宜博 / lemonboss

把「人类提的一个需求」与「机器执行的一件活」拆成两级。这不是新概念：
27-NAMING §四 早就定义了 goal 1 : task N，graph_runs.goal_id / task_id
两列从 P3 起就一直在写，却没有任何表接得住 —— 本次补上那两张缺席的表。

## 交付
- goals / tasks 两张表 + CRUD + depends_on 环检测 + ID 生成器
  T-{base36}-{4hex}：原格式同毫秒必撞，而 tasks.id 是主键，
  「一个 goal 拆 N 条 task」是循环建行，撞了就是 500
- goal / task 全套端点；POST /:cid/tasks 向后兼容（不带 goal_id 自动
  建 goal）；退役 /api/goals 与 /:cid/goals 两个 OKR 别名（零调用方）
- 终态回写 + goal 收敛 + OKR 写一次：钩子挂在唯一漏斗
  graph-run-sse.transitionRun 上，而不是枚举路径 —— stopRun 与
  「预算耗尽 → blocked」两条最常见的释放路径都不走 settleRun，
  枚举一次漏一次。goal 收敛用 CAS 闸门，并行完成的 N 个 task 只有
  一个赢家做不可重放的副作用（写 OKR / 唤醒上级）
- blocked 在 task/goal 两层都不是终态：它是「挂起等人介入」，
  与 completed/failed/cancelled 不同类。否则预算耗尽后加预算恢复、
  跑完，两次条件更新静默命中 0 行，最终 run=completed 而
  task=blocked/goal=failed/OKR=failed 永久对不上（实跑复现过）
- goal 级是唯一汇报出口：删掉 run 级 reportRunOutcome（零其它调用方），
  1 goal:1 task 形态下它会把上级 agent 就同一件事唤醒两次
- dispatch 挑第一条可跑的 draft，而不是恒取 seq 最小那条 ——
  否则「第 1 条依赖第 2 条」这种合法输入会让 goal 永远下达不了
- 路径缺陷：writeTaskGoalArtifact 不认 GRAPH_RUNS_DIR 而读侧认，
  设了 env 就写进 A 处、从 B 处读，describeTask 拿到 null 后静默退回
  兜底文案「执行图节点任务」；三处模块加载时快照改为调用时读
- 存量回填脚本（幂等 + --dry-run）：不做的话批 1 反而让历史任务
  更看不见 —— 正是本批要修的问题的反向放大

## 过程
三轮多 agent 编排 + 每轮对抗复核，共报出 19 条缺陷（10 条首轮实现的、
4 条第二轮修复引入的、5 条判定为非问题）。全部已修并有用例覆盖。
新增测试 4 个文件，含不变式测试 runs-root-single-holder（凡是声明了
GRAPH_RUNS_DIR 覆盖的模块，该覆盖必须真的被用到）。

全量：116 文件 / 1057 测试全绿。

## 未做（属批 2-5）
task-planning 与 goal 级 org-validator 验收（批 2）、调度器与
run_status='queued'（批 3）、并行（批 4）、两套任务体系统一（批 5）。

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

system/templates/ 已随 28 号改造整体并入 system/agents/，目录在磁盘和 git 里都已不存在。
但引用还散在各处，其中几处是 agent 运行时真会照着读写的：

本体提示词（读不到就静默降级，不报错）
  workgraph-planning/agent.md   system/templates/base/ ×3、模板库路径 ×1
  orggraph-planning/agent.md    同上 ×1
  orggraph-planning/tools.md    ×1
  org-innovator/agent.md        四条产出落点 system/templates/weibo-scraper/train/*

skill 代码里的硬编码目标
  evolver-youtube-crawler 的 refactor.js / mock_setup.js / evolve.js 共 4 处
  innovator-hunt/collect_seed.js —— 这处是真 bug 且已发作过：
    写的是裸相对路径 'system/templates/…'，相对 cwd 解析，于是在 agent 自己目录下
    造出一棵野生嵌套树 system/agents/innovator-hunt/system/templates/…
    现在改成由 __dirname 推导，不再依赖 cwd（cwd 已经是深度 3 的任务态目录）

图模板契约（work-graph-templates / org-graph-templates 的 README）
  CI 防线的三条规则写的还是「在 system/templates/ 下必须有目录」「在
  system/templates/_registry.json 里必须有条目」，与实际执行的检查已经对不上

DevLoop PRD（13 份 HTML + 重新生成的 52 份 _spec + build-manifest + search-index）
  写的是 system/templates/devloop-pm.md（扁平 .md）。根和形状都错：
  loop-controller.js:166 实际读的是 system/agents/{agentName}/prompt.md。
  按真实形状改，然后跑 spec:extract / extract-manifest / build-search-index 重新生成。

顺带订正两处早于本次改造就已过期的内容：
- 「避开 6 个命名冲突 id」这条约束列的 digester / evolver / hunter / innovator
  四个 id 根本不存在（早已改名），而它的理由（两个目录下各有一份、内容不同步）
  也已随合并消失。约束保留（元 agent 本来就不该进执行流），理由与清单按实际本体重写。
- orggraph-planning/agent.md 里「真相源是 company.json.agents[]」——
  28 号起真相源是 company_agents 表，company.json.agents[] 仅作兼容保留。

刻意不动的三类（改了是净损失）：
  历史说明   server/ 下解释「原来指向 X、批次 1 并进了 Y」的注释、docs/done/、tasks/
  完成证明   server/tests/ 里断言该目录已不存在的守卫
  运行态记录 未跟踪的 workspace/ conversations/ 与 train/ 下的历次训练报告

新增 server/tests/unit/no-stale-templates-path.test.js 守住活定义这一档：
扫 system/ 与 fixtures/ 下被 git 跟踪的文件（跟踪=人工维护的定义，
未跟踪=运行态产物），零例外。带「样本非空」前置断言防 git 失灵时退化成永远通过。
改坏一处实测能精确点名到文件行号。

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

28 号把本体根从 system/templates/ 搬到 system/agents/，agent-locator 就是
为了当这个路径的唯一持有者而建的。但搬完之后仓库里仍有 13 处自己拼这个路径，
等于 locator 只是多了一份副本、没有真正收敛：

  server/routes/company.js            9 处（6 个 TEMPLATES_DIR + 3 个 DATA_DIR，
                                          同一文件里只有 1 处用了 locator）
  server/services/task-service.js     1 处
  server/src/core/skill-config-loader.js  1 处
  server/src/core/devloop/loop-controller.js  1 处
  scripts/extract-agent-prompts.js    1 处

危害不是「不好看」，而是下一次再搬时改 12 处、漏 1 处：漏掉的那处指向一个
不存在的目录，而本仓库读这类路径几乎都包在 fs.existsSync() 守卫里 ——
目录没了不报错，只是静默跳过。这个形状刚在 scripts/demo-harness-company.js
上实测过（base 本体没挂上，demo 跑出来的 agent 没有四段式骨架，脚本照常打印成功）。

局部变量名保留不动（TEMPLATES_DIR / DATA_DIR / SYSTEM_AGENTS_DIR / agentsRoot /
OUT_DIR），只把取值改成 locator.AGENTS_ROOT —— 名字是局部别名，无害；
「路径这个事实」则收敛成一处，下次再搬只改 agent-locator.js。

新增 server/tests/unit/agents-root-single-holder.test.js 锁住这条不变式：
扫 server/ packages/ scripts/ 下所有源码，禁止 path.resolve/join 自己拼
「以 ../ 开头、以 system/agents 结尾」的字面量。带「样本非空」前置断言，
防止扫描路径写错时退化成永远通过。改坏一处实测能精确点名到文件行号。

线索来自并行会话（它在准备改 company.js 时发现同一文件里 7 份定义）。
实际比它看到的更多：它只查了 TEMPLATES_DIR，同文件另有 3 个 DATA_DIR、
另外 3 个文件各 1 处。

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

设计见 docs/done/system-design/28-agent-registry-unification.md。

改造前 Agent 本体散在三处（system/agents/ 11 个、system/templates/ 50 个、
data/companies/{id}/agents/ 17 个），同一个 AgentScaffold 被三个 baseDir 实例化。
后果是同一角色在 N 家公司下有 N 份互不相干的副本，模板更新不会同步；
org-coder / org-planner 这类走 hireFromBaseMetaAgent 造出来的本体
legacy_path 指回自己公司目录，永远无法被第二家公司复用。

