@cursor/july 0.1.15 → 0.1.16

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (74) hide show
  1. package/dist/docs/404.html +2 -2
  2. package/dist/docs/ab.html +3 -3
  3. package/dist/docs/assets/{app.DpdGZTLe.js → app.DjHC-Ggf.js} +1 -1
  4. package/dist/docs/assets/chunks/@localSearchIndexroot.DZtu0ZIc.js +1 -0
  5. package/dist/docs/assets/chunks/{VPLocalSearchBox.IB-0QqIT.js → VPLocalSearchBox.DwviwmIq.js} +1 -1
  6. package/dist/docs/assets/chunks/{theme.-fYBoNtR.js → theme.BIpeYSon.js} +2 -2
  7. package/dist/docs/assets/{example-agents_index.md.BPXjUtRB.js → example-agents_index.md.D2PEVSXl.js} +2 -2
  8. package/dist/docs/assets/{example-agents_index.md.BPXjUtRB.lean.js → example-agents_index.md.D2PEVSXl.lean.js} +1 -1
  9. package/dist/docs/assets/example-agents_security-reviewer.md.BZSNycMf.js +19 -0
  10. package/dist/docs/assets/{example-agents_security-reviewer.md.CE9v-aKm.lean.js → example-agents_security-reviewer.md.BZSNycMf.lean.js} +1 -1
  11. package/dist/docs/building-with-agents.html +3 -3
  12. package/dist/docs/concepts.html +3 -3
  13. package/dist/docs/deployment.html +3 -3
  14. package/dist/docs/evals.html +3 -3
  15. package/dist/docs/example-agents/approval-buddy.html +3 -3
  16. package/dist/docs/example-agents/benny.html +3 -3
  17. package/dist/docs/example-agents/bugbot.html +3 -3
  18. package/dist/docs/example-agents/codebase-wiki.html +3 -3
  19. package/dist/docs/example-agents/codeowners-review.html +3 -3
  20. package/dist/docs/example-agents/concierge.html +3 -3
  21. package/dist/docs/example-agents/fsd.html +3 -3
  22. package/dist/docs/example-agents/index.html +5 -5
  23. package/dist/docs/example-agents/knowledge-base.html +3 -3
  24. package/dist/docs/example-agents/oncall.html +3 -3
  25. package/dist/docs/example-agents/security-reviewer.html +14 -14
  26. package/dist/docs/example-agents/slack-agent.html +3 -3
  27. package/dist/docs/example-agents/weather-agent.html +3 -3
  28. package/dist/docs/guides/agent-to-agent.html +3 -3
  29. package/dist/docs/guides/cloud-runtime.html +3 -3
  30. package/dist/docs/guides/github.html +3 -3
  31. package/dist/docs/guides/human-in-the-loop.html +3 -3
  32. package/dist/docs/guides/mcp-oauth.html +3 -3
  33. package/dist/docs/guides/slack.html +3 -3
  34. package/dist/docs/guides/webhooks.html +3 -3
  35. package/dist/docs/hashmap.json +1 -1
  36. package/dist/docs/hillclimbing.html +3 -3
  37. package/dist/docs/index.html +3 -3
  38. package/dist/docs/quickstart.html +3 -3
  39. package/dist/docs/reference/agent-config.html +3 -3
  40. package/dist/docs/reference/channels.html +3 -3
  41. package/dist/docs/reference/cli.html +3 -3
  42. package/dist/docs/reference/connections.html +3 -3
  43. package/dist/docs/reference/hooks.html +3 -3
  44. package/dist/docs/reference/http-api.html +3 -3
  45. package/dist/docs/reference/instructions.html +3 -3
  46. package/dist/docs/reference/playground.html +3 -3
  47. package/dist/docs/reference/project-layout.html +3 -3
  48. package/dist/docs/reference/prompt.html +3 -3
  49. package/dist/docs/reference/schedules.html +3 -3
  50. package/dist/docs/reference/sessions.html +3 -3
  51. package/dist/docs/reference/skills.html +3 -3
  52. package/dist/docs/reference/subagents.html +3 -3
  53. package/dist/docs/reference/tools.html +3 -3
  54. package/dist/docs/scaffolding-agents.html +3 -3
  55. package/dist/docs/storage.html +3 -3
  56. package/dist/docs/troubleshooting.html +3 -3
  57. package/dist/evals.d.ts +18 -0
  58. package/dist/evals.d.ts.map +1 -1
  59. package/dist/evals.js +30 -0
  60. package/dist/internal/eval-runner.d.ts.map +1 -1
  61. package/dist/internal/eval-runner.js +3 -2
  62. package/dist/internal/evals-client.d.ts.map +1 -1
  63. package/dist/internal/evals-client.js +3 -2
  64. package/dist/playground/assets/{index-BVMOoiek.js → index-Bwl4Onx4.js} +46 -47
  65. package/dist/playground/assets/{index-DYmP4b--.css → index-ByV4nfch.css} +1 -1
  66. package/dist/playground/index.html +2 -2
  67. package/docs/example-agents/index.md +1 -1
  68. package/docs/example-agents/security-reviewer.md +23 -21
  69. package/package.json +1 -1
  70. package/src/evals.ts +44 -0
  71. package/src/internal/eval-runner.ts +6 -1
  72. package/src/internal/evals-client.ts +9 -2
  73. package/dist/docs/assets/chunks/@localSearchIndexroot.D2d8CfFS.js +0 -1
  74. package/dist/docs/assets/example-agents_security-reviewer.md.CE9v-aKm.js +0 -19
@@ -9,9 +9,9 @@
9
9
  <link rel="preload stylesheet" href="/docs/assets/style.Bj-IXa5W.css" as="style">
10
10
  <link rel="preload stylesheet" href="/docs/vp-icons.css" as="style">
11
11
 
12
- <script type="module" src="/docs/assets/app.DpdGZTLe.js"></script>
12
+ <script type="module" src="/docs/assets/app.DjHC-Ggf.js"></script>
13
13
  <link rel="preload" href="/docs/assets/inter-roman-latin.Di8DUHzh.woff2" as="font" type="font/woff2" crossorigin="">
14
- <link rel="modulepreload" href="/docs/assets/chunks/theme.-fYBoNtR.js">
14
+ <link rel="modulepreload" href="/docs/assets/chunks/theme.BIpeYSon.js">
15
15
  <link rel="modulepreload" href="/docs/assets/chunks/framework.CAZyNGu9.js">
16
16
  <link rel="modulepreload" href="/docs/assets/storage.md.DRTdnFvd.lean.js">
17
17
  <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>
@@ -42,7 +42,7 @@
42
42
  <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;"> defineStorage</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">({</span></span>
43
43
  <span class="line"><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;"> ...</span><span style="--shiki-light:#6F42C1;--shiki-dark:#B392F0;">cursorHostedStorage</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">(),</span></span>
44
44
  <span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">});</span></span></code></pre></div><p>Built-in helpers:</p><table tabindex="0"><thead><tr><th>Import</th><th>Backend</th></tr></thead><tbody><tr><td><code>@cursor/july/storage/file-kv</code></td><td>File-per-key under <code>.agent-serve/kv</code></td></tr><tr><td><code>@cursor/july/storage/cursor-hosted</code></td><td>Platform Bugbot <code>agent_serve_*</code> via control-plane proxy</td></tr><tr><td><code>@cursor/july/storage/postgres-kv</code></td><td>Same tables; you supply <code>BUGBOTDB_URL</code> / <code>AGENT_SERVE_DEPLOYMENT_ID</code></td></tr></tbody></table></div></div></main><footer class="VPDocFooter" data-v-53b9fda6 data-v-3958cc3f><!--[--><!--]--><!----><nav class="prev-next" aria-labelledby="doc-footer-aria-label" data-v-3958cc3f><span class="visually-hidden" id="doc-footer-aria-label" data-v-3958cc3f>Pager</span><div class="pager" data-v-3958cc3f><a class="VPLink link pager-link prev" href="/docs/ab.html" data-v-3958cc3f><!--[--><span class="desc" data-v-3958cc3f>Previous page</span><span class="title" data-v-3958cc3f>Live A/B metrics</span><!--]--></a></div><div class="pager" data-v-3958cc3f><a class="VPLink link pager-link next" href="/docs/hillclimbing.html" data-v-3958cc3f><!--[--><span class="desc" data-v-3958cc3f>Next page</span><span class="title" data-v-3958cc3f>Hillclimbing</span><!--]--></a></div></nav></footer><!--[--><!--]--></div></div></div><!--[--><!--]--></div></div><!----><!--[--><!--]--></div></div>
45
- <script>window.__VP_HASH_MAP__=JSON.parse("{\"ab.md\":\"BMCZ6Hd7\",\"building-with-agents.md\":\"CJCtZCyi\",\"concepts.md\":\"Cfb9b-k1\",\"deployment.md\":\"TecHo0_2\",\"evals.md\":\"DYOjkRCX\",\"example-agents_approval-buddy.md\":\"DFGBYLcc\",\"example-agents_benny.md\":\"B0gjhI-p\",\"example-agents_bugbot.md\":\"DelIdhxB\",\"example-agents_codebase-wiki.md\":\"DC6sgwn0\",\"example-agents_codeowners-review.md\":\"Ku_tG2RY\",\"example-agents_concierge.md\":\"4rQTSMXt\",\"example-agents_fsd.md\":\"CzgUrDfi\",\"example-agents_index.md\":\"BPXjUtRB\",\"example-agents_knowledge-base.md\":\"BPJiVueF\",\"example-agents_oncall.md\":\"BG_sUMly\",\"example-agents_security-reviewer.md\":\"CE9v-aKm\",\"example-agents_slack-agent.md\":\"buLbgvBf\",\"example-agents_weather-agent.md\":\"C9Qv-W0o\",\"guides_agent-to-agent.md\":\"Bpzgq2Pq\",\"guides_cloud-runtime.md\":\"gVzabdQL\",\"guides_github.md\":\"DOOCpqsW\",\"guides_human-in-the-loop.md\":\"DlUqsp1S\",\"guides_mcp-oauth.md\":\"DqmEOQY1\",\"guides_slack.md\":\"FWale6Ip\",\"guides_webhooks.md\":\"B1EswtUu\",\"hillclimbing.md\":\"DHNast08\",\"index.md\":\"t0TM2Qzz\",\"quickstart.md\":\"BU6Iwi_9\",\"reference_agent-config.md\":\"DrW2JUM8\",\"reference_channels.md\":\"DdmiKgqf\",\"reference_cli.md\":\"DnYfr5V2\",\"reference_connections.md\":\"CsSr3rDz\",\"reference_hooks.md\":\"DyLVfE1O\",\"reference_http-api.md\":\"BncLd3PZ\",\"reference_instructions.md\":\"CgoV-YEb\",\"reference_playground.md\":\"CPZhfYaO\",\"reference_project-layout.md\":\"Bd_CKtNS\",\"reference_prompt.md\":\"BaiweQxE\",\"reference_schedules.md\":\"w_F2mXB6\",\"reference_sessions.md\":\"DLd6mvbv\",\"reference_skills.md\":\"B_jHN7JL\",\"reference_subagents.md\":\"zWAMNfi1\",\"reference_tools.md\":\"BRSDnTbN\",\"scaffolding-agents.md\":\"C3pTrmoE\",\"storage.md\":\"DRTdnFvd\",\"troubleshooting.md\":\"CmQkmnzC\"}");window.__VP_SITE_DATA__=JSON.parse("{\"lang\":\"en-US\",\"dir\":\"ltr\",\"title\":\"agentkit\",\"description\":\"Filesystem-first framework for building and serving Cursor agents.\",\"base\":\"/docs/\",\"head\":[],\"router\":{\"prefetchLinks\":true},\"appearance\":true,\"themeConfig\":{\"nav\":[{\"text\":\"Quickstart\",\"link\":\"/quickstart\"},{\"text\":\"Guides\",\"link\":\"/guides/webhooks\"},{\"text\":\"Examples\",\"link\":\"/example-agents/\"},{\"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\":\"Concepts\",\"link\":\"/concepts\"}]},{\"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\":\"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\":\"Cloud runtime\",\"link\":\"/guides/cloud-runtime\"}]},{\"text\":\"Example agents\",\"items\":[{\"text\":\"Choose an example\",\"link\":\"/example-agents/\"},{\"text\":\"Weather agent\",\"link\":\"/example-agents/weather-agent\"},{\"text\":\"Slack agent\",\"link\":\"/example-agents/slack-agent\"},{\"text\":\"Concierge\",\"link\":\"/example-agents/concierge\"},{\"text\":\"Playbook router\",\"link\":\"/example-agents/benny\"},{\"text\":\"Alert investigator\",\"link\":\"/example-agents/oncall\"},{\"text\":\"PR evidence reviewer\",\"link\":\"/example-agents/bugbot\"},{\"text\":\"Approval Buddy\",\"link\":\"/example-agents/approval-buddy\"},{\"text\":\"Security Reviewer\",\"link\":\"/example-agents/security-reviewer\"},{\"text\":\"Remote PR coordinator\",\"link\":\"/example-agents/fsd\"},{\"text\":\"Knowledge base\",\"link\":\"/example-agents/knowledge-base\"},{\"text\":\"Codebase wiki\",\"link\":\"/example-agents/codebase-wiki\"},{\"text\":\"Codeowners review\",\"link\":\"/example-agents/codeowners-review\"}]},{\"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\":\"Channels\",\"link\":\"/reference/channels\"},{\"text\":\"Schedules & reminders\",\"link\":\"/reference/schedules\"},{\"text\":\"Hooks\",\"link\":\"/reference/hooks\"},{\"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>
45
