@cursor/july 0.1.109 → 0.1.112

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 (1166) hide show
  1. package/AGENTS.md +1 -1
  2. package/README.md +0 -15
  3. package/dist/bin/agent-serve.js +99 -67
  4. package/dist/channels/bitbucket/api.js +8 -8
  5. package/dist/channels/bitbucket/binding.js +4 -4
  6. package/dist/channels/bitbucket/bitbucket-channel.js +1 -1
  7. package/dist/channels/bitbucket/bitbucket-webhook.js +1 -1
  8. package/dist/channels/bitbucket/checks.d.ts.map +1 -1
  9. package/dist/channels/bitbucket/checks.js +1 -1
  10. package/dist/channels/bitbucket/cursor-account.js +1 -1
  11. package/dist/channels/bitbucket/events.js +1 -1
  12. package/dist/channels/change-monitors/change-monitors-channel.js +1 -1
  13. package/dist/channels/checks.d.ts.map +1 -1
  14. package/dist/channels/checks.js +2 -2
  15. package/dist/channels/deployments/deployments-channel.js +1 -1
  16. package/dist/channels/github/cursor-account.js +3 -3
  17. package/dist/channels/github/defaults.d.ts.map +1 -1
  18. package/dist/channels/github/defaults.js +5 -3
  19. package/dist/channels/github/events.js +1 -1
  20. package/dist/channels/github/forward.js +8 -8
  21. package/dist/channels/github/github-channel.d.ts +29 -19
  22. package/dist/channels/github/github-channel.d.ts.map +1 -1
  23. package/dist/channels/github/github-channel.js +46 -32
  24. package/dist/channels/github/progress.d.ts.map +1 -1
  25. package/dist/channels/github/progress.js +7 -2
  26. package/dist/channels/github/state.d.ts +6 -0
  27. package/dist/channels/github/state.d.ts.map +1 -1
  28. package/dist/channels/github/types.d.ts +6 -0
  29. package/dist/channels/github/types.d.ts.map +1 -1
  30. package/dist/channels/gitlab/binding.js +4 -4
  31. package/dist/channels/gitlab/checks.d.ts.map +1 -1
  32. package/dist/channels/gitlab/checks.js +1 -1
  33. package/dist/channels/gitlab/cursor-account.js +1 -1
  34. package/dist/channels/gitlab/events.js +1 -1
  35. package/dist/channels/gitlab/gitlab-channel.js +1 -1
  36. package/dist/channels/gitlab/gitlab-webhook.js +1 -1
  37. package/dist/channels/gitlab/replay.js +2 -2
  38. package/dist/channels/origin/binding.d.ts +2 -0
  39. package/dist/channels/origin/binding.d.ts.map +1 -1
  40. package/dist/channels/origin/binding.js +3 -3
  41. package/dist/channels/origin/checks.d.ts +19 -7
  42. package/dist/channels/origin/checks.d.ts.map +1 -1
  43. package/dist/channels/origin/checks.js +13 -9
  44. package/dist/channels/origin/cursor-account.js +1 -1
  45. package/dist/channels/origin/defaults.d.ts.map +1 -1
  46. package/dist/channels/origin/defaults.js +3 -1
  47. package/dist/channels/origin/events.js +1 -1
  48. package/dist/channels/origin/origin-channel.d.ts.map +1 -1
  49. package/dist/channels/origin/origin-channel.js +2 -1
  50. package/dist/channels/origin/origin-webhook.js +2 -2
  51. package/dist/channels/slack/agentic-delivery.d.ts +23 -0
  52. package/dist/channels/slack/agentic-delivery.d.ts.map +1 -0
  53. package/dist/channels/slack/agentic-delivery.js +560 -0
  54. package/dist/channels/slack/agentic-posted.d.ts +30 -0
  55. package/dist/channels/slack/agentic-posted.d.ts.map +1 -0
  56. package/dist/channels/slack/agentic-posted.js +102 -0
  57. package/dist/channels/slack/agentic-signals.d.ts +48 -0
  58. package/dist/channels/slack/agentic-signals.d.ts.map +1 -0
  59. package/dist/channels/slack/agentic-signals.js +204 -0
  60. package/dist/channels/slack/api.d.ts +20 -1
  61. package/dist/channels/slack/api.d.ts.map +1 -1
  62. package/dist/channels/slack/api.js +43 -11
  63. package/dist/channels/slack/approvals.js +1 -1
  64. package/dist/channels/slack/auth.d.ts.map +1 -1
  65. package/dist/channels/slack/auth.js +3 -1
  66. package/dist/channels/slack/blocks.js +3 -3
  67. package/dist/channels/slack/bot-mentions.d.ts.map +1 -1
  68. package/dist/channels/slack/bot-mentions.js +5 -5
  69. package/dist/channels/slack/channel-watch.js +1 -1
  70. package/dist/channels/slack/cli-project.js +3 -3
  71. package/dist/channels/slack/defaults.d.ts +3 -0
  72. package/dist/channels/slack/defaults.d.ts.map +1 -1
  73. package/dist/channels/slack/defaults.js +90 -29
  74. package/dist/channels/slack/dispatch.d.ts +44 -1
  75. package/dist/channels/slack/dispatch.d.ts.map +1 -1
  76. package/dist/channels/slack/dispatch.js +323 -107
  77. package/dist/channels/slack/doctor.js +1 -1
  78. package/dist/channels/slack/eval-directive.js +1 -1
  79. package/dist/channels/slack/external-policy.d.ts +2 -1
  80. package/dist/channels/slack/external-policy.d.ts.map +1 -1
  81. package/dist/channels/slack/external-policy.js +13 -2
  82. package/dist/channels/slack/footer.d.ts +30 -0
  83. package/dist/channels/slack/footer.d.ts.map +1 -0
  84. package/dist/channels/slack/footer.js +88 -0
  85. package/dist/channels/slack/index.d.ts +2 -0
  86. package/dist/channels/slack/index.d.ts.map +1 -1
  87. package/dist/channels/slack/index.js +2 -0
  88. package/dist/channels/slack/interactive.d.ts.map +1 -1
  89. package/dist/channels/slack/interactive.js +5 -3
  90. package/dist/channels/slack/live-delivery.d.ts +1 -1
  91. package/dist/channels/slack/live-delivery.d.ts.map +1 -1
  92. package/dist/channels/slack/live-delivery.js +20 -6
  93. package/dist/channels/slack/log.d.ts.map +1 -1
  94. package/dist/channels/slack/log.js +1 -1
  95. package/dist/channels/slack/manifest.js +1 -1
  96. package/dist/channels/slack/nudge-carrier.js +1 -1
  97. package/dist/channels/slack/nudge-store.js +2 -2
  98. package/dist/channels/slack/paint-start.d.ts +22 -0
  99. package/dist/channels/slack/paint-start.d.ts.map +1 -0
  100. package/dist/channels/slack/paint-start.js +91 -0
  101. package/dist/channels/slack/placeholder.d.ts +62 -0
  102. package/dist/channels/slack/placeholder.d.ts.map +1 -0
  103. package/dist/channels/slack/placeholder.js +268 -0
  104. package/dist/channels/slack/progress-delivery.d.ts.map +1 -1
  105. package/dist/channels/slack/progress-delivery.js +13 -4
  106. package/dist/channels/slack/reasoning-chip.d.ts +8 -0
  107. package/dist/channels/slack/reasoning-chip.d.ts.map +1 -0
  108. package/dist/channels/slack/reasoning-chip.js +30 -0
  109. package/dist/channels/slack/recording-sink.d.ts +29 -0
  110. package/dist/channels/slack/recording-sink.d.ts.map +1 -0
  111. package/dist/channels/slack/recording-sink.js +142 -0
  112. package/dist/channels/slack/reply-options.d.ts +8 -1
  113. package/dist/channels/slack/reply-options.d.ts.map +1 -1
  114. package/dist/channels/slack/reply-options.js +59 -14
  115. package/dist/channels/slack/setup.js +1 -1
  116. package/dist/channels/slack/slack-channel.d.ts +2 -2
  117. package/dist/channels/slack/slack-channel.d.ts.map +1 -1
  118. package/dist/channels/slack/slack-channel.js +58 -30
  119. package/dist/channels/slack/socket-mode.js +2 -2
  120. package/dist/channels/slack/thread-context.js +5 -5
  121. package/dist/channels/slack/tool-approval-events.d.ts +5 -0
  122. package/dist/channels/slack/tool-approval-events.d.ts.map +1 -1
  123. package/dist/channels/slack/tool-approval-events.js +50 -38
  124. package/dist/channels/slack/tool-cards.js +1 -1
  125. package/dist/channels/slack/tool-chip.d.ts +9 -0
  126. package/dist/channels/slack/tool-chip.d.ts.map +1 -0
  127. package/dist/channels/slack/tool-chip.js +25 -0
  128. package/dist/channels/slack/types.d.ts +49 -7
  129. package/dist/channels/slack/types.d.ts.map +1 -1
  130. package/dist/channels/slack/upload.d.ts +13 -0
  131. package/dist/channels/slack/upload.d.ts.map +1 -0
  132. package/dist/channels/slack/upload.js +135 -0
  133. package/dist/channels.d.ts +10 -14
  134. package/dist/channels.d.ts.map +1 -1
  135. package/dist/channels.js +9 -21
  136. package/dist/dashboard-session-url.d.ts +15 -0
  137. package/dist/dashboard-session-url.d.ts.map +1 -0
  138. package/dist/dashboard-session-url.js +25 -0
  139. package/dist/docs/404.html +3 -3
  140. package/dist/docs/architecture.svg +59 -0
  141. package/dist/docs/assets/app.DxTdhphC.js +309 -0
  142. package/dist/docs/assets/building-with-agents.md.BBCx0AUo.js +9 -0
  143. package/dist/docs/assets/building-with-agents.md.BBCx0AUo.lean.js +1 -0
  144. package/dist/docs/assets/chunks/@localSearchIndexroot.QmjDU6Jh.js +1 -0
  145. package/dist/docs/assets/chunks/{VPLocalSearchBox.CVQERt56.js → VPLocalSearchBox.CR3KTF0X.js} +2 -2
  146. package/dist/docs/assets/chunks/arc.CVVqBOdS.js +1 -0
  147. package/dist/docs/assets/chunks/architectureDiagram-Q4EWVU46.CJHGP4ki.js +36 -0
  148. package/dist/docs/assets/chunks/baseUniq.r7UVVRBP.js +1 -0
  149. package/dist/docs/assets/chunks/blockDiagram-DXYQGD6D.DKmMaTre.js +132 -0
  150. package/dist/docs/assets/chunks/c4Diagram-AHTNJAMY.DDJsntUO.js +10 -0
  151. package/dist/docs/assets/chunks/channel.BjpoSbz_.js +1 -0
  152. package/dist/docs/assets/chunks/chunk-4BX2VUAB.BK2rKt6W.js +1 -0
  153. package/dist/docs/assets/chunks/chunk-4TB4RGXK.DRLV8RnF.js +206 -0
  154. package/dist/docs/assets/chunks/chunk-55IACEB6.DaKjxtb7.js +1 -0
  155. package/dist/docs/assets/chunks/chunk-EDXVE4YY.C5sPCIT1.js +1 -0
  156. package/dist/docs/assets/chunks/chunk-FMBD7UC4.CSGWyNTB.js +15 -0
  157. package/dist/docs/assets/chunks/chunk-OYMX7WX6.D5tK9XEr.js +231 -0
  158. package/dist/docs/assets/chunks/chunk-QZHKN3VN.BeZGd1UZ.js +1 -0
  159. package/dist/docs/assets/chunks/chunk-YZCP3GAM.U_tfWwQR.js +1 -0
  160. package/dist/docs/assets/chunks/classDiagram-6PBFFD2Q.BgxOlMHw.js +1 -0
  161. package/dist/docs/assets/chunks/classDiagram-v2-HSJHXN6E.BgxOlMHw.js +1 -0
  162. package/dist/docs/assets/chunks/clone.DRuGBKZC.js +1 -0
  163. package/dist/docs/assets/chunks/cose-bilkent-S5V4N54A.DVeRXIb6.js +1 -0
  164. package/dist/docs/assets/chunks/cytoscape.esm.BQk4lpUV.js +331 -0
  165. package/dist/docs/assets/chunks/dagre-KV5264BT.BpKJAeRZ.js +4 -0
  166. package/dist/docs/assets/chunks/defaultLocale.C4B-KCzX.js +1 -0
  167. package/dist/docs/assets/chunks/diagram-5BDNPKRD.BQOtrd1Z.js +10 -0
  168. package/dist/docs/assets/chunks/diagram-G4DWMVQ6.CSDAhjPI.js +24 -0
  169. package/dist/docs/assets/chunks/diagram-MMDJMWI5.Dpztst2S.js +43 -0
  170. package/dist/docs/assets/chunks/diagram-TYMM5635.qJHRizHR.js +24 -0
  171. package/dist/docs/assets/chunks/erDiagram-SMLLAGMA.vbDotH3l.js +85 -0
  172. package/dist/docs/assets/chunks/flowDiagram-DWJPFMVM.CqS_ZQr4.js +162 -0
  173. package/dist/docs/assets/chunks/{framework.BCISBCiQ.js → framework.BNw1pucY.js} +6 -6
  174. package/dist/docs/assets/chunks/ganttDiagram-T4ZO3ILL.DTLdR4pN.js +292 -0
  175. package/dist/docs/assets/chunks/gitGraphDiagram-UUTBAWPF.D04lnbnr.js +106 -0
  176. package/dist/docs/assets/chunks/graph.BlfqLJsM.js +1 -0
  177. package/dist/docs/assets/chunks/infoDiagram-42DDH7IO.tAooImWA.js +2 -0
  178. package/dist/docs/assets/chunks/init.Gi6I4Gst.js +1 -0
  179. package/dist/docs/assets/chunks/ishikawaDiagram-UXIWVN3A.ClUsVqnJ.js +70 -0
  180. package/dist/docs/assets/chunks/journeyDiagram-VCZTEJTY.C3tUgyCg.js +139 -0
  181. package/dist/docs/assets/chunks/kanban-definition-6JOO6SKY.CtD9-QCe.js +89 -0
  182. package/dist/docs/assets/chunks/katex.DkKDou_j.js +257 -0
  183. package/dist/docs/assets/chunks/layout.D38U-LnT.js +1 -0
  184. package/dist/docs/assets/chunks/linear.BJmssyhN.js +1 -0
  185. package/dist/docs/assets/chunks/min.DNgXoouU.js +1 -0
  186. package/dist/docs/assets/chunks/mindmap-definition-QFDTVHPH.Dcp6cxeu.js +96 -0
  187. package/dist/docs/assets/chunks/ordinal.DBvzRdQf.js +1 -0
  188. package/dist/docs/assets/chunks/pieDiagram-DEJITSTG.CLDw6zIs.js +30 -0
  189. package/dist/docs/assets/chunks/quadrantDiagram-34T5L4WZ.CYaeeY4c.js +7 -0
  190. package/dist/docs/assets/chunks/requirementDiagram-MS252O5E.gMYuRpq2.js +84 -0
  191. package/dist/docs/assets/chunks/sankeyDiagram-XADWPNL6.CZqyHFbc.js +10 -0
  192. package/dist/docs/assets/chunks/sequenceDiagram-FGHM5R23.BTsCjUDN.js +157 -0
  193. package/dist/docs/assets/chunks/stateDiagram-FHFEXIEX.CftT9mLJ.js +1 -0
  194. package/dist/docs/assets/chunks/stateDiagram-v2-QKLJ7IA2.-43J68xB.js +1 -0
  195. package/dist/docs/assets/chunks/{theme.Dnsd3XOn.js → theme.B_7J9ZsV.js} +2 -2
  196. package/dist/docs/assets/chunks/timeline-definition-GMOUNBTQ.DbU3WUNw.js +120 -0
  197. package/dist/docs/assets/chunks/vennDiagram-DHZGUBPP.ixsq-q2u.js +34 -0
  198. package/dist/docs/assets/chunks/virtual_mermaid-config.DDnGl6nM.js +1 -0
  199. package/dist/docs/assets/chunks/wardley-RL74JXVD.WRXz-Dux.js +162 -0
  200. package/dist/docs/assets/chunks/wardleyDiagram-NUSXRM2D.C0ewvgbp.js +20 -0
  201. package/dist/docs/assets/chunks/xychartDiagram-5P7HB3ND.nAEhF4bO.js +7 -0
  202. package/dist/docs/assets/deployment.md.D2jQZuFx.js +32 -0
  203. package/dist/docs/assets/deployment.md.D2jQZuFx.lean.js +1 -0
  204. package/dist/docs/assets/evals.md.BYvfZ-PO.js +72 -0
  205. package/dist/docs/assets/evals.md.BYvfZ-PO.lean.js +1 -0
  206. package/dist/docs/assets/guides_agent-to-agent.md.8oDTfu-E.js +30 -0
  207. package/dist/docs/assets/guides_agent-to-agent.md.8oDTfu-E.lean.js +1 -0
  208. package/dist/docs/assets/guides_bitbucket.md.mpevW-VP.js +145 -0
  209. package/dist/docs/assets/guides_bitbucket.md.mpevW-VP.lean.js +1 -0
  210. package/dist/docs/assets/guides_cloud-agents.md.Cp1O3u-X.js +15 -0
  211. package/dist/docs/assets/guides_cloud-agents.md.Cp1O3u-X.lean.js +1 -0
  212. package/dist/docs/assets/guides_convert-automation.md.CqEyfP6Y.js +43 -0
  213. package/dist/docs/assets/guides_convert-automation.md.CqEyfP6Y.lean.js +1 -0
  214. package/dist/docs/assets/guides_github.md.BwpBp3ed.js +156 -0
  215. package/dist/docs/assets/guides_github.md.BwpBp3ed.lean.js +1 -0
  216. package/dist/docs/assets/guides_gitlab.md.DaEC3nMk.js +153 -0
  217. package/dist/docs/assets/guides_gitlab.md.DaEC3nMk.lean.js +1 -0
  218. package/dist/docs/assets/guides_grokbot-agents.md.CMhZNdEU.js +16 -0
  219. package/dist/docs/assets/guides_grokbot-agents.md.CMhZNdEU.lean.js +1 -0
  220. package/dist/docs/assets/guides_improve.md.Bnp4F99w.js +22 -0
  221. package/dist/docs/assets/guides_improve.md.Bnp4F99w.lean.js +1 -0
  222. package/dist/docs/assets/guides_mcp-oauth.md.bSFakfCY.js +50 -0
  223. package/dist/docs/assets/guides_mcp-oauth.md.bSFakfCY.lean.js +1 -0
  224. package/dist/docs/assets/guides_opentelemetry.md.BKDxQmmd.js +35 -0
  225. package/dist/docs/assets/guides_opentelemetry.md.BKDxQmmd.lean.js +1 -0
  226. package/dist/docs/assets/guides_slack.md.Bo96y42E.js +70 -0
  227. package/dist/docs/assets/guides_slack.md.Bo96y42E.lean.js +1 -0
  228. package/dist/docs/assets/guides_webhooks.md.1A72_VEE.js +92 -0
  229. package/dist/docs/assets/guides_webhooks.md.1A72_VEE.lean.js +1 -0
  230. package/dist/docs/assets/hillclimbing.md.D4E1o5Sa.js +7 -0
  231. package/dist/docs/assets/hillclimbing.md.D4E1o5Sa.lean.js +1 -0
  232. package/dist/docs/assets/index.md.C-t81M5J.js +17 -0
  233. package/dist/docs/assets/index.md.C-t81M5J.lean.js +1 -0
  234. package/dist/docs/assets/{quickstart.md.DdQOF7Y8.js → quickstart.md.DAvVhuuU.js} +30 -38
  235. package/dist/docs/assets/quickstart.md.DAvVhuuU.lean.js +1 -0
  236. package/dist/docs/assets/{reference_agent-config.md.CvoL6pof.js → reference_agent-config.md.DGPyw7ms.js} +1 -1
  237. package/dist/docs/assets/{reference_agent-config.md.CvoL6pof.lean.js → reference_agent-config.md.DGPyw7ms.lean.js} +1 -1
  238. package/dist/docs/assets/{reference_artifacts.md.Dior32Qw.js → reference_artifacts.md.Bu_4HmsD.js} +1 -1
  239. package/dist/docs/assets/{reference_artifacts.md.Dior32Qw.lean.js → reference_artifacts.md.Bu_4HmsD.lean.js} +1 -1
  240. package/dist/docs/assets/{reference_channels.md.CAo-iK4j.js → reference_channels.md.nFWbzAic.js} +2 -12
  241. package/dist/docs/assets/{reference_channels.md.CAo-iK4j.lean.js → reference_channels.md.nFWbzAic.lean.js} +1 -1
  242. package/dist/docs/assets/{reference_cli.md.Deg7849l.js → reference_cli.md.DLWDz9ij.js} +5 -3
  243. package/dist/docs/assets/{reference_cli.md.Deg7849l.lean.js → reference_cli.md.DLWDz9ij.lean.js} +1 -1
  244. package/dist/docs/assets/{reference_connections.md.BojkC6c5.js → reference_connections.md.CmyrlXfY.js} +4 -4
  245. package/dist/docs/assets/{reference_connections.md.BojkC6c5.lean.js → reference_connections.md.CmyrlXfY.lean.js} +1 -1
  246. package/dist/docs/assets/reference_evals.md.DNJzM_yf.js +57 -0
  247. package/dist/docs/assets/reference_evals.md.DNJzM_yf.lean.js +1 -0
  248. package/dist/docs/assets/reference_extensions.md.Ceq-qT8d.js +58 -0
  249. package/dist/docs/assets/reference_extensions.md.Ceq-qT8d.lean.js +1 -0
  250. package/dist/docs/assets/{reference_hooks.md.BlM_bOg6.js → reference_hooks.md.B7uzNENk.js} +3 -3
  251. package/dist/docs/assets/{reference_hooks.md.BlM_bOg6.lean.js → reference_hooks.md.B7uzNENk.lean.js} +1 -1
  252. package/dist/docs/assets/{reference_http-api.md.BwaCo-VO.js → reference_http-api.md.CduHavZ2.js} +3 -3
  253. package/dist/docs/assets/{reference_http-api.md.BwaCo-VO.lean.js → reference_http-api.md.CduHavZ2.lean.js} +1 -1
  254. package/dist/docs/assets/{reference_instructions.md.CR7XSsGk.js → reference_instructions.md.CU1My5My.js} +1 -1
  255. package/dist/docs/assets/{reference_instructions.md.CR7XSsGk.lean.js → reference_instructions.md.CU1My5My.lean.js} +1 -1
  256. package/dist/docs/assets/{reference_playground.md.DLnoaczX.js → reference_playground.md.Ch2d0Iqi.js} +1 -1
  257. package/dist/docs/assets/{reference_playground.md.DLnoaczX.lean.js → reference_playground.md.Ch2d0Iqi.lean.js} +1 -1
  258. package/dist/docs/assets/{reference_project-layout.md.BEU8MtQV.js → reference_project-layout.md.BGhgpy9V.js} +3 -3
  259. package/dist/docs/assets/{reference_project-layout.md.BEU8MtQV.lean.js → reference_project-layout.md.BGhgpy9V.lean.js} +1 -1
  260. package/dist/docs/assets/{reference_prompt.md.DnaD5dNK.js → reference_prompt.md.Ccp0R53H.js} +1 -1
  261. package/dist/docs/assets/{reference_prompt.md.DnaD5dNK.lean.js → reference_prompt.md.Ccp0R53H.lean.js} +1 -1
  262. package/dist/docs/assets/{reference_schedules.md.DI_JrHgq.js → reference_schedules.md.B2Nm6FaD.js} +1 -1
  263. package/dist/docs/assets/{reference_schedules.md.DI_JrHgq.lean.js → reference_schedules.md.B2Nm6FaD.lean.js} +1 -1
  264. package/dist/docs/assets/{reference_sessions.md.CyXV1MUw.js → reference_sessions.md.1_6Vyv7x.js} +1 -1
  265. package/dist/docs/assets/{reference_sessions.md.CyXV1MUw.lean.js → reference_sessions.md.1_6Vyv7x.lean.js} +1 -1
  266. package/dist/docs/assets/{reference_skills.md.l2ezAcaN.js → reference_skills.md.DjQkRefx.js} +1 -1
  267. package/dist/docs/assets/{reference_skills.md.l2ezAcaN.lean.js → reference_skills.md.DjQkRefx.lean.js} +1 -1
  268. package/dist/docs/assets/{reference_subagents.md.CfsIloPm.js → reference_subagents.md.BHsSMMyO.js} +2 -2
  269. package/dist/docs/assets/{reference_subagents.md.CfsIloPm.lean.js → reference_subagents.md.BHsSMMyO.lean.js} +1 -1
  270. package/dist/docs/assets/{reference_tools.md.aGrn99hP.js → reference_tools.md.BYzUTeVA.js} +4 -4
  271. package/dist/docs/assets/{reference_tools.md.aGrn99hP.lean.js → reference_tools.md.BYzUTeVA.lean.js} +1 -1
  272. package/dist/docs/assets/{style.DCD_zyg3.css → style.Cfo2vbik.css} +1 -1
  273. package/dist/docs/assets/{templates_agentic-owners.md.BZSH4N9z.js → templates_agentic-owners.md.9M575F5C.js} +1 -1
  274. package/dist/docs/assets/{templates_agentic-owners.md.BZSH4N9z.lean.js → templates_agentic-owners.md.9M575F5C.lean.js} +1 -1
  275. package/dist/docs/assets/{templates_pr-autofixer.md.Bds_XWcV.js → templates_pr-autofixer.md.ws0DDXDy.js} +1 -1