本次：
- G1 单一注册表：system/templates/ 整体并入 system/agents/，base → _base。
  7 个同名 id 逐个裁决，被丢弃的一份归档到 docs/_archive/ 而非删除。
  source_kind(template/global_agent/company_hired) → origin(builtin/created)。
- G2 运行态下沉：CLI 的 cwd 从本体根改为 system/agents/{aid}/{cid}/{taskId}/。
  memory / conversations 落公司态 {aid}/{cid}/，按公司隔离不串。
  sessionPool 的 key 含 (companyId, taskId)，两家公司调同一 agent 不复用会话。
- G2b 产物不下沉：交付物仍落 data/companies/{cid}/，system/agents/ 只留运行痕迹。
  写入边界按链路分叉——graph 节点走节点私有目录（被 indexNodeOutputs 索引），
  chat 走公司 workspace，同一提示词里不再出现两条互斥指令。
- G3 公司只存引用：data/companies/{id}/agents/ 删除，新增 company_agents 关联表。
  不复用 org_graph_nodes——后者是执行流图，work 层本体被雇时不写它，天生覆盖不全。
- G4 缺则创建：本体缺失时从 _base 复制骨架进 system/agents/{id}/，
  agent-creator 填 agent.md/soul.md 后才从 draft 转 active（哨兵判据，
  骨架未填时哨兵仍在，不许被 hire）。产物即刻是全系统可复用的本体。

新增 server/services/agent-locator.js 收编原先散在 6 处的寻址逻辑。

边界守卫（graph-engine）的豁免从「本体根上五个文件名」放宽为整棵 system/agents/：
新本体的骨架本来就要进 git，gitignore 挡不住 ?? system/agents/{newId}/，
旧判据会把一个真正成功的招聘节点判成 boundary_escape fail。

存量迁移见 scripts/migrate-agent-registry.js（幂等，备份到 data/_migration-backup-*）。

真 Claude CLI E2E 已验证：新建公司 → orggraph-planning 自动规划 →
自动招聘 org-planner/org-coder/org-validator 三节点流水线；
data/companies/{cid}/agents/ 不存在，company_agents 4 行，
system_agents 56→56（零新建私有本体，纯复用），git status 零增量。

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

用户授权清理 system/templates/ 的过期引用。全仓库核了 34 处，
结论与预期相反：没有该删的死代码，但有两处正在静默失效。

真正坏掉的（demo-harness-company.js）：
  path.join(ROOT, 'system/templates/base/agent.md')   → system/agents/_base/
  path.join(ROOT, 'system/templates/base/config.json') → system/agents/_base/
两处都包在 fs.existsSync() 里，所以目录消失后**不报错**，只是
静默跳过 base 本体的挂载 —— demo 跑出来的 agent 没有四段式骨架，
但脚本照常打印成功。又一个静默降级。

顺带：real-pm-smoke.js 的提示文案、migrate-agent-naming.js 里
已失效的遍历项、docs/README.md 的 qa-judge 落点。

CLAUDE.md 目录速查表原来只有 `system/templates/devloop-*/` 一行，
连 system/agents/ 都没列。换成两行并写清三个容易踩的点：目录才是
数据源头（seedAgents 直接扫目录）、_registry.json 只补
benchmark_score、_ 前缀是保留 id 会被跳过。

**刻意不动的**：server/tests/ 下 30 处引用。它们分两类，都得留 ——
① 记录迁移过程的注释；② 断言目录已不存在的守卫
（`expect(git(['ls-files','--','system/templates'])).toBe('')`、
`expect(fs.existsSync(...)).toBe(false)`）。删掉后者等于删掉
「迁移已完成」的证明。legacy_path 那几个测试夹具同理，是历史数据形态。

验证：三个脚本 node --check 通过；改后的四个路径实测存在。

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

控制台原先只能看引擎的事件轨（stream.log / timeline.ndjson），里面是结构化事件、
自由文本还被截断到 600 字；引擎更是根本不消费流式 chunk（onAcpEvent 只取
session/result 的 usage）。所以 LLM 的逐字输出从来不在它的轨道上。

新端点 GET /api/graph-runs/:id/nodes/:nodeRunId/transcript **惰性读** Claude CLI
自己的会话文件：不进 SSE、不进节点行、不落第二份库 —— 那正是引擎当初决定不存全文的
三条理由要避免的（输出无上限而 getRunState 每次轮询 SELECT * 全量回传 /
产物已有 output_ref 这个唯一真相源 / fail_reason 是选边匹配键不能掺自由文本）。
这里没有推翻那个设计，只是多开一个读取入口。

目录推导与条目规范化抽到 server/services/agent-transcript.js，
scripts/tail-agent.js 改为复用它 —— 一份实现两个入口。今天已经修过三次
「两份必须保持一致的实现漂了」，不想制造第四次。

## 界面上明说的三个前提（不藏）

1. transcript 按 (公司, 角色) 分、**不按节点分**，只能用节点 started_at/completed_at
   截时间窗口 —— 近似而非精确对齐，窗口边界原样显示。
2. <env_status>（harness 每轮注入的环境块，几 KB 机器噪音）服务端剥掉，
   但**剥了几处如实显示**。静默删内容比留噪音更坏。
3. 默认只看 agent 说的话；喂进去的内容（提示词全文、工具返回）要勾选才出来 ——
   提示词里有写入边界与公司上下文，不默认摊开，但可以看。

subgraph 节点不给这个 tab（它自己不调 agent，活在子图里）—— 给了就是个空 tab，
而空 tab 会被读成「没记录」。正在跑的节点靠「刷新」取最新，**不轮询**
（整份会话几百 KB，跟着 run 状态轮询太贵）。

## 三处「看着对、实际错」都有用例钉住

① listRoles 的目录前缀差一个 '-'：path.join 丢掉空的最后一段，切出来的角色名
   全带前导 '-'（实测 '-sdd-planning'）。我是靠肉眼看输出发现的，所以补回归测试。
② 路由取本体取错层：本体绑在定义层节点上，graph_run_nodes 只有 def_node_id，
   第一版直接读运行时行 → SqliteError: no such column。
③ 找不到文件时回 ok:false + 期望目录，不回空列表 ——
   空列表会被读成「这个 agent 没说过话」，而真相是「我们没找到文件」。

另外测试当场抓到我自己那个诚实机制的漏洞：整条正文都是 env_status 的条目会被剥空，
normalize 早返回 null 导致它剥掉的那一处**没计入总数** —— 号称如实回报却少报。
改成 parts 空但剥过东西时仍返回，由 readEntries 先记账再决定入不入列表。

## 验证

880 全绿（88 文件）。3 处变异精确变红后逐字还原。
运行中的实例上走查过：org-planner-sdd 的原文逐条带时间戳显示，
第一条就是它去读上游 prd.md / contract.json —— R-19 那条链路被 agent 真的用上了。
subgraph 节点（org-planner）确认没有这个 tab。

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

控制台「运行日志」看不到 LLM 逐字输出，不是坏了，是引擎按设计不存：

1. **引擎根本不消费流式 chunk**：defaultAgentExecutor 的 onAcpEvent 只处理
   session/result（累 usage）与 mock/files，文本 chunk 一个字都不接。
2. **事件里的自由文本截断到 600 字**（EVENT_TEXT_MAX），graph-engine.js 那段注释
   写了三条理由：完整输出无上限而 getRunState 每次轮询 SELECT * 全量回传；
   完整产物已有地址（output_ref）不该有第二个真相源；fail_reason 是选边的匹配键
   不能掺自由文本。
所以 stream.log / timeline.ndjson 里只有结构化事件 + 短摘要。

但 Claude CLI 自己把完整会话写在
  ~/.claude/projects/<cwd 路径的 / 换成 ->/<sessionId>.jsonl
而 agent 的 cwd 就是 data/companies/<公司>/agents/<角色>，目录名可推。
这个脚本把那份 jsonl 渲染成可读的实时流：

  node scripts/tail-agent.js <公司>                  列出哪些角色有 transcript
  node scripts/tail-agent.js <公司> <角色>            跟看（增量轮询，Ctrl+C 退出）
  node scripts/tail-agent.js <公司> <角色> --last 40  只看最后 40 条

