Merge remote-tracking branch 'origin/master' into worktree/web-multimodal-image-input
# Conflicts: # .agents/notes/implemented/architecture/2026-07-25-web-input-machine-and-slash-pipeline.i18n.yaml # apps/web/tests/code-mode-fixture.snapshot.ts # docs/architecture.i18n.yaml # docs/core-data-structures/core.i18n.yaml # docs/module-graph.md # packages/README.i18n.yaml # packages/client/runtime/README.i18n.yaml # packages/client/runtime/README.md # packages/client/runtime/README.zh.md # packages/client/test-runtime/tests/runtime.spec.tsx # packages/client/ui-conversation/README.i18n.yaml # packages/client/ui-conversation/package.json # packages/client/ui-conversation/src/client/chat/ChatView.tsx # packages/client/ui-conversation/src/client/skeleton/ConversationSession.tsx # packages/client/ui-conversation/src/client/skeleton/InputBar.tsx # packages/client/ui-conversation/tests/skeleton.spec.tsx # packages/compact/compact-basic/README.i18n.yaml # packages/compact/compact-basic/README.zh.md # packages/compact/compact-basic/src/summarizer.ts # packages/host/apiproxy/src/api/sessions.ts # packages/llm/llm-pi-ai/README.i18n.yaml # packages/llm/llm/README.i18n.yaml # packages/ui/tui/README.i18n.yaml # pnpm-lock.yaml
This commit is contained in:
@@ -3,4 +3,4 @@
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write examples/README.md
|
||||
README.md: 7f12178d1b67f1ebfac6f4f0e31403c54106e98f
|
||||
README.zh.md: 72ab92602d0a53cabdbfa8bc34838061df25d1c7
|
||||
README.zh.md: c7c1bf76593661616464558e554d57340d7c03b1
|
||||
|
||||
@@ -2,11 +2,11 @@
|
||||
|
||||
[English](README.md) | 中文
|
||||
|
||||
展示 harness 如何接线的可运行演示(不是 workspace)。每个示例都是一个 **轻量叶节点**:一份选择可替换后端、加载一个应用包(package)并可添加可选产品工具的 `cordis.yml`。组合和启动粘合代码位于 [`@deepseek-ai/dsh-tui-demo`](../packages/examples/tui-demo)、[`@deepseek-ai/dsh-cli-demo`](../packages/examples/cli-demo)、[`@deepseek-ai/dsh-acp-demo`](../packages/examples/acp-demo) 及它们共享的 [`@deepseek-ai/dsh-agent-spine-demo`](../packages/examples/agent-spine-demo) 组合包中。没有 `start.ts`;终端 `demo:*` 脚本通过 [`dsh`](../apps/cli/README.md) CLI(命令行界面)启动(该 CLI 挂载 `tui-demo` 组合包),无头/ACP(Agent Client Protocol)脚本则调用 `cli-demo`/`acp-demo` bin。
|
||||
展示 harness 如何组装的可运行演示(不是 workspace)。每个示例都是一个 **轻量叶节点**:一份选择可替换后端、加载一个应用包(package)并可添加可选产品工具的 `cordis.yml`。组合和启动粘合代码位于 [`@deepseek-ai/dsh-tui-demo`](../packages/examples/tui-demo)、[`@deepseek-ai/dsh-cli-demo`](../packages/examples/cli-demo)、[`@deepseek-ai/dsh-acp-demo`](../packages/examples/acp-demo) 及它们共享的 [`@deepseek-ai/dsh-agent-spine-demo`](../packages/examples/agent-spine-demo) 组合包中。没有 `start.ts`;终端 `demo:*` 脚本通过 [`dsh`](../apps/cli/README.md) CLI(命令行界面)启动(该 CLI 挂载 `tui-demo` 组合包),无头/ACP(Agent Client Protocol)脚本则调用 `cli-demo`/`acp-demo` bin。
|
||||
|
||||
## headless-agent
|
||||
|
||||
非交互式 agent(智能体)演示:接受一个位置任务,在 `@deepseek-ai/dsh-cli-demo` 应用上运行一个完整模型/工具轮次,持久化新会话,打印 `text`、`json` 或 `stream-json`,然后退出。
|
||||
非交互式 agent(智能体)演示:接受一个位置参数形式的任务,在 `@deepseek-ai/dsh-cli-demo` 应用上运行一个完整模型/工具轮次,持久化新会话,打印 `text`、`json` 或 `stream-json`,然后退出。
|
||||
|
||||
运行:`pnpm run demo:headless "task"`(需要 `DEEPSEEK_API_KEY`)。输出契约、安全边界和快照套件详见 [headless-agent/README.md](headless-agent/README.md)。
|
||||
|
||||
@@ -18,18 +18,18 @@
|
||||
|
||||
## jsonrpc-agent
|
||||
|
||||
通过 Python SDK 驱动的无人值守编码 agent:JSON-RPC stdio、仅前台 `bash`、`read`/`write`/`edit`、一个前台 `subagent`、`todo_write`、JSONL 持久化和压缩。它不包含终端 UI、stdout 日志、批准、skill 和后台任务控制。详见 [jsonrpc-agent/README.md](jsonrpc-agent/README.md)。
|
||||
通过 Python SDK 驱动的无人值守编码 agent:JSON-RPC stdio、仅前台 `bash`、`read`/`write`/`edit`、一个前台 `subagent`、`todo_write`、JSONL 持久化和压缩。它不包含终端 UI、stdout 日志、批准、skill(技能)和后台任务控制。详见 [jsonrpc-agent/README.md](jsonrpc-agent/README.md)。
|
||||
|
||||
## cordis-agent
|
||||
|
||||
**自指** 演示:编码主干加 [`@deepseek-ai/dsh-tool-cordis`](../packages/cordis/tool-cordis),其三个工具(`cordis_inspect`/`cordis_mount`/`cordis_unmount`)使 agent 可以检查当前 DSH 进程、挂载模型编写的临时 Plugin(事件监听器、一个全新工具,或一个供另一临时 Plugin 注入的服务),并再次卸载它们。这些 Plugin 只存在于内存中,共享一个内部 `cordis-dynamic` fiber 子树;`ctx.fs`/`ctx.web` 仅作为它们可用的能力提供方。
|
||||
**自指** 演示:编码主干加 [`@deepseek-ai/dsh-tool-cordis`](../packages/cordis/tool-cordis),其三个工具(`cordis_inspect`/`cordis_mount`/`cordis_unmount`)使 agent 可以检查当前 DSH 进程、挂载模型编写的临时插件(事件监听器、一个全新工具,或一个供另一个临时插件注入的服务),并再次卸载它们。这些插件只存在于内存中,共享一个内部 `cordis-dynamic` fiber 子树;`ctx.fs`/`ctx.web` 仅作为它们可用的能力提供方。
|
||||
|
||||
使用 `pnpm run demo:cordis` 运行 TUI,使用 `pnpm run demo:cordis web` 在 `http://127.0.0.1:3081` 启动浏览器 UI,或使用 `pnpm run demo:cordis acp` 启动 ACP 服务器(三者均需 `DEEPSEEK_API_KEY`)。分阶段演示脚本详见 [cordis-agent/README.md](cordis-agent/README.md),设计与沙箱注意事项详见[工具集 Agent Note](../.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md)。
|
||||
使用 `pnpm run demo:cordis` 运行 TUI,使用 `pnpm run demo:cordis web` 在 `http://127.0.0.1:3081` 启动浏览器 UI,或使用 `pnpm run demo:cordis acp` 启动 ACP 服务器(三者均需 `DEEPSEEK_API_KEY`)。分阶段演示脚本详见 [cordis-agent/README.md](cordis-agent/README.md),设计与沙箱注意事项详见[工具集 Agent Note(agent 决策记录)](../.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md)。
|
||||
|
||||
## acp-agent
|
||||
|
||||
作为 **Agent Client Protocol (ACP)** 自动化服务器通过 JSON-RPC stdio 公开的 agent,由 [`@deepseek-ai/dsh-acp-demo`](../packages/examples/acp-demo) 提供。程序化客户端可以创建新会话、发送文本提示词、消费已提交的 assistant 文本、回答一次性权限请求并取消工作。它拥有 ACP 无密钥快照套件。
|
||||
一个通过 JSON-RPC stdio 公开、作为 **Agent Client Protocol (ACP)** 自动化服务器运行的 agent,由 [`@deepseek-ai/dsh-acp-demo`](../packages/examples/acp-demo) 提供。程序化客户端可以创建新会话、发送文本提示词、消费已提交的 assistant 文本、回答一次性权限请求并取消工作。它拥有 ACP 无密钥快照套件。
|
||||
|
||||
运行:`pnpm run demo:acp`(需要 `DEEPSEEK_API_KEY`);`pnpm run demo:code-mode acp` 通过 `code-mode.cordis.yml` 覆盖以 Code Mode 启动同一服务器。协议与快照测试契约详见 [acp-agent/README.md](acp-agent/README.md)。
|
||||
|
||||
默认 `cordis.yml` 组合 [`@deepseek-ai/dsh-sandbox-local`](../packages/sandbox/sandbox-local)、[`@deepseek-ai/dsh-bash-sandbox`](../packages/bash/bash-sandbox) 和 [`@deepseek-ai/dsh-user-approval`](../packages/ui/user-approval)。`workspace-write` 将 bash 和文件系统变更限制在每个会话 workspace 中;范围更广的重试会通过 ACP 成为一次性机器权限请求。
|
||||
默认 `cordis.yml` 组合 [`@deepseek-ai/dsh-sandbox-local`](../packages/sandbox/sandbox-local)、[`@deepseek-ai/dsh-bash-sandbox`](../packages/bash/bash-sandbox) 和 [`@deepseek-ai/dsh-user-approval`](../packages/ui/user-approval)。`workspace-write` 将 bash 和文件系统变更限制在每个会话 workspace 中;请求更广泛沙箱权限的重试会通过 ACP 触发一次性的机器权限请求。
