diff --git a/AGENTS.md b/AGENTS.md
index 44aa15aea5..22c1f47aa8 100644
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -85,14 +85,14 @@ pnpm exec vitest run --config vitest.e2e.config.ts packages/ui/stdio-agent/tests
 
 ## Secrets / .env
 
-Real-API tests and demos read `DEEPSEEK_API_KEY` and optional `DEEPSEEK_BASE_URL` from the environment or a gitignored root `.env` loaded by `process.loadEnvFile()`. cordis.yml uses `!!js` (never `!js`) for env vars. Never commit credentials. CI e2e self-skips without a key; [docs/testing.md](docs/testing.md) owns the with-key policy.
+Real-API tests and demos read `DEEPSEEK_API_KEY`, optional `DEEPSEEK_BASE_URL`, and root `.env`. cordis.yml allows `!!js` (never `!js`) only under plugin `config`; Loader metadata is static, so conditional composition uses overlays ([primer](docs/cordis-primer.md#loader-configuration)). Never commit credentials. CI e2e skips without a key; [testing.md](docs/testing.md) owns key policy.
 
 ## Conventions
 
 - Every npm package is `@deepseek-ai/dsh-<name>`; vendored packages keep upstream names and are `private: true`. `cordis` is a peerDependency (+ dev) of every harness package.
 - ESM everywhere (`"type": "module"`). Cross-package imports use package names, never relative paths; in-package relative imports use explicit `.ts` extensions. Dev/test/demo run unbuilt via tsx + the root tsconfig `paths` map; builds are for outside consumers only.
 - **Registrations are effects**: every contribution goes through `ctx.effect()` / `ctx.on()`; a registry's `register()` returns the disposer.
-- **Typed events use declaration merging**; extensible unions use merge-extensible maps. Event JSDoc needs `@mode` and payload `@param` tags; public service methods document parameters and non-void returns. Catalog gates enforce this.
+- **Typed events use declaration merging** and merge-extensible maps. Event JSDoc needs `@mode` and payload `@param`; scoped keys absent from payloads need `@dshScopeScan unsupported`. Public service methods document parameters and non-void returns.
 - **Switch on discriminant tags.** Closed unions end in `assertNever`; merge-extensible unions fall through a documented default.
 - **Waterfall listeners MUST call `next()`** to delegate; returning without it is the veto ([semantics](docs/cordis-primer.md#cordis-waterfall-semantics)).
 - **Model-visible ⟺ logged**: anything that reaches a model request must be reconstructable from the session log; a new model-visible input requires a session event.
diff --git a/docs/architecture.md b/docs/architecture.md
index b276124a8b..64a64d26f4 100644
--- a/docs/architecture.md
+++ b/docs/architecture.md
@@ -110,7 +110,7 @@ Every session event is turn-enclosed. Reloading a crashed session preserves the
 
 ### Agent Scope
 
-Every live agent owns a scoped `agent.ctx`. Its registrations shadow same-named globals, receive only that agent's dispatches, and unwind with the agent. `CreateAgentOptions.setup(agentCtx)` composes the scope before publication. See the [agent-scope RFC](rfc/implemented/architecture/2026-07-08-agent-scope-contexts.md); subagent composition controls are documented [separately](rfc/implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.md).
+Every live agent owns a scoped `agent.ctx`. Its registrations shadow same-named globals, receive only that agent's dispatches, and unwind with the agent. `CreateAgentOptions.setup(agentCtx)` composes the scope before publication. The [semantic-gates RFC](rfc/implemented/process/2026-07-14-typescript-program-backed-semantic-gates.md) defines typed resolvers that derive carrier checks from merged `Events` signatures and `scopeTarget`, eliminating the handwritten event table. See the [agent-scope RFC](rfc/implemented/architecture/2026-07-08-agent-scope-contexts.md); subagent composition controls are documented [separately](rfc/implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.md).
 
 ## State
 
diff --git a/docs/cookbook/adding-a-package.i18n.yaml b/docs/cookbook/adding-a-package.i18n.yaml
new file mode 100644
index 0000000000..27c31ba1ef
--- /dev/null
+++ b/docs/cookbook/adding-a-package.i18n.yaml
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write
+adding-a-package.md: 2930cee9ab64b382f6211335ae639bce45629d1d
+adding-a-package.zh.md: 10e906c320203c3658c103fc8936540f72697d65
diff --git a/docs/cookbook/adding-a-package.md b/docs/cookbook/adding-a-package.md
index db0684b762..2930cee9ab 100644
--- a/docs/cookbook/adding-a-package.md
+++ b/docs/cookbook/adding-a-package.md
@@ -1,6 +1,8 @@
 # Cookbook: adding a workspace package
 
-The file-by-file checklist for a new `@deepseek-ai/dsh-<name>` package. (Verified by the bash and adapter packages; if it drifts, fix it here.)
+English | [中文](adding-a-package.zh.md)
+
+The file-by-file checklist for a new `@deepseek-ai/dsh-<name>` package. This checklist is validated against the bash and adapter packages as templates; if it drifts from them, fix it here.
 
 ## 1. Create the package
 
diff --git a/docs/cookbook/adding-a-package.zh.md b/docs/cookbook/adding-a-package.zh.md
new file mode 100644
index 0000000000..10e906c320
--- /dev/null
+++ b/docs/cookbook/adding-a-package.zh.md
@@ -0,0 +1,83 @@
+# 实操手册：添加 workspace 包（package）
+
+[English](adding-a-package.md) | 中文
+
+为新建 `@deepseek-ai/dsh-<name>` 包提供的逐文件清单。本清单以 bash 和 adapter 这两个包为模板进行验证；如果清单与模板有出入，请在此修正。
+
+## 1. 创建包
+
+```
+packages/<group>/<pkg>/
+  package.json     # copy from packages/core/tools, adjust name/description/deps
+  tsconfig.json    # extends ../../../tsconfig.base.json, rootDir src,
+                   # outDir lib/types, references: ../../../vendor/cosmokit,
+                   # ../../../vendor/cordis (+ ../../../vendor/schemastery if
+                   # you use Config, + ../../<group>/<dep> for each dsh dep)
+  src/index.ts     # service default export or plugin (name/inject/apply/Config)
+  tests/<x>.spec.ts
+  README.md        # service API, events, extension points, design notes,
+                   # + gated Model Experience context blocks or short sentence
+                   # + the gated "Known Limitations and Deferred Work" section
+                   # (or a whitelist entry in scripts/verify-package-readme-limitations.ts)
+```
+
+当已有分组与包的角色匹配时，选择该分组（`core`、`llm`、`bash`、`compact`、`subagent`、`todo`、`session-persistence`、`ui`、`util` 或 `support`）。允许新建分组，但分组只是纯容器：没有 `package.json`，没有源文件，包仍然恰好位于其下一层。
+
+package.json 不变式（由 `pnpm run constraints` / `scripts/check-workspace-constraints.ts` 强制执行）：`private: true`，`version` 与根 `package.json` 一致，`type: module`，`main: "lib/index.js"`，`types: "lib/types/index.d.ts"`，`exports["."].types: "./lib/types/index.d.ts"`，`exports["."].default: "./lib/index.js"`，`cordis` 同时出现在 peerDependencies 和 devDependencies 中（相同范围）。每个 dsh 对等依赖（peer dependency）都要在 devDependencies 中镜像。`schemastery` 放在 `dependencies` 中（它是运行时校验器），与 agent-loop 保持一致。`files` 列表要精确：`lib/index.js`、`lib/types/**/*.d.ts`、`lib/types/**/*.d.ts.map` 和 `src`；不要发布 `lib/types` 下的 JS 或 JS-map 中间产物，也不要发布陈旧的根声明文件。带有 `bin` 的 CLI 应用包在 `files` 中将 `lib/bin.js` 紧跟在 `lib/index.js` 之后。
+
+包内的相对导入在源码中使用显式 `.ts` 后缀（例如 `export * from './types.ts'`）。编译器在输出的 JS 中将其重写为 `.js`，在声明文件中保留显式 `.ts` 后缀；标准的 NodeNext/Node16 TypeScript 消费方会将其解析到同目录的 `.d.ts` 文件。
+
+## 2. 在根配置中注册
+
+| 文件 | 变更 |
+|---|---|
+| `tsconfig.base.json` | 已有分组无需编辑；新分组需为 `@deepseek-ai/dsh-*` 通配符添加 `./packages/<group>/*/src` 候选路径 |
+| `tsconfig.json` | 在 `references` 中添加 `{ "path": "./packages/<group>/<pkg>" }` |
+| `tsconfig.build.json` | 在 `references` 中添加 `{ "path": "./packages/<group>/<pkg>" }` |
+| `knip.json` | 仅当包有非 `*.spec.ts` 入口时需要（如 `*.e2e.ts` → 添加 per-workspace override，参照 `packages/llm/llm-deepseek`） |
+
+以下内容由 glob 或包 manifest 发现机制自动覆盖，无需手动编辑：根 `package.json` workspaces、`scripts/publint-all.ts`、`tsdown.config.ts`、`vitest.config.ts`、`eslint.config.mjs`、`scripts/check-workspace-constraints.ts`。
+
+## 3. 确定包拓扑
+
+对于可替换的能力，将接口、实现、消费方拆分为独立的包（见 docs/architecture.md § "Capability seams"——bash 三组件是模板）。单一用途的插件保持为一个包。
+
+## 4. 编写包 README
+
+将包特有的服务 API、配置、事件、扩展点和设计说明放在前面。limitations 部分记录持久的消费方缺口和本包拥有的非显而易见的维护者约束；日常清理事项留在源码 TODO 或 RFC 中。间接的 Model Experience 语句可以点名暴露本包贡献的消费方，但不重述该消费方的实现。包 README 以如下规范序列结尾：
+
+````markdown
+## Model Experience
+
+### Request surface and condition
+
+**What the model sees**: An exact data-dependent shape, an anchored generated-catalog link, or an introduction to the verbatim literal below.
+
+**Token effect**: Fixed, conditional, retained, replaced, capped, or zero-direct token effect.
+
+#### Verbatim text for this context surface, when needed
+
+```markdown
+Stable system-prompt prose of any length, or another long non-generated literal, copied exactly from source.
+```
+
+## Known Limitations and Deferred Work
+
+- **Consumer-visible gap** — exact boundary, consequence, or maintainer constraint.
+````
+
+根据实现填写 Model Experience。每个直接、条件、上限、生命周期或辅助模型的 surface 使用一个 H3，包含上述两个字段。引用包拥有的稳定文本：系统提示词放在带标题的 H4 加 `markdown` 围栏中，其他短文本以命名占位符内联，其他长文本使用相同的嵌套形式。仅概述数据依赖或提供方拥有的文本。tool-schema surface 链接到生成的[工具目录](../tool-catalog.md)中对应的锚定章节，仅说明该处缺失的差异。当作用域可以隐藏 prompt 或 schema 其中之一而不影响另一个时，将二者分开。[行文标准](../../.agents/skills/dsh-prose-standard/SKILL.md)约束完整性与归属；验证器强制执行机械形状。
+
+没有上下文效果或仅有消费方拥有路径的包使用 [`SENTENCE_MODEL_EXPERIENCE`](../../scripts/verify-package-readme-model-experience.ts) 中经过审计的 `None, as ` 或 `Indirectly, through ` 语句；与模型无关的通用包可以改为加入 `NO_MODEL_EXPERIENCE_SECTION`。两种情况都不要展开为对另一个包工作的描述。limitations [allowlist](../../scripts/verify-package-readme-limitations.ts) 独立管理。[Model Experience RFC](../rfc/implemented/process/2026-07-12-package-model-experience-contract.md) 记录了设计动机。
+
+## 5. 验证
+
+```sh
+pnpm install        # registers the workspace
+pnpm run doc-sync
+pnpm run constraints && pnpm run typecheck && pnpm run lint
+pnpm run test:coverage  # 100% per-file over src (types.ts exempt)
+pnpm run build && pnpm run hygiene
+```
+
+测试要求：每个注册表/注册操作都需要一个 HMR（热模块替换）安全测试（从子 fiber 注册，dispose（资源释放）它，断言清理完成）。鼓励编写充分的测试——见 [docs/testing.md](../testing.md)。
diff --git a/docs/cookbook/adding-a-tool.i18n.yaml b/docs/cookbook/adding-a-tool.i18n.yaml
new file mode 100644
index 0000000000..7ff1ffff7a
--- /dev/null
+++ b/docs/cookbook/adding-a-tool.i18n.yaml
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write
+adding-a-tool.md: 4920c98894326fb8eab3b3d5df298baf1da33c1d
+adding-a-tool.zh.md: 3caf1e62f15f2f15103836b4d3f22be20ba02385
diff --git a/docs/cookbook/adding-a-tool.md b/docs/cookbook/adding-a-tool.md
index 86803fdebb..4920c98894 100644
--- a/docs/cookbook/adding-a-tool.md
+++ b/docs/cookbook/adding-a-tool.md
@@ -1,5 +1,7 @@
 # Cookbook: adding a tool
 
+English | [中文](adding-a-tool.zh.md)
+
 How to give the model a new capability. Reference implementations: `examples/echo-agent/src/echo-tool.ts` (minimal) and `packages/bash/tool-bash` (production-grade, three-package seam).
 
 ## The minimal shape
@@ -49,7 +51,7 @@ Follow tool-bash's background pattern: a `run_in_background` flag returns a task
 
 ## Execution policy and observation
 
-Prefer not to build deployment policy into the tool. Use `tools/pre-execute` for extensible allow/deny/ask policy (the [permission-gate example](./extension-cookbook.md#a-hook-plugin-permission-gate)), `ctx.tools.guard()` for a final monotonic deny that later listeners cannot undo, `tools/execute` to wrap core dispatch with a deadline/retry/metrics scope, `tools/post-execute` to transform or attach model-facing context, and `tools/result` to observe the immutable normalized outcome without changing it. A sandboxing implementation can also sit behind the tool's executor capability seam; the exact contracts are in the [`dsh-tools` README](../../packages/core/tools/README.md#extension-points).
+Prefer not to build deployment policy into the tool. Use `tools/pre-execute` for extensible allow/deny/ask policy (the [permission-gate example](./extension-cookbook.md#a-hook-plugin-permission-gate-example)), `ctx.tools.guard()` for a final monotonic deny that later listeners cannot undo, `tools/execute` to wrap core dispatch with a deadline/retry/metrics scope, `tools/post-execute` to transform or attach model-facing context, and `tools/result` to observe the immutable normalized outcome without changing it. A sandboxing implementation can also sit behind the tool's executor capability seam; the exact contracts are in the [`dsh-tools` README](../../packages/core/tools/README.md#extension-points).
 
 ## Code Mode reaches your tool for free
 
diff --git a/docs/cookbook/adding-a-tool.zh.md b/docs/cookbook/adding-a-tool.zh.md
new file mode 100644
index 0000000000..3caf1e62f1
--- /dev/null
+++ b/docs/cookbook/adding-a-tool.zh.md
@@ -0,0 +1,85 @@
+# 实操手册：添加工具
+
+[English](adding-a-tool.md) | 中文
+
+如何为模型赋予一项新能力。参考实现：`examples/echo-agent/src/echo-tool.ts`（最小化）和 `packages/bash/tool-bash`（生产级，由三个包（package）构成的 seam）。
+
+## 最小形态
+
+```ts
+import { readFile } from 'node:fs/promises'
+import type { Context } from 'cordis'
+import { defineTool } from '@deepseek-ai/dsh-tools'
+
+export const name = 'my-tool'
+export const inject = ['tools']
+
+export function apply(ctx: Context) {
+  ctx.tools.register(defineTool({
+    name: 'read_file',
+    description: 'Read a file from disk.',          // what the model sees
+    parameters: {
+      path: { type: 'string', required: true, description: 'Absolute path' },
+      limit: { type: 'number' },                     // optional by default
+    },
+    async execute(args, exec) {
+      // args is TYPED from the schema: { path: string; limit?: number }
+      // exec carries immutable identity + token; signal is the operational field
+      return [{ type: 'text', text: await readFile(args.path, 'utf8') }]
+    },
+  }))
+}
+```
+
+注册基于副作用：dispose（资源释放）插件 fiber 即注销该工具（请编写 HMR（热模块替换）测试）。schema 会自动流入系统提示词的组装过程。
+
+## execute() 契约的规则
+
+- **参数已为你校验。** `defineTool` 在 `execute` 运行前，会根据 `SchemaSpec` 校验模型生成的 `arguments`（类型、必填键、枚举成员、嵌套对象/数组——见[运行时参数校验](../rfc/implemented/architecture/2026-06-11-runtime-arg-validation.md)），因此 `execute` 内部的 args 已匹配 `InferArgs`。你仍需手动检查 DSL 无法表达的值约束（非空字符串、正数、跨字段规则），对这些情况抛出描述性 Error。直接注册的原始 JSON-Schema 工具（MCP）不由 harness 校验，它们自行校验输入。
+- **注册借用你的只读定义。** 类型化的同进程贡献不是序列化边界；注册后不要修改其 schema 或替换回调。`schemas()` 只物化显式的模型可见投影。如需热替换工具，请 dispose 其所属副作用并注册替代品；回调闭包内的可变状态仍是普通的插件状态。
+- **执行身份受保护。** 注册表在一次递归遍历中将 `arguments` 物化为分离的无损 JSON，在策略开始前冻结该值，并分配一个不透明的 `exec.token`；`callId`、`name`、`arguments`、`agent`、`token` 以及可选的外层传输 `parent` token 在整个分发过程中保持不可变。`parent` 仅用于身份标识，不暴露活跃的外层执行。请将 `args` 视为只读输入。around-dispatch 包装器只能添加、替换或移除 `exec.signal`，以施加取消或截止时间。
+- **抛出异常或返回非 JSON 数据意味着 `isError`。** 注册表捕获异常，并在观察者运行前物化最终结果。格式错误或非 JSON 的结果变为 `{ isError: true }`，防止出现无法记录的活跃成功。基础设施故障请抛异常；当模型需要解读领域失败时，请在结果文本中报告。
+- **遵守 `exec.signal`。** 信号触发时取消进行中的工作。
+- **使用 `meta` 附加持久化的卡片数据（可选）。** `execute` 可以返回 `{ content, meta }` 而非裸的 `ContentBlock[]`。`meta` 是 JSON 可序列化的载荷，核心将其视为不透明数据，持久化在 `tool/result` 事件上并回传给你的 `presentResult`（这样需要 `args` 之外信息的卡片——如 `write`/`edit` 的已应用 hunk diff——在会话回放中依然存活）。仅在此处放 UI 数据，绝不放入模型可见的 `content`。
+- **使用 `exec.agent` 发送异步通知。** `agent.inject(content, {source: {kind: 'plugin', plugin: '<name>'}})` 追加持久化上下文，下一次模型请求会看到它——这不是唤醒（空闲的 agent（智能体）保持空闲）。请防范已 dispose 的 agent（try/catch）。
+
+## 长时间运行的工作
+
+遵循 tool-bash 的后台模式：`run_in_background` 标志立即返回一个 task id；配套工具增量轮询和终止；完成通知通过 `agent.inject()` 到达。限定缓冲区大小，将完整输出溢写到磁盘，避免静默丢失。
+
+> TODO: 目前每个工具都手动重新实现这套后台模式。未来需要一个通用的长时间运行工具层，统一处理 task id、增量轮询、终止和完成通知。
+
+## 执行策略与观测
+
+尽量不要把部署策略内建到工具中。使用 `tools/pre-execute` 实现可扩展的允许/拒绝/询问策略（见[权限门禁示例](./extension-cookbook.md#a-hook-plugin-permission-gate-example)）；使用 `ctx.tools.guard()` 设置最终的单调拒绝（后续监听器无法撤销）；使用 `tools/execute` 为核心分发包装截止时间/重试/指标作用域；使用 `tools/post-execute` 转换或附加模型可见的上下文；使用 `tools/result` 观测不可变的归一化结果而不改变它。沙箱实现也可以位于工具执行器的能力 seam 之后；确切契约见 [`dsh-tools` README](../../packages/core/tools/README.md#extension-points)。
+
+## Code Mode 自动触达你的工具
+
+在 [Code Mode](../../packages/core/tools/README.md) 中，每个可见的已注册工具都可通过 `await tools.<name>(args)` 调用，无需额外集成。SDK 从同一份 JSON Schema 派生参数，调用重新进入正常的执行流水线。请将描述写成面向模型的 API 文档；非文本结果块在程序中变为占位符。
+
+## 工具在编辑器中的渲染方式（ACP 展示）
+
+工具的 `execute` 返回模型可见的内容；其**编辑器卡片**是一个独立的、可选的关注点，通过 `defineTool` 选项中的两个纯展示方法声明。请与 `execute` 同步设计，而非事后补充——编辑器（如 Zed，通过 ACP（Agent Client Protocol）桥接）会展示该卡片，没有展示方法的工具回退为一个朴素的通用卡片（标题 = 工具名，原始 args 作为输入）。
+
+两个方法都返回一个 **`card` 标签的渲染意图**——选择与你的工具行为匹配的卡片类型：
+
+- `presentCall(args)` → 一个 `ToolCallView`（PENDING 卡片）：
+  - `{ card: 'generic', title, kind?, rawInput?, content?, locations? }`——默认。设置 `kind` 获取图标（`read`/`search`/…）；设置 `locations: [{ path, line? }]` 标注工具涉及的文件，使有能力的编辑器跟随/跳转。
+  - `{ card: 'terminal', title, description?, cwd? }`——你的调用本身就是 shell 命令。`title` 是命令，`description` 渲染在终端卡片上方。（tool-bash。）
+  - `{ card: 'diff', title, diffs, locations? }`——你的调用创建或修改文件。`diffs: [{ path, oldText, newText }]`（新文件时 `oldText: null`）渲染为内联 diff 卡片。（tool-fs `write`/`edit`。）
+- `presentResult(args, { content, isError, meta? })` 返回完成后的卡片：
+  - `generic` 提供可选的标题和内容。
+  - `terminal` 提供原始输出和可选的退出元数据；桥接层渲染能力特定或围栏回退视图。
+  - `diff` 提供已应用的 hunk，通常由持久化的 `result.meta` 携带，使回放能重现它们。变更类工具保留 diff 结果，因为 ACP 更新会替换 pending 卡片的内容。
+
+硬性规则（违反会出问题）：
+
+- **纯函数。** 这些方法在实时流式输出和会话日志回放时都会运行，因此必须是 `args`（加 result）的纯函数——不做 I/O、不读会话状态、不用时钟/随机数。diff 从 args 派生（`write` 使用 `oldText: null`，因为调用时的展示器没有文件先前内容）；**桥接层**（而非工具）填充会话 cwd 并相对化展示路径标题。如果你发现自己想在 `presentCall` 内获取文件旧内容或工作目录，请停下——那属于桥接层或未来的 result-event 形态，不属于展示器。
+- **UI 格式不进入模型结果。** 围栏 ` ```console ` 块、diff、相对化路径——这些都不得出现在 `execute` 返回给模型的内容中；它们只存在于展示层。（`terminal` 结果视图携带原始 `output`；桥接层添加围栏。）
+- **`defineTool` 对展示路径做软校验。** 格式错误或旧版日志中的 arg 形态会使包装器返回 `undefined`（通用回退）而非抛异常——展示绝不能导致回放崩溃。
+
+中性词汇定义在 `dsh-tools` 中（绝不在工具中导入 ACP 类型）；ACP 桥接层将每个 `card` 映射到协议格式（wire format）。设计与原因见[渲染意图联合体 RFC](../rfc/implemented/architecture/2026-07-02-tool-render-intent-union.md)；`dsh-tool-fs`（generic/diff）和 `dsh-tool-bash`（terminal）是参考实现。
+
+## 每个工具必须的测试
+
+覆盖参数拒绝、每种结果形态和 HMR dispose。对于有副作用的工具，使用脚本化的 `MockAdapter` 驱动真实工具通过 agent loop（智能体循环），并断言其 `tool/call` 和 `tool/result` 会话事件。对于编辑器卡片，断言 `presentCall` 和 `presentResult` 的精确视图，并通过真实桥接层添加一个 [ACP 快照](../rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md)；终端卡片的场景设置 `terminalOutput: true` 以覆盖 capable-client 路径。
diff --git a/docs/cookbook/adding-a-vendored-package.i18n.yaml b/docs/cookbook/adding-a-vendored-package.i18n.yaml
new file mode 100644
index 0000000000..0a359ead84
--- /dev/null
+++ b/docs/cookbook/adding-a-vendored-package.i18n.yaml
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write
+adding-a-vendored-package.md: d7b5b93b59fb39d8369be6eb42fb0a8b977c68b4
+adding-a-vendored-package.zh.md: 86b1e6c959180ba15b6fcb56b6dfe5a3be791b47
diff --git a/docs/cookbook/adding-a-vendored-package.md b/docs/cookbook/adding-a-vendored-package.md
index 59df2f617b..d7b5b93b59 100644
--- a/docs/cookbook/adding-a-vendored-package.md
+++ b/docs/cookbook/adding-a-vendored-package.md
@@ -1,5 +1,7 @@
 # Cookbook: adding a vendored package
 
+English | [中文](adding-a-vendored-package.zh.md)
+
 When the harness needs another upstream Cordis package (e.g. `@cordisjs/plugin-http`), it is **vendored** as pinned source under `vendor/`, not added as an npm dependency — see [the vendoring decision](../rfc/implemented/process/2026-06-11-vendor-cordis-as-source.md) for why. [vendor/README.md](../../vendor/README.md) covers *updating* an already-vendored package; this guide is the file-by-file checklist for adding a **new** one. (Verified against the existing vendored set; if it drifts, fix it here.)
 
 ## 1. Copy the source in
diff --git a/docs/cookbook/adding-a-vendored-package.zh.md b/docs/cookbook/adding-a-vendored-package.zh.md
new file mode 100644
index 0000000000..86b1e6c959
--- /dev/null
+++ b/docs/cookbook/adding-a-vendored-package.zh.md
@@ -0,0 +1,60 @@
+# 实操手册：添加一个 vendored 包（package）
+
+[English](adding-a-vendored-package.md) | 中文
+
+当 harness 需要引入另一个上游 Cordis 包（如 `@cordisjs/plugin-http`）时，应将其作为固定版本的源码 **vendor** 到 `vendor/` 下，而非作为 npm 依赖添加——原因见[vendoring 决策](../rfc/implemented/process/2026-06-11-vendor-cordis-as-source.md)。[vendor/README.md](../../vendor/README.md) 介绍如何*更新*已有的 vendored 包；本指南是添加**新** vendored 包的逐文件清单。（已对照现有 vendored 集合验证；如有偏差，请在此修正。）
+
+## 1. 复制源码
+
+```
+vendor/<dir>/
+  package.json     # from upstream; set "private": true, keep name/exports/type
+  tsconfig.json    # extends ../../tsconfig.base.json (see shape below)
+  src/             # the upstream src/ verbatim
+  README.md LICENSE # if upstream ships them
+```
+
+`tsconfig.json` 与其他 vendored 包保持一致：`rootDir: src`、`outDir: lib/types`、上游代码所需的严格性放宽项，以及对所导入的每个其他 vendored 包的 `references` 条目：
+
+```jsonc
+{
+  "extends": "../../tsconfig.base.json",
+  "compilerOptions": {
+    "rootDir": "src", "outDir": "lib/types",
+    "noUncheckedIndexedAccess": false, "exactOptionalPropertyTypes": false,
+    "noImplicitOverride": false, "noUnusedLocals": false, "noUnusedParameters": false
+  },
+  "include": ["src"],
+  "references": [{ "path": "../cordis" }, { "path": "../cosmokit" }]
+}
+```
+
+`package.json` 的不变式：`"private": true`（vendored 包永不发布）；保留上游的 `name`/`version`/`exports`/`type`；声明元数据指向 `lib/types`；发布 `.d.ts` 与 `.d.ts.map` 声明输出；在 `peerDependencies` 中列出其 Cordis 依赖（与上游 manifest（元数据清单）一致）。传递性上游依赖本身也必须被 vendor 或已存在于仓库中——vendor 一个包往往意味着 vendor 其整条依赖树（如 `@cordisjs/plugin-http` 会拉入 `@cordisjs/fetch-file`）。
+
+vendored TypeScript 源码中的本地相对导入/导出在复制后使用显式 `.ts` 后缀。这是仓库本地的构建形态与上游的差异：`rewriteRelativeImportExtensions` 输出 `.js` 运行时导入，而声明文件保留显式 `.ts` 后缀，使 NodeNext/Node16 的 TypeScript 消费方能够解析。
+
+## 2. 在根配置中注册
+
+| 文件 | 修改内容 |
+|---|---|
+| `tsconfig.base.json` | 在 `paths` 中添加 `"<npm-name>": ["./vendor/<dir>/src"]` |
+| `tsconfig.json` | 在 `references` 中添加 `{ "path": "./vendor/<dir>" }` |
+| `tsconfig.build.json` | 在 `references` 中添加 `{ "path": "./vendor/<dir>" }`（置于 `packages/*` 条目之前） |
+| `vendor/README.md` | 添加一行 manifest 表格行（dir、npm name、version、upstream repo、commit SHA）并记录所有本地修改 |
+| `scripts/publint-all.ts` | 仅当该 vendored 包本身从此仓库发布时才需要（vendored 依赖通常不发布——跳过） |
+
+以下由 glob 自动覆盖，无需手动编辑：根 `package.json` 的 workspaces（`vendor/*`）、`tsdown.config.ts`、`vitest.config.ts`、`eslint.config.mjs`。只有当构建形态偏离根默认值时（双 ESM/CJS 或多入口——参见 `vendor/schemastery` 和 `vendor/logger-console`），才需要单独的 `vendor/<dir>/tsdown.config.ts`；其入口应读取 `lib/types` 下输出的 JS。
+
+## 3. 注意 manifest 守卫
+
+`scripts/check-vendor-manifest.sh`（pre-commit 钩子）会在 `vendor/*/src` 下有暂存改动但 `vendor/README.md` 未一起暂存时失败。请将 manifest 更新与源码一起暂存，以通过提交检查。
+
+## 4. 验证
+
+```sh
+pnpm install        # registers the workspace
+pnpm run typecheck
+pnpm run build && pnpm run test && pnpm run constraints
+```
+
+源码 `paths` 映射由构建配置和根类型检查配置共享。重要的隔离边界是 project-reference 图：vendored 源码必须通过其自身的 `vendor/<dir>/tsconfig.json` 被引用，而非被拉入根目录的严格程序中。
diff --git a/docs/cookbook/adding-an-llm-adapter.i18n.yaml b/docs/cookbook/adding-an-llm-adapter.i18n.yaml
new file mode 100644
index 0000000000..497ae08c32
--- /dev/null
+++ b/docs/cookbook/adding-an-llm-adapter.i18n.yaml
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write
+adding-an-llm-adapter.md: f20442b8c2ce823452a3ea13409f202185d12d04
+adding-an-llm-adapter.zh.md: 2864dd1e18742c7449e24f22504a5a38976ab450
diff --git a/docs/cookbook/adding-an-llm-adapter.md b/docs/cookbook/adding-an-llm-adapter.md
index 866f401d42..f20442b8c2 100644
--- a/docs/cookbook/adding-an-llm-adapter.md
+++ b/docs/cookbook/adding-an-llm-adapter.md
@@ -1,5 +1,7 @@
 # Cookbook: adding an LLM adapter
 
+English | [中文](adding-an-llm-adapter.zh.md)
+
 How to connect a new model provider. Reference implementations: `packages/llm/llm-deepseek` (hand-rolled HTTP/SSE) and `packages/llm/llm-pi-ai` (wrapping an LLM library). Read the `StreamChunk` doc in `packages/llm/llm/src/types.ts` first — it records the protocol conventions both adapters were verified against.
 
 ## The shape
diff --git a/docs/cookbook/adding-an-llm-adapter.zh.md b/docs/cookbook/adding-an-llm-adapter.zh.md
new file mode 100644
index 0000000000..2864dd1e18
--- /dev/null
+++ b/docs/cookbook/adding-an-llm-adapter.zh.md
@@ -0,0 +1,46 @@
+# 实操手册：添加 LLM 适配器
+
+[English](adding-an-llm-adapter.md) | 中文
+
+如何接入一个新的模型提供方。参考实现：`packages/llm/llm-deepseek`（手写 HTTP/SSE）与 `packages/llm/llm-pi-ai`（封装 LLM 库）。请先阅读 `packages/llm/llm/src/types.ts` 中的 `StreamChunk` 文档——它记录了两个适配器都经过验证的协议约定。
+
+## 基本形态
+
+```ts ignore-check
+class MyAdapter extends LlmAdapter {
+  async * stream(options: GenerateOptions): AsyncIterable<StreamChunk> { … }
+}
+
+export const name = 'llm-myprovider'
+export const inject = ['llm']
+export const Config: z<Config> = z.object({ apiKey: z.string(), … })
+
+export function apply(ctx: Context, config: Config) {
+  ctx.llm.registerAdapter(['my-provider'], new MyAdapter(…))
+}
+```
+
+注册基于副作用（HMR 安全）；每个提供方路由仅对应一个适配器，重复注册会抛出异常，多路由注册要么全部成功，要么全部失败。`options.provider` 用于选择适配器，`options.model` 是提供方模型 ID，因此动态模型目录适配器无需重新配置生命周期即可提供新模型。密钥采用 Cordis 原生方式管理：schemastery Config 带环境变量回退，通过 cordis.yml 的 `!!js process.env.MY_KEY` 注入。代码中禁止临时读取密钥文件。
+
+## 协议义务（两个实现共同验证的契约）
+
+- 在 `finish` **之前**发出 `usage`；`finish` 之后**不再发出任何内容**。稳健做法：缓冲 finish/usage 直到提供方的流结束标记，再统一 flush（可处理提供方在末尾发送仅含 usage 的分片的情况）。
+- 工具调用的 `arguments` 全程为原始 JSON 字符串；流式片段以 `argumentsDelta` 发送。如果你的提供方返回已解析的对象，请在 `block-end` 时重新 stringify。
+- 按首次出现的流顺序分配块 `index`；同一个块的每次 delta 复用该 index。
+- 错误有且仅有两条合法路径：从 `stream()` **抛出**（传输与协议故障——使用带稳定 code 的 `LlmError`），或以 `finish {kind: 'error' | 'aborted'}` 结束流（提供方带内故障）。消费方两者都处理；按故障类别选择路径并加以文档化。
+- 遵守 `options.signal`（将其传递给 fetch 或你的 SDK）。
+- 如果 `GenerateOptions` 中某个字段你的提供方无法支持（例如提供方不支持 stop sequences 时收到 `stop` 列表）：抛出 `LlmError(..., 'UNSUPPORTED')`，而非静默丢弃。
+- 如果提供方在后续调用中需要响应 ID、签名或其他原生元数据，请将其最小无损 JSON 投影作为 `finish.replayState` 发出。重建历史时验证该状态。只有历史提供方路由和目标提供方路由当前由完全相同的适配器实例拥有时，`LlmService` 才会传递该状态；由适配器决定同模型、跨模型或跨提供方恢复是否合法。状态缺失时，切勿仅根据提供方/模型名称推断原生回放。
+
+提供方特有的请求旋钮（thinking 模式、effort 级别）放在**适配器**的 Config 中，而非 `GenerateOptions` 中——核心词汇保持提供方无关。
+
+## 经验证有效的结构
+
+将适配器拆分为可测试的阶段（llm-deepseek 的布局）：协议格式（wire format）类型（`types.ts`，豁免覆盖率）→ 请求序列化器 → SSE/传输解析器 → 分片转换状态机 → 一个将它们串联的薄适配器类。每个阶段配备独立的单元测试套件。
+
+## 测试
+
+- **单元测试：mock 提供方，而非 harness。** 用脚本化的 `node:http` 服务器模拟提供方的协议格式，覆盖正常路径、所有错误状态码、畸形载荷、连接提前关闭和中止——无需网络，且能满足 100% 逐文件覆盖率门禁。对基于 SDK 的适配器同样适用（将 SDK 的 baseURL 指向 mock 服务器）。
+- **恶意分帧测试。** 在任意字节位置（包括 UTF-8 字符中间）切割流载荷——真实网络环境正是如此。
+- **E2E：`tests/*.e2e.ts`**，通过 `pnpm run test:e2e` 运行，以 `describe.skipIf(!process.env.MY_KEY)` 守卫，确保无密钥的 CI 保持绿色。覆盖具有代表性的模型/提供方/API 系列以及你映射的每种提供方模式、一次包含后续轮次（历史中带工具结果）的工具调用往返，以及仅做宽松断言（子串/结构匹配、有界的 maxTokens——真实模型是非确定性的）。
+- 在 `knip.json` 中注册 e2e 文件模式（per-workspace `entry` 覆盖），否则 knip 会将其标记为未使用。
diff --git a/docs/cookbook/extension-cookbook.i18n.yaml b/docs/cookbook/extension-cookbook.i18n.yaml
new file mode 100644
index 0000000000..ef1d8d606f
--- /dev/null
+++ b/docs/cookbook/extension-cookbook.i18n.yaml
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write
+extension-cookbook.md: 40ee22b352c884d7f295c87726c54ab8e166c844
+extension-cookbook.zh.md: 4e5bc68c973649574bcb2404bea00096eb9ca41f
diff --git a/docs/cookbook/extension-cookbook.md b/docs/cookbook/extension-cookbook.md
index a2aa255ccf..40ee22b352 100644
--- a/docs/cookbook/extension-cookbook.md
+++ b/docs/cookbook/extension-cookbook.md
@@ -1,14 +1,18 @@
 # Cookbook: extension plugin shapes
 
+English | [中文](extension-cookbook.zh.md)
+
+> FIXME: This important guide has not received sufficient human design review; complete that review before the first release.
+
 The three plugin shapes you write against the harness extension surface, as illustrative snippets (elided imports and helper stubs — not copy-paste-complete). For the full step-by-step guides see [adding a package](./adding-a-package.md), [adding a tool](./adding-a-tool.md), and [adding an LLM adapter](./adding-an-llm-adapter.md); for the seams these hook into see [docs/architecture.md](../architecture.md).
 
 ## A tool plugin
 
 A tool registers on `ctx.tools`. The annotated `defineTool` example (typed `execute` args, result shaping, the `run_in_background` pattern) lives in [adding-a-tool.md](./adding-a-tool.md) — that guide is the source of truth for the tool shape. Raw JSON-Schema `ToolDefinition`s are also accepted by `ctx.tools.register()` directly (that is how MCP-sourced tools arrive); `defineTool` is the typed sugar for first-party tools.
 
