test(workflow-utils): add error path tests for createLlmAdapter

Cover non-ok HTTP response (500) and network failure (ECONNREFUSED).
Per review feedback from 星月 🌙 on PR #278.

.knowledge/architecture.md

@@ -33,6 +33,7 @@ Senses own both the "what" (compute logic) and the "when" (config-driven schedul
 - One worker per Workflow type (on-demand)
 - Workers never talk to each other
 - All user code runs in isolated Workers; kernel never loads user code directly
+- **`WorkerRuntime`** (`packages/daemon/src/worker-runtime.ts`) centralizes fork lifecycle for both sense groups (`worker-pool.ts`) and workflow types (`workflow-manager.ts`); see `.knowledge/worker-isolation.md`
 
 ## Storage Systems
 

.knowledge/worker-isolation.md

@@ -12,6 +12,12 @@ Kernel (Main Process)
 └── Workflow Worker (review) ── review workflow instances
 ```
 
+### WorkerRuntime (RFC-006)
+
+Forked worker processes are managed by **`WorkerRuntime`** (`worker-runtime.ts`): one Node child per logical key, cold start, optional respawn after crash, drain/evict, and coordinated shutdown over IPC. **`worker-pool.ts`** (sense groups) and **`workflow-manager.ts`** (workflow types) both configure and delegate to `createWorkerRuntime` instead of owning ad-hoc fork logic.
+
+Worker **entrypoints** (`sense-worker.ts`, `workflow-worker.ts`) import lightweight helpers only — e.g. `worker-signals.ts` for session broadcast signal handling — so they do not pull in the parent-side runtime module.
+
 ## Isolation Boundaries
 
 ### 1. Sense Workers
@@ -111,10 +117,10 @@ workflows:
 ### Process Management
 
 #### Signal Handling
-Workers ignore session broadcast signals (SIGINT/SIGTERM):
+Workers ignore session broadcast signals (SIGINT/SIGTERM) via `ignoreSessionBroadcastSignals()` in `worker-signals.ts`:
 ```typescript
 // Workers ignore terminal signals; kernel coordinates shutdown
-process.on("SIGINT", () => {}); 
+process.on("SIGINT", () => {});
 process.on("SIGTERM", () => {});
 ```
 

CLAUDE.md

@@ -98,6 +98,13 @@ type ComputeResult<T> =
   | { signal: T; workflow: WorkflowTrigger | null };
 ```
 
+### Workflow Naming
+
+Workflow identifiers — `WorkflowDefinition.name`, the directory under `workflows/`, and keys under `workflows:` in `nerve.yaml` — must use **verb-first** kebab-case phrases so the name reads as an action.
+
+- ✅ `solve-issue`, `extract-knowledge`, `develop-sense`
+- ❌ `knowledge-extraction`, `issue-solver`
+
 ### Workflow authoring (user modules)
 
 Roles and moderators take **ThreadContext** (`threadId`, `start`, `steps`) — not separate `StartStep` / message arrays.

docs/dead-code-analysis.md

@@ -0,0 +1,146 @@
+# Nerve 单仓死代码分析报告
+
+**分析日期**: 2026-04-30  
+**范围**: `packages/core`, `daemon`, `store`, `cli`, `khala`, `workflow-utils`, `workflow-meta`, `adapter-cursor`, `adapter-hermes` 的 TypeScript 源码与 `package.json` 依赖。  
+**方法**: 全仓 `ripgrep` 交叉验证 `import` / `export` 路径；未运行 Knip/TS 死代码专项工具。  
+**说明**: 未包含 `role-reviewer` / `role-committer` / `skills` 等包（你列出的范围外），但 `workflow-meta` 对其中部分有依赖，相关结论已注明。
+
+---
+
+## 方法限制（读前必读）
+
+| 限制 | 影响 |
+|------|------|
+| **动态 `import(url)`** | `cli` 的 `loadDaemonModule` 在运行时加载 `@uncaged/nerve-daemon`，静态分析无法把 `createKernel` 等映射到具体导出。 |
+| **已发布包的公共 API** | 大量导出仅被仓外消费者使用；本报告中的「仓内未引用」≠「应删除」。 |
+| **构建入口** | Rslib 多入口（如 `sense-worker`、`workflow-worker`、`daemon-bootstrap`）视为存活入口，不作为孤儿文件。 |
+| **内部未导出函数** | 未做逐函数调用图；「死函数」仅列出高置信个例。 |
+
+---
+
+## 1. 未使用导出（仓内无 `import`）
+
+以下符号在 **monorepo 内** 没有任何文件从 `@uncaged/nerve-core` / `@uncaged/nerve-workflow-utils` / `@uncaged/nerve-daemon` 等包根导出处引用（测试与定义自身除外）。
+
+### 1.1 `@uncaged/nerve-core`
+
+| 路径 | 未使用项 | 置信度 | 建议 |
+|------|----------|--------|------|
+| `packages/core/src/index.ts` → `agent.js` | `KNOWN_AGENT_ADAPTER_IDS` | **高** | **调查**：若 CLI/校验应约束 adapter id，可接入；否则可从公共 API 移除或保留作文档性常量并注明。 |
+| `packages/core/src/index.ts` → `sense.js` | `labelSenseTrigger`（`senseTriggerLabels` 在 `cli`/`daemon` 有使用） | **高（相对仓内）** | **保留或收敛导出**：仅 `senseTriggerLabels` 对外即可；`labelSenseTrigger` 可作为内部函数若不需要单独暴露。 |
+| `packages/core/src/index.ts` → `util.js` | `parseDurationStringToMs`（仅 `config.ts` 内部使用） | **高** | **调查**：无需在 `index` 再导出则改为非导出或移除 re-export，减少 API 面。 |
+| `packages/core/src/index.ts` → `sense.js` | 类型 `SenseModule` | **中** | **保留**：用户文档/外部 Sense 模块常用；仓内未按名引用属正常。 |
+| `packages/core/src/index.ts` → `config.js` | 单独导出的类型 `NerveApiConfig`（仅 `config.ts` 与 `index` 出现） | **低** | **保留**：通常随 `NerveConfig` 一并使用；单独 export 多为 TS 公共类型便利。 |
+
+### 1.2 `@uncaged/nerve-workflow-utils`
+
+下列项在 **`packages/*/src/**/*.ts` 中无人从包入口导入**（`workflow-meta`、`role-committer` 等主要只用 `createRole`、`decorateRole`、`onFail`、`withDryRun`、`LlmExtractorConfig`）。
+
+| 路径 | 未使用项 | 置信度 | 建议 |
+|------|----------|--------|------|
+| `packages/workflow-utils/src/index.ts` | `createLlmAdapter` | **高** | **保留（对外 API）** 或标注文档；仓内无调用。 |
+| 同上 | `llmExtract`、`llmExtractWithRetry` | **高** | **保留**：高级用法 / 文档示例；内部与测试使用。 |
+| 同上 | `mergeExtractConfig`、`ExtractConfigLayer` | **高** | **调查**：若 RFC 分层配置仍在推进则保留；否则评估移除导出。 |
+| 同上 | `assertZodMetaSchemas`、`createLlmExtractFn`、`extractMetaOrThrow`、`zodMeta`、`ZodMetaSchema` | **高** | **保留（对外 API）**；当前仅 `workflow-utils` 测试与内部 `create-role` 链路使用 `extractMetaOrThrow`。 |
+| 同上 | `readNerveYaml`、`nerveAgentContext` 及相关类型 | **高** | **调查**：若已无 YAML 上下文注入场景可删导出；否则保留给 Agent 工具链。 |
+| 同上 | `spawnSafe`、`nerveCommandEnv` 及 `Spawn*` 类型（从 core 再导出） | **高** | **删除再导出或改为文档链接**：仓内均直接从 `@uncaged/nerve-core` 引用 spawn。 |
+| 同上 | `isDryRun` | **高** | **删除或实现**：见 §3「死函数」。 |
+| 同上 | `LlmMessage`、`MetaExtractConfig`、`LlmChatError`、`LlmError`、`LlmProvider` 等类型再导出 | **中** | **保留**：供外部精细类型标注；仓内未单独 import。 |
+
+### 1.3 `@uncaged/nerve-daemon`
+
+| 路径 | 未使用项 | 置信度 | 建议 |
+|------|----------|--------|------|
+| `packages/daemon/src/index.ts` → `agent-adapters/echo.js` | `createEchoAgent` | **高** | **调查**：无任何测试或运行时引用；若设计保留 `type: "echo"` 适配器，应在 workflow/agent 装载路径接线或删除导出与文件。 |
+| `packages/daemon/src/index.ts`（及其它导出） | 多数 IPC / runtime 符号 | **低** | **保留**：动态加载与外部集成无法静态判定；仅 `createEchoAgent` 可确定为当前静态图下的死角。 |
+
+### 1.4 `@uncaged/nerve-adapter-cursor` / `@uncaged/nerve-adapter-hermes`
+
+| 路径 | 未使用项 | 置信度 | 建议 |
+|------|----------|--------|------|
+| `packages/adapter-cursor/src/index.ts` | `cursorAdapter`、`createCursorAdapter`（以及 `cursorAgent` 仅被 `workflow-utils/src/role-cursor.ts` 使用） | **中** | **保留**：默认实例与工厂供下游与工作流仓使用；仓内业务包未直接 import `cursorAdapter` 属预期。 |
+| `packages/adapter-hermes/src/index.ts` | `hermesAdapter`、`createHermesAdapter`（`hermesAgent` 经 `workflow-utils` 间接使用） | **中** | 同上。 |
+
+### 1.5 `@uncaged/nerve-cli`
+
+| 路径 | 未使用项 | 置信度 | 建议 |
+|------|----------|--------|------|
+| `packages/cli/src/index.ts` | `getNerveRoot`、`loadDaemonModule` 等程序化导出 | **高（仓内）** | **保留**：无任何 workspace 包引用 `@uncaged/nerve-cli`；面向 CLI 二次开发者。 |
+
+---
+
+## 2. 孤儿文件（非入口、未被其它源码引用）
+
+在当前 Rslib / `cli` 入口定义下，**未发现**「零 import、且非 entry / 非测试」的 `.ts` 业务文件：
+
+- `workflow-utils` 下的 `role-cursor.ts`、`role-hermes.ts`、`role-llm.ts`、`role-react.ts` 虽**未出现在包 `index.ts`**，但被 `packages/workflow-utils/src/__tests__/role-factories.test.ts` 直接引用，**不是孤儿文件**。
+- `daemon` 的 `sense-worker.ts`、`workflow-worker.ts` 等为 **显式构建入口**。
+
+**置信度**: 对全表扫描为 **中**（未跑依赖图工具；动态路径可能掩盖极少数脚本引用）。
+
+---
+
+## 3. 死函数（内部未导出且未被调用）
+
+| 路径 | 说明 | 置信度 | 建议 |
+|------|------|--------|------|
+| `packages/workflow-utils/src/role-types.ts` | `isDryRun(_start: StartStep)`：导出在 `index.ts`，但全仓无调用（函数体恒返回 `false` 且标注 deprecated） | **高** | **删除**或改为内部常量；若需向后兼容则保留并文档标注「保留占位」。 |
+
+其它内部函数未系统逐文件枚举。
+
+---
+
+## 4. 未使用的 npm 依赖（package.json）
+
+在声明范围内通过源码 `import` 抽查：**未发现明显「完全未使用」的生产依赖**。
+
+| 包 | 依赖 | 结论 |
+|----|------|------|
+| `cli` | `citty`、`yaml`、`picomatch` | 均有对应源码引用。 |
+| `khala` | `hono`、`jsonata`、`ulidx`、`@uncaged/nerve-core` | 均有引用。 |
+| `core` / `daemon` | `yaml`、`drizzle-orm` | 均有引用。 |
+| `workflow-utils` / `workflow-meta` | `zod`、workspace 包 | 均有引用。 |
+
+**置信度**: **中**（未对 peer、可选路径、CLI `bin` 专用依赖做自动化扫描）。
+
+---
+
+## 5. 陈旧测试夹具 / 未引用辅助文件
+
+未发现独立的「fixture 目录」明显失联；`cli` 下 `e2e-harness`、`__tests__` 内 helper 均有对应测试引用。
+
+**置信度**: **低**（未枚举每个 `__tests__` 资源文件）。
+
+---
+
+## 6. 重构遗留 / 文档漂移
+
+| 项目 | 位置 | 说明 | 置信度 | 建议 |
+|------|------|------|--------|------|
+| 已更名 API 仍出现在 README | `packages/core/README.md` | 仍描述 `parseSenseWorkflowDirective`、`ParsedSenseWorkflowDirective`、`SenseComputeRoute`；源码已为 `parseWorkflowTrigger` / `routeSenseComputeOutput` / `RoutedSenseOutput` | **高** | **更新文档**（本次分析不改代码，仅记录）。 |
+| Hermes 选项合并注释 | `packages/workflow-utils/src/shared/hermes-agent.ts` | 注释称 absorbed from `hermes-options.ts`，该文件已不存在 | **中** | **清理注释**，避免误导。 |
+| `KNOWN_AGENT_ADAPTER_IDS` 含 `codex` | `packages/core/src/agent.ts` | 仓内无 `codex` 适配器包；与常量未被引用叠加 | **中** | **对齐产品**：实现适配器或从列表移除。 |
+
+未发现用户提到的 `worker-fork-support` 等字符串副本（全仓无匹配）。
+
+---
+
+## 7. 汇总建议优先级
+
+1. **高优先级调查**: `createEchoAgent` 与 `KNOWN_AGENT_ADAPTER_IDS` — 要么接入运行时，要么删减以免维护假象。  
+2. **API 面收敛**: `parseDurationStringToMs`、`labelSenseTrigger` 若无意对外，可从 `core` 公共导出移除。  
+3. **`workflow-utils`**: 评估 `isDryRun` 删除；`spawnSafe` 等从 `workflow-utils` 再导出是否仍有必要。  
+4. **文档**: 修正 `packages/core/README.md` 中 Sense→Workflow 路由 API 名称。  
+
+---
+
+## 8. 重新验证命令示例
+
+后续可在本地采用工具增强置信度（非本次执行）：
+
+```bash
+pnpm add -D -w knip
+pnpm exec knip
+```
+
+或在各包对 `@uncaged/nerve-*` 的导出做面向消费者的契约测试，避免误删对外 API。

