feat: add canonical typed tool outputs
This commit is contained in:
Tianyi Cui
@@ -97,7 +97,8 @@ forever:
|
||||
exclusive -> one-call barrier
|
||||
parallel -> rolling pool, <= maxParallelToolCalls in flight; reclassify before start
|
||||
each start -> 'tool/call' -> ordered tools/pre-execute -> concurrent tools/execute
|
||||
each model-order result -> ordered tools/post-execute -> 'tool/result'
|
||||
body value -> validate/snapshot -> Native/meta projection
|
||||
each model-order result -> ordered tools/post-execute -> projected 'tool/result'
|
||||
append accepted tool-batch context after all recorded results, then steering
|
||||
agent/post-step
|
||||
'step/end'
|
||||
@@ -110,7 +111,7 @@ forever:
|
||||
|
||||
Each step assembles ordered prompt sections, tool schemas, and `{{name}}` variables; unknown or valueless references fail the turn. `dsh-system-prompt` owns the harness identity and default persona, which an agent scope may shadow. The loop supplies `model` and `cwd` ([prompt ownership](../.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md)).
|
||||
|
||||
Tool-time context—including async `agent.inject()` notices and post-tool `additionalContexts`—settles after results. Steering drains; before signal closure, `agent/post-step` observes durable output, results, context, and steering. Leftovers queue. Terminal `agent/turn-stop` runs after continuation and steering folding, remains authoritative through close/flush, and discards later steering while preserving queued prompts.
|
||||
Tool success separates an execution-local canonical JSON value from Native projections; post-policy replaces one projection or blocks, and the loop persists only projections ([contract](../.agents/notes/implemented/architecture/2026-07-20-canonical-tool-output-contract.md)). Tool-time context—including async `agent.inject()` notices and post-tool `additionalContexts`—settles after results. Steering drains; before signal closure, `agent/post-step` observes durable output, results, context, and steering. Leftovers queue. Terminal `agent/turn-stop` runs after continuation and steering folding, remains authoritative through close/flush, and discards later steering while preserving queued prompts.
|
||||
|
||||
Pruning precedes summaries; overflow retries require durable progress. Bounded transient retries compose on `agent/request-error`; cancellation wins ([compaction](../.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md), [retry](../.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.md)).
|
||||
|
||||
|
||||
@@ -27,7 +27,7 @@ export interface AcpConfig {
|
||||
|
||||
Depends on: `Stream` (`@agentclientprotocol/sdk`)
|
||||
|
||||
Source: [`packages/ui/acp/src/index.ts:247`](../packages/ui/acp/src/index.ts)
|
||||
Source: [`packages/ui/acp/src/index.ts:248`](../packages/ui/acp/src/index.ts)
|
||||
|
||||
## `@deepseek-ai/dsh-acp-demo`
|
||||
|
||||
@@ -666,7 +666,7 @@ export interface StreamableHttpConfig {
|
||||
}
|
||||
```
|
||||
|
||||
Source: [`packages/mcp/mcp-client/src/index.ts:91`](../packages/mcp/mcp-client/src/index.ts)
|
||||
Source: [`packages/mcp/mcp-client/src/index.ts:93`](../packages/mcp/mcp-client/src/index.ts)
|
||||
|
||||
## `@deepseek-ai/dsh-permission`
|
||||
|
||||
@@ -923,7 +923,7 @@ export interface Config {
|
||||
}
|
||||
```
|
||||
|
||||
Source: [`packages/spill/spill-policy/src/index.ts:45`](../packages/spill/spill-policy/src/index.ts)
|
||||
Source: [`packages/spill/spill-policy/src/index.ts:50`](../packages/spill/spill-policy/src/index.ts)
|
||||
|
||||
## `@deepseek-ai/dsh-subagent-acp`
|
||||
|
||||
@@ -1157,7 +1157,7 @@ export interface Config {
|
||||
}
|
||||
```
|
||||
|
||||
Source: [`packages/workflow/tool-ralph/src/index.ts:22`](../packages/workflow/tool-ralph/src/index.ts)
|
||||
Source: [`packages/workflow/tool-ralph/src/index.ts:23`](../packages/workflow/tool-ralph/src/index.ts)
|
||||
|
||||
## `@deepseek-ai/dsh-tool-skill`
|
||||
|
||||
@@ -1227,7 +1227,7 @@ export interface Config {
|
||||
|
||||
Depends on: [`AgentOptions`](core-data-structures/core.md)
|
||||
|
||||
Source: [`packages/subagent/tool-subagent/src/index.ts:23`](../packages/subagent/tool-subagent/src/index.ts)
|
||||
Source: [`packages/subagent/tool-subagent/src/index.ts:24`](../packages/subagent/tool-subagent/src/index.ts)
|
||||
|
||||
## `@deepseek-ai/dsh-tool-tasks`
|
||||
|
||||
@@ -1281,7 +1281,7 @@ export interface Config {
|
||||
}
|
||||
```
|
||||
|
||||
Source: [`packages/workflow/tool-workflow/src/index.ts:26`](../packages/workflow/tool-workflow/src/index.ts)
|
||||
Source: [`packages/workflow/tool-workflow/src/index.ts:27`](../packages/workflow/tool-workflow/src/index.ts)
|
||||
|
||||
## `@deepseek-ai/dsh-tools`
|
||||
|
||||
@@ -1303,7 +1303,7 @@ export interface Config {
|
||||
export type ToolPresentationMode = 'native' | 'code' | 'both'
|
||||
```
|
||||
|
||||
Source: [`packages/core/tools/src/index.ts:397`](../packages/core/tools/src/index.ts)
|
||||
Source: [`packages/core/tools/src/index.ts:448`](../packages/core/tools/src/index.ts)
|
||||
|
||||
## `@deepseek-ai/dsh-tui`
|
||||
|
||||
|
||||
@@ -2,5 +2,5 @@
|
||||
# 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: 94cb4fcfa9a0155fd57ef18f9a855a264c2eff84
|
||||
adding-a-tool.zh.md: 637dc3381765e57c2d0420164ac13fde7fb590fe
|
||||
adding-a-tool.md: f94ddfaa9df53c0ee4596d683e676baae6bd85b2
|
||||
adding-a-tool.zh.md: 915dc8250c2bcfc490483f87c71e725b1f92f635
|
||||
|
||||
@@ -22,10 +22,14 @@ export function apply(ctx: Context) {
|
||||
path: { type: 'string', required: true, description: 'Absolute path' },
|
||||
limit: { type: 'number' }, // optional by default
|
||||
},
|
||||
output: {
|
||||
schema: { type: 'string' },
|
||||
render: (_args, value) => [{ type: 'text', text: value }],
|
||||
},
|
||||
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') }]
|
||||
return readFile(args.path, 'utf8')
|
||||
},
|
||||
}))
|
||||
}
|
||||
@@ -38,9 +42,10 @@ Registration is effect-based: disposing the plugin fiber unregisters the tool (w
|
||||
- **Args are validated for you.** `defineTool` validates model-generated `arguments` against the unified `ParameterSchemaSpec` before `execute` runs (types, required keys, literal constraints, exact-one unions, and nested values — [runtime arg validation](../../.agents/notes/implemented/architecture/2026-06-11-runtime-arg-validation.md)), so inside `execute` the args match `InferArgs`. Explicit object nodes declare `additionalProperties: true | false`; the implicit parameter root stays open. You still hand-check constraints the DSL does not express, such as non-empty strings, positive numbers, or cross-field rules. Raw JSON-Schema tools registered directly own their input validation.
|
||||
- **Registration borrows your readonly definition.** A typed same-process contribution is not a serialization boundary; do not mutate its schema or replace callbacks after registration. `schemas()` materializes only the explicit model-facing projection. To hot-swap a tool, dispose its owning effect and register the replacement; mutable state inside the callback's closure remains ordinary plugin state.
