@grok/agent-sdk 0.2.29 → 0.3.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/dist/channels/slack/cli-project.js +1 -1
- package/dist/docs/404.html +2 -2
- package/dist/docs/assets/{app.DMrZKFjI.js → app.BzTUBOAD.js} +4 -4
- package/dist/docs/assets/building-with-agents.md.BqJ7AAjG.js +6 -0
- package/dist/docs/assets/{building-with-agents.md.Bf1yH2tG.lean.js → building-with-agents.md.BqJ7AAjG.lean.js} +1 -1
- package/dist/docs/assets/changelog.md.BWhC6DET.js +1 -0
- package/dist/docs/assets/changelog.md.BWhC6DET.lean.js +1 -0
- package/dist/docs/assets/chunks/@localSearchIndexroot.CWxwVoCG.js +1 -0
- package/dist/docs/assets/chunks/{VPLocalSearchBox.DQvuw1KA.js → VPLocalSearchBox.DsnRlUT5.js} +1 -1
- package/dist/docs/assets/chunks/{arc.ahOG-Qza.js → arc.DH8GOhiv.js} +1 -1
- package/dist/docs/assets/chunks/{architectureDiagram-Q4EWVU46.BcgfYNO_.js → architectureDiagram-Q4EWVU46.9m9ObyuE.js} +1 -1
- package/dist/docs/assets/chunks/{baseUniq.DeIYZrWh.js → baseUniq.BXHpx1lE.js} +1 -1
- package/dist/docs/assets/chunks/{blockDiagram-DXYQGD6D.HjJ2goMX.js → blockDiagram-DXYQGD6D.xY3EX59q.js} +1 -1
- package/dist/docs/assets/chunks/{c4Diagram-AHTNJAMY.C1QTb9GM.js → c4Diagram-AHTNJAMY.DnqgMVgc.js} +1 -1
- package/dist/docs/assets/chunks/channel.Cctv0f7X.js +1 -0
- package/dist/docs/assets/chunks/{chunk-4BX2VUAB.UuZiDiVp.js → chunk-4BX2VUAB.BjFxK2A3.js} +1 -1
- package/dist/docs/assets/chunks/{chunk-4TB4RGXK.5A3YmkhI.js → chunk-4TB4RGXK.BujS_Spt.js} +1 -1
- package/dist/docs/assets/chunks/{chunk-55IACEB6.B4uf1yYV.js → chunk-55IACEB6.YbTjhdaM.js} +1 -1
- package/dist/docs/assets/chunks/{chunk-EDXVE4YY.CoXBce8t.js → chunk-EDXVE4YY.DnQ8t4GC.js} +1 -1
- package/dist/docs/assets/chunks/{chunk-FMBD7UC4.DnC5NO4e.js → chunk-FMBD7UC4.B67AwAmj.js} +1 -1
- package/dist/docs/assets/chunks/{chunk-OYMX7WX6.CzfHCeIi.js → chunk-OYMX7WX6.DrZIAFOm.js} +1 -1
- package/dist/docs/assets/chunks/{chunk-QZHKN3VN.C6tcwkVd.js → chunk-QZHKN3VN.BLmmydkn.js} +1 -1
- package/dist/docs/assets/chunks/{chunk-YZCP3GAM._oboyZ1A.js → chunk-YZCP3GAM.DaoOfw0O.js} +1 -1
- package/dist/docs/assets/chunks/classDiagram-6PBFFD2Q.DU5sqchW.js +1 -0
- package/dist/docs/assets/chunks/classDiagram-v2-HSJHXN6E.DU5sqchW.js +1 -0
- package/dist/docs/assets/chunks/clone.B9rdNt6j.js +1 -0
- package/dist/docs/assets/chunks/{cose-bilkent-S5V4N54A.BfPVKeId.js → cose-bilkent-S5V4N54A.DMQuNhM5.js} +1 -1
- package/dist/docs/assets/chunks/{dagre-KV5264BT.CLMLc0lD.js → dagre-KV5264BT.CZoGVuUf.js} +1 -1
- package/dist/docs/assets/chunks/{diagram-5BDNPKRD.C7OF7UfH.js → diagram-5BDNPKRD.CLt9uOyL.js} +1 -1
- package/dist/docs/assets/chunks/{diagram-G4DWMVQ6.Dpao0Bl1.js → diagram-G4DWMVQ6.DpczEm1G.js} +1 -1
- package/dist/docs/assets/chunks/{diagram-MMDJMWI5.DLnM9eLp.js → diagram-MMDJMWI5.D4r13DvJ.js} +1 -1
- package/dist/docs/assets/chunks/{diagram-TYMM5635.BcpVgA_M.js → diagram-TYMM5635.CYU9eGFu.js} +1 -1
- package/dist/docs/assets/chunks/{erDiagram-SMLLAGMA.CsL5JuCV.js → erDiagram-SMLLAGMA.QA9naWEw.js} +1 -1
- package/dist/docs/assets/chunks/{flowDiagram-DWJPFMVM.MFihq9AF.js → flowDiagram-DWJPFMVM.BbNoVZYd.js} +1 -1
- package/dist/docs/assets/chunks/{ganttDiagram-T4ZO3ILL.CJeLodyG.js → ganttDiagram-T4ZO3ILL.IHjDoG7r.js} +1 -1
- package/dist/docs/assets/chunks/{gitGraphDiagram-UUTBAWPF.1HhlE45Z.js → gitGraphDiagram-UUTBAWPF.B21VMdf5.js} +1 -1
- package/dist/docs/assets/chunks/{graph.BS02KkWA.js → graph.DgJ4L-8V.js} +1 -1
- package/dist/docs/assets/chunks/{infoDiagram-42DDH7IO.fp5gvytQ.js → infoDiagram-42DDH7IO.CQjrcthc.js} +1 -1
- package/dist/docs/assets/chunks/{ishikawaDiagram-UXIWVN3A.C6Wk1V4I.js → ishikawaDiagram-UXIWVN3A.D4tPGtVo.js} +1 -1
- package/dist/docs/assets/chunks/{journeyDiagram-VCZTEJTY.qJt4uJ_H.js → journeyDiagram-VCZTEJTY.BD3WaNbQ.js} +1 -1
- package/dist/docs/assets/chunks/{kanban-definition-6JOO6SKY.z2tG9kly.js → kanban-definition-6JOO6SKY.Ca0o4Tqz.js} +1 -1
- package/dist/docs/assets/chunks/{layout.BPCkdejr.js → layout.DXXqX4MQ.js} +1 -1
- package/dist/docs/assets/chunks/{linear.CL3TC3u7.js → linear.5c61gNw4.js} +1 -1
- package/dist/docs/assets/chunks/{min.SPrSp704.js → min.B1-NAjHX.js} +1 -1
- package/dist/docs/assets/chunks/{mindmap-definition-QFDTVHPH.DgrQRFZW.js → mindmap-definition-QFDTVHPH.BELznv3-.js} +1 -1
- package/dist/docs/assets/chunks/{pieDiagram-DEJITSTG.Ba7yxiW2.js → pieDiagram-DEJITSTG.qPzO1mq5.js} +1 -1
- package/dist/docs/assets/chunks/{quadrantDiagram-34T5L4WZ.Bvskad4p.js → quadrantDiagram-34T5L4WZ.CxIvzbjX.js} +1 -1
- package/dist/docs/assets/chunks/{requirementDiagram-MS252O5E.Ce70ugV9.js → requirementDiagram-MS252O5E.CqA0iJx8.js} +1 -1
- package/dist/docs/assets/chunks/{sankeyDiagram-XADWPNL6.BJ5OEULO.js → sankeyDiagram-XADWPNL6.XRTutBnb.js} +1 -1
- package/dist/docs/assets/chunks/{sequenceDiagram-FGHM5R23.C8a1hDs6.js → sequenceDiagram-FGHM5R23.E--7bRLQ.js} +1 -1
- package/dist/docs/assets/chunks/{stateDiagram-FHFEXIEX.D2D8A5CK.js → stateDiagram-FHFEXIEX.C4vGu8zq.js} +1 -1
- package/dist/docs/assets/chunks/stateDiagram-v2-QKLJ7IA2.ECMu2BdJ.js +1 -0
- package/dist/docs/assets/chunks/{theme.DRciHmS1.js → theme.DMj_7q3B.js} +2 -2
- package/dist/docs/assets/chunks/{timeline-definition-GMOUNBTQ.C4ePrY8-.js → timeline-definition-GMOUNBTQ.C7LgNVAL.js} +1 -1
- package/dist/docs/assets/chunks/{vennDiagram-DHZGUBPP.Dzso6dEA.js → vennDiagram-DHZGUBPP.HUwoZcy_.js} +1 -1
- package/dist/docs/assets/chunks/{wardley-RL74JXVD.djgXR0ar.js → wardley-RL74JXVD.BxFEFYZS.js} +1 -1
- package/dist/docs/assets/chunks/{wardleyDiagram-NUSXRM2D.Bf2ICxjh.js → wardleyDiagram-NUSXRM2D.B2pSo5rB.js} +1 -1
- package/dist/docs/assets/chunks/{xychartDiagram-5P7HB3ND.DEH4BcVJ.js → xychartDiagram-5P7HB3ND.NQhMiOOL.js} +1 -1
- package/dist/docs/assets/deployment.md.BtqJrHhp.js +31 -0
- package/dist/docs/assets/{deployment.md.KW0Ni_rY.lean.js → deployment.md.BtqJrHhp.lean.js} +1 -1
- package/dist/docs/assets/evals.md.Dne6VRmZ.js +49 -0
- package/dist/docs/assets/evals.md.Dne6VRmZ.lean.js +1 -0
- package/dist/docs/assets/{guides_agent-to-agent.md.D1D5f6Jc.js → guides_agent-to-agent.md.BcmSqL2z.js} +8 -8
- package/dist/docs/assets/guides_agent-to-agent.md.BcmSqL2z.lean.js +1 -0
- package/dist/docs/assets/{guides_bitbucket.md.DkjkBRU8.js → guides_bitbucket.md.BiA6ZMFW.js} +27 -27
- package/dist/docs/assets/{guides_bitbucket.md.DkjkBRU8.lean.js → guides_bitbucket.md.BiA6ZMFW.lean.js} +1 -1
- package/dist/docs/assets/guides_cloud-agents.md.CiXAW6on.js +9 -0
- package/dist/docs/assets/{guides_cloud-agents.md.Ceyjv0ul.lean.js → guides_cloud-agents.md.CiXAW6on.lean.js} +1 -1
- package/dist/docs/assets/guides_convert-automation.md.BvTxsJ8J.js +26 -0
- package/dist/docs/assets/{guides_convert-automation.md.BjraCvok.lean.js → guides_convert-automation.md.BvTxsJ8J.lean.js} +1 -1
