@cursor/bdk 0.2.13 → 0.2.15

package/dist/docs/reference/evals.html

@@ -9,51 +9,51 @@
     <link rel="preload stylesheet" href="/docs/assets/style.Dwls12uf.css" as="style">
     <link rel="preload stylesheet" href="/docs/vp-icons.css" as="style">
     
-    <script type="module" src="/docs/assets/app.CaLG1pPt.js"></script>
+    <script type="module" src="/docs/assets/app.CRMxF0qX.js"></script>
     <link rel="preload" href="/docs/assets/inter-roman-latin.Di8DUHzh.woff2" as="font" type="font/woff2" crossorigin="">
     <link rel="modulepreload" href="/docs/assets/chunks/framework.BNw1pucY.js">
-    <link rel="modulepreload" href="/docs/assets/chunks/theme.DO1avLBn.js">
+    <link rel="modulepreload" href="/docs/assets/chunks/theme.m_Ethbkv.js">
     <link rel="modulepreload" href="/docs/assets/chunks/katex.DkKDou_j.js">
-    <link rel="modulepreload" href="/docs/assets/chunks/dagre-KV5264BT.aSbEUwT7.js">
-    <link rel="modulepreload" href="/docs/assets/chunks/cose-bilkent-S5V4N54A.tezXBs9b.js">
-    <link rel="modulepreload" href="/docs/assets/chunks/c4Diagram-AHTNJAMY.w1d6QxV7.js">
-    <link rel="modulepreload" href="/docs/assets/chunks/flowDiagram-DWJPFMVM.BFMtUSv-.js">
-    <link rel="modulepreload" href="/docs/assets/chunks/erDiagram-SMLLAGMA.H40W4HWE.js">
-    <link rel="modulepreload" href="/docs/assets/chunks/gitGraphDiagram-UUTBAWPF.Cyc5mzZD.js">
-    <link rel="modulepreload" href="/docs/assets/chunks/ganttDiagram-T4ZO3ILL.CbYiu7Dt.js">
-    <link rel="modulepreload" href="/docs/assets/chunks/infoDiagram-42DDH7IO.Bz6KCA3a.js">
-    <link rel="modulepreload" href="/docs/assets/chunks/pieDiagram-DEJITSTG.BtpHnIB_.js">
-    <link rel="modulepreload" href="/docs/assets/chunks/quadrantDiagram-34T5L4WZ.Cx4oCSRR.js">
-    <link rel="modulepreload" href="/docs/assets/chunks/xychartDiagram-5P7HB3ND.b4pZF3D5.js">
-    <link rel="modulepreload" href="/docs/assets/chunks/requirementDiagram-MS252O5E.BC0hXWlW.js">
-    <link rel="modulepreload" href="/docs/assets/chunks/sequenceDiagram-FGHM5R23.CWSdHYAF.js">
-    <link rel="modulepreload" href="/docs/assets/chunks/classDiagram-6PBFFD2Q.Cmtm6WkN.js">
-    <link rel="modulepreload" href="/docs/assets/chunks/classDiagram-v2-HSJHXN6E.Cmtm6WkN.js">
-    <link rel="modulepreload" href="/docs/assets/chunks/stateDiagram-FHFEXIEX.0MVPRI28.js">
-    <link rel="modulepreload" href="/docs/assets/chunks/stateDiagram-v2-QKLJ7IA2.N4Am6sXd.js">
-    <link rel="modulepreload" href="/docs/assets/chunks/journeyDiagram-VCZTEJTY.D0t_ltlb.js">
-    <link rel="modulepreload" href="/docs/assets/chunks/timeline-definition-GMOUNBTQ.BuRinAVi.js">
-    <link rel="modulepreload" href="/docs/assets/chunks/mindmap-definition-QFDTVHPH.Bc72Utls.js">
-    <link rel="modulepreload" href="/docs/assets/chunks/kanban-definition-6JOO6SKY.DyyNsMfi.js">
-    <link rel="modulepreload" href="/docs/assets/chunks/sankeyDiagram-XADWPNL6.Dg8T1SEp.js">
-    <link rel="modulepreload" href="/docs/assets/chunks/diagram-TYMM5635.BbAnLEBB.js">
-    <link rel="modulepreload" href="/docs/assets/chunks/diagram-MMDJMWI5.CmdSUP6L.js">
-    <link rel="modulepreload" href="/docs/assets/chunks/blockDiagram-DXYQGD6D.D51mJop2.js">
-    <link rel="modulepreload" href="/docs/assets/chunks/diagram-5BDNPKRD.vnT6aJ57.js">
-    <link rel="modulepreload" href="/docs/assets/chunks/architectureDiagram-Q4EWVU46.C5qkGp7y.js">
-    <link rel="modulepreload" href="/docs/assets/chunks/ishikawaDiagram-UXIWVN3A.DDJ_7_Fq.js">
-    <link rel="modulepreload" href="/docs/assets/chunks/vennDiagram-DHZGUBPP.DXf0PCoJ.js">
-    <link rel="modulepreload" href="/docs/assets/chunks/diagram-G4DWMVQ6.hGYdrDa2.js">
-    <link rel="modulepreload" href="/docs/assets/chunks/wardleyDiagram-NUSXRM2D.T4ThngYV.js">
+    <link rel="modulepreload" href="/docs/assets/chunks/dagre-KV5264BT.Bk_CcQPr.js">
+    <link rel="modulepreload" href="/docs/assets/chunks/cose-bilkent-S5V4N54A.4q0YNZN6.js">
+    <link rel="modulepreload" href="/docs/assets/chunks/c4Diagram-AHTNJAMY.D_Z3mqAl.js">
+    <link rel="modulepreload" href="/docs/assets/chunks/flowDiagram-DWJPFMVM.B61NGNYu.js">
+    <link rel="modulepreload" href="/docs/assets/chunks/erDiagram-SMLLAGMA.BN1YUmEV.js">
+    <link rel="modulepreload" href="/docs/assets/chunks/gitGraphDiagram-UUTBAWPF.CBPs2W_2.js">
+    <link rel="modulepreload" href="/docs/assets/chunks/ganttDiagram-T4ZO3ILL.DR-tto3M.js">
+    <link rel="modulepreload" href="/docs/assets/chunks/infoDiagram-42DDH7IO.obPv-fFg.js">
+    <link rel="modulepreload" href="/docs/assets/chunks/pieDiagram-DEJITSTG.BFp11AYt.js">
+    <link rel="modulepreload" href="/docs/assets/chunks/quadrantDiagram-34T5L4WZ.ChX7xo6B.js">
+    <link rel="modulepreload" href="/docs/assets/chunks/xychartDiagram-5P7HB3ND.DtXsNUaf.js">
+    <link rel="modulepreload" href="/docs/assets/chunks/requirementDiagram-MS252O5E.DbKtHG_Q.js">
+    <link rel="modulepreload" href="/docs/assets/chunks/sequenceDiagram-FGHM5R23.BYso9LlE.js">
+    <link rel="modulepreload" href="/docs/assets/chunks/classDiagram-6PBFFD2Q.irslOV8B.js">
+    <link rel="modulepreload" href="/docs/assets/chunks/classDiagram-v2-HSJHXN6E.irslOV8B.js">
+    <link rel="modulepreload" href="/docs/assets/chunks/stateDiagram-FHFEXIEX.D8l54jqW.js">
+    <link rel="modulepreload" href="/docs/assets/chunks/stateDiagram-v2-QKLJ7IA2.CAYMmzGj.js">
+    <link rel="modulepreload" href="/docs/assets/chunks/journeyDiagram-VCZTEJTY.BoVHerYZ.js">
+    <link rel="modulepreload" href="/docs/assets/chunks/timeline-definition-GMOUNBTQ.BLdhhyy9.js">
+    <link rel="modulepreload" href="/docs/assets/chunks/mindmap-definition-QFDTVHPH.DLPMLJlv.js">
+    <link rel="modulepreload" href="/docs/assets/chunks/kanban-definition-6JOO6SKY.CfYmPHZg.js">
+    <link rel="modulepreload" href="/docs/assets/chunks/sankeyDiagram-XADWPNL6.Spw8tv-7.js">
+    <link rel="modulepreload" href="/docs/assets/chunks/diagram-TYMM5635.DSzlJp2D.js">
+    <link rel="modulepreload" href="/docs/assets/chunks/diagram-MMDJMWI5.BxtXxgIR.js">
+    <link rel="modulepreload" href="/docs/assets/chunks/blockDiagram-DXYQGD6D.sxrH_f0l.js">
+    <link rel="modulepreload" href="/docs/assets/chunks/diagram-5BDNPKRD.CgreoM_Z.js">
+    <link rel="modulepreload" href="/docs/assets/chunks/architectureDiagram-Q4EWVU46.CA-hBJCN.js">
+    <link rel="modulepreload" href="/docs/assets/chunks/ishikawaDiagram-UXIWVN3A.CXHTUcM3.js">
+    <link rel="modulepreload" href="/docs/assets/chunks/vennDiagram-DHZGUBPP.CyGT2F_P.js">
+    <link rel="modulepreload" href="/docs/assets/chunks/diagram-G4DWMVQ6.DlZGpm6W.js">
+    <link rel="modulepreload" href="/docs/assets/chunks/wardleyDiagram-NUSXRM2D.p_Sz9p1i.js">
     <link rel="modulepreload" href="/docs/assets/chunks/virtual_mermaid-config.DDnGl6nM.js">
-    <link rel="modulepreload" href="/docs/assets/reference_evals.md.D5i8PuXJ.lean.js">
+    <link rel="modulepreload" href="/docs/assets/reference_evals.md.if--BLd0.lean.js">
     <script id="check-dark-mode">(()=>{const e=localStorage.getItem("vitepress-theme-appearance")||"auto",a=window.matchMedia("(prefers-color-scheme: dark)").matches;(!e||e==="auto"?a:e==="dark")&&document.documentElement.classList.add("dark")})();</script>
     <script id="check-mac-os">document.documentElement.classList.toggle("mac",/Mac|iPhone|iPod|iPad/i.test(navigator.platform));</script>
     <link rel="alternate" type="text/plain" href="/docs/llms.txt">
     <link rel="alternate" type="text/markdown" href="/docs/reference/evals.md">
   </head>
   <body>
-    <div id="app"><div class="Layout" data-v-5ebc75e4><!--[--><!--]--><!--[--><span tabindex="-1" data-v-7de63af3></span><a href="#VPContent" class="VPSkipLink visually-hidden" data-v-7de63af3>Skip to content</a><!--]--><!----><header class="VPNav" data-v-5ebc75e4 data-v-e8579816><div class="VPNavBar" data-v-e8579816 data-v-bbf4446f><div class="wrapper" data-v-bbf4446f><div class="container" data-v-bbf4446f><div class="title" data-v-bbf4446f><div class="VPNavBarTitle has-sidebar" data-v-bbf4446f data-v-ebd5f04e><a class="title" href="/docs/" data-v-ebd5f04e><!--[--><!--]--><!----><span data-v-ebd5f04e>Grok Bot Development Kit (BDK)</span><!--[--><!--[--><!--[--><!--[--><span class="bdk-version" title="BDK 0.2.13 (@cursor/bdk package)" data-v-d89e5038>0.2.13</span><!--]--><!--]--><!--]--><!--]--></a></div></div><div class="content" data-v-bbf4446f><div class="content-body" data-v-bbf4446f><!--[--><!--]--><div class="VPNavBarSearch search" data-v-bbf4446f><!--[--><!----><div id="local-search"><button type="button" class="DocSearch DocSearch-Button" aria-label="Search"><span class="DocSearch-Button-Container"><span class="vp-icon DocSearch-Search-Icon"></span><span class="DocSearch-Button-Placeholder">Search</span></span><span class="DocSearch-Button-Keys"><kbd class="DocSearch-Button-Key"></kbd><kbd class="DocSearch-Button-Key">K</kbd></span></button></div><!