@tangle-network/agent-eval 1.0.18 → 1.0.20
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 +20 -21
- 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 +13 -14
- package/dist/analyst/index.js.map +1 -1
- package/dist/{analyze-runs-pJ4fhnYg.d.ts → analyze-runs-DicleUI_.d.ts} +4 -4
- package/dist/{analyze-runs-pJ4fhnYg.d.ts.map → analyze-runs-DicleUI_.d.ts.map} +1 -1
- package/dist/{analyze-runs-C7vWBDhl.js → analyze-runs-e9vfXY--.js} +6 -110
- package/dist/analyze-runs-e9vfXY--.js.map +1 -0
- package/dist/app-grade/index.d.ts +12 -7
- package/dist/app-grade/index.d.ts.map +1 -1
- package/dist/app-grade/index.js +14 -10
- package/dist/app-grade/index.js.map +1 -1
- package/dist/{benchmark-command-Bqqvv9Tk.js → benchmark-command-BGZD77Un.js} +16 -17
- package/dist/benchmark-command-BGZD77Un.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-Ze7SjhT9.js} +2 -2
- package/dist/{calibration-CbZPApIO.js.map → calibration-Ze7SjhT9.js.map} +1 -1
- package/dist/campaign/index.d.ts +7 -7
- package/dist/campaign/index.js +13 -13
- package/dist/{campaign-DzLlT0So.js → campaign-BfDMncQN.js} +16 -17
- package/dist/{campaign-DzLlT0So.js.map → campaign-BfDMncQN.js.map} +1 -1
- package/dist/{campaign-evidence-CcA7a67m.js → campaign-evidence-BuKlRzSA.js} +4 -4
- package/dist/{campaign-evidence-CcA7a67m.js.map → campaign-evidence-BuKlRzSA.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 +9 -9
- 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-BYIW7QJ4.js +24 -0
- package/dist/cluster-bootstrap-BYIW7QJ4.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 +15 -16
- 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-DJWievVw.js} +4 -4
- package/dist/{decision-point-CNyoKOkz.js.map → decision-point-DJWievVw.js.map} +1 -1
- package/dist/{default-registry-BNv7eB1C.d.ts → default-registry-BpGFsSpZ.d.ts} +7 -7
- package/dist/{default-registry-BNv7eB1C.d.ts.map → default-registry-BpGFsSpZ.d.ts.map} +1 -1
- package/dist/{default-registry-BB9_jzyH.js → default-registry-CdMtoY-s.js} +5 -5
- package/dist/{default-registry-BB9_jzyH.js.map → default-registry-CdMtoY-s.js.map} +1 -1
- package/dist/{define-agent-eval-DKVYlm-T.d.ts → define-agent-eval-DcK8mg63.d.ts} +7 -7
- package/dist/{define-agent-eval-DKVYlm-T.d.ts.map → define-agent-eval-DcK8mg63.d.ts.map} +1 -1
- package/dist/{define-agent-eval-CjF2nTA3.js → define-agent-eval-DuQNZajG.js} +7 -7
- package/dist/{define-agent-eval-CjF2nTA3.js.map → define-agent-eval-DuQNZajG.js.map} +1 -1
- package/dist/diagnosis/index.d.ts +2 -2
- package/dist/diagnosis/index.js +1 -1
- package/dist/{dspy-rlm-engine-_MEe2jIO.js → dspy-rlm-engine-cWyn8G1a.js} +4 -4
- package/dist/{dspy-rlm-engine-_MEe2jIO.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-LmpC_5fm.js} +2 -2
- package/dist/{eval-campaign-CZSCjxVb.js.map → eval-campaign-LmpC_5fm.js.map} +1 -1
- package/dist/{evaluation-DYAIkPQB.d.ts → evaluation-BCejQgkV.d.ts} +4 -4
- package/dist/{evaluation-DYAIkPQB.d.ts.map → evaluation-BCejQgkV.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-za-SsIap.js → external-optimizer-process-2ImGH_LR.js} +2 -2