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
|
||||
# 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
|
||||
# pnpm run verify-translation-pairing --write examples/acp-agent/README.md
|
||||
README.md: 0d63ec1f2d9165b9faf0817bd94fbe15b97fa961
|
||||
README.zh.md: 0c5f8866ea640843513fd9a4c15a17ed4db59d3b
|
||||
README.zh.md: 84482aad8352ab38527dcf4d9e1bfefc8d496c91
|
||||
|
||||
@@ -2,29 +2,29 @@
|
||||
|
||||
[English](README.md) | 中文
|
||||
|
||||
通过 JSON-RPC stdio 提供的自动化导向 [Agent Client Protocol](https://agentclientprotocol.com) 服务器。它面向父 agent(智能体)、subagent 提供方和其他程序化客户端,而非产品 UI。
|
||||
通过 JSON-RPC stdio 提供的面向自动化的 [Agent Client Protocol(ACP)](https://agentclientprotocol.com) 服务器。它面向 parent agent(父智能体)、subagent 提供方和其他程序化客户端,而非产品 UI。
|
||||
|
||||
```sh
|
||||
pnpm run demo:acp # needs DEEPSEEK_API_KEY (repo-root .env or env)
|
||||
pnpm run demo:code-mode acp # same protocol with the Code Mode tool transport
|
||||
```
|
||||
|
||||
该叶节点加载 ACP 应用、DeepSeek 适配器、受沙箱限制的 bash 与文件系统栈、一次性批准策略、压缩(compaction)、subagent、工作流、钩子、派生会话查询索引和重复守卫。应用为每次 `session/new` 创建一个新 agent,将会话持久化到 JSONL,并保持 stdout 只含协议内容。[`session-query.cordis.yml`](session-query.cordis.yml) 为其专用快照显式选用 workspace 授权的查询工具和通用超时/溢出策略;[`fs.cordis.yml`](fs.cordis.yml) 为文件系统场景添加溢出存储,[`code-mode.cordis.yml`](code-mode.cordis.yml) 添加 `run_code` 及其生成的 TypeScript SDK,[`web.cordis.yml`](web.cordis.yml) 则为 web-fetch 快照添加 web seam、本地抓取提供方、`web_fetch` 与一个回环 HTML fixture 服务器。
|
||||
该叶节点加载 ACP 应用、DeepSeek 适配器、受沙箱限制的 bash 与文件系统栈、一次性批准策略、压缩(compaction)、subagent、工作流、钩子、派生会话查询索引和重复守卫。应用为每次 `session/new` 创建一个新 agent,将会话持久化到 JSONL,并保持 stdout 只含协议内容。[`session-query.cordis.yml`](session-query.cordis.yml) 为其专用快照显式选用 workspace 授权的查询工具和通用超时/溢出策略;[`fs.cordis.yml`](fs.cordis.yml) 为文件系统场景添加溢出存储,[`code-mode.cordis.yml`](code-mode.cordis.yml) 添加 `run_code` 及其生成的 TypeScript SDK,[`web.cordis.yml`](web.cordis.yml) 则为 web-fetch 快照添加 web seam、本地抓取提供方、`web_fetch` 与一个回环 HTML fixture(测试前置数据)服务器。
|
||||
|
||||
## 协议通道
|
||||
|
||||
Stdout 只携带以换行分隔的 ACP JSON-RPC。`@deepseek-ai/dsh-acp-demo` 不安装 stdout logger;叶节点的附加项必须使用 stderr 输出诊断信息。
|
||||
Stdout 只携带以换行分隔的 ACP JSON-RPC。`@deepseek-ai/dsh-acp-demo` 不安装 stdout logger;该叶节点新增的组件必须使用 stderr 输出诊断信息。
|
||||
|
||||
自动化契约(支持的方法、基线提示词内容、已提交文本输出,以及有意缺少的 UI 界面)位于 [`@deepseek-ai/dsh-acp`](../../packages/acp/acp/README.md)。
|
||||
|
||||
## 会话 workspace 与权限
|
||||
|
||||
每次 `session/new` 都提供一个绝对 `cwd`。受沙箱限制的 bash 与文件系统变更会根据该会话 cwd 解析 `workspace-write`,因此并发会话可以使用不同的项目根目录;平台临时根目录仍是共享可写暂存空间(参见[沙箱契约](../../packages/sandbox/sandbox/README.md))。`DSH_PERMISSION_MODE` 在部署和测试中选择 `workspace-write` 或 `danger-full-access`。
|
||||
每次 `session/new` 都提供一个绝对 `cwd`。受沙箱限制的 bash 和文件系统修改会以该会话 cwd 为基准应用 `workspace-write`,因此并发会话可以使用不同的项目根目录;平台临时根目录仍是共享可写暂存空间(参见[沙箱契约](../../packages/sandbox/sandbox/README.md))。`DSH_PERMISSION_MODE` 在部署和测试中选择 `workspace-write` 或 `danger-full-access`。
|
||||
|
||||
在 `workspace-write` 下,模型请求扩大沙箱权限的重试会触发 `session/request_permission`,选项为 `allow_once` 和 `reject_once`。客户端以程序方式决策;解除对话框或答案不可用时会失败闭合。选定结果仅适用于该次重试,并通过常规工具结果/审计路径记录。服务器绝不公开权限选择器,也不持久化客户端策略。
|
||||
在 `workspace-write` 下,如果模型重试请求更广泛的沙箱访问权限,就会触发 `session/request_permission`,选项为 `allow_once` 和 `reject_once`。客户端以程序方式决策;客户端放弃选择或无法给出答复时,系统会按拒绝处理。选定结果仅适用于该次重试,并通过常规工具结果/审计路径记录。服务器绝不公开权限选择器,也不持久化客户端策略。
|
||||
|
||||
## 快照测试
|
||||
|
||||
此示例拥有 ACP 快照套件。它会启动真实自动化服务器,通过 `dsh-llm-replay` 回放已提交的模型流,并比较规范化后的协议输出与重新持久化的会话日志。录制使用真实模型;刷新会复用已提交的回放输入。覆盖场景包括抛出/挂起行为,可选 `workspace/` fixture(测试前置数据)则为外部状态检查预置环境。
|
||||
此示例拥有 ACP 快照套件。它会启动真实自动化服务器,通过 `dsh-llm-replay` 回放已提交的模型流,并比较规范化后的协议输出与重新持久化的会话日志。录制使用真实模型;刷新会复用已提交的回放输入。覆盖配置涵盖抛错/挂起行为,可选的 `workspace/` fixture 则为环境状态检查预置状态。
|
||||
|
||||
大多数场景锁定后端行为,而非 ACP 专用行为;[仅面向自动化的 ACP 决策](../../.agents/notes/implemented/simplification/2026-07-23-acp-automation-only-protocol.md#snapshot-boundary)说明了为何该覆盖仍与传输层耦合。
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
{"type":"turn/start","seq":0,"time":1783654655602,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
|
||||
{"type":"user/message","seq":1,"time":1783654655603,"data":{"content":[{"type":"text","text":"Load the snapshot-skill skill with the skill tool, then reply DONE."}],"source":{"kind":"user"},"role":"user","id":"9c670f1c-3508-4b98-9cae-21f363652d6e"},"surfaceOp":"append"}
|
||||
{"type":"session/title","seq":2,"time":1783654655603,"data":{"title":"Load the snapshot-skill skill with","messageSeqs":[1],"source":{"kind":"fallback"}}}
|
||||
{"type":"user/message","seq":3,"time":1784903324926,"data":{"content":[{"type":"text","text":"<system-reminder>\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n<available_skills>\n- `snapshot-skill`: Exercise project skill discovery and loading in snapshot tests.\n</available_skills>\n\nIf the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.\n</system-reminder>"}],"source":{"kind":"plugin","plugin":"dsh-tool-skill"},"role":"user","id":"4f537803-7424-41eb-887f-f39676b89187"},"surfaceOp":"append"}
|
||||
{"type":"user/message","seq":3,"time":1784903324926,"data":{"content":[{"type":"text","text":"<system-reminder>\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n<available_skills>\n- `model-only-skill`: Prove user-disabled skills remain available to the model.\n- `snapshot-skill`: Exercise project skill discovery and loading in snapshot tests.\n</available_skills>\n\nIf the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.\n</system-reminder>"}],"source":{"kind":"plugin","plugin":"dsh-tool-skill"},"role":"user","id":"4f537803-7424-41eb-887f-f39676b89187"},"surfaceOp":"append"}
|
||||
{"type":"step/start","seq":4,"time":1784903324927,"data":{"turn":1,"step":1}}
|
||||
{"type":"request/header","seq":5,"time":1784903324928,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
|
||||
{"type":"assistant/chunk","seq":6,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
|
||||
|
||||
@@ -0,0 +1,7 @@
|
||||
---
|
||||
name: model-only-skill
|
||||
description: Prove user-disabled skills remain available to the model.