  276. package/dist/docs/assets/{templates_pr-autofixer.md.Bds_XWcV.lean.js → templates_pr-autofixer.md.ws0DDXDy.lean.js} +1 -1
  277. package/dist/docs/assets/{templates_security-reviewer.md.lshxbCLK.js → templates_security-reviewer.md.KEFYXzfK.js} +1 -1
  278. package/dist/docs/assets/{templates_security-reviewer.md.lshxbCLK.lean.js → templates_security-reviewer.md.KEFYXzfK.lean.js} +1 -1
  279. package/dist/docs/assets/templates_thermo-quality-review.md.VNJ_mohX.js +3 -0
  280. package/dist/docs/assets/templates_thermo-quality-review.md.VNJ_mohX.lean.js +1 -0
  281. package/dist/docs/assets/templates_thermo-review.md.Hi3zWOkP.js +3 -0
  282. package/dist/docs/assets/templates_thermo-review.md.Hi3zWOkP.lean.js +1 -0
  283. package/dist/docs/assets/{templates_triage.md.Co4UNzkZ.js → templates_triage.md.CVGe_FG6.js} +1 -1
  284. package/dist/docs/assets/{templates_triage.md.Co4UNzkZ.lean.js → templates_triage.md.CVGe_FG6.lean.js} +1 -1
  285. package/dist/docs/assets/troubleshooting.md.mnfFG2Em.js +1 -0
  286. package/dist/docs/assets/troubleshooting.md.mnfFG2Em.lean.js +1 -0
  287. package/dist/docs/building-with-agents.html +47 -18
  288. package/dist/docs/building-with-agents.md +94 -84
  289. package/dist/docs/deployment.html +62 -48
  290. package/dist/docs/deployment.md +117 -364
  291. package/dist/docs/evals.html +88 -194
  292. package/dist/docs/evals.md +146 -673
  293. package/dist/docs/guides/agent-to-agent.html +65 -12
  294. package/dist/docs/guides/agent-to-agent.md +125 -91
  295. package/dist/docs/guides/bitbucket.html +182 -14
  296. package/dist/docs/guides/bitbucket.md +249 -48
  297. package/dist/docs/guides/cloud-agents.html +49 -10
  298. package/dist/docs/guides/cloud-agents.md +123 -66
  299. package/dist/docs/guides/convert-automation.html +83 -19
  300. package/dist/docs/guides/convert-automation.md +156 -147
  301. package/dist/docs/guides/github.html +187 -62
  302. package/dist/docs/guides/github.md +260 -245
  303. package/dist/docs/guides/gitlab.html +187 -15
  304. package/dist/docs/guides/gitlab.md +249 -50
  305. package/dist/docs/guides/grokbot-agents.html +51 -11
  306. package/dist/docs/guides/grokbot-agents.md +116 -63
  307. package/dist/docs/guides/improve.html +51 -10
  308. package/dist/docs/guides/improve.md +111 -58
  309. package/dist/docs/guides/mcp-oauth.html +77 -22
  310. package/dist/docs/guides/mcp-oauth.md +111 -121
  311. package/dist/docs/guides/opentelemetry.html +72 -30
  312. package/dist/docs/guides/opentelemetry.md +105 -187
  313. package/dist/docs/guides/slack.html +89 -24
  314. package/dist/docs/guides/slack.md +170 -191
  315. package/dist/docs/guides/webhooks.html +100 -200
  316. package/dist/docs/guides/webhooks.md +154 -386
  317. package/dist/docs/hashmap.json +1 -1
  318. package/dist/docs/hillclimbing.html +47 -11
  319. package/dist/docs/hillclimbing.md +101 -55
  320. package/dist/docs/index.html +57 -12
  321. package/dist/docs/index.md +83 -150
  322. package/dist/docs/llms-full.txt +6244 -10784
  323. package/dist/docs/llms.txt +23 -46
  324. package/dist/docs/quickstart.html +70 -45
  325. package/dist/docs/quickstart.md +44 -105
  326. package/dist/docs/reference/agent-config.html +41 -8
  327. package/dist/docs/reference/artifacts.html +41 -8
  328. package/dist/docs/reference/channels.html +41 -18
  329. package/dist/docs/reference/channels.md +0 -16
  330. package/dist/docs/reference/cli.html +44 -9
  331. package/dist/docs/reference/cli.md +2 -16
  332. package/dist/docs/reference/connections.html +43 -10
  333. package/dist/docs/reference/connections.md +3 -5
  334. package/dist/docs/reference/evals.html +116 -0
  335. package/dist/docs/reference/evals.md +293 -0
  336. package/dist/docs/reference/extensions.html +83 -54
  337. package/dist/docs/reference/extensions.md +127 -199
  338. package/dist/docs/reference/hooks.html +42 -9
  339. package/dist/docs/reference/hooks.md +34 -36
  340. package/dist/docs/reference/http-api.html +42 -9
  341. package/dist/docs/reference/http-api.md +5 -5
  342. package/dist/docs/reference/instructions.html +41 -8
  343. package/dist/docs/reference/playground.html +40 -7
  344. package/dist/docs/reference/playground.md +2 -2
  345. package/dist/docs/reference/project-layout.html +42 -9
  346. package/dist/docs/reference/project-layout.md +3 -4
  347. package/dist/docs/reference/prompt.html +41 -8
  348. package/dist/docs/reference/schedules.html +41 -8
  349. package/dist/docs/reference/sessions.html +40 -7
  350. package/dist/docs/reference/sessions.md +5 -4
  351. package/dist/docs/reference/skills.html +41 -8
  352. package/dist/docs/reference/subagents.html +41 -8
  353. package/dist/docs/reference/subagents.md +2 -4
  354. package/dist/docs/reference/tools.html +43 -10
  355. package/dist/docs/reference/tools.md +2 -5
  356. package/dist/docs/templates/agentic-owners.html +41 -8
  357. package/dist/docs/templates/pr-autofixer.html +41 -8
  358. package/dist/docs/templates/security-reviewer.html +41 -8
  359. package/dist/docs/templates/thermo-quality-review.html +62 -0
  360. package/dist/docs/templates/thermo-quality-review.md +75 -0
  361. package/dist/docs/templates/thermo-review.html +62 -0
  362. package/dist/docs/templates/thermo-review.md +74 -0
  363. package/dist/docs/templates/triage.html +41 -8
  364. package/dist/docs/troubleshooting.html +41 -8
  365. package/dist/docs/troubleshooting.md +97 -67
  366. package/dist/evals/assertions.js +19 -19
  367. package/dist/evals/expect.js +1 -1
  368. package/dist/evals/judge.js +1 -1
  369. package/dist/evals/reporters.d.ts.map +1 -1
  370. package/dist/evals/reporters.js +8 -8
  371. package/dist/evals/run-facts.js +2 -2
  372. package/dist/evals.d.ts +1 -1
  373. package/dist/evals.d.ts.map +1 -1
  374. package/dist/evals.js +7 -7
  375. package/dist/extensions/cursor-cloud-agents/extension.js +1 -1
  376. package/dist/extensions/cursor-cloud-agents/lib/backend.js +3 -3
  377. package/dist/extensions/cursor-cloud-agents/lib/fleet.js +1 -1
  378. package/dist/extensions/cursor-cloud-agents/lib/repos.js +6 -6
  379. package/dist/extensions/cursor-cloud-agents/lib/transcript.d.ts.map +1 -1
  380. package/dist/extensions/cursor-cloud-agents/lib/transcript.js +2 -2
  381. package/dist/extensions/cursor-cloud-agents/skills/handoff.md +3 -7
  382. package/dist/extensions/cursor-cloud-agents/tools/list.js +1 -1
  383. package/dist/extensions/improve/extension.d.ts +3 -1
  384. package/dist/extensions/improve/extension.d.ts.map +1 -1
  385. package/dist/extensions/improve/extension.js +4 -2
  386. package/dist/extensions/improve/skills/yourself.js +2 -2
  387. package/dist/extensions/slack-communication/extension.d.ts +28 -0
  388. package/dist/extensions/slack-communication/extension.d.ts.map +1 -0
  389. package/dist/extensions/slack-communication/extension.js +32 -0
  390. package/dist/extensions/slack-communication/skills/slack-voice.d.ts +5 -0
  391. package/dist/extensions/slack-communication/skills/slack-voice.d.ts.map +1 -0
  392. package/dist/extensions/slack-communication/skills/slack-voice.js +54 -0
  393. package/dist/extensions/slack-communication/tools/delete-message.d.ts +4 -0
  394. package/dist/extensions/slack-communication/tools/delete-message.d.ts.map +1 -0
  395. package/dist/extensions/slack-communication/tools/delete-message.js +29 -0
  396. package/dist/extensions/slack-communication/tools/edit-message.d.ts +4 -0
  397. package/dist/extensions/slack-communication/tools/edit-message.d.ts.map +1 -0
  398. package/dist/extensions/slack-communication/tools/edit-message.js +37 -0
  399. package/dist/extensions/slack-communication/tools/post-card.d.ts +4 -0
  400. package/dist/extensions/slack-communication/tools/post-card.d.ts.map +1 -0
  401. package/dist/extensions/slack-communication/tools/post-card.js +25 -0
  402. package/dist/extensions/slack-communication/tools/post-file.d.ts +4 -0
  403. package/dist/extensions/slack-communication/tools/post-file.d.ts.map +1 -0
  404. package/dist/extensions/slack-communication/tools/post-file.js +76 -0
  405. package/dist/extensions/slack-communication/tools/post-update.d.ts +4 -0
  406. package/dist/extensions/slack-communication/tools/post-update.d.ts.map +1 -0
  407. package/dist/extensions/slack-communication/tools/post-update.js +36 -0
  408. package/dist/extensions/slack-communication/tools/react.d.ts +4 -0
  409. package/dist/extensions/slack-communication/tools/react.d.ts.map +1 -0
  410. package/dist/extensions/slack-communication/tools/react.js +27 -0
  411. package/dist/extensions/slack-communication/tools/set-status.d.ts +4 -0
  412. package/dist/extensions/slack-communication/tools/set-status.d.ts.map +1 -0
  413. package/dist/extensions/slack-communication/tools/set-status.js +18 -0
  414. package/dist/files-backends/cursor-hosted.d.ts +18 -6
  415. package/dist/files-backends/cursor-hosted.d.ts.map +1 -1
  416. package/dist/files-backends/cursor-hosted.js +357 -74
  417. package/dist/files-backends/local-fs.js +1 -1
  418. package/dist/files.d.ts +15 -0
  419. package/dist/files.d.ts.map +1 -1
  420. package/dist/filesystem.d.ts +46 -2
  421. package/dist/filesystem.d.ts.map +1 -1
  422. package/dist/filesystem.js +160 -113
  423. package/dist/index.d.ts +7 -10
  424. package/dist/index.d.ts.map +1 -1
  425. package/dist/index.js +5 -7
  426. package/dist/internal/advertise-tools.js +6 -6
  427. package/dist/internal/approval-gate.js +1 -1
  428. package/dist/internal/artifacts-store.js +3 -3
  429. package/dist/internal/as-of.js +2 -2
  430. package/dist/internal/authored-alias-hooks.js +1 -1
  431. package/dist/internal/builtin-tools/reminders.js +2 -2
  432. package/dist/internal/chat-client.js +5 -5
  433. package/dist/internal/cli-ax.d.ts +7 -0
  434. package/dist/internal/cli-ax.d.ts.map +1 -1
  435. package/dist/internal/cli-ax.js +140 -27
  436. package/dist/internal/cli-bitbucket.js +10 -10
  437. package/dist/internal/cli-convert-automation.js +2 -2
  438. package/dist/internal/cli-cursor.d.ts +3 -11
  439. package/dist/internal/cli-cursor.d.ts.map +1 -1
  440. package/dist/internal/cli-cursor.js +5 -10
  441. package/dist/internal/cli-deploy.d.ts +12 -2
  442. package/dist/internal/cli-deploy.d.ts.map +1 -1
  443. package/dist/internal/cli-deploy.js +328 -96
  444. package/dist/internal/cli-docs.js +5 -5
  445. package/dist/internal/cli-github.js +15 -16
  446. package/dist/internal/cli-gitlab.js +10 -10
  447. package/dist/internal/cli-manifest.js +1 -1
  448. package/dist/internal/cli-mcp-oauth.d.ts.map +1 -1
  449. package/dist/internal/cli-mcp-oauth.js +5 -5
  450. package/dist/internal/cli-mcp.js +3 -3
  451. package/dist/internal/cli-skills.js +2 -2
  452. package/dist/internal/cli-slack.js +5 -5
  453. package/dist/internal/cloud-turn-cost.js +1 -1
  454. package/dist/internal/continuation-identity.d.ts.map +1 -1
  455. package/dist/internal/continuation-identity.js +15 -9
  456. package/dist/internal/conversation-mirror.d.ts.map +1 -1
  457. package/dist/internal/conversation-mirror.js +33 -2
  458. package/dist/internal/convert-automation/convert-workflow.js +25 -24
  459. package/dist/internal/convert-automation/types.d.ts +8 -0
  460. package/dist/internal/convert-automation/types.d.ts.map +1 -1
  461. package/dist/internal/cursor/account-mcp.d.ts +2 -2
  462. package/dist/internal/cursor/account-mcp.d.ts.map +1 -1
  463. package/dist/internal/cursor/account-mcp.js +32 -27
  464. package/dist/internal/cursor/backend-client.d.ts +15 -10
  465. package/dist/internal/cursor/backend-client.d.ts.map +1 -1
  466. package/dist/internal/cursor/backend-client.js +17 -11
  467. package/dist/internal/cursor/credentials.js +1 -1
  468. package/dist/internal/cursor/hosted-store-secrets.d.ts +16 -0
  469. package/dist/internal/cursor/hosted-store-secrets.d.ts.map +1 -1
  470. package/dist/internal/cursor/hosted-store-secrets.js +25 -0
  471. package/dist/internal/cursor-account-mcp-auth.js +9 -9
  472. package/dist/internal/cursor-agent-template.d.ts +1 -1
  473. package/dist/internal/cursor-agent-template.d.ts.map +1 -1
  474. package/dist/internal/cursor-agent-template.js +2 -0
  475. package/dist/internal/cursor-deployment-relay.js +9 -9
  476. package/dist/internal/cursor-event-relay.js +10 -10
  477. package/dist/internal/cursor-relay-core.js +2 -2
  478. package/dist/internal/deploy-client.d.ts +106 -9
  479. package/dist/internal/deploy-client.d.ts.map +1 -1
  480. package/dist/internal/deploy-client.js +171 -23
  481. package/dist/internal/deploy-manifest.d.ts +13 -0
  482. package/dist/internal/deploy-manifest.d.ts.map +1 -1
  483. package/dist/internal/deploy-manifest.js +32 -16
  484. package/dist/internal/discovery/agent-config.d.ts +5 -0
  485. package/dist/internal/discovery/agent-config.d.ts.map +1 -1
  486. package/dist/internal/discovery/agent-config.js +27 -0
  487. package/dist/internal/discovery/agent.d.ts.map +1 -1
  488. package/dist/internal/discovery/agent.js +10 -8
  489. package/dist/internal/discovery/channels.js +4 -4
  490. package/dist/internal/discovery/connections.js +4 -4
  491. package/dist/internal/discovery/cursor-plugin.js +12 -12
  492. package/dist/internal/discovery/extension-overlay.js +3 -3
  493. package/dist/internal/discovery/extensions.js +6 -6
  494. package/dist/internal/discovery/info.js +9 -9
  495. package/dist/internal/discovery/instructions.js +1 -1
  496. package/dist/internal/discovery/project.d.ts.map +1 -1
  497. package/dist/internal/discovery/project.js +4 -4
  498. package/dist/internal/discovery/services.js +1 -1
  499. package/dist/internal/discovery/tools.js +1 -1
  500. package/dist/internal/docs-site.js +2 -2
  501. package/dist/internal/env-file.js +1 -1
  502. package/dist/internal/eval-run-store.d.ts.map +1 -1
  503. package/dist/internal/eval-run-store.js +7 -7
  504. package/dist/internal/eval-runner.js +14 -14
  505. package/dist/internal/evals-client.js +4 -4
  506. package/dist/internal/event-log.js +8 -8
  507. package/dist/internal/event-mapper.d.ts +18 -0
  508. package/dist/internal/event-mapper.d.ts.map +1 -1
  509. package/dist/internal/event-mapper.js +34 -2
  510. package/dist/internal/filesystem/format.d.ts.map +1 -1
  511. package/dist/internal/filesystem/format.js +6 -3
  512. package/dist/internal/filesystem/scratch.js +3 -3
  513. package/dist/internal/filesystem/tools.d.ts.map +1 -1
  514. package/dist/internal/filesystem/tools.js +7 -7
  515. package/dist/internal/filesystem/walk.d.ts +7 -4
  516. package/dist/internal/filesystem/walk.d.ts.map +1 -1
  517. package/dist/internal/filesystem/walk.js +35 -12
  518. package/dist/internal/framework-file-storage.d.ts +6 -2
  519. package/dist/internal/framework-file-storage.d.ts.map +1 -1
  520. package/dist/internal/framework-file-storage.js +91 -2
  521. package/dist/internal/framework-storage-selection.d.ts +0 -6
  522. package/dist/internal/framework-storage-selection.d.ts.map +1 -1
  523. package/dist/internal/framework-storage-selection.js +2 -11
  524. package/dist/internal/github-fanout.js +3 -3
  525. package/dist/internal/guest-network.js +4 -4
  526. package/dist/internal/host-files.js +1 -1
  527. package/dist/internal/host-kv.js +2 -2
  528. package/dist/internal/hosted-admission-adapter.d.ts +5 -0
  529. package/dist/internal/hosted-admission-adapter.d.ts.map +1 -1
  530. package/dist/internal/hosted-catch-protocol.d.ts.map +1 -1
  531. package/dist/internal/hosted-catch-protocol.js +2 -4
  532. package/dist/internal/hosted-catch.js +1 -1
  533. package/dist/internal/hosted-delivery-protocol.d.ts +46 -0
  534. package/dist/internal/hosted-delivery-protocol.d.ts.map +1 -1
  535. package/dist/internal/hosted-delivery-protocol.js +126 -9
  536. package/dist/internal/hosted-delivery.d.ts.map +1 -1
  537. package/dist/internal/hosted-delivery.js +209 -64
  538. package/dist/internal/hosted-execution-diag.js +3 -3
  539. package/dist/internal/hosted-execution-latency.d.ts +80 -0
  540. package/dist/internal/hosted-execution-latency.d.ts.map +1 -0
  541. package/dist/internal/hosted-execution-latency.js +220 -0
  542. package/dist/internal/hosting.d.ts +5 -5
  543. package/dist/internal/hosting.d.ts.map +1 -1
  544. package/dist/internal/hosting.js +5 -6
  545. package/dist/internal/http-channel-define.d.ts +11 -0
  546. package/dist/internal/http-channel-define.d.ts.map +1 -0
  547. package/dist/internal/http-channel-define.js +18 -0
  548. package/dist/internal/http-channel.d.ts +2 -3
  549. package/dist/internal/http-channel.d.ts.map +1 -1
  550. package/dist/internal/http-channel.js +3 -4
  551. package/dist/internal/http-control-plane-session.d.ts +7 -3
  552. package/dist/internal/http-control-plane-session.d.ts.map +1 -1
  553. package/dist/internal/http-control-plane-session.js +22 -10
  554. package/dist/internal/incoming-headers-to-fetch.d.ts +10 -0
  555. package/dist/internal/incoming-headers-to-fetch.d.ts.map +1 -0
  556. package/dist/internal/incoming-headers-to-fetch.js +41 -0
  557. package/dist/internal/init-interview.js +7 -7
  558. package/dist/internal/init-project.d.ts.map +1 -1
  559. package/dist/internal/init-project.js +18 -14
  560. package/dist/internal/init-scaffold.js +1 -1
  561. package/dist/internal/inline-stdio-mcp.js +2 -2
  562. package/dist/internal/install-cursor-skills.js +10 -10
  563. package/dist/internal/json-schema.js +1 -1
  564. package/dist/internal/local-control-plane.d.ts.map +1 -1
  565. package/dist/internal/local-control-plane.js +3 -3
  566. package/dist/internal/local-env.js +3 -3
  567. package/dist/internal/log-ring.js +1 -1
  568. package/dist/internal/logs-client.js +1 -1
  569. package/dist/internal/mcp-endpoint.js +8 -8
  570. package/dist/internal/mcp-host.js +4 -4
  571. package/dist/internal/mcp-oauth-on-demand.js +3 -3
  572. package/dist/internal/mcp-oauth.js +5 -5
  573. package/dist/internal/net.js +2 -2
  574. package/dist/internal/otel/config.js +3 -3
  575. package/dist/internal/otel/runtime.js +13 -13
  576. package/dist/internal/peer-connections.js +2 -2
  577. package/dist/internal/platform-schedule-sync.js +1 -1
  578. package/dist/internal/platform-timers.js +1 -1
  579. package/dist/internal/playground/static.js +2 -2
  580. package/dist/internal/playground/toolchain.js +2 -2
  581. package/dist/internal/playground-proxy.js +3 -3
  582. package/dist/internal/process-memory-telemetry.js +1 -1
  583. package/dist/internal/reminder-runner.d.ts.map +1 -1
  584. package/dist/internal/reminder-runner.js +7 -7
  585. package/dist/internal/reminder-store.js +1 -1
  586. package/dist/internal/request-error-status.d.ts.map +1 -1
  587. package/dist/internal/request-error-status.js +9 -0
  588. package/dist/internal/resolved-connections.js +8 -8
  589. package/dist/internal/result-output.d.ts +14 -2
  590. package/dist/internal/result-output.d.ts.map +1 -1
  591. package/dist/internal/result-output.js +45 -2
  592. package/dist/internal/router.js +4 -4
  593. package/dist/internal/run-client.js +2 -2
  594. package/dist/internal/schedule-runner.js +6 -6
  595. package/dist/internal/scm/pr-url.d.ts +3 -1
  596. package/dist/internal/scm/pr-url.d.ts.map +1 -1
  597. package/dist/internal/scm/pr-url.js +10 -2
  598. package/dist/internal/sdk-runner.d.ts.map +1 -1
  599. package/dist/internal/sdk-runner.js +14 -15
  600. package/dist/internal/serve-restart.js +1 -1
  601. package/dist/internal/server.d.ts.map +1 -1
  602. package/dist/internal/server.js +175 -126