- package/dist/docs/assets/{guides_github.md.CgN5sNbW.js → guides_github.md.6jiEH7dg.js} +11 -19
- package/dist/docs/assets/{guides_github.md.CgN5sNbW.lean.js → guides_github.md.6jiEH7dg.lean.js} +1 -1
- package/dist/docs/assets/{guides_gitlab.md.DCE0p7_w.js → guides_gitlab.md.DcKusOcU.js} +63 -73
- package/dist/docs/assets/{guides_gitlab.md.DCE0p7_w.lean.js → guides_gitlab.md.DcKusOcU.lean.js} +1 -1
- package/dist/docs/assets/guides_improve.md.o3WOGR7n.js +16 -0
- package/dist/docs/assets/{guides_improve.md.BFYtrtLE.lean.js → guides_improve.md.o3WOGR7n.lean.js} +1 -1
- package/dist/docs/assets/{guides_jev.md.CEqLgjj9.js → guides_jev.md.DGCzkMUN.js} +20 -60
- package/dist/docs/assets/{guides_jev.md.CEqLgjj9.lean.js → guides_jev.md.DGCzkMUN.lean.js} +1 -1
- package/dist/docs/assets/{guides_mcp-oauth.md.DrGY92u4.js → guides_mcp-oauth.md.C-Sx_IPa.js} +3 -5
- package/dist/docs/assets/{guides_mcp-oauth.md.DrGY92u4.lean.js → guides_mcp-oauth.md.C-Sx_IPa.lean.js} +1 -1
- package/dist/docs/assets/guides_migrate.md.BbhHYeCr.js +3 -0
- package/dist/docs/assets/{guides_migrate.md.RS9Eu-Xh.lean.js → guides_migrate.md.BbhHYeCr.lean.js} +1 -1
- package/dist/docs/assets/guides_opentelemetry.md.BRSktBHt.js +26 -0
- package/dist/docs/assets/guides_opentelemetry.md.BRSktBHt.lean.js +1 -0
- package/dist/docs/assets/guides_pagerduty.md.pMXUkZZc.js +61 -0
- package/dist/docs/assets/guides_pagerduty.md.pMXUkZZc.lean.js +1 -0
- package/dist/docs/assets/guides_slack.md.BgIGG9ur.js +82 -0
- package/dist/docs/assets/{guides_slack.md.BwXHURvY.lean.js → guides_slack.md.BgIGG9ur.lean.js} +1 -1
- package/dist/docs/assets/{guides_webhooks.md.BJk63ZTs.js → guides_webhooks.md.B5DXt2v1.js} +7 -7
- package/dist/docs/assets/{guides_webhooks.md.BJk63ZTs.lean.js → guides_webhooks.md.B5DXt2v1.lean.js} +1 -1
- package/dist/docs/assets/hillclimbing.md.3TkdF79A.js +5 -0
- package/dist/docs/assets/hillclimbing.md.3TkdF79A.lean.js +1 -0
- package/dist/docs/assets/index.md.DRfaoRCZ.js +20 -0
- package/dist/docs/assets/{index.md.CAruw_rp.lean.js → index.md.DRfaoRCZ.lean.js} +1 -1
- package/dist/docs/assets/quickstart.md.r-oE8nkX.js +113 -0
- package/dist/docs/assets/{quickstart.md.CljDaJBi.lean.js → quickstart.md.r-oE8nkX.lean.js} +1 -1
- package/dist/docs/assets/reference_access.md.C5lblfUC.js +1 -0
- package/dist/docs/assets/reference_access.md.C5lblfUC.lean.js +1 -0
- package/dist/docs/assets/reference_agent-config.md.C0Tp_Fk9.js +27 -0
- package/dist/docs/assets/{reference_agent-config.md.Ck29qYNj.lean.js → reference_agent-config.md.C0Tp_Fk9.lean.js} +1 -1
- package/dist/docs/assets/reference_artifacts.md.BJpAI7h9.js +17 -0
- package/dist/docs/assets/{reference_artifacts.md.C-hKR2hp.lean.js → reference_artifacts.md.BJpAI7h9.lean.js} +1 -1
- package/dist/docs/assets/reference_channels.md.CPWOpdsC.js +21 -0
- package/dist/docs/assets/{reference_channels.md.DsJfGSBJ.lean.js → reference_channels.md.CPWOpdsC.lean.js} +1 -1
- package/dist/docs/assets/reference_cli.md.B8GdpaRj.js +83 -0
- package/dist/docs/assets/reference_cli.md.B8GdpaRj.lean.js +1 -0
- package/dist/docs/assets/reference_connections.md.DoY4vrDH.js +54 -0
- package/dist/docs/assets/{reference_connections.md.BoAotr7_.lean.js → reference_connections.md.DoY4vrDH.lean.js} +1 -1
- package/dist/docs/assets/reference_evals.md.DgfUtfIc.js +69 -0
- package/dist/docs/assets/{reference_evals.md.2BXeMiO2.lean.js → reference_evals.md.DgfUtfIc.lean.js} +1 -1
- package/dist/docs/assets/{reference_extensions.md.DI5X5x8p.js → reference_extensions.md.DHbW6eOf.js} +6 -8
- package/dist/docs/assets/{reference_extensions.md.DI5X5x8p.lean.js → reference_extensions.md.DHbW6eOf.lean.js} +1 -1
- package/dist/docs/assets/reference_hooks.md.CSWmOwMM.js +39 -0
- package/dist/docs/assets/reference_hooks.md.CSWmOwMM.lean.js +1 -0
- package/dist/docs/assets/reference_http-api.md.C7Cb0r2J.js +7 -0
- package/dist/docs/assets/{reference_http-api.md._RWELr3d.lean.js → reference_http-api.md.C7Cb0r2J.lean.js} +1 -1
- package/dist/docs/assets/reference_instructions.md.CV6Qq0UX.js +14 -0
- package/dist/docs/assets/reference_instructions.md.CV6Qq0UX.lean.js +1 -0
- package/dist/docs/assets/reference_limits.md.CbdtFr4T.js +8 -0
- package/dist/docs/assets/reference_limits.md.CbdtFr4T.lean.js +1 -0
- package/dist/docs/assets/reference_memory.md.CdoJISM-.js +3 -0
- package/dist/docs/assets/{reference_memory.md.Dd7cyV9V.lean.js → reference_memory.md.CdoJISM-.lean.js} +1 -1
- package/dist/docs/assets/reference_playground.md.DIUsRAcy.js +1 -0
- package/dist/docs/assets/{reference_playground.md.CQiJk9CM.lean.js → reference_playground.md.DIUsRAcy.lean.js} +1 -1
- package/dist/docs/assets/reference_project-layout.md.9DiKoE16.js +26 -0
- package/dist/docs/assets/reference_project-layout.md.9DiKoE16.lean.js +1 -0
- package/dist/docs/assets/reference_schedules.md.RhQ9ZLo1.js +45 -0
- package/dist/docs/assets/{reference_schedules.md.RC47aFm4.lean.js → reference_schedules.md.RhQ9ZLo1.lean.js} +1 -1
- package/dist/docs/assets/reference_sessions.md.NXVQt9mP.js +22 -0
- package/dist/docs/assets/{reference_sessions.md.C7KFhWXV.lean.js → reference_sessions.md.NXVQt9mP.lean.js} +1 -1
- package/dist/docs/assets/{reference_skills.md.Dej2zQxi.js → reference_skills.md.DzCPNPkG.js} +4 -4
- package/dist/docs/assets/{reference_skills.md.Dej2zQxi.lean.js → reference_skills.md.DzCPNPkG.lean.js} +1 -1
- package/dist/docs/assets/reference_subagents.md.Dvpq2sUu.js +10 -0
- package/dist/docs/assets/{reference_subagents.md.CAhvW4yS.lean.js → reference_subagents.md.Dvpq2sUu.lean.js} +1 -1
- package/dist/docs/assets/reference_tools.md.B2OaR1Nb.js +62 -0
- package/dist/docs/assets/{reference_tools.md.DQr7Fnhu.lean.js → reference_tools.md.B2OaR1Nb.lean.js} +1 -1
- package/dist/docs/assets/templates_agentic-owners.md.B6ZmKAzT.js +13 -0
- package/dist/docs/assets/{templates_agentic-owners.md.Dh2nDSqg.lean.js → templates_agentic-owners.md.B6ZmKAzT.lean.js} +1 -1
- package/dist/docs/assets/templates_reviews.md.dr9Xv_KM.js +10 -0
- package/dist/docs/assets/templates_reviews.md.dr9Xv_KM.lean.js +1 -0
- package/dist/docs/assets/troubleshooting.md.DfKKvW1R.js +3 -0
- package/dist/docs/assets/{troubleshooting.md.CGOdNVAL.lean.js → troubleshooting.md.DfKKvW1R.lean.js} +1 -1
- package/dist/docs/building-with-agents.html +41 -44
- package/dist/docs/building-with-agents.md +11 -104
- package/dist/docs/changelog.html +37 -37
- package/dist/docs/changelog.md +5 -155
- package/dist/docs/deployment.html +54 -54
- package/dist/docs/deployment.md +83 -262
- package/dist/docs/evals.html +52 -71
- package/dist/docs/evals.md +33 -129
- package/dist/docs/guides/agent-to-agent.html +43 -43
- package/dist/docs/guides/agent-to-agent.md +27 -64
