@grok/agent-sdk 0.2.28 → 0.3.0

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 (528) hide show
  1. package/AGENTS.md +29 -29
  2. package/dist/bin/agent-serve.d.ts +2 -2
  3. package/dist/bin/agent-serve.js +3 -3
  4. package/dist/channels/pagerduty/api.js +1 -1
  5. package/dist/channels/pagerduty/pagerduty-channel.d.ts +1 -1
  6. package/dist/channels/pagerduty/pagerduty-channel.d.ts.map +1 -1
  7. package/dist/channels/pagerduty/pagerduty-channel.js +1 -1
  8. package/dist/channels/pagerduty/replay.d.ts +1 -1
  9. package/dist/channels/pagerduty/replay.js +4 -4
  10. package/dist/channels/slack/cli-project.js +1 -1
  11. package/dist/docs/404.html +2 -2
  12. package/dist/docs/assets/{app.DF9vlcdn.js → app.BzTUBOAD.js} +4 -4
  13. package/dist/docs/assets/building-with-agents.md.BqJ7AAjG.js +6 -0
  14. package/dist/docs/assets/{building-with-agents.md.Bf1yH2tG.lean.js → building-with-agents.md.BqJ7AAjG.lean.js} +1 -1
  15. package/dist/docs/assets/changelog.md.BWhC6DET.js +1 -0
  16. package/dist/docs/assets/changelog.md.BWhC6DET.lean.js +1 -0
  17. package/dist/docs/assets/chunks/@localSearchIndexroot.CWxwVoCG.js +1 -0
  18. package/dist/docs/assets/chunks/{VPLocalSearchBox.D8OuwKO0.js → VPLocalSearchBox.DsnRlUT5.js} +1 -1
  19. package/dist/docs/assets/chunks/{arc.DCq_TCYV.js → arc.DH8GOhiv.js} +1 -1
  20. package/dist/docs/assets/chunks/{architectureDiagram-Q4EWVU46.PWRNTPbk.js → architectureDiagram-Q4EWVU46.9m9ObyuE.js} +1 -1
  21. package/dist/docs/assets/chunks/{baseUniq.BeRPvRUL.js → baseUniq.BXHpx1lE.js} +1 -1
  22. package/dist/docs/assets/chunks/{blockDiagram-DXYQGD6D.BuRmZVSo.js → blockDiagram-DXYQGD6D.xY3EX59q.js} +1 -1
  23. package/dist/docs/assets/chunks/{c4Diagram-AHTNJAMY.7DKSMwuv.js → c4Diagram-AHTNJAMY.DnqgMVgc.js} +1 -1
  24. package/dist/docs/assets/chunks/channel.Cctv0f7X.js +1 -0
  25. package/dist/docs/assets/chunks/{chunk-4BX2VUAB.7VrO9-9i.js → chunk-4BX2VUAB.BjFxK2A3.js} +1 -1
  26. package/dist/docs/assets/chunks/{chunk-4TB4RGXK.CHystNE2.js → chunk-4TB4RGXK.BujS_Spt.js} +1 -1
  27. package/dist/docs/assets/chunks/{chunk-55IACEB6.Nuh9TbTq.js → chunk-55IACEB6.YbTjhdaM.js} +1 -1
  28. package/dist/docs/assets/chunks/{chunk-EDXVE4YY.CA0EKugm.js → chunk-EDXVE4YY.DnQ8t4GC.js} +1 -1
  29. package/dist/docs/assets/chunks/{chunk-FMBD7UC4.F9_mp7U8.js → chunk-FMBD7UC4.B67AwAmj.js} +1 -1
  30. package/dist/docs/assets/chunks/{chunk-OYMX7WX6.CEU4QfE1.js → chunk-OYMX7WX6.DrZIAFOm.js} +1 -1
  31. package/dist/docs/assets/chunks/{chunk-QZHKN3VN.B8h_x9_i.js → chunk-QZHKN3VN.BLmmydkn.js} +1 -1
  32. package/dist/docs/assets/chunks/{chunk-YZCP3GAM.Btfb-rKg.js → chunk-YZCP3GAM.DaoOfw0O.js} +1 -1
  33. package/dist/docs/assets/chunks/classDiagram-6PBFFD2Q.DU5sqchW.js +1 -0
  34. package/dist/docs/assets/chunks/classDiagram-v2-HSJHXN6E.DU5sqchW.js +1 -0
  35. package/dist/docs/assets/chunks/clone.B9rdNt6j.js +1 -0
  36. package/dist/docs/assets/chunks/{cose-bilkent-S5V4N54A.DKvc96Wa.js → cose-bilkent-S5V4N54A.DMQuNhM5.js} +1 -1
  37. package/dist/docs/assets/chunks/{dagre-KV5264BT.CMo0cy1b.js → dagre-KV5264BT.CZoGVuUf.js} +1 -1
  38. package/dist/docs/assets/chunks/{diagram-5BDNPKRD.DDgMOQhB.js → diagram-5BDNPKRD.CLt9uOyL.js} +1 -1
  39. package/dist/docs/assets/chunks/{diagram-G4DWMVQ6.BdJnoIsU.js → diagram-G4DWMVQ6.DpczEm1G.js} +1 -1
  40. package/dist/docs/assets/chunks/{diagram-MMDJMWI5.oSvhAZaL.js → diagram-MMDJMWI5.D4r13DvJ.js} +1 -1
  41. package/dist/docs/assets/chunks/{diagram-TYMM5635.C9zZLIE-.js → diagram-TYMM5635.CYU9eGFu.js} +1 -1
  42. package/dist/docs/assets/chunks/{erDiagram-SMLLAGMA.BNhVyccy.js → erDiagram-SMLLAGMA.QA9naWEw.js} +1 -1
  43. package/dist/docs/assets/chunks/{flowDiagram-DWJPFMVM.BEFLLBiU.js → flowDiagram-DWJPFMVM.BbNoVZYd.js} +1 -1
  44. package/dist/docs/assets/chunks/{ganttDiagram-T4ZO3ILL.BdUzXBgY.js → ganttDiagram-T4ZO3ILL.IHjDoG7r.js} +1 -1
  45. package/dist/docs/assets/chunks/{gitGraphDiagram-UUTBAWPF.Rd3LlOIJ.js → gitGraphDiagram-UUTBAWPF.B21VMdf5.js} +1 -1
  46. package/dist/docs/assets/chunks/{graph.DnJC1GpG.js → graph.DgJ4L-8V.js} +1 -1
  47. package/dist/docs/assets/chunks/{infoDiagram-42DDH7IO.xv0xntDJ.js → infoDiagram-42DDH7IO.CQjrcthc.js} +1 -1
  48. package/dist/docs/assets/chunks/{ishikawaDiagram-UXIWVN3A.BaGIlviU.js → ishikawaDiagram-UXIWVN3A.D4tPGtVo.js} +1 -1
  49. package/dist/docs/assets/chunks/{journeyDiagram-VCZTEJTY.Cof_h0fp.js → journeyDiagram-VCZTEJTY.BD3WaNbQ.js} +1 -1
  50. package/dist/docs/assets/chunks/{kanban-definition-6JOO6SKY.C5GozFuU.js → kanban-definition-6JOO6SKY.Ca0o4Tqz.js} +1 -1
  51. package/dist/docs/assets/chunks/{layout.zc9UShLc.js → layout.DXXqX4MQ.js} +1 -1
  52. package/dist/docs/assets/chunks/{linear.BoqrFVcJ.js → linear.5c61gNw4.js} +1 -1
  53. package/dist/docs/assets/chunks/{min.DwIfr8hG.js → min.B1-NAjHX.js} +1 -1
  54. package/dist/docs/assets/chunks/{mindmap-definition-QFDTVHPH.Dkq2yTtp.js → mindmap-definition-QFDTVHPH.BELznv3-.js} +1 -1
  55. package/dist/docs/assets/chunks/{pieDiagram-DEJITSTG.B4CpTmHK.js → pieDiagram-DEJITSTG.qPzO1mq5.js} +1 -1
  56. package/dist/docs/assets/chunks/{quadrantDiagram-34T5L4WZ.BqXnFC9C.js → quadrantDiagram-34T5L4WZ.CxIvzbjX.js} +1 -1
  57. package/dist/docs/assets/chunks/{requirementDiagram-MS252O5E.DhIN2z-E.js → requirementDiagram-MS252O5E.CqA0iJx8.js} +1 -1
  58. package/dist/docs/assets/chunks/{sankeyDiagram-XADWPNL6.BhxUAmg2.js → sankeyDiagram-XADWPNL6.XRTutBnb.js} +1 -1
  59. package/dist/docs/assets/chunks/{sequenceDiagram-FGHM5R23.BqgU7HU-.js → sequenceDiagram-FGHM5R23.E--7bRLQ.js} +1 -1
  60. package/dist/docs/assets/chunks/{stateDiagram-FHFEXIEX.B1BCO18N.js → stateDiagram-FHFEXIEX.C4vGu8zq.js} +1 -1
  61. package/dist/docs/assets/chunks/stateDiagram-v2-QKLJ7IA2.ECMu2BdJ.js +1 -0
  62. package/dist/docs/assets/chunks/{theme.oV7rddEz.js → theme.DMj_7q3B.js} +2 -2
  63. package/dist/docs/assets/chunks/{timeline-definition-GMOUNBTQ.oRI8UwMC.js → timeline-definition-GMOUNBTQ.C7LgNVAL.js} +1 -1
  64. package/dist/docs/assets/chunks/{vennDiagram-DHZGUBPP.DmuWrIxN.js → vennDiagram-DHZGUBPP.HUwoZcy_.js} +1 -1
  65. package/dist/docs/assets/chunks/{wardley-RL74JXVD.CEBjM5ov.js → wardley-RL74JXVD.BxFEFYZS.js} +1 -1
  66. package/dist/docs/assets/chunks/{wardleyDiagram-NUSXRM2D.m5zsCOF9.js → wardleyDiagram-NUSXRM2D.B2pSo5rB.js} +1 -1
  67. package/dist/docs/assets/chunks/{xychartDiagram-5P7HB3ND.cPN-587n.js → xychartDiagram-5P7HB3ND.NQhMiOOL.js} +1 -1
  68. package/dist/docs/assets/deployment.md.BtqJrHhp.js +31 -0
  69. package/dist/docs/assets/{deployment.md.DDmjAVbg.lean.js → deployment.md.BtqJrHhp.lean.js} +1 -1
  70. package/dist/docs/assets/evals.md.Dne6VRmZ.js +49 -0
  71. package/dist/docs/assets/evals.md.Dne6VRmZ.lean.js +1 -0
  72. package/dist/docs/assets/{guides_agent-to-agent.md.D1D5f6Jc.js → guides_agent-to-agent.md.BcmSqL2z.js} +8 -8
  73. package/dist/docs/assets/guides_agent-to-agent.md.BcmSqL2z.lean.js +1 -0
  74. package/dist/docs/assets/{guides_bitbucket.md.DkjkBRU8.js → guides_bitbucket.md.BiA6ZMFW.js} +27 -27
  75. package/dist/docs/assets/{guides_bitbucket.md.DkjkBRU8.lean.js → guides_bitbucket.md.BiA6ZMFW.lean.js} +1 -1
  76. package/dist/docs/assets/guides_cloud-agents.md.CiXAW6on.js +9 -0
  77. package/dist/docs/assets/{guides_cloud-agents.md.Ceyjv0ul.lean.js → guides_cloud-agents.md.CiXAW6on.lean.js} +1 -1
