@meetkai/mka1 0.54.22 → 0.54.24
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/README.md +302 -285
- package/bin/mcp-server.js +5917 -3364
- package/bin/mcp-server.js.map +47 -18
- package/dist/commonjs/funcs/llmEvalsAppendAgentTrials.d.ts +19 -0
- package/dist/commonjs/funcs/llmEvalsAppendAgentTrials.d.ts.map +1 -0
- package/dist/commonjs/funcs/llmEvalsAppendAgentTrials.js +136 -0
- package/dist/commonjs/funcs/llmEvalsAppendAgentTrials.js.map +1 -0
- package/dist/commonjs/funcs/llmEvalsGetRunOverview.d.ts +20 -0
- package/dist/commonjs/funcs/llmEvalsGetRunOverview.d.ts.map +1 -0
- package/dist/commonjs/funcs/llmEvalsGetRunOverview.js +138 -0
- package/dist/commonjs/funcs/llmEvalsGetRunOverview.js.map +1 -0
- package/dist/commonjs/funcs/llmEvalsGetSampleTrajectory.d.ts +19 -0
- package/dist/commonjs/funcs/llmEvalsGetSampleTrajectory.d.ts.map +1 -0
- package/dist/commonjs/funcs/llmEvalsGetSampleTrajectory.js +142 -0
- package/dist/commonjs/funcs/llmEvalsGetSampleTrajectory.js.map +1 -0
- package/dist/commonjs/funcs/llmEvalsGetSuiteLeaderboard.d.ts +20 -0
- package/dist/commonjs/funcs/llmEvalsGetSuiteLeaderboard.d.ts.map +1 -0
- package/dist/commonjs/funcs/llmEvalsGetSuiteLeaderboard.js +142 -0
- package/dist/commonjs/funcs/llmEvalsGetSuiteLeaderboard.js.map +1 -0
- package/dist/commonjs/funcs/llmEvalsImportAgentRun.d.ts +19 -0
- package/dist/commonjs/funcs/llmEvalsImportAgentRun.d.ts.map +1 -0
- package/dist/commonjs/funcs/llmEvalsImportAgentRun.js +130 -0
- package/dist/commonjs/funcs/llmEvalsImportAgentRun.js.map +1 -0
- package/dist/commonjs/funcs/llmEvalsUploadSampleTrajectory.d.ts +20 -0
- package/dist/commonjs/funcs/llmEvalsUploadSampleTrajectory.d.ts.map +1 -0
- package/dist/commonjs/funcs/llmEvalsUploadSampleTrajectory.js +146 -0
- package/dist/commonjs/funcs/llmEvalsUploadSampleTrajectory.js.map +1 -0
- package/dist/commonjs/funcs/llmResponsesCreate.d.ts +25 -0
- package/dist/commonjs/funcs/llmResponsesCreate.d.ts.map +1 -0
- package/dist/commonjs/funcs/llmResponsesCreate.js +137 -0
- package/dist/commonjs/funcs/llmResponsesCreate.js.map +1 -0
- package/dist/commonjs/lib/config.d.ts +2 -2
- package/dist/commonjs/lib/config.js +2 -2
- package/dist/commonjs/mcp-server/mcp-server.js +1 -1
- package/dist/commonjs/mcp-server/server.d.ts.map +1 -1
- package/dist/commonjs/mcp-server/server.js +15 -1
- package/dist/commonjs/mcp-server/server.js.map +1 -1
- package/dist/commonjs/mcp-server/tools/llmEvalsAppendAgentTrials.d.ts +8 -0
- package/dist/commonjs/mcp-server/tools/llmEvalsAppendAgentTrials.d.ts.map +1 -0
- package/dist/commonjs/mcp-server/tools/llmEvalsAppendAgentTrials.js +64 -0
- package/dist/commonjs/mcp-server/tools/llmEvalsAppendAgentTrials.js.map +1 -0
- package/dist/commonjs/mcp-server/tools/llmEvalsGetRunOverview.d.ts +8 -0
- package/dist/commonjs/mcp-server/tools/llmEvalsGetRunOverview.d.ts.map +1 -0
- package/dist/commonjs/mcp-server/tools/llmEvalsGetRunOverview.js +64 -0
- package/dist/commonjs/mcp-server/tools/llmEvalsGetRunOverview.js.map +1 -0
- package/dist/commonjs/mcp-server/tools/llmEvalsGetSampleTrajectory.d.ts +8 -0
- package/dist/commonjs/mcp-server/tools/llmEvalsGetSampleTrajectory.d.ts.map +1 -0
- package/dist/commonjs/mcp-server/tools/llmEvalsGetSampleTrajectory.js +64 -0
- package/dist/commonjs/mcp-server/tools/llmEvalsGetSampleTrajectory.js.map +1 -0
- package/dist/commonjs/mcp-server/tools/llmEvalsGetSuiteLeaderboard.d.ts +8 -0
- package/dist/commonjs/mcp-server/tools/llmEvalsGetSuiteLeaderboard.d.ts.map +1 -0
- package/dist/commonjs/mcp-server/tools/llmEvalsGetSuiteLeaderboard.js +64 -0
- package/dist/commonjs/mcp-server/tools/llmEvalsGetSuiteLeaderboard.js.map +1 -0
- package/dist/commonjs/mcp-server/tools/llmEvalsImportAgentRun.d.ts +8 -0
- package/dist/commonjs/mcp-server/tools/llmEvalsImportAgentRun.d.ts.map +1 -0
- package/dist/commonjs/mcp-server/tools/llmEvalsImportAgentRun.js +64 -0
- package/dist/commonjs/mcp-server/tools/llmEvalsImportAgentRun.js.map +1 -0
- package/dist/commonjs/mcp-server/tools/llmEvalsUploadSampleTrajectory.d.ts +8 -0
- package/dist/commonjs/mcp-server/tools/llmEvalsUploadSampleTrajectory.d.ts.map +1 -0
- package/dist/commonjs/mcp-server/tools/llmEvalsUploadSampleTrajectory.js +64 -0
- package/dist/commonjs/mcp-server/tools/llmEvalsUploadSampleTrajectory.js.map +1 -0
- package/dist/commonjs/mcp-server/tools/llmResponsesCreate.d.ts +8 -0
- package/dist/commonjs/mcp-server/tools/llmResponsesCreate.d.ts.map +1 -0
- package/dist/commonjs/mcp-server/tools/llmResponsesCreate.js +64 -0
- package/dist/commonjs/mcp-server/tools/llmResponsesCreate.js.map +1 -0
- package/dist/commonjs/models/components/appendagenttrialsrequest.d.ts +111 -0
- package/dist/commonjs/models/components/appendagenttrialsrequest.d.ts.map +1 -0
- package/dist/commonjs/models/components/appendagenttrialsrequest.js +136 -0
- package/dist/commonjs/models/components/appendagenttrialsrequest.js.map +1 -0
- package/dist/commonjs/models/components/evalleaderboardrow.d.ts +85 -0
- package/dist/commonjs/models/components/evalleaderboardrow.d.ts.map +1 -0
- package/dist/commonjs/models/components/evalleaderboardrow.js +129 -0
- package/dist/commonjs/models/components/evalleaderboardrow.js.map +1 -0
- package/dist/commonjs/models/components/evalrunoverview.d.ts +101 -0
- package/dist/commonjs/models/components/evalrunoverview.d.ts.map +1 -0
- package/dist/commonjs/models/components/evalrunoverview.js +150 -0
- package/dist/commonjs/models/components/evalrunoverview.js.map +1 -0
- package/dist/commonjs/models/components/evalsampleobject.d.ts +32 -0
- package/dist/commonjs/models/components/evalsampleobject.d.ts.map +1 -1
- package/dist/commonjs/models/components/evalsampleobject.js +20 -0
- package/dist/commonjs/models/components/evalsampleobject.js.map +1 -1
- package/dist/commonjs/models/components/evalsampletrajectoryuploadedobject.d.ts +32 -0
- package/dist/commonjs/models/components/evalsampletrajectoryuploadedobject.d.ts.map +1 -0
- package/dist/commonjs/models/components/evalsampletrajectoryuploadedobject.js +87 -0
- package/dist/commonjs/models/components/evalsampletrajectoryuploadedobject.js.map +1 -0
- package/dist/commonjs/models/components/evalsuiteleaderboard.d.ts +35 -0
- package/dist/commonjs/models/components/evalsuiteleaderboard.d.ts.map +1 -0
- package/dist/commonjs/models/components/evalsuiteleaderboard.js +78 -0
- package/dist/commonjs/models/components/evalsuiteleaderboard.js.map +1 -0
- package/dist/commonjs/models/components/importagentrunrequest.d.ts +164 -0
- package/dist/commonjs/models/components/importagentrunrequest.d.ts.map +1 -0
- package/dist/commonjs/models/components/importagentrunrequest.js +182 -0
- package/dist/commonjs/models/components/importagentrunrequest.js.map +1 -0
- package/dist/commonjs/models/components/index.d.ts +8 -0
- package/dist/commonjs/models/components/index.d.ts.map +1 -1
- package/dist/commonjs/models/components/index.js +8 -0
- package/dist/commonjs/models/components/index.js.map +1 -1
- package/dist/commonjs/models/components/responsescreaterequest.d.ts +432 -0
- package/dist/commonjs/models/components/responsescreaterequest.d.ts.map +1 -0
- package/dist/commonjs/models/components/responsescreaterequest.js +455 -0
- package/dist/commonjs/models/components/responsescreaterequest.js.map +1 -0
- package/dist/commonjs/models/components/uploadevalsampletrajectoryrequest.d.ts +34 -0
- package/dist/commonjs/models/components/uploadevalsampletrajectoryrequest.d.ts.map +1 -0
- package/dist/commonjs/models/components/uploadevalsampletrajectoryrequest.js +71 -0
- package/dist/commonjs/models/components/uploadevalsampletrajectoryrequest.js.map +1 -0
- package/dist/commonjs/models/operations/appendagentevaltrials.d.ts +264 -0
- package/dist/commonjs/models/operations/appendagentevaltrials.d.ts.map +1 -0
- package/dist/commonjs/models/operations/appendagentevaltrials.js +371 -0
- package/dist/commonjs/models/operations/appendagentevaltrials.js.map +1 -0
- package/dist/commonjs/models/operations/cancelevalrun.d.ts +20 -0
- package/dist/commonjs/models/operations/cancelevalrun.d.ts.map +1 -1
- package/dist/commonjs/models/operations/cancelevalrun.js +16 -0
- package/dist/commonjs/models/operations/cancelevalrun.js.map +1 -1
- package/dist/commonjs/models/operations/createevalrun.d.ts +20 -0
- package/dist/commonjs/models/operations/createevalrun.d.ts.map +1 -1
- package/dist/commonjs/models/operations/createevalrun.js +16 -0
- package/dist/commonjs/models/operations/createevalrun.js.map +1 -1
- package/dist/commonjs/models/operations/createresponse.d.ts +64 -0
- package/dist/commonjs/models/operations/createresponse.d.ts.map +1 -0
- package/dist/commonjs/models/operations/createresponse.js +128 -0
- package/dist/commonjs/models/operations/createresponse.js.map +1 -0
- package/dist/commonjs/models/operations/getevalrun.d.ts +20 -0
- package/dist/commonjs/models/operations/getevalrun.d.ts.map +1 -1
- package/dist/commonjs/models/operations/getevalrun.js +16 -0
- package/dist/commonjs/models/operations/getevalrun.js.map +1 -1
- package/dist/commonjs/models/operations/getevalrunoverview.d.ts +24 -0
- package/dist/commonjs/models/operations/getevalrunoverview.d.ts.map +1 -0
- package/dist/commonjs/models/operations/getevalrunoverview.js +73 -0
- package/dist/commonjs/models/operations/getevalrunoverview.js.map +1 -0
- package/dist/commonjs/models/operations/getevalsampletrajectory.d.ts +75 -0
- package/dist/commonjs/models/operations/getevalsampletrajectory.d.ts.map +1 -0
- package/dist/commonjs/models/operations/getevalsampletrajectory.js +133 -0
- package/dist/commonjs/models/operations/getevalsampletrajectory.js.map +1 -0
- package/dist/commonjs/models/operations/getevalsuiteleaderboard.d.ts +32 -0
- package/dist/commonjs/models/operations/getevalsuiteleaderboard.d.ts.map +1 -0
- package/dist/commonjs/models/operations/getevalsuiteleaderboard.js +83 -0
- package/dist/commonjs/models/operations/getevalsuiteleaderboard.js.map +1 -0
- package/dist/commonjs/models/operations/importagentevalrun.d.ts +262 -0
- package/dist/commonjs/models/operations/importagentevalrun.d.ts.map +1 -0
- package/dist/commonjs/models/operations/importagentevalrun.js +367 -0
- package/dist/commonjs/models/operations/importagentevalrun.js.map +1 -0
- package/dist/commonjs/models/operations/index.d.ts +7 -0
- package/dist/commonjs/models/operations/index.d.ts.map +1 -1
- package/dist/commonjs/models/operations/index.js +7 -0
- package/dist/commonjs/models/operations/index.js.map +1 -1
- package/dist/commonjs/models/operations/listevalruns.d.ts +20 -0
- package/dist/commonjs/models/operations/listevalruns.d.ts.map +1 -1
- package/dist/commonjs/models/operations/listevalruns.js +16 -0
- package/dist/commonjs/models/operations/listevalruns.js.map +1 -1
- package/dist/commonjs/models/operations/listevalscheduleruns.d.ts +20 -0
- package/dist/commonjs/models/operations/listevalscheduleruns.d.ts.map +1 -1
- package/dist/commonjs/models/operations/listevalscheduleruns.js +16 -0
- package/dist/commonjs/models/operations/listevalscheduleruns.js.map +1 -1
- package/dist/commonjs/models/operations/listevalsuiteleaderboardruns.d.ts +20 -0
- package/dist/commonjs/models/operations/listevalsuiteleaderboardruns.d.ts.map +1 -1
- package/dist/commonjs/models/operations/listevalsuiteleaderboardruns.js +16 -0
- package/dist/commonjs/models/operations/listevalsuiteleaderboardruns.js.map +1 -1
- package/dist/commonjs/models/operations/rerunfailedevalsamples.d.ts +20 -0
- package/dist/commonjs/models/operations/rerunfailedevalsamples.d.ts.map +1 -1
- package/dist/commonjs/models/operations/rerunfailedevalsamples.js +16 -0
- package/dist/commonjs/models/operations/rerunfailedevalsamples.js.map +1 -1
- package/dist/commonjs/models/operations/retryfailedevalrun.d.ts +20 -0
- package/dist/commonjs/models/operations/retryfailedevalrun.d.ts.map +1 -1
- package/dist/commonjs/models/operations/retryfailedevalrun.js +16 -0
