@tangle-network/agent-eval 1.0.19 → 1.0.21
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/CHANGELOG.md +19 -27
- package/dist/adapters/http.d.ts +2 -2
- package/dist/{agent-profile-CPv4tENR.d.ts → agent-profile-BO8ruI6R.d.ts} +3 -3
- package/dist/{agent-profile-CPv4tENR.d.ts.map → agent-profile-BO8ruI6R.d.ts.map} +1 -1
- package/dist/analyst/index.d.ts +14 -14
- package/dist/analyst/index.js +11 -12
- package/dist/analyst/index.js.map +1 -1
- package/dist/{analyze-runs-pJ4fhnYg.d.ts → analyze-runs-DYYe18Gw.d.ts} +4 -4
- package/dist/{analyze-runs-pJ4fhnYg.d.ts.map → analyze-runs-DYYe18Gw.d.ts.map} +1 -1
- package/dist/{analyze-runs-C7vWBDhl.js → analyze-runs-jLTRKuoK.js} +6 -110
- package/dist/analyze-runs-jLTRKuoK.js.map +1 -0
- package/dist/app-grade/index.d.ts +4 -4
- package/dist/app-grade/index.js +3 -3
- package/dist/{benchmark-command-DSJQeYom.js → benchmark-command-CoNndRCk.js} +13 -14
- package/dist/benchmark-command-CoNndRCk.js.map +1 -0
- package/dist/benchmarks/index.d.ts +4 -4
- package/dist/benchmarks/index.js +4 -5
- package/dist/benchmarks/index.js.map +1 -1
- package/dist/builder-eval/index.js +1 -1
- package/dist/{calibration-CbZPApIO.js → calibration-Cf-wpqqO.js} +2 -2
- package/dist/{calibration-CbZPApIO.js.map → calibration-Cf-wpqqO.js.map} +1 -1
- package/dist/campaign/index.d.ts +7 -7
- package/dist/campaign/index.js +10 -10
- package/dist/{campaign-BABipFel.js → campaign-Bl07uIaf.js} +14 -15
- package/dist/{campaign-BABipFel.js.map → campaign-Bl07uIaf.js.map} +1 -1
- package/dist/{campaign-evidence-DONEWvVY.js → campaign-evidence-NtH29ctt.js} +3 -3
- package/dist/{campaign-evidence-DONEWvVY.js.map → campaign-evidence-NtH29ctt.js.map} +1 -1
- package/dist/{chat-client-D0me8iwq.js → chat-client-Zz97O3NB.js} +2 -2
- package/dist/{chat-client-D0me8iwq.js.map → chat-client-Zz97O3NB.js.map} +1 -1
- package/dist/{chat-json-call-C473CwTt.js → chat-json-call-Dgi7-RH-.js} +2 -2
- package/dist/{chat-json-call-C473CwTt.js.map → chat-json-call-Dgi7-RH-.js.map} +1 -1
- package/dist/cli.js +7 -7
- package/dist/{types-0KglnQ9o.d.ts → cluster-Cd0MRbr9.d.ts} +44 -2
- package/dist/cluster-Cd0MRbr9.d.ts.map +1 -0
- package/dist/cluster-bootstrap-B0MTOBRU.js +24 -0
- package/dist/cluster-bootstrap-B0MTOBRU.js.map +1 -0
- package/dist/{completion-verifier-7KEfroqx.d.ts → completion-verifier-BEpsr3N4.d.ts} +2 -2
- package/dist/{completion-verifier-7KEfroqx.d.ts.map → completion-verifier-BEpsr3N4.d.ts.map} +1 -1
- package/dist/{completion-verifier-ClmJV_Yc.js → completion-verifier-DFyYFezn.js} +3 -3
- package/dist/{completion-verifier-ClmJV_Yc.js.map → completion-verifier-DFyYFezn.js.map} +1 -1
- package/dist/contract/index.d.ts +10 -10
- package/dist/contract/index.js +14 -15
- package/dist/contract/index.js.map +1 -1
- package/dist/{cost-ledger-CS8R3IZj.js → cost-ledger-DfhStGcZ.js} +2 -2
- package/dist/{cost-ledger-CS8R3IZj.js.map → cost-ledger-DfhStGcZ.js.map} +1 -1
- package/dist/{decision-point-CNyoKOkz.js → decision-point-Di2LATNH.js} +4 -4
- package/dist/{decision-point-CNyoKOkz.js.map → decision-point-Di2LATNH.js.map} +1 -1
- package/dist/{default-registry-BB9_jzyH.js → default-registry-CdFbxPnr.js} +5 -5
- package/dist/{default-registry-BB9_jzyH.js.map → default-registry-CdFbxPnr.js.map} +1 -1
- package/dist/{default-registry-BbXr18AT.d.ts → default-registry-aPvwtzEM.d.ts} +7 -7
- package/dist/{default-registry-BbXr18AT.d.ts.map → default-registry-aPvwtzEM.d.ts.map} +1 -1
- package/dist/{define-agent-eval-Q4FdXGj7.js → define-agent-eval-BROmIwn1.js} +6 -6
- package/dist/{define-agent-eval-Q4FdXGj7.js.map → define-agent-eval-BROmIwn1.js.map} +1 -1
- package/dist/{define-agent-eval-D_DQMH04.d.ts → define-agent-eval-Bx3b9B01.d.ts} +7 -7
- package/dist/{define-agent-eval-D_DQMH04.d.ts.map → define-agent-eval-Bx3b9B01.d.ts.map} +1 -1
- package/dist/diagnosis/index.d.ts +2 -2
- package/dist/diagnosis/index.js +1 -1
- package/dist/{dspy-rlm-engine-CqQc0R2l.js → dspy-rlm-engine-cWyn8G1a.js} +4 -4
- package/dist/{dspy-rlm-engine-CqQc0R2l.js.map → dspy-rlm-engine-cWyn8G1a.js.map} +1 -1