|
||||
- **Execution identity is protected.** The registry materializes `arguments` as detached lossless JSON in one recursive pass, freezes that value before policy starts, and assigns an opaque `exec.token`; `callId`, `name`, `arguments`, `agent`, `token`, and an optional enclosing-transport `parent` token stay immutable through dispatch. `parent` is identity-only and exposes no live outer execution. Treat `args` as readonly input. An around-dispatch wrapper may add, replace, or remove only `exec.signal` to impose cancellation or a deadline.
|
||||
- **Throwing or returning non-JSON data means `isError`.** The registry catches throws and materializes the final result before observers run. A malformed or non-JSON result becomes `{ isError: true }`, preventing a live success that cannot be logged. Throw for infrastructure failures; report domain failures in result text when the model must interpret them.
|
||||
- **Declare and return one canonical JSON value.** `output.schema` uses `ValueSchemaSpec` and may have an object, array, scalar, or null root. `execute` returns only the inferred value; the registry snapshots it as lossless JSON, validates it, freezes it, and passes it to `output.render(args, value)`. Do not return content blocks from the body or make callers parse prose for ids and fields.
|
||||
- **Throwing or returning an invalid value means `isError`.** The registry catches throws and contains schema, renderer, metadata-projector, and lossless-JSON failures before observers run. Throw for infrastructure failures. Represent a successful domain outcome in the canonical value even when its Native renderer explains a non-ideal state, such as a non-zero process exit.
|
||||
- **Honor `exec.signal`.** Cancel in-flight work when it fires.
|
||||
- **Attach durable card data with `meta` (optional).** `execute` may return `{ content, meta }` instead of a bare `ContentBlock[]` — `meta` is a JSON-serializable payload the core treats as opaque, persisted on the `tool/result` event and handed back to your `presentResult` (so a card that needs more than `args`, like `write`/`edit`'s applied-hunk diff, survives a session replay). Keep UI-only data here, never in the model-facing `content`.
|
||||
- **Project durable card data with `presentationMeta` (optional).** `output.presentationMeta(args, value)` derives replayable JSON from the same canonical value. The core persists it on `tool/result` and hands it to `presentResult`, so a card that needs result-time facts—such as `write`/`edit` applied hunks—survives replay without persisting the canonical value. The projector is skipped for nested Code dispatches because they have no cards.
|
||||
- **Use `exec.agent` for async notifications.** `agent.inject(content, {source: {kind: 'plugin', plugin: '<name>'}})` appends durable context the NEXT model request sees — it is not a wake-up (an idle agent stays idle). Guard against disposed agents (try/catch).
|
||||
|
||||
## Long-running work
|
||||
@@ -51,7 +56,7 @@ The producer supplies synchronous `cancel`, non-rejecting `done` that settles af
|
||||
|
||||
## 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-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).
|
||||
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 canonical dispatch with a deadline/retry/metrics scope, `tools/post-execute` to replace either presentation content or the canonical value, block, or attach model-facing context, and `tools/result` to observe the immutable normalized outcome. A content replacement leaves programmatic access to `value` intact; confidentiality policy blocks or replaces the value. 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
|
||||
|
||||
@@ -59,7 +64,7 @@ In [Code Mode](../../packages/core/tools/README.md), every visible registered to
|
||||
|
||||
## How your tool renders in an editor (ACP presentation)
|
||||
|
||||
Your tool's `execute` returns model-facing content; its **editor card** is a separate, optional concern you declare with two pure display methods on the `defineTool` options. Design this alongside `execute`, not after — an editor (Zed, over the ACP bridge) shows the card, and a tool with no presentation falls back to a bland generic card (title = tool name, raw args as input).
|
||||
Your tool's `output.render` returns model-facing content; its **editor card** is a separate concern declared through pure presentation projections and optional `presentCall` / `presentResult` methods. Design these alongside the canonical value—an editor (Zed, over the ACP bridge) shows the card, and a tool with no UI presentation falls back to a generic card (title = tool name, raw args as input).
|
||||
|
||||
Both methods return a **`card`-tagged render intent** — pick the card kind that matches what your tool does:
|
||||
|
||||
@@ -70,16 +75,16 @@ Both methods return a **`card`-tagged render intent** — pick the card kind tha
|
||||
- `presentResult(args, { content, isError, meta? })` returns the completed card:
|
||||
- `generic` supplies an optional title and content.
|
||||
- `terminal` supplies raw output and optional exit metadata; the bridge renders the capability-specific or fenced fallback view.
|
||||
- `diff` supplies applied hunks, often carried in persisted `result.meta` so replay reproduces them. Mutation tools keep a diff result because an ACP update replaces the pending card's content.
|
||||
- `diff` supplies applied hunks, often derived by `output.presentationMeta` and carried in persisted `result.meta` so replay reproduces them. Mutation tools keep a diff result because an ACP update replaces the pending card's content.
|
||||
|
||||
Hard rules (they bite if broken):
|
||||
|
||||
- **Purity.** These run on live streaming AND on session-log REPLAY, so they must be pure functions of `args` (+ the result) — NO I/O, NO reading session state, NO clock/random. A diff is derived from the args (`write` uses `oldText: null` because a call-time presenter has no prior file content); the BRIDGE, not the tool, fills the session cwd and relativizes a display-path title. If you find yourself wanting the file's old content or the working directory inside `presentCall`, stop — that belongs on the bridge or a future result-event shape, not the presenter.
|
||||
- **UI-only formatting stays out of the model result.** A fenced ` ```console ` block, a diff, a relativized path — none of these may appear in what `execute` returns to the model; they live only in the presentation. (A `terminal` result view carries RAW `output`; the bridge adds the fences.)
|
||||
- **UI-only formatting stays out of the model result.** A fenced ` ```console ` block, a diff, a relativized path—none of these belongs in the canonical value or Native content merely to serve an editor. `output.render` owns model-facing prose; `presentationMeta` plus the card presenters own replayable UI state. A `terminal` result view carries raw output and the bridge adds fences.
|
||||
- **`defineTool` soft-validates the display path.** A malformed/older logged arg shape makes the wrapper return `undefined` (a generic fallback) rather than throw — display must never crash a replay.
|
||||
|
||||
The neutral vocabulary lives in `dsh-tools` (never import an ACP type into a tool); the ACP bridge maps each `card` to the wire. The design and the why are in [the render-intent-union Agent Note](../../.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.md); `dsh-tool-fs` (generic/diff) and `dsh-tool-bash` (terminal) are the reference implementations.
|
||||
|
||||
## Tests every tool needs
|
||||
|
||||
Cover argument rejection, every result shape, and HMR disposal. For a side-effecting tool, drive the real tool through the agent loop with a scripted `MockAdapter` and assert its `tool/call` and `tool/result` session events. For an editor card, assert the exact `presentCall` and `presentResult` views and add an [ACP snapshot](../../.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md) through the real bridge; a terminal card's scenario sets `terminalOutput: true` to exercise the capable-client path.
|
||||
Cover argument rejection, every canonical value and Native rendering shape, output-schema rejection, and HMR disposal. For a side-effecting tool, drive the real tool through the agent loop with a scripted `MockAdapter` and assert its `tool/call` and projected `tool/result` session events; prove the canonical value itself is not persisted. For an editor card, assert the exact `presentCall` and `presentResult` views and add an [ACP snapshot](../../.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md) through the real bridge; a terminal card's scenario sets `terminalOutput: true` to exercise the capable-client path.