  78. package/dist/docs/assets/guides_convert-automation.md.BvTxsJ8J.js +26 -0
  79. package/dist/docs/assets/{guides_convert-automation.md.BjraCvok.lean.js → guides_convert-automation.md.BvTxsJ8J.lean.js} +1 -1
  80. package/dist/docs/assets/{guides_github.md.CgN5sNbW.js → guides_github.md.6jiEH7dg.js} +11 -19
  81. package/dist/docs/assets/{guides_github.md.CgN5sNbW.lean.js → guides_github.md.6jiEH7dg.lean.js} +1 -1
  82. package/dist/docs/assets/{guides_gitlab.md.DCE0p7_w.js → guides_gitlab.md.DcKusOcU.js} +63 -73
  83. package/dist/docs/assets/{guides_gitlab.md.DCE0p7_w.lean.js → guides_gitlab.md.DcKusOcU.lean.js} +1 -1
  84. package/dist/docs/assets/guides_improve.md.o3WOGR7n.js +16 -0
  85. package/dist/docs/assets/{guides_improve.md.BFYtrtLE.lean.js → guides_improve.md.o3WOGR7n.lean.js} +1 -1
  86. package/dist/docs/assets/{guides_jev.md.Ccw4pedT.js → guides_jev.md.DGCzkMUN.js} +20 -60
  87. package/dist/docs/assets/{guides_jev.md.Ccw4pedT.lean.js → guides_jev.md.DGCzkMUN.lean.js} +1 -1
  88. package/dist/docs/assets/{guides_mcp-oauth.md.ekpWOZCC.js → guides_mcp-oauth.md.C-Sx_IPa.js} +3 -5
  89. package/dist/docs/assets/{guides_mcp-oauth.md.ekpWOZCC.lean.js → guides_mcp-oauth.md.C-Sx_IPa.lean.js} +1 -1
  90. package/dist/docs/assets/guides_migrate.md.BbhHYeCr.js +3 -0
  91. package/dist/docs/assets/{guides_migrate.md.RS9Eu-Xh.lean.js → guides_migrate.md.BbhHYeCr.lean.js} +1 -1
  92. package/dist/docs/assets/guides_opentelemetry.md.BRSktBHt.js +26 -0
  93. package/dist/docs/assets/guides_opentelemetry.md.BRSktBHt.lean.js +1 -0
  94. package/dist/docs/assets/guides_pagerduty.md.pMXUkZZc.js +61 -0
  95. package/dist/docs/assets/guides_pagerduty.md.pMXUkZZc.lean.js +1 -0
  96. package/dist/docs/assets/guides_slack.md.BgIGG9ur.js +82 -0
  97. package/dist/docs/assets/{guides_slack.md.BqiGSYGX.lean.js → guides_slack.md.BgIGG9ur.lean.js} +1 -1
  98. package/dist/docs/assets/{guides_webhooks.md.BJk63ZTs.js → guides_webhooks.md.B5DXt2v1.js} +7 -7
  99. package/dist/docs/assets/{guides_webhooks.md.BJk63ZTs.lean.js → guides_webhooks.md.B5DXt2v1.lean.js} +1 -1
  100. package/dist/docs/assets/hillclimbing.md.3TkdF79A.js +5 -0
  101. package/dist/docs/assets/hillclimbing.md.3TkdF79A.lean.js +1 -0
  102. package/dist/docs/assets/index.md.DRfaoRCZ.js +20 -0
  103. package/dist/docs/assets/index.md.DRfaoRCZ.lean.js +1 -0
  104. package/dist/docs/assets/quickstart.md.r-oE8nkX.js +113 -0
  105. package/dist/docs/assets/{quickstart.md.DaLk4ZIF.lean.js → quickstart.md.r-oE8nkX.lean.js} +1 -1
  106. package/dist/docs/assets/reference_access.md.C5lblfUC.js +1 -0
  107. package/dist/docs/assets/{reference_access.md.CExlH_mR.lean.js → reference_access.md.C5lblfUC.lean.js} +1 -1
  108. package/dist/docs/assets/reference_agent-config.md.C0Tp_Fk9.js +27 -0
  109. package/dist/docs/assets/{reference_agent-config.md.11E_xe--.lean.js → reference_agent-config.md.C0Tp_Fk9.lean.js} +1 -1
  110. package/dist/docs/assets/reference_artifacts.md.BJpAI7h9.js +17 -0
  111. package/dist/docs/assets/{reference_artifacts.md.C-hKR2hp.lean.js → reference_artifacts.md.BJpAI7h9.lean.js} +1 -1
  112. package/dist/docs/assets/reference_channels.md.CPWOpdsC.js +21 -0
  113. package/dist/docs/assets/{reference_channels.md.DsJfGSBJ.lean.js → reference_channels.md.CPWOpdsC.lean.js} +1 -1
  114. package/dist/docs/assets/reference_cli.md.B8GdpaRj.js +83 -0
  115. package/dist/docs/assets/reference_cli.md.B8GdpaRj.lean.js +1 -0
  116. package/dist/docs/assets/reference_connections.md.DoY4vrDH.js +54 -0
  117. package/dist/docs/assets/{reference_connections.md.BoAotr7_.lean.js → reference_connections.md.DoY4vrDH.lean.js} +1 -1
  118. package/dist/docs/assets/reference_evals.md.DgfUtfIc.js +69 -0
  119. package/dist/docs/assets/{reference_evals.md.DYKjGFi-.lean.js → reference_evals.md.DgfUtfIc.lean.js} +1 -1
  120. package/dist/docs/assets/{reference_extensions.md.pEVj72Xo.js → reference_extensions.md.DHbW6eOf.js} +6 -8
  121. package/dist/docs/assets/{reference_extensions.md.pEVj72Xo.lean.js → reference_extensions.md.DHbW6eOf.lean.js} +1 -1
  122. package/dist/docs/assets/reference_hooks.md.CSWmOwMM.js +39 -0
  123. package/dist/docs/assets/reference_hooks.md.CSWmOwMM.lean.js +1 -0
  124. package/dist/docs/assets/reference_http-api.md.C7Cb0r2J.js +7 -0
  125. package/dist/docs/assets/{reference_http-api.md._RWELr3d.lean.js → reference_http-api.md.C7Cb0r2J.lean.js} +1 -1
  126. package/dist/docs/assets/reference_instructions.md.CV6Qq0UX.js +14 -0
  127. package/dist/docs/assets/reference_instructions.md.CV6Qq0UX.lean.js +1 -0
  128. package/dist/docs/assets/reference_limits.md.CbdtFr4T.js +8 -0
  129. package/dist/docs/assets/reference_limits.md.CbdtFr4T.lean.js +1 -0
  130. package/dist/docs/assets/reference_memory.md.CdoJISM-.js +3 -0
  131. package/dist/docs/assets/{reference_memory.md.Dd7cyV9V.lean.js → reference_memory.md.CdoJISM-.lean.js} +1 -1
  132. package/dist/docs/assets/reference_playground.md.DIUsRAcy.js +1 -0
  133. package/dist/docs/assets/{reference_playground.md.CQiJk9CM.lean.js → reference_playground.md.DIUsRAcy.lean.js} +1 -1
  134. package/dist/docs/assets/reference_project-layout.md.9DiKoE16.js +26 -0
  135. package/dist/docs/assets/reference_project-layout.md.9DiKoE16.lean.js +1 -0
  136. package/dist/docs/assets/reference_schedules.md.RhQ9ZLo1.js +45 -0
  137. package/dist/docs/assets/{reference_schedules.md.RC47aFm4.lean.js → reference_schedules.md.RhQ9ZLo1.lean.js} +1 -1
  138. package/dist/docs/assets/reference_sessions.md.NXVQt9mP.js +22 -0
  139. package/dist/docs/assets/{reference_sessions.md.C7KFhWXV.lean.js → reference_sessions.md.NXVQt9mP.lean.js} +1 -1
  140. package/dist/docs/assets/{reference_skills.md.Dej2zQxi.js → reference_skills.md.DzCPNPkG.js} +4 -4
  141. package/dist/docs/assets/{reference_skills.md.Dej2zQxi.lean.js → reference_skills.md.DzCPNPkG.lean.js} +1 -1
  142. package/dist/docs/assets/reference_subagents.md.Dvpq2sUu.js +10 -0
  143. package/dist/docs/assets/{reference_subagents.md.CAhvW4yS.lean.js → reference_subagents.md.Dvpq2sUu.lean.js} +1 -1
  144. package/dist/docs/assets/reference_tools.md.B2OaR1Nb.js +62 -0
  145. package/dist/docs/assets/{reference_tools.md.DQr7Fnhu.lean.js → reference_tools.md.B2OaR1Nb.lean.js} +1 -1
  146. package/dist/docs/assets/templates_agentic-owners.md.B6ZmKAzT.js +13 -0
  147. package/dist/docs/assets/{templates_agentic-owners.md.Dh2nDSqg.lean.js → templates_agentic-owners.md.B6ZmKAzT.lean.js} +1 -1
  148. package/dist/docs/assets/templates_reviews.md.dr9Xv_KM.js +10 -0
  149. package/dist/docs/assets/templates_reviews.md.dr9Xv_KM.lean.js +1 -0
  150. package/dist/docs/assets/troubleshooting.md.DfKKvW1R.js +3 -0
  151. package/dist/docs/assets/{troubleshooting.md.AGJ3jDzj.lean.js → troubleshooting.md.DfKKvW1R.lean.js} +1 -1
  152. package/dist/docs/building-with-agents.html +41 -44
  153. package/dist/docs/building-with-agents.md +11 -104
  154. package/dist/docs/changelog.html +37 -37
  155. package/dist/docs/changelog.md +5 -145
  156. package/dist/docs/deployment.html +54 -54
  157. package/dist/docs/deployment.md +86 -265
  158. package/dist/docs/evals.html +52 -71
  159. package/dist/docs/evals.md +33 -127
  160. package/dist/docs/guides/agent-to-agent.html +43 -43
  161. package/dist/docs/guides/agent-to-agent.md +27 -64
  162. package/dist/docs/guides/bitbucket.html +62 -62
  163. package/dist/docs/guides/bitbucket.md +73 -134
