@tangle-network/agent-eval 0.161.0 → 0.163.2
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 +51 -0
- package/dist/{active-curriculum-CD5TU2yW.js → active-curriculum-OjIWgrUJ.js} +2 -2
- package/dist/{active-curriculum-CD5TU2yW.js.map → active-curriculum-OjIWgrUJ.js.map} +1 -1
- package/dist/analyst/index.d.ts +2 -2
- package/dist/analyst/index.d.ts.map +1 -1
- package/dist/analyst/index.js +3 -3
- package/dist/{baseline-BhPRQBVn.js → baseline-BC-eBZ7U.js} +2 -2
- package/dist/{baseline-BhPRQBVn.js.map → baseline-BC-eBZ7U.js.map} +1 -1
- package/dist/{benchmark-command-BVtaq_ve.js → benchmark-command-CF-4GEWZ.js} +9 -8
- package/dist/benchmark-command-CF-4GEWZ.js.map +1 -0
- package/dist/benchmarks/index.d.ts +1 -1
- package/dist/benchmarks/index.js +3 -3
- package/dist/builder-eval/index.d.ts.map +1 -1
- package/dist/builder-eval/index.js +22 -8
- package/dist/builder-eval/index.js.map +1 -1
- package/dist/campaign/index.js +8 -8
- package/dist/{campaign-BSmOwskD.js → campaign-DQZmc2Dq.js} +12 -12
- package/dist/{campaign-BSmOwskD.js.map → campaign-DQZmc2Dq.js.map} +1 -1
- package/dist/{chat-json-call-6g5sJobJ.js → chat-json-call-5Jxna-aV.js} +2 -2
- package/dist/{chat-json-call-6g5sJobJ.js.map → chat-json-call-5Jxna-aV.js.map} +1 -1
- package/dist/cli.js +3 -3
- package/dist/contract/index.js +7 -7
- package/dist/{counterfactual-D_VWavVm.js → counterfactual-Bjq1mlUu.js} +2 -2
- package/dist/{counterfactual-D_VWavVm.js.map → counterfactual-Bjq1mlUu.js.map} +1 -1
- package/dist/{define-agent-eval-h-s-sI-v.js → define-agent-eval-D08pWIJb.js} +13 -13
- package/dist/{define-agent-eval-h-s-sI-v.js.map → define-agent-eval-D08pWIJb.js.map} +1 -1
- package/dist/{descriptive-jDOuI6mz.js → descriptive-1V17A-qa.js} +2 -2
- package/dist/{descriptive-jDOuI6mz.js.map → descriptive-1V17A-qa.js.map} +1 -1
- package/dist/{dspy-rlm-engine-DptEII26.js → dspy-rlm-engine-DhA9qKIm.js} +2 -2
- package/dist/{dspy-rlm-engine-DptEII26.js.map → dspy-rlm-engine-DhA9qKIm.js.map} +1 -1
- package/dist/emitter-D_jYSGRd.d.ts.map +1 -1
- package/dist/{emitter-BpYFQPj4.js → emitter-DeQHiDMm.js} +13 -6
- package/dist/emitter-DeQHiDMm.js.map +1 -0
- package/dist/{eval-campaign-BsXWL2-2.js → eval-campaign-BfohKmzx.js} +3 -3
- package/dist/{eval-campaign-BsXWL2-2.js.map → eval-campaign-BfohKmzx.js.map} +1 -1