- package/dist/commonjs/models/operations/retryfailedevalrun.js.map +1 -1
- package/dist/commonjs/models/operations/uploadevalsampletrajectory.d.ts +31 -0
- package/dist/commonjs/models/operations/uploadevalsampletrajectory.d.ts.map +1 -0
- package/dist/commonjs/models/operations/uploadevalsampletrajectory.js +86 -0
- package/dist/commonjs/models/operations/uploadevalsampletrajectory.js.map +1 -0
- package/dist/commonjs/react-query/index.d.ts +7 -0
- package/dist/commonjs/react-query/index.d.ts.map +1 -1
- package/dist/commonjs/react-query/index.js +7 -0
- package/dist/commonjs/react-query/index.js.map +1 -1
- package/dist/commonjs/react-query/llmEvalsAppendAgentTrials.d.ts +28 -0
- package/dist/commonjs/react-query/llmEvalsAppendAgentTrials.d.ts.map +1 -0
- package/dist/commonjs/react-query/llmEvalsAppendAgentTrials.js +47 -0
- package/dist/commonjs/react-query/llmEvalsAppendAgentTrials.js.map +1 -0
- package/dist/commonjs/react-query/llmEvalsGetRunOverview.core.d.ts +16 -0
- package/dist/commonjs/react-query/llmEvalsGetRunOverview.core.d.ts.map +1 -0
- package/dist/commonjs/react-query/llmEvalsGetRunOverview.core.js +37 -0
- package/dist/commonjs/react-query/llmEvalsGetRunOverview.core.js.map +1 -0
- package/dist/commonjs/react-query/llmEvalsGetRunOverview.d.ts +40 -0
- package/dist/commonjs/react-query/llmEvalsGetRunOverview.d.ts.map +1 -0
- package/dist/commonjs/react-query/llmEvalsGetRunOverview.js +60 -0
- package/dist/commonjs/react-query/llmEvalsGetRunOverview.js.map +1 -0
- package/dist/commonjs/react-query/llmEvalsGetSampleTrajectory.core.d.ts +16 -0
- package/dist/commonjs/react-query/llmEvalsGetSampleTrajectory.core.d.ts.map +1 -0
- package/dist/commonjs/react-query/llmEvalsGetSampleTrajectory.core.js +45 -0
- package/dist/commonjs/react-query/llmEvalsGetSampleTrajectory.core.js.map +1 -0
- package/dist/commonjs/react-query/llmEvalsGetSampleTrajectory.d.ts +44 -0
- package/dist/commonjs/react-query/llmEvalsGetSampleTrajectory.d.ts.map +1 -0
- package/dist/commonjs/react-query/llmEvalsGetSampleTrajectory.js +65 -0
- package/dist/commonjs/react-query/llmEvalsGetSampleTrajectory.js.map +1 -0
- package/dist/commonjs/react-query/llmEvalsGetSuiteLeaderboard.core.d.ts +20 -0
- package/dist/commonjs/react-query/llmEvalsGetSuiteLeaderboard.core.d.ts.map +1 -0
- package/dist/commonjs/react-query/llmEvalsGetSuiteLeaderboard.core.js +41 -0
- package/dist/commonjs/react-query/llmEvalsGetSuiteLeaderboard.core.js.map +1 -0
- package/dist/commonjs/react-query/llmEvalsGetSuiteLeaderboard.d.ts +48 -0
- package/dist/commonjs/react-query/llmEvalsGetSuiteLeaderboard.d.ts.map +1 -0
- package/dist/commonjs/react-query/llmEvalsGetSuiteLeaderboard.js +65 -0
- package/dist/commonjs/react-query/llmEvalsGetSuiteLeaderboard.js.map +1 -0
- package/dist/commonjs/react-query/llmEvalsImportAgentRun.d.ts +28 -0
- package/dist/commonjs/react-query/llmEvalsImportAgentRun.d.ts.map +1 -0
- package/dist/commonjs/react-query/llmEvalsImportAgentRun.js +47 -0
- package/dist/commonjs/react-query/llmEvalsImportAgentRun.js.map +1 -0
- package/dist/commonjs/react-query/llmEvalsUploadSampleTrajectory.d.ts +29 -0
- package/dist/commonjs/react-query/llmEvalsUploadSampleTrajectory.d.ts.map +1 -0
- package/dist/commonjs/react-query/llmEvalsUploadSampleTrajectory.js +47 -0
- package/dist/commonjs/react-query/llmEvalsUploadSampleTrajectory.js.map +1 -0
- package/dist/commonjs/react-query/llmResponsesCreate.d.ts +34 -0
- package/dist/commonjs/react-query/llmResponsesCreate.d.ts.map +1 -0
- package/dist/commonjs/react-query/llmResponsesCreate.js +50 -0
- package/dist/commonjs/react-query/llmResponsesCreate.js.map +1 -0
- package/dist/commonjs/sdk/evals.d.ts +42 -0
- package/dist/commonjs/sdk/evals.d.ts.map +1 -1
- package/dist/commonjs/sdk/evals.js +60 -0
- package/dist/commonjs/sdk/evals.js.map +1 -1
- package/dist/commonjs/sdk/responses.d.ts +11 -0
- package/dist/commonjs/sdk/responses.d.ts.map +1 -1
- package/dist/commonjs/sdk/responses.js +13 -1
- package/dist/commonjs/sdk/responses.js.map +1 -1
- package/dist/esm/funcs/llmEvalsAppendAgentTrials.d.ts +19 -0
- package/dist/esm/funcs/llmEvalsAppendAgentTrials.d.ts.map +1 -0
- package/dist/esm/funcs/llmEvalsAppendAgentTrials.js +100 -0
- package/dist/esm/funcs/llmEvalsAppendAgentTrials.js.map +1 -0
- package/dist/esm/funcs/llmEvalsGetRunOverview.d.ts +20 -0
- package/dist/esm/funcs/llmEvalsGetRunOverview.d.ts.map +1 -0
- package/dist/esm/funcs/llmEvalsGetRunOverview.js +102 -0
- package/dist/esm/funcs/llmEvalsGetRunOverview.js.map +1 -0
- package/dist/esm/funcs/llmEvalsGetSampleTrajectory.d.ts +19 -0
- package/dist/esm/funcs/llmEvalsGetSampleTrajectory.d.ts.map +1 -0
- package/dist/esm/funcs/llmEvalsGetSampleTrajectory.js +106 -0
- package/dist/esm/funcs/llmEvalsGetSampleTrajectory.js.map +1 -0
- package/dist/esm/funcs/llmEvalsGetSuiteLeaderboard.d.ts +20 -0
- package/dist/esm/funcs/llmEvalsGetSuiteLeaderboard.d.ts.map +1 -0
- package/dist/esm/funcs/llmEvalsGetSuiteLeaderboard.js +106 -0
- package/dist/esm/funcs/llmEvalsGetSuiteLeaderboard.js.map +1 -0
- package/dist/esm/funcs/llmEvalsImportAgentRun.d.ts +19 -0
- package/dist/esm/funcs/llmEvalsImportAgentRun.d.ts.map +1 -0
- package/dist/esm/funcs/llmEvalsImportAgentRun.js +94 -0
- package/dist/esm/funcs/llmEvalsImportAgentRun.js.map +1 -0
- package/dist/esm/funcs/llmEvalsUploadSampleTrajectory.d.ts +20 -0
- package/dist/esm/funcs/llmEvalsUploadSampleTrajectory.d.ts.map +1 -0
- package/dist/esm/funcs/llmEvalsUploadSampleTrajectory.js +110 -0
- package/dist/esm/funcs/llmEvalsUploadSampleTrajectory.js.map +1 -0
- package/dist/esm/funcs/llmResponsesCreate.d.ts +25 -0
- package/dist/esm/funcs/llmResponsesCreate.d.ts.map +1 -0
- package/dist/esm/funcs/llmResponsesCreate.js +100 -0
- package/dist/esm/funcs/llmResponsesCreate.js.map +1 -0
- package/dist/esm/lib/config.d.ts +2 -2
- package/dist/esm/lib/config.js +2 -2
- package/dist/esm/mcp-server/mcp-server.js +1 -1
- package/dist/esm/mcp-server/server.d.ts.map +1 -1
- package/dist/esm/mcp-server/server.js +15 -1
- package/dist/esm/mcp-server/server.js.map +1 -1
- package/dist/esm/mcp-server/tools/llmEvalsAppendAgentTrials.d.ts +8 -0
- package/dist/esm/mcp-server/tools/llmEvalsAppendAgentTrials.d.ts.map +1 -0
- package/dist/esm/mcp-server/tools/llmEvalsAppendAgentTrials.js +28 -0
- package/dist/esm/mcp-server/tools/llmEvalsAppendAgentTrials.js.map +1 -0
- package/dist/esm/mcp-server/tools/llmEvalsGetRunOverview.d.ts +8 -0
- package/dist/esm/mcp-server/tools/llmEvalsGetRunOverview.d.ts.map +1 -0
- package/dist/esm/mcp-server/tools/llmEvalsGetRunOverview.js +28 -0
- package/dist/esm/mcp-server/tools/llmEvalsGetRunOverview.js.map +1 -0
- package/dist/esm/mcp-server/tools/llmEvalsGetSampleTrajectory.d.ts +8 -0
- package/dist/esm/mcp-server/tools/llmEvalsGetSampleTrajectory.d.ts.map +1 -0
- package/dist/esm/mcp-server/tools/llmEvalsGetSampleTrajectory.js +28 -0
- package/dist/esm/mcp-server/tools/llmEvalsGetSampleTrajectory.js.map +1 -0
- package/dist/esm/mcp-server/tools/llmEvalsGetSuiteLeaderboard.d.ts +8 -0
- package/dist/esm/mcp-server/tools/llmEvalsGetSuiteLeaderboard.d.ts.map +1 -0
- package/dist/esm/mcp-server/tools/llmEvalsGetSuiteLeaderboard.js +28 -0
- package/dist/esm/mcp-server/tools/llmEvalsGetSuiteLeaderboard.js.map +1 -0
- package/dist/esm/mcp-server/tools/llmEvalsImportAgentRun.d.ts +8 -0
- package/dist/esm/mcp-server/tools/llmEvalsImportAgentRun.d.ts.map +1 -0
- package/dist/esm/mcp-server/tools/llmEvalsImportAgentRun.js +28 -0
- package/dist/esm/mcp-server/tools/llmEvalsImportAgentRun.js.map +1 -0
- package/dist/esm/mcp-server/tools/llmEvalsUploadSampleTrajectory.d.ts +8 -0
- package/dist/esm/mcp-server/tools/llmEvalsUploadSampleTrajectory.d.ts.map +1 -0
- package/dist/esm/mcp-server/tools/llmEvalsUploadSampleTrajectory.js +28 -0
- package/dist/esm/mcp-server/tools/llmEvalsUploadSampleTrajectory.js.map +1 -0
- package/dist/esm/mcp-server/tools/llmResponsesCreate.d.ts +8 -0
- package/dist/esm/mcp-server/tools/llmResponsesCreate.d.ts.map +1 -0
- package/dist/esm/mcp-server/tools/llmResponsesCreate.js +28 -0
- package/dist/esm/mcp-server/tools/llmResponsesCreate.js.map +1 -0
- package/dist/esm/models/components/appendagenttrialsrequest.d.ts +111 -0
- package/dist/esm/models/components/appendagenttrialsrequest.d.ts.map +1 -0
- package/dist/esm/models/components/appendagenttrialsrequest.js +96 -0
- package/dist/esm/models/components/appendagenttrialsrequest.js.map +1 -0
- package/dist/esm/models/components/evalleaderboardrow.d.ts +85 -0
- package/dist/esm/models/components/evalleaderboardrow.d.ts.map +1 -0
- package/dist/esm/models/components/evalleaderboardrow.js +89 -0
- package/dist/esm/models/components/evalleaderboardrow.js.map +1 -0
- package/dist/esm/models/components/evalrunoverview.d.ts +101 -0
- package/dist/esm/models/components/evalrunoverview.d.ts.map +1 -0
- package/dist/esm/models/components/evalrunoverview.js +108 -0
- package/dist/esm/models/components/evalrunoverview.js.map +1 -0
- package/dist/esm/models/components/evalsampleobject.d.ts +32 -0
- package/dist/esm/models/components/evalsampleobject.d.ts.map +1 -1
- package/dist/esm/models/components/evalsampleobject.js +20 -0
- package/dist/esm/models/components/evalsampleobject.js.map +1 -1
- package/dist/esm/models/components/evalsampletrajectoryuploadedobject.d.ts +32 -0
- package/dist/esm/models/components/evalsampletrajectoryuploadedobject.d.ts.map +1 -0
- package/dist/esm/models/components/evalsampletrajectoryuploadedobject.js +49 -0
- package/dist/esm/models/components/evalsampletrajectoryuploadedobject.js.map +1 -0
- package/dist/esm/models/components/evalsuiteleaderboard.d.ts +35 -0
- package/dist/esm/models/components/evalsuiteleaderboard.d.ts.map +1 -0
- package/dist/esm/models/components/evalsuiteleaderboard.js +40 -0
- package/dist/esm/models/components/evalsuiteleaderboard.js.map +1 -0
- package/dist/esm/models/components/importagentrunrequest.d.ts +164 -0
- package/dist/esm/models/components/importagentrunrequest.d.ts.map +1 -0
- package/dist/esm/models/components/importagentrunrequest.js +142 -0
- package/dist/esm/models/components/importagentrunrequest.js.map +1 -0
- package/dist/esm/models/components/index.d.ts +8 -0
- package/dist/esm/models/components/index.d.ts.map +1 -1
- package/dist/esm/models/components/index.js +8 -0
- package/dist/esm/models/components/index.js.map +1 -1
- package/dist/esm/models/components/responsescreaterequest.d.ts +432 -0
- package/dist/esm/models/components/responsescreaterequest.d.ts.map +1 -0
- package/dist/esm/models/components/responsescreaterequest.js +403 -0
- package/dist/esm/models/components/responsescreaterequest.js.map +1 -0
- package/dist/esm/models/components/uploadevalsampletrajectoryrequest.d.ts +34 -0
- package/dist/esm/models/components/uploadevalsampletrajectoryrequest.d.ts.map +1 -0
- package/dist/esm/models/components/uploadevalsampletrajectoryrequest.js +33 -0
- package/dist/esm/models/components/uploadevalsampletrajectoryrequest.js.map +1 -0
- package/dist/esm/models/operations/appendagentevaltrials.d.ts +264 -0
- package/dist/esm/models/operations/appendagentevaltrials.d.ts.map +1 -0
- package/dist/esm/models/operations/appendagentevaltrials.js +323 -0
- package/dist/esm/models/operations/appendagentevaltrials.js.map +1 -0
- package/dist/esm/models/operations/cancelevalrun.d.ts +20 -0
- package/dist/esm/models/operations/cancelevalrun.d.ts.map +1 -1
- package/dist/esm/models/operations/cancelevalrun.js +16 -0
- package/dist/esm/models/operations/cancelevalrun.js.map +1 -1
- package/dist/esm/models/operations/createevalrun.d.ts +20 -0
- package/dist/esm/models/operations/createevalrun.d.ts.map +1 -1
- package/dist/esm/models/operations/createevalrun.js +16 -0
- package/dist/esm/models/operations/createevalrun.js.map +1 -1
- package/dist/esm/models/operations/createresponse.d.ts +64 -0
- package/dist/esm/models/operations/createresponse.d.ts.map +1 -0
- package/dist/esm/models/operations/createresponse.js +86 -0