- package/dist/docs/guides/bitbucket.html +62 -62
- package/dist/docs/guides/bitbucket.md +73 -134
- package/dist/docs/guides/cloud-agents.html +37 -37
- package/dist/docs/guides/cloud-agents.md +23 -53
- package/dist/docs/guides/convert-automation.html +39 -56
- package/dist/docs/guides/convert-automation.md +31 -115
- package/dist/docs/guides/github.html +46 -54
- package/dist/docs/guides/github.md +49 -131
- package/dist/docs/guides/gitlab.html +98 -108
- package/dist/docs/guides/gitlab.md +104 -184
- package/dist/docs/guides/improve.html +38 -43
- package/dist/docs/guides/improve.md +24 -90
- package/dist/docs/guides/jev.html +55 -95
- package/dist/docs/guides/jev.md +53 -160
- package/dist/docs/guides/mcp-oauth.html +38 -40
- package/dist/docs/guides/mcp-oauth.md +33 -67
- package/dist/docs/guides/migrate.html +38 -43
- package/dist/docs/guides/migrate.md +56 -130
- package/dist/docs/guides/opentelemetry.html +41 -43
- package/dist/docs/guides/opentelemetry.md +32 -27
- package/dist/docs/guides/pagerduty.html +50 -49
- package/dist/docs/guides/pagerduty.md +65 -199
- package/dist/docs/guides/slack.html +51 -57
- package/dist/docs/guides/slack.md +76 -204
- package/dist/docs/guides/webhooks.html +42 -42
- package/dist/docs/guides/webhooks.md +64 -146
- package/dist/docs/hashmap.json +1 -1
- package/dist/docs/hillclimbing.html +40 -42
- package/dist/docs/hillclimbing.md +40 -102
- package/dist/docs/index.html +55 -61
- package/dist/docs/index.md +49 -83
- package/dist/docs/llms-full.txt +2262 -5721
- package/dist/docs/llms.txt +9 -14
- package/dist/docs/quickstart.html +95 -152
- package/dist/docs/quickstart.md +91 -180
- package/dist/docs/reference/access.html +36 -36
- package/dist/docs/reference/access.md +7 -12
- package/dist/docs/reference/agent-config.html +43 -56
- package/dist/docs/reference/agent-config.md +91 -174
- package/dist/docs/reference/artifacts.html +38 -39
- package/dist/docs/reference/artifacts.md +38 -62
- package/dist/docs/reference/channels.html +38 -39
- package/dist/docs/reference/channels.md +102 -151
- package/dist/docs/reference/cli.html +68 -84
- package/dist/docs/reference/cli.md +232 -697
- package/dist/docs/reference/connections.html +45 -57
- package/dist/docs/reference/connections.md +83 -164
- package/dist/docs/reference/evals.html +47 -54
- package/dist/docs/reference/evals.md +75 -141
- package/dist/docs/reference/extensions.html +41 -43
- package/dist/docs/reference/extensions.md +37 -70
- package/dist/docs/reference/hooks.html +40 -52
- package/dist/docs/reference/hooks.md +62 -133
- package/dist/docs/reference/http-api.html +38 -42
- package/dist/docs/reference/http-api.md +66 -118
- package/dist/docs/reference/instructions.html +39 -39
- package/dist/docs/reference/instructions.md +19 -29
- package/dist/docs/reference/limits.html +38 -38
- package/dist/docs/reference/limits.md +9 -21
- package/dist/docs/reference/memory.html +37 -38
- package/dist/docs/reference/memory.md +38 -75
- package/dist/docs/reference/playground.html +36 -36
- package/dist/docs/reference/playground.md +14 -22
- package/dist/docs/reference/project-layout.html +49 -48
- package/dist/docs/reference/project-layout.md +38 -84
- package/dist/docs/reference/schedules.html +46 -48
- package/dist/docs/reference/schedules.md +59 -90
- package/dist/docs/reference/sessions.html +37 -37
- package/dist/docs/reference/sessions.md +66 -113
- package/dist/docs/reference/skills.html +39 -39
- package/dist/docs/reference/skills.md +11 -31
- package/dist/docs/reference/subagents.html +37 -37
- package/dist/docs/reference/subagents.md +17 -31
- package/dist/docs/reference/tools.html +47 -64
- package/dist/docs/reference/tools.md +48 -130
- package/dist/docs/templates/agentic-owners.html +38 -38
- package/dist/docs/templates/agentic-owners.md +50 -74
- package/dist/docs/templates/reviews.html +69 -0
- package/dist/docs/templates/reviews.md +71 -0
- package/dist/docs/troubleshooting.html +38 -36
- package/dist/docs/troubleshooting.md +48 -101
- package/dist/internal/cli-deploy.js +1 -1
- package/dist/internal/cli-docs.js +1 -1
- package/dist/internal/cli-images.js +1 -1
- package/dist/internal/cli-skills.js +1 -1
- package/dist/internal/cursor/credentials.js +1 -1
- package/dist/internal/deploy-manifest.d.ts +1 -0
- package/dist/internal/deploy-manifest.d.ts.map +1 -1
- package/dist/internal/deploy-manifest.js +0 -1
- package/dist/internal/discovery/agent-config.d.ts +2 -6
- package/dist/internal/discovery/agent-config.d.ts.map +1 -1
- package/dist/internal/discovery/agent-config.js +8 -25
- package/dist/internal/discovery/agent.d.ts.map +1 -1
- package/dist/internal/discovery/agent.js +2 -3
- package/dist/internal/discovery/project.d.ts.map +1 -1
- package/dist/internal/discovery/project.js +15 -0
- package/dist/internal/init-project.d.ts.map +1 -1
- package/dist/internal/init-project.js +7 -5
- package/dist/internal/reminder-runner.js +1 -1
- package/dist/internal/session-engine.js +1 -1
- package/dist/internal/shallow-clone.js +1 -1
- package/dist/playground/assets/index-D6mVn9og.js +62 -0
- package/dist/playground/assets/index-DlALM6gr.css +1 -0
- package/dist/playground/index.html +2 -2
- package/dist/types.d.ts +4 -17
- package/dist/types.d.ts.map +1 -1
- package/docs/README.md +49 -83
- package/docs/building-with-agents.md +11 -104
- package/docs/changelog.md +6 -156
- package/docs/deployment.md +83 -262
- package/docs/evals.md +34 -130
- package/docs/guides/agent-to-agent.md +27 -64
- package/docs/guides/bitbucket.md +73 -134
- package/docs/guides/cloud-agents.md +23 -53
- package/docs/guides/convert-automation.md +31 -115
- package/docs/guides/github.md +49 -131
- package/docs/guides/gitlab.md +104 -184
- package/docs/guides/improve.md +24 -90
- package/docs/guides/jev.md +53 -160
- package/docs/guides/mcp-oauth.md +33 -67
- package/docs/guides/migrate.md +56 -130
- package/docs/guides/opentelemetry.md +37 -27
- package/docs/guides/pagerduty.md +68 -200
- package/docs/guides/slack.md +76 -204
- package/docs/guides/webhooks.md +64 -146
- package/docs/hillclimbing.md +41 -103
- package/docs/quickstart.md +91 -180
- package/docs/reference/access.md +7 -12
- package/docs/reference/agent-config.md +91 -174
- package/docs/reference/artifacts.md +38 -62
- package/docs/reference/channels.md +102 -151
- package/docs/reference/cli.md +232 -697
- package/docs/reference/connections.md +83 -164
- package/docs/reference/evals.md +75 -141
- package/docs/reference/extensions.md +37 -70
- package/docs/reference/hooks.md +61 -132
- package/docs/reference/http-api.md +66 -118
- package/docs/reference/instructions.md +20 -30
- package/docs/reference/limits.md +10 -22
- package/docs/reference/memory.md +38 -75