- package/dist/experiment/index.js +8 -8
- package/dist/{experiment-tracker-Ym6rEQT1.js → experiment-tracker-BKEumQug.js} +2 -2
- package/dist/{experiment-tracker-Ym6rEQT1.js.map → experiment-tracker-BKEumQug.js.map} +1 -1
- package/dist/{external-optimizer-process-WosTBChy.js → external-optimizer-process-BFmh36vW.js} +2 -2
- package/dist/{external-optimizer-process-WosTBChy.js.map → external-optimizer-process-BFmh36vW.js.map} +1 -1
- package/dist/{external-optimizer-subprocess-BIWbHpgD.js → external-optimizer-subprocess-CqLMW3nh.js} +2 -2
- package/dist/{external-optimizer-subprocess-BIWbHpgD.js.map → external-optimizer-subprocess-CqLMW3nh.js.map} +1 -1
- package/dist/fuzz.d.ts +1 -2
- package/dist/fuzz.d.ts.map +1 -1
- package/dist/fuzz.js +4 -10
- package/dist/fuzz.js.map +1 -1
- package/dist/index.d.ts +3 -3
- package/dist/index.js +26 -26
- package/dist/index.js.map +1 -1
- package/dist/{internal-BDHPCnjk.js → internal-BMFSR8Ns.js} +3 -19
- package/dist/internal-BMFSR8Ns.js.map +1 -0
- package/dist/{judge-calibration-zZjLz8hr.js → judge-calibration-BnpVKtnb.js} +3 -13
- package/dist/judge-calibration-BnpVKtnb.js.map +1 -0
- package/dist/judge-calibration-C5CbMYce.d.ts.map +1 -1
- package/dist/{llm-client-hgDieDNN.js → llm-client-BFMRpmqb.js} +8 -11
- package/dist/llm-client-BFMRpmqb.js.map +1 -0
- package/dist/{llm-judge-BhasIPFT.js → llm-judge-Du7WQPh7.js} +7 -7
- package/dist/{llm-judge-BhasIPFT.js.map → llm-judge-Du7WQPh7.js.map} +1 -1
- package/dist/meta-eval/index.d.ts +2 -1
- package/dist/meta-eval/index.d.ts.map +1 -1
- package/dist/meta-eval/index.js +14 -22
- package/dist/meta-eval/index.js.map +1 -1
- package/dist/openapi.json +1 -1
- package/dist/{paired-arms-D-XRF_fy.js → paired-arms-D4aeIHUy.js} +3 -3
- package/dist/{paired-arms-D-XRF_fy.js.map → paired-arms-D4aeIHUy.js.map} +1 -1
- package/dist/{paired-tests-BHIhYVdu.js → paired-tests-C8iCsioC.js} +3 -3
- package/dist/{paired-tests-BHIhYVdu.js.map → paired-tests-C8iCsioC.js.map} +1 -1
- package/dist/pipelines/index.d.ts +3 -2
- package/dist/pipelines/index.d.ts.map +1 -1
- package/dist/pipelines/index.js +4 -19
- package/dist/pipelines/index.js.map +1 -1
- package/dist/{power-and-mde-CHIrXJll.js → power-and-mde-B8F2RdcD.js} +3 -3
