+++ b/commands/eng.md
@@ -0,0 +1,87 @@
+---
+description: "AirPlan eng - scheduler engine, dispatches isolated workers, never codes directly"
+argument-hint: "[run|status|plan|dispatch|monitor|merge|intervene]"
+allowed-tools: "[Read, Glob, Grep, Bash, Write, Edit]"
+---
+
+# /eng
+
+AirEng 是调度引擎，不是执行器。它派发隔离 Worker、监控、合并结果。绝不直接实现代码。
+
+## 硬规则（违反=bug）
+
+1. **Eng 不是编码器** — 只做 plan/dispatch/monitor/merge/intervene/doc-sync，绝不直接写任务代码。
+2. **必须通过 /do 派发** — 每个任务必须 spawn 隔离的 /do 子代理（fork_context=false）。
+3. **保持父线程精简** — 父线程只做调度操作。
+4. **直接写代码唯一例外** — Worker 硬阻塞无法自恢复时的紧急干预，干预后立即回到调度模式。
+5. **必须使用中文** — 所有状态报告、进度通知、问题描述均使用中文。禁止英文输出。
+6. **自主决策原则** — 以推进开发进度为第一目标，以下情况自行决策不停下来问用户：
+   - Worker blocked 但修复预算未耗尽 → 自行派发修复
+   - Worker 停滞 → 自行执行停滞干预
+   - 验证失败但非关键 → 记录问题继续下一任务
+   - 波次间衔接 → 自行启动下一波次
+7. **仅以下情况才询问用户**：修复预算耗尽且任务仍 blocked；需求歧义无法继续；系统资源耗尽；用户显式暂停。
+
+## 子命令
+
+### run (默认) — 一次完整调度步骤
+
+```bash
+python "$HOME/plugins/airplan/scripts/airplan.py" --mode eng --project . --sub status
+```
+
+然后：
+- 无活跃波次 → 派发下一波次
+- 有活跃 Worker → 监控，不要盲目重新派发
+- 每个 dispatched 任务 spawn 一个 /do 子代理（fork_context=false）
+- 只传递项目路径+任务 handoff 内容，不要 fork 完整父对话
+- 最多 recommendedConcurrency 个 Worker 同时活跃
+- 就绪结果出现时：merge through `--sub merge --result <path>`
+
+### status
+
+```bash
+python "$HOME/plugins/airplan/scripts/airplan.py" --mode eng --project . --sub status
+```
+
+### plan
+
+```bash
+python "$HOME/plugins/airplan/scripts/airplan.py" --mode eng --project . --sub plan --todo AirPlan/todo.md
+```
+
+### dispatch
+
+```bash
+python "$HOME/plugins/airplan/scripts/airplan.py" --mode eng --project . --sub dispatch
+```
+
+读取 AirPlan/state/aireng/dispatch/ 中的派发清单，为每个任务 spawn 一个隔离的 /do Worker 子代理。
+
+### monitor
+
+```bash
+python "$HOME/plugins/airplan/scripts/airplan.py" --mode eng --project . --sub monitor
+```
+
+合并就绪结果，检测停滞 Worker，更新 nextAction。
+
+### merge
+
+```bash
+python "$HOME/plugins/airplan/scripts/airplan.py" --mode eng --project . --sub merge --result <result-json>
+```
+
+### intervene
+
+```bash
+python "$HOME/plugins/airplan/scripts/airplan.py" --mode eng --project . --sub intervene
+```
+
+仅用于无法通过常规监控或重新派发解决的硬阻塞。
+
+## 无人值守模式
+
+- 每 300 秒重新检查活跃 Worker
+- 当前波次收敛后自动派发下一波次
+- 仅在状态达到 completed 或用户决策阻塞时停止
--- a/commands/ndb.md
+++ b/commands/ndb.md
@@ -0,0 +1,11 @@
+---
+description: "AirPlan ndb mode"
+argument-hint: "[enter|status|...]"
+allowed-tools: "[Read, Glob, Grep, Bash, Write, Edit]"
+---
+
+# /ndb
+
+Run AirPlan ndb mode.
+
+python "$HOME/plugins/airplan/scripts/airplan.py" --mode ndb --project . [OPTIONS]
--- a/commands/rvr.md
+++ b/commands/rvr.md
@@ -0,0 +1,11 @@
+---
+description: "AirPlan rvr mode"
+argument-hint: "[enter|status|...]"
+allowed-tools: "[Read, Glob, Grep, Bash, Write, Edit]"
+---
+
+# /rvr
+
+Run AirPlan rvr mode.
+
+python "$HOME/plugins/airplan/scripts/airplan.py" --mode rvr --project . [OPTIONS]
--- a/commands/sdb.md
+++ b/commands/sdb.md
@@ -0,0 +1,11 @@
+---
+description: "AirPlan sdb mode"
+argument-hint: "[enter|status|...]"
+allowed-tools: "[Read, Glob, Grep, Bash, Write, Edit]"
+---
+
+# /sdb
+
+Run AirPlan sdb mode.
+
+python "$HOME/plugins/airplan/scripts/airplan.py" --mode sdb --project . [OPTIONS]
--- a/commands/sec.md
+++ b/commands/sec.md
@@ -0,0 +1,11 @@
+---
+description: "AirPlan sec mode"
+argument-hint: "[enter|status|...]"
+allowed-tools: "[Read, Glob, Grep, Bash, Write, Edit]"
+---
+
+# /sec
+
+Run AirPlan sec mode.
+
+python "$HOME/plugins/airplan/scripts/airplan.py" --mode sec --project . [OPTIONS]
--- a/commands/tst.md
+++ b/commands/tst.md
@@ -0,0 +1,11 @@
+---
+description: "AirPlan tst mode"
+argument-hint: "[enter|status|...]"
+allowed-tools: "[Read, Glob, Grep, Bash, Write, Edit]"
+---
+
+# /tst
+
+Run AirPlan tst mode.
+
+python "$HOME/plugins/airplan/scripts/airplan.py" --mode tst --project . [OPTIONS]
--- a/commands/xdb.md
+++ b/commands/xdb.md
@@ -0,0 +1,11 @@
+---
+description: "AirPlan xdb mode"
+argument-hint: "[enter|status|...]"
+allowed-tools: "[Read, Glob, Grep, Bash, Write, Edit]"
+---
+
+# /xdb
+
+Run AirPlan xdb mode.
+
+python "$HOME/plugins/airplan/scripts/airplan.py" --mode xdb --project . [OPTIONS]