|
||||
user-invocable: false
|
||||
---
|
||||
|
||||
Follow these model-only snapshot instructions.
|
||||
@@ -0,0 +1,7 @@
|
||||
---
|
||||
name: user-only-skill
|
||||
description: Prove model-disabled skills stay outside the model catalog.
|
||||
disable-model-invocation: true
|
||||
---
|
||||
|
||||
Follow these user-only snapshot instructions.
|
||||
@@ -3,4 +3,4 @@
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write examples/cordis-agent/README.md
|
||||
README.md: 55970e932bc16d8361932daa9ea55af83ef73d33
|
||||
README.zh.md: c2873b6de96a8b47ad8ea4fb2cf03a7501406300
|
||||
README.zh.md: a8ec332d8b3673d6656663eb3bfd7d37a4e328f6
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
|
||||
[English](README.md) | 中文
|
||||
|
||||
自指 harness 演示:在全屏 TUI 上运行 DeepSeek V4 编码主干,并加载 [`@deepseek-ai/dsh-tool-cordis`](../../packages/cordis/tool-cordis/README.md)。后者让模型检查当前 DSH 进程、挂载仅存于内存的临时 Plugin,并再次卸载它们。临时 Plugin 可跨 turn 保持活跃,但会在卸载、工具集卸载或 DSH 重启后消失;它们不创建文件或配置,也可能影响同一进程中的其他 session。`ctx.fs` 和 `ctx.web` 是这些 Plugin 可用的 provider-only 能力。设计详见[工具集 Agent Note](../../.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md)。
|
||||
自指 harness 演示:在全屏 TUI 上运行 DeepSeek V4 编码主干,并加载 [`@deepseek-ai/dsh-tool-cordis`](../../packages/cordis/tool-cordis/README.md)。后者让模型检查当前 DSH 进程、挂载仅存于内存的临时插件,并卸载它们。临时插件可跨轮次保持活跃,但会在卸载、工具集卸载或 DSH 重启后消失;它们不创建文件或配置,也可能影响同一进程中的其他会话。`ctx.fs` 和 `ctx.web` 仅以能力提供方形式加载,供这些插件使用。设计详见[工具集 Agent Note(agent 决策记录)](../../.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md)。
|
||||
|
||||
## 运行
|
||||
|
||||
@@ -15,7 +15,7 @@ pnpm run demo:cordis web # browser UI at http://127.0.0.1:3081
|
||||
pnpm run demo:cordis acp # ACP server
|
||||
```
|
||||
|
||||
预期演示分阶段进行:先验证监听器链接,再让 agent 扩展自身:
|
||||
预期演示分阶段进行:先验证监听器链路,再让 agent(智能体)扩展自身:
|
||||
|
||||
```
|
||||
> Mount a temporary Plugin that listens to the 'agent/status' event and logs every status change, then run `echo hi` with bash.
|
||||
@@ -30,8 +30,8 @@ pnpm run demo:cordis acp # ACP server
|
||||
[tool call] cordis_unmount({"id": "dyn-1"})
|
||||
```
|
||||
|
||||
请求 `cordis_inspect` 并使用 `what: "api"` 或 `what: "events"`,即可查看编写 Plugin 代码所用的生成服务/事件资料。还可挂载两个协作临时 Plugin(一个中调用 `ctx.provide`,另一个中使用 `inject`),观察 Cordis 如何暂停并恢复消费方。
|
||||
请求 `cordis_inspect` 并使用 `what: "api"` 或 `what: "events"`,即可查看编写插件代码所用的生成服务/事件资料。还可挂载两个协作临时插件(一个中调用 `ctx.provide`,另一个中使用 `inject`),观察 Cordis 如何暂停并恢复消费方。
|
||||
|
||||
## 端到端测试
|
||||
|
||||
`tests/keyless-smoke.e2e.ts` 使用虚拟密钥通过 Loader 启动真实 `cordis.yml`,并断言横幅、包名解析和 EOF 后干净退出。`tests/cordis-tools.e2e.ts` 是带密钥的冒烟测试:真实模型挂载一个临时状态 listener,测试验证其带标记的 console 行;然后创建并使用 `reverse_text` 工具,再通过 provide/inject 组合两个临时 Plugin。[`packages/cordis/tool-cordis`](../../packages/cordis/tool-cordis) 在每文件 100% 覆盖率门禁下承载单元覆盖。
|
||||
`tests/keyless-smoke.e2e.ts` 使用虚拟密钥通过 Loader 启动真实 `cordis.yml`,并断言横幅、包名解析,以及收到 EOF 后正常退出。`tests/cordis-tools.e2e.ts` 是带密钥的冒烟测试:真实模型挂载一个临时状态监听器,测试验证其带标记的控制台输出行;然后创建并使用 `reverse_text` 工具,再通过 provide/inject 组合两个临时插件。[`packages/cordis/tool-cordis`](../../packages/cordis/tool-cordis) 包含相关单元测试,并受逐文件 100% 覆盖率门禁约束。
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
|
||||
# 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
|
||||
# pnpm run verify-translation-pairing --write examples/headless-agent/README.md
|
||||
README.md: 445804a2611e5e8093eadf345ad10a2a7984c012
|
||||
README.zh.md: 68ec718afe0b2aca276be2689cbae74167ee1c7b
|
||||
README.zh.md: 956bc82e77f79c3f05e4b51297fd5365e6e89be1
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
|
||||
[English](README.md) | 中文
|
||||
|
||||
无头单次 agent(智能体)接线:DeepSeek V4 + 本地 bash 与文件系统工具 + subagent 委托 + 工作流与新 agent Ralph 迭代 + `todo_write` + JSONL 持久化,并以 [`@deepseek-ai/dsh-cli-demo`](../../packages/examples/cli-demo) 作为应用入口。
|
||||
无头单次 agent(智能体)接线:DeepSeek V4 + 本地 bash 与文件系统工具 + subagent 委托 + 工作流与全新 agent Ralph 迭代 + `todo_write` + JSONL 持久化,并以 [`@deepseek-ai/dsh-cli-demo`](../../packages/examples/cli-demo) 作为应用入口。
|
||||
|
||||
## 运行
|
||||
|
||||
@@ -15,12 +15,12 @@ pnpm run demo:headless --output-format json -- "summarize the implementation"
|
||||
pnpm run demo:headless --output-format stream-json -- "run the focused tests"
|
||||
```
|
||||
|
||||
必须提供且只能提供一个非空位置任务;含空格的任务需要加引号。没有 `-p` 标志。`text` 打印最后一条包含文本的 assistant 消息,`json` 打印一条 DSH 原生结果记录,`stream-json` 则在该记录之前发出顶层会话的规范任务轮次事件。子会话只通过父工具事件和结果对外显示。
|
||||
必须提供一个且仅一个非空的任务位置参数;含空格的任务需要加引号。没有 `-p` 标志。`text` 打印最后一条包含文本的 assistant 消息,`json` 打印一条 DSH 原生结果记录,`stream-json` 则在该记录之前发出顶层会话的规范任务轮次事件。子会话只通过父会话的工具事件和结果对外显示。
|
||||
|
||||
每次调用都会创建并持久化新会话,在一个轮次中运行所有模型和工具步骤,然后刷新、释放并退出。这是非交互式自动化:没有提示符、批准、恢复、第二轮次或 stdin 上下文。已配置工具可以修改启动 workspace、运行命令、spawn 子 agent,并消耗提供方 token。
|
||||