-## A hook plugin (permission gate)
+## A hook plugin (permission-gate example)
 
-A hook returns a typed decision from the `tools/pre-execute` gate to allow or deny a call — the seam where sandbox, permission, and plan-mode plugins live. (A "native hook" is just this: an ordinary cordis plugin on the interception seams, returning typed decisions — no external protocol needed.)
+This permission gate is one example of a hook plugin. It returns a typed decision from the `tools/pre-execute` gate to allow or deny a call; sandbox, permission, and plan-mode plugins can use this seam. Hook plugins can intercept other seams and are not inherently permission gates. A "native hook" is an ordinary Cordis plugin on an interception seam; it needs no external protocol.
 
 ```ts
 import type { Context } from 'cordis'
diff --git a/docs/cookbook/extension-cookbook.zh.md b/docs/cookbook/extension-cookbook.zh.md
new file mode 100644
index 0000000000..4e5bc68c97
--- /dev/null
+++ b/docs/cookbook/extension-cookbook.zh.md
@@ -0,0 +1,125 @@
+# 实操手册：扩展插件形态
+
+[English](extension-cookbook.md) | 中文
+
+> FIXME：这篇重要指南尚未经过充分的人工设计审查；请在首次发布前完成审查。
+
+针对 harness 扩展表面编写的三种插件形态，以示意性代码片段呈现（省略了 import 和辅助桩——不可直接复制运行）。完整的分步指南见[添加包（package）](./adding-a-package.md)、[添加工具](./adding-a-tool.md)和[添加 LLM（大语言模型）适配器](./adding-an-llm-adapter.md)；这些插件所挂接的 seam 见 [docs/architecture.md](../architecture.md)。
+
+## 工具插件
+
+工具在 `ctx.tools` 上注册。带注解的 `defineTool` 示例（类型化的 `execute` 参数、结果塑形、`run_in_background` 模式）见 [adding-a-tool.md](./adding-a-tool.md)——该指南是工具形态的真源。`ctx.tools.register()` 也直接接受原始 JSON-Schema `ToolDefinition`（MCP 来源的工具就是这样到达的）；`defineTool` 是为第一方工具提供的类型化语法糖。
+
+## 钩子插件（以权限门禁为例）
+
+这个权限门禁是钩子插件的一个示例。它从 `tools/pre-execute` 门禁返回一个类型化的决策，用于允许或拒绝一次调用；沙箱、权限和 plan-mode 插件都可以使用该 seam。钩子插件也可以拦截其他 seam，本身并不等同于权限门禁。「原生钩子」是在拦截 seam 上运行的普通 Cordis 插件，不需要外部协议。
+
+```ts
+import type { Context } from 'cordis'
+import type { PreToolDecision, ToolExecution } from '@deepseek-ai/dsh-tools'
+
+declare function isAllowed(exec: ToolExecution): Promise<boolean>
+
+export const name = 'permission-gate'
+
+export function apply(ctx: Context) {
+  ctx.on('tools/pre-execute', async (exec, next): Promise<PreToolDecision> => {
+    if (!(await isAllowed(exec))) {
+      return { kind: 'deny', reason: 'Denied by policy.' }
+    }
+    return next()
+  })
+}
+```
+
+这个 waterfall（瀑布式事件）是可重排的策略层。当不变式需要单调的最终拒绝时使用 `ctx.tools.guard()`；当插件需要包裹实际分发生命周期时（超时/重试/指标；仅 `exec.signal` 可替换）使用 `tools/execute`；显式结果变换使用 `tools/post-execute`；对不可变最终结果的受限观察使用 `tools/result`。选择规则见[添加工具指南](./adding-a-tool.md#execution-policy-and-observation)。
+
+## UI 插件
+
+UI 插件从 `session/event` 事件流渲染（助手 token 流以 `assistant/chunk` 形式到达，加上轮次/步骤边界与工具活动），并通过 `agent.send()` / `agent.steer()` 将输入驱动回去。
+
+```ts
+import type { Context } from 'cordis'
+import { AgentId } from '@deepseek-ai/dsh-agent'
+
+declare function render(text: string): void
+declare function onUserInput(handler: (text: string) => void): void
+
+export const name = 'my-ui'
+export const inject = ['agents']
+
+export function apply(ctx: Context) {
+  ctx.on('session/event', (_session, event) => {
+    if (event.type === 'assistant/chunk' && event.data.chunk.type === 'text-delta') {
+      render(event.data.chunk.text)
+    }
+  })
+  onUserInput(text => ctx.agents.get(AgentId('main'))?.send([{ type: 'text', text }]))
+}
+```
+
+## 客户端驱动插件（外部协议桥接）
+
+*客户端驱动*是面向协议格式（wire format）对端的 UI 插件。它拥有 stdio，因此必须禁用 stdout 日志；通过工厂创建或恢复 agent（智能体）；将 harness 事件映射为协议消息；将请求映射为 `send()` 或 `cancel()`。每个请求从持久的 `turn/end` 恰好结算一次（即使渲染失败），并通过 `AgentHandle.dispose()` 拆除 agent 以使 dispose（资源释放）达到静止状态。
+
+`packages/ui/acp` 是完整的工作示例：它将 agent 桥接到 ACP（Agent Client Protocol）（基于 stdio 的 JSON-RPC），使 Zed 及其他 ACP 编辑器能够驱动它。其 README 描述了完整的方法接口以及它在审批 seam 上注册的权限提示应答器。
+
+```ts
+import type { Context } from 'cordis'
+
+export const name = 'my-protocol-bridge'
+export const inject = ['agents', 'sessions', 'sessionPersistence']
+
+export function apply(ctx: Context) {
+  // Stream every logged assistant text/reasoning delta out to the client.
+  ctx.on('session/event', (_session, event) => {
+    if (event.type === 'assistant/chunk') {
+      const chunk = event.data.chunk
+      if (chunk.type === 'text-delta') {
+        // sendToClient({ kind: 'message_chunk', text: chunk.text })
+      }
+    }
+  })
+  // Inbound "prompt": create/resume an agent and feed it; settle on turn end.
+  // Teardown reaches quiescence via AgentHandle.dispose() (stop + await exit).
+}
+```
+
+## 可运行的组装示例
+
+三个完整示例从 `cordis.yml` 加载各自的插件树：[`examples/echo-agent`](../../examples/echo-agent)（mock 模型 + echo 工具——全 mock 骨架检查，`pnpm run demo:echo`）、[`examples/coding-agent`](../../examples/coding-agent)（DeepSeek V4 + bash 工具套件，配合终端 REPL UI，`pnpm run demo:repl`）、[`examples/acp-agent`](../../examples/acp-agent)（通过 JSON-RPC stdio 暴露为 ACP 服务器的 agent——客户端驱动形态，`pnpm run demo:acp`）。每个叶子只是其可替换后端加一个 app 包入口：stdio 演示加载 [`@deepseek-ai/dsh-stdio-agent`](../../packages/ui/stdio-agent)，ACP 演示加载 [`@deepseek-ai/dsh-acp-agent`](../../packages/ui/acp-agent)，两个 app 包通过 [`@deepseek-ai/dsh-agent-core`](../../packages/core/agent-core) bundle 共享主干。
+
+## 功能→机制映射
+
+每个产品功能都映射到一个文档化扩展 seam 上的监听器——微内核声明由此可验证（[微内核 RFC](../rfc/implemented/architecture/2026-06-11-microkernel-event-taxonomy.md)）。没有任何一行修改循环本身。
+
+`system-prompt/assemble` 是一个专家协作式的整体装配变换：其返回的装配结果具有权威性，因此监听器作者有责任保留活跃的 Code Mode 和结构化输出协议的贡献。对于需要在展示、查找和执行之间保持对齐的工具过滤，优先使用 `ctx.tools.restrict()`。
+
+| 产品功能 | 插件机制 |
+|---|---|
+| 钩子系统（用户级 + 项目级） | `agent/session-start`、`agent/prompt-submit`、`agent/request`、`agent/step-result`、`tools/pre-execute`、`tools/post-execute`、`agent/turn-continuation` 上的监听器——每个拦截 waterfall 返回一个类型化 Decision；`dsh-hooks-claude` / `dsh-hooks-codex` 桥接器将钩子配置文件映射到这些 seam 上 |
+| `/goal` | 通过 `agent/turn-continuation` 强制继续 + `steer()` 提醒 |
+| `/loop` | 在 `turn/end` 会话事件上 `send()` 下一次迭代；或强制继续 |
+| 动态工作流 | `ctx.workflows` + worker-thread 引擎 + `workflow` 工具；结构化的进程内子任务通过作用域化的 prompt/工具注册、单调工具守卫、最终 `tools/result` 提交（包括外层 `run_code`）和终端 `agent/turn-stop` 来强制输出 |
+| 排队消息 + steering（中途引导） | 核心 `Agent.send()` / `Agent.steer()` |
+| 上下文压缩（context compaction）（自动 + 手动） | `ctx.compact` seam + 串行 `agent/pre-step` seam 上的后端（`dsh-compact-basic`）；自动 = 每步之前的 token 压力检查；手动触发调用同一个 `ctx.compact` 例程（[压缩 RFC](../rfc/implemented/feature/2026-06-18-compaction-capability-seam.md)——面向模型的 `/compact` 消费方工具已推迟） |
+| 系统提示词可配置性 | `ctx.systemPrompt.section()`，支持排序与作用域局部覆盖 |
+| AGENTS.md（根目录） | 一个读取该文件的 section provider |
+| AGENTS.md（子目录，按需触发）+ 文件变更通知 | 从 watcher / tool-result 监听器调用 `agent.inject()` |
+| 内置工具 | `ctx.tools.register()`；schema 自动流入装配——`dsh-tool-*` 系列（bash、fs、web、subagent、todo）是已交付的示例 |
+| ToolSearch / 渐进式披露 | 当可见集变化时替换一个作用域化的 `ctx.tools.restrict()` 注册；注册表保持展示、查找和执行三者对齐 |
+| 工具截止时间 / 重试 / 指标 | 用 `tools/execute` 包裹核心分发；包装器可替换 `exec.signal`、委托执行，并在同一词法生命周期内检视规范化结果 |
+| 最终工具结果指标 / 审计 / 捕获 | 用 `tools/result` 观察不可变的权威结果；仅当插件需要变换结果或附加上下文时才使用 `tools/post-execute` |
+| 单调终端轮次策略 | 从串行 `agent/turn-stop` 返回 `{ action: 'stop' }`，此时 continuation 和 steering 已折叠完毕 |
+| 子进程沙箱（landlock / sandbox-exec） | 通过 `dsh-bash-sandbox` 使用 `ctx.sandbox` 后端；能力级别的拒绝使用 `tools/pre-execute` |
+| 权限系统 / AskUserQuestion | 从 `tools/pre-execute` 返回 `ask` 并通过 `ctx.approval` 应答；为普通用户提问注册一个独立的面向模型的 ask 工具 |
+| Plan mode | `tools/pre-execute`（拒绝写操作）+ 通过 `ctx.systemPrompt.section()` 或 `agent.inject()` 注入模式提示词段（model-visible ⟺ logged：`agent/request` 仅塑形调用配置） |
+| 子 agent 委派 | `ctx.subagents` 提供方注册表（`dsh-subagent-spawn`/`-fork`/`-acp`）+ `dsh-tool-subagent` 向模型暴露一个已配置的提供方 |
+| MCP | 每个服务器一个插件：发现工具 → `ctx.tools.register()` |
+| Skill（技能） | section + 工具注册；调用时通过 `inject()` 注入 skill 内容 |
+| 记忆 | section provider + 工具 |
+| 定时任务（cron） | 插件注册面向模型的调度工具；定时器触发 → 空闲时 `send(…, {source: {kind: 'cron', …}})`／忙碌时 `inject()` 通知 |
+| UI（GUI；CLI 输出 JSONL） | 监听 `session/event`（助手分片、边界、工具活动）；输入 → `send()` |
+| 遥测 / 可回放 trace | `session/event` → JSONL；回放 = `sessions.create(id, { seed })` |
+| 模型适配器 | 通过 `registerAdapter` 注册 `LlmAdapter` 子类（`dsh-llm-deepseek`、`dsh-llm-pi-ai`） |
+| 插件热重载 | 每个注册都是一个 `ctx.effect` → vendor 的 HMR（热模块替换）直接生效 |
diff --git a/docs/cookbook/responding-to-pr-review-on-a-stack.i18n.yaml b/docs/cookbook/responding-to-pr-review-on-a-stack.i18n.yaml
new file mode 100644
index 0000000000..d75b8cad3e
--- /dev/null
+++ b/docs/cookbook/responding-to-pr-review-on-a-stack.i18n.yaml
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write
+responding-to-pr-review-on-a-stack.md: 3fb7eb943eeb8d703303be3f6a844870cc26fd47
+responding-to-pr-review-on-a-stack.zh.md: d96323b853c093265931904c20996df335f82926
diff --git a/docs/cookbook/responding-to-pr-review-on-a-stack.md b/docs/cookbook/responding-to-pr-review-on-a-stack.md
index 4eb7dc482d..3fb7eb943e 100644
--- a/docs/cookbook/responding-to-pr-review-on-a-stack.md
+++ b/docs/cookbook/responding-to-pr-review-on-a-stack.md
@@ -1,6 +1,8 @@
 # Responding to review across a stacked PR chain
 
-A wave of review comments lands across several PRs in a dependent stack (`A ← B ← C …`). This is the discipline for resolving it without corrupting the stack. The two invariants it rests on are standing orders in the root [AGENTS.md](../../AGENTS.md) § Conventions: merge commits only, and never rewrite a pushed branch.
+English | [中文](responding-to-pr-review-on-a-stack.zh.md)
+
+Review comments may target several PRs in a dependent stack (`A ← B ← C …`). This guide explains how to resolve them without corrupting the stack. The two invariants it rests on are standing orders in the root [AGENTS.md](../../AGENTS.md) § Conventions: merge commits only, and never rewrite a pushed branch.
 
 ## Ground rules
 
@@ -9,7 +11,7 @@ A wave of review comments lands across several PRs in a dependent stack (`A ←
 3. **A fix lands on the PR that INTRODUCED the issue, then flows down.** When a comment on PR `B` points at code `B` introduced, fix it on `B` and merge `B` into `C` — even if `C` also carries the file. Originating the fix downstream leaves `B` shipping the unfixed code and hides the fix from `B`'s reviewer.
 4. **Each review fix is a separate commit, never an amend.** The "fix review findings" commit documents what the review caught. Amending is fine only for your own not-yet-pushed, not-yet-reviewed work.
 
-## Working the wave
+## Resolve comments through the stack
 
 1. Triage every comment on the merits before acting: verify the claim against the code — a reviewer flagging the right symptom can still mis-diagnose the cause.
 2. Map each accepted finding to its originating PR, fix it there, then merge down the chain in order.
diff --git a/docs/cookbook/responding-to-pr-review-on-a-stack.zh.md b/docs/cookbook/responding-to-pr-review-on-a-stack.zh.md
new file mode 100644
index 0000000000..d96323b853
--- /dev/null
+++ b/docs/cookbook/responding-to-pr-review-on-a-stack.zh.md
@@ -0,0 +1,26 @@
+# 在堆叠 PR 链中回应评审意见
+
+[English](responding-to-pr-review-on-a-stack.md) | 中文
+
+评审意见可能同时针对一条依赖堆叠（`A ← B ← C …`）中的多个 PR（Pull Request）。本指南说明如何在不破坏堆叠的前提下解决这些意见。它依赖的两个不变式是根 [AGENTS.md](../../AGENTS.md) § Conventions 中的常设指令：只用 merge commit，以及永远不改写已推送的分支。
+
+## 基本规则
+
+1. **每个 PR 分支一个 worktree。** 每个 PR 的修复在该 PR 自己的 worktree 中进行；并行修复绝不共享同一个 checkout。
+2. **通过将父分支向下合并来更新子分支**（在子分支中执行 `git merge <parent-branch>`，产生一个新的 merge commit）。绝不对已推送的分支做 rebase/amend/force-push：改写会使分支与父 PR 及 GitHub 记录的内容产生分歧，破坏堆叠合并图，并抹去评审修复历史。
+3. **修复落在引入问题的那个 PR 上，然后向下流动。** 当 PR `B` 上的评论指向 `B` 引入的代码时，在 `B` 上修复，再将 `B` 合并到 `C`——即使 `C` 也包含该文件。把修复发起在下游会导致 `B` 带着未修复的代码交付，并对 `B` 的评审者隐藏修复。
+4. **每个评审修复是一个独立 commit，绝不 amend。** "修复评审发现"的 commit 记录了评审捕获的内容。只有你自己尚未推送、尚未评审的工作才可以 amend。
+
+## 沿堆叠解决评审意见
+
+1. 在行动之前先就事论事地审视每条评论：对照代码验证其论断——评审者指出了正确的症状，但仍可能误诊原因。
+2. 将每个被接受的发现映射到其发起 PR，在那里修复，然后按顺序沿链向下合并。
+3. 委派的修复需要信任但验证：子 agent（智能体）的报告描述的是意图，不一定是实际落地的内容。请亲自在实际代码树上重新运行门禁；对于回归守卫，要证明它在未修复的代码上**失败**（引入回归、观察变红、再还原）——两种情况都通过的守卫什么也守不住。子 agent 将问题重新定性为「已处理」时，这是一个需要亲自深入的信号。
+4. 在评审线程中回复（`gh api repos/{owner}/{repo}/pulls/{pr}/comments/{id}/replies`），而非发顶层评论；说明修复内容及承载修复的 commit。
+5. 合并堆叠之前，检查依赖方：删除一个 PR 的 base 分支会自动关闭依赖它的 PR。用 `gh pr list --state open --base <branch> --json number --jq length` 检查每个分支（非零 = 有打开的依赖方），当子 PR 仍以该分支为 base 时，合并时不带 `--delete-branch`。完整的落地流程见 [dsh-merging-stacked-prs](../../.agents/skills/dsh-merging-stacked-prs/SKILL.md) skill（技能）。
+
+## 验证
+
+- 每个已修复的 PR 显示一个新 commit（PR 时间线中没有 force-push 图标）。
+- 每个子 PR 相对其父 PR 的 diff 仍然只包含自身的变更。
+- 门禁在堆叠中的每个 PR 上都通过，而不仅仅是顶部。
diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md
index 2b86baaf57..e765c7c0cf 100644
--- a/docs/cordis-catalog/events.md
+++ b/docs/cordis-catalog/events.md
@@ -245,7 +245,7 @@ Creation announcement during session publication. A synchronous throw vetoes and
 'session/created'(this: Scoped<Session>, session: Session): void
 ```
 
-Source: [`packages/core/session/src/index.ts:46`](../../packages/core/session/src/index.ts)
+Source: [`packages/core/session/src/index.ts:47`](../../packages/core/session/src/index.ts)
 
 ### `session/disposed` — emit
 
@@ -255,7 +255,7 @@ Emitted once when an announced session leaves the store, including publication r
 'session/disposed'(this: Scoped<Session>, session: Session): void
 ```
 
-Source: [`packages/core/session/src/index.ts:55`](../../packages/core/session/src/index.ts)
+Source: [`packages/core/session/src/index.ts:57`](../../packages/core/session/src/index.ts)
 
 ### `session/event` — emit
 
@@ -267,7 +267,7 @@ Post-commit, fire-and-forget append feed. The listener snapshot resolves before
 
 Types: [SessionEvent](../core-data-structures/core.md)
 
-Source: [`packages/core/session/src/index.ts:66`](../../packages/core/session/src/index.ts)
+Source: [`packages/core/session/src/index.ts:69`](../../packages/core/session/src/index.ts)
 
 ### `session/flush` — parallel
 
@@ -277,7 +277,7 @@ Awaited parallel durability checkpoint: every listener runs and the caller await
 'session/flush'(this: Scoped<Session>, session: Session): Promise<void> | void
 ```
 
-Source: [`packages/core/session/src/index.ts:75`](../../packages/core/session/src/index.ts)
+Source: [`packages/core/session/src/index.ts:79`](../../packages/core/session/src/index.ts)
 
 ## `skill/*`
 
@@ -311,7 +311,7 @@ A ready child settled. Scope-filtered dispatch uses the same delegating parent c
 'subagent/end'(this: Scoped<SubagentService>, info: SubagentRunEndInfo): void
 ```
 
-Source: [`packages/subagent/subagent/src/index.ts:90`](../../packages/subagent/subagent/src/index.ts)
+Source: [`packages/subagent/subagent/src/index.ts:92`](../../packages/subagent/subagent/src/index.ts)
 
 ### `subagent/provider-added` — emit
 
@@ -341,7 +341,7 @@ A provider established a ready child. For in-process providers, `ctx.agents.get(
 'subagent/start'(this: Scoped<SubagentService>, info: SubagentRunInfo): void
 ```
 
-Source: [`packages/subagent/subagent/src/index.ts:82`](../../packages/subagent/subagent/src/index.ts)
+Source: [`packages/subagent/subagent/src/index.ts:83`](../../packages/subagent/subagent/src/index.ts)
 
 ## `system-prompt/*`
 
diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md
index a3d06032f9..f7a8ec0850 100644
--- a/docs/cordis-catalog/services.md
+++ b/docs/cordis-catalog/services.md
@@ -169,7 +169,7 @@ abstract list(): Promise<SessionHeader[]>
 
 Types: [SessionEvent](../core-data-structures/core.md)
 
-Source: [`packages/session-persistence/session-persistence/src/index.ts:60`](../../packages/session-persistence/session-persistence/src/index.ts)
+Source: [`packages/session-persistence/session-persistence/src/index.ts:30`](../../packages/session-persistence/session-persistence/src/index.ts)
 
 ## `ctx.sessionQuery` — `SessionQueryService`
 
@@ -200,7 +200,7 @@ list(): Session[]
 fork(source: SessionForkSource, boundary?: number, childSessionId?: SessionId): Session
 ```
 
-Source: [`packages/core/session/src/index.ts:587`](../../packages/core/session/src/index.ts)
+Source: [`packages/core/session/src/index.ts:591`](../../packages/core/session/src/index.ts)
 
 ## `ctx.skills` — `SkillService`
 
@@ -226,7 +226,7 @@ list(): string[]
 async start(name: string, request: SubagentStartRequest): Promise<SubagentRun>
 ```
 
-Source: [`packages/subagent/subagent/src/index.ts:123`](../../packages/subagent/subagent/src/index.ts)
+Source: [`packages/subagent/subagent/src/index.ts:125`](../../packages/subagent/subagent/src/index.ts)
 
 ## `ctx.systemPrompt` — `SystemPrompt`
 
diff --git a/docs/cordis-primer.md b/docs/cordis-primer.md
index 5b14da901c..d8e92dcb67 100644
--- a/docs/cordis-primer.md
+++ b/docs/cordis-primer.md
@@ -31,6 +31,10 @@ Cooperative listeners usually mutate a shared request or decision object and the
 
 For single-decision events, short-circuiting is the design. A policy listener can return without `next()` when it owns the decision, while a listener that only annotates or observes must delegate.
 
+## Loader Configuration
+
+`@cordisjs/plugin-include` parses `!!js` into expression nodes, but the Loader interpolates only an entry's `config` before mounting the plugin. Entry metadata (`id`, `name`, `group`, `disabled`, `inject`, `intercept`, and `isolate`) remains literal; `disabled: !!js ...` is therefore a truthy object that always disables the entry. Use explicit config overlays when environment selection changes which plugins are mounted.
+
 ## Practical Rules
 
 Encapsulate behavior into plugins: a tool pipeline event belongs to `ctx.tools`, model streaming belongs to `ctx.llm`, and live agent coordination belongs to `ctx.agents`. Prefer events for interception and policy; prefer service methods for direct capability calls.
diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md
index 65464fbdf2..316797e5ec 100644
--- a/docs/event-producer-consumer.md
+++ b/docs/event-producer-consumer.md
@@ -3,7 +3,7 @@
 
 # Event Producer And Consumer Matrix
 
-This matrix shows which packages dispatch each harness-owned event and which packages listen to it. It is intentionally a table rather than one large graph: events are many-to-many, and dense relation data is easier to review in rows. Dynamic dispatch overrides cover sites that deliberately bypass `ctx.emit`, such as subagent lifecycle containment.
+This matrix shows which packages dispatch each harness-owned event and which packages listen to it. It is intentionally a table rather than one large graph: events are many-to-many, and dense relation data is easier to review in rows. Receiver and event-name types also cover contained dispatch sites that deliberately bypass `ctx.emit`, such as subagent lifecycle containment.
 
 | Event | Mode | Declared in | Dispatchers | Listeners |
 | --- | --- | --- | --- | --- |
@@ -15,7 +15,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac
 | `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:169`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - |
 | `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:226`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - |
 | `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:241`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill) |
-| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:182`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`invariants`](../packages/support/invariants) |
+| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:182`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) |
 | `agent/status` | `emit` | [`packages/core/agent/src/types.ts:159`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard), [`stdio-agent`](../packages/ui/stdio-agent) |
 | `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:252`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - |
 | `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:262`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) |
@@ -25,16 +25,16 @@ This matrix shows which packages dispatch each harness-owned event and which pac
 | `fs/observed` | `emit` | [`packages/fs/fs/src/index.ts:68`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`emit`) | [`fs-policy`](../packages/fs/fs-policy) |
 | `fs/write-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:51`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) |
 | `llm/stream` | `waterfall` | [`packages/llm/llm/src/index.ts:40`](../packages/llm/llm/src/index.ts) | [`llm`](../packages/llm/llm) (`waterfall`) | [`invariants`](../packages/support/invariants), [`llm-replay`](../packages/support/llm-replay) |
-| `session/created` | `emit` | [`packages/core/session/src/index.ts:46`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence) |
-| `session/disposed` | `emit` | [`packages/core/session/src/index.ts:55`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | - |
-| `session/event` | `emit` | [`packages/core/session/src/index.ts:66`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`acp`](../packages/ui/acp), [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence), [`stdio-agent`](../packages/ui/stdio-agent) |
-| `session/flush` | `parallel` | [`packages/core/session/src/index.ts:75`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`session-persistence`](../packages/session-persistence/session-persistence) |
+| `session/created` | `emit` | [`packages/core/session/src/index.ts:47`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence) |
+| `session/disposed` | `emit` | [`packages/core/session/src/index.ts:57`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | - |
+| `session/event` | `emit` | [`packages/core/session/src/index.ts:69`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`acp`](../packages/ui/acp), [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence), [`stdio-agent`](../packages/ui/stdio-agent) |
+| `session/flush` | `parallel` | [`packages/core/session/src/index.ts:79`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`session-persistence`](../packages/session-persistence/session-persistence) |
 | `skill/provider-added` | `emit` | [`packages/skill/skill/src/index.ts:131`](../packages/skill/skill/src/index.ts) | [`skill`](../packages/skill/skill) (`emit`) | - |
 | `skill/provider-removed` | `emit` | [`packages/skill/skill/src/index.ts:137`](../packages/skill/skill/src/index.ts) | [`skill`](../packages/skill/skill) (`emit`) | - |
-| `subagent/end` | `emit` | [`packages/subagent/subagent/src/index.ts:90`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`jsonrpc`](../packages/ui/jsonrpc) |
+| `subagent/end` | `emit` | [`packages/subagent/subagent/src/index.ts:92`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`jsonrpc`](../packages/ui/jsonrpc) |
 | `subagent/provider-added` | `emit` | [`packages/subagent/subagent/src/index.ts:66`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`emit`) | [`tool-subagent`](../packages/subagent/tool-subagent) |
 | `subagent/provider-removed` | `emit` | [`packages/subagent/subagent/src/index.ts:72`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`tool-subagent`](../packages/subagent/tool-subagent) |
-| `subagent/start` | `emit` | [`packages/subagent/subagent/src/index.ts:82`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude) |
+| `subagent/start` | `emit` | [`packages/subagent/subagent/src/index.ts:83`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude) |
 | `system-prompt/assemble` | `waterfall` | [`packages/core/system-prompt/src/index.ts:27`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`waterfall`) | - |
 | `system-prompt/change` | `emit` | [`packages/core/system-prompt/src/index.ts:33`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`emit`) | - |
 | `tools/change` | `emit` | [`packages/core/tools/src/index.ts:116`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`emit`) | - |
@@ -55,4 +55,4 @@ This matrix shows which packages dispatch each harness-owned event and which pac
 | --- | --- | --- |
 | `internal/dispatch` | - | [`invariants`](../packages/support/invariants) |
 
-Maintenance mode: hybrid generated: Cordis event declarations and most producer/listener edges are AST-scanned; dynamic dispatch sites are classified in `scripts/gen-doc-graphs.ts`.
+Maintenance mode: generated: Cordis event declarations and producer/listener edges are resolved from the repository TypeScript Program.
diff --git a/docs/i18n/terminology.md b/docs/i18n/terminology.md
index 69f0e170e0..d14d0f2fd8 100644
--- a/docs/i18n/terminology.md
+++ b/docs/i18n/terminology.md
@@ -40,7 +40,7 @@
 | Cordis | Cordis | | | |
 | dispose | dispose | dispose（资源释放） | | |
 | doc-sync | doc-sync | doc-sync（文档同步门禁） | | |
-| fiber | fiber | fiber（插件运行时） | | |
+| fiber | fiber | | | |
 | fixture | fixture | fixture（测试前置数据） | | |
 | fork | fork | | | |
 | Function Calling | Function Calling | Function Calling（函数调用） | | |
@@ -51,7 +51,6 @@
 | loader | loader | | | |
 | manifest | manifest | manifest（元数据清单） | | |
 | monorepo | monorepo | | | |
-| package | package | | | 保留英文；指 npm 包（`@deepseek-ai/dsh-*`） |
 | schema | schema | | | |
 | schema DSL | schema DSL | | | |
 | seam | seam | | | 与 `extension point` 是不同概念；根据具体语境，可译为`服务边界`或`可替换点` |
@@ -125,6 +124,7 @@
 | module | 模块 | | | |
 | orphan | 遗留 | | 孤儿、孤立 | 指英文源已不存在的 `.zh.md`（如「遗留译文」）；进程语境按 OS 惯用语译「孤儿进程」 |
 | orphan branch | 孤立分支 | | 孤儿分支 | 沿用 git 官方中文翻译 |
+| package | 包 | 包（package） | | 指 npm 包（`@deepseek-ai/dsh-*`）；`package.json` 等代码标识保持原样 |
 | pairing | 配对 | | | |
 | peer dependency | 对等依赖 | 对等依赖（peer dependency） | | |
 | permission | 权限 | | | |
diff --git a/docs/i18n/translation-prompt.md b/docs/i18n/translation-prompt.md
index a300ef64f4..60a023979a 100644
--- a/docs/i18n/translation-prompt.md
+++ b/docs/i18n/translation-prompt.md
@@ -79,6 +79,11 @@ You are a senior technical translator specializing in LLM and agent development
 
 #### When translating into English
 - Use half-width English punctuation and standard English spacing. Preserve full-width punctuation only in verbatim Chinese text.
+- Convert enumeration commas (、) to English commas; convert 「」 quotes to English double quotes.
+- Render the terminology table's English column the same way the Chinese column binds the other direction: listed terms use exactly the table's English form; first-occurrence glosses do not carry over (English prose never glosses an English term with Chinese).
+- Chinese topic-comment sentences and dropped subjects become explicit English subjects; prefer concise declaratives over nominalizations.
+- Do not transliterate Chinese engineering idioms literally: render the underlying concept (误报 → false positive, 执行红线 → enforcement frontier), consulting the terminology table first.
+- Keep the register of institutional developer documentation: contractions are acceptable, marketing language and hedging (very, quite, simply) are not.
 
 ## Terminology
 
diff --git a/docs/postmortem/0002-js-expression-disabled-filesystem-tools.md b/docs/postmortem/0002-js-expression-disabled-filesystem-tools.md
new file mode 100644
index 0000000000..191c13459c
--- /dev/null
+++ b/docs/postmortem/0002-js-expression-disabled-filesystem-tools.md
@@ -0,0 +1,45 @@
+# Post-mortem 0002: Filesystem snapshot tools were permanently disabled
+
+Status: resolved
+
+## Executive summary
+
+The ACP example attempted to enable filesystem plugins conditionally with `disabled: !!js ...`, but Cordis evaluates JavaScript expressions only inside plugin `config`. The raw expression object was truthy, so the filesystem stack was always disabled. Snapshot refresh then accepted `UNKNOWN_TOOL` results as new goldens. The fix uses an explicit filesystem overlay and adds static-config and snapshot-result guards.
+
+## Summary
+
+The default ACP composition is intentionally bash-only because its sandbox cannot confine in-process filesystem providers. Filesystem snapshot scenarios still need `read`, `write`, and `edit`, so their plugins were placed in the default `cordis.yml` with a `disabled` expression intended to enable them only for full-access launches and snapshots.
+
+Cordis Include parsed each `!!js` scalar into an expression object. The Loader recursively interpolated the plugin's `config`, but consumed entry metadata such as `disabled` directly. Every filesystem entry therefore saw a truthy object and remained disabled in every mode.
+
+## Impact
+
+Seven filesystem scenarios and the mixed workspace-edit scenario called tools that were absent from the registry. Their structured session logs carried `ToolNotFoundError` with code `UNKNOWN_TOOL`, while stdout rendered generic failed tool cards. The snapshot suite passed because both surfaces matched the refreshed fixtures; it proved deterministic replay of the regression rather than successful filesystem behavior.
+
+The live confined default did not gain unintended filesystem access. A naive interpolation fix would have created that risk: permission presets update bash sandbox and approval state at runtime, but cannot mount, unmount, or confine the filesystem stack.
+
+## Timeline
+
+- PR #261 consolidated ACP compositions and refreshed the filesystem snapshots while introducing conditional filesystem entries.
+- All unit, coverage, snapshot, documentation, build, and hygiene checks passed.
+- Review of the refreshed filesystem goldens found generic failed cards and structured `UNKNOWN_TOOL` results.
+- A real Loader boot confirmed that every `disabled` value remained an expression object and every filesystem fiber was absent.
+
+## Root cause
+
+The implementation assumed `!!js` applied to an entire Loader entry. Its actual boundary is narrower: `Entry._resolveConfig()` interpolates only `entry.options.config`; `Entry.disabled` tests `entry.options.disabled` without interpolation. The YAML tag was syntactically valid, so loading produced no diagnostic.
+
+The snapshot framework treated any deterministic transcript as valid behavior. Header pins verified the composed tool schemas, but the filesystem scenarios shared a pin from the default composition and therefore did not independently prove that their required tools were registered. Refresh rewrote the expected stdout and session logs before any semantic assertion rejected missing tools.
+
+## Guardrails added
+
+- Filesystem scenarios boot `fs.cordis.yml`, an explicit fixed full-access overlay with a paired replay config and its own request-header class.
+- [`AGENTS.md`](../../AGENTS.md) and the [Cordis primer](../cordis-primer.md#loader-configuration) state that `!!js` is valid only under plugin `config` and conditional composition uses overlays.
+- `verify-cordis-config` parses repository Cordis YAML and rejects expression nodes in Loader entry metadata, including include patches and inserted entries.
+- `dsh-acp-snapshot` rejects structured `UNKNOWN_TOOL` results in fresh runs and committed session fixtures before they can become accepted goldens.
+
+## Lessons
+
+- A syntactically accepted configuration value is not necessarily evaluated at that location; document and verify interpolation boundaries.
+- A snapshot refresh is fixture production, not correctness review. Semantic impossibilities such as a missing registered tool need assertions independent of the golden.
+- Permission controls must describe only the capabilities they actually govern. Composition-time filesystem access cannot follow a runtime bash-only preset safely.
diff --git a/docs/postmortem/README.md b/docs/postmortem/README.md
index b8a07957d9..743433a827 100644
--- a/docs/postmortem/README.md
+++ b/docs/postmortem/README.md
@@ -11,3 +11,4 @@ Every post-mortem opens with an **Executive summary**: one short paragraph a bus
 | # | Title |
 |---|---|
 | [0001](0001-acp-default-export-drops-inject.md) | ACP server crashed on connect: `export default` dropped the plugin's `inject` |
+| [0002](0002-js-expression-disabled-filesystem-tools.md) | Filesystem snapshot tools were permanently disabled by a literal `!!js` object |
diff --git a/docs/rfc/INDEX.md b/docs/rfc/INDEX.md
index 2fb5a43bc1..86ae9d955d 100644
--- a/docs/rfc/INDEX.md
+++ b/docs/rfc/INDEX.md
@@ -175,6 +175,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand;
 | [Parallel pre-push gates](implemented/process/2026-07-06-parallel-pre-push-gates.md) | 2026-07-06 |
 | [A gated Known-Limitations section in every package README](implemented/process/2026-07-10-readme-known-limitations-gate.md) | 2026-07-10 |
 | [Package Model Experience contract](implemented/process/2026-07-12-package-model-experience-contract.md) | 2026-07-12 |
+| [TypeScript Program-backed semantic gates](implemented/process/2026-07-14-typescript-program-backed-semantic-gates.md) | 2026-07-14 |
 
 ### Testing
 
diff --git a/docs/rfc/implemented/architecture/2026-06-18-session-surface.md b/docs/rfc/implemented/architecture/2026-06-18-session-surface.md
index 305c092303..6ba0df41c4 100644
--- a/docs/rfc/implemented/architecture/2026-06-18-session-surface.md
+++ b/docs/rfc/implemented/architecture/2026-06-18-session-surface.md
@@ -31,7 +31,7 @@ export type SurfaceOp =
 
 ### SurfaceManager: delta-based, not full rebuild
 
-A `SurfaceManager` class (private to `Session`) maintains the cached linked list. It tracks `_lastProcessedSeq` and processes only the **delta** (new events since the last access) rather than rescanning the entire log. Because the log is append-only, prior events never change — full rebuild is only needed after a wholesale log replacement (e.g., seeding).
+A `SurfaceManager` class (private to `Session`) maintains the cached linked list. It tracks `_lastProcessedSeq` and processes only the **delta** (new events since the last access) rather than rescanning the entire log. Because the log is append-only, prior events never change; a seeded log is simply the initial delta folded on first access.
 
 Delta processing is O(1) when no new events and O(new events) when new events arrive.
 
diff --git a/docs/rfc/implemented/architecture/2026-07-12-agent-scope-runtime-design.md b/docs/rfc/implemented/architecture/2026-07-12-agent-scope-runtime-design.md
index f09ab214f5..2c3126793f 100644
--- a/docs/rfc/implemented/architecture/2026-07-12-agent-scope-runtime-design.md
+++ b/docs/rfc/implemented/architecture/2026-07-12-agent-scope-runtime-design.md
@@ -328,7 +328,7 @@ The plugin does not police trusted setup by scanning registries or reject prompt
 
 ### Generated artifacts keep public contracts aligned
 
-The event catalog, service catalog, producer/consumer matrix, configuration catalog, module graph, tool catalog, and type-equivalence blocks are generated or freshness-gated from source. `verify-scoped-dispatch` keeps the declared scoped-event set aligned with runtime invariant coverage.
+The event catalog, service catalog, producer/consumer matrix, configuration catalog, module graph, tool catalog, type-equivalence blocks, and scoped-event resolver map are generated or freshness-gated from source. The [TypeScript semantic-gates RFC](../process/2026-07-14-typescript-program-backed-semantic-gates.md) owns Program construction, semantic event discovery, and resolver-generation rules.
 
 Behavioral tests pin scoped routing and disposal, final-entry collision cleanup, publication rollback, ordered quiescence, durable pre/post-commit behavior, live tool filtering across presentation and execution, cooperative prompt assembly, structured-output commit in native and Code Mode, async subagent startup and signal cancellation, worker terminal arbitration, ACP settlement, and process teardown.
 
diff --git a/docs/rfc/implemented/process/2026-07-14-typescript-program-backed-semantic-gates.i18n.yaml b/docs/rfc/implemented/process/2026-07-14-typescript-program-backed-semantic-gates.i18n.yaml
new file mode 100644
index 0000000000..eb411f1158
--- /dev/null
+++ b/docs/rfc/implemented/process/2026-07-14-typescript-program-backed-semantic-gates.i18n.yaml
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write
+2026-07-14-typescript-program-backed-semantic-gates.md: 3e7a76e86d83080ae1a4f91ca97cc9749c90ef29
+2026-07-14-typescript-program-backed-semantic-gates.zh.md: 0a13452012e7f6cbd3ad7994845ba1985355c089
diff --git a/docs/rfc/implemented/process/2026-07-14-typescript-program-backed-semantic-gates.md b/docs/rfc/implemented/process/2026-07-14-typescript-program-backed-semantic-gates.md
new file mode 100644
index 0000000000..3e7a76e86d
--- /dev/null
+++ b/docs/rfc/implemented/process/2026-07-14-typescript-program-backed-semantic-gates.md
@@ -0,0 +1,63 @@
+# RFC: TypeScript Program-backed semantic gates
+
+Status: implemented
+
+English | [中文](2026-07-14-typescript-program-backed-semantic-gates.zh.md)
+
+## Problem
+
+Repository gates sometimes need facts that TypeScript syntax does not carry by itself: whether a receiver is a Cordis `Context`, which concrete event names reach a forwarding helper, and whether declaration merging changed an event signature.
+
+The existing gates use TypeScript's single-file syntax model and maintain these facts through naming conventions, handwritten tables, and JSDoc.
+
+The repository needs one semantic source of truth without introducing runtime package cycles, broad fallback heuristics, or machine-readable annotations that restate information already available to TypeScript.
+
+## Decision
+
+Repository gates can combine project-wide type information through `ts.Program` and use `TypeChecker` to extract **strongly typed** facts, reducing their reliance on naming conventions, handwritten tables, and JSDoc metadata.
+
+The repository applies this model to two gates.
+
+### One project model expands the root solution
+
+[`TypeScriptProject`](../../../../scripts/ts-project.ts) parses the root `tsconfig.json`, recursively expands every project reference, and combines the referenced source roots into one no-emit semantic program. A normal program created from the solution config can redirect referenced projects to built declarations; explicit expansion keeps the package `src` files available for AST traversal and symbol identity.
+
+The wrapper owns config diagnostics, semantic compiler options, repository-relative paths, source lookup, and the shared checker. Individual gates do not glob package sources or construct partial programs independently.
+
+### A. Event relations follow receiver and value types
+
+[`gen-doc-graphs`](../../../../scripts/gen-doc-graphs.ts) classifies calls by assignability to the repository's actual `Context`, `AgentEventDispatch`, and Cordis `EventsService` types. Variable names and property spellings do not determine whether a call is an event operation.
+
+Context and agent-dispatch calls contribute only finite string-literal event sets. Direct `EventsService.dispatch()` calls recover the event slot through array literals, constant aliases, conditional branches, and resolved call sites of non-exported local helpers. Generic forwarding parameters are not concrete producers: attribution stays with the call sites that supply a closed event value.
+
+Every declared harness event must have a discovered producer. A missing producer fails generation as dead vocabulary or an unsupported semantic dispatch shape; listener-free extension points remain valid. `internal/dispatch` instrumentation is not treated as a subscription to every event it observes, so the matrix contains direct product listeners rather than manually asserted indirect relationships.
+
+### B. Scoped-event routing generates one typed resolver map
+
+[`gen-scoped-events`](../../../../scripts/gen-scoped-events.ts) scans real `scopeTarget(base, key)` calls to establish the routing-key type for each scoped base. It then finds Cordis `Events` members with `this: Scoped<Base>` and searches every payload parameter plus one public property level for a type identical to that key after removing `null` and `undefined`.
+
+Exactly one match generates a resolver. Multiple matches are ambiguous and fail. Zero matches require `@dshScopeScan unsupported`, which is reserved for events whose routing key intentionally stays outside the payload, such as owner-keyed session events and parent-keyed subagent lifecycle events. The annotation records an unsupported scan; it does not encode an event name, parameter index, property path, or replacement type.
+
+The committed [`scoped-events.generated.ts`](../../../../packages/support/invariants/src/scoped-events.generated.ts) imports every scoped-event owner for its type-side `Events` contributions. Each generated lambda accepts `Parameters<Events[K]>`, and the complete object satisfies a `Record` over the derived `ScopedEventName` union. Ordinary TypeScript compilation therefore checks event existence, parameter position, property access, and scoped-event completeness. The only cast adapts Cordis's runtime `unknown[]` dispatch boundary to the already type-checked resolver.
+
+The invariants plugin consumes this generated runtime map instead of maintaining its own table. Additional event-owner packages are dev dependencies and project references of `dsh-invariants`, not peer dependencies, so the compile-time aggregation does not expand the plugin's runtime closure.
+
+### Semantic gaps fail explicitly
+
+The generators reject missing declarations, config diagnostics, widened or generic event names, inconsistent routing-key types, ambiguous payload matches, unnecessary unsupported annotations, and stale generated output. Recovery through local helper call sites is deliberately narrow: exported or unresolved dataflow requires a new semantic rule rather than a package-specific override.
+
+## Verification
+
+`verify-doc-graphs` freshness-checks semantic producer/listener discovery, and `verify-scoped-events` freshness-checks the generated resolver map. The root TypeScript build compiles the resolver against merged `Events`; workspace constraints and runtime-closure checks ensure its type-only aggregation does not become a deployment dependency.
+
+## Alternatives considered
+
+- **Keep syntax-only scans with receiver allowlists and manual overrides.** This is simple per exception but makes renames and new helper shapes update a second representation. Completeness can detect a missing producer, but it cannot prove that the override still describes the source.
+
+## Consequences
+
+- Event relation generation follows semantic receiver identity and closed event values instead of local naming conventions.
+- Scoped-event membership, subject extraction, and runtime invariant coverage come from event declarations and real dispatch contracts rather than handwritten tables.
+- Refactors that change event names, parameter positions, subject properties, or routing-key types fail generation or compilation at the owning contract.
+- Building a flattened Program costs more startup time and memory than parsing isolated files, and semantic gates depend on a valid root project graph.
+- Generated TypeScript remains committed source: changes to event owners or dispatch shapes must regenerate it and the affected documentation.
diff --git a/docs/rfc/implemented/process/2026-07-14-typescript-program-backed-semantic-gates.zh.md b/docs/rfc/implemented/process/2026-07-14-typescript-program-backed-semantic-gates.zh.md
new file mode 100644
index 0000000000..0a13452012
--- /dev/null
+++ b/docs/rfc/implemented/process/2026-07-14-typescript-program-backed-semantic-gates.zh.md
@@ -0,0 +1,63 @@
+# RFC: 基于 TypeScript Program 的语义门禁
+
+Status: implemented
+
+[English](2026-07-14-typescript-program-backed-semantic-gates.md) | 中文
+
+## 问题
+
+仓库门禁有时需要判断 TypeScript 语法本身不携带的事实：接收者是否为 Cordis `Context`、哪些具体事件名会进入转发辅助函数、声明合并是否改变了事件签名。
+
+当前的门禁基于 TypeScript 单文件语法解析能力，使用命名约定、手写的表格、JSDoc 等方式来维护这类信息。
+
+仓库需要一个语义真源，同时不能引入运行时包（package）之间的循环依赖、宽泛的兜底启发式逻辑，或重复描述 TypeScript 已有信息的机器可读标注。
+
+## 决策
+
+仓库可以通过项目级类型信息 `ts.Program` 进行跨文件项目类型联合计算，并通过 `TypeChecker` 来提取 **强类型** 信息，用以缓解原有命名约定、手写表格、JSDoc 标注等形式。
+
+当前已完成 A / B 两个门禁的语义化改造。
+
+### 一个项目模型展开根项目配置
+
+[`TypeScriptProject`](../../../../scripts/ts-project.ts) 解析根 `tsconfig.json`，递归展开每个项目引用，并将各引用项目的源码根合并为一个不输出文件的语义 Program。直接从根项目配置创建普通 Program 时，TypeScript 可能将引用项目重定向到构建后的声明文件；显式展开可以让门禁继续遍历各包的 `src` 文件，并使用真实符号标识。
+
+该封装统一负责配置诊断、语义编译选项、仓库相对路径、源码查找和共享 TypeChecker。各门禁不再自行按文件通配模式扫描包源码，也不再分别构建不完整的 Program。
+
+### A. 事件关系由接收者类型和值类型决定
+
+[`gen-doc-graphs`](../../../../scripts/gen-doc-graphs.ts) 根据调用接收者与仓库中真实 `Context`、`AgentEventDispatch` 和 Cordis `EventsService` 类型之间的可赋值关系进行分类。变量名和属性拼写不再决定某次调用是否属于事件操作。
+
+Context 与 AgentEventDispatch 调用只贡献有限的字符串字面量事件集合。对于直接调用 `EventsService.dispatch()` 的路径，生成器会沿数组字面量、常量别名、条件分支和未导出本地辅助函数的已解析调用点恢复事件槽位。泛型转发参数不算作具体生产方：事件仍归属于传入封闭事件值的调用点。
+
+每个已声明的 harness 事件都必须存在扫描得到的生产方。找不到生产方时，生成过程会将其视为无调用方的事件词汇或尚不支持的语义 dispatch 形态并明确失败；没有监听方的扩展点仍然合法。`internal/dispatch` 插桩不会被当作它所观察的每个事件的订阅，因此关系矩阵只记录直接的产品监听方，不再手工补充间接关系。
+
+### B. 带作用域的事件路由生成一份强类型解析函数表
+
+[`gen-scoped-events`](../../../../scripts/gen-scoped-events.ts) 扫描真实的 `scopeTarget(base, key)` 调用，为每种 scoped 基础对象确定路由键类型。随后，它查找带有 `this: Scoped<Base>` 的 Cordis `Events` 成员，并在每个事件参数及其一层公开属性中搜索类型；移除 `null` 和 `undefined` 后，候选类型必须与路由键类型完全相同。
+
+恰好一个匹配项会生成解析函数。存在多个匹配项时，含义不明确，生成器会失败。没有匹配项时，事件必须标记 `@dshScopeScan unsupported`；该标记只用于路由键有意留在事件参数之外的情况，例如按所属 agent（智能体）路由的会话事件和按父 agent 路由的 subagent 生命周期事件。此标记只表示扫描不受支持，不编码事件名、参数下标、属性路径或替代类型。
+
+仓库提交的 [`scoped-events.generated.ts`](../../../../packages/support/invariants/src/scoped-events.generated.ts) 会导入每个带作用域的事件声明方，使它们从类型侧合并进 `Events`。每个生成函数都接收 `Parameters<Events[K]>`，完整对象则满足基于 `ScopedEventName` 联合类型派生出的 `Record`。因此，常规 TypeScript 编译会检查事件是否存在、参数位置、属性访问和带作用域的事件集合完整性。唯一的类型断言只负责将 Cordis 运行时的 `unknown[]` dispatch 边界适配到已经通过类型检查的解析函数。
+
+不变式插件消费这份生成的运行时表，不再维护自己的事件表。新增的事件声明方包只作为 `dsh-invariants` 的开发依赖和项目引用存在，不进入对等依赖，因此编译期聚合不会扩大插件的运行时依赖闭包。
+
+### 语义缺口必须显式失败
+
+遇到声明缺失、配置诊断、事件名被拓宽或保持泛型、路由键类型不一致、事件参数匹配不唯一、不必要的 unsupported 标记，或生成产物陈旧时，生成器都会拒绝继续。通过本地辅助函数调用点恢复信息的能力被刻意限制在窄范围内：如果数据流经过导出或无法解析的边界，应新增通用语义规则，而不是添加特定包的覆盖项。
+
+## 验证
+
+`verify-doc-graphs` 对语义生产方/监听方扫描执行新鲜度检查，`verify-scoped-events` 对生成的解析函数表执行新鲜度检查。根 TypeScript 构建会将解析函数与合并后的 `Events` 一起编译；workspace 约束和运行时依赖闭包检查则确保仅参与类型聚合的依赖不会变成部署依赖。
+
+## 考虑过的替代方案
+
+- **保留语法扫描、接收者白名单和手写覆盖项。** 每个例外都容易单独处理，但重命名和新增辅助函数形态时还必须更新第二份表示。完整性检查能够发现生产方缺失，却无法证明覆盖项仍与源码一致。
+
+## 后果
+
+- 事件关系生成依据语义接收者身份和封闭事件值，不再依赖局部命名约定；
+- 带作用域的事件成员关系、主体提取和运行时不变式覆盖来自事件声明与真实 dispatch 契约，不再来自手写表；
+- 修改事件名、参数位置、主体属性或路由键类型时，会在其所属契约处触发生成或编译失败；
+- 构建扁平化 Program 比解析孤立文件消耗更多启动时间和内存，语义门禁也依赖有效的根项目图；
+- 生成的 TypeScript 仍属于提交到仓库的源码：事件声明方或 dispatch 形态发生变化后，必须重新生成该文件和受影响的文档。
diff --git a/docs/rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md b/docs/rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md
index 00a60ad4bc..42c67320f6 100644
--- a/docs/rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md
+++ b/docs/rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md
@@ -8,11 +8,11 @@ An ACP snapshot suite needs to prove the exact composed system prompt and tool-s
 
 ## Decision
 
-Exactly one scenario per header-composition class is flagged `pinsHeader`. Its directory splits the pin by review format: `system-prompt.golden.md` contains the normalized composed prompt as ordinary Markdown, while `session.jsonl` keeps the full tool-schema list, config, and reason but stores `header.system` as `"{{system}}"`. Every other JSONL stores both the system prompt and tool list as `"{{system}}"` / `"{{tools}}"`. The pin mechanics live in [`dsh-acp-snapshot`](../../../../packages/support/acp-snapshot/README.md), whose suite factory enforces one pin per class.
+Exactly one scenario per header-composition class is flagged `pinsHeader`. Its directory splits the pin by review format: `system-prompt.golden.md` contains the normalized composed prompt as ordinary Markdown, `tool-schemas.golden.json` contains the complete initial schemas and later schema edits as structured JSON, and `session.jsonl` retains config, reason, and any model-visible prefix while storing `header.system` and `header.tools` as `"{{system}}"` / `"{{tools}}"`. Every other JSONL uses the same prompt and tool tokens and also tokenizes session-prefix content. The pin mechanics live in [`dsh-acp-snapshot`](../../../../packages/support/acp-snapshot/README.md), whose suite factory enforces one pin per class.
 