+ <script>window.__VP_HASH_MAP__=JSON.parse("{\"ab.md\":\"BMCZ6Hd7\",\"building-with-agents.md\":\"CJCtZCyi\",\"concepts.md\":\"Cfb9b-k1\",\"deployment.md\":\"TecHo0_2\",\"evals.md\":\"DYOjkRCX\",\"example-agents_approval-buddy.md\":\"DFGBYLcc\",\"example-agents_benny.md\":\"B0gjhI-p\",\"example-agents_bugbot.md\":\"DelIdhxB\",\"example-agents_codebase-wiki.md\":\"DC6sgwn0\",\"example-agents_codeowners-review.md\":\"Ku_tG2RY\",\"example-agents_concierge.md\":\"4rQTSMXt\",\"example-agents_fsd.md\":\"CzgUrDfi\",\"example-agents_index.md\":\"D2PEVSXl\",\"example-agents_knowledge-base.md\":\"BPJiVueF\",\"example-agents_oncall.md\":\"BG_sUMly\",\"example-agents_security-reviewer.md\":\"BZSNycMf\",\"example-agents_slack-agent.md\":\"buLbgvBf\",\"example-agents_weather-agent.md\":\"C9Qv-W0o\",\"guides_agent-to-agent.md\":\"Bpzgq2Pq\",\"guides_cloud-runtime.md\":\"gVzabdQL\",\"guides_github.md\":\"DOOCpqsW\",\"guides_human-in-the-loop.md\":\"DlUqsp1S\",\"guides_mcp-oauth.md\":\"DqmEOQY1\",\"guides_slack.md\":\"FWale6Ip\",\"guides_webhooks.md\":\"B1EswtUu\",\"hillclimbing.md\":\"DHNast08\",\"index.md\":\"t0TM2Qzz\",\"quickstart.md\":\"BU6Iwi_9\",\"reference_agent-config.md\":\"DrW2JUM8\",\"reference_channels.md\":\"DdmiKgqf\",\"reference_cli.md\":\"DnYfr5V2\",\"reference_connections.md\":\"CsSr3rDz\",\"reference_hooks.md\":\"DyLVfE1O\",\"reference_http-api.md\":\"BncLd3PZ\",\"reference_instructions.md\":\"CgoV-YEb\",\"reference_playground.md\":\"CPZhfYaO\",\"reference_project-layout.md\":\"Bd_CKtNS\",\"reference_prompt.md\":\"BaiweQxE\",\"reference_schedules.md\":\"w_F2mXB6\",\"reference_sessions.md\":\"DLd6mvbv\",\"reference_skills.md\":\"B_jHN7JL\",\"reference_subagents.md\":\"zWAMNfi1\",\"reference_tools.md\":\"BRSDnTbN\",\"scaffolding-agents.md\":\"C3pTrmoE\",\"storage.md\":\"DRTdnFvd\",\"troubleshooting.md\":\"CmQkmnzC\"}");window.__VP_SITE_DATA__=JSON.parse("{\"lang\":\"en-US\",\"dir\":\"ltr\",\"title\":\"agentkit\",\"description\":\"Filesystem-first framework for building and serving Cursor agents.\",\"base\":\"/docs/\",\"head\":[],\"router\":{\"prefetchLinks\":true},\"appearance\":true,\"themeConfig\":{\"nav\":[{\"text\":\"Quickstart\",\"link\":\"/quickstart\"},{\"text\":\"Guides\",\"link\":\"/guides/webhooks\"},{\"text\":\"Examples\",\"link\":\"/example-agents/\"},{\"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\":\"Concepts\",\"link\":\"/concepts\"}]},{\"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\":\"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\":\"Cloud runtime\",\"link\":\"/guides/cloud-runtime\"}]},{\"text\":\"Example agents\",\"items\":[{\"text\":\"Choose an example\",\"link\":\"/example-agents/\"},{\"text\":\"Weather agent\",\"link\":\"/example-agents/weather-agent\"},{\"text\":\"Slack agent\",\"link\":\"/example-agents/slack-agent\"},{\"text\":\"Concierge\",\"link\":\"/example-agents/concierge\"},{\"text\":\"Playbook router\",\"link\":\"/example-agents/benny\"},{\"text\":\"Alert investigator\",\"link\":\"/example-agents/oncall\"},{\"text\":\"PR evidence reviewer\",\"link\":\"/example-agents/bugbot\"},{\"text\":\"Approval Buddy\",\"link\":\"/example-agents/approval-buddy\"},{\"text\":\"Security Reviewer\",\"link\":\"/example-agents/security-reviewer\"},{\"text\":\"Remote PR coordinator\",\"link\":\"/example-agents/fsd\"},{\"text\":\"Knowledge base\",\"link\":\"/example-agents/knowledge-base\"},{\"text\":\"Codebase wiki\",\"link\":\"/example-agents/codebase-wiki\"},{\"text\":\"Codeowners review\",\"link\":\"/example-agents/codeowners-review\"}]},{\"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\":\"Channels\",\"link\":\"/reference/channels\"},{\"text\":\"Schedules & reminders\",\"link\":\"/reference/schedules\"},{\"text\":\"Hooks\",\"link\":\"/reference/hooks\"},{\"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>
46
46
 
47
47
  </body>
48
48
  </html>
@@ -9,9 +9,9 @@
9
9
  <link rel="preload stylesheet" href="/docs/assets/style.Bj-IXa5W.css" as="style">
10
10
  <link rel="preload stylesheet" href="/docs/vp-icons.css" as="style">
11
11
 
12
- <script type="module" src="/docs/assets/app.DpdGZTLe.js"></script>
12
+ <script type="module" src="/docs/assets/app.DjHC-Ggf.js"></script>
13
13
  <link rel="preload" href="/docs/assets/inter-roman-latin.Di8DUHzh.woff2" as="font" type="font/woff2" crossorigin="">
14
- <link rel="modulepreload" href="/docs/assets/chunks/theme.-fYBoNtR.js">
14
+ <link rel="modulepreload" href="/docs/assets/chunks/theme.BIpeYSon.js">
15
15
  <link rel="modulepreload" href="/docs/assets/chunks/framework.CAZyNGu9.js">
16
16
  <link rel="modulepreload" href="/docs/assets/troubleshooting.md.CmQkmnzC.lean.js">
17
17
  <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>
@@ -19,7 +19,7 @@
19
19
  </head>
20
20
  <body>
21
21
  <div id="app"><div class="Layout" data-v-05085060><!--[--><!--]--><!--[--><span tabindex="-1" data-v-30dc752a></span><a href="#VPContent" class="VPSkipLink visually-hidden" data-v-30dc752a>Skip to content</a><!--]--><!----><header class="VPNav" data-v-05085060 data-v-cbe59881><div class="VPNavBar" data-v-cbe59881 data-v-dd8a1864><div class="wrapper" data-v-dd8a1864><div class="container" data-v-dd8a1864><div class="title" data-v-dd8a1864><div class="VPNavBarTitle has-sidebar" data-v-dd8a1864 data-v-f9346b2b><a class="title" href="/docs/" data-v-f9346b2b><!--[--><!--]--><!----><span data-v-f9346b2b>agentkit</span><!--[--><!--]--></a></div></div><div class="content" data-v-dd8a1864><div class="content-body" data-v-dd8a1864><!--[--><!--]--><div class="VPNavBarSearch search" data-v-dd8a1864><!--[--><!----><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-dd8a1864 data-v-7ed6e5ac><span id="main-nav-aria-label" class="visually-hidden" data-v-7ed6e5ac> Main Navigation </span><!--[--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/quickstart.html" tabindex="0" data-v-7ed6e5ac data-v-65720067><!--[--><span data-v-65720067>Quickstart</span><!--]--></a><!--]--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/guides/webhooks.html" tabindex="0" data-v-7ed6e5ac data-v-65720067><!--[--><span data-v-65720067>Guides</span><!--]--></a><!--]--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/example-agents/" tabindex="0" data-v-7ed6e5ac data-v-65720067><!--[--><span data-v-65720067>Examples</span><!--]--></a><!--]--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/reference/project-layout.html" tabindex="0" data-v-7ed6e5ac data-v-65720067><!--[--><span data-v-65720067>Reference</span><!--]--></a><!--]--><!--]--></nav><!----><div class="VPNavBarAppearance appearance" data-v-dd8a1864 data-v-2b2b395e><button class="VPSwitch VPSwitchAppearance" type="button" role="switch" title aria-checked="false" data-v-2b2b395e data-v-182deabf data-v-2562b538><span class="check" data-v-2562b538><span class="icon" data-v-2562b538><!--[--><span class="vpi-sun sun" data-v-182deabf></span><span class="vpi-moon moon" data-v-182deabf></span><!--]--></span></span></button></div><!----><div class="VPFlyout VPNavBarExtra extra" data-v-dd8a1864 data-v-f3b584b7 data-v-82133de6><button type="button" class="button" aria-haspopup="true" aria-expanded="false" aria-label="extra navigation" data-v-82133de6><span class="vpi-more-horizontal icon" data-v-82133de6></span></button><div class="menu" data-v-82133de6><div class="VPMenu" data-v-82133de6 data-v-759c9e19><!----><!--[--><!--[--><!----><div class="group" data-v-f3b584b7><div class="item appearance" data-v-f3b584b7><p class="label" data-v-f3b584b7>Appearance</p><div class="appearance-action" data-v-f3b584b7><button class="VPSwitch VPSwitchAppearance" type="button" role="switch" title aria-checked="false" data-v-f3b584b7 data-v-182deabf data-v-2562b538><span class="check" data-v-2562b538><span class="icon" data-v-2562b538><!--[--><span class="vpi-sun sun" data-v-182deabf></span><span class="vpi-moon moon" data-v-182deabf></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-dd8a1864 data-v-ab07e844><span class="container" data-v-ab07e844><span class="top" data-v-ab07e844></span><span class="middle" data-v-ab07e844></span><span class="bottom" data-v-ab07e844></span></span></button></div></div></div></div><div class="divider" data-v-dd8a1864><div class="divider-line" data-v-dd8a1864></div></div></div><!----></header><div class="VPLocalNav has-sidebar empty" data-v-05085060 data-v-826b8761><div class="container" data-v-826b8761><button class="menu" aria-expanded="false" aria-controls="VPSidebarNav" data-v-826b8761><span class="vpi-align-left menu-icon" data-v-826b8761></span><span class="menu-text" data-v-826b8761>Menu</span></button><div class="VPLocalNavOutlineDropdown" style="--vp-vh:0px;" data-v-826b8761 data-v-01af9e73><button data-v-01af9e73>Return to top</button><!----></div></div></div><aside class="VPSidebar" data-v-05085060 data-v-5cd5b4d8><div class="curtain" data-v-5cd5b4d8></div><nav class="nav" id="VPSidebarNav" aria-labelledby="sidebar-aria-label" tabindex="-1" data-v-5cd5b4d8><span class="visually-hidden" id="sidebar-aria-label" data-v-5cd5b4d8> Sidebar Navigation </span><!--[--><!--]--><!--[--><div class="no-transition group" data-v-6b69f472><section class="VPSidebarItem level-0" data-v-6b69f472 data-v-b6893b1b><div class="item" role="button" tabindex="0" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><h2 class="text" data-v-b6893b1b>Getting started</h2><!----></div><div class="items" data-v-b6893b1b><!--[--><div class="VPSidebarItem level-1 is-link" data-v-b6893b1b><div class="item" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><a class="VPLink link link" href="/docs/" data-v-b6893b1b><!--[--><p class="text" data-v-b6893b1b>Overview</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b6893b1b><div class="item" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><a class="VPLink link link" href="/docs/quickstart.html" data-v-b6893b1b><!--[--><p class="text" data-v-b6893b1b>Quickstart</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b6893b1b><div class="item" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><a class="VPLink link link" href="/docs/scaffolding-agents.html" data-v-b6893b1b><!--[--><p class="text" data-v-b6893b1b>Scaffold an agent with Cursor</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b6893b1b><div class="item" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><a class="VPLink link link" href="/docs/concepts.html" data-v-b6893b1b><!--[--><p class="text" data-v-b6893b1b>Concepts</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-6b69f472><section class="VPSidebarItem level-0" data-v-6b69f472 data-v-b6893b1b><div class="item" role="button" tabindex="0" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><h2 class="text" data-v-b6893b1b>Improving agents</h2><!----></div><div class="items" data-v-b6893b1b><!--[--><div class="VPSidebarItem level-1 is-link" data-v-b6893b1b><div class="item" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><a class="VPLink link link" href="/docs/building-with-agents.html" data-v-b6893b1b><!--[--><p class="text" data-v-b6893b1b>Building agents with agents</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b6893b1b><div class="item" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><a class="VPLink link link" href="/docs/evals.html" data-v-b6893b1b><!--[--><p class="text" data-v-b6893b1b>Evals</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b6893b1b><div class="item" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><a class="VPLink link link" href="/docs/ab.html" data-v-b6893b1b><!--[--><p class="text" data-v-b6893b1b>Live A/B metrics</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b6893b1b><div class="item" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><a class="VPLink link link" href="/docs/storage.html" data-v-b6893b1b><!--[--><p class="text" data-v-b6893b1b>Storage</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b6893b1b><div class="item" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><a class="VPLink link link" href="/docs/hillclimbing.html" data-v-b6893b1b><!--[--><p class="text" data-v-b6893b1b>Hillclimbing</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-6b69f472><section class="VPSidebarItem level-0" data-v-6b69f472 data-v-b6893b1b><div class="item" role="button" tabindex="0" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><h2 class="text" data-v-b6893b1b>Guides</h2><!----></div><div class="items" data-v-b6893b1b><!--[--><div class="VPSidebarItem level-1 is-link" data-v-b6893b1b><div class="item" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><a class="VPLink link link" href="/docs/guides/webhooks.html" data-v-b6893b1b><!--[--><p class="text" data-v-b6893b1b>Webhooks & custom channels</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b6893b1b><div class="item" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><a class="VPLink link link" href="/docs/guides/github.html" data-v-b6893b1b><!--[--><p class="text" data-v-b6893b1b>GitHub</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b6893b1b><div class="item" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><a class="VPLink link link" href="/docs/guides/slack.html" data-v-b6893b1b><!--[--><p class="text" data-v-b6893b1b>Slack</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b6893b1b><div class="item" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><a class="VPLink link link" href="/docs/guides/human-in-the-loop.html" data-v-b6893b1b><!