@cursor/july 0.1.109 → 0.1.111
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.
- package/AGENTS.md +1 -1
- package/README.md +0 -15
- package/dist/bin/agent-serve.js +81 -66
- package/dist/channels/bitbucket/api.js +8 -8
- package/dist/channels/bitbucket/binding.js +4 -4
- package/dist/channels/bitbucket/bitbucket-channel.js +1 -1
- package/dist/channels/bitbucket/bitbucket-webhook.js +1 -1
- package/dist/channels/bitbucket/checks.d.ts.map +1 -1
- package/dist/channels/bitbucket/checks.js +1 -1
- package/dist/channels/bitbucket/cursor-account.js +1 -1
- package/dist/channels/bitbucket/events.js +1 -1
- package/dist/channels/change-monitors/change-monitors-channel.js +1 -1
- package/dist/channels/checks.d.ts.map +1 -1
- package/dist/channels/checks.js +2 -2
- package/dist/channels/deployments/deployments-channel.js +1 -1
- package/dist/channels/github/cursor-account.js +3 -3
- package/dist/channels/github/defaults.d.ts.map +1 -1
- package/dist/channels/github/defaults.js +5 -3
- package/dist/channels/github/events.js +1 -1
- package/dist/channels/github/forward.js +8 -8
- package/dist/channels/github/github-channel.d.ts.map +1 -1
- package/dist/channels/github/github-channel.js +17 -13
- package/dist/channels/github/progress.d.ts.map +1 -1
- package/dist/channels/github/progress.js +7 -2
- package/dist/channels/github/state.d.ts +6 -0
- package/dist/channels/github/state.d.ts.map +1 -1
- package/dist/channels/github/types.d.ts +6 -0
- package/dist/channels/github/types.d.ts.map +1 -1
- package/dist/channels/gitlab/binding.js +4 -4
- package/dist/channels/gitlab/checks.d.ts.map +1 -1
- package/dist/channels/gitlab/checks.js +1 -1
- package/dist/channels/gitlab/cursor-account.js +1 -1
- package/dist/channels/gitlab/events.js +1 -1
- package/dist/channels/gitlab/gitlab-channel.js +1 -1
- package/dist/channels/gitlab/gitlab-webhook.js +1 -1
- package/dist/channels/gitlab/replay.js +2 -2
- package/dist/channels/origin/binding.d.ts +2 -0
- package/dist/channels/origin/binding.d.ts.map +1 -1
- package/dist/channels/origin/binding.js +3 -3
- package/dist/channels/origin/checks.d.ts +19 -7
- package/dist/channels/origin/checks.d.ts.map +1 -1
- package/dist/channels/origin/checks.js +13 -9
- package/dist/channels/origin/cursor-account.js +1 -1
- package/dist/channels/origin/defaults.d.ts.map +1 -1
- package/dist/channels/origin/defaults.js +3 -1
- package/dist/channels/origin/events.js +1 -1
- package/dist/channels/origin/origin-channel.d.ts.map +1 -1
- package/dist/channels/origin/origin-channel.js +2 -1
- package/dist/channels/origin/origin-webhook.js +2 -2
- package/dist/channels/slack/agentic-delivery.d.ts +23 -0
- package/dist/channels/slack/agentic-delivery.d.ts.map +1 -0
- package/dist/channels/slack/agentic-delivery.js +558 -0
- package/dist/channels/slack/agentic-posted.d.ts +30 -0
- package/dist/channels/slack/agentic-posted.d.ts.map +1 -0
- package/dist/channels/slack/agentic-posted.js +102 -0
- package/dist/channels/slack/agentic-signals.d.ts +48 -0
- package/dist/channels/slack/agentic-signals.d.ts.map +1 -0
- package/dist/channels/slack/agentic-signals.js +204 -0
- package/dist/channels/slack/api.d.ts +20 -1
- package/dist/channels/slack/api.d.ts.map +1 -1
- package/dist/channels/slack/api.js +43 -11
- package/dist/channels/slack/approvals.js +1 -1
- package/dist/channels/slack/auth.d.ts.map +1 -1
- package/dist/channels/slack/auth.js +3 -1
- package/dist/channels/slack/blocks.js +3 -3
- package/dist/channels/slack/bot-mentions.d.ts.map +1 -1
- package/dist/channels/slack/bot-mentions.js +5 -5
- package/dist/channels/slack/channel-watch.js +1 -1
- package/dist/channels/slack/cli-project.js +3 -3
- package/dist/channels/slack/defaults.d.ts +3 -0
- package/dist/channels/slack/defaults.d.ts.map +1 -1
- package/dist/channels/slack/defaults.js +90 -29
- package/dist/channels/slack/dispatch.d.ts +34 -1
- package/dist/channels/slack/dispatch.d.ts.map +1 -1
- package/dist/channels/slack/dispatch.js +219 -106
- package/dist/channels/slack/doctor.js +1 -1
- package/dist/channels/slack/eval-directive.js +1 -1
- package/dist/channels/slack/external-policy.d.ts +2 -1
- package/dist/channels/slack/external-policy.d.ts.map +1 -1
- package/dist/channels/slack/external-policy.js +13 -2
- package/dist/channels/slack/footer.d.ts +30 -0
- package/dist/channels/slack/footer.d.ts.map +1 -0
- package/dist/channels/slack/footer.js +88 -0
- package/dist/channels/slack/index.d.ts +2 -0
- package/dist/channels/slack/index.d.ts.map +1 -1
- package/dist/channels/slack/index.js +2 -0
- package/dist/channels/slack/interactive.d.ts.map +1 -1
- package/dist/channels/slack/interactive.js +5 -3
- package/dist/channels/slack/live-delivery.d.ts +1 -1
- package/dist/channels/slack/live-delivery.d.ts.map +1 -1
- package/dist/channels/slack/live-delivery.js +20 -6
- package/dist/channels/slack/log.d.ts.map +1 -1
- package/dist/channels/slack/log.js +1 -1
- package/dist/channels/slack/manifest.js +1 -1
- package/dist/channels/slack/nudge-carrier.js +1 -1
- package/dist/channels/slack/nudge-store.js +2 -2
- package/dist/channels/slack/paint-start.d.ts +22 -0
- package/dist/channels/slack/paint-start.d.ts.map +1 -0
- package/dist/channels/slack/paint-start.js +91 -0
- package/dist/channels/slack/placeholder.d.ts +36 -0
- package/dist/channels/slack/placeholder.d.ts.map +1 -0
- package/dist/channels/slack/placeholder.js +240 -0
- package/dist/channels/slack/progress-delivery.d.ts.map +1 -1
- package/dist/channels/slack/progress-delivery.js +13 -4
- package/dist/channels/slack/reasoning-chip.d.ts +8 -0
- package/dist/channels/slack/reasoning-chip.d.ts.map +1 -0
- package/dist/channels/slack/reasoning-chip.js +30 -0
- package/dist/channels/slack/recording-sink.d.ts +29 -0
- package/dist/channels/slack/recording-sink.d.ts.map +1 -0
- package/dist/channels/slack/recording-sink.js +142 -0
- package/dist/channels/slack/reply-options.d.ts +8 -1
- package/dist/channels/slack/reply-options.d.ts.map +1 -1
- package/dist/channels/slack/reply-options.js +59 -14
- package/dist/channels/slack/setup.js +1 -1
- package/dist/channels/slack/slack-channel.d.ts +2 -2
- package/dist/channels/slack/slack-channel.d.ts.map +1 -1
- package/dist/channels/slack/slack-channel.js +55 -20
- package/dist/channels/slack/socket-mode.js +2 -2
- package/dist/channels/slack/thread-context.js +5 -5
- package/dist/channels/slack/tool-approval-events.d.ts +5 -0
- package/dist/channels/slack/tool-approval-events.d.ts.map +1 -1
- package/dist/channels/slack/tool-approval-events.js +50 -38
- package/dist/channels/slack/tool-cards.js +1 -1
- package/dist/channels/slack/tool-chip.d.ts +9 -0
- package/dist/channels/slack/tool-chip.d.ts.map +1 -0
- package/dist/channels/slack/tool-chip.js +25 -0
- package/dist/channels/slack/types.d.ts +49 -7
- package/dist/channels/slack/types.d.ts.map +1 -1
- package/dist/channels/slack/upload.d.ts +13 -0
- package/dist/channels/slack/upload.d.ts.map +1 -0
- package/dist/channels/slack/upload.js +135 -0
- package/dist/channels.d.ts +10 -14
- package/dist/channels.d.ts.map +1 -1
- package/dist/channels.js +9 -21
- package/dist/dashboard-session-url.d.ts +15 -0
- package/dist/dashboard-session-url.d.ts.map +1 -0
- package/dist/dashboard-session-url.js +25 -0
- package/dist/docs/404.html +3 -3
- package/dist/docs/architecture.svg +59 -0
- package/dist/docs/assets/app.Drol6mi6.js +309 -0
- package/dist/docs/assets/{building-with-agents.md.D0KbSkJn.js → building-with-agents.md.CEGVXkmO.js} +2 -2
- package/dist/docs/assets/{building-with-agents.md.D0KbSkJn.lean.js → building-with-agents.md.CEGVXkmO.lean.js} +1 -1
- package/dist/docs/assets/chunks/@localSearchIndexroot.DtXk1hy-.js +1 -0
- package/dist/docs/assets/chunks/{VPLocalSearchBox.CVQERt56.js → VPLocalSearchBox.CdqoBZJX.js} +2 -2
- package/dist/docs/assets/chunks/arc.BVX3ycTn.js +1 -0
- package/dist/docs/assets/chunks/architectureDiagram-Q4EWVU46.CcChnMxX.js +36 -0
- package/dist/docs/assets/chunks/baseUniq.xwtXO-yt.js +1 -0
- package/dist/docs/assets/chunks/blockDiagram-DXYQGD6D.CijZ_taK.js +132 -0
- package/dist/docs/assets/chunks/c4Diagram-AHTNJAMY.0FBvwBvK.js +10 -0
- package/dist/docs/assets/chunks/channel.Bkv1N-gK.js +1 -0
- package/dist/docs/assets/chunks/chunk-4BX2VUAB.CELMmMDA.js +1 -0
- package/dist/docs/assets/chunks/chunk-4TB4RGXK.C4bhFtSm.js +206 -0
- package/dist/docs/assets/chunks/chunk-55IACEB6.ZnQ9gRRQ.js +1 -0
- package/dist/docs/assets/chunks/chunk-EDXVE4YY.DPlmglG-.js +1 -0
- package/dist/docs/assets/chunks/chunk-FMBD7UC4.BrUk8pff.js +15 -0
- package/dist/docs/assets/chunks/chunk-OYMX7WX6.CcmWIncu.js +231 -0
- package/dist/docs/assets/chunks/chunk-QZHKN3VN.D65-cs8I.js +1 -0
- package/dist/docs/assets/chunks/chunk-YZCP3GAM.qoXZpG9F.js +1 -0
- package/dist/docs/assets/chunks/classDiagram-6PBFFD2Q.CZDco1o8.js +1 -0
- package/dist/docs/assets/chunks/classDiagram-v2-HSJHXN6E.CZDco1o8.js +1 -0
- package/dist/docs/assets/chunks/clone.YSt_40_s.js +1 -0
- package/dist/docs/assets/chunks/cose-bilkent-S5V4N54A.8rYtqudO.js +1 -0
- package/dist/docs/assets/chunks/cytoscape.esm.BQk4lpUV.js +331 -0
- package/dist/docs/assets/chunks/dagre-KV5264BT.DrRP1fOh.js +4 -0
- package/dist/docs/assets/chunks/defaultLocale.C4B-KCzX.js +1 -0
- package/dist/docs/assets/chunks/diagram-5BDNPKRD.DHj_xA2_.js +10 -0
- package/dist/docs/assets/chunks/diagram-G4DWMVQ6.Bz_6nAKj.js +24 -0
- package/dist/docs/assets/chunks/diagram-MMDJMWI5.BWA0xSW9.js +43 -0
- package/dist/docs/assets/chunks/diagram-TYMM5635.CpTJLNJI.js +24 -0
- package/dist/docs/assets/chunks/erDiagram-SMLLAGMA.-7AWWSrP.js +85 -0
- package/dist/docs/assets/chunks/flowDiagram-DWJPFMVM.BTnQ742_.js +162 -0
- package/dist/docs/assets/chunks/framework.dypDpWZ3.js +19 -0
- package/dist/docs/assets/chunks/ganttDiagram-T4ZO3ILL.B5_HiiQ5.js +292 -0
- package/dist/docs/assets/chunks/gitGraphDiagram-UUTBAWPF.CZcNTFZd.js +106 -0
- package/dist/docs/assets/chunks/graph.V2GLaab4.js +1 -0
- package/dist/docs/assets/chunks/infoDiagram-42DDH7IO.7pZOkCCU.js +2 -0
- package/dist/docs/assets/chunks/init.Gi6I4Gst.js +1 -0
- package/dist/docs/assets/chunks/ishikawaDiagram-UXIWVN3A.DSMo3Qa3.js +70 -0
- package/dist/docs/assets/chunks/journeyDiagram-VCZTEJTY.BNEgWN1S.js +139 -0
- package/dist/docs/assets/chunks/kanban-definition-6JOO6SKY.B-4d4tC7.js +89 -0
- package/dist/docs/assets/chunks/katex.DkKDou_j.js +257 -0
- package/dist/docs/assets/chunks/layout.Dvbn9nSb.js +1 -0
- package/dist/docs/assets/chunks/linear.D2GM4p4b.js +1 -0
- package/dist/docs/assets/chunks/min.DVBtLK-B.js +1 -0
- package/dist/docs/assets/chunks/mindmap-definition-QFDTVHPH.CnJRI55x.js +96 -0
- package/dist/docs/assets/chunks/ordinal.DBvzRdQf.js +1 -0
- package/dist/docs/assets/chunks/pieDiagram-DEJITSTG.CtoaTFlA.js +30 -0
- package/dist/docs/assets/chunks/quadrantDiagram-34T5L4WZ.DtT24_vN.js +7 -0
- package/dist/docs/assets/chunks/requirementDiagram-MS252O5E.CjSO4o8f.js +84 -0
- package/dist/docs/assets/chunks/sankeyDiagram-XADWPNL6.-wWiIVWa.js +10 -0
- package/dist/docs/assets/chunks/sequenceDiagram-FGHM5R23.DSk8s4gX.js +157 -0
- package/dist/docs/assets/chunks/stateDiagram-FHFEXIEX.BFKAsdkN.js +1 -0
- package/dist/docs/assets/chunks/stateDiagram-v2-QKLJ7IA2.C4CLm481.js +1 -0
- package/dist/docs/assets/chunks/{theme.Dnsd3XOn.js → theme.C0MctGaz.js} +2 -2
- package/dist/docs/assets/chunks/timeline-definition-GMOUNBTQ.TUNJbAFe.js +120 -0
- package/dist/docs/assets/chunks/vennDiagram-DHZGUBPP.C-RGNnk4.js +34 -0
- package/dist/docs/assets/chunks/virtual_mermaid-config.DDnGl6nM.js +1 -0
- package/dist/docs/assets/chunks/wardley-RL74JXVD.g5efOWmT.js +162 -0
- package/dist/docs/assets/chunks/wardleyDiagram-NUSXRM2D.DH4zt73Y.js +20 -0
- package/dist/docs/assets/chunks/xychartDiagram-5P7HB3ND.B-3k6bF6.js +7 -0
- package/dist/docs/assets/{deployment.md.JenwuCCB.js → deployment.md.Dm4Qo3hp.js} +5 -5
- package/dist/docs/assets/{deployment.md.JenwuCCB.lean.js → deployment.md.Dm4Qo3hp.lean.js} +1 -1
- package/dist/docs/assets/{evals.md.C7JLjoEP.js → evals.md.BLDRt5LH.js} +4 -4
- package/dist/docs/assets/{evals.md.C7JLjoEP.lean.js → evals.md.BLDRt5LH.lean.js} +1 -1
- package/dist/docs/assets/guides_agent-to-agent.md.BI0xclmy.js +14 -0
- package/dist/docs/assets/guides_agent-to-agent.md.BI0xclmy.lean.js +1 -0
- package/dist/docs/assets/{guides_bitbucket.md.DZPzmUjU.js → guides_bitbucket.md.CTpCl__f.js} +1 -1
- package/dist/docs/assets/{guides_bitbucket.md.DZPzmUjU.lean.js → guides_bitbucket.md.CTpCl__f.lean.js} +1 -1
- package/dist/docs/assets/{guides_cloud-agents.md.BsloyHdY.js → guides_cloud-agents.md.lSE_l7lH.js} +2 -2
