niceeval 0.12.2-canary.31 → 0.13.0

package/docs-site/zh/examples/integrations/claude-sdk.mdx

@@ -20,7 +20,7 @@ Adapter 负责把评估请求发给应用。应用通过 `canUseTool` 要求用
 
 接入的全部代码变更（生成时从两个目录实测统计）：
 
-<table className="gd-summary"><tbody><tr><th>{"类别"}</th><th>{"文件数"}</th><th>{"行数"}</th></tr><tr><td>{"应用侧配置（必要：依赖声明）"}</td><td>{"3"}</td><td>{"+6 −1"}</td></tr><tr><td>{"Adapter（必要：连接应用，协议映射由 NiceEval 提供）"}</td><td>{"2"}</td><td>{"+131"}</td></tr><tr><td>{"评估用例与实验（按需增长）"}</td><td>{"6"}</td><td>{"+120"}</td></tr><tr className="gd-total"><td>{"合计"}</td><td>{"11"}</td><td>{"+257 −1"}</td></tr></tbody></table>
+<table className="gd-summary"><tbody><tr><th>{"类别"}</th><th>{"文件数"}</th><th>{"行数"}</th></tr><tr><td>{"应用侧配置（必要：依赖声明）"}</td><td>{"3"}</td><td>{"+6 −1"}</td></tr><tr><td>{"Adapter（必要：连接应用，协议映射由 NiceEval 提供）"}</td><td>{"2"}</td><td>{"+131"}</td></tr><tr><td>{"评估用例与实验（按需增长）"}</td><td>{"6"}</td><td>{"+123"}</td></tr><tr className="gd-total"><td>{"合计"}</td><td>{"11"}</td><td>{"+260 −1"}</td></tr></tbody></table>
 
 ## 文件清单
 
@@ -47,7 +47,7 @@ claude-sdk/
 <div className="gd-file">
 <div className="gd-head"><span className="gd-name">{"package.json"}</span><span className="gd-stats"><span className="gd-plus">{"+2"}</span></span></div>
 <div className="gd-body">
-<table className="gd-table"><tbody><tr className="gd-expand" data-fold="gdf3"><td className="gd-ln" colSpan={2}>{"⇕"}</td><td className="gd-sign"></td><td className="gd-code">{"展开 8 行未变更代码"}</td></tr><tr className="gd-fold gdf3"><td className="gd-ln">{"1"}</td><td className="gd-ln">{"1"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"{"}</span></td></tr><tr className="gd-fold gdf3"><td className="gd-ln">{"2"}</td><td className="gd-ln">{"2"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"  "}</span><span className="gdt1">{"\"name\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"claude-sdk-example\""}</span><span className="gdt0">{","}</span></td></tr><tr className="gd-fold gdf3"><td className="gd-ln">{"3"}</td><td className="gd-ln">{"3"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"  "}</span><span className="gdt1">{"\"version\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"0.1.0\""}</span><span className="gdt0">{","}</span></td></tr><tr className="gd-fold gdf3"><td className="gd-ln">{"4"}</td><td className="gd-ln">{"4"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"  "}</span><span className="gdt1">{"\"private\""}</span><span className="gdt0">{": "}</span><span className="gdt1">{"true"}</span><span className="gdt0">{","}</span></td></tr><tr className="gd-fold gdf3"><td className="gd-ln">{"5"}</td><td className="gd-ln">{"5"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"  "}</span><span className="gdt1">{"\"type\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"module\""}</span><span className="gdt0">{","}</span></td></tr><tr className="gd-fold gdf3"><td className="gd-ln">{"6"}</td><td className="gd-ln">{"6"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"  "}</span><span className="gdt1">{"\"scripts\""}</span><span className="gdt0">{": {"}</span></td></tr><tr className="gd-fold gdf3"><td className="gd-ln">{"7"}</td><td className="gd-ln">{"7"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt1">{"\"dev\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"lsof -ti tcp:32001 | xargs kill -9 2>/dev/null; concurrently -k -n server,web -c blue,green "}</span><span className="gdt1">{"\\\""}</span><span className="gdt2">{"pnpm dev:server"}</span><span className="gdt1">{"\\\""}</span><span className="gdt2">{" "}</span><span className="gdt1">{"\\\""}</span><span className="gdt2">{"pnpm dev:web"}</span><span className="gdt1">{"\\\""}</span><span className="gdt2">{"\""}</span><span className="gdt0">{","}</span></td></tr><tr className="gd-fold gdf3"><td className="gd-ln">{"8"}</td><td className="gd-ln">{"8"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt1">{"\"dev:server\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"node --env-file .env --import tsx/esm --watch src/backend/server.ts\""}</span><span className="gdt0">{","}</span></td></tr><tr><td className="gd-ln">{"9"}</td><td className="gd-ln">{"9"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt1">{"\"dev:web\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"wait-on -t 30000 tcp:127.0.0.1:32001 && vite\""}</span><span className="gdt0">{","}</span></td></tr><tr><td className="gd-ln">{"10"}</td><td className="gd-ln">{"10"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt1">{"\"build\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"vite build\""}</span><span className="gdt0">{","}</span></td></tr><tr><td className="gd-ln">{"11"}</td><td className="gd-ln">{"11"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt1">{"\"start\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"node --env-file .env --import tsx/esm src/backend/server.ts\""}</span><span className="gdt0">{","}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"12"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt1">{"\"eval\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"niceeval\""}</span><span className="gdt0">{","}</span></td></tr><tr><td className="gd-ln">{"12"}</td><td className="gd-ln">{"13"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt1">{"\"typecheck\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"tsc --noEmit\""}</span></td></tr><tr><td className="gd-ln">{"13"}</td><td className="gd-ln">{"14"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"  },"}</span></td></tr><tr><td className="gd-ln">{"14"}</td><td className="gd-ln">{"15"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"  "}</span><span className="gdt1">{"\"dependencies\""}</span><span className="gdt0">{": {"}</span></td></tr><tr className="gd-expand" data-fold="gdf4"><td className="gd-ln" colSpan={2}>{"⇕"}</td><td className="gd-sign"></td><td className="gd-code">{"展开 9 行未变更代码"}</td></tr><tr className="gd-fold gdf4"><td className="gd-ln">{"15"}</td><td className="gd-ln">{"16"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt1">{"\"@anthropic-ai/claude-agent-sdk\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"^0.3.198\""}</span><span className="gdt0">{","}</span></td></tr><tr className="gd-fold gdf4"><td className="gd-ln">{"16"}</td><td className="gd-ln">{"17"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt1">{"\"@assistant-ui/react\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"^0.14.24\""}</span><span className="gdt0">{","}</span></td></tr><tr className="gd-fold gdf4"><td className="gd-ln">{"17"}</td><td className="gd-ln">{"18"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt1">{"\"react\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"^19.0.0\""}</span><span className="gdt0">{","}</span></td></tr><tr className="gd-fold gdf4"><td className="gd-ln">{"18"}</td><td className="gd-ln">{"19"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt1">{"\"react-dom\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"^19.0.0\""}</span><span className="gdt0">{","}</span></td></tr><tr className="gd-fold gdf4"><td className="gd-ln">{"19"}</td><td className="gd-ln">{"20"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt1">{"\"zod\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"^4.1.8\""}</span></td></tr><tr className="gd-fold gdf4"><td className="gd-ln">{"20"}</td><td className="gd-ln">{"21"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"  },"}</span></td></tr><tr className="gd-fold gdf4"><td className="gd-ln">{"21"}</td><td className="gd-ln">{"22"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"  "}</span><span className="gdt1">{"\"devDependencies\""}</span><span className="gdt0">{": {"}</span></td></tr><tr className="gd-fold gdf4"><td className="gd-ln">{"22"}</td><td className="gd-ln">{"23"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt1">{"\"@types/node\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"^22.0.0\""}</span><span className="gdt0">{","}</span></td></tr><tr className="gd-fold gdf4"><td className="gd-ln">{"23"}</td><td className="gd-ln">{"24"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt1">{"\"@types/react\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"^19.0.0\""}</span><span className="gdt0">{","}</span></td></tr><tr><td className="gd-ln">{"24"}</td><td className="gd-ln">{"25"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt1">{"\"@types/react-dom\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"^19.0.0\""}</span><span className="gdt0">{","}</span></td></tr><tr><td className="gd-ln">{"25"}</td><td className="gd-ln">{"26"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt1">{"\"@vitejs/plugin-react\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"^5.0.0\""}</span><span className="gdt0">{","}</span></td></tr><tr><td className="gd-ln">{"26"}</td><td className="gd-ln">{"27"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt1">{"\"concurrently\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"^9.0.0\""}</span><span className="gdt0">{","}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"28"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt1">{"\"niceeval\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"file:../../../..