- package/dist/esm/models/operations/createresponse.js.map +1 -0
- package/dist/esm/models/operations/getevalrun.d.ts +20 -0
- package/dist/esm/models/operations/getevalrun.d.ts.map +1 -1
- package/dist/esm/models/operations/getevalrun.js +16 -0
- package/dist/esm/models/operations/getevalrun.js.map +1 -1
- package/dist/esm/models/operations/getevalrunoverview.d.ts +24 -0
- package/dist/esm/models/operations/getevalrunoverview.d.ts.map +1 -0
- package/dist/esm/models/operations/getevalrunoverview.js +35 -0
- package/dist/esm/models/operations/getevalrunoverview.js.map +1 -0
- package/dist/esm/models/operations/getevalsampletrajectory.d.ts +75 -0
- package/dist/esm/models/operations/getevalsampletrajectory.d.ts.map +1 -0
- package/dist/esm/models/operations/getevalsampletrajectory.js +93 -0
- package/dist/esm/models/operations/getevalsampletrajectory.js.map +1 -0
- package/dist/esm/models/operations/getevalsuiteleaderboard.d.ts +32 -0
- package/dist/esm/models/operations/getevalsuiteleaderboard.d.ts.map +1 -0
- package/dist/esm/models/operations/getevalsuiteleaderboard.js +45 -0
- package/dist/esm/models/operations/getevalsuiteleaderboard.js.map +1 -0
- package/dist/esm/models/operations/importagentevalrun.d.ts +262 -0
- package/dist/esm/models/operations/importagentevalrun.d.ts.map +1 -0
- package/dist/esm/models/operations/importagentevalrun.js +319 -0
- package/dist/esm/models/operations/importagentevalrun.js.map +1 -0
- package/dist/esm/models/operations/index.d.ts +7 -0
- package/dist/esm/models/operations/index.d.ts.map +1 -1
- package/dist/esm/models/operations/index.js +7 -0
- package/dist/esm/models/operations/index.js.map +1 -1
- package/dist/esm/models/operations/listevalruns.d.ts +20 -0
- package/dist/esm/models/operations/listevalruns.d.ts.map +1 -1
- package/dist/esm/models/operations/listevalruns.js +16 -0
- package/dist/esm/models/operations/listevalruns.js.map +1 -1
- package/dist/esm/models/operations/listevalscheduleruns.d.ts +20 -0
- package/dist/esm/models/operations/listevalscheduleruns.d.ts.map +1 -1
- package/dist/esm/models/operations/listevalscheduleruns.js +16 -0
- package/dist/esm/models/operations/listevalscheduleruns.js.map +1 -1
- package/dist/esm/models/operations/listevalsuiteleaderboardruns.d.ts +20 -0
- package/dist/esm/models/operations/listevalsuiteleaderboardruns.d.ts.map +1 -1
- package/dist/esm/models/operations/listevalsuiteleaderboardruns.js +16 -0
- package/dist/esm/models/operations/listevalsuiteleaderboardruns.js.map +1 -1
- package/dist/esm/models/operations/rerunfailedevalsamples.d.ts +20 -0
- package/dist/esm/models/operations/rerunfailedevalsamples.d.ts.map +1 -1
- package/dist/esm/models/operations/rerunfailedevalsamples.js +16 -0
- package/dist/esm/models/operations/rerunfailedevalsamples.js.map +1 -1
- package/dist/esm/models/operations/retryfailedevalrun.d.ts +20 -0
- package/dist/esm/models/operations/retryfailedevalrun.d.ts.map +1 -1
- package/dist/esm/models/operations/retryfailedevalrun.js +16 -0
- package/dist/esm/models/operations/retryfailedevalrun.js.map +1 -1
- package/dist/esm/models/operations/uploadevalsampletrajectory.d.ts +31 -0
- package/dist/esm/models/operations/uploadevalsampletrajectory.d.ts.map +1 -0
- package/dist/esm/models/operations/uploadevalsampletrajectory.js +48 -0
- package/dist/esm/models/operations/uploadevalsampletrajectory.js.map +1 -0
- package/dist/esm/react-query/index.d.ts +7 -0
- package/dist/esm/react-query/index.d.ts.map +1 -1
- package/dist/esm/react-query/index.js +7 -0
- package/dist/esm/react-query/index.js.map +1 -1
- package/dist/esm/react-query/llmEvalsAppendAgentTrials.d.ts +28 -0
- package/dist/esm/react-query/llmEvalsAppendAgentTrials.d.ts.map +1 -0
- package/dist/esm/react-query/llmEvalsAppendAgentTrials.js +42 -0
- package/dist/esm/react-query/llmEvalsAppendAgentTrials.js.map +1 -0
- package/dist/esm/react-query/llmEvalsGetRunOverview.core.d.ts +16 -0
- package/dist/esm/react-query/llmEvalsGetRunOverview.core.d.ts.map +1 -0
- package/dist/esm/react-query/llmEvalsGetRunOverview.core.js +32 -0
- package/dist/esm/react-query/llmEvalsGetRunOverview.core.js.map +1 -0
- package/dist/esm/react-query/llmEvalsGetRunOverview.d.ts +40 -0
- package/dist/esm/react-query/llmEvalsGetRunOverview.d.ts.map +1 -0
- package/dist/esm/react-query/llmEvalsGetRunOverview.js +50 -0
- package/dist/esm/react-query/llmEvalsGetRunOverview.js.map +1 -0
- package/dist/esm/react-query/llmEvalsGetSampleTrajectory.core.d.ts +16 -0
- package/dist/esm/react-query/llmEvalsGetSampleTrajectory.core.d.ts.map +1 -0
- package/dist/esm/react-query/llmEvalsGetSampleTrajectory.core.js +40 -0
- package/dist/esm/react-query/llmEvalsGetSampleTrajectory.core.js.map +1 -0
- package/dist/esm/react-query/llmEvalsGetSampleTrajectory.d.ts +44 -0
- package/dist/esm/react-query/llmEvalsGetSampleTrajectory.d.ts.map +1 -0
- package/dist/esm/react-query/llmEvalsGetSampleTrajectory.js +55 -0
- package/dist/esm/react-query/llmEvalsGetSampleTrajectory.js.map +1 -0
- package/dist/esm/react-query/llmEvalsGetSuiteLeaderboard.core.d.ts +20 -0
- package/dist/esm/react-query/llmEvalsGetSuiteLeaderboard.core.d.ts.map +1 -0
- package/dist/esm/react-query/llmEvalsGetSuiteLeaderboard.core.js +36 -0
- package/dist/esm/react-query/llmEvalsGetSuiteLeaderboard.core.js.map +1 -0
- package/dist/esm/react-query/llmEvalsGetSuiteLeaderboard.d.ts +48 -0
- package/dist/esm/react-query/llmEvalsGetSuiteLeaderboard.d.ts.map +1 -0
- package/dist/esm/react-query/llmEvalsGetSuiteLeaderboard.js +55 -0
- package/dist/esm/react-query/llmEvalsGetSuiteLeaderboard.js.map +1 -0
- package/dist/esm/react-query/llmEvalsImportAgentRun.d.ts +28 -0
- package/dist/esm/react-query/llmEvalsImportAgentRun.d.ts.map +1 -0
- package/dist/esm/react-query/llmEvalsImportAgentRun.js +42 -0
- package/dist/esm/react-query/llmEvalsImportAgentRun.js.map +1 -0
- package/dist/esm/react-query/llmEvalsUploadSampleTrajectory.d.ts +29 -0
- package/dist/esm/react-query/llmEvalsUploadSampleTrajectory.d.ts.map +1 -0
- package/dist/esm/react-query/llmEvalsUploadSampleTrajectory.js +42 -0
- package/dist/esm/react-query/llmEvalsUploadSampleTrajectory.js.map +1 -0
- package/dist/esm/react-query/llmResponsesCreate.d.ts +34 -0
- package/dist/esm/react-query/llmResponsesCreate.d.ts.map +1 -0
- package/dist/esm/react-query/llmResponsesCreate.js +43 -0
- package/dist/esm/react-query/llmResponsesCreate.js.map +1 -0
- package/dist/esm/sdk/evals.d.ts +42 -0
- package/dist/esm/sdk/evals.d.ts.map +1 -1
- package/dist/esm/sdk/evals.js +60 -0
- package/dist/esm/sdk/evals.js.map +1 -1
- package/dist/esm/sdk/responses.d.ts +11 -0
- package/dist/esm/sdk/responses.d.ts.map +1 -1
- package/dist/esm/sdk/responses.js +11 -0
- package/dist/esm/sdk/responses.js.map +1 -1
- package/jsr.json +1 -1
- package/package.json +1 -1
- package/src/funcs/llmEvalsAppendAgentTrials.ts +188 -0
- package/src/funcs/llmEvalsGetRunOverview.ts +192 -0
- package/src/funcs/llmEvalsGetSampleTrajectory.ts +197 -0
- package/src/funcs/llmEvalsGetSuiteLeaderboard.ts +197 -0
- package/src/funcs/llmEvalsImportAgentRun.ts +181 -0
- package/src/funcs/llmEvalsUploadSampleTrajectory.ts +201 -0
- package/src/funcs/llmResponsesCreate.ts +188 -0
- package/src/lib/config.ts +2 -2
- package/src/mcp-server/mcp-server.ts +1 -1
- package/src/mcp-server/server.ts +15 -1
- package/src/mcp-server/tools/llmEvalsAppendAgentTrials.ts +37 -0
- package/src/mcp-server/tools/llmEvalsGetRunOverview.ts +37 -0
- package/src/mcp-server/tools/llmEvalsGetSampleTrajectory.ts +37 -0
- package/src/mcp-server/tools/llmEvalsGetSuiteLeaderboard.ts +37 -0
- package/src/mcp-server/tools/llmEvalsImportAgentRun.ts +37 -0
- package/src/mcp-server/tools/llmEvalsUploadSampleTrajectory.ts +38 -0
- package/src/mcp-server/tools/llmResponsesCreate.ts +37 -0
- package/src/models/components/appendagenttrialsrequest.ts +224 -0
- package/src/models/components/evalleaderboardrow.ts +200 -0
- package/src/models/components/evalrunoverview.ts +240 -0
- package/src/models/components/evalsampleobject.ts +48 -0
- package/src/models/components/evalsampletrajectoryuploadedobject.ts +98 -0
- package/src/models/components/evalsuiteleaderboard.ts +93 -0
- package/src/models/components/importagentrunrequest.ts +319 -0
- package/src/models/components/index.ts +8 -0
- package/src/models/components/responsescreaterequest.ts +1076 -0
- package/src/models/components/uploadevalsampletrajectoryrequest.ts +79 -0
- package/src/models/operations/appendagentevaltrials.ts +678 -0
- package/src/models/operations/cancelevalrun.ts +36 -0
- package/src/models/operations/createevalrun.ts +36 -0
- package/src/models/operations/createresponse.ts +198 -0
- package/src/models/operations/getevalrun.ts +36 -0
- package/src/models/operations/getevalrunoverview.ts +73 -0
- package/src/models/operations/getevalsampletrajectory.ts +199 -0
- package/src/models/operations/getevalsuiteleaderboard.ts +93 -0
- package/src/models/operations/importagentevalrun.ts +665 -0
- package/src/models/operations/index.ts +7 -0
- package/src/models/operations/listevalruns.ts +36 -0
- package/src/models/operations/listevalscheduleruns.ts +36 -0
- package/src/models/operations/listevalsuiteleaderboardruns.ts +36 -0
- package/src/models/operations/rerunfailedevalsamples.ts +36 -0
- package/src/models/operations/retryfailedevalrun.ts +36 -0
- package/src/models/operations/uploadevalsampletrajectory.ts +98 -0
- package/src/react-query/index.ts +7 -0
- package/src/react-query/llmEvalsAppendAgentTrials.ts +109 -0
- package/src/react-query/llmEvalsGetRunOverview.core.ts +77 -0
- package/src/react-query/llmEvalsGetRunOverview.ts +150 -0
- package/src/react-query/llmEvalsGetSampleTrajectory.core.ts +94 -0
- package/src/react-query/llmEvalsGetSampleTrajectory.ts +159 -0
- package/src/react-query/llmEvalsGetSuiteLeaderboard.core.ts +89 -0
- package/src/react-query/llmEvalsGetSuiteLeaderboard.ts +163 -0
- package/src/react-query/llmEvalsImportAgentRun.ts +109 -0
- package/src/react-query/llmEvalsUploadSampleTrajectory.ts +110 -0
- package/src/react-query/llmResponsesCreate.ts +113 -0
- package/src/sdk/evals.ts +108 -0
- package/src/sdk/responses.ts +23 -0
|
@@ -0,0 +1,19 @@
|
|
|
1
|
+
import { SDKCore } from "../core.js";
|
|
2
|
+
import { RequestOptions } from "../lib/sdks.js";
|
|
3
|
+
import { ConnectionError, InvalidRequestError, RequestAbortedError, RequestTimeoutError, UnexpectedClientError } from "../models/errors/httpclienterrors.js";
|
|
4
|
+
import { ResponseValidationError } from "../models/errors/responsevalidationerror.js";
|
|
5
|
+
import { SDKError } from "../models/errors/sdkerror.js";
|
|
6
|
+
import { SDKValidationError } from "../models/errors/sdkvalidationerror.js";
|
|
7
|
+
import * as operations from "../models/operations/index.js";
|
|
8
|
+
import { APIPromise } from "../types/async.js";
|
|
9
|
+
import { Result } from "../types/fp.js";
|
|
10
|
+
/**
|
|
11
|
+
* Append trials to an open coding-agent run
|
|
12
|
+
*
|
|
13
|
+
* @remarks
|
|
14
|
+
* Adds finished trials to a run opened with `finalize: false`, so a job started from MKA1 can be watched while it runs instead of appearing complete out of nowhere at the end. Each trial pins its own `sample_index` and upserts on (task, model, sample_index): a harness cannot tell a timeout from a lost response, so re-sending a batch is safe and replaces rather than duplicates. The whole batch and its aggregate recompute land in one transaction, serialized per run. Counts, metrics and cost are recomputed from the stored rows on every call, never accumulated from the request, so a replayed batch cannot double them. Send `finalize: true` (usually with an empty `trials`) to close the run — until then it stays `in_progress` and off the leaderboards, which only count completed runs. Appending to an already-completed or cancelled run is rejected: that record is finished, and rewriting it would silently move a number someone may have already read.
