@cursor/july 0.1.107 → 0.1.109

package/dist/docs/assets/troubleshooting.md.Cus_YZga.js

@@ -1 +0,0 @@
-import{_ as t,c as o,o as a,ag as d}from"./chunks/framework.BCISBCiQ.js";const p=JSON.parse('{"title":"Fix common agent problems","description":"Match what you see to a cause, then read a session trace when you need more detail.","frontmatter":{"title":"Fix common agent problems","description":"Match what you see to a cause, then read a session trace when you need more detail."},"headers":[],"relativePath":"troubleshooting.md","filePath":"troubleshooting.md"}'),r={name:"troubleshooting.md"};function s(n,e,c,i,l,h){return a(),o("div",null,[...e[0]||(e[0]=[d('<h1 id="fix-common-agent-problems" tabindex="-1">Fix common agent problems <a class="header-anchor" href="#fix-common-agent-problems" aria-label="Permalink to &quot;Fix common agent problems&quot;">​</a></h1><p>Start with four checks, in order:</p><ol><li>Project discovery: <code>agent-sdk validate --dir .</code></li><li>Whether the serve process is running</li><li>What the playground or HTTP API shows</li><li>The session event stream (trace)</li></ol><p>Match your symptom below. Keep the commands as <code>agent-sdk</code>. If it is not on <code>PATH</code>, use <code>npx @cursor/july</code>.</p><h2 id="what-if-serve-or-the-playground-looks-wrong" tabindex="-1">What if serve or the playground looks wrong? <a class="header-anchor" href="#what-if-serve-or-the-playground-looks-wrong" aria-label="Permalink to &quot;What if serve or the playground looks wrong?&quot;">​</a></h2><table tabindex="0"><thead><tr><th>What you see</th><th>What to do</th></tr></thead><tbody><tr><td><code>serve</code> won&#39;t start</td><td>Run <code>agent-sdk validate --dir .</code> and fix the reported errors.</td></tr><tr><td>Playground is blank or says there are no agents</td><td>The UI needs a running <code>serve</code> process. Building the playground assets alone is not enough.</td></tr><tr><td>The playground UI looks stale</td><td><code>serve --dev</code> prints a playground URL. Open that URL. Agent-file edits still need a restart (press Enter on the TTY).</td></tr><tr><td>Sessions exist but the playground list is empty</td><td>The list shows sessions for the authenticated caller. In <code>--dev</code> on loopback the list is wider. Otherwise open <code>/&lt;slug&gt;/playground?sessionId=ses_…</code>.</td></tr><tr><td>Port 3000 is already in use</td><td>For the default serve port, the CLI tries the next free port and prints a notice. Pass <code>--port</code> to pick one, or <code>--port 0</code> for any free port. Stop leftover playground or webhook-forwarder processes if you need the original port.</td></tr></tbody></table><h2 id="what-if-a-model-turn-goes-wrong" tabindex="-1">What if a model turn goes wrong? <a class="header-anchor" href="#what-if-a-model-turn-goes-wrong" aria-label="Permalink to &quot;What if a model turn goes wrong?&quot;">​</a></h2><table tabindex="0"><thead><tr><th>What you see</th><th>What to do</th></tr></thead><tbody><tr><td>Built-in file reads and greps fail; the turn retries for a long time</td><td>Run under Node 22.13+ (or <code>tsx</code>), never Bun. Look for <code>NGHTTP2_FRAME_SIZE_ERROR</code> in logs.</td></tr><tr><td>The turn fails immediately with an API-key error</td><td>Sign in with <code>agent-sdk login</code>, or set <code>CURSOR_API_KEY</code>. Discovery, <code>info</code>, <code>call</code>, and serve bring-up work without a key; model turns need one.</td></tr><tr><td>Replies quote rules or <code>AGENTS.md</code> from outside your agent project</td><td>The session workspace inherited parent-folder config. Nested git checkouts default <code>local.cwd</code> to a per-project cache directory under <code>~/.cache</code>. Point <code>defineAgent({ local: { cwd } })</code> at a checkout only when the agent should inherit that tree, or set <code>--state-root</code> to a clean directory (for example under <code>/tmp</code>).</td></tr><tr><td>Yellow box shows Datadog/Linear tools, but the model lists <code>GetDynamicTools</code> / IDE <code>cursor</code> tools and never calls them</td><td>Attached MCP sits behind harness meta-tools, or the harness cwd is still inside another checkout. Set <code>advertiseTools: true</code> for named tools on local turns. Check <code>GET /v1/info</code> <code>local.cwd</code> and <code>connections[].advertiseTools</code>.</td></tr><tr><td>Server tools, skills, or workspace seed files never appear</td><td>Server tools and sandbox seeds apply on the local runtime (cloud server tools need <code>--public-url</code> / <code>--cloud-tools-url</code>). Skills reach cloud through the Agent Store when hosting or a personal <code>CURSOR_API_KEY</code> is available; otherwise only skills already in the cloud repo. <code>validate</code> warns when this combination is present.</td></tr><tr><td><code>validate</code> and <code>run</code> succeed, but typecheck fails in CI</td><td>The CLI runs TypeScript with type-stripping only. Keep tool <code>execute</code> return types as object literals or <code>type</code> aliases, not <code>interface</code> types.</td></tr><tr><td>Login works, but turns are rejected when using custom API hosts</td><td>Point login and model traffic at the same host (<code>CURSOR_API_BASE_URL</code> and <code>CURSOR_BACKEND_URL</code>). A key from one host is rejected by the other.</td></tr></tbody></table><h2 id="what-if-the-http-api-returns-an-error" tabindex="-1">What if the HTTP API returns an error? <a class="header-anchor" href="#what-if-the-http-api-returns-an-error" aria-label="Permalink to &quot;What if the HTTP API returns an error?&quot;">​</a></h2><table tabindex="0"><thead><tr><th>What you see</th><th>What to do</th></tr></thead><tbody><tr><td><code>409</code> on a follow-up message</td><td>Refresh the <code>continuationToken</code> or confirm the session is a chat session. Task sessions do not accept follow-ups.</td></tr><tr><td><code>409 session_busy</code> on <code>call --session</code></td><td>The tool is a write (or declares no effect) and a model turn is running. Wait for the turn to finish, omit <code>--session</code> for a one-off call, or declare <code>effect: &quot;read&quot;</code> on a tool that only reads so it runs alongside turns.</td></tr><tr><td><code>403</code> on stream or follow-up</td><td>Use the same auth identity that created the session. Off localhost, pass <code>--bearer-token</code> and send it on every request.</td></tr><tr><td>Works on localhost; blocked through a tunnel or LAN</td><td>Default auth allows only direct loopback callers. Share the host with <code>--bearer-token &lt;secret&gt;</code> (or authored <code>bearerAuth</code>). Use <code>--allow-anonymous</code> only on a trusted private network.</td></tr><tr><td>A channel route fails to compile with a schema type error</td><td><code>GET</code> routes need a Zod <code>querySchema</code>. <code>POST</code> / <code>PUT</code> / <code>PATCH</code> need a Zod <code>bodySchema</code>. Use <code>z.object({})</code> or <code>z.unknown()</code> for open shapes.</td></tr></tbody></table><h2 id="what-if-github-webhooks-misbehave" tabindex="-1">What if GitHub webhooks misbehave? <a class="header-anchor" href="#what-if-github-webhooks-misbehave" aria-label="Permalink to &quot;What if GitHub webhooks misbehave?&quot;">​</a></h2><table tabindex="0"><thead><tr><th>What you see</th><th>What to do</th></tr></thead><tbody><tr><td><code>github forward</code> returns 401 on every delivery, but the hook was created</td><td>Clear <code>GITHUB_TOKEN</code> and <code>GH_TOKEN</code> for that command. The forwarder uses your <code>gh</code> CLI login: <code>GITHUB_TOKEN= GH_TOKEN= agent-sdk github forward …</code></td></tr><tr><td><code>Hook already exists</code> when starting a forwarder</td><td>GitHub allows one forwarder per repo. Run a single <code>github forward --dir &lt;parent&gt;</code> and stop stale forwarders.</td></tr><tr><td>Deliveries rejected outside <code>--dev</code></td><td>Set <code>GITHUB_WEBHOOK_SECRET</code> on the server and on the signer. Without a secret, the channel stays loopback-only.</td></tr><tr><td>You lack repo admin and can&#39;t forward</td><td>Use <code>agent-sdk github replay &lt;pr-url&gt;</code>. It needs pull access only and posts signed test payloads.</td></tr></tbody></table><h2 id="what-if-slack-stays-quiet" tabindex="-1">What if Slack stays quiet? <a class="header-anchor" href="#what-if-slack-stays-quiet" aria-label="Permalink to &quot;What if Slack stays quiet?&quot;">​</a></h2><table tabindex="0"><thead><tr><th>What you see</th><th>What to do</th></tr></thead><tbody><tr><td>Logs show <code>channel idle … missing credentials</code></td><td>Expected when tokens are missing. Run <code>agent-sdk slack create --dir &lt;agent&gt;</code> to provision the app and write the tokens, or <code>agent-sdk slack init --manual --dir &lt;agent&gt;</code> and paste the manifests at api.slack.com. Then set <code>&lt;PREFIX&gt;_SLACK_BOT_TOKEN</code> and <code>&lt;PREFIX&gt;_SLACK_APP_TOKEN</code> per agent and run <code>agent-sdk slack doctor --prefix &lt;PREFIX&gt;</code>.</td></tr><tr><td><code>slack create</code> reports the app needs admin approval</td><td>Open Slack&#39;s <strong>Request approval</strong> page (the CLI prints the link; the same URL is <strong>Send a reminder</strong> after you submit). Managed install does not file the request. Keep the CLI running, then click <strong>Retry</strong> in the dashboard after an admin approves.</td></tr><tr><td>The bot ignores ordinary channel posts</td><td>Default engagement is mentions and DMs only. Enable <code>engagement.channelPosts</code> with an allowlist, and subscribe the app to <code>message.channels</code> / <code>message.groups</code>.</td></tr><tr><td>Approve / Deny buttons do nothing</td><td>Channels that post approval cards need <code>toolApprovals: true</code>. Recreate the app with <code>slack create</code> if interactivity is off.</td></tr></tbody></table><h2 id="what-if-host-mcp-oauth-fails" tabindex="-1">What if host MCP OAuth fails? <a class="header-anchor" href="#what-if-host-mcp-oauth-fails" aria-label="Permalink to &quot;What if host MCP OAuth fails?&quot;">​</a></h2><table tabindex="0"><thead><tr><th>What you see</th><th>What to do</th></tr></thead><tbody><tr><td><code>must be defineConnection({ url, oauth: true })</code></td><td>The connection file needs <code>oauth: true</code>, or you passed the wrong connection name to <code>agent-sdk mcp oauth</code>.</td></tr><tr><td>Local auth works; hosted calls unauthorized</td><td>Finish Connect on the hosted engine, or run <code>agent-sdk mcp oauth &lt;name&gt; --store</code>. Confirm names with <code>agent-sdk secrets list &lt;slug&gt;</code>, then redeploy.</td></tr><tr><td>Model asks for <code>mcp_auth</code> or IDE MCP for a connector it already has</td><td>Attached MCP is behind meta-tools. Set <code>advertiseTools: true</code> for named tools on local turns, or call it from a host tool via <code>ctx.host.mcp</code>.</td></tr></tbody></table><p>See <a href="./guides/mcp-oauth.html">Host MCP OAuth</a> and <a href="./skills/mcp-auth.html"><code>skills/mcp-auth/SKILL.md</code></a>.</p><h2 id="what-if-a-secret-showed-up-in-a-terminal-transcript" tabindex="-1">What if a secret showed up in a terminal transcript? <a class="header-anchor" href="#what-if-a-secret-showed-up-in-a-terminal-transcript" aria-label="Permalink to &quot;What if a secret showed up in a terminal transcript?&quot;">​</a></h2><table tabindex="0"><thead><tr><th>What you see</th><th>What to do</th></tr></thead><tbody><tr><td><code>secrets set … NAME=VALUE</code> in an agent-captured terminal or shell history</td><td>Rotate the secret at the provider. Set it again with names only: <code>agent-sdk secrets set &lt;slug&gt; NAME</code> (hidden prompt) or pipe/redirect the value. <code>NAME=VALUE</code> requires <code>--from-argv</code> and still leaks into argv.</td></tr><tr><td>Alias token printed during first deploy or <code>rotate-token</code></td><td>Treat it as exposed if the transcript left your machine. Run <code>agent-sdk rotate-token &lt;slug&gt;</code>, store the new token outside agent transcripts, and update callers.</td></tr><tr><td>Someone verified a secret with <code>echo</code> / <code>printenv</code></td><td>Rotate it. Confirm presence with <code>agent-sdk secrets list &lt;slug&gt;</code> (names only), then redeploy and test the feature.</td></tr></tbody></table><h2 id="what-if-schedules-reminders-or-approvals-stall" tabindex="-1">What if schedules, reminders, or approvals stall? <a class="header-anchor" href="#what-if-schedules-reminders-or-approvals-stall" aria-label="Permalink to &quot;What if schedules, reminders, or approvals stall?&quot;">​</a></h2><table tabindex="0"><thead><tr><th>What you see</th><th>What to do</th></tr></thead><tbody><tr><td>A schedule or reminder never fires under <code>--dev</code></td><td>Dev mode does not auto-fire. Trigger with <code>POST /&lt;slug&gt;/v1/dev/schedules/&lt;id&gt;</code> or <code>POST /&lt;slug&gt;/v1/dev/reminders/&lt;id&gt;</code> (list reminders at <code>GET /v1/dev/reminders</code>).</td></tr><tr><td>A pending tool approval disappeared after restart</td><td>Parked approvals do not survive host restart. They resolve as interrupted. Run the turn again.</td></tr><tr><td>A reminder is disarmed after restart (<code>handler_lost_on_restart</code>)</td><td>Handler-form reminders live in memory. Re-arm them from the code that created them, or use prompt-form reminders.</td></tr></tbody></table><h2 id="how-do-i-read-a-session-trace" tabindex="-1">How do I read a session trace? <a class="header-anchor" href="#how-do-i-read-a-session-trace" aria-label="Permalink to &quot;How do I read a session trace?&quot;">​</a></h2><p>Look at <code>actions.requested</code> / <code>action.result</code> pairs for the tool trajectory. Count calls by tool name before blaming latency. Separate host-side work (channel <code>callTool</code>, preparation) from tools the model chose.</p><p><code>turn.failed</code> with <code>&quot;turn interrupted&quot;</code> means a follow-up or stop ended the turn on purpose.</p><p>If the model reads outside the session workspace, the prepared files don&#39;t match what the instructions expect. Fix the layout. See <a href="./hillclimbing.html">Hillclimbing</a>.</p><p><code>agent-sdk trajectory --events &lt;file&gt;</code> summarizes any saved NDJSON stream. The playground <strong>Open trace</strong> control does the same visually.</p><h2 id="what-s-next" tabindex="-1">What&#39;s next <a class="header-anchor" href="#what-s-next" aria-label="Permalink to &quot;What&#39;s next&quot;">​</a></h2><ul><li><a href="./concepts.html">Concepts</a>: the model behind these symptoms</li><li><a href="./hillclimbing.html">Hillclimbing</a>: when the agent runs but underperforms</li><li><a href="./deployment.html">Deployment</a>: auth and state on shared hosts</li></ul>',28)])])}const m=t(r,[["render",s]]);export{p as __pageData,m as default};