\""}</span><span className="gdt0">{","}</span></td></tr><tr><td className="gd-ln">{"27"}</td><td className="gd-ln">{"29"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt1">{"\"tsx\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"^4.19.2\""}</span><span className="gdt0">{","}</span></td></tr><tr><td className="gd-ln">{"28"}</td><td className="gd-ln">{"30"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt1">{"\"typescript\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"^5.7.2\""}</span><span className="gdt0">{","}</span></td></tr><tr><td className="gd-ln">{"29"}</td><td className="gd-ln">{"31"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt1">{"\"vite\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"^7.0.0\""}</span><span className="gdt0">{","}</span></td></tr><tr><td className="gd-ln">{"30"}</td><td className="gd-ln">{"32"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt1">{"\"wait-on\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"^9.0.0\""}</span></td></tr><tr><td className="gd-ln">{"31"}</td><td className="gd-ln">{"33"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"  }"}</span></td></tr><tr><td className="gd-ln">{"32"}</td><td className="gd-ln">{"34"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"}"}</span></td></tr></tbody></table>
+<table className="gd-table"><tbody><tr className="gd-expand" data-fold="gdf3"><td className="gd-ln" colSpan={2}>{"⇕"}</td><td className="gd-sign"></td><td className="gd-code">{"展开 8 行未变更代码"}</td></tr><tr className="gd-fold gdf3"><td className="gd-ln">{"1"}</td><td className="gd-ln">{"1"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"{"}</span></td></tr><tr className="gd-fold gdf3"><td className="gd-ln">{"2"}</td><td className="gd-ln">{"2"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"  "}</span><span className="gdt1">{"\"name\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"claude-sdk-example\""}</span><span className="gdt0">{","}</span></td></tr><tr className="gd-fold gdf3"><td className="gd-ln">{"3"}</td><td className="gd-ln">{"3"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"  "}</span><span className="gdt1">{"\"version\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"0.1.0\""}</span><span className="gdt0">{","}</span></td></tr><tr className="gd-fold gdf3"><td className="gd-ln">{"4"}</td><td className="gd-ln">{"4"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"  "}</span><span className="gdt1">{"\"private\""}</span><span className="gdt0">{": "}</span><span className="gdt1">{"true"}</span><span className="gdt0">{","}</span></td></tr><tr className="gd-fold gdf3"><td className="gd-ln">{"5"}</td><td className="gd-ln">{"5"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"  "}</span><span className="gdt1">{"\"type\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"module\""}</span><span className="gdt0">{","}</span></td></tr><tr className="gd-fold gdf3"><td className="gd-ln">{"6"}</td><td className="gd-ln">{"6"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"  "}</span><span className="gdt1">{"\"scripts\""}</span><span className="gdt0">{": {"}</span></td></tr><tr className="gd-fold gdf3"><td className="gd-ln">{"7"}</td><td className="gd-ln">{"7"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt1">{"\"dev\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"lsof -ti tcp:32001 | xargs kill -9 2>/dev/null; concurrently -k -n server,web -c blue,green "}</span><span className="gdt1">{"\\\""}</span><span className="gdt2">{"pnpm dev:server"}</span><span className="gdt1">{"\\\""}</span><span className="gdt2">{" "}</span><span className="gdt1">{"\\\""}</span><span className="gdt2">{"pnpm dev:web"}</span><span className="gdt1">{"\\\""}</span><span className="gdt2">{"\""}</span><span className="gdt0">{","}</span></td></tr><tr className="gd-fold gdf3"><td className="gd-ln">{"8"}</td><td className="gd-ln">{"8"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt1">{"\"dev:server\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"node --env-file .env --import tsx/esm --watch src/backend/server.ts\""}</span><span className="gdt0">{","}</span></td></tr><tr><td className="gd-ln">{"9"}</td><td className="gd-ln">{"9"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt1">{"\"dev:web\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"wait-on -t 30000 tcp:127.0.0.1:32001 && vite\""}</span><span className="gdt0">{","}</span></td></tr><tr><td className="gd-ln">{"10"}</td><td className="gd-ln">{"10"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt1">{"\"build\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"vite build\""}</span><span className="gdt0">{","}</span></td></tr><tr><td className="gd-ln">{"11"}</td><td className="gd-ln">{"11"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt1">{"\"start\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"node --env-file .env --import tsx/esm src/backend/server.ts\""}</span><span className="gdt0">{","}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"12"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt1">{"\"eval\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"niceeval\""}</span><span className="gdt0">{","}</span></td></tr><tr><td className="gd-ln">{"12"}</td><td className="gd-ln">{"13"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt1">{"\"typecheck\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"tsc --noEmit\""}</span></td></tr><tr><td className="gd-ln">{"13"}</td><td className="gd-ln">{"14"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"  },"}</span></td></tr><tr><td className="gd-ln">{"14"}</td><td className="gd-ln">{"15"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"  "}</span><span className="gdt1">{"\"dependencies\""}</span><span className="gdt0">{": {"}</span></td></tr><tr className="gd-expand" data-fold="gdf4"><td className="gd-ln" colSpan={2}>{"⇕"}</td><td className="gd-sign"></td><td className="gd-code">{"展开 9 行未变更代码"}</td></tr><tr className="gd-fold gdf4"><td className="gd-ln">{"15"}</td><td className="gd-ln">{"16"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt1">{"\"@anthropic-ai/claude-agent-sdk\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"^0.3.198\""}</span><span className="gdt0">{","}</span></td></tr><tr className="gd-fold gdf4"><td className="gd-ln">{"16"}</td><td className="gd-ln">{"17"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt1">{"\"@assistant-ui/react\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"^0.14.24\""}</span><span className="gdt0">{","}</span></td></tr><tr className="gd-fold gdf4"><td className="gd-ln">{"17"}</td><td className="gd-ln">{"18"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt1">{"\"react\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"^19.0.0\""}</span><span className="gdt0">{","}</span></td></tr><tr className="gd-fold gdf4"><td className="gd-ln">{"18"}</td><td className="gd-ln">{"19"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt1">{"\"react-dom\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"^19.0.0\""}</span><span className="gdt0">{","}</span></td></tr><tr className="gd-fold gdf4"><td className="gd-ln">{"19"}</td><td className="gd-ln">{"20"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt1">{"\"zod\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"^4.1.8\""}</span></td></tr><tr