🎉 init: 小龙的工作空间

2026-06-06 10:40:48 +08:00
commit a188ee1426
3201 changed files with 231817 additions and 0 deletions
@@ -0,0 +1,826 @@
+# Learning Loop Refactor — Verification Log
+
+> Generated: 2026-06-05 22:51 CST
+> Purpose: 逐条终端原始输出归档，避免仅剩"摘要表"
+
+---
+
+## 1. AGENTS.md §2b — Learning Context Injector (MANDATORY)
+
+### Command
+```
+sed -n '90,114p' /Users/a1234/.openclaw/workspace/AGENTS.md
+```
+
+### Raw Output
+#### 2b. Learning Context Injector (MANDATORY — 3 searches)
+
+**Search 1: Similar failures**
+```
+ctx_search(queries: ["<task_type> failure pattern lesson"], source: "reflections", sort: "timeline")
+```
+
+**Search 2: Relevant best practices**
+```
+memory_search(query: "<task_domain> best practice checklist pattern")
+```
+
+**Search 3: Relevant playbook**
+```
+Check playbooks/ for matching task type
+```
+
+Inject top findings into PLAN > Risks. Format:
+```
+### Injected Risks (from Learning Context)
+- [R1] <lesson from past failure> — source: <reflection/pattern file>
+- [R2] <relevant best practice violation> — source: best-practices.md #N
+- [R3] <playbook recommendation> — source: playbooks/<name>.md
+```
+
+
+---
+
+## 2. AGENTS.md §2c — 6 Domain Checklists
+
+### Command
+```
+sed -n '116,155p' /Users/a1234/.openclaw/workspace/AGENTS.md
+```
+
+### Raw Output
+
+**Based on task type, append the relevant checklist to PLAN:**
+
+**SQL / Schema tasks:**
+- □ FK 引用：所有 FK 用 ON CONFLICT DO UPDATE，不用 REPLACE（SQLite REPLACE = DELETE+INSERT）
+- □ DDL 解析：PRIMARY KEY / CONSTRAINT 行不能当数据字段
+- □ 迁移安全：先检查所有引用方，再改 schema
+- □ WAL 模式：多进程读写不阻塞
+
+**JavaScript / TypeScript tasks:**
+- □ Falsy 陷阱：0、''、false 用 `??` 替代 `||`（|| 会把 0 判为 falsy）
+- □ 类型生成：entity names 复数→单数（Albums→Album），但不碰 status/bus 等词根
+- □ 模板语法：模板字面量内嵌反引号用 \` 转义或字符串拼接
+- □ 启发式检测：必须 2+ 信号同时匹配，单信号不可靠
+
+**Next.js / Frontend tasks:**
+- □ 路径：Next.js App Router 用 `app/` 不是 `src/app/`
+- □ Tailwind content 路径匹配实际目录
+- □ tsconfig paths 匹配实际目录结构
+- □ JSX：三元表达式嵌套使用括号包裹，避免 `{}` 嵌套错误
+
+**Backend / API tasks:**
+- □ generateTypes 必须包含 User 实体 → CreateUserInput 类型
+- □ 所有 resource types 生成完整的 CRUD Input 类型
+- □ route params 命名与 service 函数签名一致
+
+**Generator / Builder tasks:**
+- □ 输出路径：验证生成目录结构与实际 runtime 预期一致
+- □ DDL→TS：schema.ts 中 CONSTRAINT/FK 行不能被解析为 interface 字段
+- □ Type mapping：SQL types 到 TS types 的映射表完整
+- □ Template safety：模板字面量不输出裸反引号
+
+**Release / CI tasks:**
+- □ Exit code 规范：PASS/WARN→0, FAIL→1
+- □ 回退路径：每个 destructive 操作有对应回退步骤
+- □ backward compat：新代码不改老接口
+
+If no checklist matches, add:
+- □ No domain-specific checklist available — proceed with extra caution
+
+
+---
+
+## 3. AGENTS.md §4 — MANDATORY GATE
+
+### Command
+```
+sed -n '194,207p' /Users/a1234/.openclaw/workspace/AGENTS.md
+```
+
+### Raw Output
+```
+
+**MANDATORY GATE: Pre-flight Compliance Check**
+
+Before closing any complex task, verify ALL of:
+
+- [ ] PLAN contains `### Injected Risks (from Learning Context)` section
+- [ ] At least 2 knowledge sources were searched (ctx_search / memory_search / playbooks)
+- [ ] Matching domain checklist from §2c is included in PLAN
+- [ ] If failure occurred: structured Reflection was written to `reflections/YYYY-MM-DD-<task>.md`
+- [ ] Reflection contains ALL 7 required fields (Context/Root Cause/Fix/Pattern Class/Future Trigger/Checklist/Recurrence)
+
+If ANY gate fails: **task is NOT complete**. Go back and fill the gap.