每次调用都会创建并持久化新会话,在一个轮次中运行所有模型和工具步骤,然后刷写持久化数据、执行 dispose(资源释放),再退出。这是非交互式自动化:没有提示符、批准、恢复、第二轮次或 stdin 上下文。已配置工具可以修改启动时所在的工作区、运行命令、spawn 子 agent,并消耗提供方 token。
|
||||
|
||||
## 高级与快照接线
|
||||
|
||||
[`advanced.cordis.yml`](advanced.cordis.yml) 在已交付叶节点上添加 Code Mode 和 Cordis 工具。[`advanced.cordis.snapshot.yml`](advanced.cordis.snapshot.yml) 只将实时 LLM(大语言模型)替换为回放。[`tests/`](tests/) 下的测试拥有无密钥真实 Loader 冒烟测试、密钥门控的外部状态验证冒烟测试,以及带父子会话 fixture(测试前置数据)的 `stream-json` 回放快照。
|
||||
[`advanced.cordis.yml`](advanced.cordis.yml) 在已交付叶节点上添加 Code Mode 和 Cordis 工具。[`advanced.cordis.snapshot.yml`](advanced.cordis.snapshot.yml) 只将实时 LLM(大语言模型)替换为回放。[`tests/`](tests/) 下涵盖无密钥真实 Loader 冒烟测试、密钥门控的外部状态验证冒烟测试,以及带父子会话 fixture(测试前置数据)的 `stream-json` 回放快照。
|
||||
|
||||
包级 [CLI 契约](../../packages/examples/cli-demo/README.md)记录输出记录、退出状态、取消、持久化以及模型/token 影响。
|
||||
这份包(package)级 [CLI(命令行界面)契约](../../packages/examples/cli-demo/README.md) 说明输出记录、退出状态、取消、持久化以及模型/token 影响。
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
|
||||
# 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
|
||||
# pnpm run verify-translation-pairing --write examples/jsonrpc-agent/README.md
|
||||
README.md: 6ee4e9d824315bde76b7a534679f018df9a6d3e8
|
||||
README.zh.md: dc9b6233e7074e7a9b13bf10bcd2f310b0ad7bf3
|
||||
README.zh.md: 43290fc3659750724679a370be5b33ffdca2a5cb
|
||||
|
||||
@@ -2,16 +2,16 @@
|
||||
|
||||
[English](README.md) | 中文
|
||||
|
||||
面向 Python SDK 内置 JSON-RPC 运行时的无人值守编码 agent(智能体)组合。它有意不加载终端 UI、console logger、批准界面或用户交互工具,因为 stdout 属于 SDK 协议,轮次由 SDK 驱动。
|
||||
面向 Python SDK 内置 JSON-RPC 运行时的无人值守编码 agent(智能体)组合。它有意不加载终端 UI、控制台日志记录器、批准界面或用户交互工具,因为 stdout 属于 SDK 协议,轮次由 SDK 驱动。
|
||||
|
||||
面向模型的工具为:
|
||||
|
||||
- `bash`,仅前台
|
||||
- `read`、`write` 和 `edit`
|
||||
- `subagent`,使用一个前台进程内 spawn 提供方
|
||||
- `subagent`,使用一个在进程内以前台方式运行的 spawn 提供方
|
||||
- `todo_write`
|
||||
|
||||
周边运行时还加载 JSONL 会话持久化和自动上下文压缩(compaction)。`maxTokensAsSuccess` 将受 token 上限限制的模型轮次保留为已接受的评估结果,同时保留其 `max-tokens` 原因。
|
||||
周边运行时还加载 JSONL 会话持久化和自动上下文压缩(context compaction)。`maxTokensAsSuccess` 将受 token 上限限制的模型轮次保留为已接受的评估结果,同时保留其 `max-tokens` 原因。
|
||||
|
||||
## 运行时环境
|
||||
|
||||
@@ -24,4 +24,4 @@
|
||||
| `DSH_SESSION_ROOT` | JSONL 轨迹目录 |
|
||||
| `DSH_SYSTEM_PROMPT` | 由部署提供的编码人格 |
|
||||
|
||||
通过 Python SDK 的 `cordis` 选项或 `DSH_CORDIS_CONFIG` 传入配置路径。内置可执行文件已携带此文件命名的每个插件;目标机器无需 Node.js。
|
||||
通过 Python SDK 的 `cordis` 选项或 `DSH_CORDIS_CONFIG` 传入配置路径。内置可执行文件已携带此文件中指定的每个插件;目标机器无需 Node.js。
|
||||
|
||||
@@ -3,4 +3,4 @@
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write examples/tui-agent/README.md
|
||||
README.md: ea8695d37ea247a38644392a4572c1ea9855fd44
|
||||
README.zh.md: b3f6dc18536b159379eac7433367ccf2cd8fcc53
|
||||
README.zh.md: c6acd39d8713816d870c00fa8597754d0d09880a
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
|
||||
[English](README.md) | 中文
|
||||
|
||||
全屏交互式编码 agent(智能体):DeepSeek V4、本地 bash 与文件系统工具、压缩(compaction)、subagent、工作流与新 agent Ralph 迭代、plan mode(`/plan` 进入,`exit_plan_mode` 评审退出)、超时/溢出策略,以及通过 [`@deepseek-ai/dsh-tui-demo`](../../packages/examples/tui-demo) 提供的 JSONL 持久化;该应用从 `cordis.yml` 加载。同级 [`headless-agent`](../headless-agent/README.md) 以适合单次管道的任务形式运行同一能力类,[`acp-agent`](../acp-agent/README.md) 则通过 JSON-RPC 提供该能力。
|
||||
全屏交互式编码 agent(智能体):DeepSeek V4、本地 bash 与文件系统工具、压缩(compaction)、subagent、工作流与全新 agent Ralph 迭代、plan mode(`/plan` 进入,`exit_plan_mode` 评审退出)、超时/溢出策略,以及通过 [`@deepseek-ai/dsh-tui-demo`](../../packages/examples/tui-demo) 提供的 JSONL 持久化;该应用从 `cordis.yml` 加载。同级 [`headless-agent`](../headless-agent/README.md) 以适合管道调用的单次任务形式运行同一能力类,[`acp-agent`](../acp-agent/README.md) 则通过 JSON-RPC 提供该能力。
|
||||
|
||||
## 运行
|
||||
|
||||
@@ -13,13 +13,13 @@
|
||||
pnpm run demo:tui
|
||||
```
|
||||
|
||||
演示脚本和可安装的 `dsh` CLI([`apps/cli`](../../apps/cli/README.md))都会作为已交付的默认配置启动此示例的 `cordis.yml`;`dsh` 还会应用 `~/.dsh` 中的个人覆盖,并将调用目录作为 workspace。
|
||||
演示脚本和可安装的 `dsh` CLI(命令行界面,见 [`apps/cli`](../../apps/cli/README.md))都会以此示例的 `cordis.yml` 作为已交付的默认配置启动;`dsh` 还会应用 `~/.dsh` 中的个人覆盖,并将调用目录作为工作区。
|
||||
|
||||
输入一项编码任务。agent 使用 `read`/`write`/`edit` 文件系统工具处理常规文件操作,使用 `bash`(加上面向后台任务的通用 `task_output`/`task_list`/`task_kill`)执行 shell 命令、搜索和测试。每次操作都在新的 `bash -c` 中运行(系统提示词要求模型传递 `workdir`,而不是使用 `cd`)。fs 工具和 bash 都会根据会话 workspace 解析相对路径。agent 还可以通过 `subagent`/`subagent_fork` 委托。
|
||||
输入一项编码任务。agent 使用 `read`/`write`/`edit` 文件系统工具处理常规文件操作,使用 `bash`(加上面向后台任务的通用 `task_output`/`task_list`/`task_kill`)执行 shell 命令、搜索和测试。每次 bash 调用都在新的 `bash -c` 中运行(系统提示词要求模型传递 `workdir`,而不是使用 `cd`)。文件系统工具和 bash 都会相对于会话工作区解析相对路径。agent 还可以通过 `subagent`/`subagent_fork` 委托。
|
||||
|
||||
`todo_write` 任务跟踪器是选用的,不在已交付配置中:请将 `@deepseek-ai/dsh-tool-todo` 添加到 `cordis.yml`(或在 `~/.dsh` 下使用个人配置覆盖)以公开该工具。加载后,模型会把整表计划记录到会话日志,TUI 则渲染它。
|
||||
|
||||