  164. package/dist/docs/guides/cloud-agents.html +37 -37
  165. package/dist/docs/guides/cloud-agents.md +23 -53
  166. package/dist/docs/guides/convert-automation.html +39 -56
  167. package/dist/docs/guides/convert-automation.md +31 -115
  168. package/dist/docs/guides/github.html +46 -54
  169. package/dist/docs/guides/github.md +49 -131
  170. package/dist/docs/guides/gitlab.html +98 -108
  171. package/dist/docs/guides/gitlab.md +104 -184
  172. package/dist/docs/guides/improve.html +38 -43
  173. package/dist/docs/guides/improve.md +24 -90
  174. package/dist/docs/guides/jev.html +55 -95
  175. package/dist/docs/guides/jev.md +57 -159
  176. package/dist/docs/guides/mcp-oauth.html +38 -40
  177. package/dist/docs/guides/mcp-oauth.md +34 -69
  178. package/dist/docs/guides/migrate.html +38 -43
  179. package/dist/docs/guides/migrate.md +56 -130
  180. package/dist/docs/guides/opentelemetry.html +41 -43
  181. package/dist/docs/guides/opentelemetry.md +32 -27
  182. package/dist/docs/guides/pagerduty.html +50 -49
  183. package/dist/docs/guides/pagerduty.md +65 -199
  184. package/dist/docs/guides/slack.html +51 -57
  185. package/dist/docs/guides/slack.md +76 -205
  186. package/dist/docs/guides/webhooks.html +42 -42
  187. package/dist/docs/guides/webhooks.md +64 -146
  188. package/dist/docs/hashmap.json +1 -1
  189. package/dist/docs/hillclimbing.html +40 -42
  190. package/dist/docs/hillclimbing.md +40 -102
  191. package/dist/docs/index.html +55 -62
  192. package/dist/docs/index.md +49 -82
  193. package/dist/docs/llms-full.txt +2292 -5830
  194. package/dist/docs/llms.txt +9 -15
  195. package/dist/docs/quickstart.html +96 -153
  196. package/dist/docs/quickstart.md +93 -178
  197. package/dist/docs/reference/access.html +36 -36
  198. package/dist/docs/reference/access.md +7 -12
  199. package/dist/docs/reference/agent-config.html +43 -56
  200. package/dist/docs/reference/agent-config.md +93 -176
  201. package/dist/docs/reference/artifacts.html +38 -39
  202. package/dist/docs/reference/artifacts.md +38 -62
  203. package/dist/docs/reference/channels.html +38 -39
  204. package/dist/docs/reference/channels.md +102 -151
  205. package/dist/docs/reference/cli.html +68 -84
  206. package/dist/docs/reference/cli.md +233 -698
  207. package/dist/docs/reference/connections.html +45 -57
  208. package/dist/docs/reference/connections.md +83 -164
  209. package/dist/docs/reference/evals.html +66 -53
  210. package/dist/docs/reference/evals.md +97 -128
  211. package/dist/docs/reference/extensions.html +41 -43
  212. package/dist/docs/reference/extensions.md +37 -70
  213. package/dist/docs/reference/hooks.html +40 -52
  214. package/dist/docs/reference/hooks.md +62 -133
  215. package/dist/docs/reference/http-api.html +38 -42
  216. package/dist/docs/reference/http-api.md +66 -118
  217. package/dist/docs/reference/instructions.html +39 -39
  218. package/dist/docs/reference/instructions.md +19 -29
  219. package/dist/docs/reference/limits.html +38 -38
  220. package/dist/docs/reference/limits.md +9 -21
  221. package/dist/docs/reference/memory.html +37 -38
  222. package/dist/docs/reference/memory.md +38 -75
  223. package/dist/docs/reference/playground.html +36 -36
  224. package/dist/docs/reference/playground.md +14 -22
  225. package/dist/docs/reference/project-layout.html +49 -48
  226. package/dist/docs/reference/project-layout.md +38 -84
  227. package/dist/docs/reference/schedules.html +46 -48
  228. package/dist/docs/reference/schedules.md +59 -90
  229. package/dist/docs/reference/sessions.html +37 -37
  230. package/dist/docs/reference/sessions.md +66 -113
  231. package/dist/docs/reference/skills.html +39 -39
  232. package/dist/docs/reference/skills.md +11 -31
  233. package/dist/docs/reference/subagents.html +37 -37
  234. package/dist/docs/reference/subagents.md +17 -31
  235. package/dist/docs/reference/tools.html +47 -64
  236. package/dist/docs/reference/tools.md +48 -130
  237. package/dist/docs/templates/agentic-owners.html +38 -38
  238. package/dist/docs/templates/agentic-owners.md +50 -74
  239. package/dist/docs/templates/reviews.html +69 -0
  240. package/dist/docs/templates/reviews.md +71 -0
  241. package/dist/docs/troubleshooting.html +38 -36
  242. package/dist/docs/troubleshooting.md +48 -101
  243. package/dist/evals.d.ts +2 -2
  244. package/dist/extensions/jev/extension.d.ts +12 -2
  245. package/dist/extensions/jev/extension.d.ts.map +1 -1
  246. package/dist/extensions/jev/extension.js +4 -0
  247. package/dist/extensions/jev/lib/evaluate.d.ts +31 -4
  248. package/dist/extensions/jev/lib/evaluate.d.ts.map +1 -1
  249. package/dist/extensions/jev/lib/evaluate.js +18 -4
  250. package/dist/internal/cli/command.d.ts +1 -1
  251. package/dist/internal/cli/command.js +1 -1
  252. package/dist/internal/cli/commands/channels.js +6 -6
  253. package/dist/internal/cli/commands/develop.d.ts.map +1 -1
  254. package/dist/internal/cli/commands/develop.js +23 -14
  255. package/dist/internal/cli/commands/hosted.js +4 -4
  256. package/dist/internal/cli/commands/index.d.ts +1 -1
  257. package/dist/internal/cli/commands/index.d.ts.map +1 -1
  258. package/dist/internal/cli/commands/index.js +1 -1
  259. package/dist/internal/cli/commands/mcp.js +1 -1
  260. package/dist/internal/cli/commands/project.js +4 -4
  261. package/dist/internal/cli/commands/scaffold.d.ts.map +1 -1
  262. package/dist/internal/cli/commands/scaffold.js +9 -6
  263. package/dist/internal/cli/commands/serve.d.ts +1 -1
  264. package/dist/internal/cli/commands/serve.js +5 -5
  265. package/dist/internal/cli/commands/session.d.ts.map +1 -1
  266. package/dist/internal/cli/commands/session.js +12 -7
  267. package/dist/internal/cli/dispatch.d.ts +3 -3
  268. package/dist/internal/cli/dispatch.js +3 -3
  269. package/dist/internal/cli/errors.d.ts +1 -1
  270. package/dist/internal/cli/errors.d.ts.map +1 -1
  271. package/dist/internal/cli/errors.js +1 -1
  272. package/dist/internal/cli/flags.d.ts +2 -2
  273. package/dist/internal/cli/flags.d.ts.map +1 -1
  274. package/dist/internal/cli/flags.js +2 -2
  275. package/dist/internal/cli/help-command.d.ts +1 -1
  276. package/dist/internal/cli/help-command.js +2 -2
  277. package/dist/internal/cli/help.d.ts +7 -7
  278. package/dist/internal/cli/help.d.ts.map +1 -1
  279. package/dist/internal/cli/help.js +8 -8
  280. package/dist/internal/cli-ax.d.ts.map +1 -1
  281. package/dist/internal/cli-ax.js +3 -0
  282. package/dist/internal/cli-convert-automation.d.ts +1 -1
  283. package/dist/internal/cli-convert-automation.js +1 -1
  284. package/dist/internal/cli-deploy.js +1 -1
  285. package/dist/internal/cli-docs.js +1 -1
  286. package/dist/internal/cli-images.js +1 -1
  287. package/dist/internal/cli-migrate.d.ts +1 -1
  288. package/dist/internal/cli-migrate.js +1 -1
  289. package/dist/internal/cli-pagerduty.d.ts +1 -1
  290. package/dist/internal/cli-pagerduty.js +1 -1
  291. package/dist/internal/cli-skills.js +1 -1
  292. package/dist/internal/convert-automation/types.d.ts +1 -1
  293. package/dist/internal/convert-automation/types.js +1 -1
  294. package/dist/internal/cursor/credentials.js +1 -1
  295. package/dist/internal/deploy-client.d.ts +2 -2
  296. package/dist/internal/deploy-client.d.ts.map +1 -1