- package/dist/{power-and-mde-CHIrXJll.js.map → power-and-mde-B8F2RdcD.js.map} +1 -1
- package/dist/{power-preflight-DEw-uC7q.js → power-preflight-CFXm0Vjo.js} +3 -3
- package/dist/{power-preflight-DEw-uC7q.js.map → power-preflight-CFXm0Vjo.js.map} +1 -1
- package/dist/{produced-state-DZ89riy5.js → produced-state-Be0BK3RN.js} +3 -3
- package/dist/{produced-state-DZ89riy5.js.map → produced-state-Be0BK3RN.js.map} +1 -1
- package/dist/{promotion-policy-xzA40Evo.js → promotion-policy-LY9mVQ7W.js} +3 -3
- package/dist/{promotion-policy-xzA40Evo.js.map → promotion-policy-LY9mVQ7W.js.map} +1 -1
- package/dist/{query-DxPYqpmT.d.ts → query-CwnHlu5p.d.ts} +19 -2
- package/dist/query-CwnHlu5p.d.ts.map +1 -0
- package/dist/{query-CHmMP42p.js → query-_5g6re3_.js} +44 -2
- package/dist/query-_5g6re3_.js.map +1 -0
- package/dist/random-Dn5fPWkt.js +21 -0
- package/dist/random-Dn5fPWkt.js.map +1 -0
- package/dist/record-id-DUgsK5qp.js +17 -0
- package/dist/record-id-DUgsK5qp.js.map +1 -0
- package/dist/{release-confidence-DKfD2RYU.js → release-confidence-nGDJiiwc.js} +2 -2
- package/dist/{release-confidence-DKfD2RYU.js.map → release-confidence-nGDJiiwc.js.map} +1 -1
- package/dist/reporting.js +6 -6
- package/dist/{reward-hacking-t4lB1yt8.js → reward-hacking-O5zKDANP.js} +2 -2
- package/dist/{reward-hacking-t4lB1yt8.js.map → reward-hacking-O5zKDANP.js.map} +1 -1
- package/dist/rl.d.ts.map +1 -1
- package/dist/rl.js +9 -15
- package/dist/rl.js.map +1 -1
- package/dist/{rubric-predictive-validity-CK8SCOg-.js → rubric-predictive-validity-2D5Gw9z9.js} +3 -3
- package/dist/{rubric-predictive-validity-CK8SCOg-.js.map → rubric-predictive-validity-2D5Gw9z9.js.map} +1 -1
- package/dist/{semantic-concept-judge-BSkKKHeq.js → semantic-concept-judge-BsDMOwJr.js} +2 -2
- package/dist/{semantic-concept-judge-BSkKKHeq.js.map → semantic-concept-judge-BsDMOwJr.js.map} +1 -1
- package/dist/{sequential-rYW-Ophm.js → sequential-BLMbdrD7.js} +3 -3
- package/dist/{sequential-rYW-Ophm.js.map → sequential-BLMbdrD7.js.map} +1 -1
- package/dist/{server-BtFd4uzB.js → server-BjYiJHoJ.js} +2 -2
- package/dist/{server-BtFd4uzB.js.map → server-BjYiJHoJ.js.map} +1 -1
- package/dist/{skillopt-optimization-method-DbaekMcn.js → skillopt-optimization-method-UArRo-nr.js} +6 -6
- package/dist/{skillopt-optimization-method-DbaekMcn.js.map → skillopt-optimization-method-UArRo-nr.js.map} +1 -1
