fix(acp): isolate prompt admission from agent work

This commit is contained in:
Tianyi Cui
2026-08-11 17:45:24 +08:00
parent 57fc6bc539
commit adf4878b4a
8 changed files with 103 additions and 23 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 .agents/notes/implemented/simplification/2026-07-23-acp-automation-only-protocol.md
2026-07-23-acp-automation-only-protocol.md: 3d13e3fb51819ef4f892f33f9c86554988576e36
2026-07-23-acp-automation-only-protocol.zh.md: 224c1bd611aae23937f5610665c4bd316e15c425
2026-07-23-acp-automation-only-protocol.md: 08e222d6eaec35dd7e1acc6ec6c8a3ed74bf227a
2026-07-23-acp-automation-only-protocol.zh.md: 35c945411f7223d9d8d293b39f8a56fe6a5c3700

View File

@@ -16,7 +16,7 @@ The snapshot suite complicates removal. Most ACP scenarios exercise the assemble
`@deepseek-ai/dsh-acp` is an automation transport under [`packages/acp/acp`](../../../../packages/acp/acp/README.md), outside the `ui` package group. Its public protocol is intentionally small: version negotiation, fresh sessions with one in-flight prompt each, committed assistant text/image updates, per-session cancellation, concurrent sessions, and connection-owned teardown. Prompts preserve text and supported raster images in wire order, while resource links flatten to bracketed textual references; the bridge rejects additional directories, MCP servers, audio, embedded resources, malformed or empty prompts, unknown sessions, and overlapping prompts.
Image capability is truthful rather than structural: `initialize` advertises it only when a durable attachment store exists and the configured exact provider/model resolves with explicit image input. Each image prompt rechecks the session's latest exact route, strictly decodes every block, and delegates the complete batch to `AttachmentStore.saveImages()` before publishing the user event. Cancellation reserves and aborts the admission slot before any asynchronous work, waits for already-started writes to quiesce before the prompt settles, and never publishes a late message; a completed content-addressed write may remain unreachable because destructive rollback is not valid for a deduplicated store.
Image capability is truthful rather than structural: `initialize` advertises it only when a durable attachment store exists and the configured exact provider/model resolves with explicit image input. Each image prompt rechecks the session's latest exact route, strictly decodes every block, and delegates the complete batch to `AttachmentStore.saveImages()` before publishing the user event. Cancellation reserves and aborts the admission slot before any asynchronous work, waits for already-started writes to quiesce before the prompt settles, and never publishes a late message; before the prompt enters the Agent inbox it neither cancels nor waits for unrelated Agent work. A completed content-addressed write may remain unreachable because destructive rollback is not valid for a deduplicated store. Caller-correctable image-policy failures map to invalid parameters, while route lookup, storage corruption, and persistence failures remain internal faults.
The bridge emits only committed `assistant/message` text and images. A per-session promise chain preserves block and message order while assistant image references are asynchronously re-read and integrity-verified for ACP base64 delivery; a missing or corrupt object fails prompt delivery instead of becoming a placeholder. Reasoning, raw chunks, tool activity, todos, plans, titles, retry markers, terminal metadata, diffs, locations, and resource links remain in the durable session log or in UI-specific transports. It does not provide session load/list/delete, commands, modes, configuration selectors, model switching, plan review, or human elicitation.
@@ -32,7 +32,7 @@ Disconnect and plugin disposal share one memoized quiescence boundary. Both succ
The ACP snapshot suite still boots the assembled ACP example and retains scenarios that pin backend behavior. Only scenarios driven through deleted UI methods leave the suite; semantic-checkpoint recovery runs through the headless `stream-json` example because ACP no longer loads sessions.
Protocol and lifecycle tests pin stop-reason codecs, version negotiation, truthful image capability, fresh-session creation, ordered text/image admission, resource-link flattening, all-member validation before writes, absence of inline base64 in durable events, rejection of empty or unsupported prompts, exact-agent permission ownership, multi-session isolation, prompt settlement after ordered output, verified assistant-image delivery, cancellation during admission without a late followup, failed transport closure, ACP-only reload cleanup, and teardown quiescence. An assembled keyless snapshot sends a real inline PNG through the runnable ACP example and pins only its durable reference in the session log. Built and real-stdio smokes reject stray stdout. The `session/new` branch that loses a real stdio close race remains coverage-exempt because the in-memory transport cannot reproduce that ordering; it disposes the unpublished handle, while the surrounding disposal tests pin the no-orphan invariant.
Protocol and lifecycle tests pin stop-reason codecs, version negotiation, truthful image capability, fresh-session creation, ordered text/image admission, resource-link flattening, all-member validation before writes, absence of inline base64 in durable events, rejection of empty or unsupported prompts, exact-agent permission ownership, multi-session isolation, prompt settlement after ordered output, verified assistant-image delivery, cancellation during admission without a late followup or cancellation of unrelated Agent work, exclusion of unrelated pre-inbox failures, failed transport closure, ACP-only reload cleanup, and teardown quiescence. An assembled keyless snapshot sends a real inline PNG through the runnable ACP example and pins only its durable reference in the session log. Built and real-stdio smokes reject stray stdout. The `session/new` branch that loses a real stdio close race remains coverage-exempt because the in-memory transport cannot reproduce that ordering; it disposes the unpublished handle, while the surrounding disposal tests pin the no-orphan invariant.
## Alternatives considered

