@tangle-network/agent-eval 0.144.5 → 0.144.7
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 +30 -0
- package/README.md +2 -0
- package/dist/{benchmark-Fmo42QVE.d.ts → agent-profile-CgDTo40f.d.ts} +91 -4
- package/dist/agent-profile-CgDTo40f.d.ts.map +1 -0
- package/dist/{agent-profile-cell-Cw0PVwDr.d.ts → agent-profile-cell-BOP-iA9Q.d.ts} +2 -2
- package/dist/{agent-profile-cell-Cw0PVwDr.d.ts.map → agent-profile-cell-BOP-iA9Q.d.ts.map} +1 -1
- package/dist/analyst/index.d.ts +471 -89
- package/dist/analyst/index.d.ts.map +1 -1
- package/dist/analyst/index.js +24 -5
- package/dist/analyst/index.js.map +1 -1
- package/dist/{analyze-runs-DWIvOAGk.js → analyze-runs-BNNK7irB.js} +3 -3
- package/dist/{analyze-runs-DWIvOAGk.js.map → analyze-runs-BNNK7irB.js.map} +1 -1
- package/dist/{baseline-D_fT6277.d.ts → baseline-CavEbRyH.d.ts} +2 -23
- package/dist/baseline-CavEbRyH.d.ts.map +1 -0
- package/dist/{benchmark-command-CA_NFOmy.js → benchmark-command-BCafwNrf.js} +664 -605
- package/dist/benchmark-command-BCafwNrf.js.map +1 -0
- package/dist/benchmarks/index.d.ts +1 -1
- package/dist/benchmarks/index.js +1 -1
- package/dist/{benchmarks-CWbsj0t4.js → benchmarks-CDSolHq7.js} +4 -4
- package/dist/{benchmarks-CWbsj0t4.js.map → benchmarks-CDSolHq7.js.map} +1 -1
- package/dist/campaign/index.d.ts +8 -6
- package/dist/campaign/index.js +5 -3
- package/dist/{campaign-ClpnD7Ug.js → campaign-Tdy3h62h.js} +17 -301
- package/dist/campaign-Tdy3h62h.js.map +1 -0
- package/dist/cli.js +2 -2
- package/dist/{client-DAb7MWtL.d.ts → client-DjXROWpx.d.ts} +4 -4
- package/dist/{client-DAb7MWtL.d.ts.map → client-DjXROWpx.d.ts.map} +1 -1
- package/dist/{completion-verifier-VvpHRu78.d.ts → completion-verifier-foUCLif_.d.ts} +6 -6
- package/dist/{completion-verifier-VvpHRu78.d.ts.map → completion-verifier-foUCLif_.d.ts.map} +1 -1
- package/dist/contract/index.d.ts +11 -10
- package/dist/contract/index.d.ts.map +1 -1
- package/dist/contract/index.js +7 -6
- package/dist/contract/index.js.map +1 -1
- package/dist/control.d.ts +2 -2
- package/dist/control.js +1 -1
- package/dist/{cost-ledger-FuQvHxPm.d.ts → cost-ledger-Bv_e8XHY.d.ts} +2 -2
- package/dist/{cost-ledger-FuQvHxPm.d.ts.map → cost-ledger-Bv_e8XHY.d.ts.map} +1 -1
- package/dist/counterfactual-CWPTrMH7.js +126 -0
- package/dist/counterfactual-CWPTrMH7.js.map +1 -0
- package/dist/counterfactual-CxmxAONP.d.ts +72 -0
- package/dist/counterfactual-CxmxAONP.d.ts.map +1 -0
- package/dist/{dataset-v_Y5902-.d.ts → dataset-C8xaLXdY.d.ts} +2 -2
- package/dist/{dataset-v_Y5902-.d.ts.map → dataset-C8xaLXdY.d.ts.map} +1 -1