- package/dist/{engine-rfV8Ff8V.d.ts → engine-BF8naBn7.d.ts} +2 -2
- package/dist/{engine-rfV8Ff8V.d.ts.map → engine-BF8naBn7.d.ts.map} +1 -1
- package/dist/{eval-campaign-CZSCjxVb.js → eval-campaign-Dq8DEKmy.js} +2 -2
- package/dist/{eval-campaign-CZSCjxVb.js.map → eval-campaign-Dq8DEKmy.js.map} +1 -1
- package/dist/{evaluation-SDXKL6Fx.d.ts → evaluation-CFKj_IlJ.d.ts} +4 -4
- package/dist/{evaluation-SDXKL6Fx.d.ts.map → evaluation-CFKj_IlJ.d.ts.map} +1 -1
- package/dist/{evaluation-BBI37mRe.js → evaluation-bU_bhlv-.js} +2 -2
- package/dist/{evaluation-BBI37mRe.js.map → evaluation-bU_bhlv-.js.map} +1 -1
- package/dist/evaluation.d.ts +1 -1
- package/dist/evaluation.js +1 -1
- package/dist/{exact-types-CaLLU1Pz.d.ts → exact-types-VAFjtOQN.d.ts} +2 -2
- package/dist/{exact-types-CaLLU1Pz.d.ts.map → exact-types-VAFjtOQN.d.ts.map} +1 -1
- package/dist/experiment/index.d.ts +3 -5
- package/dist/experiment/index.d.ts.map +1 -1
- package/dist/experiment/index.js +7 -12
- package/dist/experiment/index.js.map +1 -1
- package/dist/{exporters-BYBG9b1n.d.ts → exporters-dQKYD_Zo.d.ts} +2 -2
- package/dist/{exporters-BYBG9b1n.d.ts.map → exporters-dQKYD_Zo.d.ts.map} +1 -1
- package/dist/{external-optimizer-process-CfrY-nJT.js → external-optimizer-process-2ImGH_LR.js} +2 -2
- package/dist/{external-optimizer-process-CfrY-nJT.js.map → external-optimizer-process-2ImGH_LR.js.map} +1 -1
- package/dist/{external-optimizer-subprocess-BtJk8UcU.js → external-optimizer-subprocess-_C_2yriN.js} +3 -3
- package/dist/{external-optimizer-subprocess-BtJk8UcU.js.map → external-optimizer-subprocess-_C_2yriN.js.map} +1 -1
- package/dist/{feedback-trajectory-P37ju-gW.d.ts → feedback-trajectory-DTj8eVTR.d.ts} +3 -3
- package/dist/{feedback-trajectory-P37ju-gW.d.ts.map → feedback-trajectory-DTj8eVTR.d.ts.map} +1 -1
- package/dist/{findings-store-BnYN57-h.js → findings-store-BSuaV3dN.js} +7 -24
- package/dist/findings-store-BSuaV3dN.js.map +1 -0
- package/dist/fuzz.js +2 -2
- package/dist/{index-D4lT7aFu.d.ts → index-7tWvC0aW.d.ts} +28 -128
- package/dist/index-7tWvC0aW.d.ts.map +1 -0
- package/dist/{index-C3t17kHu.d.ts → index-B62BaRzH.d.ts} +7 -100
- package/dist/index-B62BaRzH.d.ts.map +1 -0
- package/dist/{index-HuSMvqR2.d.ts → index-BlTbxHlY.d.ts} +5 -5
- package/dist/{index-HuSMvqR2.d.ts.map → index-BlTbxHlY.d.ts.map} +1 -1
- package/dist/{index-AmfM3usI.d.ts → index-CM12lr9E.d.ts} +8 -8
- package/dist/{index-AmfM3usI.d.ts.map → index-CM12lr9E.d.ts.map} +1 -1
- package/dist/{index-DLVbfss9.d.ts → index-DFso1b2W.d.ts} +8 -8
- package/dist/{index-DLVbfss9.d.ts.map → index-DFso1b2W.d.ts.map} +1 -1
- package/dist/index-DNXFzSpc.d.ts +1101 -0
- package/dist/index-DNXFzSpc.d.ts.map +1 -0
- package/dist/{index-BPmj-_ta.d.ts → index-DfqAy8ct.d.ts} +10 -9
- package/dist/index-DfqAy8ct.d.ts.map +1 -0
- package/dist/index.d.ts +29 -31
- package/dist/index.js +28 -164
- package/dist/index.js.map +1 -1
- package/dist/{integrity-BAdVzT8u.d.ts → integrity-CrmnGB2T.d.ts} +2 -2
- package/dist/{integrity-BAdVzT8u.d.ts.map → integrity-CrmnGB2T.d.ts.map} +1 -1
- package/dist/{judge-gate-CIlBrn6q.js → judge-gate-CrN0PaAL.js} +3 -3
- package/dist/{judge-gate-CIlBrn6q.js.map → judge-gate-CrN0PaAL.js.map} +1 -1
- package/dist/{kind-factory-Cfz8DUCc.js → kind-factory-CV0FNCMM.js} +2 -2
- package/dist/{kind-factory-Cfz8DUCc.js.map → kind-factory-CV0FNCMM.js.map} +1 -1
- package/dist/{llm-client-BdSiZ4qz.js → llm-client-DMMSg-Ro.js} +2 -2
- package/dist/{llm-client-BdSiZ4qz.js.map → llm-client-DMMSg-Ro.js.map} +1 -1
- package/dist/{llm-judge-VD_MI6kd.js → llm-judge-C813vmpc.js} +13 -14
- package/dist/{llm-judge-VD_MI6kd.js.map → llm-judge-C813vmpc.js.map} +1 -1
- package/dist/{matrix-Yg1lHIGI.d.ts → matrix-C-GxIgeJ.d.ts} +2 -2
- package/dist/{matrix-Yg1lHIGI.d.ts.map → matrix-C-GxIgeJ.d.ts.map} +1 -1
- package/dist/meta-eval/index.d.ts +2 -2
- package/dist/meta-eval/index.js +7 -7
- package/dist/{metrics-DNCAUtuB.js → metrics-zALlR17s.js} +16 -17
- package/dist/metrics-zALlR17s.js.map +1 -0
- package/dist/multishot/golden/index.d.ts +1 -1