- package/dist/docs/assets/{guides_cloud-agents.md.BsloyHdY.lean.js → guides_cloud-agents.md.lSE_l7lH.lean.js} +1 -1
- package/dist/docs/assets/{guides_convert-automation.md.B4sjlodG.js → guides_convert-automation.md.Ck6Cr68A.js} +1 -1
- package/dist/docs/assets/{guides_convert-automation.md.B4sjlodG.lean.js → guides_convert-automation.md.Ck6Cr68A.lean.js} +1 -1
- package/dist/docs/assets/{guides_github.md.TZaTZlfz.js → guides_github.md.D6ER29dG.js} +1 -1
- package/dist/docs/assets/{guides_github.md.TZaTZlfz.lean.js → guides_github.md.D6ER29dG.lean.js} +1 -1
- package/dist/docs/assets/{guides_gitlab.md.BmqwQfdG.js → guides_gitlab.md.P-TjBnS5.js} +1 -1
- package/dist/docs/assets/{guides_gitlab.md.BmqwQfdG.lean.js → guides_gitlab.md.P-TjBnS5.lean.js} +1 -1
- package/dist/docs/assets/guides_grokbot-agents.md.WBZIOvkz.js +9 -0
- package/dist/docs/assets/{guides_grokbot-agents.md.DyV-WArv.lean.js → guides_grokbot-agents.md.WBZIOvkz.lean.js} +1 -1
- package/dist/docs/assets/{guides_improve.md.BGVk32bK.js → guides_improve.md.BKaDuKKK.js} +1 -1
- package/dist/docs/assets/{guides_improve.md.BGVk32bK.lean.js → guides_improve.md.BKaDuKKK.lean.js} +1 -1
- package/dist/docs/assets/{guides_mcp-oauth.md.Dp6cDP7f.js → guides_mcp-oauth.md.DMNMpXtO.js} +1 -1
- package/dist/docs/assets/{guides_mcp-oauth.md.Dp6cDP7f.lean.js → guides_mcp-oauth.md.DMNMpXtO.lean.js} +1 -1
- package/dist/docs/assets/{guides_opentelemetry.md.SCRMskno.js → guides_opentelemetry.md._CRfDyzH.js} +14 -14
- package/dist/docs/assets/{guides_opentelemetry.md.SCRMskno.lean.js → guides_opentelemetry.md._CRfDyzH.lean.js} +1 -1
- package/dist/docs/assets/{guides_slack.md.D4RVMM4G.js → guides_slack.md.DdT8rmsj.js} +12 -4
- package/dist/docs/assets/{guides_slack.md.D4RVMM4G.lean.js → guides_slack.md.DdT8rmsj.lean.js} +1 -1
- package/dist/docs/assets/{guides_webhooks.md.CJK484ex.js → guides_webhooks.md.aQW10HRe.js} +2 -2
- package/dist/docs/assets/{guides_webhooks.md.CJK484ex.lean.js → guides_webhooks.md.aQW10HRe.lean.js} +1 -1
- package/dist/docs/assets/hillclimbing.md.Dq4kkVIL.js +1 -0
- package/dist/docs/assets/hillclimbing.md.Dq4kkVIL.lean.js +1 -0
- package/dist/docs/assets/index.md.BFVyY2KT.js +17 -0
- package/dist/docs/assets/index.md.BFVyY2KT.lean.js +1 -0
- package/dist/docs/assets/{quickstart.md.DdQOF7Y8.js → quickstart.md.D3MjSZN-.js} +30 -38
- package/dist/docs/assets/quickstart.md.D3MjSZN-.lean.js +1 -0
- package/dist/docs/assets/{reference_agent-config.md.CvoL6pof.js → reference_agent-config.md.CfVA-LZJ.js} +1 -1
- package/dist/docs/assets/{reference_agent-config.md.CvoL6pof.lean.js → reference_agent-config.md.CfVA-LZJ.lean.js} +1 -1
- package/dist/docs/assets/{reference_artifacts.md.Dior32Qw.js → reference_artifacts.md.Vf7qyIZ-.js} +1 -1
- package/dist/docs/assets/{reference_artifacts.md.Dior32Qw.lean.js → reference_artifacts.md.Vf7qyIZ-.lean.js} +1 -1
- package/dist/docs/assets/{reference_channels.md.CAo-iK4j.js → reference_channels.md.icqLKcTc.js} +2 -12
- package/dist/docs/assets/{reference_channels.md.CAo-iK4j.lean.js → reference_channels.md.icqLKcTc.lean.js} +1 -1
- package/dist/docs/assets/{reference_cli.md.Deg7849l.js → reference_cli.md.B2dBL6L8.js} +3 -3
- package/dist/docs/assets/{reference_cli.md.Deg7849l.lean.js → reference_cli.md.B2dBL6L8.lean.js} +1 -1
- package/dist/docs/assets/{reference_connections.md.BojkC6c5.js → reference_connections.md.Cb3U_c8n.js} +4 -4
- package/dist/docs/assets/{reference_connections.md.BojkC6c5.lean.js → reference_connections.md.Cb3U_c8n.lean.js} +1 -1
- package/dist/docs/assets/{reference_extensions.md.ZAVUyuEX.js → reference_extensions.md.wlFD3cUR.js} +2 -2
- package/dist/docs/assets/{reference_extensions.md.ZAVUyuEX.lean.js → reference_extensions.md.wlFD3cUR.lean.js} +1 -1
- package/dist/docs/assets/{reference_hooks.md.BlM_bOg6.js → reference_hooks.md.CZuynAxj.js} +3 -3
- package/dist/docs/assets/{reference_hooks.md.BlM_bOg6.lean.js → reference_hooks.md.CZuynAxj.lean.js} +1 -1
- package/dist/docs/assets/{reference_http-api.md.BwaCo-VO.js → reference_http-api.md.DTKcYE6L.js} +3 -3
- package/dist/docs/assets/{reference_http-api.md.BwaCo-VO.lean.js → reference_http-api.md.DTKcYE6L.lean.js} +1 -1
- package/dist/docs/assets/{reference_instructions.md.CR7XSsGk.js → reference_instructions.md.D7gkckK-.js} +1 -1
- package/dist/docs/assets/{reference_instructions.md.CR7XSsGk.lean.js → reference_instructions.md.D7gkckK-.lean.js} +1 -1
- package/dist/docs/assets/{reference_playground.md.DLnoaczX.js → reference_playground.md.D2YExv5K.js} +1 -1
- package/dist/docs/assets/{reference_playground.md.DLnoaczX.lean.js → reference_playground.md.D2YExv5K.lean.js} +1 -1
- package/dist/docs/assets/{reference_project-layout.md.BEU8MtQV.js → reference_project-layout.md.DPxbUJyt.js} +3 -3
- package/dist/docs/assets/{reference_project-layout.md.BEU8MtQV.lean.js → reference_project-layout.md.DPxbUJyt.lean.js} +1 -1
- package/dist/docs/assets/{reference_prompt.md.DnaD5dNK.js → reference_prompt.md.BQ5uAv1F.js} +1 -1
- package/dist/docs/assets/{reference_prompt.md.DnaD5dNK.lean.js → reference_prompt.md.BQ5uAv1F.lean.js} +1 -1
- package/dist/docs/assets/{reference_schedules.md.DI_JrHgq.js → reference_schedules.md.BasfZWO-.js} +1 -1
- package/dist/docs/assets/{reference_schedules.md.DI_JrHgq.lean.js → reference_schedules.md.BasfZWO-.lean.js} +1 -1
- package/dist/docs/assets/{reference_sessions.md.CyXV1MUw.js → reference_sessions.md.YKvIsWAx.js} +1 -1
- package/dist/docs/assets/{reference_sessions.md.CyXV1MUw.lean.js → reference_sessions.md.YKvIsWAx.lean.js} +1 -1
- package/dist/docs/assets/{reference_skills.md.l2ezAcaN.js → reference_skills.md.rNgpsGd0.js} +1 -1
- package/dist/docs/assets/{reference_skills.md.l2ezAcaN.lean.js → reference_skills.md.rNgpsGd0.lean.js} +1 -1
- package/dist/docs/assets/{reference_subagents.md.CfsIloPm.js → reference_subagents.md.e5qitjJt.js} +2 -2
- package/dist/docs/assets/{reference_subagents.md.CfsIloPm.lean.js → reference_subagents.md.e5qitjJt.lean.js} +1 -1
- package/dist/docs/assets/{reference_tools.md.aGrn99hP.js → reference_tools.md.BdCO2aHZ.js} +4 -4
- package/dist/docs/assets/{reference_tools.md.aGrn99hP.lean.js → reference_tools.md.BdCO2aHZ.lean.js} +1 -1
- package/dist/docs/assets/{style.DCD_zyg3.css → style.Cfo2vbik.css} +1 -1
- package/dist/docs/assets/{templates_agentic-owners.md.BZSH4N9z.js → templates_agentic-owners.md.Da_AGDlH.js} +1 -1
- package/dist/docs/assets/{templates_agentic-owners.md.BZSH4N9z.lean.js → templates_agentic-owners.md.Da_AGDlH.lean.js} +1 -1
- package/dist/docs/assets/{templates_pr-autofixer.md.Bds_XWcV.js → templates_pr-autofixer.md.DqxocIGh.js} +1 -1
- package/dist/docs/assets/{templates_pr-autofixer.md.Bds_XWcV.lean.js → templates_pr-autofixer.md.DqxocIGh.lean.js} +1 -1
- package/dist/docs/assets/{templates_security-reviewer.md.lshxbCLK.js → templates_security-reviewer.md.Bhnvd8VE.js} +1 -1
- package/dist/docs/assets/{templates_security-reviewer.md.lshxbCLK.lean.js → templates_security-reviewer.md.Bhnvd8VE.lean.js} +1 -1
- package/dist/docs/assets/{templates_triage.md.Co4UNzkZ.js → templates_triage.md.BdBWO9Ic.js} +1 -1
- package/dist/docs/assets/{templates_triage.md.Co4UNzkZ.lean.js → templates_triage.md.BdBWO9Ic.lean.js} +1 -1
- package/dist/docs/assets/{troubleshooting.md.CYEAO9bM.js → troubleshooting.md.BcgNoYtJ.js} +1 -1
- package/dist/docs/assets/{troubleshooting.md.CYEAO9bM.lean.js → troubleshooting.md.BcgNoYtJ.lean.js} +1 -1
- package/dist/docs/building-with-agents.html +41 -8
- package/dist/docs/building-with-agents.md +13 -15
- package/dist/docs/deployment.html +44 -11
- package/dist/docs/deployment.md +6 -7
- package/dist/docs/evals.html +44 -11
- package/dist/docs/evals.md +5 -5
- package/dist/docs/guides/agent-to-agent.html +48 -11
- package/dist/docs/guides/agent-to-agent.md +40 -83
- package/dist/docs/guides/bitbucket.html +41 -8
- package/dist/docs/guides/cloud-agents.html +41 -8
- package/dist/docs/guides/cloud-agents.md +24 -20
- package/dist/docs/guides/convert-automation.html +41 -8
- package/dist/docs/guides/github.html +41 -8
- package/dist/docs/guides/github.md +1 -1
- package/dist/docs/guides/gitlab.html +41 -8
- package/dist/docs/guides/grokbot-agents.html +41 -8
- package/dist/docs/guides/grokbot-agents.md +26 -19
- package/dist/docs/guides/improve.html +41 -8
- package/dist/docs/guides/mcp-oauth.html +41 -8
- package/dist/docs/guides/mcp-oauth.md +1 -1
- package/dist/docs/guides/opentelemetry.html +53 -20
- package/dist/docs/guides/opentelemetry.md +28 -41
- package/dist/docs/guides/slack.html +51 -10
- package/dist/docs/guides/slack.md +53 -4
- package/dist/docs/guides/webhooks.html +42 -9
- package/dist/docs/guides/webhooks.md +3 -4
- package/dist/docs/hashmap.json +1 -1
- package/dist/docs/hillclimbing.html +40 -10
- package/dist/docs/hillclimbing.md +5 -5
- package/dist/docs/index.html +57 -12
- package/dist/docs/index.md +81 -150
- package/dist/docs/llms-full.txt +5779 -10297
- package/dist/docs/llms.txt +3 -29
- package/dist/docs/quickstart.html +70 -45
- package/dist/docs/quickstart.md +44 -105
- package/dist/docs/reference/agent-config.html +41 -8
- package/dist/docs/reference/artifacts.html +41 -8
- package/dist/docs/reference/channels.html +41 -18
- package/dist/docs/reference/channels.md +0 -16
- package/dist/docs/reference/cli.html +42 -9
- package/dist/docs/reference/cli.md +0 -16
- package/dist/docs/reference/connections.html +43 -10
- package/dist/docs/reference/connections.md +3 -5
- package/dist/docs/reference/extensions.html +42 -9
- package/dist/docs/reference/extensions.md +2 -2
- package/dist/docs/reference/hooks.html +42 -9
- package/dist/docs/reference/hooks.md +2 -4
- package/dist/docs/reference/http-api.html +42 -9
- package/dist/docs/reference/http-api.md +5 -5
- package/dist/docs/reference/instructions.html +41 -8
- package/dist/docs/reference/playground.html +40 -7
- package/dist/docs/reference/playground.md +2 -2
- package/dist/docs/reference/project-layout.html +42 -9
- package/dist/docs/reference/project-layout.md +3 -4
- package/dist/docs/reference/prompt.html +41 -8
- package/dist/docs/reference/schedules.html +41 -8
- package/dist/docs/reference/sessions.html +40 -7
- package/dist/docs/reference/sessions.md +5 -4
- package/dist/docs/reference/skills.html +41 -8
- package/dist/docs/reference/subagents.html +41 -8
- package/dist/docs/reference/subagents.md +2 -4
- package/dist/docs/reference/tools.html +43 -10
- package/dist/docs/reference/tools.md +2 -5
- package/dist/docs/templates/agentic-owners.html +41 -8
- package/dist/docs/templates/pr-autofixer.html +41 -8
- package/dist/docs/templates/security-reviewer.html +41 -8
- package/dist/docs/templates/triage.html +41 -8
- package/dist/docs/troubleshooting.html +40 -7
- package/dist/docs/troubleshooting.md +1 -2
- package/dist/evals/assertions.js +19 -19
- package/dist/evals/expect.js +1 -1
- package/dist/evals/judge.js +1 -1
- package/dist/evals/reporters.d.ts.map +1 -1
- package/dist/evals/reporters.js +8 -8
- package/dist/evals/run-facts.js +2 -2
- package/dist/evals.d.ts +1 -1
- package/dist/evals.d.ts.map +1 -1
- package/dist/evals.js +7 -7
- package/dist/extensions/cursor-cloud-agents/extension.js +1 -1
- package/dist/extensions/cursor-cloud-agents/lib/backend.js +3 -3
- package/dist/extensions/cursor-cloud-agents/lib/fleet.js +1 -1
- package/dist/extensions/cursor-cloud-agents/lib/repos.js +6 -6
- package/dist/extensions/cursor-cloud-agents/lib/transcript.d.ts.map +1 -1
- package/dist/extensions/cursor-cloud-agents/lib/transcript.js +2 -2
- package/dist/extensions/cursor-cloud-agents/tools/list.js +1 -1
- package/dist/extensions/improve/skills/yourself.js +1 -1
- package/dist/extensions/slack-communication/extension.d.ts +28 -0
- package/dist/extensions/slack-communication/extension.d.ts.map +1 -0
- package/dist/extensions/slack-communication/extension.js +32 -0
- package/dist/extensions/slack-communication/skills/slack-voice.d.ts +5 -0
- package/dist/extensions/slack-communication/skills/slack-voice.d.ts.map +1 -0
- package/dist/extensions/slack-communication/skills/slack-voice.js +54 -0
- package/dist/extensions/slack-communication/tools/delete-message.d.ts +4 -0
- package/dist/extensions/slack-communication/tools/delete-message.d.ts.map +1 -0
- package/dist/extensions/slack-communication/tools/delete-message.js +29 -0
- package/dist/extensions/slack-communication/tools/edit-message.d.ts +4 -0
- package/dist/extensions/slack-communication/tools/edit-message.d.ts.map +1 -0
