Merge remote-tracking branch 'origin/master' into fs-overwrite-diff-bound-v2

examples/acp-agent/README.i18n.yaml

@@ -3,4 +3,4 @@
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write examples/acp-agent/README.md
 README.md: 61c6efafe9dde4f91385beebdfd426c57006187b
-README.zh.md: 343e55722a4dda7c5cc5e0de6b5fecf250b9ab13
+README.zh.md: bd1b0e2200271a71074fbb2475167c25eb309d77

examples/acp-agent/README.zh.md

@@ -9,16 +9,16 @@ pnpm run demo:acp             # needs DEEPSEEK_API_KEY (repo-root .env or env)
 pnpm run demo:code-mode       # 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。可选 overlay 可添加会话查询、文件系统溢出存储、Code Mode 或 Web 抓取。
+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。可选 overlay 可添加会话查询、文件系统 spill 存储、Code Mode 或 Web 抓取。
 
 ## 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；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)。
+自动化约定（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 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` 为部署选择 `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[沙箱约定](../../packages/sandbox/sandbox/README.md)）。`DSH_PERMISSION_MODE` 为部署选择 `workspace-write` 或 `danger-full-access`。
 
 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。

examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.expected.md

@@ -60,7 +60,7 @@ interface ToolArgsMap {
     /** Exact service key or event name whose original JSDoc to include; valid only with what:"api" or what:"events". */
     name?: string;
   } & Record<string, JsonValue>;
-  /** Mount a temporary Cordis Plugin in the current DSH process. This creates an in-memory runtime Plugin, not an installed or configured Plugin. It remains active across later turns until cordis_unmount, toolset unload, or DSH restart. It does not create files, install a package, change cordis.yml or personal/project config, survive restart, or automatically become permanent. To keep it, ask the Agent to implement a normal local, project, or repository Plugin through the regular development workflow. It may affect other sessions in the same process; the sandbox is not a security boundary, and injected services reach the real runtime. `code` runs now as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:"api" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:"events"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Temporary Plugins can COMPOSE: one Plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically by cordis_unmount. Sandbox globals: `console` (tagged `[cordis:<id>]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned when unmounted) — cordis_inspect what:"api" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime. */
+  /** Mount a temporary Cordis Plugin in the current DSH process. This creates an in-memory runtime Plugin, not an installed or configured Plugin. It remains active across later turns until cordis_unmount, toolset unload, or DSH restart. It does not create files, install a package, change cordis.yml or personal/project config, survive restart, or automatically become permanent. To keep it, ask the Agent to implement a normal local, project, or repository Plugin through the regular development workflow. It may affect other sessions in the same process; the sandbox is not a security boundary, and injected services reach the real runtime. `code` runs now as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:"api" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:"events"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Temporary Plugins can COMPOSE: one Plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically by cordis_unmount. Sandbox globals: `console` (tagged `[cordis:<id>]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned when unmounted) — cordis_inspect what:"api" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` SHORT-CIRCUITS the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime. */
   cordis_mount: {
     /** JavaScript body returning a temporary Plugin; evaluated now and saved nowhere. */
     code: string;

examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.expected.json

@@ -72,7 +72,7 @@
     },
     {
       "name": "cordis_mount",
-      "description": "Mount a temporary Cordis Plugin in the current DSH process. This creates an in-memory runtime Plugin, not an installed or configured Plugin. It remains active across later turns until cordis_unmount, toolset unload, or DSH restart. It does not create files, install a package, change cordis.yml or personal/project config, survive restart, or automatically become permanent. To keep it, ask the Agent to implement a normal local, project, or repository Plugin through the regular development workflow. It may affect other sessions in the same process; the sandbox is not a security boundary, and injected services reach the real runtime. `code` runs now as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Temporary Plugins can COMPOSE: one Plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically by cordis_unmount. Sandbox globals: `console` (tagged `[cordis:<id>]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned when unmounted) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.",
+      "description": "Mount a temporary Cordis Plugin in the current DSH process. This creates an in-memory runtime Plugin, not an installed or configured Plugin. It remains active across later turns until cordis_unmount, toolset unload, or DSH restart. It does not create files, install a package, change cordis.yml or personal/project config, survive restart, or automatically become permanent. To keep it, ask the Agent to implement a normal local, project, or repository Plugin through the regular development workflow. It may affect other sessions in the same process; the sandbox is not a security boundary, and injected services reach the real runtime. `code` runs now as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Temporary Plugins can COMPOSE: one Plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically by cordis_unmount. Sandbox globals: `console` (tagged `[cordis:<id>]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned when unmounted) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` SHORT-CIRCUITS the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.",
       "parameters": {
         "type": "object",
         "properties": {

examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl

@@ -25,7 +25,7 @@
 {"type":"assistant/chunk","seq":23,"time":1785730459921,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
 {"type":"assistant/message","seq":24,"time":1785730459921,"data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"tool-call","id":"inspect-tools-event","name":"cordis_inspect","arguments":"{\"what\":\"events\",\"name\":\"tools/pre-execute\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"283c82b3-1bda-481c-a716-c35f363c9752"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[19,20,21,22,23],"surfaceOp":"append"}
 {"type":"tool/call","seq":25,"time":1785730459921,"data":{"turn":1,"step":2,"callId":"inspect-tools-event","name":"cordis_inspect","arguments":"{\"what\":\"events\",\"name\":\"tools/pre-execute\"}"}}
-{"type":"tool/result","seq":26,"time":1785730459929,"data":{"turn":1,"step":2,"message":{"source":{"kind":"tool","callId":"inspect-tools-event"},"content":[{"type":"tool-result","toolCallId":"inspect-tools-event","content":[{"type":"text","text":"## events\n- tools/pre-execute [waterfall] — Allow, deny, or ask before dispatch.\n    /**\n     * Allow, deny, or ask before dispatch. `next()` delegates to allow; missing\n     * approval support turns `ask` into denial. Async gates must observe\n     * `exec.signal`; the registry rechecks cancellation after they settle but\n     * never abandons their promise.\n     * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent's calls.\n     * @param exec - the pending call (name, parsed arguments, caller agent).\n     * @mode waterfall\n     */\n    'tools/pre-execute'(this: Scoped<ToolRegistry>, exec: ToolExecution, next: () => Promise<PreToolDecision>): Promise<PreToolDecision>\nwaterfall listeners receive a trailing next() and MUST call it to delegate — returning without next() vetoes the chain."}],"isError":false}],"role":"user","id":"c187306a-d73c-4bcd-b76c-8607ddbc0974"}},"sourceEventSeqs":[25],"surfaceOp":"append"}
+{"type":"tool/result","seq":26,"time":1785730459929,"data":{"turn":1,"step":2,"message":{"source":{"kind":"tool","callId":"inspect-tools-event"},"content":[{"type":"tool-result","toolCallId":"inspect-tools-event","content":[{"type":"text","text":"## events\n- tools/pre-execute [waterfall] — Allow, deny, or ask before dispatch.\n    /**\n     * Allow, deny, or ask before dispatch. `next()` delegates to allow; missing\n     * approval support turns `ask` into denial. Async gates must observe\n     * `exec.signal`; the registry rechecks cancellation after they settle but\n     * never abandons their promise.\n     * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent's calls.\n     * @param exec - the pending call (name, parsed arguments, caller agent).\n     * @mode waterfall\n     */\n    'tools/pre-execute'(this: Scoped<ToolRegistry>, exec: ToolExecution, next: () => Promise<PreToolDecision>): Promise<PreToolDecision>\nwaterfall listeners receive a trailing next() and MUST call it to delegate — returning without next() short-circuits the chain."}],"isError":false}],"role":"user","id":"c187306a-d73c-4bcd-b76c-8607ddbc0974"}},"sourceEventSeqs":[25],"surfaceOp":"append"}
 {"type":"step/end","seq":27,"time":1785730459929,"data":{"turn":1,"step":2}}
 {"type":"step/start","seq":28,"time":1785730459939,"data":{"turn":1,"step":3}}
 {"type":"assistant/chunk","seq":29,"time":1784449176735,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}