|
||||
|
||||
@@ -22,10 +22,14 @@ export function apply(ctx: Context) {
|
||||
path: { type: 'string', required: true, description: 'Absolute path' },
|
||||
limit: { type: 'number' }, // optional by default
|
||||
},
|
||||
output: {
|
||||
schema: { type: 'string' },
|
||||
render: (_args, value) => [{ type: 'text', text: value }],
|
||||
},
|
||||
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') }]
|
||||
return readFile(args.path, 'utf8')
|
||||
},
|
||||
}))
|
||||
}
|
||||
@@ -38,9 +42,10 @@ export function apply(ctx: Context) {
|
||||
- **参数已为你校验。** `defineTool` 在 `execute` 运行前，会根据统一的 `ParameterSchemaSpec` 校验模型生成的 `arguments`（类型、必填键、字面量约束、恰好匹配一个分支的联合以及嵌套值——见[运行时参数校验](../../.agents/notes/implemented/architecture/2026-06-11-runtime-arg-validation.md)），因此 `execute` 内的 args 会匹配 `InferArgs`。显式对象节点必须声明 `additionalProperties: true | false`；隐式参数根对象保持开放。你仍需手动检查 schema DSL 无法表达的约束，例如非空字符串、正数或跨字段规则。直接注册的原始 JSON Schema 工具自行负责输入校验。
|
||||
- **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。
|
||||
- **声明并返回一个规范 JSON 值。** `output.schema` 使用 `ValueSchemaSpec`，根可以是对象、数组、标量或 null。`execute` 只返回推导出的值；注册表将其快照为无损 JSON，完成校验和冻结后，再传给 `output.render(args, value)`。工具主体不要返回内容块，也不要迫使调用方从自然语言中解析 id 和字段。
|
||||
- **抛出异常或返回无效值意味着 `isError`。** 注册表会捕获异常，并在观察者运行前收敛 schema、渲染器、元数据投影器和无损 JSON 失败。基础设施故障请抛异常。成功的领域结果即使表示不理想的状态，也应写入规范值；其 Native 渲染器可以解释该状态，例如进程以非零状态退出。
|
||||
- **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 `presentationMeta` 投影持久化的卡片数据（可选）。** `output.presentationMeta(args, value)` 从同一个规范值派生可回放的 JSON。核心将其持久化在 `tool/result` 上并传给 `presentResult`，因此需要结果期事实的卡片——例如 `write`／`edit` 的已应用 hunk——无需持久化规范值也能在回放中重现。嵌套 Code 分发没有卡片，因此会跳过该投影器。
|
||||
- **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
|
||||
@@ -51,7 +56,7 @@ producer 提供同步的 `cancel`、在资源清理后 settle 且不 reject 的
|
||||
|
||||
## 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)。
|
||||
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` 为规范分发包装截止时间／重试／指标作用域；使用 `tools/post-execute` 替换展示内容或规范值、阻止调用，或附加模型可见上下文；使用 `tools/result` 观测不可变的归一化结果而不改变它。替换内容不会阻止程序化访问 `value`；保密策略必须阻止调用或替换值。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
|
||||
|
||||
@@ -59,7 +64,7 @@ producer 提供同步的 `cancel`、在资源清理后 settle 且不 reject 的
|
||||
|
||||
## 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）。
|
||||
工具的 `output.render` 返回模型可见的内容；其**编辑器卡片**是另一项独立关注点，通过纯展示投影以及可选的 `presentCall`／`presentResult` 方法声明。请将这些内容与规范值一并设计：编辑器（如 Zed，通过 ACP（Agent Client Protocol）桥接）会展示该卡片，没有 UI 展示方法的工具则回退到通用卡片（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：
|
||||
|
||||
@@ -70,16 +75,16 @@ producer 提供同步的 `cancel`、在资源清理后 settle 且不 reject 的
|
||||
- `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。
|
||||
- `diff` 提供已应用的 hunk，通常由 `output.presentationMeta` 派生并通过持久化的 `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。）
|
||||
- **UI 格式不进入模型结果。** 围栏 ` ```console ` 块、diff、相对化路径均不应仅为服务编辑器而进入规范值或 Native 内容。`output.render` 负责模型可见的自然语言；`presentationMeta` 和卡片展示器负责可回放的 UI 状态。`terminal` 结果视图携带原始输出，由桥接层添加围栏。
|
||||
- **`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 Agent Note](../../.agents/notes/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](../../.agents/notes/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。
|
||||
覆盖参数拒绝、每种规范值和 Native 渲染形态、输出 schema 拒绝以及 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` 和投影后的 `tool/result` 会话事件；同时证明规范值本身未被持久化。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](../../.agents/notes/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。
|
||||
|
||||
@@ -760,7 +760,7 @@ A tool was registered or unregistered, or a scoped restriction changed (the avai
|
||||
'tools/change'(): void
|
||||
```
|
||||
|
||||
Source: [`packages/core/tools/src/index.ts:131`](../../packages/core/tools/src/index.ts)
|
||||
Source: [`packages/core/tools/src/index.ts:135`](../../packages/core/tools/src/index.ts)
|
||||
|
||||
### `tools/execute` — waterfall
|
||||
|
||||
@@ -780,7 +780,7 @@ Around-dispatch waterfall for timeout, retry, or metrics. `next()` returns a nor
|
||||
|
||||
Types: [Scoped](../core-data-structures/scope.md) · [ToolExecution](../core-data-structures/tools.md) · [ToolExecutionResult](../core-data-structures/tools.md) · [ToolRegistry](../core-data-structures/tools.md)
|
||||
|
||||
Source: [`packages/core/tools/src/index.ts:104`](../../packages/core/tools/src/index.ts)
|
||||
Source: [`packages/core/tools/src/index.ts:108`](../../packages/core/tools/src/index.ts)
|
||||
|
||||
### `tools/post-execute` — waterfall
|
||||
|
||||
@@ -800,7 +800,7 @@ Accept, replace, enrich, or block a normalized dispatch result. `next()` accepts
|
||||
|
||||
Types: [PostToolDecision](../core-data-structures/tools.md) · [Scoped](../core-data-structures/scope.md) · [ToolExecution](../core-data-structures/tools.md) · [ToolExecutionResult](../core-data-structures/tools.md) · [ToolRegistry](../core-data-structures/tools.md)
|
||||
|
||||
Source: [`packages/core/tools/src/index.ts:113`](../../packages/core/tools/src/index.ts)
|
||||
Source: [`packages/core/tools/src/index.ts:117`](../../packages/core/tools/src/index.ts)
|
||||
|
||||
### `tools/pre-execute` — waterfall
|
||||
|
||||
@@ -819,7 +819,7 @@ Allow, deny, or ask before dispatch. `next()` delegates to allow; missing approv
|
||||
|
||||
Types: [PreToolDecision](../core-data-structures/tools.md) · [Scoped](../core-data-structures/scope.md) · [ToolExecution](../core-data-structures/tools.md) · [ToolRegistry](../core-data-structures/tools.md)
|
||||
|
||||
Source: [`packages/core/tools/src/index.ts:95`](../../packages/core/tools/src/index.ts)
|
||||
Source: [`packages/core/tools/src/index.ts:99`](../../packages/core/tools/src/index.ts)
|
||||
|
||||
### `tools/result` — emit
|
||||
|
||||
@@ -838,7 +838,7 @@ Observe the frozen, lossless-JSON final outcome. Listener failures are contained
|
||||
|
||||
Types: [Scoped](../core-data-structures/scope.md) · [ToolExecution](../core-data-structures/tools.md) · [ToolExecutionResult](../core-data-structures/tools.md) · [ToolRegistry](../core-data-structures/tools.md)
|
||||
|
||||
Source: [`packages/core/tools/src/index.ts:121`](../../packages/core/tools/src/index.ts)
|
||||
Source: [`packages/core/tools/src/index.ts:125`](../../packages/core/tools/src/index.ts)
|
||||
|
||||
## `workflow/*`
|
||||
|
||||
|
||||
@@ -1361,7 +1361,7 @@ async execute(exec: ToolExecutionInput): Promise<ToolExecutionResult>
|
||||
|
||||
Types: [ScopeKey](../core-data-structures/scope.md) · [ToolDefinition](../core-data-structures/tools.md) · [ToolExecutionInput](../core-data-structures/tools.md) · [ToolExecutionMode](../core-data-structures/tools.md) · [ToolExecutionResult](../core-data-structures/tools.md) · [ToolGuard](../core-data-structures/tools.md) · [ToolRestriction](../core-data-structures/tools.md) · [ToolSchema](../core-data-structures/tools.md)
|
||||
|
||||
Source: [`packages/core/tools/src/index.ts:453`](../../packages/core/tools/src/index.ts)
|
||||
Source: [`packages/core/tools/src/index.ts:504`](../../packages/core/tools/src/index.ts)
|
||||
|
||||
## `ctx.userInteraction` — `UserInteractionService`
|
||||
|
||||
|
||||
@@ -73,15 +73,24 @@ interface SessionEventMap {
|
||||
*/
|
||||
'tool/call': { turn: number; step: number; callId: CallId; name: string; arguments: string }
|
||||
/**
|
||||
* A completed tool call's model-facing result, plus an optional tool-private
|
||||
* `meta` presentation payload. `meta` is opaque to the core (`unknown` — the
|
||||
* producing tool owns its shape and reads it back in `presentResult`) but MUST
|
||||
* be JSON-serializable: `Session.append` runtime-validates all event data with
|
||||
* `isJsonValue`, so a non-serializable `meta` is rejected at the source, and the
|
||||
* durable log reproduces the identical card on replay. Absent unless the tool
|
||||
* attaches one (e.g. `dsh-tool-fs` carries its result-time contextual diff here).