package/dist/docs/skills/ab.html

@@ -1,52 +0,0 @@
-<!DOCTYPE html>
-<html lang="en-US" dir="ltr">
-  <head>
-    <meta charset="utf-8">
-    <meta name="viewport" content="width=device-width,initial-scale=1">
-    <title>Agent SDK A/B metrics (defineAB) | Agent SDK</title>
-    <meta name="description" content="Author defineAB live A/B metrics under agent/ab. Sticky variants and onSample on live runs. Not a test runner. Use when comparing variants on traffic; use defineEval for regression gates.">
-    <meta name="generator" content="VitePress v1.6.4">
-    <link rel="preload stylesheet" href="/docs/assets/style.DCD_zyg3.css" as="style">
-    <link rel="preload stylesheet" href="/docs/vp-icons.css" as="style">
-    
-    <script type="module" src="/docs/assets/app.CtuckIiL.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/theme.DhpIe0Pa.js">
-    <link rel="modulepreload" href="/docs/assets/chunks/framework.BCISBCiQ.js">
-    <link rel="modulepreload" href="/docs/assets/skills_ab.md.CsFNatVx.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/skills/ab.md">
-  </head>
-  <body>
-    <div id="app"><div class="Layout" data-v-990b7706><!--[--><!--]--><!--[--><span tabindex="-1" data-v-0b74bec0></span><a href="#VPContent" class="VPSkipLink visually-hidden" data-v-0b74bec0>Skip to content</a><!--]--><!----><header class="VPNav" data-v-990b7706 data-v-af996e33><div class="VPNavBar" data-v-af996e33 data-v-c7f322eb><div class="wrapper" data-v-c7f322eb><div class="container" data-v-c7f322eb><div class="title" data-v-c7f322eb><div class="VPNavBarTitle has-sidebar" data-v-c7f322eb data-v-d1664c59><a class="title" href="/docs/" data-v-d1664c59><!--[--><!--]--><!----><span data-v-d1664c59>Agent SDK</span><!--[--><!--[--><!--[--><!--[--><span class="agent-sdk-version" title="@cursor/july 0.1.107" data-v-c26a5f4f>0.1.107</span><!--]--><!--]--><!--]--><!--]--></a></div></div><div class="content" data-v-c7f322eb><div class="content-body" data-v-c7f322eb><!--[--><!--]--><div class="VPNavBarSearch search" data-v-c7f322eb><!--[--><!----><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-c7f322eb data-v-ab749b05><span id="main-nav-aria-label" class="visually-hidden" data-v-ab749b05> Main Navigation </span><!--[--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/quickstart.html" tabindex="0" data-v-ab749b05 data-v-ef8d136f><!--[--><span data-v-ef8d136f>Quickstart</span><!--]--></a><!--]--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/guides/webhooks.html" tabindex="0" data-v-ab749b05 data-v-ef8d136f><!--[--><span data-v-ef8d136f>Guides</span><!--]--></a><!--]--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/templates/demo.html" tabindex="0" data-v-ab749b05 data-v-ef8d136f><!--[--><span data-v-ef8d136f>Templates</span><!--]--></a><!--]--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/reference/project-layout.html" tabindex="0" data-v-ab749b05 data-v-ef8d136f><!--[--><span data-v-ef8d136f>Reference</span><!--]--></a><!--]--><!--]--></nav><!----><div class="VPNavBarAppearance appearance" data-v-c7f322eb data-v-7c6c0ede><button class="VPSwitch VPSwitchAppearance" type="button" role="switch" title aria-checked="false" data-v-7c6c0ede data-v-87b8a6bb data-v-9f798512><span class="check" data-v-9f798512><span class="icon" data-v-9f798512><!--[--><span class="vpi-sun sun" data-v-87b8a6bb></span><span class="vpi-moon moon" data-v-87b8a6bb></span><!--]--></span></span></button></div><!----><div class="VPFlyout VPNavBarExtra extra" data-v-c7f322eb data-v-e53d4296 data-v-79fc383b><button type="button" class="button" aria-haspopup="true" aria-expanded="false" aria-label="extra navigation" data-v-79fc383b><span class="vpi-more-horizontal icon" data-v-79fc383b></span></button><div class="menu" data-v-79fc383b><div class="VPMenu" data-v-79fc383b data-v-0d780c53><!----><!--[--><!--[--><!----><div class="group" data-v-e53d4296><div class="item appearance" data-v-e53d4296><p class="label" data-v-e53d4296>Appearance</p><div class="appearance-action" data-v-e53d4296><button class="VPSwitch VPSwitchAppearance" type="button" role="switch" title aria-checked="false" data-v-e53d4296 data-v-87b8a6bb data-v-9f798512><span class="check" data-v-9f798512><span class="icon" data-v-9f798512><!--[--><span class="vpi-sun sun" data-v-87b8a6bb></span><span class="vpi-moon moon" data-v-87b8a6bb></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-c7f322eb data-v-edf597df><span class="container" data-v-edf597df><span class="top" data-v-edf597df></span><span class="middle" data-v-edf597df></span><span class="bottom" data-v-edf597df></span></span></button></div></div></div></div><div class="divider" data-v-c7f322eb><div class="divider-line" data-v-c7f322eb></div></div></div><!----></header><div class="VPLocalNav has-sidebar empty" data-v-990b7706 data-v-054265d6><div class="container" data-v-054265d6><button class="menu" aria-expanded="false" aria-controls="VPSidebarNav" data-v-054265d6><span class="vpi-align-left menu-icon" data-v-054265d6></span><span class="menu-text" data-v-054265d6>Menu</span></button><div class="VPLocalNavOutlineDropdown" style="--vp-vh:0px;" data-v-054265d6 data-v-65e16bd4><button data-v-65e16bd4>Return to top</button><!----></div></div></div><aside class="VPSidebar" data-v-990b7706 data-v-03069692><div class="curtain" data-v-03069692></div><nav class="nav" id="VPSidebarNav" aria-labelledby="sidebar-aria-label" tabindex="-1" data-v-03069692><span class="visually-hidden" id="sidebar-aria-label" data-v-03069692> Sidebar Navigation </span><!--[--><!--]--><!--[--><div class="no-transition group" data-v-53da167f><section class="VPSidebarItem level-0" data-v-53da167f data-v-9a4aac52><div class="item" role="button" tabindex="0" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><h2 class="text" data-v-9a4aac52>Getting started</h2><!----></div><div class="items" data-v-9a4aac52><!--[--><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Overview</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/quickstart.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Quickstart</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/scaffolding-agents.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Scaffold an agent with Cursor</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/guides/convert-automation.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Convert a Cursor Automation</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/concepts.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Concepts</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-53da167f><section class="VPSidebarItem level-0" data-v-53da167f data-v-9a4aac52><div class="item" role="button" tabindex="0" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><h2 class="text" data-v-9a4aac52>Templates</h2><!----></div><div class="items" data-v-9a4aac52><!--[--><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/templates/demo.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Demo agent</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/templates/grokbot-agents.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Grok Bot agents</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/templates/code-wiki.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Code wiki</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/templates/agents-md.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Living AGENTS.md</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/templates/security-reviewer.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Security reviewer</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/templates/security-help.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Security help</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/templates/agentic-owners.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Agentic Owners</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/templates/pr-autofixer.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>PR autofixer</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/templates/triage.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Triage agent</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-53da167f><section class="VPSidebarItem level-0" data-v-53da167f data-v-9a4aac52><div class="item" role="button" tabindex="0" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><h2 class="text" data-v-9a4aac52>Improving agents</h2><!----></div><div class="items" data-v-9a4aac52><!--[--><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/building-with-agents.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Building agents with agents</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/evals.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Evals</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/ab.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Live A/B metrics</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/storage.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Storage</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/hillclimbing.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Hillclimbing</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-53da167f><section class="VPSidebarItem level-0 collapsible collapsed" data-v-53da167f data-v-9a4aac52><div class="item" role="button" tabindex="0" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><h2 class="text" data-v-9a4aac52>Coding-agent skills</h2><div class="caret" role="button" aria-label="toggle section" tabindex="0" data-v-9a4aac52><span class="vpi-chevron-right caret-icon" data-v-9a4aac52></span></div></div><div class="items" data-v-9a4aac52><!--[--><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/skills/" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Overview</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/skills/ab.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>ab</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/skills/create-agent.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>create-agent</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/skills/debug.