--[--><p class="text" data-v-b6893b1b>Human-in-the-loop approvals</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b6893b1b><div class="item" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><a class="VPLink link link" href="/docs/guides/agent-to-agent.html" data-v-b6893b1b><!--[--><p class="text" data-v-b6893b1b>Agent-to-agent</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b6893b1b><div class="item" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><a class="VPLink link link" href="/docs/guides/cloud-runtime.html" data-v-b6893b1b><!--[--><p class="text" data-v-b6893b1b>Cloud runtime</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-6b69f472><section class="VPSidebarItem level-0" data-v-6b69f472 data-v-b6893b1b><div class="item" role="button" tabindex="0" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><h2 class="text" data-v-b6893b1b>Example agents</h2><!----></div><div class="items" data-v-b6893b1b><!--[--><div class="VPSidebarItem level-1 is-link" data-v-b6893b1b><div class="item" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><a class="VPLink link link" href="/docs/example-agents/" data-v-b6893b1b><!--[--><p class="text" data-v-b6893b1b>Choose an example</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b6893b1b><div class="item" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><a class="VPLink link link" href="/docs/example-agents/weather-agent.html" data-v-b6893b1b><!--[--><p class="text" data-v-b6893b1b>Weather agent</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b6893b1b><div class="item" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><a class="VPLink link link" href="/docs/example-agents/slack-agent.html" data-v-b6893b1b><!--[--><p class="text" data-v-b6893b1b>Slack agent</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b6893b1b><div class="item" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><a class="VPLink link link" href="/docs/example-agents/concierge.html" data-v-b6893b1b><!--[--><p class="text" data-v-b6893b1b>Concierge</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b6893b1b><div class="item" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><a class="VPLink link link" href="/docs/example-agents/benny.html" data-v-b6893b1b><!--[--><p class="text" data-v-b6893b1b>Playbook router</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b6893b1b><div class="item" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><a class="VPLink link link" href="/docs/example-agents/oncall.html" data-v-b6893b1b><!--[--><p class="text" data-v-b6893b1b>Alert investigator</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b6893b1b><div class="item" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><a class="VPLink link link" href="/docs/example-agents/bugbot.html" data-v-b6893b1b><!--[--><p class="text" data-v-b6893b1b>PR evidence reviewer</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b6893b1b><div class="item" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><a class="VPLink link link" href="/docs/example-agents/approval-buddy.html" data-v-b6893b1b><!--[--><p class="text" data-v-b6893b1b>Approval Buddy</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b6893b1b><div class="item" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><a class="VPLink link link" href="/docs/example-agents/security-reviewer.html" data-v-b6893b1b><!--[--><p class="text" data-v-b6893b1b>Security Reviewer</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b6893b1b><div class="item" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><a class="VPLink link link" href="/docs/example-agents/fsd.html" data-v-b6893b1b><!--[--><p class="text" data-v-b6893b1b>Remote PR coordinator</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b6893b1b><div class="item" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><a class="VPLink link link" href="/docs/example-agents/knowledge-base.html" data-v-b6893b1b><!--[--><p class="text" data-v-b6893b1b>Knowledge base</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b6893b1b><div class="item" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><a class="VPLink link link" href="/docs/example-agents/codebase-wiki.html" data-v-b6893b1b><!--[--><p class="text" data-v-b6893b1b>Codebase wiki</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b6893b1b><div class="item" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><a class="VPLink link link" href="/docs/example-agents/codeowners-review.html" data-v-b6893b1b><!--[--><p class="text" data-v-b6893b1b>Codeowners review</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-6b69f472><section class="VPSidebarItem level-0 has-active" data-v-6b69f472 data-v-b6893b1b><div class="item" role="button" tabindex="0" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><h2 class="text" data-v-b6893b1b>Operating</h2><!----></div><div class="items" data-v-b6893b1b><!--[--><div class="VPSidebarItem level-1 is-link" data-v-b6893b1b><div class="item" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><a class="VPLink link link" href="/docs/deployment.html" data-v-b6893b1b><!--[--><p class="text" data-v-b6893b1b>Deployment</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b6893b1b><div class="item" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><a class="VPLink link link" href="/docs/troubleshooting.html" data-v-b6893b1b><!--[--><p class="text" data-v-b6893b1b>Fix common problems</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-6b69f472><section class="VPSidebarItem level-0 collapsible" data-v-6b69f472 data-v-b6893b1b><div class="item" role="button" tabindex="0" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><h2 class="text" data-v-b6893b1b>Reference</h2><div class="caret" role="button" aria-label="toggle section" tabindex="0" data-v-b6893b1b><span class="vpi-chevron-right caret-icon" data-v-b6893b1b></span></div></div><div class="items" data-v-b6893b1b><!--[--><div class="VPSidebarItem level-1 is-link" data-v-b6893b1b><div class="item" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><a class="VPLink link link" href="/docs/reference/project-layout.html" data-v-b6893b1b><!--[--><p class="text" data-v-b6893b1b>Project layout</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b6893b1b><div class="item" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><a class="VPLink link link" href="/docs/reference/agent-config.html" data-v-b6893b1b><!--[--><p class="text" data-v-b6893b1b>Agent config</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b6893b1b><div class="item" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><a class="VPLink link link" href="/docs/reference/instructions.html" data-v-b6893b1b><!--[--><p class="text" data-v-b6893b1b>Instructions</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b6893b1b><div class="item" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><a class="VPLink link link" href="/docs/reference/tools.html" data-v-b6893b1b><!--[--><p class="text" data-v-b6893b1b>Tools</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b6893b1b><div class="item" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><a class="VPLink link link" href="/docs/reference/prompt.html" data-v-b6893b1b><!--[--><p class="text" data-v-b6893b1b>prompt</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b6893b1b><div class="item" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><a class="VPLink link link" href="/docs/reference/skills.html" data-v-b6893b1b><!--[--><p class="text" data-v-b6893b1b>Skills</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b6893b1b><div class="item" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><a class="VPLink link link" href="/docs/reference/connections.html" data-v-b6893b1b><!--[--><p class="text" data-v-b6893b1b>MCP Connections</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b6893b1b><div class="item" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><a class="VPLink link link" href="/docs/reference/subagents.html" data-v-b6893b1b><!--[--><p class="text" data-v-b6893b1b>Subagents</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b6893b1b><div class="item" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><a class="VPLink link link" href="/docs/reference/channels.html" data-v-b6893b1b><!--[--><p class="text" data-v-b6893b1b>Channels</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b6893b1b><div class="item" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><a class="VPLink link link" href="/docs/reference/schedules.html" data-v-b6893b1b><!--[--><p class="text" data-v-b6893b1b>Schedules & reminders</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b6893b1b><div class="item" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><a class="VPLink link link" href="/docs/reference/hooks.html" data-v-b6893b1b><!--[--><p class="text" data-v-b6893b1b>Hooks</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b6893b1b><div class="item" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><a class="VPLink link link" href="/docs/reference/sessions.html" data-v-b6893b1b><!--[--><p class="text" data-v-b6893b1b>Sessions & streaming</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b6893b1b><div class="item" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><a class="VPLink link link" href="/docs/reference/playground.html" data-v-b6893b1b><!--[--><p class="text" data-v-b6893b1b>Playground</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b6893b1b><div class="item" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><a class="VPLink link link" href="/docs/reference/cli.html" data-v-b6893b1b><!--[--><p class="text" data-v-b6893b1b>CLI</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-b6893b1b><div class="item" data-v-b6893b1b><div class="indicator" data-v-b6893b1b></div><a class="VPLink link link" href="/docs/reference/http-api.html" data-v-b6893b1b><!--[--><p class="text" data-v-b6893b1b>HTTP API</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><!--]--><!--[--><!--]--></nav></aside><div class="VPContent has-sidebar" id="VPContent" data-v-05085060 data-v-8eedf2ac><div class="VPDoc has-sidebar has-aside" data-v-8eedf2ac data-v-53b9fda6><!--[--><!--]--><div class="container" data-v-53b9fda6><div class="aside" data-v-53b9fda6><div class="aside-curtain" data-v-53b9fda6></div><div class="aside-container" data-v-53b9fda6><div class="aside-content" data-v-53b9fda6><div class="VPDocAside" data-v-53b9fda6 data-v-e448ecab><!--[--><!--]--><!--[--><!--]--><nav aria-labelledby="doc-outline-aria-label" class="VPDocAsideOutline" data-v-e448ecab data-v-b0b42374><div class="content" data-v-b0b42374><div class="outline-marker" data-v-b0b42374></div><div aria-level="2" class="outline-title" id="doc-outline-aria-label" role="heading" data-v-b0b42374>On this page</div><ul class="VPDocOutlineItem root" data-v-b0b42374 data-v-ae03bd52><!--[--><!--]--></ul></div></nav><!--[--><!--]--><div class="spacer" data-v-e448ecab></div><!--[--><!--]--><!----><!--[--><!--]--><!--[--><!--]--></div></div></div></div><div class="content" data-v-53b9fda6><div class="content-container" data-v-53b9fda6><!--[--><!--]--><main class="main" data-v-53b9fda6><div style="position:relative;" class="vp-doc _docs_troubleshooting" data-v-53b9fda6><div><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>agentkit 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>agentkit</code>; see <a href="./README.html#run-the-cli">Run the CLI</a> if you still need an alias.</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>agentkit 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>Edits to the playground don&#39;t show up</td><td>Use <code>serve --dev</code> and open the printed playground HMR URL (often port <code>5273</code>), not only the static <code>:3000</code> URL.</td></tr><tr><td>Sessions exist on disk 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> or inspect <code>sessions/</code> under your state root.</td></tr><tr><td>Port 3000 or 5273 is already in use</td><td>Find and stop the listener (<code>lsof -iTCP:3000 -sTCP:LISTEN</code> on macOS/Linux), and any leftover Vite or webhook-forwarder processes.