+
+
+---
+
+## 4. AGENTS.md §5 — T1-T7 Auto-Capture
+
+### Command
+```
+sed -n '210,238p' /Users/a1234/.openclaw/workspace/AGENTS.md
+```
+
+### Raw Output
+**ALWAYS check these conditions after fixing a failure. Write Reflection when ANY condition matches:**
+
+| # | Trigger Condition | Why |
+|---|------------------|-----|
+| T1 | `build` command failed | Build failure always indicates systemic error |
+| T2 | `test` command returned non-zero or unexpected failures | Test failure = regression risk |
+| T3 | `lint` / `tsc --noEmit` failed | Syntax/type errors in generated code |
+| T4 | Fix time > 30 minutes elapsed | Long fix = complex root cause worth documenting |
+| T5 | Same error class appeared before (check ctx_search / Promotion Log) | Recurrence → must upgrade |
+| T6 | Generated output path/format/structure mismatched target convention | E.g. `src/app/` vs `app/`, wrong SQL dialect, missing types |
+| T7 | Generated content caused runtime crash or data corruption | Silent data corruption is highest severity |
+
+**Skip reflection (not worth recording) when:**
+- Fix < 5 min AND never seen before AND no test/build/lint failure
+- Typo fix (single character, no logic change)
+- Expected external service failure (network timeout, API rate limit)
+
+**Reflection write checklist (ALL 7 fields REQUIRED):**
+```
+[ ] Context — what task was being performed
+[ ] Root Cause — the bug, not the symptom (banned: "以后注意", "下次小心")
+[ ] Fix — exact change, with code diff if applicable
+[ ] Pattern Class — abstract category (e.g. "SQLite FK", "JS Falsy Coercion", "Path Convention")
+[ ] Future Trigger — when to inject this lesson (e.g. "any SQL schema change")
+[ ] Checklist — ≥2 actionable checks for next time
+[ ] Recurrence Count — 1 (update on each recurrence)
+```
+
+---
+
+---
+
+## 5. AGENTS.md §3 — Auto-Capture + Promotion Check
+
+### Command
+```
+sed -n '165,182p' /Users/a1234/.openclaw/workspace/AGENTS.md
+```
+
+### Raw Output
+3. If local → fix, verify, continue
+4. If structural → **REPLAN** — output a revised PLAN section
+5. If same step fails 3 times → **PAUSE** and ask user
+6. **Auto-Capture Check** (after fix, before continuing):
+   → See complete trigger rules in §5 Auto-Capture Trigger (T1-T7)
+   → If ANY trigger matches → write structured Reflection to `reflections/YYYY-MM-DD-<task>.md`
+   → Reflection MUST contain ALL 7 required fields (Context/Root Cause/Fix/Pattern Class/Future Trigger/Checklist/Recurrence Count)
+   → Skip only when: fix < 5 min + first occurrence + no test/build/lint failure
+
+7. **Promotion Check** (after Reflection written):
+   | Appearances | Action | Destination |
+   |------------|--------|------------|
+   | 1st | Reflection | reflections/ |
+   | 2nd | Pattern | patterns/design-patterns.md (new section) |
+   | 3rd | Best Practice | patterns/best-practices.md (numbered entry) |
+   | 4th | Checklist Item | AGENTS.md §2c Domain Checklists |
+   | 5th | Hard Rule | AGENTS.md §2c (bolded, marked ⚠️ HARD RULE) |
+
+
+---
+
+## 6. AGENTS.md — Learning Loop §
+
+### Command
+```
+sed -n '240,305p' /Users/a1234/.openclaw/workspace/AGENTS.md
+```
+
+### Raw Output
+## Learning Loop 🔄
+
+> Knowledge stored in reflections/patterns/playbooks MUST flow back into Planning.
+> This section closes the loop.