- package/dist/multishot/index.d.ts +2 -2
- package/dist/multishot/index.js +1 -1
- package/dist/openapi.json +1 -1
- package/dist/{outcome-observations-DZu5hLYF.js → outcome-observations-DPkH-LHQ.js} +2 -3
- package/dist/{outcome-observations-DZu5hLYF.js.map → outcome-observations-DPkH-LHQ.js.map} +1 -1
- package/dist/paired-arms-DjMEtYI9.js +338 -0
- package/dist/paired-arms-DjMEtYI9.js.map +1 -0
- package/dist/{paired-promotion-decision-CiueaTTj.js → paired-promotion-decision-Bi9__RQS.js} +2 -3
- package/dist/{paired-promotion-decision-CiueaTTj.js.map → paired-promotion-decision-Bi9__RQS.js.map} +1 -1
- package/dist/{paired-promotion-decision-BDnqepZ1.d.ts → paired-promotion-decision-DJU3fZxH.d.ts} +3 -113
- package/dist/paired-promotion-decision-DJU3fZxH.d.ts.map +1 -0
- package/dist/{pareto-a3EOmjfe.js → pareto-fJZg8pXm.js} +3 -6
- package/dist/{pareto-a3EOmjfe.js.map → pareto-fJZg8pXm.js.map} +1 -1
- package/dist/pipelines/index.js +1 -1
- package/dist/{prime-protocol-DKRk4l4U.d.ts → prime-protocol-D1NkJRuD.d.ts} +2 -2
- package/dist/{prime-protocol-DKRk4l4U.d.ts.map → prime-protocol-D1NkJRuD.d.ts.map} +1 -1
- package/dist/{promotion-gate-DOkgJcLW.d.ts → promotion-gate-Da0xV4sa.d.ts} +3 -67
- package/dist/promotion-gate-Da0xV4sa.d.ts.map +1 -0
- package/dist/{promotion-policy-DLPcEnCf.js → promotion-policy-DCgftbnd.js} +4 -4
- package/dist/{promotion-policy-DLPcEnCf.js.map → promotion-policy-DCgftbnd.js.map} +1 -1
- package/dist/{proposal-findings-BfzzZ_lN.js → proposal-findings-DWs94yT8.js} +2 -2
- package/dist/{proposal-findings-BfzzZ_lN.js.map → proposal-findings-DWs94yT8.js.map} +1 -1
- package/dist/{registry-Ck7w-rr5.d.ts → registry-BAcEbzKm.d.ts} +4 -4
- package/dist/{registry-Ck7w-rr5.d.ts.map → registry-BAcEbzKm.d.ts.map} +1 -1
- package/dist/{release-confidence-nfQNh3eb.js → release-confidence-DGtuPDxJ.js} +2 -2
- package/dist/{release-confidence-nfQNh3eb.js.map → release-confidence-DGtuPDxJ.js.map} +1 -1
- package/dist/reporting.d.ts +4 -5
- package/dist/reporting.d.ts.map +1 -1
- package/dist/reporting.js +5 -7
- package/dist/reporting.js.map +1 -1
- package/dist/{researcher-CLnNJ7Or.d.ts → researcher-CSlc84Bp.d.ts} +4 -4
- package/dist/{researcher-CLnNJ7Or.d.ts.map → researcher-CSlc84Bp.d.ts.map} +1 -1
- package/dist/{reward-hacking-B88f-Kh7.js → reward-hacking-BYiDFbIl.js} +2 -3
- package/dist/{reward-hacking-B88f-Kh7.js.map → reward-hacking-BYiDFbIl.js.map} +1 -1
- package/dist/rl.d.ts +9 -8
- package/dist/rl.d.ts.map +1 -1
- package/dist/rl.js +8 -10
- package/dist/rl.js.map +1 -1
- package/dist/rollout/index.d.ts +4 -4
- package/dist/rollout/index.js +1 -1
- package/dist/{rollout-Cu7kHGIe.js → rollout-DKa54qer.js} +2 -2
- package/dist/{rollout-Cu7kHGIe.js.map → rollout-DKa54qer.js.map} +1 -1
- package/dist/{rubric-predictive-validity-D_6ZPTNR.js → rubric-predictive-validity-DL7gJ51F.js} +2 -2
- package/dist/{rubric-predictive-validity-D_6ZPTNR.js.map → rubric-predictive-validity-DL7gJ51F.js.map} +1 -1
- package/dist/{run-record-CbUi2adH.js → run-record-CFbnkE1K.js} +2 -2
- package/dist/{run-record-CbUi2adH.js.map → run-record-CFbnkE1K.js.map} +1 -1
- package/dist/{runtime-rollouts-kGn1K5ut.js → runtime-rollouts-BNrm5nC_.js} +2 -2
- package/dist/{runtime-rollouts-kGn1K5ut.js.map → runtime-rollouts-BNrm5nC_.js.map} +1 -1
- package/dist/{schema-CfoA9U_U.d.ts → schema-PDKQ_iNE.d.ts} +2 -131
- package/dist/schema-PDKQ_iNE.d.ts.map +1 -0
- package/dist/search/index.d.ts +2 -2
- package/dist/search/index.js +2 -2
- package/dist/{search-kernel-DjqaPJqL.d.ts → search-kernel-CQGLbmgn.d.ts} +3 -3
- package/dist/{search-kernel-DjqaPJqL.d.ts.map → search-kernel-CQGLbmgn.d.ts.map} +1 -1
- package/dist/{search-summary-RJ5zXjHN.js → search-summary-sPWiYtSl.js} +4 -4
- package/dist/{search-summary-RJ5zXjHN.js.map → search-summary-sPWiYtSl.js.map} +1 -1
- package/dist/{sequential-BPbvgzfe.js → sequential-9TVb5Nu5.js} +3 -3
- package/dist/{sequential-BPbvgzfe.js.map → sequential-9TVb5Nu5.js.map} +1 -1
- package/dist/{sequential-Bb_pdTqG.d.ts → sequential-B9p6uoV8.d.ts} +9 -2