|
|
15
|
+
*
|
|
16
|
+
* If set, this operation will use {@link Security.bearerAuth} from the global security.
|
|
17
|
+
*/
|
|
18
|
+
export declare function llmEvalsAppendAgentTrials(client: SDKCore, request: operations.AppendAgentEvalTrialsRequest, options?: RequestOptions): APIPromise<Result<operations.AppendAgentEvalTrialsResponseBody, SDKError | ResponseValidationError | ConnectionError | RequestAbortedError | RequestTimeoutError | InvalidRequestError | UnexpectedClientError | SDKValidationError>>;
|
|
19
|
+
//# sourceMappingURL=llmEvalsAppendAgentTrials.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"llmEvalsAppendAgentTrials.d.ts","sourceRoot":"","sources":["../../../src/funcs/llmEvalsAppendAgentTrials.ts"],"names":[],"mappings":"AAIA,OAAO,EAAE,OAAO,EAAE,MAAM,YAAY,CAAC;AAMrC,OAAO,EAAE,cAAc,EAAE,MAAM,gBAAgB,CAAC;AAGhD,OAAO,EACL,eAAe,EACf,mBAAmB,EACnB,mBAAmB,EACnB,mBAAmB,EACnB,qBAAqB,EACtB,MAAM,sCAAsC,CAAC;AAC9C,OAAO,EAAE,uBAAuB,EAAE,MAAM,6CAA6C,CAAC;AACtF,OAAO,EAAE,QAAQ,EAAE,MAAM,8BAA8B,CAAC;AACxD,OAAO,EAAE,kBAAkB,EAAE,MAAM,wCAAwC,CAAC;AAC5E,OAAO,KAAK,UAAU,MAAM,+BAA+B,CAAC;AAC5D,OAAO,EAAW,UAAU,EAAE,MAAM,mBAAmB,CAAC;AACxD,OAAO,EAAE,MAAM,EAAE,MAAM,gBAAgB,CAAC;AAExC;;;;;;;GAOG;AACH,wBAAgB,yBAAyB,CACvC,MAAM,EAAE,OAAO,EACf,OAAO,EAAE,UAAU,CAAC,4BAA4B,EAChD,OAAO,CAAC,EAAE,cAAc,GACvB,UAAU,CACX,MAAM,CACJ,UAAU,CAAC,iCAAiC,EAC1C,QAAQ,GACR,uBAAuB,GACvB,eAAe,GACf,mBAAmB,GACnB,mBAAmB,GACnB,mBAAmB,GACnB,qBAAqB,GACrB,kBAAkB,CACrB,CACF,CAMA"}
|
|
@@ -0,0 +1,136 @@
|
|
|
1
|
+
"use strict";
|
|
2
|
+
/*
|
|
3
|
+
* Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT.
|
|
4
|
+
*/
|
|
5
|
+
var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
|
|
6
|
+
if (k2 === undefined) k2 = k;
|
|
7
|
+
var desc = Object.getOwnPropertyDescriptor(m, k);
|
|
8
|
+
if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
|
|
9
|
+
desc = { enumerable: true, get: function() { return m[k]; } };
|
|
10
|
+
}
|
|
11
|
+
Object.defineProperty(o, k2, desc);
|
|
12
|
+
}) : (function(o, m, k, k2) {
|
|
13
|
+
if (k2 === undefined) k2 = k;
|
|
14
|
+
o[k2] = m[k];
|
|
15
|
+
}));
|
|
16
|
+
var __setModuleDefault = (this && this.__setModuleDefault) || (Object.create ? (function(o, v) {
|
|
17
|
+
Object.defineProperty(o, "default", { enumerable: true, value: v });
|
|
18
|
+
}) : function(o, v) {
|
|
19
|
+
o["default"] = v;
|
|
20
|
+
});
|
|
21
|
+
var __importStar = (this && this.__importStar) || (function () {
|
|
22
|
+
var ownKeys = function(o) {
|
|
23
|
+
ownKeys = Object.getOwnPropertyNames || function (o) {
|
|
24
|
+
var ar = [];
|
|
25
|
+
for (var k in o) if (Object.prototype.hasOwnProperty.call(o, k)) ar[ar.length] = k;
|
|
26
|
+
return ar;
|
|
27
|
+
};
|
|
28
|
+
return ownKeys(o);
|
|
29
|
+
};
|
|
30
|
+
return function (mod) {
|
|
31
|
+
if (mod && mod.__esModule) return mod;
|
|
32
|
+
var result = {};
|
|
33
|
+
if (mod != null) for (var k = ownKeys(mod), i = 0; i < k.length; i++) if (k[i] !== "default") __createBinding(result, mod, k[i]);
|
|
34
|
+
__setModuleDefault(result, mod);
|
|
35
|
+
return result;
|
|
36
|
+
};
|
|
37
|
+
})();
|
|
38
|
+
Object.defineProperty(exports, "__esModule", { value: true });
|
|
39
|
+
exports.llmEvalsAppendAgentTrials = llmEvalsAppendAgentTrials;
|
|
40
|
+
const encodings_js_1 = require("../lib/encodings.js");
|
|
41
|
+
const http_js_1 = require("../lib/http.js");
|
|
42
|
+
const M = __importStar(require("../lib/matchers.js"));
|
|
43
|
+
const primitives_js_1 = require("../lib/primitives.js");
|
|
44
|
+
const schemas_js_1 = require("../lib/schemas.js");
|
|
45
|
+
const security_js_1 = require("../lib/security.js");
|
|
46
|
+
const url_js_1 = require("../lib/url.js");
|
|
47
|
+
const operations = __importStar(require("../models/operations/index.js"));
|
|
48
|
+
const async_js_1 = require("../types/async.js");
|
|
49
|
+
/**
|
|
50
|
+
* Append trials to an open coding-agent run
|
|
51
|
+
*
|
|
52
|
+
* @remarks
|
|
53
|
+
* Adds finished trials to a run opened with `finalize: false`, so a job started from MKA1 can be watched while it runs instead of appearing complete out of nowhere at the end. Each trial pins its own `sample_index` and upserts on (task, model, sample_index): a harness cannot tell a timeout from a lost response, so re-sending a batch is safe and replaces rather than duplicates. The whole batch and its aggregate recompute land in one transaction, serialized per run. Counts, metrics and cost are recomputed from the stored rows on every call, never accumulated from the request, so a replayed batch cannot double them. Send `finalize: true` (usually with an empty `trials`) to close the run — until then it stays `in_progress` and off the leaderboards, which only count completed runs. Appending to an already-completed or cancelled run is rejected: that record is finished, and rewriting it would silently move a number someone may have already read.
|
|
54
|
+
*
|
|
55
|
+
* If set, this operation will use {@link Security.bearerAuth} from the global security.
|
|
56
|
+
*/
|
|
57
|
+
function llmEvalsAppendAgentTrials(client, request, options) {
|
|
58
|
+
return new async_js_1.APIPromise($do(client, request, options));
|
|
59
|
+
}
|
|
60
|
+
async function $do(client, request, options) {
|
|
61
|
+
const parsed = (0, schemas_js_1.safeParse)(request, (value) => operations.AppendAgentEvalTrialsRequest$outboundSchema.parse(value), "Input validation failed");
|
|
62
|
+
if (!parsed.ok) {
|
|
63
|
+
return [parsed, { status: "invalid" }];
|
|
64
|
+
}
|
|
65
|
+
const payload = parsed.value;
|
|
66
|
+
const body = (0, encodings_js_1.encodeJSON)("body", payload.AppendAgentTrialsRequest, {
|
|
67
|
+
explode: true,
|
|
68
|
+
});
|
|
69
|
+
const pathParams = {
|
|
70
|
+
run_id: (0, encodings_js_1.encodeSimple)("run_id", payload.run_id, {
|
|
71
|
+
explode: false,
|
|
72
|
+
charEncoding: "percent",
|
|
73
|
+
}),
|
|
74
|
+
};
|
|
75
|
+
const path = (0, url_js_1.pathToFunc)("/api/v1/llm/evals/runs/{run_id}/trials")(pathParams);
|
|
76
|
+
const headers = new Headers((0, primitives_js_1.compactMap)({
|
|
77
|
+
"Content-Type": "application/json",
|
|
78
|
+
Accept: "application/json",
|
|
79
|
+
"X-On-Behalf-Of": (0, encodings_js_1.encodeSimple)("X-On-Behalf-Of", payload["X-On-Behalf-Of"], { explode: false, charEncoding: "none" }),
|
|
80
|
+
}));
|
|
81
|
+
const secConfig = await (0, security_js_1.extractSecurity)(client._options.bearerAuth);
|
|
82
|
+
const securityInput = secConfig == null ? {} : { bearerAuth: secConfig };
|
|
83
|
+
const requestSecurity = (0, security_js_1.resolveGlobalSecurity)(securityInput, [0]);
|
|
84
|
+
const context = {
|
|
85
|
+
options: client._options,
|
|
86
|
+
baseURL: options?.serverURL ?? client._baseURL ?? "",
|
|
87
|
+
operationID: "appendAgentEvalTrials",
|
|
88
|
+
oAuth2Scopes: null,
|
|
89
|
+
resolvedSecurity: requestSecurity,
|
|
90
|
+
securitySource: client._options.bearerAuth,
|
|
91
|
+
retryConfig: options?.retries
|
|
92
|
+
|| client._options.retryConfig
|
|
93
|
+
|| {
|
|
94
|
+
strategy: "backoff",
|
|
95
|
+
backoff: {
|
|
96
|
+
initialInterval: 500,
|
|
97
|
+
maxInterval: 5000,
|
|
98
|
+
exponent: 1.5,
|
|
99
|
+
maxElapsedTime: 15000,
|
|
100
|
+
},
|
|
101
|
+
retryConnectionErrors: true,
|
|
102
|
+
}
|
|
103
|
+
|| { strategy: "none" },
|
|
104
|
+
retryCodes: options?.retryCodes || ["429", "500", "502", "503", "504"],
|
|
105
|
+
};
|
|
106
|
+
const requestRes = client._createRequest(context, {
|
|
107
|
+
security: requestSecurity,
|
|
108
|
+
method: "POST",
|
|
109
|
+
baseURL: options?.serverURL,
|
|
110
|
+
path: path,
|
|
111
|
+
headers: headers,
|
|
112
|
+
body: body,
|
|
113
|
+
userAgent: client._options.userAgent,
|
|
114
|
+
timeoutMs: options?.timeoutMs || client._options.timeoutMs || -1,
|
|
115
|
+
}, options);
|
|
116
|
+
if (!requestRes.ok) {
|