只渲染 assistant 的 text 当「LLM 输出」：user 侧的 text 是喂进去的东西（提示词全文、
每轮注入的 <env_status>），跟看时纯噪音 —— 第一版没滤，实测满屏 env_status。
user 侧只留 tool_result（agent 到底读到了什么，这个有用）。

在运行中的实例上验过：mycompany/sdd-planning 正在跑时列表、--last、跟看三种都对，
角色名写错时明确报「目录不存在 + 先跑列表看有哪些」，不静默空跑。

ponytail: projects 目录名按 CLI 现行的「/ → -」规则推导，规则变了会找不到目录
（会明说，不会假装没输出）。

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

测试 736/736 全绿（68 文件，起点 719/66，净增 17 条，未改任何既有断言）。

W1 · seed 接进启动流程 + 悬空行回收
- server/index.js 与 agent-server.js 均在 listen() 前调 runStartupSeedSafely()
  （幂等、失败降级记日志、不挡服务启动）
- seedTemplates() 此前**没有任何运行时调用方**，只有测试与手动脚本引用，
  于是 system/templates/ 新增本体永远进不了 system_agents，而
  work_graph_nodes.system_agent_id 是指向该表的外键
- 占位 id 回收：legacy_path 已失效的 company_hired 行改为可被 template 就地转正，
  保留行 id 以保外键。此前 seedTemplates 遇占用即 skip，导致污染不可逆：
  lookupSharedAgentMd 恒 null → hire 静默退回全量拷贝 → 模板改动对已雇公司不生效
- 生产库实查：company_hired 0 行（原 10 条悬空全清）、template 45、
  verifyCounts().ok=true、foreign_key_check 空

W2 · 项目根分配（四环闭合）
- ensureProjectRoot 复用 path-resolver.allocateProjectRoot（sandbox 模式）
- 分配 → 进 agent_call 与 planning 两处提示词 + callAgent metadata
  → 落 artifacts/project-root.json（wx 独占）→ readProjectRootRecord 读回
- 子 run 经 createRun 继承 root_run_id，跨层共享同一项目根
- 核实 data/companies/ 在 .gitignore 内，故项目根内的合法写入不会被 W3 守卫误报

W3 · 产出边界守卫（部分，文档如实标注）
- 真 CLI 是子进程直接写盘，引擎拦不住，守卫只能拒收结果、不能回滚
- 7 条「拦不住」的情形逐条列明；文档自述「在 cwd 隔离做掉之前，
  真跑仍应在可丢弃的工作副本里做」

W4 · 修验收 fail-open（性质严重）
- benchmark-validator / testdata-validator 的 Step 表教 agent 写 verdict:"fail"，
  而引擎 FAILING_VERDICTS={attributed,inconclusive} 不含它 → 契约非法的产物
  被判 success 放行。失效方向是放行不是拦截
- org-validator 的审计字段 verdict → audit_verdict：它与 work 层判词写同一路径
  （nodes/<nodeRunId>/attempt-<n>.json），此前只靠「该节点恰好是 subgraph」
  才没被 readNodeProduct 当判词读，属隐患藏在巧合里
- 新增防线 template-verdicts.test.js，从 graph-engine.js 源码取
  FAILING_VERDICTS / ATTRIBUTION_REASONS 扫全部模板；经三次变异验证有效
  （改回 "fail" / 改回 verdict / 造 "ok" 均变红并报精确行号）

真 CLI 冒烟未执行，两条理由（终验 agent 自行判断，符合任务给的门槛）：
① W3 按其自身文档明确「不是沙箱」且要求真跑在可丢弃副本里做，而当前是主仓库、
   持有未提交交付物、且有并行 agent 在写，W3 自述的误判项必然触发；
② 断点已零成本静态证明：getAgentConfig 解析裸名只查 system/agents/、
   从不查 system/templates/，resolveAgentName 不做按需 hire，实测 prd-planning /
   sdd-planning / benchmark-validator / testdata-validator / validator-triager /
   org-validator 全部 throw「Agent not found」。花 $3-8 复现已知断点无意义。
故「做完这四件就能真跑」不成立，真跑挪到 W5/W6 之后。

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

界面走查（真 server + HTTP + 真 AgentManager，底层 mock 协议）已把
manual 模式全流程点通：org 节点起子图 → 下钻 work graph → 单步 →
第 3 步触发回退（徽标 0/3→1/3、run 级 1/5 双层计数同时可见）→
归因记录与 remediation_note 完整送达 → 收敛后父节点结算、左栏前移。

mock 侧补两处缺失接线（都是「四环漏一环」，非新功能）
- ClaudeCliProtocol._sendMockPrompt 按 agent 类型查 fixture：图执行侧的
  agent 名带公司前缀（resolveAgentName 返回 {cid}:{id}），fixture 不该
  按公司复制一份。DevLoop 侧名字不含冒号，行为不变
- graph-engine.defaultAgentExecutor 接住 mock/files 事件：此前只有
  DevLoop 的 loop-controller 接，图执行侧没接，于是 mock 下
  readNodeProduct 永远找不到 attempt-{n}.json，validator 系节点恒 blocked。
  写入限制在节点产物目录内，越界丢弃并留痕

新增 5 份 P3 fixture（workgraph-planning / prd-planning / sdd-planning /
coder-validator / validator-triager），coder-validator 用 sequence 演示
一次回退。图必须放 chunks 不能只放 result——callAgent 的 output 来自
流式 chunks，session/result 的文本不进 output。

控制台入口：CompanyDashboard 加「🕸️ 执行控制台」按钮（路由早已注册，
此前无任何入口，只能手敲 URL）。

scripts/p3-demo-setup.js：手工测试准备脚本（雇人+写图+起 run），头部
写明它是两个已知缺口的绕行，缺口修好后第 1 步即可删。

_registry.json 补齐 6 条本体登记（brd/prd/sdd-planning、goal-benchmark、
benchmark/testdata-validator）——同轮新增的 template-refs 防线测试正是
因为缺这 6 条而变红，防线抓到了「交付与报告不符」。

文档
- 27-REQ R-18：招聘归 workgraph-planning（方案 a）、停用 mock 改真 CLI
- 27-P3B 真实运行前置（新增）：11 个工作项分三批，含现状核实 10 条证据
  （seedTemplates 无运行时调用方、10 条悬空 company_hired 行、
   FAILING_VERDICTS 不含 "fail" 导致验收假放行等）

测试 719/719 全绿（66 文件）。

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

命名轴是「节点在哪一层图里」，把散落的老 agent 归到它实际所处的层级：

  innovator → org-innovator      type='cxo'，是 org graph 层的节点
  hunter    → innovator-hunt     innovator work graph 第 1 阶段
  digester  → innovator-digest   第 2 阶段（输入是 hunt 产出）
  evolver   → innovator-evolver  第 3 阶段

依据：retrain-pipeline.js 的 stepConfigs 就是按 hunter → digester → evolver 顺序
跑的，行 231 明写 steps: ['re_hunt','re_digest','evolve'] —— 这三个本来就是
innovator 的 work graph 三阶段，只是名字没体现出来。

■ 迁移（scripts/migrate-agent-naming.js，--dry-run + 幂等可重跑）
- 8 个目录（system/agents/ + system/templates/），用 git mv 保留历史
- system_agents 表 4 行的 id 与 legacy_path
- 公司实例目录与 company.json.agents[]（本次无公司雇过这四个，实际 0 条）

■ 代码引用点（5 处，手工改）
- retrain-pipeline.js: stepConfigs 的 agent 字段 ×3、agentToStep 映射的 key ×3、
  call_sub_agent 的 evolver 判断
- agent-chat.js: agent 列表过滤里的 innovator
- company.js: 模板训练触发的 agentId