className="gd-fold gdf4"><td className="gd-ln">{"20"}</td><td className="gd-ln">{"21"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"  },"}</span></td></tr><tr className="gd-fold gdf4"><td className="gd-ln">{"21"}</td><td className="gd-ln">{"22"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"  "}</span><span className="gdt1">{"\"devDependencies\""}</span><span className="gdt0">{": {"}</span></td></tr><tr className="gd-fold gdf4"><td className="gd-ln">{"22"}</td><td className="gd-ln">{"23"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt1">{"\"@types/node\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"^24.0.0\""}</span><span className="gdt0">{","}</span></td></tr><tr className="gd-fold gdf4"><td className="gd-ln">{"23"}</td><td className="gd-ln">{"24"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt1">{"\"@types/react\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"^19.0.0\""}</span><span className="gdt0">{","}</span></td></tr><tr><td className="gd-ln">{"24"}</td><td className="gd-ln">{"25"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt1">{"\"@types/react-dom\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"^19.0.0\""}</span><span className="gdt0">{","}</span></td></tr><tr><td className="gd-ln">{"25"}</td><td className="gd-ln">{"26"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt1">{"\"@vitejs/plugin-react\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"^5.0.0\""}</span><span className="gdt0">{","}</span></td></tr><tr><td className="gd-ln">{"26"}</td><td className="gd-ln">{"27"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt1">{"\"concurrently\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"^9.0.0\""}</span><span className="gdt0">{","}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"28"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt1">{"\"niceeval\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"file:../../../..\""}</span><span className="gdt0">{","}</span></td></tr><tr><td className="gd-ln">{"27"}</td><td className="gd-ln">{"29"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt1">{"\"tsx\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"^4.19.2\""}</span><span className="gdt0">{","}</span></td></tr><tr><td className="gd-ln">{"28"}</td><td className="gd-ln">{"30"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt1">{"\"typescript\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"^5.7.2\""}</span><span className="gdt0">{","}</span></td></tr><tr><td className="gd-ln">{"29"}</td><td className="gd-ln">{"31"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt1">{"\"vite\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"^7.0.0\""}</span><span className="gdt0">{","}</span></td></tr><tr><td className="gd-ln">{"30"}</td><td className="gd-ln">{"32"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt1">{"\"wait-on\""}</span><span className="gdt0">{": "}</span><span className="gdt2">{"\"^9.0.0\""}</span></td></tr><tr><td className="gd-ln">{"31"}</td><td className="gd-ln">{"33"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"  }"}</span></td></tr><tr><td className="gd-ln">{"32"}</td><td className="gd-ln">{"34"}</td><td className="gd-sign"></td><td className="gd-code"><span className="gdt0">{"}"}</span></td></tr></tbody></table>
 </div>
 </div>
 
@@ -82,23 +82,23 @@ claude-sdk/
 </div>
 
 <div className="gd-file">
-<div className="gd-head"><span className="gd-name">{"evals/basic-qa.eval.ts"}</span><span className="gd-stats"><span className="gd-plus">{"+21"}</span></span></div>
+<div className="gd-head"><span className="gd-name">{"evals/basic-qa.eval.ts"}</span><span className="gd-stats"><span className="gd-plus">{"+22"}</span></span></div>
 <div className="gd-body">
-<table className="gd-table"><tbody><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"1"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt4">{"import"}</span><span className="gdt0">{" { defineEval } "}</span><span className="gdt4">{"from"}</span><span className="gdt0">{" "}</span><span className="gdt2">{"\"niceeval\""}</span><span className="gdt0">{";"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"2"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"3"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"// 这条 eval 验证 agent 能正常问答、不瞎调工具,顺带冒烟 usage 有没有从 result 消息的"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"4"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"// usage/total_cost_usd 正确映射进 Turn.usage。"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"5"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt4">{"export"}</span><span className="gdt0">{" "}</span><span className="gdt4">{"default"}</span><span className="gdt0">{" "}</span><span className="gdt5">{"defineEval"}</span><span className="gdt0">{"({"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"6"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"  description: "}</span><span className="gdt2">{"\"测试 agent 能正常问答且不瞎调工具\""}</span><span className="gdt0">{","}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"7"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"8"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"  "}</span><span className="gdt4">{"async"}</span><span className="gdt0">{" "}</span><span className="gdt5">{"test"}</span><span className="gdt0">{"("}</span><span className="gdt7">{"t"}</span><span className="gdt0">{") {"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"9"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt4">{"const"}</span><span className="gdt0">{" "}</span><span className="gdt1">{"turn"}</span><span className="gdt0">{" "}</span><span className="gdt4">{"="}</span><span className="gdt0">{" "}</span><span className="gdt4">{"await"}</span><span className="gdt0">{" t."}</span><span className="gdt5">{"send"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"用一句话介绍一下你自己,这轮不用查天气也不用算数。\""}</span><span className="gdt0">{");"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"10"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt4">{"await"}</span><span className="gdt0">{" turn."}</span><span className="gdt5">{"succeeded"}</span><span className="gdt0">{"()."}</span><span className="gdt5">{"orStop"}</span><span className="gdt0">{"();"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"11"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"12"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt4">{"await"}</span><span className="gdt0">{" t."}</span><span className="gdt5">{"group"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"正常收发、没有多余工具调用\""}</span><span className="gdt0">{", () "}</span><span className="gdt4">{"=>"}</span><span className="gdt0">{" {"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"13"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"      t."}</span><span className="gdt5">{"succeeded"}</span><span className="gdt0">{"();"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"14"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"      t."}</span><span className="gdt5">{"usedNoTools"}</span><span className="gdt0">{"();"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"15"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    });"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"16"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"17"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    t."}</span><span className="gdt5">{"maxTokens"}</span><span className="gdt0">{"("}</span><span className="gdt1">{"20_000"}</span><span className="gdt0">{");"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"18"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"19"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    t.judge.autoevals."}</span><span className="gdt5">{"closedQA"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"助手是否用一两句话正常介绍了自己,而不是报错或答非所问?\""}</span><span className="gdt0">{")."}</span><span className="gdt5">{"gate"}</span><span className="gdt0">{"("}</span><span className="gdt1">{"0.6"}</span><span className="gdt0">{");"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"20"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"  },"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"21"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"});"}</span></td></tr></tbody></table>