+
+### Loop Architecture
+
+```
+Failure/Success
+    ↓
+Reflection (structured, with Pattern Class)
+    ↓
+Promotion Check (1→2→3→4→5 appearances)
+    ↓
+Pattern → Best Practice → Checklist → Hard Rule
+    ↓
+Pre-flight Injector (§2b) + Domain Checklists (§2c)
+    ↓
+Next Plan includes past lessons
+    ↓
+Execution
+    ↓
+Verification → triggers new Reflection if needed
+    ↓
+(loop closes)
+```
+
+### Promotion Rules
+
+| Count | Promotion To | Location |
+|-------|-------------|----------|
+| 1st | Reflection | `reflections/YYYY-MM-DD-<task>.md` |
+| 2nd | Design Pattern | `patterns/design-patterns.md` (new Anti-Pattern section) |
+| 3rd | Best Practice | `patterns/best-practices.md` (numbered entry) |
+| 4th | Domain Checklist | AGENTS.md §2c (update matching checklist, or create new) |
+| 5th | Hard Rule | AGENTS.md §2c (bolded, marked ⚠️ HARD RULE) |
+
+### Quality Gate for Reflections
+
+A valid Reflection MUST include ALL of:
+- [ ] Context (what task)
+- [ ] Root Cause (the bug, not the symptom)
+- [ ] Fix (exact change)
+- [ ] Pattern Class (abstract category)
+- [ ] Future Trigger (when to re-inject)
+- [ ] Checklist (actionable items)
+- [ ] Recurrence Count
+
+**Rejected:** "以后注意", "下次小心", "当时没想清楚", "应该多测试"
+**Accepted:** "SQLite FK: REPLACE=DELETE+INSERT, use ON CONFLICT DO UPDATE"
+
+### Storage Locations
+
+```
+reflections/              ← First occurrence of a failure pattern
+patterns/design-patterns  ← Abstract reusable anti-patterns (≥2 occurrences)
+patterns/best-practices   ← Validated rules (≥3 occurrences)
+AGENTS.md §2c             ← Domain Checklists (≥4 occurrences)
+AGENTS.md §2c ⚠️          ← Hard Rules (≥5 occurrences)
+
+playbooks/                ← Successful multi-step workflows (not failure-driven)
+vault.md §Self-Evolution  ← History of promotions (timeline)
+```
+
+---
+
+
+---
+
+## 7. Reflection: falsy-coercion (full file)
+
+### Command
+```
+cat /Users/a1234/.openclaw/workspace/reflections/2026-06-05-falsy-coercion.md
+```
+
+### Raw Output
+```
+# Reflection: `||` vs `??` Falsy Coercion Bug
+
+> Date: 2026-06-05 | Severity: P1 | Recurrence: 2
+
+## Context
+Cross-Agent Certification (PR-30) — Fleet score ranking. Using `order[status] || 6` for certification ranking.
+
+## Root Cause
+JavaScript `||` operator treats `0` as falsy. When `order["healthy"] = 0`, `order["healthy"] || 6` evaluates to `6`, pushing healthy agents to bottom of ranking instead of top. The certification result was reversed — healthy fleets got low scores.
+
+## Fix
+Changed `order[status] || 6` → `order[status] ?? 6`. Nullish coalescing (`??`) only triggers on `null`/`undefined`, not on `0`.
+
+## Pattern Class
+**JS/TS Falsy Coercion Trap** — `||` treats `0`, `""`, `false` as falsy. Use `??` for numeric/boolean defaults.
+
+## Future Trigger
+- Any JS/TS code writing numeric defaults
+- Any ranking/scoring/ordering logic
+- Any code with `value || default` where value can legitimately be 0
+
+## Checklist
+- [ ] Grep all `||` in scoring/ranking/ordering code → replace with `??` if value can be 0
+- [ ] For all numeric defaults: `||` → `??`
+- [ ] Add `||` vs `??` check to JS/TS Domain Checklist
+
+## Recurrence Count
+2 — previously hit in Agent Evolution FK index scoring (same pattern: `count || 0` skipped real zeros)
+```
+
+### 7-field check
+```
+grep -c '^## Context\|^## Root Cause\|^## Fix\|^## Pattern Class\|^## Future Trigger\|^## Checklist\|^## Recurrence' /Users/a1234/.openclaw/workspace/reflections/2026-06-05-falsy-coercion.md
+```
+Result:
+7
+
+### Banned phrase check
+```