</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>agentkit 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. Point <code>defineAgent({ local: { cwd } })</code> outside that tree, or set <code>--state-root</code> to a clean directory (for example under <code>/tmp</code>).</td></tr><tr><td>Server tools, skills, or workspace seed files never appear</td><td>The agent runtime is <code>cloud</code>. Those features apply on the local runtime. <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> (it rotates on each accepted follow-up), wait if the session is busy, or confirm the session is a chat session (task and schedule sessions are not followable).</td></tr><tr><td><code>409 session_busy</code> on <code>call --session</code></td><td>Wait for the model turn to finish, or omit <code>--session</code> for a one-off call.</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= agentkit 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>agentkit 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. Set <code>&lt;PREFIX&gt;_SLACK_BOT_TOKEN</code> and <code>&lt;PREFIX&gt;_SLACK_APP_TOKEN</code> per agent, then run <code>agentkit slack doctor --prefix &lt;PREFIX&gt;</code>.</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>Re-import a Slack app manifest with interactivity enabled. Channels that post approval cards need <code>toolApprovals: true</code> (and <code>interactivity: true</code> when you compose events by hand).</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>agentkit mcp oauth</code>.</td></tr><tr><td>Local auth works; hosted calls unauthorized</td><td>Run <code>agentkit mcp oauth &lt;name&gt; --store</code>, confirm names with <code>agentkit secrets list &lt;slug&gt;</code>, then redeploy.</td></tr><tr><td>Model asks for <code>mcp_auth</code> or IDE MCP for a privileged server</td><td>That connection is likely <code>hostOnly</code>. Call it from a host tool via <code>ctx.host.mcp</code>, and update instructions.</td></tr></tbody></table><p>See <a href="./guides/mcp-oauth.html">Host MCP OAuth</a> and <a href="./../skills/mcp-auth/SKILL.html"><code>skills/mcp-auth/SKILL.md</code></a>.</p><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>agentkit 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></div></div></main><footer class="VPDocFooter" data-v-53b9fda6 data-v-3958cc3f><!--[--><!--]--><!----><nav class="prev-next" aria-labelledby="doc-footer-aria-label" data-v-3958cc3f><span class="visually-hidden" id="doc-footer-aria-label" data-v-3958cc3f>Pager</span><div class="pager" data-v-3958cc3f><a class="VPLink link pager-link prev" href="/docs/deployment.html" data-v-3958cc3f><!--[--><span class="desc" data-v-3958cc3f>Previous page</span><span class="title" data-v-3958cc3f>Deployment</span><!--]--></a></div><div class="pager" data-v-3958cc3f><a class="VPLink link pager-link next" href="/docs/reference/project-layout.html" data-v-3958cc3f><!--[--><span class="desc" data-v-3958cc3f>Next page</span><span class="title" data-v-3958cc3f>Project layout</span><!--]--></a></div></nav></footer><!--[--><!--]--></div></div></div><!--[--><!--]--></div></div><!----><!--[--><!--]--></div></div>
22
- <script>window.__VP_HASH_MAP__=JSON.parse("{\"ab.md\":\"BMCZ6Hd7\",\"building-with-agents.md\":\"CJCtZCyi\",\"concepts.md\":\"Cfb9b-k1\",\"deployment.md\":\"TecHo0_2\",\"evals.md\":\"DYOjkRCX\",\"example-agents_approval-buddy.md\":\"DFGBYLcc\",\"example-agents_benny.md\":\"B0gjhI-p\",\"example-agents_bugbot.md\":\"DelIdhxB\",\"example-agents_codebase-wiki.md\":\"DC6sgwn0\",\"example-agents_codeowners-review.md\":\"Ku_tG2RY\",\"example-agents_concierge.md\":\"4rQTSMXt\",\"example-agents_fsd.md\":\"CzgUrDfi\",\"example-agents_index.md\":\"BPXjUtRB\",\"example-agents_knowledge-base.md\":\"BPJiVueF\",\"example-agents_oncall.md\":\"BG_sUMly\",\"example-agents_security-reviewer.md\":\"CE9v-aKm\",\"example-agents_slack-agent.md\":\"buLbgvBf\",\"example-agents_weather-agent.md\":\"C9Qv-W0o\",\"guides_agent-to-agent.md\":\"Bpzgq2Pq\",\"guides_cloud-runtime.md\":\"gVzabdQL\",\"guides_github.md\":\"DOOCpqsW\",\"guides_human-in-the-loop.md\":\"DlUqsp1S\",\"guides_mcp-oauth.md\":\"DqmEOQY1\",\"guides_slack.md\":\"FWale6Ip\",\"guides_webhooks.md\":\"B1EswtUu\",\"hillclimbing.md\":\"DHNast08\",\"index.md\":\"t0TM2Qzz\",\"quickstart.md\":\"BU6Iwi_9\",\"reference_agent-config.md\":\"DrW2JUM8\",\"reference_channels.md\":\"DdmiKgqf\",\"reference_cli.md\":\"DnYfr5V2\",\"reference_connections.md\":\"CsSr3rDz\",\"reference_hooks.md\":\"DyLVfE1O\",\"reference_http-api.md\":\"BncLd3PZ\",\"reference_instructions.md\":\"CgoV-YEb\",\"reference_playground.md\":\"CPZhfYaO\",\"reference_project-layout.md\":\"Bd_CKtNS\",\"reference_prompt.md\":\"BaiweQxE\",\"reference_schedules.md\":\"w_F2mXB6\",\"reference_sessions.md\":\"DLd6mvbv\",\"reference_skills.md\":\"B_jHN7JL\",\"reference_subagents.md\":\"zWAMNfi1\",\"reference_tools.md\":\"BRSDnTbN\",\"scaffolding-agents.md\":\"C3pTrmoE\",\"storage.md\":\"DRTdnFvd\",\"troubleshooting.md\":\"CmQkmnzC\"}");window.__VP_SITE_DATA__=JSON.parse("{\"lang\":\"en-US\",\"dir\":\"ltr\",\"title\":\"agentkit\",\"description\":\"Filesystem-first framework for building and serving Cursor agents.\",\"base\":\"/docs/\",\"head\":[],\"router\":{\"prefetchLinks\":true},\"appearance\":true,\"themeConfig\":{\"nav\":[{\"text\":\"Quickstart\",\"link\":\"/quickstart\"},{\"text\":\"Guides\",\"link\":\"/guides/webhooks\"},{\"text\":\"Examples\",\"link\":\"/example-agents/\"},{\"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\":\"Concepts\",\"link\":\"/concepts\"}]},{\"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\":\"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\":\"Cloud runtime\",\"link\":\"/guides/cloud-runtime\"}]},{\"text\":\"Example agents\",\"items\":[{\"text\":\"Choose an example\",\"link\":\"/example-agents/\"},{\"text\":\"Weather agent\",\"link\":\"/example-agents/weather-agent\"},{\"text\":\"Slack agent\",\"link\":\"/example-agents/slack-agent\"},{\"text\":\"Concierge\",\"link\":\"/example-agents/concierge\"},{\"text\":\"Playbook router\",\"link\":\"/example-agents/benny\"},{\"text\":\"Alert investigator\",\"link\":\"/example-agents/oncall\"},{\"text\":\"PR evidence reviewer\",\"link\":\"/example-agents/bugbot\"},{\"text\":\"Approval Buddy\",\"link\":\"/example-agents/approval-buddy\"},{\"text\":\"Security Reviewer\",\"link\":\"/example-agents/security-reviewer\"},{\"text\":\"Remote PR coordinator\",\"link\":\"/example-agents/fsd\"},{\"text\":\"Knowledge base\",\"link\":\"/example-agents/knowledge-base\"},{\"text\":\"Codebase wiki\",\"link\":\"/example-agents/codebase-wiki\"},{\"text\":\"Codeowners review\",\"link\":\"/example-agents/codeowners-review\"}]},{\"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\":\"Channels\",\"link\":\"/reference/channels\"},{\"text\":\"Schedules & reminders\",\"link\":\"/reference/schedules\"},{\"text\":\"Hooks\",\"link\":\"/reference/hooks\"},{\"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>
22
+ <script>window.__VP_HASH_MAP__=JSON.parse("{\"ab.md\":\"BMCZ6Hd7\",\"building-with-agents.md\":\"CJCtZCyi\",\"concepts.md\":\"Cfb9b-k1\",\"deployment.md\":\"TecHo0_2\",\"evals.md\":\"DYOjkRCX\",\"example-agents_approval-buddy.md\":\"DFGBYLcc\",\"example-agents_benny.md\":\"B0gjhI-p\",\"example-agents_bugbot.md\":\"DelIdhxB\",\"example-agents_codebase-wiki.md\":\"DC6sgwn0\",\"example-agents_codeowners-review.md\":\"Ku_tG2RY\",\"example-agents_concierge.md\":\"4rQTSMXt\",\"example-agents_fsd.md\":\"CzgUrDfi\",\"example-agents_index.md\":\"D2PEVSXl\",\"example-agents_knowledge-base.md\":\"BPJiVueF\",\"example-agents_oncall.md\":\"BG_sUMly\",\"example-agents_security-reviewer.md\":\"BZSNycMf\",\"example-agents_slack-agent.md\":\"buLbgvBf\",\"example-agents_weather-agent.md\":\"C9Qv-W0o\",\"guides_agent-to-agent.md\":\"Bpzgq2Pq\",\"guides_cloud-runtime.md\":\"gVzabdQL\",\"guides_github.md\":\"DOOCpqsW\",\"guides_human-in-the-loop.md\":\"DlUqsp1S\",\"guides_mcp-oauth.md\":\"DqmEOQY1\",\"guides_slack.md\":\"FWale6Ip\",\"guides_webhooks.md\":\"B1EswtUu\",\"hillclimbing.md\":\"DHNast08\",\"index.md\":\"t0TM2Qzz\",\"quickstart.md\":\"BU6Iwi_9\",\"reference_agent-config.md\":\"DrW2JUM8\",\"reference_channels.md\":\"DdmiKgqf\",\"reference_cli.md\":\"DnYfr5V2\",\"reference_connections.md\":\"CsSr3rDz\",\"reference_hooks.md\":\"DyLVfE1O\",\"reference_http-api.md\":\"BncLd3PZ\",\"reference_instructions.md\":\"CgoV-YEb\",\"reference_playground.md\":\"CPZhfYaO\",\"reference_project-layout.md\":\"Bd_CKtNS\",\"reference_prompt.md\":\"BaiweQxE\",\"reference_schedules.md\":\"w_F2mXB6\",\"reference_sessions.md\":\"DLd6mvbv\",\"reference_skills.md\":\"B_jHN7JL\",\"reference_subagents.md\":\"zWAMNfi1\",\"reference_tools.md\":\"BRSDnTbN\",\"scaffolding-agents.md\":\"C3pTrmoE\",\"storage.md\":\"DRTdnFvd\",\"troubleshooting.md\":\"CmQkmnzC\"}");window.__VP_SITE_DATA__=JSON.parse("{\"lang\":\"en-US\",\"dir\":\"ltr\",\"title\":\"agentkit\",\"description\":\"Filesystem-first framework for building and serving Cursor agents.\",\"base\":\"/docs/\",\"head\":[],\"router\":{\"prefetchLinks\":true},\"appearance\":true,\"themeConfig\":{\"nav\":[{\"text\":\"Quickstart\",\"link\":\"/quickstart\"},{\"text\":\"Guides\",\"link\":\"/guides/webhooks\"},{\"text\":\"Examples\",\"link\":\"/example-agents/\"},{\"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\":\"Concepts\",\"link\":\"/concepts\"}]},{\"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\":\"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\":\"Cloud runtime\",\"link\":\"/guides/cloud-runtime\"}]},{\"text\":\"Example agents\",\"items\":[{\"text\":\"Choose an example\",\"link\":\"/example-agents/\"},{\"text\":\"Weather agent\",\"link\":\"/example-agents/weather-agent\"},{\"text\":\"Slack agent\",\"link\":\"/example-agents/slack-agent\"},{\"text\":\"Concierge\",\"link\":\"/example-agents/concierge\"},{\"text\":\"Playbook router\",\"link\":\"/example-agents/benny\"},{\"text\":\"Alert investigator\",\"link\":\"/example-agents/oncall\"},{\"text\":\"PR evidence reviewer\",\"link\":\"/example-agents/bugbot\"},{\"text\":\"Approval Buddy\",\"link\":\"/example-agents/approval-buddy\"},{\"text\":\"Security Reviewer\",\"link\":\"/example-agents/security-reviewer\"},{\"text\":\"Remote PR coordinator\",\"link\":\"/example-agents/fsd\"},{\"text\":\"Knowledge base\",\"link\":\"/example-agents/knowledge-base\"},{\"text\":\"Codebase wiki\",\"link\":\"/example-agents/codebase-wiki\"},{\"text\":\"Codeowners review\",\"link\":\"/example-agents/codeowners-review\"}]},{\"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\":\"Channels\",\"link\":\"/reference/channels\"},{\"text\":\"Schedules & reminders\",\"link\":\"/reference/schedules\"},{\"text\":\"Hooks\",\"link\":\"/reference/hooks\"},{\"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>
23
23
 
24
24
  </body>
25
25
  </html>
package/dist/evals.d.ts CHANGED
@@ -200,6 +200,24 @@ export declare function expandEvalDefinition(fileId: string, definition: EvalDef
200
200
  * - multiple filters: OR
201
201
  */
202
202
  export declare function matchesEvalIdFilter(caseId: string, filter: string): boolean;
203
+ /**
204
+ * Tag for suite-aggregator datapoints that wait on sibling cases from the
205
+ * same eval file (e.g. `deepsec-recall/overall`). Selecting a summary case
206
+ * alone expands the batch to the whole file via
207
+ * {@link expandSummarySuiteSelection}.
208
+ */
209
+ export declare const EVAL_SUMMARY_TAG = "summary";
210
+ /** True when `tags` marks a suite-aggregator case. */
211
+ export declare function isEvalSummaryCase(tags: readonly string[] | undefined): boolean;
212
+ /**
213
+ * If `selected` includes any summary-tagged suite aggregator, pull in every
214
+ * other datapoint from the same `fileId` so the aggregator is not run alone.
215
+ * Preserves discovery order from `all`.
216
+ */
217
+ export declare function expandSummarySuiteSelection<T extends {
218
+ id: string;
219
+ fileId: string;
220
+ }>(all: readonly T[], selected: readonly T[], isSummary: (item: T) => boolean): T[];
203
221
  /**
204
222
  * Hard ceiling for concurrent eval cases.