- package/dist/extensions/slack-communication/tools/edit-message.js +37 -0
- package/dist/extensions/slack-communication/tools/post-card.d.ts +4 -0
- package/dist/extensions/slack-communication/tools/post-card.d.ts.map +1 -0
- package/dist/extensions/slack-communication/tools/post-card.js +25 -0
- package/dist/extensions/slack-communication/tools/post-file.d.ts +4 -0
- package/dist/extensions/slack-communication/tools/post-file.d.ts.map +1 -0
- package/dist/extensions/slack-communication/tools/post-file.js +76 -0
- package/dist/extensions/slack-communication/tools/post-update.d.ts +4 -0
- package/dist/extensions/slack-communication/tools/post-update.d.ts.map +1 -0
- package/dist/extensions/slack-communication/tools/post-update.js +36 -0
- package/dist/extensions/slack-communication/tools/react.d.ts +4 -0
- package/dist/extensions/slack-communication/tools/react.d.ts.map +1 -0
- package/dist/extensions/slack-communication/tools/react.js +27 -0
- package/dist/extensions/slack-communication/tools/set-status.d.ts +4 -0
- package/dist/extensions/slack-communication/tools/set-status.d.ts.map +1 -0
- package/dist/extensions/slack-communication/tools/set-status.js +18 -0
- package/dist/files-backends/cursor-hosted.d.ts +18 -6
- package/dist/files-backends/cursor-hosted.d.ts.map +1 -1
- package/dist/files-backends/cursor-hosted.js +357 -74
- package/dist/files-backends/local-fs.js +1 -1
- package/dist/files.d.ts +15 -0
- package/dist/files.d.ts.map +1 -1
- package/dist/filesystem.d.ts.map +1 -1
- package/dist/filesystem.js +15 -15
- package/dist/index.d.ts +5 -8
- package/dist/index.d.ts.map +1 -1
- package/dist/index.js +4 -6
- package/dist/internal/advertise-tools.js +6 -6
- package/dist/internal/approval-gate.js +1 -1
- package/dist/internal/artifacts-store.js +3 -3
- package/dist/internal/as-of.js +2 -2
- package/dist/internal/authored-alias-hooks.js +1 -1
- package/dist/internal/builtin-tools/reminders.js +2 -2
- package/dist/internal/chat-client.js +5 -5
- package/dist/internal/cli-ax.d.ts +1 -0
- package/dist/internal/cli-ax.d.ts.map +1 -1
- package/dist/internal/cli-ax.js +68 -13
- package/dist/internal/cli-bitbucket.js +10 -10
- package/dist/internal/cli-convert-automation.js +2 -2
- package/dist/internal/cli-cursor.d.ts +3 -11
- package/dist/internal/cli-cursor.d.ts.map +1 -1
- package/dist/internal/cli-cursor.js +5 -10
- package/dist/internal/cli-deploy.d.ts +12 -2
- package/dist/internal/cli-deploy.d.ts.map +1 -1
- package/dist/internal/cli-deploy.js +328 -96
- package/dist/internal/cli-docs.js +5 -5
- package/dist/internal/cli-github.js +15 -16
- package/dist/internal/cli-gitlab.js +10 -10
- package/dist/internal/cli-manifest.js +1 -1
- package/dist/internal/cli-mcp-oauth.d.ts.map +1 -1
- package/dist/internal/cli-mcp-oauth.js +5 -5
- package/dist/internal/cli-mcp.js +3 -3
- package/dist/internal/cli-skills.js +2 -2
- package/dist/internal/cli-slack.js +5 -5
- package/dist/internal/cloud-turn-cost.js +1 -1
- package/dist/internal/continuation-identity.d.ts.map +1 -1
- package/dist/internal/continuation-identity.js +14 -9
- package/dist/internal/conversation-mirror.d.ts.map +1 -1
- package/dist/internal/conversation-mirror.js +33 -2
- package/dist/internal/convert-automation/convert-workflow.js +25 -24
- package/dist/internal/convert-automation/types.d.ts +8 -0
- package/dist/internal/convert-automation/types.d.ts.map +1 -1
- package/dist/internal/cursor/account-mcp.d.ts +2 -2
- package/dist/internal/cursor/account-mcp.d.ts.map +1 -1
- package/dist/internal/cursor/account-mcp.js +32 -27
- package/dist/internal/cursor/backend-client.d.ts +15 -10
- package/dist/internal/cursor/backend-client.d.ts.map +1 -1
- package/dist/internal/cursor/backend-client.js +17 -11
- package/dist/internal/cursor/credentials.js +1 -1
- package/dist/internal/cursor/hosted-store-secrets.d.ts +16 -0
- package/dist/internal/cursor/hosted-store-secrets.d.ts.map +1 -1
- package/dist/internal/cursor/hosted-store-secrets.js +25 -0
- package/dist/internal/cursor-account-mcp-auth.js +9 -9
- package/dist/internal/cursor-deployment-relay.js +9 -9
- package/dist/internal/cursor-event-relay.js +10 -10
- package/dist/internal/cursor-relay-core.js +2 -2
- package/dist/internal/deploy-client.d.ts +106 -9
- package/dist/internal/deploy-client.d.ts.map +1 -1
- package/dist/internal/deploy-client.js +171 -23
- package/dist/internal/deploy-manifest.d.ts +13 -0
- package/dist/internal/deploy-manifest.d.ts.map +1 -1
- package/dist/internal/deploy-manifest.js +32 -16
- package/dist/internal/discovery/agent-config.d.ts +5 -0
- package/dist/internal/discovery/agent-config.d.ts.map +1 -1
- package/dist/internal/discovery/agent-config.js +27 -0
- package/dist/internal/discovery/agent.d.ts.map +1 -1
- package/dist/internal/discovery/agent.js +10 -8
- package/dist/internal/discovery/channels.js +4 -4
- package/dist/internal/discovery/connections.js +4 -4
- package/dist/internal/discovery/cursor-plugin.js +12 -12
- package/dist/internal/discovery/extension-overlay.js +3 -3
- package/dist/internal/discovery/extensions.js +6 -6
- package/dist/internal/discovery/info.js +9 -9
- package/dist/internal/discovery/instructions.js +1 -1
- package/dist/internal/discovery/project.d.ts.map +1 -1
- package/dist/internal/discovery/project.js +4 -4
- package/dist/internal/discovery/services.js +1 -1
- package/dist/internal/discovery/tools.js +1 -1
- package/dist/internal/docs-site.js +2 -2
- package/dist/internal/env-file.js +1 -1
- package/dist/internal/eval-run-store.d.ts.map +1 -1
- package/dist/internal/eval-run-store.js +7 -7
- package/dist/internal/eval-runner.js +14 -14
- package/dist/internal/evals-client.js +4 -4
- package/dist/internal/event-log.js +8 -8
- package/dist/internal/event-mapper.d.ts +18 -0
- package/dist/internal/event-mapper.d.ts.map +1 -1
- package/dist/internal/event-mapper.js +34 -2
- package/dist/internal/filesystem/format.d.ts.map +1 -1
- package/dist/internal/filesystem/format.js +6 -3
- package/dist/internal/filesystem/scratch.js +3 -3
- package/dist/internal/filesystem/tools.d.ts.map +1 -1
- package/dist/internal/filesystem/tools.js +6 -6
- package/dist/internal/filesystem/walk.js +1 -1
- package/dist/internal/framework-file-storage.d.ts +6 -2
- package/dist/internal/framework-file-storage.d.ts.map +1 -1
- package/dist/internal/framework-file-storage.js +91 -2
- package/dist/internal/framework-storage-selection.d.ts +0 -6
- package/dist/internal/framework-storage-selection.d.ts.map +1 -1
- package/dist/internal/framework-storage-selection.js +2 -11
- package/dist/internal/github-fanout.js +3 -3
- package/dist/internal/guest-network.js +4 -4
- package/dist/internal/host-files.js +1 -1
- package/dist/internal/host-kv.js +2 -2
- package/dist/internal/hosted-admission-adapter.d.ts +2 -0
- package/dist/internal/hosted-admission-adapter.d.ts.map +1 -1
- package/dist/internal/hosted-catch-protocol.d.ts.map +1 -1
- package/dist/internal/hosted-catch-protocol.js +2 -4
- package/dist/internal/hosted-catch.js +1 -1
- package/dist/internal/hosted-delivery-protocol.d.ts +29 -0
- package/dist/internal/hosted-delivery-protocol.d.ts.map +1 -1
- package/dist/internal/hosted-delivery-protocol.js +76 -8
- package/dist/internal/hosted-delivery.d.ts.map +1 -1
- package/dist/internal/hosted-delivery.js +201 -64
- package/dist/internal/hosted-execution-diag.js +3 -3
- package/dist/internal/hosted-execution-latency.d.ts +80 -0
- package/dist/internal/hosted-execution-latency.d.ts.map +1 -0
- package/dist/internal/hosted-execution-latency.js +220 -0
- package/dist/internal/hosting.d.ts +5 -5
- package/dist/internal/hosting.d.ts.map +1 -1
- package/dist/internal/hosting.js +5 -6
- package/dist/internal/http-channel-define.d.ts +11 -0
- package/dist/internal/http-channel-define.d.ts.map +1 -0
- package/dist/internal/http-channel-define.js +18 -0
- package/dist/internal/http-channel.d.ts +2 -3
- package/dist/internal/http-channel.d.ts.map +1 -1
- package/dist/internal/http-channel.js +3 -4
- package/dist/internal/http-control-plane-session.d.ts +7 -3
- package/dist/internal/http-control-plane-session.d.ts.map +1 -1
- package/dist/internal/http-control-plane-session.js +22 -10
- package/dist/internal/incoming-headers-to-fetch.d.ts +10 -0
- package/dist/internal/incoming-headers-to-fetch.d.ts.map +1 -0
- package/dist/internal/incoming-headers-to-fetch.js +41 -0
- package/dist/internal/init-interview.js +7 -7
- package/dist/internal/init-project.d.ts.map +1 -1
- package/dist/internal/init-project.js +14 -14
- package/dist/internal/init-scaffold.js +1 -1
- package/dist/internal/inline-stdio-mcp.js +2 -2
- package/dist/internal/install-cursor-skills.js +10 -10
- package/dist/internal/json-schema.js +1 -1
- package/dist/internal/local-control-plane.d.ts.map +1 -1
- package/dist/internal/local-control-plane.js +3 -3
- package/dist/internal/local-env.js +3 -3
- package/dist/internal/log-ring.js +1 -1
- package/dist/internal/logs-client.js +1 -1
- package/dist/internal/mcp-endpoint.js +8 -8
- package/dist/internal/mcp-host.js +4 -4
- package/dist/internal/mcp-oauth-on-demand.js +3 -3
- package/dist/internal/mcp-oauth.js +5 -5
- package/dist/internal/net.js +2 -2
- package/dist/internal/otel/config.js +3 -3
- package/dist/internal/otel/runtime.js +13 -13
- package/dist/internal/peer-connections.js +2 -2
- package/dist/internal/platform-schedule-sync.js +1 -1
- package/dist/internal/platform-timers.js +1 -1
- package/dist/internal/playground/static.js +2 -2
- package/dist/internal/playground/toolchain.js +2 -2
- package/dist/internal/playground-proxy.js +3 -3
- package/dist/internal/process-memory-telemetry.js +1 -1
- package/dist/internal/reminder-runner.d.ts.map +1 -1
- package/dist/internal/reminder-runner.js +7 -7
- package/dist/internal/reminder-store.js +1 -1
- package/dist/internal/request-error-status.d.ts.map +1 -1
- package/dist/internal/request-error-status.js +9 -0
- package/dist/internal/resolved-connections.js +8 -8
- package/dist/internal/result-output.d.ts +14 -2
- package/dist/internal/result-output.d.ts.map +1 -1
- package/dist/internal/result-output.js +45 -2
- package/dist/internal/router.js +4 -4
- package/dist/internal/run-client.js +2 -2
- package/dist/internal/schedule-runner.js +6 -6
- package/dist/internal/scm/pr-url.d.ts +3 -1
- package/dist/internal/scm/pr-url.d.ts.map +1 -1
- package/dist/internal/scm/pr-url.js +10 -2
- package/dist/internal/sdk-runner.d.ts.map +1 -1
- package/dist/internal/sdk-runner.js +14 -15
- package/dist/internal/serve-restart.js +1 -1
- package/dist/internal/server.d.ts.map +1 -1
- package/dist/internal/server.js +81 -87
- package/dist/internal/session-cost.js +3 -3
- package/dist/internal/session-engine.d.ts +34 -0
- package/dist/internal/session-engine.d.ts.map +1 -1
- package/dist/internal/session-engine.js +380 -184
- package/dist/internal/session-run-log.d.ts.map +1 -1
- package/dist/internal/session-run-log.js +4 -4
- package/dist/internal/session-store.d.ts +47 -3
- package/dist/internal/session-store.d.ts.map +1 -1
- package/dist/internal/session-store.js +198 -33
- package/dist/internal/sessions-client.js +3 -3
- package/dist/internal/slack-thread-key.d.ts +7 -0
- package/dist/internal/slack-thread-key.d.ts.map +1 -0
- package/dist/internal/slack-thread-key.js +10 -0
- package/dist/internal/sleep.js +1 -1
- package/dist/internal/storage-coordinator.d.ts +17 -0
- package/dist/internal/storage-coordinator.d.ts.map +1 -1
- package/dist/internal/storage-coordinator.js +111 -11
- package/dist/internal/storage.d.ts +2 -0
- package/dist/internal/storage.d.ts.map +1 -0
- package/dist/internal/storage.js +1 -0
- package/dist/internal/store-mirror.js +4 -4
- package/dist/internal/terminal-style.js +2 -2
- package/dist/internal/tool-result.js +3 -3
- package/dist/internal/trajectory.js +7 -7
- package/dist/internal/turn-governor.js +2 -2
- package/dist/internal/turn-outbox.js +1 -1
- package/dist/internal/update-check.js +2 -2
- package/dist/internal/v2-hosting.d.ts +9 -0
- package/dist/internal/v2-hosting.d.ts.map +1 -1
- package/dist/internal/v2-hosting.js +10 -0
- package/dist/internal/workspace.d.ts +13 -10
- package/dist/internal/workspace.d.ts.map +1 -1
- package/dist/internal/workspace.js +17 -16
- package/dist/kv/memory-kv.d.ts +6 -4
- package/dist/kv/memory-kv.d.ts.map +1 -1
- package/dist/kv/memory-kv.js +9 -7
- package/dist/kv.d.ts +4 -7
- package/dist/kv.d.ts.map +1 -1
- package/dist/kv.js +4 -7
- package/dist/otel-public.d.ts +7 -0
- package/dist/otel-public.d.ts.map +1 -0