--]--></div><nav aria-labelledby="main-nav-aria-label" class="VPNavBarMenu menu" data-v-bbf4446f data-v-7fa90d1c><span id="main-nav-aria-label" class="visually-hidden" data-v-7fa90d1c> Main Navigation </span><!--[--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/quickstart.html" tabindex="0" data-v-7fa90d1c data-v-8d7ed182><!--[--><span data-v-8d7ed182>Quickstart</span><!--]--></a><!--]--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/guides/mcp-oauth.html" tabindex="0" data-v-7fa90d1c data-v-8d7ed182><!--[--><span data-v-8d7ed182>Guides</span><!--]--></a><!--]--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/guides/github.html" tabindex="0" data-v-7fa90d1c data-v-8d7ed182><!--[--><span data-v-8d7ed182>Integrations</span><!--]--></a><!--]--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/templates/security-reviewer.html" tabindex="0" data-v-7fa90d1c data-v-8d7ed182><!--[--><span data-v-8d7ed182>Templates</span><!--]--></a><!--]--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/reference/project-layout.html" tabindex="0" data-v-7fa90d1c data-v-8d7ed182><!--[--><span data-v-8d7ed182>Reference</span><!--]--></a><!--]--><!--]--></nav><!----><div class="VPNavBarAppearance appearance" data-v-bbf4446f data-v-6a44a4fa><button class="VPSwitch VPSwitchAppearance" type="button" role="switch" title aria-checked="false" data-v-6a44a4fa data-v-b541f24b data-v-a48af969><span class="check" data-v-a48af969><span class="icon" data-v-a48af969><!--[--><span class="vpi-sun sun" data-v-b541f24b></span><span class="vpi-moon moon" data-v-b541f24b></span><!--]--></span></span></button></div><!----><div class="VPFlyout VPNavBarExtra extra" data-v-bbf4446f data-v-8d21ceac data-v-269c0ea1><button type="button" class="button" aria-haspopup="true" aria-expanded="false" aria-label="extra navigation" data-v-269c0ea1><span class="vpi-more-horizontal icon" data-v-269c0ea1></span></button><div class="menu" data-v-269c0ea1><div class="VPMenu" data-v-269c0ea1 data-v-ab92b832><!----><!--[--><!--[--><!----><div class="group" data-v-8d21ceac><div class="item appearance" data-v-8d21ceac><p class="label" data-v-8d21ceac>Appearance</p><div class="appearance-action" data-v-8d21ceac><button class="VPSwitch VPSwitchAppearance" type="button" role="switch" title aria-checked="false" data-v-8d21ceac data-v-b541f24b data-v-a48af969><span class="check" data-v-a48af969><span class="icon" data-v-a48af969><!--[--><span class="vpi-sun sun" data-v-b541f24b></span><span class="vpi-moon moon" data-v-b541f24b></span><!--]--></span></span></button></div></div></div><!----><!--]--><!--]--></div></div></div><!--[--><!--]--><button type="button" class="VPNavBarHamburger hamburger" aria-label="mobile navigation" aria-expanded="false" aria-controls="VPNavScreen" data-v-bbf4446f data-v-efff335d><span class="container" data-v-efff335d><span class="top" data-v-efff335d></span><span class="middle" data-v-efff335d></span><span class="bottom" data-v-efff335d></span></span></button></div></div></div></div><div class="divider" data-v-bbf4446f><div class="divider-line" data-v-bbf4446f></div></div></div><!----></header><div class="VPLocalNav has-sidebar empty" data-v-5ebc75e4 data-v-636a9279><div class="container" data-v-636a9279><button class="menu" aria-expanded="false" aria-controls="VPSidebarNav" data-v-636a9279><span class="vpi-align-left menu-icon" data-v-636a9279></span><span class="menu-text" data-v-636a9279>Menu</span></button><div class="VPLocalNavOutlineDropdown" style="--vp-vh:0px;" data-v-636a9279 data-v-ae38d8b4><button data-v-ae38d8b4>Return to top</button><!----></div></div></div><aside class="VPSidebar" data-v-5ebc75e4 data-v-f102723c><div class="curtain" data-v-f102723c></div><nav class="nav" id="VPSidebarNav" aria-labelledby="sidebar-aria-label" tabindex="-1" data-v-f102723c><span class="visually-hidden" id="sidebar-aria-label" data-v-f102723c> Sidebar Navigation </span><!--[--><!--]--><!--[--><div class="no-transition group" data-v-9c447dd5><section class="VPSidebarItem level-0" data-v-9c447dd5 data-v-8ccd545c><div class="item" role="button" tabindex="0" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><h2 class="text" data-v-8ccd545c>Getting started</h2><!----></div><div class="items" data-v-8ccd545c><!--[--><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Overview</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/quickstart.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Building your first agent</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-9c447dd5><section class="VPSidebarItem level-0 collapsible" data-v-9c447dd5 data-v-8ccd545c><div class="item" role="button" tabindex="0" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><h2 class="text" data-v-8ccd545c>Integrations</h2><div class="caret" role="button" aria-label="toggle section" tabindex="0" data-v-8ccd545c><span class="vpi-chevron-right caret-icon" data-v-8ccd545c></span></div></div><div class="items" data-v-8ccd545c><!--[--><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/guides/github.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>GitHub</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/guides/slack.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Slack</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/guides/webhooks.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Webhooks</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/guides/convert-automation.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Cursor Automations</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/guides/opentelemetry.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>OpenTelemetry</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/guides/gitlab.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>GitLab</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/guides/bitbucket.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Bitbucket</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-9c447dd5><section class="VPSidebarItem level-0 collapsible" data-v-9c447dd5 data-v-8ccd545c><div class="item" role="button" tabindex="0" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><h2 class="text" data-v-8ccd545c>Extensions</h2><div class="caret" role="button" aria-label="toggle section" tabindex="0" data-v-8ccd545c><span class="vpi-chevron-right caret-icon" data-v-8ccd545c></span></div></div><div class="items" data-v-8ccd545c><!--[--><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/reference/extensions.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Overview</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/guides/cloud-agents.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Cloud agents</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/guides/grokbot-agents.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Grok Bot agents</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/guides/improve.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Self-improvement</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/guides/jev.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Jev</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-9c447dd5><section class="VPSidebarItem level-0 collapsible" data-v-9c447dd5 data-v-8ccd545c><div class="item" role="button" tabindex="0" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><h2 class="text" data-v-8ccd545c>Guides</h2><div class="caret" role="button" aria-label="toggle section" tabindex="0" data-v-8ccd545c><span class="vpi-chevron-right caret-icon" data-v-8ccd545c></span></div></div><div class="items" data-v-8ccd545c><!--[--><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/guides/mcp-oauth.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>MCP</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/guides/hooks.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Hooks</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/guides/agent-to-agent.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Peer agents</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/deployment.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Deployment</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/guides/migrate.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Early-alpha migration</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/evals.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Evals</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/hillclimbing.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Hillclimbing</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/building-with-agents.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Build with a coding agent</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/troubleshooting.