宜博 / lemonboss

## 验收 4：从「静态成立」变成真的跑过一次

原状态是 🟡「静态成立，未真跑」—— 人读代码把
fixture verdict → FAILING_VERDICTS → readNodeProduct → callAgentNode 判 fail
这条链读通了，但没有任何一次真跑或真链路证据。

现在 graph-real-chain-smoke ⑥ 走完整条：fixture 产出 verdict="attributed"
→ 节点 fail、fail_reason=input_underspecified、沿 fail 边点亮下游、
判词落在**下游节点**行上（判词的载体是「点亮它的那次状态转换」，不是失败节点自己）。
反向验过：verdict 改成 passed 立刻红。

写 fixture 时踩到一条值得记的：fail_reason 是封闭域 ATTRIBUTION_REASONS，
第一版编了个 contract_invalid，被**按设计降级成 null** 并留一条 timeline ——
引擎不认识的归因一律不信。判据没错，是 fixture 错。

## 验收 2 / 8：由 2026-08-20 那次真跑验掉（§六ter）

· 2 —— 19 次真 agent 调用之后 `git status --porcelain` 完全为空，交付物都在项目根内。
  这正是 §六bis「后半被并行 agent 打破」那条的干净环境重验。
· 8 —— 判据取「它引用了只可能来自提示词的内部 id」：triager 判词原文写着
  「org-coder-impl 私有目录 rn_96a8cd696dcc 下只有 _research.md」，
  rn_96a8cd696dcc 是 graph_run_nodes.id，agent 没有别的途径知道它。

## 验收 9：产出端通了，消费端没等到那个形状

真跑里 triager **确实产出了两半地址**（orgNode + workNode）——
这一条本身有分量：27-P3/P4 §八.22 第 13 处记的正是「引擎四环全通，
但产出方 agent.md 里根本没有这个键」，那半条现在通了。

紧接着「忽略跨层地址」那条**不是缺陷，是判据在正常工作**：这次回退发生在
work 层内部，edge.to 本身就是 agent_call 节点，已是最细粒度，没有跨层可言。
缺的是**那个形状**：一次 org 层回退边、且目标是 subgraph 节点。

别把「机制没验」和「机制没有」混为一谈 —— 定点重置的逻辑侧有
graph-cross-layer-address.test.js 三例注入式覆盖，缺的只是真跑里发生过一次。

## 顺带

· template-verdicts 的样本非空那条补 ENOENT 容忍。它扫**活目录**，
  而 graph-real-chain-smoke 会在 system/agents/{aid}/{cid}/ 下建了又清运行态 ——
  文件在「列出名字」和「读它」之间消失是正常的。walk() 与 violations() 早就容忍了，
  只有这一处漏了，实测偶发红过一次。**扫活目录的守卫，每一处读都要容忍 ENOENT。**
· 真跑 timeline 里发现一条未修的：每个节点的产物索引写入都撞
  UNIQUE idx_graph_files_path 失败并被降级成日志（重试时同路径再写一次）。
  后果是 files.json 产物索引在有重试的 run 上静默不全 —— 归 P4 一起处理，记在 §六ter。

全量：139 文件 / 1297 测试全绿。

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

agent_call 与 subgraph 是**两段不同的默认实现**（defaultAgentExecutor /
defaultPlanWorkGraph），各有各的 onAcpEvent 累加、各有各的守卫开关分支。
上一轮只覆盖了前者，「规划子图」那半条链仍然是零真实覆盖。

现在走完：defaultPlanWorkGraph → AgentManager → ClaudeCliProtocol(mock)
→ extractPlannedGraph 解析回复 → createWorkGraphSafely → 建子 run。

断言两处假 planner 天然绕开的接线：
· 子 run 的定义确实来自 fixture 那张图（节点名 / systemAgentId 逐个对）
· 规划那一轮烧的 token 也进了预算 —— 走的是 defaultPlanWorkGraph 自己那条
  onAcpEvent，与 agent_call 那条不是同一段代码
③ 的守卫断言补上 subgraph 分支的正反对照。

新增 fixture workgraph-planning.json：图 JSON 同时放进 chunks 与 result
（mock 下 output 取哪一半由 AgentManager 决定，不该由 fixture 来赌）。

反向验过：抽掉 fixture 里的图 JSON、或把它的 usage 归零，对应用例分别变红。

**覆盖边界写在用例注释里**：跳过 resolvePlanningAgentName 里的按需 hire
（预塞一行 company_agents）—— hire 要一条真实公司记录，那条路径另有
company-hire-org-layer.test.js 盯着；这条 smoke 验的是规划链路，不是招聘。

全量：139 文件 / 1296 测试全绿。

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

## 一、W7「零边图」不是待办 —— 它早修了，是注释在骗人

`company-service.js` 的判据注释仍写着「判据用**有没有边**」，并留着一段
「已知残留：单 org node 的最小图没有边，判据③不生效……真跑到那一步再看」。