- package/docs/reference/playground.md +14 -22
- package/docs/reference/project-layout.md +38 -84
- package/docs/reference/schedules.md +59 -90
- package/docs/reference/sessions.md +66 -113
- package/docs/reference/skills.md +12 -32
- package/docs/reference/subagents.md +17 -31
- package/docs/reference/tools.md +48 -130
- package/docs/templates/agentic-owners.md +50 -74
- package/docs/templates/reviews.md +76 -0
- package/docs/troubleshooting.md +48 -101
- package/package.json +2 -2
- package/skills/deploy/SKILL.md +1 -1
- package/skills/migrate-v2/SKILL.md +0 -1
- package/dist/docs/assets/building-with-agents.md.Bf1yH2tG.js +0 -9
- package/dist/docs/assets/changelog.md.DrLFQUlu.js +0 -1
- package/dist/docs/assets/changelog.md.DrLFQUlu.lean.js +0 -1
- package/dist/docs/assets/chunks/@localSearchIndexroot.Dpd_wxVU.js +0 -1
- package/dist/docs/assets/chunks/channel._fZX_hvU.js +0 -1
- package/dist/docs/assets/chunks/classDiagram-6PBFFD2Q.eClS1Q0E.js +0 -1
- package/dist/docs/assets/chunks/classDiagram-v2-HSJHXN6E.eClS1Q0E.js +0 -1
- package/dist/docs/assets/chunks/clone.W1Phdw9P.js +0 -1
- package/dist/docs/assets/chunks/stateDiagram-v2-QKLJ7IA2.77yf4kRr.js +0 -1
- package/dist/docs/assets/deployment.md.KW0Ni_rY.js +0 -31
- package/dist/docs/assets/evals.md.DiljU__Z.js +0 -68
- package/dist/docs/assets/evals.md.DiljU__Z.lean.js +0 -1
- package/dist/docs/assets/guides_agent-to-agent.md.D1D5f6Jc.lean.js +0 -1
- package/dist/docs/assets/guides_cloud-agents.md.Ceyjv0ul.js +0 -9
- package/dist/docs/assets/guides_convert-automation.md.BjraCvok.js +0 -43
- package/dist/docs/assets/guides_hooks.md.BjeEiM7s.js +0 -54
- package/dist/docs/assets/guides_hooks.md.BjeEiM7s.lean.js +0 -1
- package/dist/docs/assets/guides_improve.md.BFYtrtLE.js +0 -21
- package/dist/docs/assets/guides_migrate.md.RS9Eu-Xh.js +0 -8
- package/dist/docs/assets/guides_opentelemetry.md.CoZ1kNyd.js +0 -28
- package/dist/docs/assets/guides_opentelemetry.md.CoZ1kNyd.lean.js +0 -1
- package/dist/docs/assets/guides_pagerduty.md.mnKXe9U0.js +0 -60
- package/dist/docs/assets/guides_pagerduty.md.mnKXe9U0.lean.js +0 -1
- package/dist/docs/assets/guides_slack.md.BwXHURvY.js +0 -88
- package/dist/docs/assets/hillclimbing.md.By61f3uq.js +0 -7
- package/dist/docs/assets/hillclimbing.md.By61f3uq.lean.js +0 -1
- package/dist/docs/assets/index.md.CAruw_rp.js +0 -26
- package/dist/docs/assets/quickstart.md.CljDaJBi.js +0 -170
- package/dist/docs/assets/reference_access.md.CEtibb4i.js +0 -1
- package/dist/docs/assets/reference_access.md.CEtibb4i.lean.js +0 -1
- package/dist/docs/assets/reference_agent-config.md.Ck29qYNj.js +0 -40
- package/dist/docs/assets/reference_artifacts.md.C-hKR2hp.js +0 -18
- package/dist/docs/assets/reference_channels.md.DsJfGSBJ.js +0 -22
- package/dist/docs/assets/reference_cli.md.BkdLRbXg.js +0 -99
- package/dist/docs/assets/reference_cli.md.BkdLRbXg.lean.js +0 -1
- package/dist/docs/assets/reference_connections.md.BoAotr7_.js +0 -66
- package/dist/docs/assets/reference_evals.md.2BXeMiO2.js +0 -76
- package/dist/docs/assets/reference_hooks.md.B-bwJuiG.js +0 -51
- package/dist/docs/assets/reference_hooks.md.B-bwJuiG.lean.js +0 -1
- package/dist/docs/assets/reference_http-api.md._RWELr3d.js +0 -11
- package/dist/docs/assets/reference_instructions.md.yL2hXLnl.js +0 -14
- package/dist/docs/assets/reference_instructions.md.yL2hXLnl.lean.js +0 -1
- package/dist/docs/assets/reference_limits.md.BCCnvt3o.js +0 -8
- package/dist/docs/assets/reference_limits.md.BCCnvt3o.lean.js +0 -1
- package/dist/docs/assets/reference_memory.md.Dd7cyV9V.js +0 -4
- package/dist/docs/assets/reference_playground.md.CQiJk9CM.js +0 -1
- package/dist/docs/assets/reference_project-layout.md.BamcPDUn.js +0 -25
- package/dist/docs/assets/reference_project-layout.md.BamcPDUn.lean.js +0 -1
- package/dist/docs/assets/reference_prompt.md.BMjm1Jp3.js +0 -9
- package/dist/docs/assets/reference_prompt.md.BMjm1Jp3.lean.js +0 -1
- package/dist/docs/assets/reference_schedules.md.RC47aFm4.js +0 -47
- package/dist/docs/assets/reference_sessions.md.C7KFhWXV.js +0 -22
- package/dist/docs/assets/reference_subagents.md.CAhvW4yS.js +0 -10
- package/dist/docs/assets/reference_tools.md.DQr7Fnhu.js +0 -79
- package/dist/docs/assets/templates_agentic-owners.md.Dh2nDSqg.js +0 -13
- package/dist/docs/assets/templates_security-reviewer.md.DnwXdnB5.js +0 -3
- package/dist/docs/assets/templates_security-reviewer.md.DnwXdnB5.lean.js +0 -1
- package/dist/docs/assets/templates_thermo-quality-review.md.MJIdHkzE.js +0 -3
- package/dist/docs/assets/templates_thermo-quality-review.md.MJIdHkzE.lean.js +0 -1
- package/dist/docs/assets/templates_thermo-review.md.DfN1OFOl.js +0 -3
- package/dist/docs/assets/templates_thermo-review.md.DfN1OFOl.lean.js +0 -1
- package/dist/docs/assets/templates_triage.md.BYWMloV4.js +0 -9
- package/dist/docs/assets/templates_triage.md.BYWMloV4.lean.js +0 -1
- package/dist/docs/assets/troubleshooting.md.CGOdNVAL.js +0 -1
- package/dist/docs/guides/hooks.html +0 -113
- package/dist/docs/guides/hooks.md +0 -116
- package/dist/docs/package/skills/create-agent/SKILL.md +0 -178
- package/dist/docs/package/skills/evals/SKILL.md +0 -145
- package/dist/docs/package/skills/github/SKILL.md +0 -133
- package/dist/docs/package/skills/hillclimb/SKILL.md +0 -63
- package/dist/docs/package/skills/mcp-auth/SKILL.md +0 -60
- package/dist/docs/package/skills/migrate-v2/SKILL.md +0 -394
- package/dist/docs/package/skills/setup-slack/SKILL.md +0 -136
- package/dist/docs/reference/prompt.html +0 -68
- package/dist/docs/reference/prompt.md +0 -47
- package/dist/docs/templates/security-reviewer.html +0 -62
- package/dist/docs/templates/security-reviewer.md +0 -81
- package/dist/docs/templates/thermo-quality-review.html +0 -62
- package/dist/docs/templates/thermo-quality-review.md +0 -75
- package/dist/docs/templates/thermo-review.html +0 -62
- package/dist/docs/templates/thermo-review.md +0 -75
- package/dist/docs/templates/triage.html +0 -68
- package/dist/docs/templates/triage.md +0 -101
- package/dist/playground/assets/index-Cl9zvmmf.js +0 -62
- package/dist/playground/assets/index-F8b5WvWi.css +0 -1
- package/docs/guides/hooks.md +0 -121
- package/docs/reference/prompt.md +0 -52
- package/docs/templates/security-reviewer.md +0 -86
- package/docs/templates/thermo-quality-review.md +0 -80
- package/docs/templates/thermo-review.md +0 -80
- package/docs/templates/triage.md +0 -106
package/docs/guides/improve.md
CHANGED
|
@@ -5,18 +5,14 @@ description: "Let an agent propose a change to its own source through a branch a
|
|
|
5
5
|
|
|
6
6
|
# Self-improvement
|
|
7
7
|
|
|
8
|
-
The `improve` extension
|
|
9
|
-
|
|
10
|
-
|
|
11
|
-
reports the verified PR for human review.