- package/dist/otel-public.js +5 -0
- package/dist/otel.d.ts +7 -2
- package/dist/otel.d.ts.map +1 -1
- package/dist/otel.js +7 -2
- package/dist/playground/assets/index-BLlKgZtI.css +1 -0
- package/dist/playground/assets/index-CDS5p9sR.js +67 -0
- package/dist/playground/index.html +2 -2
- package/dist/prompt.js +1 -1
- package/dist/result.d.ts +10 -4
- package/dist/result.d.ts.map +1 -1
- package/dist/result.js +9 -3
- package/dist/storage-backends/cursor-hosted-v2.js +2 -2
- package/dist/storage-backends/cursor-hosted.d.ts +5 -17
- package/dist/storage-backends/cursor-hosted.d.ts.map +1 -1
- package/dist/storage-backends/cursor-hosted.js +6 -20
- package/dist/storage-backends/file-kv.js +7 -7
- package/dist/storage.d.ts +20 -2
- package/dist/storage.d.ts.map +1 -1
- package/dist/storage.js +7 -6
- package/dist/types.d.ts +67 -11
- package/dist/types.d.ts.map +1 -1
- package/dist/types.js +12 -4
- package/docs/README.md +83 -152
- package/docs/building-with-agents.md +13 -15
- package/docs/deployment.md +6 -7
- package/docs/evals.md +5 -5
- package/docs/guides/agent-to-agent.md +41 -84
- package/docs/guides/cloud-agents.md +25 -20
- package/docs/guides/github.md +1 -1
- package/docs/guides/grokbot-agents.md +27 -19
- package/docs/guides/mcp-oauth.md +1 -1
- package/docs/guides/opentelemetry.md +28 -41
- package/docs/guides/slack.md +53 -4
- package/docs/guides/webhooks.md +3 -4
- package/docs/hillclimbing.md +5 -5
- package/docs/quickstart.md +45 -106
- package/docs/reference/channels.md +0 -16
- package/docs/reference/cli.md +0 -16
- package/docs/reference/connections.md +3 -5
- package/docs/reference/extensions.md +2 -2
- package/docs/reference/hooks.md +2 -4
- package/docs/reference/http-api.md +5 -5
- package/docs/reference/playground.md +2 -2
- package/docs/reference/project-layout.md +3 -4
- package/docs/reference/sessions.md +5 -4
- package/docs/reference/subagents.md +2 -4
- package/docs/reference/tools.md +2 -5
- package/docs/troubleshooting.md +1 -2
- package/package.json +55 -37
- package/skills/framework-map/SKILL.md +2 -2
- package/skills/otel/SKILL.md +8 -18
- package/src/bin/agent-serve.ts +93 -72
- package/src/channels/bitbucket/api.ts +8 -8
- package/src/channels/bitbucket/binding.ts +4 -4
- package/src/channels/bitbucket/bitbucket-channel.ts +1 -1
- package/src/channels/bitbucket/bitbucket-webhook.ts +1 -1
- package/src/channels/bitbucket/checks.ts +3 -4
- package/src/channels/bitbucket/cursor-account.ts +1 -1
- package/src/channels/bitbucket/events.ts +1 -1
- package/src/channels/change-monitors/change-monitors-channel.ts +2 -2
- package/src/channels/checks.ts +5 -4
- package/src/channels/deployments/deployments-channel.ts +1 -1
- package/src/channels/github/api.ts +1 -1
- package/src/channels/github/checks.ts +1 -1
- package/src/channels/github/cursor-account.ts +3 -3
- package/src/channels/github/defaults.ts +8 -4
- package/src/channels/github/events.ts +1 -1
- package/src/channels/github/forward.ts +8 -8
- package/src/channels/github/github-channel.ts +19 -2
- package/src/channels/github/progress.ts +7 -2
- package/src/channels/github/state.ts +6 -0
- package/src/channels/github/types.ts +6 -0
- package/src/channels/gitlab/binding.ts +4 -4
- package/src/channels/gitlab/checks.ts +3 -4
- package/src/channels/gitlab/cursor-account.ts +1 -1
- package/src/channels/gitlab/events.ts +1 -1
- package/src/channels/gitlab/gitlab-channel.ts +1 -1
- package/src/channels/gitlab/gitlab-webhook.ts +1 -1
- package/src/channels/gitlab/replay.ts +2 -2
- package/src/channels/origin/binding.ts +6 -3
- package/src/channels/origin/checks.ts +27 -17
- package/src/channels/origin/cursor-account.ts +1 -1
- package/src/channels/origin/defaults.ts +5 -1
- package/src/channels/origin/events.ts +1 -1
- package/src/channels/origin/origin-channel.ts +2 -1
- package/src/channels/origin/origin-webhook.ts +2 -2
- package/src/channels/slack/agentic-delivery.ts +659 -0
- package/src/channels/slack/agentic-posted.ts +148 -0
- package/src/channels/slack/agentic-signals.ts +248 -0
- package/src/channels/slack/api.ts +51 -11
- package/src/channels/slack/approvals.ts +1 -1
- package/src/channels/slack/attachments.ts +1 -1
- package/src/channels/slack/auth.ts +3 -1
- package/src/channels/slack/blocks.ts +3 -3
- package/src/channels/slack/bot-mentions.ts +5 -7
- package/src/channels/slack/channel-watch.ts +1 -1
- package/src/channels/slack/cli-project.ts +3 -3
- package/src/channels/slack/defaults.ts +109 -37
- package/src/channels/slack/dispatch.ts +299 -170
- package/src/channels/slack/doctor.ts +1 -1
- package/src/channels/slack/eval-directive.ts +1 -1
- package/src/channels/slack/external-policy.ts +15 -2
- package/src/channels/slack/footer.ts +108 -0
- package/src/channels/slack/index.ts +2 -0
- package/src/channels/slack/interactive.ts +4 -2
- package/src/channels/slack/live-delivery.ts +23 -7
- package/src/channels/slack/log.ts +1 -1
- package/src/channels/slack/manifest.ts +1 -1
- package/src/channels/slack/nudge-carrier.ts +1 -1
- package/src/channels/slack/nudge-store.ts +2 -2
- package/src/channels/slack/paint-start.ts +93 -0
- package/src/channels/slack/placeholder.ts +315 -0
- package/src/channels/slack/progress-delivery.ts +14 -1
- package/src/channels/slack/reasoning-chip.ts +48 -0
- package/src/channels/slack/recording-sink.ts +176 -0
- package/src/channels/slack/reply-options.ts +71 -15
- package/src/channels/slack/setup.ts +1 -1
- package/src/channels/slack/slack-channel.ts +73 -13
- package/src/channels/slack/socket-mode.ts +2 -2
- package/src/channels/slack/thread-context.ts +5 -5
- package/src/channels/slack/tool-approval-events.ts +54 -38
- package/src/channels/slack/tool-cards.ts +1 -1
- package/src/channels/slack/tool-chip.ts +36 -0
- package/src/channels/slack/types.ts +47 -7
- package/src/channels/slack/upload.ts +142 -0
- package/src/channels.ts +12 -30
- package/src/dashboard-session-url.ts +32 -0
- package/src/evals/assertions.ts +19 -19
- package/src/evals/expect.ts +1 -1
- package/src/evals/judge.ts +1 -1
- package/src/evals/reporters.ts +8 -9
- package/src/evals/run-facts.ts +2 -2
- package/src/evals.ts +7 -10
- package/src/extensions/cursor-cloud-agents/extension.ts +1 -1
- package/src/extensions/cursor-cloud-agents/lib/backend.ts +3 -3
- package/src/extensions/cursor-cloud-agents/lib/fleet.ts +1 -1
- package/src/extensions/cursor-cloud-agents/lib/repos.ts +3 -3
- package/src/extensions/cursor-cloud-agents/lib/transcript.ts +3 -4
- package/src/extensions/cursor-cloud-agents/tools/list.ts +1 -1
- package/src/extensions/improve/skills/yourself.ts +1 -1
- package/src/extensions/slack-communication/evals/harness.ts +728 -0
- package/src/extensions/slack-communication/evals/slack-communication.eval.ts +953 -0
- package/src/extensions/slack-communication/evals/slack-placeholder.eval.ts +194 -0
- package/src/extensions/slack-communication/extension.ts +45 -0
- package/src/extensions/slack-communication/skills/slack-voice.ts +59 -0
- package/src/extensions/slack-communication/tools/delete-message.ts +34 -0
- package/src/extensions/slack-communication/tools/edit-message.ts +42 -0
- package/src/extensions/slack-communication/tools/post-card.ts +28 -0
- package/src/extensions/slack-communication/tools/post-file.ts +85 -0
- package/src/extensions/slack-communication/tools/post-update.ts +41 -0
- package/src/extensions/slack-communication/tools/react.ts +33 -0
- package/src/extensions/slack-communication/tools/set-status.ts +21 -0
- package/src/files-backends/cursor-hosted.ts +502 -98
- package/src/files-backends/local-fs.ts +1 -1
- package/src/files.ts +15 -0
- package/src/filesystem.ts +16 -18
- package/src/index.ts +4 -36
- package/src/internal/advertise-tools.ts +6 -6
- package/src/internal/approval-gate.ts +1 -1
- package/src/internal/artifacts-store.ts +3 -3
- package/src/internal/as-of.ts +2 -2
- package/src/internal/authored-alias-hooks.ts +1 -1
- package/src/internal/authored-loaders.ts +2 -3
- package/src/internal/builtin-tools/reminders.ts +2 -2
- package/src/internal/chat-client.ts +5 -5
- package/src/internal/cli-ax.ts +84 -14
- package/src/internal/cli-bitbucket.ts +11 -11
- package/src/internal/cli-convert-automation.ts +2 -2
- package/src/internal/cli-cursor.ts +5 -16
- package/src/internal/cli-deploy.ts +389 -104
- package/src/internal/cli-docs.ts +5 -5
- package/src/internal/cli-github.ts +16 -19
- package/src/internal/cli-gitlab.ts +11 -11
- package/src/internal/cli-manifest.ts +1 -1
- package/src/internal/cli-mcp-oauth.ts +5 -7
- package/src/internal/cli-mcp.ts +3 -3
- package/src/internal/cli-skills.ts +2 -2
- package/src/internal/cli-slack.ts +5 -5
- package/src/internal/cloud-turn-cost.ts +1 -1
- package/src/internal/continuation-identity.ts +13 -9
- package/src/internal/conversation-mirror.ts +36 -3
- package/src/internal/convert-automation/convert-workflow.ts +27 -27
- package/src/internal/convert-automation/types.ts +9 -0
- package/src/internal/cursor/account-mcp.ts +48 -31
- package/src/internal/cursor/backend-client.ts +28 -17
- package/src/internal/cursor/credentials.ts +1 -1
- package/src/internal/cursor/hosted-store-secrets.ts +34 -0
- package/src/internal/cursor-account-mcp-auth.ts +9 -9
- package/src/internal/cursor-deployment-relay.ts +10 -10
- package/src/internal/cursor-event-relay.ts +10 -10
- package/src/internal/cursor-relay-core.ts +2 -2
- package/src/internal/deploy-client.ts +266 -24
- package/src/internal/deploy-manifest.ts +46 -8
- package/src/internal/discovery/agent-config.ts +34 -0
- package/src/internal/discovery/agent.ts +14 -6
- package/src/internal/discovery/channels.ts +4 -4
- package/src/internal/discovery/connections.ts +4 -4
- package/src/internal/discovery/cursor-plugin.ts +12 -12
- package/src/internal/discovery/extension-overlay.ts +3 -3
- package/src/internal/discovery/extensions.ts +6 -6
- package/src/internal/discovery/info.ts +9 -9
- package/src/internal/discovery/instructions.ts +1 -1
- package/src/internal/discovery/project.ts +4 -4
- package/src/internal/discovery/services.ts +1 -1
- package/src/internal/discovery/tools.ts +1 -1
- package/src/internal/docs-site.ts +2 -2
- package/src/internal/env-file.ts +2 -2
- package/src/internal/eval-run-store.ts +7 -9
- package/src/internal/eval-runner.ts +20 -20
- package/src/internal/evals-client.ts +6 -6
- package/src/internal/event-log.ts +10 -10
- package/src/internal/event-mapper.ts +37 -2
- package/src/internal/filesystem/format.ts +11 -12
- package/src/internal/filesystem/scratch.ts +3 -3
- package/src/internal/filesystem/tools.ts +6 -8
- package/src/internal/filesystem/walk.ts +1 -1
- package/src/internal/framework-file-storage.ts +104 -4
- package/src/internal/framework-storage-selection.ts +2 -12
- package/src/internal/github-fanout.ts +4 -4
- package/src/internal/guest-network.ts +4 -4
- package/src/internal/host-files.ts +1 -1
- package/src/internal/host-kv.ts +2 -2
- package/src/internal/hosted-admission-adapter.ts +2 -0
- package/src/internal/hosted-catch-protocol.ts +3 -5
- package/src/internal/hosted-catch.ts +1 -1
- package/src/internal/hosted-delivery-protocol.ts +111 -13
- package/src/internal/hosted-delivery.ts +286 -81
- package/src/internal/hosted-execution-diag.ts +3 -3
- package/src/internal/hosted-execution-latency.ts +334 -0
- package/src/internal/hosting.ts +5 -6
- package/src/internal/http-channel-define.ts +27 -0
- package/src/internal/http-channel.ts +3 -4
- package/src/internal/http-control-plane-session.ts +24 -11
- package/src/internal/incoming-headers-to-fetch.ts +54 -0
- package/src/internal/init-interview.ts +7 -7
- package/src/internal/init-project.ts +14 -16
- package/src/internal/init-scaffold.ts +1 -1
- package/src/internal/inline-stdio-mcp.ts +2 -2
- package/src/internal/install-cursor-skills.ts +11 -11
- package/src/internal/json-schema.ts +1 -1
- package/src/internal/local-control-plane.ts +4 -5
- package/src/internal/local-env.ts +3 -3
- package/src/internal/log-ring.ts +1 -1
- package/src/internal/logs-client.ts +1 -1
- package/src/internal/mcp-endpoint.ts +10 -10
- package/src/internal/mcp-host.ts +9 -9
- package/src/internal/mcp-oauth-on-demand.ts +3 -3
- package/src/internal/mcp-oauth.ts +5 -5
- package/src/internal/net.ts +2 -2
- package/src/internal/otel/config.ts +3 -3
- package/src/internal/otel/runtime.ts +14 -14
- package/src/internal/peer-connections.ts +2 -2
- package/src/internal/platform-schedule-sync.ts +1 -1
- package/src/internal/platform-timers.ts +1 -1
- package/src/internal/playground/static.ts +2 -2