- package/dist/{sequential-Bb_pdTqG.d.ts.map → sequential-B9p6uoV8.d.ts.map} +1 -1
- package/dist/{sequential-Bjs5roiK.js → sequential-CAksw6EU.js} +32 -2
- package/dist/{sequential-Bjs5roiK.js.map → sequential-CAksw6EU.js.map} +1 -1
- package/dist/{server-CPKyf3bz.js → server-DFVwfoZq.js} +3 -3
- package/dist/{server-CPKyf3bz.js.map → server-DFVwfoZq.js.map} +1 -1
- package/dist/{skillopt-optimization-method-D9Hlmhjg.js → skillopt-optimization-method-QO1nU8Kz.js} +9 -9
- package/dist/{skillopt-optimization-method-D9Hlmhjg.js.map → skillopt-optimization-method-QO1nU8Kz.js.map} +1 -1
- package/dist/{statistical-heldout-C-tgpUuu.d.ts → statistical-heldout-CvOwNqt9.d.ts} +6 -282
- package/dist/statistical-heldout-CvOwNqt9.d.ts.map +1 -0
- package/dist/{statistical-heldout-NBxC7jGo.js → statistical-heldout-DLO4Ebos.js} +3 -3
- package/dist/{statistical-heldout-NBxC7jGo.js.map → statistical-heldout-DLO4Ebos.js.map} +1 -1
- package/dist/statistics-CvvC-MPv.js +2634 -0
- package/dist/statistics-CvvC-MPv.js.map +1 -0
- package/dist/statistics.d.ts +3 -0
- package/dist/statistics.js +3 -0
- package/dist/{store-otlp-BfPRa2p8.js → store-otlp-C-jyj3WX.js} +2 -2
- package/dist/{store-otlp-BfPRa2p8.js.map → store-otlp-C-jyj3WX.js.map} +1 -1
- package/dist/{store-tool-spans-BgwVHXma.d.ts → store-tool-spans-B3z_Qb5u.d.ts} +5 -5
- package/dist/{store-tool-spans-BgwVHXma.d.ts.map → store-tool-spans-B3z_Qb5u.d.ts.map} +1 -1
- package/dist/{store-tool-spans-BrSWHB9O.js → store-tool-spans-DalWlKY8.js} +3 -3
- package/dist/{store-tool-spans-BrSWHB9O.js.map → store-tool-spans-DalWlKY8.js.map} +1 -1
- package/dist/{summary-report-C3IJvp0i.js → summary-report-BEhqoxrA.js} +4 -52
- package/dist/summary-report-BEhqoxrA.js.map +1 -0
- package/dist/{summary-report-0La5vejY.d.ts → summary-report-DyZquTaH.d.ts} +2 -2
- package/dist/{summary-report-0La5vejY.d.ts.map → summary-report-DyZquTaH.d.ts.map} +1 -1
- package/dist/supervisor-run/index.d.ts +2 -2
- package/dist/supervisor-run/index.js +1 -1
- package/dist/{systemone-CpDppX8s.d.ts → systemone-DVk-Crtu.d.ts} +7 -7
- package/dist/{systemone-CpDppX8s.d.ts.map → systemone-DVk-Crtu.d.ts.map} +1 -1
- package/dist/{systemone-review-nbuMxxmi.d.ts → systemone-review-CToBl1oa.d.ts} +2 -2
- package/dist/{systemone-review-nbuMxxmi.d.ts.map → systemone-review-CToBl1oa.d.ts.map} +1 -1
- package/dist/systemone.d.ts +3 -3
- package/dist/systemone.js +2 -2
- package/dist/{tool-groups-BQsjZD9F.d.ts → tool-groups-R5RO9OHn.d.ts} +3 -3
- package/dist/tool-groups-R5RO9OHn.d.ts.map +1 -0
- package/dist/{tool-waste-Czt3aWID.js → tool-waste-BqSmmPUz.js} +2 -3
- package/dist/{tool-waste-Czt3aWID.js.map → tool-waste-BqSmmPUz.js.map} +1 -1
- package/dist/{trace-questions-CpTrtEcm.d.ts → trace-questions-BY6taxnl.d.ts} +3 -3
- package/dist/{trace-questions-CpTrtEcm.d.ts.map → trace-questions-BY6taxnl.d.ts.map} +1 -1
- package/dist/trace-repair/index.d.ts +1 -1
- package/dist/trace-repair/index.js +1 -2
- package/dist/trace-repair/index.js.map +1 -1
- package/dist/traces.d.ts +5 -5
- package/dist/traces.js +3 -3
- package/dist/{tree-DIHp6UQ0.js → tree-C-N2kP-8.js} +4 -6
- package/dist/{tree-DIHp6UQ0.js.map → tree-C-N2kP-8.js.map} +1 -1
- package/dist/{types-DsuOcYsE.d.ts → types-BsdcSWnf.d.ts} +2 -2
- package/dist/{types-DsuOcYsE.d.ts.map → types-BsdcSWnf.d.ts.map} +1 -1
- package/dist/{types-DNB9hIXa.d.ts → types-DUVhW5V1.d.ts} +3 -2
- package/dist/types-DUVhW5V1.d.ts.map +1 -0
- package/dist/{types-wDBk14lj.d.ts → types-ip2D3-Ib.d.ts} +5 -4
- package/dist/types-ip2D3-Ib.d.ts.map +1 -0
- package/dist/{types-B9s9Xo5_.d.ts → types-kBMNdo1X.d.ts} +3 -9
- package/dist/types-kBMNdo1X.d.ts.map +1 -0
- package/dist/wire/index.d.ts +4 -4
- package/dist/wire/index.js +1 -1
- package/docs/design/statistics-decisions.md +45 -364
- package/docs/design.md +1 -1
- package/docs/research-report-methodology.md +1 -1
- package/package.json +6 -1
- package/dist/agreement-irr-DXcXEt4I.js +0 -182
- package/dist/agreement-irr-DXcXEt4I.js.map +0 -1
- package/dist/analyze-runs-C7vWBDhl.js.map +0 -1