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>debug</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/skills/evals.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>evals</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/skills/framework-map.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>framework-map</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/skills/github.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>github</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/skills/hillclimb.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>hillclimb</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/skills/mcp-auth.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>mcp-auth</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/skills/otel.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>otel</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/skills/setup-slack.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>setup-slack</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-53da167f><section class="VPSidebarItem level-0" data-v-53da167f data-v-9a4aac52><div class="item" role="button" tabindex="0" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><h2 class="text" data-v-9a4aac52>Guides</h2><!----></div><div class="items" data-v-9a4aac52><!--[--><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/guides/webhooks.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Webhooks & custom channels</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/guides/github.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>GitHub</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/guides/slack.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Slack</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/guides/human-in-the-loop.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Human-in-the-loop approvals</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/guides/agent-to-agent.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Agent-to-agent</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/guides/mcp-oauth.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Host MCP OAuth</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/guides/cloud-agents.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Cursor cloud agents</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/guides/grokbot-agents.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Cursor Grok Bot agents</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/guides/opentelemetry.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>OpenTelemetry</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-53da167f><section class="VPSidebarItem level-0" data-v-53da167f data-v-9a4aac52><div class="item" role="button" tabindex="0" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><h2 class="text" data-v-9a4aac52>Operating</h2><!----></div><div class="items" data-v-9a4aac52><!--[--><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/deployment.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Deployment</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/troubleshooting.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Fix common problems</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-53da167f><section class="VPSidebarItem level-0 collapsible" data-v-53da167f data-v-9a4aac52><div class="item" role="button" tabindex="0" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><h2 class="text" data-v-9a4aac52>Reference</h2><div class="caret" role="button" aria-label="toggle section" tabindex="0" data-v-9a4aac52><span class="vpi-chevron-right caret-icon" data-v-9a4aac52></span></div></div><div class="items" data-v-9a4aac52><!--[--><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/project-layout.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Project layout</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/agent-config.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Agent config</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/instructions.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Instructions</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/tools.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Tools</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/prompt.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>prompt</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/skills.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Skills</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/connections.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>MCP Connections</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/subagents.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Subagents</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/extensions.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Extensions</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/channels.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Channels</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/schedules.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Schedules & reminders</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/hooks.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Hooks</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/artifacts.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Artifacts</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/result.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Turn result</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/sessions.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Sessions & streaming</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/playground.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Playground</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/cli.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>CLI</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/http-api.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>HTTP API</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><!--]--><!--[--><!--]--></nav></aside><div class="VPContent has-sidebar" id="VPContent" data-v-990b7706 data-v-7a16121a><div class="VPDoc has-sidebar has-aside" data-v-7a16121a data-v-38549ef7><!--[--><!--]--><div class="container" data-v-38549ef7><div class="aside" data-v-38549ef7><div class="aside-curtain" data-v-38549ef7></div><div class="aside-container" data-v-38549ef7><div class="aside-content" data-v-38549ef7><div class="VPDocAside" data-v-38549ef7 data-v-da90486d><!--[--><!--]--><!--[--><!--]--><nav aria-labelledby="doc-outline-aria-label" class="VPDocAsideOutline" data-v-da90486d data-v-0895f2d7><div class="content" data-v-0895f2d7><div class="outline-marker" data-v-0895f2d7></div><div aria-level="2" class="outline-title" id="doc-outline-aria-label" role="heading" data-v-0895f2d7>On this page</div><ul class="VPDocOutlineItem root" data-v-0895f2d7 data-v-0cae2091><!--[--><!--]--></ul></div></nav><!--[--><!--]--><div class="spacer" data-v-da90486d></div><!--[--><!--]--><!----><!--[--><!--]--><!--[--><!--]--></div></div></div></div><div class="content" data-v-38549ef7><div class="content-container" data-v-38549ef7><!--[--><!--]--><main class="main" data-v-38549ef7><div style="position:relative;" class="vp-doc _docs_skills_ab" data-v-38549ef7><div><h1 id="agent-sdk-a-b-metrics-defineab" tabindex="-1">Agent SDK A/B metrics (<code>defineAB</code>) <a class="header-anchor" href="#agent-sdk-a-b-metrics-defineab" aria-label="Permalink to &quot;Agent SDK A/B metrics (`defineAB`)&quot;">​</a></h1><p>Live metrics plug-in. No <code>agent-sdk ab</code> CLI. No assertion API. Reference: <code>docs/ab.md</code>.</p><table tabindex="0"><thead><tr><th></th><th><code>defineEval</code></th><th><code>defineAB</code></th></tr></thead><tbody><tr><td>Job</td><td>Gates on frozen fixtures</td><td>Metrics on live runs</td></tr><tr><td>Location</td><td><code>evals/**/*.eval.ts</code></td><td><code>agent/ab.ts</code> or <code>agent/ab/&lt;name&gt;.ts</code></td></tr><tr><td>How it runs</td><td><code>agent-sdk eval</code></td><td>Under <code>serve</code> / <code>run</code></td></tr></tbody></table><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;">import</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> { defineAB, splitBySessionHash } </span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;">from</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;"> &quot;@cursor/july/ab&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">;</span></span>
-<span class="line"></span>
-<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;"> defineAB</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">({</span></span>
-<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">  name: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">&quot;concise-instructions&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">,</span></span>
-<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">  variants: {</span></span>
-<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">    control: { label: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">&quot;Baseline&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> },</span></span>
-<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">    treatment: {</span></span>
-<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">      label: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">&quot;Shorter&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">,</span></span>
-<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">      instructions: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">&quot;Keep replies to one short paragraph.&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>
-<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">  },</span></span>
-<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">  split: </span><span style="--shiki-light:#6F42C1;--shiki-dark:#B392F0;">splitBySessionHash</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">({ holdout: </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">0.1</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> }),</span></span>
