@tangle-network/agent-eval 0.150.2 → 0.161.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +149 -1
- package/README.md +7 -3
- package/dist/{active-curriculum-C4mk67HP.js → active-curriculum-CD5TU2yW.js} +3 -13
- package/dist/active-curriculum-CD5TU2yW.js.map +1 -0
- package/dist/{agent-profile-cell-BkcRDikH.d.ts → agent-profile-cell-CTOZJUuE.d.ts} +4 -2
- package/dist/agent-profile-cell-CTOZJUuE.d.ts.map +1 -0
- package/dist/analyst/index.d.ts +19 -36
- package/dist/analyst/index.d.ts.map +1 -1
- package/dist/analyst/index.js +8 -8
- package/dist/analyst/index.js.map +1 -1
- package/dist/{backend-integrity-DOCa_QrR.d.ts → backend-integrity-DxuQCu_A.d.ts} +4 -3
- package/dist/backend-integrity-DxuQCu_A.d.ts.map +1 -0
- package/dist/{benchmark-BtAWA8nT.d.ts → benchmark-CGPp-kDC.d.ts} +3 -3
- package/dist/{benchmark-BtAWA8nT.d.ts.map → benchmark-CGPp-kDC.d.ts.map} +1 -1
- package/dist/{benchmark-command-BU1Las59.js → benchmark-command-BVtaq_ve.js} +26 -31
- package/dist/benchmark-command-BVtaq_ve.js.map +1 -0
- package/dist/benchmarks/index.d.ts +6 -19
- package/dist/benchmarks/index.d.ts.map +1 -1
- package/dist/benchmarks/index.js +4 -4
- package/dist/benchmarks/index.js.map +1 -1
- package/dist/builder-eval/index.d.ts +3 -3
- package/dist/builder-eval/index.js +2 -2
- package/dist/campaign/index.d.ts +9 -9
- package/dist/campaign/index.js +7 -7
- package/dist/{campaign-la-gEYNz.js → campaign-BSmOwskD.js} +77 -795
- package/dist/campaign-BSmOwskD.js.map +1 -0
- package/dist/{canonical-D-XsTQ6_.js → canonical-IL-Bu-14.js} +26 -2
- package/dist/canonical-IL-Bu-14.js.map +1 -0
- package/dist/{capture-fetch-BBVFzhkk.d.ts → capture-fetch-CqwsJkkG.d.ts} +3 -3
- package/dist/{capture-fetch-BBVFzhkk.d.ts.map → capture-fetch-CqwsJkkG.d.ts.map} +1 -1
- package/dist/{chat-client-Bvmxedyv.js → chat-client-DlMlAeYI.js} +5 -55
- package/dist/{chat-client-Bvmxedyv.js.map → chat-client-DlMlAeYI.js.map} +1 -1
- package/dist/chat-json-call-6g5sJobJ.js +53 -0
- package/dist/chat-json-call-6g5sJobJ.js.map +1 -0
- package/dist/cli.js +54 -19
- package/dist/cli.js.map +1 -1
- package/dist/{client-LIuo-KPv.js → client-CX7KqIdB.js} +3 -3
- package/dist/client-CX7KqIdB.js.map +1 -0
- package/dist/{client-kPQYT_56.d.ts → client-L9VVPkim.d.ts} +4 -4
- package/dist/{client-kPQYT_56.d.ts.map → client-L9VVPkim.d.ts.map} +1 -1
- package/dist/contract/index.d.ts +13 -27
- package/dist/contract/index.d.ts.map +1 -1
- package/dist/contract/index.js +14 -17
- package/dist/contract/index.js.map +1 -1
- package/dist/{counterfactual--bpysZF0.d.ts → counterfactual-BaFUWK3H.d.ts} +4 -4
- package/dist/{counterfactual--bpysZF0.d.ts.map → counterfactual-BaFUWK3H.d.ts.map} +1 -1
- package/dist/{counterfactual-lDfCx0Uz.js → counterfactual-D_VWavVm.js} +2 -2
- package/dist/{counterfactual-lDfCx0Uz.js.map → counterfactual-D_VWavVm.js.map} +1 -1
- package/dist/{dataset-CJjKqQfA.d.ts → dataset-DQqhOCPt.d.ts} +5 -4
- package/dist/{dataset-CJjKqQfA.d.ts.map → dataset-DQqhOCPt.d.ts.map} +1 -1
- package/dist/{default-registry-Cw0Ohdoj.d.ts → default-registry-G9CKMNkc.d.ts} +7 -8
- package/dist/{default-registry-Cw0Ohdoj.d.ts.map → default-registry-G9CKMNkc.d.ts.map} +1 -1
- package/dist/{define-agent-eval-CEQWL9Hy.d.ts → define-agent-eval-Dx1JnPEa.d.ts} +26 -6
- package/dist/define-agent-eval-Dx1JnPEa.d.ts.map +1 -0
- package/dist/{define-agent-eval-C8V8sMqP.js → define-agent-eval-h-s-sI-v.js} +15 -9
- package/dist/define-agent-eval-h-s-sI-v.js.map +1 -0
- package/dist/{dspy-rlm-engine-CBYlPvNy.js → dspy-rlm-engine-DptEII26.js} +95 -15