+grep -ic '以后注意\|下次小心\|当时没想清楚\|应该多测试' /Users/a1234/.openclaw/workspace/reflections/2026-06-05-falsy-coercion.md; echo "(exit=$?  ;  1=clean)"
+```
+Result:
+0
+exit=1
+
+---
+
+## 8. Reflection: nextjs-path (full file)
+
+### Command
+```
+cat /Users/a1234/.openclaw/workspace/reflections/2026-06-05-nextjs-path.md
+```
+
+### Raw Output
+```
+# Reflection: Next.js `src/app/` vs `app/` Path Convention
+
+> Date: 2026-06-05 | Severity: P0 | Recurrence: 1
+
+## Context
+Domain Benchmark Suite v1 — frontend-builder-agent.mjs 生成的 Next.js 项目输出到 `src/app/` 目录。10/10 项目 Build 失败（0/10 Build）。Next.js App Router 默认 pages directory 是 `app/`。
+
+## Root Cause
+Frontend Builder Agent 的初始设计内嵌了错误的路径假设。模板代码输出到 `src/app/`，但 Next.js `app/` router 不从 `src/app/` 读取。Tailwind content 配置和 tsconfig paths 也指向了错误路径。
+
+## Fix
+全局替换：
+- `src/app/` → `app/`
+- 更新 tsconfig paths 匹配 `app/`
+- 更新 tailwind.config content 匹配 `app/**/*.{ts,tsx}`
+
+## Pattern Class
+**Path Convention Mismatch** — Generator/Builders 有硬编码路径假设，与实际 runtime 的 convention 不一致。
+
+## Future Trigger
+- Any Next.js project generation
+- Any framework-specific builder agent creation
+- Any path-dependent code generation
+
+## Checklist
+- [ ] 验证生成器输出目录与目标框架的 default convention 一致
+- [ ] 在生成器写完第一版后立即跑 build smoke test
+- [ ] tsconfig paths 与 tailwind content 与 pages directory 三者一致性检查
+
+## Recurrence Count
+1
+```
+
+### 7-field check
+Result:
+7
+
+---
+
+## 9. Reflection: ddl-leakage (full file)
+
+### Command
+```
+cat /Users/a1234/.openclaw/workspace/reflections/2026-06-05-ddl-leakage.md
+```
+
+### Raw Output
+```
+# Reflection: DDL CONSTRAINT Leakage into TypeScript Interfaces
+
+> Date: 2026-06-05 | Severity: P0 | Recurrence: 1
+
+## Context
+Backend Builder Agent (SF-04) — `schema.ts` 生成时 DDL PRIMARY KEY / FOREIGN KEY / CONSTRAINT 行被当作数据列，泄露进 TypeScript interface 定义。
+
+Example: `"PRIMARY KEY (id)"` → parsed as column `PRIMARY` with type `KEY`, `FOREIGN KEY (user_id) REFERENCES users(id)` → parsed as column `FOREIGN` etc.
+
+## Root Cause
+DDL parser 没有区分 "column definition" 行和 "constraint" 行。`CREATE TABLE` 语句中的 CONSTRAINT 子句以特殊关键字开头（PRIMARY KEY, FOREIGN KEY, UNIQUE, CHECK），不应被解析为列定义。
+
+## Fix
+Added `isConstraintLine()` check before parsing each line as a column. Lines starting with `PRIMARY KEY`, `FOREIGN KEY`, `UNIQUE (`, `CHECK (` are skipped in column parsing.
+
+## Pattern Class
+**DDL-to-Code Mapping Error** — SQL DDL 的多层结构（column/constraint/index）被扁平化为单一映射时丢失语义。
+
+## Future Trigger
+- Any SQL schema → code generation
+- Any DDL parser
+- Any ORM code generator
+
+## Checklist
+- [ ] DDL 解析器必须有 column / constraint / index 三层分离
+- [ ] Constraint 行识别：PRIMARY KEY, FOREIGN KEY, UNIQUE (, CHECK (
+- [ ] 生成后验证：interface 字段数 ≤ 表列数（不含约束行）
+- [ ] 跑 benchmark 验证所有领域 schema 生成正确
+
+## Recurrence Count
+1
+```
+
+### 7-field check
+Result:
+7
+
+---
+
+## 10. Reflection: jsx-template (full file)
+
+### Command
+```
+cat /Users/a1234/.openclaw/workspace/reflections/2026-06-05-jsx-template.md
+```
+
+### Raw Output
+```
+# Reflection: JSX Template Ternary Nesting Syntax Error
+
+> Date: 2026-06-05 | Severity: P0 | Recurrence: 1
+
+## Context
+Frontend Builder Agent (SF-03) — fallback page 模板中的三元表达式产生了语法错误。模板生成代码如 `{loading ? {<Spinner />} : {<div>No data</div>}}`。
+
+## Root Cause
+生成器模板中 JSX 三元表达式嵌套了多余的 `{}`。模板本身输出 `{` 字符，内嵌的 JSX 也带 `{` — 双层花括号导致 React 解析失败。
+
+Incorrect output pattern: `{condition ? {<JSX />} : {<AnotherJSX />}}`
+Correct: `{condition ? <JSX /> : <AnotherJSX />}` 或 `{condition ? (<JSX />) : null}`
+
+## Fix
+Fixed template to not wrap JSX branches in extra `{}`. The outer `{}` (JSX expression) already handles one level; inner JSX elements don't get re-wrapped.