+<table className="gd-table"><tbody><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"1"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt4">{"import"}</span><span className="gdt0">{" { defineEval } "}</span><span className="gdt4">{"from"}</span><span className="gdt0">{" "}</span><span className="gdt2">{"\"niceeval\""}</span><span className="gdt0">{";"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"2"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"3"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"// 这条 eval 验证 agent 能正常问答、不瞎调工具,顺带冒烟 usage 有没有从 result 消息的"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"4"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"// usage/total_cost_usd 正确映射进 Turn.usage。"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"5"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt4">{"export"}</span><span className="gdt0">{" "}</span><span className="gdt4">{"default"}</span><span className="gdt0">{" "}</span><span className="gdt5">{"defineEval"}</span><span className="gdt0">{"({"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"6"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"  judge: "}</span><span className="gdt1">{"true"}</span><span className="gdt0">{","}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"7"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"  description: "}</span><span className="gdt2">{"\"测试 agent 能正常问答且不瞎调工具\""}</span><span className="gdt0">{","}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"8"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"9"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"  "}</span><span className="gdt4">{"async"}</span><span className="gdt0">{" "}</span><span className="gdt5">{"test"}</span><span className="gdt0">{"("}</span><span className="gdt7">{"t"}</span><span className="gdt0">{") {"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"10"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt4">{"const"}</span><span className="gdt0">{" "}</span><span className="gdt1">{"turn"}</span><span className="gdt0">{" "}</span><span className="gdt4">{"="}</span><span className="gdt0">{" "}</span><span className="gdt4">{"await"}</span><span className="gdt0">{" t."}</span><span className="gdt5">{"send"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"用一句话介绍一下你自己,这轮不用查天气也不用算数。\""}</span><span className="gdt0">{");"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"11"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt4">{"await"}</span><span className="gdt0">{" turn."}</span><span className="gdt5">{"succeeded"}</span><span className="gdt0">{"()."}</span><span className="gdt5">{"orStop"}</span><span className="gdt0">{"();"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"12"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"13"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt4">{"await"}</span><span className="gdt0">{" t."}</span><span className="gdt5">{"group"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"正常收发、没有多余工具调用\""}</span><span className="gdt0">{", () "}</span><span className="gdt4">{"=>"}</span><span className="gdt0">{" {"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"14"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"      t."}</span><span className="gdt5">{"succeeded"}</span><span className="gdt0">{"();"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"15"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"      t."}</span><span className="gdt5">{"usedNoTools"}</span><span className="gdt0">{"();"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"16"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    });"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"17"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"18"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    t."}</span><span className="gdt5">{"maxTokens"}</span><span className="gdt0">{"("}</span><span className="gdt1">{"20_000"}</span><span className="gdt0">{");"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"19"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"20"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    turn.judge.autoevals."}</span><span className="gdt5">{"closedQA"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"助手是否用一两句话正常介绍了自己,而不是报错或答非所问?\""}</span><span className="gdt0">{")."}</span><span className="gdt5">{"gate"}</span><span className="gdt0">{"("}</span><span className="gdt1">{"0.6"}</span><span className="gdt0">{");"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"21"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"  },"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"22"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"});"}</span></td></tr></tbody></table>
 </div>
 </div>
 
 <div className="gd-file">
 <div className="gd-head"><span className="gd-name">{"evals/hitl-approve.eval.ts"}</span><span className="gd-stats"><span className="gd-plus">{"+23"}</span></span></div>
 <div className="gd-body">
-<table className="gd-table"><tbody><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"1"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt4">{"import"}</span><span className="gdt0">{" { defineEval } "}</span><span className="gdt4">{"from"}</span><span className="gdt0">{" "}</span><span className="gdt2">{"\"niceeval\""}</span><span className="gdt0">{";"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"2"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt4">{"import"}</span><span className="gdt0">{" { equals } "}</span><span className="gdt4">{"from"}</span><span className="gdt0">{" "}</span><span className="gdt2">{"\"niceeval/expect\""}</span><span className="gdt0">{";"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"3"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"4"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"// calculate 工具经 canUseTool 挂了审批(见 agents/claude-sdk.ts、origin src/backend/agent.ts)。"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"5"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"// 这条验证批准分支:approve 之后工具正常执行,calledTool 的 status 是 \"completed\"。"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"6"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"//"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"7"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"// 提示词不提\"审批\"——不同模型在提示词里看到\"审批\"字样时,有的会倾向于用文字问\"可以吗\""}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"8"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"// 而不是真的发起工具调用;审批门是服务端 canUseTool 自动挂的,跟用户怎么问无关。"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"9"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt4">{"export"}</span><span className="gdt0">{" "}</span><span className="gdt4">{"default"}</span><span className="gdt0">{" "}</span><span className="gdt5">{"defineEval"}</span><span className="gdt0">{"({"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"10"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"  description: "}</span><span className="gdt2">{"\"HITL:calculate 经批准后正常执行\""}</span><span className="gdt0">{","}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"11"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"12"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"  "}</span><span className="gdt4">{"async"}</span><span className="gdt0">{" "}</span><span className="gdt5">{"test"}</span><span className="gdt0">{"("}</span><span className="gdt7">{"t"}</span><span className="gdt0">{") {"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"13"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt4">{"const"}</span><span className="gdt0">{" "}</span><span className="gdt1">{"draft"}</span><span className="gdt0">{" "}</span><span className="gdt4">{"="}</span><span className="gdt0">{" "}</span><span className="gdt4">{"await"}</span><span className="gdt0">{" t."}</span><span className="gdt5">{"send"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"用计算器算一下 (23+19)*3 等于多少\""}</span><span className="gdt0">{");"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"14"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    t."