examples/headless-agent/README.i18n.yaml

@@ -3,4 +3,4 @@
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write examples/headless-agent/README.md
 README.md: 6e80e56dec70c2be341ae5dfbad70e13a5109715
-README.zh.md: ea8c41b9ae75f0cee3edd78e59408f37c19182d3
+README.zh.md: 9e409735f03afc62cd788fa2a5d1afdef0fa6c2a

examples/headless-agent/README.zh.md

@@ -19,13 +19,13 @@ pnpm run dsh run "fix the failing test in this workspace"
 
 ## E2B POC overlay
 
-[`e2b.cordis.yml`](e2b.cordis.yml) 使用一个共享 E2B 沙箱替换本地文件系统与进程管理提供方，同时保留 `dsh-bash-local` 和相同的面向模型工具。请在 git 忽略的根目录 `.env` 中，将 `E2B_API_KEY` 与 `DEEPSEEK_API_KEY` 放在一起，然后运行凭据门控的实机组合测试；它在同一个沙箱中驱动 FS、Bash、PTY 和 LSP，并证明沙箱最终被删除：
+[`e2b.cordis.yml`](e2b.cordis.yml) 使用一个共享 E2B 沙箱替换本地文件系统与子进程提供方，同时保留 `dsh-bash-local` 和相同的面向模型工具。请在 git 忽略的根目录 `.env` 中，将 `E2B_API_KEY` 与 `DEEPSEEK_API_KEY` 放在一起，然后运行凭据门控的实机组合测试；它在同一个沙箱中驱动 FS、Bash、PTY 和 LSP，并证明沙箱最终被删除：
 
 ```sh
 pnpm exec vitest run --config vitest.e2e.config.ts packages/e2b/e2b/tests/composition.e2e.ts
 ```
 
-该 overlay 会在沙箱中创建拼写相同的绝对 cwd，但不会上传或挂载宿主工作区。文件与 Bash 变更只存在于 E2B；Cordis、模型调用、agent／会话状态、会话日志、skill（技能）和 SDK 缓冲仍在宿主上。该组合会在超时和资源释放时终止其沙箱。它是提供方组合 POC，而不是完整 harness 迁移或工作区同步功能。
+该 overlay 会在沙箱中创建相同的绝对 cwd，但不会上传或挂载宿主工作区。文件与 Bash 变更只存在于 E2B；Cordis、模型调用、agent／会话状态、会话日志、skill（技能）和 SDK 缓冲仍在宿主上。该组合会在超时和资源释放时终止其沙箱。它是提供方组合 POC，而不是完整 harness 迁移或工作区同步功能。
 
 ## 高级配置
 

examples/headless-agent/tests/fixtures/cli-mock-llm.ts

@@ -29,6 +29,10 @@ class CliMockAdapter extends LlmAdapter {
   }
 
   async * stream(options: GenerateOptions): AsyncIterable<StreamChunk> {
+    if (process.env.DSH_CLI_MOCK_FAILURE === '1') {
+      yield { type: 'finish', reason: { kind: 'error', failure: { code: 'SERVER', message: 'CLI mock provider failed' } } }
+      return
+    }
     const toolResult = options.messages.at(-1)?.content.find(block => block.type === 'tool-result')
     if (toolResult === undefined) {
       const args = JSON.stringify({ command: 'printf CLI_TOOL_ROUND_TRIP', description: 'Prove the CLI tool round trip.' })