- package/dist/dspy-rlm-engine-DptEII26.js.map +1 -0
- package/dist/{emitter-CPBAhxum.js → emitter-BpYFQPj4.js} +2 -18
- package/dist/emitter-BpYFQPj4.js.map +1 -0
- package/dist/{emitter-DGQGoLyj.d.ts → emitter-D_jYSGRd.d.ts} +4 -20
- package/dist/{emitter-DGQGoLyj.d.ts.map → emitter-D_jYSGRd.d.ts.map} +1 -1
- package/dist/{engine-BLzhNzoY.d.ts → engine-Cu5qD5Fc.d.ts} +9 -11
- package/dist/{engine-BLzhNzoY.d.ts.map → engine-Cu5qD5Fc.d.ts.map} +1 -1
- package/dist/{eval-campaign-CQuZrLR_.js → eval-campaign-BsXWL2-2.js} +17 -28
- package/dist/eval-campaign-BsXWL2-2.js.map +1 -0
- package/dist/{exact-types-ccQAyut1.d.ts → exact-types-qnexxJ1Z.d.ts} +2 -2
- package/dist/{exact-types-ccQAyut1.d.ts.map → exact-types-qnexxJ1Z.d.ts.map} +1 -1
- package/dist/{exec-y-DCLqK7.js → exec-D9WpA2p-.js} +2 -2
- package/dist/exec-D9WpA2p-.js.map +1 -0
- package/dist/experiment/index.d.ts +45 -11
- package/dist/experiment/index.d.ts.map +1 -1
- package/dist/experiment/index.js +30 -11
- package/dist/experiment/index.js.map +1 -1
- package/dist/{experiment-tracker-0MhuPArU.d.ts → experiment-tracker-DCO6Cz4s.d.ts} +2 -2
- package/dist/{experiment-tracker-0MhuPArU.d.ts.map → experiment-tracker-DCO6Cz4s.d.ts.map} +1 -1
- package/dist/{exporters-q9iL-2Jf.js → exporters-Df7TgHFv.js} +3 -3
- package/dist/exporters-Df7TgHFv.js.map +1 -0
- package/dist/{external-optimizer-contracts-DbLsm4Po.d.ts → external-optimizer-contracts-szBJ_1vh.d.ts} +2 -2
- package/dist/{external-optimizer-contracts-DbLsm4Po.d.ts.map → external-optimizer-contracts-szBJ_1vh.d.ts.map} +1 -1
- package/dist/{external-optimizer-process-x9oEXKsU.js → external-optimizer-process-WosTBChy.js} +4 -4
- package/dist/{external-optimizer-process-x9oEXKsU.js.map → external-optimizer-process-WosTBChy.js.map} +1 -1
- package/dist/{external-optimizer-subprocess-CKNb42oM.js → external-optimizer-subprocess-BIWbHpgD.js} +4 -4
- package/dist/{external-optimizer-subprocess-CKNb42oM.js.map → external-optimizer-subprocess-BIWbHpgD.js.map} +1 -1
- package/dist/{failure-cluster-BLURuWG4.d.ts → failure-cluster-CXL8NbEw.d.ts} +3 -3
- package/dist/{failure-cluster-BLURuWG4.d.ts.map → failure-cluster-CXL8NbEw.d.ts.map} +1 -1
- package/dist/{feedback-trajectory-DpTTjo0q.d.ts → feedback-trajectory-B3ZHaHV_.d.ts} +7 -7
- package/dist/{feedback-trajectory-DpTTjo0q.d.ts.map → feedback-trajectory-B3ZHaHV_.d.ts.map} +1 -1
- package/dist/fuzz.js +1 -1
- package/dist/{hf-dataset-XggBupCr.js → hf-dataset-D8_RNIis.js} +4 -4
- package/dist/{hf-dataset-XggBupCr.js.map → hf-dataset-D8_RNIis.js.map} +1 -1
- package/dist/hosted/index.d.ts +3 -14
- package/dist/hosted/index.d.ts.map +1 -1
- package/dist/hosted/index.js +2 -2
- package/dist/{index-Aj3WO3_a.d.ts → index-CGtH1piv.d.ts} +48 -26
- package/dist/index-CGtH1piv.d.ts.map +1 -0
- package/dist/{index-BNPtkBPf.d.ts → index-D-IiQIBB.d.ts} +5 -10
- package/dist/index-D-IiQIBB.d.ts.map +1 -0
- package/dist/{index-IQccV3Ou.d.ts → index-D-V8gCs_.d.ts} +13 -90
- package/dist/index-D-V8gCs_.d.ts.map +1 -0
- package/dist/{index-B8Ui1mr1.d.ts → index-lfaSeKSD.d.ts} +18 -2
- package/dist/index-lfaSeKSD.d.ts.map +1 -0
- package/dist/index-vrJugRal.d.ts +1 -0
- package/dist/index.d.ts +68 -56
- package/dist/index.d.ts.map +1 -1
- package/dist/index.js +59 -110
- package/dist/index.js.map +1 -1
- package/dist/{insight-report-BeT8KCgI.d.ts → insight-report-DRe8LB6d.d.ts} +4 -4
- package/dist/{insight-report-BeT8KCgI.d.ts.map → insight-report-DRe8LB6d.d.ts.map} +1 -1
- package/dist/{integrity-DL91tucI.js → integrity-CyWSSoQS.js} +2 -2