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Troubleshooting</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-9c447dd5><section class="VPSidebarItem level-0 collapsible" data-v-9c447dd5 data-v-8ccd545c><div class="item" role="button" tabindex="0" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><h2 class="text" data-v-8ccd545c>Templates</h2><div class="caret" role="button" aria-label="toggle section" tabindex="0" data-v-8ccd545c><span class="vpi-chevron-right caret-icon" data-v-8ccd545c></span></div></div><div class="items" data-v-8ccd545c><!--[--><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/templates/grokbot-agents.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Grok Bot agents</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/templates/security-reviewer.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Security reviewer</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/templates/thermo-review.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Thermo review</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/templates/thermo-quality-review.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Thermo quality review</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/templates/agentic-owners.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Agentic Approver</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/templates/triage.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Triage agent</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-9c447dd5><section class="VPSidebarItem level-0 collapsible has-active" data-v-9c447dd5 data-v-8ccd545c><div class="item" role="button" tabindex="0" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><h2 class="text" data-v-8ccd545c>Reference</h2><div class="caret" role="button" aria-label="toggle section" tabindex="0" data-v-8ccd545c><span class="vpi-chevron-right caret-icon" data-v-8ccd545c></span></div></div><div class="items" data-v-8ccd545c><!--[--><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/reference/project-layout.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Project layout</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/reference/agent-config.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Agent config</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/reference/instructions.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Instructions</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/reference/tools.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Tools</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/reference/prompt.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>prompt</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/reference/skills.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Skills</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/reference/connections.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>MCP Connections</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/reference/subagents.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Subagents</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/reference/channels.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Channels</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/reference/schedules.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Schedules & reminders</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/reference/hooks.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Hooks</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/reference/evals.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Evals</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/reference/artifacts.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Artifacts</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/reference/sessions.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Sessions & streaming</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/reference/playground.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Playground</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/reference/cli.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>CLI</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/reference/http-api.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>HTTP API</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><!--]--><!--[--><!--]--></nav></aside><div class="VPContent has-sidebar" id="VPContent" data-v-5ebc75e4 data-v-4ab733be><div class="VPDoc has-sidebar has-aside" data-v-4ab733be data-v-4e7466dc><!--[--><!--]--><div class="container" data-v-4e7466dc><div class="aside" data-v-4e7466dc><div class="aside-curtain" data-v-4e7466dc></div><div class="aside-container" data-v-4e7466dc><div class="aside-content" data-v-4e7466dc><div class="VPDocAside" data-v-4e7466dc data-v-4f3f9a30><!--[--><!--]--><!--[--><!--]--><nav aria-labelledby="doc-outline-aria-label" class="VPDocAsideOutline" data-v-4f3f9a30 data-v-aacbb3fc><div class="content" data-v-aacbb3fc><div class="outline-marker" data-v-aacbb3fc></div><div aria-level="2" class="outline-title" id="doc-outline-aria-label" role="heading" data-v-aacbb3fc>On this page</div><ul class="VPDocOutlineItem root" data-v-aacbb3fc data-v-0ffefe2a><!--[--><!--]--></ul></div></nav><!--[--><!--]--><div class="spacer" data-v-4f3f9a30></div><!--[--><!--]--><!----><!--[--><!--]--><!--[--><!--]--></div></div></div></div><div class="content" data-v-4e7466dc><div class="content-container" data-v-4e7466dc><!--[--><!--]--><main class="main" data-v-4e7466dc><div style="position:relative;" class="vp-doc _docs_reference_evals" data-v-4e7466dc><div><h1 id="evals" tabindex="-1">Evals <a class="header-anchor" href="#evals" aria-label="Permalink to &quot;Evals&quot;">​</a></h1><p>Evals run fixed cases against an agent and record whether its turns, tools, events, and output meet a contract. Files under the project-root <code>evals/</code> directory define cases with <code>@cursor/bdk/evals</code>; the runner discovers their IDs, executes them, and reports every assertion. See the <a href="./../evals.html">Evals guide</a> for the regression workflow.</p><h2 id="eval-discovery-and-case-ids" tabindex="-1">Eval discovery and case IDs <a class="header-anchor" href="#eval-discovery-and-case-ids" aria-label="Permalink to &quot;Eval discovery and case IDs&quot;">​</a></h2><p>Eval files live under the project-root <code>evals/</code> directory and end in <code>.eval.ts</code> or <code>.eval.js</code>. The path under that directory becomes the eval ID:</p><ul><li><code>evals/readiness.eval.ts</code> becomes <code>readiness</code>.</li><li><code>evals/builds/api.eval.ts</code> becomes <code>builds/api</code>.</li><li><code>evals/builds/index.eval.ts</code> becomes <code>builds</code>.</li></ul><p>Export one <code>defineEval</code> with either <code>test</code> or <code>cases</code>, not both. A case ID appends one path segment to the file ID:</p><div class="language-ts vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">ts</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;">export</span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;"> default</span><span style="--shiki-light:#6F42C1;--shiki-dark:#B392F0;"> defineEval</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">({</span></span>
+    <div id="app"><div class="Layout" data-v-5ebc75e4><!--[--><!--]--><!--[--><span tabindex="-1" data-v-7de63af3></span><a href="#VPContent" class="VPSkipLink visually-hidden" data-v-7de63af3>Skip to content</a><!--]--><!----><header class="VPNav" data-v-5ebc75e4 data-v-e8579816><div class="VPNavBar" data-v-e8579816 data-v-bbf4446f><div class="wrapper" data-v-bbf4446f><div class="container" data-v-bbf4446f><div class="title" data-v-bbf4446f><div class="VPNavBarTitle has-sidebar" data-v-bbf4446f data-v-ebd5f04e><a class="title" href="/docs/" data-v-ebd5f04e><!--[--><!--]--><!----><span data-v-ebd5f04e>Grok Bot Development Kit (BDK)</span><!--[--><!--[--><!--[--><!--[--><span class="bdk-version" title="BDK 0.2.15 (@cursor/bdk package)" data-v-d89e5038>0.2.15</span><!--]--><!--]--><!--]--><!--]--></a></div></div><div class="content" data-v-bbf4446f><div class="content-body" data-v-bbf4446f><!--[--><!--]--><div class="VPNavBarSearch search" data-v-bbf4446f><!--[--><!----><div id="local-search"><button type="button" class="DocSearch DocSearch-Button" aria-label="Search"><span class="DocSearch-Button-Container"><span class="vp-icon DocSearch-Search-Icon"></span><span class="DocSearch-Button-Placeholder">Search</span></span><span class="DocSearch-Button-Keys"><kbd class="DocSearch-Button-Key"></kbd><kbd class="DocSearch-Button-Key">K</kbd></span></button></div><!