}</span><span className="gdt5">{"check"}</span><span className="gdt0">{"(draft.status, "}</span><span className="gdt5">{"equals"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"waiting\""}</span><span className="gdt0">{"));"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"15"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"16"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    t."}</span><span className="gdt5">{"requireInputRequest"}</span><span className="gdt0">{"({ action: "}</span><span className="gdt2">{"\"mcp__demo-tools__calculate\""}</span><span className="gdt0">{" });"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"17"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"18"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt4">{"const"}</span><span className="gdt0">{" "}</span><span className="gdt1">{"approved"}</span><span className="gdt0">{" "}</span><span className="gdt4">{"="}</span><span className="gdt0">{" "}</span><span className="gdt4">{"await"}</span><span className="gdt0">{" t."}</span><span className="gdt5">{"respond"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"approve\""}</span><span className="gdt0">{");"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"19"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    approved."}</span><span className="gdt5">{"succeeded"}</span><span className="gdt0">{"();"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"20"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    t."}</span><span className="gdt5">{"calledTool"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"mcp__demo-tools__calculate\""}</span><span className="gdt0">{", { status: "}</span><span className="gdt2">{"\"completed\""}</span><span className="gdt0">{" });"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"21"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    t."}</span><span className="gdt5">{"messageIncludes"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"/"}</span><span className="gdt8">{"126"}</span><span className="gdt2">{"/"}</span><span className="gdt0">{");"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"22"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"  },"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"23"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"});"}</span></td></tr></tbody></table>
+<table className="gd-table"><tbody><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"1"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt4">{"import"}</span><span className="gdt0">{" { defineEval } "}</span><span className="gdt4">{"from"}</span><span className="gdt0">{" "}</span><span className="gdt2">{"\"niceeval\""}</span><span className="gdt0">{";"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"2"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt4">{"import"}</span><span className="gdt0">{" { equals, toolMatch } "}</span><span className="gdt4">{"from"}</span><span className="gdt0">{" "}</span><span className="gdt2">{"\"niceeval/expect\""}</span><span className="gdt0">{";"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"3"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"4"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"// calculate 工具经 canUseTool 挂了审批(见 agents/claude-sdk.ts、origin src/backend/agent.ts)。"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"5"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"// 这条验证批准分支:approve 之后工具正常执行,calledTool 的 status 是 \"completed\"。"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"6"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"//"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"7"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"// 提示词不提\"审批\"——不同模型在提示词里看到\"审批\"字样时,有的会倾向于用文字问\"可以吗\""}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"8"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"// 而不是真的发起工具调用;审批门是服务端 canUseTool 自动挂的,跟用户怎么问无关。"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"9"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt4">{"export"}</span><span className="gdt0">{" "}</span><span className="gdt4">{"default"}</span><span className="gdt0">{" "}</span><span className="gdt5">{"defineEval"}</span><span className="gdt0">{"({"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"10"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"  description: "}</span><span className="gdt2">{"\"HITL:calculate 经批准后正常执行\""}</span><span className="gdt0">{","}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"11"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"12"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"  "}</span><span className="gdt4">{"async"}</span><span className="gdt0">{" "}</span><span className="gdt5">{"test"}</span><span className="gdt0">{"("}</span><span className="gdt7">{"t"}</span><span className="gdt0">{") {"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"13"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt4">{"const"}</span><span className="gdt0">{" "}</span><span className="gdt1">{"draft"}</span><span className="gdt0">{" "}</span><span className="gdt4">{"="}</span><span className="gdt0">{" "}</span><span className="gdt4">{"await"}</span><span className="gdt0">{" t."}</span><span className="gdt5">{"send"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"用计算器算一下 (23+19)*3 等于多少\""}</span><span className="gdt0">{");"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"14"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    t."}</span><span className="gdt5">{"check"}</span><span className="gdt0">{"(draft.status, "}</span><span className="gdt5">{"equals"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"waiting\""}</span><span className="gdt0">{"));"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"15"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"16"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    t."}</span><span className="gdt5">{"requireInputRequest"}</span><span className="gdt0">{"({ action: "}</span><span className="gdt2">{"\"mcp__demo-tools__calculate\""}</span><span className="gdt0">{" });"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"17"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"18"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt4">{"const"}</span><span className="gdt0">{" "}</span><span className="gdt1">{"approved"}</span><span className="gdt0">{" "}</span><span className="gdt4">{"="}</span><span className="gdt0">{" "}</span><span className="gdt4">{"await"}</span><span className="gdt0">{" t."}</span><span className="gdt5">{"respond"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"approve\""}</span><span className="gdt0">{");"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"19"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    approved."}</span><span className="gdt5">{"succeeded"}</span><span className="gdt0">{"();"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"20"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    t."}</span><span className="gdt5">{"calledTool"}</span><span className="gdt0">{"("}</span><span className="gdt5">{"toolMatch"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"mcp__demo-tools__calculate\""}</span><span className="gdt0">{", { status: "}</span><span className="gdt2">{"\"completed\""}</span><span className="gdt0">{" }));"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"21"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    t."}</span><span className="gdt5">{"messageIncludes"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"/"}</span><span className="gdt8">{"126"}</span><span className="gdt2">{"/"}</span><span className="gdt0">{");"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"22"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"  },"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"23"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"});"}</span></td></tr></tbody></table>
 </div>
 </div>
 
 <div className="gd-file">
 <div className="gd-head"><span className="gd-name">{"evals/hitl-deny.eval.ts"}</span><span className="gd-stats"><span className="gd-plus">{"+25"}</span></span></div>
 <div className="gd-body">