-<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">  derive: {</span></span>
-<span class="line"><span style="--shiki-light:#6F42C1;--shiki-dark:#B392F0;">    weatherCalls</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: (</span><span style="--shiki-light:#E36209;--shiki-dark:#FFAB70;">event</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">) </span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;">=&gt;</span></span>
-<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">      event.type </span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;">===</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;"> &quot;action.result&quot;</span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;"> &amp;&amp;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> event.data.toolName </span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;">===</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;"> &quot;get_weather&quot;</span></span>
-<span class="line"><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;">        ?</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> 1</span></span>
-<span class="line"><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;">        :</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> null</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">,</span></span>
-<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">  },</span></span>
-<span class="line"><span style="--shiki-light:#6F42C1;--shiki-dark:#B392F0;">  onSample</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">(</span><span style="--shiki-light:#E36209;--shiki-dark:#FFAB70;">sample</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">) {</span></span>
-<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">    console.</span><span style="--shiki-light:#6F42C1;--shiki-dark:#B392F0;">log</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">(sample.variant, sample.metrics.toolCalls, sample.metrics.wallTimeMs);</span></span>
-<span class="line"><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><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;">async </span><span style="--shiki-light:#6F42C1;--shiki-dark:#B392F0;">execute</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">(input, ctx) {</span></span>
-<span class="line"><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;">  if</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> (ctx.session.abs?.[</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">&quot;concise-instructions&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">] </span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;">===</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;"> &quot;treatment&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">) {</span></span>
-<span class="line"><span style="--shiki-light:#6A737D;--shiki-dark:#6A737D;">    // treatment-specific behavior</span></span>
-<span class="line"><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><p>Enrollment is at session creation. Eval sessions skip it. Do not use <code>splitIf</code> to filter evals. Split helpers and <code>onSample</code> fields: <code>docs/ab.md</code>.</p><p>Pick a name, arm labels, a split, and a real <code>onSample</code> sink. Do not invent credentials.</p></div></div></main><footer class="VPDocFooter" data-v-38549ef7 data-v-215f93e6><!--[--><!--]--><!----><nav class="prev-next" aria-labelledby="doc-footer-aria-label" data-v-215f93e6><span class="visually-hidden" id="doc-footer-aria-label" data-v-215f93e6>Pager</span><div class="pager" data-v-215f93e6><!----></div><div class="pager" data-v-215f93e6><a class="VPLink link pager-link next" href="/docs/" data-v-215f93e6><!--[--><span class="desc" data-v-215f93e6>Next page</span><span class="title" data-v-215f93e6>Overview</span><!--]--></a></div></nav></footer><!--[--><!--]--></div></div></div><!--[--><!--]--></div></div><!----><!--[--><!--]--></div></div>
-    <script>window.__VP_HASH_MAP__=JSON.parse("{\"ab.md\":\"mlVgqvSk\",\"building-with-agents.md\":\"CUSWxlP_\",\"concepts.md\":\"DgEcZOfT\",\"deployment.md\":\"MFPKqsqI\",\"evals.md\":\"CbMoebP1\",\"guides_agent-to-agent.md\":\"BDb0t1QV\",\"guides_cloud-agents.md\":\"DS8RIjwx\",\"guides_convert-automation.md\":\"B4sjlodG\",\"guides_github.md\":\"c0gdGJ-D\",\"guides_grokbot-agents.md\":\"DVqdhBKb\",\"guides_human-in-the-loop.md\":\"By1G2T3_\",\"guides_mcp-oauth.md\":\"Dp6cDP7f\",\"guides_opentelemetry.md\":\"SCRMskno\",\"guides_slack.md\":\"9oHPye9o\",\"guides_webhooks.md\":\"DKdA43Qm\",\"hillclimbing.md\":\"CpTGTCle\",\"index.md\":\"BW_6tOgR\",\"quickstart.md\":\"DdQOF7Y8\",\"reference_agent-config.md\":\"CHNpiyp4\",\"reference_artifacts.md\":\"Dior32Qw\",\"reference_channels.md\":\"D-qTqwcq\",\"reference_cli.md\":\"Dm67hd2D\",\"reference_connections.md\":\"Di6jJAXF\",\"reference_extensions.md\":\"CGmMLblt\",\"reference_hooks.md\":\"Ddt5DdgJ\",\"reference_http-api.md\":\"oySXBO8o\",\"reference_instructions.md\":\"CR7XSsGk\",\"reference_playground.md\":\"4myJPxrf\",\"reference_project-layout.md\":\"DuBu9a96\",\"reference_prompt.md\":\"DnaD5dNK\",\"reference_result.md\":\"BK5SxDrf\",\"reference_schedules.md\":\"DI_JrHgq\",\"reference_sessions.md\":\"CueyOHSL\",\"reference_skills.md\":\"l2ezAcaN\",\"reference_subagents.md\":\"CfsIloPm\",\"reference_tools.md\":\"aGrn99hP\",\"scaffolding-agents.md\":\"em43xlY1\",\"skills_ab.md\":\"CsFNatVx\",\"skills_create-agent.md\":\"BVoWPcan\",\"skills_debug.md\":\"CDbPhHfg\",\"skills_evals.md\":\"723kpUmA\",\"skills_framework-map.md\":\"haibFyoB\",\"skills_github.md\":\"D0JahM8c\",\"skills_hillclimb.md\":\"B_zJerxA\",\"skills_index.md\":\"DKwIxzGg\",\"skills_mcp-auth.md\":\"DGvFP3HE\",\"skills_otel.md\":\"B5Ddv1xH\",\"skills_setup-slack.md\":\"BBgx8lUz\",\"storage.md\":\"BOHeqk2M\",\"templates_agentic-owners.md\":\"BZSH4N9z\",\"templates_agents-md.md\":\"CXSMZljE\",\"templates_code-wiki.md\":\"CDYZIBFN\",\"templates_demo.md\":\"BeQX9V3H\",\"templates_grokbot-agents.md\":\"c1s6Flp9\",\"templates_pr-autofixer.md\":\"Bds_XWcV\",\"templates_security-help.md\":\"C3Ny_Qr2\",\"templates_security-reviewer.md\":\"lshxbCLK\",\"templates_triage.md\":\"Co4UNzkZ\",\"troubleshooting.md\":\"Cus_YZga\"}");window.__VP_SITE_DATA__=JSON.parse("{\"lang\":\"en-US\",\"dir\":\"ltr\",\"title\":\"Agent SDK\",\"description\":\"Filesystem-first framework for building and serving Cursor agents.\",\"base\":\"/docs/\",\"head\":[],\"router\":{\"prefetchLinks\":true},\"appearance\":true,\"themeConfig\":{\"sdkVersion\":\"0.1.107\",\"nav\":[{\"text\":\"Quickstart\",\"link\":\"/quickstart\"},{\"text\":\"Guides\",\"link\":\"/guides/webhooks\"},{\"text\":\"Templates\",\"link\":\"/templates/demo\"},{\"text\":\"Reference\",\"link\":\"/reference/project-layout\"}],\"search\":{\"provider\":\"local\"},\"outline\":{\"level\":[2,3]},\"sidebar\":[{\"text\":\"Getting started\",\"items\":[{\"text\":\"Overview\",\"link\":\"/\"},{\"text\":\"Quickstart\",\"link\":\"/quickstart\"},{\"text\":\"Scaffold an agent with Cursor\",\"link\":\"/scaffolding-agents\"},{\"text\":\"Convert a Cursor Automation\",\"link\":\"/guides/convert-automation\"},{\"text\":\"Concepts\",\"link\":\"/concepts\"}]},{\"text\":\"Templates\",\"items\":[{\"text\":\"Demo agent\",\"link\":\"/templates/demo\"},{\"text\":\"Grok Bot agents\",\"link\":\"/templates/grokbot-agents\"},{\"text\":\"Code wiki\",\"link\":\"/templates/code-wiki\"},{\"text\":\"Living AGENTS.md\",\"link\":\"/templates/agents-md\"},{\"text\":\"Security reviewer\",\"link\":\"/templates/security-reviewer\"},{\"text\":\"Security help\",\"link\":\"/templates/security-help\"},{\"text\":\"Agentic Owners\",\"link\":\"/templates/agentic-owners\"},{\"text\":\"PR autofixer\",\"link\":\"/templates/pr-autofixer\"},{\"text\":\"Triage agent\",\"link\":\"/templates/triage\"}]},{\"text\":\"Improving agents\",\"items\":[{\"text\":\"Building agents with agents\",\"link\":\"/building-with-agents\"},{\"text\":\"Evals\",\"link\":\"/evals\"},{\"text\":\"Live A/B metrics\",\"link\":\"/ab\"},{\"text\":\"Storage\",\"link\":\"/storage\"},{\"text\":\"Hillclimbing\",\"link\":\"/hillclimbing\"}]},{\"text\":\"Coding-agent skills\",\"collapsed\":true,\"items\":[{\"text\":\"Overview\",\"link\":\"/skills/\"},{\"text\":\"ab\",\"link\":\"/skills/ab\"},{\"text\":\"create-agent\",\"link\":\"/skills/create-agent\"},{\"text\":\"debug\",\"link\":\"/skills/debug\"},{\"text\":\"evals\",\"link\":\"/skills/evals\"},{\"text\":\"framework-map\",\"link\":\"/skills/framework-map\"},{\"text\":\"github\",\"link\":\"/skills/github\"},{\"text\":\"hillclimb\",\"link\":\"/skills/hillclimb\"},{\"text\":\"mcp-auth\",\"link\":\"/skills/mcp-auth\"},{\"text\":\"otel\",\"link\":\"/skills/otel\"},{\"text\":\"setup-slack\",\"link\":\"/skills/setup-slack\"}]},{\"text\":\"Guides\",\"items\":[{\"text\":\"Webhooks & custom channels\",\"link\":\"/guides/webhooks\"},{\"text\":\"GitHub\",\"link\":\"/guides/github\"},{\"text\":\"Slack\",\"link\":\"/guides/slack\"},{\"text\":\"Human-in-the-loop approvals\",\"link\":\"/guides/human-in-the-loop\"},{\"text\":\"Agent-to-agent\",\"link\":\"/guides/agent-to-agent\"},{\"text\":\"Host MCP OAuth\",\"link\":\"/guides/mcp-oauth\"},{\"text\":\"Cursor cloud agents\",\"link\":\"/guides/cloud-agents\"},{\"text\":\"Cursor Grok Bot agents\",\"link\":\"/guides/grokbot-agents\"},{\"text\":\"OpenTelemetry\",\"link\":\"/guides/opentelemetry\"}]},{\"text\":\"Operating\",\"items\":[{\"text\":\"Deployment\",\"link\":\"/deployment\"},{\"text\":\"Fix common problems\",\"link\":\"/troubleshooting\"}]},{\"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\":\"Extensions\",\"link\":\"/reference/extensions\"},{\"text\":\"Channels\",\"link\":\"/reference/channels\"},{\"text\":\"Schedules & reminders\",\"link\":\"/reference/schedules\"},{\"text\":\"Hooks\",\"link\":\"/reference/hooks\"},{\"text\":\"Artifacts\",\"link\":\"/reference/artifacts\"},{\"text\":\"Turn result\",\"link\":\"/reference/result\"},{\"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/skills/ab.md