- package/src/internal/playground/toolchain.ts +2 -2
- package/src/internal/playground-proxy.ts +3 -3
- package/src/internal/process-memory-telemetry.ts +1 -1
- package/src/internal/reminder-runner.ts +8 -10
- package/src/internal/reminder-store.ts +1 -1
- package/src/internal/request-error-status.ts +9 -0
- package/src/internal/resolved-connections.ts +8 -8
- package/src/internal/result-output.ts +62 -5
- package/src/internal/router.ts +4 -4
- package/src/internal/run-client.ts +2 -2
- package/src/internal/schedule-runner.ts +6 -6
- package/src/internal/scm/pr-url.ts +11 -2
- package/src/internal/sdk-runner.ts +14 -28
- package/src/internal/serve-restart.ts +1 -1
- package/src/internal/server.ts +97 -99
- package/src/internal/session-cost.ts +3 -3
- package/src/internal/session-engine.ts +504 -244
- package/src/internal/session-run-log.ts +4 -6
- package/src/internal/session-store.ts +213 -39
- package/src/internal/sessions-client.ts +3 -3
- package/src/internal/slack-thread-key.ts +11 -0
- package/src/internal/sleep.ts +1 -1
- package/src/internal/storage-coordinator.ts +118 -21
- package/src/internal/storage.ts +1 -0
- package/src/internal/store-mirror.ts +4 -4
- package/src/internal/terminal-style.ts +2 -2
- package/src/internal/tool-result.ts +3 -3
- package/src/internal/trajectory.ts +7 -7
- package/src/internal/turn-governor.ts +2 -2
- package/src/internal/turn-outbox.ts +1 -1
- package/src/internal/update-check.ts +2 -2
- package/src/internal/v2-hosting.ts +14 -0
- package/src/internal/workspace.ts +17 -17
- package/src/kv/memory-kv.ts +9 -7
- package/src/kv.ts +4 -7
- package/src/otel-public.ts +24 -0
- package/src/otel.ts +7 -2
- package/src/prompt.ts +1 -1
- package/src/result.ts +10 -8
- package/src/storage-backends/cursor-hosted-v2.ts +2 -2
- package/src/storage-backends/cursor-hosted.ts +6 -23
- package/src/storage-backends/file-kv.ts +7 -7
- package/src/storage.ts +22 -7
- package/src/types.ts +82 -17
- package/templates/agentic-owners/agent/channels/github.ts +3 -6
- package/templates/agentic-owners/agent/lib/github.ts +5 -5
- package/templates/agentic-owners/agent/lib/owners/decision.ts +13 -10
- package/templates/agentic-owners/agent/lib/owners/handles.ts +2 -2
- package/templates/agentic-owners/agent/lib/owners/match.ts +3 -3
- package/templates/agentic-owners/agent/lib/owners/matching.ts +1 -1
- package/templates/agentic-owners/agent/lib/owners/parse.ts +4 -9
- package/templates/agentic-owners/agent/lib/owners/prompt.ts +1 -1
- package/templates/agentic-owners/agent/lib/review.ts +37 -30
- package/templates/agentic-owners/evals/owners.eval.ts +2 -2
- package/templates/agentic-owners/package.json +1 -1
- package/templates/agents-md/agent/lib/collect.ts +16 -10
- package/templates/agents-md/agent/lib/config.ts +1 -1
- package/templates/agents-md/agent/tools/apply_agents.ts +10 -8
- package/templates/agents-md/package.json +1 -1
- package/templates/code-wiki/agent/channels/github.ts +4 -7
- package/templates/code-wiki/agent/lib/repos.ts +1 -1
- package/templates/code-wiki/agent/tools/apply_wiki.ts +3 -4
- package/templates/code-wiki/package.json +1 -1
- package/templates/demo/agent/lib/collect.ts +6 -2
- package/templates/demo/agent/lib/repos.ts +1 -1
- package/templates/demo/agent/tools/record_demo.ts +1 -1
- package/templates/demo/evals/demo.eval.ts +1 -5
- package/templates/demo/package.json +1 -1
- package/templates/grokbot-agents/package.json +1 -1
- package/templates/pr-autofixer/agent/channels/github.ts +16 -13
- package/templates/pr-autofixer/agent/lib/merge-watch.ts +2 -4
- package/templates/pr-autofixer/agent/lib/repos.ts +2 -2
- package/templates/pr-autofixer/agent/lib/webhook-routing.ts +1 -1
- package/templates/pr-autofixer/package.json +1 -1
- package/templates/security-help/agent/lib/repos.ts +1 -1
- package/templates/security-help/package.json +1 -1
- package/templates/security-reviewer/agent/lib/repos.ts +1 -1
- package/templates/security-reviewer/agent/tools/post_findings.ts +1 -3
- package/templates/security-reviewer/package.json +1 -1
- package/templates/triage/agent/lib/actuate.ts +26 -41
- package/templates/triage/agent/lib/parse-queue-event.ts +2 -1
- package/templates/triage/agent/lib/verify-webhook.ts +10 -5
- package/templates/triage/agent/tools/record_triage.ts +1 -4
- package/templates/triage/package.json +1 -1
- package/dist/client.d.ts +0 -14
- package/dist/client.d.ts.map +0 -1
- package/dist/client.js +0 -12
- package/dist/docs/assets/app.Cr-wVbnB.js +0 -1
- package/dist/docs/assets/chunks/@localSearchIndexroot.CFVQ4S17.js +0 -1
- package/dist/docs/assets/chunks/framework.BCISBCiQ.js +0 -19
- package/dist/docs/assets/concepts.md.B4o63Gul.js +0 -1
- package/dist/docs/assets/concepts.md.B4o63Gul.lean.js +0 -1
- package/dist/docs/assets/guides_agent-to-agent.md.BDb0t1QV.js +0 -10
- package/dist/docs/assets/guides_agent-to-agent.md.BDb0t1QV.lean.js +0 -1
- package/dist/docs/assets/guides_grokbot-agents.md.DyV-WArv.js +0 -9
- package/dist/docs/assets/guides_human-in-the-loop.md.By1G2T3_.js +0 -28
- package/dist/docs/assets/guides_human-in-the-loop.md.By1G2T3_.lean.js +0 -1
- package/dist/docs/assets/hillclimbing.md.BOiVo1tf.js +0 -4
- package/dist/docs/assets/hillclimbing.md.BOiVo1tf.lean.js +0 -1
- package/dist/docs/assets/index.md.DD9Q2XuJ.js +0 -5
- package/dist/docs/assets/index.md.DD9Q2XuJ.lean.js +0 -1
- package/dist/docs/assets/quickstart.md.DdQOF7Y8.lean.js +0 -1
- package/dist/docs/assets/reference_result.md.BK5SxDrf.js +0 -19
- package/dist/docs/assets/reference_result.md.BK5SxDrf.lean.js +0 -1
- package/dist/docs/assets/scaffolding-agents.md.Kctn3OVb.js +0 -1
- package/dist/docs/assets/scaffolding-agents.md.Kctn3OVb.lean.js +0 -1
- package/dist/docs/assets/skills_create-agent.md.Q3h6Je-e.js +0 -8
- package/dist/docs/assets/skills_create-agent.md.Q3h6Je-e.lean.js +0 -1
- package/dist/docs/assets/skills_debug.md.CVjCXMFF.js +0 -1
- package/dist/docs/assets/skills_debug.md.CVjCXMFF.lean.js +0 -1
- package/dist/docs/assets/skills_deploy.md.CWqi_ZxW.js +0 -35
- package/dist/docs/assets/skills_deploy.md.CWqi_ZxW.lean.js +0 -1
- package/dist/docs/assets/skills_evals.md.DFxYPErF.js +0 -25
- package/dist/docs/assets/skills_evals.md.DFxYPErF.lean.js +0 -1
- package/dist/docs/assets/skills_framework-map.md.BxLSOhSY.js +0 -1
- package/dist/docs/assets/skills_framework-map.md.BxLSOhSY.lean.js +0 -1
- package/dist/docs/assets/skills_github.md.hgFX_oKY.js +0 -16
- package/dist/docs/assets/skills_github.md.hgFX_oKY.lean.js +0 -1
- package/dist/docs/assets/skills_hillclimb.md.B_zJerxA.js +0 -7
- package/dist/docs/assets/skills_hillclimb.md.B_zJerxA.lean.js +0 -1
- package/dist/docs/assets/skills_index.md.DL7EHaQ-.js +0 -1
- package/dist/docs/assets/skills_index.md.DL7EHaQ-.lean.js +0 -1
- package/dist/docs/assets/skills_mcp-auth.md.DGvFP3HE.js +0 -18
- package/dist/docs/assets/skills_mcp-auth.md.DGvFP3HE.lean.js +0 -1
- package/dist/docs/assets/skills_otel.md.B5Ddv1xH.js +0 -8
- package/dist/docs/assets/skills_otel.md.B5Ddv1xH.lean.js +0 -1
- package/dist/docs/assets/skills_setup-slack.md.BBgx8lUz.js +0 -20
- package/dist/docs/assets/skills_setup-slack.md.BBgx8lUz.lean.js +0 -1
- package/dist/docs/assets/storage.md.BUrhJ-Zz.js +0 -30
- package/dist/docs/assets/storage.md.BUrhJ-Zz.lean.js +0 -1
- package/dist/docs/assets/templates_agents-md.md.CXSMZljE.js +0 -2
- package/dist/docs/assets/templates_agents-md.md.CXSMZljE.lean.js +0 -1
- package/dist/docs/assets/templates_code-wiki.md.CDYZIBFN.js +0 -2
- package/dist/docs/assets/templates_code-wiki.md.CDYZIBFN.lean.js +0 -1
- package/dist/docs/assets/templates_demo.md.BeQX9V3H.js +0 -4
- package/dist/docs/assets/templates_demo.md.BeQX9V3H.lean.js +0 -1
- package/dist/docs/assets/templates_grokbot-agents.md.c1s6Flp9.js +0 -3
- package/dist/docs/assets/templates_grokbot-agents.md.c1s6Flp9.lean.js +0 -1
- package/dist/docs/assets/templates_security-help.md.C3Ny_Qr2.js +0 -4
- package/dist/docs/assets/templates_security-help.md.C3Ny_Qr2.lean.js +0 -1
- package/dist/docs/concepts.html +0 -27
- package/dist/docs/concepts.md +0 -166
- package/dist/docs/design/filesystem.md +0 -376
- package/dist/docs/design/runtime-abstraction.md +0 -1756
- package/dist/docs/guides/human-in-the-loop.html +0 -54
- package/dist/docs/guides/human-in-the-loop.md +0 -126
- package/dist/docs/reference/result.html +0 -45
- package/dist/docs/reference/result.md +0 -89
- package/dist/docs/scaffolding-agents.html +0 -27
- package/dist/docs/scaffolding-agents.md +0 -130
- package/dist/docs/skills/create-agent.html +0 -34
- package/dist/docs/skills/create-agent.md +0 -160
- package/dist/docs/skills/debug.html +0 -27
- package/dist/docs/skills/debug.md +0 -36
- package/dist/docs/skills/deploy.html +0 -61
- package/dist/docs/skills/deploy.md +0 -161
- package/dist/docs/skills/evals.html +0 -51
- package/dist/docs/skills/evals.md +0 -137
- package/dist/docs/skills/framework-map.html +0 -27
- package/dist/docs/skills/framework-map.md +0 -99
- package/dist/docs/skills/github.html +0 -42
- package/dist/docs/skills/github.md +0 -93
- package/dist/docs/skills/hillclimb.html +0 -33
- package/dist/docs/skills/hillclimb.md +0 -55
- package/dist/docs/skills/index.html +0 -27
- package/dist/docs/skills/index.md +0 -21
- package/dist/docs/skills/mcp-auth.html +0 -44
- package/dist/docs/skills/mcp-auth.md +0 -76
- package/dist/docs/skills/otel.html +0 -34
- package/dist/docs/skills/otel.md +0 -53
- package/dist/docs/skills/setup-slack.html +0 -46
- package/dist/docs/skills/setup-slack.md +0 -141
- package/dist/docs/storage.html +0 -56
- package/dist/docs/storage.md +0 -167
- package/dist/docs/templates/agents-md.html +0 -28
- package/dist/docs/templates/agents-md.md +0 -105
- package/dist/docs/templates/code-wiki.html +0 -28
- package/dist/docs/templates/code-wiki.md +0 -91
- package/dist/docs/templates/demo.html +0 -30
- package/dist/docs/templates/demo.md +0 -80
- package/dist/docs/templates/grokbot-agents.html +0 -29
- package/dist/docs/templates/grokbot-agents.md +0 -48
- package/dist/docs/templates/security-help.html +0 -30
- package/dist/docs/templates/security-help.md +0 -65
- package/dist/internal/tenant-slack/relay.d.ts +0 -75
- package/dist/internal/tenant-slack/relay.d.ts.map +0 -1
- package/dist/internal/tenant-slack/relay.js +0 -148
- package/dist/playground/assets/index-Bhxzrcf6.css +0 -1
- package/dist/playground/assets/index-CqLX5uF3.js +0 -67
- package/docs/concepts.md +0 -171
- package/docs/design/filesystem.md +0 -376
- package/docs/design/runtime-abstraction.md +0 -1756
- package/docs/guides/human-in-the-loop.md +0 -131
- package/docs/reference/result.md +0 -94
- package/docs/scaffolding-agents.md +0 -135
- package/docs/skills/index.md +0 -26
- package/docs/storage.md +0 -172
- package/docs/templates/agents-md.md +0 -110
- package/docs/templates/code-wiki.md +0 -96
- package/docs/templates/demo.md +0 -85
- package/docs/templates/grokbot-agents.md +0 -53
- package/docs/templates/security-help.md +0 -70
- package/src/client.ts +0 -23
- package/src/internal/tenant-slack/relay.ts +0 -203
- package/templates/pr-autofixer/agent/storage.ts +0 -7
package/dist/docs/evals.html
CHANGED
|
@@ -6,21 +6,54 @@
|
|
|
6
6
|
<title>Evals | Agent SDK</title>
|
|
7
7
|
<meta name="description" content="Write defineEval cases that gate an agent's trajectory, run them with agent-sdk eval locally and in CI, and lock every kept improvement with a regression check.">
|
|
8
8
|
<meta name="generator" content="VitePress v1.6.4">
|
|
9
|
-
<link rel="preload stylesheet" href="/docs/assets/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.
|
|
12
|
+
<script type="module" src="/docs/assets/app.Drol6mi6.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/
|
|
15
|
-
<link rel="modulepreload" href="/docs/assets/chunks/
|
|
16
|
-
<link rel="modulepreload" href="/docs/assets/
|
|
14
|
+
<link rel="modulepreload" href="/docs/assets/chunks/framework.dypDpWZ3.js">
|
|
15
|
+
<link rel="modulepreload" href="/docs/assets/chunks/theme.C0MctGaz.js">
|
|
16
|
+
<link rel="modulepreload" href="/docs/assets/chunks/katex.DkKDou_j.js">
|
|
17
|
+
<link rel="modulepreload" href="/docs/assets/chunks/dagre-KV5264BT.DrRP1fOh.js">
|
|
18
|
+
<link rel="modulepreload" href="/docs/assets/chunks/cose-bilkent-S5V4N54A.8rYtqudO.js">
|
|
19
|
+
<link rel="modulepreload" href="/docs/assets/chunks/c4Diagram-AHTNJAMY.0FBvwBvK.js">
|
|
20
|
+
<link rel="modulepreload" href="/docs/assets/chunks/flowDiagram-DWJPFMVM.BTnQ742_.js">
|
|
21
|
+