  297. package/dist/internal/deploy-manifest.d.ts +1 -0
  298. package/dist/internal/deploy-manifest.d.ts.map +1 -1
  299. package/dist/internal/deploy-manifest.js +0 -1
  300. package/dist/internal/discovery/agent-config.d.ts +2 -6
  301. package/dist/internal/discovery/agent-config.d.ts.map +1 -1
  302. package/dist/internal/discovery/agent-config.js +8 -25
  303. package/dist/internal/discovery/agent.d.ts.map +1 -1
  304. package/dist/internal/discovery/agent.js +2 -3
  305. package/dist/internal/discovery/project.d.ts.map +1 -1
  306. package/dist/internal/discovery/project.js +15 -0
  307. package/dist/internal/init-project.d.ts +7 -3
  308. package/dist/internal/init-project.d.ts.map +1 -1
  309. package/dist/internal/init-project.js +60 -12
  310. package/dist/internal/init-scaffold.d.ts +2 -1
  311. package/dist/internal/init-scaffold.d.ts.map +1 -1
  312. package/dist/internal/init-scaffold.js +20 -7
  313. package/dist/internal/peer-connections.js +1 -1
  314. package/dist/internal/reminder-runner.js +1 -1
  315. package/dist/internal/server.d.ts +1 -1
  316. package/dist/internal/session-cost.d.ts +4 -4
  317. package/dist/internal/session-cost.d.ts.map +1 -1
  318. package/dist/internal/session-cost.js +4 -4
  319. package/dist/internal/session-engine.d.ts +1 -1
  320. package/dist/internal/session-engine.js +2 -2
  321. package/dist/internal/shallow-clone.js +1 -1
  322. package/dist/playground/assets/index-D6mVn9og.js +62 -0
  323. package/dist/playground/assets/index-DlALM6gr.css +1 -0
  324. package/dist/playground/index.html +2 -2
  325. package/dist/types.d.ts +9 -22
  326. package/dist/types.d.ts.map +1 -1
  327. package/docs/README.md +49 -82
  328. package/docs/building-with-agents.md +11 -104
  329. package/docs/changelog.md +6 -146
  330. package/docs/deployment.md +86 -265
  331. package/docs/evals.md +34 -128
  332. package/docs/guides/agent-to-agent.md +27 -64
  333. package/docs/guides/bitbucket.md +73 -134
  334. package/docs/guides/cloud-agents.md +23 -53
  335. package/docs/guides/convert-automation.md +31 -115
  336. package/docs/guides/github.md +49 -131
  337. package/docs/guides/gitlab.md +104 -184
  338. package/docs/guides/improve.md +24 -90
  339. package/docs/guides/jev.md +57 -159
  340. package/docs/guides/mcp-oauth.md +34 -69
  341. package/docs/guides/migrate.md +56 -130
  342. package/docs/guides/opentelemetry.md +37 -27
  343. package/docs/guides/pagerduty.md +68 -200
  344. package/docs/guides/slack.md +76 -205
  345. package/docs/guides/webhooks.md +64 -146
  346. package/docs/hillclimbing.md +41 -103
  347. package/docs/quickstart.md +93 -178
  348. package/docs/reference/access.md +7 -12
  349. package/docs/reference/agent-config.md +93 -176
  350. package/docs/reference/artifacts.md +38 -62
  351. package/docs/reference/channels.md +102 -151
  352. package/docs/reference/cli.md +233 -698
  353. package/docs/reference/connections.md +83 -164
  354. package/docs/reference/evals.md +97 -128
  355. package/docs/reference/extensions.md +37 -70
  356. package/docs/reference/hooks.md +61 -132
  357. package/docs/reference/http-api.md +66 -118
  358. package/docs/reference/instructions.md +20 -30
  359. package/docs/reference/limits.md +10 -22
  360. package/docs/reference/memory.md +38 -75
  361. package/docs/reference/playground.md +14 -22
  362. package/docs/reference/project-layout.md +38 -84
  363. package/docs/reference/schedules.md +59 -90
  364. package/docs/reference/sessions.md +66 -113
  365. package/docs/reference/skills.md +12 -32
  366. package/docs/reference/subagents.md +17 -31
  367. package/docs/reference/tools.md +48 -130
  368. package/docs/templates/agentic-owners.md +50 -74
  369. package/docs/templates/reviews.md +76 -0
  370. package/docs/troubleshooting.md +48 -101
  371. package/package.json +3 -9
  372. package/skills/cli/SKILL.md +15 -15
  373. package/skills/create-agent/SKILL.md +20 -19
  374. package/skills/debug/SKILL.md +4 -4
  375. package/skills/deploy/SKILL.md +2 -2
  376. package/skills/evals/SKILL.md +8 -8
  377. package/skills/framework-map/SKILL.md +3 -3
  378. package/skills/github/SKILL.md +7 -7
  379. package/skills/hillclimb/SKILL.md +4 -4
  380. package/skills/mcp-auth/SKILL.md +3 -3
  381. package/skills/migrate-v2/SKILL.md +40 -41
  382. package/skills/otel/SKILL.md +2 -2
  383. package/skills/setup-slack/SKILL.md +8 -8
  384. package/templates/agentic-owners/README.md +5 -5
  385. package/templates/agentic-owners/bot/tools/record_review.ts +1 -1
  386. package/templates/agentic-owners/package.json +1 -1
  387. package/templates/agents-md/README.md +4 -4
  388. package/templates/agents-md/package.json +1 -1
  389. package/templates/code-wiki/README.md +3 -3
  390. package/templates/code-wiki/package.json +1 -1
  391. package/templates/demo/README.md +3 -3
  392. package/templates/demo/package.json +1 -1
  393. package/templates/pr-autofixer/package.json +1 -1
  394. package/templates/security-help/README.md +5 -5
  395. package/templates/security-help/package.json +1 -1
  396. package/templates/security-reviewer/README.md +3 -3
  397. package/templates/security-reviewer/package.json +1 -1
  398. package/templates/thermo-quality-review/README.md +4 -4
  399. package/templates/thermo-quality-review/package.json +1 -1
  400. package/templates/thermo-review/README.md +4 -4
  401. package/templates/thermo-review/package.json +1 -1
  402. package/templates/triage/README.md +3 -3
  403. package/templates/triage/overlays/jira/README.md +3 -3
  404. package/templates/triage/overlays/linear/README.md +3 -3
  405. package/templates/triage/package.json +1 -1
  406. package/dist/docs/assets/building-with-agents.md.Bf1yH2tG.js +0 -9
  407. package/dist/docs/assets/changelog.md.fZ-NNFeJ.js +0 -1
  408. package/dist/docs/assets/changelog.md.fZ-NNFeJ.lean.js +0 -1
  409. package/dist/docs/assets/chunks/@localSearchIndexroot.mfzjiOsL.js +0 -1
  410. package/dist/docs/assets/chunks/channel.goFR5lbe.js +0 -1
  411. package/dist/docs/assets/chunks/classDiagram-6PBFFD2Q.B2yLtFja.js +0 -1
  412. package/dist/docs/assets/chunks/classDiagram-v2-HSJHXN6E.B2yLtFja.js +0 -1
  413. package/dist/docs/assets/chunks/clone.CztV97Wu.js +0 -1
  414. package/dist/docs/assets/chunks/stateDiagram-v2-QKLJ7IA2.CZlVHdDZ.js +0 -1
  415. package/dist/docs/assets/deployment.md.DDmjAVbg.js +0 -31
  416. package/dist/docs/assets/evals.md.OjKb7tNA.js +0 -68
  417. package/dist/docs/assets/evals.md.OjKb7tNA.lean.js +0 -1
  418. package/dist/docs/assets/guides_agent-to-agent.md.D1D5f6Jc.lean.js +0 -1
  419. package/dist/docs/assets/guides_cloud-agents.md.Ceyjv0ul.js +0 -9
  420. package/dist/docs/assets/guides_convert-automation.md.BjraCvok.js +0 -43
  421. package/dist/docs/assets/guides_grokbot-agents.md.D0PpM_Gf.js +0 -15
  422. package/dist/docs/assets/guides_grokbot-agents.md.D0PpM_Gf.lean.js +0 -1
  423. package/dist/docs/assets/guides_hooks.md.BjeEiM7s.js +0 -54
  424. package/dist/docs/assets/guides_hooks.md.BjeEiM7s.lean.js +0 -1
  425. package/dist/docs/assets/guides_improve.md.BFYtrtLE.js +0 -21
  426. package/dist/docs/assets/guides_migrate.md.RS9Eu-Xh.js +0 -8
  427. package/dist/docs/assets/guides_opentelemetry.md.CoZ1kNyd.js +0 -28
  428. package/dist/docs/assets/guides_opentelemetry.md.CoZ1kNyd.lean.js +0 -1
  429. package/dist/docs/assets/guides_pagerduty.md.mnKXe9U0.js +0 -60