@@ -1,50 +0,0 @@
-# Agent SDK A/B metrics (`defineAB`)
-
-Live metrics plug-in. No `agent-sdk ab` CLI. No assertion API.
-Reference: `docs/ab.md`.
-
-| | `defineEval` | `defineAB` |
-| --- | --- | --- |
-| Job | Gates on frozen fixtures | Metrics on live runs |
-| Location | `evals/**/*.eval.ts` | `agent/ab.ts` or `agent/ab/<name>.ts` |
-| How it runs | `agent-sdk eval` | Under `serve` / `run` |
-
-```ts
-import { defineAB, splitBySessionHash } from "@cursor/july/ab";
-
-export default defineAB({
-  name: "concise-instructions",
-  variants: {
-    control: { label: "Baseline" },
-    treatment: {
-      label: "Shorter",
-      instructions: "Keep replies to one short paragraph.",
-    },
-  },
-  split: splitBySessionHash({ holdout: 0.1 }),
-  derive: {
-    weatherCalls: (event) =>
-      event.type === "action.result" && event.data.toolName === "get_weather"
-        ? 1
-        : null,
-  },
-  onSample(sample) {
-    console.log(sample.variant, sample.metrics.toolCalls, sample.metrics.wallTimeMs);
-  },
-});
-```
-
-```ts
-async execute(input, ctx) {
-  if (ctx.session.abs?.["concise-instructions"] === "treatment") {
-    // treatment-specific behavior
-  }
-}
-```
-
-Enrollment is at session creation. Eval sessions skip it. Do not
-use `splitIf` to filter evals. Split helpers and `onSample`
-fields: `docs/ab.md`.
-
-Pick a name, arm labels, a split, and a real `onSample` sink. Do
-not invent credentials.