+
+## Pattern Class
+**Template Code Generation Syntax** — 代码生成器的模板本身使用目标语言语法时，转义/嵌套层次需仔细处理。
+
+## Future Trigger
+- Any code generator that outputs JSX/TSX
+- Any template-based code generation
+- Any string-template code with nested braces/quotes
+
+## Checklist
+- [ ] 生成器模板验证：输出后立即 `tsc --noEmit` 检查语法
+- [ ] JSX 三元表达式：禁止 `{cond ? {<X />} : {<Y />}}` 模式
+- [ ] 模板中使用 `\`` 或字符串拼接替代包含反引号的模板字面量
+- [ ] Benchmark smoke test 覆盖所有生成项目的 build
+
+## Recurrence Count
+1
+```
+
+### 7-field check
+Result:
+7
+
+---
+
+## 11. Old Reflection: 2026-06-03 (upgraded, head 30)
+
+### Command
+```
+head -30 /Users/a1234/.openclaw/workspace/reflections/2026-06-03-agent-evolution.md
+```
+
+### Raw Output
+```
+# Reflection: Agent Evolution Mode — 四阶段全流程
+
+> Date: 2026-06-03 | Severity: P0/P1 (multiple failures) | Recurrence: see individual patterns
+
+## Context
+深度学习 ECC/Headroom/CodeGraph → 提取能力 → 增强 OpenClaw。4 Phase，16 模块，7,000 行，5h（预估 42.5h）。
+
+## Pattern Classes Extracted
+
+### PC-1: SQLite FK Constraint (P0) — Pattern Class: SQL FK/DELETE semantic
+- **Root Cause**: INSERT OR REPLACE causes rowid change → FK breaks
+- **Fix**: ON CONFLICT DO UPDATE preserves original rowid
+- **Future Trigger**: any SQL schema modification, batch inserts with FK
+
+### PC-2: Heuristic False Positive (P1) — Pattern Class: single-signal detection
+- **Root Cause**: `[2026-...` prefix triggered JSON detection without valid parse
+- **Fix**: require 2+ signals (prefix + valid JSON.parse)
+- **Future Trigger**: any heuristic/content-type detection logic
+
+### PC-3: Nested Structure Parsing (P1) — Pattern Class: protocol-level vs structural parsing
+- **Root Cause**: parser relied on structured JSON nesting, failed on content arrays
+- **Fix**: match "type":"tool_result" byte patterns instead of tree traversal
+- **Future Trigger**: any nested data structure parsing
+
+### PC-4: Overly Aggressive Sampling (P2) — Pattern Class: lossy strategy without safety net
+- **Root Cause**: TimeSeries strategy kept only anchor points (500→5), dropped errors
+- **Fix**: include error/outlier detection alongside anchor selection
+- **Future Trigger**: any sampling/compression strategy design
+
+## 成功经验
+```
+
+### Pattern Class / Future Trigger / Recurrence count
+Result:
+10
+
+---
+
+## 12. Old Reflection: 2026-06-04 (upgraded, head 20)
+
+### Command
+```
+head -20 /Users/a1234/.openclaw/workspace/reflections/2026-06-04-memory-audit.md
+```
+
+### Raw Output
+```
+# Reflection: Memory System Full Audit
+
+> Date: 2026-06-04 | Severity: P0/P1/P2 mixed | Recurrence: 1
+
+## Context
+记忆系统全量审计 + 全链路修复。6 维度扫描（文件/远程/版本/自动化/索引/寄存器），P0(5)→P1(5)→P2(4)。
+
+## Pattern Class: Infrastructure Drift
+
+**Root Cause**: 脚本存在 ≠ 脚本在运行。Dream Cycle cron 从未配置，index.md 从未自动更新（15→75 条差距）。
+
+**Fix**: 添加 3 个 cron jobs（Dream Cycle + Git push + Health check），session-compact.sh 加 pre-compact hook。
+
+**Future Trigger**: any automated maintenance system, any cron-scheduled task, any script that "should run automatically"
+
+**Checklist**:
+- [ ] 新脚本添加后立即验证 cron/trigger 是否配置
+- [ ] 定期检查 index/registers 的 freshness
+- [ ] 引用即承诺——引用未创建的文件要么创建要么删引用
+
+```
+
+### Pattern Class / Future Trigger / Recurrence count
+Result:
+3
+
+---
+
+## 13. patterns/best-practices.md — full numbered entry list