TUI 渲染 Markdown 历史、推理、工具所有的终端/diff/通用卡片、token 总量,以及加载 `todo_write` 时的最新计划。较长的工具正文保留首尾预览;Ctrl+O 展开或折叠所有卡片。Enter 用于提交,或在 agent 运行时进行 steering(中途引导);Ctrl+R 切换推理,Escape 取消,`/help` 列出命令。`/plan` 为下一步骤选择 plan mode;`/plan <message>` 还会将消息提交到该步骤,`/plan off` 则在没有模型输入的情况下选择默认 mode。`/status` 会展开当前会话的标识、活动计数、精确 token/缓存 bucket、上下文用量和时间戳,而不中断正在运行的轮次。`/model` 打开当前提供方目录的键盘选择器;使用 Up/Down 聚焦模型,使用 Shift+Tab 循环切换为该模型公布的推理强度,再用 Enter 选择;也可以使用 `/model <model>` 和 `/model <provider>/<model>` 直接选择。`ask_user_question` 会打开一个位于左下方的宽键盘面板,包含批次进度和编号选项。
|
||||
TUI 渲染 Markdown 历史、推理(reasoning)、工具自有的终端/diff/通用卡片、token 总量,以及加载 `todo_write` 时的最新计划。较长的工具正文保留首尾预览;Ctrl+O 展开或折叠所有卡片。Enter 用于提交,或在 agent 运行时进行 steering(中途引导);Ctrl+R 切换推理,Escape 取消,`/help` 列出命令。`/plan` 为下一步骤选择 plan mode;`/plan <message>` 还会将消息提交到该步骤,`/plan off` 则在没有模型输入的情况下选择默认 mode。`/status` 会展开当前会话的标识、活动计数、精确 token/缓存 bucket、上下文用量和时间戳,而不中断正在运行的轮次。`/model` 打开当前提供方目录的键盘选择器;使用 Up/Down 聚焦模型,使用 Shift+Tab 循环切换为该模型公布的推理强度,再用 Enter 选择;也可以使用 `/model <model>` 和 `/model <provider>/<model>` 直接选择。`ask_user_question` 会打开一个位于左下方的宽键盘面板,包含批次进度和编号选项。
|
||||
|
||||
### 恢复早先的会话
|
||||
|
||||
@@ -29,11 +29,11 @@ TUI 渲染 Markdown 历史、推理、工具所有的终端/diff/通用卡
|
||||
dsh --resume <prior-session-id>
|
||||
```
|
||||
|
||||
`/resume` 打开可搜索键盘选择器,显示标题、活动、上一轮结果、模型路由、持久 goal 阶段和实时/已持久化状态。已安装的 `dsh` 宿主会刷新并释放当前应用,然后以 `dsh --resume <id>` 替换进程。TUI 仍会在退出时打印该命令,并在自定义宿主无法移交时显示它。`dsh --resume <id>` 在启动上下文中提供 id,`cordis.yml` 会读取它(`resumeSessionId: !!js "typeof resumeSessionId === 'string' ? resumeSessionId : undefined"`);没有标志时,agent 会开始新会话。缺失或无法读取的 id 不会启动 agent,而会发出 `agent-loop/config-start-failed`:TUI 打印失败并以非零状态退出。选择器没有跨进程会话锁,因此拥有并发宿主的部署必须自行协调会话所有权。
|
||||
`/resume` 打开可搜索键盘选择器,显示标题、活动、上一轮结果、模型路由、持久化目标阶段和实时/已持久化状态。已安装的 `dsh` 宿主会等待刷写完成,对当前应用执行 dispose(资源释放),然后以 `dsh --resume <id>` 替换进程。TUI 仍会在退出时打印该命令,并在自定义宿主无法移交时显示它。`dsh --resume <id>` 在启动上下文中提供 id,`cordis.yml` 会读取它(`resumeSessionId: !!js "typeof resumeSessionId === 'string' ? resumeSessionId : undefined"`);没有标志时,agent 会开始新会话。缺失或无法读取的 id 不会启动 agent,而会发出 `agent-loop/config-start-failed`:TUI 打印失败并以非零状态退出。选择器没有跨进程会话锁,因此拥有并发宿主的部署必须自行协调会话所有权。
|
||||
|
||||
## Code Mode
|
||||
|
||||
[`code-mode.cordis.yml`](code-mode.cordis.yml) 在同一树上覆盖 worker 线程运行时和 `tools: { mode: code }`。模型会收到一个 `run_code` 传输工具,加上一份为可见工具生成的 TypeScript SDK;只有程序输出会返回模型上下文。使用 `mode: both` 可在 `run_code` 旁同时公开原生调用。执行契约详见 [Code Mode Agent Note](../../.agents/notes/implemented/feature/2026-06-15-code-mode.md)。
|
||||
[`code-mode.cordis.yml`](code-mode.cordis.yml) 在同一树上覆盖 worker 线程运行时和 `tools: { mode: code }`。模型会收到一个 `run_code` 传输工具,加上一份为可见工具生成的 TypeScript SDK;只有程序输出会返回模型上下文。使用 `mode: both` 可在 `run_code` 旁同时公开原生调用。执行契约详见 [Code Mode Agent Note(agent 决策记录)](../../.agents/notes/implemented/feature/2026-06-15-code-mode.md)。
|
||||
|
||||
```sh
|
||||
pnpm run demo:code-mode # this overlay under the TUI (default UI)
|
||||
@@ -54,27 +54,27 @@ pnpm run demo:code-mode acp # the acp-agent example's same-shaped overlay
|
||||
|---|---|
|
||||
| `hmr` (`@cordisjs/plugin-hmr`) | 开发/演示的编辑-重载循环:它是 **叶节点** 配置项(不内置到应用),因为它依赖 Loader 的内部模块访问 |
|
||||
| `llm-deepseek` | 默认原生适配器 |
|
||||
| `bash` (`dsh-bash-local`) | 执行器实现:bash seam 的可替换一半。面向模型的 `bash` schema(`tool-bash`)和通用 `task_*` 控制(`tool-tasks`)由 `dsh-agent-spine-demo` 提供,因此叶节点只选择执行器 |
|
||||
| `bash` (`dsh-bash-local`) | 执行器实现:bash seam 中可替换的实现侧。面向模型的 `bash` schema(`tool-bash`)和通用 `task_*` 控制(`tool-tasks`)由 `dsh-agent-spine-demo` 提供,因此叶节点只选择执行器 |
|
||||
| `tui-agent` (`@deepseek-ai/dsh-tui-demo`) | 应用组合包:agent-spine 演示 + JSONL 持久化 + pi-tui 通道 + 预创建的 `main` agent |
|
||||
| `subagent`, `subagent-spawn`, `subagent-fork` | subagent 提供方注册表加两个进程内后端:新子 agent,以及用父 agent 已完成轮次前缀播种的子 agent |
|
||||
| `tool-subagent`, `tool-subagent-fork` | 两次面向模型的 `dsh-tool-subagent` 加载,每次绑定不同提供方,并以不同工具名(`subagent`、`subagent_fork`)公开 |
|
||||
| `workflow-workerthread`, `tool-workflow` | worker 线程工作流引擎及其面向模型的 `workflow` 工具,子调用通过 spawn 后端路由 |
|
||||
| `plan-mode` | 插件拥有的 `/plan [message]` 进入命令和 `/plan off` 退出命令、plan-mode 提示词策略、工具限制,以及经评审的 `exit_plan_mode` 转换 |
|
||||
| `fs-local`, `fs-policy`, `tool-fs` | 文件系统栈:本地 `ctx.fs` 提供方、先读后写/编辑策略门禁(位于 `fs/*` 事件门禁),以及面向模型的 `read`/`write`/`edit` 工具。相对路径根据会话 workspace 解析 |
|
||||
| `fs-local`, `fs-policy`, `tool-fs` | 文件系统栈:本地 `ctx.fs` 提供方、先读后写/编辑策略门禁(位于 `fs/*` 事件门禁),以及面向模型的 `read`/`write`/`edit` 工具。相对路径相对于会话工作区解析 |
|
||||
|
||||
## 端到端测试(`pnpm run test:e2e`)
|
||||
|
||||
与 UI 无关的带密钥套件通过 `tests/harness.ts` 以程序方式组装完整栈(无 PTY、无 Loader):
|
||||
|
||||
- `tests/full-loop.e2e.ts`:canary 测试:真实模型通过真实 bash 工具运行 `echo e2e-ok`;断言 `tool/call`/`tool/result` 会话事件和最终答案。
|
||||
- `tests/coding-task.e2e.ts`:类 swebench 冒烟测试:临时目录包含 `add.js`(其中 `a - b` 写在本应是 `a + b` 的位置)和失败的 `add.test.js`;agent 必须修复错误并验证。测试会自行重新运行 `node add.test.js` 并检查文件,不信任 agent 的声称。