packages/cli/package.json

@@ -10,7 +10,7 @@
   },
   "main": "dist/index.js",
   "types": "dist/index.d.ts",
-  "files": ["dist"],
+  "files": ["dist", "skills"],
   "publishConfig": {
     "access": "public"
   },

packages/cli/skills/cursor/.cursorrules

@@ -0,0 +1,587 @@
+<!-- nerve-cli-version: __NERVE_CLI_VERSION__ -->
+
+## Cursor Agent 使用提示
+
+在 Cursor 中与 Agent 对话时，可以用以下方式指代代码与配置：
+
+- **`@Files` / `@file`**：引用单个文件，例如 `@nerve.yaml`、`@senses/cpu-usage/src/index.ts`，减少幻觉并让修改对准正确路径。
+- **`@Folder` / `@Codebase`**：需要跨目录理解工作区结构时使用；改动前仍应优先打开相关 sense/workflow 源文件确认。
+- **`@Terminal`**：把 CLI 输出纳入上下文，便于对照 `nerve daemon logs`、`nerve sense query` 等结果。
+- **`@Docs`**：若项目或依赖有文档索引，可用来对齐 API 与约定。
+- 工作区根目录下的 **`nerve.yaml`**、`senses/`、`workflows/` 是 nerve 的核心入口；讨论调度与配置时优先 `@` 这些路径。
+- 本规则由 `nerve agent inject cursor` 安装；更新 CLI 后在同一目录再次执行可覆盖为新版。
+
+---
+
+# Nerve — AI Agent 观测引擎
+
+Nerve 是一个轻量级观测引擎守护进程。它持续观测外部状态，通过声明式规则响应变化，编排多步骤工作流。
+
+## 核心架构
+
+```
+External World → Sense → Signal → Workflow → Log
+```
+
+| 概念 | 说明 |
+|------|------|
+| **Sense** | 观测函数，`compute()` 采样或推导数据。返回非 null 则发出 Signal，可选触发 Workflow。每个 Sense 有独立 SQLite 数据库。 |
+| **Signal** | Sense 返回非 null 时发出的通知。纯事实，无意图。通过内存 Signal Bus 分发，不持久化。 |
+| **Workflow** | 有状态的多步骤执行。包含 Role（有副作用的执行者）和 Moderator（纯路由器）。每个实例是一个 Thread，有唯一 runId。 |
+| **Log** | 不可变审计日志。记录执行、状态转换、错误。不能触发 Sense（防止反馈循环）。 |
+| **Engine** | 内核，持有 Signal Bus、Process Manager、Workflow Manager。不直接加载用户代码。 |
+| **Daemon** | 引擎运行时，作为后台进程运行。 |
+
+**关键规则：**
+- 因果链单向：External → Sense → Signal → Workflow + Log
+- 进程隔离：每个 Sense group 一个 worker（长期），每个 Workflow 类型一个 worker（按需）
+- 两个扩展点：Sense（观测什么 + 何时）、Workflow（做什么）
+
+## 工作区结构
+
+由 `nerve init` 生成的工作区根目录（默认 `~/.uncaged-nerve/`）包含 **`AGENT.md`**。实现 sense/workflow 前先阅读该文件：它与本文 skill 对齐，约定目录布局、`createRole` 用法以及**始终在仓库根目录**执行的构建命令。
+
+```
+~/.uncaged-nerve/
+├── AGENT.md               # 人类 / Agent 可读的工作区约定（init 生成）
+├── nerve.yaml             # 核心配置
+├── package.json           # 单一根包（sense/workflow 下不再有独立 package）
+├── scripts/build.mjs      # 根目录 esbuild；通过 npm/pnpm 的 build 脚本调用
+├── senses/
+│   └── <name>/
+│       ├── src/index.ts   # exports compute() + table
+│       ├── src/schema.ts  # Drizzle 表定义
+│       └── migrations/    # SQL 迁移
+├── workflows/
+│   └── <name>/
+│       ├── index.ts       # default export：WorkflowDefinition
+│       ├── moderator.ts   # 可选：抽出 moderator，由 index 导入
+│       ├── build.ts       # 可选：共享常量 / 纯函数（避免 index 臃肿；非 esbuild 入口）
+│       └── roles/
+│           └── <role>.ts  # 每角色单文件（推荐平铺，而非 roles/<role>/index.ts）
+└── data/                  # 运行时数据（SQLite、blobs）
+```
+
+### 命名约定
+
+- **Workflow**：动词开头的 kebab-case（例如 `review-pull-request`、`deploy-staging`）。避免单独名词式命名（如 `notifications`）。
+- **Sense**：描述性名词 kebab-case（例如 `cpu-usage`）。
+
+---
+
+## CLI 完整参考
+
+全局选项：`--host <host:port>`（连接远程 daemon）、`--api-token <secret>`（Bearer 认证）
+
+### 初始化与脚手架
+
+```bash
+nerve init                          # 初始化工作区
+nerve init --from <git-url>         # 从 git 仓库克隆工作区
+nerve init workspace                # 只初始化工作区结构
+
+nerve create sense <name>           # 创建 sense 脚手架
+nerve create sense <name> --force   # 覆盖已有
+nerve create workflow <name>        # 创建 workflow 脚手架
+nerve create workflow <name> --force
+
+nerve validate                      # 验证 nerve.yaml 配置
+```
+
+### Daemon 管理
+
+```bash
+nerve daemon start                  # 启动后台 daemon
+nerve daemon start --port 3000      # 指定 HTTP API 端口
+nerve daemon stop                   # 停止 daemon
+nerve daemon restart                # 重启
+nerve daemon status                 # 查看状态
+nerve daemon logs                   # 查看日志
+nerve daemon logs --follow          # 实时日志
+nerve daemon logs --n 50            # 最近 50 行
+
+nerve dev                           # 前台开发模式（不 fork daemon）
+nerve dev --port 3000               # 指定端口
+```
+
+### Sense 操作
+
+```bash
+nerve sense list                    # 列出所有注册的 sense
+nerve sense trigger <name>          # 手动触发 sense 计算
+nerve sense schema <name>           # 查看 sense 数据库表结构
+nerve sense schema <name> --json    # JSON 格式
+nerve sense query <name> <sql>      # 对 sense 数据库执行只读 SQL
+nerve sense query <name> "SELECT * FROM samples ORDER BY ts DESC LIMIT 10" --json
+```
+
+### Workflow 操作
+
+```bash
+nerve workflow list                 # 列出 nerve.yaml 中定义的 workflow
+nerve workflow status               # 查看运行中的 workflow 状态
+nerve workflow trigger <name>       # 触发 workflow
+nerve workflow trigger <name> --prompt "检查生产环境"
+nerve workflow trigger <name> --maxRounds 50
+nerve workflow trigger <name> --dryRun   # 干跑模式
+```
+
+### Thread（Workflow 执行记录）
+
+```bash
+nerve thread list                   # 列出最近的 workflow 执行
+nerve thread list --all             # 包含已完成/失败的
+nerve thread list --workflow <name> # 按 workflow 过滤
+nerve thread list --limit 50        # 最多 50 条
+
+nerve thread show <runId>           # 查看 role 对话轮次
+nerve thread show <runId> --budget 16000  # 增大输出预算（默认 8000 字符）
+
+nerve thread inspect <runId>        # 查看详情和事件
+
+nerve thread kill <runId>           # 终止运行中/排队中的 thread
+```
+
+### Store（日志归档）
+
+```bash
+nerve store archive                 # 导出旧日志到 JSONL 归档
+nerve store archive --vacuum        # 归档后 VACUUM 数据库
+```
+
+### Knowledge（知识库）
+
+```bash
+nerve knowledge sync                # 从 knowledge.yaml 重建索引
+nerve knowledge query "搜索内容"     # 搜索知识库
+nerve knowledge query "内容" --limit 5
+nerve knowledge query "内容" -g     # 搜索所有注册仓库
+```
+
+### Remote（远程 daemon）
+
+```bash
+nerve remote add <name> <host:port> --token <secret>
+nerve remote list
+nerve remote show <name>
+nerve remote set-url <name> <host>
+nerve remote set-token <name> <token>
+nerve remote remove <name>
+nerve remote default <name>         # 设为默认远程
+```
+
+### Agent（向 Hermes 注入本 skill）
+
+```bash
+nerve agent status                  # CLI 版本与各 Hermes 注入目录中的 skill 版本
+nerve agent inject hermes           # 安装到 ~/.hermes/skills/nerve
+nerve agent inject hermes --profile <name>   # 写入 ~/.hermes/profiles/<name>/skills/nerve
+nerve agent update                  # 将所有已注入目录更新到当前 CLI 对应版本
+nerve agent remove hermes           # 移除默认 profile 的注入
+nerve agent remove hermes --profile <name>
+
+nerve agent inject cursor              # 在 cwd 生成 .cursorrules
+nerve agent inject cursor --path /foo  # 在指定目录生成
+nerve agent remove cursor [--path /foo]
+```
+
+---
+
+## nerve.yaml 配置参考
+
+```yaml
+# 引擎全局配置
+max_rounds: 100              # moderator 最大轮次（默认 100）
+
+# Sense 配置
+senses:
+  cpu-usage:
+    group: system            # 必填，同 group 的 sense 共享 worker
+    interval: 10s            # 轮询间隔（duration: 5s, 10m, 1h）
+    throttle: 5s             # 最小计算间隔
+    timeout: 10s             # compute 超时
+    grace_period: null       # 优雅关闭等待
+    retention: 10000         # _signals 表最大行数（默认 10000）
+
+  system-health:
+    group: derived
+    on: [cpu-usage, disk-usage]  # 响应式：被列出的 sense 发出 signal 时触发
+    throttle: null
+    timeout: null
+
+# Workflow 配置
+workflows:
+  my-workflow:
+    concurrency: 1           # 必填，并发数
+    overflow: drop           # 必填，超并发时处理：drop | queue
+    max_queue: 100           # overflow=queue 时的队列上限（默认 100）
+
+# HTTP API
+api:
+  port: 3000                 # null = 不启用 HTTP
+  host: "127.0.0.1"         # 监听地址
+  token: null                # 非 loopback 时必填
+
+# LLM Extract（可选）
+extract:
+  provider: anthropic
+  model: claude-sonnet-4-20250514
+```
+
+---
+
+## Sense 开发指南
+
+### compute 函数签名
+
+Sense 的 `compute` **无参数**。它不接收数据库句柄：daemon 在 worker 内调用 `SenseComputeFn`，由运行时负责把非 null 结果的 `signal` 写入该 sense 的 Drizzle 表并记入 `_signals`。超时由运行时控制（对应 `nerve.yaml` 里的 `timeout`），无需在业务代码里读取 `AbortSignal`。
+
+```typescript
+import type { ComputeResult, SenseComputeFn } from "@uncaged/nerve-core";
+
+export const compute: SenseComputeFn<MySignalShape> = async () => {
+  // ...
+};
+// 或等价地：
+export async function compute(): Promise<ComputeResult<MySignalShape>> {
+  // ...
+}
+```
+
+（运行时定义见 `@uncaged/nerve-core` 的 `SenseComputeFn` / `SenseModule`，daemon 侧在 `sense-runtime.ts` 的 `executeCompute` 中插入 `result.signal`。）
+
+### 返回值
+
+```typescript
+// 返回 null = 静默，不发 signal
+// 返回非 null = 发出 signal（并写入业务表），可选触发 workflow
+type ComputeResult<T> =
+  | null
+  | { signal: T; workflow: WorkflowTrigger | null };
+
+type WorkflowTrigger = {
+  name: string;          // workflow 名称（对应 nerve.yaml 中的 key）
+  maxRounds: number;     // moderator 最大轮次
+  prompt: string;        // 初始 prompt
+  dryRun: boolean;       // 干跑模式
+};
+```
+
+若返回值是普通对象且不含 `signal` 字段，内核会按 shorthand 视为 `{ signal: payload, workflow: null }`（见 core 的 `routeSenseComputeOutput`）。
+
+### Sense 模块导出
+
+```typescript
+// senses/<name>/src/index.ts
+import type { ComputeResult } from "@uncaged/nerve-core";
+import { table } from "./schema.js";
+
+type Row = { ts: number; value: number };
+
+export async function compute(): Promise<ComputeResult<Row>> {
+  const row: Row = { ts: Date.now(), value: Math.random() }; // 替换为真实观测逻辑
+  return { signal: row, workflow: null };