  603. package/dist/internal/session-cost.js +3 -3
  604. package/dist/internal/session-engine.d.ts +34 -0
  605. package/dist/internal/session-engine.d.ts.map +1 -1
  606. package/dist/internal/session-engine.js +386 -184
  607. package/dist/internal/session-run-log.d.ts.map +1 -1
  608. package/dist/internal/session-run-log.js +4 -4
  609. package/dist/internal/session-store.d.ts +47 -3
  610. package/dist/internal/session-store.d.ts.map +1 -1
  611. package/dist/internal/session-store.js +198 -33
  612. package/dist/internal/sessions-client.js +3 -3
  613. package/dist/internal/skill-catalog.d.ts +28 -0
  614. package/dist/internal/skill-catalog.d.ts.map +1 -0
  615. package/dist/internal/skill-catalog.js +44 -0
  616. package/dist/internal/slack-thread-key.d.ts +7 -0
  617. package/dist/internal/slack-thread-key.d.ts.map +1 -0
  618. package/dist/internal/slack-thread-key.js +10 -0
  619. package/dist/internal/sleep.js +1 -1
  620. package/dist/internal/storage-coordinator.d.ts +17 -0
  621. package/dist/internal/storage-coordinator.d.ts.map +1 -1
  622. package/dist/internal/storage-coordinator.js +111 -11
  623. package/dist/internal/storage.d.ts +2 -0
  624. package/dist/internal/storage.d.ts.map +1 -0
  625. package/dist/internal/storage.js +1 -0
  626. package/dist/internal/store-mirror.js +4 -4
  627. package/dist/internal/terminal-style.js +2 -2
  628. package/dist/internal/tool-result.js +3 -3
  629. package/dist/internal/trajectory.js +7 -7
  630. package/dist/internal/turn-governor.js +2 -2
  631. package/dist/internal/turn-outbox.js +1 -1
  632. package/dist/internal/update-check.js +2 -2
  633. package/dist/internal/v2-hosting.d.ts +9 -0
  634. package/dist/internal/v2-hosting.d.ts.map +1 -1
  635. package/dist/internal/v2-hosting.js +10 -0
  636. package/dist/internal/workspace.d.ts +13 -10
  637. package/dist/internal/workspace.d.ts.map +1 -1
  638. package/dist/internal/workspace.js +17 -16
  639. package/dist/kv/memory-kv.d.ts +6 -4
  640. package/dist/kv/memory-kv.d.ts.map +1 -1
  641. package/dist/kv/memory-kv.js +9 -7
  642. package/dist/kv.d.ts +4 -7
  643. package/dist/kv.d.ts.map +1 -1
  644. package/dist/kv.js +4 -7
  645. package/dist/otel-public.d.ts +7 -0
  646. package/dist/otel-public.d.ts.map +1 -0
  647. package/dist/otel-public.js +5 -0
  648. package/dist/otel.d.ts +7 -2
  649. package/dist/otel.d.ts.map +1 -1
  650. package/dist/otel.js +7 -2
  651. package/dist/playground/assets/index-B1c1LeIf.js +67 -0
  652. package/dist/playground/assets/index-CK2LX3iD.css +1 -0
  653. package/dist/playground/index.html +2 -2
  654. package/dist/prompt.js +1 -1
  655. package/dist/result.d.ts +10 -4
  656. package/dist/result.d.ts.map +1 -1
  657. package/dist/result.js +9 -3
  658. package/dist/storage-backends/cursor-hosted-v2.js +2 -2
  659. package/dist/storage-backends/cursor-hosted.d.ts +5 -17
  660. package/dist/storage-backends/cursor-hosted.d.ts.map +1 -1
  661. package/dist/storage-backends/cursor-hosted.js +6 -20
  662. package/dist/storage-backends/file-kv.js +7 -7
  663. package/dist/storage.d.ts +20 -2
  664. package/dist/storage.d.ts.map +1 -1
  665. package/dist/storage.js +7 -6
  666. package/dist/types.d.ts +76 -11
  667. package/dist/types.d.ts.map +1 -1
  668. package/dist/types.js +12 -4
  669. package/docs/README.md +85 -152
  670. package/docs/building-with-agents.md +96 -86
  671. package/docs/deployment.md +118 -365
  672. package/docs/evals.md +147 -674
  673. package/docs/guides/agent-to-agent.md +126 -92
  674. package/docs/guides/bitbucket.md +250 -49
  675. package/docs/guides/cloud-agents.md +124 -67
  676. package/docs/guides/convert-automation.md +157 -148
  677. package/docs/guides/github.md +261 -246
  678. package/docs/guides/gitlab.md +250 -51
  679. package/docs/guides/grokbot-agents.md +117 -64
  680. package/docs/guides/improve.md +112 -59
  681. package/docs/guides/mcp-oauth.md +112 -122
  682. package/docs/guides/opentelemetry.md +106 -188
  683. package/docs/guides/slack.md +171 -192
  684. package/docs/guides/webhooks.md +155 -387
  685. package/docs/hillclimbing.md +102 -56
  686. package/docs/quickstart.md +45 -106
  687. package/docs/reference/channels.md +0 -16
  688. package/docs/reference/cli.md +2 -16
  689. package/docs/reference/connections.md +3 -5
  690. package/docs/reference/evals.md +298 -0
  691. package/docs/reference/extensions.md +128 -200
  692. package/docs/reference/hooks.md +34 -36
  693. package/docs/reference/http-api.md +5 -5
  694. package/docs/reference/playground.md +2 -2
  695. package/docs/reference/project-layout.md +3 -4
  696. package/docs/reference/sessions.md +5 -4
  697. package/docs/reference/subagents.md +2 -4
  698. package/docs/reference/tools.md +2 -5
  699. package/docs/templates/thermo-quality-review.md +80 -0
  700. package/docs/templates/thermo-review.md +79 -0
  701. package/docs/troubleshooting.md +98 -68
  702. package/package.json +55 -37
  703. package/skills/framework-map/SKILL.md +2 -2
  704. package/skills/github/SKILL.md +21 -13
  705. package/skills/otel/SKILL.md +8 -18
  706. package/src/bin/agent-serve.ts +115 -72
  707. package/src/channels/bitbucket/api.ts +8 -8
  708. package/src/channels/bitbucket/binding.ts +4 -4
  709. package/src/channels/bitbucket/bitbucket-channel.ts +1 -1
  710. package/src/channels/bitbucket/bitbucket-webhook.ts +1 -1
  711. package/src/channels/bitbucket/checks.ts +3 -4
  712. package/src/channels/bitbucket/cursor-account.ts +1 -1
  713. package/src/channels/bitbucket/events.ts +1 -1
  714. package/src/channels/change-monitors/change-monitors-channel.ts +2 -2
  715. package/src/channels/checks.ts +5 -4
  716. package/src/channels/deployments/deployments-channel.ts +1 -1
  717. package/src/channels/github/api.ts +1 -1
  718. package/src/channels/github/checks.ts +1 -1
  719. package/src/channels/github/cursor-account.ts +3 -3
  720. package/src/channels/github/defaults.ts +8 -4
  721. package/src/channels/github/events.ts +1 -1
  722. package/src/channels/github/forward.ts +8 -8
  723. package/src/channels/github/github-channel.ts +48 -21
  724. package/src/channels/github/progress.ts +7 -2
  725. package/src/channels/github/state.ts +6 -0
  726. package/src/channels/github/types.ts +6 -0
  727. package/src/channels/gitlab/binding.ts +4 -4
  728. package/src/channels/gitlab/checks.ts +3 -4
  729. package/src/channels/gitlab/cursor-account.ts +1 -1
  730. package/src/channels/gitlab/events.ts +1 -1
  731. package/src/channels/gitlab/gitlab-channel.ts +1 -1
  732. package/src/channels/gitlab/gitlab-webhook.ts +1 -1
  733. package/src/channels/gitlab/replay.ts +2 -2
  734. package/src/channels/origin/binding.ts +6 -3
  735. package/src/channels/origin/checks.ts +27 -17
  736. package/src/channels/origin/cursor-account.ts +1 -1
  737. package/src/channels/origin/defaults.ts +5 -1
  738. package/src/channels/origin/events.ts +1 -1
  739. package/src/channels/origin/origin-channel.ts +2 -1
  740. package/src/channels/origin/origin-webhook.ts +2 -2
  741. package/src/channels/slack/agentic-delivery.ts +661 -0
  742. package/src/channels/slack/agentic-posted.ts +148 -0
  743. package/src/channels/slack/agentic-signals.ts +248 -0
  744. package/src/channels/slack/api.ts +51 -11
  745. package/src/channels/slack/approvals.ts +1 -1
  746. package/src/channels/slack/attachments.ts +1 -1
  747. package/src/channels/slack/auth.ts +3 -1
  748. package/src/channels/slack/blocks.ts +3 -3
  749. package/src/channels/slack/bot-mentions.ts +5 -7
  750. package/src/channels/slack/channel-watch.ts +1 -1
  751. package/src/channels/slack/cli-project.ts +3 -3
  752. package/src/channels/slack/defaults.ts +109 -37
  753. package/src/channels/slack/dispatch.ts +419 -168
  754. package/src/channels/slack/doctor.ts +1 -1
  755. package/src/channels/slack/eval-directive.ts +1 -1
  756. package/src/channels/slack/external-policy.ts +15 -2
  757. package/src/channels/slack/footer.ts +108 -0
  758. package/src/channels/slack/index.ts +2 -0
  759. package/src/channels/slack/interactive.ts +4 -2
  760. package/src/channels/slack/live-delivery.ts +23 -7
  761. package/src/channels/slack/log.ts +1 -1
  762. package/src/channels/slack/manifest.ts +1 -1
  763. package/src/channels/slack/nudge-carrier.ts +1 -1
  764. package/src/channels/slack/nudge-store.ts +2 -2
  765. package/src/channels/slack/paint-start.ts +93 -0
  766. package/src/channels/slack/placeholder.ts +366 -0
  767. package/src/channels/slack/progress-delivery.ts +14 -1
  768. package/src/channels/slack/reasoning-chip.ts +48 -0
  769. package/src/channels/slack/recording-sink.ts +176 -0
  770. package/src/channels/slack/reply-options.ts +71 -15
  771. package/src/channels/slack/setup.ts +1 -1
  772. package/src/channels/slack/slack-channel.ts +81 -14
  773. package/src/channels/slack/socket-mode.ts +2 -2
  774. package/src/channels/slack/thread-context.ts +5 -5
  775. package/src/channels/slack/tool-approval-events.ts +54 -38
  776. package/src/channels/slack/tool-cards.ts +1 -1
  777. package/src/channels/slack/tool-chip.ts +36 -0
  778. package/src/channels/slack/types.ts +47 -7
  779. package/src/channels/slack/upload.ts +142 -0
  780. package/src/channels.ts +12 -30
  781. package/src/dashboard-session-url.ts +32 -0
  782. package/src/evals/assertions.ts +19 -19
  783. package/src/evals/expect.ts +1 -1
  784. package/src/evals/judge.ts +1 -1
  785. package/src/evals/reporters.ts +8 -9
  786. package/src/evals/run-facts.ts +2 -2
  787. package/src/evals.ts +7 -10
  788. package/src/extensions/cursor-cloud-agents/extension.ts +1 -1
  789. package/src/extensions/cursor-cloud-agents/lib/backend.ts +3 -3
  790. package/src/extensions/cursor-cloud-agents/lib/fleet.ts +1 -1
  791. package/src/extensions/cursor-cloud-agents/lib/repos.ts +3 -3
  792. package/src/extensions/cursor-cloud-agents/lib/transcript.ts +3 -4
  793. package/src/extensions/cursor-cloud-agents/skills/handoff.md +3 -7
  794. package/src/extensions/cursor-cloud-agents/tools/list.ts +1 -1
  795. package/src/extensions/improve/extension.ts +4 -2
  796. package/src/extensions/improve/skills/yourself.ts +2 -2
  797. package/src/extensions/slack-communication/evals/harness.ts +728 -0
  798. package/src/extensions/slack-communication/evals/slack-communication.eval.ts +953 -0
  799. package/src/extensions/slack-communication/evals/slack-placeholder.eval.ts +194 -0
  800. package/src/extensions/slack-communication/extension.ts +45 -0
  801. package/src/extensions/slack-communication/skills/slack-voice.ts +59 -0
  802. package/src/extensions/slack-communication/tools/delete-message.ts +34 -0
  803. package/src/extensions/slack-communication/tools/edit-message.ts +42 -0
  804. package/src/extensions/slack-communication/tools/post-card.ts +28 -0
  805. package/src/extensions/slack-communication/tools/post-file.ts +85 -0
  806. package/src/extensions/slack-communication/tools/post-update.ts +41 -0
  807. package/src/extensions/slack-communication/tools/react.ts +33 -0
  808. package/src/extensions/slack-communication/tools/set-status.ts +21 -0
  809. package/src/files-backends/cursor-hosted.ts +502 -98
  810. package/src/files-backends/local-fs.ts +1 -1
  811. package/src/files.ts +15 -0
  812. package/src/filesystem.ts +182 -81
  813. package/src/index.ts +7 -36
  814. package/src/internal/advertise-tools.ts +6 -6
  815. package/src/internal/approval-gate.ts +1 -1
  816. package/src/internal/artifacts-store.ts +3 -3
  817. package/src/internal/as-of.ts +2 -2
  818. package/src/internal/authored-alias-hooks.ts +1 -1
  819. package/src/internal/authored-loaders.ts +2 -3
  820. package/src/internal/builtin-tools/reminders.ts +2 -2
  821. package/src/internal/chat-client.ts +5 -5
  822. package/src/internal/cli-ax.ts +172 -29
  823. package/src/internal/cli-bitbucket.ts +11 -11
  824. package/src/internal/cli-convert-automation.ts +2 -2
  825. package/src/internal/cli-cursor.ts +5 -16
  826. package/src/internal/cli-deploy.ts +389 -104
  827. package/src/internal/cli-docs.ts +5 -5
  828. package/src/internal/cli-github.ts +16 -19
  829. package/src/internal/cli-gitlab.ts +11 -11
  830. package/src/internal/cli-manifest.ts +1 -1
  831. package/src/internal/cli-mcp-oauth.ts +5 -7
  832. package/src/internal/cli-mcp.ts +3 -3
  833. package/src/internal/cli-skills.ts +2 -2
  834. package/src/internal/cli-slack.ts +5 -5
  835. package/src/internal/cloud-turn-cost.ts +1 -1
  836. package/src/internal/continuation-identity.ts +14 -9
  837. package/src/internal/conversation-mirror.ts +36 -3
  838. package/src/internal/convert-automation/convert-workflow.ts +27 -27
  839. package/src/internal/convert-automation/types.ts +9 -0
  840. package/src/internal/cursor/account-mcp.ts +48 -31
  841. package/src/internal/cursor/backend-client.ts +28 -17
  842. package/src/internal/cursor/credentials.ts +1 -1
  843. package/src/internal/cursor/hosted-store-secrets.ts +34 -0
  844. package/src/internal/cursor-account-mcp-auth.ts +9 -9
  845. package/src/internal/cursor-agent-template.ts +2 -0
  846. package/src/internal/cursor-deployment-relay.ts +10 -10
  847. package/src/internal/cursor-event-relay.ts +10 -10
  848. package/src/internal/cursor-relay-core.ts +2 -2
  849. package/src/internal/deploy-client.ts +266 -24
  850. package/src/internal/deploy-manifest.ts +46 -8
  851. package/src/internal/discovery/agent-config.ts +34 -0
  852. package/src/internal/discovery/agent.ts +14 -6
  853. package/src/internal/discovery/channels.ts +4 -4
  854. package/src/internal/discovery/connections.ts +4 -4
  855. package/src/internal/discovery/cursor-plugin.ts +12 -12
  856. package/src/internal/discovery/extension-overlay.ts +3 -3
  857. package/src/internal/discovery/extensions.ts +6 -6
  858. package/src/internal/discovery/info.ts +9 -9
  859. package/src/internal/discovery/instructions.ts +1 -1
  860. package/src/internal/discovery/project.ts +4 -4
  861. package/src/internal/discovery/services.ts +1 -1
  862. package/src/internal/discovery/tools.ts +1 -1
  863. package/src/internal/docs-site.ts +2 -2
  864. package/src/internal/env-file.ts +2 -2
  865. package/src/internal/eval-run-store.ts +7 -9
  866. package/src/internal/eval-runner.ts +20 -20
  867. package/src/internal/evals-client.ts +6 -6
  868. package/src/internal/event-log.ts +10 -10
  869. package/src/internal/event-mapper.ts +37 -2
  870. package/src/internal/filesystem/format.ts +11 -12
  871. package/src/internal/filesystem/scratch.ts +3 -3
  872. package/src/internal/filesystem/tools.ts +8 -8
  873. package/src/internal/filesystem/walk.ts +61 -16
  874. package/src/internal/framework-file-storage.ts +104 -4
  875. package/src/internal/framework-storage-selection.ts +2 -12
  876. package/src/internal/github-fanout.ts +4 -4
  877. package/src/internal/guest-network.ts +4 -4
  878. package/src/internal/host-files.ts +1 -1
  879. package/src/internal/host-kv.ts +2 -2
  880. package/src/internal/hosted-admission-adapter.ts +5 -0
  881. package/src/internal/hosted-catch-protocol.ts +3 -5
  882. package/src/internal/hosted-catch.ts +1 -1
  883. package/src/internal/hosted-delivery-protocol.ts +189 -14
  884. package/src/internal/hosted-delivery.ts +294 -81
  885. package/src/internal/hosted-execution-diag.ts +3 -3
  886. package/src/internal/hosted-execution-latency.ts +334 -0
  887. package/src/internal/hosting.ts +5 -6
  888. package/src/internal/http-channel-define.ts +27 -0
  889. package/src/internal/http-channel.ts +3 -4
  890. package/src/internal/http-control-plane-session.ts +24 -11
  891. package/src/internal/incoming-headers-to-fetch.ts +54 -0
  892. package/src/internal/init-interview.ts +7 -7
  893. package/src/internal/init-project.ts +18 -16
  894. package/src/internal/init-scaffold.ts +1 -1
  895. package/src/internal/inline-stdio-mcp.ts +2 -2
  896. package/src/internal/install-cursor-skills.ts +11 -11
  897. package/src/internal/json-schema.ts +1 -1
  898. package/src/internal/local-control-plane.ts +4 -5
  899. package/src/internal/local-env.ts +3 -3
  900. package/src/internal/log-ring.ts +1 -1
  901. package/src/internal/logs-client.ts +1 -1
  902. package/src/internal/mcp-endpoint.ts +10 -10
  903. package/src/internal/mcp-host.ts +9 -9
  904. package/src/internal/mcp-oauth-on-demand.ts +3 -3
  905. package/src/internal/mcp-oauth.ts +5 -5
  906. package/src/internal/net.ts +2 -2
  907. package/src/internal/otel/config.ts +3 -3
  908. package/src/internal/otel/runtime.ts +14 -14
  909. package/src/internal/peer-connections.ts +2 -2
  910. package/src/internal/platform-schedule-sync.ts +1 -1
  911. package/src/internal/platform-timers.ts +1 -1
  912. package/src/internal/playground/static.ts +2 -2
  913. package/src/internal/playground/toolchain.ts +2 -2
  914. package/src/internal/playground-proxy.ts +3 -3
  915. package/src/internal/process-memory-telemetry.ts +1 -1
  916. package/src/internal/reminder-runner.ts +8 -10
  917. package/src/internal/reminder-store.ts +1 -1
  918. package/src/internal/request-error-status.ts +9 -0
  919. package/src/internal/resolved-connections.ts +8 -8
  920. package/src/internal/result-output.ts +62 -5
  921. package/src/internal/router.ts +4 -4
  922. package/src/internal/run-client.ts +2 -2
  923. package/src/internal/schedule-runner.ts +6 -6
  924. package/src/internal/scm/pr-url.ts +11 -2
  925. package/src/internal/sdk-runner.ts +14 -28
  926. package/src/internal/serve-restart.ts +1 -1
  927. package/src/internal/server.ts +201 -140
  928. package/src/internal/session-cost.ts +3 -3
  929. package/src/internal/session-engine.ts +516 -244
  930. package/src/internal/session-run-log.ts +4 -6
  931. package/src/internal/session-store.ts +213 -39
  932. package/src/internal/sessions-client.ts +3 -3
  933. package/src/internal/skill-catalog.ts +69 -0
  934. package/src/internal/slack-thread-key.ts +11 -0
  935. package/src/internal/sleep.ts +1 -1
  936. package/src/internal/storage-coordinator.ts +118 -21
  937. package/src/internal/storage.ts +1 -0
  938. package/src/internal/store-mirror.ts +4 -4
  939. package/src/internal/terminal-style.ts +2 -2
  940. package/src/internal/tool-result.ts +3 -3
  941. package/src/internal/trajectory.ts +7 -7
  942. package/src/internal/turn-governor.ts +2 -2
  943. package/src/internal/turn-outbox.ts +1 -1
  944. package/src/internal/update-check.ts +2 -2
  945. package/src/internal/v2-hosting.ts +14 -0
  946. package/src/internal/workspace.ts +17 -17
  947. package/src/kv/memory-kv.ts +9 -7
  948. package/src/kv.ts +4 -7
  949. package/src/otel-public.ts +24 -0
  950. package/src/otel.ts +7 -2
  951. package/src/prompt.ts +1 -1
  952. package/src/result.ts +10 -8
  953. package/src/storage-backends/cursor-hosted-v2.ts +2 -2
  954. package/src/storage-backends/cursor-hosted.ts +6 -23
  955. package/src/storage-backends/file-kv.ts +7 -7
  956. package/src/storage.ts +22 -7
  957. package/src/types.ts +91 -17
  958. package/templates/agentic-owners/agent/channels/github.ts +3 -6
  959. package/templates/agentic-owners/agent/lib/github.ts +5 -5
  960. package/templates/agentic-owners/agent/lib/owners/decision.ts +13 -10
  961. package/templates/agentic-owners/agent/lib/owners/handles.ts +2 -2
  962. package/templates/agentic-owners/agent/lib/owners/match.ts +3 -3
  963. package/templates/agentic-owners/agent/lib/owners/matching.ts +1 -1
  964. package/templates/agentic-owners/agent/lib/owners/parse.ts +4 -9
  965. package/templates/agentic-owners/agent/lib/owners/prompt.ts +1 -1