  430. package/dist/docs/assets/guides_pagerduty.md.mnKXe9U0.lean.js +0 -1
  431. package/dist/docs/assets/guides_slack.md.BqiGSYGX.js +0 -88
  432. package/dist/docs/assets/hillclimbing.md.By61f3uq.js +0 -7
  433. package/dist/docs/assets/hillclimbing.md.By61f3uq.lean.js +0 -1
  434. package/dist/docs/assets/index.md.CVRjO09Y.js +0 -27
  435. package/dist/docs/assets/index.md.CVRjO09Y.lean.js +0 -1
  436. package/dist/docs/assets/quickstart.md.DaLk4ZIF.js +0 -170
  437. package/dist/docs/assets/reference_access.md.CExlH_mR.js +0 -1
  438. package/dist/docs/assets/reference_agent-config.md.11E_xe--.js +0 -40
  439. package/dist/docs/assets/reference_artifacts.md.C-hKR2hp.js +0 -18
  440. package/dist/docs/assets/reference_channels.md.DsJfGSBJ.js +0 -22
  441. package/dist/docs/assets/reference_cli.md.DQ3dCgmk.js +0 -99
  442. package/dist/docs/assets/reference_cli.md.DQ3dCgmk.lean.js +0 -1
  443. package/dist/docs/assets/reference_connections.md.BoAotr7_.js +0 -66
  444. package/dist/docs/assets/reference_evals.md.DYKjGFi-.js +0 -56
  445. package/dist/docs/assets/reference_hooks.md.B-bwJuiG.js +0 -51
  446. package/dist/docs/assets/reference_hooks.md.B-bwJuiG.lean.js +0 -1
  447. package/dist/docs/assets/reference_http-api.md._RWELr3d.js +0 -11
  448. package/dist/docs/assets/reference_instructions.md.yL2hXLnl.js +0 -14
  449. package/dist/docs/assets/reference_instructions.md.yL2hXLnl.lean.js +0 -1
  450. package/dist/docs/assets/reference_limits.md.Da1HegjB.js +0 -8
  451. package/dist/docs/assets/reference_limits.md.Da1HegjB.lean.js +0 -1
  452. package/dist/docs/assets/reference_memory.md.Dd7cyV9V.js +0 -4
  453. package/dist/docs/assets/reference_playground.md.CQiJk9CM.js +0 -1
  454. package/dist/docs/assets/reference_project-layout.md.BamcPDUn.js +0 -25
  455. package/dist/docs/assets/reference_project-layout.md.BamcPDUn.lean.js +0 -1
  456. package/dist/docs/assets/reference_prompt.md.BMjm1Jp3.js +0 -9
  457. package/dist/docs/assets/reference_prompt.md.BMjm1Jp3.lean.js +0 -1
  458. package/dist/docs/assets/reference_schedules.md.RC47aFm4.js +0 -47
  459. package/dist/docs/assets/reference_sessions.md.C7KFhWXV.js +0 -22
  460. package/dist/docs/assets/reference_subagents.md.CAhvW4yS.js +0 -10
  461. package/dist/docs/assets/reference_tools.md.DQr7Fnhu.js +0 -79
  462. package/dist/docs/assets/templates_agentic-owners.md.Dh2nDSqg.js +0 -13
  463. package/dist/docs/assets/templates_security-reviewer.md.DnwXdnB5.js +0 -3
  464. package/dist/docs/assets/templates_security-reviewer.md.DnwXdnB5.lean.js +0 -1
  465. package/dist/docs/assets/templates_thermo-quality-review.md.MJIdHkzE.js +0 -3
  466. package/dist/docs/assets/templates_thermo-quality-review.md.MJIdHkzE.lean.js +0 -1
  467. package/dist/docs/assets/templates_thermo-review.md.DfN1OFOl.js +0 -3
  468. package/dist/docs/assets/templates_thermo-review.md.DfN1OFOl.lean.js +0 -1
  469. package/dist/docs/assets/templates_triage.md.BYWMloV4.js +0 -9
  470. package/dist/docs/assets/templates_triage.md.BYWMloV4.lean.js +0 -1
  471. package/dist/docs/assets/troubleshooting.md.AGJ3jDzj.js +0 -1
  472. package/dist/docs/guides/grokbot-agents.html +0 -74
  473. package/dist/docs/guides/grokbot-agents.md +0 -129
  474. package/dist/docs/guides/hooks.html +0 -113
  475. package/dist/docs/guides/hooks.md +0 -116
  476. package/dist/docs/reference/prompt.html +0 -68
  477. package/dist/docs/reference/prompt.md +0 -47
  478. package/dist/docs/templates/security-reviewer.html +0 -62
  479. package/dist/docs/templates/security-reviewer.md +0 -81
  480. package/dist/docs/templates/thermo-quality-review.html +0 -62
  481. package/dist/docs/templates/thermo-quality-review.md +0 -75
  482. package/dist/docs/templates/thermo-review.html +0 -62
  483. package/dist/docs/templates/thermo-review.md +0 -75
  484. package/dist/docs/templates/triage.html +0 -68
  485. package/dist/docs/templates/triage.md +0 -101
  486. package/dist/extensions/cursor-grokbot-agents/extension.d.ts +0 -71
  487. package/dist/extensions/cursor-grokbot-agents/extension.d.ts.map +0 -1
  488. package/dist/extensions/cursor-grokbot-agents/extension.js +0 -64
  489. package/dist/extensions/cursor-grokbot-agents/lib/agents.d.ts +0 -11
  490. package/dist/extensions/cursor-grokbot-agents/lib/agents.d.ts.map +0 -1
  491. package/dist/extensions/cursor-grokbot-agents/lib/agents.js +0 -31
  492. package/dist/extensions/cursor-grokbot-agents/lib/backend.d.ts +0 -56
  493. package/dist/extensions/cursor-grokbot-agents/lib/backend.d.ts.map +0 -1
  494. package/dist/extensions/cursor-grokbot-agents/lib/backend.js +0 -139
  495. package/dist/extensions/cursor-grokbot-agents/lib/contacts.d.ts +0 -28
  496. package/dist/extensions/cursor-grokbot-agents/lib/contacts.d.ts.map +0 -1
  497. package/dist/extensions/cursor-grokbot-agents/lib/contacts.js +0 -46
  498. package/dist/extensions/cursor-grokbot-agents/lib/conversation.d.ts +0 -53
  499. package/dist/extensions/cursor-grokbot-agents/lib/conversation.d.ts.map +0 -1
  500. package/dist/extensions/cursor-grokbot-agents/lib/conversation.js +0 -186
  501. package/dist/extensions/cursor-grokbot-agents/lib/inputs.d.ts +0 -4
  502. package/dist/extensions/cursor-grokbot-agents/lib/inputs.d.ts.map +0 -1
  503. package/dist/extensions/cursor-grokbot-agents/lib/inputs.js +0 -15
  504. package/dist/extensions/cursor-grokbot-agents/lib/lock.d.ts +0 -12
  505. package/dist/extensions/cursor-grokbot-agents/lib/lock.d.ts.map +0 -1
  506. package/dist/extensions/cursor-grokbot-agents/lib/lock.js +0 -24
  507. package/dist/extensions/cursor-grokbot-agents/skills/consult.md +0 -40
  508. package/dist/extensions/cursor-grokbot-agents/tools/ask.d.ts +0 -4
  509. package/dist/extensions/cursor-grokbot-agents/tools/ask.d.ts.map +0 -1
  510. package/dist/extensions/cursor-grokbot-agents/tools/ask.js +0 -26
  511. package/dist/extensions/cursor-grokbot-agents/tools/check.d.ts +0 -4
  512. package/dist/extensions/cursor-grokbot-agents/tools/check.d.ts.map +0 -1
  513. package/dist/extensions/cursor-grokbot-agents/tools/check.js +0 -21
  514. package/dist/extensions/cursor-grokbot-agents/tools/interrupt.d.ts +0 -4
  515. package/dist/extensions/cursor-grokbot-agents/tools/interrupt.d.ts.map +0 -1
  516. package/dist/extensions/cursor-grokbot-agents/tools/interrupt.js +0 -13
  517. package/dist/extensions/cursor-grokbot-agents/tools/list.d.ts +0 -4
  518. package/dist/extensions/cursor-grokbot-agents/tools/list.d.ts.map +0 -1
  519. package/dist/extensions/cursor-grokbot-agents/tools/list.js +0 -22
  520. package/dist/playground/assets/index-BMpVzZzC.css +0 -1
  521. package/dist/playground/assets/index-_3zz3yh8.js +0 -62
  522. package/docs/guides/grokbot-agents.md +0 -134
  523. package/docs/guides/hooks.md +0 -121
  524. package/docs/reference/prompt.md +0 -52
  525. package/docs/templates/security-reviewer.md +0 -86
  526. package/docs/templates/thermo-quality-review.md +0 -80
  527. package/docs/templates/thermo-review.md +0 -80
  528. package/docs/templates/triage.md +0 -106
package/docs/evals.md CHANGED
@@ -1,26 +1,18 @@
1
1
  ---
2
2
  title: "Evals"
3
- description: "Protect agent decisions with fixed inputs, trajectory assertions, and regression checks that run locally or in CI."
3
+ description: "Measure and Improve agent behavior with Evals"
4
4
  ---
5
5
 