- package/dist/{default-registry-BwbZ9N9v.d.ts → default-registry-BZhStdjl.d.ts} +6 -5
- package/dist/default-registry-BZhStdjl.d.ts.map +1 -0
- package/dist/{default-registry-RLNNoeEP.js → default-registry-BaQXW1Ow.js} +2 -2
- package/dist/{default-registry-RLNNoeEP.js.map → default-registry-BaQXW1Ow.js.map} +1 -1
- package/dist/{dspy-rlm-engine-19FQEMBK.js → dspy-rlm-engine-BiN49gK6.js} +4 -3
- package/dist/{dspy-rlm-engine-19FQEMBK.js.map → dspy-rlm-engine-BiN49gK6.js.map} +1 -1
- package/dist/{tool-groups-ByZiqpVk.d.ts → engine-nB64f48I.d.ts} +21 -34
- package/dist/engine-nB64f48I.d.ts.map +1 -0
- package/dist/{errors-DkfjIDvD.d.ts → errors-CKPfb2aH.d.ts} +2 -2
- package/dist/{errors-DkfjIDvD.d.ts.map → errors-CKPfb2aH.d.ts.map} +1 -1
- package/dist/errors-D-LKuDhb.js.map +1 -1
- package/dist/{eval-campaign-lZcDIwQM.js → eval-campaign-DNjCvAm-.js} +7 -6
- package/dist/{eval-campaign-lZcDIwQM.js.map → eval-campaign-DNjCvAm-.js.map} +1 -1
- package/dist/{exact-types-BQ7W90C4.d.ts → exact-types-Djvzosly.d.ts} +2 -2
- package/dist/{exact-types-BQ7W90C4.d.ts.map → exact-types-Djvzosly.d.ts.map} +1 -1
- package/dist/exec-BLtYZdWo.js +49 -0
- package/dist/exec-BLtYZdWo.js.map +1 -0
- package/dist/experiment/index.d.ts +802 -0
- package/dist/experiment/index.d.ts.map +1 -0
- package/dist/experiment/index.js +1108 -0
- package/dist/experiment/index.js.map +1 -0
- package/dist/experiment-tracker-CnRICnMl.js +500 -0
- package/dist/experiment-tracker-CnRICnMl.js.map +1 -0
- package/dist/experiment-tracker-IMntXr6J.d.ts +299 -0
- package/dist/experiment-tracker-IMntXr6J.d.ts.map +1 -0
- package/dist/{external-optimizer-contracts-CdmX2K2S.d.ts → external-optimizer-contracts-CZuJNcT5.d.ts} +3 -3
- package/dist/{external-optimizer-contracts-CdmX2K2S.d.ts.map → external-optimizer-contracts-CZuJNcT5.d.ts.map} +1 -1
- package/dist/{feedback-trajectory-WK7x4mhy.d.ts → feedback-trajectory-Rh280oXo.d.ts} +4 -4
- package/dist/{feedback-trajectory-WK7x4mhy.d.ts.map → feedback-trajectory-Rh280oXo.d.ts.map} +1 -1
- package/dist/fuzz.d.ts +2 -2
- package/dist/hosted/index.d.ts +3 -3
- package/dist/{index-BZUe-ODI.d.ts → index-BZ3-y4YL.d.ts} +3 -3
- package/dist/{index-BZUe-ODI.d.ts.map → index-BZ3-y4YL.d.ts.map} +1 -1
- package/dist/{index-DSC51roc.d.ts → index-C3ssXVLv.d.ts} +2 -2
- package/dist/{index-DSC51roc.d.ts.map → index-C3ssXVLv.d.ts.map} +1 -1
- package/dist/{index-CsuAo2-J.d.ts → index-C5HOo4ZF2.d.ts} +5 -5
- package/dist/index-C5HOo4ZF2.d.ts.map +1 -0
- package/dist/{index-DEb46kc6.d.ts → index-CvSN3IG1.d.ts} +2 -2
- package/dist/{index-DEb46kc6.d.ts.map → index-CvSN3IG1.d.ts.map} +1 -1