■ 刻意不动的三类同形异义（改了会坏）
1. skill 内部子目录名 {skillDir}/hunter/knowhow.md —— 那是 hunt/digest/evolve
   三阶段的产物目录约定，与 agent 名同形但不同义。涉及 open-api.js:402、
   retrain-pipeline.js:148/374、evolution-loop.js:178、sync-skills.js 的 INTERNAL_DIRS
2. skill 命名空间白名单 —— skill-dir-manager.js 的 CORE_SKILLS、
   migrate-trained-skills.js 的 SYSTEM_SKILLS，那里的 'innovator' 指同名 skill
3. conversations/ 与 system/tasklog/ 下的历史记录 —— 运行态数据，不改写历史

evolver-youtube-crawler 按 §3.4 列为待定，迁移脚本按精确目录名匹配，未误伤。

这四个重命名顺带解决了 27 号文档 §七 挂了很久的 6 个命名冲突 id —— 重命名后
system/agents/ 与 system/templates/ 下不再有同名目录（只剩 agent-creator 与
evolver-youtube-crawler 两个，前者是基础设施角色按规则不改名）。

验证：npm run test:unit 693 全绿（64 files）；test-company-e2e 114/114；
迁移脚本二次执行 dirs=0 dbRows=0 skipped=8（幂等）。

未触碰另一进程正在进行的 P3 文件（graph-engine.js / graph-run-sse.js /
work-graph-db.js / 27-p3-p4-work-graph-console.md / 27-requirement.md）。

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

代码层：
- server/services/goals.js → okr-service.js；GoalsService → OkrService
  · this.goalsDir → okrDir，目录 goals/ → okr/
  · ID 前缀 G- → O-；落盘文件 goal.json → objective.json
  · updateGoal → updateObjective，_nextGoalId/_saveGoal 等同步改名
  · parseNodeId 层级名 ['Goal','Objective','KeyResult','SubTask']
    → ['Objective','KeyResult','SubTask','SubTask']（OKR 无 Goal 这一层）
- server/routes/goals.js → okr.js；:goalId → :objectiveId
- 7 处调用点同步：index.js / agent-server.js / agent-chat.js / company.js /
  company-heartbeat-service.js / prompt-builder.js / test-company-e2e.js
- 前端 OkrDashboard.vue / CompanyDashboard.vue 切到 /api/okr（前后端命名终于一致）
- bin/lemon.js 新增 okr create/add-node/list/status

向后兼容（不破坏任何现有调用方）：
- /api/goals/* 与 /api/company/:cid/goals/* 全部保留为别名，与新路径同时挂载
- task dispatch/report 同时接受 objectiveId(新) 与 goalId(旧)，写入时两字段都留
- bin/lemon.js 保留 goal * 命令别名

迁移脚本 scripts/migrate-goals-to-okr.js（npm run okr:migrate）：
- 目录 data/{,companies/*/}goals/ → okr/；条目 G-xxx → O-xxx
- 改写 objective.json 的 id / nodes 的 key / children 数组、_index.json、
  progress.json 的 goalId、history.log 文本、system/tasklog/*.json 的 goalId+nodeId
- --dry-run 预演；幂等；迁移前自动备份为 *.bak-goals（已加入 .gitignore）
- 处理一个反直觉边界：OkrService 构造函数会自动 mkdir 目标目录，"okr/ 已存在"
  不等于"已迁移过"——只要服务被 require 过一次就留下空壳。用 isEmptyOkrDir()
  区分空壳与真实数据，空壳移除后继续迁移。这个 bug 是在 fixture 上验证时发现的。
- 同样在 fixture 上发现并修掉：nodeId 的值漏改写、tasklog 迁移不幂等

验证：新增 server/tests/unit/okr-service.test.js（7 例，覆盖新命名工作正常 +
迁移纯函数的 ID 改写）；全量 npm run test:unit 652 例全绿。

范围说明：NAMING §五 的 benchmark 三分（skill-/agent-/goal-）本轮未动代码——
该节自身的建议就是存量保持现状、只对新增代码强制前缀，因为 benchmark_runs 等表
服务于线上 Arena 排行榜，改表名/路由是另一次独立迁移。
§二-四 的新 agent id 尚不存在实体，待 P2/P3 实现时按规范创建。

已知遗留（非本次引入）：server/scripts/test-company-e2e.js 早已失效——它按
data/{id}/ 找公司，而 company-service 用的是 data/companies/{id}/，在 HEAD 版本
同样全部断言失败。本次只同步了其中的 OKR 命名，未修这个路径问题。

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

# Conflicts:
#	system/agents/master/.claude/scheduled_tasks.json

Adds server/services/graph-db.js (new data/graph.sqlite: system_agents,
org_graph_nodes, org_graph_edges) and graph-seed-service.js, which scans
system/agents/, system/templates/, and data/companies/*/company.json into
seed rows without touching company-service.js's existing hire/copy path.

Real repo data diverged from the design doc's original estimates (8 not 10
global agents; 39 not 34 template dirs; system/agents/ and system/templates/
turn out to share 6 ids describing the "same" agent from two different
files) — documented in docs/todo/system-design/27-graph-agent-architecture.md
section 7 for P1/P2 to resolve.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

First successful real-CLI agent invocation. After REAL.1 (system-prompt
injection) + REAL.2 (mtime-diff file detection) wired, the only remaining
gate was Claude auth. Once CLAUDE_CODE_OAUTH_TOKEN was added to the
project .env, scripts/real-pm-smoke.js completed cleanly:

  Wire-up status:
    ✓ process spawn
    ✓ stream chunks       (3)
    ✓ result text          (Claude returned "DONE")
    ✓ files written        (6: prd/index, feature-tree, user-flows,
                              product/overview, assets/shell.{css,js})
    ✓ git commit           (8cb0493)
  5/5 checks passed · elapsed 163s

PM output quality (real Claude, not mock):
- valid <article data-doc="prd" data-rev="1"> + <section data-rev="1">
  structure per system prompt
- nav links use correct relative paths across 4 chapters
- pid (p-7gwlbl) embedded in HTML metadata
- 中文 prose in the requested 克制 voice

Spec-deviation confirmed (no MCP tool gateway yet — Claude only has
built-in Read/Write/Bash):
- ✗ agent-state/pm.json (no update_runtime_state tool)
- ✗ agent-state/pm-todo.json (no write_todolist tool)
- ✗ history/prd-rev-001.html (no archive_doc tool)
- ✗ timeline.ndjson 'prd_drafted' event (no timeline_append tool)
- ✓ core PRD site IS produced — sufficient to prove pipeline

──── code ────

- scripts/real-pm-smoke.js — loads root .env via dotenv resolved
  from server/node_modules (script dir has no node_modules of its own).

──── ambient ────

Files modified by user/linter while real-CLI work was in flight; merged
without revert:
- server/routes/devloop.js — new GET /:pid/requirements endpoint
- server/services/devloop/path-resolver.js — listProjects() includes
  archived flag + helpers; supports project archive lifecycle
- server/services/devloop/git-vault.js — commit() now accepts files[]
  to scope which paths the commit covers (avoids dragging linked-existing
  user's unstaged files into chore commits)
- server/src/core/devloop/loop-controller.js — createProject uses
  explicit files:['project.json','timeline.ndjson'] for first chore
  commit (avoids same issue)
- server/tests/devloop/path-resolver.test.js — coverage for archive/
  patch/hardDelete helpers
- web/src/components/devloop/RequirementListSection.vue (new)
- web/src/views/DevLoopNewRequirement.vue (new)
- web/src/views/DevLoopDashboard.vue — mounts RequirementListSection
- web/src/views/DevLoopProjects.vue — list page polish
- web/src/router/index.js — adds /devloop/:pid/requirements/new route
- web/src/components/devloop/DashboardHeader.vue — back link tweak

Test results: 233/233 vitest pass (was 230 → +3 path-resolver cases).

──── ⚠ SECURITY NOTE ────

.env is currently TRACKED in git (committed in b1a348b) even though
.gitignore lists it. Existing committed contents include credentials for
DOUBAO / FEISHU / GITHUB / GOOGLE / JWT. The CLAUDE_CODE_OAUTH_TOKEN +
AZURE_OPENAI_API_KEY I just added to .env are NOT in this commit — they
stay in your working tree only.