|
|
12
|
-
|
|
13
|
-
Durable behavior does not change until that source is merged and
|
|
14
|
-
deployed.
|
|
8
|
+
The `improve` extension lets an agent turn "change how you work" into a change
|
|
9
|
+
to its own source. The agent writes a brief, a Cursor cloud agent edits a
|
|
10
|
+
checkout and opens a pull request, and the agent reports the pull request.
|
|
15
11
|
|
|
16
12
|
## Mount it
|
|
17
13
|
|
|
18
|
-
Mount Cloud agents with the agent's own repository
|
|
19
|
-
mount `improve` with
|
|
14
|
+
Mount [Cloud agents](./cloud-agents.md) with the agent's own repository in
|
|
15
|
+
`cloud.repos`, then mount `improve` with its source directory.
|
|
20
16
|
|
|
21
17
|
```ts
|
|
22
18
|
// bot/extensions/cloud.ts
|
|
@@ -24,12 +20,7 @@ import cursorCloudAgents from "@grok/agent-sdk/extensions/cursor-cloud-agents";
|
|
|
24
20
|
|
|
25
21
|
export default cursorCloudAgents({
|
|
26
22
|
cloud: {
|
|
27
|
-
repos: [
|
|
28
|
-
{
|
|
29
|
-
url: "https://github.com/acme/agents",
|
|
30
|
-
startingRef: "main",
|
|
31
|
-
},
|
|
32
|
-
],
|
|
23
|
+
repos: [{ url: "https://github.com/acme/agents", startingRef: "main" }],
|
|
33
24
|
autoCreatePR: true,
|
|
34
25
|
},
|
|
35
26
|
});
|
|
@@ -46,89 +37,32 @@ export default improve({
|
|
|
46
37
|
});
|
|
47
38
|
```
|
|
48
39
|
|
|
49
|
-
|
|
50
|
-
`improve__yourself` skill. It does not contribute a tool that can bypass
|
|
51
|
-
the normal repository workflow.
|
|
52
|
-
|
|
53
|
-
## Ask for one behavioral change
|
|
54
|
-
|
|
55
|
-
State the change, how to tell it worked, and what behavior must stay
|
|
56
|
-
fixed. The agent maps the request to instructions, a skill, a tool,
|
|
57
|
-
channel configuration, or the model setting before preparing the coding
|
|
58
|
-
brief.
|
|
59
|
-
|
|
60
|
-
> Improve yourself: stop opening incident replies with a summary.
|
|
61
|
-
> Start with the decision, keep the existing evidence bullets, and
|
|
62
|
-
> preserve every current eval.
|
|
63
|
-
|
|
64
|
-
The success criterion and freeze line keep the cloud agent from turning
|
|
65
|
-
a narrow behavior request into an unrelated refactor.
|
|
40
|
+
`improve` adds the `improve__yourself` skill and no tools.
|
|
66
41
|
|
|
67
|
-
##
|
|
42
|
+
## Ask for one change
|
|
68
43
|
|
|
69
|
-
|
|
70
|
-
ref. It reports the complete cloud-agent ID
|
|
71
|
-
and URL immediately, then checks the same run instead of launching
|
|
72
|
-
another agent for follow-up work.
|
|
44
|
+
Say what to change, how to tell it worked, and what must not change.
|
|
73
45
|
|
|
74
|
-
|
|
75
|
-
|
|
76
|
-
|
|
77
|
-
deliverable.
|
|
46
|
+
> Improve yourself. Stop opening incident replies with a summary. Start with
|
|
47
|
+
> the decision, keep the existing evidence bullets, and preserve every current
|
|
48
|
+
> eval.
|
|
78
49
|
|
|
79
|
-
|
|
80
|
-
|
|
50
|
+
The agent launches one cloud agent and reports its URL. When the pull request
|
|
51
|
+
opens, the agent tells you what changed and which checks passed.
|
|
81
52
|
|
|
82
53
|
## Review, merge, then deploy
|
|
83
54
|
|
|
84
|
-
The
|
|
85
|
-
|
|
86
|
-
the
|
|
87
|
-
|
|
88
|
-
This separation gives each boundary a real control:
|
|
89
|
-
|
|
90
|
-
- Repository permissions limit who can push the branch.
|
|
91
|
-
- Branch protection and review policy govern the merge.
|
|
92
|
-
- Deployment authorization governs the running agent.
|
|
93
|
-
|
|
94
|
-
After deployment, repeat the original request or regression eval to
|
|
95
|
-
confirm the behavior changed without crossing the freeze line.
|
|
55
|
+
The agent can open a pull request, but it can't merge or deploy. Someone on your
|
|
56
|
+
team reviews and merges it, and the change goes live on your next deploy.
|
|
57
|
+
Afterward, repeat the original request to confirm the change.
|
|
96
58
|
|
|
97
59
|
## Configure it
|
|
98
60
|
|
|
99
61
|
- `repo` is the source repository URL.
|
|
100
|
-
- `path` is the agent's repository
|
|
101
|
-
- `ref` is the
|
|
102
|
-
|
|
103
|
-
- `
|
|
104
|
-
|
|
105
|
-
|
|
106
|
-
|
|
107
|
-
|
|
108
|
-
`notes` and `deploy` insert prose into the contributed skill. They do
|
|
109
|
-
not run checks, merge a branch, or trigger a deployment.
|
|
110
|
-
|
|
111
|
-
Validation checks the URL and path shape. It does not prove the source
|
|
112
|
-
exists, matches the current deployment, or appears in the Cloud agents
|
|
113
|
-
repository allowlist, so keep those values aligned yourself.
|
|
114
|
-
|
|
115
|
-
## What the extension enforces
|
|
116
|
-
|
|
117
|
-
`improve__yourself` is model guidance for locating the change, writing a
|
|
118
|
-
brief, following repository rules, opening a PR, and reporting it. Rules
|
|
119
|
-
such as "never merge" are instructions, not framework-enforced
|
|
120
|
-
permissions.
|
|
121
|
-
|
|
122
|
-
Use repository and deployment controls for hard enforcement. The
|
|
123
|
-
extension provides a repeatable path through those controls; it does not
|
|
124
|
-
replace them.