-<table className="gd-table"><tbody><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"1"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt4">{"import"}</span><span className="gdt0">{" { defineEval } "}</span><span className="gdt4">{"from"}</span><span className="gdt0">{" "}</span><span className="gdt2">{"\"niceeval\""}</span><span className="gdt0">{";"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"2"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt4">{"import"}</span><span className="gdt0">{" { equals } "}</span><span className="gdt4">{"from"}</span><span className="gdt0">{" "}</span><span className="gdt2">{"\"niceeval/expect\""}</span><span className="gdt0">{";"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"3"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"4"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"// deny 分支:人否决和工具故障是两回事——calledTool 的 status 应该是 \"rejected\""}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"5"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"// (来自 system/permission_denied 帧,见 agents/claude-sdk.ts),noFailedActions() 依然通过。"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"6"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"//"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"7"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"// deepseek-v4-flash 被拒绝一次后,偶尔会不死心、原样再试一次同一个工具调用(新的 tool_use id,"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"8"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"// 同一个 gated 工具),这一轮又会停在新的 input.requested 上——不是 adapter 的映射 bug(每次"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"9"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"// 拒绝都正确落 rejected),是模型行为。deny 到它放弃为止,给个上限避免死循环。"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"10"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt4">{"export"}</span><span className="gdt0">{" "}</span><span className="gdt4">{"default"}</span><span className="gdt0">{" "}</span><span className="gdt5">{"defineEval"}</span><span className="gdt0">{"({"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"11"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"  description: "}</span><span className="gdt2">{"\"HITL:calculate 被拒绝后标记 rejected 而不是 failed\""}</span><span className="gdt0">{","}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"12"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"13"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"  "}</span><span className="gdt4">{"async"}</span><span className="gdt0">{" "}</span><span className="gdt5">{"test"}</span><span className="gdt0">{"("}</span><span className="gdt7">{"t"}</span><span className="gdt0">{") {"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"14"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt4">{"await"}</span><span className="gdt0">{" t."}</span><span className="gdt5">{"send"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"用计算器算一下 (23+19)*3 等于多少\""}</span><span className="gdt0">{");"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"15"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    t."}</span><span className="gdt5">{"requireInputRequest"}</span><span className="gdt0">{"({ action: "}</span><span className="gdt2">{"\"mcp__demo-tools__calculate\""}</span><span className="gdt0">{" });"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"16"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"17"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt4">{"let"}</span><span className="gdt0">{" denied "}</span><span className="gdt4">{"="}</span><span className="gdt0">{" "}</span><span className="gdt4">{"await"}</span><span className="gdt0">{" t."}</span><span className="gdt5">{"respond"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"deny\""}</span><span className="gdt0">{");"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"18"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt4">{"for"}</span><span className="gdt0">{" ("}</span><span className="gdt4">{"let"}</span><span className="gdt0">{" attempt "}</span><span className="gdt4">{"="}</span><span className="gdt0">{" "}</span><span className="gdt1">{"0"}</span><span className="gdt0">{"; attempt "}</span><span className="gdt4">{"<"}</span><span className="gdt0">{" "}</span><span className="gdt1">{"3"}</span><span className="gdt0">{" "}</span><span className="gdt4">{"&&"}</span><span className="gdt0">{" denied.status "}</span><span className="gdt4">{"==="}</span><span className="gdt0">{" "}</span><span className="gdt2">{"\"waiting\""}</span><span className="gdt0">{"; attempt"}</span><span className="gdt4">{"++"}</span><span className="gdt0">{") {"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"19"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"      denied "}</span><span className="gdt4">{"="}</span><span className="gdt0">{" "}</span><span className="gdt4">{"await"}</span><span className="gdt0">{" t."}</span><span className="gdt5">{"respond"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"deny\""}</span><span className="gdt0">{");"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"20"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    }"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"21"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    t."}</span><span className="gdt5">{"check"}</span><span className="gdt0">{"(denied.status, "}</span><span className="gdt5">{"equals"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"completed\""}</span><span className="gdt0">{"));"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"22"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    t."}</span><span className="gdt5">{"calledTool"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"mcp__demo-tools__calculate\""}</span><span className="gdt0">{", { status: "}</span><span className="gdt2">{"\"rejected\""}</span><span className="gdt0">{" });"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"23"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    t."}</span><span className="gdt5">{"noFailedActions"}</span><span className="gdt0">{"();"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"24"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"  },"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"25"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"});"}</span></td></tr></tbody></table>
+<table className="gd-table"><tbody><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"1"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt4">{"import"}</span><span className="gdt0">{" { defineEval } "}</span><span className="gdt4">{"from"}</span><span className="gdt0">{" "}</span><span className="gdt2">{"\"niceeval\""}</span><span className="gdt0">{";"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"2"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt4">{"import"}</span><span className="gdt0">{" { equals, toolMatch } "}</span><span className="gdt4">{"from"}</span><span className="gdt0">{" "}</span><span className="gdt2">{"\"niceeval/expect\""}</span><span className="gdt0">{";"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"3"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"4"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"// deny 分支:人否决和工具故障是两回事——calledTool 的 status 应该是 \"rejected\""}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"5"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"// (来自 system/permission_denied 帧,见 agents/claude-sdk.ts),noFailedActions() 依然通过。"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"6"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"//"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"7"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"// deepseek-v4-flash 被拒绝一次后,偶尔会不死心、原样再试一次同一个工具调用(新的 tool_use id,"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"8"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"// 同一个 gated 工具),这一轮又会停在新的 input.requested 上——不是 adapter 的映射 bug(每次"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"9"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"// 拒绝都正确落 rejected),是模型行为。deny 到它放弃为止,给个上限避免死循环。"