6
6
  # Evals
7
7
 
8
- An eval sends a fixed input to the real agent and checks the resulting
9
- trajectory: whether the turn succeeded, which tools ran, and what shape
10
- the answer took. Use evals to protect behavior you already understand,
11
- not to discover what the prompt should do.
8
+ An eval sends a fixed input to the real agent and checks which tools ran and what the answer looks
9
+ like. To improve an agent and lock each win with an eval, follow [Hillclimbing](./hillclimbing.md).
12
10
 
13
- Evals run real model turns and real tools. Guard external writes before
14
- running a suite against an agent that can post, merge, or deploy.
11
+ Evals run real tools, so [guard any writes](#keep-side-effects-out-of-eval-sessions) first.
15
12
 
16
13
  ## Protect a tool decision
17
14
 
18
- This smoke case asks for a PR verdict, requires the read-only inspection
19
- tool, and fails if the agent tries to approve. The CLI reports all three
20
- decisions together instead of stopping at the first miss.
21
-
22
- Use the [Jev extension](./guides/jev.md) when host code needs a typed
23
- choice, score, or boolean before it writes.
15
+ The case below passes only if the agent calls the inspection tool and doesn't approve.
24
16
 
25
17
  ```ts
26
18
  // evals/readiness.eval.ts
@@ -29,9 +21,7 @@ import { defineEval, includes } from "@grok/agent-sdk/evals";
29
21
  export default defineEval({
30
22
  tags: ["smoke"],
31
23
  async test(t) {
32
- await t.send(
33
- "Is https://github.com/acme/checkout/pull/42 ready to approve?"
34
- );
24
+ await t.send("Is https://github.com/acme/checkout/pull/42 ready to approve?");
35
25
 
36
26
  t.succeeded();
37
27
  t.calledTool("inspect_pr");
@@ -41,8 +31,7 @@ export default defineEval({
41
31
  });
42
32
  ```
43
33
 