  966. package/templates/agentic-owners/agent/lib/review.ts +37 -30
  967. package/templates/agentic-owners/evals/owners.eval.ts +2 -2
  968. package/templates/agentic-owners/package.json +1 -1
  969. package/templates/agents-md/agent/lib/collect.ts +16 -10
  970. package/templates/agents-md/agent/lib/config.ts +1 -1
  971. package/templates/agents-md/agent/tools/apply_agents.ts +10 -8
  972. package/templates/agents-md/package.json +1 -1
  973. package/templates/code-wiki/agent/channels/github.ts +4 -7
  974. package/templates/code-wiki/agent/lib/repos.ts +1 -1
  975. package/templates/code-wiki/agent/tools/apply_wiki.ts +3 -4
  976. package/templates/code-wiki/package.json +1 -1
  977. package/templates/demo/agent/lib/collect.ts +6 -2
  978. package/templates/demo/agent/lib/repos.ts +1 -1
  979. package/templates/demo/agent/tools/record_demo.ts +1 -1
  980. package/templates/demo/evals/demo.eval.ts +1 -5
  981. package/templates/demo/package.json +1 -1
  982. package/templates/grokbot-agents/package.json +1 -1
  983. package/templates/pr-autofixer/agent/channels/github.ts +16 -13
  984. package/templates/pr-autofixer/agent/lib/merge-watch.ts +2 -4
  985. package/templates/pr-autofixer/agent/lib/repos.ts +2 -2
  986. package/templates/pr-autofixer/agent/lib/webhook-routing.ts +1 -1
  987. package/templates/pr-autofixer/package.json +1 -1
  988. package/templates/security-help/agent/lib/repos.ts +1 -1
  989. package/templates/security-help/package.json +1 -1
  990. package/templates/security-reviewer/agent/lib/repos.ts +1 -1
  991. package/templates/security-reviewer/agent/tools/post_findings.ts +1 -3
  992. package/templates/security-reviewer/package.json +1 -1
  993. package/templates/thermo-quality-review/README.md +35 -0
  994. package/templates/thermo-quality-review/agent/agent.ts +8 -0
  995. package/templates/thermo-quality-review/agent/channels/github.ts +42 -0
  996. package/templates/thermo-quality-review/agent/instructions.md +43 -0
  997. package/templates/thermo-quality-review/agent/tools/post_findings.ts +70 -0
  998. package/templates/thermo-quality-review/evals/evals.config.ts +5 -0
  999. package/templates/thermo-quality-review/evals/review.eval.ts +62 -0
  1000. package/templates/thermo-quality-review/package.json +18 -0
  1001. package/templates/thermo-quality-review/tsconfig.json +12 -0
  1002. package/templates/thermo-review/README.md +35 -0
  1003. package/templates/thermo-review/agent/agent.ts +8 -0
  1004. package/templates/thermo-review/agent/channels/github.ts +42 -0
  1005. package/templates/thermo-review/agent/instructions.md +40 -0
  1006. package/templates/thermo-review/agent/tools/post_findings.ts +70 -0
  1007. package/templates/thermo-review/evals/evals.config.ts +5 -0
  1008. package/templates/thermo-review/evals/review.eval.ts +53 -0
  1009. package/templates/thermo-review/package.json +18 -0
  1010. package/templates/thermo-review/tsconfig.json +12 -0
  1011. package/templates/triage/agent/lib/actuate.ts +26 -41
  1012. package/templates/triage/agent/lib/parse-queue-event.ts +2 -1
  1013. package/templates/triage/agent/lib/verify-webhook.ts +10 -5
  1014. package/templates/triage/agent/tools/record_triage.ts +1 -4
  1015. package/templates/triage/package.json +1 -1
  1016. package/dist/client.d.ts +0 -14
  1017. package/dist/client.d.ts.map +0 -1
  1018. package/dist/client.js +0 -12
  1019. package/dist/docs/assets/app.Cr-wVbnB.js +0 -1
  1020. package/dist/docs/assets/building-with-agents.md.D0KbSkJn.js +0 -13
  1021. package/dist/docs/assets/building-with-agents.md.D0KbSkJn.lean.js +0 -1
  1022. package/dist/docs/assets/chunks/@localSearchIndexroot.CFVQ4S17.js +0 -1
  1023. package/dist/docs/assets/concepts.md.B4o63Gul.js +0 -1
  1024. package/dist/docs/assets/concepts.md.B4o63Gul.lean.js +0 -1
  1025. package/dist/docs/assets/deployment.md.JenwuCCB.js +0 -51
  1026. package/dist/docs/assets/deployment.md.JenwuCCB.lean.js +0 -1
  1027. package/dist/docs/assets/evals.md.C7JLjoEP.js +0 -211
  1028. package/dist/docs/assets/evals.md.C7JLjoEP.lean.js +0 -1
  1029. package/dist/docs/assets/guides_agent-to-agent.md.BDb0t1QV.js +0 -10
  1030. package/dist/docs/assets/guides_agent-to-agent.md.BDb0t1QV.lean.js +0 -1
  1031. package/dist/docs/assets/guides_bitbucket.md.DZPzmUjU.js +0 -10
  1032. package/dist/docs/assets/guides_bitbucket.md.DZPzmUjU.lean.js +0 -1
  1033. package/dist/docs/assets/guides_cloud-agents.md.BsloyHdY.js +0 -9
  1034. package/dist/docs/assets/guides_cloud-agents.md.BsloyHdY.lean.js +0 -1
  1035. package/dist/docs/assets/guides_convert-automation.md.B4sjlodG.js +0 -12
  1036. package/dist/docs/assets/guides_convert-automation.md.B4sjlodG.lean.js +0 -1
  1037. package/dist/docs/assets/guides_github.md.TZaTZlfz.js +0 -64
  1038. package/dist/docs/assets/guides_github.md.TZaTZlfz.lean.js +0 -1
  1039. package/dist/docs/assets/guides_gitlab.md.BmqwQfdG.js +0 -14
  1040. package/dist/docs/assets/guides_gitlab.md.BmqwQfdG.lean.js +0 -1
  1041. package/dist/docs/assets/guides_grokbot-agents.md.DyV-WArv.js +0 -9
  1042. package/dist/docs/assets/guides_grokbot-agents.md.DyV-WArv.lean.js +0 -1
  1043. package/dist/docs/assets/guides_human-in-the-loop.md.By1G2T3_.js +0 -28
  1044. package/dist/docs/assets/guides_human-in-the-loop.md.By1G2T3_.lean.js +0 -1
  1045. package/dist/docs/assets/guides_improve.md.BGVk32bK.js +0 -14
  1046. package/dist/docs/assets/guides_improve.md.BGVk32bK.lean.js +0 -1
  1047. package/dist/docs/assets/guides_mcp-oauth.md.Dp6cDP7f.js +0 -28
  1048. package/dist/docs/assets/guides_mcp-oauth.md.Dp6cDP7f.lean.js +0 -1
  1049. package/dist/docs/assets/guides_opentelemetry.md.SCRMskno.js +0 -26
  1050. package/dist/docs/assets/guides_opentelemetry.md.SCRMskno.lean.js +0 -1
  1051. package/dist/docs/assets/guides_slack.md.D4RVMM4G.js +0 -38
  1052. package/dist/docs/assets/guides_slack.md.D4RVMM4G.lean.js +0 -1
  1053. package/dist/docs/assets/guides_webhooks.md.CJK484ex.js +0 -225
  1054. package/dist/docs/assets/guides_webhooks.md.CJK484ex.lean.js +0 -1
  1055. package/dist/docs/assets/hillclimbing.md.BOiVo1tf.js +0 -4
  1056. package/dist/docs/assets/hillclimbing.md.BOiVo1tf.lean.js +0 -1
  1057. package/dist/docs/assets/index.md.DD9Q2XuJ.js +0 -5
  1058. package/dist/docs/assets/index.md.DD9Q2XuJ.lean.js +0 -1
  1059. package/dist/docs/assets/quickstart.md.DdQOF7Y8.lean.js +0 -1
  1060. package/dist/docs/assets/reference_extensions.md.ZAVUyuEX.js +0 -62
  1061. package/dist/docs/assets/reference_extensions.md.ZAVUyuEX.lean.js +0 -1
  1062. package/dist/docs/assets/reference_result.md.BK5SxDrf.js +0 -19
  1063. package/dist/docs/assets/reference_result.md.BK5SxDrf.lean.js +0 -1
  1064. package/dist/docs/assets/scaffolding-agents.md.Kctn3OVb.js +0 -1
  1065. package/dist/docs/assets/scaffolding-agents.md.Kctn3OVb.lean.js +0 -1
  1066. package/dist/docs/assets/skills_create-agent.md.Q3h6Je-e.js +0 -8
  1067. package/dist/docs/assets/skills_create-agent.md.Q3h6Je-e.lean.js +0 -1
  1068. package/dist/docs/assets/skills_debug.md.CVjCXMFF.js +0 -1
  1069. package/dist/docs/assets/skills_debug.md.CVjCXMFF.lean.js +0 -1
  1070. package/dist/docs/assets/skills_deploy.md.CWqi_ZxW.js +0 -35
  1071. package/dist/docs/assets/skills_deploy.md.CWqi_ZxW.lean.js +0 -1
  1072. package/dist/docs/assets/skills_evals.md.DFxYPErF.js +0 -25
  1073. package/dist/docs/assets/skills_evals.md.DFxYPErF.lean.js +0 -1
  1074. package/dist/docs/assets/skills_framework-map.md.BxLSOhSY.js +0 -1
  1075. package/dist/docs/assets/skills_framework-map.md.BxLSOhSY.lean.js +0 -1
  1076. package/dist/docs/assets/skills_github.md.hgFX_oKY.js +0 -16
  1077. package/dist/docs/assets/skills_github.md.hgFX_oKY.lean.js +0 -1
  1078. package/dist/docs/assets/skills_hillclimb.md.B_zJerxA.js +0 -7
  1079. package/dist/docs/assets/skills_hillclimb.md.B_zJerxA.lean.js +0 -1
  1080. package/dist/docs/assets/skills_index.md.DL7EHaQ-.js +0 -1
  1081. package/dist/docs/assets/skills_index.md.DL7EHaQ-.lean.js +0 -1
  1082. package/dist/docs/assets/skills_mcp-auth.md.DGvFP3HE.js +0 -18
  1083. package/dist/docs/assets/skills_mcp-auth.md.DGvFP3HE.lean.js +0 -1
  1084. package/dist/docs/assets/skills_otel.md.B5Ddv1xH.js +0 -8
  1085. package/dist/docs/assets/skills_otel.md.B5Ddv1xH.lean.js +0 -1
  1086. package/dist/docs/assets/skills_setup-slack.md.BBgx8lUz.js +0 -20
  1087. package/dist/docs/assets/skills_setup-slack.md.BBgx8lUz.lean.js +0 -1
  1088. package/dist/docs/assets/storage.md.BUrhJ-Zz.js +0 -30
  1089. package/dist/docs/assets/storage.md.BUrhJ-Zz.lean.js +0 -1
  1090. package/dist/docs/assets/templates_agents-md.md.CXSMZljE.js +0 -2
  1091. package/dist/docs/assets/templates_agents-md.md.CXSMZljE.lean.js +0 -1
  1092. package/dist/docs/assets/templates_code-wiki.md.CDYZIBFN.js +0 -2
  1093. package/dist/docs/assets/templates_code-wiki.md.CDYZIBFN.lean.js +0 -1
  1094. package/dist/docs/assets/templates_demo.md.BeQX9V3H.js +0 -4
  1095. package/dist/docs/assets/templates_demo.md.BeQX9V3H.lean.js +0 -1
  1096. package/dist/docs/assets/templates_grokbot-agents.md.c1s6Flp9.js +0 -3
  1097. package/dist/docs/assets/templates_grokbot-agents.md.c1s6Flp9.lean.js +0 -1
  1098. package/dist/docs/assets/templates_security-help.md.C3Ny_Qr2.js +0 -4
  1099. package/dist/docs/assets/templates_security-help.md.C3Ny_Qr2.lean.js +0 -1
  1100. package/dist/docs/assets/troubleshooting.md.CYEAO9bM.js +0 -1
  1101. package/dist/docs/assets/troubleshooting.md.CYEAO9bM.lean.js +0 -1
  1102. package/dist/docs/concepts.html +0 -27
  1103. package/dist/docs/concepts.md +0 -166
  1104. package/dist/docs/design/filesystem.md +0 -376
  1105. package/dist/docs/design/runtime-abstraction.md +0 -1756
  1106. package/dist/docs/guides/human-in-the-loop.html +0 -54
  1107. package/dist/docs/guides/human-in-the-loop.md +0 -126
  1108. package/dist/docs/reference/result.html +0 -45
  1109. package/dist/docs/reference/result.md +0 -89
  1110. package/dist/docs/scaffolding-agents.html +0 -27
  1111. package/dist/docs/scaffolding-agents.md +0 -130
  1112. package/dist/docs/skills/create-agent.html +0 -34
  1113. package/dist/docs/skills/create-agent.md +0 -160
  1114. package/dist/docs/skills/debug.html +0 -27
  1115. package/dist/docs/skills/debug.md +0 -36
  1116. package/dist/docs/skills/deploy.html +0 -61
  1117. package/dist/docs/skills/deploy.md +0 -161
  1118. package/dist/docs/skills/evals.html +0 -51
  1119. package/dist/docs/skills/evals.md +0 -137
  1120. package/dist/docs/skills/framework-map.html +0 -27
  1121. package/dist/docs/skills/framework-map.md +0 -99
  1122. package/dist/docs/skills/github.html +0 -42
  1123. package/dist/docs/skills/github.md +0 -93
  1124. package/dist/docs/skills/hillclimb.html +0 -33
  1125. package/dist/docs/skills/hillclimb.md +0 -55
  1126. package/dist/docs/skills/index.html +0 -27
  1127. package/dist/docs/skills/index.md +0 -21
  1128. package/dist/docs/skills/mcp-auth.html +0 -44
  1129. package/dist/docs/skills/mcp-auth.md +0 -76
  1130. package/dist/docs/skills/otel.html +0 -34
  1131. package/dist/docs/skills/otel.md +0 -53
  1132. package/dist/docs/skills/setup-slack.html +0 -46
  1133. package/dist/docs/skills/setup-slack.md +0 -141
  1134. package/dist/docs/storage.html +0 -56
  1135. package/dist/docs/storage.md +0 -167
  1136. package/dist/docs/templates/agents-md.html +0 -28
  1137. package/dist/docs/templates/agents-md.md +0 -105
  1138. package/dist/docs/templates/code-wiki.html +0 -28
  1139. package/dist/docs/templates/code-wiki.md +0 -91
  1140. package/dist/docs/templates/demo.html +0 -30
  1141. package/dist/docs/templates/demo.md +0 -80
  1142. package/dist/docs/templates/grokbot-agents.html +0 -29
  1143. package/dist/docs/templates/grokbot-agents.md +0 -48
  1144. package/dist/docs/templates/security-help.html +0 -30
  1145. package/dist/docs/templates/security-help.md +0 -65
  1146. package/dist/internal/tenant-slack/relay.d.ts +0 -75
  1147. package/dist/internal/tenant-slack/relay.d.ts.map +0 -1
  1148. package/dist/internal/tenant-slack/relay.js +0 -148
  1149. package/dist/playground/assets/index-Bhxzrcf6.css +0 -1
  1150. package/dist/playground/assets/index-CqLX5uF3.js +0 -67
  1151. package/docs/concepts.md +0 -171
  1152. package/docs/design/filesystem.md +0 -376
  1153. package/docs/design/runtime-abstraction.md +0 -1756
  1154. package/docs/guides/human-in-the-loop.md +0 -131
  1155. package/docs/reference/result.md +0 -94
  1156. package/docs/scaffolding-agents.md +0 -135
  1157. package/docs/skills/index.md +0 -26
  1158. package/docs/storage.md +0 -172
  1159. package/docs/templates/agents-md.md +0 -110
  1160. package/docs/templates/code-wiki.md +0 -96
  1161. package/docs/templates/demo.md +0 -85
  1162. package/docs/templates/grokbot-agents.md +0 -53
  1163. package/docs/templates/security-help.md +0 -70
  1164. package/src/client.ts +0 -23
  1165. package/src/internal/tenant-slack/relay.ts +0 -203
  1166. package/templates/pr-autofixer/agent/storage.ts +0 -7
@@ -4,27 +4,63 @@
4
4
  <meta charset="utf-8">
5
5
  <meta name="viewport" content="width=device-width,initial-scale=1">
6
6
  <title>Hillclimbing | Agent SDK</title>
7
- <meta name="description" content="Improve an agent one measured round at a time, with the hillclimb skill running the loop with you.">
7
+ <meta name="description" content="Improve one agent behavior at a time by measuring fixed inputs, changing one lever, and locking each win with an eval.">
8
8
  <meta name="generator" content="VitePress v1.6.4">
9
- <link rel="preload stylesheet" href="/docs/assets/style.DCD_zyg3.css" as="style">
9
+ <link rel="preload stylesheet" href="/docs/assets/style.Cfo2vbik.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.Cr-wVbnB.js"></script>
12
+ <script type="module" src="/docs/assets/app.DxTdhphC.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.Dnsd3XOn.js">
15
- <link rel="modulepreload" href="/docs/assets/chunks/framework.BCISBCiQ.js">
16
- <link rel="modulepreload" href="/docs/assets/hillclimbing.md.BOiVo1tf.lean.js">
14
+ <link rel="modulepreload" href="/docs/assets/chunks/framework.BNw1pucY.js">
15
+ <link rel="modulepreload" href="/docs/assets/chunks/theme.B_7J9ZsV.js">
16
+ <link rel="modulepreload" href="/docs/assets/chunks/katex.DkKDou_j.js">
17
+ <link rel="modulepreload" href="/docs/assets/chunks/dagre-KV5264BT.BpKJAeRZ.js">
18
+ <link rel="modulepreload" href="/docs/assets/chunks/cose-bilkent-S5V4N54A.DVeRXIb6.js">
19
+ <link rel="modulepreload" href="/docs/assets/chunks/c4Diagram-AHTNJAMY.DDJsntUO.js">
20
+ <link rel="modulepreload" href="/docs/assets/chunks/flowDiagram-DWJPFMVM.CqS_ZQr4.js">
21
+ <link rel="modulepreload" href="/docs/assets/chunks/erDiagram-SMLLAGMA.vbDotH3l.js">
22
+ <link rel="modulepreload" href="/docs/assets/chunks/gitGraphDiagram-UUTBAWPF.D04lnbnr.js">
23
+ <link rel="modulepreload" href="/docs/assets/chunks/ganttDiagram-T4ZO3ILL.DTLdR4pN.js">
24
+ <link rel="modulepreload" href="/docs/assets/chunks/infoDiagram-42DDH7IO.tAooImWA.js">
25
+ <link rel="modulepreload" href="/docs/assets/chunks/pieDiagram-DEJITSTG.CLDw6zIs.js">
26
+ <link rel="modulepreload" href="/docs/assets/chunks/quadrantDiagram-34T5L4WZ.CYaeeY4c.js">
27
+ <link rel="modulepreload" href="/docs/assets/chunks/xychartDiagram-5P7HB3ND.nAEhF4bO.js">
28
+ <link rel="modulepreload" href="/docs/assets/chunks/requirementDiagram-MS252O5E.gMYuRpq2.js">
29
+ <link rel="modulepreload" href="/docs/assets/chunks/sequenceDiagram-FGHM5R23.BTsCjUDN.js">
30
+ <link rel="modulepreload" href="/docs/assets/chunks/classDiagram-6PBFFD2Q.BgxOlMHw.js">
31
+ <link rel="modulepreload" href="/docs/assets/chunks/classDiagram-v2-HSJHXN6E.BgxOlMHw.js">
32
+ <link rel="modulepreload" href="/docs/assets/chunks/stateDiagram-FHFEXIEX.CftT9mLJ.js">
33
+ <link rel="modulepreload" href="/docs/assets/chunks/stateDiagram-v2-QKLJ7IA2.-43J68xB.js">
34
+ <link rel="modulepreload" href="/docs/assets/chunks/journeyDiagram-VCZTEJTY.C3tUgyCg.js">
35
+ <link rel="modulepreload" href="/docs/assets/chunks/timeline-definition-GMOUNBTQ.DbU3WUNw.js">
36
+ <link rel="modulepreload" href="/docs/assets/chunks/mindmap-definition-QFDTVHPH.Dcp6cxeu.js">
37
+ <link rel="modulepreload" href="/docs/assets/chunks/kanban-definition-6JOO6SKY.CtD9-QCe.js">
38
+ <link rel="modulepreload" href="/docs/assets/chunks/sankeyDiagram-XADWPNL6.CZqyHFbc.js">
39
+ <link rel="modulepreload" href="/docs/assets/chunks/diagram-TYMM5635.qJHRizHR.js">
40
+ <link rel="modulepreload" href="/docs/assets/chunks/diagram-MMDJMWI5.Dpztst2S.js">
41
+ <link rel="modulepreload" href="/docs/assets/chunks/blockDiagram-DXYQGD6D.DKmMaTre.js">
42
+ <link rel="modulepreload" href="/docs/assets/chunks/diagram-5BDNPKRD.BQOtrd1Z.js">
43
+ <link rel="modulepreload" href="/docs/assets/chunks/architectureDiagram-Q4EWVU46.CJHGP4ki.js">
44
+ <link rel="modulepreload" href="/docs/assets/chunks/ishikawaDiagram-UXIWVN3A.ClUsVqnJ.js">
45
+ <link rel="modulepreload" href="/docs/assets/chunks/vennDiagram-DHZGUBPP.ixsq-q2u.js">
46
+ <link rel="modulepreload" href="/docs/assets/chunks/diagram-G4DWMVQ6.CSDAhjPI.js">
47
+ <link rel="modulepreload" href="/docs/assets/chunks/wardleyDiagram-NUSXRM2D.C0ewvgbp.js">
48
+ <link rel="modulepreload" href="/docs/assets/chunks/virtual_mermaid-config.DDnGl6nM.js">
49
+ <link rel="modulepreload" href="/docs/assets/hillclimbing.md.D4E1o5Sa.lean.js">
17
50
  <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>
18
51
  <script id="check-mac-os">document.documentElement.classList.toggle("mac",/Mac|iPhone|iPod|iPad/i.test(navigator.platform));</script>
19
52
  <link rel="alternate" type="text/plain" href="/docs/llms.txt">
20
53
  <link rel="alternate" type="text/markdown" href="/docs/hillclimbing.md">
21
54
  </head>
22
55
  <body>
23