-The pure `scrubSystemPrompts` normalizer applies to every stored session fixture and tokenizes both an initial header's prompt and a header delta's inserted prompt lines. `scrubRequestHeaders` additionally tokenizes tool schemas and session-prefix content for non-pinning scenarios while retaining structural facts: system-delta positions and arity, added/removed/changed tool names, prefix message count, field presence, config, and reason. Record and refresh write-back apply the appropriate scrub before writing JSONL and regenerate the Markdown prompt from the normalized live header, so neither path can reintroduce prompt text into JSONL or leave the readable snapshot stale.
+The pure `scrubSystemPrompts` and `scrubToolSchemas` normalizers apply to every stored session fixture and independently tokenize initial-header content plus header-delta bulk. `scrubRequestHeaders` also tokenizes session-prefix content for non-pinning scenarios while retaining structural facts: system-delta positions and arity, added/removed/changed tool names, prefix message count, field presence, config, and reason. Record and refresh write-back apply the appropriate scrub before writing JSONL and regenerate both sidecars from the normalized live header and deltas, so neither path can reintroduce prompt/schema bulk into JSONL or leave a review artifact stale.
 
-Guards make the split self-enforcing. On disk, every `session*.jsonl` is a fixed point of `scrubSystemPrompts`, only non-pinning fixtures are fixed points of the full header scrub, `system-prompt.golden.md` exists exactly beside pinning fixtures, and each class has one pin. Live, every `request/header` produced by a parent, spawn child, fork child, initial request, or resume must match both halves of its class's pin after volatile-value normalization. A header without a string prompt or any `request/header-delta` fails loud because the two static pin artifacts cannot represent it.
+Guards make the split self-enforcing. On disk, every `session*.jsonl` is a fixed point of both prompt and schema scrubbers, only non-pinning fixtures must be fixed points of the full header scrub, both sidecars exist exactly beside pinning fixtures in canonical newline-terminated formats, and each class has one pin. Live, every `request/header` produced by a parent, spawn child, fork child, initial request, or resume must match the reconstructed pin after volatile-value normalization; the pinning run's prompt and schema deltas must also match their sidecars. A header without a string prompt, without an array-valued tool list, or with an undeclared `request/header-delta` fails loud.
 
 One pin covers the whole suite because every session — parent, spawn child, fork child — composes the identical tool list and the identical prompt modulo cwd, and the uniformity guard fails the suite the moment that stops holding. If header composition ever becomes session-dependent by design (a restricted subagent toolset, say), the divergent shape gets its own pinning scenario.
 
@@ -21,13 +21,13 @@ One pin covers the whole suite because every session — parent, spawn child, fo
 - **Re-record or hand-edit every fixture per change** — preserves exact headers but buries behavioral diffs under duplicated prompt and schema content.
 - **Scrub at compare time only, keeping fixtures raw** — lets compares pass while committed fixtures retain stale duplicate content and rewrite wholesale on the next recording. Stored tokens state honestly what each JSONL does not pin.
 - **Scrub everywhere, pin nowhere** — loses the only end-to-end record of the composed header as actually sent (prompt assembly, registered-tool order, full schemas). The generated tool catalog documents each tool in isolation; only a real fixture pins the composed set.
-- **Keep the one full pin entirely in JSONL** — removes suite-wide duplication but leaves system-prompt changes as an escaped one-line diff entangled with the tool list. Markdown gives prompt prose its natural review format without weakening the header assertion.
+- **Keep the one full pin entirely in JSONL** — removes suite-wide duplication but leaves prompt and schema changes as one escaped line. Markdown and structured JSON give each surface its natural review format without weakening the reconstructed-header assertion.
 - **Slim the session log itself (log a content digest, store the header elsewhere)** — violates the reconstructability contract: the product log must reproduce each request bit-for-bit ([reconstructable-requests RFC](../architecture/2026-07-05-reconstructable-requests.md)). Header bulk is a test-artifact concern, solved in test normalization; the live log is untouched.
 
 ## Verification
 
-The suite replays every scenario against the split pins. Unit coverage exercises both scrub levels, Markdown formatting, record/refresh regeneration, normalized prompt extraction, fixed-point enforcement, required-file symmetry, header uniformity, and delta rejection.
+The suite replays every scenario against the split pins. Unit coverage exercises the independent and full scrubbers, both sidecar formats, record/refresh regeneration, normalized prompt/schema extraction, fixed-point enforcement, required-file symmetry, reconstructed-header uniformity, and delta rejection.
 