package/dist/internal/ab-collector.d.ts

@@ -1,44 +0,0 @@
-/**
- * Stream-native collector for {@link defineAB} experiments.
- *
- * Pure fold over the session event log:
- * - sticky arm = last `ab.assigned` for that experiment
- * - metrics accumulate from the stream; `onSample` on turn complete/fail
- *
- * Enrollment is written by the engine at session creation (not here).
- * In-memory state is a cache: on cold start (or after park eviction) the
- * collector replays `events.ndjson` so counters survive restart.
- *
- * Hydration note: the engine appends before dispatch, so the first-touch
- * replay already includes the current event — after rebuild we return
- * without folding it again (and without re-firing `onSample`).
- */
-import { type ABMetricSample } from "../ab.js";
-import type { DiscoveredAB, SessionEvent, SessionInfo } from "../types.js";
-export type { DiscoveredAB };
-export interface ABCollectorOptions {
-    /**
-     * Durable sample export (the `defineStorage` `abs` table, via the
-     * coordinator). Fire-and-forget; must never throw.
-     */
-    persistSample?: (sample: ABMetricSample) => void;
-}
-export declare class ABCollector {
-    private readonly experiments;
-    private readonly logger;
-    private readonly loadEvents;
-    private readonly state;
-    private readonly hydrated;
-    private readonly persistSample;
-    constructor(experiments: readonly DiscoveredAB[], logger: (line: string) => void, loadEvents: (sessionId: string) => Promise<SessionEvent[]>, options?: ABCollectorOptions);
-    get enabled(): boolean;
-    /**
-     * Fold one live event. On first touch (or after eviction), replays the
-     * durable log first so enrollment + metrics match disk.
-     */
-    onEvent(event: SessionEvent, sessionInfo: SessionInfo, agentName: string): Promise<void>;
-    private drop;
-    private fold;
-    private sessionAccum;
-}
-//# sourceMappingURL=ab-collector.d.ts.map