<link rel="modulepreload" href="/docs/assets/chunks/erDiagram-SMLLAGMA.-7AWWSrP.js">
|
|
22
|
+
<link rel="modulepreload" href="/docs/assets/chunks/gitGraphDiagram-UUTBAWPF.CZcNTFZd.js">
|
|
23
|
+
<link rel="modulepreload" href="/docs/assets/chunks/ganttDiagram-T4ZO3ILL.B5_HiiQ5.js">
|
|
24
|
+
<link rel="modulepreload" href="/docs/assets/chunks/infoDiagram-42DDH7IO.7pZOkCCU.js">
|
|
25
|
+
<link rel="modulepreload" href="/docs/assets/chunks/pieDiagram-DEJITSTG.CtoaTFlA.js">
|
|
26
|
+
<link rel="modulepreload" href="/docs/assets/chunks/quadrantDiagram-34T5L4WZ.DtT24_vN.js">
|
|
27
|
+
<link rel="modulepreload" href="/docs/assets/chunks/xychartDiagram-5P7HB3ND.B-3k6bF6.js">
|
|
28
|
+
<link rel="modulepreload" href="/docs/assets/chunks/requirementDiagram-MS252O5E.CjSO4o8f.js">
|
|
29
|
+
<link rel="modulepreload" href="/docs/assets/chunks/sequenceDiagram-FGHM5R23.DSk8s4gX.js">
|
|
30
|
+
<link rel="modulepreload" href="/docs/assets/chunks/classDiagram-6PBFFD2Q.CZDco1o8.js">
|
|
31
|
+
<link rel="modulepreload" href="/docs/assets/chunks/classDiagram-v2-HSJHXN6E.CZDco1o8.js">
|
|
32
|
+
<link rel="modulepreload" href="/docs/assets/chunks/stateDiagram-FHFEXIEX.BFKAsdkN.js">
|
|
33
|
+
<link rel="modulepreload" href="/docs/assets/chunks/stateDiagram-v2-QKLJ7IA2.C4CLm481.js">
|
|
34
|
+
<link rel="modulepreload" href="/docs/assets/chunks/journeyDiagram-VCZTEJTY.BNEgWN1S.js">
|
|
35
|
+
<link rel="modulepreload" href="/docs/assets/chunks/timeline-definition-GMOUNBTQ.TUNJbAFe.js">
|
|
36
|
+
<link rel="modulepreload" href="/docs/assets/chunks/mindmap-definition-QFDTVHPH.CnJRI55x.js">
|
|
37
|
+
<link rel="modulepreload" href="/docs/assets/chunks/kanban-definition-6JOO6SKY.B-4d4tC7.js">
|
|
38
|
+
<link rel="modulepreload" href="/docs/assets/chunks/sankeyDiagram-XADWPNL6.-wWiIVWa.js">
|
|
39
|
+
<link rel="modulepreload" href="/docs/assets/chunks/diagram-TYMM5635.CpTJLNJI.js">
|
|
40
|
+
<link rel="modulepreload" href="/docs/assets/chunks/diagram-MMDJMWI5.BWA0xSW9.js">
|
|
41
|
+
<link rel="modulepreload" href="/docs/assets/chunks/blockDiagram-DXYQGD6D.CijZ_taK.js">
|
|
42
|
+
<link rel="modulepreload" href="/docs/assets/chunks/diagram-5BDNPKRD.DHj_xA2_.js">
|
|
43
|
+
<link rel="modulepreload" href="/docs/assets/chunks/architectureDiagram-Q4EWVU46.CcChnMxX.js">
|
|
44
|
+
<link rel="modulepreload" href="/docs/assets/chunks/ishikawaDiagram-UXIWVN3A.DSMo3Qa3.js">
|
|
45
|
+
<link rel="modulepreload" href="/docs/assets/chunks/vennDiagram-DHZGUBPP.C-RGNnk4.js">
|
|
46
|
+
<link rel="modulepreload" href="/docs/assets/chunks/diagram-G4DWMVQ6.Bz_6nAKj.js">
|
|
47
|
+
<link rel="modulepreload" href="/docs/assets/chunks/wardleyDiagram-NUSXRM2D.DH4zt73Y.js">
|
|
48
|
+
<link rel="modulepreload" href="/docs/assets/chunks/virtual_mermaid-config.DDnGl6nM.js">
|
|
49
|
+
<link rel="modulepreload" href="/docs/assets/evals.md.BLDRt5LH.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/evals.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_evals" data-v-38549ef7><div><h1 id="evals" tabindex="-1">Evals <a class="header-anchor" href="#evals" aria-label="Permalink to "Evals""></a></h1><p>An eval sends a fixed message to your agent and asserts over the trajectory it records: the turn completed, the right tool ran with the right input, the reply has the right shape. Evals are how you know a prompt tweak helped, a refactor didn't regress the agent, and last month's fix still holds.</p><p>Nothing is mocked. The runner starts (or targets) a real agent server, drives sessions over the public API, and grades the events it gets back. The model runs and server tools execute, so <a href="#keep-side-effects-out-of-eval-sessions">keep side effects out of eval sessions</a> before you point an eval at an agent that posts anywhere.</p><h2 id="evals-hooks-or-hillclimbing" tabindex="-1">Evals, hooks, or hillclimbing? <a class="header-anchor" href="#evals-hooks-or-hillclimbing" aria-label="Permalink to "Evals, hooks, or hillclimbing?""></a></h2><p>All three read the same session event stream. Pick by the question you are asking.</p><table tabindex="0"><thead><tr><th>You want to</th><th>Use</th></tr></thead><tbody><tr><td>Gate one fixed input's behavior, locally and in CI</td><td>Evals (this page)</td></tr><tr><td>Observe every live session: metrics, audit, alerts</td><td><a href="./reference/hooks.html">Hooks</a></td></tr><tr><td>Improve an agent one measured round at a time</td><td><a href="./hillclimbing.html">Hillclimbing</a>; each kept win lands an eval</td></tr></tbody></table><p><a href="./reference/hooks.html#hooks-channel-events-or-evals">Hooks, channel events, or evals?</a> has the side-by-side table.</p><h3 id="when-not-to-write-an-eval" tabindex="-1">When not to write an eval <a class="header-anchor" href="#when-not-to-write-an-eval" aria-label="Permalink to "When not to write an eval""></a></h3><ul><li>Test a server tool's own logic with <code>agent-sdk call <tool> --dir . --input '{...}'</code> or a unit test. No model turn, no credential.</li><li>Explore a prompt with <code>agent-sdk run --dir . --message "..."</code> and read the trajectory. Write the eval once you know which decision to gate.</li><li>Stop a bad turn while it runs with <a href="./reference/tools.html#gate-a-tool-on-human-approval"><code>needsApproval</code></a> on the tool or <a href="./reference/result.html"><code>defineResult</code></a>. Evals grade after the fact.</li></ul><h2 id="write-your-first-eval" tabindex="-1">Write your first eval <a class="header-anchor" href="#write-your-first-eval" aria-label="Permalink to "Write your first eval""></a></h2><p>Evals live under the project-root <code>evals/</code> directory, a sibling of <code>agent/</code>. <code>agent/evals/</code> is silently ignored. Discovery loads every <code>.eval.ts</code> (or <code>.eval.js</code>) file under <code>evals/</code>, plus one config file.</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>my-agent/</span></span>
|
|
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 0.1.111" data-v-97e8f22b>0.1.111</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-improving Agents</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>Self Improving 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/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/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/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_evals" data-v-afe580da><div><h1 id="evals" tabindex="-1">Evals <a class="header-anchor" href="#evals" aria-label="Permalink to "Evals""></a></h1><p>An eval sends a fixed message to your agent and asserts over the trajectory it records: the turn completed, the right tool ran with the right input, the reply has the right shape. Evals are how you know a prompt tweak helped, a refactor didn't regress the agent, and last month's fix still holds.</p><p>Nothing is mocked. The runner starts (or targets) a real agent server, drives sessions over the public API, and grades the events it gets back. The model runs and server tools execute, so <a href="#keep-side-effects-out-of-eval-sessions">keep side effects out of eval sessions</a> before you point an eval at an agent that posts anywhere.</p><h2 id="evals-hooks-or-hillclimbing" tabindex="-1">Evals, hooks, or hillclimbing? <a class="header-anchor" href="#evals-hooks-or-hillclimbing" aria-label="Permalink to "Evals, hooks, or hillclimbing?""></a></h2><p>All three read the same session event stream. Pick by the question you are asking.</p><table tabindex="0"><thead><tr><th>You want to</th><th>Use</th></tr></thead><tbody><tr><td>Gate one fixed input's behavior, locally and in CI</td><td>Evals (this page)</td></tr><tr><td>Observe every live session: metrics, audit, alerts</td><td><a href="./reference/hooks.html">Hooks</a></td></tr><tr><td>Improve an agent one measured round at a time</td><td><a href="./hillclimbing.html">Hillclimbing</a>; each kept win lands an eval</td></tr></tbody></table><p><a href="./reference/hooks.html#hooks-channel-events-or-evals">Hooks, channel events, or evals?</a> has the side-by-side table.</p><h3 id="when-not-to-write-an-eval" tabindex="-1">When not to write an eval <a class="header-anchor" href="#when-not-to-write-an-eval" aria-label="Permalink to "When not to write an eval""></a></h3><ul><li>Test a server tool's own logic with <code>agent-sdk call <tool> --dir . --input '{...}'</code> or a unit test. No model turn, no credential.</li><li>Explore a prompt with <code>agent-sdk run --dir . --message "..."</code> and read the trajectory. Write the eval once you know which decision to gate.</li><li>Stop a bad turn while it runs with <a href="./reference/tools.html#gate-a-tool-on-human-approval"><code>needsApproval</code></a> on the tool or <code>defineResult</code>. Evals grade after the fact.</li></ul><h2 id="write-your-first-eval" tabindex="-1">Write your first eval <a class="header-anchor" href="#write-your-first-eval" aria-label="Permalink to "Write your first eval""></a></h2><p>Evals live under the project-root <code>evals/</code> directory, a sibling of <code>agent/</code>. <code>agent/evals/</code> is silently ignored. Discovery loads every <code>.eval.ts</code> (or <code>.eval.js</code>) file under <code>evals/</code>, plus one config file.</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>my-agent/</span></span>
|
|
24
57
|
<span class="line"><span> agent/</span></span>
|
|
25
58
|
<span class="line"><span> agent.ts</span></span>
|
|
26
59
|
<span class="line"><span> tools/inspect_pr.ts</span></span>
|
|
@@ -80,7 +113,7 @@
|
|
|
80
113
|
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> },</span></span>
|
|
81
114
|
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> },</span></span>
|
|
82
115
|
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> ],</span></span>
|
|
83
|
-
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">});</span></span></code></pre></div><p>Case ids are single path segments, unique within the file. A case can set its own <code>description</code>, <code>tags</code>, <code>timeoutMs</code>, <code>iterations</code>, <code>judge</code>, <code>reporters</code>, and <code>metadata</code>. A case-level value replaces the file-level one for that datapoint, except <code>metadata</code>, which merges with case keys winning, and <code>reporters</code>, which adds to the file's list. <code>metadata</code> is free-form data carried onto the result and every reporter.</p><p>A file may instead export an array of <code>defineEval</code> calls to fan out over a dataset. Ids are then the file id plus a zero-padded index (<code>sql/0000</code>, <code>sql/0001</code>, ...); see <a href="#load-a-dataset">Load a dataset</a>. Prefer <code>cases</code> when datapoints are hand-written and deserve stable names.</p><h3 id="iterations" tabindex="-1">Iterations <a class="header-anchor" href="#iterations" aria-label="Permalink to "Iterations""></a></h3><p><code>iterations</code> (file or case, default <code>1</code>, cap <code>100</code>) runs a datapoint repeatedly. Discovery expands <code>iterations: 3</code> on case <code>nyc</code> to runnable ids <code>weather/nyc/1</code>, <code>weather/nyc/2</code>, and <code>weather/nyc/3</code>. The filter <code>weather/nyc</code> still selects all three. Each expanded case exposes <code>t.iteration</code> and <code>t.iterations</code>.</p><p><code>maxConcurrency</code> counts authored datapoints, not expanded iterations. Iterations of one datapoint share a concurrency slot and run in sequence, so a suite of 11 cases with 3 iterations each and <code>maxConcurrency: 20</code> has at most 11 cases in flight.</p><h2 id="drive-the-agent-with-t-send" tabindex="-1">Drive the agent with <code>t.send</code> <a class="header-anchor" href="#drive-the-agent-with-t-send" aria-label="Permalink to "Drive the agent with `t.send`""></a></h2><p><code>t.send(message, options?)</code> runs one turn and waits for it to settle: complete, park on an approval request, or fail. Several sends in one case share the session, which is how you write multi-turn evals.</p><p>Each send resolves to a turn result: <code>message</code> (the assistant text), <code>sessionId</code>, <code>events</code>, <code>toolCalls</code> (tool names in order), <code>ok</code>, and <code>index</code>. The turn carries the same assertion vocabulary as <code>t</code>, scoped to that turn, so you can grade an intermediate turn before the next send overwrites <code>t.reply</code>. <code>turn.expectOk()</code> throws when the turn failed, for later steps that depend on it.</p><p>Read the whole case with <code>t.reply</code> (last assistant text), <code>t.events</code> (every event so far), <code>t.turns</code> (settled turns, oldest first), and <code>t.sessionId</code>. <code>t.signal</code> aborts when the case hits its timeout; pass it to your own async work.</p><p>Three options apply on the first send only, because they shape session creation:</p><table tabindex="0"><thead><tr><th>Option</th><th>Effect</th></tr></thead><tbody><tr><td><code>workspaceFiles</code></td><td><code>{ path: contents }</code> seeded into the local session workspace. Prefer this over machine-local paths</td></tr><tr><td><code>workspaceDir</code></td><td>Absolute harness cwd for the local runtime</td></tr><tr><td><code>cloud</code></td><td>Per-session cloud options merged over the agent's static <code>cloud</code> config. Pin a fixture repo here for cloud evals instead of on the agent's default <code>cloud.repos</code>. On the cloud runtime, seeded files reach the agent as described under <a href="./