- package/dist/{store-tool-spans-Dlh9vkFK.js → store-tool-spans-BVga3c37.js} +21 -17
- package/dist/store-tool-spans-BVga3c37.js.map +1 -0
- package/dist/store-tool-spans-DPUG7UUY.d.ts.map +1 -1
- package/dist/{student-t-CvBq2mve.js → student-t-BA-Uy51p.js} +2 -2
- package/dist/{student-t-CvBq2mve.js.map → student-t-BA-Uy51p.js.map} +1 -1
- package/dist/{summary-report-BI5hUtvK.js → summary-report-BXeQ5Ues.js} +6 -6
- package/dist/{summary-report-BI5hUtvK.js.map → summary-report-BXeQ5Ues.js.map} +1 -1
- package/dist/supervisor-run/index.js +1 -1
- package/dist/{tool-waste-BqzmVdJk.js → tool-waste-8BQiUc8K.js} +4 -4
- package/dist/{tool-waste-BqzmVdJk.js.map → tool-waste-8BQiUc8K.js.map} +1 -1
- package/dist/{tool-waste-Dro0gJi3.d.ts → tool-waste-CKc7bYIg.d.ts} +2 -2
- package/dist/{tool-waste-Dro0gJi3.d.ts.map → tool-waste-CKc7bYIg.d.ts.map} +1 -1
- package/dist/trace-repair/index.js +1 -1
- package/dist/traces.d.ts +2 -2
- package/dist/traces.d.ts.map +1 -1
- package/dist/traces.js +8 -17
- package/dist/traces.js.map +1 -1
- package/dist/trajectory-replay/index.d.ts.map +1 -1
- package/dist/trajectory-replay/index.js +3 -13
- package/dist/trajectory-replay/index.js.map +1 -1
- package/dist/{types-BPb2Kf_C2.d.ts → types-BPb2Kf_C.d.ts} +1 -1
- package/dist/types-BPb2Kf_C.d.ts.map +1 -0
- package/dist/types-Bfk0uxRj.d.ts.map +1 -1
- package/dist/wire/index.js +1 -1
- package/package.json +2 -2
- package/dist/benchmark-command-BVtaq_ve.js.map +0 -1
- package/dist/emitter-BpYFQPj4.js.map +0 -1
- package/dist/internal-BDHPCnjk.js.map +0 -1
- package/dist/judge-calibration-zZjLz8hr.js.map +0 -1
- package/dist/llm-client-hgDieDNN.js.map +0 -1
- package/dist/query-CHmMP42p.js.map +0 -1
- package/dist/query-DxPYqpmT.d.ts.map +0 -1
- package/dist/store-tool-spans-Dlh9vkFK.js.map +0 -1
- package/dist/types-BPb2Kf_C2.d.ts.map +0 -1
package/dist/rl.d.ts.map
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"rl.d.ts","names":[],"sources":["../src/rl/active-curriculum.ts","../src/rl/adaptation-eval.ts","../src/rl/compute-curves.ts","../src/rl/contamination.ts","../src/rl/rollout-input.ts","../src/rl/preferences.ts","../src/rl/process-reward.ts","../src/rl/exporters.ts","../src/rl/dataset.ts","../src/rl/corpus.ts","../