- package/dist/benchmark-command-DSJQeYom.js.map +0 -1
- package/dist/cluster-bootstrap-BteuR1hg.js +0 -65
- package/dist/cluster-bootstrap-BteuR1hg.js.map +0 -1
- package/dist/descriptive-B3Eb7tX0.js +0 -229
- package/dist/descriptive-B3Eb7tX0.js.map +0 -1
- package/dist/findings-store-BnYN57-h.js.map +0 -1
- package/dist/index-BPmj-_ta.d.ts.map +0 -1
- package/dist/index-C3t17kHu.d.ts.map +0 -1
- package/dist/index-D4lT7aFu.d.ts.map +0 -1
- package/dist/judge-calibration-DKR6Xi-w.js +0 -319
- package/dist/judge-calibration-DKR6Xi-w.js.map +0 -1
- package/dist/judge-calibration-DnrbQaXI.d.ts +0 -144
- package/dist/judge-calibration-DnrbQaXI.d.ts.map +0 -1
- package/dist/mean-D1d6gedE.js +0 -284
- package/dist/mean-D1d6gedE.js.map +0 -1
- package/dist/metrics-DNCAUtuB.js.map +0 -1
- package/dist/multiplicity-DAd4xaDC.js +0 -100
- package/dist/multiplicity-DAd4xaDC.js.map +0 -1
- package/dist/multiplicity-D_SEsc5j.d.ts +0 -41
- package/dist/multiplicity-D_SEsc5j.d.ts.map +0 -1
- package/dist/paired-arms-3-tsXvvC.js +0 -740
- package/dist/paired-arms-3-tsXvvC.js.map +0 -1
- package/dist/paired-binary-CMzmSSd5.js +0 -372
- package/dist/paired-binary-CMzmSSd5.js.map +0 -1
- package/dist/paired-promotion-decision-BDnqepZ1.d.ts.map +0 -1
- package/dist/paired-tests-Buh6feJ4.js +0 -211
- package/dist/paired-tests-Buh6feJ4.js.map +0 -1
- package/dist/power-and-mde-g3vOn0XK.js +0 -99
- package/dist/power-and-mde-g3vOn0XK.js.map +0 -1
- package/dist/promotion-gate-DOkgJcLW.d.ts.map +0 -1
- package/dist/random-BN150Q_X.d.ts +0 -79
- package/dist/random-BN150Q_X.d.ts.map +0 -1
- package/dist/schema-CfoA9U_U.d.ts.map +0 -1
- package/dist/sequential-eprocess-C1YLwFaz.js +0 -129
- package/dist/sequential-eprocess-C1YLwFaz.js.map +0 -1
- package/dist/statistical-heldout-C-tgpUuu.d.ts.map +0 -1
- package/dist/summary-report-C3IJvp0i.js.map +0 -1
- package/dist/tool-groups-BQsjZD9F.d.ts.map +0 -1
- package/dist/types-0KglnQ9o.d.ts.map +0 -1
- package/dist/types-B9s9Xo5_.d.ts.map +0 -1
- package/dist/types-DNB9hIXa.d.ts.map +0 -1
- package/dist/types-wDBk14lj.d.ts.map +0 -1
package/dist/traces.d.ts
CHANGED
|
@@ -1,13 +1,13 @@
|
|
|
1
1
|
import { c as ValidationError, o as LimitExceededError, s as NotFoundError, t as AgentEvalError } from "./errors-E9I2hldP.js";
|
|
2
2
|
import { C as TraceRunOutcome, E as isToolSpan, S as TraceEvent, T as isLlmSpan, _ as Span, a as FAILURE_CLASSES, b as SpanStatus, c as JudgeSpan, d as RetrievalSpan, f as Run, g as SandboxSpan, h as RunStatus, i as EventKind, l as LlmSpan, m as RunLayer, n as BudgetLedgerEntry, o as FailureClass, p as RunCaptureReport, r as BudgetSpec, s as GenericSpan, t as Artifact, u as Message, v as SpanBase, w as isJudgeSpan, x as ToolSpan, y as SpanKind } from "./schema-CkIvnmLU.js";
|
|
3
3
|
import { a as RunRecord, c as RunSplitTag, d as RunTokenUsage, u as RunTerminalOutcome } from "./run-record-D2BFMPGl.js";
|
|
4
|
-
import { $ as
|
|
5
|
-
import {
|
|
4
|
+
import { $ as ErrorCluster, G as ReadSpanSourceInput, J as TRACE_ANALYSIS_LIMITS, K as ReadSpanSourceResult, Q as DatasetOverview, U as createBoundedTraceAnalysisStore, W as BoundedTraceAnalysisStoreOptions, X as TraceAnalysisStoreContext, Y as TraceAnalysisStore, Z as DEFAULT_TRACE_ANALYST_BUDGETS, at as TraceAnalystFilters, ct as TraceAnalystSpanStatus, dt as ViewTraceOversized, et as QueryTracesPage, ft as ViewTraceResult, it as TraceAnalystByteBudgets, lt as TraceAnalystTraceSummary, nt as SearchTraceResult, ot as TraceAnalystSpan, q as SpanSourceReader, rt as SpanMatchRecord, st as TraceAnalystSpanKind, tt as SearchSpanResult, ut as ViewSpansResult } from "./types-kBMNdo1X.js";
|
|
5
|
+
import { $ as InMemoryRawProviderSinkOptions, Q as InMemoryRawProviderSink, X as FileSystemRawProviderSink, Z as FileSystemRawProviderSinkOptions, at as RawProviderSinkFilter, et as NoopRawProviderSink, it as RawProviderSink, nt as RawProviderDirection, rt as RawProviderEvent, tt as ProviderRedactor } from "./cluster-Cd0MRbr9.js";
|
|
6
6
|