- package/dist/{index-CNOCxBLh.d.ts → index-CvXXlyz7.d.ts} +3 -3
- package/dist/{index-CNOCxBLh.d.ts.map → index-CvXXlyz7.d.ts.map} +1 -1
- package/dist/{index-DGIzNtRv.d.ts → index-CwDrUMe0.d.ts} +3 -3
- package/dist/{index-DGIzNtRv.d.ts.map → index-CwDrUMe0.d.ts.map} +1 -1
- package/dist/{index-CpxZSlB7.d.ts → index-Sh2I0DRc.d.ts} +15 -649
- package/dist/index-Sh2I0DRc.d.ts.map +1 -0
- package/dist/index.d.ts +252 -451
- package/dist/index.d.ts.map +1 -1
- package/dist/index.js +271 -751
- package/dist/index.js.map +1 -1
- package/dist/{insight-report-D5m1z0_n.d.ts → insight-report-C6h6F_4L.d.ts} +4 -4
- package/dist/{insight-report-D5m1z0_n.d.ts.map → insight-report-C6h6F_4L.d.ts.map} +1 -1
- package/dist/{integrity-DRXobPEs.d.ts → integrity-BuqEKu-x.d.ts} +3 -3
- package/dist/{integrity-DRXobPEs.d.ts.map → integrity-BuqEKu-x.d.ts.map} +1 -1
- package/dist/integrity-MLzHOfV9.js +141 -0
- package/dist/integrity-MLzHOfV9.js.map +1 -0
- package/dist/kind-factory-BHIgPmzS.js.map +1 -1
- package/dist/ledger-core/index.d.ts +1 -1
- package/dist/{llm-client-D3EoChAU.js → llm-client-DzvMUsS_.js} +310 -10
- package/dist/llm-client-DzvMUsS_.js.map +1 -0
- package/dist/matrix/index.d.ts +2 -2
- package/dist/meta-eval/index.d.ts +2 -2
- package/dist/{mint-DD-0oQTA.js → mint-CGEkzPLf.js} +2 -2
- package/dist/{mint-DD-0oQTA.js.map → mint-CGEkzPLf.js.map} +1 -1
- package/dist/{multi-layer-verifier-BHY1gWAc.d.ts → multi-layer-verifier-DnAqwl0h.d.ts} +2 -2
- package/dist/{multi-layer-verifier-BHY1gWAc.d.ts.map → multi-layer-verifier-DnAqwl0h.d.ts.map} +1 -1
- package/dist/multishot/index.d.ts +3 -3
- package/dist/openapi.json +1 -1
- package/dist/paired-promotion-decision-B6zJ3gYM.d.ts +114 -0
- package/dist/paired-promotion-decision-B6zJ3gYM.d.ts.map +1 -0
- package/dist/pipelines/index.d.ts +2 -1
- package/dist/pipelines/index.d.ts.map +1 -1
- package/dist/pre-registration-DakwTRXk.js +96 -0
- package/dist/pre-registration-DakwTRXk.js.map +1 -0
- package/dist/prime-bridge-transport-6feEglLf.d.ts +49 -0
- package/dist/prime-bridge-transport-6feEglLf.d.ts.map +1 -0
- package/dist/prime-protocol-BfSalTfR.js +453 -0
- package/dist/prime-protocol-BfSalTfR.js.map +1 -0
- package/dist/profile-cell.d.ts +1 -1
- package/dist/profile-cell.js +242 -1
- package/dist/profile-cell.js.map +1 -0
- package/dist/promotion-policy-ChWhTDBH.d.ts +289 -0
- package/dist/promotion-policy-ChWhTDBH.d.ts.map +1 -0
- package/dist/promotion-policy-CrLrmys8.js +682 -0
- package/dist/promotion-policy-CrLrmys8.js.map +1 -0
- package/dist/{propose-review-control-BciUCZoh.js → propose-review-control-qgWLA6E9.js} +2 -2