|
||||
- `tests/resume.e2e.ts`:跨进程持久连续性:第一次运行告诉真实模型一个密码并将轮次持久化到临时 JSONL 根目录,然后释放整个上下文;第二次运行在同一根目录上创建新上下文,恢复会话 id 并要求模型回忆密码。只有重新水化的日志能够提供该回忆。
|
||||
- `tests/compaction.e2e.ts`:压缩冒烟测试:一项真实多步 bash 任务在故意设得很小的上下文窗口中运行,使自动压缩监听器在会话中途触发。测试验证外部状态:真实日志中出现 `compact/start…end` 对,表层缩减(替换节点遮蔽旧节点),且 agent 在压缩后仍给出正确最终答案。
|
||||
- `tests/todo-write.e2e.ts`:加载选用 `todo_write` 工具,由真实模型驱动,测试验证产生的 `todo/write` 会话事件。
|
||||
- `tests/code-mode.e2e.ts`:带密钥 Code Mode 证明:使用真实模型和双工具任务,断言线上工具列表精确为 `[run_code]`,`tool/code-dispatch` 事件位于父调用下,且筛选后的答案已返回。
|
||||
- `tests/coding-task.e2e.ts`:类 swebench 冒烟测试:临时目录包含 `add.js`(其中 `a - b` 写在本应是 `a + b` 的位置)和失败的 `add.test.js`;agent 必须修复错误并验证。测试会自行重新运行 `node add.test.js` 并检查文件,不信任 agent 的说法。
|
||||
- `tests/resume.e2e.ts`:跨进程持久连续性:第一次运行告诉真实模型一个密码并将轮次持久化到临时 JSONL 根目录,然后 dispose 整个上下文;第二次运行在同一根目录上创建新上下文,恢复会话 id 并要求模型回忆密码。只有重新水化的日志能够提供该回忆。
|
||||
- `tests/compaction.e2e.ts`:压缩冒烟测试:一项真实多步 bash 任务在故意设得很小的上下文窗口中运行,使自动压缩监听器在会话中途触发。测试验证外部状态:真实日志中出现 `compact/start…end` 对,模型可见内容缩减(一个替换节点遮蔽了较旧节点),且 agent 在压缩后仍给出正确最终答案。
|
||||
- `tests/todo-write.e2e.ts`:加载选用的 `todo_write` 工具,由真实模型驱动,测试验证产生的 `todo/write` 会话事件。
|
||||
- `tests/code-mode.e2e.ts`:带密钥 Code Mode 证明:使用真实模型和双工具任务,断言协议层工具列表精确为 `[run_code]`,`tool/code-dispatch` 事件位于父调用下,且筛选后的答案已返回。
|
||||
|
||||
这些测试在没有 `DEEPSEEK_API_KEY` 时自行跳过。无密钥 `tests/tui-keyless-smoke.e2e.ts` 通过 PTY 启动真实 Loader 树(唯一获准的 PTY 界面):基础启动 + `/plan` + `/exit`,一次带问题对话框和工具往返的脚本 LLM 对话,Code Mode 覆盖欢迎行,以及恢复失败退出路径。
|
||||
这些测试在没有 `DEEPSEEK_API_KEY` 时自行跳过。无密钥 `tests/tui-keyless-smoke.e2e.ts` 通过 PTY 启动真实 Loader 树(唯一获准的 PTY 界面):基础启动 + `/plan` + `/exit`,一次带问题对话框和工具往返的脚本 LLM(大语言模型)对话,Code Mode 覆盖配置的欢迎行,以及恢复失败退出路径。
|
||||
|
||||
## 快照测试
|
||||
|
||||
`tests/snapshots/<scenario>/session.jsonl` 提供已录制的用户提示词和模型分片;同级子日志驱动 subagent 和工作流。无密钥套件通过真实循环和工具实现执行这些脚本,然后比较可读的预期终端单元格/样式输出。使用 `pnpm run test:snapshot:refresh` 刷新仅展示变更;已录制模型旅程改变时,使用 DeepSeek 密钥运行 `pnpm run test:snapshot:record`。已实现的 [TUI 快照 Agent Note](../../.agents/notes/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md) 拥有场景矩阵,以及已录制旅程、瞬时包快照与 PTY 覆盖之间的分工。
|
||||
`tests/snapshots/<scenario>/session.jsonl` 提供已录制的用户提示词和模型分片;同级子日志驱动 subagent 和工作流。无密钥套件通过真实循环和工具实现执行这些脚本,然后比较可读的预期终端单元格/样式输出。对于仅涉及展示的变更,使用 `pnpm run test:snapshot:refresh`;已录制的模型流程改变时,使用 DeepSeek 密钥运行 `pnpm run test:snapshot:record`。已实现的 [TUI 快照 Agent Note](../../.agents/notes/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md) 规定了场景矩阵,以及已录制旅程、包级瞬态快照与 PTY 覆盖之间的分工。
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
import { mkdirSync, writeFileSync } from 'node:fs'
|
||||
import { mkdtemp, rm } from 'node:fs/promises'
|
||||
import { tmpdir } from 'node:os'
|
||||
import { join } from 'node:path'
|
||||
import { dirname, join } from 'node:path'
|
||||
import { execa } from 'execa'
|
||||
import { resolveExampleLaunch, type ExampleLaunch } from '@deepseek-ai/dsh-loader-smoke'
|
||||
|
||||
@@ -36,7 +37,16 @@ while time.monotonic() < deadline:
|
||||
if chunk:
|
||||
output.extend(chunk)
|
||||
while action_index < len(actions) and actions[action_index]["waitFor"].encode() in output:
|
||||
os.write(fd, actions[action_index]["send"].encode())
|
||||
action = actions[action_index]
|
||||
if "writeFile" in action:
|
||||
target = os.path.join(cwd, action["writeFile"]["path"])
|
||||
os.makedirs(os.path.dirname(target), exist_ok=True)
|
||||
with open(target, "w", encoding="utf-8") as handle:
|
||||
handle.write(action["writeFile"]["content"])
|
||||
if "send" in action:
|
||||
os.write(fd, action["send"].encode())
|
||||
else:
|
||||
os.write(fd, action["send"].encode())
|
||||
action_index += 1
|
||||
waited, candidate = os.waitpid(pid, os.WNOHANG)
|
||||
if waited == pid:
|
||||
@@ -56,11 +66,14 @@ if actual_exit != int(expected_exit):
|
||||
sys.exit(125)
|
||||
`
|
||||
|
||||
/** One terminal action sent after its marker has rendered. */
|
||||
interface TuiPtyAction {
|
||||
readonly waitFor: string
|
||||
readonly send: string
|
||||
}
|
||||
/** One terminal input or workspace mutation performed after its marker renders. */
|
||||
type TuiPtyAction =
|
||||
| { readonly waitFor: string; readonly send: string }
|
||||
| {
|
||||
readonly waitFor: string
|
||||
readonly writeFile: { readonly path: string; readonly content: string }
|
||||
readonly send?: string
|
||||
}
|
||||
|
||||
/** Inputs for a keyless real-Loader TUI process smoke. */
|
||||
export interface TuiPtySmokeOptions {
|
||||
@@ -157,7 +170,16 @@ async function runWindowsPtySmoke(
|
||||
terminal.onData((chunk) => {
|
||||
output += chunk
|
||||
while (actionIndex < actions.length && output.includes(actions[actionIndex]!.waitFor)) {
|
||||
terminal.write(actions[actionIndex]!.send)
|
||||
const action = actions[actionIndex]!