Recommended follow-up (separate commit):
  git rm --cached .env
  git commit -m "chore: stop tracking .env (already gitignored)"
And rotate every key that was in the previous committed .env.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

Two parallel pieces of plumbing — neither has been exercised end-to-end yet
(real CLI gated on `claude /login`; Projects list view served alongside
existing pages):

──── real-CLI wire-up (REAL.1 + REAL.2) ────

LemonBoss now has a clean toggle between mock & real Claude CLI:

- packages/acp-core/protocol/ClaudeCliProtocol.js
  * `options.systemPrompt` → `--append-system-prompt <prompt>` so each
    devloop agent receives its role-specific prompt.md without losing
    Claude's default tool-use conventions.
  * `options.maxBudgetUsd` → `--max-budget-usd` (note: only effective in
    `--print` mode; documented inline).

- server/src/core/devloop/loop-controller.js
  * callAgent now branches on `opts.mock`:
    - mock (P1-P5 path, untouched): fixture sequence + `mock/files` event
    - real: read system/templates/{agent}/prompt.md, pass as systemPrompt,
      snapshot project file mtimes pre-call, diff post-call to compute
      `files_written` — no fixture, no mock/files needed.
  * `_snapshotMtimes(root)` helper walks the project tree (skipping
    .git / node_modules / .cache / .tmp) and returns Map<relPath,mtime>.
  * timeline event payload now carries `real: true` flag.

- scripts/real-pm-smoke.js — minimal real-CLI sanity:
  spawns claude, injects PM prompt, prints which files were written +
  git commit sha. Hard timeout 5min. Single agent → expected spend
  $0.10-0.30 per run when authenticated.

Current status: process spawn + system-prompt injection + stream-json
flow all verified up to the `Not logged in · Please run /login` gate.
Auth is the only remaining blocker for executing the real smoke.

──── project CRUD routes ────

server/routes/devloop.js + server/services/devloop/path-resolver.js
add the lifecycle pieces the Projects list view needs:

- GET    /projects?include_archived=true   list w/ archive filter
- PATCH  /projects/:pid                    edit name + idea_summary
- DELETE /projects/:pid                    soft delete (archive)
- DELETE /projects/:pid?hard=true          hard delete (rm -rf sandbox;
                                            unregister linked)
- POST   /projects/:pid/restore            un-archive

path-resolver exposes matching helpers: listProjects({includeArchived}),
patchProjectMeta(pid,patch), hardDeleteProject(pid).

──── UI ────

- web/src/views/DevLoopProjects.vue (320 lines, new)  — Projects list
- web/src/router/index.js — adds `/devloop` → DevLoopProjects
- web/src/components/devloop/DashboardHeader.vue — back-link now points
  to `/devloop` (project list) instead of `/company`.

──── housekeeping ────

- CLAUDE.md / start.sh — start.sh now boots server/index.js (full route
  surface incl. /api/devloop) instead of the historical agent-server.js;
  docs updated to reflect this.

──── tests (+12) ────

- server/tests/devloop/routes-crud.test.js — 12 cases:
  PATCH validation (4) · soft DELETE + list filter (4) · POST /restore
  (1) · hard DELETE (2) · GET /projects default behavior (1).

Results:
- phase0-verify .. phase5-verify: 8+7+7+6+9+9+7 all pass
- vitest devloop+acp-core: 230/230 (was 218 → +12)

Specs:
- docs/prd/newfunction/_spec/arch-acp-bridge.md · Mock Mode
- docs/prd/newfunction/_spec/plan-migration.md · "自举乐趣" (real path
  prep)

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

Self-bootstrap demo: hits the same HTTP API a human would, asking
DevLoop to add a /restart endpoint to itself. End-to-end:
  1. POST /projects  (PM + Architect scaffold)
  2. GET  /state
  3. POST /run        (L1 + L2 → ship)
  4. GET  /{bugs,timeline,changelog,units/todo-be}
  5. POST /feedback   (PM incremental → PRD rev 1→2)
  6. POST /run        (re-ship)
  7. POST /sign-off   (→ shipped-final)
  8. POST /feedback   (→ 400 InvalidProjectStatusTransition)

Run: node scripts/self-bootstrap.js (artifacts retained for inspection)

Output proves the three-layer Loop survives a real curl-equivalent
session: 12 git commits auto-generated, 20 timeline events emitted,
prd_rev bumped, sdd_rev unchanged (happy path), bugs.ndjson empty
(no integration failures), .git contains full agent provenance.

For production: drop LEMONBOSS_CLAUDE_MODE=mock — the protocol layer
will route to real Claude CLI without any code change in
LoopController / routes.

Specs: docs/prd/newfunction/_spec/plan-migration.md · "自举乐趣"

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

…b-pages + UI endpoints)

Completes the §P4 acceptance UI scope that was deferred in commit
0594b1d. Adds the full Vue Dashboard + Ops sub-pages with live SSE
stream + auto-reconnect, unit DAG with detail drawer, PRD/SDD diff
panel, feedback modal, and 4 ops views (Bugs / Loops / Changelog /
Progress).

Vue surface (≈1480 lines):
- web/src/views/DevLoopDashboard.vue (~110 lines)
  * 4-region grid: status header / loop bar / units DAG / live stream /
    PRD diff. Polls /state every 2.5s; opens feedback modal & unit
    drawer; mounts Sign Off / Abandon controls.
- web/src/views/DevLoopOps.vue (~50 lines) — tab container.
- web/src/components/devloop/DashboardHeader.vue
  * Status badge (7 states color-coded), NEW REQUIREMENT button,
    Sign Off / Abandon buttons (disabled per FSM), Ops nav link.
- web/src/components/devloop/LoopStatusBar.vue
  * 4-phase pipeline (Docs → L1 → L2 → Ship), highlights active phase.
- web/src/components/devloop/UnitsDAG.vue
  * SVG DAG rendered from topological waves; per-unit status color;
    click → emits select → opens UnitDrawer.
- web/src/components/devloop/UnitDrawer.vue
  * Slide-in panel showing unit metadata + last 3 runs + result
    summary + coder.log tail (last 1KB).
- web/src/components/devloop/LiveAgentStream.vue
  * EventSource subscriber listening to project.status,
    unit.state, integration.result, triage.result, sdd.updated,
    prd.updated, human_intervention_needed, etc. Manual 5s reconnect
    on disconnect (browser's built-in Last-Event-ID is honored).
- web/src/components/devloop/PrdDiffPanel.vue
  * Reads changelog.ndjson, renders prd_rev / sdd_rev entries with
    trigger labels.
- web/src/components/devloop/FeedbackModal.vue
  * POSTs /feedback with PM incremental — shows rev bump on success.
- web/src/components/devloop/ops/BuglistView.vue
  * Filterable bug table; status badges; severity / category columns.
- web/src/components/devloop/ops/LoopLogView.vue
  * Timeline grouped by L1 (unit.*) / L2 (integration/triage/sdd/l2_*) /
    L3 (project.status/shipped/prd.updated/human_intervention) /
    System (rest). Free-text substring filter.
- web/src/components/devloop/ops/ChangelogView.vue
  * Tabular prd_rev/sdd_rev entries with by/trigger/summary columns.
- web/src/components/devloop/ops/ProgressView.vue
  * 6 metric cards (status, PRD rev, SDD rev, units passed bar,
    L2 rounds bar, open bugs) + per-unit breakdown table.

Router:
- web/src/router/index.js — adds:
  * /devloop/:pid              → DevLoopDashboard
  * /devloop/:pid/ops/:tab(bugs|loops|changelog|progress) → DevLoopOps

Backend UI-supporting endpoints (server/routes/devloop.js):
- GET /api/devloop/projects/:pid/timeline?limit=N
    Reads timeline.ndjson, returns last N events reversed.
- GET /api/devloop/projects/:pid/changelog
    Returns full changelog.ndjson entries reversed.
- GET /api/devloop/projects/:pid/units/:unitId
    Returns { unit, runs (last 3 result.json), coder_log_tail }.
    404 on unknown unit.