+}
+
+export { table };
+```
+
+### Schema 定义
+
+```typescript
+// senses/<name>/src/schema.ts
+import { sqliteTable, integer, real } from "drizzle-orm/sqlite-core";
+
+export const table = sqliteTable("samples", {
+  ts: integer("ts").notNull(),
+  value: real("value").notNull(),
+});
+```
+
+### 调度方式
+
+1. **interval 轮询**：`interval: 10s` — 每 10 秒执行一次
+2. **响应式触发**：`on: [cpu-usage]` — 当 cpu-usage 发出 signal 时触发
+3. 两者可以组合
+
+### 调试
+
+```bash
+nerve dev                           # 前台运行，看实时输出
+nerve sense trigger <name>          # 手动触发一次
+nerve sense query <name> "SELECT * FROM samples ORDER BY ts DESC LIMIT 5"
+```
+
+### 完整示例：CPU 监控
+
+```typescript
+// senses/cpu-usage/src/schema.ts
+import { sqliteTable, integer, real } from "drizzle-orm/sqlite-core";
+
+export const table = sqliteTable("samples", {
+  ts: integer("ts").notNull(),
+  value: real("value").notNull(),
+});
+
+// senses/cpu-usage/src/index.ts
+import os from "node:os";
+import type { ComputeResult } from "@uncaged/nerve-core";
+import { table } from "./schema.js";
+
+type Row = { ts: number; value: number };
+
+export async function compute(): Promise<ComputeResult<Row>> {
+  const oneMin = os.loadavg()[0];
+  return { signal: { ts: Date.now(), value: oneMin }, workflow: null };
+}
+
+export { table };
+```
+
+nerve.yaml:
+```yaml
+senses:
+  cpu-usage:
+    group: system
+    interval: 10s
+    throttle: 5s
+    timeout: 10s
+    retention: 10000
+```
+
+---
+
+## Workflow 开发指南
+
+### 核心类型
+
+```typescript
+import type {
+  WorkflowDefinition,
+  RoleResult,
+  ThreadContext,
+  RoleMeta,
+  Moderator,
+} from "@uncaged/nerve-core";
+import { END } from "@uncaged/nerve-core";
+
+// Role<Meta> — (ctx: ThreadContext) => Promise<RoleResult<Meta>>
+// RoleResult<Meta> — { content: string; meta: Meta }
+// ThreadContext<M extends RoleMeta> — threadId, start（__start__ 帧）, steps（各 role 轮次）
+// Moderator<M> — (ctx) => 下一个 role 名 | END
+// WorkflowDefinition<M extends RoleMeta> — name, roles, moderator
+```
+
+### createRole 四元组（接入 LLM 时推荐）
+
+工作区根目录需安装 **`@uncaged/nerve-workflow-utils`**（及所选 agent 适配器包）。默认 `nerve init` 的 `package.json` 不含该依赖时，在 `~/.uncaged-nerve` 下执行 `pnpm add @uncaged/nerve-workflow-utils`（或 npm 等价命令）。
+
+使用 **`createRole`**，按固定顺序传入四件事：
+
+1. **adapter** — `AgentFn`，`(ctx, systemPrompt) => Promise<string>`（原始模型输出文本）。
+2. **prompt** — `string`，或 `async (ctx: ThreadContext) => string`。
+3. **meta** — `z.ZodType<M>`，供 moderator 路由的结构化 meta。
+4. **extract** — `{ provider: LlmProvider; dryRun: boolean | null }`，声明从回复中抽取 meta 时用的 LLM（OpenAI 兼容）及是否 dry-run。
+
+```typescript
+import { createLlmAdapter, createRole } from "@uncaged/nerve-workflow-utils";
+import type { ThreadContext } from "@uncaged/nerve-core";
+import { z } from "zod";
+
+const provider = {
+  baseUrl: "https://api.example.com/v1",
+  apiKey: process.env.EXAMPLE_API_KEY!,
+  model: "gpt-4o-mini",
+};
+
+const planMeta = z.object({ next: z.enum(["execute", "stop"]) });
+
+export const planner = createRole(
+  createLlmAdapter(provider),
+  async (ctx: ThreadContext) => `规划任务：${ctx.start.content}`,
+  planMeta,
+  { provider, dryRun: null },
+);
+```
+
+`createLlmAdapter` 仅位于 **`@uncaged/nerve-workflow-utils`**：用 `LlmProvider` 生成 `AgentFn`，单轮对话里 **system** 来自 `createRole` 解析后的 prompt 字符串，**user** 为线程起点 `ctx.start.content`。
+
+### 基本 Workflow 示例（平铺 `roles/<role>.ts`）
+
+```typescript
+// workflows/example/roles/main.ts
+import type { RoleResult, ThreadContext } from "@uncaged/nerve-core";
+
+export async function main(ctx: ThreadContext): Promise<RoleResult<{ round: number }>> {
+  const prompt = ctx.start.content;
+  return {
+    content: `处理完成: ${prompt}`,
+    meta: { round: ctx.steps.length },
+  };
+}
+```
+
+```typescript
+// workflows/example/index.ts
+import type { ThreadContext, WorkflowDefinition } from "@uncaged/nerve-core";
+import { END } from "@uncaged/nerve-core";
+
+import { main } from "./roles/main.js";
+
+type Meta = Record<"main", { round: number }>;
+
+const workflow: WorkflowDefinition<Meta> = {
+  name: "example",
+  roles: { main },
+  moderator(ctx: ThreadContext<Meta>) {
+    return ctx.steps.length === 0 ? "main" : END;
+  },
+};
+
+export default workflow;
+```
+
+可选：将 `moderator` 挪到 `moderator.ts` 再 `import { route } from "./moderator.js"`，保持 `index.ts` 只负责组装 `WorkflowDefinition`。
+
+### 多 Role Workflow 示例
+
+```typescript
+// workflows/plan-execute-review/roles/planner.ts
+import type { RoleResult, ThreadContext } from "@uncaged/nerve-core";
+
+export async function planner(ctx: ThreadContext): Promise<RoleResult<{ status: string }>> {
+  void ctx;
+  return { content: "计划: ...", meta: { status: "planned" } };
+}
+```
+
+```typescript
+// workflows/plan-execute-review/roles/executor.ts
+import type { RoleResult, ThreadContext } from "@uncaged/nerve-core";
+
+export async function executor(ctx: ThreadContext): Promise<RoleResult<{ status: string }>> {
+  void ctx;
+  return { content: "执行: ...", meta: { status: "executed" } };
+}
+```
+
+```typescript
+// workflows/plan-execute-review/roles/reviewer.ts
+import type { RoleResult, ThreadContext } from "@uncaged/nerve-core";
+
+export async function reviewer(ctx: ThreadContext): Promise<RoleResult<{ status: string }>> {
+  void ctx;
+  return { content: "审核通过", meta: { status: "approved" } };
+}
+```
+
+```typescript
+// workflows/plan-execute-review/index.ts
+import type { WorkflowDefinition, ThreadContext } from "@uncaged/nerve-core";
+import { END } from "@uncaged/nerve-core";
+
+import { executor } from "./roles/executor.js";
+import { planner } from "./roles/planner.js";
+import { reviewer } from "./roles/reviewer.js";
+
+type Roles = Record<"planner" | "executor" | "reviewer", { status: string }>;
+
+const workflow: WorkflowDefinition<Roles> = {
+  name: "plan-execute-review",
+  roles: { planner, executor, reviewer },
+  moderator(ctx: ThreadContext<Roles>) {
+    if (ctx.steps.length === 0) return "planner";
+    const last = ctx.steps[ctx.steps.length - 1];
+    if (last.role === "planner") return "executor";
+    if (last.role === "executor") return "reviewer";
+    return END;
+  },
+};
+
+export default workflow;
+```
+
+### Agent 适配器
+
+Workflow role 可以集成 AI agent。已知适配器 **ID**：`echo`、`cursor`、`hermes`、`codex`。
+
+```typescript
+type AgentFn = (ctx: ThreadContext, systemPrompt: string) => Promise<string>;
+```
+
+没有现成 agent 包时，用 **`createLlmAdapter`（`@uncaged/nerve-workflow-utils`）** 从 OpenAI 兼容的 `LlmProvider` 构造 `AgentFn`，再交给 **`createRole`** 的四元组。
+
+### Workflow 运行状态
+
+`queued` → `started` → `completed` | `failed` | `crashed` | `killed` | `interrupted` | `dropped`
+
+---
+
+## 日常操作 Pattern
+
+### 查看系统整体状态
+
+```bash
+nerve daemon status                 # daemon 是否在运行
+nerve sense list                    # 所有 sense 及其调度配置
+nerve workflow status               # 运行中的 workflow
+nerve thread list                   # 最近的 workflow 执行记录
+```
+
+### 检查某个 sense 的历史数据
+
+```bash
+nerve sense query cpu-usage "SELECT * FROM samples ORDER BY ts DESC LIMIT 10" --json
+nerve sense schema cpu-usage        # 查看表结构
+```
+
+### 手动触发 workflow
+
+```bash
+nerve workflow trigger my-workflow --prompt "手动检查"
+nerve thread list --workflow my-workflow  # 查看执行状态
+nerve thread show <runId>           # 查看对话详情
+```
+
+### 排查 sense 报错
+
+```bash
+nerve daemon logs --follow          # 查看实时日志
+nerve sense trigger <name>          # 手动触发看报错
+nerve dev                           # 前台模式，更详细的输出
+```
+
+### 开发新 sense
+
+```bash
+nerve create sense my-sensor        # 脚手架
+# 编辑 senses/my-sensor/src/index.ts 和 schema.ts
+nerve validate                      # 验证配置
+nerve dev                           # 前台测试
+nerve sense trigger my-sensor       # 单次触发验证
+nerve sense query my-sensor "SELECT * FROM ..."  # 检查数据
+```
+
+### 开发新 workflow
+
+```bash
+nerve create workflow my-flow       # 脚手架（当前 CLI 可能仍生成 roles/<name>/ 子目录）
+# 推荐对齐 AGENT.md：workflows/my-flow/index.ts + roles/<role>.ts（平铺），moderator 可拆到 moderator.ts
+nerve validate                      # 验证配置
+cd ~/.uncaged-nerve && npm run build   # 工作区根目录构建（等价：pnpm run build）；勿在单个 workflow 子目录单独跑 build
+nerve workflow trigger my-flow --prompt "测试" --dryRun  # 干跑
+nerve thread show <runId>           # 查看执行轨迹
+```
+
+---
+
+## Pitfalls
+
+- **Sense 返回值**：返回 `null` 表示静默（不发 signal）；返回 `{ signal, workflow }` 才发 signal。不要返回 undefined。
+- **Sense 持久化**：daemon 在 `compute()` 返回非 null 时自动执行 `db.insert(table).values(signal)` 并写入 `_signals`；业务代码不要自行 insert。
+- **no optional properties**：nerve 代码规范禁止 `?:`，用 `T | null` 代替。
+- **函数式风格**：用 `function` + `type`，不用 `class` + `interface`。
+- **workflow 用 default export**：工作区里通常只有 `workflows/<name>/index.ts` 使用 default export（daemon 加载约定）。
+- **_signals 表**：每个 sense 自动有 `_signals` 表记录 signal 历史，受 `retention` 配置限制。
+- **concurrency + overflow**：workflow 必须配置并发策略，否则验证失败。
+- **moderator 是同步函数**：不要加 async，moderator 是纯路由逻辑，不能有副作用。