- package/dist/{integrity-DL91tucI.js.map → integrity-CyWSSoQS.js.map} +1 -1
- package/dist/{integrity-B0dZ96EO.d.ts → integrity-DUNX9Fao.d.ts} +3 -3
- package/dist/{integrity-B0dZ96EO.d.ts.map → integrity-DUNX9Fao.d.ts.map} +1 -1
- package/dist/{kind-factory-DmAa0h3K.js → kind-factory-DY8FdoXf.js} +3 -71
- package/dist/kind-factory-DY8FdoXf.js.map +1 -0
- package/dist/ledger-core/index.d.ts +2 -2
- package/dist/ledger-core/index.js +3 -3
- package/dist/{ledger-core-DTae9rv_.js → ledger-core-BOzlRygb.js} +2 -2
- package/dist/{ledger-core-DTae9rv_.js.map → ledger-core-BOzlRygb.js.map} +1 -1
- package/dist/{llm-client-Bg32RW0j.js → llm-client-hgDieDNN.js} +53 -98
- package/dist/llm-client-hgDieDNN.js.map +1 -0
- package/dist/{llm-judge-BqqMS8t7.js → llm-judge-BhasIPFT.js} +1135 -77
- package/dist/llm-judge-BhasIPFT.js.map +1 -0
- package/dist/{matrix-DrVnRp4G.d.ts → matrix-eXKRMHnL.d.ts} +74 -72
- package/dist/matrix-eXKRMHnL.d.ts.map +1 -0
- package/dist/meta-eval/index.d.ts +8 -6
- package/dist/meta-eval/index.d.ts.map +1 -1
- package/dist/meta-eval/index.js +8 -6
- package/dist/meta-eval/index.js.map +1 -1
- package/dist/{mint-BV6tLVWl.js → mint-DfODW1KW.js} +3 -3
- package/dist/{mint-BV6tLVWl.js.map → mint-DfODW1KW.js.map} +1 -1
- package/dist/multishot/golden/index.d.ts +2 -8
- package/dist/multishot/golden/index.d.ts.map +1 -1
- package/dist/multishot/golden/index.js +56 -86
- package/dist/multishot/golden/index.js.map +1 -1
- package/dist/multishot/index.d.ts +11 -46
- package/dist/multishot/index.d.ts.map +1 -1
- package/dist/multishot/index.js +30 -83
- package/dist/multishot/index.js.map +1 -1
- package/dist/openapi.json +1 -1
- package/dist/{opencode-sqlite-DJWAXLms.js → opencode-sqlite-eK6HW6dr.js} +2 -6
- package/dist/{opencode-sqlite-DJWAXLms.js.map → opencode-sqlite-eK6HW6dr.js.map} +1 -1
- package/dist/pipelines/index.d.ts +5 -5
- package/dist/pipelines/index.js +3 -3
- package/dist/{pre-registration-zFSLEiFU.d.ts → pre-registration-CzFCcwYk.d.ts} +55 -40
- package/dist/pre-registration-CzFCcwYk.d.ts.map +1 -0
- package/dist/pre-registration-KN9jkh58.js +110 -0
- package/dist/pre-registration-KN9jkh58.js.map +1 -0
- package/dist/{produced-state-Bnq4FaDO.js → produced-state-DZ89riy5.js} +8 -8
- package/dist/produced-state-DZ89riy5.js.map +1 -0
- package/dist/profile-cell.d.ts +1 -1
- package/dist/profile-cell.js +31 -5
- package/dist/profile-cell.js.map +1 -1
- package/dist/{promotion-policy-DLOUkYhI.d.ts → promotion-policy-DtnOIZvk.d.ts} +2 -2
- package/dist/{promotion-policy-DLOUkYhI.d.ts.map → promotion-policy-DtnOIZvk.d.ts.map} +1 -1
- package/dist/{query-Di7eEQ79.js → query-CHmMP42p.js} +20 -11
- package/dist/query-CHmMP42p.js.map +1 -0
- package/dist/{query-CJ_DX8vl.d.ts → query-DxPYqpmT.d.ts} +10 -4
- package/dist/query-DxPYqpmT.d.ts.map +1 -0
- package/dist/raw-provider-sink-BU29Sh8h.d.ts +134 -0
- package/dist/raw-provider-sink-BU29Sh8h.d.ts.map +1 -0
- package/dist/{registry-BQwrSYpC.d.ts → registry-8You7OK1.d.ts} +5 -7
- package/dist/{registry-BQwrSYpC.d.ts.map → registry-8You7OK1.d.ts.map} +1 -1
- package/dist/{release-confidence-BknrpBnO.js → release-confidence-DKfD2RYU.js} +28 -14
- package/dist/release-confidence-DKfD2RYU.js.map +1 -0
- package/dist/{release-confidence-4XrqlpFD.d.ts → release-confidence-Dqt0NFep.d.ts} +7 -6
- package/dist/release-confidence-Dqt0NFep.d.ts.map +1 -0
- package/dist/reporting.d.ts +3 -3
- package/dist/reporting.js +3 -3
- package/dist/{researcher-DJnoUE8c.d.ts → researcher-Cz565b7D.d.ts} +34 -21
- package/dist/researcher-Cz565b7D.d.ts.map +1 -0