- <div id="app"><div class="Layout" data-v-990b7706><!--[--><!--]--><!--[--><span tabindex="-1" data-v-0b74bec0></span><a href="#VPContent" class="VPSkipLink visually-hidden" data-v-0b74bec0>Skip to content</a><!--]--><!----><header class="VPNav" data-v-990b7706 data-v-af996e33><div class="VPNavBar" data-v-af996e33 data-v-c7f322eb><div class="wrapper" data-v-c7f322eb><div class="container" data-v-c7f322eb><div class="title" data-v-c7f322eb><div class="VPNavBarTitle has-sidebar" data-v-c7f322eb data-v-d1664c59><a class="title" href="/docs/" data-v-d1664c59><!--[--><!--]--><!----><span data-v-d1664c59>Agent SDK</span><!--[--><!--[--><!--[--><!--[--><span class="agent-sdk-version" title="@cursor/july 0.1.109" data-v-c26a5f4f>0.1.109</span><!--]--><!--]--><!--]--><!--]--></a></div></div><div class="content" data-v-c7f322eb><div class="content-body" data-v-c7f322eb><!--[--><!--]--><div class="VPNavBarSearch search" data-v-c7f322eb><!--[--><!----><div id="local-search"><button type="button" class="DocSearch DocSearch-Button" aria-label="Search"><span class="DocSearch-Button-Container"><span class="vp-icon DocSearch-Search-Icon"></span><span class="DocSearch-Button-Placeholder">Search</span></span><span class="DocSearch-Button-Keys"><kbd class="DocSearch-Button-Key"></kbd><kbd class="DocSearch-Button-Key">K</kbd></span></button></div><!--]--></div><nav aria-labelledby="main-nav-aria-label" class="VPNavBarMenu menu" data-v-c7f322eb data-v-ab749b05><span id="main-nav-aria-label" class="visually-hidden" data-v-ab749b05> Main Navigation </span><!--[--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/quickstart.html" tabindex="0" data-v-ab749b05 data-v-ef8d136f><!--[--><span data-v-ef8d136f>Quickstart</span><!--]--></a><!--]--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/guides/webhooks.html" tabindex="0" data-v-ab749b05 data-v-ef8d136f><!--[--><span data-v-ef8d136f>Guides</span><!--]--></a><!--]--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/templates/demo.html" tabindex="0" data-v-ab749b05 data-v-ef8d136f><!--[--><span data-v-ef8d136f>Templates</span><!--]--></a><!--]--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/reference/project-layout.html" tabindex="0" data-v-ab749b05 data-v-ef8d136f><!--[--><span data-v-ef8d136f>Reference</span><!--]--></a><!--]--><!--]--></nav><!----><div class="VPNavBarAppearance appearance" data-v-c7f322eb data-v-7c6c0ede><button class="VPSwitch VPSwitchAppearance" type="button" role="switch" title aria-checked="false" data-v-7c6c0ede data-v-87b8a6bb data-v-9f798512><span class="check" data-v-9f798512><span class="icon" data-v-9f798512><!--[--><span class="vpi-sun sun" data-v-87b8a6bb></span><span class="vpi-moon moon" data-v-87b8a6bb></span><!--]--></span></span></button></div><!----><div class="VPFlyout VPNavBarExtra extra" data-v-c7f322eb data-v-e53d4296 data-v-79fc383b><button type="button" class="button" aria-haspopup="true" aria-expanded="false" aria-label="extra navigation" data-v-79fc383b><span class="vpi-more-horizontal icon" data-v-79fc383b></span></button><div class="menu" data-v-79fc383b><div class="VPMenu" data-v-79fc383b data-v-0d780c53><!----><!--[--><!--[--><!----><div class="group" data-v-e53d4296><div class="item appearance" data-v-e53d4296><p class="label" data-v-e53d4296>Appearance</p><div class="appearance-action" data-v-e53d4296><button class="VPSwitch VPSwitchAppearance" type="button" role="switch" title aria-checked="false" data-v-e53d4296 data-v-87b8a6bb data-v-9f798512><span class="check" data-v-9f798512><span class="icon" data-v-9f798512><!--[--><span class="vpi-sun sun" data-v-87b8a6bb></span><span class="vpi-moon moon" data-v-87b8a6bb></span><!--]--></span></span></button></div></div></div><!----><!--]--><!--]--></div></div></div><!--[--><!--]--><button type="button" class="VPNavBarHamburger hamburger" aria-label="mobile navigation" aria-expanded="false" aria-controls="VPNavScreen" data-v-c7f322eb data-v-edf597df><span class="container" data-v-edf597df><span class="top" data-v-edf597df></span><span class="middle" data-v-edf597df></span><span class="bottom" data-v-edf597df></span></span></button></div></div></div></div><div class="divider" data-v-c7f322eb><div class="divider-line" data-v-c7f322eb></div></div></div><!----></header><div class="VPLocalNav has-sidebar empty" data-v-990b7706 data-v-054265d6><div class="container" data-v-054265d6><button class="menu" aria-expanded="false" aria-controls="VPSidebarNav" data-v-054265d6><span class="vpi-align-left menu-icon" data-v-054265d6></span><span class="menu-text" data-v-054265d6>Menu</span></button><div class="VPLocalNavOutlineDropdown" style="--vp-vh:0px;" data-v-054265d6 data-v-65e16bd4><button data-v-65e16bd4>Return to top</button><!----></div></div></div><aside class="VPSidebar" data-v-990b7706 data-v-03069692><div class="curtain" data-v-03069692></div><nav class="nav" id="VPSidebarNav" aria-labelledby="sidebar-aria-label" tabindex="-1" data-v-03069692><span class="visually-hidden" id="sidebar-aria-label" data-v-03069692> Sidebar Navigation </span><!--[--><!--]--><!--[--><div class="no-transition group" data-v-53da167f><section class="VPSidebarItem level-0" data-v-53da167f data-v-9a4aac52><div class="item" role="button" tabindex="0" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><h2 class="text" data-v-9a4aac52>Getting started</h2><!----></div><div class="items" data-v-9a4aac52><!--[--><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Overview</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/quickstart.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Quickstart</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/scaffolding-agents.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Scaffold an agent with Cursor</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/guides/convert-automation.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Convert a Cursor Automation</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/concepts.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Concepts</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-53da167f><section class="VPSidebarItem level-0" data-v-53da167f data-v-9a4aac52><div class="item" role="button" tabindex="0" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><h2 class="text" data-v-9a4aac52>Templates</h2><!----></div><div class="items" data-v-9a4aac52><!--[--><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/templates/demo.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Demo agent</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/templates/grokbot-agents.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Grok Bot agents</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/templates/code-wiki.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Code wiki</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/templates/agents-md.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Living AGENTS.md</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/templates/security-reviewer.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Security reviewer</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/templates/security-help.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Security help</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/templates/agentic-owners.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Agentic Owners</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/templates/pr-autofixer.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>PR autofixer</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/templates/triage.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Triage agent</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-53da167f><section class="VPSidebarItem level-0 has-active" data-v-53da167f data-v-9a4aac52><div class="item" role="button" tabindex="0" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><h2 class="text" data-v-9a4aac52>Improving agents</h2><!----></div><div class="items" data-v-9a4aac52><!--[--><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/building-with-agents.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Building agents with agents</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/evals.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Evals</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/storage.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Storage</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/hillclimbing.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Hillclimbing</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-53da167f><section class="VPSidebarItem level-0 collapsible collapsed" data-v-53da167f data-v-9a4aac52><div class="item" role="button" tabindex="0" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><h2 class="text" data-v-9a4aac52>Coding-agent skills</h2><div class="caret" role="button" aria-label="toggle section" tabindex="0" data-v-9a4aac52><span class="vpi-chevron-right caret-icon" data-v-9a4aac52></span></div></div><div class="items" data-v-9a4aac52><!--[--><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/skills/" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Overview</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/skills/create-agent.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>create-agent</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/skills/debug.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>debug</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/skills/deploy.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>deploy</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/skills/evals.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>evals</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/skills/framework-map.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>framework-map</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/skills/github.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>github</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/skills/hillclimb.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>hillclimb</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/skills/mcp-auth.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>mcp-auth</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/skills/otel.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>otel</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/skills/setup-slack.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>setup-slack</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-53da167f><section class="VPSidebarItem level-0" data-v-53da167f data-v-9a4aac52><div class="item" role="button" tabindex="0" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><h2 class="text" data-v-9a4aac52>Guides</h2><!----></div><div class="items" data-v-9a4aac52><!--[--><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/guides/webhooks.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Webhooks & custom channels</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/guides/github.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>GitHub</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/guides/gitlab.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>GitLab</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/guides/bitbucket.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Bitbucket</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/guides/slack.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Slack</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/guides/human-in-the-loop.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Human-in-the-loop approvals</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/guides/agent-to-agent.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Agent-to-agent</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/guides/mcp-oauth.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Host MCP OAuth</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/guides/cloud-agents.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Cursor cloud agents</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/guides/grokbot-agents.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Cursor Grok Bot agents</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/guides/improve.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Self-improvement</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/guides/opentelemetry.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>OpenTelemetry</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-53da167f><section class="VPSidebarItem level-0" data-v-53da167f data-v-9a4aac52><div class="item" role="button" tabindex="0" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><h2 class="text" data-v-9a4aac52>Operating</h2><!----></div><div class="items" data-v-9a4aac52><!--[--><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/deployment.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Deployment</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/troubleshooting.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Fix common problems</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-53da167f><section class="VPSidebarItem level-0 collapsible" data-v-53da167f data-v-9a4aac52><div class="item" role="button" tabindex="0" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><h2 class="text" data-v-9a4aac52>Reference</h2><div class="caret" role="button" aria-label="toggle section" tabindex="0" data-v-9a4aac52><span class="vpi-chevron-right caret-icon" data-v-9a4aac52></span></div></div><div class="items" data-v-9a4aac52><!--[--><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/project-layout.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Project layout</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/agent-config.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Agent config</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/instructions.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Instructions</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/tools.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Tools</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/prompt.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>prompt</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/skills.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Skills</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/connections.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>MCP Connections</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/subagents.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Subagents</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/extensions.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Extensions</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/channels.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Channels</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/schedules.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Schedules & reminders</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/hooks.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Hooks</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/artifacts.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Artifacts</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/result.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Turn result</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/sessions.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Sessions & streaming</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/playground.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Playground</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/cli.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>CLI</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/http-api.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>HTTP API</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><!--]--><!--[--><!--]--></nav></aside><div class="VPContent has-sidebar" id="VPContent" data-v-990b7706 data-v-7a16121a><div class="VPDoc has-sidebar has-aside" data-v-7a16121a data-v-38549ef7><!--[--><!--]--><div class="container" data-v-38549ef7><div class="aside" data-v-38549ef7><div class="aside-curtain" data-v-38549ef7></div><div class="aside-container" data-v-38549ef7><div class="aside-content" data-v-38549ef7><div class="VPDocAside" data-v-38549ef7 data-v-da90486d><!--[--><!--]--><!--[--><!--]--><nav aria-labelledby="doc-outline-aria-label" class="VPDocAsideOutline" data-v-da90486d data-v-0895f2d7><div class="content" data-v-0895f2d7><div class="outline-marker" data-v-0895f2d7></div><div aria-level="2" class="outline-title" id="doc-outline-aria-label" role="heading" data-v-0895f2d7>On this page</div><ul class="VPDocOutlineItem root" data-v-0895f2d7 data-v-0cae2091><!--[--><!--]--></ul></div></nav><!--[--><!--]--><div class="spacer" data-v-da90486d></div><!--[--><!--]--><!----><!--[--><!--]--><!--[--><!--]--></div></div></div></div><div class="content" data-v-38549ef7><div class="content-container" data-v-38549ef7><!--[--><!--]--><main class="main" data-v-38549ef7><div style="position:relative;" class="vp-doc _docs_hillclimbing" data-v-38549ef7><div><h1 id="hillclimbing" tabindex="-1">Hillclimbing <a class="header-anchor" href="#hillclimbing" aria-label="Permalink to &quot;Hillclimbing&quot;">​</a></h1><p>Make an agent better on fixed inputs: measure, change one lever, remeasure, and lock every kept win with an eval.</p><h2 id="what-is-hillclimbing" tabindex="-1">What is hillclimbing? <a class="header-anchor" href="#what-is-hillclimbing" aria-label="Permalink to &quot;What is hillclimbing?&quot;">​</a></h2><p>Hillclimbing is a measured improvement loop. You pin a few fixtures, name the one dominant problem in the run, change one lever, and check the same fixtures again. Keep only what helps. Every kept change lands an <a href="./evals.html">eval</a> so the win stays put.</p><p>You don&#39;t have to run the loop alone. The package ships a coding-agent skill that drives it with you.</p><div class="language-mermaid vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">mermaid</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">flowchart LR</span></span>
24
- <span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> measure[Measure] --&gt; change[Change one lever]</span></span>
25
- <span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> change --&gt; remeasure[Remeasure]</span></span>
26