packages/cli/skills/hermes/SKILL.md

@@ -36,23 +36,34 @@ External World → Sense → Signal → Workflow → Log
 
 ## 工作区结构
 
+由 `nerve init` 生成的工作区根目录（默认 `~/.uncaged-nerve/`）包含 **`AGENT.md`**。实现 sense/workflow 前先阅读该文件：它与本文 skill 对齐，约定目录布局、`createRole` 用法以及**始终在仓库根目录**执行的构建命令。
+
 ```
-~/.uncaged-nerve/          # 默认工作区（nerve init 创建）
+~/.uncaged-nerve/
+├── AGENT.md               # 人类 / Agent 可读的工作区约定（init 生成）
 ├── nerve.yaml             # 核心配置
+├── package.json           # 单一根包（sense/workflow 下不再有独立 package）
+├── scripts/build.mjs      # 根目录 esbuild；通过 npm/pnpm 的 build 脚本调用
 ├── senses/
 │   └── <name>/
 │       ├── src/index.ts   # exports compute() + table
-│       ├── src/schema.ts  # drizzle 表定义
+│       ├── src/schema.ts  # Drizzle 表定义
 │       └── migrations/    # SQL 迁移
 ├── workflows/
 │   └── <name>/
-│       ├── index.ts       # exports WorkflowDefinition
-│       └── roles/<role>/
-│           ├── index.ts   # role 实现
-│           └── prompt.md  # 可选 system prompt
+│       ├── index.ts       # default export：WorkflowDefinition
+│       ├── moderator.ts   # 可选：抽出 moderator，由 index 导入
+│       ├── build.ts       # 可选：共享常量 / 纯函数（避免 index 臃肿；非 esbuild 入口）
+│       └── roles/
+│           └── <role>.ts  # 每角色单文件（推荐平铺，而非 roles/<role>/index.ts）
 └── data/                  # 运行时数据（SQLite、blobs）
 ```
 
+### 命名约定
+
+- **Workflow**：动词开头的 kebab-case（例如 `review-pull-request`、`deploy-staging`）。避免单独名词式命名（如 `notifications`）。
+- **Sense**：描述性名词 kebab-case（例如 `cpu-usage`）。
+
 ---
 
 ## CLI 完整参考
@@ -156,6 +167,17 @@ nerve remote remove <name>
 nerve remote default <name>         # 设为默认远程
 ```
 
+### Agent（向 Hermes 注入本 skill）
+
+```bash
+nerve agent status                  # CLI 版本与各 Hermes 注入目录中的 skill 版本
+nerve agent inject hermes           # 安装到 ~/.hermes/skills/nerve
+nerve agent inject hermes --profile <name>   # 写入 ~/.hermes/profiles/<name>/skills/nerve
+nerve agent update                  # 将所有已注入目录更新到当前 CLI 对应版本
+nerve agent remove hermes           # 移除默认 profile 的注入
+nerve agent remove hermes --profile <name>
+```
+
 ---
 
 ## nerve.yaml 配置参考
@@ -205,22 +227,27 @@ extract:
 
 ### compute 函数签名
 
-```typescript
-import type { LibSQLDatabase } from "drizzle-orm/libsql";
-import type { ComputeResult, WorkflowTrigger } from "@uncaged/nerve-core";
+Sense 的 `compute` **无参数**。它不接收数据库句柄：daemon 在 worker 内调用 `SenseComputeFn`，由运行时负责把非 null 结果的 `signal` 写入该 sense 的 Drizzle 表并记入 `_signals`。超时由运行时控制（对应 `nerve.yaml` 里的 `timeout`），无需在业务代码里读取 `AbortSignal`。
 
-export async function compute(
-  db: LibSQLDatabase,                          // 此 sense 的 Drizzle ORM 数据库
-  peers: Record<string, LibSQLDatabase>,       // 其他 sense 的数据库（只读）
-  options: { signal: AbortSignal },            // 超时 abort signal
-): Promise<ComputeResult<T>>
+```typescript
+import type { ComputeResult, SenseComputeFn } from "@uncaged/nerve-core";
+
+export const compute: SenseComputeFn<MySignalShape> = async () => {
+  // ...
+};
+// 或等价地：
+export async function compute(): Promise<ComputeResult<MySignalShape>> {
+  // ...
+}
 ```
 
+（运行时定义见 `@uncaged/nerve-core` 的 `SenseComputeFn` / `SenseModule`，daemon 侧在 `sense-runtime.ts` 的 `executeCompute` 中插入 `result.signal`。）
+
 ### 返回值
 
 ```typescript
 // 返回 null = 静默，不发 signal
-// 返回非 null = 发出 signal，可选触发 workflow
+// 返回非 null = 发出 signal（并写入业务表），可选触发 workflow
 type ComputeResult<T> =
   | null
   | { signal: T; workflow: WorkflowTrigger | null };
@@ -233,21 +260,20 @@ type WorkflowTrigger = {
 };
 ```
 