src/rl/off-policy.ts","../src/rl/predictive-validity-researcher.ts","../src/rl/rl-campaign.ts","../src/rl/run-record-adapters.ts","../src/rl/sim-fidelity.ts","../src/rl/tournament.ts","../src/rl/verified-findings-dataset.ts"],"mappings":";;;;;;;;;;;;;UAqCiB;EACf;EACA;;EAEA;;EAEA;;UAGe;EACf;EACA;;EAEA;;EAEA;;UAGe;;EAEf;;;;;;EAMA;;;;;EAKA;;;;;;;;;iBAUc,wBACd,cAAc,mBACd,gBAAgB;EAAQ;EAAmB;IAC3C,MAAM,4BACL;UAoDc;EACf;;;;;;EAMA;;EAEA;EACA;;;EAGA;;;;;;;;;;;;;iBAcc,mBACd,cAAc,mBACd,gBAAgB;EAAQ;EAAmB;IAC3C,MAAM,4BACL;;iBAyDa,2BACd,MAAM,aACN;EAAQ;EAAwB;IAC/B;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;UCnMc,iBAAiB;;;;;;EAMhC,IAAI;IAAQ,UAAU;IAAG;IAAW;MAAgB;;UAGrC,0BAA0B;EACzC,WAAW;;EAEX;;EAEA;EACA,QAAQ,iBAAiB;;EAEzB;;UAGe;EACf;EACA;EACA;EACA;EACA;;EAEA,aAAa;IAAQ;IAAoB;IAAmB;IAAgB;;;UAG7D;EACf,QAAQ;;;;;EAKR;;;;;;EAMA;;iBAGoB,mBAAmB;EAAY;GACnD,MAAM,0BAA0B,KAC/B,QAAQ;UA0DM;EACf,MAAM;IACJ;IACA;IACA;IACA;IACA;IACA;;EAEF;EACA;;EAEA;;EAEA;;;;;;;iBAQc,wBACd,GAAG,iBACH,GAAG,iBACH;EAAQ;EAAqB;EAA6B;IACzD;;iBAkDa,WAAW,OAAO,iBAAiB;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;UClLlC;;EAEf;;EAEA;;EAEA,OAAO;;UAGQ;EACf;EACA;EACA;;EAEA;;EAEA;;EAEA,UAAU;;UAGK;EACf;EACA,QAAQ;;EAER;;EAEA,MAAM;;UAGS;EACf;EACA,SAAS;;;;;EAKT,cAAc,QAAQ,uBAAuB;IAC3C;IACA;IACA;IACA,UAAU;;;iBAIQ,gBAAgB,MAAM,yBAAyB,QAAQ;UAmB5D,sBAAsB;;EAErC;;EAEA,SAAS,sBAAsB,QAAQ;;EAEvC,UAAU,SAAS,MAAM;;UAGV,qBAAqB;EACpC,MAAM;EACN;EACA;EACA;;EAEA;;;iBAIoB,QAAQ,GAAG,MAAM,sBAAsB,KAAK,QAAQ,qBAAqB;UAqB9E,uBAAuB;EACtC;EACA,SAAS,sBAAsB,QAAQ;;EAEvC,YAAY,SAAS;;UAGN,sBAAsB;;EAErC;;EAEA;;EAEA,WAAW;;EAEX,gBAAgB;;EAEhB,UAAU;;;;;;iBAOU,gBAAgB,GACpC,MAAM,uBAAuB,KAC5B,QAAQ,sBAAsB;;;;;;;UAkChB;EACf;EACA;EACA;EACA;;iBAGc,eAAe,QAAQ,qBAAqB;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
|
|
1
|
+
{"version":3,"file":"rl.d.ts","names":[],"sources":["../src/rl/active-curriculum.ts","../src/rl/adaptation-eval.ts","../src/rl/compute-curves.ts","../src/rl/contamination.ts","../src/rl/rollout-input.ts","../src/rl/preferences.ts","../src/rl/process-reward.ts","../src/rl/exporters.ts","../src/rl/dataset.ts","../src/rl/corpus.ts","../src/rl/off-policy.ts","../src/rl/predictive-validity-researcher.ts","../src/rl/rl-campaign.ts","../src/rl/run-record-adapters.ts","../src/rl/sim-fidelity.ts","../src/rl/tournament.ts","../src/rl/verified