refactor(acp): reduce bridge to automation protocol

This commit is contained in:
Tianyi Cui
2026-07-24 01:40:25 +08:00
parent b06bcfd21c
commit e819a586b0
406 changed files with 3880 additions and 21325 deletions

View File

@@ -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: 788c967cffa9df06e8d96e190930d69b9f2182ed
adding-a-tool.zh.md: 4ff9ce25a66625435ccba4454f2ac4b5472e5668
adding-a-tool.md: c4deed8e13afcdc8e1a714364b086b8b0da018c1
adding-a-tool.zh.md: 103c92b596a90192aae5a6b4d1e42fbcf052cf66

View File

@@ -64,9 +64,9 @@ In [Code Mode](../../packages/core/tools/README.md), every visible registered to
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)
## How your tool renders in a UI
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).
Your tool's `output.render` returns model-facing content; its **UI card** is a separate concern declared through pure presentation projections and optional `presentCall` / `presentResult` methods. Design these alongside the canonical value. 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:
@@ -76,17 +76,17 @@ Both methods return a **`card`-tagged render intent** — pick the card kind tha
- `{ card: 'diff', title, diffs, locations? }` — your call creates or modifies a file. `diffs: [{ path, oldText, newText }]` (`oldText: null` for a new file) renders as an inline diff card. (tool-fs `write`/`edit`.)
- `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 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.
- `terminal` supplies raw output and optional exit metadata; each UI renders its capable or fallback view.
- `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 the completed view replaces the pending card.
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 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.
- **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 UI adapter, not the tool, supplies session context. If you find yourself wanting the file's old content or the working directory inside `presentCall`, stop — that belongs in durable result metadata or the adapter, not the presenter.
- **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 a UI. `output.render` owns model-facing prose; `presentationMeta` plus the card presenters own replayable UI state. A `terminal` result view carries raw output and the adapter adds any fallback framing.
- **`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.
The neutral vocabulary lives in `dsh-tools`; tools never import a UI or transport type. The TUI and host/client runtime map each `card` into their own view. 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 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.
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 a UI card, assert the exact `presentCall` and `presentResult` views and exercise the owning TUI or host/client projection. Add an assembled snapshot for the shipped model or UI behavior the tool changes.

View File

@@ -64,9 +64,9 @@ producer 提供同步的 `cancel`、在资源清理后 settle 且不 reject 的
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)
## 工具在 UI 中的渲染方式
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)。
工具的 `output.render` 返回模型可见的内容;其 **UI 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。没有 UI 展示方法的工具会回退到通用卡片(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:
@@ -76,17 +76,17 @@ producer 提供同步的 `cancel`、在资源清理后 settle 且不 reject 的
- `{ 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 `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。
- `terminal` 提供原始输出和可选的退出元数据;各 UI 根据自身能力渲染对应视图或回退视图。
- `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,因为完成后的视图会替换 pending 卡片。
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。
- **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);会话上下文由 UI 适配器而非工具提供。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:那属于持久结果元数据或适配器,不属于展示器。
- **UI 格式不进入模型结果。** 围栏 ` ```console ` 块、diff、相对化路径均不应仅为服务 UI 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,由适配器按需添加回退格式。
- **`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。
中性词汇定义在 `dsh-tools` 中;工具绝不导入 UI 或传输类型。TUI 和 host/client 运行时将每个 `card` 映射到各自的视图。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。
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 UI 卡片,断言 `presentCall` 和 `presentResult` 的精确视图,并实际运行所属 TUI 或 host/client 投影。如果工具改变了已交付的模型或 UI 行为,请添加组装应用快照。

View File

@@ -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
extension-cookbook.md: 056be4298ed2bec2b78ed777d58f1f8a60a34b78
extension-cookbook.zh.md: 41cdd4a7d14f32494d1dd5ae4a63c098d5640bdc
extension-cookbook.md: 699d9d8829dafde3a314e6d58823926241251a9b
extension-cookbook.zh.md: 09b3a90bdd7dfeea362af40a10117a653c4e3cf1

View File

@@ -58,11 +58,11 @@ export function apply(ctx: Context) {
}
```
## A client-driver plugin (external protocol bridge)
## An external protocol driver
A *client driver* is a UI plugin for a wire-protocol peer. It owns stdio, so stdout logging must be disabled, creates or resumes agents through the factory, maps harness events to protocol messages, and maps requests to `send()` or `cancel()`. Settle each request exactly once from durable `turn/end`, even if rendering fails, and tear agents down with `AgentHandle.dispose()` so disposal reaches quiescence.
A *protocol driver* adapts a wire peer to `ctx.agents`; it may serve a UI or an automation client. A stdio driver owns stdout, creates or resumes agents through the factory, maps the protocol's requests to `send()` or `cancel()`, and settles each request exactly once from durable `turn/end`. Tear agents down with `AgentHandle.dispose()` so disposal reaches quiescence.
`packages/ui/acp` is the worked example: it bridges the agent to the Agent Client Protocol (JSON-RPC over stdio) so Zed and other ACP editors can drive it. See its README for the full method surface and the permission-prompt answerer it registers on the approval seam.
[`packages/acp/acp`](../../packages/acp/acp) is the automation-only worked example: it exposes fresh text sessions over Agent Client Protocol JSON-RPC stdio, emits committed assistant text, and registers a one-shot machine permission answerer for agents it owns. Its [README](../../packages/acp/acp/README.md) owns the exact method and lifecycle contract.
```ts
import type { Context } from 'cordis'

View File

@@ -58,11 +58,11 @@ export function apply(ctx: Context) {
}
```
## 客户端驱动插件(外部协议桥接)
## 外部协议驱动
*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。
*协议驱动*将协议对端接入 `ctx.agents`;它可以服务于 UI 或自动化客户端。stdio 驱动拥有 stdout,通过工厂创建或恢复 agent(智能体),将协议请求映射为 `send()` 或 `cancel()`,并根据持久的 `turn/end` 对每个请求恰好结算一次。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。
[`packages/acp/acp`](../../packages/acp/acp) 是仅面向自动化的完整示例:它通过 ACP(Agent Client Protocol)JSON-RPC stdio 提供全新文本会话,发出已提交的助手文本,并为其拥有的 agent 注册一次性机器权限应答器。其 [README](../../packages/acp/acp/README.md) 描述了精确的方法和生命周期契约。
```ts
import type { Context } from 'cordis'