+若返回值是普通对象且不含 `signal` 字段，内核会按 shorthand 视为 `{ signal: payload, workflow: null }`（见 core 的 `routeSenseComputeOutput`）。
+
 ### Sense 模块导出
 
 ```typescript
 // senses/<name>/src/index.ts
-import type { SenseModule, ComputeResult } from "@uncaged/nerve-core";
+import type { ComputeResult } from "@uncaged/nerve-core";
 import { table } from "./schema.js";
 
-export async function compute(
-  db: LibSQLDatabase,
-  _peers: Record<string, LibSQLDatabase>,
-  _options: { signal: AbortSignal },
-): Promise<ComputeResult<number>> {
-  const value = Math.random(); // 替换为真实观测逻辑
-  await db.insert(table).values({ ts: Date.now(), value });
-  return { signal: value, workflow: null };
+type Row = { ts: number; value: number };
+
+export async function compute(): Promise<ComputeResult<Row>> {
+  const row: Row = { ts: Date.now(), value: Math.random() }; // 替换为真实观测逻辑
+  return { signal: row, workflow: null };
 }
 
 export { table };
@@ -292,18 +318,14 @@ export const table = sqliteTable("samples", {
 
 // senses/cpu-usage/src/index.ts
 import os from "node:os";
-import type { LibSQLDatabase } from "drizzle-orm/libsql";
 import type { ComputeResult } from "@uncaged/nerve-core";
 import { table } from "./schema.js";
 
-export async function compute(
-  db: LibSQLDatabase,
-  _peers: Record<string, LibSQLDatabase>,
-  _options: { signal: AbortSignal },
-): Promise<ComputeResult<number>> {
+type Row = { ts: number; value: number };
+
+export async function compute(): Promise<ComputeResult<Row>> {
   const oneMin = os.loadavg()[0];
-  await db.insert(table).values({ ts: Date.now(), value: oneMin });
-  return { signal: oneMin, workflow: null };
+  return { signal: { ts: Date.now(), value: oneMin }, workflow: null };
 }
 
 export { table };
@@ -331,55 +353,80 @@ import type {
   WorkflowDefinition,
   RoleResult,
   ThreadContext,
-  StartStep,
-  RoleStep,
+  RoleMeta,
+  Moderator,
 } from "@uncaged/nerve-core";
 import { END } from "@uncaged/nerve-core";
 
-// Role：执行者，接收上下文返回结果
-type Role<Meta> = (ctx: ThreadContext) => Promise<RoleResult<Meta>>;
-type RoleResult<Meta> = { content: string; meta: Meta };
-
-// Moderator：路由器，决定下一个 role 或结束
-type Moderator<M> = (ctx: ThreadContext<M>) => (keyof M & string) | typeof END;
-
-// ThreadContext：对话上下文
-type ThreadContext<M = RoleMeta> = {
-  threadId: string;
-  start: StartStep;       // 初始 prompt（role: "__start__"）
-  steps: RoleStep<M>[];   // 所有 role 的执行记录
-};
-
-// WorkflowDefinition：完整定义
-type WorkflowDefinition<M> = {
-  name: string;
-  roles: { [K in keyof M & string]: Role<M[K]> };
-  moderator: Moderator<M>;
-};
+// Role<Meta> — (ctx: ThreadContext) => Promise<RoleResult<Meta>>
+// RoleResult<Meta> — { content: string; meta: Meta }
+// ThreadContext<M extends RoleMeta> — threadId, start（__start__ 帧）, steps（各 role 轮次）
+// Moderator<M> — (ctx) => 下一个 role 名 | END
+// WorkflowDefinition<M extends RoleMeta> — name, roles, moderator
 ```
 
-### 基本 Workflow 示例
+### createRole 四元组（接入 LLM 时推荐）
+
+工作区根目录需安装 **`@uncaged/nerve-workflow-utils`**（及所选 agent 适配器包）。默认 `nerve init` 的 `package.json` 不含该依赖时，在 `~/.uncaged-nerve` 下执行 `pnpm add @uncaged/nerve-workflow-utils`（或 npm 等价命令）。
+
+使用 **`createRole`**，按固定顺序传入四件事：
+
+1. **adapter** — `AgentFn`，`(ctx, systemPrompt) => Promise<string>`（原始模型输出文本）。
+2. **prompt** — `string`，或 `async (ctx: ThreadContext) => string`。
+3. **meta** — `z.ZodType<M>`，供 moderator 路由的结构化 meta。
+4. **extract** — `{ provider: LlmProvider; dryRun: boolean | null }`，声明从回复中抽取 meta 时用的 LLM（OpenAI 兼容）及是否 dry-run。
 
 ```typescript
-// workflows/example/index.ts
-import type { RoleResult, ThreadContext, WorkflowDefinition } from "@uncaged/nerve-core";
-import { END } from "@uncaged/nerve-core";
+import { createLlmAdapter, createRole } from "@uncaged/nerve-workflow-utils";
+import type { ThreadContext } from "@uncaged/nerve-core";
+import { z } from "zod";
 
-type Meta = Record<"main", { round: number }>;
+const provider = {
+  baseUrl: "https://api.example.com/v1",
+  apiKey: process.env.EXAMPLE_API_KEY!,
+  model: "gpt-4o-mini",
+};
 
-async function main(ctx: ThreadContext): Promise<RoleResult<{ round: number }>> {
+const planMeta = z.object({ next: z.enum(["execute", "stop"]) });
+
+export const planner = createRole(
+  createLlmAdapter(provider),
+  async (ctx: ThreadContext) => `规划任务：${ctx.start.content}`,
+  planMeta,
+  { provider, dryRun: null },
+);
+```
+
+`createLlmAdapter` 仅位于 **`@uncaged/nerve-workflow-utils`**：用 `LlmProvider` 生成 `AgentFn`，单轮对话里 **system** 来自 `createRole` 解析后的 prompt 字符串，**user** 为线程起点 `ctx.start.content`。
+
+### 基本 Workflow 示例（平铺 `roles/<role>.ts`）
+
+```typescript
+// workflows/example/roles/main.ts
+import type { RoleResult, ThreadContext } from "@uncaged/nerve-core";
+
+export async function main(ctx: ThreadContext): Promise<RoleResult<{ round: number }>> {
   const prompt = ctx.start.content;
   return {
     content: `处理完成: ${prompt}`,
     meta: { round: ctx.steps.length },
   };
 }
+```
+
+```typescript
+// workflows/example/index.ts
+import type { ThreadContext, WorkflowDefinition } from "@uncaged/nerve-core";
+import { END } from "@uncaged/nerve-core";
+
+import { main } from "./roles/main.js";
+
+type Meta = Record<"main", { round: number }>;
 
 const workflow: WorkflowDefinition<Meta> = {
   name: "example",
   roles: { main },
   moderator(ctx: ThreadContext<Meta>) {
-    // 执行一次 main 就结束
     return ctx.steps.length === 0 ? "main" : END;
   },
 };
@@ -387,25 +434,50 @@ const workflow: WorkflowDefinition<Meta> = {
 export default workflow;
 ```
 
+可选：将 `moderator` 挪到 `moderator.ts` 再 `import { route } from "./moderator.js"`，保持 `index.ts` 只负责组装 `WorkflowDefinition`。
+
 ### 多 Role Workflow 示例
 
 ```typescript
-import type { WorkflowDefinition, RoleResult, ThreadContext } from "@uncaged/nerve-core";
-import { END } from "@uncaged/nerve-core";
+// workflows/plan-execute-review/roles/planner.ts
+import type { RoleResult, ThreadContext } from "@uncaged/nerve-core";
 
-type Roles = Record<"planner" | "executor" | "reviewer", { status: string }>;
-
-async function planner(ctx: ThreadContext): Promise<RoleResult<{ status: string }>> {
+export async function planner(ctx: ThreadContext): Promise<RoleResult<{ status: string }>> {
+  void ctx;
   return { content: "计划: ...", meta: { status: "planned" } };
 }
+```
 
-async function executor(ctx: ThreadContext): Promise<RoleResult<{ status: string }>> {
+```typescript
+// workflows/plan-execute-review/roles/executor.ts
+import type { RoleResult, ThreadContext } from "@uncaged/nerve-core";
+
+export async function executor(ctx: ThreadContext): Promise<RoleResult<{ status: string }>> {
+  void ctx;
   return { content: "执行: ...", meta: { status: "executed" } };
 }
+```
 
-async function reviewer(ctx: ThreadContext): Promise<RoleResult<{ status: string }>> {
+```typescript
+// workflows/plan-execute-review/roles/reviewer.ts
+import type { RoleResult, ThreadContext } from "@uncaged/nerve-core";
+
+export async function reviewer(ctx: ThreadContext): Promise<RoleResult<{ status: string }>> {
+  void ctx;
   return { content: "审核通过", meta: { status: "approved" } };
 }
+```
+
+```typescript
+// workflows/plan-execute-review/index.ts
+import type { WorkflowDefinition, ThreadContext } from "@uncaged/nerve-core";
+import { END } from "@uncaged/nerve-core";
+
+import { executor } from "./roles/executor.js";
+import { planner } from "./roles/planner.js";
+import { reviewer } from "./roles/reviewer.js";
+
+type Roles = Record<"planner" | "executor" | "reviewer", { status: string }>;
 
 const workflow: WorkflowDefinition<Roles> = {
   name: "plan-execute-review",
@@ -424,12 +496,14 @@ export default workflow;
 
 ### Agent 适配器
 
-Workflow role 可以集成 AI agent。已知适配器 ID：`echo`、`cursor`、`hermes`、`codex`。
+Workflow role 可以集成 AI agent。已知适配器 **ID**：`echo`、`cursor`、`hermes`、`codex`。
 
 ```typescript
 type AgentFn = (ctx: ThreadContext, systemPrompt: string) => Promise<string>;
 ```
 
+没有现成 agent 包时，用 **`createLlmAdapter`（`@uncaged/nerve-workflow-utils`）** 从 OpenAI 兼容的 `LlmProvider` 构造 `AgentFn`，再交给 **`createRole`** 的四元组。
+
 ### Workflow 运行状态
 
 `queued` → `started` → `completed` | `failed` | `crashed` | `killed` | `interrupted` | `dropped`
@@ -484,9 +558,10 @@ nerve sense query my-sensor "SELECT * FROM ..."  # 检查数据
 ### 开发新 workflow
 