package/dist/internal/ab-collector.d.ts.map

@@ -1 +0,0 @@
-{"version":3,"file":"ab-collector.d.ts","sourceRoot":"","sources":["../../src/internal/ab-collector.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;GAcG;AAEH,OAAO,EAEL,KAAK,cAAc,EAGpB,MAAM,UAAU,CAAC;AAClB,OAAO,KAAK,EAAE,YAAY,EAAE,YAAY,EAAE,WAAW,EAAE,MAAM,aAAa,CAAC;AAU3E,YAAY,EAAE,YAAY,EAAE,CAAC;AAE7B,MAAM,WAAW,kBAAkB;IACjC;;;OAGG;IACH,aAAa,CAAC,EAAE,CAAC,MAAM,EAAE,cAAc,KAAK,IAAI,CAAC;CAClD;AASD,qBAAa,WAAW;IAQpB,OAAO,CAAC,QAAQ,CAAC,WAAW;IAC5B,OAAO,CAAC,QAAQ,CAAC,MAAM;IACvB,OAAO,CAAC,QAAQ,CAAC,UAAU;IAT7B,OAAO,CAAC,QAAQ,CAAC,KAAK,CAAsC;IAC5D,OAAO,CAAC,QAAQ,CAAC,QAAQ,CAAqB;IAC9C,OAAO,CAAC,QAAQ,CAAC,aAAa,CAEhB;IAEd,YACmB,WAAW,EAAE,SAAS,YAAY,EAAE,EACpC,MAAM,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,IAAI,EAC9B,UAAU,EAAE,CAAC,SAAS,EAAE,MAAM,KAAK,OAAO,CAAC,YAAY,EAAE,CAAC,EAC3E,OAAO,CAAC,EAAE,kBAAkB,EAG7B;IAED,IAAI,OAAO,IAAI,OAAO,CAErB;IAED;;;OAGG;IACG,OAAO,CACX,KAAK,EAAE,YAAY,EACnB,WAAW,EAAE,WAAW,EACxB,SAAS,EAAE,MAAM,GAChB,OAAO,CAAC,IAAI,CAAC,CAuBf;IAED,OAAO,CAAC,IAAI;YAKE,IAAI;IA6ElB,OAAO,CAAC,YAAY;CAQrB"}

package/dist/internal/ab-collector.js

@@ -1,142 +0,0 @@
-/**
- * Stream-native collector for {@link defineAB} experiments.
- *
- * Pure fold over the session event log:
- * - sticky arm = last `ab.assigned` for that experiment
- * - metrics accumulate from the stream; `onSample` on turn complete/fail
- *
- * Enrollment is written by the engine at session creation (not here).
- * In-memory state is a cache: on cold start (or after park eviction) the
- * collector replays `events.ndjson` so counters survive restart.
- *
- * Hydration note: the engine appends before dispatch, so the first-touch
- * replay already includes the current event — after rebuild we return
- * without folding it again (and without re-firing `onSample`).
- */
-var __awaiter = (this && this.__awaiter) || function (thisArg, _arguments, P, generator) {
-    function adopt(value) { return value instanceof P ? value : new P(function (resolve) { resolve(value); }); }
-    return new (P || (P = Promise))(function (resolve, reject) {
-        function fulfilled(value) { try { step(generator.next(value)); } catch (e) { reject(e); } }
-        function rejected(value) { try { step(generator["throw"](value)); } catch (e) { reject(e); } }
-        function step(result) { result.done ? resolve(result.value) : adopt(result.value).then(fulfilled, rejected); }
-        step((generator = generator.apply(thisArg, _arguments || [])).next());
-    });
-};
-import { cloneABMetrics, } from "../ab.js";
-import { applyDeriveForEvent, emptyFoldedABSession, ensureArmAccum, foldABEvent, } from "./ab-fold.js";
-import { describeError } from "./describe-error.js";
-/** Drop cache after these — next event rehydrates from the durable log. */
-const EVICT_ON = new Set([
-    "session.waiting",
-    "session.completed",
-    "session.failed",
-]);
-export class ABCollector {
-    constructor(experiments, logger, loadEvents, options) {
-        this.experiments = experiments;
-        this.logger = logger;
-        this.loadEvents = loadEvents;
-        this.state = new Map();
-        this.hydrated = new Set();
-        this.persistSample = options === null || options === void 0 ? void 0 : options.persistSample;
-    }
-    get enabled() {
-        return this.experiments.length > 0;
-    }
-    /**
-     * Fold one live event. On first touch (or after eviction), replays the
-     * durable log first so enrollment + metrics match disk.
-     */
-    onEvent(event, sessionInfo, agentName) {
-        return __awaiter(this, void 0, void 0, function* () {
-            if (!this.enabled) {
-                return;
-            }
-            if (!this.hydrated.has(event.sessionId)) {
-                const history = yield this.loadEvents(event.sessionId);
-                // Rebuild arms + metrics only — do not re-fire onSample for past turns.
-                // History already includes `event` (append-before-dispatch).
-                for (const past of history) {
-                    yield this.fold(past, sessionInfo, agentName, { emitSamples: false });
-                }
-                this.hydrated.add(event.sessionId);
-                if (EVICT_ON.has(event.type)) {
-                    this.drop(event.sessionId);
-                }
-                return;
-            }
-            yield this.fold(event, sessionInfo, agentName, { emitSamples: true });
-            if (EVICT_ON.has(event.type)) {
-                this.drop(event.sessionId);
-            }
-        });
-    }
-    drop(sessionId) {
-        this.state.delete(sessionId);
-        this.hydrated.delete(sessionId);
-    }
-    fold(event, sessionInfo, agentName, options) {
-        return __awaiter(this, void 0, void 0, function* () {
-            var _a, _b;
-            const session = this.sessionAccum(event.sessionId);
-            if (event.type === "ab.assigned") {
-                foldABEvent(session, event);
-                return;
-            }
-            if (session.arms.size === 0) {
-                return;
-            }
-            // Built-ins for every enrolled arm (shared fold).
-            foldABEvent(session, event);
-            for (const experiment of this.experiments) {
-                const variant = session.arms.get(experiment.name);
-                if (variant === undefined || variant === null) {
-                    continue;
-                }
-                const def = experiment.definition;
-                const accum = ensureArmAccum(session, experiment.name, variant);
-                if (def.derive !== undefined) {
-                    yield applyDeriveForEvent(accum.metrics.custom, def.derive, event, {
-                        agent: { name: agentName },
-                        channel: { id: sessionInfo.channelId },
-                        session: sessionInfo,
-                        experiment: experiment.name,
-                        variant,
-                    }, (key, error) => {
-                        this.logger(`[agent-sdk] ab "${experiment.name}" derive.${key} threw: ${describeError(error)}`);
-                    });
-                }
-                if (!options.emitSamples) {
-                    continue;
-                }
-                const reason = sampleReason(event);
-                if (reason !== undefined) {
-                    const sample = Object.assign(Object.assign({ experiment: experiment.name, variant }, (((_a = def.variants[variant]) === null || _a === void 0 ? void 0 : _a.label) !== undefined
-                        ? { variantLabel: def.variants[variant].label }
-                        : {})), { sessionId: event.sessionId, channelId: sessionInfo.channelId, metrics: cloneABMetrics(accum.metrics), reason, at: event.at });
-                    try {
-                        yield def.onSample(sample);
-                    }
-                    catch (error) {
-                        this.logger(`[agent-sdk] ab "${experiment.name}" onSample threw: ${describeError(error)}`);
-                    }
-                    (_b = this.persistSample) === null || _b === void 0 ? void 0 : _b.call(this, sample);
-                }
-            }
-        });
-    }
-    sessionAccum(sessionId) {
-        let session = this.state.get(sessionId);
-        if (session === undefined) {
-            session = emptyFoldedABSession();
-            this.state.set(sessionId, session);
-        }
-        return session;
-    }
-}
-function sampleReason(event) {
-    if (event.type === "turn.completed" || event.type === "turn.failed") {
-        return event.type;
-    }
-    return undefined;
-}