--]--></div><nav aria-labelledby="main-nav-aria-label" class="VPNavBarMenu menu" data-v-bbf4446f data-v-7fa90d1c><span id="main-nav-aria-label" class="visually-hidden" data-v-7fa90d1c> Main Navigation </span><!--[--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/quickstart.html" tabindex="0" data-v-7fa90d1c data-v-8d7ed182><!--[--><span data-v-8d7ed182>Quickstart</span><!--]--></a><!--]--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/guides/mcp-oauth.html" tabindex="0" data-v-7fa90d1c data-v-8d7ed182><!--[--><span data-v-8d7ed182>Guides</span><!--]--></a><!--]--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/guides/github.html" tabindex="0" data-v-7fa90d1c data-v-8d7ed182><!--[--><span data-v-8d7ed182>Integrations</span><!--]--></a><!--]--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/templates/security-reviewer.html" tabindex="0" data-v-7fa90d1c data-v-8d7ed182><!--[--><span data-v-8d7ed182>Templates</span><!--]--></a><!--]--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/reference/project-layout.html" tabindex="0" data-v-7fa90d1c data-v-8d7ed182><!--[--><span data-v-8d7ed182>Reference</span><!--]--></a><!--]--><!--]--></nav><!----><div class="VPNavBarAppearance appearance" data-v-bbf4446f data-v-6a44a4fa><button class="VPSwitch VPSwitchAppearance" type="button" role="switch" title aria-checked="false" data-v-6a44a4fa data-v-b541f24b data-v-a48af969><span class="check" data-v-a48af969><span class="icon" data-v-a48af969><!--[--><span class="vpi-sun sun" data-v-b541f24b></span><span class="vpi-moon moon" data-v-b541f24b></span><!--]--></span></span></button></div><!----><div class="VPFlyout VPNavBarExtra extra" data-v-bbf4446f data-v-8d21ceac data-v-269c0ea1><button type="button" class="button" aria-haspopup="true" aria-expanded="false" aria-label="extra navigation" data-v-269c0ea1><span class="vpi-more-horizontal icon" data-v-269c0ea1></span></button><div class="menu" data-v-269c0ea1><div class="VPMenu" data-v-269c0ea1 data-v-ab92b832><!----><!--[--><!--[--><!----><div class="group" data-v-8d21ceac><div class="item appearance" data-v-8d21ceac><p class="label" data-v-8d21ceac>Appearance</p><div class="appearance-action" data-v-8d21ceac><button class="VPSwitch VPSwitchAppearance" type="button" role="switch" title aria-checked="false" data-v-8d21ceac data-v-b541f24b data-v-a48af969><span class="check" data-v-a48af969><span class="icon" data-v-a48af969><!--[--><span class="vpi-sun sun" data-v-b541f24b></span><span class="vpi-moon moon" data-v-b541f24b></span><!--]--></span></span></button></div></div></div><!----><!--]--><!--]--></div></div></div><!--[--><!--]--><button type="button" class="VPNavBarHamburger hamburger" aria-label="mobile navigation" aria-expanded="false" aria-controls="VPNavScreen" data-v-bbf4446f data-v-efff335d><span class="container" data-v-efff335d><span class="top" data-v-efff335d></span><span class="middle" data-v-efff335d></span><span class="bottom" data-v-efff335d></span></span></button></div></div></div></div><div class="divider" data-v-bbf4446f><div class="divider-line" data-v-bbf4446f></div></div></div><!----></header><div class="VPLocalNav has-sidebar empty" data-v-5ebc75e4 data-v-636a9279><div class="container" data-v-636a9279><button class="menu" aria-expanded="false" aria-controls="VPSidebarNav" data-v-636a9279><span class="vpi-align-left menu-icon" data-v-636a9279></span><span class="menu-text" data-v-636a9279>Menu</span></button><div class="VPLocalNavOutlineDropdown" style="--vp-vh:0px;" data-v-636a9279 data-v-ae38d8b4><button data-v-ae38d8b4>Return to top</button><!----></div></div></div><aside class="VPSidebar" data-v-5ebc75e4 data-v-f102723c><div class="curtain" data-v-f102723c></div><nav class="nav" id="VPSidebarNav" aria-labelledby="sidebar-aria-label" tabindex="-1" data-v-f102723c><span class="visually-hidden" id="sidebar-aria-label" data-v-f102723c> Sidebar Navigation </span><!--[--><!--]--><!--[--><div class="no-transition group" data-v-9c447dd5><section class="VPSidebarItem level-0" data-v-9c447dd5 data-v-8ccd545c><div class="item" role="button" tabindex="0" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><h2 class="text" data-v-8ccd545c>Getting started</h2><!----></div><div class="items" data-v-8ccd545c><!--[--><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Overview</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/quickstart.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Building your first agent</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-9c447dd5><section class="VPSidebarItem level-0 collapsible" data-v-9c447dd5 data-v-8ccd545c><div class="item" role="button" tabindex="0" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><h2 class="text" data-v-8ccd545c>Integrations</h2><div class="caret" role="button" aria-label="toggle section" tabindex="0" data-v-8ccd545c><span class="vpi-chevron-right caret-icon" data-v-8ccd545c></span></div></div><div class="items" data-v-8ccd545c><!--[--><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/guides/github.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>GitHub</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/guides/slack.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Slack</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/guides/webhooks.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Webhooks</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/guides/convert-automation.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Cursor Automations</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/guides/opentelemetry.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>OpenTelemetry</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/guides/gitlab.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>GitLab</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/guides/bitbucket.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Bitbucket</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-9c447dd5><section class="VPSidebarItem level-0 collapsible" data-v-9c447dd5 data-v-8ccd545c><div class="item" role="button" tabindex="0" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><h2 class="text" data-v-8ccd545c>Extensions</h2><div class="caret" role="button" aria-label="toggle section" tabindex="0" data-v-8ccd545c><span class="vpi-chevron-right caret-icon" data-v-8ccd545c></span></div></div><div class="items" data-v-8ccd545c><!--[--><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/reference/extensions.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Overview</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/guides/cloud-agents.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Cloud agents</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/guides/grokbot-agents.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Grok Bot agents</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/guides/improve.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Self-improvement</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/guides/jev.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Jev</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-9c447dd5><section class="VPSidebarItem level-0 collapsible" data-v-9c447dd5 data-v-8ccd545c><div class="item" role="button" tabindex="0" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><h2 class="text" data-v-8ccd545c>Guides</h2><div class="caret" role="button" aria-label="toggle section" tabindex="0" data-v-8ccd545c><span class="vpi-chevron-right caret-icon" data-v-8ccd545c></span></div></div><div class="items" data-v-8ccd545c><!--[--><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/guides/mcp-oauth.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>MCP</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/guides/hooks.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Hooks</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/guides/agent-to-agent.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Peer agents</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/deployment.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Deployment</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/guides/migrate.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Early-alpha migration</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/evals.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Evals</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/hillclimbing.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Hillclimbing</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/building-with-agents.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Build with a coding agent</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/troubleshooting.