 ```bash
-nerve create workflow my-flow       # 脚手架
-# 编辑 workflows/my-flow/index.ts 和 roles/
+nerve create workflow my-flow       # 脚手架（当前 CLI 可能仍生成 roles/<name>/ 子目录）
+# 推荐对齐 AGENT.md：workflows/my-flow/index.ts + roles/<role>.ts（平铺），moderator 可拆到 moderator.ts
 nerve validate                      # 验证配置
+cd ~/.uncaged-nerve && npm run build   # 工作区根目录构建（等价：pnpm run build）；勿在单个 workflow 子目录单独跑 build
 nerve workflow trigger my-flow --prompt "测试" --dryRun  # 干跑
 nerve thread show <runId>           # 查看执行轨迹
 ```
@@ -496,10 +571,10 @@ nerve thread show <runId>           # 查看执行轨迹
 ## Pitfalls
 
 - **Sense 返回值**：返回 `null` 表示静默（不发 signal）；返回 `{ signal, workflow }` 才发 signal。不要返回 undefined。
+- **Sense 持久化**：daemon 在 `compute()` 返回非 null 时自动执行 `db.insert(table).values(signal)` 并写入 `_signals`；业务代码不要自行 insert。
 - **no optional properties**：nerve 代码规范禁止 `?:`，用 `T | null` 代替。
 - **函数式风格**：用 `function` + `type`，不用 `class` + `interface`。
-- **workflow 用 default export**：这是唯一允许 default export 的场景。
+- **workflow 用 default export**：工作区里通常只有 `workflows/<name>/index.ts` 使用 default export（daemon 加载约定）。
 - **_signals 表**：每个 sense 自动有 `_signals` 表记录 signal 历史，受 `retention` 配置限制。
-- **peers 只读**：sense 的 `peers` 参数提供其他 sense 数据库的只读访问，不要写入。
 - **concurrency + overflow**：workflow 必须配置并发策略，否则验证失败。
 - **moderator 是同步函数**：不要加 async，moderator 是纯路由逻辑，不能有副作用。

packages/cli/src/cli.ts

@@ -3,6 +3,7 @@ import "@uncaged/nerve-daemon/experimental-warning-suppression.js";
 import { defineCommand, runMain } from "citty";
 
 import { consumeGlobalDaemonCliFlags } from "./cli-global.js";
+import { agentCommand } from "./commands/agent.js";
 import { createCommand } from "./commands/create.js";
 import { daemonCommand } from "./commands/daemon.js";
 import { devCommand } from "./commands/dev.js";
@@ -42,6 +43,7 @@ const main = defineCommand({
       "Nerve — an AI agent kernel. Global options: --host <host:port> (remote HTTP), --api-token <secret> (Bearer auth).",
   },
   subCommands: {
+    agent: agentCommand,
     init: initCommand,
     create: createCommand,
     daemon: daemonCommand,

packages/cli/src/commands/agent.ts

@@ -0,0 +1,378 @@
+import {
+  cpSync,
+  existsSync,
+  mkdirSync,
+  readFileSync,
+  readdirSync,
+  rmSync,
+  statSync,
+  writeFileSync,
+} from "node:fs";
+import { homedir } from "node:os";
+import { dirname, join, resolve as resolvePath } from "node:path";
+import { fileURLToPath } from "node:url";
+
+import { defineCommand } from "citty";
+
+function getPackageRootDir(): string {
+  const thisFile = fileURLToPath(import.meta.url);
+  let dir = dirname(thisFile);
+  for (let i = 0; i < 5; i++) {
+    if (existsSync(join(dir, "package.json"))) return dir;
+    dir = dirname(dir);
+  }
+  throw new Error("Cannot locate package root. Is the CLI package intact?");
+}
+
+function getCliVersion(): string {
+  const pkgPath = join(getPackageRootDir(), "package.json");
+  const pkg = JSON.parse(readFileSync(pkgPath, "utf8")) as { version: string };
+  return pkg.version;
+}
+
+let _cachedVersion: string | null = null;
+function cliVersion(): string {
+  if (_cachedVersion === null) _cachedVersion = getCliVersion();
+  return _cachedVersion;
+}
+
+function getSkillSourceDir(): string {
+  const root = getPackageRootDir();
+  const skillsDir = join(root, "skills");
+  if (!existsSync(skillsDir)) {
+    throw new Error("Cannot locate skills directory. Is the CLI package intact?");
+  }
+  return skillsDir;
+}
+
+function getHermesSkillDir(profile: string | null): string {
+  const hermesHome = join(homedir(), ".hermes");
+  if (profile !== null) {
+    return join(hermesHome, "profiles", profile, "skills", "nerve");
+  }
+  return join(hermesHome, "skills", "nerve");
+}
+
+function readVersionFile(skillDir: string): string | null {
+  const versionPath = join(skillDir, ".nerve-version");
+  if (!existsSync(versionPath)) return null;
+  return readFileSync(versionPath, "utf8").trim();
+}
+
+function writeVersionFile(skillDir: string, version: string): void {
+  writeFileSync(join(skillDir, ".nerve-version"), `${version}\n`, "utf8");
+}
+
+const CURSOR_VERSION_MARKER_RE = /<!--\s*nerve-cli-version:\s*([^>]+?)\s*-->/;
+
+function resolveCursorProjectDir(pathArg: string | null): string {
+  const raw = pathArg !== null && pathArg !== "" ? pathArg : process.cwd();
+  return resolvePath(raw);
+}
+
+function assertDirectory(projectDir: string, label: string): void {
+  if (!existsSync(projectDir)) {
+    process.stderr.write(`❌ ${label} does not exist: ${projectDir}\n`);
+    process.exit(1);
+  }
+  if (!statSync(projectDir).isDirectory()) {
+    process.stderr.write(`❌ ${label} is not a directory: ${projectDir}\n`);
+    process.exit(1);
+  }
+}
+
+function readCursorInjectVersion(projectDir: string): string | null {
+  const versionPath = join(projectDir, ".nerve-version");
+  if (existsSync(versionPath)) {
+    return readFileSync(versionPath, "utf8").trim();
+  }
+  const rulesPath = join(projectDir, ".cursorrules");
+  if (!existsSync(rulesPath)) return null;
+  const content = readFileSync(rulesPath, "utf8");
+  const match = content.match(CURSOR_VERSION_MARKER_RE);
+  return match !== null ? match[1].trim() : null;
+}
+
+function injectCursor(projectDir: string): void {
+  assertDirectory(projectDir, "Project directory");
+  const rulesPath = join(projectDir, ".cursorrules");
+  const existingVer = readCursorInjectVersion(projectDir);
+  if (existingVer === cliVersion() && existsSync(rulesPath)) {
+    process.stdout.write(
+      `✅ Cursor .cursorrules is already up to date (v${cliVersion()}) at ${projectDir}\n`,
+    );
+    return;
+  }
+
+  const templatePath = join(getSkillSourceDir(), "cursor", ".cursorrules");
+  if (!existsSync(templatePath)) {
+    throw new Error("Cannot locate cursor/.cursorrules template. Is the CLI package intact?");
+  }
+  let body = readFileSync(templatePath, "utf8");
+  body = body.replaceAll("__NERVE_CLI_VERSION__", cliVersion());
+  writeFileSync(rulesPath, body, "utf8");
+  writeVersionFile(projectDir, cliVersion());
+
+  const action = existingVer !== null ? "Updated" : "Installed";
+  process.stdout.write(`✅ ${action} Cursor .cursorrules v${cliVersion()} at ${projectDir}\n`);
+}
+
+function removeCursor(projectDir: string): void {
+  assertDirectory(projectDir, "Project directory");
+  const rulesPath = join(projectDir, ".cursorrules");
+  const versionPath = join(projectDir, ".nerve-version");
+  if (!existsSync(rulesPath)) {
+    process.stdout.write(`ℹ️ Cursor .cursorrules is not present at ${projectDir}\n`);
+    return;
+  }
+  rmSync(rulesPath, { force: true });
+  if (existsSync(versionPath)) {
+    rmSync(versionPath, { force: true });
+  }
+  process.stdout.write(`✅ Removed Cursor .cursorrules from ${projectDir}\n`);
+}
+
+function injectHermes(profile: string | null): void {
+  const sourceDir = join(getSkillSourceDir(), "hermes");
+  const targetDir = getHermesSkillDir(profile);
+  const existing = readVersionFile(targetDir);
+
+  if (existing === cliVersion()) {
+    const loc = profile !== null ? ` (profile: ${profile})` : "";
+    process.stdout.write(`✅ Hermes nerve skill is already up to date (v${cliVersion()})${loc}\n`);
+    return;
+  }
+
+  mkdirSync(targetDir, { recursive: true });
+  cpSync(sourceDir, targetDir, { recursive: true });
+  writeVersionFile(targetDir, cliVersion());
+
+  const action = existing !== null ? "Updated" : "Installed";
+  const loc = profile !== null ? ` (profile: ${profile})` : "";
+  process.stdout.write(`✅ ${action} Hermes nerve skill v${cliVersion()}${loc}\n`);
+  process.stdout.write(`   → ${targetDir}/SKILL.md\n`);
+}
+
+function removeHermes(profile: string | null): void {
+  const targetDir = getHermesSkillDir(profile);
+  if (!existsSync(targetDir)) {
+    process.stdout.write("ℹ️ Hermes nerve skill is not installed.\n");
+    return;
+  }
+  rmSync(targetDir, { recursive: true, force: true });
+  const loc = profile !== null ? ` (profile: ${profile})` : "";
+  process.stdout.write(`✅ Removed Hermes nerve skill${loc}\n`);
+}
+
+function printCursorStatusLine(projectDir: string): void {