- package/dist/{external-optimizer-process-za-SsIap.js.map → external-optimizer-process-2ImGH_LR.js.map} +1 -1
- package/dist/{external-optimizer-subprocess-B44kOfZb.js → external-optimizer-subprocess-_C_2yriN.js} +4 -4
- package/dist/{external-optimizer-subprocess-B44kOfZb.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-DWiBvJVM.js → findings-store-BSuaV3dN.js} +8 -25
- package/dist/findings-store-BSuaV3dN.js.map +1 -0
- package/dist/fuzz.js +2 -2
- package/dist/hosted/index.js +1 -1
- package/dist/{index-BJM4rwP2.d.ts → index-Bc8BZfzb.d.ts} +10 -9
- package/dist/index-Bc8BZfzb.d.ts.map +1 -0
- package/dist/index-BdLmBInV.d.ts +1099 -0
- package/dist/index-BdLmBInV.d.ts.map +1 -0
- package/dist/{index-BAPkHt5H.d.ts → index-CeYLLnfi.d.ts} +28 -128
- package/dist/index-CeYLLnfi.d.ts.map +1 -0
- package/dist/{index-C3t17kHu.d.ts → index-CzfdjM6o.d.ts} +7 -100
- package/dist/index-CzfdjM6o.d.ts.map +1 -0
- package/dist/{index-f09MX_H_.d.ts → index-DYNHOTTB.d.ts} +5 -5
- package/dist/{index-f09MX_H_.d.ts.map → index-DYNHOTTB.d.ts.map} +1 -1
- package/dist/{index-Dt6E4BHX.d.ts → index-D_eAFB3T.d.ts} +8 -8
- package/dist/{index-Dt6E4BHX.d.ts.map → index-D_eAFB3T.d.ts.map} +1 -1
- package/dist/{index-chNyKroE.d.ts → index-gSu9DUiw.d.ts} +8 -8
- package/dist/{index-chNyKroE.d.ts.map → index-gSu9DUiw.d.ts.map} +1 -1
- package/dist/{index-B1Bm9oJA.d.ts → index-lRKqfyg4.d.ts} +3 -7
- package/dist/index-lRKqfyg4.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/{journal-C1uLJi0w.js → journal-CTX5uK-n.js} +36 -26
- package/dist/journal-CTX5uK-n.js.map +1 -0
- package/dist/{judge-gate-CIlBrn6q.js → judge-gate-BliY81A0.js} +3 -3
- package/dist/{judge-gate-CIlBrn6q.js.map → judge-gate-BliY81A0.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/ledger-core/index.d.ts +1 -1
- package/dist/ledger-core/index.js +2 -2
- package/dist/{ledger-core-CfT-FzPf.js → ledger-core-24IxvmVY.js} +2 -2
- package/dist/{ledger-core-CfT-FzPf.js.map → ledger-core-24IxvmVY.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-CHLvjbVR.js → llm-judge-Bnxuwjxl.js} +15 -16
- package/dist/{llm-judge-CHLvjbVR.js.map → llm-judge-Bnxuwjxl.js.map} +1 -1
- package/dist/{matrix-Cy3oy7Rq.d.ts → matrix-D6zEwLvE.d.ts} +2 -2
- package/dist/{matrix-Cy3oy7Rq.d.ts.map → matrix-D6zEwLvE.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-BpicIVQi.js} +2 -3
- package/dist/{outcome-observations-DZu5hLYF.js.map → outcome-observations-BpicIVQi.js.map} +1 -1
- package/dist/paired-arms-Dep5tbsw.js +338 -0
- package/dist/paired-arms-Dep5tbsw.js.map +1 -0
- package/dist/{paired-promotion-decision-BDnqepZ1.d.ts → paired-promotion-decision-BNzPfXDw.d.ts} +3 -113
- package/dist/paired-promotion-decision-BNzPfXDw.d.ts.map +1 -0
- package/dist/{paired-promotion-decision-CiueaTTj.js → paired-promotion-decision-Nt4CkkOT.js} +2 -3
- package/dist/{paired-promotion-decision-CiueaTTj.js.map → paired-promotion-decision-Nt4CkkOT.js.map} +1 -1