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Troubleshooting</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-9c447dd5><section class="VPSidebarItem level-0 collapsible" data-v-9c447dd5 data-v-8ccd545c><div class="item" role="button" tabindex="0" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><h2 class="text" data-v-8ccd545c>Templates</h2><div class="caret" role="button" aria-label="toggle section" tabindex="0" data-v-8ccd545c><span class="vpi-chevron-right caret-icon" data-v-8ccd545c></span></div></div><div class="items" data-v-8ccd545c><!--[--><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/templates/grokbot-agents.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Grok Bot agents</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/templates/security-reviewer.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Security reviewer</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/templates/thermo-review.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Thermo review</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/templates/thermo-quality-review.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Thermo quality review</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/templates/agentic-owners.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Agentic Approver</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/templates/triage.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Triage agent</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-9c447dd5><section class="VPSidebarItem level-0 collapsible has-active" data-v-9c447dd5 data-v-8ccd545c><div class="item" role="button" tabindex="0" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><h2 class="text" data-v-8ccd545c>Reference</h2><div class="caret" role="button" aria-label="toggle section" tabindex="0" data-v-8ccd545c><span class="vpi-chevron-right caret-icon" data-v-8ccd545c></span></div></div><div class="items" data-v-8ccd545c><!--[--><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/reference/project-layout.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Project layout</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/reference/agent-config.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Agent config</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/reference/instructions.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Instructions</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/reference/tools.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Tools</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/reference/prompt.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>prompt</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/reference/skills.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Skills</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/reference/connections.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>MCP Connections</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/reference/subagents.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Subagents</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/reference/channels.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Channels</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/reference/schedules.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Schedules & reminders</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/reference/hooks.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Hooks</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/reference/evals.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Evals</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/reference/artifacts.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Artifacts</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/reference/sessions.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Sessions & streaming</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/reference/playground.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>Playground</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/reference/cli.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>CLI</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-8ccd545c><div class="item" data-v-8ccd545c><div class="indicator" data-v-8ccd545c></div><a class="VPLink link link" href="/docs/reference/http-api.html" data-v-8ccd545c><!--[--><p class="text" data-v-8ccd545c>HTTP API</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><!--]--><!--[--><!--]--></nav></aside><div class="VPContent has-sidebar" id="VPContent" data-v-5ebc75e4 data-v-4ab733be><div class="VPDoc has-sidebar has-aside" data-v-4ab733be data-v-4e7466dc><!--[--><!--]--><div class="container" data-v-4e7466dc><div class="aside" data-v-4e7466dc><div class="aside-curtain" data-v-4e7466dc></div><div class="aside-container" data-v-4e7466dc><div class="aside-content" data-v-4e7466dc><div class="VPDocAside" data-v-4e7466dc data-v-4f3f9a30><!--[--><!--]--><!--[--><!--]--><nav aria-labelledby="doc-outline-aria-label" class="VPDocAsideOutline" data-v-4f3f9a30 data-v-aacbb3fc><div class="content" data-v-aacbb3fc><div class="outline-marker" data-v-aacbb3fc></div><div aria-level="2" class="outline-title" id="doc-outline-aria-label" role="heading" data-v-aacbb3fc>On this page</div><ul class="VPDocOutlineItem root" data-v-aacbb3fc data-v-0ffefe2a><!--[--><!--]--></ul></div></nav><!--[--><!--]--><div class="spacer" data-v-4f3f9a30></div><!--[--><!--]--><!----><!--[--><!--]--><!--[--><!--]--></div></div></div></div><div class="content" data-v-4e7466dc><div class="content-container" data-v-4e7466dc><!--[--><!--]--><main class="main" data-v-4e7466dc><div style="position:relative;" class="vp-doc _docs_reference_evals" data-v-4e7466dc><div><h1 id="evals" tabindex="-1">Evals <a class="header-anchor" href="#evals" aria-label="Permalink to &quot;Evals&quot;">​</a></h1><p>Evals run fixed cases against an agent and record whether its turns, tools, events, and output meet a contract. Files under the project-root <code>evals/</code> directory define cases with <code>@cursor/bdk/evals</code>; the runner discovers their IDs, executes them, and reports every assertion. See the <a href="./../evals.html">Evals guide</a> for the regression workflow.</p><h2 id="eval-discovery-and-case-ids" tabindex="-1">Eval discovery and case IDs <a class="header-anchor" href="#eval-discovery-and-case-ids" aria-label="Permalink to &quot;Eval discovery and case IDs&quot;">​</a></h2><p>Eval files live under the project-root <code>evals/</code> directory and end in <code>.eval.ts</code> or <code>.eval.js</code>. The path under that directory becomes the eval ID:</p><ul><li><code>evals/readiness.eval.ts</code> becomes <code>readiness</code>.</li><li><code>evals/builds/api.eval.ts</code> becomes <code>builds/api</code>.</li><li><code>evals/builds/index.eval.ts</code> becomes <code>builds</code>.</li></ul><p>Export one <code>defineEval</code> with either <code>test</code> or <code>cases</code>, not both. A case ID appends one path segment to the file ID:</p><div class="language-ts vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">ts</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;">export</span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;"> default</span><span style="--shiki-light:#6F42C1;--shiki-dark:#B392F0;"> defineEval</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">({</span></span>
 <span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">  tags: [</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">&quot;smoke&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">],</span></span>
 <span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">  cases: [</span></span>
 <span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">    {</span></span>
@@ -77,7 +77,7 @@
 <span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">  maxConcurrency: </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">20</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">,</span></span>
 <span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">  timeoutMs: </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">180_000</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">,</span></span>
 <span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">  judge: { model: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">&quot;gpt-5.4-mini&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> },</span></span>