205
223
  *
@@ -1 +1 @@
1
- {"version":3,"file":"evals.d.ts","sourceRoot":"","sources":["../src/evals.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA8CG;AAIH,OAAO,KAAK,EAAE,iBAAiB,EAAE,YAAY,EAAE,MAAM,YAAY,CAAC;AAElE,MAAM,MAAM,WAAW,GACnB;IAAE,IAAI,EAAE,UAAU,CAAC;IAAC,KAAK,EAAE,MAAM,GAAG,MAAM,CAAA;CAAE,GAC5C;IAAE,IAAI,EAAE,QAAQ,CAAC;IAAC,KAAK,EAAE,OAAO,CAAA;CAAE,GAClC;IACE,IAAI,EAAE,WAAW,CAAC;IAClB,SAAS,EAAE,CAAC,KAAK,EAAE,OAAO,KAAK,OAAO,CAAC;IACvC,KAAK,EAAE,MAAM,CAAC;CACf,CAAC;AAEN,wBAAgB,QAAQ,CAAC,KAAK,EAAE,MAAM,GAAG,MAAM,GAAG,WAAW,CAE5D;AAED,wBAAgB,MAAM,CAAC,KAAK,EAAE,OAAO,GAAG,WAAW,CAElD;AAED,wBAAgB,SAAS,CACvB,SAAS,EAAE,CAAC,KAAK,EAAE,OAAO,KAAK,OAAO,EACtC,KAAK,EAAE,MAAM,GACZ,WAAW,CAEb;AAED,MAAM,WAAW,mBAAmB;IAClC,IAAI,EAAE,MAAM,CAAC;IACb,MAAM,EAAE,OAAO,CAAC;IAChB,MAAM,CAAC,EAAE,MAAM,CAAC;CACjB;AAED,MAAM,WAAW,cAAc;IAC7B,OAAO,EAAE,MAAM,CAAC;IAChB,SAAS,EAAE,MAAM,CAAC;IAClB,MAAM,EAAE,YAAY,EAAE,CAAC;IACvB,SAAS,EAAE,MAAM,EAAE,CAAC;IACpB,EAAE,EAAE,OAAO,CAAC;CACb;AAED,MAAM,WAAW,eAAe;IAC9B,oFAAoF;IACpF,YAAY,CAAC,EAAE,MAAM,CAAC;IACtB,qEAAqE;IACrE,cAAc,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;IACxC;;;;OAIG;IACH,KAAK,CAAC,EAAE,iBAAiB,CAAC;CAC3B;AAED,MAAM,WAAW,eAAe;IAC9B,+DAA+D;IAC/D,IAAI,CAAC,OAAO,EAAE,MAAM,EAAE,OAAO,CAAC,EAAE,eAAe,GAAG,OAAO,CAAC,cAAc,CAAC,CAAC;IAC1E,0DAA0D;IAC1D,QAAQ,CAAC,KAAK,EAAE,MAAM,GAAG,IAAI,CAAC;IAC9B,QAAQ,CAAC,SAAS,EAAE,MAAM,GAAG,SAAS,CAAC;IACvC,+CAA+C;IAC/C,QAAQ,CAAC,MAAM,EAAE,YAAY,EAAE,CAAC;IAChC;;;;OAIG;IACH,QAAQ,CAAC,SAAS,EAAE,MAAM,CAAC;IAC3B,yDAAyD;IACzD,QAAQ,CAAC,UAAU,EAAE,MAAM,CAAC;IAC5B,8BAA8B;IAC9B,SAAS,IAAI,IAAI,CAAC;IAClB,mDAAmD;IACnD,UAAU,CAAC,IAAI,EAAE,MAAM,GAAG,IAAI,CAAC;IAC/B,+BAA+B;IAC/B,aAAa,CAAC,IAAI,EAAE,MAAM,GAAG,IAAI,CAAC;IAClC,2CAA2C;IAC3C,eAAe,CAAC,KAAK,EAAE,MAAM,GAAG,MAAM,GAAG,IAAI,CAAC;IAC9C,wDAAwD;IACxD,KAAK,CAAC,KAAK,EAAE,OAAO,EAAE,SAAS,EAAE,WAAW,GAAG,IAAI,CAAC;IACpD,gEAAgE;IAChE,GAAG,CAAC,OAAO,EAAE,MAAM,GAAG,IAAI,CAAC;IAC3B;;;;OAIG;IACH,MAAM,CAAC,IAAI,EAAE,MAAM,EAAE,KAAK,EAAE,MAAM,GAAG,MAAM,GAAG,IAAI,CAAC;CACpD;AAED,0EAA0E;AAC1E,eAAO,MAAM,mBAAmB,MAAM,CAAC;AAEvC,0EAA0E;AAC1E,MAAM,WAAW,aAAa;IAC5B;;;;OAIG;IACH,EAAE,EAAE,MAAM,CAAC;IACX,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB,IAAI,CAAC,EAAE,MAAM,EAAE,CAAC;IAChB,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB;;;;;OAKG;IACH,UAAU,CAAC,EAAE,MAAM,CAAC;IACpB,IAAI,EAAE,CAAC,CAAC,EAAE,eAAe,KAAK,OAAO,CAAC,IAAI,CAAC,CAAC;CAC7C;AAED;;;GAGG;AACH,MAAM,WAAW,UAAU;IACzB,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB,IAAI,CAAC,EAAE,MAAM,EAAE,CAAC;IAChB,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB;;;OAGG;IACH,UAAU,CAAC,EAAE,MAAM,CAAC;IACpB,sEAAsE;IACtE,IAAI,CAAC,EAAE,CAAC,CAAC,EAAE,eAAe,KAAK,OAAO,CAAC,IAAI,CAAC,CAAC;IAC7C,wEAAwE;IACxE,KAAK,CAAC,EAAE,aAAa,EAAE,CAAC;CACzB;AAED,sEAAsE;AACtE,MAAM,WAAW,kBAAkB;IACjC,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB,IAAI,CAAC,EAAE,MAAM,EAAE,CAAC;IAChB,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,8DAA8D;IAC9D,UAAU,CAAC,EAAE,MAAM,CAAC;IACpB,+DAA+D;IAC/D,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,IAAI,EAAE,CAAC,CAAC,EAAE,eAAe,KAAK,OAAO,CAAC,IAAI,CAAC,CAAC;IAC5C,QAAQ,CAAC,YAAY,EAAE,MAAM,CAAC;CAC/B;AAED,MAAM,MAAM,cAAc,GAAG,UAAU,GAAG;IAAE,QAAQ,CAAC,YAAY,EAAE,MAAM,CAAA;CAAE,CAAC;AAE5E;;;;GAIG;AACH,wBAAgB,uBAAuB,CAAC,KAAK,EAAE,OAAO,GAAG,MAAM,CAK9D;AAED,wBAAgB,UAAU,CAAC,MAAM,EAAE,UAAU,GAAG,cAAc,CAoC7D;AAaD;;;;;;;GAOG;AACH,wBAAgB,oBAAoB,CAClC,MAAM,EAAE,MAAM,EACd,UAAU,EAAE,cAAc,GACzB,KAAK,CAAC;IAAE,EAAE,EAAE,MAAM,CAAC;IAAC,UAAU,EAAE,kBAAkB,CAAA;CAAE,CAAC,CA8BvD;AAiCD;;;;;GAKG;AACH,wBAAgB,mBAAmB,CAAC,MAAM,EAAE,MAAM,EAAE,MAAM,EAAE,MAAM,GAAG,OAAO,CAE3E;AAED;;;;;GAKG;AACH,eAAO,MAAM,0BAA0B,MAAM,CAAC;AAE9C,gGAAgG;AAChG,eAAO,MAAM,gCAAgC,KAAK,CAAC;AAEnD,iEAAiE;AACjE,eAAO,MAAM,wBAAwB,MAAM,CAAC;AAE5C,MAAM,MAAM,iBAAiB,GAAG,SAAS,GAAG,SAAS,GAAG,MAAM,CAAC;AAC/D,MAAM,MAAM,eAAe,GAAG,SAAS,GAAG,WAAW,GAAG,QAAQ,GAAG,WAAW,CAAC;AAE/E,+DAA+D;AAC/D,MAAM,WAAW,gBAAgB;IAC/B,EAAE,EAAE,MAAM,CAAC;IACX,MAAM,EAAE,MAAM,CAAC;IACf,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB,IAAI,CAAC,EAAE,MAAM,EAAE,CAAC;IAChB,MAAM,EAAE,iBAAiB,CAAC;IAC1B,EAAE,CAAC,EAAE,OAAO,CAAC;IACb,UAAU,CAAC,EAAE,mBAAmB,EAAE,CAAC;IACnC,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,UAAU,CAAC,EAAE,MAAM,CAAC;IACpB,KAAK,CAAC,EAAE,MAAM,CAAC;IACf,IAAI,CAAC,EAAE,MAAM,EAAE,CAAC;IAChB,6DAA6D;IAC7D,OAAO,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,GAAG,MAAM,CAAC,CAAC;IAC1C,MAAM,CAAC,EAAE,MAAM,EAAE,CAAC;IAClB,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,KAAK,CAAC,EAAE,MAAM,EAAE,CAAC;IACjB,SAAS,CAAC,EAAE,KAAK,CAAC;QAChB,QAAQ,EAAE,MAAM,CAAC;QACjB,IAAI,CAAC,EAAE,OAAO,CAAC;QACf,MAAM,CAAC,EAAE,OAAO,CAAC;QACjB,OAAO,EAAE,OAAO,CAAC;KAClB,CAAC,CAAC;CACJ;AAED,gFAAgF;AAChF,MAAM,WAAW,eAAe;IAC9B,KAAK,EAAE,MAAM,CAAC;IACd,MAAM,EAAE,eAAe,CAAC;IACxB,SAAS,EAAE,MAAM,CAAC;IAClB,UAAU,CAAC,EAAE,MAAM,CAAC;IACpB,KAAK,CAAC,EAAE,MAAM,CAAC;IACf,OAAO,EAAE;QAAE,MAAM,EAAE,MAAM,CAAC;QAAC,MAAM,EAAE,MAAM,CAAC;QAAC,KAAK,EAAE,MAAM,CAAC;QAAC,IAAI,EAAE,MAAM,CAAA;KAAE,CAAC;IACzE,KAAK,EAAE,gBAAgB,EAAE,CAAC;IAC1B,MAAM,EAAE;QACN,cAAc,CAAC,EAAE,MAAM,CAAC;QACxB,SAAS,CAAC,EAAE,MAAM,CAAC;QACnB,iBAAiB,CAAC,EAAE,MAAM,CAAC;QAC3B,WAAW,CAAC,EAAE,OAAO,CAAC;KACvB,CAAC;CACH;AAED,8EAA8E;AAC9E,MAAM,WAAW,gBAAgB;IAC/B,EAAE,EAAE,MAAM,CAAC;IACX,MAAM,EAAE,MAAM,CAAC;IACf,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB,IAAI,CAAC,EAAE,MAAM,EAAE,CAAC;CACjB;AAED,4DAA4D;AAC5D,MAAM,WAAW,kBAAkB;IACjC,cAAc,CAAC,EAAE,MAAM,CAAC;IACxB,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,iBAAiB,EAAE,MAAM,CAAC;IAC1B,8DAA8D;IAC9D,WAAW,EAAE,OAAO,CAAC;CACtB;AAED,wFAAwF;AACxF,MAAM,WAAW,qBAAqB;IACpC,SAAS,CAAC,EAAE,MAAM,EAAE,CAAC;IACrB,IAAI,CAAC,EAAE,MAAM,EAAE,CAAC;IAChB,wEAAwE;IACxE,SAAS,CAAC,EAAE,MAAM,CAAC;CACpB;AAED;;;;GAIG;AACH,MAAM,WAAW,YAAY;IAC3B,IAAI,IAAI,OAAO,CAAC;QACd,KAAK,EAAE,gBAAgB,EAAE,CAAC;QAC1B,MAAM,EAAE,kBAAkB,CAAC;KAC5B,CAAC,CAAC;IACH,GAAG,CAAC,KAAK,EAAE,MAAM,GAAG,OAAO,CAAC,eAAe,GAAG,SAAS,CAAC,CAAC;IACzD,kBAAkB,IAAI,OAAO,CAAC;QAC5B,IAAI,EAAE,eAAe,EAAE,CAAC;QACxB,WAAW,CAAC,EAAE,MAAM,CAAC;KACtB,CAAC,CAAC;IACH,KAAK,CAAC,KAAK,CAAC,EAAE,qBAAqB,GAAG,OAAO,CAAC,eAAe,CAAC,CAAC;IAC/D,mDAAmD;IACnD,MAAM,CAAC,KAAK,EAAE,MAAM,GAAG,OAAO,CAAC,eAAe,CAAC,CAAC;CACjD;AAED,MAAM,WAAW,cAAc;IAC7B,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB;;;;OAIG;IACH,cAAc,EAAE,MAAM,CAAC;IACvB;;;;;;;;OAQG;IACH,iBAAiB,CAAC,EAAE,MAAM,CAAC;CAC5B;AAED;;;;;;GAMG;AACH,wBAAgB,gBAAgB,CAAC,MAAM,EAAE,cAAc,GAAG,cAAc,CAQvE;AAED;;GAEG;AACH,wBAAgB,2BAA2B,CAAC,KAAK,EAAE,OAAO,GAAG,MAAM,CAMlE;AAED,yDAAyD;AACzD,wBAAgB,8BAA8B,CAAC,KAAK,EAAE,OAAO,GAAG,MAAM,CAKrE;AAED;;;GAGG;AACH,wBAAgB,4BAA4B,CAAC,KAAK,EAAE,OAAO,GAAG,MAAM,CASnE"}
1