- package/dist/{reward-hacking-62tojkQd.d.ts → reward-hacking-MBf7qpSB.d.ts} +2 -2
- package/dist/{reward-hacking-62tojkQd.d.ts.map → reward-hacking-MBf7qpSB.d.ts.map} +1 -1
- package/dist/{reward-hacking-C0x0xihA.js → reward-hacking-t4lB1yt8.js} +2 -2
- package/dist/{reward-hacking-C0x0xihA.js.map → reward-hacking-t4lB1yt8.js.map} +1 -1
- package/dist/rl.d.ts +11 -42
- package/dist/rl.d.ts.map +1 -1
- package/dist/rl.js +41 -24
- package/dist/rl.js.map +1 -1
- package/dist/rollout/index.d.ts +3 -3
- package/dist/rollout/index.js +7 -7
- package/dist/{rollout-ytVQ7WT8.js → rollout-Dm2tSdiQ.js} +6 -6
- package/dist/{rollout-ytVQ7WT8.js.map → rollout-Dm2tSdiQ.js.map} +1 -1
- package/dist/{rubric-predictive-validity-CzxLoZge.js → rubric-predictive-validity-CK8SCOg-.js} +5 -15
- package/dist/rubric-predictive-validity-CK8SCOg-.js.map +1 -0
- package/dist/{rubric-predictive-validity-C7LnNvF2.d.ts → rubric-predictive-validity-CxycqzX5.d.ts} +4 -3
- package/dist/rubric-predictive-validity-CxycqzX5.d.ts.map +1 -0
- package/dist/{run-record-D2lDdSAz.js → run-record-BC0ebuRP.js} +2 -2
- package/dist/{run-record-D2lDdSAz.js.map → run-record-BC0ebuRP.js.map} +1 -1
- package/dist/{run-record-DVV82Gwh.d.ts → run-record-VVy4T9OW.d.ts} +3 -3
- package/dist/{run-record-DVV82Gwh.d.ts.map → run-record-VVy4T9OW.d.ts.map} +1 -1
- package/dist/{schema-BtVldJ3T.d.ts → schema-Bjgdsn73.d.ts} +2 -4
- package/dist/{schema-BtVldJ3T.d.ts.map → schema-Bjgdsn73.d.ts.map} +1 -1
- package/dist/{schema-Cef2cFmb.d.ts → schema-BzWDXhOR.d.ts} +2 -5
- package/dist/schema-BzWDXhOR.d.ts.map +1 -0
- package/dist/{schema-C6DW4ZHR.js → schema-C1aaAxTf.js} +2 -2
- package/dist/schema-C1aaAxTf.js.map +1 -0
- package/dist/{schema-CRhEY1SO.js → schema-k6ZBftVv.js} +2 -8
- package/dist/{schema-CRhEY1SO.js.map → schema-k6ZBftVv.js.map} +1 -1
- package/dist/{semantic-concept-judge-laMCnTLn.js → semantic-concept-judge-BSkKKHeq.js} +14 -38
- package/dist/semantic-concept-judge-BSkKKHeq.js.map +1 -0
- package/dist/{sequential-eprocess-CbUt2htw.js → sequential-eprocess-D1jKoihe.js} +49 -2
- package/dist/sequential-eprocess-D1jKoihe.js.map +1 -0
- package/dist/{sequential-C458DXNf.js → sequential-rYW-Ophm.js} +41 -16
- package/dist/sequential-rYW-Ophm.js.map +1 -0
- package/dist/{series-convergence-BxKEgBwA.d.ts → series-convergence-D9WgpXGi.d.ts} +2 -2
- package/dist/{series-convergence-BxKEgBwA.d.ts.map → series-convergence-D9WgpXGi.d.ts.map} +1 -1
- package/dist/{server-dIWwF3j_.js → server-BtFd4uzB.js} +19 -42
- package/dist/server-BtFd4uzB.js.map +1 -0
- package/dist/{skillopt-optimization-method-CPBlTcj5.js → skillopt-optimization-method-DbaekMcn.js} +794 -8
- package/dist/skillopt-optimization-method-DbaekMcn.js.map +1 -0
- package/dist/{skillopt-optimization-method-BDD_o1xE.d.ts → skillopt-optimization-method-x7TTF23P.d.ts} +20 -7
- package/dist/{skillopt-optimization-method-BDD_o1xE.d.ts.map → skillopt-optimization-method-x7TTF23P.d.ts.map} +1 -1
- package/dist/{statistical-heldout-_woZ9q9j.d.ts → statistical-heldout-Cy3EhjlC.d.ts} +21 -8
- package/dist/statistical-heldout-Cy3EhjlC.d.ts.map +1 -0
- package/dist/{steps-AmkT-GIM.d.ts → steps-CiNVJry_.d.ts} +2 -17
- package/dist/steps-CiNVJry_.d.ts.map +1 -0
- package/dist/{store-CT9YIIve.d.ts → store-B06JdC56.d.ts} +2 -2
- package/dist/{store-CT9YIIve.d.ts.map → store-B06JdC56.d.ts.map} +1 -1
- package/dist/{store-otlp-CDYWW_8N.js → store-otlp-C_Rq5I4D.js} +2 -2
- package/dist/{store-otlp-CDYWW_8N.js.map → store-otlp-C_Rq5I4D.js.map} +1 -1
- package/dist/{store-tool-spans-Br2_IUhm.d.ts → store-tool-spans-DPUG7UUY.d.ts} +6 -6