-<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">});</span></span></code></pre></div><table tabindex="0"><thead><tr><th>Option</th><th>Contract</th></tr></thead><tbody><tr><td><code>maxConcurrency</code></td><td>Required; concurrent authored datapoints, from 1 to 200</td></tr><tr><td><code>timeoutMs</code></td><td>Per-case timeout; case/file, CLI, then config precedence</td></tr><tr><td><code>judge</code></td><td>Default model for <code>t.judge</code></td></tr><tr><td><code>reporters</code></td><td>Objects notified as cases and runs complete</td></tr><tr><td><code>maxPlaygroundRuns</code></td><td>Number of server-side batches kept in playground history; defaults to 20</td></tr></tbody></table><p>A case can override <code>description</code>, <code>tags</code>, <code>timeoutMs</code>, <code>iterations</code>, <code>judge</code>, <code>reporters</code>, and <code>metadata</code>. Case metadata merges over file-level metadata; case reporters add to the file&#39;s reporters.</p><h2 id="send-turns-in-a-case" tabindex="-1">Send turns in a case <a class="header-anchor" href="#send-turns-in-a-case" aria-label="Permalink to &quot;Send turns in a case&quot;">​</a></h2><p><code>await t.send(message, options?)</code> runs one turn and waits until it finishes, fails, or parks for approval. Several sends in one test share the session.</p><p>The returned turn exposes its assistant <code>message</code>, <code>sessionId</code>, <code>events</code>, ordered <code>toolCalls</code>, <code>ok</code>, and one-based <code>index</code>. Assertions on the turn inspect only that turn; assertions on <code>t</code> inspect the whole case. Run values include <code>t.reply</code>, <code>t.events</code>, <code>t.turns</code>, <code>t.sessionId</code>, <code>t.iteration</code>, <code>t.iterations</code>, and the timeout <code>t.signal</code>.</p><p>These options apply on the first send because they shape the session:</p><table tabindex="0"><thead><tr><th>Option</th><th>Contract</th></tr></thead><tbody><tr><td><code>workspaceFiles</code></td><td>Relative path-to-content map seeded into the session workspace</td></tr><tr><td><code>workspaceDir</code></td><td>Absolute working directory for a new local session</td></tr></tbody></table><p>Use <code>turn.expectOk()</code> when later test steps depend on the turn succeeding. It throws when the turn failed.</p><h2 id="trajectory-assertions" tabindex="-1">Trajectory assertions <a class="header-anchor" href="#trajectory-assertions" aria-label="Permalink to &quot;Trajectory assertions&quot;">​</a></h2><p>Assertions record failures without stopping the test, so one case reports every violated contract.</p><table tabindex="0"><thead><tr><th>Assertion</th><th>Checks</th></tr></thead><tbody><tr><td><code>t.succeeded()</code></td><td>Run finished without failure or an unanswered approval</td></tr><tr><td><code>t.parked()</code></td><td>Run stopped on an unanswered approval</td></tr><tr><td><code>t.calledTool(name, matcher?)</code></td><td>Matching tool request occurred</td></tr><tr><td><code>t.notCalledTool(name)</code></td><td>No request for that tool occurred</td></tr><tr><td><code>t.loadedSkill(name)</code></td><td>Agent opened a named skill</td></tr><tr><td><code>t.toolOrder(names)</code></td><td>Tool requests appeared in relative order</td></tr><tr><td><code>t.usedNoTools()</code></td><td>No tool was requested</td></tr><tr><td><code>t.maxToolCalls(max)</code></td><td>Tool-call count stayed under the bound</td></tr><tr><td><code>t.noFailedActions()</code></td><td>No tool result failed</td></tr><tr><td><code>t.calledSubagent(name, matcher?)</code></td><td>Matching subagent call occurred</td></tr><tr><td><code>t.taggedArtifact(kind?, predicate?)</code></td><td>Matching durable artifact was tagged</td></tr><tr><td><code>t.event(type, matcher?)</code></td><td>Matching session event occurred</td></tr><tr><td><code>t.notEvent(type, matcher?)</code></td><td>Matching session event did not occur</td></tr><tr><td><code>t.eventOrder(matchers)</code></td><td>Event groups appeared in relative order</td></tr><tr><td><code>t.eventsSatisfy(label, predicate)</code></td><td>Predicate accepted the event stream</td></tr><tr><td><code>t.check(value, expectation)</code></td><td>Value met an expectation builder</td></tr><tr><td><code>t.score(name, value)</code></td><td>Recorded a numeric score from 0 to 1</td></tr></tbody></table><p><code>t.requireToolCall</code>, <code>t.requireInputRequest</code>, and <code>t.require</code> return the matched value and stop the remaining test body when no match exists.</p><h2 id="tool-and-event-matchers" tabindex="-1">Tool and event matchers <a class="header-anchor" href="#tool-and-event-matchers" aria-label="Permalink to &quot;Tool and event matchers&quot;">​</a></h2><p>Tool matchers can narrow by <code>input</code>, <code>output</code>, <code>status</code>, and <code>count</code>. Values accept literals, regular expressions, or predicates. Object literals partial-deep-match:</p><div class="language-ts vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">ts</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">t.</span><span style="--shiki-light:#6F42C1;--shiki-dark:#B392F0;">calledTool</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">(</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">&quot;inspect_pr&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">, {</span></span>
+<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">});</span></span></code></pre></div><table tabindex="0"><thead><tr><th>Option</th><th>Contract</th></tr></thead><tbody><tr><td><code>maxConcurrency</code></td><td>Required; concurrent authored datapoints, from 1 to 200</td></tr><tr><td><code>timeoutMs</code></td><td>Per-case timeout; case/file, CLI, then config precedence</td></tr><tr><td><code>judge</code></td><td>Default model for <code>t.judge</code></td></tr><tr><td><code>reporters</code></td><td>Objects notified as cases and runs complete</td></tr><tr><td><code>maxPlaygroundRuns</code></td><td>Number of server-side batches kept in playground history; defaults to 20</td></tr></tbody></table><p>A case can override <code>description</code>, <code>tags</code>, <code>timeoutMs</code>, <code>iterations</code>, <code>judge</code>, <code>reporters</code>, and <code>metadata</code>. Case metadata merges over file-level metadata; case reporters add to the file&#39;s reporters.</p><h2 id="send-turns-in-a-case" tabindex="-1">Send turns in a case <a class="header-anchor" href="#send-turns-in-a-case" aria-label="Permalink to &quot;Send turns in a case&quot;">​</a></h2><p><code>await t.send(message, options?)</code> runs one turn and waits until it finishes or fails. Several sends in one test share the session.</p><p>The returned turn exposes its assistant <code>message</code>, <code>sessionId</code>, <code>events</code>, ordered <code>toolCalls</code>, <code>ok</code>, and one-based <code>index</code>. Assertions on the turn inspect only that turn; assertions on <code>t</code> inspect the whole case. Run values include <code>t.reply</code>, <code>t.events</code>, <code>t.turns</code>, <code>t.sessionId</code>, <code>t.iteration</code>, <code>t.iterations</code>, and the timeout <code>t.signal</code>.</p><p>These options apply on the first send because they shape the session:</p><table tabindex="0"><thead><tr><th>Option</th><th>Contract</th></tr></thead><tbody><tr><td><code>workspaceFiles</code></td><td>Relative path-to-content map seeded into the session workspace</td></tr><tr><td><code>workspaceDir</code></td><td>Absolute working directory for a new local session</td></tr></tbody></table><p>Use <code>turn.expectOk()</code> when later test steps depend on the turn succeeding. It throws when the turn failed.</p><h2 id="trajectory-assertions" tabindex="-1">Trajectory assertions <a class="header-anchor" href="#trajectory-assertions" aria-label="Permalink to &quot;Trajectory assertions&quot;">​</a></h2><p>Assertions record failures without stopping the test, so one case reports every violated contract.</p><table tabindex="0"><thead><tr><th>Assertion</th><th>Checks</th></tr></thead><tbody><tr><td><code>t.succeeded()</code></td><td>Run finished without failure</td></tr><tr><td><code>t.calledTool(name, matcher?)</code></td><td>Matching tool request occurred</td></tr><tr><td><code>t.notCalledTool(name)</code></td><td>No request for that tool occurred</td></tr><tr><td><code>t.loadedSkill(name)</code></td><td>Agent opened a named skill</td></tr><tr><td><code>t.toolOrder(names)</code></td><td>Tool requests appeared in relative order</td></tr><tr><td><code>t.usedNoTools()</code></td><td>No tool was requested</td></tr><tr><td><code>t.maxToolCalls(max)</code></td><td>Tool-call count stayed under the bound</td></tr><tr><td><code>t.noFailedActions()</code></td><td>No tool result failed</td></tr><tr><td><code>t.calledSubagent(name, matcher?)</code></td><td>Matching subagent call occurred</td></tr><tr><td><code>t.taggedArtifact(kind?, predicate?)</code></td><td>Matching durable artifact was tagged</td></tr><tr><td><code>t.event(type, matcher?)</code></td><td>Matching session event occurred</td></tr><tr><td><code>t.notEvent(type, matcher?)