- package/dist/{pareto-B34N-vnn.js → pareto-C445lnEH.js} +6 -9
- package/dist/{pareto-B34N-vnn.js.map → pareto-C445lnEH.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-DjAsmBSZ.d.ts} +3 -67
- package/dist/promotion-gate-DjAsmBSZ.d.ts.map +1 -0
- package/dist/{promotion-policy-DLPcEnCf.js → promotion-policy-CUWOv01m.js} +4 -4
- package/dist/{promotion-policy-DLPcEnCf.js.map → promotion-policy-CUWOv01m.js.map} +1 -1
- package/dist/{proposal-findings-CZJkS_GY.js → proposal-findings-DWs94yT8.js} +2 -2
- package/dist/{proposal-findings-CZJkS_GY.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-DDrkmWxT.js} +2 -2
- package/dist/{release-confidence-nfQNh3eb.js.map → release-confidence-DDrkmWxT.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-D35yo0B8.d.ts} +4 -4
- package/dist/{researcher-CLnNJ7Or.d.ts.map → researcher-D35yo0B8.d.ts.map} +1 -1
- package/dist/{reward-hacking-B88f-Kh7.js → reward-hacking-DRb8K6N1.js} +2 -3
- package/dist/{reward-hacking-B88f-Kh7.js.map → reward-hacking-DRb8K6N1.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-BMS7SUyh.js} +2 -2
- package/dist/{rubric-predictive-validity-D_6ZPTNR.js.map → rubric-predictive-validity-BMS7SUyh.js.map} +1 -1
- package/dist/{run-record-CbUi2adH.js → run-record-CIflWk6i.js} +2 -2
- package/dist/{run-record-CbUi2adH.js.map → run-record-CIflWk6i.js.map} +1 -1
- package/dist/{runtime-rollouts-kGn1K5ut.js → runtime-rollouts-CfRyjk60.js} +2 -2
- package/dist/{runtime-rollouts-kGn1K5ut.js.map → runtime-rollouts-CfRyjk60.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-kwO-sgCq.d.ts → search-kernel-Ds2zILpY.d.ts} +4 -4
- package/dist/{search-kernel-kwO-sgCq.d.ts.map → search-kernel-Ds2zILpY.d.ts.map} +1 -1
- package/dist/{search-ledger-CV_bQQed.js → search-ledger-Dk-yk5Li.js} +4 -4
- package/dist/{search-ledger-CV_bQQed.js.map → search-ledger-Dk-yk5Li.js.map} +1 -1
- package/dist/{search-ledger-file-DTBD6X-y.js → search-ledger-file-BhOdgYIt.js} +3 -3
- package/dist/{search-ledger-file-DTBD6X-y.js.map → search-ledger-file-BhOdgYIt.js.map} +1 -1
- package/dist/{search-shipper-CA3ooBbC.js → search-shipper-Dm-_Dtvy.js} +3 -3
- package/dist/{search-shipper-CA3ooBbC.js.map → search-shipper-Dm-_Dtvy.js.map} +1 -1
- package/dist/{search-summary-DBMjdecs.js → search-summary-BSftVrGY.js} +5 -5
- package/dist/{search-summary-DBMjdecs.js.map → search-summary-BSftVrGY.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/{sequential-BPbvgzfe.js → sequential-CqG6aLWS.js} +3 -3
- package/dist/{sequential-BPbvgzfe.js.map → sequential-CqG6aLWS.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/{single-run-lock-BGlW3OSk.js → single-run-lock-CUj2tjxT.js} +2 -2
- package/dist/{single-run-lock-BGlW3OSk.js.map → single-run-lock-CUj2tjxT.js.map} +1 -1
- package/dist/{skillopt-optimization-method-D72XZZfR.js → skillopt-optimization-method-DYwEndON.js} +12 -12
- package/dist/{skillopt-optimization-method-D72XZZfR.js.map → skillopt-optimization-method-DYwEndON.js.map} +1 -1