44
- Evals live in the project-root `evals/` directory, beside `bot/`.
45
- Add the required concurrency config once:
34
+ Evals live in `evals/` beside `bot/`. Set how many cases run at once:
46
35
 
47
36
  ```ts
48
37
  // evals/evals.config.ts
@@ -53,52 +42,34 @@ export default defineEvalConfig({
53
42
  });
54
43
  ```
55
44
 
56
- ```text
45
+ ```bash
57
46
  agent-sdk eval --dir . --list
58
47
  agent-sdk eval --dir . --tag smoke
59
48
  ```
60
49
 
61
50
  ## Check answer shape or quality
62
51
 
63
- Prefer a deterministic shape check when the output has a contract. The
64
- failure tells you which field was wrong, and the case remains stable
65
- when the model changes its wording.
52
+ When the output has a contract, check its shape:
66
53
 
67
54
  ```ts
68
55
  import { matches } from "@grok/agent-sdk/evals";
69
56
  import { z } from "zod";
70
57
 
71
58
  const verdict = JSON.parse(t.reply ?? "{}");
72
- t.check(
73
- verdict,
74
- matches(
75
- z.object({
76
- ready: z.boolean(),
77
- blockers: z.array(z.string()),
78
- })
79
- )
80
- );
59
+ t.check(verdict, matches(z.object({ ready: z.boolean(), blockers: z.array(z.string()) })));
81
60
  ```
82
61
 
83
- Use a judge when correctness depends on meaning that a schema, regex, or
84
- known value cannot capture:
62
+ When correctness depends on meaning, use a judge. [Judges](./reference/evals.md#judges) covers
63
+ models and grader options.
85
64
 
86
65
  ```ts
87
- t.judge
88
- .factuality("The lint step failed on src/sidebar.ts.")
89
- .atLeast(0.8);
66
+ t.judge.factuality("The lint step failed on src/sidebar.ts.").atLeast(0.8);
90
67
  ```
91
68
 
92
- Judge checks are tracked scores until you give them a hard gate.
93
- Configure the judge model in `evals.config.ts`. The
94
- [Evals reference](./reference/evals.md#judges) owns grader options and
95
- severity rules.
96
-
97
69
  ## Test a conversation
98
70
 
99
- Several `t.send` calls in one case share a session. Assertions on a
100
- returned turn inspect only that turn, while assertions on `t` inspect
101
- the whole conversation.
71
+ Several `t.send` calls in one case share a session. An assertion on a returned turn checks only that
72
+ turn, and an assertion on `t` checks the whole conversation.
102
73
 
103
74
  ```ts
104
75
  const first = await t.send("Inspect PR 42.");
@@ -112,9 +83,7 @@ t.succeeded();
112
83
 
113
84
  ## Pin realistic inputs
114
85
 
115
- A useful eval changes only when the agent changes. Freeze canonical chat
116
- prompts, seed workspace evidence directly, and save webhook payloads
117
- instead of depending on a developer's checkout or live external state.
86
+ Seed the files the agent reads instead of depending on your checkout:
118
87
 
119
88
  ```ts
120
89
  await t.send("Review pr/diff.patch and report blockers.", {
@@ -127,47 +96,32 @@ await t.send("Review pr/diff.patch and report blockers.", {
127
96
  });
128
97
  ```
129
98
 
130
- For GitHub agents, snapshot a PR into committed fixtures:
99
+ Save a GitHub pull request's webhook payloads as fixtures:
131
100
 
132
- ```text
133
- agent-sdk github replay acme/checkout#42 \
134
- --events '*' \
135
- --dry-run \
136
- --out fixtures/github
101
+ ```bash
102
+ agent-sdk github replay https://github.com/acme/checkout/pull/42 \
103
+ --events '*' --dry-run --fixtures-dir fixtures/github
137
104
  ```
138
105
 
139
- Keep a small, fast `smoke` set for every change. Put larger datasets and
140
- drift-prone live cases behind an explicit selection. See
141
- [Datasets and fixtures](./reference/evals.md#datasets-and-fixtures) for
142
- loaders and case expansion.
106
+ [Datasets and fixtures](./reference/evals.md#datasets-and-fixtures) covers loaders for larger sets.
143
107
 
144
108
  ## Run and debug a regression suite
145
109
 
146
- Run one case while iterating, then the smoke suite before review. A
147
- failure artifact records the input, assertions, tool calls, and final
148
- text, making it the first place to look before changing the prompt.
110
+ Run one case while you iterate, then the smoke set before review:
149
111
 
150
- ```text
112
+ ```bash
151
113
  agent-sdk eval --dir . readiness
152
114
  agent-sdk eval --dir . --tag smoke
153
- agent-sdk eval --dir . --json
154
115
  ```
155
116
 
156
- By default, results land under `evals/<stamp>/` in the project state
157
- directory. Open `evals/<case-id>.json` inside that run directory for the
158
- failed case. This artifact location is independent of `--state-root`;
159
- pass `--artifacts <dir>` to choose another destination.
160
-
161
- Model turns need a credential. Resolution checks `CURSOR_API_KEY`,
162
- `CURSOR_API_KEY_FILE`, `CURSOR_SERVICE_ACCOUNT_KEY`, then a saved
163
- `agent-sdk login`. `eval --list` only discovers cases and needs none.
117
+ Each run writes a folder under `evals/` in the project state directory, or under `--artifacts <dir>`
118
+ if you pass it. Open `evals/<case-id>.json` in that folder to see a failed case's input, assertions,
119
+ tool calls, and final text. Model turns need a
120
+ [Cursor credential](./reference/cli.md#environment-variables).
164
121
 
165
122
  ## Run evals in CI
166
123
 
167
- Write machine-readable output and JUnit annotations, then let a failed
168
- gate fail the job:
169
-
170
- ```text
124
+ ```bash
171
125
  # CURSOR_API_KEY comes from the CI secret store.
172
126
  agent-sdk eval --dir . --json --no-stream \
173
127
  --junit reports/evals.xml \
@@ -175,70 +129,22 @@ agent-sdk eval --dir . --json --no-stream \
175
129
  > reports/evals.json
176
130
  ```
177
131
 
178
- Run `--tag smoke` on pull requests and the full suite on a schedule when
179
- cost or latency makes every-push coverage impractical. Use soft scores
180
- for a new probabilistic benchmark until its threshold is trustworthy.
181
-
182
- The [CLI reference](./reference/cli.md#eval) covers selectors,
183
- server-side batches, exit codes, and JSON output.
132
+ Run `--tag smoke` on pull requests and the full suite on a schedule. The
133
+ [CLI reference](./reference/cli.md#eval) covers every flag.
184
134
 
185
135
  ## Keep side effects out of eval sessions
186
136
 
187
- Eval sessions carry `purpose: "eval"`. Check it at the deterministic
188
- write boundary and return the decision without performing the external
189
- action:
137
+ Eval sessions carry `purpose: "eval"`. Check it where the tool writes, and return the decision
138
+ without the external action:
190
139
 
191
140
  ```ts
192
141
  async execute({ findings }, ctx) {
193
142
  if (ctx.session.purpose === "eval") {
194
- return {
195
- posted: false,
196
- reason: "eval",
197
- count: findings.length,
198
- };
143
+ return { posted: false, reason: "eval", count: findings.length };
199
144
  }
200
145
 
