diff --git a/.agents/notes/implemented/feature/2026-07-06-approval-seam.i18n.yaml b/.agents/notes/implemented/feature/2026-07-06-approval-seam.i18n.yaml index ec785c65c4..1b31d76e29 100644 --- a/.agents/notes/implemented/feature/2026-07-06-approval-seam.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-06-approval-seam.i18n.yaml @@ -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 -2026-07-06-approval-seam.md: e28587e0185530164f300562f7dd5e57255ac515 -2026-07-06-approval-seam.zh.md: 94ffb330cd36ae88975e8ae9d579b3b4606a5c25 +2026-07-06-approval-seam.md: 2268181bd3c5655e60b62f23b63978072d663346 +2026-07-06-approval-seam.zh.md: 67fb4f7adff359424c46b03b68d6ad7c53eeded2 diff --git a/.agents/notes/implemented/feature/2026-07-06-approval-seam.zh.md b/.agents/notes/implemented/feature/2026-07-06-approval-seam.zh.md index 94ffb330cd..67fb4f7adf 100644 --- a/.agents/notes/implemented/feature/2026-07-06-approval-seam.zh.md +++ b/.agents/notes/implemented/feature/2026-07-06-approval-seam.zh.md @@ -123,7 +123,7 @@ ACP 桥只应答其正向会话映射所拥有的精确 agent 对象。它把 `s - **谁决定一次调用是否需要 ask？** 策略生产者：返回 `permissionDecision: ask` 的钩子、任何 `tools/pre-execute` 监听器、或沙箱升级门禁。seam 和桥只负责路由和应答；二者都不注入自己对「什么值得弹出提示」的判断。 - **用户关闭提示或轮次在 ask 进行中中止时会发生什么？** 关闭映射为 `cancelled` 并携带自己的拒绝文本。已中止的 signal 直接结算为 `cancelled` 而不派发；ask 进行中的中止丢弃迟到的应答。当两个审计追加都提交时，任一路径都记录恰好一对事件，绝不会两对。 - **如果客户端以 harness 从未提供的选项应答呢？** 除已提供的 `allow_once` 之外的任何选项都映射为 `rejected`——来自不合规客户端的未知 optionId 永远不能授权。 -- **subagent 的审批如何路由？** 没有应答者拥有的 agent 穿过整个 waterfall 委派并失败关闭——进程内 subagent 被刻意设计为不可应答。`subagent-acp` 的子侧自动应答是独立的；将子 agent 的 ask 路由到父会话的编辑器已延后（§ 延后）。 +- **subagent 的审批如何路由？** 没有应答者拥有的 agent 穿过整个 waterfall 委派并失败关闭——进程内 subagent 被刻意设计为不可应答。但会话策略确实会跨过这条边界：`'never'` 父级的子 agent 通过盖章写入的覆盖项继承 `'never'`（[subagent 策略继承 Agent Note](2026-07-25-subagent-policy-inheritance.md)），因此它们一开始就被告知，而不是向空的 waterfall 发出 ask。`subagent-acp` 的子侧自动应答是独立的；将子 agent 的 ask 路由到父会话的编辑器已延后（§ 延后）。 - **`policy: 'never'` 在运行时实际改变了什么？** 服务在派发任何应答者之前，将该会话的每次 ask 解析为 `rejected`（在服务内部，因此没有注册顺序能绕过它）；系统提示词声明该策略；切换在边界处被叙述；每次成功的自动拒绝都会记录审计对。 - **热重载或 UI 插件在会话中途卸载时会发生什么？** 应答者随其拥有的 fiber 一起 dispose，因此下一次 ask 降级为 `unavailable` 而非挂在死通道上；重新挂载会重新注册应答者，无需追赶状态。 - **用户在哪里看到自己在批准什么？** 在工具调用本身：提示通过 `callId` 附着在已流式输出的调用上（包含参数），并添加发起方的人类可读 `reason`；请求本身不携带参数副本。 diff --git a/.agents/notes/implemented/feature/2026-07-06-sandbox.i18n.yaml b/.agents/notes/implemented/feature/2026-07-06-sandbox.i18n.yaml index 287deaff20..efc3e062ca 100644 --- a/.agents/notes/implemented/feature/2026-07-06-sandbox.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-06-sandbox.i18n.yaml @@ -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 -2026-07-06-sandbox.md: c1307a7201ed1bc331a86d4ffee002d69fd1d5e5 -2026-07-06-sandbox.zh.md: 4e3d4951f71a602bc78551c90dda04317d0f8284 +2026-07-06-sandbox.md: 0ecb8e853cb4e221b02c49999be7e1c2943ff5aa +2026-07-06-sandbox.zh.md: ec3cf740a218afa72f6b986d7322aad5fee8ffae diff --git a/.agents/notes/implemented/feature/2026-07-06-sandbox.zh.md b/.agents/notes/implemented/feature/2026-07-06-sandbox.zh.md index 4e3d4951f7..ec3cf740a2 100644 --- a/.agents/notes/implemented/feature/2026-07-06-sandbox.zh.md +++ b/.agents/notes/implemented/feature/2026-07-06-sandbox.zh.md @@ -92,7 +92,7 @@ Landlock launcher 源码和包工作区位于 `native/landlock-run`，与 harnes effective(session) = findLast(the session's own knob events)?.value ?? the composition-config default ``` -默认值是组合配置（`cordis.yml`）——运维人员拥有，进程范围。运行时切换是会话范围的覆盖，记录为该会话自身日志中的一条仅日志事件。重启免疫（恢复会话时回放其日志，覆盖自然恢复，无需追赶机制）和多会话隔离（一个编辑器标签页的 `workspace-write` 不会干扰另一个的 `read-only`）都是构造性的自然结果，且不存在任何外部配置存储。 +默认值是组合配置（`cordis.yml`）——运维人员拥有，进程范围。运行时切换是会话范围的覆盖，记录为该会话自身日志中的一条仅日志事件。重启免疫（恢复会话时回放其日志，覆盖自然恢复，无需追赶机制）和多会话隔离（一个编辑器标签页的 `workspace-write` 不会干扰另一个的 `read-only`）都是构造性的自然结果，且不存在任何外部配置存储。隔离并不使委派成为逃生通道：进程内 subagent 驱动器会在子 agent 的首个轮次内，把发起委派的父级的有效覆盖盖章写入每个子会话，因此收紧后的父级会约束 spawn 子 agent、fork 子 agent 与孙代 agent（[subagent 策略继承 Agent Note](2026-07-25-subagent-policy-inheritance.md)）。 **每个旋钮一种事件，由其领域拥有**——这是每个既有事件族已遵循的可合并扩展 `SessionEventMap` 惯用法（`dsh-user-approval` 中的 `approval/*`、hooks 包中的 `hook/*`）： diff --git a/examples/acp-agent/tests/snapshots/subagent-sandbox-inheritance/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/subagent-sandbox-inheritance/stdout.expected.jsonl index d95775322d..31cc1fcdf4 100644 --- a/examples/acp-agent/tests/snapshots/subagent-sandbox-inheritance/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-sandbox-inheritance/stdout.expected.jsonl @@ -1,6 +1,6 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"sessionCapabilities":{"list":{}},"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} {"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","modes":{"availableModes":[{"id":"default","name":"default"},{"id":"plan","name":"plan"}],"currentModeId":"default"},"configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"read-only","name":"read-only","description":"Read all files; every mutation is denied without a per-call approval."},{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}},{"name":"plan","description":"Enter plan mode","input":{"hint":"[message]"}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[|clear|edit |pause|resume]"}},{"name":"plan","description":"Enter or leave plan mode","input":{"hint":"[off|message]"}}]}}} {"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"read-only","options":[{"value":"read-only","name":"read-only","description":"Read all files; every mutation is denied without a per-call approval."},{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"session_info_update","title":"Use the subagent tool exactly","updatedAt":"{{updatedAt}}"}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-sandbox-inheritance/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/subagent-sandbox-inheritance/tool-schemas.expected.json index 61d317e2f8..b01e7683d1 100644 --- a/examples/acp-agent/tests/snapshots/subagent-sandbox-inheritance/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/subagent-sandbox-inheritance/tool-schemas.expected.json @@ -11,6 +11,7 @@ "description": "Questions to ask the user before continuing.", "items": { "type": "object", + "additionalProperties": true, "properties": { "id": { "type": "string", @@ -29,6 +30,7 @@ "description": "Optional choices to show the user. If you recommend one, put it first and append \"(Recommended)\" to that label.", "items": { "type": "object", + "additionalProperties": true, "properties": { "label": { "type": "string", @@ -365,6 +367,7 @@ "description": "The COMPLETE task list, replacing any previous list.", "items": { "type": "object", + "additionalProperties": true, "properties": { "content": { "type": "string", @@ -439,7 +442,7 @@ }, { "name": "workflow", - "description": "Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.", + "description": "Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const/oneOf — no pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.", "parameters": { "type": "object", "properties": { @@ -450,6 +453,7 @@ "meta": { "type": "object", "description": "The workflow identity block (plain JSON — never code).", + "additionalProperties": true, "properties": { "name": { "type": "string", @@ -468,6 +472,7 @@ "description": "Optional phase declarations matched by phase() calls.", "items": { "type": "object", + "additionalProperties": true, "properties": { "title": { "type": "string", @@ -499,7 +504,8 @@ }, "args": { "type": "object", - "description": "Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})." + "description": "Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}).", + "additionalProperties": true } }, "required": [ diff --git a/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts b/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts index ce91480ea8..46ea9e2e30 100644 --- a/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts +++ b/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts @@ -203,6 +203,9 @@ describe('startInProcessRun', () => { options: parent.options, session: parent.session, ctx: { + // The driver's synchronous inheritance capture probes both policy + // services opportunistically; this stub composes neither. + get: () => undefined, agents: { create: async (options: Parameters[0]) => { const handle = await ctx.agents.create(options)