- package/dist/{statistical-heldout-_dXihc9T.d.ts → statistical-heldout--0b1lgx4.d.ts} +6 -282
- package/dist/statistical-heldout--0b1lgx4.d.ts.map +1 -0
- package/dist/{statistical-heldout-NBxC7jGo.js → statistical-heldout-D6i58CJ5.js} +3 -3
- package/dist/{statistical-heldout-NBxC7jGo.js.map → statistical-heldout-D6i58CJ5.js.map} +1 -1
- package/dist/statistics-DCZIC-qT.js +2627 -0
- package/dist/statistics-DCZIC-qT.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-0La5vejY.d.ts → summary-report-Cv1AC-iv.d.ts} +2 -2
- package/dist/{summary-report-0La5vejY.d.ts.map → summary-report-Cv1AC-iv.d.ts.map} +1 -1
- package/dist/{summary-report-C3IJvp0i.js → summary-report-D_uussI3.js} +4 -52
- package/dist/summary-report-D_uussI3.js.map +1 -0
- package/dist/supervisor-run/index.d.ts +2 -2
- package/dist/supervisor-run/index.js +1 -1
- package/dist/{systemone-CBvL1gx-.d.ts → systemone-C3xyEKvG.d.ts} +7 -7
- package/dist/{systemone-CBvL1gx-.d.ts.map → systemone-C3xyEKvG.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-DEhKfiIE.js} +2 -3
- package/dist/{tool-waste-Czt3aWID.js.map → tool-waste-DEhKfiIE.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-DPwgM2LX.js → tree-B2y1UR8o.js} +5 -7
- package/dist/{tree-DPwgM2LX.js.map → tree-B2y1UR8o.js.map} +1 -1
- package/dist/{types-DNB9hIXa.d.ts → types-BAJ2Hb-d.d.ts} +3 -2
- package/dist/types-BAJ2Hb-d.d.ts.map +1 -0
- package/dist/{types-D91tnhzf.d.ts → types-BwF--ZRz.d.ts} +2 -2
- package/dist/{types-D91tnhzf.d.ts.map → types-BwF--ZRz.d.ts.map} +1 -1
- package/dist/{types-CBkDo7ja.d.ts → types-CeMZYsNF.d.ts} +6 -5
- package/dist/types-CeMZYsNF.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 +38 -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-Bqqvv9Tk.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-DWiBvJVM.js.map +0 -1
- package/dist/index-B1Bm9oJA.d.ts.map +0 -1
- package/dist/index-BAPkHt5H.d.ts.map +0 -1
- package/dist/index-BJM4rwP2.d.ts.map +0 -1
- package/dist/index-C3t17kHu.d.ts.map +0 -1
- package/dist/journal-C1uLJi0w.js.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-_dXihc9T.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-CBkDo7ja.d.ts.map +0 -1
- package/dist/types-DNB9hIXa.d.ts.map +0 -1
|
@@ -1,22 +1,20 @@
|
|
|
1
1
|
import { c as errorMessage, s as ValidationError, t as AgentEvalError } from "./errors-DeEEV9Vx.js";
|
|
2
2
|
import { a as hashCanonical, i as compareCodeUnits, o as jsonDocument, r as canonicalString } from "./canonical-CicJlINA.js";
|
|
3
|
-
import {
|
|
4
|
-
import {
|
|
5
|
-
import {
|
|
6
|
-
import { o as
|
|
7
|
-
import
|
|
8
|
-
import {
|
|
9
|
-
import "./ledger-core-CfT-FzPf.js";
|
|
10
|
-
import { M as fsCampaignStorage, b as AnalystFindingSchema, i as startExternalOptimizerModelProxy, j as createRunCostLedger, r as runWithCleanup, v as resolveExternalOptimizerProcessLimits } from "./external-optimizer-subprocess-B44kOfZb.js";
|
|
3
|
+
import { ct as meanOrNull, it as summarizeNumberSeries, p as pairedBootstrap, st as mean$1 } from "./statistics-DCZIC-qT.js";