 ## Consequences
 
-A system-prompt change produces a normal line-oriented Markdown diff in one file per affected composition class; a tool-description change produces one pinned JSONL line per class; ordinary behavioral fixtures remain untouched. Session fixtures display tokens for omitted content, and the live uniformity guard makes each split pin authoritative for every session in its class. The pinning scenario carries one extra generated artifact whose terminal newline is canonicalized for repository hygiene.
+A system-prompt change produces a line-oriented Markdown diff in one file per affected composition class; a tool-description change produces a structured JSON diff in one file per class; ordinary behavioral fixtures remain untouched. Session fixtures display tokens for omitted content, and the live uniformity guard makes each split pin authoritative for every session in its class. Each pinning scenario carries two generated, newline-canonicalized sidecars.
diff --git a/examples/acp-agent/README.md b/examples/acp-agent/README.md
index 8f611b7d67..7e796d4de7 100644
--- a/examples/acp-agent/README.md
+++ b/examples/acp-agent/README.md
@@ -7,7 +7,7 @@ pnpm run demo:acp          # needs DEEPSEEK_API_KEY (repo-root .env or env)
 pnpm run demo:code-mode acp   # the same server in Code Mode: one wire tool, run_code
 ```
 
-The leaf config loads the ACP app, DeepSeek adapter, sandboxed bash, approval and permission services, model-facing tools, and repeat guard. The app bundles the agent spine, JSONL persistence, and bridge, creates agents on `session/new`, and keeps stdout logger-free. [`code-mode.cordis.yml`](code-mode.cordis.yml) overlays the same tree with `run_code` and its generated TypeScript SDK; see [Code Mode](../../packages/core/tools/README.md#code-mode).
+The leaf config loads the ACP app, DeepSeek adapter, sandboxed bash, approval and permission services, model-facing tools, and repeat guard. The app bundles the agent spine, JSONL persistence, and bridge, creates agents on `session/new`, and keeps stdout logger-free. [`fs.cordis.yml`](fs.cordis.yml) adds the unconfined in-process filesystem stack for its dedicated scenarios; [`code-mode.cordis.yml`](code-mode.cordis.yml) adds `run_code` and its generated TypeScript SDK. See [Code Mode](../../packages/core/tools/README.md#code-mode).
 
 ## stdout is the protocol
 
@@ -39,11 +39,11 @@ This example hosts the ACP snapshot suite. `dsh-llm-replay` reconstructs model s
 
 The default tree composes [`@deepseek-ai/dsh-sandbox-local`](../../packages/sandbox/sandbox-local/), [`@deepseek-ai/dsh-bash-sandbox`](../../packages/bash/bash-sandbox/), [`@deepseek-ai/dsh-user-approval`](../../packages/ui/user-approval/), and [`@deepseek-ai/dsh-permission`](../../packages/ui/permission/). Bash starts in `workspace-write`; a denied operation returns a structured marker, and a retry with `sandbox_permissions` plus `justification` becomes a one-shot `session/request_permission` prompt in the editor. "Allow once" runs exactly that retry under the wider mode ([sandbox RFC § Escalation](../../docs/rfc/implemented/feature/2026-07-06-sandbox.md)).
 
-- **One session config option is live**: a capable client shows one `Permissions` select. `workspace-write` means workspace-confined bash plus `ask`; `danger-full-access` means unconfined file access plus `never`. Switching writes one `permission/preset` event through to the sandbox-mode and approval-policy events, and `session/load` reports the resumed value.
+- **One session config option is live**: a capable client shows one `Permissions` select. `workspace-write` means workspace-confined bash plus `ask`; `danger-full-access` means unconfined bash plus `never`. Switching writes one `permission/preset` event through to the sandbox-mode and approval-policy events, and `session/load` reports the resumed value.
 - **Every approval is one-shot**: the choices are `Allow once` and `Reject`; a dismissal, rejection, missing editor, or unavailable runner fails closed.
 - **The boundary is bash-only and config-fixed today**: in-process filesystem tools are omitted from the confined live default, while the sandbox workspace root remains the server's launch directory.
 
-`tests/escalation.e2e.ts` boots this default tree keyless, drives the permission select, and—with a key and usable runner—proves both approval outcomes against the filesystem. The snapshot suite uses the same tree: snapshot mode starts at `danger-full-access` so established fixtures remain runner-independent, while the permission-switching and escalation inputs explicitly select `workspace-write` before exercising that policy path. No fixture pins a real denial because kernel error text is backend-specific; real confinement remains covered by the sandbox packages' kernel e2e suites.
+`tests/escalation.e2e.ts` boots this default tree keyless, drives the permission select, and—with a key and usable runner—proves both approval outcomes against the filesystem. Most snapshots use that tree and start at `danger-full-access` so bash fixtures remain runner-independent; scenarios that call `read`, `write`, or `edit` use the fixed full-access fs overlay and a separate request-header pin. The permission-switching and escalation inputs select `workspace-write` before exercising the bash policy path. No fixture pins a real denial because kernel error text is backend-specific; real confinement remains covered by the sandbox packages' kernel e2e suites.
 
 ## MVP limitations
 
diff --git a/examples/acp-agent/composition.md b/examples/acp-agent/composition.md
index d5c3096666..b93b4cb1e2 100644
--- a/examples/acp-agent/composition.md
+++ b/examples/acp-agent/composition.md
@@ -45,12 +45,6 @@ flowchart LR
   cfg --> plugin_acp_tool_todo
   plugin_acp_repeat_tool_guard["repeat-tool-guard<br/>@deepseek-ai/dsh-repeat-tool-guard"]
   cfg --> plugin_acp_repeat_tool_guard
-  plugin_acp_fs_local["fs-local<br/>@deepseek-ai/dsh-fs-local"]
-  cfg --> plugin_acp_fs_local
-  plugin_acp_fs_policy["fs-policy<br/>@deepseek-ai/dsh-fs-policy"]
-  cfg --> plugin_acp_fs_policy
-  plugin_acp_tool_fs["tool-fs<br/>@deepseek-ai/dsh-tool-fs"]
-  cfg --> plugin_acp_tool_fs
   plugin_acp_hooks_claude["hooks-claude<br/>@deepseek-ai/dsh-hooks-claude"]
   cfg --> plugin_acp_hooks_claude
   plugin_acp_hooks_codex["hooks-codex<br/>@deepseek-ai/dsh-hooks-codex"]
@@ -74,9 +68,6 @@ flowchart LR
 | `tool-workflow` | `@deepseek-ai/dsh-tool-workflow` |
 | `tool-todo` | `@deepseek-ai/dsh-tool-todo` |
 | `repeat-tool-guard` | `@deepseek-ai/dsh-repeat-tool-guard` |
-| `fs-local` | `@deepseek-ai/dsh-fs-local` |
-| `fs-policy` | `@deepseek-ai/dsh-fs-policy` |
-| `tool-fs` | `@deepseek-ai/dsh-tool-fs` |
 | `hooks-claude` | `@deepseek-ai/dsh-hooks-claude` |
 | `hooks-codex` | `@deepseek-ai/dsh-hooks-codex` |
 
diff --git a/examples/acp-agent/cordis.yml b/examples/acp-agent/cordis.yml
index 5ad0493a1f..d309f15dfe 100644
--- a/examples/acp-agent/cordis.yml
+++ b/examples/acp-agent/cordis.yml
@@ -93,23 +93,6 @@
 - id: repeat-tool-guard
   name: '@deepseek-ai/dsh-repeat-tool-guard'
 
-# Filesystem tools do not ride the bash sandbox, so the confined default omits
-# them. Snapshots and explicit danger-full-access launches enable the local
-# provider, policy, and model-facing tools together.
-- id: fs-local
-  name: '@deepseek-ai/dsh-fs-local'
-  disabled: !!js "(process.env.DSH_PERMISSION_MODE ?? (process.env.DSH_SNAPSHOT === undefined ? 'workspace-write' : 'danger-full-access')) !== 'danger-full-access'"
-  config:
-    cwd: !!js process.cwd()
-
-- id: fs-policy
-  name: '@deepseek-ai/dsh-fs-policy'
-  disabled: !!js "(process.env.DSH_PERMISSION_MODE ?? (process.env.DSH_SNAPSHOT === undefined ? 'workspace-write' : 'danger-full-access')) !== 'danger-full-access'"
-
-- id: tool-fs
-  name: '@deepseek-ai/dsh-tool-fs'
-  disabled: !!js "(process.env.DSH_PERMISSION_MODE ?? (process.env.DSH_SNAPSHOT === undefined ? 'workspace-write' : 'danger-full-access')) !== 'danger-full-access'"
-
 # `configPath` is read once at load and resolves from the server launch cwd, not
 # `session/new.cwd`; one `hooks.json` therefore applies to every session and a
 # project-local file is not discovered. Missing config registers nothing. Hook
diff --git a/examples/acp-agent/fs.cordis.snapshot.yml b/examples/acp-agent/fs.cordis.snapshot.yml
new file mode 100644
index 0000000000..53f2d677e2
--- /dev/null
+++ b/examples/acp-agent/fs.cordis.snapshot.yml
@@ -0,0 +1,21 @@
+# Keyless filesystem snapshots apply the filesystem and replay overlays directly
+# because include patches cannot target entries behind a nested include.
+- id: base
+  name: '@cordisjs/plugin-include'
+  config:
+    path: ./cordis.yml
+    patches:
+      - id: llm-deepseek
+        name: '@deepseek-ai/dsh-llm-deepseek'
+        disabled: true
+      - insert:
+          - id: fs-local
+            name: '@deepseek-ai/dsh-fs-local'
+            config:
+              cwd: !!js process.cwd()
+          - id: fs-policy
+            name: '@deepseek-ai/dsh-fs-policy'
+          - id: tool-fs
+            name: '@deepseek-ai/dsh-tool-fs'
+          - id: llm-replay
+            name: '@deepseek-ai/dsh-llm-replay'
diff --git a/examples/acp-agent/fs.cordis.yml b/examples/acp-agent/fs.cordis.yml
new file mode 100644
index 0000000000..b60c26f96d
--- /dev/null
+++ b/examples/acp-agent/fs.cordis.yml
@@ -0,0 +1,17 @@
+# Filesystem snapshots need the in-process local provider, policy gate, and
+# model-facing tools. This explicit overlay is always full-access: the session
+# permission preset controls bash only and cannot confine or unmount these plugins.
+- id: base
+  name: '@cordisjs/plugin-include'
+  config:
+    path: ./cordis.yml
+    patches:
+      - insert:
+          - id: fs-local
+            name: '@deepseek-ai/dsh-fs-local'
+            config:
+              cwd: !!js process.cwd()
+          - id: fs-policy
+            name: '@deepseek-ai/dsh-fs-policy'
+          - id: tool-fs
+            name: '@deepseek-ai/dsh-tool-fs'
diff --git a/examples/acp-agent/tests/acp.snapshot.ts b/examples/acp-agent/tests/acp.snapshot.ts
index 64c55fa179..0d29f7b5ce 100644
--- a/examples/acp-agent/tests/acp.snapshot.ts
+++ b/examples/acp-agent/tests/acp.snapshot.ts
@@ -27,6 +27,7 @@ const AGENT = {
 const CODE_MODE_CONFIG = fileURLToPath(new URL('../code-mode.cordis.yml', import.meta.url))
 const BOTH_MODE_CONFIG = fileURLToPath(new URL('../both-mode.cordis.yml', import.meta.url))
 const ADVANCED_CONFIG = fileURLToPath(new URL('../advanced.cordis.yml', import.meta.url))
+const FS_CONFIG = fileURLToPath(new URL('../fs.cordis.yml', import.meta.url))
 
 function snapshotModeFromEnv(value: string | undefined): SnapshotSuiteOptions['mode'] {
   switch (value) {
@@ -47,19 +48,19 @@ const SCENARIOS: Scenario[] = [
   { name: 'handshake', hasModelTurn: false, recorded: false },
   { name: 'reject-extra-dirs', hasModelTurn: false, recorded: false },
   // text-turn is the pinned-header scenario: the minimal single text turn.
-  // Its system-prompt.golden.md and JSONL tool list pin the composed header.
+  // Its prompt and tool-schema sidecars pin the composed header.
   { name: 'text-turn', hasModelTurn: true, recorded: true, pinsHeader: true },
   { name: 'tool-call-turn', hasModelTurn: true, recorded: true },
   { name: 'fs-terminal-card', hasModelTurn: true, recorded: true },
   { name: 'todo-plan', hasModelTurn: true, recorded: true },
   { name: 'skill-load', hasModelTurn: true, recorded: false, pinsHeader: true, headerClass: 'skill' },
-  { name: 'workspace-edit', hasModelTurn: true, recorded: true },
-  { name: 'fs-read', hasModelTurn: true, recorded: true },
-  { name: 'fs-write', hasModelTurn: true, recorded: true },
-  { name: 'fs-edit', hasModelTurn: true, recorded: true },
-  { name: 'fs-write-overwrite', hasModelTurn: true, recorded: true },
-  { name: 'fs-read-window', hasModelTurn: true, recorded: true },
-  { name: 'fs-policy-reject', hasModelTurn: true, recorded: true },
+  { name: 'workspace-edit', hasModelTurn: true, recorded: true, pinsHeader: true, headerClass: 'fs', configPath: FS_CONFIG },
+  { name: 'fs-read', hasModelTurn: true, recorded: true, headerClass: 'fs', configPath: FS_CONFIG },
+  { name: 'fs-write', hasModelTurn: true, recorded: true, headerClass: 'fs', configPath: FS_CONFIG },
+  { name: 'fs-edit', hasModelTurn: true, recorded: true, headerClass: 'fs', configPath: FS_CONFIG },
+  { name: 'fs-write-overwrite', hasModelTurn: true, recorded: true, headerClass: 'fs', configPath: FS_CONFIG },
+  { name: 'fs-read-window', hasModelTurn: true, recorded: true, headerClass: 'fs', configPath: FS_CONFIG },
+  { name: 'fs-policy-reject', hasModelTurn: true, recorded: true, headerClass: 'fs', configPath: FS_CONFIG },
   { name: 'multi-turn', hasModelTurn: true, recorded: true },
   { name: 'error-finish', hasModelTurn: true, recorded: false, overridden: true },
   // Keyless, authored (like error-finish/cancel): deterministically forcing a
diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl
index de08513c68..25a6f76411 100644
--- a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl
+++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl
@@ -2,7 +2,7 @@
 {"type":"turn/start","seq":0,"time":1783957884563,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
 {"type":"user/message","seq":1,"time":1783957884563,"data":{"content":[{"type":"text","text":"Reply with exactly DIRECT_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"}
 {"type":"step/start","seq":2,"time":1783957884564,"data":{"turn":1,"step":1}}
-{"type":"request/header","seq":3,"time":1783957884564,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:<id>]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return <value>` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise<any>` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise<any[]>` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise<any[]>` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return <json-value>`)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}}
+{"type":"request/header","seq":3,"time":1783957884564,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
 {"type":"assistant/chunk","seq":4,"time":1783950001005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
 {"type":"assistant/chunk","seq":5,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"DIRECT_CHILD_OK"}}}
 {"type":"assistant/chunk","seq":6,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DIRECT_CHILD_OK"}}}}
diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl
index eae3106743..45d9043a4a 100644
--- a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl
+++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl
@@ -2,7 +2,7 @@
 {"type":"turn/start","seq":0,"time":1783957884700,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
 {"type":"user/message","seq":1,"time":1783957884700,"data":{"content":[{"type":"text","text":"Reply with exactly WORKFLOW_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"}
 {"type":"step/start","seq":2,"time":1783957884700,"data":{"turn":1,"step":1}}
-{"type":"request/header","seq":3,"time":1783957884701,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:<id>]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return <value>` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise<any>` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise<any[]>` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise<any[]>` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return <json-value>`)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}}
+{"type":"request/header","seq":3,"time":1783957884701,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
 {"type":"assistant/chunk","seq":4,"time":1783950002005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
 {"type":"assistant/chunk","seq":5,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"WORKFLOW_CHILD_OK"}}}
 {"type":"assistant/chunk","seq":6,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"WORKFLOW_CHILD_OK"}}}}
diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl
index 52e08e5b10..5def904acd 100644
--- a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl
+++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl
@@ -2,7 +2,7 @@
 {"type":"turn/start","seq":0,"time":1783957884479,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
 {"type":"user/message","seq":1,"time":1783957884479,"data":{"content":[{"type":"text","text":"Run this advanced flow exactly once: mount a no-op Cordis plugin named snapshot-marker; use run_code to inspect the live dynamic mounts through tools.cordis_inspect; delegate once to a direct spawn child; run one workflow that delegates to another spawn child; unmount dyn-1; then reply with exactly ADVANCED_ACP_OK."}],"source":{"kind":"user"}},"surfaceOp":"append"}
 {"type":"step/start","seq":2,"time":1783957884486,"data":{"turn":1,"step":1}}
-{"type":"request/header","seq":3,"time":1783957884486,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:<id>]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return <value>` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise<any>` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise<any[]>` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise<any[]>` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return <json-value>`)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}}
+{"type":"request/header","seq":3,"time":1783957884486,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
 {"type":"assistant/chunk","seq":4,"time":1783950000005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
 {"type":"assistant/chunk","seq":5,"time":1783950000006,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-mount","name":"cordis_mount","argumentsDelta":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}}
 {"type":"assistant/chunk","seq":6,"time":1783950000007,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}}}
diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.golden.json b/examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.golden.json
new file mode 100644
index 0000000000..ad7f782878
--- /dev/null
+++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.golden.json
@@ -0,0 +1,318 @@
+{
+  "initial": [
+    {
+      "name": "bash",
+      "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "command": {
+            "type": "string",
+            "description": "The bash command to execute."
+          },
+          "description": {
+            "type": "string",
+            "description": "Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."
+          },
+          "timeoutMs": {
+            "type": "number",
+            "description": "Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."
+          },
+          "workdir": {
+            "type": "string",
+            "description": "Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."
+          },
+          "run_in_background": {
+            "type": "boolean",
+            "description": "Run in the background and return a task id immediately. No timeout applies."
+          },
+          "sandbox_permissions": {
+            "type": "string",
+            "description": "The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.",
+            "enum": [
+              "workspace-write",
+              "danger-full-access"
+            ]
+          },
+          "justification": {
+            "type": "string",
+            "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."
+          }
+        },
+        "required": [
+          "command",
+          "description"
+        ]
+      }
+    },
+    {
+      "name": "bash_kill",
+      "description": "Ask the executor to kill a running background bash task by task id.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "task_id": {
+            "type": "string",
+            "description": "Task id returned by the bash tool."
+          }
+        },
+        "required": [
+          "task_id"
+        ]
+      }
+    },
+    {
+      "name": "bash_output",
+      "description": "Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "task_id": {
+            "type": "string",
+            "description": "Task id returned by the bash tool."
+          }
+        },
+        "required": [
+          "task_id"
+        ]
+      }
+    },
+    {
+      "name": "cordis_inspect",
+      "description": "Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "what": {
+            "type": "string",
+            "description": "Limit the report to one section. Omit for all sections.",
+            "enum": [
+              "services",
+              "plugins",
+              "tools",
+              "dynamic",
+              "api",
+              "events"
+            ]
+          }
+        }
+      }
+    },
+    {
+      "name": "cordis_mount",
+      "description": "Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:<id>]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "code": {
+            "type": "string",
+            "description": "Body of an async JS function; must `return` the plugin to mount."
+          }
+        },
+        "required": [
+          "code"
+        ]
+      }
+    },
+    {
+      "name": "cordis_unmount",
+      "description": "Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "type": "string",
+            "description": "The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."
+          }
+        },
+        "required": [
+          "id"
+        ]
+      }
+    },
+    {
+      "name": "run_code",
+      "description": "Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "code": {
+            "type": "string",
+            "description": "The program: the body of an async TypeScript function."
+          }
+        },
+        "required": [
+          "code"
+        ]
+      }
+    },
+    {
+      "name": "skill",
+      "description": "Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "name": {
+            "type": "string",
+            "description": "The exact skill name from the available skills list."
+          }
+        },
+        "required": [
+          "name"
+        ]
+      }
+    },
+    {
+      "name": "subagent",
+      "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "description": {
+            "type": "string",
+            "description": "A short (3-5 word) description of the delegated task, for display."
+          },
+          "prompt": {
+            "type": "string",
+            "description": "The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."
+          }
+        },
+        "required": [
+          "description",
+          "prompt"
+        ]
+      }
+    },
+    {
+      "name": "subagent_fork",
+      "description": "Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "description": {
+            "type": "string",
+            "description": "A short (3-5 word) description of the delegated task, for display."
+          },
+          "prompt": {
+            "type": "string",
+            "description": "The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."
+          }
+        },
+        "required": [
+          "description",
+          "prompt"
+        ]
+      }
+    },
+    {
+      "name": "todo_write",
+      "description": "Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "todos": {
+            "type": "array",
+            "description": "The COMPLETE task list, replacing any previous list.",
+            "items": {
+              "type": "object",
+              "properties": {
+                "content": {
+                  "type": "string",
+                  "description": "What the task is — a short imperative line."
+                },
+                "status": {
+                  "type": "string",
+                  "description": "pending (not started) | in_progress (now) | completed (done).",
+                  "enum": [
+                    "pending",
+                    "in_progress",
+                    "completed"
+                  ]
+                }
+              },
+              "required": [
+                "content",
+                "status"
+              ]
+            }
+          }
+        },
+        "required": [
+          "todos"
+        ]
+      }
+    },
+    {
+      "name": "workflow",
+      "description": "Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return <value>` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise<any>` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise<any[]>` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise<any[]>` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "script": {
+            "type": "string",
+            "description": "The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return <json-value>`)."
+          },
+          "meta": {
+            "type": "object",
+            "description": "The workflow identity block (plain JSON — never code).",
+            "properties": {
+              "name": {
+                "type": "string",
+                "description": "Short kebab-case workflow name."
+              },
+              "description": {
+                "type": "string",
+                "description": "One-line description of what the workflow does."
+              },
+              "whenToUse": {
+                "type": "string",
+                "description": "Optional guidance on when this workflow applies."
+              },
+              "phases": {
+                "type": "array",
+                "description": "Optional phase declarations matched by phase() calls.",
+                "items": {
+                  "type": "object",
+                  "properties": {
+                    "title": {
+                      "type": "string",
+                      "description": "The phase title phase() calls match by exact string."
+                    },
+                    "detail": {
+                      "type": "string",
+                      "description": "Optional one-line description of the phase."
+                    },
+                    "provider": {
+                      "type": "string",
+                      "description": "Optional provider override this phase is expected to use."
+                    },
+                    "model": {
+                      "type": "string",
+                      "description": "Optional model override this phase is expected to use."
+                    }
+                  },
+                  "required": [
+                    "title"
+                  ]
+                }
+              }
+            },
+            "required": [
+              "name",
+              "description"
+            ]
+          },
+          "args": {
+            "type": "object",
+            "description": "Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."
+          }
+        },
+        "required": [
+          "script",
+          "meta"
+        ]
+      }
+    }
+  ],
+  "deltas": []
+}
diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl b/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl
index 25ade25a81..98aadb2b9c 100644
--- a/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl
+++ b/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl
@@ -2,7 +2,7 @@
 {"type":"turn/start","seq":0,"time":1783611774323,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
 {"type":"user/message","seq":1,"time":1783611774323,"data":{"content":[{"type":"text","text":"Call the run_code tool (NOT the native bash tool directly) with a program that runs exactly `echo BOTH_OK` via tools.bash and returns its output. Then reply with that output only and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"}
 {"type":"step/start","seq":2,"time":1783611774324,"data":{"turn":1,"step":1}}
-{"type":"request/header","seq":3,"time":1783611774325,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return <value>` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise<any>` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise<any[]>` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise<any[]>` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return <json-value>`)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}}
+{"type":"request/header","seq":3,"time":1783611774325,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
 {"type":"assistant/chunk","seq":4,"time":1783611774792,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
 {"type":"assistant/chunk","seq":5,"time":1783611774792,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}}
 {"type":"assistant/chunk","seq":6,"time":1783611774879,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}}
diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/tool-schemas.golden.json b/examples/acp-agent/tests/snapshots/both-mode-turn/tool-schemas.golden.json
new file mode 100644
index 0000000000..aa8c986a84
--- /dev/null
+++ b/examples/acp-agent/tests/snapshots/both-mode-turn/tool-schemas.golden.json
@@ -0,0 +1,265 @@
+{
+  "initial": [
+    {
+      "name": "bash",
+      "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "command": {
+            "type": "string",
+            "description": "The bash command to execute."
+          },
+          "description": {
+            "type": "string",
+            "description": "Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."
+          },
+          "timeoutMs": {
+            "type": "number",
+            "description": "Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."
+          },
+          "workdir": {
+            "type": "string",
+            "description": "Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."
+          },
+          "run_in_background": {
+            "type": "boolean",
+            "description": "Run in the background and return a task id immediately. No timeout applies."
+          },
+          "sandbox_permissions": {
+            "type": "string",
+            "description": "The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.",
+            "enum": [
+              "workspace-write",
+              "danger-full-access"
+            ]
+          },
+          "justification": {
+            "type": "string",
+            "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."
+          }
+        },
+        "required": [
+          "command",
+          "description"
+        ]
+      }
+    },
+    {
+      "name": "bash_kill",
+      "description": "Ask the executor to kill a running background bash task by task id.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "task_id": {
+            "type": "string",
+            "description": "Task id returned by the bash tool."
+          }
+        },
+        "required": [
+          "task_id"
+        ]
+      }
+    },
+    {
+      "name": "bash_output",
+      "description": "Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "task_id": {
+            "type": "string",
+            "description": "Task id returned by the bash tool."
+          }
+        },
+        "required": [
+          "task_id"
+        ]
+      }
+    },
+    {
+      "name": "run_code",
+      "description": "Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "code": {
+            "type": "string",
+            "description": "The program: the body of an async TypeScript function."
+          }
+        },
+        "required": [
+          "code"
+        ]
+      }
+    },
+    {
+      "name": "skill",
+      "description": "Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "name": {
+            "type": "string",
+            "description": "The exact skill name from the available skills list."
+          }
+        },
+        "required": [
+          "name"
+        ]
+      }
+    },
+    {
+      "name": "subagent",
+      "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "description": {
+            "type": "string",
+            "description": "A short (3-5 word) description of the delegated task, for display."
+          },
+          "prompt": {
+            "type": "string",
+            "description": "The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."
+          }
+        },
+        "required": [
+          "description",
+          "prompt"
+        ]
+      }
+    },
+    {
+      "name": "subagent_fork",
+      "description": "Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "description": {
+            "type": "string",
+            "description": "A short (3-5 word) description of the delegated task, for display."
+          },
+          "prompt": {
+            "type": "string",
+            "description": "The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."
+          }
+        },
+        "required": [
+          "description",
+          "prompt"
+        ]
+      }
+    },
+    {
+      "name": "todo_write",
+      "description": "Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "todos": {
+            "type": "array",
+            "description": "The COMPLETE task list, replacing any previous list.",
+            "items": {
+              "type": "object",
+              "properties": {
+                "content": {
+                  "type": "string",
+                  "description": "What the task is — a short imperative line."
+                },
+                "status": {
+                  "type": "string",
+                  "description": "pending (not started) | in_progress (now) | completed (done).",
+                  "enum": [
+                    "pending",
+                    "in_progress",
+                    "completed"
+                  ]
+                }
+              },
+              "required": [
+                "content",
+                "status"
+              ]
+            }
+          }
+        },
+        "required": [
+          "todos"
+        ]
+      }
+    },
+    {
+      "name": "workflow",
+      "description": "Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return <value>` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise<any>` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise<any[]>` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise<any[]>` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "script": {
+            "type": "string",
+            "description": "The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return <json-value>`)."
+          },
+          "meta": {
+            "type": "object",
+            "description": "The workflow identity block (plain JSON — never code).",
+            "properties": {
+              "name": {
+                "type": "string",
+                "description": "Short kebab-case workflow name."
+              },
+              "description": {
+                "type": "string",
+                "description": "One-line description of what the workflow does."
+              },
+              "whenToUse": {
+                "type": "string",
+                "description": "Optional guidance on when this workflow applies."
+              },
+              "phases": {
+                "type": "array",
+                "description": "Optional phase declarations matched by phase() calls.",
+                "items": {
+                  "type": "object",
+                  "properties": {
+                    "title": {
+                      "type": "string",
+                      "description": "The phase title phase() calls match by exact string."
+                    },
+                    "detail": {
+                      "type": "string",
+                      "description": "Optional one-line description of the phase."
+                    },
+                    "provider": {
+                      "type": "string",
+                      "description": "Optional provider override this phase is expected to use."
+                    },
+                    "model": {
+                      "type": "string",
+                      "description": "Optional model override this phase is expected to use."
+                    }
+                  },
+                  "required": [
+                    "title"
+                  ]
+                }
+              }
+            },
+            "required": [
+              "name",
+              "description"
+            ]
+          },
+          "args": {
+            "type": "object",
+            "description": "Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."
+          }
+        },
+        "required": [
+          "script",
+          "meta"
+        ]
+      }
+    }
+  ],
+  "deltas": []
+}
diff --git a/examples/acp-agent/tests/snapshots/code-mode-turn/session.jsonl b/examples/acp-agent/tests/snapshots/code-mode-turn/session.jsonl
index deb4b7e136..4a72d3944b 100644
--- a/examples/acp-agent/tests/snapshots/code-mode-turn/session.jsonl
+++ b/examples/acp-agent/tests/snapshots/code-mode-turn/session.jsonl
@@ -2,7 +2,7 @@
 {"type":"turn/start","seq":0,"time":1783611771394,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
 {"type":"user/message","seq":1,"time":1783611771394,"data":{"content":[{"type":"text","text":"Using ONE run_code program: call the bash tool twice — exactly `echo CODE_ONE` then exactly `echo CODE_TWO` — and return the two outputs joined with a plus sign. Then reply with that joined string only and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"}
 {"type":"step/start","seq":2,"time":1783611771396,"data":{"turn":1,"step":1}}
-{"type":"request/header","seq":3,"time":1783611771396,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}}]},"reason":"initial"}}
+{"type":"request/header","seq":3,"time":1783611771396,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
 {"type":"assistant/chunk","seq":4,"time":1783611771869,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
 {"type":"assistant/chunk","seq":5,"time":1783611771869,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}}
 {"type":"assistant/chunk","seq":6,"time":1783611771978,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}}
diff --git a/examples/acp-agent/tests/snapshots/code-mode-turn/tool-schemas.golden.json b/examples/acp-agent/tests/snapshots/code-mode-turn/tool-schemas.golden.json
new file mode 100644
index 0000000000..61875ceb85
--- /dev/null
+++ b/examples/acp-agent/tests/snapshots/code-mode-turn/tool-schemas.golden.json
@@ -0,0 +1,21 @@
+{
+  "initial": [
+    {
+      "name": "run_code",
+      "description": "Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "code": {
+            "type": "string",
+            "description": "The program: the body of an async TypeScript function."
+          }
+        },
+        "required": [
+          "code"
+        ]
+      }
+    }
+  ],
+  "deltas": []
+}
diff --git a/examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl b/examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl
index da999eb947..6f96feddea 100644
--- a/examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl
+++ b/examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl
@@ -131,8 +131,8 @@
 {"type":"assistant/chunk","seq":129,"time":1783962245385,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
 {"type":"assistant/message","seq":130,"time":1783962245385,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a command with sandbox_permissions set to danger-full-access, no prior run needed, justified as instructed."},{"type":"tool-call","id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write file outside workspace and verify\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":1501,"outputTokens":174,"cacheReadTokens":0,"reasoningTokens":28}},"sourceEventSeqs":[7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129],"surfaceOp":"append"}
 {"type":"tool/call","seq":131,"time":1783962245385,"data":{"turn":1,"step":1,"callId":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write file outside workspace and verify\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}}
-{"type":"approval/asked","seq":132,"time":1783962245386,"data":{"id":"5d298f92-ced6-4fa0-ae01-cd0660b29f58","toolName":"bash","callId":"call_00_d0sAHpJ9mYOJi0z7KNy30441","reason":"escalate sandbox to danger-full-access: the user asked to write a file outside the workspace"}}
-{"type":"approval/decided","seq":133,"time":1783962245387,"data":{"id":"5d298f92-ced6-4fa0-ae01-cd0660b29f58","outcome":"allowed-once"}}
+{"type":"approval/asked","seq":132,"time":1783962245386,"data":{"id":"1a62141e-6b8b-46e9-b1ec-b1f316c5d143","toolName":"bash","callId":"call_00_d0sAHpJ9mYOJi0z7KNy30441","reason":"escalate sandbox to danger-full-access: the user asked to write a file outside the workspace"}}
+{"type":"approval/decided","seq":133,"time":1783962245387,"data":{"id":"1a62141e-6b8b-46e9-b1ec-b1f316c5d143","outcome":"allowed-once"}}
 {"type":"tool/result","seq":134,"time":1783962245399,"data":{"turn":1,"step":1,"callId":"call_00_d0sAHpJ9mYOJi0z7KNy30441","content":[{"type":"text","text":"escalated\n"}],"isError":false},"sourceEventSeqs":[131],"surfaceOp":"append"}
 {"type":"step/end","seq":135,"time":1783962245400,"data":{"turn":1,"step":1}}
 {"type":"step/start","seq":136,"time":1783962245400,"data":{"turn":1,"step":2}}
diff --git a/examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl b/examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl
index 657127b8f1..020a243387 100644
--- a/examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl
+++ b/examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl
@@ -155,8 +155,8 @@
 {"type":"assistant/chunk","seq":153,"time":1783962246274,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
 {"type":"assistant/message","seq":154,"time":1783962246274,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a specific command with `sandbox_permissions` set to `danger-full-access` and a specific justification. They explicitly said NOT to run it without sandbox_permissions first. Let me do exactly that."},{"type":"tool-call","id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write to /tmp and verify, then clean up\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":1509,"outputTokens":198,"cacheReadTokens":0,"reasoningTokens":48}},"sourceEventSeqs":[7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153],"surfaceOp":"append"}
 {"type":"tool/call","seq":155,"time":1783962246274,"data":{"turn":1,"step":1,"callId":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write to /tmp and verify, then clean up\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}}
-{"type":"approval/asked","seq":156,"time":1783962246275,"data":{"id":"12cac992-89a6-4bbe-9d33-3254f4f13c7a","toolName":"bash","callId":"call_00_WB1vnPomi8yr6MlcFKTj7912","reason":"escalate sandbox to danger-full-access: the user asked to write a file outside the workspace"}}
-{"type":"approval/decided","seq":157,"time":1783962246275,"data":{"id":"12cac992-89a6-4bbe-9d33-3254f4f13c7a","outcome":"rejected"}}
+{"type":"approval/asked","seq":156,"time":1783962246275,"data":{"id":"0d39ea96-412a-426d-a9dc-c7ff3ec8ddf6","toolName":"bash","callId":"call_00_WB1vnPomi8yr6MlcFKTj7912","reason":"escalate sandbox to danger-full-access: the user asked to write a file outside the workspace"}}
+{"type":"approval/decided","seq":157,"time":1783962246275,"data":{"id":"0d39ea96-412a-426d-a9dc-c7ff3ec8ddf6","outcome":"rejected"}}
 {"type":"tool/result","seq":158,"time":1783962246275,"data":{"turn":1,"step":1,"callId":"call_00_WB1vnPomi8yr6MlcFKTj7912","content":[{"type":"text","text":"Error: the user rejected escalating this command to \"danger-full-access\""}],"isError":true},"sourceEventSeqs":[155],"surfaceOp":"append"}
 {"type":"step/end","seq":159,"time":1783962246276,"data":{"turn":1,"step":1}}
 {"type":"step/start","seq":160,"time":1783962246276,"data":{"turn":1,"step":2}}
diff --git a/examples/acp-agent/tests/snapshots/fs-edit/session.jsonl b/examples/acp-agent/tests/snapshots/fs-edit/session.jsonl
index 9b4553fd46..00587e34c2 100644
--- a/examples/acp-agent/tests/snapshots/fs-edit/session.jsonl
+++ b/examples/acp-agent/tests/snapshots/fs-edit/session.jsonl
@@ -69,7 +69,7 @@
 {"type":"assistant/chunk","seq":67,"time":1783352086057,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
 {"type":"assistant/message","seq":68,"time":1783352086059,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to:\n1. Read config.txt in the current directory\n2. Use the edit tool to replace DEBUG with RELEASE\n3. Reply with exactly \"DONE\"\n\nLet me start by reading the file."},{"type":"tool-call","id":"call_00_S6krdIDHoSCGWv7WnXX97617","name":"read","arguments":"{\"file_path\": \"config.txt\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2900,"outputTokens":91,"cacheReadTokens":0,"reasoningTokens":46}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67],"surfaceOp":"append"}
 {"type":"tool/call","seq":69,"time":1783352086059,"data":{"turn":1,"step":1,"callId":"call_00_S6krdIDHoSCGWv7WnXX97617","name":"read","arguments":"{\"file_path\": \"config.txt\"}"}}
-{"type":"tool/result","seq":70,"time":1783352086065,"data":{"turn":1,"step":1,"callId":"call_00_S6krdIDHoSCGWv7WnXX97617","content":[{"type":"text","text":"Error: unknown tool \"read\""}],"isError":true,"error":{"name":"ToolNotFoundError","code":"UNKNOWN_TOOL"}},"sourceEventSeqs":[69],"surfaceOp":"append"}
+{"type":"tool/result","seq":70,"time":1783352086065,"data":{"turn":1,"step":1,"callId":"call_00_S6krdIDHoSCGWv7WnXX97617","content":[{"type":"text","text":"<path>/tmp/acp-snap-cwd-0BxHdV/config.txt</path>\n<type>file</type>\n<content>\n1: mode=DEBUG\n2: level=info\n\n(End of file - total 2 lines)\n</content>"}],"isError":false},"sourceEventSeqs":[69],"surfaceOp":"append"}
 {"type":"step/end","seq":71,"time":1783352086065,"data":{"turn":1,"step":1}}
 {"type":"step/start","seq":72,"time":1783352086066,"data":{"turn":1,"step":2}}
 {"type":"assistant/chunk","seq":73,"time":1783352086901,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
@@ -129,7 +129,7 @@
 {"type":"assistant/chunk","seq":127,"time":1783352087469,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
 {"type":"assistant/message","seq":128,"time":1783352087469,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"Now I need to replace \"DEBUG\" with \"RELEASE\" using the edit tool."},{"type":"tool-call","id":"call_00_vOytneZ0XpsLslEEJAxR6398","name":"edit","arguments":"{\"file_path\": \"config.txt\", \"old_string\": \"DEBUG\", \"new_string\": \"RELEASE\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":241,"outputTokens":98,"cacheReadTokens":2816,"reasoningTokens":18}},"sourceEventSeqs":[73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127],"surfaceOp":"append"}
 {"type":"tool/call","seq":129,"time":1783352087469,"data":{"turn":1,"step":2,"callId":"call_00_vOytneZ0XpsLslEEJAxR6398","name":"edit","arguments":"{\"file_path\": \"config.txt\", \"old_string\": \"DEBUG\", \"new_string\": \"RELEASE\"}"}}
-{"type":"tool/result","seq":130,"time":1783352087476,"data":{"turn":1,"step":2,"callId":"call_00_vOytneZ0XpsLslEEJAxR6398","content":[{"type":"text","text":"Error: unknown tool \"edit\""}],"isError":true,"error":{"name":"ToolNotFoundError","code":"UNKNOWN_TOOL"}},"sourceEventSeqs":[129],"surfaceOp":"append"}
+{"type":"tool/result","seq":130,"time":1783352087476,"data":{"turn":1,"step":2,"callId":"call_00_vOytneZ0XpsLslEEJAxR6398","content":[{"type":"text","text":"The file /tmp/acp-snap-cwd-0BxHdV/config.txt has been updated successfully."}],"isError":false,"meta":{"diffs":[{"path":"config.txt","oldText":"mode=DEBUG\nlevel=info","newText":"mode=RELEASE\nlevel=info"}]}},"sourceEventSeqs":[129],"surfaceOp":"append"}
 {"type":"step/end","seq":131,"time":1783352087477,"data":{"turn":1,"step":2}}
 {"type":"step/start","seq":132,"time":1783352087477,"data":{"turn":1,"step":3}}
 {"type":"assistant/chunk","seq":133,"time":1783352088286,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
diff --git a/examples/acp-agent/tests/snapshots/fs-edit/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-edit/stdout.golden.jsonl
index acc193ad1e..800d7d608a 100644
--- a/examples/acp-agent/tests/snapshots/fs-edit/stdout.golden.jsonl
+++ b/examples/acp-agent/tests/snapshots/fs-edit/stdout.golden.jsonl
@@ -46,8 +46,8 @@
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" file"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}}
-{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_S6krdIDHoSCGWv7WnXX97617","title":"read","kind":"other","status":"in_progress","rawInput":{"file_path":"config.txt"}}}}
-{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_S6krdIDHoSCGWv7WnXX97617","status":"failed","content":[{"type":"content","content":{"type":"text","text":"Error: unknown tool \"read\""}}]}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_S6krdIDHoSCGWv7WnXX97617","title":"Read config.txt","kind":"read","status":"in_progress","locations":[{"path":"config.txt","line":1}]}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_S6krdIDHoSCGWv7WnXX97617","status":"completed","content":[{"type":"content","content":{"type":"text","text":"<path>{{cwd}}/config.txt</path>\n<type>file</type>\n<content>\n1: mode=DEBUG\n2: level=info\n\n(End of file - total 2 lines)\n</content>"}}]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"Now"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" I"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" need"}}}}
@@ -66,8 +66,8 @@
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" edit"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" tool"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}}
-{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_vOytneZ0XpsLslEEJAxR6398","title":"edit","kind":"other","status":"in_progress","rawInput":{"file_path":"config.txt","old_string":"DEBUG","new_string":"RELEASE"}}}}
-{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_vOytneZ0XpsLslEEJAxR6398","status":"failed","content":[{"type":"content","content":{"type":"text","text":"Error: unknown tool \"edit\""}}]}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_vOytneZ0XpsLslEEJAxR6398","title":"Edit config.txt","kind":"edit","status":"in_progress","locations":[{"path":"config.txt"}],"content":[{"type":"diff","path":"config.txt","oldText":"DEBUG","newText":"RELEASE"}]}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_vOytneZ0XpsLslEEJAxR6398","status":"completed","content":[{"type":"diff","path":"config.txt","oldText":"mode=DEBUG\nlevel=info","newText":"mode=RELEASE\nlevel=info"}],"title":"Edit config.txt"}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"Done"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" The"}}}}
diff --git a/examples/acp-agent/tests/snapshots/fs-policy-reject/session.jsonl b/examples/acp-agent/tests/snapshots/fs-policy-reject/session.jsonl
index 092ef221a0..03a64d2e39 100644
--- a/examples/acp-agent/tests/snapshots/fs-policy-reject/session.jsonl
+++ b/examples/acp-agent/tests/snapshots/fs-policy-reject/session.jsonl
@@ -77,7 +77,7 @@
 {"type":"assistant/chunk","seq":75,"time":1783611703969,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
 {"type":"assistant/message","seq":76,"time":1783611703972,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to use the edit tool to replace \"blue\" with \"green\" in settings.txt without reading the file first, and then reply with just \"DONE\"."},{"type":"tool-call","id":"call_00_x0zlnXl5JOxLrAYL9y7P0119","name":"edit","arguments":"{\"file_path\": \"settings.txt\", \"old_string\": \"blue\", \"new_string\": \"green\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3132,"outputTokens":115,"cacheReadTokens":0,"reasoningTokens":36}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75],"surfaceOp":"append"}
 {"type":"tool/call","seq":77,"time":1783611703972,"data":{"turn":1,"step":1,"callId":"call_00_x0zlnXl5JOxLrAYL9y7P0119","name":"edit","arguments":"{\"file_path\": \"settings.txt\", \"old_string\": \"blue\", \"new_string\": \"green\"}"}}
-{"type":"tool/result","seq":78,"time":1783611703978,"data":{"turn":1,"step":1,"callId":"call_00_x0zlnXl5JOxLrAYL9y7P0119","content":[{"type":"text","text":"Error: unknown tool \"edit\""}],"isError":true,"error":{"name":"ToolNotFoundError","code":"UNKNOWN_TOOL"}},"sourceEventSeqs":[77],"surfaceOp":"append"}
+{"type":"tool/result","seq":78,"time":1783611703978,"data":{"turn":1,"step":1,"callId":"call_00_x0zlnXl5JOxLrAYL9y7P0119","content":[{"type":"text","text":"Error: edit requires reading \"/var/folders/2c/psb0_fmx7hbgz558xjt_f0l00000gn/T/acp-snap-cwd-QzoqnB/settings.txt\" first"}],"isError":true,"error":{"name":"FsError","code":"FS_NOT_OBSERVED"}},"sourceEventSeqs":[77],"surfaceOp":"append"}
 {"type":"step/end","seq":79,"time":1783611703978,"data":{"turn":1,"step":1}}
 {"type":"step/start","seq":80,"time":1783611703978,"data":{"turn":1,"step":2}}
 {"type":"assistant/chunk","seq":81,"time":1783611704825,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
@@ -144,7 +144,7 @@
 {"type":"assistant/chunk","seq":142,"time":1783611705572,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
 {"type":"assistant/message","seq":143,"time":1783611705573,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The edit tool requires reading the file first. The user said \"Do not read the file first\" but the tool's own constraints require reading. I need to follow the tool requirements. Let me read the file first."},{"type":"tool-call","id":"call_00_tfr0gdIclW92oIEgi7NF0891","name":"read","arguments":"{\"file_path\": \"settings.txt\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":235,"outputTokens":89,"cacheReadTokens":3072,"reasoningTokens":44}},"sourceEventSeqs":[81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142],"surfaceOp":"append"}
 {"type":"tool/call","seq":144,"time":1783611705573,"data":{"turn":1,"step":2,"callId":"call_00_tfr0gdIclW92oIEgi7NF0891","name":"read","arguments":"{\"file_path\": \"settings.txt\"}"}}
-{"type":"tool/result","seq":145,"time":1783611705579,"data":{"turn":1,"step":2,"callId":"call_00_tfr0gdIclW92oIEgi7NF0891","content":[{"type":"text","text":"Error: unknown tool \"read\""}],"isError":true,"error":{"name":"ToolNotFoundError","code":"UNKNOWN_TOOL"}},"sourceEventSeqs":[144],"surfaceOp":"append"}
+{"type":"tool/result","seq":145,"time":1783611705579,"data":{"turn":1,"step":2,"callId":"call_00_tfr0gdIclW92oIEgi7NF0891","content":[{"type":"text","text":"<path>/var/folders/2c/psb0_fmx7hbgz558xjt_f0l00000gn/T/acp-snap-cwd-QzoqnB/settings.txt</path>\n<type>file</type>\n<content>\n1: color: blue\n\n(End of file - total 1 lines)\n</content>"}],"isError":false},"sourceEventSeqs":[144],"surfaceOp":"append"}
 {"type":"step/end","seq":146,"time":1783611705579,"data":{"turn":1,"step":2}}
 {"type":"step/start","seq":147,"time":1783611705579,"data":{"turn":1,"step":3}}
 {"type":"assistant/chunk","seq":148,"time":1783611706200,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
@@ -225,7 +225,7 @@
 {"type":"assistant/chunk","seq":223,"time":1783611707096,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
 {"type":"assistant/message","seq":224,"time":1783611707097,"data":{"turn":1,"step":3,"content":[{"type":"reasoning","text":"The file contains \"color: blue\". I need to replace \"blue\" with \"green\". The edit tool said it requires reading first — now I've read it, so the edit should work."},{"type":"tool-call","id":"call_00_GVknJu2tksKkP4lALCwh0926","name":"edit","arguments":"{\"file_path\": \"settings.txt\", \"old_string\": \"blue\", \"new_string\": \"green\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":281,"outputTokens":119,"cacheReadTokens":3200,"reasoningTokens":40}},"sourceEventSeqs":[148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204,205,206,207,208,209,210,211,212,213,214,215,216,217,218,219,220,221,222,223],"surfaceOp":"append"}
 {"type":"tool/call","seq":225,"time":1783611707097,"data":{"turn":1,"step":3,"callId":"call_00_GVknJu2tksKkP4lALCwh0926","name":"edit","arguments":"{\"file_path\": \"settings.txt\", \"old_string\": \"blue\", \"new_string\": \"green\"}"}}
-{"type":"tool/result","seq":226,"time":1783611707114,"data":{"turn":1,"step":3,"callId":"call_00_GVknJu2tksKkP4lALCwh0926","content":[{"type":"text","text":"Error: unknown tool \"edit\""}],"isError":true,"error":{"name":"ToolNotFoundError","code":"UNKNOWN_TOOL"}},"sourceEventSeqs":[225],"surfaceOp":"append"}
+{"type":"tool/result","seq":226,"time":1783611707114,"data":{"turn":1,"step":3,"callId":"call_00_GVknJu2tksKkP4lALCwh0926","content":[{"type":"text","text":"The file /var/folders/2c/psb0_fmx7hbgz558xjt_f0l00000gn/T/acp-snap-cwd-QzoqnB/settings.txt has been updated successfully."}],"isError":false,"meta":{"diffs":[{"path":"settings.txt","oldText":"color: blue","newText":"color: green"}]}},"sourceEventSeqs":[225],"surfaceOp":"append"}
 {"type":"step/end","seq":227,"time":1783611707114,"data":{"turn":1,"step":3}}
 {"type":"step/start","seq":228,"time":1783611707114,"data":{"turn":1,"step":4}}
 {"type":"assistant/chunk","seq":229,"time":1783611707747,"data":{"turn":1,"step":4,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
diff --git a/examples/acp-agent/tests/snapshots/fs-policy-reject/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-policy-reject/stdout.golden.jsonl
index 5aa75c026c..fd5c9f1aea 100644
--- a/examples/acp-agent/tests/snapshots/fs-policy-reject/stdout.golden.jsonl
+++ b/examples/acp-agent/tests/snapshots/fs-policy-reject/stdout.golden.jsonl
@@ -36,8 +36,8 @@
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"D"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ONE"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\"."}}}}
-{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_x0zlnXl5JOxLrAYL9y7P0119","title":"edit","kind":"other","status":"in_progress","rawInput":{"file_path":"settings.txt","old_string":"blue","new_string":"green"}}}}
-{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_x0zlnXl5JOxLrAYL9y7P0119","status":"failed","content":[{"type":"content","content":{"type":"text","text":"Error: unknown tool \"edit\""}}]}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_x0zlnXl5JOxLrAYL9y7P0119","title":"Edit settings.txt","kind":"edit","status":"in_progress","locations":[{"path":"settings.txt"}],"content":[{"type":"diff","path":"settings.txt","oldText":"blue","newText":"green"}]}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_x0zlnXl5JOxLrAYL9y7P0119","status":"failed","content":[{"type":"content","content":{"type":"text","text":"Error: edit requires reading \"{{cwd}}/settings.txt\" first"}}]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" edit"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" tool"}}}}
@@ -82,8 +82,8 @@
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" file"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" first"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}}
-{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_tfr0gdIclW92oIEgi7NF0891","title":"read","kind":"other","status":"in_progress","rawInput":{"file_path":"settings.txt"}}}}
-{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_tfr0gdIclW92oIEgi7NF0891","status":"failed","content":[{"type":"content","content":{"type":"text","text":"Error: unknown tool \"read\""}}]}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_tfr0gdIclW92oIEgi7NF0891","title":"Read settings.txt","kind":"read","status":"in_progress","locations":[{"path":"settings.txt","line":1}]}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_tfr0gdIclW92oIEgi7NF0891","status":"completed","content":[{"type":"content","content":{"type":"text","text":"<path>{{cwd}}/settings.txt</path>\n<type>file</type>\n<content>\n1: color: blue\n\n(End of file - total 1 lines)\n</content>"}}]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" file"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" contains"}}}}
@@ -124,8 +124,8 @@
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" should"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" work"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}}
-{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_GVknJu2tksKkP4lALCwh0926","title":"edit","kind":"other","status":"in_progress","rawInput":{"file_path":"settings.txt","old_string":"blue","new_string":"green"}}}}
-{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_GVknJu2tksKkP4lALCwh0926","status":"failed","content":[{"type":"content","content":{"type":"text","text":"Error: unknown tool \"edit\""}}]}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_GVknJu2tksKkP4lALCwh0926","title":"Edit settings.txt","kind":"edit","status":"in_progress","locations":[{"path":"settings.txt"}],"content":[{"type":"diff","path":"settings.txt","oldText":"blue","newText":"green"}]}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_GVknJu2tksKkP4lALCwh0926","status":"completed","content":[{"type":"diff","path":"settings.txt","oldText":"color: blue","newText":"color: green"}],"title":"Edit settings.txt"}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" replacement"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" was"}}}}
diff --git a/examples/acp-agent/tests/snapshots/fs-read-window/session.jsonl b/examples/acp-agent/tests/snapshots/fs-read-window/session.jsonl
index fdca16f460..e587011cfd 100644
--- a/examples/acp-agent/tests/snapshots/fs-read-window/session.jsonl
+++ b/examples/acp-agent/tests/snapshots/fs-read-window/session.jsonl
@@ -91,7 +91,7 @@
 {"type":"assistant/chunk","seq":89,"time":1783352101346,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
 {"type":"assistant/message","seq":90,"time":1783352101348,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to use the read tool with offset 5 and limit 4 to read lines 5 through 8 of big.txt in the current directory. Then reply with exactly the single word DONE.\n\nLet me first check the current directory, then read the file."},{"type":"tool-call","id":"call_00_GIZwZS9a7vhWTFCIc7Z35497","name":"read","arguments":"{\"file_path\": \"big.txt\", \"offset\": 5, \"limit\": 4}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2894,"outputTokens":133,"cacheReadTokens":0,"reasoningTokens":56}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89],"surfaceOp":"append"}
 {"type":"tool/call","seq":91,"time":1783352101348,"data":{"turn":1,"step":1,"callId":"call_00_GIZwZS9a7vhWTFCIc7Z35497","name":"read","arguments":"{\"file_path\": \"big.txt\", \"offset\": 5, \"limit\": 4}"}}
-{"type":"tool/result","seq":92,"time":1783352101353,"data":{"turn":1,"step":1,"callId":"call_00_GIZwZS9a7vhWTFCIc7Z35497","content":[{"type":"text","text":"Error: unknown tool \"read\""}],"isError":true,"error":{"name":"ToolNotFoundError","code":"UNKNOWN_TOOL"}},"sourceEventSeqs":[91],"surfaceOp":"append"}
+{"type":"tool/result","seq":92,"time":1783352101353,"data":{"turn":1,"step":1,"callId":"call_00_GIZwZS9a7vhWTFCIc7Z35497","content":[{"type":"text","text":"<path>/tmp/acp-snap-cwd-N9HCkt/big.txt</path>\n<type>file</type>\n<content>\n5: line five\n6: line six\n7: line seven\n8: line eight\n\n(Showing lines 5-8 of 10. Use offset=9 to continue.)\n</content>"}],"isError":false},"sourceEventSeqs":[91],"surfaceOp":"append"}
 {"type":"step/end","seq":93,"time":1783352101353,"data":{"turn":1,"step":1}}
 {"type":"step/start","seq":94,"time":1783352101354,"data":{"turn":1,"step":2}}
 {"type":"assistant/chunk","seq":95,"time":1783352102021,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
diff --git a/examples/acp-agent/tests/snapshots/fs-read-window/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-read-window/stdout.golden.jsonl
index 05832400c8..ab3eb2da31 100644
--- a/examples/acp-agent/tests/snapshots/fs-read-window/stdout.golden.jsonl
+++ b/examples/acp-agent/tests/snapshots/fs-read-window/stdout.golden.jsonl
@@ -56,8 +56,8 @@
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" file"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}}
-{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_GIZwZS9a7vhWTFCIc7Z35497","title":"read","kind":"other","status":"in_progress","rawInput":{"file_path":"big.txt","offset":5,"limit":4}}}}
-{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_GIZwZS9a7vhWTFCIc7Z35497","status":"failed","content":[{"type":"content","content":{"type":"text","text":"Error: unknown tool \"read\""}}]}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_GIZwZS9a7vhWTFCIc7Z35497","title":"Read big.txt (5 - 8)","kind":"read","status":"in_progress","locations":[{"path":"big.txt","line":5}]}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_GIZwZS9a7vhWTFCIc7Z35497","status":"completed","content":[{"type":"content","content":{"type":"text","text":"<path>{{cwd}}/big.txt</path>\n<type>file</type>\n<content>\n5: line five\n6: line six\n7: line seven\n8: line eight\n\n(Showing lines 5-8 of 10. Use offset=9 to continue.)\n</content>"}}]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" read"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" tool"}}}}
diff --git a/examples/acp-agent/tests/snapshots/fs-read/session.jsonl b/examples/acp-agent/tests/snapshots/fs-read/session.jsonl
index 6c9ac8ab79..81737364f8 100644
--- a/examples/acp-agent/tests/snapshots/fs-read/session.jsonl
+++ b/examples/acp-agent/tests/snapshots/fs-read/session.jsonl
@@ -53,7 +53,7 @@
 {"type":"assistant/chunk","seq":51,"time":1783352073705,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
 {"type":"assistant/message","seq":52,"time":1783352073708,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to read the file greeting.txt using the read tool (not bash), then reply with exactly the single word \"DONE\"."},{"type":"tool-call","id":"call_00_hHPZCcivsIkXAGS9jTGy8417","name":"read","arguments":"{\"file_path\": \"greeting.txt\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2882,"outputTokens":75,"cacheReadTokens":0,"reasoningTokens":29}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51],"surfaceOp":"append"}
 {"type":"tool/call","seq":53,"time":1783352073709,"data":{"turn":1,"step":1,"callId":"call_00_hHPZCcivsIkXAGS9jTGy8417","name":"read","arguments":"{\"file_path\": \"greeting.txt\"}"}}
-{"type":"tool/result","seq":54,"time":1783352073717,"data":{"turn":1,"step":1,"callId":"call_00_hHPZCcivsIkXAGS9jTGy8417","content":[{"type":"text","text":"Error: unknown tool \"read\""}],"isError":true,"error":{"name":"ToolNotFoundError","code":"UNKNOWN_TOOL"}},"sourceEventSeqs":[53],"surfaceOp":"append"}
+{"type":"tool/result","seq":54,"time":1783352073717,"data":{"turn":1,"step":1,"callId":"call_00_hHPZCcivsIkXAGS9jTGy8417","content":[{"type":"text","text":"<path>/tmp/acp-snap-cwd-PEETkS/greeting.txt</path>\n<type>file</type>\n<content>\n1: hello\n\n(End of file - total 1 lines)\n</content>"}],"isError":false},"sourceEventSeqs":[53],"surfaceOp":"append"}
 {"type":"step/end","seq":55,"time":1783352073718,"data":{"turn":1,"step":1}}
 {"type":"step/start","seq":56,"time":1783352073719,"data":{"turn":1,"step":2}}
 {"type":"assistant/chunk","seq":57,"time":1783352074666,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
diff --git a/examples/acp-agent/tests/snapshots/fs-read/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-read/stdout.golden.jsonl
index 19abb7f418..fc0edbbe8b 100644
--- a/examples/acp-agent/tests/snapshots/fs-read/stdout.golden.jsonl
+++ b/examples/acp-agent/tests/snapshots/fs-read/stdout.golden.jsonl
@@ -29,8 +29,8 @@
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"D"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ONE"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\"."}}}}
-{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_hHPZCcivsIkXAGS9jTGy8417","title":"read","kind":"other","status":"in_progress","rawInput":{"file_path":"greeting.txt"}}}}
-{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_hHPZCcivsIkXAGS9jTGy8417","status":"failed","content":[{"type":"content","content":{"type":"text","text":"Error: unknown tool \"read\""}}]}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_hHPZCcivsIkXAGS9jTGy8417","title":"Read greeting.txt","kind":"read","status":"in_progress","locations":[{"path":"greeting.txt","line":1}]}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_hHPZCcivsIkXAGS9jTGy8417","status":"completed","content":[{"type":"content","content":{"type":"text","text":"<path>{{cwd}}/greeting.txt</path>\n<type>file</type>\n<content>\n1: hello\n\n(End of file - total 1 lines)\n</content>"}}]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" asked"}}}}
diff --git a/examples/acp-agent/tests/snapshots/fs-write-overwrite/session.jsonl b/examples/acp-agent/tests/snapshots/fs-write-overwrite/session.jsonl
index 4ece4483be..08ec0f1323 100644
--- a/examples/acp-agent/tests/snapshots/fs-write-overwrite/session.jsonl
+++ b/examples/acp-agent/tests/snapshots/fs-write-overwrite/session.jsonl
@@ -65,7 +65,7 @@
 {"type":"assistant/chunk","seq":63,"time":1783352093614,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
 {"type":"assistant/message","seq":64,"time":1783352093617,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to:\n1. Read data.txt using the read tool\n2. Replace its entire contents with exactly \"replaced\" using the write tool\n3. Reply with exactly \"DONE\""},{"type":"tool-call","id":"call_00_n4eRJuGoxNR07svgNtk82243","name":"read","arguments":"{\"file_path\": \"data.txt\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2899,"outputTokens":87,"cacheReadTokens":0,"reasoningTokens":42}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63],"surfaceOp":"append"}
 {"type":"tool/call","seq":65,"time":1783352093617,"data":{"turn":1,"step":1,"callId":"call_00_n4eRJuGoxNR07svgNtk82243","name":"read","arguments":"{\"file_path\": \"data.txt\"}"}}
-{"type":"tool/result","seq":66,"time":1783352093624,"data":{"turn":1,"step":1,"callId":"call_00_n4eRJuGoxNR07svgNtk82243","content":[{"type":"text","text":"Error: unknown tool \"read\""}],"isError":true,"error":{"name":"ToolNotFoundError","code":"UNKNOWN_TOOL"}},"sourceEventSeqs":[65],"surfaceOp":"append"}
+{"type":"tool/result","seq":66,"time":1783352093624,"data":{"turn":1,"step":1,"callId":"call_00_n4eRJuGoxNR07svgNtk82243","content":[{"type":"text","text":"<path>/tmp/acp-snap-cwd-hH2sGY/data.txt</path>\n<type>file</type>\n<content>\n1: original contents\n\n(End of file - total 1 lines)\n</content>"}],"isError":false},"sourceEventSeqs":[65],"surfaceOp":"append"}
 {"type":"step/end","seq":67,"time":1783352093624,"data":{"turn":1,"step":1}}
 {"type":"step/start","seq":68,"time":1783352093625,"data":{"turn":1,"step":2}}
 {"type":"assistant/chunk","seq":69,"time":1783352094455,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
@@ -114,7 +114,7 @@
 {"type":"assistant/chunk","seq":112,"time":1783352094988,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
 {"type":"assistant/message","seq":113,"time":1783352094988,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The file contains \"original contents\". Now I'll replace it with \"replaced\"."},{"type":"tool-call","id":"call_00_N23EvXjDo4c8enyWpIUq4043","name":"write","arguments":"{\"file_path\": \"data.txt\", \"content\": \"replaced\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":228,"outputTokens":79,"cacheReadTokens":2816,"reasoningTokens":17}},"sourceEventSeqs":[69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112],"surfaceOp":"append"}
 {"type":"tool/call","seq":114,"time":1783352094988,"data":{"turn":1,"step":2,"callId":"call_00_N23EvXjDo4c8enyWpIUq4043","name":"write","arguments":"{\"file_path\": \"data.txt\", \"content\": \"replaced\"}"}}
-{"type":"tool/result","seq":115,"time":1783352094995,"data":{"turn":1,"step":2,"callId":"call_00_N23EvXjDo4c8enyWpIUq4043","content":[{"type":"text","text":"Error: unknown tool \"write\""}],"isError":true,"error":{"name":"ToolNotFoundError","code":"UNKNOWN_TOOL"}},"sourceEventSeqs":[114],"surfaceOp":"append"}
+{"type":"tool/result","seq":115,"time":1783352094995,"data":{"turn":1,"step":2,"callId":"call_00_N23EvXjDo4c8enyWpIUq4043","content":[{"type":"text","text":"<path>/tmp/acp-snap-cwd-hH2sGY/data.txt</path>\n<type>file</type>\n<content>\nUpdated file\n</content>"}],"isError":false,"meta":{"diffs":[{"path":"data.txt","oldText":"original contents","newText":"replaced"}]}},"sourceEventSeqs":[114],"surfaceOp":"append"}
 {"type":"step/end","seq":116,"time":1783352094995,"data":{"turn":1,"step":2}}
 {"type":"step/start","seq":117,"time":1783352094995,"data":{"turn":1,"step":3}}
 {"type":"assistant/chunk","seq":118,"time":1783352096090,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
diff --git a/examples/acp-agent/tests/snapshots/fs-write-overwrite/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-write-overwrite/stdout.golden.jsonl
index 4801d9410d..f0ca9674cb 100644
--- a/examples/acp-agent/tests/snapshots/fs-write-overwrite/stdout.golden.jsonl
+++ b/examples/acp-agent/tests/snapshots/fs-write-overwrite/stdout.golden.jsonl
@@ -42,8 +42,8 @@
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"D"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ONE"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\""}}}}
-{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_n4eRJuGoxNR07svgNtk82243","title":"read","kind":"other","status":"in_progress","rawInput":{"file_path":"data.txt"}}}}
-{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_n4eRJuGoxNR07svgNtk82243","status":"failed","content":[{"type":"content","content":{"type":"text","text":"Error: unknown tool \"read\""}}]}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_n4eRJuGoxNR07svgNtk82243","title":"Read data.txt","kind":"read","status":"in_progress","locations":[{"path":"data.txt","line":1}]}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_n4eRJuGoxNR07svgNtk82243","status":"completed","content":[{"type":"content","content":{"type":"text","text":"<path>{{cwd}}/data.txt</path>\n<type>file</type>\n<content>\n1: original contents\n\n(End of file - total 1 lines)\n</content>"}}]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" file"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" contains"}}}}
@@ -61,8 +61,8 @@
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"re"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"placed"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\"."}}}}
-{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_N23EvXjDo4c8enyWpIUq4043","title":"write","kind":"other","status":"in_progress","rawInput":{"file_path":"data.txt","content":"replaced"}}}}
-{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_N23EvXjDo4c8enyWpIUq4043","status":"failed","content":[{"type":"content","content":{"type":"text","text":"Error: unknown tool \"write\""}}]}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_N23EvXjDo4c8enyWpIUq4043","title":"Write data.txt","kind":"edit","status":"in_progress","locations":[{"path":"data.txt"}],"content":[{"type":"diff","path":"data.txt","oldText":null,"newText":"replaced"}]}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_N23EvXjDo4c8enyWpIUq4043","status":"completed","content":[{"type":"diff","path":"data.txt","oldText":"original contents","newText":"replaced"}],"title":"Write data.txt"}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" file"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" has"}}}}
diff --git a/examples/acp-agent/tests/snapshots/fs-write/session.jsonl b/examples/acp-agent/tests/snapshots/fs-write/session.jsonl
index c7d3d4bd95..59ba868817 100644
--- a/examples/acp-agent/tests/snapshots/fs-write/session.jsonl
+++ b/examples/acp-agent/tests/snapshots/fs-write/session.jsonl
@@ -62,7 +62,7 @@
 {"type":"assistant/chunk","seq":60,"time":1783352079886,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
 {"type":"assistant/message","seq":61,"time":1783352079888,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to create a file named notes.txt with the content \"hello world\" using the write tool, then reply with \"DONE\"."},{"type":"tool-call","id":"call_00_APMUCJJm9lrTSlVbg6dB0185","name":"write","arguments":"{\"file_path\": \"notes.txt\", \"content\": \"hello world\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2891,"outputTokens":92,"cacheReadTokens":0,"reasoningTokens":30}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60],"surfaceOp":"append"}
 {"type":"tool/call","seq":62,"time":1783352079888,"data":{"turn":1,"step":1,"callId":"call_00_APMUCJJm9lrTSlVbg6dB0185","name":"write","arguments":"{\"file_path\": \"notes.txt\", \"content\": \"hello world\"}"}}
-{"type":"tool/result","seq":63,"time":1783352079897,"data":{"turn":1,"step":1,"callId":"call_00_APMUCJJm9lrTSlVbg6dB0185","content":[{"type":"text","text":"Error: unknown tool \"write\""}],"isError":true,"error":{"name":"ToolNotFoundError","code":"UNKNOWN_TOOL"}},"sourceEventSeqs":[62],"surfaceOp":"append"}
+{"type":"tool/result","seq":63,"time":1783352079897,"data":{"turn":1,"step":1,"callId":"call_00_APMUCJJm9lrTSlVbg6dB0185","content":[{"type":"text","text":"<path>/tmp/acp-snap-cwd-sNvn5N/notes.txt</path>\n<type>file</type>\n<content>\nCreated file\n</content>"}],"isError":false},"sourceEventSeqs":[62],"surfaceOp":"append"}
 {"type":"step/end","seq":64,"time":1783352079898,"data":{"turn":1,"step":1}}
 {"type":"step/start","seq":65,"time":1783352079899,"data":{"turn":1,"step":2}}
 {"type":"assistant/chunk","seq":66,"time":1783352080825,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
diff --git a/examples/acp-agent/tests/snapshots/fs-write/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-write/stdout.golden.jsonl
index d5b3ca5d15..3c01ab158c 100644
--- a/examples/acp-agent/tests/snapshots/fs-write/stdout.golden.jsonl
+++ b/examples/acp-agent/tests/snapshots/fs-write/stdout.golden.jsonl
@@ -30,8 +30,8 @@
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"D"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ONE"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\"."}}}}
-{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_APMUCJJm9lrTSlVbg6dB0185","title":"write","kind":"other","status":"in_progress","rawInput":{"file_path":"notes.txt","content":"hello world"}}}}
-{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_APMUCJJm9lrTSlVbg6dB0185","status":"failed","content":[{"type":"content","content":{"type":"text","text":"Error: unknown tool \"write\""}}]}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_APMUCJJm9lrTSlVbg6dB0185","title":"Write notes.txt","kind":"edit","status":"in_progress","locations":[{"path":"notes.txt"}],"content":[{"type":"diff","path":"notes.txt","oldText":null,"newText":"hello world"}]}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_APMUCJJm9lrTSlVbg6dB0185","status":"completed","content":[{"type":"diff","path":"notes.txt","oldText":null,"newText":"hello world"}],"title":"Write notes.txt"}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" file"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" has"}}}}
diff --git a/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl
index 6264b68db9..f807f4ed3c 100644
--- a/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl
+++ b/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl
@@ -55,8 +55,8 @@
 {"type":"tool/call","seq":53,"time":1783352172557,"data":{"turn":1,"step":1,"callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Echo HELLO\"}"}}
 {"type":"hook/invoked","seq":54,"time":1783352172558,"data":{"turn":1,"point":"PreToolUse","dialect":"claude","handlerId":"claude:PreToolUse:1","matcher":"bash"}}
 {"type":"hook/result","seq":55,"time":1783352172573,"data":{"turn":1,"point":"PreToolUse","handlerId":"claude:PreToolUse:1","decision":"ask","exitCode":0,"durationMs":14.113374999999905}}
-{"type":"approval/asked","seq":56,"time":1783962235813,"data":{"id":"5ab08815-cec4-4615-88d4-2d5b519762e8","toolName":"bash","callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","reason":"bash requires manual approval in this session"}}
-{"type":"approval/decided","seq":57,"time":1783962235813,"data":{"id":"5ab08815-cec4-4615-88d4-2d5b519762e8","outcome":"rejected"}}
+{"type":"approval/asked","seq":56,"time":1783962235813,"data":{"id":"45e41a72-c0e1-44a4-a9ee-2145a51fedf4","toolName":"bash","callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","reason":"bash requires manual approval in this session"}}
+{"type":"approval/decided","seq":57,"time":1783962235813,"data":{"id":"45e41a72-c0e1-44a4-a9ee-2145a51fedf4","outcome":"rejected"}}
 {"type":"tool/result","seq":58,"time":1783962235814,"data":{"turn":1,"step":1,"callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","content":[{"type":"text","text":"Error: the user rejected tool \"bash\""}],"isError":true},"sourceEventSeqs":[53],"surfaceOp":"append"}
 {"type":"step/end","seq":59,"time":1783962235814,"data":{"turn":1,"step":1}}
 {"type":"step/start","seq":60,"time":1783962235814,"data":{"turn":1,"step":2}}
diff --git a/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl b/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl
index c77300fe90..2de9d3028d 100644
--- a/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl
+++ b/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl
@@ -5,7 +5,7 @@
 {"type":"approval/policy","seq":3,"time":1783962244578,"data":{"policy":"ask"}}
 {"type":"user/message","seq":4,"time":1783962244578,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly this one command in a single call: printf 'before\\n' > out.txt && cat out.txt. Then reply with the single word DONE and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"}
 {"type":"step/start","seq":5,"time":1783962244579,"data":{"turn":1,"step":1}}
-{"type":"request/header","seq":6,"time":1783962244580,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return <value>` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise<any>` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise<any[]>` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise<any[]>` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return <json-value>`)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}}
+{"type":"request/header","seq":6,"time":1783962244580,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