+ {"version":3,"file":"evals.d.ts","sourceRoot":"","sources":["../src/evals.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA8CG;AAIH,OAAO,KAAK,EAAE,iBAAiB,EAAE,YAAY,EAAE,MAAM,YAAY,CAAC;AAElE,MAAM,MAAM,WAAW,GACnB;IAAE,IAAI,EAAE,UAAU,CAAC;IAAC,KAAK,EAAE,MAAM,GAAG,MAAM,CAAA;CAAE,GAC5C;IAAE,IAAI,EAAE,QAAQ,CAAC;IAAC,KAAK,EAAE,OAAO,CAAA;CAAE,GAClC;IACE,IAAI,EAAE,WAAW,CAAC;IAClB,SAAS,EAAE,CAAC,KAAK,EAAE,OAAO,KAAK,OAAO,CAAC;IACvC,KAAK,EAAE,MAAM,CAAC;CACf,CAAC;AAEN,wBAAgB,QAAQ,CAAC,KAAK,EAAE,MAAM,GAAG,MAAM,GAAG,WAAW,CAE5D;AAED,wBAAgB,MAAM,CAAC,KAAK,EAAE,OAAO,GAAG,WAAW,CAElD;AAED,wBAAgB,SAAS,CACvB,SAAS,EAAE,CAAC,KAAK,EAAE,OAAO,KAAK,OAAO,EACtC,KAAK,EAAE,MAAM,GACZ,WAAW,CAEb;AAED,MAAM,WAAW,mBAAmB;IAClC,IAAI,EAAE,MAAM,CAAC;IACb,MAAM,EAAE,OAAO,CAAC;IAChB,MAAM,CAAC,EAAE,MAAM,CAAC;CACjB;AAED,MAAM,WAAW,cAAc;IAC7B,OAAO,EAAE,MAAM,CAAC;IAChB,SAAS,EAAE,MAAM,CAAC;IAClB,MAAM,EAAE,YAAY,EAAE,CAAC;IACvB,SAAS,EAAE,MAAM,EAAE,CAAC;IACpB,EAAE,EAAE,OAAO,CAAC;CACb;AAED,MAAM,WAAW,eAAe;IAC9B,oFAAoF;IACpF,YAAY,CAAC,EAAE,MAAM,CAAC;IACtB,qEAAqE;IACrE,cAAc,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;IACxC;;;;OAIG;IACH,KAAK,CAAC,EAAE,iBAAiB,CAAC;CAC3B;AAED,MAAM,WAAW,eAAe;IAC9B,+DAA+D;IAC/D,IAAI,CAAC,OAAO,EAAE,MAAM,EAAE,OAAO,CAAC,EAAE,eAAe,GAAG,OAAO,CAAC,cAAc,CAAC,CAAC;IAC1E,0DAA0D;IAC1D,QAAQ,CAAC,KAAK,EAAE,MAAM,GAAG,IAAI,CAAC;IAC9B,QAAQ,CAAC,SAAS,EAAE,MAAM,GAAG,SAAS,CAAC;IACvC,+CAA+C;IAC/C,QAAQ,CAAC,MAAM,EAAE,YAAY,EAAE,CAAC;IAChC;;;;OAIG;IACH,QAAQ,CAAC,SAAS,EAAE,MAAM,CAAC;IAC3B,yDAAyD;IACzD,QAAQ,CAAC,UAAU,EAAE,MAAM,CAAC;IAC5B,8BAA8B;IAC9B,SAAS,IAAI,IAAI,CAAC;IAClB,mDAAmD;IACnD,UAAU,CAAC,IAAI,EAAE,MAAM,GAAG,IAAI,CAAC;IAC/B,+BAA+B;IAC/B,aAAa,CAAC,IAAI,EAAE,MAAM,GAAG,IAAI,CAAC;IAClC,2CAA2C;IAC3C,eAAe,CAAC,KAAK,EAAE,MAAM,GAAG,MAAM,GAAG,IAAI,CAAC;IAC9C,wDAAwD;IACxD,KAAK,CAAC,KAAK,EAAE,OAAO,EAAE,SAAS,EAAE,WAAW,GAAG,IAAI,CAAC;IACpD,gEAAgE;IAChE,GAAG,CAAC,OAAO,EAAE,MAAM,GAAG,IAAI,CAAC;IAC3B;;;;OAIG;IACH,MAAM,CAAC,IAAI,EAAE,MAAM,EAAE,KAAK,EAAE,MAAM,GAAG,MAAM,GAAG,IAAI,CAAC;CACpD;AAED,0EAA0E;AAC1E,eAAO,MAAM,mBAAmB,MAAM,CAAC;AAEvC,0EAA0E;AAC1E,MAAM,WAAW,aAAa;IAC5B;;;;OAIG;IACH,EAAE,EAAE,MAAM,CAAC;IACX,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB,IAAI,CAAC,EAAE,MAAM,EAAE,CAAC;IAChB,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB;;;;;OAKG;IACH,UAAU,CAAC,EAAE,MAAM,CAAC;IACpB,IAAI,EAAE,CAAC,CAAC,EAAE,eAAe,KAAK,OAAO,CAAC,IAAI,CAAC,CAAC;CAC7C;AAED;;;GAGG;AACH,MAAM,WAAW,UAAU;IACzB,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB,IAAI,CAAC,EAAE,MAAM,EAAE,CAAC;IAChB,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB;;;OAGG;IACH,UAAU,CAAC,EAAE,MAAM,CAAC;IACpB,sEAAsE;IACtE,IAAI,CAAC,EAAE,CAAC,CAAC,EAAE,eAAe,KAAK,OAAO,CAAC,IAAI,CAAC,CAAC;IAC7C,wEAAwE;IACxE,KAAK,CAAC,EAAE,aAAa,EAAE,CAAC;CACzB;AAED,sEAAsE;AACtE,MAAM,WAAW,kBAAkB;IACjC,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB,IAAI,CAAC,EAAE,MAAM,EAAE,CAAC;IAChB,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,8DAA8D;IAC9D,UAAU,CAAC,EAAE,MAAM,CAAC;IACpB,+DAA+D;IAC/D,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,IAAI,EAAE,CAAC,CAAC,EAAE,eAAe,KAAK,OAAO,CAAC,IAAI,CAAC,CAAC;IAC5C,QAAQ,CAAC,YAAY,EAAE,MAAM,CAAC;CAC/B;AAED,MAAM,MAAM,cAAc,GAAG,UAAU,GAAG;IAAE,QAAQ,CAAC,YAAY,EAAE,MAAM,CAAA;CAAE,CAAC;AAE5E;;;;GAIG;AACH,wBAAgB,uBAAuB,CAAC,KAAK,EAAE,OAAO,GAAG,MAAM,CAK9D;AAED,wBAAgB,UAAU,CAAC,MAAM,EAAE,UAAU,GAAG,cAAc,CAoC7D;AAaD;;;;;;;GAOG;AACH,wBAAgB,oBAAoB,CAClC,MAAM,EAAE,MAAM,EACd,UAAU,EAAE,cAAc,GACzB,KAAK,CAAC;IAAE,EAAE,EAAE,MAAM,CAAC;IAAC,UAAU,EAAE,kBAAkB,CAAA;CAAE,CAAC,CA8BvD;AAiCD;;;;;GAKG;AACH,wBAAgB,mBAAmB,CAAC,MAAM,EAAE,MAAM,EAAE,MAAM,EAAE,MAAM,GAAG,OAAO,CAE3E;AAED;;;;;GAKG;AACH,eAAO,MAAM,gBAAgB,YAAY,CAAC;AAE1C,sDAAsD;AACtD,wBAAgB,iBAAiB,CAC/B,IAAI,EAAE,SAAS,MAAM,EAAE,GAAG,SAAS,GAClC,OAAO,CAET;AAED;;;;GAIG;AACH,wBAAgB,2BAA2B,CACzC,CAAC,SAAS;IAAE,EAAE,EAAE,MAAM,CAAC;IAAC,MAAM,EAAE,MAAM,CAAA;CAAE,EAExC,GAAG,EAAE,SAAS,CAAC,EAAE,EACjB,QAAQ,EAAE,SAAS,CAAC,EAAE,EACtB,SAAS,EAAE,CAAC,IAAI,EAAE,CAAC,KAAK,OAAO,GAC9B,CAAC,EAAE,CAgBL;AAED;;;;;GAKG;AACH,eAAO,MAAM,0BAA0B,MAAM,CAAC;AAE9C,gGAAgG;AAChG,eAAO,MAAM,gCAAgC,KAAK,CAAC;AAEnD,iEAAiE;AACjE,eAAO,MAAM,wBAAwB,MAAM,CAAC;AAE5C,MAAM,MAAM,iBAAiB,GAAG,SAAS,GAAG,SAAS,GAAG,MAAM,CAAC;AAC/D,MAAM,MAAM,eAAe,GAAG,SAAS,GAAG,WAAW,GAAG,QAAQ,GAAG,WAAW,CAAC;AAE/E,+DAA+D;AAC/D,MAAM,WAAW,gBAAgB;IAC/B,EAAE,EAAE,MAAM,CAAC;IACX,MAAM,EAAE,MAAM,CAAC;IACf,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB,IAAI,CAAC,EAAE,MAAM,EAAE,CAAC;IAChB,MAAM,EAAE,iBAAiB,CAAC;IAC1B,EAAE,CAAC,EAAE,OAAO,CAAC;IACb,UAAU,CAAC,EAAE,mBAAmB,EAAE,CAAC;IACnC,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,UAAU,CAAC,EAAE,MAAM,CAAC;IACpB,KAAK,CAAC,EAAE,MAAM,CAAC;IACf,IAAI,CAAC,EAAE,MAAM,EAAE,CAAC;IAChB,6DAA6D;IAC7D,OAAO,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,GAAG,MAAM,CAAC,CAAC;IAC1C,MAAM,CAAC,EAAE,MAAM,EAAE,CAAC;IAClB,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,KAAK,CAAC,EAAE,MAAM,EAAE,CAAC;IACjB,SAAS,CAAC,EAAE,KAAK,CAAC;QAChB,QAAQ,EAAE,MAAM,CAAC;QACjB,IAAI,CAAC,EAAE,OAAO,CAAC;QACf,MAAM,CAAC,EAAE,OAAO,CAAC;QACjB,OAAO,EAAE,OAAO,CAAC;KAClB,CAAC,CAAC;CACJ;AAED,gFAAgF;AAChF,MAAM,WAAW,eAAe;IAC9B,KAAK,EAAE,MAAM,CAAC;IACd,MAAM,EAAE,eAAe,CAAC;IACxB,SAAS,EAAE,MAAM,CAAC;IAClB,UAAU,CAAC,EAAE,MAAM,CAAC;IACpB,KAAK,CAAC,EAAE,MAAM,CAAC;IACf,OAAO,EAAE;QAAE,MAAM,EAAE,MAAM,CAAC;QAAC,MAAM,EAAE,MAAM,CAAC;QAAC,KAAK,EAAE,MAAM,CAAC;QAAC,IAAI,EAAE,MAAM,CAAA;KAAE,CAAC;IACzE,KAAK,EAAE,gBAAgB,EAAE,CAAC;IAC1B,MAAM,EAAE;QACN,cAAc,CAAC,EAAE,MAAM,CAAC;QACxB,SAAS,CAAC,EAAE,MAAM,CAAC;QACnB,iBAAiB,CAAC,EAAE,MAAM,CAAC;QAC3B,WAAW,CAAC,EAAE,OAAO,CAAC;KACvB,CAAC;CACH;AAED,8EAA8E;AAC9E,MAAM,WAAW,gBAAgB;IAC/B,EAAE,EAAE,MAAM,CAAC;IACX,MAAM,EAAE,MAAM,CAAC;IACf,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB,IAAI,CAAC,EAAE,MAAM,EAAE,CAAC;CACjB;AAED,4DAA4D;AAC5D,MAAM,WAAW,kBAAkB;IACjC,cAAc,CAAC,EAAE,MAAM,CAAC;IACxB,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,iBAAiB,EAAE,MAAM,CAAC;IAC1B,8DAA8D;IAC9D,WAAW,EAAE,OAAO,CAAC;CACtB;AAED,wFAAwF;AACxF,MAAM,WAAW,qBAAqB;IACpC,SAAS,CAAC,EAAE,MAAM,EAAE,CAAC;IACrB,IAAI,CAAC,EAAE,MAAM,EAAE,CAAC;IAChB,wEAAwE;IACxE,SAAS,CAAC,EAAE,MAAM,CAAC;CACpB;AAED;;;;GAIG;AACH,MAAM,WAAW,YAAY;IAC3B,IAAI,IAAI,OAAO,CAAC;QACd,KAAK,EAAE,gBAAgB,EAAE,CAAC;QAC1B,MAAM,EAAE,kBAAkB,CAAC;KAC5B,CAAC,CAAC;IACH,GAAG,CAAC,KAAK,EAAE,MAAM,GAAG,OAAO,CAAC,eAAe,GAAG,SAAS,CAAC,CAAC;IACzD,kBAAkB,IAAI,OAAO,CAAC;QAC5B,IAAI,EAAE,eAAe,EAAE,CAAC;QACxB,WAAW,CAAC,EAAE,MAAM,CAAC;KACtB,CAAC,CAAC;IACH,KAAK,CAAC,KAAK,CAAC,EAAE,qBAAqB,GAAG,OAAO,CAAC,eAAe,CAAC,CAAC;IAC/D,mDAAmD;IACnD,MAAM,CAAC,KAAK,EAAE,MAAM,GAAG,OAAO,CAAC,eAAe,CAAC,CAAC;CACjD;AAED,MAAM,WAAW,cAAc;IAC7B,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB;;;;OAIG;IACH,cAAc,EAAE,MAAM,CAAC;IACvB;;;;;;;;OAQG;IACH,iBAAiB,CAAC,EAAE,MAAM,CAAC;CAC5B;AAED;;;;;;GAMG;AACH,wBAAgB,gBAAgB,CAAC,MAAM,EAAE,cAAc,GAAG,cAAc,CAQvE;AAED;;GAEG;AACH,wBAAgB,2BAA2B,CAAC,KAAK,EAAE,OAAO,GAAG,MAAM,CAMlE;AAED,yDAAyD;AACzD,wBAAgB,8BAA8B,CAAC,KAAK,EAAE,OAAO,GAAG,MAAM,CAKrE;AAED;;;GAGG;AACH,wBAAgB,4BAA4B,CAAC,KAAK,EAAE,OAAO,GAAG,MAAM,CASnE"}
package/dist/evals.js CHANGED
@@ -172,6 +172,36 @@ function expandIterations(args) {
172
172
  export function matchesEvalIdFilter(caseId, filter) {
173
173
  return caseId === filter || caseId.startsWith(`${filter}/`);
174
174
  }
175
+ /**
176
+ * Tag for suite-aggregator datapoints that wait on sibling cases from the
177
+ * same eval file (e.g. `deepsec-recall/overall`). Selecting a summary case
178
+ * alone expands the batch to the whole file via
179
+ * {@link expandSummarySuiteSelection}.
180
+ */
181
+ export const EVAL_SUMMARY_TAG = "summary";
182
+ /** True when `tags` marks a suite-aggregator case. */
183
+ export function isEvalSummaryCase(tags) {
184
+ var _a;
185
+ return (_a = tags === null || tags === void 0 ? void 0 : tags.includes(EVAL_SUMMARY_TAG)) !== null && _a !== void 0 ? _a : false;
186
+ }
187
+ /**
188
+ * If `selected` includes any summary-tagged suite aggregator, pull in every
189
+ * other datapoint from the same `fileId` so the aggregator is not run alone.
190
+ * Preserves discovery order from `all`.
191
+ */
192
+ export function expandSummarySuiteSelection(all, selected, isSummary) {
193
+ const fileIdsNeedingSuite = new Set(selected.filter((item) => isSummary(item)).map((item) => item.fileId));
194
+ if (fileIdsNeedingSuite.size === 0) {
195
+ return [...selected];
196
+ }
197
+ const selectedIds = new Set(selected.map((item) => item.id));
198
+ const extras = all.filter((item) => fileIdsNeedingSuite.has(item.fileId) && !selectedIds.has(item.id));
199
+ if (extras.length === 0) {
200
+ return [...selected];
201
+ }
202
+ const want = new Set([...selectedIds, ...extras.map((item) => item.id)]);
203
+ return all.filter((item) => want.has(item.id));
204
+ }
175
205
  /**
176
206
  * Hard ceiling for concurrent eval cases.