|
|
125
|
-
|
|
126
|
-
## What's next
|
|
127
|
-
|
|
128
|
-
- [Cloud agents](./cloud-agents.md): delegation and steering
|
|
129
|
-
- [Build with a coding agent](../building-with-agents.md): have an
|
|
130
|
-
external coding agent edit the project directly
|
|
131
|
-
- [Extensions](../reference/extensions.md): namespaces and overlays
|
|
132
|
-
- [Deployment](../deployment.md): make a merged source change live
|
|
133
|
-
- [Evals](../evals.md): protect the requested behavior before and after
|
|
134
|
-
the change
|
|
62
|
+
- `path` is the agent's directory in that repository.
|
|
63
|
+
- `ref` is the branch new pull requests target, `main` by default.
|
|
64
|
+
- `notes` adds guidance to every brief, such as a required test command.
|
|
65
|
+
- `deploy` tells the skill who deploys a merged change and when.
|
|
66
|
+
|
|
67
|
+
Validation checks only the shape of `repo` and `path`, so make sure they match
|
|
68
|
+
the deployed agent and `cloud.repos`.
|
package/docs/guides/jev.md
CHANGED
|
@@ -6,17 +6,16 @@ description: "Use typed Jev decisions to filter findings, route pull requests, a
|
|
|
6
6
|
# Use Jev in review tools
|
|
7
7
|
|
|
8
8
|
> [!WARNING]
|
|
9
|
-
>
|
|
9
|
+
> Experimental. `@grok/agent-sdk/extensions/jev` is experimental. Its
|
|
10
10
|
> exports and behavior can change in any release, without a deprecation
|
|
11
11
|
> period.
|
|
12
12
|
|
|
13
|
-
Use Jev when a review workflow needs a typed decision instead of prose.
|
|
14
|
-
|
|
15
|
-
|
|
16
|
-
follow-up. Jev returns a choice, score, or probability; your TypeScript
|
|
17
|
-
decides what happens next.
|
|
13
|
+
Use Jev when a review workflow needs a typed decision instead of prose. Jev
|
|
14
|
+
returns a choice, a score, or a probability, and your TypeScript decides what
|
|
15
|
+
happens next.
|
|
18
16
|
|
|
19
|
-
Set `TYPESAFE_API_KEY
|
|
17
|
+
Set `TYPESAFE_API_KEY`, then mount the extension. The default model is
|
|
18
|
+
`jev-latest`.
|
|
20
19
|
|
|
21
20
|
```ts
|
|
22
21
|
// bot/extensions/jev.ts
|
|
@@ -25,21 +24,17 @@ import jev from "@grok/agent-sdk/extensions/jev";
|
|
|
25
24
|
export default jev();
|
|
26
25
|
```
|
|
27
26
|
|
|
28
|
-
On Cursor
|
|
29
|
-
|
|
30
|
-
|
|
31
|
-
|
|
32
|
-
list `api.typesafe.ai` in `hosting.egressDomains` itself; see
|
|
33
|
-
[Add egress and secrets](../deployment.md#add-egress-and-secrets).
|
|
27
|
+
On Cursor hosting, the mount adds `api.typesafe.ai` to egress and
|
|
28
|
+
`TYPESAFE_API_KEY` to the expected secrets. Without the mount,
|
|
29
|
+
[add `api.typesafe.ai`](../deployment.md#add-egress-and-secrets) to
|
|
30
|
+
`hosting.egressDomains` yourself.
|
|
34
31
|
|
|
35
32
|
## Start only the review turns you need
|
|
36
33
|
|
|
37
|
-
Call Jev from a channel hook before a model turn starts.
|
|
38
|
-
|
|
39
|
-
|
|
40
|
-
|
|
41
|
-
turn; otherwise, the hook returns `null`, so the agent doesn't run or
|
|
42
|
-
post to GitHub.
|
|
34
|
+
Call Jev from a channel hook before a model turn starts. This hook asks Jev
|
|
35
|
+
whether a new pull request needs security review, based on its title, body, and
|
|
36
|
+
file names. Below the threshold, the hook returns `null`, so the agent doesn't
|
|
37
|
+
run or post anything.
|
|
43
38
|
|
|
44
39
|
```ts
|
|
45
40
|
// bot/channels/github.ts
|
|
@@ -50,7 +45,6 @@ import {
|
|
|
50
45
|
import { above, decide } from "@grok/agent-sdk/extensions/jev";
|
|
51
46
|
|
|
52
47
|
export default githubChannel({
|
|
53
|
-
botName: "security-reviewer",
|
|
54
48
|
cursorAccount: { repos: ["acme/checkout"] },
|
|
55
49
|
onPullRequest: async (ctx, pr) => {
|
|
56
50
|
if (pr.action !== "opened" && pr.action !== "ready_for_review") {
|
|
@@ -58,30 +52,21 @@ export default githubChannel({
|
|
|
58
52
|
}
|
|
59
53
|
|
|
60
54
|
const octokit = await ctx.github.getOctokit();
|
|
61
|
-
const
|
|
62
|
-
|
|
63
|
-
|
|
64
|
-
|
|
65
|
-
|
|
66
|
-
}),
|
|
67
|
-
octokit.paginate(octokit.rest.pulls.listFiles, {
|
|
68
|
-
owner: ctx.repository.owner,
|
|
69
|
-
repo: ctx.repository.name,
|
|
70
|
-
pull_number: pr.number,
|
|
71
|
-
}),
|
|
72
|
-
]);
|
|
55
|
+
const files = await octokit.paginate(octokit.rest.pulls.listFiles, {
|
|
56
|
+
owner: ctx.repository.owner,
|
|
57
|
+
repo: ctx.repository.name,
|
|
58
|
+
pull_number: pr.number,
|
|
59
|
+
});
|
|
73
60
|
const answers = await decide({
|
|
74
61
|
state: {
|
|
75
|
-
title:
|
|
76
|
-
body:
|
|
77
|
-
labels: data.labels.map(label => label.name),
|
|
62
|
+
title: pr.title,
|
|
63
|
+
body: pr.body,
|
|
78
64
|
files: files.map(file => file.filename),
|
|
79
65
|
},
|
|
80
66
|
questions: {
|
|
81
67
|
review: {
|
|
82
68
|
type: "boolean",
|
|
83
|
-
instructions:
|
|
84
|
-
"Does this change need security review? Answer yes for auth, permissions, secrets, request parsing, or external inputs.",
|
|
69
|
+
instructions: "Does this change touch auth, permissions, secrets, or external input?",
|
|
85
70
|
},
|
|
86
71
|
},
|
|
87
72
|
});
|
|
@@ -89,20 +74,15 @@ export default githubChannel({
|
|
|
89
74
|
if (!above(answers.review, 0.8)) {
|
|
90
75
|
return null;
|
|
91
76
|
}
|
|
92
|
-
// `auth` starts a model turn running as the pull request sender.
|
|
93
77
|
return { auth: defaultGitHubAuth(ctx) };
|
|
94
78
|
},
|
|
95
79
|
});
|
|
96
80
|
```
|
|
97
81
|
|
|
98
|
-
Jev receives only the pull request metadata shown here, not the diff.
|
|
99
|
-
|
|
100
82
|
## Filter findings before you post them
|
|
101
83
|
|
|
102
|
-
Let the
|
|
103
|
-
|
|
104
|
-
the author never sees the draft. Above it, the finding becomes a review
|
|
105
|
-
comment.
|
|
84
|
+
Let the model draft a finding, then ask Jev whether it's a real bug in the new
|
|
85
|
+
code. The tool posts only the drafts that clear your threshold.