|
||||
* A completed tool call's model-facing result, canonical failure detail, and
|
||||
* optional tool-private `meta` presentation payload. `meta` is opaque to the
|
||||
* core (the producing tool owns its shape and reads it back in `presentResult`)
|
||||
* but MUST be JSON-serializable: `Session.append` runtime-validates all event
|
||||
* data with `isJsonValue`, so a non-serializable `meta` is rejected at the
|
||||
* source, and the durable log reproduces the identical card on replay. Absent
|
||||
* unless the tool attaches one (e.g. `dsh-tool-fs` carries its result-time
|
||||
* contextual diff here).
|
||||
*/
|
||||
'tool/result': { turn: number; step: number; callId: CallId; content: ContentBlock[]; isError: boolean; error?: { name: string; code: string }; meta?: unknown }
|
||||
'tool/result': {
|
||||
turn: number
|
||||
step: number
|
||||
callId: CallId
|
||||
content: ContentBlock[]
|
||||
isError: boolean
|
||||
error?: { message: string; info?: { name: string; code: string } }
|
||||
meta?: JsonValue
|
||||
}
|
||||
/** Steering content injected between steps of a running turn. */
|
||||
'steering/message': { turn: number; content: ContentBlock[]; source: MessageSource }
|
||||
/** Whole-list snapshot; latest write wins on replay. Log-only UI state; never derived history. */
|
||||
|
||||
@@ -6,12 +6,27 @@ Source: [`packages/core/tools/src/index.ts`](../../packages/core/tools/src/index
|
||||
|
||||
## `ToolDefinition` — a registered tool
|
||||
|
||||
A `ToolSchema` (the model-facing fields) plus the `execute` function, host-only scheduler metadata, and optional UI presenters. The registry holds these; the loop dispatches calls through them. The registry's `schemas()` builds the model-facing `ToolSchema[]` by an explicit allowlist — `execute`/`timeoutMs`/`isConcurrencySafe`/`presentCall`/`presentResult` must never leak into a model request.
|
||||
A `ToolSchema` (the model-facing fields) plus a mandatory canonical output declaration, the `execute` function, host-only scheduler metadata, and optional UI presenters. The registry holds these; the loop dispatches calls through them. The registry's `schemas()` builds the model-facing `ToolSchema[]` by an explicit allowlist — `output`/`execute`/`timeoutMs`/`isConcurrencySafe`/`presentCall`/`presentResult` must never leak into a model request.
|
||||
|
||||
```ts type-equiv
|
||||
/** Tool-owned canonical output contract used after the body returns a JSON value. */
|
||||
interface ToolOutputDefinition {
|
||||
/** Raw supported JSON Schema enforced against every successful canonical value. */
|
||||
readonly schema: JsonSchemaNode
|
||||
/** Pure projection from validated arguments and value to Native/model content. */
|
||||
render(args: unknown, value: JsonValue): ContentBlock[]
|
||||
/** Pure replayable presentation projection, computed only for surface calls. */
|
||||
presentationMeta?(args: unknown, value: JsonValue): JsonValue
|
||||
}
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/** A registered tool: its schema plus the execution function. */
|
||||
interface ToolDefinition extends ToolSchema {
|
||||
execute(args: unknown, exec: ToolRunContext): Promise<ToolExecuteReturn>
|
||||
/** Mandatory canonical output declaration. */
|
||||
readonly output: ToolOutputDefinition
|
||||
/** Execute the tool and return only its canonical lossless-JSON value. */
|
||||
execute(args: unknown, exec: ToolRunContext): Promise<unknown>
|
||||
/**
|
||||
* Cooperative tool-call timeout budget in milliseconds. Omit for no deadline.
|
||||
* Enforced by `@deepseek-ai/dsh-timeout-policy` (a `tools/execute` wrapper); it
|
||||
@@ -46,7 +61,7 @@ interface ToolDefinition extends ToolSchema {
|
||||
presentCall?(args: unknown): ToolCallView | undefined
|
||||
/**
|
||||
* Optional: how to present the COMPLETED state, given the same `args` and the
|
||||
* `result` (`execute`'s content + whether it errored). Returns a
|
||||
* durable result projection (`content`, failure state, and optional `meta`). Returns a
|
||||
* {@link ToolResultView}, or `undefined` (or omit the method) to keep the
|
||||
* pending title and render the raw result content. Pure and side-effect-free
|
||||
* for the same replay reason.
|
||||
@@ -55,7 +70,7 @@ interface ToolDefinition extends ToolSchema {
|
||||
}
|
||||
```
|
||||
|
||||
`execute` receives `args: unknown` — a raw `ToolDefinition` validates its own input. First-party tools don't write that by hand; they use `defineTool`, which validates and narrows for them.
|
||||
`execute` receives `args: unknown` — a raw `ToolDefinition` validates its own input. First-party tools don't write that by hand; they use `defineTool`, which validates and narrows the arguments, infers the body return from `output.schema`, and types both output projectors.
|
||||
|
||||
## The unified JSON-value schema DSL
|
||||
|
||||
@@ -97,27 +112,28 @@ type ParameterSchemaSpec = Record<string, ParameterPropertySpec>
|
||||
* Infer the TypeScript value accepted by an author-facing value schema.
|
||||
* Output schemas may therefore infer object, array, scalar, or null roots.