+
+### Command
+```
+grep -n '^[0-9]*\.' /Users/a1234/.openclaw/workspace/patterns/best-practices.md
+```
+
+### Raw Output
+```
+11:1. **写完即测，不等集成** — 每个模块 run 一次确认输出正确
+12:2. **边界用例覆盖** — 空输入、超大输入、非法输入都要测
+13:3. **零依赖优先** — 核心算法不自带 npm 依赖（例外: better-sqlite3 等已安装的稳定库）
+14:4. **CLI + Library 双接口** — `node module.js` 和 `require('./module')` 都要能用
+15:5. **passthrough 是默认** — 任何操作失败时返回原始输入，不丢数据
+19:6. **Phase Isolation** — 分析/设计/实现三阶段不交叉
+20:7. **先 MVP 再扩展** — 1-3h 出第一个可用版本，验证后扩展
+21:8. **策略可插拔** — 用分发模式，新增策略不碰核心逻辑
+22:9. **降级路径明确** — 每个操作至少 2 条降级路径
+23:10. **配置可覆盖** — 全局默认 → 项目覆盖 → 运行时参数
+27:11. **FK 约束用 ON CONFLICT DO UPDATE** — SQLite 的 REPLACE = DELETE+INSERT
+28:12. **检测需多重信号** — 启发式规则必须 2+ 个信号同时匹配
+29:13. **WAL 模式开** — 多进程读不阻塞写
+30:14. **大文件分批处理** — 每 250 文件回收一次 WASM/内存
+31:15. **stderr 和 stdout 分离** — 元数据用 stderr，数据用 stdout
+35:16. **`||` vs `??` — 用 ?? 处理数字 0** — `value || default` 把 0/''/false 当 falsy。数字类用 `value ?? default`。已犯 2 次（Agent Evolution FK索引 + Cross-Agent Certification 评分排序）
+36:17. **模板字面量反引号** — 模板内嵌反引号用 \` 转义或改用字符串拼接。不输出裸反引号到生成代码
+37:18. **类型单数化** — entity 复数→单数（Albums→Album, Pets→Pet），但不碰 status/bus 等不可变词根
+41:19. **Next.js 路径：app/ 不是 src/app/** — Next.js App Router 默认 pages in `app/`。生成器必须输出到 `app/` 目录
+42:20. **DDL CONSTRAINT 泄露** — schema.ts 生成时 PRIMARY KEY / FOREIGN KEY / CONSTRAINT 行不能被解析为 TS interface 字段
+43:21. **CreateInput 完整性** — generateTypes 必须包含所有实体（包括 User）→ CreateUserInput 不能缺失
+44:22. **JSX 三元嵌套** — `{a ? {b} : {c}}` 错误。改为 `{a ? b : c}` 或 `{a ? (<Comp />) : null}`
+48:23. **子 agent 并行分析** — 3 个项目同时 spawn，2-3 分钟完成
+49:24. **子 agent 用 Pro 模型** — 代码/方案决策用 DeepSeek V4 Pro
+50:25. **任务描述要包含完整输出路径** — 子 agent 不需要父 agent 上下文也能工作
+51:26. **用 sessions_yield 等完成** — 不 poll loop
+55:27. **Exit code 规范** — PASS/WARN→0, FAIL→1。不要 PASS 也 exit 1
+56:28. **向后兼容** — 新增参数用 optional，不改既有函数签名。所有 PR 遵守零修改约束
+60:29. **每完成一个 Phase 写 daily** — 不等到全部做完
+61:30. **提取模式后立即写 patterns/** — "mental notes 不存活"
+62:31. **MEMORY.md 尽量不动** — 在缓存线以上，每次改动全缓存爆炸
+63:32. **Reflection 必须结构化** — 含 Pattern Class + Future Trigger + Checklist，禁止"以后注意"
+
+### New sections proof
+```
+grep -n 'JavaScript.*TypeScript 陷阱\|Generator.*Builder 陷阱\|CI.*Release' /Users/a1234/.openclaw/workspace/patterns/best-practices.md
+```
+Result:
+33:## JavaScript / TypeScript 陷阱
+39:## Generator / Builder 陷阱
+53:## CI / Release
+
+---
+
+## 14. patterns/design-patterns.md — Anti-Patterns
+
+### Command
+```
+grep -n 'Anti-Patterns\|AP-[123]' /Users/a1234/.openclaw/workspace/patterns/design-patterns.md
+```
+
+### Raw Output
+```
+5:> 新增: Anti-Patterns (≥2 occurrences → promoted from reflections)
+117:## Anti-Patterns (from failures, ≥2 occurrences)
+119:### AP-1: Operator Coercion Trap (2 occurrences)
+136:### AP-2: Generator Path Assumption (1 occurrence)
+147:### AP-3: DDL Flat Mapping (1 occurrence)
+
+### AP-1 full body
+```
+sed -n '119,138p' /Users/a1234/.openclaw/workspace/patterns/design-patterns.md
+```
+
+### Raw Output
+```
+### AP-1: Operator Coercion Trap (2 occurrences)
+
+**问题**: JavaScript `||` 把 `0`/`""`/`false` 当 falsy，导致排序/评分/计数逻辑出错
+
+**症状**:
+- 排序结果反转（healthy=0 排到最后）
+- FK 索引计数字段被跳过
+
+**方案**: 数值/布尔默认值用 `??`（nullish coalescing），`||` 仅用于字符串默认值。
+Grep `||` in scoring/ranking code.