- package/dist/{propose-review-control-BciUCZoh.js.map → propose-review-control-qgWLA6E9.js.map} +1 -1
- package/dist/{release-report-BZRWdq_t.d.ts → release-report-CI8uisI1.d.ts} +4 -4
- package/dist/{release-report-BZRWdq_t.d.ts.map → release-report-CI8uisI1.d.ts.map} +1 -1
- package/dist/{release-report-Sl0xfkFv.js → release-report-Dy39cbFF.js} +3 -3
- package/dist/{release-report-Sl0xfkFv.js.map → release-report-Dy39cbFF.js.map} +1 -1
- package/dist/{replay-B7S7Pdbw.d.ts → replay-DFf-teiC.d.ts} +8 -7
- package/dist/replay-DFf-teiC.d.ts.map +1 -0
- package/dist/{replay-GW61ezMW.js → replay-DyBLaKFc.js} +3 -3
- package/dist/{replay-GW61ezMW.js.map → replay-DyBLaKFc.js.map} +1 -1
- package/dist/reporting.d.ts +4 -4
- package/dist/reporting.js +2 -2
- package/dist/{researcher-BSiCoM1s.d.ts → researcher-BoaxeCzP.d.ts} +6 -6
- package/dist/{researcher-BSiCoM1s.d.ts.map → researcher-BoaxeCzP.d.ts.map} +1 -1
- package/dist/{reward-hacking-CyuzxKly.js → reward-hacking-B2tPL9a3.js} +12 -3
- package/dist/reward-hacking-B2tPL9a3.js.map +1 -0
- package/dist/{reward-hacking-DFgkEY4p.d.ts → reward-hacking-Cf1PtEOz.d.ts} +34 -4
- package/dist/reward-hacking-Cf1PtEOz.d.ts.map +1 -0
- package/dist/rl.d.ts +19 -9
- package/dist/rl.d.ts.map +1 -1
- package/dist/rl.js +16 -7
- package/dist/rl.js.map +1 -1
- package/dist/rollout/index.d.ts +2 -2
- package/dist/rollout/index.js +2 -2
- package/dist/{rollout-C2fD1cf4.js → rollout-2ECTXb2N.js} +2 -2
- package/dist/{rollout-C2fD1cf4.js.map → rollout-2ECTXb2N.js.map} +1 -1
- package/dist/{rubric-predictive-validity-C4r4Y-q8.d.ts → rubric-predictive-validity-9qAwzkZm.d.ts} +2 -2
- package/dist/{rubric-predictive-validity-C4r4Y-q8.d.ts.map → rubric-predictive-validity-9qAwzkZm.d.ts.map} +1 -1
- package/dist/{run-evidence-j5Ynww6L.d.ts → run-evidence-BDFFai9R.d.ts} +3 -3
- package/dist/{run-evidence-j5Ynww6L.d.ts.map → run-evidence-BDFFai9R.d.ts.map} +1 -1
- package/dist/{run-record-ooo9FWns.d.ts → run-record-DdSa93_W.d.ts} +4 -4
- package/dist/{run-record-ooo9FWns.d.ts.map → run-record-DdSa93_W.d.ts.map} +1 -1
- package/dist/{run-record-CWN8-VsV.js → run-record-DqOw5X6_.js} +2 -2
- package/dist/{run-record-CWN8-VsV.js.map → run-record-DqOw5X6_.js.map} +1 -1
- package/dist/{schema-Cef2cFmb.d.ts → schema-Cef2cFmb2.d.ts} +1 -1
- package/dist/schema-Cef2cFmb2.d.ts.map +1 -0
- package/dist/{semantic-concept-judge-DKRtp2sY.js → semantic-concept-judge-Bmrq6yqU.js} +2 -2
- package/dist/{semantic-concept-judge-DKRtp2sY.js.map → semantic-concept-judge-Bmrq6yqU.js.map} +1 -1
- package/dist/sequential-D-BLJBKU.js +299 -0
- package/dist/sequential-D-BLJBKU.js.map +1 -0