Tests (+5 cases):
- server/tests/devloop/routes.test.js — new P5 UI endpoints block:
  * timeline / changelog / units happy-paths
  * 404 on unknown unit and unknown pid

Acceptance:
- scripts/phase5-verify.js — 7 steps:
  ① Vue build artifacts (DevLoopDashboard.js + DevLoopOps.js chunks)
  ② POST /projects → state returns status + units
  ③ GET /timeline returns events
  ④ GET /changelog returns entries
  ⑤ GET /units/todo-be returns unit + runs
  ⑥ GET /bugs returns bug list
  ⑦ SSE /stream delivers ≥1 event after a triggering feedback POST

Vue build:
- npm run web:build → DevLoopDashboard chunk 15.63 kB,
  DevLoopOps chunk 9.09 kB, both with co-loaded CSS bundles.

Results — all 7 phase gates green:
- phase0-verify: 8/8
- phase0-test-call: 7/7
- phase1-verify: 7/7
- phase2-verify: 6/6
- phase3-verify: 9/9
- phase4-verify: 9/9
- phase5-verify: 7/7
- vitest devloop+acp-core: 218/218 (was 213 → +5)

Specs: docs/prd/newfunction/_spec/plan-migration.md · P4 L3 + UI

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

Implements the §P4 acceptance gate from plan-migration.md, with one
scope adjustment confirmed up-front: full Vue Dashboard (~1650 lines)
deferred to a future UI phase, replaced by extending the existing
P3 static status page with Sign Off / Abandon / Feedback controls.
All P4 backend acceptance criteria are scripted (phase4-verify.js).

Project status FSM (project.json.status):
- server/src/core/devloop/loop-controller.js
  * draft  →  running  →  shipped  →  shipped-final | abandoned
                ↓             ↓
          l2_blocked    (feedback flips back to running)
          l2_exhausted
  * `_setProjectStatus` validates transitions via STATUS_TRANSITIONS,
    emits SSE `project.status`, writes timeline event.
  * createProject seeds status=draft; runDocsPhase end → running;
    runProject(shipped) → shipped; all dead-end branches (l2_blocked,
    l2_exhausted) also propagate to status via _safeSetStatus.

L3 helpers:
- signOff(pid, opts) — requires status=shipped → shipped-final; commits
  a `chore: sign-off` git entry; rejects other source states with
  InvalidProjectStatusTransition.
- abandon(pid, opts) — any non-terminal → abandoned; commits + calls
  sseBroker.close(pid) to send SSE close frame to subscribers.
- submitFeedback(pid, text, opts) — rejects in shipped-final/abandoned;
  invokes PM in incremental mode; on prd_rev bump writes
  changelog.ndjson prd_rev entry + emits prd.updated SSE; if prior
  status was shipped, flips back to running so next runProject can
  rebuild.

PM incremental mock fixture:
- fixtures/devloop-mock/devloop-pm.json — converted to sequence form:
  * sequence[0] (init) — original P1 fixture (PRD rev=1, 14 files).
  * sequence[1] (incremental) — appends a new section to
    prd/feature/feature-tree.html, bumps article data-rev to 2,
    writes history/prd-rev-002.html.

Baseline happy-path Integrator:
- fixtures/devloop-mock/devloop-integrator.json — single-shot pass.
  Makes vanilla runProject ship without a scenario override.

P4 happy-path scenario:
- fixtures/devloop-mock-scenarios/happy_path/devloop-architect.json —
  single-unit (todo-be only) Architect so end-to-end ship works with
  the baseline Coder/Tester (which only know todo-be paths).

Routes:
- server/routes/devloop.js:
  * POST /projects/:pid/sign-off — 400 InvalidProjectStatusTransition
    when status != 'shipped'; 200 returns { status }.
  * POST /projects/:pid/abandon  — body { by?, reason?, note? }; 400 on
    terminal state; 200 returns { status: 'abandoned' }.
  * POST /projects/:pid/feedback — body { text (req), by?,
    mockFixtureDir? }; 400 on missing text or shipped-final/abandoned;
    200 returns { prd_rev_before, prd_rev_after, status }.
  * POST /projects: now accepts optional `mockFixtureDir` so the same
    fixture dir threads through both the create call and later
    feedback (keeps mock-sequence counters aligned).

Static status page (replaces full Vue Dashboard for P4):
- server/public/devloop-status.html — adds:
  * Status badge in header (color-coded per status).
  * Sign Off / Abandon control buttons (disabled per current state).
  * Feedback textarea + Submit button → POST /feedback.
  * Buttons reflect FSM (signoff only when shipped; abandon/feedback
    locked at terminal states).

Acceptance:
- scripts/phase4-verify.js — 9 steps, full HTTP path:
  ① POST /projects → running
  ② POST /run → shipped
  ③ POST /feedback → PRD rev 1→2 + running (+ changelog entry)
  ④ POST /run again → shipped
  ⑤ POST /sign-off → shipped-final
  ⑥ POST /feedback (after sign-off) → 400
  ⑦ POST /sign-off (after sign-off) → 400
  ⑧ second project: POST /abandon → abandoned
  ⑨ POST /abandon (after abandon) → 400

Tests (+19 cases):
- server/tests/devloop/p4-l3-feedback.test.js
  * 14 FSM cases covering happy path + abandon path + signOff
    pre-conditions + empty feedback rejection.
  * 5 route cases via fetch on ephemeral express app.

Results:
- phase0-verify: 8/8
- phase0-test-call: 7/7
- phase1-verify: 7/7
- phase2-verify: 6/6
- phase3-verify: 9/9
- phase4-verify: 9/9
- vitest devloop+acp-core: 213/213 (was 194 → +19)

Spec deviations explicit:
- Full Vue DevLoopDashboard.vue + Ops 4 sub-pages NOT implemented;
  static status page handles the demoable surface area instead.
- All backend endpoints from §P4 (sign-off, abandon, feedback) are
  complete and tested.

Specs: docs/prd/newfunction/_spec/plan-migration.md · P4 L3 + UI

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

Implements the §P3 acceptance gate from plan-migration.md: a single
POST /api/devloop/projects/:pid/run drives the full project from L1
through L2 with 4 distinct BugTriager branches, observability via SSE
stream + bugs.ndjson + changelog.ndjson, and a tiny static status page.

Mock protocol — fallback dir:
- packages/acp-core/protocol/ClaudeCliProtocol.js
  * New options.mockFallbackDir: when scenario dir lacks a per-agent
    fixture, fall back to the baseline fixtures/devloop-mock/.
    Enables scenario dirs to override only the agents that differ
    (Integrator + Triager + sometimes Architect).

Scenario fixtures — 4 L2 branches:
- fixtures/devloop-mock-scenarios/contract_mismatch/
  * Architect: sequence[init, patch] — patch bumps sdd_rev → 2,
    units.json l2_rounds → 1, marks todo-be back to pending.
  * Integrator: sequence[fail (500 vs 201), pass].
  * Triager: contract_mismatch confidence 0.85 with proposed_sdd_patch.
- fixtures/devloop-mock-scenarios/impl_bug/
  * Integrator: sequence[fail (ReferenceError), pass].
  * Triager: impl_bug confidence 0.78 affected=[todo-be], proposed=null.
- fixtures/devloop-mock-scenarios/spec_ambiguous/
  * Triager: confidence 0.4 → LoopController emits human_intervention.
- fixtures/devloop-mock-scenarios/infra_flake/
  * Integrator: sequence[crashed (EADDRINUSE), pass].
  * Triager: infra_flake confidence 0.95 affected=[].
- Each scenario also includes a 1-unit (todo-be) Architect.init fixture
  so baseline Coder/Tester (todo-be) can drive L1.

LoopController:
- server/src/core/devloop/loop-controller.js — adds:
  * runProject(pid, opts) — wave-scheduled L1 via _groupUnitsByWave,
    runIntegrator (devloop-integrator), runTriager (devloop-triager),
    then branch dispatch:
      - contract_mismatch+conf≥0.5 → Architect(patch) writes new
        units.json (already pending, l2_rounds++); emits sdd.updated +
        changelog sdd_rev entry; loop back to L1.
      - impl_bug+conf≥0.5 → unitRegistry.reset(affected); loop, no
        budget burn.
      - spec_ambiguous OR conf<0.5 → emit human_intervention_needed
        SSE, exit l2_blocked.
      - infra_flake → loop directly (no reset, no budget burn).
  * runDocsPhase + runUnit + callAgent all thread opts.mockFixtureDir
    through to the protocol.
  * Auto-attaches sseBroker to unit-registry and bug-tracker on module
    load — every FSM transition + bug op fires an SSE event.
  * bug_open at integration failure, bug_transition → fixed when
    subsequent L2 round passes.