- <span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> remeasure --&gt; measure</span></span></code></pre></div><h2 id="how-do-i-hillclimb-an-agent-with-a-coding-agent" tabindex="-1">How do I hillclimb an agent with a coding agent? <a class="header-anchor" href="#how-do-i-hillclimb-an-agent-with-a-coding-agent" aria-label="Permalink to &quot;How do I hillclimb an agent with a coding agent?&quot;">​</a></h2><p>Have Cursor read <a href="./skills/hillclimb.html"><code>skills/hillclimb/SKILL.md</code></a>.</p><p>Tell it:</p><ol><li><strong>Which agent</strong> you&#39;re improving (path or slug)</li><li><strong>One to three fixtures</strong> you&#39;ll reuse every round: a PR URL, a saved webhook body, or a canonical chat prompt</li><li><strong>What &quot;better&quot; means</strong> this round: correct tool choice, fewer tools, lower latency, or output quality. Name the freeze line too: API shape, public output, and existing evals that must stay green</li></ol><p>The skill serves the agent, hits your fixtures, reads the session trajectory, proposes one change, remeasures, and checks with you before the next round.</p><p>Other skills cover the edges:</p><table tabindex="0"><thead><tr><th>When you need…</th><th>Skill</th></tr></thead><tbody><tr><td>The measured improvement loop</td><td><a href="./skills/hillclimb.html"><code>skills/hillclimb/SKILL.md</code></a></td></tr><tr><td>An eval that locks a kept win</td><td><a href="./skills/evals.html"><code>skills/evals/SKILL.md</code></a></td></tr><tr><td>Repeatable GitHub webhook inputs</td><td><a href="./skills/github.html"><code>skills/github/SKILL.md</code></a></td></tr><tr><td>A run that misbehaves</td><td><a href="./skills/debug.html"><code>skills/debug/SKILL.md</code></a></td></tr></tbody></table><p>See <a href="./building-with-agents.html">Building agents with agents</a> for every framework skill and a good first prompt.</p><h2 id="what-do-i-need-before-a-hillclimb-round" tabindex="-1">What do I need before a hillclimb round? <a class="header-anchor" href="#what-do-i-need-before-a-hillclimb-round" aria-label="Permalink to &quot;What do I need before a hillclimb round?&quot;">​</a></h2><p>Agree on four things before you edit:</p><ol><li><strong>The target agent</strong>: the project you&#39;re improving</li><li><strong>Fixtures</strong>: one to three fixed inputs you can compare across runs</li><li><strong>Success criteria</strong>: what better means this round</li><li><strong>The freeze line</strong>: what must not change</li></ol><p>Pin the input first. A moving fixture is noise. For GitHub agents, use <code>agent-sdk github replay</code> (see the <a href="./guides/github.html">GitHub guide</a>). For a single tool without a model turn, use <code>agent-sdk call</code>. For a chat turn, use <code>agent-sdk run --dir . --message &quot;…&quot;</code>.</p><h2 id="how-do-i-run-one-hillclimb-round" tabindex="-1">How do I run one hillclimb round? <a class="header-anchor" href="#how-do-i-run-one-hillclimb-round" aria-label="Permalink to &quot;How do I run one hillclimb round?&quot;">​</a></h2><p><strong>Measure.</strong> Hit the agent the way a user would: playground, channel HTTP, or Slack in <code>--dev</code>. Or ask the hillclimb skill to do it. <code>agent-sdk run</code> returns a JSON trajectory and writes a trace under the project state directory.</p><p><strong>Reflect.</strong> Score the trajectory, not impressions. Was the answer right? Did the model thrash (too many tools, fat evidence, grep loops)? Did it invent work the host should have prepared? Name the single dominant problem for this round in one sentence. Example: &quot;Full-file dumps trigger grep loops.&quot;</p><p><strong>Change one lever.</strong> Prefer the smallest change that addresses that problem:</p><ol><li>Host prep: seed what the model needs so it doesn&#39;t hunt</li><li>Evidence shape: trim or reorder artifacts</li><li>Instructions and skills: tighten the procedure</li><li>Tool surface: remove or gate tools that invite wandering</li><li>Framework changes: only when the agent can&#39;t express the fix</li></ol><p><strong>Remeasure.</strong> Same fixtures. Diff tools, wall time, and quality side by side. Keep the change only if the target metric improves and the freeze line holds.</p><h2 id="how-do-i-lock-a-hillclimb-improvement-with-an-eval" tabindex="-1">How do I lock a hillclimb improvement with an eval? <a class="header-anchor" href="#how-do-i-lock-a-hillclimb-improvement-with-an-eval" aria-label="Permalink to &quot;How do I lock a hillclimb improvement with an eval?&quot;">​</a></h2><p>Every kept change needs an eval that would have failed before the change: a tool-choice gate, a <code>maxToolCalls</code> bound, or an output-shape check. Run <code>agent-sdk eval --dir . --json</code> between rounds. Never weaken an existing gate to pass the round.</p><p>Details live in <a href="./evals.html#keep-improvements-with-regression-evals">Keep improvements with regression evals</a>. The evals skill will author the case with you.</p><h2 id="what-habits-help-hillclimbing-stay-reliable" tabindex="-1">What habits help hillclimbing stay reliable? <a class="header-anchor" href="#what-habits-help-hillclimbing-stay-reliable" aria-label="Permalink to &quot;What habits help hillclimbing stay reliable?&quot;">​</a></h2><ul><li>One problem per round. Don&#39;t bundle &quot;trim evidence and rewrite instructions&quot; unless you chose that on purpose.</li><li>Keep fixtures fixed until you deliberately need a harder case.</li><li>Separate host work from model tools when you blame latency. Moving deterministic prep onto the host is often the biggest win. In one PR reviewer, host-prepared evidence cut turns from about 8 minutes to about 1 minute.</li><li>Spot-check quality on at least one fixture against a known-good answer. Efficiency-only climbs quietly drop findings.</li><li>Treat <code>turn.failed</code> with <code>&quot;turn interrupted&quot;</code> as expected when a follow-up or stop preempted the turn.</li><li>Don&#39;t deploy, post to real surfaces, or weaken evals as part of a climb.</li></ul><h2 id="related" tabindex="-1">Related <a class="header-anchor" href="#related" aria-label="Permalink to &quot;Related&quot;">​</a></h2><ul><li><a href="./evals.html">Evals</a></li><li><a href="./building-with-agents.html">Building agents with agents</a></li><li><a href="./guides/github.html">GitHub guide</a></li><li><a href="./troubleshooting.html">Fix common agent problems</a></li></ul></div></div></main><footer class="VPDocFooter" data-v-38549ef7 data-v-215f93e6><!--[--><!--]--><!----><nav class="prev-next" aria-labelledby="doc-footer-aria-label" data-v-215f93e6><span class="visually-hidden" id="doc-footer-aria-label" data-v-215f93e6>Pager</span><div class="pager" data-v-215f93e6><a class="VPLink link pager-link prev" href="/docs/storage.html" data-v-215f93e6><!--[--><span class="desc" data-v-215f93e6>Previous page</span><span class="title" data-v-215f93e6>Storage</span><!--]--></a></div><div class="pager" data-v-215f93e6><a class="VPLink link pager-link next" href="/docs/skills/" data-v-215f93e6><!--[--><span class="desc" data-v-215f93e6>Next page</span><span class="title" data-v-215f93e6>Overview</span><!--]--></a></div></nav></footer><!--[--><!--]--></div></div></div><!--[--><!--]--></div></div><!----><!--[--><!--]--></div></div>
27
- <script>window.__VP_HASH_MAP__=JSON.parse("{\"building-with-agents.md\":\"D0KbSkJn\",\"concepts.md\":\"B4o63Gul\",\"deployment.md\":\"JenwuCCB\",\"evals.md\":\"C7JLjoEP\",\"guides_agent-to-agent.md\":\"BDb0t1QV\",\"guides_bitbucket.md\":\"DZPzmUjU\",\"guides_cloud-agents.md\":\"BsloyHdY\",\"guides_convert-automation.md\":\"B4sjlodG\",\"guides_github.md\":\"TZaTZlfz\",\"guides_gitlab.md\":\"BmqwQfdG\",\"guides_grokbot-agents.md\":\"DyV-WArv\",\"guides_human-in-the-loop.md\":\"By1G2T3_\",\"guides_improve.md\":\"BGVk32bK\",\"guides_mcp-oauth.md\":\"Dp6cDP7f\",\"guides_opentelemetry.md\":\"SCRMskno\",\"guides_slack.md\":\"D4RVMM4G\",\"guides_webhooks.md\":\"CJK484ex\",\"hillclimbing.md\":\"BOiVo1tf\",\"index.md\":\"DD9Q2XuJ\",\"quickstart.md\":\"DdQOF7Y8\",\"reference_agent-config.md\":\"CvoL6pof\",\"reference_artifacts.md\":\"Dior32Qw\",\"reference_channels.md\":\"CAo-iK4j\",\"reference_cli.md\":\"Deg7849l\",\"reference_connections.md\":\"BojkC6c5\",\"reference_extensions.md\":\"ZAVUyuEX\",\"reference_hooks.md\":\"BlM_bOg6\",\"reference_http-api.md\":\"BwaCo-VO\",\"reference_instructions.md\":\"CR7XSsGk\",\"reference_playground.md\":\"DLnoaczX\",\"reference_project-layout.md\":\"BEU8MtQV\",\"reference_prompt.md\":\"DnaD5dNK\",\"reference_result.md\":\"BK5SxDrf\",\"reference_schedules.md\":\"DI_JrHgq\",\"reference_sessions.md\":\"CyXV1MUw\",\"reference_skills.md\":\"l2ezAcaN\",\"reference_subagents.md\":\"CfsIloPm\",\"reference_tools.md\":\"aGrn99hP\",\"scaffolding-agents.md\":\"Kctn3OVb\",\"skills_create-agent.md\":\"Q3h6Je-e\",\"skills_debug.md\":\"CVjCXMFF\",\"skills_deploy.md\":\"CWqi_ZxW\",\"skills_evals.md\":\"DFxYPErF\",\"skills_framework-map.md\":\"BxLSOhSY\",\"skills_github.md\":\"hgFX_oKY\",\"skills_hillclimb.md\":\"B_zJerxA\",\"skills_index.md\":\"DL7EHaQ-\",\"skills_mcp-auth.md\":\"DGvFP3HE\",\"skills_otel.md\":\"B5Ddv1xH\",\"skills_setup-slack.md\":\"BBgx8lUz\",\"storage.md\":\"BUrhJ-Zz\",\"templates_agentic-owners.md\":\"BZSH4N9z\",\"templates_agents-md.md\":\"CXSMZljE\",\"templates_code-wiki.md\":\"CDYZIBFN\",\"templates_demo.md\":\"BeQX9V3H\",\"templates_grokbot-agents.md\":\"c1s6Flp9\",\"templates_pr-autofixer.md\":\"Bds_XWcV\",\"templates_security-help.md\":\"C3Ny_Qr2\",\"templates_security-reviewer.md\":\"lshxbCLK\",\"templates_triage.md\":\"Co4UNzkZ\",\"troubleshooting.md\":\"CYEAO9bM\"}");window.__VP_SITE_DATA__=JSON.parse("{\"lang\":\"en-US\",\"dir\":\"ltr\",\"title\":\"Agent SDK\",\"description\":\"Filesystem-first framework for building and serving Cursor agents.\",\"base\":\"/docs/\",\"head\":[],\"router\":{\"prefetchLinks\":true},\"appearance\":true,\"themeConfig\":{\"sdkVersion\":\"0.1.109\",\"nav\":[{\"text\":\"Quickstart\",\"link\":\"/quickstart\"},{\"text\":\"Guides\",\"link\":\"/guides/webhooks\"},{\"text\":\"Templates\",\"link\":\"/templates/demo\"},{\"text\":\"Reference\",\"link\":\"/reference/project-layout\"}],\"search\":{\"provider\":\"local\"},\"outline\":{\"level\":[2,3]},\"sidebar\":[{\"text\":\"Getting started\",\"items\":[{\"text\":\"Overview\",\"link\":\"/\"},{\"text\":\"Quickstart\",\"link\":\"/quickstart\"},{\"text\":\"Scaffold an agent with Cursor\",\"link\":\"/scaffolding-agents\"},{\"text\":\"Convert a Cursor Automation\",\"link\":\"/guides/convert-automation\"},{\"text\":\"Concepts\",\"link\":\"/concepts\"}]},{\"text\":\"Templates\",\"items\":[{\"text\":\"Demo agent\",\"link\":\"/templates/demo\"},{\"text\":\"Grok Bot agents\",\"link\":\"/templates/grokbot-agents\"},{\"text\":\"Code wiki\",\"link\":\"/templates/code-wiki\"},{\"text\":\"Living AGENTS.md\",\"link\":\"/templates/agents-md\"},{\"text\":\"Security reviewer\",\"link\":\"/templates/security-reviewer\"},{\"text\":\"Security help\",\"link\":\"/templates/security-help\"},{\"text\":\"Agentic Owners\",\"link\":\"/templates/agentic-owners\"},{\"text\":\"PR autofixer\",\"link\":\"/templates/pr-autofixer\"},{\"text\":\"Triage agent\",\"link\":\"/templates/triage\"}]},{\"text\":\"Improving agents\",\"items\":[{\"text\":\"Building agents with agents\",\"link\":\"/building-with-agents\"},{\"text\":\"Evals\",\"link\":\"/evals\"},{\"text\":\"Storage\",\"link\":\"/storage\"},{\"text\":\"Hillclimbing\",\"link\":\"/hillclimbing\"}]},{\"text\":\"Coding-agent skills\",\"collapsed\":true,\"items\":[{\"text\":\"Overview\",\"link\":\"/skills/\"},{\"text\":\"create-agent\",\"link\":\"/skills/create-agent\"},{\"text\":\"debug\",\"link\":\"/skills/debug\"},{\"text\":\"deploy\",\"link\":\"/skills/deploy\"},{\"text\":\"evals\",\"link\":\"/skills/evals\"},{\"text\":\"framework-map\",\"link\":\"/skills/framework-map\"},{\"text\":\"github\",\"link\":\"/skills/github\"},{\"text\":\"hillclimb\",\"link\":\"/skills/hillclimb\"},{\"text\":\"mcp-auth\",\"link\":\"/skills/mcp-auth\"},{\"text\":\"otel\",\"link\":\"/skills/otel\"},{\"text\":\"setup-slack\",\"link\":\"/skills/setup-slack\"}]},{\"text\":\"Guides\",\"items\":[{\"text\":\"Webhooks & custom channels\",\"link\":\"/guides/webhooks\"},{\"text\":\"GitHub\",\"link\":\"/guides/github\"},{\"text\":\"GitLab\",\"link\":\"/guides/gitlab\"},{\"text\":\"Bitbucket\",\"link\":\"/guides/bitbucket\"},{\"text\":\"Slack\",\"link\":\"/guides/slack\"},{\"text\":\"Human-in-the-loop approvals\",\"link\":\"/guides/human-in-the-loop\"},{\"text\":\"Agent-to-agent\",\"link\":\"/guides/agent-to-agent\"},{\"text\":\"Host MCP OAuth\",\"link\":\"/guides/mcp-oauth\"},{\"text\":\"Cursor cloud agents\",\"link\":\"/guides/cloud-agents\"},{\"text\":\"Cursor Grok Bot agents\",\"link\":\"/guides/grokbot-agents\"},{\"text\":\"Self-improvement\",\"link\":\"/guides/improve\"},{\"text\":\"OpenTelemetry\",\"link\":\"/guides/opentelemetry\"}]},{\"text\":\"Operating\",\"items\":[{\"text\":\"Deployment\",\"link\":\"/deployment\"},{\"text\":\"Fix common problems\",\"link\":\"/troubleshooting\"}]},{\"text\":\"Reference\",\"collapsed\":false,\"items\":[{\"text\":\"Project layout\",\"link\":\"/reference/project-layout\"},{\"text\":\"Agent config\",\"link\":\"/reference/agent-config\"},{\"text\":\"Instructions\",\"link\":\"/reference/instructions\"},{\"text\":\"Tools\",\"link\":\"/reference/tools\"},{\"text\":\"prompt\",\"link\":\"/reference/prompt\"},{\"text\":\"Skills\",\"link\":\"/reference/skills\"},{\"text\":\"MCP Connections\",\"link\":\"/reference/connections\"},{\"text\":\"Subagents\",\"link\":\"/reference/subagents\"},{\"text\":\"Extensions\",\"link\":\"/reference/extensions\"},{\"text\":\"Channels\",\"link\":\"/reference/channels\"},{\"text\":\"Schedules & reminders\",\"link\":\"/reference/schedules\"},{\"text\":\"Hooks\",\"link\":\"/reference/hooks\"},{\"text\":\"Artifacts\",\"link\":\"/reference/artifacts\"},{\"text\":\"Turn result\",\"link\":\"/reference/result\"},{\"text\":\"Sessions & streaming\",\"link\":\"/reference/sessions\"},{\"text\":\"Playground\",\"link\":\"/reference/playground\"},{\"text\":\"CLI\",\"link\":\"/reference/cli\"},{\"text\":\"HTTP API\",\"link\":\"/reference/http-api\"}]}]},\"locales\":{},\"scrollOffset\":134,\"cleanUrls\":false}");</script>
56
+ <div id="app"><div class="Layout" data-v-76086e96><!--[--><!--]--><!--[--><span tabindex="-1" data-v-97fb5898></span><a href="#VPContent" class="VPSkipLink visually-hidden" data-v-97fb5898>Skip to content</a><!--]--><!----><header class="VPNav" data-v-76086e96 data-v-781b1279><div class="VPNavBar" data-v-781b1279 data-v-b33015df><div class="wrapper" data-v-b33015df><div class="container" data-v-b33015df><div class="title" data-v-b33015df><div class="VPNavBarTitle has-sidebar" data-v-b33015df data-v-a0c466dc><a class="title" href="/docs/" data-v-a0c466dc><!--[--><!--]--><!----><span data-v-a0c466dc>Agent SDK</span><!--[--><!--[--><!--[--><!--[--><span class="agent-sdk-version" title="@cursor/july 0.1.112" data-v-97e8f22b>0.1.112</span><!--]--><!--]--><!--]--><!--]--></a></div></div><div class="content" data-v-b33015df><div class="content-body" data-v-b33015df><!--[--><!--]--><div class="VPNavBarSearch search" data-v-b33015df><!--[--><!----><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-b33015df data-v-8906c751><span id="main-nav-aria-label" class="visually-hidden" data-v-8906c751> Main Navigation </span><!--[--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/quickstart.html" tabindex="0" data-v-8906c751 data-v-e9bcc08e><!--[--><span data-v-e9bcc08e>Quickstart</span><!--]--></a><!--]--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/guides/mcp-oauth.html" tabindex="0" data-v-8906c751 data-v-e9bcc08e><!--[--><span data-v-e9bcc08e>Guides</span><!--]--></a><!--]--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/guides/github.html" tabindex="0" data-v-8906c751 data-v-e9bcc08e><!--[--><span data-v-e9bcc08e>Integrations</span><!--]--></a><!--]--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/templates/security-reviewer.html" tabindex="0" data-v-8906c751 data-v-e9bcc08e><!--[--><span data-v-e9bcc08e>Templates</span><!--]--></a><!--]--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/reference/project-layout.html" tabindex="0" data-v-8906c751 data-v-e9bcc08e><!--[--><span data-v-e9bcc08e>Reference</span><!--]--></a><!--]--><!--]--></nav><!----><div class="VPNavBarAppearance appearance" data-v-b33015df data-v-959ed110><button class="VPSwitch VPSwitchAppearance" type="button" role="switch" title aria-checked="false" data-v-959ed110 data-v-79ad6d7f data-v-0a895de9><span class="check" data-v-0a895de9><span class="icon" data-v-0a895de9><!--[--><span class="vpi-sun sun" data-v-79ad6d7f></span><span class="vpi-moon moon" data-v-79ad6d7f></span><!--]--></span></span></button></div><!----><div class="VPFlyout VPNavBarExtra extra" data-v-b33015df data-v-a713f501 data-v-1d7aa189><button type="button" class="button" aria-haspopup="true" aria-expanded="false" aria-label="extra navigation" data-v-1d7aa189><span class="vpi-more-horizontal icon" data-v-1d7aa189></span></button><div class="menu" data-v-1d7aa189><div class="VPMenu" data-v-1d7aa189 data-v-e34b7e14><!----><!--[--><!--[--><!----><div class="group" data-v-a713f501><div class="item appearance" data-v-a713f501><p class="label" data-v-a713f501>Appearance</p><div class="appearance-action" data-v-a713f501><button class="VPSwitch VPSwitchAppearance" type="button" role="switch" title aria-checked="false" data-v-a713f501 data-v-79ad6d7f data-v-0a895de9><span class="check" data-v-0a895de9><span class="icon" data-v-0a895de9><!--[--><span class="vpi-sun sun" data-v-79ad6d7f></span><span class="vpi-moon moon" data-v-79ad6d7f></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-b33015df data-v-cb5d0edb><span class="container" data-v-cb5d0edb><span class="top" data-v-cb5d0edb></span><span class="middle" data-v-cb5d0edb></span><span class="bottom" data-v-cb5d0edb></span></span></button></div></div></div></div><div class="divider" data-v-b33015df><div class="divider-line" data-v-b33015df></div></div></div><!----></header><div class="VPLocalNav has-sidebar empty" data-v-76086e96 data-v-6f794310><div class="container" data-v-6f794310><button class="menu" aria-expanded="false" aria-controls="VPSidebarNav" data-v-6f794310><span class="vpi-align-left menu-icon" data-v-6f794310></span><span class="menu-text" data-v-6f794310>Menu</span></button><div class="VPLocalNavOutlineDropdown" style="--vp-vh:0px;" data-v-6f794310 data-v-bab84d9c><button data-v-bab84d9c>Return to top</button><!----></div></div></div><aside class="VPSidebar" data-v-76086e96 data-v-4daa293d><div class="curtain" data-v-4daa293d></div><nav class="nav" id="VPSidebarNav" aria-labelledby="sidebar-aria-label" tabindex="-1" data-v-4daa293d><span class="visually-hidden" id="sidebar-aria-label" data-v-4daa293d> Sidebar Navigation </span><!--[--><!--]--><!--[--><div class="no-transition group" data-v-095feacd><section class="VPSidebarItem level-0" data-v-095feacd data-v-d79cbf7e><div class="item" role="button" tabindex="0" data-v-d79cbf7e><div class="indicator" data-v-d79cbf7e></div><h2 class="text" data-v-d79cbf7e>Getting started</h2><!----></div><div class="items" data-v-d79cbf7e><!--[--><div class="VPSidebarItem level-1 is-link" data-v-d79cbf7e><div class="item" data-v-d79cbf7e><div class="indicator" data-v-d79cbf7e></div><a class="VPLink link link" href="/docs/" data-v-d79cbf7e><!--[--><p class="text" data-v-d79cbf7e>Overview</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-d79cbf7e><div class="item" data-v-d79cbf7e><div class="indicator" data-v-d79cbf7e></div><a class="VPLink link link" href="/docs/quickstart.html" data-v-d79cbf7e><!--[--><p class="text" data-v-d79cbf7e>Building your first agent</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-095feacd><section class="VPSidebarItem level-0 collapsible" data-v-095feacd data-v-d79cbf7e><div class="item" role="button" tabindex="0" data-v-d79cbf7e><div class="indicator" data-v-d79cbf7e></div><h2 class="text" data-v-d79cbf7e>Integrations</h2><div class="caret" role="button" aria-label="toggle section" tabindex="0" data-v-d79cbf7e><span class="vpi-chevron-right caret-icon" data-v-d79cbf7e></span></div></div><div class="items" data-v-d79cbf7e><!--[--><div class="VPSidebarItem level-1 is-link" data-v-d79cbf7e><div class="item" data-v-d79cbf7e><div class="indicator" data-v-d79cbf7e></div><a class="VPLink link link" href="/docs/guides/github.html" data-v-d79cbf7e><!--[--><p class="text" data-v-d79cbf7e>GitHub</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-d79cbf7e><div class="item" data-v-d79cbf7e><div class="indicator" data-v-d79cbf7e></div><a class="VPLink link link" href="/docs/guides/slack.html" data-v-d79cbf7e><!--[--><p class="text" data-v-d79cbf7e>Slack</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-d79cbf7e><div class="item" data-v-d79cbf7e><div class="indicator" data-v-d79cbf7e></div><a class="VPLink link link" href="/docs/guides/webhooks.html" data-v-d79cbf7e><!--[--><p class="text" data-v-d79cbf7e>Webhooks</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-d79cbf7e><div class="item" data-v-d79cbf7e><div class="indicator" data-v-d79cbf7e></div><a class="VPLink link link" href="/docs/guides/convert-automation.html" data-v-d79cbf7e><!--[--><p class="text" data-v-d79cbf7e>Cursor Automations</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-d79cbf7e><div class="item" data-v-d79cbf7e><div class="indicator" data-v-d79cbf7e></div><a class="VPLink link link" href="/docs/guides/opentelemetry.html" data-v-d79cbf7e><!--[--><p class="text" data-v-d79cbf7e>OpenTelemetry</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-d79cbf7e><div class="item" data-v-d79cbf7e><div class="indicator" data-v-d79cbf7e></div><a class="VPLink link link" href="/docs/guides/gitlab.html" data-v-d79cbf7e><!--[--><p class="text" data-v-d79cbf7e>GitLab</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-d79cbf7e><div class="item" data-v-d79cbf7e><div class="indicator" data-v-d79cbf7e></div><a class="VPLink link link" href="/docs/guides/bitbucket.html" data-v-d79cbf7e><!