- package/dist/{store-tool-spans-Br2_IUhm.d.ts.map → store-tool-spans-DPUG7UUY.d.ts.map} +1 -1
- package/dist/{store-tool-spans-CykkbOlv.js → store-tool-spans-Dlh9vkFK.js} +3 -3
- package/dist/{store-tool-spans-CykkbOlv.js.map → store-tool-spans-Dlh9vkFK.js.map} +1 -1
- package/dist/storyboard/index.d.ts +1 -1
- package/dist/{summary-report-DW2bEpdB.js → summary-report-BI5hUtvK.js} +6 -16
- package/dist/summary-report-BI5hUtvK.js.map +1 -0
- package/dist/{summary-report-B__Y5ub3.d.ts → summary-report-CC07PhEL.d.ts} +6 -5
- package/dist/summary-report-CC07PhEL.d.ts.map +1 -0
- package/dist/supervisor-run/index.d.ts +3 -16
- package/dist/supervisor-run/index.d.ts.map +1 -1
- package/dist/supervisor-run/index.js +3 -3
- package/dist/supervisor-run/index.js.map +1 -1
- package/dist/{task-failure-attributes--ZTP3tYO.js → task-failure-attributes-DTl-7-Kw.js} +3 -3
- package/dist/{task-failure-attributes--ZTP3tYO.js.map → task-failure-attributes-DTl-7-Kw.js.map} +1 -1
- package/dist/{tool-groups-B4tqh8jB.d.ts → tool-groups-Ci8i9ErB.d.ts} +3 -3
- package/dist/tool-groups-Ci8i9ErB.d.ts.map +1 -0
- package/dist/{tool-waste-C-VHSRwF.js → tool-waste-BqzmVdJk.js} +2 -2
- package/dist/{tool-waste-C-VHSRwF.js.map → tool-waste-BqzmVdJk.js.map} +1 -1
- package/dist/{tool-waste-DjRDEsuI.d.ts → tool-waste-Dro0gJi3.d.ts} +4 -4
- package/dist/{tool-waste-DjRDEsuI.d.ts.map → tool-waste-Dro0gJi3.d.ts.map} +1 -1
- package/dist/trace-repair/index.d.ts +4 -77
- package/dist/trace-repair/index.d.ts.map +1 -1
- package/dist/trace-repair/index.js +5 -15
- package/dist/trace-repair/index.js.map +1 -1
- package/dist/traces.d.ts +13 -23
- package/dist/traces.d.ts.map +1 -1
- package/dist/traces.js +9 -20
- package/dist/traces.js.map +1 -1
- package/dist/{trajectory-YC15QDYQ.d.ts → trajectory-Bi157Gun.d.ts} +3 -3
- package/dist/{trajectory-YC15QDYQ.d.ts.map → trajectory-Bi157Gun.d.ts.map} +1 -1
- package/dist/trajectory-replay/index.d.ts +5 -5
- package/dist/trajectory-replay/index.js +5 -5
- package/dist/{provenance-oA4-zUqm.d.ts → transient-failure-DKF5Mofa.d.ts} +468 -13
- package/dist/transient-failure-DKF5Mofa.d.ts.map +1 -0
- package/dist/types-B3jzCp0p.js.map +1 -1
- package/dist/{types-CLAwnY-L.d.ts → types-BPb2Kf_C2.d.ts} +3 -3
- package/dist/types-BPb2Kf_C2.d.ts.map +1 -0
- package/dist/types-Bfk0uxRj.d.ts +443 -0
- package/dist/types-Bfk0uxRj.d.ts.map +1 -0
- package/dist/{types-DdFNuyxQ.d.ts → types-D4s7Z6nq.d.ts} +30 -6
- package/dist/types-D4s7Z6nq.d.ts.map +1 -0
- package/dist/{types-B2NsbrNy.d.ts → types-D9ssmxKL.d.ts} +3 -3
- package/dist/{types-B2NsbrNy.d.ts.map → types-D9ssmxKL.d.ts.map} +1 -1
- package/dist/{types-I5WwVzQ7.d.ts → types-DeIUdzNd.d.ts} +2 -2
- package/dist/{types-I5WwVzQ7.d.ts.map → types-DeIUdzNd.d.ts.map} +1 -1
- package/dist/{verdict-BndeTAh_.js → verdict-B0xltqu6.js} +2 -2
- package/dist/{verdict-BndeTAh_.js.map → verdict-B0xltqu6.js.map} +1 -1
- package/dist/verdict-cache-CdVVTVmn.js +88 -0
- package/dist/verdict-cache-CdVVTVmn.js.map +1 -0
- package/dist/wire/index.d.ts +21 -111
- package/dist/wire/index.d.ts.map +1 -1
- package/dist/wire/index.js +2 -2
- package/docs/building-doctrine.md +3 -3
- package/docs/campaign-proposers.md +41 -10
- package/docs/design/statistics-decisions.md +89 -1
- package/docs/eval-surface-map.md +14 -0
- package/docs/experiment.md +19 -2
- package/docs/feedback-trajectories.md +1 -1
- package/docs/multishot-golden-records.md +4 -4
- package/docs/public-api.md +1616 -0
- package/docs/research-report-methodology.md +1 -1
- package/docs/search-history-receipts.md +39 -1