Routes:
- server/routes/devloop.js:
  * POST /projects/:pid/run now defaults to full runProject; ?only=<id>
    still drills into single-unit runUnit (P2 compatibility).
  * GET  /projects/:pid/stream — SSE with Last-Event-ID replay.
  * GET  /projects/:pid/bugs?status=&unit_id=&severity= — bug list.
- server/index.js + agent-server.js mount /public for static assets.

Static status page:
- server/public/devloop-status.html (~100 lines) — pure HTML, polls
  GET /state every 2s, renders unit DAG with status pills + timeline
  tail. URL ?pid= or input box.

Acceptance:
- scripts/phase3-verify.js — 9 steps across 4 scenarios + observability:
  ① contract_mismatch ships at sdd_rev=2 l2_rounds=1, sdd.updated SSE,
    changelog sdd_rev entry, bug open → fixed.
  ② impl_bug ships, sdd_rev=1, l2_rounds=0 (no budget burn).
  ③ spec_ambiguous → l2_blocked + human_intervention_needed SSE.
  ④ infra_flake ships, rerun_integrator action, l2_rounds=0.
  ⑤ Observability: timeline/bugs/changelog/stream.log present.
  ⑥ SSE replay from Last-Event-ID returns ≥2 historical events.

Tests (+13 cases):
- server/tests/devloop/run-project.test.js (11) — 4 scenarios end to
  end + SSE event capture.
- server/tests/devloop/routes.test.js (+2) — full-project mode + bugs
  404. Updated P2 ?only stub test → full-project 404 on unknown pid.

Results:
- phase0-verify: 8/8
- phase0-test-call: 7/7
- phase1-verify: 7/7
- phase2-verify: 6/6
- phase3-verify: 9/9
- vitest devloop+acp-core: 194/194 (was 181 → +13)

Specs:
- docs/prd/newfunction/_spec/plan-migration.md · P3 验收
- docs/prd/newfunction/_spec/loops-l2.md (failure attribution + budget)
- docs/prd/newfunction/_spec/agents-integrator.md
- docs/prd/newfunction/_spec/agents-triager.md

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

Implements the §P2 acceptance gate from plan-migration.md: a single
POST /api/devloop/projects/:pid/run?only=todo-be drives the L1 inner
loop (Coder → Tester → fail → Coder → Tester → pass), with the second
Coder pass demonstrably reflecting on the first failure.

Mock protocol — stateful sequences:
- packages/acp-core/protocol/ClaudeCliProtocol.js
  * Mock fixtures now support `sequence: [{chunks,result,files}, ...]`.
    Each protocol.connect() + sendPrompt() consumes the next variant;
    sticks on the last entry after exhausted.
  * Static `ClaudeCliProtocol.resetMockState()` clears counters between
    test runs.

Fixtures:
- fixtures/devloop-mock/devloop-architect.json — units.json now has
  status:pending + retries:0 + retry_budget per unit, plus
  units/{todo-be,todo-db,todo-fe}/spec.json so Tester has acceptance
  criteria to read.
- fixtures/devloop-mock/devloop-coder.json — sequence: implement (with
  intentional missing 400 branch) → retry (reflective fix, coder.log
  attempt:2 has last_failure/last_cause/this_fix/rationale).
- fixtures/devloop-mock/devloop-tester.json — sequence: fail (1/3
  failure with hint pointing at missing body validation) → pass (3/3).

LoopController:
- server/src/core/devloop/loop-controller.js — adds:
  * runUnit(pid, unitId, opts) — drives the L1 loop via unit-registry
    FSM (pending → coding → testing → failed → coding → testing →
    passed/blocked). Calls Coder then Tester per attempt; on failure,
    builds a retry context summarizing prior coder.log + tester
    failures and feeds it into the next Coder prompt.
  * _buildRetryContext + _findLatestTesterResult helpers.
  * callAgent now rewrites units.json.project_id to the real pid after
    mock writes (so unit-registry validation passes).

Route:
- server/routes/devloop.js — adds POST /projects/:pid/run?only=<unitId>.
  Without ?only, returns 501 (full project run lands in P3).

Acceptance:
- scripts/phase2-verify.js — 6 steps:
  1. POST /projects (PM + Architect)
  2. POST /run?only=todo-be returns ok=true, attempts=2, final=passed
  3. FSM trail matches expected 6-step transition sequence
  4. coder.log second entry has all 4 reflection fields
  5. runs/ has ≥2 result.json with first.ok=false, last.ok=true
  6. sandbox cross-unit + prd writes blocked by ToolSandboxError

Tests (5 new cases):
- server/tests/devloop/run-unit.test.js (4) — FSM trail, coder.log
  reflection, runs/ result chain, sandbox enforcement.
- server/tests/devloop/routes.test.js (+3) — POST /run validation,
  full P2 loop, 404 on unknown unit.

Results:
- phase0-verify: 8/8
- phase0-test-call: 7/7
- phase1-verify: 7/7
- phase2-verify: 6/6
- vitest devloop+acp-core: 181/181 (was 174 → +7)

Specs:
- docs/prd/newfunction/_spec/plan-migration.md · P2 验收
- docs/prd/newfunction/_spec/loops-l1.md (retryWithReflection)
- docs/prd/newfunction/_spec/agents-coder.md
- docs/prd/newfunction/_spec/agents-tester.md

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

Implements the §P1 acceptance gate from plan-migration.md: a single
POST /api/devloop/projects produces a runnable todo-demo project with
multi-page PRD/SDD sites, units.json, integration spec, agent-state,
and history snapshots — all via mock agents (no real Claude CLI cost).

Code additions:
- packages/acp-core/protocol/ClaudeCliProtocol.js
  * mock mode now emits an extra `mock/files` acp_event when the fixture
    contains a files[] array. LoopController applies it to the project
    root, letting mock agents produce real outputs.
- server/src/core/devloop/loop-controller.js (now ~280 lines)
  * callAgent(pid, agentName, prompt, opts) — single-agent invocation:
    reads system/templates/{agent}/prompt.md, runs mock protocol,
    applies fixture files[], timeline-logs, auto-commits.
  * runDocsPhase(pid, requirement) — orchestrates PM → Architect with
    `docs.complete` timeline marker.
  * getProjectState(pid) — returns project.json + units + prd_rev/sdd_rev
    + timeline tail for the GET /state endpoint.
- server/routes/devloop.js (new)
  * POST /api/devloop/projects — createProject + runDocsPhase
  * GET  /api/devloop/projects
  * GET  /api/devloop/projects/:pid/state
- server/index.js / server/agent-server.js — mount /api/devloop.

Mock fixtures (drive the full acceptance file tree):
- fixtures/devloop-mock/devloop-pm.json
  * 14 files: prd/{index,reading-guide,product/*,feature/*,flow/*,prototype/*}.html,
    prd/assets/{shell.css,shell.js,search-index.json},
    agent-state/{pm.json,pm-todo.json}, history/prd-rev-001.html.
- fixtures/devloop-mock/devloop-architect.json
  * 13 files: sdd/{index,mvcp/*}.html, sdd/assets/*,
    units.json (3 units, DAG), integration/spec.json,
    agent-state/{architect.json,architect-todo.json}, history/sdd-rev-001.html.

Acceptance:
- scripts/phase1-verify.js — spins ephemeral express app, POSTs the
  todo-demo project, asserts 23 expected paths exist + 3 units with
  l2_rounds/l2_budget + git ≥4 commits + timeline events.

Tests (12 new cases):
- server/tests/devloop/loop-controller.test.js (7) — callAgent +
  runDocsPhase + state.
- server/tests/devloop/routes.test.js (5) — POST validation, full
  POST, GET state, 404 on unknown pid.