 {"type":"assistant/chunk","seq":7,"time":1783860667444,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
 {"type":"assistant/chunk","seq":8,"time":1783860667445,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}}
 {"type":"assistant/chunk","seq":9,"time":1783860667445,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}}
diff --git a/examples/acp-agent/tests/snapshots/permission-switching/tool-schemas.golden.json b/examples/acp-agent/tests/snapshots/permission-switching/tool-schemas.golden.json
new file mode 100644
index 0000000000..d71283647e
--- /dev/null
+++ b/examples/acp-agent/tests/snapshots/permission-switching/tool-schemas.golden.json
@@ -0,0 +1,249 @@
+{
+  "initial": [
+    {
+      "name": "bash",
+      "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "command": {
+            "type": "string",
+            "description": "The bash command to execute."
+          },
+          "description": {
+            "type": "string",
+            "description": "Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."
+          },
+          "timeoutMs": {
+            "type": "number",
+            "description": "Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."
+          },
+          "workdir": {
+            "type": "string",
+            "description": "Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."
+          },
+          "run_in_background": {
+            "type": "boolean",
+            "description": "Run in the background and return a task id immediately. No timeout applies."
+          },
+          "sandbox_permissions": {
+            "type": "string",
+            "description": "The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.",
+            "enum": [
+              "workspace-write",
+              "danger-full-access"
+            ]
+          },
+          "justification": {
+            "type": "string",
+            "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."
+          }
+        },
+        "required": [
+          "command",
+          "description"
+        ]
+      }
+    },
+    {
+      "name": "bash_kill",
+      "description": "Ask the executor to kill a running background bash task by task id.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "task_id": {
+            "type": "string",
+            "description": "Task id returned by the bash tool."
+          }
+        },
+        "required": [
+          "task_id"
+        ]
+      }
+    },
+    {
+      "name": "bash_output",
+      "description": "Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "task_id": {
+            "type": "string",
+            "description": "Task id returned by the bash tool."
+          }
+        },
+        "required": [
+          "task_id"
+        ]
+      }
+    },
+    {
+      "name": "skill",
+      "description": "Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "name": {
+            "type": "string",
+            "description": "The exact skill name from the available skills list."
+          }
+        },
+        "required": [
+          "name"
+        ]
+      }
+    },
+    {
+      "name": "subagent",
+      "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "description": {
+            "type": "string",
+            "description": "A short (3-5 word) description of the delegated task, for display."
+          },
+          "prompt": {
+            "type": "string",
+            "description": "The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."
+          }
+        },
+        "required": [
+          "description",
+          "prompt"
+        ]
+      }
+    },
+    {
+      "name": "subagent_fork",
+      "description": "Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "description": {
+            "type": "string",
+            "description": "A short (3-5 word) description of the delegated task, for display."
+          },
+          "prompt": {
+            "type": "string",
+            "description": "The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."
+          }
+        },
+        "required": [
+          "description",
+          "prompt"
+        ]
+      }
+    },
+    {
+      "name": "todo_write",
+      "description": "Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "todos": {
+            "type": "array",
+            "description": "The COMPLETE task list, replacing any previous list.",
+            "items": {
+              "type": "object",
+              "properties": {
+                "content": {
+                  "type": "string",
+                  "description": "What the task is — a short imperative line."
+                },
+                "status": {
+                  "type": "string",
+                  "description": "pending (not started) | in_progress (now) | completed (done).",
+                  "enum": [
+                    "pending",
+                    "in_progress",
+                    "completed"
+                  ]
+                }
+              },
+              "required": [
+                "content",
+                "status"
+              ]
+            }
+          }
+        },
+        "required": [
+          "todos"
+        ]
+      }
+    },
+    {
+      "name": "workflow",
+      "description": "Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return <value>` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise<any>` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise<any[]>` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise<any[]>` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "script": {
+            "type": "string",
+            "description": "The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return <json-value>`)."
+          },
+          "meta": {
+            "type": "object",
+            "description": "The workflow identity block (plain JSON — never code).",
+            "properties": {
+              "name": {
+                "type": "string",
+                "description": "Short kebab-case workflow name."
+              },
+              "description": {
+                "type": "string",
+                "description": "One-line description of what the workflow does."
+              },
+              "whenToUse": {
+                "type": "string",
+                "description": "Optional guidance on when this workflow applies."
+              },
+              "phases": {
+                "type": "array",
+                "description": "Optional phase declarations matched by phase() calls.",
+                "items": {
+                  "type": "object",
+                  "properties": {
+                    "title": {
+                      "type": "string",
+                      "description": "The phase title phase() calls match by exact string."
+                    },
+                    "detail": {
+                      "type": "string",
+                      "description": "Optional one-line description of the phase."
+                    },
+                    "provider": {
+                      "type": "string",
+                      "description": "Optional provider override this phase is expected to use."
+                    },
+                    "model": {
+                      "type": "string",
+                      "description": "Optional model override this phase is expected to use."
+                    }
+                  },
+                  "required": [
+                    "title"
+                  ]
+                }
+              }
+            },
+            "required": [
+              "name",
+              "description"
+            ]
+          },
+          "args": {
+            "type": "object",
+            "description": "Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."
+          }
+        },
+        "required": [
+          "script",
+          "meta"
+        ]
+      }
+    }
+  ],
+  "deltas": []
+}
diff --git a/examples/acp-agent/tests/snapshots/skill-load/session.jsonl b/examples/acp-agent/tests/snapshots/skill-load/session.jsonl
index 0cbc14dedd..0fe1a5152c 100644
--- a/examples/acp-agent/tests/snapshots/skill-load/session.jsonl
+++ b/examples/acp-agent/tests/snapshots/skill-load/session.jsonl
@@ -2,7 +2,7 @@
 {"type":"turn/start","seq":0,"time":1783654655602,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
 {"type":"user/message","seq":1,"time":1783654655603,"data":{"content":[{"type":"text","text":"Load the snapshot-skill skill with the skill tool, then reply DONE."}],"source":{"kind":"user"}},"surfaceOp":"append"}
 {"type":"step/start","seq":2,"time":1783654655608,"data":{"turn":1,"step":1}}
-{"type":"request/header","seq":3,"time":1783654655608,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return <value>` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise<any>` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise<any[]>` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise<any[]>` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return <json-value>`)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}],"messagePrefix":[{"role":"user","content":[{"type":"text","text":"<system-reminder>\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n<available_skills>\n- `snapshot-skill`: Exercise project skill discovery and loading in snapshot tests.\n</available_skills>\n\nIf the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.\n</system-reminder>"}]}]},"reason":"initial"}}
+{"type":"request/header","seq":3,"time":1783654655608,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}","messagePrefix":[{"role":"user","content":[{"type":"text","text":"<system-reminder>\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n<available_skills>\n- `snapshot-skill`: Exercise project skill discovery and loading in snapshot tests.\n</available_skills>\n\nIf the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.\n</system-reminder>"}]}]},"reason":"initial"}}
 {"type":"assistant/chunk","seq":4,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
 {"type":"assistant/chunk","seq":5,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"Load the requested skill."}}}
 {"type":"assistant/chunk","seq":6,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}}
diff --git a/examples/acp-agent/tests/snapshots/skill-load/tool-schemas.golden.json b/examples/acp-agent/tests/snapshots/skill-load/tool-schemas.golden.json
new file mode 100644
index 0000000000..d71283647e
--- /dev/null
+++ b/examples/acp-agent/tests/snapshots/skill-load/tool-schemas.golden.json
@@ -0,0 +1,249 @@
+{
+  "initial": [
+    {
+      "name": "bash",
+      "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "command": {
+            "type": "string",
+            "description": "The bash command to execute."
+          },
+          "description": {
+            "type": "string",
+            "description": "Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."
+          },
+          "timeoutMs": {
+            "type": "number",
+            "description": "Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."
+          },
+          "workdir": {
+            "type": "string",
+            "description": "Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."
+          },
+          "run_in_background": {
+            "type": "boolean",
+            "description": "Run in the background and return a task id immediately. No timeout applies."
+          },
+          "sandbox_permissions": {
+            "type": "string",
+            "description": "The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.",
+            "enum": [
+              "workspace-write",
+              "danger-full-access"
+            ]
+          },
+          "justification": {
+            "type": "string",
+            "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."
+          }
+        },
+        "required": [
+          "command",
+          "description"
+        ]
+      }
+    },
+    {
+      "name": "bash_kill",
+      "description": "Ask the executor to kill a running background bash task by task id.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "task_id": {
+            "type": "string",
+            "description": "Task id returned by the bash tool."
+          }
+        },
+        "required": [
+          "task_id"
+        ]
+      }
+    },
+    {
+      "name": "bash_output",
+      "description": "Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "task_id": {
+            "type": "string",
+            "description": "Task id returned by the bash tool."
+          }
+        },
+        "required": [
+          "task_id"
+        ]
+      }
+    },
+    {
+      "name": "skill",
+      "description": "Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "name": {
+            "type": "string",
+            "description": "The exact skill name from the available skills list."
+          }
+        },
+        "required": [
+          "name"
+        ]
+      }
+    },
+    {
+      "name": "subagent",
+      "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "description": {
+            "type": "string",
+            "description": "A short (3-5 word) description of the delegated task, for display."
+          },
+          "prompt": {
+            "type": "string",
+            "description": "The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."
+          }
+        },
+        "required": [
+          "description",
+          "prompt"
+        ]
+      }
+    },
+    {
+      "name": "subagent_fork",
+      "description": "Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "description": {
+            "type": "string",
+            "description": "A short (3-5 word) description of the delegated task, for display."
+          },
+          "prompt": {
+            "type": "string",
+            "description": "The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."
+          }
+        },
+        "required": [
+          "description",
+          "prompt"
+        ]
+      }
+    },
+    {
+      "name": "todo_write",
+      "description": "Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "todos": {
+            "type": "array",
+            "description": "The COMPLETE task list, replacing any previous list.",
+            "items": {
+              "type": "object",
+              "properties": {
+                "content": {
+                  "type": "string",
+                  "description": "What the task is — a short imperative line."
+                },
+                "status": {
+                  "type": "string",
+                  "description": "pending (not started) | in_progress (now) | completed (done).",
+                  "enum": [
+                    "pending",
+                    "in_progress",
+                    "completed"
+                  ]
+                }
+              },
+              "required": [
+                "content",
+                "status"
+              ]
+            }
+          }
+        },
+        "required": [
+          "todos"
+        ]
+      }
+    },
+    {
+      "name": "workflow",
+      "description": "Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return <value>` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise<any>` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise<any[]>` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise<any[]>` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "script": {
+            "type": "string",
+            "description": "The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return <json-value>`)."
+          },
+          "meta": {
+            "type": "object",
+            "description": "The workflow identity block (plain JSON — never code).",
+            "properties": {
+              "name": {
+                "type": "string",
+                "description": "Short kebab-case workflow name."
+              },
+              "description": {
+                "type": "string",
+                "description": "One-line description of what the workflow does."
+              },
+              "whenToUse": {
+                "type": "string",
+                "description": "Optional guidance on when this workflow applies."
+              },
+              "phases": {
+                "type": "array",
+                "description": "Optional phase declarations matched by phase() calls.",
+                "items": {
+                  "type": "object",
+                  "properties": {
+                    "title": {
+                      "type": "string",
+                      "description": "The phase title phase() calls match by exact string."
+                    },
+                    "detail": {
+                      "type": "string",
+                      "description": "Optional one-line description of the phase."
+                    },
+                    "provider": {
+                      "type": "string",
+                      "description": "Optional provider override this phase is expected to use."
+                    },
+                    "model": {
+                      "type": "string",
+                      "description": "Optional model override this phase is expected to use."
+                    }
+                  },
+                  "required": [
+                    "title"
+                  ]
+                }
+              }
+            },
+            "required": [
+              "name",
+              "description"
+            ]
+          },
+          "args": {
+            "type": "object",
+            "description": "Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."
+          }
+        },
+        "required": [
+          "script",
+          "meta"
+        ]
+      }
+    }
+  ],
+  "deltas": []
+}
diff --git a/examples/acp-agent/tests/snapshots/text-turn/session.jsonl b/examples/acp-agent/tests/snapshots/text-turn/session.jsonl
index 69b9fccfc7..04ac2f9794 100644
--- a/examples/acp-agent/tests/snapshots/text-turn/session.jsonl
+++ b/examples/acp-agent/tests/snapshots/text-turn/session.jsonl
@@ -2,7 +2,7 @@
 {"type":"turn/start","seq":0,"time":1783600629541,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
 {"type":"user/message","seq":1,"time":1783600629541,"data":{"content":[{"type":"text","text":"Reply with exactly the word: PONG. Do not use any tools."}],"source":{"kind":"user"}},"surfaceOp":"append"}
 {"type":"step/start","seq":2,"time":1783600629542,"data":{"turn":1,"step":1}}
-{"type":"request/header","seq":3,"time":1783600629542,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return <value>` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise<any>` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise<any[]>` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise<any[]>` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return <json-value>`)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}}
+{"type":"request/header","seq":3,"time":1783600629542,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
 {"type":"assistant/chunk","seq":4,"time":1783600630819,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
 {"type":"assistant/chunk","seq":5,"time":1783600630820,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}}
 {"type":"assistant/chunk","seq":6,"time":1783600630822,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}}
diff --git a/examples/acp-agent/tests/snapshots/text-turn/tool-schemas.golden.json b/examples/acp-agent/tests/snapshots/text-turn/tool-schemas.golden.json
new file mode 100644
index 0000000000..d71283647e
--- /dev/null
+++ b/examples/acp-agent/tests/snapshots/text-turn/tool-schemas.golden.json
@@ -0,0 +1,249 @@
+{
+  "initial": [
+    {
+      "name": "bash",
+      "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "command": {
+            "type": "string",
+            "description": "The bash command to execute."
+          },
+          "description": {
+            "type": "string",
+            "description": "Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."
+          },
+          "timeoutMs": {
+            "type": "number",
+            "description": "Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."
+          },
+          "workdir": {
+            "type": "string",
+            "description": "Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."
+          },
+          "run_in_background": {
+            "type": "boolean",
+            "description": "Run in the background and return a task id immediately. No timeout applies."
+          },
+          "sandbox_permissions": {
+            "type": "string",
+            "description": "The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.",
+            "enum": [
+              "workspace-write",
+              "danger-full-access"
+            ]
+          },
+          "justification": {
+            "type": "string",
+            "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."
+          }
+        },
+        "required": [
+          "command",
+          "description"
+        ]
+      }
+    },
+    {
+      "name": "bash_kill",
+      "description": "Ask the executor to kill a running background bash task by task id.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "task_id": {
+            "type": "string",
+            "description": "Task id returned by the bash tool."
+          }
+        },
+        "required": [
+          "task_id"
+        ]
+      }
+    },
+    {
+      "name": "bash_output",
+      "description": "Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "task_id": {
+            "type": "string",
+            "description": "Task id returned by the bash tool."
+          }
+        },
+        "required": [
+          "task_id"
+        ]
+      }
+    },
+    {
+      "name": "skill",
+      "description": "Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "name": {
+            "type": "string",
+            "description": "The exact skill name from the available skills list."
+          }
+        },
+        "required": [
+          "name"
+        ]
+      }
+    },
+    {
+      "name": "subagent",
+      "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "description": {
+            "type": "string",
+            "description": "A short (3-5 word) description of the delegated task, for display."
+          },
+          "prompt": {
+            "type": "string",
+            "description": "The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."
+          }
+        },
+        "required": [
+          "description",
+          "prompt"
+        ]
+      }
+    },
+    {
+      "name": "subagent_fork",
+      "description": "Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "description": {
+            "type": "string",
+            "description": "A short (3-5 word) description of the delegated task, for display."
+          },
+          "prompt": {
+            "type": "string",
+            "description": "The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."
+          }
+        },
+        "required": [
+          "description",
+          "prompt"
+        ]
+      }
+    },
+    {
+      "name": "todo_write",
+      "description": "Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "todos": {
+            "type": "array",
+            "description": "The COMPLETE task list, replacing any previous list.",
+            "items": {
+              "type": "object",
+              "properties": {
+                "content": {
+                  "type": "string",
+                  "description": "What the task is — a short imperative line."
+                },
+                "status": {
+                  "type": "string",
+                  "description": "pending (not started) | in_progress (now) | completed (done).",
+                  "enum": [
+                    "pending",
+                    "in_progress",
+                    "completed"
+                  ]
+                }
+              },
+              "required": [
+                "content",
+                "status"
+              ]
+            }
+          }
+        },
+        "required": [
+          "todos"
+        ]
+      }
+    },
+    {
+      "name": "workflow",
+      "description": "Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return <value>` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise<any>` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise<any[]>` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise<any[]>` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "script": {
+            "type": "string",
+            "description": "The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return <json-value>`)."
+          },
+          "meta": {
+            "type": "object",
+            "description": "The workflow identity block (plain JSON — never code).",
+            "properties": {
+              "name": {
+                "type": "string",
+                "description": "Short kebab-case workflow name."
+              },
+              "description": {
+                "type": "string",
+                "description": "One-line description of what the workflow does."
+              },
+              "whenToUse": {
+                "type": "string",
+                "description": "Optional guidance on when this workflow applies."
+              },
+              "phases": {
+                "type": "array",
+                "description": "Optional phase declarations matched by phase() calls.",
+                "items": {
+                  "type": "object",
+                  "properties": {
+                    "title": {
+                      "type": "string",
+                      "description": "The phase title phase() calls match by exact string."
+                    },
+                    "detail": {
+                      "type": "string",
+                      "description": "Optional one-line description of the phase."
+                    },
+                    "provider": {
+                      "type": "string",
+                      "description": "Optional provider override this phase is expected to use."
+                    },
+                    "model": {
+                      "type": "string",
+                      "description": "Optional model override this phase is expected to use."
+                    }
+                  },
+                  "required": [
+                    "title"
+                  ]
+                }
+              }
+            },
+            "required": [
+              "name",
+              "description"
+            ]
+          },
+          "args": {
+            "type": "object",
+            "description": "Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."
+          }
+        },
+        "required": [
+          "script",
+          "meta"
+        ]
+      }
+    }
+  ],
+  "deltas": []
+}
diff --git a/examples/acp-agent/tests/snapshots/workspace-edit/session.jsonl b/examples/acp-agent/tests/snapshots/workspace-edit/session.jsonl
index 737aa77f48..6b9b03a95e 100644
--- a/examples/acp-agent/tests/snapshots/workspace-edit/session.jsonl
+++ b/examples/acp-agent/tests/snapshots/workspace-edit/session.jsonl
@@ -79,7 +79,7 @@
 {"type":"assistant/chunk","seq":77,"time":1783352265489,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
 {"type":"assistant/message","seq":78,"time":1783352265491,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to:\n1. Read the file greeting.txt\n2. Append the word WORLD as a second line\n3. Read the file back with cat to confirm\n4. Reply with DONE\n\nLet me start by reading the file to see its contents."},{"type":"tool-call","id":"call_00_OjRFB4zvxu6UALDjytZD0978","name":"read","arguments":"{\"file_path\": \"greeting.txt\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2918,"outputTokens":101,"cacheReadTokens":0,"reasoningTokens":55}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77],"surfaceOp":"append"}
 {"type":"tool/call","seq":79,"time":1783352265491,"data":{"turn":1,"step":1,"callId":"call_00_OjRFB4zvxu6UALDjytZD0978","name":"read","arguments":"{\"file_path\": \"greeting.txt\"}"}}
-{"type":"tool/result","seq":80,"time":1783352265504,"data":{"turn":1,"step":1,"callId":"call_00_OjRFB4zvxu6UALDjytZD0978","content":[{"type":"text","text":"Error: unknown tool \"read\""}],"isError":true,"error":{"name":"ToolNotFoundError","code":"UNKNOWN_TOOL"}},"sourceEventSeqs":[79],"surfaceOp":"append"}
+{"type":"tool/result","seq":80,"time":1783352265504,"data":{"turn":1,"step":1,"callId":"call_00_OjRFB4zvxu6UALDjytZD0978","content":[{"type":"text","text":"<path>/tmp/acp-snap-cwd-rxbEpP/greeting.txt</path>\n<type>file</type>\n<content>\n1: hello\n\n(End of file - total 1 lines)\n</content>"}],"isError":false},"sourceEventSeqs":[79],"surfaceOp":"append"}
 {"type":"step/end","seq":81,"time":1783352265504,"data":{"turn":1,"step":1}}
 {"type":"step/start","seq":82,"time":1783352265505,"data":{"turn":1,"step":2}}
 {"type":"assistant/chunk","seq":83,"time":1783352266385,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
diff --git a/examples/acp-agent/tests/snapshots/workspace-edit/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/workspace-edit/stdout.golden.jsonl
index 23f13ff3c2..5f6c7f4c52 100644
--- a/examples/acp-agent/tests/snapshots/workspace-edit/stdout.golden.jsonl
+++ b/examples/acp-agent/tests/snapshots/workspace-edit/stdout.golden.jsonl
@@ -55,8 +55,8 @@
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" its"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" contents"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}}
-{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_OjRFB4zvxu6UALDjytZD0978","title":"read","kind":"other","status":"in_progress","rawInput":{"file_path":"greeting.txt"}}}}
-{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_OjRFB4zvxu6UALDjytZD0978","status":"failed","content":[{"type":"content","content":{"type":"text","text":"Error: unknown tool \"read\""}}]}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_OjRFB4zvxu6UALDjytZD0978","title":"Read greeting.txt","kind":"read","status":"in_progress","locations":[{"path":"greeting.txt","line":1}]}}}
+{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_OjRFB4zvxu6UALDjytZD0978","status":"completed","content":[{"type":"content","content":{"type":"text","text":"<path>{{cwd}}/greeting.txt</path>\n<type>file</type>\n<content>\n1: hello\n\n(End of file - total 1 lines)\n</content>"}}]}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" file"}}}}
 {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" contains"}}}}
diff --git a/examples/acp-agent/tests/snapshots/workspace-edit/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/workspace-edit/system-prompt.golden.md
new file mode 100644
index 0000000000..6bb634b339
--- /dev/null
+++ b/examples/acp-agent/tests/snapshots/workspace-edit/system-prompt.golden.md
@@ -0,0 +1,19 @@
+You are an AI agent powered by the DeepSeek Harness SDK.
+
+You are a coding assistant powered by the deepseek-v4-flash model. Your working directory is {{cwd}}. Your bash tool runs under a file sandbox — a `[sandbox: file access denied …]` result is policy, not a command bug.
+
+Verify your work by running the code or tests. Keep answers brief and factual.
+
+
+Use the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files.
+
+Use the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes.
+
+Use the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session.
+
+Check the [exit code: N] marker on every bash result; investigate failures before moving on.
+
+Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).
+<!-- dsh-user-approval-policy:never -->
+
+Use the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls.
diff --git a/examples/acp-agent/tests/snapshots/workspace-edit/tool-schemas.golden.json b/examples/acp-agent/tests/snapshots/workspace-edit/tool-schemas.golden.json
new file mode 100644
index 0000000000..127ebe2ea1
--- /dev/null
+++ b/examples/acp-agent/tests/snapshots/workspace-edit/tool-schemas.golden.json
@@ -0,0 +1,324 @@
+{
+  "initial": [
+    {
+      "name": "bash",
+      "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "command": {
+            "type": "string",
+            "description": "The bash command to execute."
+          },
+          "description": {
+            "type": "string",
+            "description": "Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."
+          },
+          "timeoutMs": {
+            "type": "number",
+            "description": "Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."
+          },
+          "workdir": {
+            "type": "string",
+            "description": "Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."
+          },
+          "run_in_background": {
+            "type": "boolean",
+            "description": "Run in the background and return a task id immediately. No timeout applies."
+          },
+          "sandbox_permissions": {
+            "type": "string",
+            "description": "The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.",
+            "enum": [
+              "workspace-write",
+              "danger-full-access"
+            ]
+          },
+          "justification": {
+            "type": "string",
+            "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."
+          }
+        },
+        "required": [
+          "command",
+          "description"
+        ]
+      }
+    },
+    {
+      "name": "bash_kill",
+      "description": "Ask the executor to kill a running background bash task by task id.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "task_id": {
+            "type": "string",
+            "description": "Task id returned by the bash tool."
+          }
+        },
+        "required": [
+          "task_id"
+        ]
+      }
+    },
+    {
+      "name": "bash_output",
+      "description": "Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "task_id": {
+            "type": "string",
+            "description": "Task id returned by the bash tool."
+          }
+        },
+        "required": [
+          "task_id"
+        ]
+      }
+    },
+    {
+      "name": "edit",
+      "description": "Edit an existing UTF-8 text file by replacing literal text.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "file_path": {
+            "type": "string",
+            "description": "Path to edit, resolved by the filesystem backend."
+          },
+          "old_string": {
+            "type": "string",
+            "description": "Literal text to replace. Must match exactly."
+          },
+          "new_string": {
+            "type": "string",
+            "description": "Literal replacement text. Use an empty string to delete the match."
+          },
+          "replace_all": {
+            "type": "boolean",
+            "description": "Replace all matches. Defaults to false; when false, old_string must appear exactly once."
+          }
+        },
+        "required": [
+          "file_path",
+          "old_string",
+          "new_string"
+        ]
+      }
+    },
+    {
+      "name": "read",
+      "description": "Read a UTF-8 text file and return line-numbered content.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "file_path": {
+            "type": "string",
+            "description": "Path to read, resolved by the filesystem backend."
+          },
+          "offset": {
+            "type": "number",
+            "description": "1-based first line to return. Defaults to 1."
+          },
+          "limit": {
+            "type": "number",
+            "description": "Maximum number of lines to return. Defaults to 2000."
+          }
+        },
+        "required": [
+          "file_path"
+        ]
+      }
+    },
+    {
+      "name": "skill",
+      "description": "Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "name": {
+            "type": "string",
+            "description": "The exact skill name from the available skills list."
+          }
+        },
+        "required": [
+          "name"
+        ]
+      }
+    },
+    {
+      "name": "subagent",
+      "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "description": {
+            "type": "string",
+            "description": "A short (3-5 word) description of the delegated task, for display."
+          },
+          "prompt": {
+            "type": "string",
+            "description": "The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."
+          }
+        },
+        "required": [
+          "description",
+          "prompt"
+        ]
+      }
+    },
+    {
+      "name": "subagent_fork",
+      "description": "Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "description": {
+            "type": "string",
+            "description": "A short (3-5 word) description of the delegated task, for display."
+          },
+          "prompt": {
+            "type": "string",
+            "description": "The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."
+          }
+        },
+        "required": [
+          "description",
+          "prompt"
+        ]
+      }
+    },
+    {
+      "name": "todo_write",
+      "description": "Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "todos": {
+            "type": "array",
+            "description": "The COMPLETE task list, replacing any previous list.",
+            "items": {
+              "type": "object",
+              "properties": {
+                "content": {
+                  "type": "string",
+                  "description": "What the task is — a short imperative line."
+                },
+                "status": {
+                  "type": "string",
+                  "description": "pending (not started) | in_progress (now) | completed (done).",
+                  "enum": [
+                    "pending",
+                    "in_progress",
+                    "completed"
+                  ]
+                }
+              },
+              "required": [
+                "content",
+                "status"
+              ]
+            }
+          }
+        },
+        "required": [
+          "todos"
+        ]
+      }
+    },
+    {
+      "name": "workflow",
+      "description": "Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return <value>` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise<any>` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise<any[]>` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise<any[]>` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "script": {
+            "type": "string",
+            "description": "The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return <json-value>`)."
+          },
+          "meta": {
+            "type": "object",
+            "description": "The workflow identity block (plain JSON — never code).",
+            "properties": {
+              "name": {
+                "type": "string",
+                "description": "Short kebab-case workflow name."
+              },
+              "description": {
+                "type": "string",
+                "description": "One-line description of what the workflow does."
+              },
+              "whenToUse": {
+                "type": "string",
+                "description": "Optional guidance on when this workflow applies."
+              },
+              "phases": {
+                "type": "array",
+                "description": "Optional phase declarations matched by phase() calls.",
+                "items": {
+                  "type": "object",
+                  "properties": {
+                    "title": {
+                      "type": "string",
+                      "description": "The phase title phase() calls match by exact string."
+                    },
+                    "detail": {
+                      "type": "string",
+                      "description": "Optional one-line description of the phase."
+                    },
+                    "provider": {
+                      "type": "string",
+                      "description": "Optional provider override this phase is expected to use."
+                    },
+                    "model": {
+                      "type": "string",
+                      "description": "Optional model override this phase is expected to use."
+                    }
+                  },
+                  "required": [
+                    "title"
+                  ]
+                }
+              }
+            },
+            "required": [
+              "name",
+              "description"
+            ]
+          },
+          "args": {
+            "type": "object",
+            "description": "Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."
+          }
+        },
+        "required": [
+          "script",
+          "meta"
+        ]
+      }
+    },
+    {
+      "name": "write",
+      "description": "Create or fully replace a UTF-8 text file.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "file_path": {
+            "type": "string",
+            "description": "Path to write, resolved by the filesystem backend."
+          },
+          "content": {
+            "type": "string",
+            "description": "Full UTF-8 text content to write."
+          }
+        },
+        "required": [
+          "file_path",
+          "content"
+        ]
+      }
+    }
+  ],
+  "deltas": []
+}
diff --git a/package.json b/package.json
index 2d7a269f8d..b436a161fe 100644
--- a/package.json
+++ b/package.json
@@ -49,6 +49,7 @@
     "verify-package-readme-limitations": "tsx scripts/verify-package-readme-limitations.ts",
     "verify-node-next-types": "tsx scripts/verify-node-next-types.ts",
     "verify-runtime-closure": "tsx scripts/verify-runtime-closure.ts",
+    "verify-cordis-config": "tsx scripts/verify-cordis-config.ts",
     "gen-cordis-catalog": "tsx scripts/gen-cordis-catalog.ts",
     "gen-rfc-index": "tsx scripts/gen-rfc-index.ts",
     "verify-cordis-catalog": "tsx scripts/gen-cordis-catalog.ts --check",
@@ -64,11 +65,12 @@
     "gen-persistence-catalog": "tsx scripts/gen-persistence-catalog.ts",
     "verify-persistence-catalog": "tsx scripts/gen-persistence-catalog.ts --check",
     "gen-module-graph": "tsx scripts/gen-module-graph.ts",
-    "verify-scoped-dispatch": "tsx scripts/verify-scoped-dispatch.ts",
+    "gen-scoped-events": "tsx scripts/gen-scoped-events.ts",
+    "verify-scoped-events": "tsx scripts/gen-scoped-events.ts --check",
     "verify-module-graph": "tsx scripts/gen-module-graph.ts --check",
     "constraints": "tsx scripts/check-workspace-constraints.ts",
-    "doc-sync": "pnpm run doc-typecheck && pnpm run verify-cordis-catalog && pnpm run verify-cordis-api && pnpm run verify-export-jsdoc && pnpm run verify-tool-catalog && pnpm run verify-config-catalog && pnpm run verify-persistence-catalog && pnpm run verify-doc-graphs && pnpm run verify-scoped-dispatch && pnpm run verify-md-wrap && pnpm run verify-md-links && pnpm run verify-doc-refs && pnpm run verify-package-paths && pnpm run verify-package-readme-model-experience && pnpm run verify-mermaid && pnpm run verify-rfc-classification && pnpm run verify-rfc-format && pnpm run verify-type-equiv && pnpm run verify-translation-pairing && pnpm run verify-doc-budgets && pnpm run verify-package-readme-limitations",
-    "hygiene": "pnpm run knip && pnpm run publint && pnpm run constraints && pnpm run verify-node-next-types && pnpm run verify-runtime-closure",
+    "doc-sync": "pnpm run doc-typecheck && pnpm run verify-cordis-catalog && pnpm run verify-cordis-api && pnpm run verify-export-jsdoc && pnpm run verify-tool-catalog && pnpm run verify-config-catalog && pnpm run verify-persistence-catalog && pnpm run verify-doc-graphs && pnpm run verify-scoped-events && pnpm run verify-md-wrap && pnpm run verify-md-links && pnpm run verify-doc-refs && pnpm run verify-package-paths && pnpm run verify-package-readme-model-experience && pnpm run verify-mermaid && pnpm run verify-rfc-classification && pnpm run verify-rfc-format && pnpm run verify-type-equiv && pnpm run verify-translation-pairing && pnpm run verify-doc-budgets && pnpm run verify-package-readme-limitations",
+    "hygiene": "pnpm run knip && pnpm run publint && pnpm run constraints && pnpm run verify-cordis-config && pnpm run verify-node-next-types && pnpm run verify-runtime-closure",
     "demo:echo": "node --expose-internals --import tsx packages/ui/stdio-agent/src/bin.ts examples/echo-agent/cordis.yml",
     "demo:repl": "node --expose-internals --import tsx packages/ui/stdio-agent/src/bin.ts examples/coding-agent/cordis.yml",
     "demo:code-mode": "node scripts/demo-code-mode.mjs",
@@ -79,6 +81,7 @@
   "devDependencies": {
     "@agentclientprotocol/sdk": "0.25.1",
     "@stylistic/eslint-plugin": "^5.10.0",
+    "@types/js-yaml": "^4.0.9",
     "@types/jsdom": "^28.0.3",
     "@types/mdast": "^4.0.4",
     "@types/node": "^22.20.0",
@@ -86,6 +89,7 @@
     "eslint": "^10.4.1",
     "eslint-plugin-sonarjs": "^4.1.0",
     "fast-check": "^4.8.0",
+    "js-yaml": "^4.2.0",
     "jscpd": "^5.0.12",
     "jsdom": "29.1.1",
     "knip": "^6.16.1",
diff --git a/packages/core/session/README.md b/packages/core/session/README.md
index 05499fe353..e5b8c9fd36 100644
--- a/packages/core/session/README.md
+++ b/packages/core/session/README.md
@@ -35,7 +35,7 @@ Plain class (not a Cordis Service). Create via `ctx.sessions.create()`.
 - `session.append(type, data, opts?)` snapshots and freezes durable data and surface metadata, commits synchronously, then notifies observers with independent failure containment. Reentrant attached-session appends reject, and runtime checks cover widened unions and loaded logs.
 - `session.deriveMessages()` incrementally projects each new surface node once and returns a fresh array over shared frozen messages. Assistant projections preserve provider/model provenance and adapter-private replay state. A surface rewrite rebuilds the projection; there is no raw-log fallback.
 - `session.deriveEventMessage(event)` is the canonical per-event projection used by reconstruction and invariants.
-- `session.surface` lazily folds only new `surfaceOp` markers; `replaceGeneration` changes on every rewrite or invalidation.
+- `session.surface` lazily folds only new `surfaceOp` markers; `replaceGeneration` changes on every rewrite.
 - `session.events` is a cached frozen snapshot invalidated by append; accepted events remain deeply frozen.
 - `session.seq`, `session.id` — current sequence and readonly typed identity.
 - `session.header: SessionHeader` — detached, deep-frozen creation metadata (`version`, `id`, `createdAt`, optional `cwd`/`parentSession`/`seedLength`). Construction validates the durable record and requires its id to match `session.id`.
diff --git a/packages/core/session/src/index.ts b/packages/core/session/src/index.ts
index 6215cec736..3575bd73ff 100644
--- a/packages/core/session/src/index.ts
+++ b/packages/core/session/src/index.ts
@@ -41,6 +41,7 @@ declare module 'cordis' {
      * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners
      * receive only sessions entered through that agent's context.
      * @param session - the session just entered and announced.
+     * @dshScopeScan unsupported
      * @mode emit
      */
     'session/created'(this: Scoped<Session>, session: Session): void
@@ -50,6 +51,7 @@ declare module 'cordis' {
      * did not begin. Listener failures are logged and contained.
      * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`) reuses the owner scope.
      * @param session - the session that is no longer live in the store.
+     * @dshScopeScan unsupported
      * @mode emit
      */
     'session/disposed'(this: Scoped<Session>, session: Session): void
@@ -61,6 +63,7 @@ declare module 'cordis' {
      * receive only events from sessions entered through that agent's context.
      * @param session - the session whose log grew.
      * @param event - the appended event, exactly as recorded.
+     * @dshScopeScan unsupported
      * @mode emit
      */
     'session/event'(this: Scoped<Session>, session: Session, event: SessionEvent): void
@@ -70,6 +73,7 @@ declare module 'cordis' {
      * {@link SessionStore.flush}. Scope-filtered dispatch
      * (`@deepseek-ai/dsh-scope`) reuses the session's owner scope.
      * @param session - the session whose buffered events must reach durable storage.
+     * @dshScopeScan unsupported
      * @mode parallel
      */
     'session/flush'(this: Scoped<Session>, session: Session): Promise<void> | void
diff --git a/packages/core/session/src/surface.ts b/packages/core/session/src/surface.ts
index 5f7dac8254..37eebbf7c3 100644
--- a/packages/core/session/src/surface.ts
+++ b/packages/core/session/src/surface.ts
@@ -193,26 +193,14 @@ export function foldSurface(events: readonly SessionEvent[]): SurfaceFoldResult
 export class SurfaceManager {
   /** Incremental state shared with the complete surface fold. */
   private _state = createFoldState()
-  /** The last processed seq. -1 forces a full rebuild on first access. */
+  /** The last processed seq. -1 folds the seeded log on first access. */
   private _lastProcessedSeq = -1
 
   constructor(private log: readonly SessionEvent[]) {}
 
   /**
-   * Reset to unprocessed state. Call after the log has been replaced
-   * wholesale (e.g. after Session seed). Not needed for normal appends —
-   * those are picked up incrementally.
-   */
-  invalidate(): void {
-    this._lastProcessedSeq = -1
-    // A wholesale rebuild is a rewrite: bump the generation so incremental
-    // consumers (the session's derived-message cache) discard their view.
-    this._state = createFoldState(this._state.replaceGeneration + 1)
-  }
-
-  /**
-   * The surface's rewrite generation: bumped by every folded `replace` op and
-   * by {@link invalidate}. A replace is the ONE operation that rewrites the
+   * The surface's rewrite generation, bumped by every folded `replace` op.
+   * A replace is the ONE operation that rewrites the
    * surface non-monotonically, so an incremental consumer of {@link nodes}
    * (the session's derived-message cache) compares this between visits — an
    * unchanged generation guarantees every node it has not seen is a pure tail
diff --git a/packages/core/session/tests/derived-cache.spec.ts b/packages/core/session/tests/derived-cache.spec.ts
index 9012ba5151..8cead0642e 100644
--- a/packages/core/session/tests/derived-cache.spec.ts
+++ b/packages/core/session/tests/derived-cache.spec.ts
@@ -1,6 +1,6 @@
 /**
  * Derived-message cache contract against a scratch oracle: project new nodes
- * once, rebuild on surface generation changes, return fresh arrays over shared
+ * once, rebuild on surface replacements, return fresh arrays over shared
  * frozen messages, and remain value-equal to replay at every step.
  */
 
@@ -61,16 +61,6 @@ describe('derived-message cache', () => {
     expect(Object.isFrozen(first[0])).toBe(true)
   })
 
-  it('rebuilds after surface.invalidate() (the generation covers wholesale rebuilds too)', () => {
-    const session = new Session(SessionId('cache-invalidate'))
-    session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
-    userText(session, 'one')
-    const before = session.deriveMessages()
-    session.surface.invalidate()
-    const after = session.deriveMessages()
-    expect(after).toEqual(before)
-    expect(after[0]).not.toBe(before[0])
-  })
 })
 
 describe('Session.deriveEventMessage — the per-event projection', () => {
diff --git a/packages/core/session/tests/surface.spec.ts b/packages/core/session/tests/surface.spec.ts
index b2452fac53..434ec13bc4 100644
--- a/packages/core/session/tests/surface.spec.ts
+++ b/packages/core/session/tests/surface.spec.ts
@@ -81,14 +81,6 @@ describe('SurfaceManager', () => {
     expect(nodes[1]!.next).toBeNull()
   })
 
-  it('invalidate resets to full rebuild', () => {
-    const s = surfaceSession()
-    expect(s.surface.nodes.length).toBe(2)
-    // After invalidate, the surface should rebuild from scratch on next access.
-    ;(s.surface).invalidate()
-    expect(s.surface.nodes.length).toBe(2) // same result, but rebuilt
-  })
-
   it('empty surface yields empty nodes', () => {
     const s = new Session(SessionId('empty'))
     // Only turn boundaries, no surface nodes.
@@ -386,7 +378,7 @@ describe('surface type guards', () => {
 })
 
 describe('SurfaceManager.replaceGeneration', () => {
-  it('folds the pending log delta on access and counts replaces and invalidations', () => {
+  it('folds the pending log delta on access and counts replaces', () => {
     const s = new Session(SessionId('gen'))
     s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
     s.append('user/message', { content: [{ type: 'text', text: 'one' }], source: { kind: 'user' } }, { surfaceOp: 'append' })
@@ -400,10 +392,5 @@ describe('SurfaceManager.replaceGeneration', () => {
       content: [{ type: 'text', text: 'summary' }], source: { kind: 'plugin', plugin: 'compact' },
     }, { surfaceOp: { op: 'replace', start: nodes[0]!.seq, end: nodes[1]!.seq }, sourceEventSeqs: [nodes[0]!.seq, nodes[1]!.seq] })
     expect(s.surface.replaceGeneration).toBe(1)
-
-    // invalidate() is a rewrite too: the generation moves forward (and the
-    // refold re-counts the replace), never backwards.
-    s.surface.invalidate()
-    expect(s.surface.replaceGeneration).toBeGreaterThan(1)
   })
 })
diff --git a/packages/session-persistence/session-persistence-jsonl/src/index.ts b/packages/session-persistence/session-persistence-jsonl/src/index.ts
index d5922afa94..1d13ff424e 100644
--- a/packages/session-persistence/session-persistence-jsonl/src/index.ts
+++ b/packages/session-persistence/session-persistence-jsonl/src/index.ts
@@ -14,7 +14,7 @@ import {
   SessionPersistence, PersistenceCoordinator,
   type PersistenceBackend, type StoredPrefix,
 } from '@deepseek-ai/dsh-session-persistence'
-import type { Session, SessionEvent, SessionId, SessionHeader } from '@deepseek-ai/dsh-session'
+import type { SessionEvent, SessionId, SessionHeader } from '@deepseek-ai/dsh-session'
 import {
   encodeSegment, eventLine, logPath, parseHeaderMeta, scanLog, sessionDir, toHeaderLine,
 } from './format.ts'
@@ -83,15 +83,7 @@ export class SessionPersistenceJsonl extends SessionPersistence implements Persi
   // One method serves both public `list` and the backend hook; delegating it to
   // the coordinator would call this hook recursively.
 
-  /**
-   * The per-session init promises, exposed for white-box tests that await a
-   * specific session's onCreated (there is no public API to await one init).
-   */
-  get inits(): Map<Session, Promise<void>> {
-    return this.coordinator.inits
-  }
   /* jscpd:ignore-end */
-
   // --- PersistenceBackend hooks (the file-bytes storage primitives) ---
 
   /** Read a stored prefix by id across all cwd buckets when cwd is unknown. */
diff --git a/packages/session-persistence/session-persistence-jsonl/tests/jsonl.spec.ts b/packages/session-persistence/session-persistence-jsonl/tests/jsonl.spec.ts
index 8357246c4e..60333ee01f 100644
--- a/packages/session-persistence/session-persistence-jsonl/tests/jsonl.spec.ts
+++ b/packages/session-persistence/session-persistence-jsonl/tests/jsonl.spec.ts
@@ -488,12 +488,11 @@ describe('SessionPersistenceJsonl: edge cases', () => {
 
     // A new Session object reuses the id. Object-keyed initialization must run independently,
     // detect the disk collision, and reject instead of appending through session A's stale cursor.
-    const backend = ctx.sessionPersistence as unknown as { inits: Map<Session, Promise<void>> }
     let b!: Session
     await ctx.plugin(Object.assign((inner: Context) => {
       b = inner.sessions.create(SessionId('reuse'), { meta: { cwd: '/a' } })
     }, { inject: ['sessions'] }))
-    await expect(backend.inits.get(b)).rejects.toThrow(/already bound to a different live session|already has a persisted log on disk/)
+    await expect(ctx.sessions.flush(b)).rejects.toThrow(/already bound to a different live session|already has a persisted log on disk/)
   })
 
   it('a NO-CWD live session does NOT cross-cwd-adopt a same-id log from a real cwd bucket (loadLive is scope-exact)', async () => {
@@ -511,12 +510,11 @@ describe('SessionPersistenceJsonl: edge cases', () => {
     const ctx2 = new Context()
     await ctx2.plugin(SessionStore)
     await ctx2.plugin(SessionPersistenceJsonl, { root })
-    const backend = ctx2.sessionPersistence as unknown as { inits: Map<Session, Promise<void>> }
     let b!: Session
     await ctx2.plugin(Object.assign((inner: Context) => {
       b = inner.sessions.create(SessionId('x')) // no cwd
     }, { inject: ['sessions'] }))
-    await expect(backend.inits.get(b)).rejects.toThrow(/already has a persisted log on disk/)
+    await expect(ctx2.sessions.flush(b)).rejects.toThrow(/already has a persisted log on disk/)
 
     // The "/w" log is untouched — no no-cwd events were grafted onto it, and no
     // `_no-cwd` log for "x" was created.
@@ -533,7 +531,6 @@ describe('SessionPersistenceJsonl: edge cases', () => {
     await ctx.sessionPersistence.append(SessionId('divergent'), oneTurnLog())
     await ctx.sessionPersistence.load(SessionId('divergent'))
 
-    const backend = ctx.sessionPersistence as unknown as { inits: Map<Session, Promise<void>> }
     // A seed that keeps every seq/type/time but mutates a payload must NOT be
     // accepted as "the same session" — otherwise drain filters those seqs as
     // already persisted and the divergent payload is silently lost.
@@ -544,7 +541,7 @@ describe('SessionPersistenceJsonl: edge cases', () => {
     await ctx.plugin(Object.assign((inner: Context) => {
       bad = inner.sessions.create(SessionId('divergent'), { seed: tampered, meta: { cwd: '/a' } })
     }, { inject: ['sessions'] }))
-    await expect(backend.inits.get(bad)).rejects.toThrow(/do not match this live session|already has a persisted log/)
+    await expect(ctx.sessions.flush(bad)).rejects.toThrow(/do not match this live session|already has a persisted log/)
   })
 
   it('a second live session reusing a bound id is rejected', async () => {
@@ -557,12 +554,11 @@ describe('SessionPersistenceJsonl: edge cases', () => {
     for (const s of ctx.sessions.list()) await ctx.parallel('session/flush', s)
     await firstFiber.dispose()
 
-    const backend = ctx.sessionPersistence as unknown as { inits: Map<Session, Promise<void>> }
     let second!: Session
     await ctx.plugin(Object.assign((inner: Context) => {
       second = inner.sessions.create(SessionId('bound'), { meta: { cwd: '/a' } })
     }, { inject: ['sessions'] }))
-    await expect(backend.inits.get(second))
+    await expect(ctx.sessions.flush(second))
       .rejects.toThrow(/already bound to a different live session|already has a persisted log|do not match/)
   })
 
@@ -594,12 +590,11 @@ describe('SessionPersistenceJsonl: edge cases', () => {
     await ctx2.plugin(SessionStore)
     await ctx2.plugin(SessionPersistenceJsonl, { root })
     await writeFile(sessionDir(root, cwd), 'x') // bucket path is now a FILE
-    const backend = ctx2.sessionPersistence as unknown as { inits: Map<Session, Promise<void>> }
     let s!: Session
     await ctx2.plugin(Object.assign((inner: Context) => {
       s = inner.sessions.create(SessionId('exists-fault'), { meta: { cwd } })
     }, { inject: ['sessions'] }))
-    await expect(backend.inits.get(s)).rejects.toThrow(/ENOTDIR/)
+    await expect(ctx2.sessions.flush(s)).rejects.toThrow(/ENOTDIR/)
     await ctx2.fiber.dispose()
   })
 
diff --git a/packages/session-persistence/session-persistence-sqlite/src/index.ts b/packages/session-persistence/session-persistence-sqlite/src/index.ts
index 32b8f4ade8..7d23292e9d 100644
--- a/packages/session-persistence/session-persistence-sqlite/src/index.ts
+++ b/packages/session-persistence/session-persistence-sqlite/src/index.ts
@@ -14,7 +14,7 @@ import {
   SessionPersistence, PersistenceCoordinator,
   type PersistenceBackend, type StoredPrefix,
 } from '@deepseek-ai/dsh-session-persistence'
-import type { Session, SessionEvent, SurfaceEventType, SessionId, SessionHeader } from '@deepseek-ai/dsh-session'
+import type { SessionEvent, SurfaceEventType, SessionId, SessionHeader } from '@deepseek-ai/dsh-session'
 import {
   type JournalMode, openDatabase, rowToMeta, scanRows, type EventRow, type SessionRow,
 } from './schema.ts'
@@ -110,14 +110,6 @@ export class SessionPersistenceSqlite extends SessionPersistence implements Pers
   // One method serves both public `list` and the backend hook; delegating it to
   // the coordinator would call this hook recursively.
 
-  /**
-   * The per-session init promises, exposed for white-box tests that await a
-   * specific session's onCreated (there is no public API to await one init).
-   */
-  get inits(): Map<Session, Promise<void>> {
-    return this.coordinator.inits
-  }
-
   // --- PersistenceBackend hooks (the SQLite storage primitives) ---
 
   /** Read a stored prefix by id (ids are globally unique — no scope to scan). */
diff --git a/packages/session-persistence/session-persistence/src/coordinator.ts b/packages/session-persistence/session-persistence/src/coordinator.ts
index cbdb9ba25f..4a2fed8d34 100644
--- a/packages/session-persistence/session-persistence/src/coordinator.ts
+++ b/packages/session-persistence/session-persistence/src/coordinator.ts
@@ -8,7 +8,6 @@
 import { Context } from 'cordis'
 import { interruptedTurnClosers, SESSION_FORMAT_VERSION, snapshotJsonValue } from '@deepseek-ai/dsh-session'
 import type { Session, SessionEvent, SessionId, SessionHeader } from '@deepseek-ai/dsh-session'
-import { seedCoversPrefix } from './index.ts'
 
 /**
  * A stored session's header, valid contiguous event prefix, and optional opaque
@@ -110,6 +109,15 @@ async function settledErrors(promises: Iterable<Promise<unknown>>): Promise<unkn
   return errors
 }
 
+/** Whether a live session seed reproduces a persisted prefix exactly. */
+function seedCoversPrefix(seed: readonly SessionEvent[], prefix: readonly SessionEvent[]): boolean {
+  return prefix.length <= seed.length
+    && prefix.every((event, index) => {
+      const seedEvent = seed[index]
+      return seedEvent !== undefined && JSON.stringify(seedEvent) === JSON.stringify(event)
+    })
+}
+
 /**
  * Owns the backend-agnostic session write-path orchestration. A backend
  * constructs one (`new PersistenceCoordinator(ctx, this)`), implements
@@ -134,10 +142,10 @@ export class PersistenceCoordinator<TornMarker = unknown> {
   private chains = new Map<SessionId, Promise<unknown>>()
   /**
    * Init promises keyed by live session object, preventing an id-reusing
-   * replacement from inheriting stale initialization. Readonly access supports
-   * backend white-box tests.
+   * replacement from inheriting stale initialization. Flush is the public
+   * observation boundary; callers do not inspect this bookkeeping directly.
    */
-  readonly inits = new Map<Session, Promise<void>>()
+  private inits = new Map<Session, Promise<void>>()
 
   constructor(private ctx: Context, private backend: PersistenceBackend<TornMarker>) {
     this.installWritePath()
diff --git a/packages/session-persistence/session-persistence/src/index.ts b/packages/session-persistence/session-persistence/src/index.ts
index 87bbdde129..3e6c9c21ed 100644
--- a/packages/session-persistence/session-persistence/src/index.ts
+++ b/packages/session-persistence/session-persistence/src/index.ts
@@ -6,7 +6,6 @@
  */
 
 import { Context, Service } from 'cordis'
-import { snapshotJsonValue } from '@deepseek-ai/dsh-session'
 import type { SessionEvent, SessionId, SessionHeader } from '@deepseek-ai/dsh-session'
 
 // Re-export the metadata vocabulary so consumers import it from the seam.
@@ -22,35 +21,6 @@ declare module 'cordis' {
   }
 }
 
-/**
- * Check whether a live seed exactly reproduces a durable prefix, including full
- * payloads. This distinguishes resume/HMR rebinding from an id collision.
- * @param seed - the live session's creation-time event snapshot.
- * @param prefix - the persisted prefix the seed must reproduce.
- * @returns `true` when the prefix fits within the seed and every event matches by JSON text.
- */
-export function seedCoversPrefix(seed: readonly SessionEvent[], prefix: readonly SessionEvent[]): boolean {
-  return prefix.length <= seed.length
-    && prefix.every((event, index) => {
-      const seedEvent = seed[index]
-      return seedEvent !== undefined && JSON.stringify(seedEvent) === JSON.stringify(event)
-    })
-}
-
-/**
- * Reject a batch that is not wholly losslessly JSON-serializable. Live session
- * appends already enforce this; persistence append paths also accept replay or
- * direct batches that may bypass a live session instance. Validation uses the
- * same one-pass materializer as the coordinator, so getters are read once.
- * @param events - the complete event batch to validate.
- */
-export function assertSerializable(events: readonly SessionEvent[]): void {
-  const snapshot = snapshotJsonValue(events)
-  if (snapshot === undefined) {
-    throw new Error('session event batch is not losslessly JSON-serializable because it contains non-JSON-serializable data')
-  }
-}
-
 /**
  * Durable append-only session storage. Implementations preserve contiguous,
  * losslessly JSON-serializable events; {@link append} resolves only after
diff --git a/packages/session-persistence/session-persistence/tests/coordinator-contract.ts b/packages/session-persistence/session-persistence/tests/coordinator-contract.ts
index ffe5c7f6bd..f6692b9175 100644
--- a/packages/session-persistence/session-persistence/tests/coordinator-contract.ts
+++ b/packages/session-persistence/session-persistence/tests/coordinator-contract.ts
@@ -13,7 +13,6 @@ import { describe, expect, it } from 'vitest'
 import { Context, type Fiber } from 'cordis'
 import SessionStore, { SESSION_FORMAT_VERSION, SessionId } from '@deepseek-ai/dsh-session'
 import type { Session, SessionEvent } from '@deepseek-ai/dsh-session'
-import type { SessionPersistence } from '../src/index.ts'
 import { meta, oneTurnLog, appendLog } from './contract.ts'
 
 /**
@@ -39,11 +38,6 @@ export interface CoordinatorFixture {
 const WORK = '/w'
 const OTHER = '/other'
 
-/** The per-session init map a backend exposes for white-box init awaits. */
-function inits(persistence: SessionPersistence): Map<Session, Promise<void>> {
-  return (persistence as unknown as { inits: Map<Session, Promise<void>> }).inits
-}
-
 /** Append a whole event log to a live session, event by event (drives session/event). */
 function send(session: Session, events: readonly SessionEvent[]): void {
   appendLog(session, events)
@@ -168,7 +162,7 @@ export function runCoordinatorContract(name: string, makeFixture: () => Promise<
         const seed = oneTurnLog()
         // A fork: a brand-new id whose seed came from elsewhere.
         const forked = ctx.sessions.create(SessionId('forked'), { seed, meta: { cwd: WORK } })
-        await inits(ctx.sessionPersistence).get(forked) // onCreated persisted the seed
+        await ctx.sessions.flush(forked) // onCreated persisted the seed
         const loaded = await ctx.sessionPersistence.load(SessionId('forked'))
         expect(loaded.events).toEqual(seed)
         // A flush with no NEW events must not double-write.
@@ -197,7 +191,7 @@ export function runCoordinatorContract(name: string, makeFixture: () => Promise<
       try {
         const loaded = await second.ctx.sessionPersistence.load(SessionId('resumed'))
         const s2 = second.ctx.sessions.create(SessionId('resumed'), { seed: loaded.events, meta: { cwd: WORK } })
-        await inits(second.ctx.sessionPersistence).get(s2) // let onCreated adopt
+        await second.ctx.sessions.flush(s2) // let onCreated adopt
         s2.append('turn/start', { turn: 2, trigger: { kind: 'message', source: { kind: 'user' } } })
         s2.append('turn/end', { turn: 2, reason: { kind: 'completed' } })
         await second.ctx.parallel('session/flush', s2)
@@ -370,7 +364,7 @@ export function runCoordinatorContract(name: string, makeFixture: () => Promise<
       try {
         const s2 = second.ctx.sessions.create(SessionId('collide'), { meta: { cwd: WORK } })
         s2.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
-        await expect(inits(second.ctx.sessionPersistence).get(s2))
+        await expect(second.ctx.sessions.flush(s2))
           .rejects.toThrow(/already has a persisted log|id collision/)
       } finally {
         await second.fiber.dispose()
@@ -388,14 +382,14 @@ export function runCoordinatorContract(name: string, makeFixture: () => Promise<
         const firstFiber = await ctx.plugin(Object.assign((inner: Context) => {
           firstSession = inner.sessions.create(SessionId('abandoned'), { meta: { cwd: WORK } })
         }, { inject: ['sessions'] }))
-        await inits(ctx.sessionPersistence).get(firstSession) // register the lazy state
+        await ctx.sessions.flush(firstSession) // register the lazy state
         await firstFiber.dispose() // disposed before any append → never materialized
 
         let reuse!: Session
         await ctx.plugin(Object.assign((inner: Context) => {
           reuse = inner.sessions.create(SessionId('abandoned'), { meta: { cwd: WORK } })
         }, { inject: ['sessions'] }))
-        await expect(inits(ctx.sessionPersistence).get(reuse)).resolves.toBeUndefined()
+        await expect(ctx.sessions.flush(reuse)).resolves.toBeUndefined()
         reuse.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
         reuse.append('turn/end', { turn: 1, reason: { kind: 'completed' } })
         await ctx.parallel('session/flush', reuse)
@@ -415,7 +409,7 @@ export function runCoordinatorContract(name: string, makeFixture: () => Promise<
         const firstFiber = await ctx.plugin(Object.assign((inner: Context) => {
           first = inner.sessions.create(SessionId('buffered'), { meta: { cwd: WORK } })
         }, { inject: ['sessions'] }))
-        await inits(ctx.sessionPersistence).get(first)
+        await ctx.sessions.flush(first)
         // Append a turn but do NOT flush — events sit in the write-behind buffer.
         first.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
         first.append('turn/end', { turn: 1, reason: { kind: 'completed' } })
@@ -425,7 +419,7 @@ export function runCoordinatorContract(name: string, makeFixture: () => Promise<
         await ctx.plugin(Object.assign((inner: Context) => {
           reuse = inner.sessions.create(SessionId('buffered'), { meta: { cwd: WORK } })
         }, { inject: ['sessions'] }))
-        await expect(inits(ctx.sessionPersistence).get(reuse)).rejects.toThrow(/already bound to a different live session/)
+        await expect(ctx.sessions.flush(reuse)).rejects.toThrow(/already bound to a different live session/)
       } finally {
         await fiber.dispose()
         await fix.cleanup()
@@ -462,7 +456,7 @@ export function runCoordinatorContract(name: string, makeFixture: () => Promise<
         // A live session with that id arrives and claims it (cursor 0 matches
         // trivially), persisting its seed.
         const live = ctx.sessions.create(SessionId('lazy-claim'), { seed: oneTurnLog(), meta: { cwd: WORK } })
-        await expect(inits(ctx.sessionPersistence).get(live)).resolves.toBeUndefined()
+        await expect(ctx.sessions.flush(live)).resolves.toBeUndefined()
         const loaded = await ctx.sessionPersistence.load(SessionId('lazy-claim'))
         expect(loaded.events.map(e => e.seq)).toEqual([0, 1, 2, 3, 4, 5])
       } finally {
@@ -487,7 +481,7 @@ export function runCoordinatorContract(name: string, makeFixture: () => Promise<
         await ctx.plugin(Object.assign((inner: Context) => {
           fresh = inner.sessions.create(SessionId('preview'), { meta: { cwd: WORK } })
         }, { inject: ['sessions'] }))
-        await expect(inits(ctx.sessionPersistence).get(fresh))
+        await expect(ctx.sessions.flush(fresh))
           .rejects.toThrow(/do not match this live session|already has a persisted log|id collision/)
       } finally {
         await fiber.dispose()
@@ -511,7 +505,7 @@ export function runCoordinatorContract(name: string, makeFixture: () => Promise<
           { type: 'turn/start', seq: 6, time: 7, data: { turn: 2, trigger: { kind: 'message', source: { kind: 'user' } } } },
           { type: 'turn/end', seq: 7, time: 8, data: { turn: 2, reason: { kind: 'completed' } } },
         ], meta: { cwd: WORK } })
-        await inits(ctx.sessionPersistence).get(cont)
+        await ctx.sessions.flush(cont)
         const loaded = await ctx.sessionPersistence.load(SessionId('claim'))
         expect(loaded.events.map(e => e.seq)).toEqual([0, 1, 2, 3, 4, 5, 6, 7])
       } finally {
@@ -531,7 +525,7 @@ export function runCoordinatorContract(name: string, makeFixture: () => Promise<
         // cwd scope is the fence (without it, WORK events would append under the
         // OTHER header). Rejected as a collision.
         const live = ctx.sessions.create(SessionId('wrong-cwd-claim'), { seed: oneTurnLog(), meta: { cwd: WORK } })
-        await expect(inits(ctx.sessionPersistence).get(live)).rejects.toThrow(/different cwd|id collision/)
+        await expect(ctx.sessions.flush(live)).rejects.toThrow(/different cwd|id collision/)
       } finally {
         await fiber.dispose()
         await fix.cleanup()
@@ -549,7 +543,7 @@ export function runCoordinatorContract(name: string, makeFixture: () => Promise<
         // A live session whose SEED matches the loaded prefix but whose cwd is
         // WORK must still be rejected — the cwd guard runs before the seed check.
         const live = ctx.sessions.create(SessionId('wrong-cwd-load'), { seed: events, meta: { cwd: WORK } })
-        await expect(inits(ctx.sessionPersistence).get(live)).rejects.toThrow(/different cwd|id collision/)
+        await expect(ctx.sessions.flush(live)).rejects.toThrow(/different cwd|id collision/)
       } finally {
         await fiber.dispose()
         await fix.cleanup()
@@ -565,7 +559,7 @@ export function runCoordinatorContract(name: string, makeFixture: () => Promise<
         // A live session reusing the id but WITH cwd WORK is a cwd mismatch
         // (undefined vs WORK) and must be rejected.
         const live = ctx.sessions.create(SessionId('no-cwd-state'), { seed: oneTurnLog(), meta: { cwd: WORK } })
-        await expect(inits(ctx.sessionPersistence).get(live)).rejects.toThrow(/different cwd|id collision/)
+        await expect(ctx.sessions.flush(live)).rejects.toThrow(/different cwd|id collision/)
       } finally {
         await fiber.dispose()
         await fix.cleanup()
diff --git a/packages/session-persistence/session-persistence/tests/persistence.spec.ts b/packages/session-persistence/session-persistence/tests/persistence.spec.ts
index 13943d35a7..a937a39da7 100644
--- a/packages/session-persistence/session-persistence/tests/persistence.spec.ts
+++ b/packages/session-persistence/session-persistence/tests/persistence.spec.ts
@@ -1,9 +1,9 @@
 import { describe, expect, it } from 'vitest'
 import { Context } from 'cordis'
 import SessionStore, { SessionId, isJsonValue } from '@deepseek-ai/dsh-session'
-import type { Session, SessionEvent, SessionHeader } from '@deepseek-ai/dsh-session'
+import type { SessionEvent, SessionHeader } from '@deepseek-ai/dsh-session'
 import {
-  SessionPersistence, PersistenceCoordinator, assertSerializable, seedCoversPrefix,
+  SessionPersistence, PersistenceCoordinator,
   type PersistenceBackend, type StoredPrefix,
 } from '../src/index.ts'
 import { runPersistenceContract, meta, oneTurnLog } from './contract.ts'
@@ -53,11 +53,6 @@ class MemoryPersistence extends SessionPersistence implements PersistenceBackend
     return this.coordinator.load(id)
   }
 
-  /** White-box accessor: await a specific session's onCreated init. */
-  get inits(): Map<Session, Promise<void>> {
-    return this.coordinator.inits
-  }
-
   // --- PersistenceBackend hooks (the Map storage primitives) ---
 
   // A Map-backed store has no torn tails, so `tornMarker` is never set. Ids are
@@ -157,38 +152,3 @@ describe('SessionPersistence service registration', () => {
     await fiber.dispose()
   })
 })
-
-describe('shared persistence helpers', () => {
-  it('accepts a seed that reproduces the persisted prefix exactly', () => {
-    const log = oneTurnLog()
-    expect(seedCoversPrefix(log, log.slice(0, 3))).toBe(true)
-    expect(seedCoversPrefix(log, [])).toBe(true)
-  })
-
-  it('rejects a prefix longer than the seed', () => {
-    const log = oneTurnLog()
-    expect(seedCoversPrefix(log.slice(0, 2), log)).toBe(false)
-  })
-
-  it('rejects a same-envelope event with mutated data', () => {
-    const log = oneTurnLog()
-    const tampered = structuredClone(log)
-    const event = tampered[1]!
-    tampered[1] = {
-      ...event,
-      data: { ...event.data, content: [{ type: 'text', text: 'tampered' }] },
-    } as SessionEvent
-    expect(seedCoversPrefix(tampered, log.slice(0, 2))).toBe(false)
-  })
-
-  it('accepts JSON-serializable event data', () => {
-    expect(() => { assertSerializable(oneTurnLog()) }).not.toThrow()
-  })
-
-  it('rejects a batch containing non-JSON-serializable event data', () => {
-    const bad = [
-      { type: 'user/message', seq: 0, time: 1, data: { content: 1n } },
-    ] as unknown as SessionEvent[]
-    expect(() => { assertSerializable(bad) }).toThrow(/batch is not losslessly JSON-serializable/)
-  })
-})
diff --git a/packages/subagent/subagent/src/index.ts b/packages/subagent/subagent/src/index.ts
index 4635de9697..8657e7d06e 100644
--- a/packages/subagent/subagent/src/index.ts
+++ b/packages/subagent/subagent/src/index.ts
@@ -77,6 +77,7 @@ declare module 'cordis' {
      * parent-scoped listener observes only its own delegations. Paired with
      * `subagent/end`.
      * @param info - the provider and ready child identity.
+     * @dshScopeScan unsupported
      * @mode emit
      */
     'subagent/start'(this: Scoped<SubagentService>, info: SubagentRunInfo): void
@@ -85,6 +86,7 @@ declare module 'cordis' {
      * parent carrier as `subagent/start`, so the lifecycle pair reaches the
      * same scoped audience.
      * @param info - the run identity and terminal outcome.
+     * @dshScopeScan unsupported
      * @mode emit
      */
     'subagent/end'(this: Scoped<SubagentService>, info: SubagentRunEndInfo): void
diff --git a/packages/support/acp-snapshot/README.md b/packages/support/acp-snapshot/README.md
index 7835deb432..644ec2853d 100644
--- a/packages/support/acp-snapshot/README.md
+++ b/packages/support/acp-snapshot/README.md
@@ -5,8 +5,8 @@ The ACP snapshot suite kit: the shared machinery behind the keyless snapshot tie
 Three layers, importable separately:
 
 - **`runScenario` (harness)** — boots the real agent bin as a subprocess via tsx (unbuilt, Loader path), drives it over ACP JSON-RPC stdio from a deterministic `input.json` script, tees raw stdout for the golden + purity check, and harvests every persisted session JSONL (parent + subagent children, primary-first) after a graceful stdin-EOF shutdown. Parameterized by `AgentUnderTest` (`binScript`, `configPath`, `tsconfigPath` — absolute paths; the subprocess cwd is a temp dir outside the repo).
-- **Normalizers** — pure functions turning the two captured surfaces into stable text: `normalizeStdout` (JSON-RPC ids → first-seen sequence; UUIDs/cwd → tokens; doubles as the stdout-purity check), `normalizeSessionLog` (times zeroed, `seq` kept), `scrubSystemPrompts` (prompt text → `{{system}}` in every JSONL), and `scrubRequestHeaders` (the remaining header bulk → `{{tools}}`/`{{messagePrefix}}` outside each pin, structure kept — [pinned-header RFC](../../../docs/rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)).
-- **`defineAcpSnapshotSuite` (factory)** — registers the whole describe/it tree for a scenario table: per-scenario golden + re-persisted-log compares, record/refresh fixture write-back, the per-header-class pin (`system-prompt.golden.md` plus the JSONL's full tool schemas) with its live uniformity guard, and the fixture guard block (no orphan scenario dirs, required files present, exactly one pin per class, every JSONL prompt-scrubbed, non-pinning fixtures fully header-scrubbed). Must be called at vitest collection time.
+- **Normalizers** — pure functions turning the two captured surfaces into stable text: `normalizeStdout` (JSON-RPC ids → first-seen sequence; UUIDs/cwd → tokens; doubles as the stdout-purity check), `normalizeSessionLog` (times zeroed, `seq` kept), `scrubSystemPrompts` (prompt text → `{{system}}`), `scrubToolSchemas` (schema bulk → `{{tools}}`), and `scrubRequestHeaders` (all header bulk → `{{system}}`/`{{tools}}`/`{{messagePrefix}}` outside each pin, structure kept — [pinned-header RFC](../../../docs/rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)).
+- **`defineAcpSnapshotSuite` (factory)** — registers the whole describe/it tree for a scenario table: per-scenario golden + re-persisted-log compares, record/refresh fixture write-back, rejection of structured `UNKNOWN_TOOL` results, the per-header-class pin (`system-prompt.golden.md` plus `tool-schemas.golden.json`) with its live uniformity guard, and the fixture guard block (no orphan scenario dirs, required files present, exactly one pin per class, every JSONL prompt/schema-scrubbed, non-pinning fixtures fully header-scrubbed). Must be called at vitest collection time.
 
 A consuming `*.snapshot.ts` is the scenario table plus one factory call:
 
@@ -35,9 +35,9 @@ defineAcpSnapshotSuite({
 })
 ```
 