|
||||
if ('writeFile' in action) {
|
||||
const target = join(cwd, action.writeFile.path)
|
||||
mkdirSync(dirname(target), { recursive: true })
|
||||
writeFileSync(target, action.writeFile.content)
|
||||
const input = action.send
|
||||
if (input !== undefined) terminal.write(input)
|
||||
} else {
|
||||
terminal.write(action.send)
|
||||
}
|
||||
actionIndex += 1
|
||||
}
|
||||
})
|
||||
|
||||
@@ -0,0 +1,5 @@
|
||||
{"type":"session","version":0,"id":"31f63cc0-0198-4ab2-bfde-79a4eb4f1867","createdAt":1783352180000,"cwd":"{{cwd}}","delegationDepth":0}
|
||||
{"type":"assistant/chunk","seq":0,"time":1783352180001,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
|
||||
{"type":"assistant/chunk","seq":1,"time":1783352180002,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"USER-ONLY SKILL LOADED"}}}
|
||||
{"type":"assistant/chunk","seq":2,"time":1783352180003,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"USER-ONLY SKILL LOADED"}}}}
|
||||
{"type":"assistant/chunk","seq":3,"time":1783352180004,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
|
||||
@@ -0,0 +1,157 @@
|
||||
=== skill autocomplete ===
|
||||
terminal 100x36 buffer=normal length=36 base=0 viewport=0
|
||||
lifecycle started=1 stopped=0 progress=inactive
|
||||
title "DSH TUI snapshot"
|
||||
cursor hidden column=13 viewportRow=5 bufferRow=5
|
||||
buffer
|
||||
0| " DEEPSEEK HARNESS"
|
||||
style 1-8 fg=bright-magenta bold
|
||||
style 10-16 bold
|
||||
1| " Recorded replay: skill-invocation-policy"
|
||||
style 1-40 dim
|
||||
2| " main-session"
|
||||
style 1-12 dim
|
||||
3| <blank>
|
||||
4| "/workspace/project deepseek-v4-flash ↑0 ↓0 0% context"
|
||||
style 0-51 fg=bright-magenta bold
|
||||
style 54-70 dim
|
||||
style 73-77 dim
|
||||
style 80-89 dim
|
||||
5| " dsh > /skill "
|
||||
style 1-3 fg=bright-magenta bold
|
||||
style 5-6 dim
|
||||
style 13-13 inverse
|
||||
6| " → skill:user-only-skill (project) — User-only assembled snapshot skill. "
|
||||
style 7-78 fg=bright-magenta
|
||||
7-35| <blank>
|
||||
|
||||
|
||||
=== loaded exact invocation ===
|
||||
terminal 100x36 buffer=normal length=36 base=0 viewport=0
|
||||
lifecycle started=1 stopped=0 progress=inactive
|
||||
title "<skill name=\"user-only-skill\"> Reference — DSH TUI snapshot"
|
||||
cursor hidden column=7 viewportRow=30 bufferRow=30
|
||||
buffer
|
||||
0| " DEEPSEEK HARNESS"
|
||||
style 1-8 fg=bright-magenta bold
|
||||
style 10-16 bold
|
||||
1| " <skill name=\"user-only-skill\"> Reference"
|
||||
style 1-40 dim
|
||||
2| " main-session"
|
||||
style 1-12 dim
|
||||
3| <blank>
|
||||
4| "You "
|
||||
style 0-2 fg=bright-magenta bold underline
|
||||
5| "<skill name=\"user-only-skill\"> "
|
||||
6| "References in this skill are relative to "
|
||||
7| "/workspace/project/.agents/skills/user-only-skill. "
|
||||
8| " "
|
||||
9| "USER-ONLY BODY "
|
||||
10| "</skill> "
|
||||
11| <blank>
|
||||
12| "Context · dsh-tool-skill"
|
||||
style 0-23 dim
|
||||
13| "A skill is a reusable set of task-specific instructions. The following skills are available in this "
|
||||
style 0-99 dim
|
||||
14| "session: "
|
||||
style 0-7 dim
|
||||
15| " "
|
||||
16| "<available_skills> "
|
||||
style 0-17 dim
|
||||
17| "- `model-only-skill`: Model-only assembled snapshot skill. "
|
||||
style 0-57 dim
|
||||
18| "</available_skills> "
|
||||
style 0-18 dim
|
||||
19| " "
|
||||
20| "If the user names a skill, or the task clearly matches a skill's description, call the `skill` tool "
|
||||
style 0-99 dim
|
||||
21| "with the exact skill name before taking task actions. Load all applicable skills, then follow their "
|
||||
style 0-99 dim
|
||||
22| "full instructions. This catalog contains summaries only; do not infer or follow a skill's "
|
||||
style 0-99 dim
|
||||
23| "instructions until it has been loaded. "
|
||||
style 0-37 dim
|
||||
24| <blank>
|
||||
25| "Assistant "
|
||||
style 0-8 fg=bright-magenta bold underline
|
||||
26| "USER-ONLY SKILL LOADED "
|
||||
27| "Model wait 0.0s · Completed 2026-07-21 12:00:00 "
|
||||
style 0-46 dim
|
||||
28| <blank>
|
||||
29| "/workspace/project deepseek-v4-flash ↑0 ↓0 3% context"
|
||||
style 0-51 fg=bright-magenta bold
|
||||
style 54-70 dim
|
||||
style 73-77 dim
|
||||
style 80-89 dim
|
||||
30| " dsh ◍ "
|
||||
style 1-3 fg=bright-magenta bold
|
||||
style 5-6 dim
|
||||
style 7-7 inverse
|
||||
31-35| <blank>
|
||||
|
||||
|
||||
=== denied exact invocation ===
|
||||
terminal 100x36 buffer=normal length=36 base=0 viewport=0
|
||||
lifecycle started=1 stopped=0 progress=inactive
|
||||
title "<skill name=\"user-only-skill\"> Reference — DSH TUI snapshot"
|
||||
cursor hidden column=7 viewportRow=32 bufferRow=32
|
||||
buffer
|
||||
0| " DEEPSEEK HARNESS"
|
||||
style 1-8 fg=bright-magenta bold
|
||||
style 10-16 bold
|
||||
1| " <skill name=\"user-only-skill\"> Reference"
|
||||
style 1-40 dim
|
||||
2| " main-session"
|
||||
style 1-12 dim
|
||||
3| <blank>
|
||||
4| "You "
|
||||
style 0-2 fg=bright-magenta bold underline
|
||||
5| "<skill name=\"user-only-skill\"> "
|
||||
6| "References in this skill are relative to "
|
||||
7| "/workspace/project/.agents/skills/user-only-skill. "
|
||||
8| " "
|
||||
9| "USER-ONLY BODY "
|
||||
10| "</skill> "
|
||||
11| <blank>
|
||||
12| "Context · dsh-tool-skill"
|
||||
style 0-23 dim
|
||||
13| "A skill is a reusable set of task-specific instructions. The following skills are available in this "
|
||||
style 0-99 dim
|
||||
14| "session: "
|
||||
style 0-7 dim
|
||||
15| " "
|
||||
16| "<available_skills> "
|
||||
style 0-17 dim
|
||||
17| "- `model-only-skill`: Model-only assembled snapshot skill. "
|
||||
style 0-57 dim
|
||||
18| "</available_skills> "
|
||||
style 0-18 dim
|
||||
19| " "
|
||||
20| "If the user names a skill, or the task clearly matches a skill's description, call the `skill` tool "
|
||||
style 0-99 dim
|
||||
21| "with the exact skill name before taking task actions. Load all applicable skills, then follow their "
|
||||
style 0-99 dim
|
||||
22| "full instructions. This catalog contains summaries only; do not infer or follow a skill's "
|
||||
style 0-99 dim
|
||||
23| "instructions until it has been loaded. "
|
||||
style 0-37 dim
|
||||
24| <blank>
|
||||
25| "Assistant "
|
||||
style 0-8 fg=bright-magenta bold underline
|
||||
26| "USER-ONLY SKILL LOADED "
|
||||
27| "Model wait 0.0s · Completed 2026-07-21 12:00:00 "
|
||||
style 0-46 dim
|
||||
28| <blank>
|
||||
29| "Skill \"model-only-skill\" is not available for user invocation. "
|
||||
style 0-61 fg=yellow
|
||||
30| <blank>
|
||||
31| "/workspace/project deepseek-v4-flash ↑0 ↓0 3% context"
|
||||
style 0-51 fg=bright-magenta bold
|
||||
style 54-70 dim
|
||||
style 73-77 dim
|
||||
style 80-89 dim
|
||||
32| " dsh ◍ "
|
||||
style 1-3 fg=bright-magenta bold
|
||||
style 5-6 dim
|
||||
style 7-7 inverse
|
||||
33-35| <blank>
|
||||
@@ -0,0 +1,7 @@
|
||||
---
|
||||
name: model-only-skill
|
||||
description: Model-only assembled snapshot skill.
|
||||
user-invocable: false
|
||||
---
|
||||
|
||||
MODEL-ONLY BODY MUST NOT LOAD
|
||||
@@ -0,0 +1,7 @@
|
||||
---
|
||||
name: user-only-skill
|
||||
description: User-only assembled snapshot skill.
|
||||
disable-model-invocation: true
|
||||
---
|
||||
|
||||
USER-ONLY BODY
|
||||
@@ -217,11 +217,12 @@ describe('tui-agent keyless smoke (real Loader tree in a PTY)', () => {
|
||||
}, LOADER_SMOKE_TEST_TIMEOUT_MS)
|
||||
|
||||
it('loads a local skill via /skill: and delivers its body to the model as a user turn', async () => {
|
||||
// The whole manual-invocation path in one keyless boot: `ctx.get('skills')`
|
||||
// The whole user-only invocation path in one keyless boot: `ctx.get('skills')`
|
||||
// resolves in the shipped tree, the client-side `/skill:` command parses,
|
||||
// the local provider loads `scripted-skill` from the agents home, and the
|
||||
// rendered `<skill name="…">` block reaches the model — proven by the
|
||||
// scripted adapter echoing the fixture's body marker only when it arrives.