Results:
- phase0-verify: 8/8
- phase0-test-call: 7/7
- phase1-verify: 7/7
- vitest devloop+acp-core: 174/174 (was 162 → +12)

Specs: docs/prd/newfunction/_spec/plan-migration.md · P1 Docs MVP

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

Final P0 deliverables to make the system bootable in mock mode and
pass `scripts/phase0-verify.js` + `scripts/phase0-test-call.js` end-to-end.

ClaudeCliProtocol (mock mode):
- LEMONBOSS_CLAUDE_MODE=mock or { mock: true } in constructor enables
  mock mode. connect() becomes a no-op; sendPrompt reads fixtures from
  fixtures/devloop-mock/{agentName}.json and emits scripted session_update
  chunks + session/result(mock=true). Falls back to default.json.

Agent registry:
- 6 entries added to system/templates/_registry.json (devloop-pm,
  devloop-architect, devloop-coder, devloop-tester, devloop-integrator,
  devloop-triager).
- Per-agent dirs system/templates/devloop-{role}/ with:
  * prompt.md   — auto-extracted from agents-{role}.html §2.2
  * config.json — cli.toolPolicy.allowedTools + sandbox.writeAllowList

Tooling:
- scripts/extract-agent-prompts.js  — regex-extracts §2.2 system prompts
  from 6 agent HTML pages to system/templates/devloop-{role}/prompt.md.
- server/src/tools/devloop/index.js — central export (tools Map,
  bashHooks, dispatch).
- server/src/core/devloop/loop-controller.js (P0 skeleton) — exposes
  createProject (sandbox alloc + git init + first commit + timeline) and
  commitAfterAgent (per-agent kind-routed git commit + timeline event).

Mock fixtures:
- fixtures/devloop-mock/default.json + devloop-pm.json

Acceptance scripts:
- scripts/phase0-verify.js   — 8 static checks (35 tools loadable,
  6 agents registered, prompt+config wired, bash guard exported, services
  require, fixtures present, git-vault interface, loop-controller).
- scripts/phase0-test-call.js — 7 end-to-end steps under mock mode
  (createProject → CLI connect → sendPrompt chunks → no-op commit returns
  null → real write commits → git log ≥2 → timeline has both events).

vitest.config.js: include packages/**/*.test.js so the mock smoke test
runs in the suite.

Results:
- 162/162 devloop + acp-core tests pass (up from 159).
- phase0-verify: 8/8.
- phase0-test-call: 7/7.

Specs: docs/prd/newfunction/_spec/plan-migration.md · Quick-Start step 7

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

The 50-page PRD HTML totals ~520KB; loading it all costs Claude ~222K
tokens just for context. This adds a token-efficient sibling layer:

- scripts/extract-spec.js → npm run spec:extract / spec:check
  Walks docs/prd/newfunction/*.html and produces stripped MD into _spec/.
  Strategy varies per page (full-extract for SDD/process/data,
  shell-strip for agents to keep long system prompts intact).
  Result: 327.9KB MD (~84K tokens) — 38% of full load, saves ~138K tokens
  for every Agent invocation that reads the spec.

- scripts/git-hooks/pre-commit + scripts/install-hooks.sh
  Pre-commit guard: when any docs/prd/newfunction/*.html changes, the
  hook checks the corresponding _spec/*.md is up to date; fails commit
  if stale, telling user to `npm run spec:extract`. Auto-installed via
  package.json `prepare` script on `npm install`.

- docs/prd/newfunction/_spec/ (51 .md files + CONVENTIONS.md)
  Machine-readable mirror of HTML. Used by:
  - Coder/Architect/Tester agents when reading spec at runtime
  - External Claude Code sessions doing reproducibility
  - CI checks (npm run spec:check)
  NOT hand-edited; regenerated from HTML by extract-spec.js.

- CLAUDE.md: 1-line note directing future agents to read _spec/*.md
  preferentially, fall back to *.html only for wireframes/SVG/full
  human-readable context.

This is the user's pre-existing scaffolding that the previous commits
hadn't pulled in yet. Now tracked + enforced by hook.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

DevLoop: a 3-layer Loop (L1 Unit / L2 Integration / L3 Human) auto-development
system that takes a one-line human requirement and produces multi-page HTML
PRD + SDD + units.json + full backend/frontend code via 6 specialized agents.

This commit adds the complete documentation set:

50 HTML pages organized in 8 sections (3-level menu + global search):
- 01 Overview · 02 PRD · 03 Design (loops + 6 agents)
- 04 SDD (MVCP × 4) · 05 Prototype · 06 Architecture
- 07 API · 08 Ops · 09 Plan

Key specs:
- 6 agent skills (PM/Architect/Coder/Tester/Integrator/BugTriager), each with
  full system prompt, 13-17 tool signatures, 3 E2E samples, helper source code
- 52 MVCP definitions, 100% machine-extractable via data-* anchors
- 79 tool signatures with implementation guidance (arch-tool-registry)
- ACP bridge spec (arch-acp-bridge): how LoopController calls into LemonBoss
  agent-manager without breaking existing Master/Innovator flows
- 5-phase plan P0→P4 (~9.5 weeks): P0 bootstrap (tool impl + ACP bridge),
  P1 docs MVP, P2 single unit L1, P3 L1+L2 loop, P4 L3 feedback + UI
- Persistence layer: AgentState (M-10), Memory (M-11), Todolist (M-12),
  Timeline (M-13), Bugs (M-14), Changelog (M-15) + crash recovery (P-8)
- Cost & concurrency budgets (plan-cost-concurrency)
- Code lifecycle: stay-in-sandbox v1 + export API + future GitHub PR (v2)

Plus supporting scripts (zero deps, regex-based):
- scripts/extract-manifest.js: extracts MVCP defs to build-manifest.json,
  used to verify all definitions have path + shape (currently 100%)
- scripts/build-search-index.js: builds assets/search-index.json (183KB),
  enables Ctrl+K global search across all 50 pages

The PRD itself is meta-executable: a future Claude Code session reading
plan-reproducibility.html can rebuild the entire DevLoop runtime from the
docs alone.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

- Moved data/system/ → system/ (agents, templates, skills, data, workspace)
- Updated all server route/service path references
- Updated all script path references
- Updated all documentation references
- Restructured .gitignore for cleaner system/ vs data/ boundary

system/ = platform-shared assets (system agents, template library)
data/ = tenant-specific company instance data

scripts/demo-harness-company.js creates a company, hires a Base Agent
worker, and simulates the full RPEV lifecycle with real API calls:
- Company creation (skipBootstrap)
- Agent hiring with base template
- meta-research initial skill mount
- 3 transition API calls (plan → execute → verify)
- Hot Swap verification at each stage
- Artifact production validation

scripts/test-harness.js covers:
- Meta-Skill file existence & content
- Base Agent template completeness
- Hot Swap simulation
- Context Flush simulation
- _lessons.md injection
- billing.log format
- GoalsService new statuses
- CLI registration
- Transition API route verification
- Optional --online mode for live API tests

- Implement OKR GoalsService with hierarchical node tracking
- Add /api/goals routes and integrate with dispatch/report APIs
- Create Innovator agent with Hunt→Digest→Evolving pipeline
- Create Hunter (l3-hunt), Digester (l2-digest), Evolver (evolving) meta agents
- Copy L1/L2 dependency skills into each agent's .claude/skills/
- Fix buildSystemPrompt to scan ALL skill subdirectories (critical)
- Fix agent list sorting: master pinned top, rest by lastActiveAt
- Rename master-001→master, innovator-001→innovator
- Establish meta agent output convention: write to target agent dir
- Add CXO agent base class for management agents
- Update CEO agent with delegation-first management model

- Agent as Micro-Container: each agent lives in data/agents/{id}/ with full encapsulation
- Persona vs Capability split: agent.md (identity) + .claude/skills/main_skill/SKILL.md (workflow)
- Conversations co-located: data/agents/{id}/conversations/ replaces global dir
- Meta Skills renamed: meta_hunt, meta_digest, meta_creator, meta_evolving, meta_benchmark, meta_research
- Dynamic Hot-Reload: AgentManager.getAgentConfig() falls back to filesystem scan
- Parallel Sub-Agent orchestration via Promise.all with multi-terminal UI
- Removed SQLite dependency, global skills/ directory, and legacy conversations/
- Full architecture docs: 18-local-filesystem-first-agent-encapsulation.md