-A scenario booting a differently-composed tree sets its own `configPath` (an overlay whose basename still ends in `cordis.yml`, so the bin's replay swap finds the sibling `*cordis.snapshot.yml`) and, when that composition changes the request header, its own `headerClass` with its own pinning scenario — the acp-agent example's Code Mode scenarios are the template. Each pinning directory's generated `system-prompt.golden.md` is the reviewable snapshot of the normalized composed prompt; `session.jsonl` stores `"system":"{{system}}"` while retaining the complete tool list.
+A scenario booting a differently-composed tree sets its own `configPath` (an overlay whose basename still ends in `cordis.yml`, so the bin's replay swap finds the sibling `*cordis.snapshot.yml`) and, when that composition changes the request header, its own `headerClass` with its own pinning scenario — the acp-agent example's Code Mode and filesystem scenarios are templates. Each pinning directory stores the normalized composed prompt in generated `system-prompt.golden.md` and the initial schemas plus schema deltas in generated `tool-schemas.golden.json`; `session.jsonl` stores `"system":"{{system}}","tools":"{{tools}}"` while retaining config, reason, and any model-visible prefix.
 
-Examples use a `cordis.snapshot.yml` overlay with [`dsh-llm-replay`](../llm-replay/README.md). Recording calls the live model and updates model fixtures; keyless refresh replays those fixtures and updates derived stdout, session-log, and prompt snapshots. See the [snapshot RFC](../../../docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md).
+Examples use a `cordis.snapshot.yml` overlay with [`dsh-llm-replay`](../llm-replay/README.md). Recording calls the live model and updates model fixtures; keyless refresh replays those fixtures and updates derived stdout, session-log, prompt, and tool-schema snapshots. See the [snapshot RFC](../../../docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md).
 
 `suite.ts` imports Vitest, so use this package only inside a Vitest run. The ACP-specific script queues permission answers by stable option kind and maps them to current option ids; a missing answer cancels, while an unavailable kind fails the scenario after cancelling the agent request. It can also set session config options or assert that unknown ids and values are rejected in the transcript.
 
diff --git a/packages/support/acp-snapshot/src/index.ts b/packages/support/acp-snapshot/src/index.ts
index 5afb7ecf66..bdf8cccaf7 100644
--- a/packages/support/acp-snapshot/src/index.ts
+++ b/packages/support/acp-snapshot/src/index.ts
@@ -20,6 +20,7 @@ export {
   normalizeStdout,
   scrubRequestHeaders,
   scrubSystemPrompts,
+  scrubToolSchemas,
   type NormalizeContext,
 } from './normalize.ts'
 export {
diff --git a/packages/support/acp-snapshot/src/normalize.ts b/packages/support/acp-snapshot/src/normalize.ts
index 81ee42e9e3..e3f32792ab 100644
--- a/packages/support/acp-snapshot/src/normalize.ts
+++ b/packages/support/acp-snapshot/src/normalize.ts
@@ -1,8 +1,8 @@
 /**
  * Pure ACP transcript and session-log normalizers. They scrub session ids, temp cwd, RPC ids,
  * timestamps, and hook duration while preserving deterministic event sequence numbers.
- * Request-header scrubbers stay separate so one scenario per header class can pin tools and a
- * readable prompt while other fixtures omit duplicated header bulk.
+ * Request-header scrubbers stay composable so one scenario per header class can pin prompt and
+ * tool-schema sidecars while retaining any model-visible prefix in the session log.
  * @module @deepseek-ai/dsh-acp-snapshot/normalize
  */
 
@@ -123,7 +123,21 @@ export function normalizeSessionLog(rawLog: string, ctx: NormalizeContext): stri
  * @returns The JSONL with system-prompt content tokenized.
  */
 export function scrubSystemPrompts(rawLog: string): string {
-  return scrubHeaderContent(rawLog, false)
+  return scrubHeaderContent(rawLog, { system: true })
+}
+
+/**
+ * Replace tool schemas in request headers and header deltas with `{{tools}}`
+ * tokens while retaining field presence, tool names, and delta structure.
+ * System prompts and session-prefix messages stay verbatim so pinning fixtures
+ * can move only schema bulk into their dedicated JSON sidecar. Lines without a
+ * tool payload pass through byte-for-byte; the transform is idempotent.
+ *
+ * @param rawLog The raw session `.jsonl` content.
+ * @returns The JSONL with tool-schema content tokenized.
+ */
+export function scrubToolSchemas(rawLog: string): string {
+  return scrubHeaderContent(rawLog, { tools: true })
 }
 
 /**
@@ -138,11 +152,18 @@ export function scrubSystemPrompts(rawLog: string): string {
  * @returns The JSONL with all header bulk tokenized, other lines byte-identical.
  */
 export function scrubRequestHeaders(rawLog: string): string {
-  return scrubHeaderContent(rawLog, true)
+  return scrubHeaderContent(rawLog, { system: true, tools: true, prefix: true })
 }
 
-/** Transform header content, optionally including tool schemas and the session prefix. */
-function scrubHeaderContent(rawLog: string, scrubToolsAndPrefix: boolean): string {
+/** Which independent request-header payloads a scrubber replaces. */
+interface HeaderScrubOptions {
+  system?: boolean
+  tools?: boolean
+  prefix?: boolean
+}
+
+/** Transform the selected request-header payloads. */
+function scrubHeaderContent(rawLog: string, options: HeaderScrubOptions): string {
   const lines = rawLog.split('\n')
   const out = lines.map((line) => {
     if (line.trim().length === 0) return line
@@ -153,9 +174,9 @@ function scrubHeaderContent(rawLog: string, scrubToolsAndPrefix: boolean): strin
       const header = data.header as Record<string, unknown> | null | undefined
       if (header === null || typeof header !== 'object') return line
       let touched = false
-      if ('system' in header) { header.system = SYSTEM; touched = true }
-      if (scrubToolsAndPrefix && 'tools' in header) { header.tools = TOOLS; touched = true }
-      if (scrubToolsAndPrefix && Array.isArray(header.messagePrefix)) {
+      if (options.system === true && 'system' in header) { header.system = SYSTEM; touched = true }
+      if (options.tools === true && 'tools' in header) { header.tools = TOOLS; touched = true }
+      if (options.prefix === true && Array.isArray(header.messagePrefix)) {
         header.messagePrefix = header.messagePrefix.map(() => MESSAGE_PREFIX)
         touched = true
       }
@@ -164,16 +185,16 @@ function scrubHeaderContent(rawLog: string, scrubToolsAndPrefix: boolean): strin
     if (record.type === 'request/header-delta') {
       let touched = false
       const system = data.system as Record<string, unknown> | null | undefined
-      if (system !== null && typeof system === 'object' && Array.isArray(system.insert)) {
+      if (options.system === true && system !== null && typeof system === 'object' && Array.isArray(system.insert)) {
         system.insert = system.insert.map(() => SYSTEM)
         touched = true
       }
       const tools = data.tools as Record<string, unknown> | null | undefined
-      if (scrubToolsAndPrefix && tools !== null && typeof tools === 'object') {
+      if (options.tools === true && tools !== null && typeof tools === 'object') {
         if (Array.isArray(tools.added)) { tools.added = tools.added.map(scrubToolSchema); touched = true }
         if (Array.isArray(tools.changed)) { tools.changed = tools.changed.map(scrubToolSchema); touched = true }
       }
-      if (scrubToolsAndPrefix && Array.isArray(data.messagePrefix)) {
+      if (options.prefix === true && Array.isArray(data.messagePrefix)) {
         data.messagePrefix = data.messagePrefix.map(() => MESSAGE_PREFIX)
         touched = true
       }
diff --git a/packages/support/acp-snapshot/src/suite.ts b/packages/support/acp-snapshot/src/suite.ts
index 8930b03d2f..dc1675eac0 100644
--- a/packages/support/acp-snapshot/src/suite.ts
+++ b/packages/support/acp-snapshot/src/suite.ts
@@ -4,8 +4,8 @@
  * output. Record mode refreshes reproducible model scenarios from the live API, while refresh
  * mode replays committed scripts and rewrites derived artifacts without a key.
  *
- * Exactly one scenario per header-composition class pins tool schemas in JSONL and the system
- * prompt in Markdown. Every live header is checked against that pin, so session-dependent
+ * Exactly one scenario per header-composition class pins the system prompt and tool schemas in
+ * dedicated sidecars. Every live header is checked against that pin, so session-dependent
  * composition must declare a separate class instead of escaping coverage.
  * @module @deepseek-ai/dsh-acp-snapshot/suite
  */
@@ -21,11 +21,18 @@ import {
   normalizeStdout,
   scrubRequestHeaders,
   scrubSystemPrompts,
+  scrubToolSchemas,
 } from './normalize.ts'
 
 /** The readable system-prompt snapshot beside each header-pinning fixture. */
 const SYSTEM_PROMPT_SNAPSHOT = 'system-prompt.golden.md'
 
+/** The structured tool-schema snapshot beside each header-pinning fixture. */
+const TOOL_SCHEMAS_SNAPSHOT = 'tool-schemas.golden.json'
+
+/** Stable session-log token standing in for the sidecar's initial schemas. */
+const TOOLS_TOKEN = '{{tools}}'
+
 /** A snapshot scenario and how its fixtures are produced. */
 export interface Scenario {
   name: string
@@ -68,8 +75,8 @@ export interface Scenario {
    */
   childSessions?: number
   /**
-   * Whether this scenario is its header class's sole request-header pin. Its Markdown file owns
-   * the prompt, its JSONL keeps tool schemas, and every classmate is checked for equality.
+   * Whether this scenario is its header class's sole request-header pin. Dedicated sidecars own
+   * the prompt and tool schemas, while every classmate is checked for equality.
    */
   pinsHeader?: boolean
   /**
@@ -184,6 +191,98 @@ export function normalizedSystemPrompts(rawLog: string, ctx: NormalizeContext):
   })
 }
 
+/**
+ * The normalized tool-schema arrays carried by request headers in a session
+ * JSONL, in log order. Headers without an array-valued tools field are omitted
+ * so callers can assert one schema set per header explicitly.
+ *
+ * @param rawLog The session `.jsonl` content to inspect.
+ * @param ctx The volatile values of the run that produced it.
+ * @returns The normalized initial tool-schema arrays, in header order.
+ */
+export function normalizedToolSchemas(rawLog: string, ctx: NormalizeContext): unknown[][] {
+  return normalizedHeaders(rawLog, ctx).flatMap((header) => {
+    if (header === null || typeof header !== 'object') return []
+    const tools = (header as { tools?: unknown }).tools
+    return Array.isArray(tools) ? [tools] : []
+  })
+}
+
+/**
+ * Extract normalized tool-schema edits from request-header deltas in log order.
+ * Deltas without an object-valued tools edit are omitted; their remaining
+ * structure stays pinned in the session JSONL.
+ *
+ * @param rawLog The session `.jsonl` content to inspect.
+ * @param ctx The volatile values of the run that produced it.
+ * @returns The normalized tool-schema edits, in event order.
+ */
+export function normalizedToolSchemaDeltas(rawLog: string, ctx: NormalizeContext): unknown[] {
+  return normalizeSessionLog(rawLog, ctx)
+    .split('\n')
+    .filter(line => line.trim().length > 0)
+    .map(line => JSON.parse(line) as { type?: unknown; data?: { tools?: unknown } })
+    .filter(record => record.type === 'request/header-delta')
+    .flatMap((record) => {
+      const tools = record.data?.tools
+      return tools !== null && typeof tools === 'object' && !Array.isArray(tools) ? [tools] : []
+    })
+}
+
+/** The structured contents of a tool-schema sidecar. */
+export interface ToolSchemasSnapshot {
+  /** The complete tool schemas from the pinned request header. */
+  initial: unknown[]
+  /** Complete tool-schema edits from subsequent request-header deltas. */
+  deltas: unknown[]
+}
+
+/**
+ * Render tool schemas and later schema edits as canonical, readable JSON.
+ *
+ * @param initial The pinned request header's complete tool schemas.
+ * @param deltas Complete tool-schema edits from request-header deltas.
+ * @returns A pretty-printed JSON snapshot ending in one newline.
+ */
+export function formatToolSchemasSnapshot(initial: readonly unknown[], deltas: readonly unknown[] = []): string {
+  return `${JSON.stringify({ initial, deltas }, null, 2)}\n`
+}
+
+/**
+ * Parse and validate the stable top-level shape of a tool-schema sidecar.
+ *
+ * @param snapshot The JSON sidecar text.
+ * @returns Its initial schemas and schema deltas.
+ */
+export function parseToolSchemasSnapshot(snapshot: string): ToolSchemasSnapshot {
+  const parsed = JSON.parse(snapshot) as unknown
+  if (parsed === null || typeof parsed !== 'object' || Array.isArray(parsed)) {
+    throw new Error('acp-snapshot: tool-schema snapshot must be an object')
+  }
+  const { initial, deltas } = parsed as { initial?: unknown; deltas?: unknown }
+  if (!Array.isArray(initial) || !Array.isArray(deltas)) {
+    throw new Error('acp-snapshot: tool-schema snapshot must carry array-valued initial and deltas fields')
+  }
+  return { initial, deltas }
+}
+
+/**
+ * Restore a sidecar's initial schemas into a tokenized pinned header.
+ *
+ * @param header The parsed request header carrying `tools: "{{tools}}"`.
+ * @param snapshot The parsed tool-schema sidecar.
+ * @returns A copy of the header with its complete initial schemas restored.
+ */
+export function restorePinnedToolSchemas(header: unknown, snapshot: ToolSchemasSnapshot): unknown {
+  if (header === null || typeof header !== 'object' || Array.isArray(header)) {
+    throw new Error('acp-snapshot: pinned request header must be an object')
+  }
+  if ((header as { tools?: unknown }).tools !== TOOLS_TOKEN) {
+    throw new Error(`acp-snapshot: pinned request header tools must equal ${TOOLS_TOKEN}`)
+  }
+  return { ...header, tools: snapshot.initial }
+}
+
 /** One normalized system-prompt edit carried by a `request/header-delta`. */
 export interface SystemPromptDeltaSnapshot {
   /** How many leading lines remain from the prior prompt. */
@@ -274,6 +373,27 @@ function parseJsonlRecords(text: string): Record<string, unknown>[] {
     .map(line => JSON.parse(line) as Record<string, unknown>)
 }
 
+/**
+ * Find tool calls whose structured result reports `UNKNOWN_TOOL`.
+ *
+ * Snapshot refresh must not turn a missing registration into accepted behavior;
+ * intentional unknown-tool behavior belongs in a focused unit or e2e test.
+ *
+ * @param rawLog The session JSONL to inspect.
+ * @returns The failing call ids in log order, using a diagnostic placeholder when absent.
+ */
+export function unknownToolCallIds(rawLog: string): string[] {
+  return parseJsonlRecords(rawLog).flatMap((record) => {
+    if (record.type !== 'tool/result') return []
+    const data = record.data
+    if (data === null || typeof data !== 'object') return []
+    const { callId, error } = data as { callId?: unknown; error?: unknown }
+    if (error === null || typeof error !== 'object') return []
+    if ((error as { code?: unknown }).code !== 'UNKNOWN_TOOL') return []
+    return [typeof callId === 'string' ? callId : '<missing callId>']
+  })
+}
+
 /**
  * Build the cross-log id/cwd replacements used by refresh write-back.
  *
@@ -401,6 +521,11 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void {
           ...scenario.configPath !== undefined ? { configPath: scenario.configPath } : {},
         })
 
+        for (const log of result.sessionLogs) {
+          expect(unknownToolCallIds(log.content), `session ${log.id}: snapshot scenarios must not accept UNKNOWN_TOOL`)
+            .toEqual([])
+        }
+
         // Scrub every volatile id the run produced: the ACP server-issued session id plus every
         // harvested log's recorded id (a subagent child id never surfaces over ACP, but it
         // appears in the child's own log header).
@@ -413,9 +538,9 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void {
         }
 
         // Record writes live model fixtures; keyless refresh writes every comparable replayed
-        // fixture. Pins keep tools but all JSONL files scrub prompt text.
+        // fixture. Pinning JSONL keeps prefixes but moves prompts and schemas into sidecars.
         const scrub = scenario.pinsHeader === true
-          ? scrubSystemPrompts
+          ? (log: string): string => scrubToolSchemas(scrubSystemPrompts(log))
           : scrubRequestHeaders
         const fixtureFiles = ['session.jsonl', ...Array.from({ length: childSessions }, (_, i) => `session.${i + 1}.jsonl`)]
         const existingFixtures = REFRESHING
@@ -452,6 +577,18 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void {
               normalizedSystemPromptDeltas(primary.content, ctx),
             )
             await writeFile(join(dir, SYSTEM_PROMPT_SNAPSHOT), snapshot)
+
+            const schemaSets = result.sessionLogs.flatMap(log => normalizedToolSchemas(log.content, ctx))
+            expect(schemaSets.length, `${mode} produced no tool schemas to snapshot`).toBeGreaterThan(0)
+            const initialSchemaSnapshot = formatToolSchemasSnapshot(schemaSets[0] as unknown[])
+            for (const schemas of schemaSets) {
+              expect(formatToolSchemasSnapshot(schemas), 'the pinning run produced divergent tool schemas')
+                .toEqual(initialSchemaSnapshot)
+            }
+            await writeFile(join(dir, TOOL_SCHEMAS_SNAPSHOT), formatToolSchemasSnapshot(
+              schemaSets[0] as unknown[],
+              normalizedToolSchemaDeltas(primary.content, ctx),
+            ))
           }
         }
 
@@ -475,7 +612,7 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void {
         }
 
         // Header-uniformity guard: every live header in a class must equal the class pin split
-        // across its JSONL header (system token + real tools) and readable Markdown prompt.
+        // across tokenized JSONL plus readable prompt and structured schema sidecars.
         /* v8 ignore next -- construction guarantees the pin exists; a miss would fail the one-header assertion loudly. */
         const pinningScenario = pinningByClass.get(classOf(scenario)) ?? scenario
         const pinningDir = join(snapshotsDir, pinningScenario.name)
@@ -483,8 +620,11 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void {
         const pinned = normalizedHeaders(pinnedFixture, fixtureContext(pinnedFixture))
         const promptSnapshot = await readFile(join(pinningDir, SYSTEM_PROMPT_SNAPSHOT), 'utf8')
         const initialPromptSnapshot = initialSystemPromptSnapshot(promptSnapshot)
+        const toolSchemasSnapshot = await readFile(join(pinningDir, TOOL_SCHEMAS_SNAPSHOT), 'utf8')
+        const toolSchemas = parseToolSchemasSnapshot(toolSchemasSnapshot)
         expect(pinned.length, `the pinning fixture (${pinningScenario.name}) must carry exactly one request/header`)
           .toBe(1)
+        const pinnedHeader = restorePinnedToolSchemas(pinned[0], toolSchemas)
         for (const [logIndex, log] of result.sessionLogs.entries()) {
           const expectedDeltas = scenario.pinsHeader === true && logIndex === 0
             ? scenario.expectedHeaderDeltas ?? 0
@@ -493,11 +633,14 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void {
             .toBe(expectedDeltas)
           const headers = normalizedHeaders(scrubSystemPrompts(log.content), ctx)
           const prompts = normalizedSystemPrompts(log.content, ctx)
+          const schemaSets = normalizedToolSchemas(log.content, ctx)
           expect(prompts.length, `session ${log.id}: every request/header must carry a string system prompt`)
             .toBe(headers.length)
+          expect(schemaSets.length, `session ${log.id}: every request/header must carry an array-valued tools field`)
+            .toBe(headers.length)
           for (const [k, header] of headers.entries()) {
             expect(header, `session ${log.id}: request/header #${k + 1} diverged from the pinned (${pinningScenario.name}) header`)
-              .toEqual(pinned[0])
+              .toEqual(pinnedHeader)
             expect(formatSystemPromptSnapshot(prompts[k] as string), `session ${log.id}: initial system prompt #${k + 1} diverged from ${pinningScenario.name}/${SYSTEM_PROMPT_SNAPSHOT}`)
               .toEqual(initialPromptSnapshot)
           }
@@ -507,6 +650,11 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void {
               normalizedSystemPromptDeltas(log.content, ctx),
             ), `session ${log.id}: system-prompt deltas diverged from ${pinningScenario.name}/${SYSTEM_PROMPT_SNAPSHOT}`)
               .toEqual(promptSnapshot)
+            expect(formatToolSchemasSnapshot(
+              schemaSets[0] as unknown[],
+              normalizedToolSchemaDeltas(log.content, ctx),
+            ), `session ${log.id}: tool-schema deltas diverged from ${pinningScenario.name}/${TOOL_SCHEMAS_SNAPSHOT}`)
+              .toEqual(toolSchemasSnapshot)
           }
         }
       })
@@ -535,6 +683,8 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void {
           .toBe(overridden === true)
         expect(existsSync(join(dir, SYSTEM_PROMPT_SNAPSHOT)), `${name}/${SYSTEM_PROMPT_SNAPSHOT} presence must match \`pinsHeader\``)
           .toBe(pinsHeader === true)
+        expect(existsSync(join(dir, TOOL_SCHEMAS_SNAPSHOT)), `${name}/${TOOL_SCHEMAS_SNAPSHOT} presence must match \`pinsHeader\``)
+          .toBe(pinsHeader === true)
         // A nested-agent scenario ships one child fixture per recorded subagent
         // session (`session.1.jsonl` …), the replay source for that child session.
         for (const childFixture of childFixturePaths(dir, childSessions ?? 0)) {
@@ -558,7 +708,7 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void {
       }
     })
 
-    it('every pinning fixture carries one request/header, one readable prompt, and its declared deltas', async () => {
+    it('every pinning fixture carries one tokenized request/header, two sidecars, and its declared deltas', async () => {
       // The live uniformity guard runs only in NON-pinning scenarios, so a class made of just
       // its pinning scenario would otherwise accept a re-recorded pin with several headers or
       // an undeclared mid-run header-delta — shapes the pin design cannot represent.
@@ -566,18 +716,24 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void {
         const fixture = await readFile(join(snapshotsDir, scenario.name, 'session.jsonl'), 'utf8')
         const headers = normalizedHeaders(fixture, fixtureContext(fixture))
         const promptSnapshot = await readFile(join(snapshotsDir, scenario.name, SYSTEM_PROMPT_SNAPSHOT), 'utf8')
+        const toolSchemasSnapshot = await readFile(join(snapshotsDir, scenario.name, TOOL_SCHEMAS_SNAPSHOT), 'utf8')
+        const toolSchemas = parseToolSchemasSnapshot(toolSchemasSnapshot)
         expect(headers.length, `${scenario.name}: a pinning fixture must carry exactly one request/header`).toBe(1)
+        expect(() => restorePinnedToolSchemas(headers[0], toolSchemas), `${scenario.name}: tools must use the sidecar token`)
+          .not.toThrow()
         expect(promptSnapshot.length, `${scenario.name}/${SYSTEM_PROMPT_SNAPSHOT} must not be empty`).toBeGreaterThan(0)
         expect(promptSnapshot.endsWith('\n'), `${scenario.name}/${SYSTEM_PROMPT_SNAPSHOT} must end in a newline`).toBe(true)
+        expect(toolSchemasSnapshot, `${scenario.name}/${TOOL_SCHEMAS_SNAPSHOT} must use canonical JSON formatting`)
+          .toBe(formatToolSchemasSnapshot(toolSchemas.initial, toolSchemas.deltas))
         expect(headerDeltaCount(fixture), `${scenario.name}: a pinning fixture must carry exactly its declared request/header-deltas`)
           .toBe(scenario.expectedHeaderDeltas ?? 0)
       }
     })
 