package/dist/internal/ab-fold.d.ts

@@ -1,36 +0,0 @@
-/**
- * Pure fold of a session event stream into A/B arms + cumulative metrics.
- * Shared by {@link ABCollector} (live) and {@link buildABSnapshot} (read API).
- */
-import { type ABCollectContext, type ABDefinition, type ABMetrics } from "../ab.js";
-import type { DiscoveredAB, SessionEvent, SessionInfo } from "../types.js";
-export interface ABArmAccum {
-    variant: string;
-    metrics: ABMetrics;
-    turnStartedAt: string | null;
-}
-export interface FoldedABSession {
-    /** experiment → variant key, or `null` for sticky skip */
-    arms: Map<string, string | null>;
-    /** experiment → metrics (only for enrolled arms) */
-    metrics: Map<string, ABArmAccum>;
-}
-export declare function emptyFoldedABSession(): FoldedABSession;
-/** Ensure a metrics bucket exists for an enrolled arm. */
-export declare function ensureArmAccum(state: FoldedABSession, experiment: string, variant: string): ABArmAccum;
-/** Fold one event's built-in metrics + assignment. Does not run `derive`. */
-export declare function foldABEvent(state: FoldedABSession, event: SessionEvent): void;
-export declare function foldABStream(events: readonly SessionEvent[]): FoldedABSession;
-/**
- * Apply `derive` extractors for one event into `custom` counters.
- * Errors are reported via `onError` and skipped.
- */
-export declare function applyDeriveForEvent(custom: Record<string, number>, derive: NonNullable<ABDefinition["derive"]>, event: SessionEvent, collectCtx: ABCollectContext, onError: (key: string, error: unknown) => void): Promise<void>;
-/**
- * Re-run `derive` extractors over the stream for enrolled arms.
- * Mutates `state.metrics` in place. Errors are logged and skipped.
- */
-export declare function applyABDerive(state: FoldedABSession, events: readonly SessionEvent[], experiments: readonly DiscoveredAB[], sessionInfo: SessionInfo, agentName: string, logger: (line: string) => void): Promise<void>;
-export declare function applyBuiltinMetrics(accum: ABArmAccum, event: SessionEvent): void;
-export declare function cloneFoldedMetrics(accum: ABArmAccum | undefined): ABMetrics | undefined;
-//# sourceMappingURL=ab-fold.d.ts.map

package/dist/internal/ab-fold.d.ts.map

@@ -1 +0,0 @@
-{"version":3,"file":"ab-fold.d.ts","sourceRoot":"","sources":["../../src/internal/ab-fold.ts"],"names":[],"mappings":"AAAA;;;GAGG;AAEH,OAAO,EACL,KAAK,gBAAgB,EACrB,KAAK,YAAY,EACjB,KAAK,SAAS,EAGf,MAAM,UAAU,CAAC;AAClB,OAAO,KAAK,EAAE,YAAY,EAAE,YAAY,EAAE,WAAW,EAAE,MAAM,aAAa,CAAC;AAG3E,MAAM,WAAW,UAAU;IACzB,OAAO,EAAE,MAAM,CAAC;IAChB,OAAO,EAAE,SAAS,CAAC;IACnB,aAAa,EAAE,MAAM,GAAG,IAAI,CAAC;CAC9B;AAED,MAAM,WAAW,eAAe;IAC9B,0DAA0D;IAC1D,IAAI,EAAE,GAAG,CAAC,MAAM,EAAE,MAAM,GAAG,IAAI,CAAC,CAAC;IACjC,oDAAoD;IACpD,OAAO,EAAE,GAAG,CAAC,MAAM,EAAE,UAAU,CAAC,CAAC;CAClC;AAED,wBAAgB,oBAAoB,IAAI,eAAe,CAEtD;AAED,0DAA0D;AAC1D,wBAAgB,cAAc,CAC5B,KAAK,EAAE,eAAe,EACtB,UAAU,EAAE,MAAM,EAClB,OAAO,EAAE,MAAM,GACd,UAAU,CAWZ;AAED,6EAA6E;AAC7E,wBAAgB,WAAW,CAAC,KAAK,EAAE,eAAe,EAAE,KAAK,EAAE,YAAY,GAAG,IAAI,CA0B7E;AAED,wBAAgB,YAAY,CAAC,MAAM,EAAE,SAAS,YAAY,EAAE,GAAG,eAAe,CAM7E;AAED;;;GAGG;AACH,wBAAsB,mBAAmB,CACvC,MAAM,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,EAC9B,MAAM,EAAE,WAAW,CAAC,YAAY,CAAC,QAAQ,CAAC,CAAC,EAC3C,KAAK,EAAE,YAAY,EACnB,UAAU,EAAE,gBAAgB,EAC5B,OAAO,EAAE,CAAC,GAAG,EAAE,MAAM,EAAE,KAAK,EAAE,OAAO,KAAK,IAAI,GAC7C,OAAO,CAAC,IAAI,CAAC,CAWf;AAiBD;;;GAGG;AACH,wBAAsB,aAAa,CACjC,KAAK,EAAE,eAAe,EACtB,MAAM,EAAE,SAAS,YAAY,EAAE,EAC/B,WAAW,EAAE,SAAS,YAAY,EAAE,EACpC,WAAW,EAAE,WAAW,EACxB,SAAS,EAAE,MAAM,EACjB,MAAM,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,IAAI,GAC7B,OAAO,CAAC,IAAI,CAAC,CAiCf;AAED,wBAAgB,mBAAmB,CACjC,KAAK,EAAE,UAAU,EACjB,KAAK,EAAE,YAAY,GAClB,IAAI,CAoCN;AAcD,wBAAgB,kBAAkB,CAChC,KAAK,EAAE,UAAU,GAAG,SAAS,GAC5B,SAAS,GAAG,SAAS,CAKvB"}