|
|
4
|
+
import { o as withLedgerFileLock, s as writeLedgerFileAtomically } from "./journal-CTX5uK-n.js";
|
|
5
|
+
import { a as resolveModelPricing } from "./metrics-zALlR17s.js";
|
|
6
|
+
import { a as CostLedgerPersistenceError, i as CostCeilingReachedError, n as CostAccountingIncompleteError, o as CostReceiptCaptureError, r as CostCallConflictError, s as CostReservationExceededError, t as CostLedger } from "./cost-ledger-DfhStGcZ.js";
|
|
7
|
+
import "./ledger-core-24IxvmVY.js";
|
|
8
|
+
import { M as fsCampaignStorage, b as AnalystFindingSchema, i as startExternalOptimizerModelProxy, j as createRunCostLedger, r as runWithCleanup, v as resolveExternalOptimizerProcessLimits } from "./external-optimizer-subprocess-_C_2yriN.js";
|
|
11
9
|
import { c as redactText } from "./redact-zp_ILC4l.js";
|
|
12
10
|
import { i as makeFinding } from "./types-CL1_N7AZ.js";
|
|
13
|
-
import { t as acquireSingleRunLock } from "./single-run-lock-
|
|
11
|
+
import { t as acquireSingleRunLock } from "./single-run-lock-CUj2tjxT.js";
|
|
14
12
|
import { a as LlmCallError, n as isRecord, o as LlmResponseError } from "./json-DtvZNAU9.js";
|
|
15
|
-
import { A as RawAnalystFindingSchema, U as assertValidAnalystUsageReceipt, W as usageReceiptFromCostLedger, j as evidenceRefsFromRawFinding, k as RAW_FINDING_SCHEMA_PROMPT, m as TRACE_ANALYSIS_LIMITS, n as runTraceAnalyst } from "./kind-factory-
|
|
16
|
-
import { n as callLlmJson } from "./llm-client-
|
|
17
|
-
import { t as createDspyRlmTraceEngine } from "./dspy-rlm-engine-
|
|
18
|
-
import { i as otlpTextToTraceAnalysisStore, n as DEFAULT_MAX_TRACE_FILE_BYTES, t as BufferTraceStore } from "./store-otlp-
|
|
19
|
-
import "./external-optimizer-process-
|
|
13
|
+
import { A as RawAnalystFindingSchema, U as assertValidAnalystUsageReceipt, W as usageReceiptFromCostLedger, j as evidenceRefsFromRawFinding, k as RAW_FINDING_SCHEMA_PROMPT, m as TRACE_ANALYSIS_LIMITS, n as runTraceAnalyst } from "./kind-factory-CV0FNCMM.js";
|
|
14
|
+
import { n as callLlmJson } from "./llm-client-DMMSg-Ro.js";
|
|
15
|
+
import { t as createDspyRlmTraceEngine } from "./dspy-rlm-engine-cWyn8G1a.js";
|
|
16
|
+
import { i as otlpTextToTraceAnalysisStore, n as DEFAULT_MAX_TRACE_FILE_BYTES, t as BufferTraceStore } from "./store-otlp-C-jyj3WX.js";
|
|
17
|
+
import "./external-optimizer-process-2ImGH_LR.js";
|
|
20
18
|
import { t as assertEqualDeclarativeTerms } from "./equal-terms-K11VHmR3.js";
|
|
21
19
|
import { c as runPrimeExchange, l as decodeReplyRows, n as buildPrimePrompt, o as primeProtocolSha256, s as projectPrimeTrajectory, t as analystUsageReceiptFromPrimeUsage } from "./prime-protocol-CrhpXRz9.js";
|
|
22
20
|
import { t as nodeHttpPrimeBridgeTransport } from "./prime-bridge-transport-Csd5SQg7.js";
|
|
@@ -1863,7 +1861,7 @@ Object.freeze([
|
|
|
1863
1861
|
"package.json",
|
|
1864
1862
|
"pnpm-lock.yaml"
|
|
1865
1863
|
]);
|
|
1866
|
-
const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 = "