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"10"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt4">{"export"}</span><span className="gdt0">{" "}</span><span className="gdt4">{"default"}</span><span className="gdt0">{" "}</span><span className="gdt5">{"defineEval"}</span><span className="gdt0">{"({"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"11"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"  description: "}</span><span className="gdt2">{"\"HITL:calculate 被拒绝后标记 rejected 而不是 failed\""}</span><span className="gdt0">{","}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"12"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"13"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"  "}</span><span className="gdt4">{"async"}</span><span className="gdt0">{" "}</span><span className="gdt5">{"test"}</span><span className="gdt0">{"("}</span><span className="gdt7">{"t"}</span><span className="gdt0">{") {"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"14"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt4">{"await"}</span><span className="gdt0">{" t."}</span><span className="gdt5">{"send"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"用计算器算一下 (23+19)*3 等于多少\""}</span><span className="gdt0">{");"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"15"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    t."}</span><span className="gdt5">{"requireInputRequest"}</span><span className="gdt0">{"({ action: "}</span><span className="gdt2">{"\"mcp__demo-tools__calculate\""}</span><span className="gdt0">{" });"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"16"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"17"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt4">{"let"}</span><span className="gdt0">{" denied "}</span><span className="gdt4">{"="}</span><span className="gdt0">{" "}</span><span className="gdt4">{"await"}</span><span className="gdt0">{" t."}</span><span className="gdt5">{"respond"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"deny\""}</span><span className="gdt0">{");"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"18"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt4">{"for"}</span><span className="gdt0">{" ("}</span><span className="gdt4">{"let"}</span><span className="gdt0">{" attempt "}</span><span className="gdt4">{"="}</span><span className="gdt0">{" "}</span><span className="gdt1">{"0"}</span><span className="gdt0">{"; attempt "}</span><span className="gdt4">{"<"}</span><span className="gdt0">{" "}</span><span className="gdt1">{"3"}</span><span className="gdt0">{" "}</span><span className="gdt4">{"&&"}</span><span className="gdt0">{" denied.status "}</span><span className="gdt4">{"==="}</span><span className="gdt0">{" "}</span><span className="gdt2">{"\"waiting\""}</span><span className="gdt0">{"; attempt"}</span><span className="gdt4">{"++"}</span><span className="gdt0">{") {"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"19"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"      denied "}</span><span className="gdt4">{"="}</span><span className="gdt0">{" "}</span><span className="gdt4">{"await"}</span><span className="gdt0">{" t."}</span><span className="gdt5">{"respond"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"deny\""}</span><span className="gdt0">{");"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"20"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    }"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"21"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    t."}</span><span className="gdt5">{"check"}</span><span className="gdt0">{"(denied.status, "}</span><span className="gdt5">{"equals"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"completed\""}</span><span className="gdt0">{"));"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"22"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    t."}</span><span className="gdt5">{"calledTool"}</span><span className="gdt0">{"("}</span><span className="gdt5">{"toolMatch"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"mcp__demo-tools__calculate\""}</span><span className="gdt0">{", { status: "}</span><span className="gdt2">{"\"rejected\""}</span><span className="gdt0">{" }));"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"23"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    t."}</span><span className="gdt5">{"noFailedActions"}</span><span className="gdt0">{"();"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"24"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"  },"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"25"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"});"}</span></td></tr></tbody></table>
 </div>
 </div>
 
@@ -110,9 +110,9 @@ claude-sdk/
 </div>
 
 <div className="gd-file">
-<div className="gd-head"><span className="gd-name">{"evals/weather-tool.eval.ts"}</span><span className="gd-stats"><span className="gd-plus">{"+22"}</span></span></div>
+<div className="gd-head"><span className="gd-name">{"evals/weather-tool.eval.ts"}</span><span className="gd-stats"><span className="gd-plus">{"+24"}</span></span></div>
 <div className="gd-body">
-<table className="gd-table"><tbody><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"1"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt4">{"import"}</span><span className="gdt0">{" { defineEval } "}</span><span className="gdt4">{"from"}</span><span className="gdt0">{" "}</span><span className="gdt2">{"\"niceeval\""}</span><span className="gdt0">{";"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"2"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"3"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"// 这条 eval 验证 agent 遇到实时天气问题时会调 get_weather,而不是直接编一个答案。"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"4"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"// 工具名是 MCP 命名空间下的真实名字 mcp__demo-tools__get_weather(不是裸的 get_weather),"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"5"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"// 见 agents/claude-sdk.ts 头注释。"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"6"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt4">{"export"}</span><span className="gdt0">{" "}</span><span className="gdt4">{"default"}</span><span className="gdt0">{" "}</span><span className="gdt5">{"defineEval"}</span><span className="gdt0">{"({"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"7"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"  description: "}</span><span className="gdt2">{"\"测试 agent 在天气问题中正确调用 get_weather 并基于结果作答\""}</span><span className="gdt0">{","}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"8"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"9"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"  "}</span><span className="gdt4">{"async"}</span><span className="gdt0">{" "}</span><span className="gdt5">{"test"}</span><span className="gdt0">{"("}</span><span className="gdt7">{"t"}</span><span className="gdt0">{") {"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"10"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt4">{"const"}</span><span className="gdt0">{" "}</span><span className="gdt1">{"turn"}</span><span className="gdt0">{" "}</span><span className="gdt4">{"="}</span><span className="gdt0">{" "}</span><span className="gdt4">{"await"}</span><span className="gdt0">{" t."}</span><span className="gdt5">{"send"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"北京今天天气怎么样?\""}</span><span className="gdt0">{");"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"11"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt4">{"await"}</span><span className="gdt0">{" turn."}</span><span className="gdt5">{"succeeded"}</span><span className="gdt0">{"()."}</span><span className="gdt5">{"orStop"}</span><span className="gdt0">{"();"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"12"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"13"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt4">{"await"}</span><span className="gdt0">{" t."}</span><span className="gdt5">{"group"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"调用 get_weather 且城市正确\""}</span><span className="gdt0">{", () "}</span><span className="gdt4">{"=>"}</span><span className="gdt0">{" {"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"14"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"      t."