View File

@@ -16,7 +16,7 @@ ACP 仍有一个有用的职责:另一个 agent智能体或自动化控
`@deepseek-ai/dsh-acp` 是位于 [`packages/acp/acp`](../../../../packages/acp/acp/README.md) 下、独立于 `ui` 包组的自动化传输层。其公开协议特意保持精简版本协商、全新会话每个会话最多允许一个进行中的提示词、已提交的助手文本图片更新、按会话取消、并发会话以及由连接负责的资源清理。提示词按协议顺序保留文本与受支持光栅图片资源链接则展平为方括号文本引用桥接层会拒绝附加目录、MCP 服务器、音频、嵌入资源、格式错误或空提示词、未知会话和重叠提示词。
图片能力必须真实,而不能只看结构:只有持久附件存储存在,且配置的确切提供方/模型解析后明确支持图片输入时,`initialize` 才会公布该能力。每个图片提示词都会重新检查会话的最新确切路由、严格解码全部块,并在发布用户事件前把完整批次委托给 `AttachmentStore.saveImages()`。取消会在任何异步工作前预留并中止准入槽位,使提示词在已经启动的写入停稳后才结算,而且绝不发布迟到消息;已经完成的内容寻址写入可能保持不可达,因为对去重存储执行破坏性回滚并不正确
图片能力必须真实,而不能只看结构:只有持久附件存储存在,且配置的确切提供方/模型解析后明确支持图片输入时,`initialize` 才会公布该能力。每个图片提示词都会重新检查会话的最新确切路由、严格解码全部块,并在发布用户事件前把完整批次委托给 `AttachmentStore.saveImages()`。取消会在任何异步工作前预留并中止准入槽位,使提示词在已经启动的写入停稳后才结算,而且绝不发布迟到消息;提示词进入 Agent inbox 前既不会取消,也不会等待无关的 Agent 工作。已经完成的内容寻址写入可能保持不可达,因为对去重存储执行破坏性回滚并不正确。可由调用方修正的图片策略失败会映射为无效参数,路由查询、存储损坏和持久化失败则仍属于内部故障
桥接层只发出已提交的 `assistant/message` 文本与图片。每个会话使用一条 Promise 链,在异步重新读取并校验助手图片引用、将其转换为 ACP base64 交付时保持块与消息顺序对象缺失或损坏会使提示词交付失败而不是变成占位符。推理、原始分片、工具活动、待办事项、计划、标题、重试标记、终端元数据、diff、位置和资源链接仍保留在持久会话日志或 UI 专用传输层中。它不提供会话加载、列出与删除、命令、模式、配置选择器、模型切换、plan 评审或面向人类的询问。
@@ -32,7 +32,7 @@ ACP 仍有一个有用的职责:另一个 agent智能体或自动化控
ACP 快照套件仍会启动组装后的 ACP 示例,并保留用于锁定后端行为的场景。从该套件移出的只有通过已删除的 UI 方法驱动的场景;由于 ACP 不再加载会话,语义检查点恢复通过 headless `stream-json` 示例执行。
协议与生命周期测试会锁定停止原因编解码器、版本协商、真实图片能力、新会话创建、有序文本/图片准入、资源链接展平、写入前校验全部成员、持久事件中不含内联 base64、拒绝空提示词或不受支持的提示词、基于同一 agent 对象的权限归属、多会话隔离、在有序输出后结算提示词、经过校验的助手图片交付、准入期间取消且不产生迟到 followup、传输关闭失败、ACP 专属重载清理,以及拆卸完全停稳。组装后的无密钥快照通过可运行 ACP 示例发送一张真实内联 PNG并在会话日志中只固定其持久引用。构建产物冒烟测试与真实 stdio 冒烟测试会拒绝混入 stdout 的额外输出。`session/new` 中在真实 stdio 关闭竞态中落败的分支仍豁免覆盖率要求,因为内存传输层无法复现这一顺序;该分支会 dispose 尚未发布的 handle而周边 dispose 测试会锁定无遗留资源不变式。
协议与生命周期测试会锁定停止原因编解码器、版本协商、真实图片能力、新会话创建、有序文本/图片准入、资源链接展平、写入前校验全部成员、持久事件中不含内联 base64、拒绝空提示词或不受支持的提示词、基于同一 agent 对象的权限归属、多会话隔离、在有序输出后结算提示词、经过校验的助手图片交付、准入期间取消且不产生迟到 followup 或取消无关 Agent 工作、排除进入 inbox 前的无关失败、传输关闭失败、ACP 专属重载清理,以及拆卸完全停稳。组装后的无密钥快照通过可运行 ACP 示例发送一张真实内联 PNG并在会话日志中只固定其持久引用。构建产物冒烟测试与真实 stdio 冒烟测试会拒绝混入 stdout 的额外输出。`session/new` 中在真实 stdio 关闭竞态中落败的分支仍豁免覆盖率要求,因为内存传输层无法复现这一顺序;该分支会 dispose 尚未发布的 handle而周边 dispose 测试会锁定无遗留资源不变式。
## 考虑过的替代方案