|
||||
// and the local provider admits a model-disabled skill by the omitted
|
||||
// `user-invocable` default. The rendered `<skill name="…">` block reaches
|
||||
// the model — proven by the scripted adapter echoing the fixture's body
|
||||
// marker only when it arrives.
|
||||
const output = await smoke({
|
||||
label: 'tui-agent skill',
|
||||
tempDirPrefix: 'tui-agent-skill-',
|
||||
@@ -232,6 +233,7 @@ describe('tui-agent keyless smoke (real Loader tree in a PTY)', () => {
|
||||
'---',
|
||||
'name: scripted-skill',
|
||||
'description: Keyless PTY proof that the skill command loads a local skill into the conversation.',
|
||||
'disable-model-invocation: true',
|
||||
'---',
|
||||
'',
|
||||
'SCRIPTED SKILL BODY MARKER',
|
||||
@@ -250,6 +252,36 @@ describe('tui-agent keyless smoke (real Loader tree in a PTY)', () => {
|
||||
expect(output).toContain('\u001B[?2004l')
|
||||
}, LOADER_SMOKE_TEST_TIMEOUT_MS)
|
||||
|
||||
it('adds a watched local skill to live /skill: autocomplete without restarting', async () => {
|
||||
const skill = [
|
||||
'---',
|
||||
'name: hot-added-skill',
|
||||
'description: HOT_ADDED_COMPLETION_MARKER',
|
||||
'---',
|
||||
'',
|
||||
'Hot-added body.',
|
||||
'',
|
||||
].join('\n')
|
||||
const output = await smoke({
|
||||
label: 'tui-agent hot-added skill autocomplete',
|
||||
tempDirPrefix: 'tui-agent-hot-skill-',
|
||||
configPath: scriptedConfigPath,
|
||||
actions: [
|
||||
{
|
||||
waitFor: 'scripted TUI ready.',
|
||||
writeFile: {
|
||||
path: '.agents/skills/hot-added-skill/SKILL.md',
|
||||
content: skill,
|
||||
},
|
||||
send: '/skill:hot',
|
||||
},
|
||||
{ waitFor: 'HOT_ADDED_COMPLETION_MARKER', send: '\x03/exit\r' },
|
||||
],
|
||||
})
|
||||
expect(output).toContain('HOT_ADDED_COMPLETION_MARKER')
|
||||
expect(output).toContain('\u001B[?2004l')
|
||||
}, LOADER_SMOKE_TEST_TIMEOUT_MS)
|
||||
|
||||
it('fuzzy-completes an @file path without reading or submitting the file', async () => {
|
||||
const output = await smoke({
|
||||
label: 'tui-agent file autocomplete',
|
||||
|
||||
@@ -41,6 +41,7 @@ const UUID_RE = /[0-9a-f]{8}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{12}/gi
|
||||
|
||||
type SnapshotMode = 'replay' | 'record' | 'refresh'
|
||||
type Composition = 'native' | 'code' | 'advanced'
|
||||
type ScenarioInteraction = 'skill-invocation-policy'
|
||||
|
||||
interface Scenario {
|
||||
name: string
|
||||
@@ -65,6 +66,8 @@ interface Scenario {
|
||||
* preview + locator while the program value stays whole.
|
||||
*/
|
||||
spillMaxInlineBytes?: number
|
||||
/** Run scenario-specific terminal input instead of replaying recorded user prompts. */
|
||||
interaction?: ScenarioInteraction
|
||||
}
|
||||
|
||||
const SCENARIOS: Scenario[] = [
|
||||
@@ -98,6 +101,14 @@ const SCENARIOS: Scenario[] = [
|
||||
recorded: true,
|
||||
seedWorkspace: true,
|
||||
},
|
||||
{
|
||||
name: 'skill-invocation-policy',
|
||||
composition: 'native',
|
||||
expectedTools: [],
|
||||
recorded: false,
|
||||
seedWorkspace: true,
|
||||
interaction: 'skill-invocation-policy',
|
||||
},
|
||||
{
|
||||
name: 'code-mode',
|
||||
composition: 'code',
|
||||
@@ -269,9 +280,10 @@ async function runScenario(scenario: Scenario): Promise<ScenarioResult> {
|
||||
const dir = scenarioDir(scenario)
|
||||
const fixtureFile = join(dir, 'session.jsonl')
|
||||
const childFiles = childFixturePaths(scenario)
|
||||
const fixture = await readFile(fixtureFile, 'utf8')
|
||||
const prompts = userPrompts(fixture)
|
||||
expect(prompts.length, `${scenario.name} must carry at least one recorded user prompt`).toBeGreaterThan(0)
|
||||
const prompts = userPrompts(await readFile(fixtureFile, 'utf8'))
|
||||
if (scenario.interaction === undefined) {
|
||||
expect(prompts.length, `${scenario.name} must carry at least one recorded user prompt`).toBeGreaterThan(0)
|
||||
}
|
||||
|
||||
const cwd = await mkdtemp(join(SNAPSHOT_TMP_ROOT, `dsh-tui-snapshot-${scenario.name}-`))
|
||||
const displayCwd = `/tmp/${basename(cwd)}`
|
||||
@@ -310,6 +322,63 @@ async function runScenario(scenario: Scenario): Promise<ScenarioResult> {
|
||||
})
|
||||
await settleTerminal(terminal)
|
||||
|
||||
let interactionSnapshot: string | undefined
|
||||
if (scenario.interaction === 'skill-invocation-policy') {
|
||||
terminal.send('/skill')
|
||||
await settleTerminal(terminal)
|
||||
const discovery = normalizeTerminalSnapshot(
|
||||
await terminal.snapshot({ includeScrollback: true }),
|
||||
cwd,
|
||||
displayCwd,
|
||||
)
|
||||
expect(discovery).toContain('user-only-skill')
|
||||
expect(discovery).not.toContain('model-only-skill')
|
||||
|
||||
terminal.send('\x03')
|
||||
await settleTerminal(terminal)
|
||||
const skillContext = ctx
|
||||
const skillTurnEnded = new Promise<void>((resolve) => {
|
||||
const detach = skillContext.on('session/event', (session, event) => {
|
||||
if (session !== agent.session || event.type !== 'turn/end') return
|
||||
detach()
|
||||
resolve()
|
||||
})
|
||||
})
|
||||
terminal.send('/skill:user-only-skill')
|
||||
terminal.send('\r')
|
||||
await skillTurnEnded
|
||||
await agent.whenIdle()
|
||||
await settleTerminal(terminal)
|
||||
const loaded = normalizeTerminalSnapshot(
|
||||
await terminal.snapshot({ includeScrollback: true }),
|
||||
cwd,
|
||||
displayCwd,
|
||||
)
|
||||
expect(loaded).toContain('USER-ONLY SKILL LOADED')
|
||||
|
||||
terminal.send('/skill:model-only-skill')
|
||||
terminal.send('\r')
|
||||
await settleTerminal(terminal)
|
||||
const denied = normalizeTerminalSnapshot(
|
||||
await terminal.snapshot({ includeScrollback: true }),
|
||||
cwd,
|
||||
displayCwd,
|
||||
)
|
||||
expect(denied).toContain('model-only-skill')
|
||||
expect(denied).toContain('not available for user invocation.')
|
||||
expect(denied).not.toContain('MODEL-ONLY BODY MUST NOT LOAD')
|
||||
interactionSnapshot = [
|
||||
'=== skill autocomplete ===',
|
||||
discovery,
|
||||
'',
|
||||
'=== loaded exact invocation ===',
|
||||
loaded,
|
||||
'',
|
||||
'=== denied exact invocation ===',
|
||||
denied,
|
||||
].join('\n')
|
||||
}
|
||||
|
||||
let remainingPrompts = prompts
|
||||
if (scenario.enterPlanMode === true) {
|
||||
const firstPrompt = prompts[0]!
|
||||
@@ -392,7 +461,7 @@ async function runScenario(scenario: Scenario): Promise<ScenarioResult> {
|
||||
}
|
||||
|
||||
expect(terminal.themeViolations(), `${scenario.name} must remain theme-agnostic`).toEqual([])
|
||||
const snapshot = normalizeTerminalSnapshot(
|
||||
const snapshot = interactionSnapshot ?? normalizeTerminalSnapshot(
|
||||
await terminal.snapshot({ includeScrollback: true }),
|
||||
cwd,
|
||||
displayCwd,
|
||||
|
||||
Reference in New Issue
Block a user