|
||||
*/
|
||||
type InferValue<S extends ValueSchemaSpec> =
|
||||
S extends StringValueSchemaSpec ? InferScalar<S, string> :
|
||||
S extends NumberValueSchemaSpec | IntegerValueSchemaSpec ? InferScalar<S, number> :
|
||||
S extends BooleanValueSchemaSpec ? InferScalar<S, boolean> :
|
||||
S extends NullValueSchemaSpec ? null :
|
||||
S extends ArrayValueSchemaSpec
|
||||
? S extends { items: infer I extends ValueSchemaSpec } ? InferValue<I>[] : JsonValue[]
|
||||
: S extends ObjectValueSchemaSpec ? InferObject<S> :
|
||||
S extends JsonValueSchemaSpec ? JsonValue :
|
||||
S extends OneOfValueSchemaSpec ? InferValue<S['oneOf'][number]> :
|
||||
never
|
||||
type InferValue<S extends ValueSchemaSpec, D extends readonly unknown[] = readonly []> =
|
||||
D['length'] extends 12 ? JsonValue :
|
||||
S extends StringValueSchemaSpec ? InferScalar<S, string> :
|
||||
S extends NumberValueSchemaSpec | IntegerValueSchemaSpec ? InferScalar<S, number> :
|
||||
S extends BooleanValueSchemaSpec ? InferScalar<S, boolean> :
|
||||
S extends NullValueSchemaSpec ? null :
|
||||
S extends ArrayValueSchemaSpec
|
||||
? S extends { items: infer I extends ValueSchemaSpec } ? InferValue<I, NextDepth<D>>[] : JsonValue[]
|
||||
: S extends ObjectValueSchemaSpec ? InferObject<S, NextDepth<D>> :
|
||||
S extends JsonValueSchemaSpec ? JsonValue :
|
||||
S extends OneOfValueSchemaSpec ? InferValue<S['oneOf'][number], NextDepth<D>> :
|
||||
never
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/** Infer the TypeScript argument object for an implicit parameter schema. */
|
||||
type InferArgs<S extends ParameterSchemaSpec> = InferProperties<S>
|
||||
type InferArgs<S extends ParameterSchemaSpec> = InferProperties<S, readonly []>
|
||||
```
|
||||
|
||||
`defineTool({ name, description, parameters, execute, … })` ties parameter inference to `parameterSchemaSpecToJsonSchema()` and `validateArgs()`. `valueSchemaSpecToJsonSchema()` compiles value/output declarations through the same enforced raw subset. A parameter mismatch throws `ToolArgsError` (`INVALID_ARGS`), which the registry returns through the normal tool-error path. Raw JSON Schema remains open by default; unsupported keywords reject instead of being accepted without enforcement.
|
||||
`defineTool({ name, description, parameters, output, execute, … })` ties parameter inference to `parameterSchemaSpecToJsonSchema()` and `validateArgs()`, and ties `execute`/`render`/`presentationMeta` to `InferValue<OutputSchema>`. Inference widens to `JsonValue` after twelve nested nodes so large schemas remain compilable; runtime validation keeps walking the complete schema. `valueSchemaSpecToJsonSchema()` compiles output declarations through the same enforced raw subset. A parameter mismatch throws `ToolArgsError` (`INVALID_ARGS`); an invalid body or post-policy value throws `ToolOutputError` (`INVALID_TOOL_OUTPUT`). Both use the normal tool-error path. Raw JSON Schema remains open by default; unsupported keywords reject instead of being accepted without enforcement.
|
||||
|
||||
Registration is a trusted same-process contract. The registry borrows the typed definition as readonly input and validates only semantic requirements such as a positive finite `timeoutMs`; `schemas()` materializes the explicit model-facing projection at the model boundary so execution and presentation share one resolved definition without leaking callbacks onto the wire.
|
||||
Registration is a trusted same-process contract. The registry borrows the typed definition as readonly input, requires `output`, validates its raw schema, and checks semantic requirements such as a positive finite `timeoutMs`; `schemas()` materializes the explicit model-facing projection at the model boundary so execution and presentation share one resolved definition without leaking callbacks onto the wire.
|
||||
|
||||
## `ToolRestriction` — one scope's live global filter
|
||||
|
||||
@@ -230,34 +246,48 @@ type ToolGuard = (execution: Readonly<ToolExecution>) => string | undefined
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/** The outcome of one tool call. */
|
||||
interface ToolExecutionResult {
|
||||
content: ContentBlock[]
|
||||
isError: boolean
|
||||
/**
|
||||
* Set when the call failed with a {@link HarnessError}: machine-routable
|
||||
* `{ name, code }` for retry/sandbox plugins and replay. The model-facing
|
||||
* text in `content` is always present; this is extra structure for code.
|
||||
*/
|
||||
error?: ToolErrorInfo
|
||||
/**
|
||||
* Model-facing context for the next request, separate from this tool result. The loop
|
||||
* accepts it into the active-batch FIFO, then appends after recorded results even if interrupted.
|
||||
*/
|
||||
additionalContexts?: HookContext[]
|
||||
/**
|
||||
* The tool-private presentation payload from a successful `execute` (the object
|
||||
* return form). Threaded onto the `tool/result` session event and back into
|
||||
* {@link ToolResult} for `presentResult`. Opaque (`unknown`); absent when the
|
||||
* tool attached none or the call failed.
|
||||
*/
|
||||
meta?: unknown
|
||||
/** Canonical failure detail; internal routing information remains optional. */
|
||||
interface ToolFailure {
|
||||
/** Human-readable failure message without the Native `Error: ` envelope. */
|
||||
message: string
|
||||
/** Internal error class/code used by policy and durable diagnostics. */
|
||||
info?: ToolErrorInfo
|
||||
}
|
||||
```
|
||||
|
||||
The result carries only the outcome. Call identity remains on the immutable `ToolExecution` that accompanies it through every hook and on the durable `tool/call` / `tool/result` session events, so wrappers cannot create a second, disagreeing identity.
|
||||
```ts type-equiv
|
||||
/** Successful canonical tool execution, including its Native/model projection. */
|
||||
interface ToolExecutionSuccess {
|
||||
readonly isError: false
|
||||
/** Execution-local canonical value; deliberately omitted from durable events. */
|
||||
readonly value: JsonValue
|
||||
readonly content: ContentBlock[]
|
||||
readonly error?: never
|
||||
readonly meta?: JsonValue
|
||||
readonly additionalContexts?: HookContext[]
|
||||
}
|
||||
```
|
||||
|
||||
The registry materializes and freezes the final accepted result immediately before `tools/result`. Its content, structured error, additional context, and presentation metadata must round-trip losslessly through JSON; an invalid outcome becomes a JSON-safe `isError` result, so the observed live outcome is safe for the later durable `tool/result` append.
|
||||
```ts type-equiv
|
||||
/** Failed canonical tool execution; failures never carry a successful value. */
|
||||
interface ToolExecutionFailure {
|
||||
readonly isError: true
|
||||
readonly error: ToolFailure
|
||||
readonly value?: never
|
||||
readonly content: ContentBlock[]
|
||||
readonly meta?: JsonValue
|
||||
readonly additionalContexts?: HookContext[]
|
||||
}
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/** The discriminated, execution-local outcome of one tool call. */
|
||||
type ToolExecutionResult = ToolExecutionSuccess | ToolExecutionFailure
|
||||
```
|
||||
|
||||
The result carries only the outcome. Call identity remains on the immutable `ToolExecution` that accompanies it through every hook and on the durable `tool/call` / `tool/result` session events, so wrappers cannot create a second, disagreeing identity. The canonical `value` is execution-local: the loop persists only `content`, `error`, and `meta`, while `tool/code-dispatch` stores a bounded summary. Replay reproduces presentation but cannot reconstruct intermediate values.
|
||||
|
||||
On success the registry snapshots and validates the body value, freezes it, and invokes the pure renderer plus the optional direct-surface metadata projector. It separately materializes the durable presentation fields immediately before `tools/result`; an invalid value, renderer/projector failure, or non-JSON presentation becomes a JSON-safe `isError`. The final live observer therefore sees the exact execution-local value beside fields safe for the later durable append.
|
||||
|
||||
Each interception waterfall returns a typed **Decision** (the idiom shared with the `agent/*` seams). `tools/pre-execute` listeners receive `(exec, next)` and return a `PreToolDecision`; `tools/execute` wrappers return a `ToolExecutionResult`; `tools/post-execute` listeners receive `(exec, result, next)` and return a `PostToolDecision`:
|
||||
|
||||
@@ -276,17 +306,18 @@ type PreToolDecision =
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
* Post-dispatch decision: accept or replace content, attach context for the next
|
||||
* request, or block by turning corrective feedback into an error result.