-    it('every committed JSONL omits system prompts and only pinning fixtures keep other header bulk', async () => {
-      // System prompts always live in the readable Markdown artifact. Header
-      // pins keep tool schemas/prefixes in JSONL; every other fixture tokenizes
-      // all header bulk. Fixed-point checks make both storage rules fail loud.
+    it('every committed JSONL has valid tool results and canonical header storage', async () => {
+      // Prompts and schemas always leave JSONL. Header pins retain prefixes;
+      // every other fixture tokenizes those too. Fixed-point checks make both
+      // storage rules fail loud.
       for (const scenario of scenarios) {
         const dir = join(snapshotsDir, scenario.name)
         const files = [
@@ -586,12 +742,13 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void {
         ]
         for (const file of files) {
           const fixture = await readFile(join(dir, file), 'utf8')
+          expect(unknownToolCallIds(fixture), `${scenario.name}/${file} contains UNKNOWN_TOOL`)
+            .toEqual([])
           expect(scrubSystemPrompts(fixture), `${scenario.name}/${file} carries an unscrubbed system prompt`)
             .toEqual(fixture)
-          if (scenario.pinsHeader === true) {
-            expect(scrubRequestHeaders(fixture), `${scenario.name}/${file} must pin the non-system header content`)
-              .not.toEqual(fixture)
-          } else {
+          expect(scrubToolSchemas(fixture), `${scenario.name}/${file} carries unscrubbed tool schemas`)
+            .toEqual(fixture)
+          if (scenario.pinsHeader !== true) {
             expect(scrubRequestHeaders(fixture), `${scenario.name}/${file} carries unscrubbed header content`)
               .toEqual(fixture)
           }
diff --git a/packages/support/acp-snapshot/tests/fixtures/record-suite/rec-pin/session.jsonl b/packages/support/acp-snapshot/tests/fixtures/record-suite/rec-pin/session.jsonl
index d496dbdb1d..e9dd3fb16c 100644
--- a/packages/support/acp-snapshot/tests/fixtures/record-suite/rec-pin/session.jsonl
+++ b/packages/support/acp-snapshot/tests/fixtures/record-suite/rec-pin/session.jsonl
@@ -1,2 +1,2 @@
 {"type":"session","id":"ccdc749f-56f3-4267-9750-598b5c60b7b2","createdAt":600,"cwd":"/var/folders/2g/b32ct0qn1d728l_v6tdkjytr0000gn/T/acp-snap-cwd-nOQ4Gy"}
-{"type":"request/header","seq":0,"time":4,"data":{"header":{"config":{"model":"fake"},"system":"{{system}}","tools":[{"name":"t1","description":"D1","parameters":{"type":"object"}}]},"reason":"initial"}}
+{"type":"request/header","seq":0,"time":4,"data":{"header":{"config":{"model":"fake"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
diff --git a/packages/support/acp-snapshot/tests/fixtures/record-suite/rec-pin/tool-schemas.golden.json b/packages/support/acp-snapshot/tests/fixtures/record-suite/rec-pin/tool-schemas.golden.json
new file mode 100644
index 0000000000..f96325d18b
--- /dev/null
+++ b/packages/support/acp-snapshot/tests/fixtures/record-suite/rec-pin/tool-schemas.golden.json
@@ -0,0 +1,12 @@
+{
+  "initial": [
+    {
+      "name": "t1",
+      "description": "D1",
+      "parameters": {
+        "type": "object"
+      }
+    }
+  ],
+  "deltas": []
+}
diff --git a/packages/support/acp-snapshot/tests/fixtures/suite/pin-turn/session.jsonl b/packages/support/acp-snapshot/tests/fixtures/suite/pin-turn/session.jsonl
index 0215afd538..92947ccb9b 100644
--- a/packages/support/acp-snapshot/tests/fixtures/suite/pin-turn/session.jsonl
+++ b/packages/support/acp-snapshot/tests/fixtures/suite/pin-turn/session.jsonl
@@ -1,4 +1,4 @@
 {"type":"session","id":"12121212-3434-4545-8686-787878787878","createdAt":7,"cwd":"/rec/pin-cwd"}
-{"type":"request/header","seq":0,"time":7,"data":{"header":{"config":{"model":"fake"},"system":"{{system}}","tools":[{"name":"t1","description":"D1","parameters":{"type":"object"}}]},"reason":"initial"}}
+{"type":"request/header","seq":0,"time":7,"data":{"header":{"config":{"model":"fake"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
 {"type":"request/header-delta","seq":1,"time":7,"data":{"system":{"keepStart":1,"keepEnd":0,"insert":["{{system}}"]}}}
 {"type":"turn/start","seq":2,"time":7,"data":{"turn":1}}
diff --git a/packages/support/acp-snapshot/tests/fixtures/suite/pin-turn/tool-schemas.golden.json b/packages/support/acp-snapshot/tests/fixtures/suite/pin-turn/tool-schemas.golden.json
new file mode 100644
index 0000000000..f96325d18b
--- /dev/null
+++ b/packages/support/acp-snapshot/tests/fixtures/suite/pin-turn/tool-schemas.golden.json
@@ -0,0 +1,12 @@
+{
+  "initial": [
+    {
+      "name": "t1",
+      "description": "D1",
+      "parameters": {
+        "type": "object"
+      }
+    }
+  ],
+  "deltas": []
+}
diff --git a/packages/support/acp-snapshot/tests/normalize.spec.ts b/packages/support/acp-snapshot/tests/normalize.spec.ts
index bdde120a76..d6c95045f6 100644
--- a/packages/support/acp-snapshot/tests/normalize.spec.ts
+++ b/packages/support/acp-snapshot/tests/normalize.spec.ts
@@ -5,6 +5,7 @@ import {
   normalizeStdout,
   scrubRequestHeaders,
   scrubSystemPrompts,
+  scrubToolSchemas,
 } from '../src/normalize.ts'
 
 /**
@@ -306,3 +307,45 @@ describe('scrubSystemPrompts', () => {
     expect(scrubSystemPrompts(out)).toBe(out)
   })
 })
+
+describe('scrubToolSchemas', () => {
+  it('scrubs only tool-schema payloads while keeping prompts and prefixes verbatim', () => {
+    const header = JSON.stringify({
+      type: 'request/header', seq: 1, time: 2,
+      data: {
+        header: {
+          system: 'full prompt',
+          tools: [{ name: 'read', description: 'full schema', parameters: { type: 'object' } }],
+          messagePrefix: [{ role: 'user', content: [{ type: 'text', text: 'full prefix' }] }],
+        },
+        reason: 'initial',
+      },
+    })
+    const delta = JSON.stringify({
+      type: 'request/header-delta', seq: 2, time: 3,
+      data: {
+        system: { keepStart: 1, keepEnd: 2, insert: ['new prompt line'] },
+        tools: { added: [{ name: 'grep', description: 'new schema' }], changed: [{ name: 'read', description: 'changed schema' }] },
+        messagePrefix: [{ role: 'user', content: [{ type: 'text', text: 'changed prefix' }] }],
+      },
+    })
+    const systemOnly = JSON.stringify({
+      type: 'request/header', seq: 3, time: 4,
+      data: { header: { system: 'prompt only' }, reason: 'resume' },
+    })
+
+    const out = scrubToolSchemas(`${header}\n${delta}\n${systemOnly}\n`)
+    expect(out).toContain('"tools":"{{tools}}"')
+    expect(out).toContain('"added":[{"name":"grep","description":"{{tools}}"}]')
+    expect(out).toContain('"changed":[{"name":"read","description":"{{tools}}"}]')
+    expect(out).not.toContain('full schema')
+    expect(out).not.toContain('new schema')
+    expect(out).not.toContain('changed schema')
+    expect(out).toContain('full prompt')
+    expect(out).toContain('new prompt line')
+    expect(out).toContain('full prefix')
+    expect(out).toContain('changed prefix')
+    expect(out.split('\n')[2]).toBe(systemOnly)
+    expect(scrubToolSchemas(out)).toBe(out)
+  })
+})
diff --git a/packages/support/acp-snapshot/tests/suite.spec.ts b/packages/support/acp-snapshot/tests/suite.spec.ts
index c76dd32a92..204647d8c9 100644
--- a/packages/support/acp-snapshot/tests/suite.spec.ts
+++ b/packages/support/acp-snapshot/tests/suite.spec.ts
@@ -9,12 +9,18 @@ import {
   childFixturePaths,
   fixtureContext,
   formatSystemPromptSnapshot,
+  formatToolSchemasSnapshot,
   headerDeltaCount,
   normalizedHeaders,
   normalizedSystemPromptDeltas,
   normalizedSystemPrompts,
+  normalizedToolSchemaDeltas,
+  normalizedToolSchemas,
+  parseToolSchemasSnapshot,
   refreshFixtureReplacements,
+  restorePinnedToolSchemas,
   stabilizeRefreshLog,
+  unknownToolCallIds,
 } from '../src/suite.ts'
 
 /**
@@ -70,6 +76,7 @@ afterAll(async () => {
 function staleRefreshFixtures(dir: string): void {
   writeFileSync(join(dir, 'plain-turn', 'stdout.golden.jsonl'), 'stale stdout\n')
   writeFileSync(join(dir, 'pin-turn', 'system-prompt.golden.md'), 'STALE PROMPT\n')
+  writeFileSync(join(dir, 'pin-turn', 'tool-schemas.golden.json'), '{"initial":[{"name":"stale"}],"deltas":[]}\n')
 
   const plainBehaviorFile = join(dir, 'plain-turn', 'behavior.json')
   const plainBehavior = JSON.parse(readFileSync(plainBehaviorFile, 'utf8')) as Record<string, unknown>
@@ -125,6 +132,9 @@ describe('defineAcpSnapshotSuite: refresh write-back', () => {
       'NEW PROMPT LINE',
       '',
     ].join('\n'))
+    const schemas = readFileSync(join(refreshDir, 'pin-turn', 'tool-schemas.golden.json'), 'utf8')
+    expect(schemas).toContain('"description": "D1"')
+    expect(schemas).not.toContain('"name":"stale"')
   })
 })
 
@@ -235,6 +245,40 @@ describe('normalizedSystemPrompts', () => {
   })
 })
 
+describe('normalizedToolSchemas', () => {
+  it('extracts normalized schema arrays and omits absent or non-array fields', () => {
+    const log = [
+      '{"type":"session","id":"a","createdAt":5,"cwd":"/w"}',
+      '{"type":"request/header","seq":0,"time":9,"data":{"header":{"tools":[{"name":"read","description":"work in /w"}]}}}',
+      '{"type":"request/header","seq":1,"time":9,"data":{"header":{}}}',
+      '{"type":"request/header","seq":2,"time":9,"data":{"header":{"tools":null}}}',
+      '{"type":"request/header","seq":3,"time":9,"data":{"header":null}}',
+      '{"type":"request/header","seq":4,"time":9,"data":{"header":"invalid"}}',
+      '',
+    ].join('\n')
+    expect(normalizedToolSchemas(log, { sessionIds: [], cwd: '/w' })).toEqual([
+      [{ name: 'read', description: 'work in {{cwd}}' }],
+    ])
+  })
+})
+
+describe('normalizedToolSchemaDeltas', () => {
+  it('extracts and normalizes object-valued schema edits', () => {
+    const log = [
+      '{"type":"request/header-delta","data":{"tools":{"added":[{"name":"read","description":"work in /w"}]}}}',
+      '{"type":"request/header-delta","data":{"tools":null}}',
+      '{"type":"request/header-delta","data":{"tools":"invalid"}}',
+      '{"type":"request/header-delta","data":{"tools":[]}}',
+      '{"type":"request/header-delta","data":{"system":{"insert":[]}}}',
+      '{"type":"request/header","data":{"tools":{"added":[]}}}',
+      '',
+    ].join('\n')
+    expect(normalizedToolSchemaDeltas(log, { sessionIds: [], cwd: '/w' })).toEqual([
+      { added: [{ name: 'read', description: 'work in {{cwd}}' }] },
+    ])
+  })
+})
+
 describe('normalizedSystemPromptDeltas', () => {
   it('extracts and normalizes well-formed system edits', () => {
     const log = [
@@ -269,6 +313,39 @@ describe('formatSystemPromptSnapshot', () => {
   })
 })
 
+describe('tool-schema snapshots', () => {
+  const snapshot = {
+    initial: [{ name: 'read', description: 'Read a file.' }],
+    deltas: [{ added: [{ name: 'grep', description: 'Search files.' }] }],
+  }
+
+  it('formats and parses canonical structured JSON', () => {
+    const formatted = formatToolSchemasSnapshot(snapshot.initial, snapshot.deltas)
+    expect(formatted).toBe(`${JSON.stringify(snapshot, null, 2)}\n`)
+    expect(parseToolSchemasSnapshot(formatted)).toEqual(snapshot)
+  })
+
+  it('rejects invalid top-level and field shapes', () => {
+    expect(() => parseToolSchemasSnapshot('null')).toThrow(/must be an object/)
+    expect(() => parseToolSchemasSnapshot('"invalid"')).toThrow(/must be an object/)
+    expect(() => parseToolSchemasSnapshot('[]')).toThrow(/must be an object/)
+    expect(() => parseToolSchemasSnapshot('{"initial":{},"deltas":[]}')).toThrow(/array-valued/)
+    expect(() => parseToolSchemasSnapshot('{"initial":[],"deltas":{}}')).toThrow(/array-valued/)
+  })
+
+  it('restores initial schemas into the pinned header token', () => {
+    expect(restorePinnedToolSchemas({ system: '{{system}}', tools: '{{tools}}' }, snapshot))
+      .toEqual({ system: '{{system}}', tools: snapshot.initial })
+  })
+
+  it('rejects invalid headers and a missing tool token', () => {
+    expect(() => restorePinnedToolSchemas(null, snapshot)).toThrow(/must be an object/)
+    expect(() => restorePinnedToolSchemas('invalid', snapshot)).toThrow(/must be an object/)
+    expect(() => restorePinnedToolSchemas([], snapshot)).toThrow(/must be an object/)
+    expect(() => restorePinnedToolSchemas({ tools: [] }, snapshot)).toThrow(/must equal/)
+  })
+})
+
 describe('headerDeltaCount', () => {
   it('counts request/header-delta events, ignoring blanks and other lines', () => {
     const delta = JSON.stringify({ type: 'request/header-delta', seq: 2, time: 9, data: {} })
@@ -278,6 +355,27 @@ describe('headerDeltaCount', () => {
   })
 })
 
+describe('unknownToolCallIds', () => {
+  it('returns structured UNKNOWN_TOOL call ids and ignores other results', () => {
+    const log = [
+      '{"type":"tool/result","data":{"callId":"missing","error":{"code":"UNKNOWN_TOOL"}}}',
+      '{"type":"tool/result","data":{"callId":"failed","error":{"code":"EXECUTION_FAILED"}}}',
+      '{"type":"tool/result","data":null}',
+      '{"type":"tool/result","data":"invalid"}',
+      '{"type":"tool/result","data":{"error":null}}',
+      '{"type":"tool/result","data":{"error":"invalid"}}',
+      '{"type":"assistant/message","data":{"error":{"code":"UNKNOWN_TOOL"}}}',
+      '{"type":"tool/result","data":{"error":{"code":"UNKNOWN_TOOL"}}}',
+      '',
+    ].join('\n')
+    expect(unknownToolCallIds(log)).toEqual(['missing', '<missing callId>'])
+  })
+
+  it('returns no failures for ordinary tool results', () => {
+    expect(unknownToolCallIds('{"type":"tool/result","data":{"callId":"ok"}}\n')).toEqual([])
+  })
+})
+
 describe('refreshFixtureReplacements', () => {
   it('maps fresh ids and cwd values to the existing fixture values, skipping non-replacements', () => {
     const log = (content: string): HarvestedLog => ({ id: 'diagnostic', createdAt: 1, content })
diff --git a/packages/support/invariants/package.json b/packages/support/invariants/package.json
index 3568465d18..85a249dbd1 100644
--- a/packages/support/invariants/package.json
+++ b/packages/support/invariants/package.json
@@ -33,6 +33,10 @@
     "@deepseek-ai/dsh-llm": "workspace:^",
     "@deepseek-ai/dsh-scope": "workspace:^",
     "@deepseek-ai/dsh-session": "workspace:^",
+    "@deepseek-ai/dsh-subagent": "workspace:^",
+    "@deepseek-ai/dsh-system-prompt": "workspace:^",
+    "@deepseek-ai/dsh-tools": "workspace:^",
+    "@deepseek-ai/dsh-user-approval": "workspace:^",
     "cordis": "^4.0.0-rc.6"
   }
 }
diff --git a/packages/support/invariants/src/index.ts b/packages/support/invariants/src/index.ts
index f5b7828a3d..8da5429b06 100644
--- a/packages/support/invariants/src/index.ts
+++ b/packages/support/invariants/src/index.ts
@@ -14,6 +14,7 @@ import type { CallId, GenerateOptions } from '@deepseek-ai/dsh-llm'
 import type { Agent, AgentStatus } from '@deepseek-ai/dsh-agent'
 import { Session, SessionId, foldRequestHeader } from '@deepseek-ai/dsh-session'
 import type { SessionEvent, SurfaceEventType } from '@deepseek-ai/dsh-session'
+import { scopedSubjectResolverFor } from './scoped-events.generated.ts'
 
 export const name = 'invariants'
 export const inject = ['sessions']
@@ -75,17 +76,6 @@ interface SessionTraceTransition {
   seq: number
 }
 
-/** Event payload prefix for scoped seams whose first argument names its agent. */
-interface AgentSubject {
-  agent: Agent
-}
-
-/** Structural subject fields used without coupling this dev plugin to owning services. */
-interface ScopedSubjectFields {
-  agent?: Agent
-  scope?: object
-}
-
 /** Assert that a step-scoped event names the currently open turn and step. */
 function requireOpenStep(trace: SessionTrace, kind: string, turn: number, step: number): void {
   if (trace.openTurn !== turn || trace.openStep !== step) {
@@ -410,40 +400,12 @@ export function apply(ctx: Context): void {
   // (agent-scoped listeners over-hear foreign agents), and a mis-keyed one
   // delivers to the wrong agent's listeners. `internal/dispatch` fires
   // synchronously before listener delivery, so a violation throws at the
-  // dispatching call site. The table maps each family to how its subject is
-  // read from the event arguments; `null` = the subject is not recoverable
-  // from the arguments (session events key by the OWNING agent; subagent
-  // lifecycle events key by the delegating parent), so only carrier
-  // PRESENCE is asserted there.
-  const scopedSubject: Record<string, ((args: unknown[]) => unknown) | null> = {
-    'agent/created': args => args[0],
-    'agent/disposed': args => args[0],
-    'agent/status': args => args[0],
-    'agent/queued': args => args[0],
-    'agent/session-start': args => args[0],
-    'agent/pre-step': args => args[0],
-    'agent/prompt-submit': args => args[0],
-    'agent/request': args => args[0],
-    'agent/session-prefix': args => args[0],
-    'agent/step-result': args => args[0],
-    'agent/turn-continuation': args => args[0],
-    'agent/turn-stop': args => args[0],
-    'agent/error': args => args[0],
-    'approval/request': args => (args[0] as AgentSubject).agent,
-    'tools/pre-execute': args => (args[0] as ScopedSubjectFields).agent,
-    'tools/execute': args => (args[0] as ScopedSubjectFields).agent,
-    'tools/post-execute': args => (args[0] as ScopedSubjectFields).agent,
-    'tools/result': args => (args[0] as ScopedSubjectFields).agent,
-    'system-prompt/assemble': args => (args[1] as ScopedSubjectFields).scope,
-    'session/created': null,
-    'session/disposed': null,
-    'session/event': null,
-    'session/flush': null,
-    'subagent/start': null,
-    'subagent/end': null,
-  }
+  // dispatching call site. The generated table maps each family to the unique
+  // payload path whose Program type matches the real scopeTarget routing key;
+  // `null` means the key is external to the payload, so only carrier presence
+  // can be asserted.
   ctx.on('internal/dispatch', (_mode, name, args, thisArg) => {
-    const subjectOf = scopedSubject[name]
+    const subjectOf = scopedSubjectResolverFor(name)
     if (subjectOf === undefined) return
     if (!isScopeCarrier(thisArg)) {
       throw new InvariantError(
diff --git a/packages/support/invariants/src/scoped-events.generated.ts b/packages/support/invariants/src/scoped-events.generated.ts
new file mode 100644
index 0000000000..06cca6bf55
--- /dev/null
+++ b/packages/support/invariants/src/scoped-events.generated.ts
@@ -0,0 +1,69 @@
+/**
+ * Generated scoped-event routing-subject resolvers for dsh-invariants.
+ * Do not edit by hand; run `pnpm run gen-scoped-events`.
+ *
+ * @module @deepseek-ai/dsh-invariants/scoped-events.generated
+ */
+
+import type { Events } from 'cordis'
+import type { Scoped } from '@deepseek-ai/dsh-scope'
+import type {} from '@deepseek-ai/dsh-agent'
+import type {} from '@deepseek-ai/dsh-session'
+import type {} from '@deepseek-ai/dsh-subagent'
+import type {} from '@deepseek-ai/dsh-system-prompt'
+import type {} from '@deepseek-ai/dsh-tools'
+import type {} from '@deepseek-ai/dsh-user-approval'
+
+type ScopedEventName = {
+  [K in keyof Events]: ThisParameterType<Events[K]> extends Scoped<object> ? K : never
+}[keyof Events]
+
+type ScopedSubjectResolver = (args: readonly unknown[]) => unknown
+
+function adapt<K extends ScopedEventName>(
+  resolver: (args: Parameters<Events[K]>) => unknown,
+): ScopedSubjectResolver {
+  return args => resolver(args as Parameters<Events[K]>)
+}
+
+const scopedSubjectResolvers = Object.freeze({
+  'agent/created': adapt<'agent/created'>(args => args[0]),
+  'agent/disposed': adapt<'agent/disposed'>(args => args[0]),
+  'agent/error': adapt<'agent/error'>(args => args[0]),
+  'agent/pre-step': adapt<'agent/pre-step'>(args => args[0]),
+  'agent/prompt-submit': adapt<'agent/prompt-submit'>(args => args[0]),
+  'agent/queued': adapt<'agent/queued'>(args => args[0]),
+  'agent/request': adapt<'agent/request'>(args => args[0]),
+  'agent/session-prefix': adapt<'agent/session-prefix'>(args => args[0]),
+  'agent/session-start': adapt<'agent/session-start'>(args => args[0]),
+  'agent/status': adapt<'agent/status'>(args => args[0]),
+  'agent/step-result': adapt<'agent/step-result'>(args => args[0]),
+  'agent/turn-continuation': adapt<'agent/turn-continuation'>(args => args[0]),
+  'agent/turn-stop': adapt<'agent/turn-stop'>(args => args[0]),
+  'approval/request': adapt<'approval/request'>(args => args[0].agent),
+  'session/created': null,
+  'session/disposed': null,
+  'session/event': null,
+  'session/flush': null,
+  'subagent/end': null,
+  'subagent/start': null,
+  'system-prompt/assemble': adapt<'system-prompt/assemble'>(args => args[1].scope),
+  'tools/execute': adapt<'tools/execute'>(args => args[0].agent),
+  'tools/post-execute': adapt<'tools/post-execute'>(args => args[0].agent),
+  'tools/pre-execute': adapt<'tools/pre-execute'>(args => args[0].agent),
+  'tools/result': adapt<'tools/result'>(args => args[0].agent),
+} as const satisfies Readonly<Record<ScopedEventName, ScopedSubjectResolver | null>>)
+
+const scopedSubjectResolverIndex: Readonly<Record<string, ScopedSubjectResolver | null>> = scopedSubjectResolvers
+
+/**
+ * Resolve the routing key named by one scoped event payload. A null
+ * resolver means the payload cannot expose its external routing key, so the
+ * invariant checks carrier presence only.
+ * @param event - runtime Cordis event name.
+ * @returns the generated subject resolver, null for presence-only,
+ *   or undefined when the event is not scope-filtered.
+ */
+export function scopedSubjectResolverFor(event: string): ScopedSubjectResolver | null | undefined {
+  return scopedSubjectResolverIndex[event]
+}
diff --git a/packages/support/invariants/tests/invariants.spec.ts b/packages/support/invariants/tests/invariants.spec.ts
index f642d06f41..cf30cf0164 100644
--- a/packages/support/invariants/tests/invariants.spec.ts
+++ b/packages/support/invariants/tests/invariants.spec.ts
@@ -834,7 +834,7 @@ describe('scoped-dispatch invariants', () => {
 
   it('accepts a matching carrier and rejects a mismatched one for EVERY agent-subject event', async () => {
     const ctx = await scopedCtx()
-    // Real Session objects: the session-start tracker WeakSet-keys them.
+    // Real Session objects keep the synthetic Agent handles structurally valid.
     const agent = { id: 'a1', session: new Session(SessionId('a1-s')) } as unknown as Agent
     const other = { id: 'a2', session: new Session(SessionId('a2-s')) } as unknown as Agent
     // One dispatch per table row keeps every subject extractor covered: the
diff --git a/packages/support/invariants/tsconfig.json b/packages/support/invariants/tsconfig.json
index cd17f67d7c..6c5bc479b5 100644
--- a/packages/support/invariants/tsconfig.json
+++ b/packages/support/invariants/tsconfig.json
@@ -25,6 +25,18 @@
     },
     {
       "path": "../../core/scope"
+    },
+    {
+      "path": "../../core/system-prompt"
+    },
+    {
+      "path": "../../ui/user-approval"
+    },
+    {
+      "path": "../../core/tools"
+    },
+    {
+      "path": "../../subagent/subagent"
     }
   ]
 }
diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml
index 650addb80a..1905b80887 100644
--- a/pnpm-lock.yaml
+++ b/pnpm-lock.yaml
@@ -14,6 +14,9 @@ importers:
       '@stylistic/eslint-plugin':
         specifier: ^5.10.0
         version: 5.10.0(eslint@10.5.0(jiti@2.7.0))
+      '@types/js-yaml':
+        specifier: ^4.0.9
+        version: 4.0.9
       '@types/jsdom':
         specifier: ^28.0.3
         version: 28.0.3
@@ -35,6 +38,9 @@ importers:
       fast-check:
         specifier: ^4.8.0
         version: 4.8.0
+      js-yaml:
+        specifier: ^4.2.0
+        version: 4.2.0
       jscpd:
         specifier: ^5.0.12
         version: 5.0.12
@@ -1101,6 +1107,18 @@ importers:
       '@deepseek-ai/dsh-session':
         specifier: workspace:^
         version: link:../../core/session
+      '@deepseek-ai/dsh-subagent':
+        specifier: workspace:^
+        version: link:../../subagent/subagent
+      '@deepseek-ai/dsh-system-prompt':
+        specifier: workspace:^
+        version: link:../../core/system-prompt
+      '@deepseek-ai/dsh-tools':
+        specifier: workspace:^
+        version: link:../../core/tools
+      '@deepseek-ai/dsh-user-approval':
+        specifier: workspace:^
+        version: link:../../ui/user-approval
       cordis:
         specifier: ^4.0.0-rc.6
         version: 4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.4)
@@ -1308,28 +1326,6 @@ importers:
         specifier: ^4.0.0-rc.6
         version: 4.0.0-rc.6(@cordisjs/plugin-include@vendor+include)(@cordisjs/plugin-loader@vendor+loader)
 
-  packages/ui/permission:
-    dependencies:
-      schemastery:
-        specifier: ^3.18.0
-        version: 3.18.0
-    devDependencies:
-      '@deepseek-ai/dsh-bash':
-        specifier: workspace:^
-        version: link:../../bash/bash
-      '@deepseek-ai/dsh-sandbox':
-        specifier: workspace:^
-        version: link:../../sandbox/sandbox
-      '@deepseek-ai/dsh-session':
-        specifier: workspace:^
-        version: link:../../core/session
-      '@deepseek-ai/dsh-user-approval':
-        specifier: workspace:^
-        version: link:../user-approval
-      cordis:
-        specifier: ^4.0.0-rc.6
-        version: 4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.4)
-
   packages/ui/jsonrpc:
     dependencies:
       schemastery:
@@ -1374,6 +1370,28 @@ importers:
         specifier: ^4.0.0-rc.6
         version: 4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.4)
 
+  packages/ui/permission:
+    dependencies:
+      schemastery:
+        specifier: ^3.18.0
+        version: 3.18.0
+    devDependencies:
+      '@deepseek-ai/dsh-bash':
+        specifier: workspace:^
+        version: link:../../bash/bash
+      '@deepseek-ai/dsh-sandbox':
+        specifier: workspace:^
+        version: link:../../sandbox/sandbox
+      '@deepseek-ai/dsh-session':
+        specifier: workspace:^
+        version: link:../../core/session
+      '@deepseek-ai/dsh-user-approval':
+        specifier: workspace:^
+        version: link:../user-approval
+      cordis:
+        specifier: ^4.0.0-rc.6
+        version: 4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.4)
+
   packages/ui/stdio-agent:
     devDependencies:
       '@cordisjs/plugin-include':
@@ -3173,6 +3191,9 @@ packages:
   '@types/geojson@7946.0.16':
     resolution: {integrity: sha512-6C8nqWur3j98U6+lXDfTUWIfgvZU+EumvpHKcYjujKH7woYyLj2sUmff0tRhrqM7BohUw7Pz3ZB1jj2gW9Fvmg==}
 
+  '@types/js-yaml@4.0.9':
+    resolution: {integrity: sha512-k4MGaQl5TGo/iipqb2UDG2UwjXziSWkh0uysQelTlJpX1qGlpUZYm8PnO4DxG1qBomtJUdYJ6qR6xdIah10JLg==}
+
   '@types/jsdom@28.0.3':
     resolution: {integrity: sha512-/HQ2uFoetFTXuye8vzIcHw2z6Fwi7Hi/qcgC+RoS9NCyewiqxhVGqlG+ViGB6lkax481R6dmhf1I7lIGlzJStQ==}
 
@@ -6013,6 +6034,8 @@ snapshots:
 
   '@types/geojson@7946.0.16': {}
 
+  '@types/js-yaml@4.0.9': {}
+
   '@types/jsdom@28.0.3':
     dependencies:
       '@types/node': 25.9.3
diff --git a/scripts/doc-budgets.manifest.json b/scripts/doc-budgets.manifest.json
index a03f7ca25a..80957af255 100644
--- a/scripts/doc-budgets.manifest.json
+++ b/scripts/doc-budgets.manifest.json
@@ -2,7 +2,7 @@
   "AGENTS.md": 1370,
   "docs/AGENTS.md": 1100,
   "docs/architecture.md": 1790,
-  "docs/cordis-primer.md": 550,
+  "docs/cordis-primer.md": 600,
   "docs/defensive-patterns.md": 550,
   "docs/testing.md": 800,
   "examples/AGENTS.md": 200,
diff --git a/scripts/gen-doc-graphs.ts b/scripts/gen-doc-graphs.ts
index 468a46e904..a6660f7cd3 100644
--- a/scripts/gen-doc-graphs.ts
+++ b/scripts/gen-doc-graphs.ts
@@ -5,7 +5,7 @@
  * `--check` verifies the generated set.
  */
 
-import { existsSync, globSync, mkdirSync, readFileSync, writeFileSync } from 'node:fs'
+import { existsSync, mkdirSync, readFileSync, writeFileSync } from 'node:fs'
 import { dirname, relative, resolve } from 'node:path'
 import ts from 'typescript'
 import { collectEvents, collectServices } from './gen-cordis-catalog.ts'
@@ -15,6 +15,7 @@ import {
   graphNodeId as nodeId,
   type PackageGraphNode,
 } from './package-graph.ts'
+import { TypeScriptProject } from './ts-project.ts'
 
 const root = resolve(import.meta.dirname, '..')
 type Pkg = PackageGraphNode
@@ -45,6 +46,14 @@ interface EventRelation {
   listeners: Set<string>
 }
 
+interface PackageSource {
+  rel: string
+  pkg: string
+  sourceFile: ts.SourceFile
+}
+
+type EventReceiverKind = 'context' | 'agent-dispatch' | 'events-service'
+
 const GROUP_ORDER = [
   'util',
   'llm',
@@ -242,51 +251,6 @@ const SERVICE_ROLES: ServiceRole[] = [
   },
 ]
 
-const DYNAMIC_EVENT_DISPATCHERS: Array<{ event: string; pkg: string; method: string }> = [
-  // Creation notifications preserve synchronous veto/rollback but observe
-  // returned promises explicitly so async listener rejection is not unhandled.
-  { event: 'agent/created', pkg: 'agent', method: 'events.dispatch' },
-  // Registry disposal reuses the stable carrier captured before entry commit
-  // and contains each listener directly rather than rebuilding via agentEvents.
-  { event: 'agent/disposed', pkg: 'agent', method: 'events.dispatch' },
-  { event: 'session/created', pkg: 'session', method: 'events.dispatch' },
-  // Session event callbacks are likewise resolved before the log push, then
-  // invoked individually after commit so observer failures are contained.
-  { event: 'session/event', pkg: 'session', method: 'events.dispatch' },
-  // Flush resolves the scoped callback set directly so internal instrumentation
-  // cannot substitute the accepted session before parallel invocation.
-  { event: 'session/flush', pkg: 'session', method: 'events.dispatch' },
-  // Session disposal uses direct callback resolution so teardown contains each
-  // synchronous throw and returned-promise rejection independently.
-  { event: 'session/disposed', pkg: 'session', method: 'events.dispatch' },
-  // tools/result uses ctx.events.dispatch directly so the registry can invoke
-  // every synchronous observer while containing each callback independently.
-  { event: 'tools/result', pkg: 'tools', method: 'events.dispatch' },
-  // Subagent lifecycle events intentionally bypass ctx.emit and call
-  // ctx.events.dispatch directly so one throwing listener cannot starve later
-  // listeners or strand an already-started child run.
-  { event: 'subagent/start', pkg: 'subagent', method: 'events.dispatch' },
-  { event: 'subagent/end', pkg: 'subagent', method: 'events.dispatch' },
-  // provider-removed fires inside the provider registration's DISPOSER and
-  // routes through the same contained dispatch (see emitLifecycle in
-  // dsh-subagent), so the AST scan cannot attribute it either.
-  { event: 'subagent/provider-removed', pkg: 'subagent', method: 'events.dispatch' },
-  // The workflow/* lifecycle events dispatch the same way, for the same
-  // per-listener-containment reason (WorkflowService.emitWorkflowEvent).
-  { event: 'workflow/start', pkg: 'workflow', method: 'events.dispatch' },
-  { event: 'workflow/phase', pkg: 'workflow', method: 'events.dispatch' },
-  { event: 'workflow/log', pkg: 'workflow', method: 'events.dispatch' },
-  { event: 'workflow/agent-start', pkg: 'workflow', method: 'events.dispatch' },
-  { event: 'workflow/agent-end', pkg: 'workflow', method: 'events.dispatch' },
-  { event: 'workflow/end', pkg: 'workflow', method: 'events.dispatch' },
-]
-
-const DYNAMIC_EVENT_LISTENERS: Array<{ event: string; pkg: string }> = [
-  // The invariants oracle marks the session started from its global
-  // internal/dispatch listener before product session-start callbacks run.
-  { event: 'agent/session-start', pkg: 'invariants' },
-]
-
 function generatedHeader(title: string): string[] {
   return [
     '<!-- Generated by scripts/gen-doc-graphs.ts - do not edit by hand.',
@@ -505,81 +469,256 @@ function renderAppComposition(example: AppExample): string {
   return lines.join('\n')
 }
 
-function collectEventRelations(): Map<string, EventRelation> {
-  const out = new Map<string, EventRelation>()
-  const ensure = (event: string): EventRelation => {
-    const existing = out.get(event)
-    if (existing) return existing
-    const next = { dispatchers: new Map<string, Set<string>>(), listeners: new Set<string>() }
-    out.set(event, next)
-    return next
+/** Collect event dispatch/listener relations from real cross-file receiver types. */
+class EventRelationCollector {
+  private readonly relations = new Map<string, EventRelation>()
+  private readonly callSites = new Map<ts.SignatureDeclaration | ts.JSDocSignature, ts.CallExpression[]>()
+  private readonly contextType: ts.Type
+  private readonly agentDispatchType: ts.Type
+  private readonly eventsServiceType: ts.Type
+
+  constructor(
+    private readonly project: TypeScriptProject,
+    private readonly sources: readonly PackageSource[],
+  ) {
+    this.contextType = this.declaredType('vendor/cordis/src/context.ts', 'Context')
+    this.agentDispatchType = this.declaredType('packages/core/agent/src/dispatch.ts', 'AgentEventDispatch')
+    this.eventsServiceType = this.declaredType('vendor/cordis/src/events.ts', 'EventsService')
+    this.indexCallSites()
   }
-  for (const rel of globSync('packages/*/*/src/**/*.ts', { cwd: root }).sort()) {
-    const [, , leaf] = rel.split('/')
-    if (leaf === undefined) continue
-    const text = readFileSync(resolve(root, rel), 'utf8')
-    const sf = ts.createSourceFile(rel, text, ts.ScriptTarget.Latest, true)
+
+  /** Return all event relations discovered from the Program. */
+  collect(): Map<string, EventRelation> {
+    for (const source of this.sources) this.visitSource(source)
+    return this.relations
+  }
+
+  /** Resolve one named class/interface declaration to its merged instance type. */
+  private declaredType(relativePath: string, name: string): ts.Type {
+    const sourceFile = this.project.sourceFile(relativePath)
+    const declaration = sourceFile.statements.find((statement): statement is ts.ClassDeclaration | ts.InterfaceDeclaration => {
+      return (ts.isClassDeclaration(statement) || ts.isInterfaceDeclaration(statement)) && statement.name?.text === name
+    })
+    const symbol = declaration?.name && this.project.checker.getSymbolAtLocation(declaration.name)
+    if (!symbol) throw new Error(`cannot resolve TypeScript type ${name} from ${relativePath}`)
+    return this.project.checker.getDeclaredTypeOfSymbol(symbol)
+  }
+
+  /** Index resolved local function calls for narrow argument-flow recovery. */
+  private indexCallSites(): void {
+    const visit = (node: ts.Node): void => {
+      if (ts.isCallExpression(node)) {
+        const declaration = this.project.checker.getResolvedSignature(node)?.declaration
+        if (declaration) {
+          const calls = this.callSites.get(declaration) ?? []
+          calls.push(node)
+          this.callSites.set(declaration, calls)
+        }
+      }
+      ts.forEachChild(node, visit)
+    }
+    for (const source of this.sources) visit(source.sourceFile)
+  }
+
+  /** Walk one package source file and classify event API calls by receiver type. */
+  private visitSource(source: PackageSource): void {
     const visit = (node: ts.Node): void => {
       if (ts.isCallExpression(node) && ts.isPropertyAccessExpression(node.expression)) {
+        const receiverKind = this.receiverKind(node.expression.expression)
         const method = node.expression.name.text
-        if (!isCordisContextReceiver(node.expression, sf)) {
-          ts.forEachChild(node, visit)
-          return
-        }
-        if (method === 'on') {
-          const event = eventArg(node.arguments, method)
-          if (event) ensure(event).listeners.add(leaf)
-        } else if (method === 'emit' || method === 'parallel' || method === 'serial' || method === 'waterfall') {
-          const event = eventArg(node.arguments, method)
-          if (event) {
-            const relation = ensure(event)
-            const methods = relation.dispatchers.get(leaf) ?? new Set<string>()
-            methods.add(method)
-            relation.dispatchers.set(leaf, methods)
+        if (receiverKind === 'events-service' && method === 'dispatch') {
+          const argumentList = node.arguments[1]
+          if (argumentList) {
+            for (const event of this.eventNamesFromArgumentList(argumentList, new Set())) {
+              this.addDispatcher(event, source.pkg, 'events.dispatch')
+            }
+          }
+        } else if (receiverKind === 'context' || receiverKind === 'agent-dispatch') {
+          const eventNames = this.eventNamesFromCall(node, receiverKind)
+          if (method === 'on' || method === 'once') {
+            for (const event of eventNames) this.ensure(event).listeners.add(source.pkg)
+          } else if (method === 'emit' || method === 'parallel' || method === 'serial' || method === 'waterfall') {
+            for (const event of eventNames) this.addDispatcher(event, source.pkg, method)
           }
         }
       }
       ts.forEachChild(node, visit)
     }
-    visit(sf)
+    visit(source.sourceFile)
   }
-  for (const entry of DYNAMIC_EVENT_DISPATCHERS) {
-    const relation = ensure(entry.event)
-    const methods = relation.dispatchers.get(entry.pkg) ?? new Set<string>()
-    methods.add(entry.method)
-    relation.dispatchers.set(entry.pkg, methods)
+
+  /** Classify a receiver using assignability to the repository's actual event API types. */
+  private receiverKind(receiver: ts.Expression): EventReceiverKind | undefined {
+    const type = this.project.checker.getTypeAtLocation(receiver)
+    if (type.flags & (ts.TypeFlags.Any | ts.TypeFlags.Unknown | ts.TypeFlags.Never)) return undefined
+    if (this.project.checker.isTypeAssignableTo(type, this.eventsServiceType)) return 'events-service'
+    if (this.project.checker.isTypeAssignableTo(type, this.contextType)) return 'context'
+    if (this.project.checker.isTypeAssignableTo(type, this.agentDispatchType)) return 'agent-dispatch'
+    return undefined
   }
-  for (const entry of DYNAMIC_EVENT_LISTENERS) {
-    ensure(entry.event).listeners.add(entry.pkg)
+
+  /** Resolve the event-name argument for Context and fused agent dispatch calls. */
+  private eventNamesFromCall(call: ts.CallExpression, receiverKind: Exclude<EventReceiverKind, 'events-service'>): Set<string> {
+    const candidates = receiverKind === 'context' ? call.arguments.slice(0, 2) : call.arguments.slice(0, 1)
+    for (const candidate of candidates) {
+      const values = this.finiteStringValues(candidate)
+      if (values) return values
+    }
+    return new Set()
   }
+
+  /** Recover the event slot from the argument array handed to EventsService.dispatch(). */
+  private eventNamesFromArgumentList(expression: ts.Expression, seen: Set<ts.Node>): Set<string> {
+    const current = unwrapExpression(expression)
+    if (seen.has(current)) return new Set()
+    seen.add(current)
+
+    if (ts.isArrayLiteralExpression(current)) {
+      for (const element of current.elements.slice(0, 2)) {
+        if (ts.isOmittedExpression(element) || ts.isSpreadElement(element)) continue
+        const values = this.finiteStringValues(element)
+        if (values) return values
+      }
+      return new Set()
+    }
+    if (ts.isConditionalExpression(current)) {
+      return unionSets(
+        this.eventNamesFromArgumentList(current.whenTrue, new Set(seen)),
+        this.eventNamesFromArgumentList(current.whenFalse, new Set(seen)),
+      )
+    }
+    if (!ts.isIdentifier(current)) return new Set()
+
+    const symbol = this.project.checker.getSymbolAtLocation(current)
+    if (!symbol) return new Set()
+    const events = new Set<string>()
+    for (const declaration of symbol.declarations ?? []) {
+      if (ts.isVariableDeclaration(declaration) && declaration.initializer && isConstDeclaration(declaration)) {
+        addAll(events, this.eventNamesFromArgumentList(declaration.initializer, new Set(seen)))
+      } else if (ts.isParameter(declaration)) {
+        addAll(events, this.eventNamesFromParameter(declaration, seen))
+      }
+    }
+    return events
+  }
+
+  /** Follow a non-exported local helper parameter back to every resolved call site. */
+  private eventNamesFromParameter(parameter: ts.ParameterDeclaration, seen: Set<ts.Node>): Set<string> {
+    const owner = parameter.parent
+    if (!ts.isFunctionDeclaration(owner) || hasExportModifier(owner)) return new Set()
+    const index = owner.parameters.indexOf(parameter)
+    if (index < 0) return new Set()
+    const events = new Set<string>()
+    for (const call of this.callSites.get(owner) ?? []) {
+      const argument = call.arguments[index]
+      if (argument) addAll(events, this.eventNamesFromArgumentList(argument, new Set(seen)))
+    }
+    return events
+  }
+
+  /** Return a finite string-literal value set, rejecting widened and generic strings. */
+  private finiteStringValues(expression: ts.Expression): Set<string> | undefined {
+    const current = unwrapExpression(expression)
+    if (ts.isStringLiteralLike(current)) return new Set([current.text])
+    if (this.isForwardedAgentEventParameter(current)) return undefined
+    return finiteStringTypeValues(this.project.checker.getTypeAtLocation(current))
+  }
+
+  /** Reject the contextual parameter inside the AgentEventDispatch forwarding object. */
+  private isForwardedAgentEventParameter(expression: ts.Expression): boolean {
+    if (!ts.isIdentifier(expression)) return false
+    const declarations = this.project.checker.getSymbolAtLocation(expression)?.declarations ?? []
+    return declarations.some((declaration) => {
+      if (!ts.isParameter(declaration)) return false
+      const method = declaration.parent
+      if (!ts.isMethodDeclaration(method) || !ts.isObjectLiteralExpression(method.parent)) return false
+      const contextualType = this.project.checker.getContextualType(method.parent)
+      return contextualType !== undefined
+        && this.project.checker.isTypeAssignableTo(contextualType, this.agentDispatchType)
+    })
+  }
+
+  /** Get or create one relation row. */
+  private ensure(event: string): EventRelation {
+    const existing = this.relations.get(event)
+    if (existing) return existing
+    const relation = { dispatchers: new Map<string, Set<string>>(), listeners: new Set<string>() }
+    this.relations.set(event, relation)
+    return relation
+  }
+
+  /** Add one dispatcher method without duplicating package/method labels. */
+  private addDispatcher(event: string, pkg: string, method: string): void {
+    const relation = this.ensure(event)
+    const methods = relation.dispatchers.get(pkg) ?? new Set<string>()
+    methods.add(method)
+    relation.dispatchers.set(pkg, methods)
+  }
+}
+
+/** Peel syntax-only wrappers that do not change an expression's runtime value. */
+function unwrapExpression(expression: ts.Expression): ts.Expression {
+  let current = expression
+  while (
+    ts.isParenthesizedExpression(current)
+    || ts.isAsExpression(current)
+    || ts.isTypeAssertionExpression(current)
+    || ts.isNonNullExpression(current)
+    || ts.isSatisfiesExpression(current)
+  ) {
+    current = current.expression
+  }
+  return current
+}
+
+/** Return every value only when a type is a closed string-literal union. */
+function finiteStringTypeValues(type: ts.Type): Set<string> | undefined {
+  if (type.flags & ts.TypeFlags.StringLiteral) {
+    return new Set([(type as ts.StringLiteralType).value])
+  }
+  if (type.flags & ts.TypeFlags.Never) return new Set()
+  if (!type.isUnion()) return undefined
+  const values = new Set<string>()
+  for (const member of type.types) {
+    const memberValues = finiteStringTypeValues(member)
+    if (!memberValues) return undefined
+    addAll(values, memberValues)
+  }
+  return values
+}
+
+/** Return whether a variable declaration belongs to a const declaration list. */
+function isConstDeclaration(declaration: ts.VariableDeclaration): boolean {
+  return (declaration.parent.flags & ts.NodeFlags.Const) !== 0
+}
+
+/** Return whether a declaration is visible to callers outside its source module. */
+function hasExportModifier(node: ts.Node): boolean {
+  return ts.canHaveModifiers(node) && (ts.getModifiers(node)?.some((modifier) => {
+    return modifier.kind === ts.SyntaxKind.ExportKeyword || modifier.kind === ts.SyntaxKind.DefaultKeyword
+  }) ?? false)
+}
+
+/** Add every member of source to target. */
+function addAll<T>(target: Set<T>, source: ReadonlySet<T>): void {
+  for (const value of source) target.add(value)
+}
+
+/** Return the union of two sets without mutating either input. */
+function unionSets<T>(left: ReadonlySet<T>, right: ReadonlySet<T>): Set<T> {
+  const out = new Set(left)
+  addAll(out, right)
   return out
 }
 