+  const rulesPath = join(projectDir, ".cursorrules");
+  const label = `Cursor (${projectDir})`;
+  if (!existsSync(rulesPath)) {
+    process.stdout.write(`  ${label}: ❌ not installed\n`);
+    return;
+  }
+  const ver = readCursorInjectVersion(projectDir);
+  if (ver === null) {
+    process.stdout.write(
+      `  ${label}: ⚠️ installed (unknown version; run \`nerve agent inject cursor\`)\n`,
+    );
+    return;
+  }
+  if (ver === cliVersion()) {
+    process.stdout.write(`  ${label}: ✅ v${ver}\n`);
+  } else {
+    process.stdout.write(
+      `  ${label}: ⚠️ v${ver} → v${cliVersion()} available (run \`nerve agent inject cursor\`)\n`,
+    );
+  }
+}
+
+function printStatus(): void {
+  process.stdout.write(`nerve agent skills (CLI v${cliVersion()})\n\n`);
+
+  printCursorStatusLine(process.cwd());
+  process.stdout.write("\n");
+
+  // Default profile
+  const defaultDir = getHermesSkillDir(null);
+  const defaultVer = readVersionFile(defaultDir);
+  printAgentLine("Hermes (default)", defaultVer);
+
+  // Named profiles
+  const profilesDir = join(homedir(), ".hermes", "profiles");
+  if (existsSync(profilesDir)) {
+    const profiles = readdirSync(profilesDir, { withFileTypes: true })
+      .filter((d) => d.isDirectory())
+      .map((d) => d.name);
+
+    for (const profile of profiles) {
+      const dir = getHermesSkillDir(profile);
+      const ver = readVersionFile(dir);
+      if (ver !== null) {
+        printAgentLine(`Hermes (${profile})`, ver);
+      }
+    }
+  }
+
+  process.stdout.write("\n");
+}
+
+function printAgentLine(label: string, version: string | null): void {
+  if (version === null) {
+    process.stdout.write(`  ${label}: ❌ not installed\n`);
+  } else if (version === cliVersion()) {
+    process.stdout.write(`  ${label}: ✅ v${version}\n`);
+  } else {
+    process.stdout.write(
+      `  ${label}: ⚠️ v${version} → v${cliVersion()} available (run \`nerve agent update\`)\n`,
+    );
+  }
+}
+
+const injectCommand = defineCommand({
+  meta: {
+    name: "inject",
+    description: "Inject nerve skill into an AI agent",
+  },
+  args: {
+    target: {
+      type: "positional",
+      description: "Agent target: hermes | cursor",
+    },
+    profile: {
+      type: "string",
+      description: "Hermes profile name (default: main profile)",
+    },
+    path: {
+      type: "string",
+      description: "Project directory for Cursor rules (default: cwd); only used with cursor",
+    },
+  },
+  run({ args }) {
+    const target = args.target;
+    if (target === "hermes") {
+      if (args.path != null && args.path !== "") {
+        process.stderr.write("❌ --path applies only to the cursor target\n");
+        process.exit(1);
+      }
+      injectHermes(args.profile ?? null);
+      return;
+    }
+    if (target === "cursor") {
+      if (args.profile != null && args.profile !== "") {
+        process.stderr.write("❌ --profile applies only to the hermes target\n");
+        process.exit(1);
+      }
+      const pathArg = args.path != null && args.path !== "" ? args.path : null;
+      injectCursor(resolveCursorProjectDir(pathArg));
+      return;
+    }
+    process.stderr.write(`❌ Unknown agent target: ${target}\n`);
+    process.stderr.write("   Supported targets: hermes, cursor\n");
+    process.exit(1);
+  },
+});
+
+const updateCommand = defineCommand({
+  meta: {
+    name: "update",
+    description: "Update all injected nerve skills to current CLI version",
+  },
+  run() {
+    let updated = 0;
+
+    // Default profile
+    const defaultDir = getHermesSkillDir(null);
+    if (existsSync(defaultDir)) {
+      injectHermes(null);
+      updated++;
+    }
+
+    // Named profiles
+    const profilesDir = join(homedir(), ".hermes", "profiles");
+    if (existsSync(profilesDir)) {
+      const profiles = readdirSync(profilesDir, { withFileTypes: true })
+        .filter((d) => d.isDirectory())
+        .map((d) => d.name);
+
+      for (const profile of profiles) {
+        const dir = getHermesSkillDir(profile);
+        if (existsSync(dir)) {
+          injectHermes(profile);
+          updated++;
+        }
+      }
+    }
+
+    if (updated === 0) {
+      process.stdout.write("ℹ️ No injected skills found. Run `nerve agent inject hermes` first.\n");
+    }
+  },
+});
+
+const removeCommand = defineCommand({
+  meta: {
+    name: "remove",
+    description: "Remove injected nerve skill from an AI agent",
+  },
+  args: {
+    target: {
+      type: "positional",
+      description: "Agent target: hermes | cursor",
+    },
+    profile: {
+      type: "string",
+      description: "Hermes profile name (default: main profile)",
+    },
+    path: {
+      type: "string",
+      description: "Project directory for Cursor rules (default: cwd); only used with cursor",
+    },
+  },
+  run({ args }) {
+    const target = args.target;
+    if (target === "hermes") {
+      if (args.path != null && args.path !== "") {
+        process.stderr.write("❌ --path applies only to the cursor target\n");
+        process.exit(1);
+      }
+      removeHermes(args.profile ?? null);
+      return;
+    }
+    if (target === "cursor") {
+      if (args.profile != null && args.profile !== "") {
+        process.stderr.write("❌ --profile applies only to the hermes target\n");
+        process.exit(1);
+      }
+      const pathArg = args.path != null && args.path !== "" ? args.path : null;
+      removeCursor(resolveCursorProjectDir(pathArg));
+      return;
+    }
+    process.stderr.write(`❌ Unknown agent target: ${target}\n`);
+    process.stderr.write("   Supported targets: hermes, cursor\n");
+    process.exit(1);
+  },
+});
+
+const statusCommand = defineCommand({
+  meta: {
+    name: "status",
+    description: "Show injection status of nerve skills across agents",
+  },
+  run() {
+    printStatus();
+  },
+});
+
+export const agentCommand = defineCommand({
+  meta: {
+    name: "agent",
+    description: "Manage nerve skill injection for AI agents",
+  },
+  subCommands: {
+    inject: injectCommand,
+    update: updateCommand,
+    remove: removeCommand,
+    status: statusCommand,
+  },
+});

packages/core/README.md

@@ -4,11 +4,11 @@ Shared types and configuration parser for the [nerve](../../README.md) observati
 
 ## What's Inside
 
-- **Type definitions** — `Signal`, `SenseConfig`, `SenseInfo`, `SenseReflexConfig`, `ReflexConfig` (sense-only), `WorkflowConfig`, `NerveConfig`, and related types
+- **Type definitions** — `Signal`, `SenseConfig`, `SenseInfo`, `WorkflowConfig`, `NerveConfig`, and related types
 - **Config parser** — `parseNerveConfig(yaml)` validates and parses `nerve.yaml` into `NerveConfig` (rejects reflex entries that declare a `workflow` key; reflexes only schedule senses)
-- **Sense → workflow routing** — `parseSenseWorkflowDirective`, `routeSenseComputeOutput`, and types `ParsedSenseWorkflowDirective`, `SenseComputeRoute`
+- **Sense → workflow routing** — `parseWorkflowTrigger`, `routeSenseComputeOutput`, and types `WorkflowTrigger`, `RoutedSenseOutput`
 - **Daemon IPC protocol** — request/response types (`DaemonIpcRequest`, `DaemonIpcResponse`, …) and `parseDaemonIpcRequest` for newline-delimited JSON on the CLI ↔ daemon socket
-- **Workflow automaton types** — `START` / `END` sentinel constants, `WorkflowMessage`, `StartStep`, `RoleStep`, `ModeratorContext` (`start` + `steps`; empty `steps` on first moderator call), `Moderator` (single `context` argument), `WorkflowDefinition`, `Role`, `SenseResult`, plus `DEFAULT_ENGINE_MAX_ROUNDS`
+- **Workflow automaton types** — `START` / `END` sentinel constants, `WorkflowMessage`, `StartStep`, `RoleStep`, `ModeratorContext` (`start` + `steps`; empty `steps` on first moderator call), `Moderator` (single `context` argument), `WorkflowDefinition`, `Role`, `RoleResult`, plus `DEFAULT_ENGINE_MAX_ROUNDS`
 - **Result type** — `Result<T>` with `ok()` / `err()` helpers for explicit error handling (no thrown exceptions for parse paths)
 
 ## Usage
@@ -26,23 +26,31 @@ if (result.ok) {
 ### Sense return → signal vs workflow
 