|
||||
* Post-dispatch decision: accept, replace one projection, attach context for the
|
||||
* next request, or block by turning corrective feedback into an error result.
|
||||
*/
|
||||
type PostToolDecision =
|
||||
| { kind: 'accept'; content?: ContentBlock[]; additionalContexts?: HookContext[] }
|
||||
| { kind: 'accept'; content?: ContentBlock[]; value?: never; additionalContexts?: HookContext[] }
|
||||
| { kind: 'accept'; value: JsonValue; content?: never; additionalContexts?: HookContext[] }
|
||||
| { kind: 'block'; feedback: ContentBlock[]; additionalContexts?: HookContext[] }
|
||||
```
|
||||
|
||||
Call `next()` for the default or return a decision to short-circuit. Pre-policy may deny or ask; only `allowed-once` proceeds, while a non-grant, missing approval channel or service, or agent-less request becomes a denial. Guards may still impose a final denial. Arguments cannot be rewritten because history, audit, UI, and execution must agree.
|
||||
|
||||
Post-policy may replace content; a block becomes an `isError` result containing its corrective feedback. `tools/result` receives the frozen execution and result after normalization; observers cannot transform them, and observer failures are contained. Unknown and throwing tools both become structured errors (`ToolNotFoundError` maps to `UNKNOWN_TOOL`), so the call fails without ending the turn.
|
||||
Post-policy may replace either content or value, never both. Content replacement preserves the canonical value and existing metadata; value replacement is revalidated and recomputes content/metadata; a block removes the value and becomes an `isError` containing corrective feedback. Content replacement is presentation policy, not confidentiality policy: a listener that must hide the programmatic value blocks or replaces it. `tools/result` receives the frozen execution and result after normalization; observers cannot transform them, and observer failures are contained. Unknown and throwing tools both become structured errors (`ToolNotFoundError` maps to `UNKNOWN_TOOL`), so the call fails without ending the turn.
|
||||
|
||||
## The enforced raw JSON Schema subset
|
||||
|
||||
|
||||
@@ -41,11 +41,11 @@ This matrix shows which packages dispatch each harness-owned event and which pac
|
||||
| `subagent/start` | `emit` | [`packages/subagent/subagent/src/index.ts:130`](../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`) | [`acp`](../packages/ui/acp) |
|
||||
| `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:131`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`emit`) | - |
|
||||
| `tools/execute` | `waterfall` | [`packages/core/tools/src/index.ts:104`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`waterfall`) | [`timeout-policy`](../packages/timeout/timeout-policy) |
|
||||
| `tools/post-execute` | `waterfall` | [`packages/core/tools/src/index.ts:113`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard), [`spill-policy`](../packages/spill/spill-policy), [`workspace-context`](../packages/context/workspace-context) |
|
||||
| `tools/pre-execute` | `waterfall` | [`packages/core/tools/src/index.ts:95`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) |
|
||||
| `tools/result` | `emit` | [`packages/core/tools/src/index.ts:121`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`events.dispatch`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess), [`workspace-context`](../packages/context/workspace-context) |
|
||||
| `tools/change` | `emit` | [`packages/core/tools/src/index.ts:135`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`emit`) | - |
|
||||
| `tools/execute` | `waterfall` | [`packages/core/tools/src/index.ts:108`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`waterfall`) | [`timeout-policy`](../packages/timeout/timeout-policy) |
|
||||
| `tools/post-execute` | `waterfall` | [`packages/core/tools/src/index.ts:117`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard), [`spill-policy`](../packages/spill/spill-policy), [`tool-fs-search`](../packages/fs/tool-fs-search), [`workspace-context`](../packages/context/workspace-context) |
|
||||
| `tools/pre-execute` | `waterfall` | [`packages/core/tools/src/index.ts:99`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) |
|
||||
| `tools/result` | `emit` | [`packages/core/tools/src/index.ts:125`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`events.dispatch`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess), [`workspace-context`](../packages/context/workspace-context) |
|
||||
| `workflow/agent-end` | `emit` | [`packages/workflow/workflow/src/index.ts:81`](../packages/workflow/workflow/src/index.ts) | [`workflow`](../packages/workflow/workflow) (`events.dispatch`) | - |
|
||||
| `workflow/agent-start` | `emit` | [`packages/workflow/workflow/src/index.ts:70`](../packages/workflow/workflow/src/index.ts) | [`workflow`](../packages/workflow/workflow) (`events.dispatch`) | - |
|
||||
| `workflow/end` | `emit` | [`packages/workflow/workflow/src/index.ts:91`](../packages/workflow/workflow/src/index.ts) | [`workflow`](../packages/workflow/workflow) (`events.dispatch`) | - |
|
||||
|
||||
@@ -79,7 +79,7 @@ export type SessionEvent<T extends SessionEventType = SessionEventType> = {
|
||||
}[T]
|
||||
```
|
||||
|
||||
Sources: [`packages/core/session/src/types.ts:267`](../packages/core/session/src/types.ts) · [`packages/core/session/src/types.ts:274`](../packages/core/session/src/types.ts) · [`packages/core/session/src/types.ts:304`](../packages/core/session/src/types.ts) · [`packages/core/session/src/types.ts:336`](../packages/core/session/src/types.ts)
|
||||
Sources: [`packages/core/session/src/types.ts:276`](../packages/core/session/src/types.ts) · [`packages/core/session/src/types.ts:283`](../packages/core/session/src/types.ts) · [`packages/core/session/src/types.ts:313`](../packages/core/session/src/types.ts) · [`packages/core/session/src/types.ts:345`](../packages/core/session/src/types.ts)
|
||||
|
||||
## Events
|
||||
|
||||
@@ -356,7 +356,7 @@ Source: [`packages/core/session/src/types.ts:213`](../packages/core/session/src/
|
||||
'request/header': { header: EpochHeader; reason: RequestHeaderReason }
|
||||
```
|
||||
|
||||
Source: [`packages/core/session/src/types.ts:263`](../packages/core/session/src/types.ts)
|
||||
Source: [`packages/core/session/src/types.ts:272`](../packages/core/session/src/types.ts)
|
||||
|
||||
### `sandbox/*`
|
||||
|
||||
@@ -387,7 +387,7 @@ Source: [`packages/sandbox/sandbox-policy/src/session-mode.ts:34`](../packages/s
|
||||
|
||||
Types: [ContentBlock](core-data-structures/core.md) · [MessageSource](core-data-structures/core.md)
|
||||
|
||||
Source: [`packages/core/session/src/types.ts:256`](../packages/core/session/src/types.ts)
|
||||
Source: [`packages/core/session/src/types.ts:265`](../packages/core/session/src/types.ts)
|
||||
|
||||
### `step/*`
|
||||
|
||||
@@ -420,7 +420,7 @@ Source: [`packages/core/session/src/types.ts:204`](../packages/core/session/src/
|
||||
|
||||
Types: [TodoItem](core-data-structures/session.md)
|
||||
|
||||
Source: [`packages/core/session/src/types.ts:258`](../packages/core/session/src/types.ts)
|
||||
Source: [`packages/core/session/src/types.ts:267`](../packages/core/session/src/types.ts)
|
||||
|
||||
### `tool/*`
|
||||
|
||||
@@ -468,20 +468,29 @@ Source: [`packages/core/tools/src/code-mode.ts:34`](../packages/core/tools/src/c
|
||||
|
||||
```ts persistence-catalog
|
||||
/**
|
||||
* A completed tool call's model-facing result, plus an optional tool-private
|
||||
* `meta` presentation payload. `meta` is opaque to the core (`unknown` — the
|
||||
* producing tool owns its shape and reads it back in `presentResult`) but MUST
|
||||
* be JSON-serializable: `Session.append` runtime-validates all event data with
|
||||
* `isJsonValue`, so a non-serializable `meta` is rejected at the source, and the
|
||||
* durable log reproduces the identical card on replay. Absent unless the tool
|
||||
* attaches one (e.g. `dsh-tool-fs` carries its result-time contextual diff here).