import { a as RunFilter, i as InMemoryTraceStore, n as FileSystemTraceStore, o as SpanFilter, r as FileSystemTraceStoreOptions, s as TraceStore, t as EventFilter } from "./store-CMs5wGXP.js";
|
|
7
7
|
import { a as SpanHandle, i as RunCompleteHookContext, n as CaptureWrite, o as TraceEmitter, r as RunCompleteHook, s as TraceEmitterOptions, t as CaptureErrorHandler } from "./emitter-mAXC5PSN.js";
|
|
8
|
-
import { d as BuildTraceAnalysisToolsOptions, f as TRACE_ANALYST_TOOL_NAMESPACE, h as buildTraceAnalysisToolDescriptors, m as UNTRUSTED_TRACE_TEXT, p as TraceAnalysisToolDescriptor } from "./engine-
|
|
9
|
-
import { A as TraceInsightReadiness, B as isTraceInsightEvidence, C as TraceInsightContext, D as TraceInsightPromptInput, E as TraceInsightPanelRole, F as describeTraceInsightScope, G as AnalyzeTracesResult, H as tokenizeDomainWords, I as domainEvidencePattern, K as analyzeTraces, L as inferDomainKeywords, M as TraceInsightTask, N as buildTraceInsightContext, O as TraceInsightQualityGate, P as buildTraceInsightPrompt, R as isTraceInsightArtifact, S as TraceInsightAttribution, T as TraceInsightFinding, U as AnalyzeTracesInput, V as scoreTraceInsightReadiness, W as AnalyzeTracesOptions, _ as ToolSpansToTraceAnalysisStoreOptions, a as captureFetchToRawSink, b as OtlpSpan, c as ExtractedUsage, d as extractUsageFromSse, f as OtlpFileTraceStore, g as spanRecordsToTraceAnalysisStore, h as otlpTextToTraceAnalysisStore, i as CaptureFetchOptions, j as TraceInsightSuite, k as TraceInsightQuestion, l as SseUsageMode, m as SpanRecordsToTraceAnalysisStoreOptions, n as toolSpansToTraceAnalysisStore, o as OtlpFlatLine, p as OtlpFileTraceStoreOptions, r as CaptureFetchContext, s as ExtractUsageFromSseOptions, t as ToolTraceMissingError, u as extractUsage, v as OtlpExport, w as TraceInsightEvidence, x as exportRunAsOtlp, y as OtlpResourceSpans, z as isTraceInsightAttribution } from "./store-tool-spans-
|
|
10
|
-
import { a as RunIntegrityReport, i as RunIntegrityIssueCode, n as RunIntegrityExpectations, o as assertRunCaptured, r as RunIntegrityIssue, t as RunIntegrityError } from "./integrity-
|
|
8
|
+
import { d as BuildTraceAnalysisToolsOptions, f as TRACE_ANALYST_TOOL_NAMESPACE, h as buildTraceAnalysisToolDescriptors, m as UNTRUSTED_TRACE_TEXT, p as TraceAnalysisToolDescriptor } from "./engine-BF8naBn7.js";
|
|
9
|
+
import { A as TraceInsightReadiness, B as isTraceInsightEvidence, C as TraceInsightContext, D as TraceInsightPromptInput, E as TraceInsightPanelRole, F as describeTraceInsightScope, G as AnalyzeTracesResult, H as tokenizeDomainWords, I as domainEvidencePattern, K as analyzeTraces, L as inferDomainKeywords, M as TraceInsightTask, N as buildTraceInsightContext, O as TraceInsightQualityGate, P as buildTraceInsightPrompt, R as isTraceInsightArtifact, S as TraceInsightAttribution, T as TraceInsightFinding, U as AnalyzeTracesInput, V as scoreTraceInsightReadiness, W as AnalyzeTracesOptions, _ as ToolSpansToTraceAnalysisStoreOptions, a as captureFetchToRawSink, b as OtlpSpan, c as ExtractedUsage, d as extractUsageFromSse, f as OtlpFileTraceStore, g as spanRecordsToTraceAnalysisStore, h as otlpTextToTraceAnalysisStore, i as CaptureFetchOptions, j as TraceInsightSuite, k as TraceInsightQuestion, l as SseUsageMode, m as SpanRecordsToTraceAnalysisStoreOptions, n as toolSpansToTraceAnalysisStore, o as OtlpFlatLine, p as OtlpFileTraceStoreOptions, r as CaptureFetchContext, s as ExtractUsageFromSseOptions, t as ToolTraceMissingError, u as extractUsage, v as OtlpExport, w as TraceInsightEvidence, x as exportRunAsOtlp, y as OtlpResourceSpans, z as isTraceInsightAttribution } from "./store-tool-spans-B3z_Qb5u.js";
|
|
10
|
+
import { a as RunIntegrityReport, i as RunIntegrityIssueCode, n as RunIntegrityExpectations, o as assertRunCaptured, r as RunIntegrityIssue, t as RunIntegrityError } from "./integrity-CrmnGB2T.js";
|
|
11
11
|