</code></td><td>Matching session event did not occur</td></tr><tr><td><code>t.eventOrder(matchers)</code></td><td>Event groups appeared in relative order</td></tr><tr><td><code>t.eventsSatisfy(label, predicate)</code></td><td>Predicate accepted the event stream</td></tr><tr><td><code>t.check(value, expectation)</code></td><td>Value met an expectation builder</td></tr><tr><td><code>t.score(name, value)</code></td><td>Recorded a numeric score from 0 to 1</td></tr></tbody></table><p><code>t.requireToolCall</code>, <code>t.requireInputRequest</code>, and <code>t.require</code> return the matched value and stop the remaining test body when no match exists.</p><h2 id="tool-and-event-matchers" tabindex="-1">Tool and event matchers <a class="header-anchor" href="#tool-and-event-matchers" aria-label="Permalink to &quot;Tool and event matchers&quot;">​</a></h2><p>Tool matchers can narrow by <code>input</code>, <code>output</code>, <code>status</code>, and <code>count</code>. Values accept literals, regular expressions, or predicates. Object literals partial-deep-match:</p><div class="language-ts vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">ts</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">t.</span><span style="--shiki-light:#6F42C1;--shiki-dark:#B392F0;">calledTool</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">(</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">&quot;inspect_pr&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">, {</span></span>
 <span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">  input: { verdict: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">&quot;review&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> },</span></span>
 <span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">  status: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">&quot;completed&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">,</span></span>
 <span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">  count: </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">1</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">,</span></span>
@@ -109,7 +109,7 @@
 <span class="line"><span>bdk eval --dir . --tag smoke</span></span></code></pre></div><p>ID filters match an exact ID and its descendants. Repeated IDs use OR; repeated tags use OR. When both are present, a case must match both groups.</p><h2 id="inspect-run-artifacts" tabindex="-1">Inspect run artifacts <a class="header-anchor" href="#inspect-run-artifacts" aria-label="Permalink to &quot;Inspect run artifacts&quot;">​</a></h2><p>Default run artifacts go under <code>evals/&lt;stamp&gt;/</code> in the project state directory and include <code>summary.json</code>, <code>results.jsonl</code>, and <code>evals/&lt;case-id&gt;.json</code>. <code>--artifacts &lt;dir&gt;</code> chooses another destination; <code>--no-artifacts</code> disables them. This location is independent of <code>--state-root</code>.</p><h2 id="run-evals-against-a-server" tabindex="-1">Run evals against a server <a class="header-anchor" href="#run-evals-against-a-server" aria-label="Permalink to &quot;Run evals against a server&quot;">​</a></h2><p>The playground <strong>Evals</strong> view starts batches on its running server, and <code>--url</code> targets a named running server:</p><div class="language-text vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">text</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span>bdk eval --url http://127.0.0.1:3000/vulnerability-scanner --tag smoke</span></span>
 <span class="line"><span>bdk eval status &lt;eval-id&gt; --url http://127.0.0.1:3000/vulnerability-scanner</span></span>
 <span class="line"><span>bdk eval cancel &lt;eval-id&gt; --url http://127.0.0.1:3000/vulnerability-scanner</span></span></code></pre></div><p>Server-side batches use the target&#39;s discovered cases and return an eval ID for <code>status</code> or <code>cancel</code>. Local reporter and concurrency flags don&#39;t apply to <code>--url</code> runs.</p><h2 id="related" tabindex="-1">Related <a class="header-anchor" href="#related" aria-label="Permalink to &quot;Related&quot;">​</a></h2><ul><li><a href="./../evals.html">Evals guide</a></li><li><a href="./cli.html#eval">CLI reference</a></li><li><a href="./sessions.html">Sessions</a></li><li><a href="./artifacts.html">Artifacts</a></li></ul></div></div></main><footer class="VPDocFooter" data-v-4e7466dc data-v-5e6607d6><!--[--><!--]--><!----><nav class="prev-next" aria-labelledby="doc-footer-aria-label" data-v-5e6607d6><span class="visually-hidden" id="doc-footer-aria-label" data-v-5e6607d6>Pager</span><div class="pager" data-v-5e6607d6><a class="VPLink link pager-link prev" href="/docs/reference/hooks.html" data-v-5e6607d6><!--[--><span class="desc" data-v-5e6607d6>Previous page</span><span class="title" data-v-5e6607d6>Hooks</span><!--]--></a></div><div class="pager" data-v-5e6607d6><a class="VPLink link pager-link next" href="/docs/reference/artifacts.html" data-v-5e6607d6><!--[--><span class="desc" data-v-5e6607d6>Next page</span><span class="title" data-v-5e6607d6>Artifacts</span><!--]--></a></div></nav></footer><!--[--><!--]--></div></div></div><!--[--><!--]--></div></div><!----><!--[--><!--]--></div></div>
-    <script>window.__VP_HASH_MAP__=JSON.parse("{\"building-with-agents.md\":\"Df87rAe1\",\"deployment.md\":\"BYuEcDBv\",\"evals.md\":\"C851kViu\",\"guides_agent-to-agent.md\":\"Cps5NiCV\",\"guides_bitbucket.md\":\"CKUayYtD\",\"guides_cloud-agents.md\":\"CWJjS9No\",\"guides_convert-automation.md\":\"DMEX9nF-\",\"guides_github.md\":\"TuNiZAOQ\",\"guides_gitlab.md\":\"CtNI4fSH\",\"guides_grokbot-agents.md\":\"tD1smFhU\",\"guides_hooks.md\":\"5Ce3NXxZ\",\"guides_improve.md\":\"CRrYq22s\",\"guides_jev.md\":\"D7XH4JH3\",\"guides_mcp-oauth.md\":\"DR3zhC9r\",\"guides_migrate.md\":\"sCAvvlC6\",\"guides_opentelemetry.md\":\"jcPNrQbH\",\"guides_slack.md\":\"Bn-WupSE\",\"guides_webhooks.md\":\"BBvAm_VF\",\"hillclimbing.md\":\"Dxvd-0gT\",\"index.md\":\"Dxxr7pFa\",\"quickstart.md\":\"BK5gjHM2\",\"reference_agent-config.md\":\"DrtLxWgR\",\"reference_artifacts.md\":\"DLV9MZES\",\"reference_channels.md\":\"LbNIJBwd\",\"reference_cli.md\":\"dYCAL2lB\",\"reference_connections.md\":\"DLrgAd5f\",\"reference_evals.md\":\"D5i8PuXJ\",\"reference_extensions.md\":\"OUacPetl\",\"reference_hooks.md\":\"B-eGa2km\",\"reference_http-api.md\":\"DbFNOubV\",\"reference_instructions.md\":\"DrcHZXig\",\"reference_playground.md\":\"1hx0gcIu\",\"reference_project-layout.md\":\"C2JMRh7p\",\"reference_prompt.md\":\"DqPh71XN\",\"reference_schedules.md\":\"BuJ8fgMa\",\"reference_sessions.md\":\"CyM7ARz1\",\"reference_skills.md\":\"C0guGcH0\",\"reference_subagents.md\":\"gmPt5J-M\",\"reference_tools.md\":\"DzIY9JzY\",\"templates_agentic-owners.md\":\"CvmABtia\",\"templates_grokbot-agents.md\":\"2sydjFiO\",\"templates_security-reviewer.md\":\"Gh6EF9Us\",\"templates_thermo-quality-review.md\":\"B77UyTrX\",\"templates_thermo-review.md\":\"DRJ7mC5U\",\"templates_triage.md\":\"CNN6b0JZ\",\"troubleshooting.md\":\"x-GBa7wN\"}");window.__VP_SITE_DATA__=JSON.parse("{\"lang\":\"en-US\",\"dir\":\"ltr\",\"title\":\"Grok Bot Development Kit (BDK)\",\"description\":\"Build and serve bots and agents from versioned Markdown and TypeScript.\",\"base\":\"/docs/\",\"head\":[],\"router\":{\"prefetchLinks\":true},\"appearance\":true,\"themeConfig\":{\"sdkVersion\":\"0.2.13\",\"nav\":[{\"text\":\"Quickstart\",\"link\":\"/quickstart\"},{\"text\":\"Guides\",\"link\":\"/guides/mcp-oauth\"},{\"text\":\"Integrations\",\"link\":\"/guides/github\"},{\"text\":\"Templates\",\"link\":\"/templates/security-reviewer\"},{\"text\":\"Reference\",\"link\":\"/reference/project-layout\"}],\"search\":{\"provider\":\"local\"},\"outline\":{\"level\":[2,3]},\"sidebar\":[{\"text\":\"Getting started\",\"items\":[{\"text\":\"Overview\",\"link\":\"/\"},{\"text\":\"Building your first agent\",\"link\":\"/quickstart\"}]},{\"text\":\"Integrations\",\"collapsed\":false,\"items\":[{\"text\":\"GitHub\",\"link\":\"/guides/github\"},{\"text\":\"Slack\",\"link\":\"/guides/slack\"},{\"text\":\"Webhooks\",\"link\":\"/guides/webhooks\"},{\"text\":\"Cursor Automations\",\"link\":\"/guides/convert-automation\"},{\"text\":\"OpenTelemetry\",\"link\":\"/guides/opentelemetry\"},{\"text\":\"GitLab\",\"link\":\"/guides/gitlab\"},{\"text\":\"Bitbucket\",\"link\":\"/guides/bitbucket\"}]},{\"text\":\"Extensions\",\"collapsed\":false,\"items\":[{\"text\":\"Overview\",\"link\":\"/reference/extensions\"},{\"text\":\"Cloud agents\",\"link\":\"/guides/cloud-agents\"},{\"text\":\"Grok Bot agents\",\"link\":\"/guides/grokbot-agents\"},{\"text\":\"Self-improvement\",\"link\":\"/guides/improve\"},{\"text\":\"Jev\",\"link\":\"/guides/jev\"}]},{\"text\":\"Guides\",\"collapsed\":false,\"items\":[{\"text\":\"MCP\",\"link\":\"/guides/mcp-oauth\"},{\"text\":\"Hooks\",\"link\":\"/guides/hooks\"},{\"text\":\"Peer