-findings-dataset.ts"],"mappings":";;;;;;;;;;;;;UAqCiB;EACf;EACA;;EAEA;;EAEA;;UAGe;EACf;EACA;;EAEA;;EAEA;;UAGe;;EAEf;;;;;;EAMA;;;;;EAKA;;;;;;;;;iBAUc,wBACd,cAAc,mBACd,gBAAgB;EAAQ;EAAmB;IAC3C,MAAM,4BACL;UAoDc;EACf;;;;;;EAMA;;EAEA;EACA;;;EAGA;;;;;;;;;;;;;iBAcc,mBACd,cAAc,mBACd,gBAAgB;EAAQ;EAAmB;IAC3C,MAAM,4BACL;;iBAyDa,2BACd,MAAM,aACN;EAAQ;EAAwB;IAC/B;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;UCnMc,iBAAiB;;;;;;EAMhC,IAAI;IAAQ,UAAU;IAAG;IAAW;MAAgB;;UAGrC,0BAA0B;EACzC,WAAW;;EAEX;;EAEA;EACA,QAAQ,iBAAiB;;EAEzB;;UAGe;EACf;EACA;EACA;EACA;EACA;;EAEA,aAAa;IAAQ;IAAoB;IAAmB;IAAgB;;;UAG7D;EACf,QAAQ;;;;;EAKR;;;;;;EAMA;;iBAGoB,mBAAmB;EAAY;GACnD,MAAM,0BAA0B,KAC/B,QAAQ;UA0DM;EACf,MAAM;IACJ;IACA;IACA;IACA;IACA;IACA;;EAEF;EACA;;EAEA;;EAEA;;;;;;;iBAQc,wBACd,GAAG,iBACH,GAAG,iBACH;EAAQ;EAAqB;EAA6B;IACzD;;iBAkDa,WAAW,OAAO,iBAAiB;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;UClLlC;;EAEf;;EAEA;;EAEA,OAAO;;UAGQ;EACf;EACA;EACA;;EAEA;;EAEA;;EAEA,UAAU;;UAGK;EACf;EACA,QAAQ;;EAER;;EAEA,MAAM;;UAGS;EACf;EACA,SAAS;;;;;EAKT,cAAc,QAAQ,uBAAuB;IAC3C;IACA;IACA;IACA,UAAU;;;iBAIQ,gBAAgB,MAAM,yBAAyB,QAAQ;UAmB5D,sBAAsB;;EAErC;;EAEA,SAAS,sBAAsB,QAAQ;;EAEvC,UAAU,SAAS,MAAM;;UAGV,qBAAqB;EACpC,MAAM;EACN;EACA;EACA;;EAEA;;;iBAIoB,QAAQ,GAAG,MAAM,sBAAsB,KAAK,QAAQ,qBAAqB;UAqB9E,uBAAuB;EACtC;EACA,SAAS,sBAAsB,QAAQ;;EAEvC,YAAY,SAAS;;UAGN,sBAAsB;;EAErC;;EAEA;;EAEA,WAAW;;EAEX,gBAAgB;;EAEhB,UAAU;;;;;;iBAOU,gBAAgB,GACpC,MAAM,uBAAuB,KAC5B,QAAQ,sBAAsB;;;;;;;UAkChB;EACf;EACA;EACA;EACA;;iBAGc,eAAe,QAAQ,qBAAqB;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;KC1KhD;UAOK,qBAAqB;EACpC,MAAM;;EAEN,QAAQ,UAAU,MAAM,QAAQ,KAAK;;EAErC;;UAGe,wBAAwB;;EAEvC,aAAa,GAAG;;EAEhB,WAAW;;;;;EAKX,YAAY;EACZ,eAAe,qBAAqB;;;;;;EAMpC,UAAU,GAAG,MAAM;;UAGJ;;EAEf;;;;;EAKA;;;;;EAKA;;UAGe;EACf,aAAa;IACX;IACA;IACA;IACA;;IAEA;;;EAGF;IAAc;IAAW;;EACzB;EACA;EACA;EACA;;EAEA;;iBAGoB,sBAAsB,GAC1C,OAAO,wBAAwB,IAC/B,OAAM,4BACL,QAAQ;;;;;;;iBA0FK,gBAAgB;EAAY;GAC1C,uBACA,UAAS,cAAc,yBACtB,qBAAqB;;;;;;iBAoBR,aAAa;EAAY;GACvC,iBAAiB,gBAAgB,8BACjC,eACC,qBAAqB;;;;;;iBAgBR,uBAAuB;EAAY;GACjD,gBACA,iCACC,qBAAqB;;;;;;;;;;;;;UCxMP;;;;;;;;;;;EAWf,OAAO;;;;KCKG;UAKK;;EAEf;;EAEA;EACA;;EAEA;EACA;;EAEA;;;;;;EAMA;IAAW;IAAgB;;;EAE3B;;;;;EAKA;IACE;IACA;IACA;IACA;IACA;IACA;;;UAIa;EACf,WAAW;;;;;EAKX;;;;;;EAMA,QAAQ;;EAER;;UAGe;EACf,OAAO;;EAEP;;EAEA;;EAEA;;