- package/docs/trace-analysis.md +1 -1
- package/docs/trace-repair-admission.md +1 -1
- package/docs/trace-repair-continuation.md +1 -1
- package/docs/verdicts.md +24 -0
- package/package.json +6 -2
- package/dist/active-curriculum-C4mk67HP.js.map +0 -1
- package/dist/agent-profile-cell-BkcRDikH.d.ts.map +0 -1
- package/dist/backend-integrity-DOCa_QrR.d.ts.map +0 -1
- package/dist/benchmark-command-BU1Las59.js.map +0 -1
- package/dist/campaign-la-gEYNz.js.map +0 -1
- package/dist/canonical-D-XsTQ6_.js.map +0 -1
- package/dist/client-LIuo-KPv.js.map +0 -1
- package/dist/define-agent-eval-C8V8sMqP.js.map +0 -1
- package/dist/define-agent-eval-CEQWL9Hy.d.ts.map +0 -1
- package/dist/dspy-rlm-engine-CBYlPvNy.js.map +0 -1
- package/dist/emitter-CPBAhxum.js.map +0 -1
- package/dist/eval-campaign-CQuZrLR_.js.map +0 -1
- package/dist/exec-y-DCLqK7.js.map +0 -1
- package/dist/exporters-q9iL-2Jf.js.map +0 -1
- package/dist/index-Aj3WO3_a.d.ts.map +0 -1
- package/dist/index-B8Ui1mr1.d.ts.map +0 -1
- package/dist/index-BNPtkBPf.d.ts.map +0 -1
- package/dist/index-C1ravkGA.d.ts +0 -1
- package/dist/index-IQccV3Ou.d.ts.map +0 -1
- package/dist/kind-factory-DmAa0h3K.js.map +0 -1
- package/dist/llm-client-Bg32RW0j.js.map +0 -1
- package/dist/llm-judge-BqqMS8t7.js.map +0 -1
- package/dist/matrix-DrVnRp4G.d.ts.map +0 -1
- package/dist/pre-registration-DakwTRXk.js +0 -96
- package/dist/pre-registration-DakwTRXk.js.map +0 -1
- package/dist/pre-registration-zFSLEiFU.d.ts.map +0 -1
- package/dist/produced-state-Bnq4FaDO.js.map +0 -1
- package/dist/provenance-oA4-zUqm.d.ts.map +0 -1
- package/dist/query-CJ_DX8vl.d.ts.map +0 -1
- package/dist/query-Di7eEQ79.js.map +0 -1
- package/dist/release-confidence-4XrqlpFD.d.ts.map +0 -1
- package/dist/release-confidence-BknrpBnO.js.map +0 -1
- package/dist/researcher-DJnoUE8c.d.ts.map +0 -1
- package/dist/rubric-predictive-validity-C7LnNvF2.d.ts.map +0 -1
- package/dist/rubric-predictive-validity-CzxLoZge.js.map +0 -1
- package/dist/schema-C6DW4ZHR.js.map +0 -1
- package/dist/schema-Cef2cFmb.d.ts.map +0 -1
- package/dist/semantic-concept-judge-laMCnTLn.js.map +0 -1
- package/dist/sequential-C458DXNf.js.map +0 -1
- package/dist/sequential-eprocess-CbUt2htw.js.map +0 -1
- package/dist/server-dIWwF3j_.js.map +0 -1
- package/dist/skillopt-optimization-method-CPBlTcj5.js.map +0 -1
- package/dist/statistical-heldout-_woZ9q9j.d.ts.map +0 -1
- package/dist/steps-AmkT-GIM.d.ts.map +0 -1
- package/dist/summary-report-B__Y5ub3.d.ts.map +0 -1
- package/dist/summary-report-DW2bEpdB.js.map +0 -1
- package/dist/tool-groups-B4tqh8jB.d.ts.map +0 -1
- package/dist/types-CLAwnY-L.d.ts.map +0 -1
- package/dist/types-DdFNuyxQ.d.ts.map +0 -1
- package/dist/types-jUBXJ7Iz.d.ts +0 -884
- package/dist/types-jUBXJ7Iz.d.ts.map +0 -1
- package/dist/verdict-cache-mZf5FEiY.js +0 -107
- package/dist/verdict-cache-mZf5FEiY.js.map +0 -1
package/dist/experiment/index.js
CHANGED
|
@@ -1,16 +1,18 @@
|
|
|
1
1
|
import { n as CaptureIntegrityError, s as ValidationError } from "../errors-Dngq5h35.js";
|
|
2
|
-
import {
|
|
2
|
+
import { r as canonicalString } from "../canonical-IL-Bu-14.js";
|
|
3
|
+
import { a as verifyManifest, i as signManifest, n as hashJson, r as manifestContentDigest, t as evaluateHypothesis } from "../pre-registration-KN9jkh58.js";
|
|
3
4
|
import { c as mulberry32 } from "../internal-BDHPCnjk.js";
|
|
4
5
|
import { a as requiredSampleSize, c as holm, i as requiredPairedSampleSize, n as mcnemarRequiredN, o as benjaminiHochberg, r as pairedMde, s as bonferroni, t as mcnemarPower } from "../power-and-mde-CHIrXJll.js";