agents\",\"link\":\"/guides/agent-to-agent\"},{\"text\":\"Deployment\",\"link\":\"/deployment\"},{\"text\":\"Early-alpha migration\",\"link\":\"/guides/migrate\"},{\"text\":\"Evals\",\"link\":\"/evals\"},{\"text\":\"Hillclimbing\",\"link\":\"/hillclimbing\"},{\"text\":\"Build with a coding agent\",\"link\":\"/building-with-agents\"},{\"text\":\"Troubleshooting\",\"link\":\"/troubleshooting\"}]},{\"text\":\"Templates\",\"collapsed\":false,\"items\":[{\"text\":\"Grok Bot agents\",\"link\":\"/templates/grokbot-agents\"},{\"text\":\"Security reviewer\",\"link\":\"/templates/security-reviewer\"},{\"text\":\"Thermo review\",\"link\":\"/templates/thermo-review\"},{\"text\":\"Thermo quality review\",\"link\":\"/templates/thermo-quality-review\"},{\"text\":\"Agentic Approver\",\"link\":\"/templates/agentic-owners\"},{\"text\":\"Triage agent\",\"link\":\"/templates/triage\"}]},{\"text\":\"Reference\",\"collapsed\":false,\"items\":[{\"text\":\"Project layout\",\"link\":\"/reference/project-layout\"},{\"text\":\"Agent config\",\"link\":\"/reference/agent-config\"},{\"text\":\"Instructions\",\"link\":\"/reference/instructions\"},{\"text\":\"Tools\",\"link\":\"/reference/tools\"},{\"text\":\"prompt\",\"link\":\"/reference/prompt\"},{\"text\":\"Skills\",\"link\":\"/reference/skills\"},{\"text\":\"MCP Connections\",\"link\":\"/reference/connections\"},{\"text\":\"Subagents\",\"link\":\"/reference/subagents\"},{\"text\":\"Channels\",\"link\":\"/reference/channels\"},{\"text\":\"Schedules & reminders\",\"link\":\"/reference/schedules\"},{\"text\":\"Hooks\",\"link\":\"/reference/hooks\"},{\"text\":\"Evals\",\"link\":\"/reference/evals\"},{\"text\":\"Artifacts\",\"link\":\"/reference/artifacts\"},{\"text\":\"Sessions & streaming\",\"link\":\"/reference/sessions\"},{\"text\":\"Playground\",\"link\":\"/reference/playground\"},{\"text\":\"CLI\",\"link\":\"/reference/cli\"},{\"text\":\"HTTP API\",\"link\":\"/reference/http-api\"}]}]},\"locales\":{},\"scrollOffset\":134,\"cleanUrls\":false}");</script>
+    <script>window.__VP_HASH_MAP__=JSON.parse("{\"building-with-agents.md\":\"Bi9CQ-bR\",\"deployment.md\":\"hKKN9I4c\",\"evals.md\":\"CHR34K1Y\",\"guides_agent-to-agent.md\":\"Cps5NiCV\",\"guides_bitbucket.md\":\"CKUayYtD\",\"guides_cloud-agents.md\":\"CBK7W0-O\",\"guides_convert-automation.md\":\"DMEX9nF-\",\"guides_github.md\":\"TuNiZAOQ\",\"guides_gitlab.md\":\"CtNI4fSH\",\"guides_grokbot-agents.md\":\"BwAykJ7U\",\"guides_hooks.md\":\"B_bKG1oA\",\"guides_improve.md\":\"CZKVt1cT\",\"guides_jev.md\":\"D7XH4JH3\",\"guides_mcp-oauth.md\":\"BM_eFC0L\",\"guides_migrate.md\":\"sCAvvlC6\",\"guides_opentelemetry.md\":\"jcPNrQbH\",\"guides_slack.md\":\"Bn-WupSE\",\"guides_webhooks.md\":\"Cpdc3BDX\",\"hillclimbing.md\":\"Dxvd-0gT\",\"index.md\":\"BIBHIQtU\",\"quickstart.md\":\"CduLGBAB\",\"reference_agent-config.md\":\"DrtLxWgR\",\"reference_artifacts.md\":\"DLV9MZES\",\"reference_channels.md\":\"DYg0CLud\",\"reference_cli.md\":\"BYNIHwbi\",\"reference_connections.md\":\"CxbLpaaP\",\"reference_evals.md\":\"if--BLd0\",\"reference_extensions.md\":\"OUacPetl\",\"reference_hooks.md\":\"DbJC8mcZ\",\"reference_http-api.md\":\"CrqhTv6S\",\"reference_instructions.md\":\"DrcHZXig\",\"reference_playground.md\":\"q4MI-0td\",\"reference_project-layout.md\":\"C2JMRh7p\",\"reference_prompt.md\":\"DqPh71XN\",\"reference_schedules.md\":\"03Ryy9ca\",\"reference_sessions.md\":\"C_uzIWuy\",\"reference_skills.md\":\"Ckddg6KX\",\"reference_subagents.md\":\"gmPt5J-M\",\"reference_tools.md\":\"08XR7lIl\",\"templates_agentic-owners.md\":\"CvmABtia\",\"templates_grokbot-agents.md\":\"DgpPEs7B\",\"templates_security-reviewer.md\":\"Gh6EF9Us\",\"templates_thermo-quality-review.md\":\"B77UyTrX\",\"templates_thermo-review.md\":\"DRJ7mC5U\",\"templates_triage.md\":\"CNN6b0JZ\",\"troubleshooting.md\":\"PCafNCb5\"}");window.__VP_SITE_DATA__=JSON.parse("{\"lang\":\"en-US\",\"dir\":\"ltr\",\"title\":\"Grok Bot Development Kit (BDK)\",\"description\":\"Build and serve bots and agents from versioned Markdown and TypeScript.\",\"base\":\"/docs/\",\"head\":[],\"router\":{\"prefetchLinks\":true},\"appearance\":true,\"themeConfig\":{\"sdkVersion\":\"0.2.15\",\"nav\":[{\"text\":\"Quickstart\",\"link\":\"/quickstart\"},{\"text\":\"Guides\",\"link\":\"/guides/mcp-oauth\"},{\"text\":\"Integrations\",\"link\":\"/guides/github\"},{\"text\":\"Templates\",\"link\":\"/templates/security-reviewer\"},{\"text\":\"Reference\",\"link\":\"/reference/project-layout\"}],\"search\":{\"provider\":\"local\"},\"outline\":{\"level\":[2,3]},\"sidebar\":[{\"text\":\"Getting started\",\"items\":[{\"text\":\"Overview\",\"link\":\"/\"},{\"text\":\"Building your first agent\",\"link\":\"/quickstart\"}]},{\"text\":\"Integrations\",\"collapsed\":false,\"items\":[{\"text\":\"GitHub\",\"link\":\"/guides/github\"},{\"text\":\"Slack\",\"link\":\"/guides/slack\"},{\"text\":\"Webhooks\",\"link\":\"/guides/webhooks\"},{\"text\":\"Cursor Automations\",\"link\":\"/guides/convert-automation\"},{\"text\":\"OpenTelemetry\",\"link\":\"/guides/opentelemetry\"},{\"text\":\"GitLab\",\"link\":\"/guides/gitlab\"},{\"text\":\"Bitbucket\",\"link\":\"/guides/bitbucket\"}]},{\"text\":\"Extensions\",\"collapsed\":false,\"items\":[{\"text\":\"Overview\",\"link\":\"/reference/extensions\"},{\"text\":\"Cloud agents\",\"link\":\"/guides/cloud-agents\"},{\"text\":\"Grok Bot agents\",\"link\":\"/guides/grokbot-agents\"},{\"text\":\"Self-improvement\",\"link\":\"/guides/improve\"},{\"text\":\"Jev\",\"link\":\"/guides/jev\"}]},{\"text\":\"Guides\",\"collapsed\":false,\"items\":[{\"text\":\"MCP\",\"link\":\"/guides/mcp-oauth\"},{\"text\":\"Hooks\",\"link\":\"/guides/hooks\"},{\"text\":\"Peer agents\",\"link\":\"/guides/agent-to-agent\"},{\"text\":\"Deployment\",\"link\":\"/deployment\"},{\"text\":\"Early-alpha migration\",\"link\":\"/guides/migrate\"},{\"text\":\"Evals\",\"link\":\"/evals\"},{\"text\":\"Hillclimbing\",\"link\":\"/hillclimbing\"},{\"text\":\"Build with a coding agent\",\"link\":\"/building-with-agents\"},{\"text\":\"Troubleshooting\",\"link\":\"/troubleshooting\"}]},{\"text\":\"Templates\",\"collapsed\":false,\"items\":[{\"text\":\"Grok Bot agents\",\"link\":\"/templates/grokbot-agents\"},{\"text\":\"Security reviewer\",\"link\":\"/templates/security-reviewer\"},{\"text\":\"Thermo review\",\"link\":\"/templates/thermo-review\"},{\"text\":\"Thermo quality review\",\"link\":\"/templates/thermo-quality-review\"},{\"text\":\"Agentic Approver\",\"link\":\"/templates/agentic-owners\"},{\"text\":\"Triage agent\",\"link\":\"/templates/triage\"}]},{\"text\":\"Reference\",\"collapsed\":false,\"items\":[{\"text\":\"Project layout\",\"link\":\"/reference/project-layout\"},{\"text\":\"Agent config\",\"link\":\"/reference/agent-config\"},{\"text\":\"Instructions\",\"link\":\"/reference/instructions\"},{\"text\":\"Tools\",\"link\":\"/reference/tools\"},{\"text\":\"prompt\",\"link\":\"/reference/prompt\"},{\"text\":\"Skills\",\"link\":\"/reference/skills\"},{\"text\":\"MCP Connections\",\"link\":\"/reference/connections\"},{\"text\":\"Subagents\",\"link\":\"/reference/subagents\"},{\"text\":\"Channels\",\"link\":\"/reference/channels\"},{\"text\":\"Schedules & reminders\",\"link\":\"/reference/schedules\"},{\"text\":\"Hooks\",\"link\":\"/reference/hooks\"},{\"text\":\"Evals\",\"link\":\"/reference/evals\"},{\"text\":\"Artifacts\",\"link\":\"/reference/artifacts\"},{\"text\":\"Sessions & streaming\",\"link\":\"/reference/sessions\"},{\"text\":\"Playground\",\"link\":\"/reference/playground\"},{\"text\":\"CLI\",\"link\":\"/reference/cli\"},{\"text\":\"HTTP API\",\"link\":\"/reference/http-api\"}]}]},\"locales\":{},\"scrollOffset\":134,\"cleanUrls\":false}");</script>
     
   </body>
 </html>

package/dist/docs/reference/evals.md

@@ -83,8 +83,7 @@ file-level metadata; case reporters add to the file's reporters.
 ## Send turns in a case
 
 `await t.send(message, options?)` runs one turn and waits until it
-finishes, fails, or parks for approval. Several sends in one test share
-the session.
+finishes or fails. Several sends in one test share the session.
 
 The returned turn exposes its assistant `message`, `sessionId`,
 `events`, ordered `toolCalls`, `ok`, and one-based `index`. Assertions
@@ -110,8 +109,7 @@ reports every violated contract.
 
 | Assertion | Checks |
 | --- | --- |
-| `t.succeeded()` | Run finished without failure or an unanswered approval |
-| `t.parked()` | Run stopped on an unanswered approval |
+| `t.succeeded()` | Run finished without failure |
 | `t.calledTool(name, matcher?)` | Matching tool request occurred |
 | `t.notCalledTool(name)` | No request for that tool occurred |
 | `t.loadedSkill(name)` | Agent opened a named skill |