-function isCordisContextReceiver(expr: ts.PropertyAccessExpression, sf: ts.SourceFile): boolean {
-  // The chained fused-dispatch spelling: `agentEvents(ctx, agent).emit(…)` —
-  // the receiver is a call expression, not an identifier.
-  if (ts.isCallExpression(expr.expression) && expr.expression.expression.getText(sf) === 'agentEvents') {
-    return true
-  }
-  const target = expr.expression.getText(sf)
-  if (target === 'ctx' || target === 'this.ctx') return true
-  // Scoped-dispatch spellings are conventional names. Keep this list in sync
-  // with renames or the relationship matrix can silently lose an edge.
-  return target === 'events' || target === 'childCtx' || target === 'this.loopCtx' || target === 'emitCtx'
-}
-
-function eventArg(args: ts.NodeArray<ts.Expression>, method: string): string | undefined {
-  if (method === 'waterfall') {
-    const arg = args.find(ts.isStringLiteralLike)
-    return arg?.text
-  }
-  const first = args[0]
-  if (first && ts.isStringLiteralLike(first)) return first.text
-  // Scope-carrier dispatch: `emit(carrier, 'event/name', …)` puts the event
-  // name second. Accept a string literal in position 1 when position 0 is a
-  // non-literal expression (the carrier).
-  const second = args[1]
-  return second && ts.isStringLiteralLike(second) ? second.text : undefined
+function collectEventRelations(): Map<string, EventRelation> {
+  const project = new TypeScriptProject(root)
+  const sources = project.sourceFiles().flatMap((sourceFile): PackageSource[] => {
+    const rel = project.relativePath(sourceFile)
+    const match = /^packages\/[^/]+\/([^/]+)\/src\/.+\.ts$/.exec(rel)
+    return match?.[1] ? [{ rel, pkg: match[1], sourceFile }] : []
+  }).sort((left, right) => left.rel.localeCompare(right.rel))
+  return new EventRelationCollector(project, sources).collect()
 }
 
 function relationPackages(map: Map<string, Set<string>>, pkgsByShort: Map<string, Pkg>): string {
@@ -599,10 +738,10 @@ function renderEventRelations(pkgs: Pkg[]): string {
   const events = collectEvents()
   const relations = collectEventRelations()
   const pkgsByShort = new Map(pkgs.map(pkg => [pkg.short, pkg]))
-  const maintenance = 'hybrid generated: Cordis event declarations and most producer/listener edges are AST-scanned; dynamic dispatch sites are classified in `scripts/gen-doc-graphs.ts`'
+  const maintenance = 'generated: Cordis event declarations and producer/listener edges are resolved from the repository TypeScript Program'
   const lines = generatedHeader('Event Producer And Consumer Matrix')
   lines.push(
-    'This matrix shows which packages dispatch each harness-owned event and which packages listen to it. It is intentionally a table rather than one large graph: events are many-to-many, and dense relation data is easier to review in rows. Dynamic dispatch overrides cover sites that deliberately bypass `ctx.emit`, such as subagent lifecycle containment.',
+    'This matrix shows which packages dispatch each harness-owned event and which packages listen to it. It is intentionally a table rather than one large graph: events are many-to-many, and dense relation data is easier to review in rows. Receiver and event-name types also cover contained dispatch sites that deliberately bypass `ctx.emit`, such as subagent lifecycle containment.',
     '',
     '| Event | Mode | Declared in | Dispatchers | Listeners |',
     '| --- | --- | --- | --- | --- |',
@@ -612,7 +751,7 @@ function renderEventRelations(pkgs: Pkg[]): string {
     lines.push(`| \`${event.name}\` | \`${event.mode}\` | ${sourceLink(event.source)} | ${relationPackages(relation.dispatchers, pkgsByShort)} | ${listenerPackages(relation.listeners, pkgsByShort)} |`)
   }
   // Every declared event needs a dispatcher: zero means dead vocabulary or an
-  // unrecognized dispatch spelling. Listener-free extension points remain valid.
+  // unrecognized semantic dispatch shape. Listener-free extension points remain valid.
   const undispatched = [...events]
     .filter(event => (relations.get(event.name)?.dispatchers.size ?? 0) === 0)
     .map(event => event.name)
@@ -620,8 +759,8 @@ function renderEventRelations(pkgs: Pkg[]): string {
   if (undispatched.length > 0) {
     throw new Error(
       `event-producer-consumer matrix: no dispatcher found for declared event${undispatched.length > 1 ? 's' : ''} `
-      + `${undispatched.map(name => `"${name}"`).join(', ')} — dead vocabulary, or a dispatch spelling the scan misses `
-      + '(teach scripts/gen-doc-graphs.ts the spelling or add a DYNAMIC_EVENT_DISPATCHERS override)',
+      + `${undispatched.map(name => `"${name}"`).join(', ')} — dead vocabulary, or a dispatch shape the semantic scan misses `
+      + '(teach scripts/gen-doc-graphs.ts the shape)',
     )
   }
   const declared = new Set(events.map(event => event.name))
diff --git a/scripts/gen-scoped-events.ts b/scripts/gen-scoped-events.ts
new file mode 100644
index 0000000000..a7b93493ca
--- /dev/null
+++ b/scripts/gen-scoped-events.ts
@@ -0,0 +1,441 @@
+/**
+ * Generate the dev-invariants scoped-event resolver map from the
+ * repository TypeScript Program.
+ *
+ * A scoped event declares `this: Scoped<Base>`. Real `scopeTarget(base, key)`
+ * calls establish the routing-key type for that base. The generator searches
+ * every event payload parameter and one property level for exactly one type
+ * equivalent to that key. Each generated resolver compiles against the merged
+ * `Events` parameter tuple. Zero matches require `@dshScopeScan unsupported`;
+ * multiple matches are ambiguous and always fail loud.
+ *
+ *   `tsx scripts/gen-scoped-events.ts`          -> write the generated source
+ *   `tsx scripts/gen-scoped-events.ts --check`  -> exit 1 when it is stale
+ */
+
+import { existsSync, readFileSync, writeFileSync } from 'node:fs'
+import { resolve } from 'node:path'
+import ts from 'typescript'
+import { pointer, rawJsDoc } from './jsdoc.ts'
+import { TypeScriptProject } from './ts-project.ts'
+
+const root = resolve(import.meta.dirname, '..')
+const OUT = 'packages/support/invariants/src/scoped-events.generated.ts'
+const SCOPE_DOC_MARKER = 'Scope-filtered dispatch'
+
+interface ScopeTargetContract {
+  baseType: ts.Type
+  keyType: ts.Type
+  source: string
+}
+
+interface SubjectCandidate {
+  path: string
+  parameter: number
+  property?: string
+  type: ts.Type
+}
+
+interface ScopedEventResolver {
+  event: string
+  candidate: SubjectCandidate | null
+  ownerPackage: string
+}
+
+interface ScopeTag {
+  present: boolean
+  unsupported: boolean
+}
+
+/** Program-backed analyzer and renderer for the generated scoped-event resolvers. */
+class ScopedEventGenerator {
+  private readonly checker: ts.TypeChecker
+  private readonly packageSources: ts.SourceFile[]
+  private readonly scopeTargetDeclaration: ts.FunctionDeclaration
+  private readonly scopedSymbol: ts.Symbol
+  private readonly violations: string[] = []
+  private readonly packageNames = new Map<string, string>()
+
+  constructor(private readonly project: TypeScriptProject) {
+    this.checker = project.checker
+    this.packageSources = project.sourceFiles().filter((sourceFile) => {
+      return /^packages\/[^/]+\/[^/]+\/src\/.+\.ts$/.test(project.relativePath(sourceFile))
+    })
+    this.scopeTargetDeclaration = this.functionDeclaration(
+      'packages/core/scope/src/index.ts',
+      'scopeTarget',
+    )
+    this.scopedSymbol = this.typeAliasSymbol(
+      'packages/core/scope/src/index.ts',
+      'Scoped',
+    )
+  }
+
+  /** Render the complete generated TypeScript module or throw every contract violation. */
+  render(): string {
+    const contracts = this.collectScopeTargetContracts()
+    const resolvers = this.collectScopedEventResolvers(contracts)
+    if (this.violations.length > 0) {
+      throw new Error(
+        `gen-scoped-events: ${this.violations.length} scoped-event contract violation(s):\n`
+        + this.violations.map(violation => `  - ${violation}`).join('\n'),
+      )
+    }
+    const ownerImports = [...new Set(resolvers.map(resolver => resolver.ownerPackage))]
+      .sort()
+      .map(packageName => `import type {} from ${quote(packageName)}`)
+    return [
+      '/**',
+      ' * Generated scoped-event routing-subject resolvers for dsh-invariants.',
+      ' * Do not edit by hand; run `pnpm run gen-scoped-events`.',
+      ' *',
+      ' * @module @deepseek-ai/dsh-invariants/scoped-events.generated',
+      ' */',
+      '',
+      "import type { Events } from 'cordis'",
+      "import type { Scoped } from '@deepseek-ai/dsh-scope'",
+      ...ownerImports,
+      '',
+      'type ScopedEventName = {',
+      '  [K in keyof Events]: ThisParameterType<Events[K]> extends Scoped<object> ? K : never',
+      '}[keyof Events]',
+      '',
+      'type ScopedSubjectResolver = (args: readonly unknown[]) => unknown',
+      '',
+      'function adapt<K extends ScopedEventName>(',
+      '  resolver: (args: Parameters<Events[K]>) => unknown,',
+      '): ScopedSubjectResolver {',
+      '  return args => resolver(args as Parameters<Events[K]>)',
+      '}',
+      '',
+      'const scopedSubjectResolvers = Object.freeze({',
+      ...resolvers.map(({ event, candidate }) => {
+        if (candidate === null) return `  '${event}': null,`
+        const subject = candidate.property === undefined
+          ? `args[${candidate.parameter}]`
+          : `args[${candidate.parameter}].${candidate.property}`
+        return `  '${event}': adapt<'${event}'>(args => ${subject}),`
+      }),
+      '} as const satisfies Readonly<Record<ScopedEventName, ScopedSubjectResolver | null>>)',
+      '',
+      'const scopedSubjectResolverIndex: Readonly<Record<string, ScopedSubjectResolver | null>> = scopedSubjectResolvers',
+      '',
+      '/**',
+      ' * Resolve the routing key named by one scoped event payload. A null',
+      ' * resolver means the payload cannot expose its external routing key, so the',
+      ' * invariant checks carrier presence only.',
+      ' * @param event - runtime Cordis event name.',
+      ' * @returns the generated subject resolver, null for presence-only,',
+      ' *   or undefined when the event is not scope-filtered.',
+      ' */',
+      'export function scopedSubjectResolverFor(event: string): ScopedSubjectResolver | null | undefined {',
+      '  return scopedSubjectResolverIndex[event]',
+      '}',
+      '',
+    ].join('\n')
+  }
+
+  /** Resolve one named function declaration from a known source file. */
+  private functionDeclaration(relativePath: string, name: string): ts.FunctionDeclaration {
+    const sourceFile = this.project.sourceFile(relativePath)
+    const declaration = sourceFile.statements.find((statement): statement is ts.FunctionDeclaration => {
+      return ts.isFunctionDeclaration(statement) && statement.name?.text === name
+    })
+    if (!declaration) throw new Error(`gen-scoped-events: cannot resolve function ${name} from ${relativePath}`)
+    return declaration
+  }
+
+  /** Resolve one named type-alias symbol from a known source file. */
+  private typeAliasSymbol(relativePath: string, name: string): ts.Symbol {
+    const sourceFile = this.project.sourceFile(relativePath)
+    const declaration = sourceFile.statements.find((statement): statement is ts.TypeAliasDeclaration => {
+      return ts.isTypeAliasDeclaration(statement) && statement.name.text === name
+    })
+    const symbol = declaration && this.checker.getSymbolAtLocation(declaration.name)
+    if (!symbol) throw new Error(`gen-scoped-events: cannot resolve type ${name} from ${relativePath}`)
+    return symbol
+  }
+
+  /** Collect every real scopeTarget(base, key) base/key type contract. */
+  private collectScopeTargetContracts(): ScopeTargetContract[] {
+    const contracts: ScopeTargetContract[] = []
+    const visit = (sourceFile: ts.SourceFile, node: ts.Node): void => {
+      if (ts.isCallExpression(node)
+        && this.checker.getResolvedSignature(node)?.declaration === this.scopeTargetDeclaration) {
+        const base = node.arguments[0]
+        const key = node.arguments[1]
+        if (!base || !key) {
+          const source = pointer(this.project.relativePath(sourceFile), sourceFile, node)
+          this.violations.push(`${source} calls scopeTarget without base and key arguments`)
+        } else {
+          contracts.push({
+            baseType: this.checker.getTypeAtLocation(base),
+            keyType: this.checker.getTypeAtLocation(key),
+            source: pointer(this.project.relativePath(sourceFile), sourceFile, node),
+          })
+        }
+      }
+      ts.forEachChild(node, (child) => { visit(sourceFile, child) })
+    }
+    for (const sourceFile of this.packageSources) visit(sourceFile, sourceFile)
+    return contracts
+  }
+
+  /** Collect every Events member and derive its generated resolver. */
+  private collectScopedEventResolvers(contracts: readonly ScopeTargetContract[]): ScopedEventResolver[] {
+    const resolvers: ScopedEventResolver[] = []
+    for (const sourceFile of this.packageSources) {
+      const rel = this.project.relativePath(sourceFile)
+      const ownerPackage = this.packageName(packageRootFor(rel))
+      const visit = (node: ts.Node): void => {
+        if (ts.isInterfaceDeclaration(node) && node.name.text === 'Events' && isCordisModuleInterface(node)) {
+          for (const member of node.members) {
+            if (!ts.isMethodSignature(member) || !ts.isStringLiteral(member.name)) continue
+            const event = member.name.text
+            const raw = rawJsDoc(sourceFile.text, member)
+            const where = `event '${event}' (${pointer(rel, sourceFile, member)})`
+            const tag = parseScopeTag(raw, where, this.violations)
+            const thisParameter = member.parameters.find(isThisParameter)
+            const scopedBase = thisParameter && this.scopedBaseType(thisParameter)
+            if (!scopedBase) {
+              if (raw.includes(SCOPE_DOC_MARKER)) {
+                this.violations.push(
+                  `${where} documents scope-filtered dispatch but its signature has no this: Scoped<...> receiver`,
+                )
+              }
+              if (tag.present) {
+                this.violations.push(`${where} has @dshScopeScan metadata but is not a Scoped event`)
+              }
+              continue
+            }
+            if (!raw.includes(SCOPE_DOC_MARKER)) {
+              this.violations.push(
+                `${where} has this: Scoped<...> but its JSDoc does not explain "${SCOPE_DOC_MARKER}"`,
+              )
+            }
+            const keyType = this.routingKeyType(where, scopedBase, contracts)
+            if (!keyType) continue
+            const candidates = this.subjectCandidates(member)
+              .filter(candidate => this.typesEquivalent(candidate.type, keyType))
+            if (candidates.length > 1) {
+              this.violations.push(
+                `${where} has multiple routing-key candidates for ${this.typeText(keyType)}: `
+                + candidates.map(candidate => `${candidate.path}: ${this.typeText(candidate.type)}`).join(', '),
+              )
+              continue
+            }
+            if (candidates.length === 0) {
+              if (!tag.unsupported) {
+                const keyLabel = this.typeText(keyType)
+                this.violations.push(
+                  `${where} exposes no parameter or one-level property equivalent to routing key type ${keyLabel}; `
+                  + 'add @dshScopeScan unsupported only when the key is intentionally absent from the payload',
+                )
+              }
+              resolvers.push({ event, candidate: null, ownerPackage })
+              continue
+            }
+            if (tag.unsupported) {
+              this.violations.push(
+                `${where} has unnecessary @dshScopeScan unsupported; ${candidates[0]?.path} exposes the routing key`,
+              )
+              continue
+            }
+            resolvers.push({ event, candidate: candidates[0] ?? null, ownerPackage })
+          }
+        }
+        ts.forEachChild(node, visit)
+      }
+      visit(sourceFile)
+    }
+    return resolvers.sort((left, right) => left.event.localeCompare(right.event))
+  }
+
+  /** Extract the Base type from one exact this: Scoped<Base> parameter. */
+  private scopedBaseType(parameter: ts.ParameterDeclaration): ts.Type | undefined {
+    const type = this.checker.getTypeAtLocation(parameter)
+    if (type.aliasSymbol !== this.scopedSymbol) return undefined
+    return type.aliasTypeArguments?.[0]
+  }
+
+  /** Resolve one unambiguous key type for a scoped carrier base. */
+  private routingKeyType(
+    where: string,
+    scopedBase: ts.Type,
+    contracts: readonly ScopeTargetContract[],
+  ): ts.Type | undefined {
+    const matches = contracts.filter((contract) => {
+      return this.checker.isTypeAssignableTo(this.normalizedType(contract.baseType), this.normalizedType(scopedBase))
+    })
+    if (matches.length === 0) {
+      this.violations.push(
+        `${where} has no matching scopeTarget(base, key) call for carrier base ${this.typeText(scopedBase)}`,
+      )
+      return undefined
+    }
+    const keyTypes: ts.Type[] = []
+    for (const match of matches) {
+      if (!keyTypes.some(type => this.typesEquivalent(type, match.keyType))) keyTypes.push(match.keyType)
+    }
+    if (keyTypes.length > 1) {
+      this.violations.push(
+        `${where} carrier base ${this.typeText(scopedBase)} has inconsistent routing-key types: `
+        + matches.map(match => `${this.typeText(match.keyType)} at ${match.source}`).join(', '),
+      )
+      return undefined
+    }
+    return keyTypes[0]
+  }
+
+  /** Enumerate every payload parameter and every accessible one-level property. */
+  private subjectCandidates(member: ts.MethodSignature): SubjectCandidate[] {
+    const candidates: SubjectCandidate[] = []
+    let runtimeIndex = 0
+    for (const parameter of member.parameters) {
+      if (isThisParameter(parameter)) continue
+      const directPath = `args[${runtimeIndex}]`
+      const parameterType = this.checker.getTypeAtLocation(parameter)
+      candidates.push({ path: directPath, parameter: runtimeIndex, type: parameterType })
+      for (const property of this.checker.getPropertiesOfType(this.normalizedType(parameterType))) {
+        const name = property.getName()
+        if (name.startsWith('__@') || hasNonPublicDeclaration(property)) continue
+        candidates.push({
+          path: `${directPath}.${name}`,
+          parameter: runtimeIndex,
+          property: name,
+          type: this.checker.getTypeOfSymbolAtLocation(property, parameter),
+        })
+      }
+      runtimeIndex += 1
+    }
+    return dedupeCandidates(candidates)
+  }
+
+  /** Read and cache one workspace package name. */
+  private packageName(packageRoot: string): string {
+    const cached = this.packageNames.get(packageRoot)
+    if (cached) return cached
+    const manifest: unknown = JSON.parse(readFileSync(resolve(root, packageRoot, 'package.json'), 'utf8'))
+    const name: unknown = typeof manifest === 'object' && manifest !== null
+      ? Reflect.get(manifest, 'name')
+      : undefined
+    if (typeof name !== 'string') throw new Error(`gen-scoped-events: ${packageRoot}/package.json has no name`)
+    this.packageNames.set(packageRoot, name)
+    return name
+  }
+
+  /** Compare exact Program type identities after removing null and undefined. */
+  private typesEquivalent(left: ts.Type, right: ts.Type): boolean {
+    const normalizedLeft = this.normalizedType(left)
+    const normalizedRight = this.normalizedType(right)
+    if (normalizedLeft.flags & (ts.TypeFlags.Any | ts.TypeFlags.Unknown)) return false
+    if (normalizedRight.flags & (ts.TypeFlags.Any | ts.TypeFlags.Unknown)) return false
+    return normalizedLeft === normalizedRight
+  }
+
+  /** Remove null and undefined from a routing or candidate type. */
+  private normalizedType(type: ts.Type): ts.Type {
+    return this.checker.getNonNullableType(type)
+  }
+
+  /** Render a stable diagnostic type label. */
+  private typeText(type: ts.Type): string {
+    return this.checker.typeToString(type, undefined, ts.TypeFormatFlags.NoTruncation)
+  }
+}
+
+/** Return whether an Events interface is inside declare module 'cordis'. */
+function isCordisModuleInterface(node: ts.InterfaceDeclaration): boolean {
+  const block = node.parent
+  const declaration = block.parent
+  return ts.isModuleBlock(block)
+    && ts.isModuleDeclaration(declaration)
+    && ts.isStringLiteral(declaration.name)
+    && declaration.name.text === 'cordis'
+}
+
+/** Return whether a parameter is the explicit TypeScript this receiver. */
+function isThisParameter(parameter: ts.ParameterDeclaration): boolean {
+  return ts.isIdentifier(parameter.name) && parameter.name.text === 'this'
+}
+
+/** Parse and validate the optional @dshScopeScan unsupported tag. */
+function parseScopeTag(raw: string, where: string, violations: string[]): ScopeTag {
+  const tags = raw
+    .replace(/^\/\*\*/, '')
+    .replace(/\*\/$/, '')
+    .split('\n')
+    .map(line => line.replace(/^\s*\*?\s?/, '').trim())
+    .filter(line => line.startsWith('@dshScopeScan'))
+  if (tags.length > 1) violations.push(`${where} has multiple @dshScopeScan tags`)
+  if (tags.length === 0) return { present: false, unsupported: false }
+  const unsupported = tags[0] === '@dshScopeScan unsupported'
+  if (!unsupported) {
+    violations.push(
+      `${where} has invalid scoped-event scan metadata '${tags[0]}'; expected '@dshScopeScan unsupported'`,
+    )
+  }
+  return { present: true, unsupported }
+}
+
+/** Return whether a property has a private or protected declaration. */
+function hasNonPublicDeclaration(symbol: ts.Symbol): boolean {
+  return (symbol.declarations ?? []).some((declaration) => {
+    if (!ts.canHaveModifiers(declaration)) return false
+    return ts.getModifiers(declaration)?.some((modifier) => {
+      return modifier.kind === ts.SyntaxKind.PrivateKeyword || modifier.kind === ts.SyntaxKind.ProtectedKeyword
+    }) ?? false
+  })
+}
+
+/** Deduplicate candidate paths contributed by merged/intersection types. */
+function dedupeCandidates(candidates: readonly SubjectCandidate[]): SubjectCandidate[] {
+  const seen = new Set<string>()
+  return candidates.filter((candidate) => {
+    if (seen.has(candidate.path)) return false
+    seen.add(candidate.path)
+    return true
+  })
+}
+
+/** Return the workspace package root owning one package source file. */
+function packageRootFor(relativePath: string): string {
+  const match = /^(packages\/[^/]+\/[^/]+)\/src\//.exec(relativePath)
+  if (!match?.[1]) throw new Error(`gen-scoped-events: cannot derive package root from ${relativePath}`)
+  return match[1]
+}
+
+/** Quote a generated property key as a single-quoted TypeScript string. */
+function quote(value: string): string {
+  return `'${value.replaceAll('\\', '\\\\').replaceAll("'", "\\'")}'`
+}
+
+/**
+ * Render the generated scoped-event resolver module for one repository root.
+ * @param projectRoot - repository root carrying tsconfig.json.
+ * @returns complete generated TypeScript source.
+ */
+export function renderScopedEvents(projectRoot: string = root): string {
+  return new ScopedEventGenerator(new TypeScriptProject(projectRoot)).render()
+}
+
+/** Generate or freshness-check the fixed invariants source file. */
+function main(): void {
+  const content = renderScopedEvents()
+  const output = resolve(root, OUT)
+  if (process.argv.includes('--check')) {
+    const committed = existsSync(output) ? readFileSync(output, 'utf8') : null
+    if (committed === content) {
+      console.log(`gen-scoped-events: ${OUT} is up to date.`)
+      return
+    }
+    console.error(`gen-scoped-events: ${OUT} is stale. Run \`pnpm run gen-scoped-events\` and commit it.`)
+    process.exit(1)
+  }
+  writeFileSync(output, content)
+  console.log(`gen-scoped-events: wrote ${OUT}.`)
+}
+
+if (process.argv[1] && import.meta.filename === resolve(process.argv[1])) {
+  main()
+}
diff --git a/scripts/run-gates.ts b/scripts/run-gates.ts
index 0e5e50a894..7f23a666ae 100644
--- a/scripts/run-gates.ts
+++ b/scripts/run-gates.ts
@@ -153,6 +153,7 @@ function gatesForMode(selected: Mode): Gate[] {
     case 'pre-push':
       return [
         pnpmScript('runtime-closure', 'verify-runtime-closure', { label: 'runtime closure' }),
+        pnpmScript('cordis-config', 'verify-cordis-config', { label: 'Cordis config' }),
         pnpmScript('test', 'test'),
         pnpmScript('duplication', 'duplication'),
         pnpmScript('snapshot', 'test:snapshot'),
@@ -168,6 +169,7 @@ function ciPrimaryGates(): Gate[] {
   return [
     pnpmScript('runtime-closure', 'verify-runtime-closure', { label: 'runtime closure' }),
     pnpmScript('constraints', 'constraints'),
+    pnpmScript('cordis-config', 'verify-cordis-config', { label: 'Cordis config' }),
     pnpmScript('typecheck', 'typecheck'),
     lintGate(),
     pnpmScript('duplication', 'duplication'),
@@ -191,6 +193,7 @@ function ciStaticGates(): Gate[] {
   return [
     pnpmScript('runtime-closure', 'verify-runtime-closure', { label: 'runtime closure' }),
     pnpmScript('constraints', 'constraints'),
+    pnpmScript('cordis-config', 'verify-cordis-config', { label: 'Cordis config' }),
     demoSmokeGate(),
     ...docSyncLeafGates(),
     pnpmScript('module-graph', 'verify-module-graph', { label: 'module graph' }),
@@ -273,7 +276,7 @@ function docSyncLeafGates(): Gate[] {
     pnpmScript('config-catalog', 'verify-config-catalog', { label: 'config catalog' }),
     pnpmScript('persistence-catalog', 'verify-persistence-catalog', { label: 'persistence catalog' }),
     pnpmScript('doc-graphs', 'verify-doc-graphs', { label: 'doc graphs' }),
-    pnpmScript('scoped-dispatch', 'verify-scoped-dispatch', { label: 'scoped dispatch' }),
+    pnpmScript('scoped-events', 'verify-scoped-events', { label: 'scoped events' }),
     pnpmScript('markdown-wrap', 'verify-md-wrap', { label: 'markdown wrap' }),
     pnpmScript('markdown-links', 'verify-md-links', { label: 'markdown links' }),
     pnpmScript('doc-refs', 'verify-doc-refs', { label: 'doc refs' }),
diff --git a/scripts/translation-pairing.manifest.json b/scripts/translation-pairing.manifest.json
index cea3eb393a..35a957e57d 100644
--- a/scripts/translation-pairing.manifest.json
+++ b/scripts/translation-pairing.manifest.json
@@ -2,6 +2,12 @@
   "requiredSince": "2026-07-14",
   "required": [
     "README.md",
+    "docs/cookbook/adding-a-package.md",
+    "docs/cookbook/adding-a-tool.md",
+    "docs/cookbook/adding-a-vendored-package.md",
+    "docs/cookbook/adding-an-llm-adapter.md",
+    "docs/cookbook/extension-cookbook.md",
+    "docs/cookbook/responding-to-pr-review-on-a-stack.md",
     "docs/development.md",
     "docs/i18n/README.md",
     "docs/i18n/translation-rules.md",
diff --git a/scripts/ts-project.ts b/scripts/ts-project.ts
new file mode 100644
index 0000000000..0b59aee873
--- /dev/null
+++ b/scripts/ts-project.ts
@@ -0,0 +1,113 @@
+/**
+ * Shared TypeScript Program construction for repository gates that need real
+ * cross-file symbols and types instead of isolated syntax trees.
+ */
+
+import { relative, resolve } from 'node:path'
+import ts from 'typescript'
+
+interface ProjectGraph {
+  rootNames: string[]
+  options: ts.CompilerOptions
+}
+
+const configHost: ts.ParseConfigFileHost = {
+  useCaseSensitiveFileNames: ts.sys.useCaseSensitiveFileNames,
+  readDirectory: (...args) => ts.sys.readDirectory(...args),
+  fileExists: fileName => ts.sys.fileExists(fileName),
+  readFile: fileName => ts.sys.readFile(fileName),
+  getCurrentDirectory: () => ts.sys.getCurrentDirectory(),
+  onUnRecoverableConfigFileDiagnostic(diagnostic) {
+    throw new Error(ts.flattenDiagnosticMessageText(diagnostic.messageText, '\n'))
+  },
+}
+
+/** Parse a root tsconfig and flatten all referenced projects into one semantic graph. */
+function loadProjectGraph(projectRoot: string): ProjectGraph {
+  const rootConfigPath = resolve(projectRoot, 'tsconfig.json')
+  const rootConfig = parseConfig(rootConfigPath)
+  const rootNames = new Set<string>()
+  const visited = new Set<string>()
+
+  const collect = (configPath: string, parsed: ts.ParsedCommandLine): void => {
+    if (visited.has(configPath)) return
+    visited.add(configPath)
+    for (const fileName of parsed.fileNames) rootNames.add(fileName)
+    for (const reference of parsed.projectReferences ?? []) {
+      const referencePath = ts.resolveProjectReferencePath(reference)
+      collect(referencePath, parseConfig(referencePath))
+    }
+  }
+  collect(rootConfigPath, rootConfig)
+
+  return {
+    rootNames: [...rootNames],
+    options: rootConfig.options,
+  }
+}
+
+/** Parse one config file and fail loud on any config diagnostic. */
+function parseConfig(configPath: string): ts.ParsedCommandLine {
+  const parsed = ts.getParsedCommandLineOfConfigFile(configPath, {}, configHost)
+  if (!parsed) throw new Error(`cannot parse TypeScript config ${configPath}`)
+  if (parsed.errors.length > 0) {
+    throw new Error(parsed.errors.map(error => ts.flattenDiagnosticMessageText(error.messageText, '\n')).join('\n'))
+  }
+  return parsed
+}
+
+/** Disable emit-only options after loading the root solution config. */
+function semanticCompilerOptions(options: ts.CompilerOptions): ts.CompilerOptions {
+  return {
+    ...options,
+    noEmit: true,
+    composite: false,
+    declaration: false,
+    declarationMap: false,
+    sourceMap: false,
+    incremental: false,
+  }
+}
+
+/** A repository-scoped TypeScript Program and its shared TypeChecker. */
+export class TypeScriptProject {
+  /** The bound cross-file TypeScript program. */
+  readonly program: ts.Program
+  /** The checker shared by every semantic query in this project. */
+  readonly checker: ts.TypeChecker
+
+  constructor(private readonly projectRoot: string) {
+    const graph = loadProjectGraph(projectRoot)
+    this.program = ts.createProgram(graph.rootNames, semanticCompilerOptions(graph.options))
+    this.checker = this.program.getTypeChecker()
+  }
+
+  /**
+   * Return every source file loaded into the flattened root project graph.
+   * @returns program source files, including libraries and external dependencies.
+   */
+  sourceFiles(): readonly ts.SourceFile[] {
+    return this.program.getSourceFiles()
+  }
+
+  /**
+   * Render a loaded source file relative to the project root.
+   * @param sourceFile - a source file from this project.
+   * @returns a slash-separated repository-relative path.
+   */
+  relativePath(sourceFile: ts.SourceFile): string {
+    return relative(this.projectRoot, sourceFile.fileName).replaceAll('\\', '/')
+  }
+
+  /**
+   * Return one program source file by repository-relative path.
+   * @param relativePath - path relative to the project root.
+   * @returns the source file bound into this project.
+   * @throws if a requested root or imported source was not loaded.
+   */
+  sourceFile(relativePath: string): ts.SourceFile {
+    const sourceFile = this.program.getSourceFile(resolve(this.projectRoot, relativePath))
+    if (!sourceFile) throw new Error(`TypeScript project did not load ${relativePath}`)
+    return sourceFile
+  }
+}
diff --git a/scripts/verify-cordis-config.ts b/scripts/verify-cordis-config.ts
new file mode 100644
index 0000000000..131bcf0e58
--- /dev/null
+++ b/scripts/verify-cordis-config.ts
@@ -0,0 +1,111 @@
+/**
+ * Reject JavaScript expressions in Cordis Loader entry metadata.
+ *
+ * The Loader interpolates only a plugin entry's `config`; expression objects in
+ * fields such as `disabled` remain truthy data and silently change composition.
+ */
+
+import { globSync, readFileSync } from 'node:fs'
+import { resolve } from 'node:path'
+import * as yaml from 'js-yaml'
+
+interface JsExpr {
+  __jsExpr: string
+}
+
+const root = resolve(import.meta.dirname, '..')
+const metadataFields = ['id', 'name', 'group', 'disabled', 'inject', 'intercept', 'isolate'] as const
+const jsExprType = new yaml.Type('tag:yaml.org,2002:js', {
+  kind: 'scalar',
+  resolve: data => typeof data === 'string',
+  construct: (data: unknown): JsExpr => {
+    if (typeof data !== 'string') throw new TypeError('!!js requires a scalar string')
+    return { __jsExpr: data }
+  },
+})
+const schema = yaml.JSON_SCHEMA.extend(jsExprType)
+
+const files = globSync(['**/*cordis*.yml', '**/*cordis*.yaml'], {
+  cwd: root,
+  exclude: ['.claude/**', 'node_modules/**', 'vendor/**'],
+}).sort()
+const errors: string[] = []
+
+for (const file of files) {
+  const document: unknown = yaml.load(readFileSync(resolve(root, file), 'utf8'), { schema })
+  if (!isUnknownArray(document)) {
+    errors.push(`${file}: root must be a Loader entry array`)
+    continue
+  }
+  for (let index = 0; index < document.length; index++) {
+    validateEntry(document[index], file, `[${index}]`)
+  }
+}
+
+if (errors.length > 0) {
+  console.error('verify-cordis-config: Loader entry metadata is static; move !!js under plugin config or select an explicit overlay.')
+  for (const error of errors) console.error(`- ${error}`)
+  process.exitCode = 1
+} else {
+  console.log(`verify-cordis-config: ${files.length} config files passed.`)
+}
+
+function validateEntry(value: unknown, file: string, path: string): void {
+  if (!isRecord(value)) {
+    errors.push(`${file}${path}: entry must be an object`)
+    return
+  }
+  validateMetadata(value, file, path)
+  if ((value.group === true || value.name === '@cordisjs/plugin-group') && isUnknownArray(value.config)) {
+    for (let index = 0; index < value.config.length; index++) {
+      validateEntry(value.config[index], file, `${path}.config[${index}]`)
+    }
+  }
+  if (value.name !== '@cordisjs/plugin-include') return
+  const config = value.config
+  if (!isRecord(config) || !isUnknownArray(config.patches)) return
+  for (let index = 0; index < config.patches.length; index++) {
+    const patch = config.patches[index]
+    const patchPath = `${path}.config.patches[${index}]`
+    if (!isRecord(patch)) continue
+    validateMetadata(patch, file, patchPath)
+    if (!isUnknownArray(patch.insert)) continue
+    for (let insertIndex = 0; insertIndex < patch.insert.length; insertIndex++) {
+      validateEntry(patch.insert[insertIndex], file, `${patchPath}.insert[${insertIndex}]`)
+    }
+  }
+}
+
+function validateMetadata(entry: Record<string, unknown>, file: string, path: string): void {
+  for (const field of metadataFields) {
+    if (!(field in entry)) continue
+    const expressionPaths: string[] = []
+    collectExpressionPaths(entry[field], `${path}.${field}`, expressionPaths)
+    for (const expressionPath of expressionPaths) errors.push(`${file}${expressionPath}: !!js is not interpolated here`)
+  }
+}
+
+function collectExpressionPaths(value: unknown, path: string, output: string[]): void {
+  if (isJsExpr(value)) {
+    output.push(path)
+    return
+  }
+  if (isUnknownArray(value)) {
+    for (let index = 0; index < value.length; index++) collectExpressionPaths(value[index], `${path}[${index}]`, output)
+    return
+  }
+  if (!isRecord(value)) return
+  for (const [key, child] of Object.entries(value)) collectExpressionPaths(child, `${path}.${key}`, output)
+}
+
+function isJsExpr(value: unknown): value is JsExpr {
+  return isRecord(value) && typeof value.__jsExpr === 'string'
+}
+
+function isRecord(value: unknown): value is Record<string, unknown> {
+  return value !== null && typeof value === 'object'
+}
+
+function isUnknownArray(value: unknown): value is unknown[] {
+  return Array.isArray(value)
+}
diff --git a/scripts/verify-scoped-dispatch.ts b/scripts/verify-scoped-dispatch.ts
deleted file mode 100644
index 64e2333340..0000000000
--- a/scripts/verify-scoped-dispatch.ts
+++ /dev/null
@@ -1,69 +0,0 @@
-/**
- * Scoped-dispatch drift gate: the set of scope-filtered events is declared in TWO places that
- * must never diverge — the dev-invariants runtime table (the `scopedSubject` map in
- * `packages/support/invariants/src/index.ts`, which enforces carriers at dispatch time) and
- * the event declarations' JSDoc (the "Scope-filtered dispatch" sentence rendered into the
- * events catalog, which tells plugin authors what a scoped listener will and won't hear).
- * Registry-subject notifications are intentionally unfiltered and belong in neither set.
- */
-
-import { globSync, readFileSync } from 'node:fs'
-import { resolve } from 'node:path'
-
-const root = resolve(import.meta.dirname, '..')
-
-/** The marker sentence every scope-filtered event's JSDoc carries. */
-const MARKER = 'Scope-filtered dispatch'
-
-/** Events that are deliberately UNFILTERED registry-subject notifications. */
-const REGISTRY_SUBJECT = new Set(['tools/change', 'system-prompt/change', 'subagent/provider-added', 'subagent/provider-removed'])
-
-function invariantTable(): Set<string> {
-  const source = readFileSync(resolve(root, 'packages/support/invariants/src/index.ts'), 'utf8')
-  const start = source.indexOf('const scopedSubject')
-  if (start < 0) throw new Error('verify-scoped-dispatch: cannot find the scopedSubject table in dsh-invariants')
-  const block = source.slice(start, source.indexOf('}', start))
-  return new Set([...block.matchAll(/'([a-z-]+\/[a-z-]+)':/g)].flatMap(match => match[1] === undefined ? [] : [match[1]]))
-}
-
-function documentedSet(): Set<string> {
-  const documented = new Set<string>()
-  for (const rel of globSync('packages/*/*/src/**/*.ts', { cwd: root })) {
-    const source = readFileSync(resolve(root, rel), 'utf8')
-    if (!source.includes(MARKER)) continue
-    // Each event declaration: a JSDoc block followed by the quoted event name.
-    // Tolerate `//` comment lines between the JSDoc and the declaration
-    // (e.g. an inline TODO under the doc block).
-    for (const match of source.matchAll(/\/\*\*([\s\S]*?)\*\/\s*\n(?:\s*\/\/[^\n]*\n)*\s*'([a-z-]+\/[a-z-]+)'\(/g)) {
-      const [, doc, event] = match
-      if (doc === undefined || event === undefined) continue
-      if (doc.includes(MARKER)) documented.add(event)
-    }
-  }
-  return documented
-}
-
-const table = invariantTable()
-const documented = documentedSet()
-
-const problems: string[] = []
-for (const event of table) {
-  if (!documented.has(event)) {
-    problems.push(`"${event}" is enforced by the dev-invariants carrier table but its declaration JSDoc carries no "${MARKER}" sentence — document the filtering plugin authors will observe.`)
-  }
-  if (REGISTRY_SUBJECT.has(event)) {
-    problems.push(`"${event}" is a registry-subject notification (deliberately unfiltered) but appears in the dev-invariants carrier table.`)
-  }
-}
-for (const event of documented) {
-  if (!table.has(event)) {
-    problems.push(`"${event}" documents scope-filtered dispatch but is missing from the dev-invariants carrier table (packages/support/invariants) — a bare dispatch of it would silently revert to global delivery.`)
-  }
-}
-
-if (problems.length > 0) {
-  console.error(`verify-scoped-dispatch: ${problems.length} drift(s) between the invariant table and the documented scoped-event set:`)
-  for (const problem of problems) console.error(`  - ${problem}`)
-  process.exit(1)
-}
-console.log(`verify-scoped-dispatch: ${table.size} scope-filtered event(s) consistent between the invariant table and the declaration docs.`)