|
117
|
+
return [requestRes, { status: "invalid" }];
|
|
118
|
+
}
|
|
119
|
+
const req = requestRes.value;
|
|
120
|
+
const doResult = await client._do(req, {
|
|
121
|
+
context,
|
|
122
|
+
isErrorStatusCode: (statusCode) => (0, http_js_1.matchStatusCode)({ status: statusCode }, ["4XX", "5XX"]),
|
|
123
|
+
retryConfig: context.retryConfig,
|
|
124
|
+
retryCodes: context.retryCodes,
|
|
125
|
+
});
|
|
126
|
+
if (!doResult.ok) {
|
|
127
|
+
return [doResult, { status: "request-error", request: req }];
|
|
128
|
+
}
|
|
129
|
+
const response = doResult.value;
|
|
130
|
+
const [result] = await M.match(M.json(200, operations.AppendAgentEvalTrialsResponseBody$inboundSchema), M.fail("4XX"), M.fail("5XX"))(response, req);
|
|
131
|
+
if (!result.ok) {
|
|
132
|
+
return [result, { status: "complete", request: req, response }];
|
|
133
|
+
}
|
|
134
|
+
return [result, { status: "complete", request: req, response }];
|
|
135
|
+
}
|
|
136
|
+
//# sourceMappingURL=llmEvalsAppendAgentTrials.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"llmEvalsAppendAgentTrials.js","sourceRoot":"","sources":["../../../src/funcs/llmEvalsAppendAgentTrials.ts"],"names":[],"mappings":";AAAA;;GAEG;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;AAiCH,8DAsBC;AApDD,sDAA+D;AAC/D,4CAAiD;AACjD,sDAAwC;AACxC,wDAAkD;AAClD,kDAA8C;AAE9C,oDAA4E;AAC5E,0CAA2C;AAW3C,0EAA4D;AAC5D,gDAAwD;AAGxD;;;;;;;GAOG;AACH,SAAgB,yBAAyB,CACvC,MAAe,EACf,OAAgD,EAChD,OAAwB;IAcxB,OAAO,IAAI,qBAAU,CAAC,GAAG,CACvB,MAAM,EACN,OAAO,EACP,OAAO,CACR,CAAC,CAAC;AACL,CAAC;AAED,KAAK,UAAU,GAAG,CAChB,MAAe,EACf,OAAgD,EAChD,OAAwB;IAiBxB,MAAM,MAAM,GAAG,IAAA,sBAAS,EACtB,OAAO,EACP,CAAC,KAAK,EAAE,EAAE,CACR,UAAU,CAAC,2CAA2C,CAAC,KAAK,CAAC,KAAK,CAAC,EACrE,yBAAyB,CAC1B,CAAC;IACF,IAAI,CAAC,MAAM,CAAC,EAAE,EAAE,CAAC;QACf,OAAO,CAAC,MAAM,EAAE,EAAE,MAAM,EAAE,SAAS,EAAE,CAAC,CAAC;IACzC,CAAC;IACD,MAAM,OAAO,GAAG,MAAM,CAAC,KAAK,CAAC;IAC7B,MAAM,IAAI,GAAG,IAAA,yBAAU,EAAC,MAAM,EAAE,OAAO,CAAC,wBAAwB,EAAE;QAChE,OAAO,EAAE,IAAI;KACd,CAAC,CAAC;IAEH,MAAM,UAAU,GAAG;QACjB,MAAM,EAAE,IAAA,2BAAY,EAAC,QAAQ,EAAE,OAAO,CAAC,MAAM,EAAE;YAC7C,OAAO,EAAE,KAAK;YACd,YAAY,EAAE,SAAS;SACxB,CAAC;KACH,CAAC;IACF,MAAM,IAAI,GAAG,IAAA,mBAAU,EAAC,wCAAwC,CAAC,CAAC,UAAU,CAAC,CAAC;IAE9E,MAAM,OAAO,GAAG,IAAI,OAAO,CAAC,IAAA,0BAAU,EAAC;QACrC,cAAc,EAAE,kBAAkB;QAClC,MAAM,EAAE,kBAAkB;QAC1B,gBAAgB,EAAE,IAAA,2BAAY,EAC5B,gBAAgB,EAChB,OAAO,CAAC,gBAAgB,CAAC,EACzB,EAAE,OAAO,EAAE,KAAK,EAAE,YAAY,EAAE,MAAM,EAAE,CACzC;KACF,CAAC,CAAC,CAAC;IAEJ,MAAM,SAAS,GAAG,MAAM,IAAA,6BAAe,EAAC,MAAM,CAAC,QAAQ,CAAC,UAAU,CAAC,CAAC;IACpE,MAAM,aAAa,GAAG,SAAS,IAAI,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,EAAE,UAAU,EAAE,SAAS,EAAE,CAAC;IACzE,MAAM,eAAe,GAAG,IAAA,mCAAqB,EAAC,aAAa,EAAE,CAAC,CAAC,CAAC,CAAC,CAAC;IAElE,MAAM,OAAO,GAAG;QACd,OAAO,EAAE,MAAM,CAAC,QAAQ;QACxB,OAAO,EAAE,OAAO,EAAE,SAAS,IAAI,MAAM,CAAC,QAAQ,IAAI,EAAE;QACpD,WAAW,EAAE,uBAAuB;QACpC,YAAY,EAAE,IAAI;QAElB,gBAAgB,EAAE,eAAe;QAEjC,cAAc,EAAE,MAAM,CAAC,QAAQ,CAAC,UAAU;QAC1C,WAAW,EAAE,OAAO,EAAE,OAAO;eACxB,MAAM,CAAC,QAAQ,CAAC,WAAW;eAC3B;gBACD,QAAQ,EAAE,SAAS;gBACnB,OAAO,EAAE;oBACP,eAAe,EAAE,GAAG;oBACpB,WAAW,EAAE,IAAI;oBACjB,QAAQ,EAAE,GAAG;oBACb,cAAc,EAAE,KAAK;iBACtB;gBACD,qBAAqB,EAAE,IAAI;aAC5B;eACE,EAAE,QAAQ,EAAE,MAAM,EAAE;QACzB,UAAU,EAAE,OAAO,EAAE,UAAU,IAAI,CAAC,KAAK,EAAE,KAAK,EAAE,KAAK,EAAE,KAAK,EAAE,KAAK,CAAC;KACvE,CAAC;IAEF,MAAM,UAAU,GAAG,MAAM,CAAC,cAAc,CAAC,OAAO,EAAE;QAChD,QAAQ,EAAE,eAAe;QACzB,MAAM,EAAE,MAAM;QACd,OAAO,EAAE,OAAO,EAAE,SAAS;QAC3B,IAAI,EAAE,IAAI;QACV,OAAO,EAAE,OAAO;QAChB,IAAI,EAAE,IAAI;QACV,SAAS,EAAE,MAAM,CAAC,QAAQ,CAAC,SAAS;QACpC,SAAS,EAAE,OAAO,EAAE,SAAS,IAAI,MAAM,CAAC,QAAQ,CAAC,SAAS,IAAI,CAAC,CAAC;KACjE,EAAE,OAAO,CAAC,CAAC;IACZ,IAAI,CAAC,UAAU,CAAC,EAAE,EAAE,CAAC;QACnB,OAAO,CAAC,UAAU,EAAE,EAAE,MAAM,EAAE,SAAS,EAAE,CAAC,CAAC;IAC7C,CAAC;IACD,MAAM,GAAG,GAAG,UAAU,CAAC,KAAK,CAAC;IAE7B,MAAM,QAAQ,GAAG,MAAM,MAAM,CAAC,GAAG,CAAC,GAAG,EAAE;QACrC,OAAO;QACP,iBAAiB,EAAE,CAAC,UAAkB,EAAE,EAAE,CACxC,IAAA,yBAAe,EAAC,EAAE,MAAM,EAAE,UAAU,EAAc,EAAE,CAAC,KAAK,EAAE,KAAK,CAAC,CAAC;QACrE,WAAW,EAAE,OAAO,CAAC,WAAW;QAChC,UAAU,EAAE,OAAO,CAAC,UAAU;KAC/B,CAAC,CAAC;IACH,IAAI,CAAC,QAAQ,CAAC,EAAE,EAAE,CAAC;QACjB,OAAO,CAAC,QAAQ,EAAE,EAAE,MAAM,EAAE,eAAe,EAAE,OAAO,EAAE,GAAG,EAAE,CAAC,CAAC;IAC/D,CAAC;IACD,MAAM,QAAQ,GAAG,QAAQ,CAAC,KAAK,CAAC;IAEhC,MAAM,CAAC,MAAM,CAAC,GAAG,MAAM,CAAC,CAAC,KAAK,CAW5B,CAAC,CAAC,IAAI,CAAC,GAAG,EAAE,UAAU,CAAC,+CAA+C,CAAC,EACvE,CAAC,CAAC,IAAI,CAAC,KAAK,CAAC,EACb,CAAC,CAAC,IAAI,CAAC,KAAK,CAAC,CACd,CAAC,QAAQ,EAAE,GAAG,CAAC,CAAC;IACjB,IAAI,CAAC,MAAM,CAAC,EAAE,EAAE,CAAC;QACf,OAAO,CAAC,MAAM,EAAE,EAAE,MAAM,EAAE,UAAU,EAAE,OAAO,EAAE,GAAG,EAAE,QAAQ,EAAE,CAAC,CAAC;IAClE,CAAC;IAED,OAAO,CAAC,MAAM,EAAE,EAAE,MAAM,EAAE,UAAU,EAAE,OAAO,EAAE,GAAG,EAAE,QAAQ,EAAE,CAAC,CAAC;AAClE,CAAC"}
|
|
@@ -0,0 +1,20 @@
|
|
|
1
|
+
import { SDKCore } from "../core.js";
|
|
2
|
+
import { RequestOptions } from "../lib/sdks.js";
|
|
3
|
+
import * as components from "../models/components/index.js";
|
|
4
|
+
import { ConnectionError, InvalidRequestError, RequestAbortedError, RequestTimeoutError, UnexpectedClientError } from "../models/errors/httpclienterrors.js";
|
|
5
|
+
import { ResponseValidationError } from "../models/errors/responsevalidationerror.js";
|
|
6
|
+
import { SDKError } from "../models/errors/sdkerror.js";
|
|
7
|
+
import { SDKValidationError } from "../models/errors/sdkvalidationerror.js";
|
|
8
|
+
import * as operations from "../models/operations/index.js";
|
|
9
|
+
import { APIPromise } from "../types/async.js";
|
|
10
|
+
import { Result } from "../types/fp.js";
|
|
11
|
+
/**
|
|
12
|
+
* Get an eval run overview
|
|
13
|
+
*
|
|
14
|
+
* @remarks
|
|
15
|
+
* Aggregate header for one run's trials view: trial counts, average reward, cost, and the input/output/cached token split. Its own route rather than fields on the run object because it scans the run's samples — folding it into `GET /evals/runs/{run_id}` would charge that scan to every run list and to the status polling that runs for the whole length of an eval. `trials.errored` overlaps `trials.failed` instead of partitioning it: a coding-agent trial can carry an agent timeout in `error` and still be completed and scored. `trials.retried` counts trials rerun through rerun-failed, read from the pre-rerun snapshot, since a rerun overwrites the sample in place.
|
|
16
|
+
*
|
|
17
|
+
* If set, this operation will use {@link Security.bearerAuth} from the global security.
|
|
18
|
+
*/
|
|
19
|
+
export declare function llmEvalsGetRunOverview(client: SDKCore, request: operations.GetEvalRunOverviewRequest, options?: RequestOptions): APIPromise<Result<components.EvalRunOverview, SDKError | ResponseValidationError | ConnectionError | RequestAbortedError | RequestTimeoutError | InvalidRequestError | UnexpectedClientError | SDKValidationError>>;
|
|
20
|
+
//# sourceMappingURL=llmEvalsGetRunOverview.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"llmEvalsGetRunOverview.d.ts","sourceRoot":"","sources":["../../../src/funcs/llmEvalsGetRunOverview.ts"],"names":[],"mappings":"AAIA,OAAO,EAAE,OAAO,EAAE,MAAM,YAAY,CAAC;AAMrC,OAAO,EAAE,cAAc,EAAE,MAAM,gBAAgB,CAAC;AAGhD,OAAO,KAAK,UAAU,MAAM,+BAA+B,CAAC;AAC5D,OAAO,EACL,eAAe,EACf,mBAAmB,EACnB,mBAAmB,EACnB,mBAAmB,EACnB,qBAAqB,EACtB,MAAM,sCAAsC,CAAC;AAC9C,OAAO,EAAE,uBAAuB,EAAE,MAAM,6CAA6C,CAAC;AACtF,OAAO,EAAE,QAAQ,EAAE,MAAM,8BAA8B,CAAC;AACxD,OAAO,EAAE,kBAAkB,EAAE,MAAM,wCAAwC,CAAC;AAC5E,OAAO,KAAK,UAAU,MAAM,+BAA+B,CAAC;AAC5D,OAAO,EAAW,UAAU,EAAE,MAAM,mBAAmB,CAAC;AACxD,OAAO,EAAE,MAAM,EAAE,MAAM,gBAAgB,CAAC;AAExC;;;;;;;GAOG;AACH,wBAAgB,sBAAsB,CACpC,MAAM,EAAE,OAAO,EACf,OAAO,EAAE,UAAU,CAAC,yBAAyB,EAC7C,OAAO,CAAC,EAAE,cAAc,GACvB,UAAU,CACX,MAAM,CACJ,UAAU,CAAC,eAAe,EACxB,QAAQ,GACR,uBAAuB,GACvB,eAAe,GACf,mBAAmB,GACnB,mBAAmB,GACnB,mBAAmB,GACnB,qBAAqB,GACrB,kBAAkB,CACrB,CACF,CAMA"}
|
|
@@ -0,0 +1,138 @@
|
|
|
1
|
+
"use strict";
|
|
2
|
+
/*
|
|
3
|
+
* Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT.