201
146
  return await postFindings(findings);
202
147
  }
203
148
  ```
204
149
 
205
- This preserves the tool call in the trajectory, so the eval can still
206
- assert that the agent chose to post.
207
-
208
- ## Evals, hooks, or hillclimbing?
209
-
210
- Use an eval to gate one fixed input. Use a
211
- [hook](./reference/hooks.md) to observe every live session for metrics,
212
- auditing, or alerts. Use [hillclimbing](./hillclimbing.md) to decide
213
- which source change improves a fixed set of inputs; every kept
214
- hillclimb change should add an eval.
215
-
216
- ## Gates and scores
217
-
218
- `t.succeeded()`, tool assertions, and deterministic checks are hard
219
- gates by default. A failed gate fails the case. `.soft()` records a
220
- measurement without blocking, while `.atLeast(threshold)` records a
221
- score and marks a miss as `scored`.
222
-
223
- Start with decisions and output shape: the intended tool, the tempting
224
- wrong tool, and one structural check. Exact prose is rarely a stable
225
- contract.
226
-
227
- ## Keep improvements with regression evals
228
-
229
- Every kept improvement needs an eval that would have failed before the
230
- change. A tool-choice gate, bounded `maxToolCalls`, or output-shape check
231
- turns the improvement into a durable contract.
232
-
233
- Never weaken an existing gate to make a new implementation pass. That
234
- moves the freeze line instead of proving the change.
235
-
236
- ## Related
237
-
238
- - [Evals reference](./reference/evals.md): complete authoring and runner
239
- contracts
240
- - [`skills/evals/SKILL.md`](../skills/evals/SKILL.md): author and seed
241
- cases with a coding agent
242
- - [Hillclimbing](./hillclimbing.md): measure a change and lock the win
243
- - [Sessions](./reference/sessions.md): events available to trajectory
244
- assertions
150
+ The tool call stays in the trajectory, so the eval can still assert that the agent chose to post.
@@ -5,18 +5,15 @@ description: "Let one Agent SDK agent consult an independent specialist, continu
5
5
 
6
6
  # Peer agents
7
7
 
8
- A peer connection lets one agent ask an independent specialist for help.
9
- On Cursor-managed hosting, team-owned agents reach peers by deployment
10
- slug. Deploy both agents and Agent SDK handles routing and authentication; you
11
- don't configure a URL, header, or secret. The specialist keeps its own
12
- instructions, tools, and session while the caller decides when to delegate
13
- and returns the answer to the user.
8
+ A peer connection lets one agent ask an independent specialist for help. The
9
+ specialist keeps its own instructions, tools, and sessions. On Cursor hosting,
10
+ team-owned agents reach each other by deployment slug, and Agent SDK handles
11
+ routing and authentication for you.
14
12
 
15
13
  ## Delegate a question to a specialist
16
14
 
17
- Ask the concierge about the weather and it hands the question to the
18
- specialist. The weather agent answers in its own context, then the
19
- concierge returns that answer to you.
15
+ Ask the concierge about the weather, and it hands the question to the weather
16
+ agent and returns the answer.
20
17
 
21
18
  ```ts
22
19
  // bot/mcp-connections/weather.ts
@@ -28,30 +25,27 @@ export default defineConnection({
28
25
  });
29
26
  ```
30
27
 
31
- Give the concierge a narrow routing rule:
28
+ The filename, `weather.ts`, becomes the
29
+ [MCP server name](../reference/connections.md#peer-mcp-connection), and `agent`
30
+ is the specialist's lowercase deployment slug. Give the concierge a one-way
31
+ routing rule, so the agents never pass a request back and forth:
32
32
 
33
33
  ```md
34
34
  When a request needs current weather, ask the `weather` peer. Return its
35
35
  answer.
36
36
  ```
37
37
 
38
- Deploy the specialist and caller from pushed Git refs:
38
+ Deploy both agents from pushed Git refs:
39
39
 
40
40
  ```bash
41
41
  agent-sdk deploy --dir ./agents/weather-agent --slug weather-agent
42
42
  agent-sdk deploy --dir ./agents/concierge --slug concierge
43
43
  ```
44
44
 
45
- The connection filename, `weather.ts`, becomes the MCP server name the
46
- concierge calls. Set `agent` to the specialist's lowercase deployment slug.
47
-
48
45
  ## Continue the specialist's session
49
46
 
50
- Ask a follow-up about the same forecast and the specialist picks up
51
- where it left off, with its own instructions and tool history still in
52
- place. The first `ask` returns `{ status, sessionId, reply }` as text on
53
- the `callTool` result. Parse `sessionId` and pass it on the next `ask`
54
- so the peer remembers its earlier work instead of starting fresh.
47
+ The first `ask` returns `{ status, sessionId, reply }` as text. Pass that
48
+ `sessionId` on the next `ask` to continue the specialist's earlier work.
55
49
 
56
50
  ```ts
57
51
  const first = await ctx.host.mcp.callTool("weather", "ask", {
@@ -69,8 +63,8 @@ await ctx.host.mcp.callTool("weather", "ask", {
69
63
  });
70
64
  ```
71
65
 
72
- If the specialist is still working, `ask` returns `status: "running"`
73
- with the session ID, and you can do other work before calling `check`.
66
+ If the specialist is still working, `ask` returns `status: "running"`, and
67
+ `check` waits for the answer.
74
68
 
75
69
  ```ts
76
70
  await ctx.host.mcp.callTool("weather", "check", {
@@ -79,14 +73,12 @@ await ctx.host.mcp.callTool("weather", "check", {
79
73
  });
80
74
  ```
81
75
 
82
- The peer owns this session, so follow-ups continue the specialist's
83
- context.
84
-
85
- ## Call a deterministic peer tool
76
+ ## Call a peer tool directly
86
77
 
87
- You need a forecast for Paris, and the weather agent already has
88
- `get_forecast`. Host code calls that tool in the specialist's workspace
89
- and the forecast comes back to the concierge, with no second model turn.
78
+ Use `call_tool` when you want to run a tool on a peer agent directly, without
79
+ starting a model turn on that agent. The peer needs at least one server tool,
80
+ and the call follows the
81
+ [direct-call rules](../reference/tools.md#call-a-tool-without-a-model-turn).
90
82
 
91
83
  ```ts
92
84
  const result = await ctx.host.mcp.callTool("weather", "call_tool", {
@@ -108,12 +100,9 @@ return {
108
100
  };
109
101
  ```
110
102
 
111
- `call_tool` appears only when the peer declares at least one
112
- deterministic server tool.
113
-
114
103
  ## Try it locally
115
104
 
116
- Run both projects under one process to try the same connection locally:
105
+ To try it locally, run both projects in one process:
117
106
 
118
107
  ```bash
119
108
  agent-sdk dev ./agents
@@ -121,14 +110,12 @@ agent-sdk chat --url http://127.0.0.1:3000/concierge \
121
110
  --message "What's the weather in Paris right now?"
122
111
  ```
123
112
 
124
- In a local multi-agent serve, `agent` is the specialist's mount slug,
125
- normally its directory name.
113
+ Locally, `agent` is the specialist's mount slug, usually its directory name.
126
114
 
127
115
  ## Peer or subagent?
128
116
 
129
- Use a [subagent](../reference/subagents.md) to split one agent's job
130
- into roles that share its project. Use a peer when the specialist is a
131
- complete agent you would also run, inspect, or expose on its own.
117
+ Use a [subagent](../reference/subagents.md) to split one agent's job into roles.
118
+ Use a peer when the specialist is a complete agent you also run on its own.
132
119
 
133
120
  | | Subagent | Peer |
134
121
  | --- | --- | --- |
@@ -136,32 +123,8 @@ complete agent you would also run, inspect, or expose on its own.
136
123
  | Tools and connections | Inherits the parent project | Owns its project surface |
137
124
  | Reachability | Parent only | Local co-hosted agents, or declared deployments on the same team |
138
125
 
139
- ## Affinity
140
-
141
- Peer sessions appear in the specialist's playground. Only the calling
142
- deployment can continue a hosted peer session.
143
-
144
- ## Practices
145
-
146
- - Give each caller a one-way routing rule, and don't configure reciprocal
147
- routes for the same request.
148
-
149
- - Prefer `ask` when the specialist should reason. Use `call_tool` when
150
- host code already knows which server tool to run.
151
-
152
126
  ## Other hosts
153
127
 
154
- For self-hosting, run peers under one `agent-sdk` process. If turns run on remote
155
- workers, protect the process with `--bearer-token` and set its external URL
156
- with `--public-url`. Hosts that run one agent per process can supply
157
- `--peers-url`; Cursor-managed hosting configures it automatically. See
158
- [Deployment](../deployment.md) for the secure hosting setup.
159
-
160
- ## Related
161
-
162
- - [MCP connections](../reference/connections.md#peer-mcp-connection):
163
- peer configuration and connection naming
164
- - [MCP endpoint](../reference/http-api.md#mcp-endpoint): exact `ask`,
165
- `check`, and `call_tool` schemas
166
- - [Subagents](../reference/subagents.md): specialists inside one agent
167
- - [Deployment](../deployment.md): secure shared-host setup
128
+ To self-host, run the peers under one `agent-sdk` process, and if turns run on
129
+ remote workers, protect it with `--bearer-token` and set `--public-url` as
130
+ [Deployment](../deployment.md) describes.