|
|
116
|
+
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">});</span></span></code></pre></div><p>Case ids are single path segments, unique within the file. A case can set its own <code>description</code>, <code>tags</code>, <code>timeoutMs</code>, <code>iterations</code>, <code>judge</code>, <code>reporters</code>, and <code>metadata</code>. A case-level value replaces the file-level one for that datapoint, except <code>metadata</code>, which merges with case keys winning, and <code>reporters</code>, which adds to the file's list. <code>metadata</code> is free-form data carried onto the result and every reporter.</p><p>A file may instead export an array of <code>defineEval</code> calls to fan out over a dataset. Ids are then the file id plus a zero-padded index (<code>sql/0000</code>, <code>sql/0001</code>, ...); see <a href="#load-a-dataset">Load a dataset</a>. Prefer <code>cases</code> when datapoints are hand-written and deserve stable names.</p><h3 id="iterations" tabindex="-1">Iterations <a class="header-anchor" href="#iterations" aria-label="Permalink to "Iterations""></a></h3><p><code>iterations</code> (file or case, default <code>1</code>, cap <code>100</code>) runs a datapoint repeatedly. Discovery expands <code>iterations: 3</code> on case <code>nyc</code> to runnable ids <code>weather/nyc/1</code>, <code>weather/nyc/2</code>, and <code>weather/nyc/3</code>. The filter <code>weather/nyc</code> still selects all three. Each expanded case exposes <code>t.iteration</code> and <code>t.iterations</code>.</p><p><code>maxConcurrency</code> counts authored datapoints, not expanded iterations. Iterations of one datapoint share a concurrency slot and run in sequence, so a suite of 11 cases with 3 iterations each and <code>maxConcurrency: 20</code> has at most 11 cases in flight.</p><h2 id="drive-the-agent-with-t-send" tabindex="-1">Drive the agent with <code>t.send</code> <a class="header-anchor" href="#drive-the-agent-with-t-send" aria-label="Permalink to "Drive the agent with `t.send`""></a></h2><p><code>t.send(message, options?)</code> runs one turn and waits for it to settle: complete, park on an approval request, or fail. Several sends in one case share the session, which is how you write multi-turn evals.</p><p>Each send resolves to a turn result: <code>message</code> (the assistant text), <code>sessionId</code>, <code>events</code>, <code>toolCalls</code> (tool names in order), <code>ok</code>, and <code>index</code>. The turn carries the same assertion vocabulary as <code>t</code>, scoped to that turn, so you can grade an intermediate turn before the next send overwrites <code>t.reply</code>. <code>turn.expectOk()</code> throws when the turn failed, for later steps that depend on it.</p><p>Read the whole case with <code>t.reply</code> (last assistant text), <code>t.events</code> (every event so far), <code>t.turns</code> (settled turns, oldest first), and <code>t.sessionId</code>. <code>t.signal</code> aborts when the case hits its timeout; pass it to your own async work.</p><p>Three options apply on the first send only, because they shape session creation:</p><table tabindex="0"><thead><tr><th>Option</th><th>Effect</th></tr></thead><tbody><tr><td><code>workspaceFiles</code></td><td><code>{ path: contents }</code> seeded into the local session workspace. Prefer this over machine-local paths</td></tr><tr><td><code>workspaceDir</code></td><td>Absolute harness cwd for the local runtime</td></tr><tr><td><code>cloud</code></td><td>Per-session cloud options merged over the agent's static <code>cloud</code> config. Pin a fixture repo here for cloud evals instead of on the agent's default <code>cloud.repos</code>. On the cloud runtime, seeded files reach the agent as described under <a href="./reference/agent-config.html#choose-a-runtime">Choose a runtime</a></td></tr></tbody></table><div class="language-ts vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">ts</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;">await</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> t.</span><span style="--shiki-light:#6F42C1;--shiki-dark:#B392F0;">send</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">(</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">"Review pr/diff.patch and post findings."</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">, {</span></span>
|
|
84
117
|
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> workspaceFiles: {</span></span>
|
|
85
118
|
<span class="line"><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;"> "pr/diff.patch"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: [</span></span>
|
|
86
119
|
<span class="line"><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;"> "diff --git a/app/routes/search.ts b/app/routes/search.ts"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">,</span></span>
|
|
@@ -130,7 +163,7 @@
|
|
|
130
163
|
<span class="line"><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;"> return</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> { posted: </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">false</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">, reason: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">"eval"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">, count: findings.</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">length</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> };</span></span>
|
|
131
164
|
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> }</span></span>
|
|
132
165
|
<span class="line"><span style="--shiki-light:#6A737D;--shiki-dark:#6A737D;"> // post the review</span></span>
|
|
133
|
-
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">}</span></span></code></pre></div><p>Return a shaped result instead of throwing, so the eval can still assert <code>t.calledTool("post_findings", { input: ... })</code> on the decision. The same check belongs in <a href="./reference/hooks.html">hooks</a> that meter or page and in <
|
|
166
|
+
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">}</span></span></code></pre></div><p>Return a shaped result instead of throwing, so the eval can still assert <code>t.calledTool("post_findings", { input: ... })</code> on the decision. The same check belongs in <a href="./reference/hooks.html">hooks</a> that meter or page and in <code>defineResult</code> commits.</p><h2 id="worked-examples" tabindex="-1">Worked examples <a class="header-anchor" href="#worked-examples" aria-label="Permalink to "Worked examples""></a></h2><h3 id="multi-turn-grade-each-turn" tabindex="-1">Multi-turn: grade each turn <a class="header-anchor" href="#multi-turn-grade-each-turn" aria-label="Permalink to "Multi-turn: grade each turn""></a></h3><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:#6A737D;--shiki-dark:#6A737D;">// evals/intro.eval.ts</span></span>
|
|
134
167
|
<span class="line"><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;">import</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> { defineEval, includes, satisfies } </span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;">from</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;"> "@cursor/july/evals"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">;</span></span>
|
|
135
168
|
<span class="line"></span>
|
|
136
169
|
<span class="line"><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;">export</span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;"> default</span><span style="--shiki-light:#6F42C1;--shiki-dark:#B392F0;"> defineEval</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">({</span></span>
|
|
@@ -190,7 +223,7 @@
|
|
|
190
223
|
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> maxConcurrency: </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">20</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">,</span></span>
|
|
191
224
|
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> timeoutMs: </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">180_000</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">,</span></span>
|
|
192
225
|
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> judge: { model: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">"gpt-5.4-mini"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> },</span></span>
|
|
193
|
-
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">});</span></span></code></pre></div><table tabindex="0"><thead><tr><th>Option</th><th>Default</th><th>Meaning</th></tr></thead><tbody><tr><td><code>maxConcurrency</code></td><td>required</td><td>Datapoints in flight at once, 1-200</td></tr><tr><td><code>timeoutMs</code></td><td><code>180_000</code></td><td>Per-case timeout. Precedence: case or file <code>timeoutMs</code>, then <code>--timeout-ms</code>, then this value</td></tr><tr><td><code>judge</code></td><td>unset</td><td>Default judge model for <code>t.judge.*</code></td></tr><tr><td><code>reporters</code></td><td>unset</td><td>Destinations that observe every case; <code>--skip-report</code> suppresses them</td></tr><tr><td><code>maxPlaygroundRuns</code></td><td><code>20</code></td><td>Batches kept in playground history (cap 500). Counts <code>--prod</code> and <code>--url</code> batches, not the default local run</td></tr></tbody></table><p>Reporters ship results somewhere; the runner still does the grading. <code>JUnit({ filePath, suiteName? })</code> writes JUnit XML and <code>Artifacts({ dir })</code> writes per-case files, both from <code>@cursor/july/evals/reporters</code>. A custom reporter is an object with any of <code>onRunStart</code>, <code>onEvalComplete</code>, and <code>onRunComplete</code>. A reporter that throws is logged and never fails the run. CI usually attaches the built-in two with <code>--junit</code> and <code>--artifacts</code> instead of <code>reporters</code>, so output paths stay with the pipeline, not the eval author.</p><p>Playground batches survive restarts when the project
|
|
226
|
+
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">});</span></span></code></pre></div><table tabindex="0"><thead><tr><th>Option</th><th>Default</th><th>Meaning</th></tr></thead><tbody><tr><td><code>maxConcurrency</code></td><td>required</td><td>Datapoints in flight at once, 1-200</td></tr><tr><td><code>timeoutMs</code></td><td><code>180_000</code></td><td>Per-case timeout. Precedence: case or file <code>timeoutMs</code>, then <code>--timeout-ms</code>, then this value</td></tr><tr><td><code>judge</code></td><td>unset</td><td>Default judge model for <code>t.judge.*</code></td></tr><tr><td><code>reporters</code></td><td>unset</td><td>Destinations that observe every case; <code>--skip-report</code> suppresses them</td></tr><tr><td><code>maxPlaygroundRuns</code></td><td><code>20</code></td><td>Batches kept in playground history (cap 500). Counts <code>--prod</code> and <code>--url</code> batches, not the default local run</td></tr></tbody></table><p>Reporters ship results somewhere; the runner still does the grading. <code>JUnit({ filePath, suiteName? })</code> writes JUnit XML and <code>Artifacts({ dir })</code> writes per-case files, both from <code>@cursor/july/evals/reporters</code>. A custom reporter is an object with any of <code>onRunStart</code>, <code>onEvalComplete</code>, and <code>onRunComplete</code>. A reporter that throws is logged and never fails the run. CI usually attaches the built-in two with <code>--junit</code> and <code>--artifacts</code> instead of <code>reporters</code>, so output paths stay with the pipeline, not the eval author.</p><p>Playground batches survive restarts when the project configures durable storage. Otherwise they live in process memory until <code>serve</code> exits.</p><h2 id="run-evals-from-the-cli" tabindex="-1">Run evals from the CLI <a class="header-anchor" href="#run-evals-from-the-cli" aria-label="Permalink to "Run evals from the CLI""></a></h2><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;"> --list</span><span style="--shiki-light:#6A737D;--shiki-dark:#6A737D;"> # discover only</span></span>