**那个残留在 `58a2865`（08-17）就修掉了**：`orgGraphMembership` 现在的主判据是
`authored_by='planner'` 的节点存在（「orggraph-planning 提交过一张图」的直接证据，
零边也认），边数降为存量行的回落判据；守卫 `company-hire-org-layer.test.js` 的
`CO_ZEROEDGE` + `W7-fix` 两条盯着。

注释没跟着改，于是它把读的人**引向一个已经修好的缺陷**去重修一遍 —— 我就是这么被
带偏的：读到那段注释就没再往 `orgGraphMembership` 里跟，还据此往待办清单里写了一条。
这是「指路牌失效」那一族，和 CLAUDE.md 死链同型，只是方向相反（那边指向不存在的东西，
这边描述已不存在的洞）。

判据的措辞也改了：**「成型」的判据在 graph-service.orgGraphMembership()，不在这里**，
免得下一个人照注释理解。P3B 文档与 docs/README.md 的对应条目一并更正。

## 二、还上「真实路径 smoke 进 CI」那笔欠账的一半（27-P3/P4 §十 硬规矩 2）

原话是「凡是靠注入点验的能力，都要有一条真实路径的 smoke 进 CI 才算验收完成 ——
这条欠账仍未还」。此前唯一走真实路径的 `scripts/real-pm-smoke.js` 要真 API 额度、
人工跑、而且验的是 DevLoop 不是图执行。

做法是把「真 LLM」和「真代码路径」拆开：**只把最外层的 CLI 子进程换成 fixture 回放**，
setAgentExecutor / setPlanWorkGraph 一个都不调。链路完整走
advanceOne → defaultAgentExecutor → AgentManager → ClaudeCliProtocol
→ onAcpEvent → 落盘 → readNodeProduct → settleNode → spendBudget → 边界守卫。

三条断言各盯一处**假 executor 天然绕开**的接线：
· ① mock/files 真的落到节点产物目录（假 executor 直接 return，这一环整个不存在）
· ② token 用量真的从 session/result.usage 数进预算 —— **就是 §六 验收 10 卡了两轮的那一维**
· ③ boundaryGuardApplicable 在这条路径上为真（注入假 executor 时它恒为假，
     那条唯一有实际后果的分支实际零覆盖）；带反向对照，注入后必须变假

反向验过：断掉①的落盘、断掉②的累加，对应用例分别变红。

为此改了一处 mock：session/result 的 usage 原来硬编码 {input:0,output:0}，
现在 fixture 可指定（缺省仍是 0，既有 fixture 行为一个字不变）。
**不改这一处，token 那一维在 CI 里永远产不出数** —— 验收 10 当初就是卡在这儿。

**没还清的部分写在文档里，别当成还清了**：真 LLM 仍进不了 CI；
subgraph 那一支（defaultPlanWorkGraph）仍只有注入式覆盖；
多节点 / 回退边 / 熔断没进这条 smoke，它只推一个节点。

afterAll 清掉真实链路建出的公司态目录（gitignore 挡着不进库，但留着会让别的
用例遍历 system/agents/ 时多扫一份）。

全量：139 文件 / 1295 测试全绿。

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>

真 CLI 冒烟（worktree 隔离，PORT 3010）九轮来首次把 work 节点跑起来：
orggraph-planning 真跑 3 分钟自主裁成单 org node 零边图 → workgraph-planning
第 1 轮产出合法图 → **自己按 Step 6 把 brd-planning / planner-validator 雇进公司**
（W5/W6 核心验收成立，且 W7 判据生效、两者都没写进 org_graph_nodes）→
第一个 work 节点 brd-planning 真起 CLI 子进程，产出 brd.md / contract.json /
attempt-0.json 全部落在 run 目录内。图内预算仅 2 次调用 / 13998 tokens（上限 15）。

W5/W6 · workgraph-planning 自雇：撤掉「你不招人也不辞人」，Step 6 加招聘环节，
  写死「先雇、再提交图」的顺序，给出失败分级与幂等要求
W7 · work 层招聘不写 org_graph_nodes：按 type 与 work graph 骨架点名两条判据区分层级，
  P2 「hire org 角色 → org graph 出现该节点」的语义保持不变
W8 · 控制台「规划组织结构」按钮（抽成 ReplanOrgGraphButton.vue，带过渡态与秒表），
  接 POST /:companyId/org-graph/replan（该端点此前无任何前端调用方）；
  新增 fixtures/devloop-mock/orggraph-planning.json
W12 · 节点失败留痕：node.output 带 output_excerpt、新增 node.error 事件。
  真跑当场救场——守卫误判那条归因正是靠它才查得出来，
  换成之前看到的只有「节点 fail、无原因、无痕迹」

测试 753/753 全绿（71 文件，起点 736/68）。

已知未修（下一轮）：子 run 转终态不回写父 node_run 导致任务永久卡死；
applyBoundaryGuard 用整仓 git diff 判归属会把并行 agent 的写算到当前节点头上；
W12 的 fail_reason 未落库（概览 tab 仍为空）；POST /:cid/tasks 无前端调用方。

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>

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>