|
||||
* A completed tool call's model-facing result, canonical failure detail, and
|
||||
* optional tool-private `meta` presentation payload. `meta` is opaque to the
|
||||
* core (the producing tool owns its shape and reads it back in `presentResult`)
|
||||
* but MUST be JSON-serializable: `Session.append` runtime-validates all event
|
||||
* data with `isJsonValue`, so a non-serializable `meta` is rejected at the
|
||||
* source, and the durable log reproduces the identical card on replay. Absent
|
||||
* unless the tool attaches one (e.g. `dsh-tool-fs` carries its result-time
|
||||
* contextual diff here).
|
||||
*/
|
||||
'tool/result': { turn: number; step: number; callId: CallId; content: ContentBlock[]; isError: boolean; error?: { name: string; code: string }; meta?: unknown }
|
||||
'tool/result': {
|
||||
turn: number
|
||||
step: number
|
||||
callId: CallId
|
||||
content: ContentBlock[]
|
||||
isError: boolean
|
||||
error?: { message: string; info?: { name: string; code: string } }
|
||||
meta?: JsonValue
|
||||
}
|
||||
```
|
||||
|
||||
Types: [CallId](core-data-structures/core.md) · [ContentBlock](core-data-structures/core.md)
|
||||
|
||||
Source: [`packages/core/session/src/types.ts:254`](../packages/core/session/src/types.ts)
|
||||
Source: [`packages/core/session/src/types.ts:255`](../packages/core/session/src/types.ts)
|
||||
|
||||
### `turn/*`
|
||||
|
||||
|
||||
@@ -203,7 +203,7 @@ Source: [`packages/cordis/tool-cordis/src/index.ts`](../packages/cordis/tool-cor
|
||||
|
||||
### `cordis_mount`
|
||||
|
||||
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'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. 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.
|
||||
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 } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. 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.
|
||||
|
||||
```json
|
||||
{
|
||||
|
||||
@@ -2,5 +2,5 @@
|
||||
# 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
|
||||
index.md: d7d657ff7b8cb9001dd5e9c3af658a7a3c45b5b7
|
||||
index.zh.md: 7a134f7aaed470b87ee8ca8978dd39593de2651b
|
||||
index.md: 5a9f8dfb8f2d87dfbd2ba30b4d09d002ae9b635c
|
||||
index.zh.md: 08aca87cbc02d1b0dfbe6fe2d92b3f6e87075097
|
||||
|
||||
@@ -138,8 +138,12 @@ export function apply(ctx: Context) {
|
||||
parameters: {
|
||||
name: { type: 'string', required: true },
|
||||
},
|
||||
output: {
|
||||
schema: { type: 'string' },
|
||||
render: (_args, value) => [{ type: 'text', text: value }],
|
||||
},
|
||||
async execute(args) {
|
||||
return [{ type: 'text', text: `Hello, ${args.name}!` }]
|
||||
return `Hello, ${args.name}!`
|
||||
},
|
||||
}))
|
||||
}
|
||||
|
||||
@@ -138,8 +138,12 @@ export function apply(ctx: Context) {
|
||||
parameters: {
|
||||
name: { type: 'string', required: true },
|
||||
},
|
||||
output: {
|
||||
schema: { type: 'string' },
|
||||
render: (_args, value) => [{ type: 'text', text: value }],
|
||||
},
|
||||
async execute(args) {
|
||||
return [{ type: 'text', text: `Hello, ${args.name}!` }]
|
||||
return `Hello, ${args.name}!`
|
||||
},
|
||||
}))
|
||||
}
|
||||
|
||||
@@ -2,5 +2,5 @@
|
||||
# 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
|
||||
tool.md: 17adbfc5f7eb804856dfe39b4d2b4a65374b6414
|
||||
tool.zh.md: 8857e16ca836dfa5b158a68581bd3c715dcb1ac5
|
||||
tool.md: 7b211cfef54306f7c316dc08da1df759dcbf1b06
|
||||
tool.zh.md: 214b35b28de0c647737bc8297b13b4997947b52e
|
||||
|
||||
@@ -20,9 +20,13 @@ export function apply(ctx: Context) {
|
||||
parameters: {
|
||||
name: { type: 'string', required: true, description: 'The name to greet' },
|
||||
},
|
||||
output: {
|
||||
schema: { type: 'string' },
|
||||
render: (_args, value) => [{ type: 'text', text: value }],
|
||||
},
|
||||
async execute(args) {
|
||||
// args is inferred as { name: string }.
|
||||
return [{ type: 'text', text: `Hello, ${args.name}!` }]
|
||||
return `Hello, ${args.name}!`
|
||||
},
|
||||
}))
|
||||
}
|
||||
@@ -107,33 +111,45 @@ export const tool = defineTool({
|
||||
name: 'example',
|
||||
description: 'Return an example result.',
|
||||
parameters: {},
|
||||
output: {
|
||||
schema: { type: 'string' },
|
||||
render: (_args, value) => [{ type: 'text', text: value }],
|
||||
},
|
||||
async execute(args, exec) {
|
||||
// args: inferred from parameters
|
||||
// exec: ToolExecution context
|
||||
|
||||
// Return a ContentBlock array.
|
||||
// Return the value declared by output.schema.
|
||||
void args
|
||||
void exec
|
||||
return [{ type: 'text', text: 'result here' }]
|
||||
return 'result here'
|
||||
},
|
||||
})
|
||||
```
|
||||
|
||||
### Return value
|
||||
|
||||
`execute` returns a `ContentBlock[]` that becomes the tool result visible to the model:
|
||||
`execute` returns the lossless JSON value declared by `output.schema`. `output.render(args, value)` separately turns that validated value into the Native/model-facing content:
|
||||
|
||||
```ts ignore-check
|
||||
// Text result
|
||||
return [{ type: 'text', text: 'file content here...' }]
|
||||
|
||||
// Multiple blocks
|
||||
return [
|
||||
{ type: 'text', text: 'Found 3 matches:' },
|
||||
{ type: 'text', text: matchResults.join('\n') },
|
||||
]
|
||||
output: {
|
||||
schema: {
|
||||
type: 'object',
|
||||
additionalProperties: false,
|
||||
properties: {
|
||||
path: { type: 'string', required: true },
|
||||
content: { type: 'string', required: true },
|
||||
},
|
||||
},
|
||||
render: (_args, value) => [{ type: 'text', text: value.content }],
|
||||
},
|
||||
async execute(args) {
|
||||
return { path: args.path, content: await readFile(args.path, 'utf8') }
|
||||
}
|
||||
```
|
||||
|
||||
The canonical value is available to execution-time programmatic callers and is not persisted in `tool/result`; the rendered content and optional `presentationMeta` are the replayable projections. A body value that does not satisfy the schema, or is not lossless JSON, becomes an `INVALID_TOOL_OUTPUT` failure.
|
||||
|
||||
### Argument validation
|
||||
|
||||
Before calling `execute`, `defineTool` validates model-generated arguments. Invalid input raises `ToolArgsError`; the framework turns it into an `isError` result so the model can correct its call.
|
||||
@@ -148,6 +164,10 @@ A tool can define UI presentation methods for terminal and ACP clients:
|
||||
defineTool({
|
||||
name: 'bash',
|
||||
// ...