+
+**来源**:
+- 2026-06-03: Agent Evolution FK 索引 `count || 0`
+- 2026-06-05: PR-30 Cross-Agent Certification `order[status] || 6`
+
+---
+
+### AP-2: Generator Path Assumption (1 occurrence)
+
+**问题**: Builder/Generator 有硬编码路径假设（如 `src/app/`），与实际 framework convention 不一致
+
+---
+
+## 15. vault.md — Promotion Log + Learning Loop
+
+### Command
+```
+grep -n 'Learning Loop\|Promotion Log\|闭环\|1st→\|2nd→\|3rd→' /Users/a1234/.openclaw/workspace/memory/vault.md
+```
+
+### Raw Output
+```
+142:### Learning Loop v1 (2026-06-05 建立)
+144:闭环架构：
+152:1st→Reflection  2nd→Anti-Pattern  3rd→Best Practice  4th→Domain Checklist  5th→Hard Rule
+159:### Promotion Log (≥2 occurrences tracked)
+
+### Promotion Log table
+```
+sed -n '/Promotion Log/,/已验证模式/p' /Users/a1234/.openclaw/workspace/memory/vault.md
+```
+
+### Raw Output
+```
+### Promotion Log (≥2 occurrences tracked)
+
+| Pattern Class | Count | Stage | Promoted To |
+|--------------|-------|-------|------------|
+| JS Falsy Coercion (`\|\|` vs `??`) | 2 | Anti-Pattern | patterns/design-patterns.md §AP-1 |
+| Generator Path Assumption | 1 | Reflection | reflections/2026-06-05-nextjs-path.md |
+| DDL Flat Mapping | 1 | Reflection | reflections/2026-06-05-ddl-leakage.md |
+| JSX Template Nesting | 1 | Reflection | reflections/2026-06-05-jsx-template.md |
+
+### 已验证模式 (从 Agent Evolution 提取)
+
+---
+
+## 16. MEMORY.md — Learning Loop reference
+
+### Command
+```
+grep 'Learning Loop' /Users/a1234/.openclaw/workspace/MEMORY.md
+```
+
+### Raw Output
+```
+具体技巧：注释写 WHY · Fast-Path 入口 · 错误三分类 · 目录即模块 · 失败快速 · Pre-flight Check · Failure Replanning · Learning Loop (2026-06-05)
+
+---
+
+## 17. Reflections directory listing
+
+### Command
+```
+ls -la /Users/a1234/.openclaw/workspace/reflections/
+```
+
+### Raw Output
+```
+total 56
+drwx------   8 a1234  staff   256 Jun  5 22:37 .
+drwx------  62 a1234  staff  1984 Jun  5 22:05 ..