examples/headless-agent/tests/fixtures/dsh-run.cordis.yml

@@ -1,4 +1,4 @@
-- id: api-gateway
+- id: agent-default-model
   config:
     provider: cli-mock
     model: cli-mock

examples/headless-agent/tests/fixtures/repository-plugin/dsh-plugin.mjs

@@ -1,9 +1,19 @@
 // Generated by dsh-plugin-prepare. Do not edit.
 const manifest = {"name":"headless-repository-fixture","skills":["dsh-plugin-assets/skills/0"]}
+// Value mirror: Cordis const enum FiberState.ACTIVE; keep aligned with dsh-repository-plugin source.ts.
+const FIBER_ACTIVE = 2
 export const name = "headless-repository-fixture"
 export const inject = ["loader","skills"]
+async function mount(ctx, plugin, label, config) {
+  const fiber = ctx.plugin(plugin, config)
+  await fiber
+  if (fiber.state !== FIBER_ACTIVE) {
+    const missing = Object.keys(fiber.inject).filter(service => fiber.ctx.get(service) === undefined)
+    throw new Error(`${label} did not activate (waiting for services: ${missing.join(', ') || 'unknown'})`)
+  }
+}
 export async function apply(ctx) {
   const runtime = ctx.loader.builtins["dsh-repository-plugin"]
   if (runtime === undefined) throw new Error("missing Cordis builtin dsh-repository-plugin")
-  await ctx.plugin(runtime, { baseUrl: import.meta.url, manifest })
+  await mount(ctx, runtime, 'repository Plugin runtime', { baseUrl: import.meta.url, manifest })
 }

examples/headless-agent/tests/headless.snapshot.ts

@@ -54,6 +54,7 @@ const reasoningConfigPath = fileURLToPath(new URL('./fixtures/cli.cordis.yml', i
 const deepseekDefaultsConfigPath = fileURLToPath(new URL('./fixtures/deepseek-defaults.cordis.yml', import.meta.url))
 const dshRunOverlayPath = fileURLToPath(new URL('./fixtures/dsh-run.cordis.yml', import.meta.url))
 const dshRunSessionExpected = join(snapshotsDir, 'dsh-run', 'session.expected.jsonl')
+const dshRunFailureExpected = join(snapshotsDir, 'dsh-run', 'stderr.expected.txt')
 const cliMockLlmPluginPath = fileURLToPath(new URL('./fixtures/cli-mock-llm.ts', import.meta.url))
 const refreshing = process.env.DSH_SNAPSHOT === 'refresh'
 
@@ -196,6 +197,16 @@ async function persistedLogs(cwd: string, root: string = join(cwd, '.sessions'))
   }))
 }
 
+/** Install the keyless product-CLI adapter into the temporary headless profile. */
+async function prepareCliMockFixture(cwd: string): Promise<void> {
+  const fixtureDir = join(cwd, '.dsh', 'profiles', 'headless', 'snapshot-fixtures')
+  await mkdir(fixtureDir, { recursive: true })
+  await Promise.all([
+    copyFile(cliMockLlmPluginPath, join(fixtureDir, 'cli-mock-llm.ts')),
+    writeFile(join(fixtureDir, 'package.json'), '{"type":"module"}\n'),
+  ])
+}
+
 describe('headless stream-json snapshots', () => {
   it('runs one task through the product dsh run command', async () => {
     const task = 'Prove the product dsh run path with one real tool round trip.'
@@ -211,14 +222,7 @@ describe('headless stream-json snapshots', () => {
         DSH_TELEMETRY_DISABLED: '1',
         NODE_OPTIONS: [process.env.NODE_OPTIONS, '--disable-warning=ExperimentalWarning'].filter(Boolean).join(' '),
       },
-      prepare: async (cwd) => {
-        const fixtureDir = join(cwd, '.dsh', 'profiles', 'headless', 'snapshot-fixtures')
-        await mkdir(fixtureDir, { recursive: true })
-        await Promise.all([
-          copyFile(cliMockLlmPluginPath, join(fixtureDir, 'cli-mock-llm.ts')),
-          writeFile(join(fixtureDir, 'package.json'), '{"type":"module"}\n'),
-        ])
-      },
+      prepare: prepareCliMockFixture,
       inspect: async (cwd) => {
         const logs = await persistedLogs(cwd, join(cwd, '.dsh', 'sessions'))
         expect(logs).toHaveLength(1)
@@ -234,7 +238,28 @@ describe('headless stream-json snapshots', () => {
     })
 