- package/dist/{server-Df00sdwz.js → server-iu0ede49.js} +2 -2
- package/dist/{server-Df00sdwz.js.map → server-iu0ede49.js.map} +1 -1
- package/dist/{single-run-lock-D5iN0Xzb.js → single-run-lock-BMQEv1wG.js} +7 -161
- package/dist/single-run-lock-BMQEv1wG.js.map +1 -0
- package/dist/{skill-usage-DUvvudWR.d.ts → skill-usage-CJlWEUFt.d.ts} +11 -11
- package/dist/{skill-usage-DUvvudWR.d.ts.map → skill-usage-CJlWEUFt.d.ts.map} +1 -1
- package/dist/{skillopt-optimization-method-CGz9ywhM.d.ts → skillopt-optimization-method-BO7NAl3b.d.ts} +11 -297
- package/dist/skillopt-optimization-method-BO7NAl3b.d.ts.map +1 -0
- package/dist/{skillopt-optimization-method-C4FX42dy.js → skillopt-optimization-method-CQwZ-ZX8.js} +8 -652
- package/dist/skillopt-optimization-method-CQwZ-ZX8.js.map +1 -0
- package/dist/statistical-heldout-Dn9ruizm.d.ts +555 -0
- package/dist/statistical-heldout-Dn9ruizm.d.ts.map +1 -0
- package/dist/{statistics-B4u_CiFd.d.ts → statistics-D6Uebe_4.d.ts} +2 -2
- package/dist/{statistics-B4u_CiFd.d.ts.map → statistics-D6Uebe_4.d.ts.map} +1 -1
- package/dist/steps-BArUxhna.d.ts +51 -0
- package/dist/steps-BArUxhna.d.ts.map +1 -0
- package/dist/{integrity-fdt8XPAv.js → store-DNe_Uv1Q.js} +2 -140
- package/dist/store-DNe_Uv1Q.js.map +1 -0
- package/dist/{summary-report-BOM6dfP7.d.ts → summary-report-DuUS_i7W.d.ts} +4 -115
- package/dist/summary-report-DuUS_i7W.d.ts.map +1 -0
- package/dist/{summary-report-9A5y7EsK.js → summary-report-Lf-5I7xh.js} +2 -2
- package/dist/{summary-report-9A5y7EsK.js.map → summary-report-Lf-5I7xh.js.map} +1 -1
- package/dist/supervisor-run/index.d.ts +2 -2
- package/dist/supervisor-run/index.js +1 -1
- package/dist/{supervisor-run-DiyQVczd.js → supervisor-run-D_sokXcO.js} +32 -8
- package/dist/{supervisor-run-DiyQVczd.js.map → supervisor-run-D_sokXcO.js.map} +1 -1
- package/dist/tool-groups-DIVBnJyl.d.ts +28 -0
- package/dist/tool-groups-DIVBnJyl.d.ts.map +1 -0
- package/dist/trace-repair/index.d.ts +2102 -0
- package/dist/trace-repair/index.d.ts.map +1 -0
- package/dist/trace-repair/index.js +3878 -0
- package/dist/trace-repair/index.js.map +1 -0
- package/dist/traces.d.ts +6 -6
- package/dist/traces.js +3 -2
- package/dist/trajectory-YC15QDYQ.d.ts +24 -0
- package/dist/trajectory-YC15QDYQ.d.ts.map +1 -0
- package/dist/trajectory-replay/index.d.ts +781 -0
- package/dist/trajectory-replay/index.d.ts.map +1 -0
- package/dist/trajectory-replay/index.js +2103 -0
- package/dist/trajectory-replay/index.js.map +1 -0
- package/dist/{types-BjMFz88h.d.ts → types-D216SgwM.d.ts} +228 -9
- package/dist/types-D216SgwM.d.ts.map +1 -0