+-rw-------   1 a1234  staff  5304 Jun  5 22:41 2026-06-03-agent-evolution.md
+-rw-------   1 a1234  staff  2630 Jun  5 22:41 2026-06-04-memory-audit.md
+-rw-------   1 a1234  staff  1432 Jun  5 22:37 2026-06-05-ddl-leakage.md
+-rw-------   1 a1234  staff  1258 Jun  5 22:36 2026-06-05-falsy-coercion.md
+-rw-------   1 a1234  staff  1436 Jun  5 22:37 2026-06-05-jsx-template.md
+-rw-------   1 a1234  staff  1265 Jun  5 22:36 2026-06-05-nextjs-path.md
+
+---
+
+## 18. Cross-file consistency: vault Promotion Log ↔ design-patterns AP counts
+
+### vault says about AP-1
+```
+grep -A1 'JS Falsy Coercion' /Users/a1234/.openclaw/workspace/memory/vault.md | head -2
+```
+Result:
+| JS Falsy Coercion (`\|\|` vs `??`) | 2 | Anti-Pattern | patterns/design-patterns.md §AP-1 |
+| Generator Path Assumption | 1 | Reflection | reflections/2026-06-05-nextjs-path.md |
+
+### design-patterns says about AP-1
+```
+grep 'AP-1.*occurrences' /Users/a1234/.openclaw/workspace/patterns/design-patterns.md
+```
+Result:
+### AP-1: Operator Coercion Trap (2 occurrences)
+
+### vault says about Path Assumption
+```
+grep -A1 'Generator Path' /Users/a1234/.openclaw/workspace/memory/vault.md
+```
+Result:
+| Generator Path Assumption | 1 | Reflection | reflections/2026-06-05-nextjs-path.md |
+| DDL Flat Mapping | 1 | Reflection | reflections/2026-06-05-ddl-leakage.md |
+
+### design-patterns says about AP-2
+```
+grep 'AP-2.*occurrence' /Users/a1234/.openclaw/workspace/patterns/design-patterns.md
+```
+Result:
+### AP-2: Generator Path Assumption (1 occurrence)
+
+---
+
+## 19. 4 new reflections — aggregate 7-field + banned check
+
+### Command
+```
+for f in /Users/a1234/.openclaw/workspace/reflections/2026-06-05-*.md; do
+  name=$(basename "$f")
+  fields=$(grep -c '^## Context\|^## Root Cause\|^## Fix\|^## Pattern Class\|^## Future Trigger\|^## Checklist\|^## Recurrence' "$f")
+  banned=$(grep -ic '以后注意\|下次小心\|当时没想清楚\|应该多测试' "$f" || echo 0)
+  echo "$name: fields=$fields/7 banned=$banned"
+done
+```
+
+### Raw Output
+```
+2026-06-05-ddl-leakage.md: fields=7/7 banned=0
+0
+2026-06-05-falsy-coercion.md: fields=7/7 banned=0
+0
+2026-06-05-jsx-template.md: fields=7/7 banned=0
+0
+2026-06-05-nextjs-path.md: fields=7/7 banned=0
+0
+
+---
+
+## 20. AGENTS.md section structure (numbering integrity)
+
+### Command
+```
+grep -n '^###\|^##' /Users/a1234/.openclaw/workspace/AGENTS.md | head -35
+```
+
+### Raw Output
+```
+5:## Cache Stability ⚡
+12:## Session Startup
+18:## Execution Protocol — Planning Layer 🔵
+24:### 0. Complexity Classification (MUST run first)
+52:### 1. Planning Protocol (Complex Tasks ONLY)
+57:## PLAN
+58:### Goal
+61:### Subtasks
+66:### Risks
+70:### Verification Strategy
+78:### 2. Pre-flight Check (Complex Tasks ONLY)
+82:#### 2a. Dependency Scan
+90:#### 2b. Learning Context Injector (MANDATORY — 3 searches)
+109:### Injected Risks (from Learning Context)
+115:#### 2c. Domain Checklist Injection
+156:### 3. Failure Replanning Protocol
+183:### 4. Verification Protocol (Complex Tasks ONLY)
+188:## VERIFICATION
+208:### 5. Auto-Capture Trigger — COMPLETE Rule Set (after ANY failure)
+240:## Learning Loop 🔄
+245:### Loop Architecture
+267:### Promotion Rules
+277:### Quality Gate for Reflections
+291:### Storage Locations
+306:## Memory
+314:## Red Lines
+322:## External vs Internal
+327:## Group Chats
+335:## Security Baseline 🔒
+344:## Heartbeats
+
+---
+
+## END OF VERIFICATION LOG
+
+- Total checks: 20
+- Files verified: AGENTS.md, patterns/best-practices.md, patterns/design-patterns.md, memory/vault.md, MEMORY.md
+- Reflections: 2026-06-05-falsy-coercion.md, 2026-06-05-nextjs-path.md, 2026-06-05-ddl-leakage.md, 2026-06-05-jsx-template.md
+- Old reflections upgraded: 2026-06-03-agent-evolution.md, 2026-06-04-memory-audit.md
+- Cross-file consistency: vault Promotion Log ↔ design-patterns AP counts — MATCH
+- All 4 new reflections: 7/7 required fields, 0 banned phrases
+- ARCHIVED for future audit traceability