|
|
5
6
|
import { f as mcnemar, g as pairedRiskDifferenceScore, h as pairedRiskDifferenceExact, m as pairedRiskDifference, n as pairArms, r as pairRunRecords, t as comparePairedArms, v as wilson } from "../paired-arms-D-XRF_fy.js";
|
|
6
7
|
import { r as pairedBootstrap, t as BOOTSTRAP_GATE_MIN_N } from "../paired-tests-BHIhYVdu.js";
|
|
7
|
-
import { t as eProcess } from "../sequential-eprocess-
|
|
8
|
-
import { n as contentHash } from "../verdict-cache-
|
|
8
|
+
import { t as eProcess } from "../sequential-eprocess-D1jKoihe.js";
|
|
9
|
+
import { n as contentHash } from "../verdict-cache-CdVVTVmn.js";
|
|
9
10
|
import { a as heldoutSignificance, o as pairHoldout, t as powerPreflight } from "../power-preflight-DEw-uC7q.js";
|
|
10
11
|
import { a as inMemoryExperimentStore, r as fileExperimentStore, t as ExperimentTracker } from "../experiment-tracker-Ym6rEQT1.js";
|
|
11
12
|
import { n as pairedEvalueSequence, r as sequentialCrossingHorizon } from "../sequential-CzK5DarL.js";
|
|
12
13
|
import { n as paretoPolicy, r as paretoSignificanceGate, t as buildEvidenceVector } from "../promotion-policy-xzA40Evo.js";
|
|
13
|
-
import { n as sequentialPairedGate, t as sequentialDecide } from "../sequential-
|
|
14
|
+
import { n as sequentialPairedGate, t as sequentialDecide } from "../sequential-rYW-Ophm.js";
|
|
15
|
+
import { createHash } from "node:crypto";
|
|
14
16
|
import { z } from "zod";
|
|
15
17
|
//#region src/experiment/ast.ts
|
|
16
18
|
/**
|
|
@@ -864,11 +866,11 @@ function deepFreeze(value) {
|
|
|
864
866
|
/** Validate, canonicalize, and hash a spec into its registration. */
|
|
865
867
|
async function sealExperiment(spec, options = {}) {
|
|
866
868
|
const validated = defineExperiment(spec);
|
|
867
|
-
const digest =
|
|
869
|
+
const digest = specDigest(validated, "sha256-rfc8785");
|
|
868
870
|
return {
|
|
869
871
|
spec: validated,
|
|
870
872
|
digest,
|
|
871
|
-
algo: "sha256-
|
|
873
|
+
algo: "sha256-rfc8785",
|
|
872
874
|
sealedAt: options.sealedAt ?? (/* @__PURE__ */ new Date()).toISOString(),
|
|
873
875
|
initialDigest: digest,
|
|
874
876
|
amendments: []
|
|
@@ -882,11 +884,11 @@ async function sealExperiment(spec, options = {}) {
|
|
|
882
884
|
async function amendExperiment(sealed, amendment) {
|
|
883
885
|
await assertSealIntact(sealed);
|
|
884
886
|
const validated = defineExperiment(amendment.spec);
|
|
885
|
-
const digest =
|
|
887
|
+
const digest = specDigest(validated, "sha256-rfc8785");
|
|
886
888
|
return {
|
|
887
889
|
spec: validated,
|
|
888
890
|
digest,
|
|
889
|
-
algo: "sha256-
|
|
891
|
+
algo: "sha256-rfc8785",
|
|
890
892
|
sealedAt: sealed.sealedAt,
|
|
891
893
|
initialDigest: sealed.initialDigest,
|
|
892
894
|
amendments: [...sealed.amendments, {
|
|
@@ -897,9 +899,26 @@ async function amendExperiment(sealed, amendment) {
|
|
|
897
899
|
}]
|
|
898
900
|
};
|
|
899
901
|
}
|
|
900
|
-
/** True when the sealed digest still matches the spec it carries
|
|
902
|
+
/** True when the sealed digest still matches the spec it carries, under the
|
|
903
|
+
* scheme the seal declares. */
|
|
901
904
|
async function verifySealedExperiment(sealed) {
|
|
902
|
-
return
|
|
905
|
+
return specDigest(sealed.spec, sealed.algo) === sealed.digest;
|
|
906
|
+
}
|
|
907
|
+
/**
|
|
908
|
+
* Serialize a spec under `algo` and digest it. `'sha256-content'` is read-only
|
|
909
|
+
* — it exists so a seal written by an earlier release still verifies, and no
|
|
910
|
+
* path that WRITES a digest may pass it.