}</span><span className="gdt5">{"calledTool"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"mcp__demo-tools__get_weather\""}</span><span className="gdt0">{", { input: { city: "}</span><span className="gdt2">{"\"北京\""}</span><span className="gdt0">{" } });"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"15"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"      t."}</span><span className="gdt5">{"messageIncludes"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"/"}</span><span className="gdt8">{"°C"}</span><span className="gdt4">{"|"}</span><span className="gdt8">{"气温"}</span><span className="gdt4">{"|"}</span><span className="gdt8">{"天气"}</span><span className="gdt4">{"|"}</span><span className="gdt8">{"晴"}</span><span className="gdt4">{"|"}</span><span className="gdt8">{"多云"}</span><span className="gdt4">{"|"}</span><span className="gdt8">{"雨"}</span><span className="gdt4">{"|"}</span><span className="gdt8">{"阴"}</span><span className="gdt2">{"/"}</span><span className="gdt0">{");"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"16"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    });"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"17"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"18"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    t.judge.autoevals"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"19"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"      ."}</span><span className="gdt5">{"closedQA"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"助手是否给出了具体的天气数据(温度或天气状况),而不是拒绝回答或含糊其辞?\""}</span><span className="gdt0">{")"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"20"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"      ."}</span><span className="gdt5">{"atLeast"}</span><span className="gdt0">{"("}</span><span className="gdt1">{"0.7"}</span><span className="gdt0">{");"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"21"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"  },"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"22"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"});"}</span></td></tr></tbody></table>
+<table className="gd-table"><tbody><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"1"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt4">{"import"}</span><span className="gdt0">{" { defineEval } "}</span><span className="gdt4">{"from"}</span><span className="gdt0">{" "}</span><span className="gdt2">{"\"niceeval\""}</span><span className="gdt0">{";"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"2"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt4">{"import"}</span><span className="gdt0">{" { jsonMatch, toolMatch } "}</span><span className="gdt4">{"from"}</span><span className="gdt0">{" "}</span><span className="gdt2">{"\"niceeval/expect\""}</span><span className="gdt0">{";"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"3"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"4"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"// 这条 eval 验证 agent 遇到实时天气问题时会调 get_weather,而不是直接编一个答案。"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"5"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"// 工具名是 MCP 命名空间下的真实名字 mcp__demo-tools__get_weather(不是裸的 get_weather),"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"6"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt6">{"// 见 agents/claude-sdk.ts 头注释。"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"7"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt4">{"export"}</span><span className="gdt0">{" "}</span><span className="gdt4">{"default"}</span><span className="gdt0">{" "}</span><span className="gdt5">{"defineEval"}</span><span className="gdt0">{"({"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"8"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"  judge: "}</span><span className="gdt1">{"true"}</span><span className="gdt0">{","}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"9"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"  description: "}</span><span className="gdt2">{"\"测试 agent 在天气问题中正确调用 get_weather 并基于结果作答\""}</span><span className="gdt0">{","}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"10"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"11"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"  "}</span><span className="gdt4">{"async"}</span><span className="gdt0">{" "}</span><span className="gdt5">{"test"}</span><span className="gdt0">{"("}</span><span className="gdt7">{"t"}</span><span className="gdt0">{") {"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"12"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt4">{"const"}</span><span className="gdt0">{" "}</span><span className="gdt1">{"turn"}</span><span className="gdt0">{" "}</span><span className="gdt4">{"="}</span><span className="gdt0">{" "}</span><span className="gdt4">{"await"}</span><span className="gdt0">{" t."}</span><span className="gdt5">{"send"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"北京今天天气怎么样?\""}</span><span className="gdt0">{");"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"13"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt4">{"await"}</span><span className="gdt0">{" turn."}</span><span className="gdt5">{"succeeded"}</span><span className="gdt0">{"()."}</span><span className="gdt5">{"orStop"}</span><span className="gdt0">{"();"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"14"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"15"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    "}</span><span className="gdt4">{"await"}</span><span className="gdt0">{" t."}</span><span className="gdt5">{"group"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"调用 get_weather 且城市正确\""}</span><span className="gdt0">{", () "}</span><span className="gdt4">{"=>"}</span><span className="gdt0">{" {"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"16"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"      t."}</span><span className="gdt5">{"calledTool"}</span><span className="gdt0">{"("}</span><span className="gdt5">{"toolMatch"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"mcp__demo-tools__get_weather\""}</span><span className="gdt0">{", { input: "}</span><span className="gdt5">{"jsonMatch"}</span><span className="gdt0">{"({ city: "}</span><span className="gdt2">{"\"北京\""}</span><span className="gdt0">{" }) }));"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"17"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"      t."}</span><span className="gdt5">{"messageIncludes"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"/"}</span><span className="gdt8">{"°C"}</span><span className="gdt4">{"|"}</span><span className="gdt8">{"气温"}</span><span className="gdt4">{"|"}</span><span className="gdt8">{"天气"}</span><span className="gdt4">{"|"}</span><span className="gdt8">{"晴"}</span><span className="gdt4">{"|"}</span><span className="gdt8">{"多云"}</span><span className="gdt4">{"|"}</span><span className="gdt8">{"雨"}</span><span className="gdt4">{"|"}</span><span className="gdt8">{"阴"}</span><span className="gdt2">{"/"}</span><span className="gdt0">{");"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"18"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    });"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"19"}</td><td className="gd-sign">{"+"}</td><td className="gd-code">{" "}</td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"20"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"    turn.judge.autoevals"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"21"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"      ."}</span><span className="gdt5">{"closedQA"}</span><span className="gdt0">{"("}</span><span className="gdt2">{"\"助手是否给出了具体的天气数据(温度或天气状况),而不是拒绝回答或含糊其辞?\""}</span><span className="gdt0">{")"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"22"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"      ."}</span><span className="gdt5">{"gate"}</span><span className="gdt0">{"("}</span><span className="gdt1">{"0.7"}</span><span className="gdt0">{");"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"23"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"  },"}</span></td></tr><tr className="gd-add"><td className="gd-ln"></td><td className="gd-ln">{"24"}</td><td className="gd-sign">{"+"}</td><td className="gd-code"><span className="gdt0">{"});"}</span></td></tr></tbody></table>
 </div>
 </div>