|
|
4
|
+
*/
|
|
5
|
+
var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
|
|
6
|
+
if (k2 === undefined) k2 = k;
|
|
7
|
+
var desc = Object.getOwnPropertyDescriptor(m, k);
|
|
8
|
+
if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
|
|
9
|
+
desc = { enumerable: true, get: function() { return m[k]; } };
|
|
10
|
+
}
|
|
11
|
+
Object.defineProperty(o, k2, desc);
|
|
12
|
+
}) : (function(o, m, k, k2) {
|
|
13
|
+
if (k2 === undefined) k2 = k;
|
|
14
|
+
o[k2] = m[k];
|
|
15
|
+
}));
|
|
16
|
+
var __setModuleDefault = (this && this.__setModuleDefault) || (Object.create ? (function(o, v) {
|
|
17
|
+
Object.defineProperty(o, "default", { enumerable: true, value: v });
|
|
18
|
+
}) : function(o, v) {
|
|
19
|
+
o["default"] = v;
|
|
20
|
+
});
|
|
21
|
+
var __importStar = (this && this.__importStar) || (function () {
|
|
22
|
+
var ownKeys = function(o) {
|
|
23
|
+
ownKeys = Object.getOwnPropertyNames || function (o) {
|
|
24
|
+
var ar = [];
|
|
25
|
+
for (var k in o) if (Object.prototype.hasOwnProperty.call(o, k)) ar[ar.length] = k;
|
|
26
|
+
return ar;
|
|
27
|
+
};
|
|
28
|
+
return ownKeys(o);
|
|
29
|
+
};
|
|
30
|
+
return function (mod) {
|
|
31
|
+
if (mod && mod.__esModule) return mod;
|
|
32
|
+
var result = {};
|
|
33
|
+
if (mod != null) for (var k = ownKeys(mod), i = 0; i < k.length; i++) if (k[i] !== "default") __createBinding(result, mod, k[i]);
|
|
34
|
+
__setModuleDefault(result, mod);
|
|
35
|
+
return result;
|
|
36
|
+
};
|
|
37
|
+
})();
|
|
38
|
+
Object.defineProperty(exports, "__esModule", { value: true });
|
|
39
|
+
exports.llmEvalsGetRunOverview = llmEvalsGetRunOverview;
|
|
40
|
+
const encodings_js_1 = require("../lib/encodings.js");
|
|
41
|
+
const http_js_1 = require("../lib/http.js");
|
|
42
|
+
const M = __importStar(require("../lib/matchers.js"));
|
|
43
|
+
const primitives_js_1 = require("../lib/primitives.js");
|
|
44
|
+
const schemas_js_1 = require("../lib/schemas.js");
|
|
45
|
+
const security_js_1 = require("../lib/security.js");
|
|
46
|
+
const url_js_1 = require("../lib/url.js");
|
|
47
|
+
const components = __importStar(require("../models/components/index.js"));
|
|
48
|
+
const operations = __importStar(require("../models/operations/index.js"));
|
|
49
|
+
const async_js_1 = require("../types/async.js");
|
|
50
|
+
/**
|
|
51
|
+
* Get an eval run overview
|
|
52
|
+
*
|
|
53
|
+
* @remarks
|
|
54
|
+
* Aggregate header for one run's trials view: trial counts, average reward, cost, and the input/output/cached token split. Its own route rather than fields on the run object because it scans the run's samples — folding it into `GET /evals/runs/{run_id}` would charge that scan to every run list and to the status polling that runs for the whole length of an eval. `trials.errored` overlaps `trials.failed` instead of partitioning it: a coding-agent trial can carry an agent timeout in `error` and still be completed and scored. `trials.retried` counts trials rerun through rerun-failed, read from the pre-rerun snapshot, since a rerun overwrites the sample in place.
|
|
55
|
+
*
|
|
56
|
+
* If set, this operation will use {@link Security.bearerAuth} from the global security.
|
|
57
|
+
*/
|
|
58
|
+
function llmEvalsGetRunOverview(client, request, options) {
|
|
59
|
+
return new async_js_1.APIPromise($do(client, request, options));
|
|
60
|
+
}
|
|
61
|
+
async function $do(client, request, options) {
|
|
62
|
+
const parsed = (0, schemas_js_1.safeParse)(request, (value) => operations.GetEvalRunOverviewRequest$outboundSchema.parse(value), "Input validation failed");
|
|
63
|
+
if (!parsed.ok) {
|
|
64
|
+
return [parsed, { status: "invalid" }];
|
|
65
|
+
}
|
|
66
|
+
const payload = parsed.value;
|
|
67
|
+
const body = null;
|
|
68
|
+
const pathParams = {
|
|
69
|
+
run_id: (0, encodings_js_1.encodeSimple)("run_id", payload.run_id, {
|
|
70
|
+
explode: false,
|
|
71
|
+
charEncoding: "percent",
|
|
72
|
+
}),
|
|
73
|
+
};
|
|
74
|
+
const path = (0, url_js_1.pathToFunc)("/api/v1/llm/evals/runs/{run_id}/overview")(pathParams);
|
|
75
|
+
const query = (0, encodings_js_1.encodeFormQuery)({
|
|
76
|
+
"metric": payload.metric,
|
|
77
|
+
});
|
|
78
|
+
const headers = new Headers((0, primitives_js_1.compactMap)({
|
|
79
|
+
Accept: "application/json",
|
|
80
|
+
"X-On-Behalf-Of": (0, encodings_js_1.encodeSimple)("X-On-Behalf-Of", payload["X-On-Behalf-Of"], { explode: false, charEncoding: "none" }),
|
|
81
|
+
}));
|
|
82
|
+
const secConfig = await (0, security_js_1.extractSecurity)(client._options.bearerAuth);
|
|
83
|
+
const securityInput = secConfig == null ? {} : { bearerAuth: secConfig };
|
|
84
|
+
const requestSecurity = (0, security_js_1.resolveGlobalSecurity)(securityInput, [0]);
|
|
85
|
+
const context = {
|
|
86
|
+
options: client._options,
|
|
87
|
+
baseURL: options?.serverURL ?? client._baseURL ?? "",
|
|
88
|
+
operationID: "getEvalRunOverview",
|
|
89
|
+
oAuth2Scopes: null,
|
|
90
|
+
resolvedSecurity: requestSecurity,
|
|
91
|
+
securitySource: client._options.bearerAuth,
|
|
92
|
+
retryConfig: options?.retries
|
|
93
|
+
|| client._options.retryConfig
|
|
94
|
+
|| {
|
|
95
|
+
strategy: "backoff",
|
|
96
|
+
backoff: {
|
|
97
|
+
initialInterval: 500,
|
|
98
|
+
maxInterval: 5000,
|
|
99
|
+
exponent: 1.5,
|
|
100
|
+
maxElapsedTime: 15000,
|
|
101
|
+
},
|
|
102
|
+
retryConnectionErrors: true,
|
|
103
|
+
}
|
|
104
|
+
|| { strategy: "none" },
|
|
105
|
+
retryCodes: options?.retryCodes || ["429", "500", "502", "503", "504"],
|
|
106
|
+
};
|
|
107
|
+
const requestRes = client._createRequest(context, {
|
|
108
|
+
security: requestSecurity,
|
|
109
|
+
method: "GET",
|
|
110
|
+
baseURL: options?.serverURL,
|
|
111
|
+
path: path,
|
|
112
|
+
headers: headers,
|
|
113
|
+
query: query,
|
|
114
|
+
body: body,
|
|
115
|
+
userAgent: client._options.userAgent,
|
|
116
|
+
timeoutMs: options?.timeoutMs || client._options.timeoutMs || -1,
|
|
117
|
+
}, options);
|
|
118
|
+
if (!requestRes.ok) {
|
|
119
|
+
return [requestRes, { status: "invalid" }];
|
|
120
|
+
}
|
|
121
|
+
const req = requestRes.value;
|
|
122
|
+
const doResult = await client._do(req, {
|
|
123
|
+
context,
|
|
124
|
+
isErrorStatusCode: (statusCode) => (0, http_js_1.matchStatusCode)({ status: statusCode }, ["4XX", "5XX"]),
|
|
125
|
+
retryConfig: context.retryConfig,
|
|
126
|
+
retryCodes: context.retryCodes,
|
|
127
|
+
});
|
|
128
|
+
if (!doResult.ok) {
|
|
129
|
+
return [doResult, { status: "request-error", request: req }];
|
|
130
|
+
}
|
|
131
|
+
const response = doResult.value;
|
|
132
|
+
const [result] = await M.match(M.json(200, components.EvalRunOverview$inboundSchema), M.fail("4XX"), M.fail("5XX"))(response, req);
|
|
133
|
+
if (!result.ok) {
|
|
134
|
+
return [result, { status: "complete", request: req, response }];
|
|
135
|
+
}
|
|
136
|
+
return [result, { status: "complete", request: req, response }];
|
|
137
|
+
}
|
|
138
|
+
//# sourceMappingURL=llmEvalsGetRunOverview.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"llmEvalsGetRunOverview.js","sourceRoot":"","sources":["../../../src/funcs/llmEvalsGetRunOverview.ts"],"names":[],"mappings":";AAAA;;GAEG;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;AAkCH,wDAsBC;AArDD,sDAAoE;AACpE,4CAAiD;AACjD,sDAAwC;AACxC,wDAAkD;AAClD,kDAA8C;AAE9C,oDAA4E;AAC5E,0CAA2C;AAC3C,0EAA4D;AAW5D,0EAA4D;AAC5D,gDAAwD;AAGxD;;;;;;;GAOG;AACH,SAAgB,sBAAsB,CACpC,MAAe,EACf,OAA6C,EAC7C,OAAwB;IAcxB,OAAO,IAAI,qBAAU,CAAC,GAAG,CACvB,MAAM,EACN,OAAO,EACP,OAAO,CACR,CAAC,CAAC;AACL,CAAC;AAED,KAAK,UAAU,GAAG,CAChB,MAAe,EACf,OAA6C,EAC7C,OAAwB;IAiBxB,MAAM,MAAM,GAAG,IAAA,sBAAS,EACtB,OAAO,EACP,CAAC,KAAK,EAAE,EAAE,CAAC,UAAU,CAAC,wCAAwC,CAAC,KAAK,CAAC,KAAK,CAAC,EAC3E,yBAAyB,CAC1B,CAAC;IACF,IAAI,CAAC,MAAM,CAAC,EAAE,EAAE,CAAC;QACf,OAAO,CAAC,MAAM,EAAE,EAAE,MAAM,EAAE,SAAS,EAAE,CAAC,CAAC;IACzC,CAAC;IACD,MAAM,OAAO,GAAG,MAAM,CAAC,KAAK,CAAC;IAC7B,MAAM,IAAI,GAAG,IAAI,CAAC;IAElB,MAAM,UAAU,GAAG;QACjB,MAAM,EAAE,IAAA,2BAAY,EAAC,QAAQ,EAAE,OAAO,CAAC,MAAM,EAAE;YAC7C,OAAO,EAAE,KAAK;YACd,YAAY,EAAE,SAAS;SACxB,CAAC;KACH,CAAC;IACF,MAAM,IAAI,GAAG,IAAA,mBAAU,EAAC,0CAA0C,CAAC,CACjE,UAAU,CACX,CAAC;IAEF,MAAM,KAAK,GAAG,IAAA,8BAAe,EAAC;QAC5B,QAAQ,EAAE,OAAO,CAAC,MAAM;KACzB,CAAC,CAAC;IAEH,MAAM,OAAO,GAAG,IAAI,OAAO,CAAC,IAAA,0BAAU,EAAC;QACrC,MAAM,EAAE,kBAAkB;QAC1B,gBAAgB,EAAE,IAAA,2BAAY,EAC5B,gBAAgB,EAChB,OAAO,CAAC,gBAAgB,CAAC,EACzB,EAAE,OAAO,EAAE,KAAK,EAAE,YAAY,EAAE,MAAM,EAAE,CACzC;KACF,CAAC,CAAC,CAAC;IAEJ,MAAM,SAAS,GAAG,MAAM,IAAA,6BAAe,EAAC,MAAM,CAAC,QAAQ,CAAC,UAAU,CAAC,CAAC;IACpE,MAAM,aAAa,GAAG,SAAS,IAAI,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,EAAE,UAAU,EAAE,SAAS,EAAE,CAAC;IACzE,MAAM,eAAe,GAAG,IAAA,mCAAqB,EAAC,aAAa,EAAE,CAAC,CAAC,CAAC,CAAC,CAAC;IAElE,MAAM,OAAO,GAAG;QACd,OAAO,EAAE,MAAM,CAAC,QAAQ;QACxB,OAAO,EAAE,OAAO,EAAE,SAAS,IAAI,MAAM,CAAC,QAAQ,IAAI,EAAE;QACpD,WAAW,EAAE,oBAAoB;QACjC,YAAY,EAAE,IAAI;QAElB,gBAAgB,EAAE,eAAe;QAEjC,cAAc,EAAE,MAAM,CAAC,QAAQ,CAAC,UAAU;QAC1C,WAAW,EAAE,OAAO,EAAE,OAAO;eACxB,MAAM,CAAC,QAAQ,CAAC,WAAW;eAC3B;gBACD,QAAQ,EAAE,SAAS;gBACnB,OAAO,EAAE;oBACP,eAAe,EAAE,GAAG;oBACpB,WAAW,EAAE,IAAI;oBACjB,QAAQ,EAAE,GAAG;oBACb,cAAc,EAAE,KAAK;iBACtB;gBACD,qBAAqB,EAAE,IAAI;aAC5B;eACE,EAAE,QAAQ,EAAE,MAAM,EAAE;QACzB,UAAU,EAAE,OAAO,EAAE,UAAU,IAAI,CAAC,KAAK,EAAE,KAAK,EAAE,KAAK,EAAE,KAAK,EAAE,KAAK,CAAC;KACvE,CAAC;IAEF,MAAM,UAAU,GAAG,MAAM,CAAC,cAAc,CAAC,OAAO,EAAE;QAChD,QAAQ,EAAE,eAAe;QACzB,MAAM,EAAE,KAAK;QACb,OAAO,EAAE,OAAO,EAAE,SAAS;QAC3B,IAAI,EAAE,IAAI;QACV,OAAO,EAAE,OAAO;QAChB,KAAK,EAAE,KAAK;QACZ,IAAI,EAAE,IAAI;QACV,SAAS,EAAE,MAAM,CAAC,QAAQ,CAAC,SAAS;QACpC,SAAS,EAAE,OAAO,EAAE,SAAS,IAAI,MAAM,CAAC,QAAQ,CAAC,SAAS,IAAI,CAAC,CAAC;KACjE,EAAE,OAAO,CAAC,CAAC;IACZ,IAAI,CAAC,UAAU,CAAC,EAAE,EAAE,CAAC;QACnB,OAAO,CAAC,UAAU,EAAE,EAAE,MAAM,EAAE,SAAS,EAAE,CAAC,CAAC;IAC7C,CAAC;IACD,MAAM,GAAG,GAAG,UAAU,CAAC,KAAK,CAAC;IAE7B,MAAM,QAAQ,GAAG,MAAM,MAAM,CAAC,GAAG,CAAC,GAAG,EAAE;QACrC,OAAO;QACP,iBAAiB,EAAE,CAAC,UAAkB,EAAE,EAAE,CACxC,IAAA,yBAAe,EAAC,EAAE,MAAM,EAAE,UAAU,EAAc,EAAE,CAAC,KAAK,EAAE,KAAK,CAAC,CAAC;QACrE,WAAW,EAAE,OAAO,CAAC,WAAW;QAChC,UAAU,EAAE,OAAO,CAAC,UAAU;KAC/B,CAAC,CAAC;IACH,IAAI,CAAC,QAAQ,CAAC,EAAE,EAAE,CAAC;QACjB,OAAO,CAAC,QAAQ,EAAE,EAAE,MAAM,EAAE,eAAe,EAAE,OAAO,EAAE,GAAG,EAAE,CAAC,CAAC;IAC/D,CAAC;IACD,MAAM,QAAQ,GAAG,QAAQ,CAAC,KAAK,CAAC;IAEhC,MAAM,CAAC,MAAM,CAAC,GAAG,MAAM,CAAC,CAAC,KAAK,CAW5B,CAAC,CAAC,IAAI,CAAC,GAAG,EAAE,UAAU,CAAC,6BAA6B,CAAC,EACrD,CAAC,CAAC,IAAI,CAAC,KAAK,CAAC,EACb,CAAC,CAAC,IAAI,CAAC,KAAK,CAAC,CACd,CAAC,QAAQ,EAAE,GAAG,CAAC,CAAC;IACjB,IAAI,CAAC,MAAM,CAAC,EAAE,EAAE,CAAC;QACf,OAAO,CAAC,MAAM,EAAE,EAAE,MAAM,EAAE,UAAU,EAAE,OAAO,EAAE,GAAG,EAAE,QAAQ,EAAE,CAAC,CAAC;IAClE,CAAC;IAED,OAAO,CAAC,MAAM,EAAE,EAAE,MAAM,EAAE,UAAU,EAAE,OAAO,EAAE,GAAG,EAAE,QAAQ,EAAE,CAAC,CAAC;AAClE,CAAC"}
|
|
@@ -0,0 +1,19 @@
|
|
|
1
|
+
import { SDKCore } from "../core.js";
|
|
2
|
+
import { RequestOptions } from "../lib/sdks.js";
|
|
3
|
+
import { ConnectionError, InvalidRequestError, RequestAbortedError, RequestTimeoutError, UnexpectedClientError } from "../models/errors/httpclienterrors.js";
|
|
4
|
+
import { ResponseValidationError } from "../models/errors/responsevalidationerror.js";
|
|
5
|
+
import { SDKError } from "../models/errors/sdkerror.js";
|
|
6
|
+
import { SDKValidationError } from "../models/errors/sdkvalidationerror.js";
|
|
7
|
+
import * as operations from "../models/operations/index.js";
|
|
8
|
+
import { APIPromise } from "../types/async.js";
|
|
9
|
+
import { Result } from "../types/fp.js";
|
|
10
|
+
/**
|
|
11
|
+
* Get an eval sample trajectory
|
|
12
|
+
*
|
|
13
|
+
* @remarks
|
|
14
|
+
* Returns one coding-agent trial's session — the steps the agent took, verbatim in the harness's interchange format (see `schema_version`, e.g. `ATIF-v1.7`). Deliberately not part of the samples list: a trajectory averages ~92 KB and that list pages up to 500 rows. Sample indices are unique per (task, model), not per run, so pass `task_id` and/or `model` when the run covers more than one; an index that matches several trials returns 400 rather than guessing, and never falls back to another trial's session. Returns 404 when the sample does not exist or recorded no trajectory.