--[--><p class="text" data-v-d79cbf7e>Bitbucket</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-095feacd><section class="VPSidebarItem level-0 collapsible" data-v-095feacd data-v-d79cbf7e><div class="item" role="button" tabindex="0" data-v-d79cbf7e><div class="indicator" data-v-d79cbf7e></div><h2 class="text" data-v-d79cbf7e>Extensions</h2><div class="caret" role="button" aria-label="toggle section" tabindex="0" data-v-d79cbf7e><span class="vpi-chevron-right caret-icon" data-v-d79cbf7e></span></div></div><div class="items" data-v-d79cbf7e><!--[--><div class="VPSidebarItem level-1 is-link" data-v-d79cbf7e><div class="item" data-v-d79cbf7e><div class="indicator" data-v-d79cbf7e></div><a class="VPLink link link" href="/docs/reference/extensions.html" data-v-d79cbf7e><!--[--><p class="text" data-v-d79cbf7e>Overview</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-d79cbf7e><div class="item" data-v-d79cbf7e><div class="indicator" data-v-d79cbf7e></div><a class="VPLink link link" href="/docs/guides/cloud-agents.html" data-v-d79cbf7e><!--[--><p class="text" data-v-d79cbf7e>Cloud agents</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-d79cbf7e><div class="item" data-v-d79cbf7e><div class="indicator" data-v-d79cbf7e></div><a class="VPLink link link" href="/docs/guides/grokbot-agents.html" data-v-d79cbf7e><!--[--><p class="text" data-v-d79cbf7e>Grok Bot agents</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-d79cbf7e><div class="item" data-v-d79cbf7e><div class="indicator" data-v-d79cbf7e></div><a class="VPLink link link" href="/docs/guides/improve.html" data-v-d79cbf7e><!--[--><p class="text" data-v-d79cbf7e>Self-improvement</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-095feacd><section class="VPSidebarItem level-0 collapsible has-active" data-v-095feacd data-v-d79cbf7e><div class="item" role="button" tabindex="0" data-v-d79cbf7e><div class="indicator" data-v-d79cbf7e></div><h2 class="text" data-v-d79cbf7e>Guides</h2><div class="caret" role="button" aria-label="toggle section" tabindex="0" data-v-d79cbf7e><span class="vpi-chevron-right caret-icon" data-v-d79cbf7e></span></div></div><div class="items" data-v-d79cbf7e><!--[--><div class="VPSidebarItem level-1 is-link" data-v-d79cbf7e><div class="item" data-v-d79cbf7e><div class="indicator" data-v-d79cbf7e></div><a class="VPLink link link" href="/docs/guides/mcp-oauth.html" data-v-d79cbf7e><!--[--><p class="text" data-v-d79cbf7e>MCP</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-d79cbf7e><div class="item" data-v-d79cbf7e><div class="indicator" data-v-d79cbf7e></div><a class="VPLink link link" href="/docs/guides/agent-to-agent.html" data-v-d79cbf7e><!--[--><p class="text" data-v-d79cbf7e>Agent-to-agent</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-d79cbf7e><div class="item" data-v-d79cbf7e><div class="indicator" data-v-d79cbf7e></div><a class="VPLink link link" href="/docs/deployment.html" data-v-d79cbf7e><!--[--><p class="text" data-v-d79cbf7e>Deployment</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-d79cbf7e><div class="item" data-v-d79cbf7e><div class="indicator" data-v-d79cbf7e></div><a class="VPLink link link" href="/docs/evals.html" data-v-d79cbf7e><!--[--><p class="text" data-v-d79cbf7e>Evals</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-d79cbf7e><div class="item" data-v-d79cbf7e><div class="indicator" data-v-d79cbf7e></div><a class="VPLink link link" href="/docs/hillclimbing.html" data-v-d79cbf7e><!--[--><p class="text" data-v-d79cbf7e>Hillclimbing</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-d79cbf7e><div class="item" data-v-d79cbf7e><div class="indicator" data-v-d79cbf7e></div><a class="VPLink link link" href="/docs/building-with-agents.html" data-v-d79cbf7e><!--[--><p class="text" data-v-d79cbf7e>Build with a coding agent</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-d79cbf7e><div class="item" data-v-d79cbf7e><div class="indicator" data-v-d79cbf7e></div><a class="VPLink link link" href="/docs/troubleshooting.html" data-v-d79cbf7e><!--[--><p class="text" data-v-d79cbf7e>Troubleshooting</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-095feacd><section class="VPSidebarItem level-0 collapsible" data-v-095feacd data-v-d79cbf7e><div class="item" role="button" tabindex="0" data-v-d79cbf7e><div class="indicator" data-v-d79cbf7e></div><h2 class="text" data-v-d79cbf7e>Templates</h2><div class="caret" role="button" aria-label="toggle section" tabindex="0" data-v-d79cbf7e><span class="vpi-chevron-right caret-icon" data-v-d79cbf7e></span></div></div><div class="items" data-v-d79cbf7e><!--[--><div class="VPSidebarItem level-1 is-link" data-v-d79cbf7e><div class="item" data-v-d79cbf7e><div class="indicator" data-v-d79cbf7e></div><a class="VPLink link link" href="/docs/templates/security-reviewer.html" data-v-d79cbf7e><!--[--><p class="text" data-v-d79cbf7e>Security reviewer</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-d79cbf7e><div class="item" data-v-d79cbf7e><div class="indicator" data-v-d79cbf7e></div><a class="VPLink link link" href="/docs/templates/thermo-review.html" data-v-d79cbf7e><!--[--><p class="text" data-v-d79cbf7e>Thermo review</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-d79cbf7e><div class="item" data-v-d79cbf7e><div class="indicator" data-v-d79cbf7e></div><a class="VPLink link link" href="/docs/templates/thermo-quality-review.html" data-v-d79cbf7e><!--[--><p class="text" data-v-d79cbf7e>Thermo quality review</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-d79cbf7e><div class="item" data-v-d79cbf7e><div class="indicator" data-v-d79cbf7e></div><a class="VPLink link link" href="/docs/templates/agentic-owners.html" data-v-d79cbf7e><!--[--><p class="text" data-v-d79cbf7e>Agentic Approver</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-d79cbf7e><div class="item" data-v-d79cbf7e><div class="indicator" data-v-d79cbf7e></div><a class="VPLink link link" href="/docs/templates/pr-autofixer.html" data-v-d79cbf7e><!--[--><p class="text" data-v-d79cbf7e>PR autofixer</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-d79cbf7e><div class="item" data-v-d79cbf7e><div class="indicator" data-v-d79cbf7e></div><a class="VPLink link link" href="/docs/templates/triage.html" data-v-d79cbf7e><!--[--><p class="text" data-v-d79cbf7e>Triage agent</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-095feacd><section class="VPSidebarItem level-0 collapsible" data-v-095feacd data-v-d79cbf7e><div class="item" role="button" tabindex="0" data-v-d79cbf7e><div class="indicator" data-v-d79cbf7e></div><h2 class="text" data-v-d79cbf7e>Reference</h2><div class="caret" role="button" aria-label="toggle section" tabindex="0" data-v-d79cbf7e><span class="vpi-chevron-right caret-icon" data-v-d79cbf7e></span></div></div><div class="items" data-v-d79cbf7e><!--[--><div class="VPSidebarItem level-1 is-link" data-v-d79cbf7e><div class="item" data-v-d79cbf7e><div class="indicator" data-v-d79cbf7e></div><a class="VPLink link link" href="/docs/reference/project-layout.html" data-v-d79cbf7e><!--[--><p class="text" data-v-d79cbf7e>Project layout</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-d79cbf7e><div class="item" data-v-d79cbf7e><div class="indicator" data-v-d79cbf7e></div><a class="VPLink link link" href="/docs/reference/agent-config.html" data-v-d79cbf7e><!--[--><p class="text" data-v-d79cbf7e>Agent config</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-d79cbf7e><div class="item" data-v-d79cbf7e><div class="indicator" data-v-d79cbf7e></div><a class="VPLink link link" href="/docs/reference/instructions.html" data-v-d79cbf7e><!--[--><p class="text" data-v-d79cbf7e>Instructions</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-d79cbf7e><div class="item" data-v-d79cbf7e><div class="indicator" data-v-d79cbf7e></div><a class="VPLink link link" href="/docs/reference/tools.html" data-v-d79cbf7e><!--[--><p class="text" data-v-d79cbf7e>Tools</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-d79cbf7e><div class="item" data-v-d79cbf7e><div class="indicator" data-v-d79cbf7e></div><a class="VPLink link link" href="/docs/reference/prompt.html" data-v-d79cbf7e><!--[--><p class="text" data-v-d79cbf7e>prompt</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-d79cbf7e><div class="item" data-v-d79cbf7e><div class="indicator" data-v-d79cbf7e></div><a class="VPLink link link" href="/docs/reference/skills.html" data-v-d79cbf7e><!--[--><p class="text" data-v-d79cbf7e>Skills</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-d79cbf7e><div class="item" data-v-d79cbf7e><div class="indicator" data-v-d79cbf7e></div><a class="VPLink link link" href="/docs/reference/connections.html" data-v-d79cbf7e><!--[--><p class="text" data-v-d79cbf7e>MCP Connections</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-d79cbf7e><div class="item" data-v-d79cbf7e><div class="indicator" data-v-d79cbf7e></div><a class="VPLink link link" href="/docs/reference/subagents.html" data-v-d79cbf7e><!--[--><p class="text" data-v-d79cbf7e>Subagents</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-d79cbf7e><div class="item" data-v-d79cbf7e><div class="indicator" data-v-d79cbf7e></div><a class="VPLink link link" href="/docs/reference/channels.html" data-v-d79cbf7e><!--[--><p class="text" data-v-d79cbf7e>Channels</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-d79cbf7e><div class="item" data-v-d79cbf7e><div class="indicator" data-v-d79cbf7e></div><a class="VPLink link link" href="/docs/reference/schedules.html" data-v-d79cbf7e><!--[--><p class="text" data-v-d79cbf7e>Schedules & reminders</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-d79cbf7e><div class="item" data-v-d79cbf7e><div class="indicator" data-v-d79cbf7e></div><a class="VPLink link link" href="/docs/reference/hooks.html" data-v-d79cbf7e><!--[--><p class="text" data-v-d79cbf7e>Hooks</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-d79cbf7e><div class="item" data-v-d79cbf7e><div class="indicator" data-v-d79cbf7e></div><a class="VPLink link link" href="/docs/reference/evals.html" data-v-d79cbf7e><!--[--><p class="text" data-v-d79cbf7e>Evals</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-d79cbf7e><div class="item" data-v-d79cbf7e><div class="indicator" data-v-d79cbf7e></div><a class="VPLink link link" href="/docs/reference/artifacts.html" data-v-d79cbf7e><!--[--><p class="text" data-v-d79cbf7e>Artifacts</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-d79cbf7e><div class="item" data-v-d79cbf7e><div class="indicator" data-v-d79cbf7e></div><a class="VPLink link link" href="/docs/reference/sessions.html" data-v-d79cbf7e><!--[--><p class="text" data-v-d79cbf7e>Sessions & streaming</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-d79cbf7e><div class="item" data-v-d79cbf7e><div class="indicator" data-v-d79cbf7e></div><a class="VPLink link link" href="/docs/reference/playground.html" data-v-d79cbf7e><!--[--><p class="text" data-v-d79cbf7e>Playground</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-d79cbf7e><div class="item" data-v-d79cbf7e><div class="indicator" data-v-d79cbf7e></div><a class="VPLink link link" href="/docs/reference/cli.html" data-v-d79cbf7e><!--[--><p class="text" data-v-d79cbf7e>CLI</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-d79cbf7e><div class="item" data-v-d79cbf7e><div class="indicator" data-v-d79cbf7e></div><a class="VPLink link link" href="/docs/reference/http-api.html" data-v-d79cbf7e><!--[--><p class="text" data-v-d79cbf7e>HTTP API</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><!--]--><!--[--><!--]--></nav></aside><div class="VPContent has-sidebar" id="VPContent" data-v-76086e96 data-v-258cbba4><div class="VPDoc has-sidebar has-aside" data-v-258cbba4 data-v-afe580da><!--[--><!--]--><div class="container" data-v-afe580da><div class="aside" data-v-afe580da><div class="aside-curtain" data-v-afe580da></div><div class="aside-container" data-v-afe580da><div class="aside-content" data-v-afe580da><div class="VPDocAside" data-v-afe580da data-v-fb5275a4><!--[--><!--]--><!--[--><!--]--><nav aria-labelledby="doc-outline-aria-label" class="VPDocAsideOutline" data-v-fb5275a4 data-v-b3783f18><div class="content" data-v-b3783f18><div class="outline-marker" data-v-b3783f18></div><div aria-level="2" class="outline-title" id="doc-outline-aria-label" role="heading" data-v-b3783f18>On this page</div><ul class="VPDocOutlineItem root" data-v-b3783f18 data-v-72702c6e><!--[--><!--]--></ul></div></nav><!--[--><!--]--><div class="spacer" data-v-fb5275a4></div><!--[--><!--]--><!----><!--[--><!--]--><!--[--><!--]--></div></div></div></div><div class="content" data-v-afe580da><div class="content-container" data-v-afe580da><!--[--><!--]--><main class="main" data-v-afe580da><div style="position:relative;" class="vp-doc _docs_hillclimbing" data-v-afe580da><div><h1 id="hillclimbing" tabindex="-1">Hillclimbing <a class="header-anchor" href="#hillclimbing" aria-label="Permalink to &quot;Hillclimbing&quot;">​</a></h1><p>Hillclimbing improves an agent through controlled before-and-after comparisons. Keep the inputs fixed, name one failure, change one lever, and retain the change only when the same run gets better without crossing the freeze line.</p><p>The companion <a href="./../skills/hillclimb/SKILL.html"><code>hillclimb</code> skill</a> can run this loop with you.</p><h2 id="correct-a-wrong-tool-choice" tabindex="-1">Correct a wrong tool choice <a class="header-anchor" href="#correct-a-wrong-tool-choice" aria-label="Permalink to &quot;Correct a wrong tool choice&quot;">​</a></h2><p>Suppose a PR reviewer calls <code>approve_pr</code> before <code>inspect_pr</code>. Pin one PR fixture, record the original tool order, then tighten the instruction that owns the decision. The improved run should inspect first and leave approval untouched.</p><div class="language-bash vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">bash</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#6F42C1;--shiki-dark:#B392F0;">agent-sdk</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;"> run</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> --dir</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;"> .</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> \</span></span>
57
+ <span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> --message</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;"> &quot;Is https://github.com/acme/checkout/pull/42 ready?&quot;</span></span></code></pre></div><p>Lock the result with the intended and tempting-wrong paths:</p><div class="language-ts vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">ts</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">t.</span><span style="--shiki-light:#6F42C1;--shiki-dark:#B392F0;">succeeded</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">();</span></span>
58
+ <span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">t.</span><span style="--shiki-light:#6F42C1;--shiki-dark:#B392F0;">calledTool</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">(</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">&quot;inspect_pr&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">);</span></span>
59
+ <span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">t.</span><span style="--shiki-light:#6F42C1;--shiki-dark:#B392F0;">notCalledTool</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">(</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">&quot;approve_pr&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">);</span></span></code></pre></div><p>Do not change the tool implementation, prompt, and evidence together. If tool choice improves, you should know which edit caused it.</p><h2 id="reduce-wandering-or-latency" tabindex="-1">Reduce wandering or latency <a class="header-anchor" href="#reduce-wandering-or-latency" aria-label="Permalink to &quot;Reduce wandering or latency&quot;">​</a></h2><p>A slow run often repeats reads, searches broad directories, or asks the model to discover evidence the host already has. Compare the trajectory by tool name and wall time, then move deterministic preparation ahead of the turn or trim the evidence shape.</p><div class="language-text vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">text</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span>before: 14 tool calls, 92 seconds, 6 repeated reads</span></span>
60
+ <span class="line"><span>after: 5 tool calls, 31 seconds, 0 repeated reads</span></span></code></pre></div><p>Keep the change only if the answer still finds the same known issue. Efficiency without a quality check can make an agent fast by making it incomplete.</p><h2 id="improve-quality-without-changing-the-contract" tabindex="-1">Improve quality without changing the contract <a class="header-anchor" href="#improve-quality-without-changing-the-contract" aria-label="Permalink to &quot;Improve quality without changing the contract&quot;">​</a></h2><p>For answer quality, freeze the public shape before editing: required sections, API fields, side effects, and existing evals. Compare both runs against a known-good answer or a small set of gold findings, then change the instructions or skill that owns the missing judgment.</p><div class="language-text vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">text</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span>fixture: saved checkout PR diff</span></span>
61
+ <span class="line"><span>success: report both gold findings with file paths</span></span>
62
