feat: return typed values from Code Mode
This commit is contained in:
@@ -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: f94ddfaa9df53c0ee4596d683e676baae6bd85b2
|
||||
adding-a-tool.zh.md: 915dc8250c2bcfc490483f87c71e725b1f92f635
|
||||
adding-a-tool.md: 3ad7240c2210ef52b62d9a62561eb4b912a2b278
|
||||
adding-a-tool.zh.md: 79a2d0f82e0bf805e3f7be960a73fc762160c22f
|
||||
|
||||
@@ -50,9 +50,9 @@ Registration is effect-based: disposing the plugin fiber unregisters the tool (w
|
||||
|
||||
## Long-running work
|
||||
|
||||
Gate `run_in_background` with producer config, reject a pre-aborted call, then register through `ctx.tasks.start({ kind, label, owner: exec.agent, run })`. The runtime validates ownership and control-surface availability before `run()` starts work, then supplies the id, session fence, generic control tools, notices, and owner cleanup.
|
||||
Gate `run_in_background` with producer config, reject a pre-aborted call, then register through `ctx.tasks.start({ kind, label, owner: exec.agent, run })`. The runtime validates ownership and control-surface availability before `run()` starts work, then supplies the id, session fence, generic control tools, notices, and owner cleanup. A successful background branch returns a typed canonical handle such as `{ kind: 'background', taskId }`; its Native renderer may keep human prose such as `started background task bash-1`, but Code Mode must never parse that prose to recover the id.
|
||||
|
||||
The producer supplies synchronous `cancel`, non-rejecting `done` that settles after resource cleanup, and optional consuming `readOutput` with bounded-output formatting. Once the id is returned, use a task-owned cancellation signal rather than `exec.signal`. See the [background task runtime Agent Note](../../.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.md) and `dsh-tool-bash` for a stream producer.
|
||||
The producer supplies synchronous `cancel`, non-rejecting `done` that settles after resource cleanup, and optional consuming `readOutput` with bounded-output formatting. A pre-aborted call is a failure because no task exists whose id could satisfy the successful output schema. Once `ctx.tasks.start()` publishes the id, use a task-owned cancellation signal rather than `exec.signal`: later outer-call cancellation stops waiting for the call but does not kill published work; `task_kill`, owner disposal, and service teardown own that lifetime. Foreground work remains coupled to `exec.signal`. See the [background task runtime Agent Note](../../.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.md) and `dsh-tool-bash` for a stream producer.
|
||||
|
||||
## Execution policy and observation
|
||||
|
||||
@@ -60,7 +60,9 @@ Prefer not to build deployment policy into the tool. Use `tools/pre-execute` for
|
||||
|
||||
## Code Mode reaches your tool for free
|
||||
|
||||
In [Code Mode](../../packages/core/tools/README.md), every visible registered tool is available as `await tools.<name>(args)` without extra integration. The SDK derives parameters from the same JSON Schema, and calls re-enter the normal execution pipeline. Write descriptions as model-facing API docs; non-text result blocks become placeholders in programs.
|
||||
In [Code Mode](../../packages/core/tools/README.md), every visible registered tool is available as `await tools.<name>(args)` without extra integration. The generated `ToolArgsMap` and `ToolOutputMap` derive exact argument and canonical-return types from the same schemas, and calls re-enter the normal execution pipeline. A successful call resolves to the final canonical JSON value after policy, not to rendered Native content. A failed call rejects with the real `ToolCallError`; programs can inspect only its `name`, `toolName`, and human-readable `message`, not internal error codes or a failure union.
|
||||
|
||||
Design `output.schema` as a useful programmatic API: return handles and fields directly, allow scalar/array/null roots when they are the honest value, and keep human explanation in `output.render`. Intermediate values are execution-local, are not persisted or prompt-truncated, and have no byte cap, so the producer's truthful acquisition bounds and process memory still matter. Only the outer `run_code` logs/result cross the configurable output cap and model-facing spill pipeline.
|
||||
|
||||
## How your tool renders in an editor (ACP presentation)
|
||||
|
||||
|
||||
@@ -50,9 +50,9 @@ export function apply(ctx: Context) {
|
||||
|
||||
## 长时间运行的工作
|
||||
|
||||
通过 producer 配置控制 `run_in_background`,拒绝已预先中止的调用,然后使用 `ctx.tasks.start({ kind, label, owner: exec.agent, run })` 注册任务。运行时会在 `run()` 启动工作前校验 owner 和控制面是否可用,随后提供 id、会话围栏、通用控制工具、通知和 owner cleanup。
|
||||
通过 producer 配置控制 `run_in_background`,拒绝已预先中止的调用,然后使用 `ctx.tasks.start({ kind, label, owner: exec.agent, run })` 注册任务。运行时会在 `run()` 启动工作前校验 owner 和控制面是否可用,随后提供 id、会话围栏、通用控制工具、通知和 owner cleanup。成功的后台分支会返回类型化的规范句柄,如 `{ kind: 'background', taskId }`;其 Native 渲染器可以保留 `started background task bash-1` 这类供人阅读的自然语言,但 Code Mode 绝不能通过解析该文本取得 id。
|
||||
|
||||
producer 提供同步的 `cancel`、在资源清理后 settle 且不 reject 的 `done`,以及可选的消费式 `readOutput`(负责有界输出的格式化)。返回 id 后,应使用 task 自有的取消信号,而不是 `exec.signal`。流式 producer 的示例和完整契约见[后台 task 运行时 Agent Note](../../.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.md)与 `dsh-tool-bash`。
|
||||
producer 提供同步的 `cancel`、在资源清理后 settle 且不 reject 的 `done`,以及可选的消费式 `readOutput`(负责有界输出的格式化)。预先中止的调用属于失败,因为此时没有任务,其 id 无法满足成功输出 schema。`ctx.tasks.start()` 发布 id 后,应使用任务自有的取消信号,而不是 `exec.signal`:之后取消外层调用只会停止等待本次调用,不会终止已经发布的工作;该生命周期归 `task_kill`、owner dispose 和服务 teardown 所有。前台工作仍与 `exec.signal` 耦合。流式 producer 的示例和完整契约见[后台 task 运行时 Agent Note](../../.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.md)与 `dsh-tool-bash`。
|
||||
|
||||
## 执行策略与观测
|
||||
|
||||
@@ -60,7 +60,9 @@ producer 提供同步的 `cancel`、在资源清理后 settle 且不 reject 的
|
||||
|
||||
## 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。
|
||||
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。生成的 `ToolArgsMap` 和 `ToolOutputMap` 会根据同一组 schema 分别派生精确的参数类型与规范返回类型,调用则重新进入正常的执行流水线。成功调用会解析为策略处理后的最终规范 JSON 值,而不是渲染后的 Native 内容。失败调用会以真正的 `ToolCallError` reject;程序只能检查其 `name`、`toolName` 和可供人阅读的 `message`,无法取得内部错误代码或失败联合。
|
||||
|
||||
请把 `output.schema` 设计为实用的程序化 API:直接返回句柄与字段;当标量、数组或 null 确实就是结果时,允许采用相应的根类型;将面向人类的解释放入 `output.render`。中间值只存在于执行期间,不会被持久化或按提示词上限截断,也不设字节上限,因此生产方如实声明的采集边界和进程内存仍然重要。只有外层 `run_code` 日志/结果会受到可配置输出上限和面向模型的输出落盘流水线约束。
|
||||
|
||||
## 工具在编辑器中的渲染方式(ACP 展示)
|
||||
|
||||
|
||||
Reference in New Issue
Block a user