 ```typescript
-import { parseSenseWorkflowDirective, routeSenseComputeOutput } from "@uncaged/nerve-core";
+import { parseWorkflowTrigger, routeSenseComputeOutput } from "@uncaged/nerve-core";
 
-const directive = parseSenseWorkflowDirective("my-workflow|8|Hello from sense");
+const directive = parseWorkflowTrigger({
+  name: "my-workflow",
+  maxRounds: 8,
+  prompt: "Hello from sense",
+  dryRun: false,
+});
 if (directive.ok) {
-  console.log(directive.value.workflowName, directive.value.maxRounds, directive.value.prompt);
+  console.log(directive.value.name, directive.value.maxRounds, directive.value.prompt);
 }
 
 const route = routeSenseComputeOutput({
-  metric: 42,
-  workflow: "my-workflow|8|Run now",
+  signal: { metric: 42 },
+  workflow: {
+    name: "my-workflow",
+    maxRounds: 8,
+    prompt: "Run now",
+    dryRun: false,
+  },
 });
-if (route.kind === "launch") {
-  // engine starts workflow; no Signal to the bus for this return
-  console.log(route.launch);
-} else {
-  // normal signal with payload
-  console.log(route.payload);
+if (route.ok && route.value.workflow !== null) {
+  console.log(route.value.workflow);
+} else if (route.ok) {
+  console.log(route.value.signal);
 }
 ```
 

packages/core/src/agent.ts

@@ -21,9 +21,3 @@ export class ExtractError extends Error {
     Object.setPrototypeOf(this, new.target.prototype);
   }
 }
-
-/**
- * Agent adapter ids referenced by tooling / docs (RFC-003).
- * Workflows import adapter packages directly; echo may be used in tests via a small factory.
- */
-export const KNOWN_AGENT_ADAPTER_IDS = ["echo", "cursor", "hermes", "codex"] as const;

packages/core/src/index.ts

@@ -13,7 +13,7 @@ export type {
 } from "./config.js";
 export type { Signal, SenseInfo } from "./sense.js";
 export type { SenseComputeFn, SenseModule } from "./sense.js";
-export { labelSenseTrigger, senseTriggerLabels } from "./sense.js";
+export { senseTriggerLabels } from "./sense.js";
 export type {
   WorkflowMessage,
   RoleResult,
@@ -29,7 +29,6 @@ export type {
   WorkflowDefinition,
 } from "./workflow.js";
 export { START, END, DEFAULT_ENGINE_MAX_ROUNDS } from "./workflow.js";
-export { parseDurationStringToMs } from "./util.js";
 export type { Schema, ExtractFn } from "./agent.js";
 export { ExtractError } from "./agent.js";
 export type { Result } from "./util.js";
@@ -46,7 +45,6 @@ export { parseNerveConfig } from "./config.js";
 export type { KnowledgeConfig } from "./config.js";
 export { parseKnowledgeYaml } from "./config.js";
 export { isPlainRecord } from "./util.js";
-export { KNOWN_AGENT_ADAPTER_IDS } from "./agent.js";
 
 export type { RoutedSenseOutput } from "./sense.js";
 export { parseWorkflowTrigger, routeSenseComputeOutput } from "./sense.js";

packages/daemon/src/agent-adapters/echo.ts

@@ -1,9 +0,0 @@
-import type { AgentConfig, AgentFn, ThreadContext } from "@uncaged/nerve-core";
-
-/**
- * Echo adapter (`type: "echo"`) — returns the assembled prompt unchanged.
- * Used for tests and dry-run wiring before real adapters exist.
- */
-export function createEchoAgent(_config: AgentConfig): AgentFn {
-  return async (_ctx: ThreadContext, prompt: string) => prompt;
-}

packages/daemon/src/index.ts

@@ -56,5 +56,3 @@ export type {
 
 export { createWorkflowManager } from "./workflow-manager.js";
 export type { WorkflowManager } from "./workflow-manager.js";
-
-export { createEchoAgent } from "./agent-adapters/echo.js";

packages/daemon/src/sense-worker.ts

@@ -25,7 +25,7 @@ import type { WorkerToParentMessage } from "./ipc.js";
 import { parseParentMessage } from "./ipc.js";
 import { executeCompute, loadSenseModule, openSenseDb } from "./sense-runtime.js";
 import type { SenseRuntime } from "./sense-runtime.js";
-import { ignoreSessionBroadcastSignals } from "./worker-fork-support.js";
+import { ignoreSessionBroadcastSignals } from "./worker-signals.js";
 
 // ---------------------------------------------------------------------------
 // IPC helpers

packages/daemon/src/worker-fork-support.ts

@@ -1,45 +0,0 @@
-import type { ChildProcess } from "node:child_process";
-
-const STDERR_TAIL_MAX_CHARS = 16_384;
-
-/**
- * Forked workers inherit the parent's process group. In foreground `nerve dev`,
- * terminal-driven SIGINT/SIGTERM is delivered to the whole group, so workers can exit
- * on the default handler before the kernel sends `{ type: "shutdown" }` over IPC.
- * Swallow these in worker processes so the parent coordinates shutdown (issue #55).
- * Only call when `process.send` is defined (fork IPC); standalone `node …-worker.js` keeps default Ctrl+C behaviour.
- */
-export function ignoreSessionBroadcastSignals(): void {
-  const swallow = (): void => {};
-  process.on("SIGINT", swallow);
-  process.on("SIGTERM", swallow);
-}
-
-export function teeCapturedStderr(child: ChildProcess, tail: { value: string }): void {
-  const stream = child.stderr;
-  if (stream === null || stream === undefined) return;
-  stream.setEncoding("utf8");
-  stream.on("data", (chunk: string | Buffer) => {
-    const text = typeof chunk === "string" ? chunk : chunk.toString("utf8");
-    process.stderr.write(text);
-    tail.value = (tail.value + text).slice(-STDERR_TAIL_MAX_CHARS);
-  });
-}
-
-export function formatChildExitSummary(code: number | null, signal: NodeJS.Signals | null): string {
-  const codeStr = code === null || code === undefined ? "null" : String(code);
-  if (signal) {
-    return `code=${codeStr} signal=${signal}`;
-  }
-  return `code=${codeStr}`;
-}
-
-export function formatCapturedStderrTail(tail: string, maxChars = 800): string {
-  const trimmed = tail.trim();
-  if (trimmed.length === 0) return "";
-  const normalized = trimmed.replace(/\r?\n/g, "\\n");
-  if (normalized.length <= maxChars) {
-    return ` worker_stderr=${normalized}`;
-  }
-  return ` worker_stderr=…${normalized.slice(-maxChars)}`;
-}

packages/daemon/src/worker-pool.ts

@@ -6,8 +6,11 @@ import { dirname, join } from "node:path";
 import { fileURLToPath } from "node:url";
 
 import type { ComputeMessage } from "./ipc.js";
-import { formatCapturedStderrTail, formatChildExitSummary } from "./worker-fork-support.js";
-import { createWorkerRuntime } from "./worker-runtime.js";
+import {
+  createWorkerRuntime,
+  formatCapturedStderrTail,
+  formatChildExitSummary,
+} from "./worker-runtime.js";
 
 export function resolveWorkerScript(): string {
   const __filename = fileURLToPath(import.meta.url);

packages/daemon/src/worker-runtime.ts

@@ -8,6 +8,24 @@ import { isPlainRecord } from "@uncaged/nerve-core";
 
 const STDERR_TAIL_MAX_CHARS = 2048;
 
+export function formatChildExitSummary(code: number | null, signal: NodeJS.Signals | null): string {
+  const codeStr = code === null || code === undefined ? "null" : String(code);
+  if (signal) {
+    return `code=${codeStr} signal=${signal}`;
+  }
+  return `code=${codeStr}`;
+}
+
+export function formatCapturedStderrTail(tail: string, maxChars = 800): string {
+  const trimmed = tail.trim();
+  if (trimmed.length === 0) return "";
+  const normalized = trimmed.replace(/\r?\n/g, "\\n");
+  if (normalized.length <= maxChars) {
+    return ` worker_stderr=${normalized}`;
+  }
+  return ` worker_stderr=…${normalized.slice(-maxChars)}`;
+}
+
 export type WorkerDrainOpts = {
   shutdownTimeoutMs: number | null;
 };

packages/daemon/src/worker-signals.ts

@@ -0,0 +1,17 @@
+/**
+ * Worker-process signal handling (fork IPC children only).
+ * Worker entrypoints import this module — not worker-runtime.ts (parent/kernel code).
+ */
+
+/**
+ * Forked workers inherit the parent's process group. In foreground `nerve dev`,
+ * terminal-driven SIGINT/SIGTERM is delivered to the whole group, so workers can exit
+ * on the default handler before the kernel sends `{ type: "shutdown" }` over IPC.
+ * Swallow these in worker processes so the parent coordinates shutdown (issue #55).
+ * Only call when `process.send` is defined (fork IPC); standalone `node …-worker.js` keeps default Ctrl+C behaviour.
+ */
+export function ignoreSessionBroadcastSignals(): void {
+  const swallow = (): void => {};
+  process.on("SIGINT", swallow);
+  process.on("SIGTERM", swallow);
+}

packages/daemon/src/workflow-manager.ts

@@ -11,8 +11,11 @@ import type { NerveConfig, WorkflowConfig, WorkflowStatus } from "@uncaged/nerve
 import type { LogStore } from "@uncaged/nerve-store";
 import type { KillThreadMessage, StartThreadMessage, ThreadEventMessage } from "./ipc.js";
 import { parseWorkerMessage } from "./ipc.js";
-import { formatCapturedStderrTail, formatChildExitSummary } from "./worker-fork-support.js";
-import { createWorkerRuntime } from "./worker-runtime.js";
+import {
+  createWorkerRuntime,
+  formatCapturedStderrTail,
+  formatChildExitSummary,
+} from "./worker-runtime.js";
 import {
   DEFAULT_MAX_QUEUE,
   WORKER_SHUTDOWN_TIMEOUT_MS,

packages/daemon/src/workflow-worker.ts

@@ -30,7 +30,7 @@ import type {
   WorkerToParentMessage,
 } from "./ipc.js";
 import { parseParentMessage } from "./ipc.js";
-import { ignoreSessionBroadcastSignals } from "./worker-fork-support.js";
+import { ignoreSessionBroadcastSignals } from "./worker-signals.js";
 
 // ---------------------------------------------------------------------------
 // IPC helpers

packages/workflow-meta/src/develop-sense/roles/planner.ts

@@ -17,6 +17,8 @@ Also look at existing senses in the \`senses/\` directory for patterns.
 
 Pick a good kebab-case name for this sense. Produce a PLAN (not code) in markdown:
 
+**Naming:** Sense names describe **what is observed or derived** (often noun-style compounds, e.g. \`linux-system-health\`, \`git-workspace-status\`). That differs from **workflow** names, which must be **verb-first** action phrases (\`extract-knowledge\`, \`develop-sense\`).
+
 ## Sense Design
 ### Name — kebab-case
 ### Fields — name, type (integer/real/text), description

packages/workflow-utils/src/__tests__/create-llm-adapter.test.ts

@@ -51,4 +51,28 @@ describe("createLlmAdapter", () => {
       { role: "user", content: "trigger text" },
     ]);
   });
+
+  it("throws on non-ok fetch response", async () => {
+    const fetchMock = vi.fn().mockResolvedValue({
+      ok: false,
+      status: 500,
+      text: async () => "Internal Server Error",
+    });
+    vi.stubGlobal("fetch", fetchMock);
+
+    const provider = { baseUrl: "https://api.example/v1", apiKey: "k", model: "m" };
+    const adapter = createLlmAdapter(provider);
+
+    await expect(adapter(makeCtx("t1", "hi"), "sys")).rejects.toThrow("llm:");
+  });
+
+  it("throws on fetch network failure", async () => {
+    const fetchMock = vi.fn().mockRejectedValue(new Error("ECONNREFUSED"));
+    vi.stubGlobal("fetch", fetchMock);
+
+    const provider = { baseUrl: "https://api.example/v1", apiKey: "k", model: "m" };
+    const adapter = createLlmAdapter(provider);
+
+    await expect(adapter(makeCtx("t1", "hi"), "sys")).rejects.toThrow();
+  });
 });

packages/workflow-utils/src/index.ts

@@ -26,13 +26,11 @@ export {
 } from "./role-decorators.js";
 export {
   nerveCommandEnv,
-  spawnSafe,
   type SpawnEnv,
   type SpawnError,
   type SpawnResult,
   type SpawnSafeOptions,
 } from "@uncaged/nerve-core";
 export type { LlmError, LlmProvider } from "./shared/llm-extract.js";
-export { isDryRun } from "./role-types.js";
 export type { LlmMessage, MetaExtractConfig } from "./role-types.js";
 export type { LlmChatError } from "./shared/llm-chat.js";

packages/workflow-utils/src/role-types.ts

@@ -1,16 +1,8 @@
-import type { SpawnEnv, StartStep, ThreadContext } from "@uncaged/nerve-core";
+import type { SpawnEnv, ThreadContext } from "@uncaged/nerve-core";
 import type { z } from "zod";
 
 import type { LlmProvider } from "./shared/llm-extract.js";
 
-/**
- * @deprecated `dryRun` has been removed from `StartStep.meta` (RFC-005).
- * Use adapter/role-level `dryRun` config instead.
- */
-export function isDryRun(_start: StartStep): boolean {
-  return false;
-}
-
 export type CliPromptFn = (ctx: ThreadContext) => Promise<string>;
 
 export type LlmMessage = { role: "system" | "user" | "assistant"; content: string };

packages/workflow-utils/src/shared/hermes-agent.ts

@@ -3,7 +3,7 @@ import type { HermesRoleDefaults, HermesRoleRequired } from "../role-types.js";
 export { hermesAgent } from "@uncaged/nerve-adapter-hermes";
 export type { HermesAgentOptions } from "@uncaged/nerve-adapter-hermes";
 
-// --- Hermes options resolution (absorbed from hermes-options.ts) ---
+// --- Hermes role defaults resolution ---
 
 const HERMES_DEFAULTS: HermesRoleDefaults = {
   model: null,