chore: remove remaining SDK toolchain residue
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 .agents/notes/implemented/simplification/2026-07-23-acp-automation-only-protocol.md
|
||||
2026-07-23-acp-automation-only-protocol.md: 56c433acf59d3a0c4b5c8b6605e422d3c4efede2
|
||||
2026-07-23-acp-automation-only-protocol.zh.md: bf326ce9f6fea8c55b842bc61e3d8521032ea4d1
|
||||
2026-07-23-acp-automation-only-protocol.md: 56dcaf8b4327a008f26b884264958cac02d6541a
|
||||
2026-07-23-acp-automation-only-protocol.zh.md: a34e179a1d38c1867ea8165b149a9ec7716c1c0e
|
||||
|
||||
@@ -20,7 +20,7 @@ The bridge emits only committed `assistant/message` text. Reasoning, raw chunks,
|
||||
|
||||
One-shot `session/request_permission` remains. It is a machine policy channel for bridge-owned agents, not a human approval UI: the answerer accepts only an exact agent object in the bridge's live session map, delegates foreign or call-less requests, and maps failed RPCs to the fail-closed unavailable outcome. The client chooses allow once, reject once, or cancel, and the bridge never turns that response into a durable grant. Asking policy stays in the approval seam and its producers; [`dsh-subagent-acp`](../../../../packages/subagent/subagent-acp/README.md) uses this channel programmatically.
|
||||
|
||||
The app composition contains the agent spine, persistence, checkpoint policy, and ACP transport. It does not mount command, session-query, session-reference, plan-mode, permission-picker, or user-interaction services for ACP. SDK scaffolding likewise treats `ask_user_question` as TUI-only.
|
||||
The app composition contains the agent spine, persistence, checkpoint policy, and ACP transport. It does not mount command, session-query, session-reference, plan-mode, permission-picker, or user-interaction services for ACP.
|
||||
|
||||
The transport programs interface-level agent, session, and approval services rather than the concrete agent loop. Tool execution stays inside the harness; ACP never delegates shell execution to an editor. stdout carries framed JSON-RPC only, so the app mounts no stdout logger and the bridge does not monkey-patch process output.
|
||||
|
||||
|
||||
@@ -20,7 +20,7 @@ ACP 仍有一个有用的职责:另一个 agent(智能体)或自动化控
|
||||
|
||||
保留一次性 `session/request_permission`。它是为桥接层拥有的 agent 提供的机器策略通道,而不是面向人类的审批 UI:应答者只接受桥接层当前会话映射中登记的同一 agent 对象;外部请求或缺少调用标识的请求会继续委派;RPC 失败则映射为拒绝请求的 `unavailable` 结果。客户端可选择允许一次、拒绝一次或取消,桥接层绝不会将该响应转换为持久授权。询问策略仍归审批 seam 及其生产者所有;[`dsh-subagent-acp`](../../../../packages/subagent/subagent-acp/README.md) 会以程序化方式使用该通道。
|
||||
|
||||
应用组装包含 agent 主干、持久化、检查点策略和 ACP 传输层。它不会为 ACP 挂载命令、会话查询、会话引用、plan mode、权限选择器或用户交互服务。SDK 脚手架同样将 `ask_user_question` 视为 TUI 专属功能。
|
||||
应用组装包含 agent 主干、持久化、检查点策略和 ACP 传输层。它不会为 ACP 挂载命令、会话查询、会话引用、plan mode、权限选择器或用户交互服务。
|
||||
|
||||
传输层调用 agent、会话和审批的接口服务,而不依赖具体的 agent loop。工具执行仍留在 harness 内;ACP 绝不会把 shell 执行委派给编辑器。stdout 只承载分帧 JSON-RPC,因此 app 不挂载 stdout logger,桥接层也不会 monkey-patch 进程输出。
|
||||
|
||||
|
||||
Reference in New Issue
Block a user