|
|
911
|
+
*/
|
|
912
|
+
function specDigest(spec, algo) {
|
|
913
|
+
const serialized = algo === "sha256-rfc8785" ? canonicalString(spec) : JSON.stringify(sortKeysDeep(spec));
|
|
914
|
+
return createHash("sha256").update(serialized, "utf8").digest("hex");
|
|
915
|
+
}
|
|
916
|
+
function sortKeysDeep(value) {
|
|
917
|
+
if (value === null || typeof value !== "object") return value;
|
|
918
|
+
if (Array.isArray(value)) return value.map(sortKeysDeep);
|
|
919
|
+
const out = {};
|
|
920
|
+
for (const key of Object.keys(value).sort()) out[key] = sortKeysDeep(value[key]);
|
|
921
|
+
return out;
|
|
903
922
|
}
|
|
904
923
|
async function assertSealIntact(sealed) {
|
|
905
924
|
if (!await verifySealedExperiment(sealed)) throw new SealIntegrityError(`sealed experiment '${sealed.spec.id}' digest ${sealed.digest} does not match its spec — the registration was tampered with`);
|
|
@@ -1510,6 +1529,6 @@ function mixSeed(seed, effect) {
|
|
|
1510
1529
|
return (seed ^ Math.round(effect * 1000003) * 2654435769) >>> 0 | 0;
|
|
1511
1530
|
}
|
|
1512
1531
|
//#endregion
|
|
1513
|
-
export { BOOTSTRAP_GATE_MIN_N,
|
|
1532
|
+
export { BOOTSTRAP_GATE_MIN_N, DesignRefusalError, EVIDENCE_AUTHORITY_KINDS, EVIDENCE_RECEIPT_VERSION, EVIDENCE_STATES, ExperimentTracker, FunnelIntegrityError, INDEPENDENT_EVIDENCE_AUTHORITY_KINDS, MatchedBudgetError, SealIntegrityError, amendExperiment, assertDesignAdequate, assertFunnelReconciles, assertMatchedBudgets, benjaminiHochberg, bonferroni, buildEvidenceVector, buildFunnel, classifyReissue, clusteredPower, comparePairedArms, composeFunnels, computeEstimand, computeInterval, createEvidenceReceipt, defineExperiment, eProcess, evaluateCondition, evaluateHaltRule, evaluateHypothesis, evaluateIdentityGate, evaluateOracleDeterminismGate, evaluatePopulationReproducibilityGate, evaluatePowerFloorGate, evaluatePredicate, evaluateProvenanceGate, evidenceRegistryRecordSchema, executeAdmissionRule, executeDecisionRule, fileExperimentStore, hashJson, heldoutSignificance, holm, inMemoryExperimentStore, isIndependentEvidence, manifestContentDigest, mcnemar, mcnemarPower, mcnemarRequiredN, mulberry32, openSealedExperiment, pairArms, pairHoldout, pairRunRecords, pairedBootstrap, pairedEvalueSequence, pairedMde, pairedRiskDifference, pairedRiskDifferenceExact, pairedRiskDifferenceScore, paretoPolicy, paretoSignificanceGate, parseEvidenceRegistryRecord, powerPreflight, projectNLadderBudget, readField, renderEvidenceIndex, renderFunnelTable, requiredPairedSampleSize, requiredSampleSize, runSelectionRule, runUniformPassBudget, sealExperiment, sequentialCrossingHorizon, sequentialDecide, sequentialPairedGate, signManifest, validateEvidenceRegistry, verifyEvidenceReceipt, verifyManifest, verifyMatchedBudgets, verifySealedExperiment, wilson };
|
|
1514
1533
|
|
|
1515
1534
|
//# sourceMappingURL=index.js.map
|