|
|
106
86
|
|
|
107
87
|
```ts
|
|
108
88
|
// bot/tools/post_finding.ts
|
|
@@ -112,14 +92,12 @@ import { defineTool } from "@grok/agent-sdk/tools";
|
|
|
112
92
|
import { z } from "zod";
|
|
113
93
|
|
|
114
94
|
export default defineTool({
|
|
115
|
-
description:
|
|
116
|
-
"Post one security finding on this session's pull request. Call once. Hold when it is not a real bug.",
|
|
95
|
+
description: "Post one security finding on this session's pull request.",
|
|
117
96
|
inputSchema: z.object({
|
|
118
|
-
|
|
119
|
-
|
|
120
|
-
draft: z.string().describe("The finding to post, one or two sentences."),
|
|
97
|
+
summary: z.string(),
|
|
98
|
+
draft: z.string().describe("The finding, in one or two sentences."),
|
|
121
99
|
}),
|
|
122
|
-
async execute({
|
|
100
|
+
async execute({ summary, draft }, ctx) {
|
|
123
101
|
if (ctx.session.purpose === "eval") {
|
|
124
102
|
return { posted: false, reason: "eval" };
|
|
125
103
|
}
|
|
@@ -130,12 +108,11 @@ export default defineTool({
|
|
|
130
108
|
}
|
|
131
109
|
|
|
132
110
|
const answers = await decide({
|
|
133
|
-
state: {
|
|
111
|
+
state: { summary, draft },
|
|
134
112
|
questions: {
|
|
135
113
|
real: {
|
|
136
114
|
type: "boolean",
|
|
137
|
-
instructions:
|
|
138
|
-
"Is the draft an exploitable bug in the new code, not a style note or a hypothetical?",
|
|
115
|
+
instructions: "Is the draft an exploitable bug in the new code?",
|
|
139
116
|
},
|
|
140
117
|
},
|
|
141
118
|
});
|
|
@@ -152,19 +129,14 @@ export default defineTool({
|
|
|
152
129
|
event: "COMMENT",
|
|
153
130
|
body: draft,
|
|
154
131
|
});
|
|
155
|
-
return {
|
|
156
|
-
posted: true,
|
|
157
|
-
pr: `${ref.owner}/${ref.repo}#${ref.number}`,
|
|
158
|
-
};
|
|
132
|
+
return { posted: true };
|
|
159
133
|
},
|
|
160
134
|
});
|
|
161
135
|
```
|
|
162
136
|
|
|
163
137
|
## Approve changes by risk tier
|
|
164
138
|
|
|
165
|
-
|
|
166
|
-
pull request in a closed set of risk tiers. Approve only a confident
|
|
167
|
-
`very-low` or `low`; send everything else to a person.
|
|
139
|
+
Ask Jev for one risk tier. Approve only a confident `very-low` or `low`.
|
|
168
140
|
|
|
169
141
|
```ts
|
|
170
142
|
import { decide, needsHuman } from "@grok/agent-sdk/extensions/jev";
|
|
@@ -192,117 +164,38 @@ if (needsHuman(answers.risk) || tier === "medium" || tier === "high") {
|
|
|
192
164
|
return { verdict: "approve", tier };
|
|
193
165
|
```
|
|
194
166
|
|
|
195
|
-
Your
|
|
196
|
-
that verdict. The model does not choose the repository, pull request, or
|
|
197
|
-
approval event.
|
|
198
|
-
|
|
199
|
-
## Open documentation follow-ups selectively
|
|
200
|
-
|
|
201
|
-
After a pull request merges, a code-wiki agent can ask whether the
|
|
202
|
-
change introduced a durable fact that belongs in the docs. A low
|
|
203
|
-
probability skips the follow-up, while a high probability opens a
|
|
204
|
-
documentation pull request.
|
|
205
|
-
|
|
206
|
-
```ts
|
|
207
|
-
import { above, decide } from "@grok/agent-sdk/extensions/jev";
|
|
208
|
-
import { openDocsPullRequest } from "../lib/wiki";
|
|
209
|
-
|
|
210
|
-
const answers = await decide({
|
|
211
|
-
state: { title, summary },
|
|
212
|
-
questions: {
|
|
213
|
-
updateDocs: {
|
|
214
|
-
type: "boolean",
|
|
215
|
-
instructions:
|
|
216
|
-
"Does this merge change a durable contract that the project docs should explain?",
|
|
217
|
-
},
|
|
218
|
-
},
|
|
219
|
-
});
|
|
220
|
-
|
|
221
|
-
if (!above(answers.updateDocs, 0.8)) {
|
|
222
|
-
return { action: "skip" };
|
|
223
|
-
}
|
|
224
|
-
return openDocsPullRequest({ title, summary });
|
|
225
|
-
```
|
|
167
|
+
Your tool resolves the pull request from the session and posts that verdict, as the [Agentic Owners template](../templates/agentic-owners.md) does.
|
|
226
168
|
|
|
227
169
|
## Write tools with Jev
|
|
228
170
|
|
|
229
|
-
Call `decide`
|
|
230
|
-
|
|
171
|
+
Call `decide` to get the answer map, or `evaluate` to get `{ answers }`. Use a
|
|
172
|
+
boolean for a yes-or-no gate, a choice for a closed set such as risk tiers, and
|
|
173
|
+
a score for an ordered rubric. `above` returns `true` when a probability or
|
|
174
|
+
score meets your threshold. `needsHuman` returns `true` when the answer's
|
|
175
|
+
confidence falls below `0.7` by default. Calibrate both on pull requests you've
|
|
176
|
+
already labeled.
|
|
231
177
|
|
|
232
|
-
|
|
233
|
-
|
|
234
|
-
`true` when a boolean probability or score meets the threshold.
|
|
235
|
-
`needsHuman` returns `true` when a boolean probability or the selected
|
|
236
|
-
choice's probability falls below the confidence threshold.
|
|
237
|
-
|
|
238
|
-
Keep the questions atomic and combine them in TypeScript. For example,
|
|
239
|
-
ask separately whether a finding is real, whether its impact is
|
|
240
|
-
user-visible, and whether the changed line is new. Your code owns the
|
|
241
|
-
rule that decides whether all three are enough to post.
|
|
178
|
+
Ask Jev one question per call, and write the rule that combines the answers in
|
|
179
|
+
your own code.
|
|
242
180
|
|
|
243
181
|
## Let the agent ask Jev
|
|
244
182
|
|
|
245
|
-
|
|
246
|
-
|
|
247
|
-
|
|
248
|
-
|
|
249
|
-
The tool accepts one state and a list of boolean, choice, or score
|
|
250
|
-
questions. It returns `{ answers }` and never posts, approves, or opens
|
|
251
|
-
a pull request. Use it when the agent needs the result during the turn.
|
|
252
|
-
Use `decide` inside a project tool when the answer and the write belong
|
|
253
|
-
in one operation.
|
|
254
|
-
|
|
255
|
-
## Skills included with the extension
|
|
256
|
-
|
|
257
|
-
The extension adds two skills by default:
|
|
258
|
-
|
|
259
|
-
- `jev__questions` teaches the model how to structure atomic questions,
|
|
260
|
-
choose a question type, and read the answers.
|
|
261
|
-
|
|
262
|
-
- `jev__gated-write` teaches the model to put `decide` and the write in
|
|
263
|
-
one server tool, hold on low confidence, and skip writes during evals.
|
|
264
|
-
|
|
265
|
-
The model sees each skill's description and loads the full procedure
|
|
266
|
-
when it applies.
|
|
183
|
+
The mount also gives the model a read-only tool named `<namespace>__evaluate`,
|
|
184
|
+
which is `jev__evaluate` with the mount shown earlier. The model can call it
|
|
185
|
+
during a turn, and it never posts or approves anything. When the answer and the
|
|
186
|
+
write belong together, call `decide` inside a project tool instead.
|
|
267
187
|
|
|
268
188
|
## Choose what to mount
|
|
269
189
|
|
|
270
|
-
|
|
271
|
-
|
|
272
|
-
|
|
190
|
+
Mounting Jev also adds two skills. `jev__questions` teaches the model to write
|
|
191
|
+
atomic questions and read the answers, and `jev__gated-write` teaches it to put
|
|
192
|
+
`decide` and the write in one server tool. Set `harnessTools: false` to keep Jev
|
|
193
|
+
inside your own tools, or `skills: false` if your agent has its own Jev
|
|
194
|
+
instructions.
|
|
273
195
|
|
|
274
196
|
```ts
|
|
275
|
-
|
|
276
|
-
import jev from "@grok/agent-sdk/extensions/jev";
|
|
277
|
-
|
|
278
|
-
export default jev({
|
|
279
|
-
harnessTools: false,
|
|
280
|
-
skills: true,
|
|
281
|
-
});
|
|
197
|
+
export default jev({ harnessTools: false, skills: true });
|
|
282
198
|
```
|
|
283
199
|
|
|
284
|
-
|
|
285
|
-
`
|
|
286
|
-
the exported helpers, so project tools can still import `decide`,
|
|
287
|
-
`above`, and `needsHuman`.
|
|
288
|
-
|
|
289
|
-
## Practices
|
|
290
|
-
|
|
291
|
-
- Pass the pull request title, a short summary, and the draft finding.
|
|
292
|
-
Don't send the checkout.
|
|
293
|
-
|
|
294
|
-
- Calibrate `above` and `needsHuman` on pull requests you have already
|
|
295
|
-
labeled. `needsHuman` defaults to `0.7`.