|
||||
output: {
|
||||
schema: { type: 'string' },
|
||||
render: (_args, value) => [{ type: 'text', text: value }],
|
||||
},
|
||||
presentCall(args) {
|
||||
return {
|
||||
card: 'terminal',
|
||||
@@ -196,13 +216,24 @@ export function apply(ctx: Context) {
|
||||
path: { type: 'string', required: true, description: 'Directory path' },
|
||||
extension: { type: 'string', description: 'Filter by extension (e.g. ".ts")' },
|
||||
},
|
||||
output: {
|
||||
schema: {
|
||||
type: 'object',
|
||||
additionalProperties: false,
|
||||
properties: {
|
||||
count: { type: 'integer', required: true },
|
||||
files: { type: 'array', required: true, items: { type: 'string' } },
|
||||
},
|
||||
},
|
||||
render: (_args, value) => [{ type: 'text', text: `Found ${value.count} files.` }],
|
||||
},
|
||||
async execute(args) {
|
||||
const entries = await readdir(args.path, { withFileTypes: true })
|
||||
let files = entries.filter(e => e.isFile())
|
||||
if (args.extension) {
|
||||
files = files.filter(f => f.name.endsWith(args.extension!))
|
||||
}
|
||||
return [{ type: 'text', text: `Found ${files.length} files.` }]
|
||||
return { count: files.length, files: files.map(file => file.name) }
|
||||
},
|
||||
}))
|
||||
}
|
||||
|
||||
@@ -20,9 +20,13 @@ export function apply(ctx: Context) {
|
||||
parameters: {
|
||||
name: { type: 'string', required: true, description: 'The name to greet' },
|
||||
},
|
||||
output: {
|
||||
schema: { type: 'string' },
|
||||
render: (_args, value) => [{ type: 'text', text: value }],
|
||||
},
|
||||
async execute(args) {
|
||||
// args is inferred as { name: string }.
|
||||
return [{ type: 'text', text: `Hello, ${args.name}!` }]
|
||||
return `Hello, ${args.name}!`
|
||||
},
|
||||
}))
|
||||
}
|
||||
@@ -107,33 +111,45 @@ export const tool = defineTool({
|
||||
name: 'example',
|
||||
description: 'Return an example result.',
|
||||
parameters: {},
|
||||
output: {
|
||||
schema: { type: 'string' },
|
||||
render: (_args, value) => [{ type: 'text', text: value }],
|
||||
},
|
||||
async execute(args, exec) {
|
||||
// args: inferred from parameters
|
||||
// exec: ToolExecution context
|
||||
|
||||
// Return a ContentBlock array.
|
||||
// Return the value declared by output.schema.
|
||||
void args
|
||||
void exec
|
||||
return [{ type: 'text', text: 'result here' }]
|
||||
return 'result here'
|
||||
},
|
||||
})
|
||||
```
|
||||
|
||||
### 返回值
|
||||
|
||||
`execute` 必须返回一个 `ContentBlock[]`，告诉模型 tool 的执行结果：
|
||||
`execute` 返回由 `output.schema` 声明的无损 JSON 值。`output.render(args, value)` 会将经过校验的值另外转换为 Native／模型可见的内容：
|
||||
|
||||
```ts ignore-check
|
||||
// Text result
|
||||
return [{ type: 'text', text: 'file content here...' }]
|
||||
|
||||
// Multiple blocks
|
||||
return [
|
||||
{ type: 'text', text: 'Found 3 matches:' },
|
||||
{ type: 'text', text: matchResults.join('\n') },
|
||||
]
|
||||
output: {
|
||||
schema: {
|
||||
type: 'object',
|
||||
additionalProperties: false,
|
||||
properties: {
|
||||
path: { type: 'string', required: true },
|
||||
content: { type: 'string', required: true },
|
||||
},
|
||||
},
|
||||
render: (_args, value) => [{ type: 'text', text: value.content }],
|
||||
},
|
||||
async execute(args) {
|
||||
return { path: args.path, content: await readFile(args.path, 'utf8') }
|
||||
}
|
||||
```
|
||||
|
||||
执行期间的程序化调用方可以使用规范值，但 `tool/result` 不会持久化该值；渲染后的内容和可选的 `presentationMeta` 才是可回放的投影。工具主体返回的值若不满足 schema 或不是无损 JSON，就会变为 `INVALID_TOOL_OUTPUT` 失败。
|
||||
|
||||
### 参数校验
|
||||
|
||||
`defineTool` 在调用 `execute` 之前会自动校验模型生成的参数。如果参数不合法，会抛出 `ToolArgsError`，框架将其转换为 `isError` 结果返回给模型，让模型自行修正。
|
||||
@@ -148,6 +164,10 @@ Tool 可以定义 UI 渲染方法，用于在终端或 ACP 客户端中展示 to
|
||||
defineTool({
|
||||
name: 'bash',
|
||||
// ...
|
||||
output: {
|
||||
schema: { type: 'string' },
|
||||
render: (_args, value) => [{ type: 'text', text: value }],
|
||||
},
|
||||
presentCall(args) {
|
||||
return {
|
||||
card: 'terminal',
|
||||
@@ -196,13 +216,24 @@ export function apply(ctx: Context) {
|
||||
path: { type: 'string', required: true, description: 'Directory path' },
|
||||
extension: { type: 'string', description: 'Filter by extension (e.g. ".ts")' },
|
||||
},
|
||||
output: {
|
||||
schema: {
|
||||
type: 'object',
|
||||
additionalProperties: false,
|
||||
properties: {
|
||||
count: { type: 'integer', required: true },
|
||||
files: { type: 'array', required: true, items: { type: 'string' } },
|
||||
},
|
||||
},
|
||||
render: (_args, value) => [{ type: 'text', text: `Found ${value.count} files.` }],
|
||||
},
|
||||
async execute(args) {
|
||||
const entries = await readdir(args.path, { withFileTypes: true })
|
||||
let files = entries.filter(e => e.isFile())
|
||||
if (args.extension) {
|
||||
files = files.filter(f => f.name.endsWith(args.extension!))
|
||||
}
|
||||
return [{ type: 'text', text: `Found ${files.length} files.` }]
|
||||
return { count: files.length, files: files.map(file => file.name) }
|
||||
},
|
||||
}))
|
||||
}
|
||||
|
||||
@@ -2,5 +2,5 @@
|
||||
# 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
|
||||
index.md: 0261b49b071167f7c2a33f78bbc1959cc6f1879f
|
||||
index.zh.md: 5819344430fcbde31bf825e9815120983e44e3f6
|
||||
index.md: e197d499d7f5bd9911ea60bebf584251cd4ed915
|
||||
index.zh.md: 8b8d08f9d0c6d0ca8d95fbaa3281c98b7a600fe4
|
||||
|
||||
@@ -132,9 +132,13 @@ export function apply(ctx: Context) {
|
||||
parameters: {
|
||||
input: { type: 'string', required: true },
|
||||
},
|
||||
output: {
|
||||
schema: { type: 'string' },
|
||||
render: (_args, value) => [{ type: 'text', text: value }],
|
||||
},
|
||||
async execute(args) {
|
||||
const result = await ctx.myCap.execute({ input: args.input })
|
||||
return [{ type: 'text', text: result.output }]
|
||||
return result.output
|
||||
},
|
||||
}))
|
||||
}
|
||||
|
||||
@@ -132,9 +132,13 @@ export function apply(ctx: Context) {
|
||||
parameters: {
|
||||
input: { type: 'string', required: true },
|
||||
},
|
||||
output: {
|
||||
schema: { type: 'string' },
|
||||
render: (_args, value) => [{ type: 'text', text: value }],
|
||||
},
|
||||
async execute(args) {
|
||||
const result = await ctx.myCap.execute({ input: args.input })
|
||||
return [{ type: 'text', text: result.output }]
|
||||
return result.output
|
||||
},
|
||||
}))
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user