import { C as classifyKey, E as normalizeKey, _ as redactText, a as RedactionFinding, c as SafetyCategory, d as ShareSafetyVerdict, f as assessShareSafety, g as redactForShare, h as redact, i as RedactOptions, l as ShareSafetyFinding, m as emptyRedactionReport, o as RedactionProfile, p as combineVerdicts, r as REDACTION_VERSION, s as RedactionReport, t as AssessOptions, u as ShareSafetyStatus, v as shareAllowed, w as detectCredential } from "./redact-jrT0APTU.js";
|
|
12
12
|
import { D as asNumber, E as applyLlmSpanOtlpAttributes, O as contextInputTokens, T as TOOL_NAME_ATTR_KEYS, _ as LlmSpanOtlpInput, a as LLM_CACHE_WRITE_TOKEN_ATTR_KEYS, c as LLM_COST_USD, d as LLM_MODEL_ATTR_KEYS, f as LLM_MODEL_NAME, g as LLM_REASONING_TOKEN_ATTR_KEYS, h as LLM_REASONING_TOKENS, i as LLM_CACHE_WRITE_TOKENS, k as firstNumberAttr, l as LLM_INPUT_TOKENS, m as LLM_OUTPUT_TOKEN_ATTR_KEYS, n as LLM_CACHED_TOKENS, o as LLM_CONTEXT_TOKENS, p as LLM_OUTPUT_TOKENS, r as LLM_CACHED_TOKEN_ATTR_KEYS, s as LLM_COST_ATTR_KEYS, t as INPUT_VALUE, u as LLM_INPUT_TOKEN_ATTR_KEYS, v as OPENINFERENCE_SPAN_KIND, w as TOOL_NAME, x as SPAN_KIND_ATTR_KEYS, y as OUTPUT_VALUE } from "./attribute-vocabulary-5oo8ykIx.js";
|
|
13
13
|
import { a as llmSpans, c as toolSpans, i as judgeSpans, n as argHash, o as runFailureClass, r as groupBy, s as runsForScenario, t as RunMetric } from "./query-UD0B08Sb.js";
|
package/dist/traces.js
CHANGED
|
@@ -2,16 +2,16 @@ import { i as isToolSpan, n as isJudgeSpan, r as isLlmSpan, t as FAILURE_CLASSES
|
|
|
2
2
|
import { c as validateRunRecord, i as modelHasSnapshot } from "./run-record-CpLS4Uid.js";
|
|
3
3
|
import { a as llmSpans, c as runsForScenario, i as judgeSpans, l as toolSpans, n as groupBy, o as runFailureClass, t as argHash } from "./query-CGXzO9d4.js";
|
|
4
4
|
import { a as emptyRedactionReport, c as redactText, f as classifyKey, g as normalizeKey, i as combineVerdicts, l as shareAllowed, n as REDACTION_VERSION, o as redact, p as detectCredential, r as assessShareSafety, s as redactForShare } from "./redact-zp_ILC4l.js";
|
|
5
|
-
import { C as asString, D as projectOtlpFlatLine, E as firstStringAttr, O as spanEpochMillis, S as TraceNotFoundError, _ as TraceAnalysisStoreContractError, a as UNTRUSTED_TRACE_TEXT, b as TraceFileMissingError, c as createBoundedTraceAnalysisStore, g as TraceAnalysisLimitError, h as SpanNotFoundError, i as TRACE_ANALYST_TOOL_NAMESPACE, m as TRACE_ANALYSIS_LIMITS, o as buildTraceAnalysisToolDescriptors, p as DEFAULT_TRACE_ANALYST_BUDGETS, v as TraceAnalysisValidationError, w as compareSpanTime, x as TraceFileTooLargeError } from "./kind-factory-
|
|
5
|
+
import { C as asString, D as projectOtlpFlatLine, E as firstStringAttr, O as spanEpochMillis, S as TraceNotFoundError, _ as TraceAnalysisStoreContractError, a as UNTRUSTED_TRACE_TEXT, b as TraceFileMissingError, c as createBoundedTraceAnalysisStore, g as TraceAnalysisLimitError, h as SpanNotFoundError, i as TRACE_ANALYST_TOOL_NAMESPACE, m as TRACE_ANALYSIS_LIMITS, o as buildTraceAnalysisToolDescriptors, p as DEFAULT_TRACE_ANALYST_BUDGETS, v as TraceAnalysisValidationError, w as compareSpanTime, x as TraceFileTooLargeError } from "./kind-factory-CV0FNCMM.js";
|
|
6
6
|
import { INPUT_VALUE, LLM_CACHED_TOKENS, LLM_CACHED_TOKEN_ATTR_KEYS, LLM_CACHE_WRITE_TOKENS, LLM_CACHE_WRITE_TOKEN_ATTR_KEYS, LLM_CONTEXT_TOKENS, LLM_COST_ATTR_KEYS, LLM_COST_USD, LLM_INPUT_TOKENS, LLM_INPUT_TOKEN_ATTR_KEYS, LLM_MODEL_ATTR_KEYS, LLM_MODEL_NAME, LLM_OUTPUT_TOKENS, LLM_OUTPUT_TOKEN_ATTR_KEYS, LLM_REASONING_TOKENS, LLM_REASONING_TOKEN_ATTR_KEYS, OPENINFERENCE_SPAN_KIND, OUTPUT_VALUE, SPAN_KIND_ATTR_KEYS, TOOL_NAME, TOOL_NAME_ATTR_KEYS, applyLlmSpanOtlpAttributes, asNumber, contextInputTokens, firstNumberAttr } from "./trace-attributes.js";
|
|
7
7
|
import { n as extractUsageFromSse, t as extractUsage } from "./extract-usage-ISFqhfDz.js";
|
|
8
8
|
import { n as InMemoryRawProviderSink, r as NoopRawProviderSink, t as FileSystemRawProviderSink } from "./raw-provider-sink-RbaEv2vB.js";
|
|
9
|
-