|
|
15
|
+
*
|
|
16
|
+
* If set, this operation will use {@link Security.bearerAuth} from the global security.
|
|
17
|
+
*/
|
|
18
|
+
export declare function llmEvalsGetSampleTrajectory(client: SDKCore, request: operations.GetEvalSampleTrajectoryRequest, options?: RequestOptions): APIPromise<Result<operations.GetEvalSampleTrajectoryResponseBody, SDKError | ResponseValidationError | ConnectionError | RequestAbortedError | RequestTimeoutError | InvalidRequestError | UnexpectedClientError | SDKValidationError>>;
|
|
19
|
+
//# sourceMappingURL=llmEvalsGetSampleTrajectory.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"llmEvalsGetSampleTrajectory.d.ts","sourceRoot":"","sources":["../../../src/funcs/llmEvalsGetSampleTrajectory.ts"],"names":[],"mappings":"AAIA,OAAO,EAAE,OAAO,EAAE,MAAM,YAAY,CAAC;AAMrC,OAAO,EAAE,cAAc,EAAE,MAAM,gBAAgB,CAAC;AAGhD,OAAO,EACL,eAAe,EACf,mBAAmB,EACnB,mBAAmB,EACnB,mBAAmB,EACnB,qBAAqB,EACtB,MAAM,sCAAsC,CAAC;AAC9C,OAAO,EAAE,uBAAuB,EAAE,MAAM,6CAA6C,CAAC;AACtF,OAAO,EAAE,QAAQ,EAAE,MAAM,8BAA8B,CAAC;AACxD,OAAO,EAAE,kBAAkB,EAAE,MAAM,wCAAwC,CAAC;AAC5E,OAAO,KAAK,UAAU,MAAM,+BAA+B,CAAC;AAC5D,OAAO,EAAW,UAAU,EAAE,MAAM,mBAAmB,CAAC;AACxD,OAAO,EAAE,MAAM,EAAE,MAAM,gBAAgB,CAAC;AAExC;;;;;;;GAOG;AACH,wBAAgB,2BAA2B,CACzC,MAAM,EAAE,OAAO,EACf,OAAO,EAAE,UAAU,CAAC,8BAA8B,EAClD,OAAO,CAAC,EAAE,cAAc,GACvB,UAAU,CACX,MAAM,CACJ,UAAU,CAAC,mCAAmC,EAC5C,QAAQ,GACR,uBAAuB,GACvB,eAAe,GACf,mBAAmB,GACnB,mBAAmB,GACnB,mBAAmB,GACnB,qBAAqB,GACrB,kBAAkB,CACrB,CACF,CAMA"}
|
|
@@ -0,0 +1,142 @@
|
|
|
1
|
+
"use strict";
|
|
2
|
+
/*
|
|
3
|
+
* Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT.
|
|
4
|
+
*/
|
|
5
|
+
var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
|
|
6
|
+
if (k2 === undefined) k2 = k;
|
|
7
|
+
var desc = Object.getOwnPropertyDescriptor(m, k);
|
|
8
|
+
if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
|
|
9
|
+
desc = { enumerable: true, get: function() { return m[k]; } };
|
|
10
|
+
}
|
|
11
|
+
Object.defineProperty(o, k2, desc);
|
|
12
|
+
}) : (function(o, m, k, k2) {
|
|
13
|
+
if (k2 === undefined) k2 = k;
|
|
14
|
+
o[k2] = m[k];
|
|
15
|
+
}));
|
|
16
|
+
var __setModuleDefault = (this && this.__setModuleDefault) || (Object.create ? (function(o, v) {
|
|
17
|
+
Object.defineProperty(o, "default", { enumerable: true, value: v });
|
|
18
|
+
}) : function(o, v) {
|
|
19
|
+
o["default"] = v;
|
|
20
|
+
});
|
|
21
|
+
var __importStar = (this && this.__importStar) || (function () {
|
|
22
|
+
var ownKeys = function(o) {
|
|
23
|
+
ownKeys = Object.getOwnPropertyNames || function (o) {
|
|
24
|
+
var ar = [];
|
|
25
|
+
for (var k in o) if (Object.prototype.hasOwnProperty.call(o, k)) ar[ar.length] = k;
|
|
26
|
+
return ar;
|
|
27
|
+
};
|
|
28
|
+
return ownKeys(o);
|
|
29
|
+
};
|
|
30
|
+
return function (mod) {
|
|
31
|
+
if (mod && mod.__esModule) return mod;
|
|
32
|
+
var result = {};
|
|
33
|
+
if (mod != null) for (var k = ownKeys(mod), i = 0; i < k.length; i++) if (k[i] !== "default") __createBinding(result, mod, k[i]);
|
|
34
|
+
__setModuleDefault(result, mod);
|
|
35
|
+
return result;
|
|
36
|
+
};
|
|
37
|
+
})();
|
|
38
|
+
Object.defineProperty(exports, "__esModule", { value: true });
|
|
39
|
+
exports.llmEvalsGetSampleTrajectory = llmEvalsGetSampleTrajectory;
|
|
40
|
+
const encodings_js_1 = require("../lib/encodings.js");
|
|
41
|
+
const http_js_1 = require("../lib/http.js");
|
|
42
|
+
const M = __importStar(require("../lib/matchers.js"));
|
|
43
|
+
const primitives_js_1 = require("../lib/primitives.js");
|
|
44
|
+
const schemas_js_1 = require("../lib/schemas.js");
|
|
45
|
+
const security_js_1 = require("../lib/security.js");
|
|
46
|
+
const url_js_1 = require("../lib/url.js");
|
|
47
|
+
const operations = __importStar(require("../models/operations/index.js"));
|
|
48
|
+
const async_js_1 = require("../types/async.js");
|
|
49
|
+
/**
|
|
50
|
+
* Get an eval sample trajectory
|
|
51
|
+
*
|
|
52
|
+
* @remarks
|
|
53
|
+
* Returns one coding-agent trial's session — the steps the agent took, verbatim in the harness's interchange format (see `schema_version`, e.g. `ATIF-v1.7`). Deliberately not part of the samples list: a trajectory averages ~92 KB and that list pages up to 500 rows. Sample indices are unique per (task, model), not per run, so pass `task_id` and/or `model` when the run covers more than one; an index that matches several trials returns 400 rather than guessing, and never falls back to another trial's session. Returns 404 when the sample does not exist or recorded no trajectory.
|
|
54
|
+
*
|
|
55
|
+
* If set, this operation will use {@link Security.bearerAuth} from the global security.
|
|
56
|
+
*/
|
|
57
|
+
function llmEvalsGetSampleTrajectory(client, request, options) {
|
|
58
|
+
return new async_js_1.APIPromise($do(client, request, options));
|
|
59
|
+
}
|
|
60
|
+
async function $do(client, request, options) {
|
|
61
|
+
const parsed = (0, schemas_js_1.safeParse)(request, (value) => operations.GetEvalSampleTrajectoryRequest$outboundSchema.parse(value), "Input validation failed");
|
|
62
|
+
if (!parsed.ok) {
|
|
63
|
+
return [parsed, { status: "invalid" }];
|
|
64
|
+
}
|
|
65
|
+
const payload = parsed.value;
|
|
66
|
+
const body = null;
|
|
67
|
+
const pathParams = {
|
|
68
|
+
run_id: (0, encodings_js_1.encodeSimple)("run_id", payload.run_id, {
|
|
69
|
+
explode: false,
|
|
70
|
+
charEncoding: "percent",
|
|
71
|
+
}),
|
|
72
|
+
sample_index: (0, encodings_js_1.encodeSimple)("sample_index", payload.sample_index, {
|
|
73
|
+
explode: false,
|
|
74
|
+
charEncoding: "percent",
|
|
75
|
+
}),
|
|
76
|
+
};
|
|
77
|
+
const path = (0, url_js_1.pathToFunc)("/api/v1/llm/evals/runs/{run_id}/samples/{sample_index}/trajectory")(pathParams);
|
|
78
|
+
const query = (0, encodings_js_1.encodeFormQuery)({
|
|
79
|
+
"model": payload.model,
|
|
80
|
+
"task_id": payload.task_id,
|
|
81
|
+
});
|
|
82
|
+
const headers = new Headers((0, primitives_js_1.compactMap)({
|
|
83
|
+
Accept: "application/json",
|
|
84
|
+
"X-On-Behalf-Of": (0, encodings_js_1.encodeSimple)("X-On-Behalf-Of", payload["X-On-Behalf-Of"], { explode: false, charEncoding: "none" }),
|
|
85
|
+
}));
|
|
86
|
+
const secConfig = await (0, security_js_1.extractSecurity)(client._options.bearerAuth);
|
|
87
|
+
const securityInput = secConfig == null ? {} : { bearerAuth: secConfig };
|
|
88
|
+
const requestSecurity = (0, security_js_1.resolveGlobalSecurity)(securityInput, [0]);
|
|
89
|
+
const context = {
|
|
90
|
+
options: client._options,
|
|
91
|
+
baseURL: options?.serverURL ?? client._baseURL ?? "",
|
|
92
|
+
operationID: "getEvalSampleTrajectory",
|
|
93
|
+
oAuth2Scopes: null,
|
|
94
|
+
resolvedSecurity: requestSecurity,
|
|
95
|
+
securitySource: client._options.bearerAuth,
|
|
96
|
+
retryConfig: options?.retries
|
|
97
|
+
|| client._options.retryConfig
|
|
98
|
+
|| {
|
|
99
|
+
strategy: "backoff",
|
|
100
|
+
backoff: {
|
|
101
|
+
initialInterval: 500,
|
|
102
|
+
maxInterval: 5000,
|
|
103
|
+
exponent: 1.5,
|
|
104
|
+
maxElapsedTime: 15000,
|
|
105
|
+
},
|
|
106
|
+
retryConnectionErrors: true,
|
|
107
|
+
}
|
|
108
|
+
|| { strategy: "none" },
|
|
109
|
+
retryCodes: options?.retryCodes || ["429", "500", "502", "503", "504"],
|
|
110
|
+
};
|
|
111
|
+
const requestRes = client._createRequest(context, {
|
|
112
|
+
security: requestSecurity,
|
|
113
|
+
method: "GET",
|
|
114
|
+
baseURL: options?.serverURL,
|
|
115
|
+
path: path,
|
|
116
|
+
headers: headers,
|
|
117
|
+
query: query,
|
|
118
|
+
body: body,
|
|
119
|
+
userAgent: client._options.userAgent,
|
|
120
|
+
timeoutMs: options?.timeoutMs || client._options.timeoutMs || -1,
|
|
121
|
+
}, options);
|
|
122
|
+
if (!requestRes.ok) {
|
|
123
|
+
return [requestRes, { status: "invalid" }];
|
|
124
|
+
}
|
|
125
|
+
const req = requestRes.value;
|
|
126
|
+
const doResult = await client._do(req, {