|
|
296
|
-
|
|
297
|
-
## Related
|
|
298
|
-
|
|
299
|
-
- [Agentic owners](../templates/agentic-owners.md): a risk tier, then
|
|
300
|
-
the host approves or asks for reviewers
|
|
301
|
-
- [Security reviewer](../templates/security-reviewer.md): a finding, or
|
|
302
|
-
no comment
|
|
303
|
-
- [Thermo review](../templates/thermo-review.md): bugs and breakage,
|
|
304
|
-
posted the same way
|
|
305
|
-
- [Code wiki](../reference/cli.md#init): documentation
|
|
306
|
-
follow-ups after a merge
|
|
307
|
-
- [Evals](../evals.md): checks on the full turn
|
|
308
|
-
- [GitHub agents](./github.md): how the review gets onto the pull request
|
|
200
|
+
Neither switch removes the exported helpers, so project tools can still import
|
|
201
|
+
`decide`, `above`, and `needsHuman`.
|
package/docs/guides/mcp-oauth.md
CHANGED
|
@@ -5,16 +5,12 @@ description: "Authorize a private MCP server locally, constrain its tools, and c
|
|
|
5
5
|
|
|
6
6
|
# Connect a private MCP server with OAuth
|
|
7
7
|
|
|
8
|
-
Host MCP OAuth lets
|
|
9
|
-
without putting tokens in
|
|
10
|
-
the server speaks OAuth and its credentials should belong to the serve
|
|
11
|
-
host instead of a person's Cursor account.
|
|
8
|
+
Host MCP OAuth lets the machine running your agent authorize a remote
|
|
9
|
+
MCP server without putting tokens in your source or workspace.
|
|
12
10
|
|
|
13
11
|
## Use a private MCP tool locally
|
|
14
12
|
|
|
15
|
-
Declare the
|
|
16
|
-
the agent. The next local turn can call the server's named tools with
|
|
17
|
-
the credentials stored on that host.
|
|
13
|
+
Declare the server and authorize it once in the browser.
|
|
18
14
|
|
|
19
15
|
```ts
|
|
20
16
|
// bot/mcp-connections/inventory.ts
|
|
@@ -27,47 +23,37 @@ export default defineConnection({
|
|
|
27
23
|
});
|
|
28
24
|
```
|
|
29
25
|
|
|
30
|
-
```
|
|
26
|
+
```bash
|
|
31
27
|
agent-sdk mcp oauth inventory
|
|
32
|
-
agent-sdk run --dir . \
|
|
33
|
-
--message "Which east-coast warehouse has SKU-142 in stock?"
|
|
34
28
|
```
|
|
35
29
|
|
|
36
|
-
The filename is the connection name
|
|
37
|
-
`
|
|
38
|
-
authorization, so run `mcp oauth` again after moving the endpoint.
|
|
30
|
+
The filename is the connection name. If you change the server URL, run
|
|
31
|
+
`mcp oauth` again.
|
|
39
32
|
|
|
40
33
|
## Connect on first use
|
|
41
34
|
|
|
42
|
-
|
|
43
|
-
|
|
44
|
-
|
|
45
|
-
retries and the turn continues without restarting the agent.
|
|
46
|
-
|
|
47
|
-
```text
|
|
48
|
-
agent-sdk serve --dir . --dev
|
|
49
|
-
```
|
|
50
|
-
|
|
51
|
-
Connect authorizes the process that is running now.
|
|
35
|
+
Without a prior `mcp oauth`, the first call to the server pauses the
|
|
36
|
+
turn, and the playground shows **Connect**. Finish the browser flow,
|
|
37
|
+
and the call retries in the running process.
|
|
52
38
|
|
|
53
39
|
A turn waits for Connect only when a person can click it:
|
|
54
40
|
|
|
55
41
|
- A playground or HTTP chat turn.
|
|
56
|
-
- A Slack message, when the channel shows Connect
|
|
57
|
-
|
|
42
|
+
- A Slack message, when the channel shows Connect through
|
|
43
|
+
`slackChannel({ toolApprovals: true })` or `buildToolApprovalEvents`
|
|
44
|
+
in `events`.
|
|
58
45
|
|
|
59
|
-
The wait stops after 10 minutes
|
|
60
|
-
|
|
61
|
-
|
|
62
|
-
`Reconnect <connection
|
|
63
|
-
playground. Authorize those
|
|
46
|
+
The wait stops after 10 minutes or when the turn is interrupted.
|
|
47
|
+
Schedules, reminders, webhooks, evals, and Slack channels without
|
|
48
|
+
Connect don't wait. A required connection fails the call with
|
|
49
|
+
`Reconnect <connection>`, and an `optional` one is skipped, even in the
|
|
50
|
+
playground. Authorize those ahead of time with `mcp oauth`.
|
|
64
51
|
|
|
65
52
|
## Keep privileged tools behind a wrapper
|
|
66
53
|
|
|
67
|
-
|
|
68
|
-
|
|
69
|
-
|
|
70
|
-
on the host.
|
|
54
|
+
The model never sees a connection under `bot/host-connections/`. A
|
|
55
|
+
server tool reaches it through `ctx.host.mcp` and exposes one narrow
|
|
56
|
+
operation.
|
|
71
57
|
|
|
72
58
|
```ts
|
|
73
59
|
// bot/host-connections/inventory.ts
|
|
@@ -105,48 +91,28 @@ export default defineTool({
|
|
|
105
91
|
});
|
|
106
92
|
```
|
|
107
93
|
|
|
108
|
-
The model sees `get_stock`, not the unrestricted inventory server.
|
|
109
|
-
Use this shape when code should own an allowlist or another side-effect
|
|
110
|
-
gate.
|
|
111
|
-
|
|
112
94
|
## Use an OAuth server from a hosted agent
|
|
113
95
|
|
|
114
|
-
Tokens from `mcp oauth` stay
|
|
115
|
-
|
|
116
|
-
Cursor-managed agent, add the server under MCP in the Cursor dashboard,
|
|
96
|
+
Tokens from `mcp oauth` stay on the machine that authorized them. For a
|
|
97
|
+
Cursor-hosted agent, add the server under MCP in the Cursor dashboard,
|
|
117
98
|
reach it through a
|
|
118
99
|
[`cursorAccount: true` connection](../reference/connections.md#cursor-account-mcp-connection),
|
|
119
100
|
and connect it from [Deployed Agents](https://cursor.com/dashboard/deployed-agents).
|
|
120
|
-
|
|
121
|
-
|
|
122
|
-
expose, so narrow the connection's `servers` list and keep privileged
|
|
123
|
-
operations behind a host-side wrapper.
|
|
101
|
+
Anyone who can use the agent can use that connection, so narrow its
|
|
102
|
+
`servers` list.
|
|
124
103
|
|
|
125
104
|
## Choose where credentials live
|
|
126
105
|
|
|
127
|
-
|
|
128
|
-
|
|
129
|
-
|
|
130
|
-
|
|
131
|
-
|
|
132
|
-
- Choose `url` with `oauth: true` when the machine running `agent-sdk serve`
|
|
133
|
-
should hold OAuth credentials.
|
|
134
|
-
|
|
135
|
-
- Choose `url` with static `headers` when the server uses an API key or
|
|
136
|
-
bearer token instead of OAuth.
|
|
106
|
+
| Connection | Credentials live in | Use it when |
|
|
107
|
+
| --- | --- | --- |
|
|
108
|
+
| `cursorAccount: true` | Cursor's backend | You connected the server in the Cursor dashboard |
|
|
109
|
+
| `url` with `oauth: true` | The serve host | The serve host should own access |
|
|
110
|
+
| `url` with `headers` | Your secrets | The server takes an API key or bearer token |
|
|
137
111
|
|
|
138
|
-
Host OAuth
|
|
139
|
-
|
|
140
|
-
caller needs a different downstream identity.
|
|
112
|
+
Host OAuth can't share a connection with per-session `auth`, which
|
|
113
|
+
gives each caller its own downstream identity.
|
|
141
114
|
|
|
142
115
|
## Related
|
|
143
116
|
|
|
144
|
-
-
|
|
145
|
-
|
|
146
|
-
- [MCP connections](../reference/connections.md): transports, account
|
|
147
|
-
connectors, per-session auth, and tool filtering
|
|
148
|
-
- [CLI reference](../reference/cli.md#mcp-oauth): OAuth command flags
|
|
149
|
-
and browser callback behavior
|
|
150
|
-
- [Deployment](../deployment.md): hosted egress and secrets
|
|
151
|
-
- [Troubleshooting](../troubleshooting.md): authorization symptoms and
|
|
152
|
-
remedies
|
|
117
|
+
- Follow the `bdk-mcp-auth` skill, then run `agent-sdk mcp oauth <connection>`.
|
|
118
|
+
- [MCP connections](../reference/connections.md)
|