177
207
  *
@@ -1 +1 @@
1
- {"version":3,"file":"eval-runner.d.ts","sourceRoot":"","sources":["../../src/internal/eval-runner.ts"],"names":[],"mappings":"AAAA;;;;;;;;GAQG;AAMH,OAAO,KAAK,EACV,mBAAmB,EACnB,kBAAkB,EAClB,cAAc,EAMf,MAAM,aAAa,CAAC;AAOrB,OAAO,KAAK,EAAE,YAAY,EAAE,MAAM,aAAa,CAAC;AAMhD,MAAM,WAAW,cAAc;IAC7B,8EAA8E;IAC9E,EAAE,EAAE,MAAM,CAAC;IACX,sEAAsE;IACtE,MAAM,EAAE,MAAM,CAAC;IACf,IAAI,EAAE,MAAM,CAAC;IACb,UAAU,EAAE,kBAAkB,CAAC;CAChC;AAED,MAAM,WAAW,aAAa;IAC5B,EAAE,EAAE,MAAM,CAAC;IACX,IAAI,EAAE,MAAM,CAAC;IACb,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB,EAAE,EAAE,OAAO,CAAC;IACZ,UAAU,EAAE,mBAAmB,EAAE,CAAC;IAClC,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,iDAAiD;IACjD,MAAM,EAAE,MAAM,EAAE,CAAC;IACjB,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,KAAK,CAAC,EAAE,MAAM,EAAE,CAAC;IACjB,wDAAwD;IACxD,SAAS,CAAC,EAAE,KAAK,CAAC;QAChB,QAAQ,EAAE,MAAM,CAAC;QACjB,IAAI,CAAC,EAAE,OAAO,CAAC;QACf,MAAM,CAAC,EAAE,OAAO,CAAC;QACjB,OAAO,EAAE,OAAO,CAAC;KAClB,CAAC,CAAC;IACH,KAAK,CAAC,EAAE,MAAM,CAAC;IACf,IAAI,EAAE,MAAM,EAAE,CAAC;IACf,mFAAmF;IACnF,OAAO,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,GAAG,MAAM,CAAC,CAAC;IACzC,UAAU,EAAE,MAAM,CAAC;CACpB;AAED,MAAM,WAAW,oBAAoB;IACnC,SAAS,CAAC,EAAE,MAAM,EAAE,CAAC;IACrB,IAAI,CAAC,EAAE,MAAM,EAAE,CAAC;CACjB;AAED,MAAM,WAAW,eAAgB,SAAQ,oBAAoB;IAC3D,WAAW,EAAE,MAAM,CAAC;IACpB,OAAO,EAAE,MAAM,CAAC;IAChB,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB,wDAAwD;IACxD,OAAO,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;IACjC,OAAO,CAAC,EAAE,OAAO,CAAC;IAClB,OAAO,CAAC,EAAE,CAAC,KAAK,EAAE,YAAY,KAAK,IAAI,CAAC;IACxC,4EAA4E;IAC5E,WAAW,CAAC,EAAE,CAAC,EAAE,EAAE,MAAM,KAAK,IAAI,CAAC;IACnC,iDAAiD;IACjD,UAAU,CAAC,EAAE,CAAC,MAAM,EAAE,aAAa,KAAK,IAAI,CAAC;IAC7C,kFAAkF;IAClF,WAAW,CAAC,EAAE,CAAC,EAAE,EAAE,MAAM,EAAE,KAAK,EAAE,YAAY,KAAK,IAAI,CAAC;IACxD,YAAY,CAAC,EAAE,CAAC,YAAY,EAAE,MAAM,KAAK,OAAO,CAAC,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,CAAC,CAAC;IAC1E;;;OAGG;IACH,UAAU,CAAC,EAAE;QACX,KAAK,EAAE,SAAS,cAAc,EAAE,CAAC;QACjC,MAAM,EAAE,OAAO,CAAC,cAAc,CAAC,CAAC;KACjC,CAAC;IACF,wEAAwE;IACxE,MAAM,CAAC,EAAE,WAAW,CAAC;CACtB;AAuCD,wBAAsB,aAAa,CACjC,WAAW,EAAE,MAAM,EACnB,YAAY,GAAE,CACZ,YAAY,EAAE,MAAM,KACjB,OAAO,CAAC,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,CAAiB,GACpD,OAAO,CAAC;IACT,KAAK,EAAE,cAAc,EAAE,CAAC;IACxB,MAAM,EAAE,OAAO,CAAC,cAAc,CAAC,CAAC;CACjC,CAAC,CA4CD;AAED,8EAA8E;AAC9E,wBAAgB,qBAAqB,CACnC,KAAK,EAAE,SAAS,cAAc,EAAE,EAChC,OAAO,GAAE,oBAAyB,GACjC,cAAc,EAAE,CAalB;AAED,wBAAsB,kBAAkB,CACtC,OAAO,EAAE,eAAe,GACvB,OAAO,CAAC,aAAa,EAAE,CAAC,CA6D1B;AAED;;;GAGG;AACH,wBAAgB,oBAAoB,CAAC,UAAU,EAAE,cAAc,GAAG,MAAM,CAWvE;AAED;;;GAGG;AACH,wBAAgB,8BAA8B,CAC5C,KAAK,EAAE,SAAS,cAAc,EAAE,GAC/B,cAAc,EAAE,EAAE,CAmBpB"}
1
+ {"version":3,"file":"eval-runner.d.ts","sourceRoot":"","sources":["../../src/internal/eval-runner.ts"],"names":[],"mappings":"AAAA;;;;;;;;GAQG;AAMH,OAAO,KAAK,EACV,mBAAmB,EACnB,kBAAkB,EAClB,cAAc,EAMf,MAAM,aAAa,CAAC;AASrB,OAAO,KAAK,EAAE,YAAY,EAAE,MAAM,aAAa,CAAC;AAMhD,MAAM,WAAW,cAAc;IAC7B,8EAA8E;IAC9E,EAAE,EAAE,MAAM,CAAC;IACX,sEAAsE;IACtE,MAAM,EAAE,MAAM,CAAC;IACf,IAAI,EAAE,MAAM,CAAC;IACb,UAAU,EAAE,kBAAkB,CAAC;CAChC;AAED,MAAM,WAAW,aAAa;IAC5B,EAAE,EAAE,MAAM,CAAC;IACX,IAAI,EAAE,MAAM,CAAC;IACb,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB,EAAE,EAAE,OAAO,CAAC;IACZ,UAAU,EAAE,mBAAmB,EAAE,CAAC;IAClC,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,iDAAiD;IACjD,MAAM,EAAE,MAAM,EAAE,CAAC;IACjB,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,KAAK,CAAC,EAAE,MAAM,EAAE,CAAC;IACjB,wDAAwD;IACxD,SAAS,CAAC,EAAE,KAAK,CAAC;QAChB,QAAQ,EAAE,MAAM,CAAC;QACjB,IAAI,CAAC,EAAE,OAAO,CAAC;QACf,MAAM,CAAC,EAAE,OAAO,CAAC;QACjB,OAAO,EAAE,OAAO,CAAC;KAClB,CAAC,CAAC;IACH,KAAK,CAAC,EAAE,MAAM,CAAC;IACf,IAAI,EAAE,MAAM,EAAE,CAAC;IACf,mFAAmF;IACnF,OAAO,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,GAAG,MAAM,CAAC,CAAC;IACzC,UAAU,EAAE,MAAM,CAAC;CACpB;AAED,MAAM,WAAW,oBAAoB;IACnC,SAAS,CAAC,EAAE,MAAM,EAAE,CAAC;IACrB,IAAI,CAAC,EAAE,MAAM,EAAE,CAAC;CACjB;AAED,MAAM,WAAW,eAAgB,SAAQ,oBAAoB;IAC3D,WAAW,EAAE,MAAM,CAAC;IACpB,OAAO,EAAE,MAAM,CAAC;IAChB,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB,wDAAwD;IACxD,OAAO,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;IACjC,OAAO,CAAC,EAAE,OAAO,CAAC;IAClB,OAAO,CAAC,EAAE,CAAC,KAAK,EAAE,YAAY,KAAK,IAAI,CAAC;IACxC,4EAA4E;IAC5E,WAAW,CAAC,EAAE,CAAC,EAAE,EAAE,MAAM,KAAK,IAAI,CAAC;IACnC,iDAAiD;IACjD,UAAU,CAAC,EAAE,CAAC,MAAM,EAAE,aAAa,KAAK,IAAI,CAAC;IAC7C,kFAAkF;IAClF,WAAW,CAAC,EAAE,CAAC,EAAE,EAAE,MAAM,EAAE,KAAK,EAAE,YAAY,KAAK,IAAI,CAAC;IACxD,YAAY,CAAC,EAAE,CAAC,YAAY,EAAE,MAAM,KAAK,OAAO,CAAC,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,CAAC,CAAC;IAC1E;;;OAGG;IACH,UAAU,CAAC,EAAE;QACX,KAAK,EAAE,SAAS,cAAc,EAAE,CAAC;QACjC,MAAM,EAAE,OAAO,CAAC,cAAc,CAAC,CAAC;KACjC,CAAC;IACF,wEAAwE;IACxE,MAAM,CAAC,EAAE,WAAW,CAAC;CACtB;AAuCD,wBAAsB,aAAa,CACjC,WAAW,EAAE,MAAM,EACnB,YAAY,GAAE,CACZ,YAAY,EAAE,MAAM,KACjB,OAAO,CAAC,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,CAAiB,GACpD,OAAO,CAAC;IACT,KAAK,EAAE,cAAc,EAAE,CAAC;IACxB,MAAM,EAAE,OAAO,CAAC,cAAc,CAAC,CAAC;CACjC,CAAC,CA4CD;AAED,8EAA8E;AAC9E,wBAAgB,qBAAqB,CACnC,KAAK,EAAE,SAAS,cAAc,EAAE,EAChC,OAAO,GAAE,oBAAyB,GACjC,cAAc,EAAE,CAgBlB;AAED,wBAAsB,kBAAkB,CACtC,OAAO,EAAE,eAAe,GACvB,OAAO,CAAC,aAAa,EAAE,CAAC,CA6D1B;AAED;;;GAGG;AACH,wBAAgB,oBAAoB,CAAC,UAAU,EAAE,cAAc,GAAG,MAAM,CAWvE;AAED;;;GAGG;AACH,wBAAgB,8BAA8B,CAC5C,KAAK,EAAE,SAAS,cAAc,EAAE,GAC/B,cAAc,EAAE,EAAE,CAmBpB"}
@@ -19,7 +19,7 @@ var __awaiter = (this && this.__awaiter) || function (thisArg, _arguments, P, ge
19
19
  import { readdir } from "node:fs/promises";
20
20
  import { join, relative, resolve } from "node:path";
21
21
  import { pathToFileURL } from "node:url";
22
- import { EVAL_MAX_CONCURRENCY_LIMIT, expandEvalDefinition, matchesEvalIdFilter, normalizeEvalMaxConcurrency, } from "../evals.js";
22
+ import { EVAL_MAX_CONCURRENCY_LIMIT, expandEvalDefinition, expandSummarySuiteSelection, isEvalSummaryCase, matchesEvalIdFilter, normalizeEvalMaxConcurrency, } from "../evals.js";
23
23
  import { isDefinitionOfKind } from "./brand.js";
24
24
  import { mapPool } from "./map-pool.js";
25
25
  import { RunSessionTimeoutError, runSession } from "./run-client.js";
@@ -114,7 +114,8 @@ export function filterDiscoveredEvals(evals, options = {}) {
114
114
  if (options.tags !== undefined && options.tags.length > 0) {
115
115
  selected = selected.filter((e) => { var _a; return ((_a = e.definition.tags) !== null && _a !== void 0 ? _a : []).some((t) => options.tags.includes(t)); });
116
116
  }
117
- return selected;
117
+ // Suite aggregators (`summary` tag) need sibling cases from the same file.