|
|
127
|
+
context,
|
|
128
|
+
isErrorStatusCode: (statusCode) => (0, http_js_1.matchStatusCode)({ status: statusCode }, ["4XX", "5XX"]),
|
|
129
|
+
retryConfig: context.retryConfig,
|
|
130
|
+
retryCodes: context.retryCodes,
|
|
131
|
+
});
|
|
132
|
+
if (!doResult.ok) {
|
|
133
|
+
return [doResult, { status: "request-error", request: req }];
|
|
134
|
+
}
|
|
135
|
+
const response = doResult.value;
|
|
136
|
+
const [result] = await M.match(M.json(200, operations.GetEvalSampleTrajectoryResponseBody$inboundSchema), M.fail("4XX"), M.fail("5XX"))(response, req);
|
|
137
|
+
if (!result.ok) {
|
|
138
|
+
return [result, { status: "complete", request: req, response }];
|
|
139
|
+
}
|
|
140
|
+
return [result, { status: "complete", request: req, response }];
|
|
141
|
+
}
|
|
142
|
+
//# sourceMappingURL=llmEvalsGetSampleTrajectory.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"llmEvalsGetSampleTrajectory.js","sourceRoot":"","sources":["../../../src/funcs/llmEvalsGetSampleTrajectory.ts"],"names":[],"mappings":";AAAA;;GAEG;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;AAiCH,kEAsBC;AApDD,sDAAoE;AACpE,4CAAiD;AACjD,sDAAwC;AACxC,wDAAkD;AAClD,kDAA8C;AAE9C,oDAA4E;AAC5E,0CAA2C;AAW3C,0EAA4D;AAC5D,gDAAwD;AAGxD;;;;;;;GAOG;AACH,SAAgB,2BAA2B,CACzC,MAAe,EACf,OAAkD,EAClD,OAAwB;IAcxB,OAAO,IAAI,qBAAU,CAAC,GAAG,CACvB,MAAM,EACN,OAAO,EACP,OAAO,CACR,CAAC,CAAC;AACL,CAAC;AAED,KAAK,UAAU,GAAG,CAChB,MAAe,EACf,OAAkD,EAClD,OAAwB;IAiBxB,MAAM,MAAM,GAAG,IAAA,sBAAS,EACtB,OAAO,EACP,CAAC,KAAK,EAAE,EAAE,CACR,UAAU,CAAC,6CAA6C,CAAC,KAAK,CAAC,KAAK,CAAC,EACvE,yBAAyB,CAC1B,CAAC;IACF,IAAI,CAAC,MAAM,CAAC,EAAE,EAAE,CAAC;QACf,OAAO,CAAC,MAAM,EAAE,EAAE,MAAM,EAAE,SAAS,EAAE,CAAC,CAAC;IACzC,CAAC;IACD,MAAM,OAAO,GAAG,MAAM,CAAC,KAAK,CAAC;IAC7B,MAAM,IAAI,GAAG,IAAI,CAAC;IAElB,MAAM,UAAU,GAAG;QACjB,MAAM,EAAE,IAAA,2BAAY,EAAC,QAAQ,EAAE,OAAO,CAAC,MAAM,EAAE;YAC7C,OAAO,EAAE,KAAK;YACd,YAAY,EAAE,SAAS;SACxB,CAAC;QACF,YAAY,EAAE,IAAA,2BAAY,EAAC,cAAc,EAAE,OAAO,CAAC,YAAY,EAAE;YAC/D,OAAO,EAAE,KAAK;YACd,YAAY,EAAE,SAAS;SACxB,CAAC;KACH,CAAC;IACF,MAAM,IAAI,GAAG,IAAA,mBAAU,EACrB,mEAAmE,CACpE,CAAC,UAAU,CAAC,CAAC;IAEd,MAAM,KAAK,GAAG,IAAA,8BAAe,EAAC;QAC5B,OAAO,EAAE,OAAO,CAAC,KAAK;QACtB,SAAS,EAAE,OAAO,CAAC,OAAO;KAC3B,CAAC,CAAC;IAEH,MAAM,OAAO,GAAG,IAAI,OAAO,CAAC,IAAA,0BAAU,EAAC;QACrC,MAAM,EAAE,kBAAkB;QAC1B,gBAAgB,EAAE,IAAA,2BAAY,EAC5B,gBAAgB,EAChB,OAAO,CAAC,gBAAgB,CAAC,EACzB,EAAE,OAAO,EAAE,KAAK,EAAE,YAAY,EAAE,MAAM,EAAE,CACzC;KACF,CAAC,CAAC,CAAC;IAEJ,MAAM,SAAS,GAAG,MAAM,IAAA,6BAAe,EAAC,MAAM,CAAC,QAAQ,CAAC,UAAU,CAAC,CAAC;IACpE,MAAM,aAAa,GAAG,SAAS,IAAI,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,EAAE,UAAU,EAAE,SAAS,EAAE,CAAC;IACzE,MAAM,eAAe,GAAG,IAAA,mCAAqB,EAAC,aAAa,EAAE,CAAC,CAAC,CAAC,CAAC,CAAC;IAElE,MAAM,OAAO,GAAG;QACd,OAAO,EAAE,MAAM,CAAC,QAAQ;QACxB,OAAO,EAAE,OAAO,EAAE,SAAS,IAAI,MAAM,CAAC,QAAQ,IAAI,EAAE;QACpD,WAAW,EAAE,yBAAyB;QACtC,YAAY,EAAE,IAAI;QAElB,gBAAgB,EAAE,eAAe;QAEjC,cAAc,EAAE,MAAM,CAAC,QAAQ,CAAC,UAAU;QAC1C,WAAW,EAAE,OAAO,EAAE,OAAO;eACxB,MAAM,CAAC,QAAQ,CAAC,WAAW;eAC3B;gBACD,QAAQ,EAAE,SAAS;gBACnB,OAAO,EAAE;oBACP,eAAe,EAAE,GAAG;oBACpB,WAAW,EAAE,IAAI;oBACjB,QAAQ,EAAE,GAAG;oBACb,cAAc,EAAE,KAAK;iBACtB;gBACD,qBAAqB,EAAE,IAAI;aAC5B;eACE,EAAE,QAAQ,EAAE,MAAM,EAAE;QACzB,UAAU,EAAE,OAAO,EAAE,UAAU,IAAI,CAAC,KAAK,EAAE,KAAK,EAAE,KAAK,EAAE,KAAK,EAAE,KAAK,CAAC;KACvE,CAAC;IAEF,MAAM,UAAU,GAAG,MAAM,CAAC,cAAc,CAAC,OAAO,EAAE;QAChD,QAAQ,EAAE,eAAe;QACzB,MAAM,EAAE,KAAK;QACb,OAAO,EAAE,OAAO,EAAE,SAAS;QAC3B,IAAI,EAAE,IAAI;QACV,OAAO,EAAE,OAAO;QAChB,KAAK,EAAE,KAAK;QACZ,IAAI,EAAE,IAAI;QACV,SAAS,EAAE,MAAM,CAAC,QAAQ,CAAC,SAAS;QACpC,SAAS,EAAE,OAAO,EAAE,SAAS,IAAI,MAAM,CAAC,QAAQ,CAAC,SAAS,IAAI,CAAC,CAAC;KACjE,EAAE,OAAO,CAAC,CAAC;IACZ,IAAI,CAAC,UAAU,CAAC,EAAE,EAAE,CAAC;QACnB,OAAO,CAAC,UAAU,EAAE,EAAE,MAAM,EAAE,SAAS,EAAE,CAAC,CAAC;IAC7C,CAAC;IACD,MAAM,GAAG,GAAG,UAAU,CAAC,KAAK,CAAC;IAE7B,MAAM,QAAQ,GAAG,MAAM,MAAM,CAAC,GAAG,CAAC,GAAG,EAAE;QACrC,OAAO;QACP,iBAAiB,EAAE,CAAC,UAAkB,EAAE,EAAE,CACxC,IAAA,yBAAe,EAAC,EAAE,MAAM,EAAE,UAAU,EAAc,EAAE,CAAC,KAAK,EAAE,KAAK,CAAC,CAAC;QACrE,WAAW,EAAE,OAAO,CAAC,WAAW;QAChC,UAAU,EAAE,OAAO,CAAC,UAAU;KAC/B,CAAC,CAAC;IACH,IAAI,CAAC,QAAQ,CAAC,EAAE,EAAE,CAAC;QACjB,OAAO,CAAC,QAAQ,EAAE,EAAE,MAAM,EAAE,eAAe,EAAE,OAAO,EAAE,GAAG,EAAE,CAAC,CAAC;IAC/D,CAAC;IACD,MAAM,QAAQ,GAAG,QAAQ,CAAC,KAAK,CAAC;IAEhC,MAAM,CAAC,MAAM,CAAC,GAAG,MAAM,CAAC,CAAC,KAAK,CAW5B,CAAC,CAAC,IAAI,CAAC,GAAG,EAAE,UAAU,CAAC,iDAAiD,CAAC,EACzE,CAAC,CAAC,IAAI,CAAC,KAAK,CAAC,EACb,CAAC,CAAC,IAAI,CAAC,KAAK,CAAC,CACd,CAAC,QAAQ,EAAE,GAAG,CAAC,CAAC;IACjB,IAAI,CAAC,MAAM,CAAC,EAAE,EAAE,CAAC;QACf,OAAO,CAAC,MAAM,EAAE,EAAE,MAAM,EAAE,UAAU,EAAE,OAAO,EAAE,GAAG,EAAE,QAAQ,EAAE,CAAC,CAAC;IAClE,CAAC;IAED,OAAO,CAAC,MAAM,EAAE,EAAE,MAAM,EAAE,UAAU,EAAE,OAAO,EAAE,GAAG,EAAE,QAAQ,EAAE,CAAC,CAAC;AAClE,CAAC"}
|
|
@@ -0,0 +1,20 @@
|
|
|
1
|
+
import { SDKCore } from "../core.js";
|
|
2
|
+
import { RequestOptions } from "../lib/sdks.js";
|
|
3
|
+
import * as components from "../models/components/index.js";
|
|
4
|
+
import { ConnectionError, InvalidRequestError, RequestAbortedError, RequestTimeoutError, UnexpectedClientError } from "../models/errors/httpclienterrors.js";
|
|
5
|
+
import { ResponseValidationError } from "../models/errors/responsevalidationerror.js";
|
|
6
|
+
import { SDKError } from "../models/errors/sdkerror.js";
|
|
7
|
+
import { SDKValidationError } from "../models/errors/sdkvalidationerror.js";
|
|
8
|
+
import * as operations from "../models/operations/index.js";
|
|
9
|
+
import { APIPromise } from "../types/async.js";
|
|
10
|
+
import { Result } from "../types/fp.js";
|
|
11
|
+
/**
|
|
12
|
+
* Get the coding-agent leaderboard for an eval suite
|
|
13
|
+
*
|
|
14
|
+
* @remarks
|
|
15
|
+
* Ranks the suite's completed coding-agent runs, one row per (agent, model, effort). Only runs that recorded an `agent_name` participate — a QA or transcription run of the same suite has no agent to attribute a score to and is not a board row. `accuracy` is the mean of `metric` (default `reward`) over the row's scored trials, and `accuracy_ci` is the 95% Wald interval around it; both are derived per request rather than stored, so rerunning a failed trial moves them instead of leaving a stale copy behind. `agent_version` is reported but is not part of the row identity, so an agent upgrade does not split a row in two. Rows are ordered by accuracy descending, nulls last. Pass `suite_version` when the suite has more than one, otherwise the board mixes task sets.
|
|
16
|
+
*
|
|
17
|
+
* If set, this operation will use {@link Security.bearerAuth} from the global security.
|
|
18
|
+
*/
|
|
19
|
+
export declare function llmEvalsGetSuiteLeaderboard(client: SDKCore, request: operations.GetEvalSuiteLeaderboardRequest, options?: RequestOptions): APIPromise<Result<components.EvalSuiteLeaderboard, SDKError | ResponseValidationError | ConnectionError | RequestAbortedError | RequestTimeoutError | InvalidRequestError | UnexpectedClientError | SDKValidationError>>;
|
|
20
|
+
//# sourceMappingURL=llmEvalsGetSuiteLeaderboard.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"llmEvalsGetSuiteLeaderboard.d.ts","sourceRoot":"","sources":["../../../src/funcs/llmEvalsGetSuiteLeaderboard.ts"],"names":[],"mappings":"AAIA,OAAO,EAAE,OAAO,EAAE,MAAM,YAAY,CAAC;AAMrC,OAAO,EAAE,cAAc,EAAE,MAAM,gBAAgB,CAAC;AAGhD,OAAO,KAAK,UAAU,MAAM,+BAA+B,CAAC;AAC5D,OAAO,EACL,eAAe,EACf,mBAAmB,EACnB,mBAAmB,EACnB,mBAAmB,EACnB,qBAAqB,EACtB,MAAM,sCAAsC,CAAC;AAC9C,OAAO,EAAE,uBAAuB,EAAE,MAAM,6CAA6C,CAAC;AACtF,OAAO,EAAE,QAAQ,EAAE,MAAM,8BAA8B,CAAC;AACxD,OAAO,EAAE,kBAAkB,EAAE,MAAM,wCAAwC,CAAC;AAC5E,OAAO,KAAK,UAAU,MAAM,+BAA+B,CAAC;AAC5D,OAAO,EAAW,UAAU,EAAE,MAAM,mBAAmB,CAAC;AACxD,OAAO,EAAE,MAAM,EAAE,MAAM,gBAAgB,CAAC;AAExC;;;;;;;GAOG;AACH,wBAAgB,2BAA2B,CACzC,MAAM,EAAE,OAAO,EACf,OAAO,EAAE,UAAU,CAAC,8BAA8B,EAClD,OAAO,CAAC,EAAE,cAAc,GACvB,UAAU,CACX,MAAM,CACJ,UAAU,CAAC,oBAAoB,EAC7B,QAAQ,GACR,uBAAuB,GACvB,eAAe,GACf,mBAAmB,GACnB,mBAAmB,GACnB,mBAAmB,GACnB,qBAAqB,GACrB,kBAAkB,CACrB,CACF,CAMA"}
|