     expect(result.stdout).toBe('CLI tool round trip complete: CLI_TOOL_ROUND_TRIP\n')
-    expect(result.stderr).toMatch(/^dsh: observing at http:\/\/127\.0\.0\.1:\d+\n$/u)
+    expect(result.stderr).toBe('')
+  }, LOADER_SMOKE_TEST_TIMEOUT_MS)
+
+  it('prints a terminal model failure through the product dsh run command', async () => {
+    const result = await runLoaderSmoke({
+      label: 'product dsh run model failure snapshot',
+      tempDirPrefix: 'headless-snapshot-dsh-run-failure-',
+      binScript: dshBinScript,
+      configPath: dshRunOverlayPath,
+      binArgs: ['run', '--patch', dshRunOverlayPath, 'Trigger the keyless model failure.'],
+      tsconfigPath,
+      expectedExitCode: 1,
+      env: {
+        DSH_CLI_MOCK_FAILURE: '1',
+        DSH_TELEMETRY_DISABLED: '1',
+        NODE_OPTIONS: [process.env.NODE_OPTIONS, '--disable-warning=ExperimentalWarning'].filter(Boolean).join(' '),
+      },
+      prepare: prepareCliMockFixture,
+    })
+
+    expect(result.stdout).toBe('\n')
+    await expect(result.stderr).toMatchFileSnapshot(dshRunFailureExpected)
   }, LOADER_SMOKE_TEST_TIMEOUT_MS)
 
   it('prints the original Loader activation error through the assembled one-shot app', async () => {

examples/headless-agent/tests/keyless-smoke.e2e.ts

@@ -6,7 +6,12 @@ import { join } from 'node:path'
 import { fileURLToPath } from 'node:url'
 import { describe, expect, it } from 'vitest'
 import { LOADER_SMOKE_TEST_TIMEOUT_MS, runLoaderSmoke } from '@deepseek-ai/dsh-loader-smoke'
-import { PREPARED_ENTRY_FILENAME, prepareDshPlugin } from '@deepseek-ai/dsh-repository-plugin'
+import {
+  PREPARED_ENTRY_FILENAME,
+  REPOSITORY_PLUGIN_PREPARE_COMMAND,
+  REPOSITORY_PLUGIN_PACKAGE_NAME,
+  prepareDshPlugin,
+} from '@deepseek-ai/dsh-repository-plugin'
 import type { SessionEvent } from '@deepseek-ai/dsh-session'
 
 const binScript = fileURLToPath(new URL('./fixtures/headless-driver.ts', import.meta.url))
@@ -72,6 +77,8 @@ describe('headless-agent keyless smoke', () => {
       await writeFile(join(plugin, 'package.json'), `${JSON.stringify({
         name: 'headless-repository-fixture',
         version: '0.0.0',
+        scripts: { prepack: REPOSITORY_PLUGIN_PREPARE_COMMAND },
+        devDependencies: { [REPOSITORY_PLUGIN_PACKAGE_NAME]: '0.0.1' },
         dsh: { skills: ['../skills'] },
       }, undefined, 2)}\n`)
       await prepareDshPlugin(plugin)