import { _ as exportRunAsOtlp, a as spanStatusToOtlp, c as describeTraceInsightScope, d as isTraceInsightArtifact, f as isTraceInsightAttribution, g as analyzeTraces, h as tokenizeDomainWords, i as epochMillisToIso, l as domainEvidencePattern, m as scoreTraceInsightReadiness, n as toolSpansToTraceAnalysisStore, o as buildTraceInsightContext, p as isTraceInsightEvidence, r as createOtlpFlatLine, s as buildTraceInsightPrompt, t as ToolTraceMissingError, u as inferDomainKeywords, v as captureFetchToRawSink } from "./store-tool-spans-
|
|
9
|
+
import { _ as exportRunAsOtlp, a as spanStatusToOtlp, c as describeTraceInsightScope, d as isTraceInsightArtifact, f as isTraceInsightAttribution, g as analyzeTraces, h as tokenizeDomainWords, i as epochMillisToIso, l as domainEvidencePattern, m as scoreTraceInsightReadiness, n as toolSpansToTraceAnalysisStore, o as buildTraceInsightContext, p as isTraceInsightEvidence, r as createOtlpFlatLine, s as buildTraceInsightPrompt, t as ToolTraceMissingError, u as inferDomainKeywords, v as captureFetchToRawSink } from "./store-tool-spans-DalWlKY8.js";
|
|
10
10
|
import { t as TraceEmitter } from "./emitter-DhQ65mza.js";
|
|
11
11
|
import { n as assertRunCaptured, t as RunIntegrityError } from "./integrity-DOHt1mwU.js";
|
|
12
12
|
import { n as traceSpanKindToOpenInferenceKind, t as applyToolSpanOtlpAttributes } from "./otlp-attributes-Boeb7gtH.js";
|
|
13
13
|
import { n as InMemoryTraceStore, t as FileSystemTraceStore } from "./store-ZykIyQmy.js";
|
|
14
|
-
import { a as spanRecordsToTraceAnalysisStore, i as otlpTextToTraceAnalysisStore, r as OtlpFileTraceStore } from "./store-otlp-
|
|
14
|
+
import { a as spanRecordsToTraceAnalysisStore, i as otlpTextToTraceAnalysisStore, r as OtlpFileTraceStore } from "./store-otlp-C-jyj3WX.js";
|
|
15
15
|
import { i as summarizeTraceErrors, n as recordAggregateMeasurements, r as summarizeExecutionMeasurements, t as readTaskFailureLabels } from "./task-failure-attributes-CC6VuIpk.js";
|
|
16
16
|
import { readFileSync, readdirSync, statSync, writeFileSync } from "node:fs";
|
|
17
17
|
import { join } from "node:path";
|
|
@@ -1,10 +1,8 @@
|
|
|
1
1
|
import { a as hashCanonical, i as compareCodeUnits, r as canonicalString } from "./canonical-CicJlINA.js";
|
|
2
|
-
import {
|
|
2
|
+
import { D as holm, ct as mean, f as DECISION_PAIRED_DELTA_STATISTIC, ft as medianInPlace, h as pairedSignTest, mt as zQuantile } from "./statistics-CvvC-MPv.js";
|
|
3
3
|
import { t as mulberry32 } from "./random-DrzcgC7F.js";
|
|
4
|
-
import { r as
|
|
5
|
-
import {
|
|
6
|
-
import { i as pairedDeltaTest, r as minimumPairsForPairedDeltaTest } from "./paired-promotion-decision-CiueaTTj.js";
|
|
7
|
-
import { A as normalizeSignedZero, D as searchEstimateMethod, O as searchPosterior, b as verifySearchClaim, d as rankingSplit, f as summarizeSamples, k as seedFromDigest, n as paretoFrontier, o as searchPolicyView, u as INSUFFICIENT_FROM, w as estimateNode } from "./pareto-a3EOmjfe.js";
|
|
4
|
+
import { i as pairedDeltaTest, r as minimumPairsForPairedDeltaTest } from "./paired-promotion-decision-Bi9__RQS.js";
|
|
5
|
+
import { A as normalizeSignedZero, D as searchEstimateMethod, O as searchPosterior, b as verifySearchClaim, d as rankingSplit, f as summarizeSamples, k as seedFromDigest, n as paretoFrontier, o as searchPolicyView, u as INSUFFICIENT_FROM, w as estimateNode } from "./pareto-fJZg8pXm.js";
|
|
8
6
|
import { l as searchUnitScores } from "./search-ledger-Dk-yk5Li.js";
|
|
9
7
|
import { t as roundDecimal } from "./round-decimal-ZmjAQPo1.js";
|
|
10
8
|
import { defineInlineResource } from "@tangle-network/agent-interface";
|
|
@@ -4112,4 +4110,4 @@ function tree(state) {
|
|
|
4112
4110
|
}
|
|
4113
4111
|
export { vectorEmbedding as _, skillCalibration as a, editCreditText as b, META_SEARCH_SCORE_SOURCE as c, searchPolicyGenome as d, landscape as f, surfaceTextEdits as g, lineageEdits as h, nextUnitExtension as i, metaSearch as l, formatLandscape as m, taskMatrix as n, skillManifold as o, draftOnPlateau as p, formatSkillManifold as r, renderMetaSearchText as s, tree as t, metaSearchScore as u, front as v, editCredit as y };
|
|
4114
4112
|
|
|
4115
|
-
//# sourceMappingURL=tree-
|
|
4113
|
+
//# sourceMappingURL=tree-C-N2kP-8.js.map
|