- package/dist/{types-yLK8gXE9.d.ts → types-D4mog56g.d.ts} +2 -2
- package/dist/{types-yLK8gXE9.d.ts.map → types-D4mog56g.d.ts.map} +1 -1
- package/dist/{types-CZt1PBIk.d.ts → types-DF_Udrp-.d.ts} +54 -5
- package/dist/{types-CZt1PBIk.d.ts.map → types-DF_Udrp-.d.ts.map} +1 -1
- package/dist/{types-Dcoaqcsc.d.ts → types-DYuNHo9R.d.ts} +5 -5
- package/dist/{types-Dcoaqcsc.d.ts.map → types-DYuNHo9R.d.ts.map} +1 -1
- package/dist/usage-receipt-EVI8B8Xu.js.map +1 -1
- package/dist/verdict-DExhxfgR.d.ts +201 -0
- package/dist/verdict-DExhxfgR.d.ts.map +1 -0
- package/dist/verdict-cache-BCcOh0kF.js +159 -0
- package/dist/verdict-cache-BCcOh0kF.js.map +1 -0
- package/dist/wire/index.d.ts +3 -3
- package/dist/wire/index.js +1 -1
- package/docs/building-doctrine.md +15 -0
- package/docs/charter.md +112 -0
- package/docs/experiment.md +104 -0
- package/docs/prime-analyst.md +1 -0
- package/docs/trace-analysis.md +26 -0
- package/docs/trace-repair-admission.md +194 -0
- package/docs/trace-repair-analyst-arms.md +121 -0
- package/docs/trace-repair-continuation.md +107 -0
- package/docs/trace-repair-grader.md +163 -0
- package/docs/trajectory-replay.md +110 -0
- package/docs/verification-strategies.md +103 -0
- package/package.json +21 -4
- package/dist/agent-profile-cell-CbfBm2g6.js +0 -335
- package/dist/agent-profile-cell-CbfBm2g6.js.map +0 -1
- package/dist/baseline-D_fT6277.d.ts.map +0 -1
- package/dist/benchmark-Fmo42QVE.d.ts.map +0 -1
- package/dist/benchmark-command-CA_NFOmy.js.map +0 -1
- package/dist/campaign-ClpnD7Ug.js.map +0 -1
- package/dist/default-registry-BwbZ9N9v.d.ts.map +0 -1
- package/dist/index-CpxZSlB7.d.ts.map +0 -1
- package/dist/index-CsuAo2-J.d.ts.map +0 -1
- package/dist/integrity-fdt8XPAv.js.map +0 -1
- package/dist/llm-client-D3EoChAU.js.map +0 -1
- package/dist/replay-B7S7Pdbw.d.ts.map +0 -1
- package/dist/reward-hacking-CyuzxKly.js.map +0 -1
- package/dist/reward-hacking-DFgkEY4p.d.ts.map +0 -1
- package/dist/schema-Cef2cFmb.d.ts.map +0 -1
- package/dist/single-run-lock-D5iN0Xzb.js.map +0 -1
- package/dist/skillopt-optimization-method-C4FX42dy.js.map +0 -1
- package/dist/skillopt-optimization-method-CGz9ywhM.d.ts.map +0 -1
- package/dist/summary-report-BOM6dfP7.d.ts.map +0 -1
- package/dist/tool-groups-ByZiqpVk.d.ts.map +0 -1
- package/dist/types-BjMFz88h.d.ts.map +0 -1
- package/dist/verdict-Dps8_okt.d.ts +0 -37
- package/dist/verdict-Dps8_okt.d.ts.map +0 -1
There are too many changes on this page to be displayed.
The amount of changes on this page would crash your brower.
You can still verify the content by downloading the package file manually.