+ <span class="line"><span>freeze: findings JSON shape; no review post; existing smoke evals</span></span></code></pre></div><p>A wording change is not a win by itself. Keep it when correctness rises and every frozen behavior remains intact.</p><h2 id="run-one-measured-round" tabindex="-1">Run one measured round <a class="header-anchor" href="#run-one-measured-round" aria-label="Permalink to &quot;Run one measured round&quot;">​</a></h2><p>Agree on four inputs before editing:</p><ol><li><strong>Target:</strong> the agent path or slug.</li><li><strong>Fixtures:</strong> one to three prompts, saved payloads, or pinned PRs.</li><li><strong>Success:</strong> the metric or decision that should improve.</li><li><strong>Freeze line:</strong> behavior that must not move.</li></ol><p>Then run one loop:</p><ol><li>Exercise the agent through the same surface a user would.</li><li>Read the trajectory and name the dominant failure in one sentence.</li><li>Change one lever.</li><li>Rerun the same fixtures.</li><li>Compare correctness, efficiency, and contract fit.</li><li>Keep, revert, or narrow the change.</li></ol><p>Do not replace a fixture mid-round. A moving input makes the comparison meaningless.</p><h2 id="choose-the-smallest-lever" tabindex="-1">Choose the smallest lever <a class="header-anchor" href="#choose-the-smallest-lever" aria-label="Permalink to &quot;Choose the smallest lever&quot;">​</a></h2><p>Start with the earliest place that can remove the failure:</p><ol><li><strong>Host preparation:</strong> fetch deterministic evidence before the turn.</li><li><strong>Evidence shape:</strong> trim, order, or label what the model receives.</li><li><strong>Instructions or skills:</strong> clarify the decision procedure.</li><li><strong>Tool surface:</strong> remove or gate tools that invite wandering.</li><li><strong>Framework:</strong> change it only when the agent cannot express the fix.</li></ol><p>Changing the host or evidence often improves both quality and latency because the model spends less time searching for ground truth.</p><h2 id="lock-every-kept-win" tabindex="-1">Lock every kept win <a class="header-anchor" href="#lock-every-kept-win" aria-label="Permalink to &quot;Lock every kept win&quot;">​</a></h2><p>Each retained change needs an eval that would have failed before it. Use a tool-choice assertion, <code>maxToolCalls</code> bound, output-shape check, or quality score that captures the measured improvement.</p><div class="language-bash vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">bash</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#6F42C1;--shiki-dark:#B392F0;">agent-sdk</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;"> eval</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> --dir</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;"> .</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> --tag</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;"> smoke</span></span></code></pre></div><p>Never weaken an existing gate to make the round pass. The eval is the record that the improvement survived after the fixture and source change leave your working memory.</p><h2 id="run-the-loop-with-a-coding-agent" tabindex="-1">Run the loop with a coding agent <a class="header-anchor" href="#run-the-loop-with-a-coding-agent" aria-label="Permalink to &quot;Run the loop with a coding agent&quot;">​</a></h2><p>Ask the coding agent to read <a href="./../skills/hillclimb/SKILL.html"><code>skills/hillclimb/SKILL.md</code></a>, then give it the target, fixtures, success criterion, and freeze line. It will measure the current run, propose one change, remeasure, and ask before starting another round.</p><p>Use saved or local surfaces during a climb. Do not deploy or post to a real external channel unless that side effect is part of an explicitly approved fixture.</p><h2 id="related" tabindex="-1">Related <a class="header-anchor" href="#related" aria-label="Permalink to &quot;Related&quot;">​</a></h2><ul><li><a href="./evals.html">Evals</a>: author the regression check for a kept win</li><li><a href="./reference/evals.html">Evals reference</a>: trajectory assertions and scores</li><li><a href="./building-with-agents.html">Building agents with agents</a>: delegate creation and verification to a coding agent</li><li><a href="./troubleshooting.html">Fix common agent problems</a>: diagnose a run that is broken instead of underperforming</li></ul></div></div></main><footer class="VPDocFooter" data-v-afe580da data-v-feab96e0><!--[--><!--]--><!----><nav class="prev-next" aria-labelledby="doc-footer-aria-label" data-v-feab96e0><span class="visually-hidden" id="doc-footer-aria-label" data-v-feab96e0>Pager</span><div class="pager" data-v-feab96e0><a class="VPLink link pager-link prev" href="/docs/evals.html" data-v-feab96e0><!--[--><span class="desc" data-v-feab96e0>Previous page</span><span class="title" data-v-feab96e0>Evals</span><!--]--></a></div><div class="pager" data-v-feab96e0><a class="VPLink link pager-link next" href="/docs/building-with-agents.html" data-v-feab96e0><!--[--><span class="desc" data-v-feab96e0>Next page</span><span class="title" data-v-feab96e0>Build with a coding agent</span><!--]--></a></div></nav></footer><!--[--><!--]--></div></div></div><!--[--><!--]--></div></div><!----><!--[--><!--]--></div></div>
63
+ <script>window.__VP_HASH_MAP__=JSON.parse("{\"building-with-agents.md\":\"BBCx0AUo\",\"deployment.md\":\"D2jQZuFx\",\"evals.md\":\"BYvfZ-PO\",\"guides_agent-to-agent.md\":\"8oDTfu-E\",\"guides_bitbucket.md\":\"mpevW-VP\",\"guides_cloud-agents.md\":\"Cp1O3u-X\",\"guides_convert-automation.md\":\"CqEyfP6Y\",\"guides_github.md\":\"BwpBp3ed\",\"guides_gitlab.md\":\"DaEC3nMk\",\"guides_grokbot-agents.md\":\"CMhZNdEU\",\"guides_improve.md\":\"Bnp4F99w\",\"guides_mcp-oauth.md\":\"bSFakfCY\",\"guides_opentelemetry.md\":\"BKDxQmmd\",\"guides_slack.md\":\"Bo96y42E\",\"guides_webhooks.md\":\"1A72_VEE\",\"hillclimbing.md\":\"D4E1o5Sa\",\"index.md\":\"C-t81M5J\",\"quickstart.md\":\"DAvVhuuU\",\"reference_agent-config.md\":\"DGPyw7ms\",\"reference_artifacts.md\":\"Bu_4HmsD\",\"reference_channels.md\":\"nFWbzAic\",\"reference_cli.md\":\"DLWDz9ij\",\"reference_connections.md\":\"CmyrlXfY\",\"reference_evals.md\":\"DNJzM_yf\",\"reference_extensions.md\":\"Ceq-qT8d\",\"reference_hooks.md\":\"B7uzNENk\",\"reference_http-api.md\":\"CduHavZ2\",\"reference_instructions.md\":\"CU1My5My\",\"reference_playground.md\":\"Ch2d0Iqi\",\"reference_project-layout.md\":\"BGhgpy9V\",\"reference_prompt.md\":\"Ccp0R53H\",\"reference_schedules.md\":\"B2Nm6FaD\",\"reference_sessions.md\":\"1_6Vyv7x\",\"reference_skills.md\":\"DjQkRefx\",\"reference_subagents.md\":\"BHsSMMyO\",\"reference_tools.md\":\"BYzUTeVA\",\"templates_agentic-owners.md\":\"9M575F5C\",\"templates_pr-autofixer.md\":\"ws0DDXDy\",\"templates_security-reviewer.md\":\"KEFYXzfK\",\"templates_thermo-quality-review.md\":\"VNJ_mohX\",\"templates_thermo-review.md\":\"Hi3zWOkP\",\"templates_triage.md\":\"CVGe_FG6\",\"troubleshooting.md\":\"mnfFG2Em\"}");window.__VP_SITE_DATA__=JSON.parse("{\"lang\":\"en-US\",\"dir\":\"ltr\",\"title\":\"Agent SDK\",\"description\":\"Filesystem-first framework for building and serving Cursor agents.\",\"base\":\"/docs/\",\"head\":[],\"router\":{\"prefetchLinks\":true},\"appearance\":true,\"themeConfig\":{\"sdkVersion\":\"0.1.112\",\"nav\":[{\"text\":\"Quickstart\",\"link\":\"/quickstart\"},{\"text\":\"Guides\",\"link\":\"/guides/mcp-oauth\"},{\"text\":\"Integrations\",\"link\":\"/guides/github\"},{\"text\":\"Templates\",\"link\":\"/templates/security-reviewer\"},{\"text\":\"Reference\",\"link\":\"/reference/project-layout\"}],\"search\":{\"provider\":\"local\"},\"outline\":{\"level\":[2,3]},\"sidebar\":[{\"text\":\"Getting started\",\"items\":[{\"text\":\"Overview\",\"link\":\"/\"},{\"text\":\"Building your first agent\",\"link\":\"/quickstart\"}]},{\"text\":\"Integrations\",\"collapsed\":false,\"items\":[{\"text\":\"GitHub\",\"link\":\"/guides/github\"},{\"text\":\"Slack\",\"link\":\"/guides/slack\"},{\"text\":\"Webhooks\",\"link\":\"/guides/webhooks\"},{\"text\":\"Cursor Automations\",\"link\":\"/guides/convert-automation\"},{\"text\":\"OpenTelemetry\",\"link\":\"/guides/opentelemetry\"},{\"text\":\"GitLab\",\"link\":\"/guides/gitlab\"},{\"text\":\"Bitbucket\",\"link\":\"/guides/bitbucket\"}]},{\"text\":\"Extensions\",\"collapsed\":false,\"items\":[{\"text\":\"Overview\",\"link\":\"/reference/extensions\"},{\"text\":\"Cloud agents\",\"link\":\"/guides/cloud-agents\"},{\"text\":\"Grok Bot agents\",\"link\":\"/guides/grokbot-agents\"},{\"text\":\"Self-improvement\",\"link\":\"/guides/improve\"}]},{\"text\":\"Guides\",\"collapsed\":false,\"items\":[{\"text\":\"MCP\",\"link\":\"/guides/mcp-oauth\"},{\"text\":\"Agent-to-agent\",\"link\":\"/guides/agent-to-agent\"},{\"text\":\"Deployment\",\"link\":\"/deployment\"},{\"text\":\"Evals\",\"link\":\"/evals\"},{\"text\":\"Hillclimbing\",\"link\":\"/hillclimbing\"},{\"text\":\"Build with a coding agent\",\"link\":\"/building-with-agents\"},{\"text\":\"Troubleshooting\",\"link\":\"/troubleshooting\"}]},{\"text\":\"Templates\",\"collapsed\":false,\"items\":[{\"text\":\"Security reviewer\",\"link\":\"/templates/security-reviewer\"},{\"text\":\"Thermo review\",\"link\":\"/templates/thermo-review\"},{\"text\":\"Thermo quality review\",\"link\":\"/templates/thermo-quality-review\"},{\"text\":\"Agentic Approver\",\"link\":\"/templates/agentic-owners\"},{\"text\":\"PR autofixer\",\"link\":\"/templates/pr-autofixer\"},{\"text\":\"Triage agent\",\"link\":\"/templates/triage\"}]},{\"text\":\"Reference\",\"collapsed\":false,\"items\":[{\"text\":\"Project layout\",\"link\":\"/reference/project-layout\"},{\"text\":\"Agent config\",\"link\":\"/reference/agent-config\"},{\"text\":\"Instructions\",\"link\":\"/reference/instructions\"},{\"text\":\"Tools\",\"link\":\"/reference/tools\"},{\"text\":\"prompt\",\"link\":\"/reference/prompt\"},{\"text\":\"Skills\",\"link\":\"/reference/skills\"},{\"text\":\"MCP Connections\",\"link\":\"/reference/connections\"},{\"text\":\"Subagents\",\"link\":\"/reference/subagents\"},{\"text\":\"Channels\",\"link\":\"/reference/channels\"},{\"text\":\"Schedules & reminders\",\"link\":\"/reference/schedules\"},{\"text\":\"Hooks\",\"link\":\"/reference/hooks\"},{\"text\":\"Evals\",\"link\":\"/reference/evals\"},{\"text\":\"Artifacts\",\"link\":\"/reference/artifacts\"},{\"text\":\"Sessions & streaming\",\"link\":\"/reference/sessions\"},{\"text\":\"Playground\",\"link\":\"/reference/playground\"},{\"text\":\"CLI\",\"link\":\"/reference/cli\"},{\"text\":\"HTTP API\",\"link\":\"/reference/http-api\"}]}]},\"locales\":{},\"scrollOffset\":134,\"cleanUrls\":false}");</script>
28
64
 
29
65
  </body>
30
66
  </html>
@@ -1,88 +1,134 @@
1
1
  # Hillclimbing
2
2
 
3
- Make an agent better on fixed inputs: measure, change one lever, remeasure, and lock every kept win with an eval.
3
+ Hillclimbing improves an agent through controlled before-and-after
4
+ comparisons. Keep the inputs fixed, name one failure, change one lever,
5
+ and retain the change only when the same run gets better without
6
+ crossing the freeze line.
4
7
 
5
- ## What is hillclimbing?
8
+ The companion [`hillclimb` skill](https://github.com/cursor/cursor/blob/main/packages/agent-serve/skills/hillclimb/SKILL.md) can run
9
+ this loop with you.
6
10
 
7
- Hillclimbing is a measured improvement loop. You pin a few fixtures, name the one dominant problem in the run, change one lever, and check the same fixtures again. Keep only what helps. Every kept change lands an [eval](/docs/evals.md) so the win stays put.
11
+ ## Correct a wrong tool choice
8
12
 
9
- You don't have to run the loop alone. The package ships a coding-agent skill that drives it with you.
13
+ Suppose a PR reviewer calls `approve_pr` before `inspect_pr`. Pin one PR
14
+ fixture, record the original tool order, then tighten the instruction
15
+ that owns the decision. The improved run should inspect first and leave
16
+ approval untouched.
10
17
 
11
- ```mermaid
12
- flowchart LR
13
- measure[Measure] --> change[Change one lever]
14
- change --> remeasure[Remeasure]
15
- remeasure --> measure
18
+ ```bash
19
+ agent-sdk run --dir . \
20
+ --message "Is https://github.com/acme/checkout/pull/42 ready?"
16
21
  ```
17
22
 
18
- ## How do I hillclimb an agent with a coding agent?
23
+ Lock the result with the intended and tempting-wrong paths:
19
24
 
20
- Have Cursor read [`skills/hillclimb/SKILL.md`](/docs/skills/hillclimb.md).
25
+ ```ts
26
+ t.succeeded();
27
+ t.calledTool("inspect_pr");
28
+ t.notCalledTool("approve_pr");
29
+ ```
30
+
31
+ Do not change the tool implementation, prompt, and evidence together.
32
+ If tool choice improves, you should know which edit caused it.
21
33
 
22
- Tell it:
34
+ ## Reduce wandering or latency
23
35
 
24
- 1. **Which agent** you're improving (path or slug)
25
- 2. **One to three fixtures** you'll reuse every round: a PR URL, a saved webhook body, or a canonical chat prompt
26
- 3. **What "better" means** this round: correct tool choice, fewer tools, lower latency, or output quality. Name the freeze line too: API shape, public output, and existing evals that must stay green
36
+ A slow run often repeats reads, searches broad directories, or asks the
37
+ model to discover evidence the host already has. Compare the trajectory
38
+ by tool name and wall time, then move deterministic preparation ahead
39
+ of the turn or trim the evidence shape.
27
40
 
28
- The skill serves the agent, hits your fixtures, reads the session trajectory, proposes one change, remeasures, and checks with you before the next round.
41
+ ```text
42
+ before: 14 tool calls, 92 seconds, 6 repeated reads
43
+ after: 5 tool calls, 31 seconds, 0 repeated reads
44
+ ```
29
45
 
30
- Other skills cover the edges:
46
+ Keep the change only if the answer still finds the same known issue.
47
+ Efficiency without a quality check can make an agent fast by making it
48
+ incomplete.
31
49
 
32
- | When you need… | Skill |
33
- | --- | --- |
34
- | The measured improvement loop | [`skills/hillclimb/SKILL.md`](/docs/skills/hillclimb.md) |
35
- | An eval that locks a kept win | [`skills/evals/SKILL.md`](/docs/skills/evals.md) |
36
- | Repeatable GitHub webhook inputs | [`skills/github/SKILL.md`](/docs/skills/github.md) |
37
- | A run that misbehaves | [`skills/debug/SKILL.md`](/docs/skills/debug.md) |
50
+ ## Improve quality without changing the contract
38
51
 
39
- See [Building agents with agents](/docs/building-with-agents.md) for every framework skill and a good first prompt.
52
+ For answer quality, freeze the public shape before editing: required
53
+ sections, API fields, side effects, and existing evals. Compare both
54
+ runs against a known-good answer or a small set of gold findings, then
55
+ change the instructions or skill that owns the missing judgment.
56
+
57
+ ```text
58
+ fixture: saved checkout PR diff
59
+ success: report both gold findings with file paths
60
+ freeze: findings JSON shape; no review post; existing smoke evals
61
+ ```
40
62
 
41
- ## What do I need before a hillclimb round?
63
+ A wording change is not a win by itself. Keep it when correctness rises
64
+ and every frozen behavior remains intact.
42
65
 
43
- Agree on four things before you edit:
66
+ ## Run one measured round
44
67
 
45
- 1. **The target agent**: the project you're improving
46
- 2. **Fixtures**: one to three fixed inputs you can compare across runs
47
- 3. **Success criteria**: what better means this round
48
- 4. **The freeze line**: what must not change
68
+ Agree on four inputs before editing:
49
69
 
50
- Pin the input first. A moving fixture is noise. For GitHub agents, use `agent-sdk github replay` (see the [GitHub guide](/docs/guides/github.md)). For a single tool without a model turn, use `agent-sdk call`. For a chat turn, use `agent-sdk run --dir . --message "…"`.
70
+ 1. **Target:** the agent path or slug.
71
+ 2. **Fixtures:** one to three prompts, saved payloads, or pinned PRs.
72
+ 3. **Success:** the metric or decision that should improve.
73
+ 4. **Freeze line:** behavior that must not move.
51
74
 
52
- ## How do I run one hillclimb round?
75
+ Then run one loop:
53
76
 
54
- **Measure.** Hit the agent the way a user would: playground, channel HTTP, or Slack in `--dev`. Or ask the hillclimb skill to do it. `agent-sdk run` returns a JSON trajectory and writes a trace under the project state directory.
77
+ 1. Exercise the agent through the same surface a user would.
78
+ 2. Read the trajectory and name the dominant failure in one sentence.
79
+ 3. Change one lever.
80
+ 4. Rerun the same fixtures.
81
+ 5. Compare correctness, efficiency, and contract fit.
82
+ 6. Keep, revert, or narrow the change.
55
83
 
56
- **Reflect.** Score the trajectory, not impressions. Was the answer right? Did the model thrash (too many tools, fat evidence, grep loops)? Did it invent work the host should have prepared? Name the single dominant problem for this round in one sentence. Example: "Full-file dumps trigger grep loops."
84
+ Do not replace a fixture mid-round. A moving input makes the comparison
85
+ meaningless.
57
86
 
58
- **Change one lever.** Prefer the smallest change that addresses that problem:
87
+ ## Choose the smallest lever
59
88
 
60
- 1. Host prep: seed what the model needs so it doesn't hunt
61
- 2. Evidence shape: trim or reorder artifacts
62
- 3. Instructions and skills: tighten the procedure
63
- 4. Tool surface: remove or gate tools that invite wandering
64
- 5. Framework changes: only when the agent can't express the fix
89
+ Start with the earliest place that can remove the failure:
65
90
 
66
- **Remeasure.** Same fixtures. Diff tools, wall time, and quality side by side. Keep the change only if the target metric improves and the freeze line holds.
91
+ 1. **Host preparation:** fetch deterministic evidence before the turn.
92
+ 2. **Evidence shape:** trim, order, or label what the model receives.
93
+ 3. **Instructions or skills:** clarify the decision procedure.
94
+ 4. **Tool surface:** remove or gate tools that invite wandering.
95
+ 5. **Framework:** change it only when the agent cannot express the fix.
67
96
 
68
- ## How do I lock a hillclimb improvement with an eval?
97
+ Changing the host or evidence often improves both quality and latency
98
+ because the model spends less time searching for ground truth.
99
+
100
+ ## Lock every kept win
101
+
102
+ Each retained change needs an eval that would have failed before it. Use
103
+ a tool-choice assertion, `maxToolCalls` bound, output-shape check, or
104
+ quality score that captures the measured improvement.
105
+
106
+ ```bash
107
+ agent-sdk eval --dir . --tag smoke
108
+ ```
69
109
 
70
- Every kept change needs an eval that would have failed before the change: a tool-choice gate, a `maxToolCalls` bound, or an output-shape check. Run `agent-sdk eval --dir . --json` between rounds. Never weaken an existing gate to pass the round.
110
+ Never weaken an existing gate to make the round pass. The eval is the
111
+ record that the improvement survived after the fixture and source
112
+ change leave your working memory.
71
113
 
72
- Details live in [Keep improvements with regression evals](/docs/evals.md#keep-improvements-with-regression-evals). The evals skill will author the case with you.
114
+ ## Run the loop with a coding agent
73
115
 
74
- ## What habits help hillclimbing stay reliable?
116
+ Ask the coding agent to read
117
+ [`skills/hillclimb/SKILL.md`](https://github.com/cursor/cursor/blob/main/packages/agent-serve/skills/hillclimb/SKILL.md), then give
118
+ it the target, fixtures, success criterion, and freeze line. It will
119
+ measure the current run, propose one change, remeasure, and ask before
120
+ starting another round.
75
121
 
76
- - One problem per round. Don't bundle "trim evidence and rewrite instructions" unless you chose that on purpose.
77
- - Keep fixtures fixed until you deliberately need a harder case.
78
- - Separate host work from model tools when you blame latency. Moving deterministic prep onto the host is often the biggest win. In one PR reviewer, host-prepared evidence cut turns from about 8 minutes to about 1 minute.
79
- - Spot-check quality on at least one fixture against a known-good answer. Efficiency-only climbs quietly drop findings.
80
- - Treat `turn.failed` with `"turn interrupted"` as expected when a follow-up or stop preempted the turn.
81
- - Don't deploy, post to real surfaces, or weaken evals as part of a climb.
122
+ Use saved or local surfaces during a climb. Do not deploy or post to a
123
+ real external channel unless that side effect is part of an explicitly
124
+ approved fixture.
82
125
 
83
126
  ## Related
84
127
 
85
- - [Evals](/docs/evals.md)
86
- - [Building agents with agents](/docs/building-with-agents.md)
87
- - [GitHub guide](/docs/guides/github.md)
88
- - [Fix common agent problems](/docs/troubleshooting.md)
128
+ - [Evals](/docs/evals.md): author the regression check for a kept win
129
+ - [Evals reference](/docs/reference/evals.md): trajectory assertions and
130
+ scores
131
+ - [Building agents with agents](/docs/building-with-agents.md): delegate
132
+ creation and verification to a coding agent
133
+ - [Fix common agent problems](/docs/troubleshooting.md): diagnose a run
134
+ that is broken instead of underperforming