118
+ return expandSummarySuiteSelection(evals, selected, (e) => isEvalSummaryCase(e.definition.tags));
118
119
  }
119
120
  export function runDiscoveredEvals(options) {
120
121
  return __awaiter(this, void 0, void 0, function* () {
@@ -1 +1 @@
1
- {"version":3,"file":"evals-client.d.ts","sourceRoot":"","sources":["../../src/internal/evals-client.ts"],"names":[],"mappings":"AAAA;;;;;;;GAOG;AAEH,OAAO,KAAK,EAAE,eAAe,EAAE,MAAM,aAAa,CAAC;AAEnD,OAAO,KAAK,EAAE,aAAa,EAAE,MAAM,kBAAkB,CAAC;AACtD,OAAO,EAAuB,KAAK,WAAW,EAAE,MAAM,sBAAsB,CAAC;AAI7E,MAAM,MAAM,mBAAmB,GAC3B,mBAAmB,GACnB,sBAAsB,GACtB,sBAAsB,GACtB,kBAAkB,GAClB,cAAc,GACd,aAAa,GACb,eAAe,GACf,SAAS,CAAC;AAEd,qBAAa,eAAgB,SAAQ,KAAK;IAGtC,QAAQ,CAAC,MAAM,CAAC,EAAE,MAAM;IACxB,QAAQ,CAAC,IAAI,CAAC,EAAE,mBAAmB;IACnC,QAAQ,CAAC,WAAW,CAAC,EAAE,MAAM;IAJ/B,YACE,OAAO,EAAE,MAAM,EACN,MAAM,CAAC,EAAE,MAAM,YAAA,EACf,IAAI,CAAC,EAAE,mBAAmB,YAAA,EAC1B,WAAW,CAAC,EAAE,MAAM,YAAA,EAI9B;CACF;AAED,MAAM,WAAW,kBAAkB;IACjC,EAAE,EAAE,MAAM,CAAC;IACX,MAAM,EAAE,MAAM,CAAC;IACf,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB,IAAI,CAAC,EAAE,MAAM,EAAE,CAAC;CACjB;AAED,MAAM,WAAW,qBAAsB,SAAQ,WAAW;IACxD,OAAO,EAAE,MAAM,CAAC;IAChB,SAAS,CAAC,EAAE,MAAM,EAAE,CAAC;IACrB,IAAI,CAAC,EAAE,MAAM,EAAE,CAAC;IAChB,gEAAgE;IAChE,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,qEAAqE;IACrE,OAAO,CAAC,EAAE,OAAO,CAAC;IAClB,SAAS,CAAC,EAAE,OAAO,KAAK,CAAC;IACzB,kDAAkD;IAClD,MAAM,CAAC,EAAE,MAAM,CAAC;IAChB,6CAA6C;IAC7C,MAAM,CAAC,EAAE,WAAW,CAAC;IACrB,oDAAoD;IACpD,UAAU,CAAC,EAAE,CAAC,IAAI,EAAE,eAAe,KAAK,IAAI,CAAC;CAC9C;AAED;;;GAGG;AACH,wBAAsB,cAAc,CAClC,OAAO,EAAE,qBAAqB,GAC7B,OAAO,CAAC;IAAE,QAAQ,EAAE,eAAe,CAAC;IAAC,OAAO,EAAE,aAAa,EAAE,CAAA;CAAE,CAAC,CA+BlE;AAED,iFAAiF;AACjF,wBAAsB,eAAe,CAAC,IAAI,EAAE;IAC1C,OAAO,EAAE,MAAM,CAAC;IAChB,IAAI,CAAC,EAAE,WAAW,CAAC;IACnB,SAAS,CAAC,EAAE,OAAO,KAAK,CAAC;IACzB,SAAS,CAAC,EAAE,MAAM,EAAE,CAAC;IACrB,IAAI,CAAC,EAAE,MAAM,EAAE,CAAC;IAChB,MAAM,CAAC,EAAE,WAAW,CAAC;CACtB,GAAG,OAAO,CAAC,kBAAkB,EAAE,CAAC,CAgEhC;AAED,wBAAsB,kBAAkB,CAAC,IAAI,EAAE;IAC7C,OAAO,EAAE,MAAM,CAAC;IAChB,IAAI,CAAC,EAAE,WAAW,CAAC;IACnB,SAAS,CAAC,EAAE,OAAO,KAAK,CAAC;IACzB,SAAS,CAAC,EAAE,MAAM,EAAE,CAAC;IACrB,IAAI,CAAC,EAAE,MAAM,EAAE,CAAC;IAChB,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,OAAO,CAAC,EAAE,OAAO,CAAC;IAClB,MAAM,CAAC,EAAE,WAAW,CAAC;CACtB,GAAG,OAAO,CAAC,eAAe,CAAC,CAuF3B;AAED,0EAA0E;AAC1E,wBAAsB,mBAAmB,CAAC,IAAI,EAAE;IAC9C,OAAO,EAAE,MAAM,CAAC;IAChB,KAAK,EAAE,MAAM,CAAC;IACd,IAAI,CAAC,EAAE,WAAW,CAAC;IACnB,SAAS,CAAC,EAAE,OAAO,KAAK,CAAC;IACzB,MAAM,CAAC,EAAE,WAAW,CAAC;CACtB,GAAG,OAAO,CAAC,eAAe,CAAC,CAsE3B;AAED,6DAA6D;AAC7D,wBAAsB,gBAAgB,CAAC,IAAI,EAAE;IAC3C,OAAO,EAAE,MAAM,CAAC;IAChB,KAAK,EAAE,MAAM,CAAC;IACd,IAAI,CAAC,EAAE,WAAW,CAAC;IACnB,SAAS,CAAC,EAAE,OAAO,KAAK,CAAC;IACzB,MAAM,CAAC,EAAE,WAAW,CAAC;CACtB,GAAG,OAAO,CAAC,eAAe,CAAC,CAmC3B;AAED,oDAAoD;AACpD,wBAAsB,kBAAkB,CAAC,IAAI,EAAE;IAC7C,OAAO,EAAE,MAAM,CAAC;IAChB,IAAI,CAAC,EAAE,WAAW,CAAC;IACnB,SAAS,CAAC,EAAE,OAAO,KAAK,CAAC;IACzB,MAAM,CAAC,EAAE,WAAW,CAAC;CACtB,GAAG,OAAO,CAAC;IAAE,IAAI,EAAE,eAAe,EAAE,CAAC;IAAC,WAAW,CAAC,EAAE,MAAM,CAAA;CAAE,CAAC,CAyC7D;AAED,wBAAsB,iBAAiB,CAAC,IAAI,EAAE;IAC5C,OAAO,EAAE,MAAM,CAAC;IAChB,KAAK,EAAE,MAAM,CAAC;IACd,IAAI,CAAC,EAAE,WAAW,CAAC;IACnB,SAAS,CAAC,EAAE,OAAO,KAAK,CAAC;IACzB,MAAM,CAAC,EAAE,MAAM,CAAC;IAChB,MAAM,CAAC,EAAE,WAAW,CAAC;IACrB,UAAU,CAAC,EAAE,CAAC,IAAI,EAAE,eAAe,KAAK,IAAI,CAAC;CAC9C,GAAG,OAAO,CAAC,eAAe,CAAC,CAoB3B;AAED,wBAAgB,wBAAwB,CACtC,QAAQ,EAAE,eAAe,GACxB,aAAa,EAAE,CAiBjB"}
1
+ {"version":3,"file":"evals-client.d.ts","sourceRoot":"","sources":["../../src/internal/evals-client.ts"],"names":[],"mappings":"AAAA;;;;;;;GAOG;AAEH,OAAO,KAAK,EAAE,eAAe,EAAE,MAAM,aAAa,CAAC;AAMnD,OAAO,KAAK,EAAE,aAAa,EAAE,MAAM,kBAAkB,CAAC;AACtD,OAAO,EAAuB,KAAK,WAAW,EAAE,MAAM,sBAAsB,CAAC;AAI7E,MAAM,MAAM,mBAAmB,GAC3B,mBAAmB,GACnB,sBAAsB,GACtB,sBAAsB,GACtB,kBAAkB,GAClB,cAAc,GACd,aAAa,GACb,eAAe,GACf,SAAS,CAAC;AAEd,qBAAa,eAAgB,SAAQ,KAAK;IAGtC,QAAQ,CAAC,MAAM,CAAC,EAAE,MAAM;IACxB,QAAQ,CAAC,IAAI,CAAC,EAAE,mBAAmB;IACnC,QAAQ,CAAC,WAAW,CAAC,EAAE,MAAM;IAJ/B,YACE,OAAO,EAAE,MAAM,EACN,MAAM,CAAC,EAAE,MAAM,YAAA,EACf,IAAI,CAAC,EAAE,mBAAmB,YAAA,EAC1B,WAAW,CAAC,EAAE,MAAM,YAAA,EAI9B;CACF;AAED,MAAM,WAAW,kBAAkB;IACjC,EAAE,EAAE,MAAM,CAAC;IACX,MAAM,EAAE,MAAM,CAAC;IACf,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB,IAAI,CAAC,EAAE,MAAM,EAAE,CAAC;CACjB;AAED,MAAM,WAAW,qBAAsB,SAAQ,WAAW;IACxD,OAAO,EAAE,MAAM,CAAC;IAChB,SAAS,CAAC,EAAE,MAAM,EAAE,CAAC;IACrB,IAAI,CAAC,EAAE,MAAM,EAAE,CAAC;IAChB,gEAAgE;IAChE,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,qEAAqE;IACrE,OAAO,CAAC,EAAE,OAAO,CAAC;IAClB,SAAS,CAAC,EAAE,OAAO,KAAK,CAAC;IACzB,kDAAkD;IAClD,MAAM,CAAC,EAAE,MAAM,CAAC;IAChB,6CAA6C;IAC7C,MAAM,CAAC,EAAE,WAAW,CAAC;IACrB,oDAAoD;IACpD,UAAU,CAAC,EAAE,CAAC,IAAI,EAAE,eAAe,KAAK,IAAI,CAAC;CAC9C;AAED;;;GAGG;AACH,wBAAsB,cAAc,CAClC,OAAO,EAAE,qBAAqB,GAC7B,OAAO,CAAC;IAAE,QAAQ,EAAE,eAAe,CAAC;IAAC,OAAO,EAAE,aAAa,EAAE,CAAA;CAAE,CAAC,CA+BlE;AAED,iFAAiF;AACjF,wBAAsB,eAAe,CAAC,IAAI,EAAE;IAC1C,OAAO,EAAE,MAAM,CAAC;IAChB,IAAI,CAAC,EAAE,WAAW,CAAC;IACnB,SAAS,CAAC,EAAE,OAAO,KAAK,CAAC;IACzB,SAAS,CAAC,EAAE,MAAM,EAAE,CAAC;IACrB,IAAI,CAAC,EAAE,MAAM,EAAE,CAAC;IAChB,MAAM,CAAC,EAAE,WAAW,CAAC;CACtB,GAAG,OAAO,CAAC,kBAAkB,EAAE,CAAC,CAmEhC;AAED,wBAAsB,kBAAkB,CAAC,IAAI,EAAE;IAC7C,OAAO,EAAE,MAAM,CAAC;IAChB,IAAI,CAAC,EAAE,WAAW,CAAC;IACnB,SAAS,CAAC,EAAE,OAAO,KAAK,CAAC;IACzB,SAAS,CAAC,EAAE,MAAM,EAAE,CAAC;IACrB,IAAI,CAAC,EAAE,MAAM,EAAE,CAAC;IAChB,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,OAAO,CAAC,EAAE,OAAO,CAAC;IAClB,MAAM,CAAC,EAAE,WAAW,CAAC;CACtB,GAAG,OAAO,CAAC,eAAe,CAAC,CAuF3B;AAED,0EAA0E;AAC1E,wBAAsB,mBAAmB,CAAC,IAAI,EAAE;IAC9C,OAAO,EAAE,MAAM,CAAC;IAChB,KAAK,EAAE,MAAM,CAAC;IACd,IAAI,CAAC,EAAE,WAAW,CAAC;IACnB,SAAS,CAAC,EAAE,OAAO,KAAK,CAAC;IACzB,MAAM,CAAC,EAAE,WAAW,CAAC;CACtB,GAAG,OAAO,CAAC,eAAe,CAAC,CAsE3B;AAED,6DAA6D;AAC7D,wBAAsB,gBAAgB,CAAC,IAAI,EAAE;IAC3C,OAAO,EAAE,MAAM,CAAC;IAChB,KAAK,EAAE,MAAM,CAAC;IACd,IAAI,CAAC,EAAE,WAAW,CAAC;IACnB,SAAS,CAAC,EAAE,OAAO,KAAK,CAAC;IACzB,MAAM,CAAC,EAAE,WAAW,CAAC;CACtB,GAAG,OAAO,CAAC,eAAe,CAAC,CAmC3B;AAED,oDAAoD;AACpD,wBAAsB,kBAAkB,CAAC,IAAI,EAAE;IAC7C,OAAO,EAAE,MAAM,CAAC;IAChB,IAAI,CAAC,EAAE,WAAW,CAAC;IACnB,SAAS,CAAC,EAAE,OAAO,KAAK,CAAC;IACzB,MAAM,CAAC,EAAE,WAAW,CAAC;CACtB,GAAG,OAAO,CAAC;IAAE,IAAI,EAAE,eAAe,EAAE,CAAC;IAAC,WAAW,CAAC,EAAE,MAAM,CAAA;CAAE,CAAC,CAyC7D;AAED,wBAAsB,iBAAiB,CAAC,IAAI,EAAE;IAC5C,OAAO,EAAE,MAAM,CAAC;IAChB,KAAK,EAAE,MAAM,CAAC;IACd,IAAI,CAAC,EAAE,WAAW,CAAC;IACnB,SAAS,CAAC,EAAE,OAAO,KAAK,CAAC;IACzB,MAAM,CAAC,EAAE,MAAM,CAAC;IAChB,MAAM,CAAC,EAAE,WAAW,CAAC;IACrB,UAAU,CAAC,EAAE,CAAC,IAAI,EAAE,eAAe,KAAK,IAAI,CAAC;CAC9C,GAAG,OAAO,CAAC,eAAe,CAAC,CAoB3B;AAED,wBAAgB,wBAAwB,CACtC,QAAQ,EAAE,eAAe,GACxB,aAAa,EAAE,CAiBjB"}
@@ -15,7 +15,7 @@ var __awaiter = (this && this.__awaiter) || function (thisArg, _arguments, P, ge
15
15
  step((generator = generator.apply(thisArg, _arguments || [])).next());
16
16
  });
17
17
  };
18
- import { matchesEvalIdFilter } from "../evals.js";
18
+ import { expandSummarySuiteSelection, isEvalSummaryCase, matchesEvalIdFilter, } from "../evals.js";
19
19
  import { mergeRequestHeaders } from "./request-headers.js";
20
20
  const DEFAULT_POLL_MS = 1000;
21
21
  export class RemoteEvalError extends Error {
@@ -106,7 +106,8 @@ export function listRemoteEvals(args) {
106
106
  if (args.tags !== undefined && args.tags.length > 0) {
107
107
  selected = selected.filter((e) => { var _a; return ((_a = e.tags) !== null && _a !== void 0 ? _a : []).some((t) => args.tags.includes(t)); });
108
108
  }
109
- return selected;
109
+ // Match server-side filterDiscoveredEvals: summary → whole file.
110
+ return expandSummarySuiteSelection(listed, selected, (e) => isEvalSummaryCase(e.tags));
110
111
  });
111
112
  }
112
113
  export function startRemoteEvalRun(args) {