|
|
1864
|
+
const ANALYST_BENCHMARK_DEPENDENCY_LOCK_SHA256 = "5168b25401e307b8b6d6cd305bcc7d3fcfe5619a9977f54ba33e7eba9a899a48";
|
|
1867
1865
|
const ANALYST_BENCHMARK_EVIDENCE_DEPENDENCY_LOCK_SHA256 = "1e03f2daed356d60316aabefb407ec1e437ac94d408d61eea4ae096e9c6fbb5b";
|
|
1868
1866
|
const ANALYST_BENCHMARK_EVIDENCE_IMPLEMENTATION_SHA256 = "4dba263b6256a30d56c7fdb2d992d3a953c0035d731f359b704db806f68f75ac";
|
|
1869
1867
|
const ANALYST_BENCHMARK_IMPLEMENTATION_FILES = Object.freeze([
|
|
@@ -1982,6 +1980,7 @@ const ANALYST_BENCHMARK_IMPLEMENTATION_FILES = Object.freeze([
|
|
|
1982
1980
|
"src/metrics.ts",
|
|
1983
1981
|
"src/record-id.ts",
|
|
1984
1982
|
"src/statistics/agreement-irr.ts",
|
|
1983
|
+
"src/statistics/cluster.ts",
|
|
1985
1984
|
"src/statistics/comparison-effects.ts",
|
|
1986
1985
|
"src/statistics/descriptive.ts",
|
|
1987
1986
|
"src/statistics/distribution-summary.ts",
|
|
@@ -2019,7 +2018,7 @@ const ANALYST_BENCHMARK_IMPLEMENTATION_FILES = Object.freeze([
|
|
|
2019
2018
|
"src/trace/redaction/detectors.ts",
|
|
2020
2019
|
"src/verdict-cache.ts"
|
|
2021
2020
|
]);
|
|
2022
|
-
const ANALYST_BENCHMARK_IMPLEMENTATION_SHA256 = "
|
|
2021
|
+
const ANALYST_BENCHMARK_IMPLEMENTATION_SHA256 = "4bde21abd8be95c3f261d22b0207e90f9b572a7a1ca1eaabf972ca9a598d90d5";
|
|
2023
2022
|
// src/analyst/benchmark-evidence-validation.ts
|
|
2024
2023
|
const MIN_ACTION_EXCERPT_CHARACTERS = 12;
|
|
2025
2024
|
const MAX_LABEL_SCAN_DEPTH = 64;
|
|
@@ -6856,4 +6855,4 @@ function shellQuote(value) {
|
|
|
6856
6855
|
}
|
|
6857
6856
|
export { agentRxBenchmarkCase as A, ANALYST_BENCHMARK_COST_LEDGER_FILE as C, AGENT_RX_UPSTREAM_REVISION as D, ANALYST_BENCHMARK_OBSERVATIONS_FILE as E, runAnalystBenchmark as F, traceStoreEvidenceResolver as I, normalizeAgentRxCategory as M, externalId as N, codeTraceBenchCase as O, positiveStep as P, ANALYST_BENCHMARK_IMPLEMENTATION_FILES as S, ANALYST_BENCHMARK_MANIFEST_FILE as T, readAnalystBenchmarkArtifact as _, runInlineAnalystDefinition as a, ANALYST_BENCHMARK_EVIDENCE_DEPENDENCY_LOCK_SHA256 as b, publicRlmAnalystDefinition as c, publicDirectAnalystDefinition as d, runChunkedAnalystDefinition as f, expandCodeTraceFailureBlocks as g, analystDefinitionProtocolSha256 as h, primeCodeTraceAnalystDefinition as i, agentRxPredictionsToFindings as j, codeTracerPredictionsToFindings as k, runReplVariableAnalystDefinition as l, analystDefinitionAsymmetries as m, createPrimeBenchmarkRunner as n, loadPublicBenchmarkRows as o, AnalystExpressivenessError as p, primeAnalystProtocolSha256 as r, createPublicBenchmarkRlmRunner as s, runAnalystBenchmarkCommand as t, createPublicBenchmarkDirectRunner as u, CODE_TRACE_BENCH_ANALYST_PROMPT as v, ANALYST_BENCHMARK_LOCAL_RECEIPT_FILE as w, ANALYST_BENCHMARK_EVIDENCE_IMPLEMENTATION_SHA256 as x, publicBenchmarkProtocolSha256 as y };
|
|
6858
6857
|
|
|
6859
|
-
//# sourceMappingURL=benchmark-command-
|
|
6858
|
+
//# sourceMappingURL=benchmark-command-BGZD77Un.js.map
|