examples/headless-agent/tests/snapshots/dsh-run/session.expected.jsonl

@@ -2,11 +2,11 @@
 {"type":"permission/preset","seq":0,"time":0,"data":{"preset":"danger-full-access"}}
 {"type":"sandbox/mode","seq":1,"time":0,"data":{"mode":"danger-full-access"}}
 {"type":"approval/policy","seq":2,"time":0,"data":{"policy":"never"}}
-{"type":"agent/inbox/spliced","seq":3,"time":0,"data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Prove the product dsh run path with one real tool round trip."}],"source":{"kind":"user","rpcId":"{{sessionId}}"},"role":"user","id":"{{sessionId}}"}]}}
+{"type":"agent/inbox/spliced","seq":3,"time":0,"data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Prove the product dsh run path with one real tool round trip."}],"source":{"kind":"user"},"role":"user","id":"{{sessionId}}"}]}}
 {"type":"turn/start","seq":4,"time":0,"data":{"turn":1}}
 {"type":"agent/inbox/spliced","seq":5,"time":0,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}}
 {"type":"step/start","seq":6,"time":0,"data":{"turn":1,"step":1}}
-{"type":"user/message","seq":7,"time":0,"data":{"content":[{"type":"text","text":"Prove the product dsh run path with one real tool round trip."}],"source":{"kind":"user","rpcId":"{{sessionId}}"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
+{"type":"user/message","seq":7,"time":0,"data":{"content":[{"type":"text","text":"Prove the product dsh run path with one real tool round trip."}],"source":{"kind":"user"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
 {"type":"user/message","seq":8,"time":0,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
 {"type":"session/title","seq":9,"time":0,"data":{"title":"Prove the product dsh run","messageSeqs":[7],"source":{"kind":"fallback"}}}
 {"type":"request/header","seq":10,"time":0,"data":{"header":{"config":{"provider":"cli-mock","model":"cli-mock","reasoningEffort":"high"},"adapterDefaults":{"reasoningEffort":true},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}

examples/headless-agent/tests/snapshots/dsh-run/stderr.expected.txt

@@ -0,0 +1 @@
+dsh: SERVER: CLI mock provider failed

examples/jsonrpc-agent/README.i18n.yaml

@@ -3,4 +3,4 @@
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write examples/jsonrpc-agent/README.md
 README.md: bcc1027d2edb30ab374dfa2ed13ad8e6360d923b
-README.zh.md: 197c25d7b4f5645aeb7e92d8c36ef4a423beb2e8
+README.zh.md: ce255e4dd70bf8c5c6edc51afbe03bb4c66560a0

examples/jsonrpc-agent/README.zh.md

@@ -26,11 +26,11 @@
 
 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。
 
-## 持久工具变体
+## 持久化工具变体
 
 [`persistent-tools.cordis.yml`](persistent-tools.cordis.yml) 是一个最小可运行变体，面向模型的能力严格只有：
 
-- agent 独占、状态持久的 `bash`
+- 所有者作用域内持久化的 `bash`
 - 提供 `view`、`create`、`str_replace` 与 `insert` 的 `str_replace_editor`
 
-它组合本地 PTY、文件系统 intent 策略与会话沙箱策略。
+它组合了本地 PTY、文件系统意图策略与会话沙箱策略。

examples/web-cordis/README.i18n.yaml

@@ -3,4 +3,4 @@
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write examples/web-cordis/README.md
 README.md: 21fe0a210b2e591a96dc254014a0f91ed9afa2ba
-README.zh.md: 35158affd5cbdd6f8fa7f5910500f21c2b241309
+README.zh.md: b3fecb4312dbcbaeff460a21f1d2db6b5288f9ad

examples/web-cordis/README.zh.md

@@ -18,4 +18,4 @@ pnpm run demo:cordis
 pnpm run demo:cordis acp
 ```
 
-这两条命令都需要 `DEEPSEEK_API_KEY`。工具、生命周期和安全契约由 [Cordis 工具参考](../../packages/self-modification/tool-cordis/README.md)定义。
+这两条命令都需要 `DEEPSEEK_API_KEY`。工具、生命周期和安全约定由 [Cordis 工具参考](../../packages/self-modification/tool-cordis/README.md)定义。