|
|
194
227
|
<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:#6A737D;--shiki-dark:#6A737D;"> # run all</span></span>
|
|
195
228
|
<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:#032F62;--shiki-dark:#9ECBFF;"> builds/checkout</span><span style="--shiki-light:#6A737D;--shiki-dark:#6A737D;"> # one datapoint</span></span>
|
|
196
229
|
<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:#032F62;--shiki-dark:#9ECBFF;"> builds</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;"> search</span><span style="--shiki-light:#6A737D;--shiki-dark:#6A737D;"> # several ids or prefixes</span></span>
|
|
@@ -230,8 +263,8 @@
|
|
|
230
263
|
<span class="line"><span style="--shiki-light:#6A737D;--shiki-dark:#6A737D;"># Eval ID: <evalId></span></span>
|
|
231
264
|
<span class="line"><span style="--shiki-light:#6A737D;--shiki-dark:#6A737D;"># Playground: <deployment>/playground?view=evals&evalRunId=<evalId></span></span>
|
|
232
265
|
<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:#032F62;--shiki-dark:#9ECBFF;"> status</span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;"> <</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">evalI</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">d</span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;">></span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> --prod</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> --slug</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;"> vulnerability-scanner</span></span>
|
|
233
|
-
<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:#032F62;--shiki-dark:#9ECBFF;"> cancel</span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;"> <</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">evalI</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">d</span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;">></span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> --prod</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> --slug</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;"> vulnerability-scanner</span></span></code></pre></div><p>The CLI prints the Eval ID as soon as the batch is accepted. Pass <code>--no-wait</code> to return right away and poll with <code>eval status</code> later; it exits <code>3</code> while the batch is still running. Hosted history follows <code>maxPlaygroundRuns</code> and the persistence rule under <a href="#configure-eval-runs">Configure eval runs</a>. The HTTP surface is under <a href="./reference/http-api.html#playground-eval-routes">Playground eval routes</a>.</p><h2 id="keep-improvements-with-regression-evals" tabindex="-1">Keep improvements with regression evals <a class="header-anchor" href="#keep-improvements-with-regression-evals" aria-label="Permalink to "Keep improvements with regression evals""></a></h2><p>Every <a href="./hillclimbing.html">hillclimb</a> round that keeps a change must land an eval that would have failed before the change. If you can't express the improvement as a gate (a <code>calledTool</code> shift, a bounded <code>maxToolCalls</code>, an output-shape check), the improvement is unverified, and it'll regress silently.</p><p>The rule cuts the other way too: never weaken an existing gate to make a round pass. That's the freeze line moving, and it turns your regression suite into a list of checks that no longer protect anything.</p><h2 id="what-s-next" tabindex="-1">What's next <a class="header-anchor" href="#what-s-next" aria-label="Permalink to "What's next""></a></h2><p>Continue with these pages:</p><ul><li><a href="./hillclimbing.html">Hillclimbing</a>: the loop evals make trustworthy</li><li><a href="./building-with-agents.html">Building agents with agents</a>: have a coding agent write the first suite</li><li><a href="./guides/github.html">GitHub guide</a>: deterministic webhook fixtures with <code>github replay</code></li><li><a href="./reference/sessions.html">Sessions and streaming</a>: the events <code>t.events</code> contains</li></ul></div></div></main><footer class="VPDocFooter" data-v-
|
|
234
|
-
<script>window.__VP_HASH_MAP__=JSON.parse("{\"building-with-agents.md\":\"
|
|
266
|
+
<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:#032F62;--shiki-dark:#9ECBFF;"> cancel</span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;"> <</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">evalI</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">d</span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;">></span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> --prod</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> --slug</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;"> vulnerability-scanner</span></span></code></pre></div><p>The CLI prints the Eval ID as soon as the batch is accepted. Pass <code>--no-wait</code> to return right away and poll with <code>eval status</code> later; it exits <code>3</code> while the batch is still running. Hosted history follows <code>maxPlaygroundRuns</code> and the persistence rule under <a href="#configure-eval-runs">Configure eval runs</a>. The HTTP surface is under <a href="./reference/http-api.html#playground-eval-routes">Playground eval routes</a>.</p><h2 id="keep-improvements-with-regression-evals" tabindex="-1">Keep improvements with regression evals <a class="header-anchor" href="#keep-improvements-with-regression-evals" aria-label="Permalink to "Keep improvements with regression evals""></a></h2><p>Every <a href="./hillclimbing.html">hillclimb</a> round that keeps a change must land an eval that would have failed before the change. If you can't express the improvement as a gate (a <code>calledTool</code> shift, a bounded <code>maxToolCalls</code>, an output-shape check), the improvement is unverified, and it'll regress silently.</p><p>The rule cuts the other way too: never weaken an existing gate to make a round pass. That's the freeze line moving, and it turns your regression suite into a list of checks that no longer protect anything.</p><h2 id="what-s-next" tabindex="-1">What's next <a class="header-anchor" href="#what-s-next" aria-label="Permalink to "What's next""></a></h2><p>Continue with these pages:</p><ul><li><a href="./hillclimbing.html">Hillclimbing</a>: the loop evals make trustworthy</li><li><a href="./building-with-agents.html">Building agents with agents</a>: have a coding agent write the first suite</li><li><a href="./guides/github.html">GitHub guide</a>: deterministic webhook fixtures with <code>github replay</code></li><li><a href="./reference/sessions.html">Sessions and streaming</a>: the events <code>t.events</code> contains</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/deployment.html" data-v-feab96e0><!--[--><span class="desc" data-v-feab96e0>Previous page</span><span class="title" data-v-feab96e0>Deployment</span><!--]--></a></div><div class="pager" data-v-feab96e0><a class="VPLink link pager-link next" href="/docs/hillclimbing.html" data-v-feab96e0><!--[--><span class="desc" data-v-feab96e0>Next page</span><span class="title" data-v-feab96e0>Hillclimbing</span><!--]--></a></div></nav></footer><!--[--><!--]--></div></div></div><!--[--><!--]--></div></div><!----><!--[--><!--]--></div></div>
|
|
267
|
+
<script>window.__VP_HASH_MAP__=JSON.parse("{\"building-with-agents.md\":\"CEGVXkmO\",\"deployment.md\":\"Dm4Qo3hp\",\"evals.md\":\"BLDRt5LH\",\"guides_agent-to-agent.md\":\"BI0xclmy\",\"guides_bitbucket.md\":\"CTpCl__f\",\"guides_cloud-agents.md\":\"lSE_l7lH\",\"guides_convert-automation.md\":\"Ck6Cr68A\",\"guides_github.md\":\"D6ER29dG\",\"guides_gitlab.md\":\"P-TjBnS5\",\"guides_grokbot-agents.md\":\"WBZIOvkz\",\"guides_improve.md\":\"BKaDuKKK\",\"guides_mcp-oauth.md\":\"DMNMpXtO\",\"guides_opentelemetry.md\":\"_CRfDyzH\",\"guides_slack.md\":\"DdT8rmsj\",\"guides_webhooks.md\":\"aQW10HRe\",\"hillclimbing.md\":\"Dq4kkVIL\",\"index.md\":\"BFVyY2KT\",\"quickstart.md\":\"D3MjSZN-\",\"reference_agent-config.md\":\"CfVA-LZJ\",\"reference_artifacts.md\":\"Vf7qyIZ-\",\"reference_channels.md\":\"icqLKcTc\",\"reference_cli.md\":\"B2dBL6L8\",\"reference_connections.md\":\"Cb3U_c8n\",\"reference_extensions.md\":\"wlFD3cUR\",\"reference_hooks.md\":\"CZuynAxj\",\"reference_http-api.md\":\"DTKcYE6L\",\"reference_instructions.md\":\"D7gkckK-\",\"reference_playground.md\":\"D2YExv5K\",\"reference_project-layout.md\":\"DPxbUJyt\",\"reference_prompt.md\":\"BQ5uAv1F\",\"reference_schedules.md\":\"BasfZWO-\",\"reference_sessions.md\":\"YKvIsWAx\",\"reference_skills.md\":\"rNgpsGd0\",\"reference_subagents.md\":\"e5qitjJt\",\"reference_tools.md\":\"BdCO2aHZ\",\"templates_agentic-owners.md\":\"Da_AGDlH\",\"templates_pr-autofixer.md\":\"DqxocIGh\",\"templates_security-reviewer.md\":\"Bhnvd8VE\",\"templates_triage.md\":\"BdBWO9Ic\",\"troubleshooting.md\":\"BcgNoYtJ\"}");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\":\"0.1.111\",\"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-improving Agents\",\"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\":\"Self Improving Agents\",\"link\":\"/building-with-agents\"},{\"text\":\"Troubleshooting\",\"link\":\"/troubleshooting\"}]},{\"text\":\"Templates\",\"collapsed\":false,\"items\":[{\"text\":\"Security reviewer\",\"link\":\"/templates/security-reviewer\"},{\"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\":\"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>
|
|
235
268
|
|
|
236
269
|
</body>
|
|
237
270
|
</html>
|
package/dist/docs/evals.md
CHANGED
|
@@ -36,7 +36,7 @@ has the side-by-side table.
|
|
|
36
36
|
gate.
|
|
37
37
|
- Stop a bad turn while it runs with
|
|
38
38
|
[`needsApproval`](/docs/reference/tools.md#gate-a-tool-on-human-approval)
|
|
39
|
-
on the tool or
|
|
39
|
+
on the tool or `defineResult`. Evals grade
|
|
40
40
|
after the fact.
|
|
41
41
|
|
|
42
42
|
## Write your first eval
|
|
@@ -201,7 +201,7 @@ creation:
|
|
|
201
201
|
| --- | --- |
|
|
202
202
|
| `workspaceFiles` | `{ path: contents }` seeded into the local session workspace. Prefer this over machine-local paths |
|
|
203
203
|
| `workspaceDir` | Absolute harness cwd for the local runtime |
|
|
204
|
-
| `cloud` | Per-session cloud options merged over the agent's static `cloud` config. Pin a fixture repo here for cloud evals instead of on the agent's default `cloud.repos`. On the cloud runtime, seeded files reach the agent as described under [
|
|
204
|
+
| `cloud` | Per-session cloud options merged over the agent's static `cloud` config. Pin a fixture repo here for cloud evals instead of on the agent's default `cloud.repos`. On the cloud runtime, seeded files reach the agent as described under [Choose a runtime](/docs/reference/agent-config.md#choose-a-runtime) |
|
|
205
205
|
|
|
206
206
|
```ts
|
|
207
207
|
await t.send("Review pr/diff.patch and post findings.", {
|
|
@@ -436,7 +436,7 @@ async execute({ findings }, ctx) {
|
|
|
436
436
|
Return a shaped result instead of throwing, so the eval can still
|
|
437
437
|
assert `t.calledTool("post_findings", { input: ... })` on the decision.
|
|
438
438
|
The same check belongs in [hooks](/docs/reference/hooks.md) that meter or
|
|
439
|
-
page and in
|
|
439
|
+
page and in `defineResult` commits.
|
|
440
440
|
|
|
441
441
|
## Worked examples
|
|
442
442
|
|
|
@@ -598,8 +598,8 @@ throws is logged and never fails the run. CI usually attaches the
|
|
|
598
598
|
built-in two with `--junit` and `--artifacts` instead of `reporters`,
|
|
599
599
|
so output paths stay with the pipeline, not the eval author.
|
|
600
600
|
|
|
601
|
-
Playground batches survive restarts when the project
|
|
602
|
-
|
|
601
|
+
Playground batches survive restarts when the project configures
|
|
602
|
+
durable storage. Otherwise they live in process
|
|
603
603
|
memory until `serve` exits.
|
|
604
604
|
|
|
605
605
|
## Run evals from the CLI
|