EAEA,UAAU;;;;;;EAMV;;;;;;;;;;;;;;;;;;;;iBAuCc,mBACd,OAAO,qBACP,OAAM,4BACL;;;;;;;;;;;;;;;;;;iBAqMmB,YACpB,SAAS,oBACT,SAAS,YACT,SAAS,qBACR,QAAQ;EAAQ;EAAgB;EAAgB;;;;;;;;;;;iBAkCnC,kBACd,SAAS,oBACT,SAAS,qBACR;EAAQ;EAAoB;EAAqB;EAAuB;;;;UChX1D;;EAEf;EACA;;EAEA;;EAEA,MAAM;;EAEN;;EAEA;;;;;EAKA;;EAEA;;EAEA;;UAGe;;EAEf,WAAW;;EAEX,MAAM,MAAM,OAAO,QAAQ,KAAK;;UAGjB;;;;;;EAMf,SAAS;;EAET,aAAa,MAAM;;iBAGC,mBACpB,OAAO,YACP,eACA,MAAM,4BACL,QAAQ;UAgCM;EACf;EACA;EACA;;EAEA;;EAEA;;EAEA;EACA;;iBAGc,yBAAyB,aAAa,eAAe;UA+CpD;;EAEf;EACA;;EAEA;EACA;;EAEA;EACA;;EAEA;EACA;;;;;;;;;;;;;;;;;iBAkBc,iBACd,kBAAkB,YAAY,eAC9B;EAAQ;EAAoB;IAC3B;;;UC3Jc;;EAEf,WAAW,2BAA2B;;EAEtC,eAAe,2BAA2B;;UAG3B;EACf;EACA;EACA;;EAEA;;EAEA,OAAO;;;KAIG,iBAAiB;;;;;;;;;;;;;;;;iBAwBP,UACpB,SAAS,oBACT,SAAS,YACT,SAAS,iBACR,QAAQ;;iBAwCK,WAAW,MAAM;UAMhB;;EAEf;;EAEA;;;;;EAKA,cAAc;;UAGC,oBACP,KAAK;;EAEb,WAAW,2BAA2B;;EAEtC,eAAe,2BAA2B;;UAG3B;EACf;EACA;EACA;;EAEA;EACA,OAAO;;;;;;;;;;;;;;;;;;;iBAoBa,WACpB,OAAO,qBACP,SAAS,cACR,QAAQ;iBAyDK,YAAY,MAAM;UAMjB,mBAAmB;;EAElC,WAAW,2BAA2B;;EAEtC,eAAe,2BAA2B;;EAE1C,YAAY,MAAM;;EAElB,WAAW,MAAM;;EAEjB;;UAGe;EACf,UAAU;IAAQ;IAAuC;;EACzD,OAAO;;;;;;;;;;;;;;;;;;;;iBAqBa,UACpB,OAAO,qBACP,SAAS,aACR,QAAQ;iBAkDK,WAAW,MAAM;UAMhB;;EAEf,WAAW,2BAA2B;;EAEtC,aAAa,eAAe,4BAA4B;;EAExD,YAAY,eAAe,uCAAuC;;UAGnD;EACf;;EAEA;EACA;EACA;EACA;EACA;EACA;EACA;EACA,OAAO;;UAGQ,uBAAuB;;;;;;;;;;EAUtC;;;;;;;;;;;;;;;;;;;;;iBAsBoB,UACpB,SAAS,qBACT,SAAS,YACT,SAAS,iBACR,QAAQ;iBA8FK,WAAW,MAAM;UAMhB;EACf;EACA;EACA;EACA;EACA;EACA;;;;;;;;;;;;iBAoBc,mBAAmB,aAAa,cAAc,SAAS;;;KChf3D;cACN;KACM,wBAAwB;iBAIpB,uBAAuB,iBAAiB;;;UA2BvC;EACf;EACA;;EAEA;;;EAGA;;;EAGA;IAAU,MAAM;IAAY;IAAgB;;EAC5C;EACA;EACA;;EAEA;;EAEA,UAAU;;EAEV;IACE;IACA;IACA;;;UAIa;EACf;EACA;EACA;EACA;EACA;EACA;;UAGe;EACf;;EAEA;;EAEA,QAAQ,OAAO;EACf,QAAQ;;EAER;;EAEA;EACA;EACA;IAAe;IAAe;;EAC9B;;;;;;EAMA;;UAGe,0BAA0B;EACzC,SAAS;EACT,WAAW,QAAQ,OAAO;EAC1B,OAAO;;UAGQ;EACf,UAAU;;EAEV,OAAO;;;;;;;;;iBAyDa,eACpB,OAAO,qBACP,SAAS,cAAc,YACvB,QAAQ,iBACR;EAAgB,SAAS;EAAoB,SAAS;IACrD,QAAQ;;iBA2DK,oBAAoB,GAAG;;;;;KCzO3B,eAAe;EAAc;EAAiB;;UAEzC;EACf;;;EAGA;EACA;;;;;;;;iBASc,eAAe,SAAS,gBAAgB,qBAAqB;;iBAqB7D,WAAW,qBAAqB;UAmB/B;;EAEf;;EAEA,SAAS;;EAET;;;;;;;;;;;;;;;iBAgBoB,uBACpB,oBACA,QAAQ,iBACR,OAAM,iBACL,QAAQ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;UCnEM;;EAEf;;EAEA;;;;;;EAMA;;;;;;EAMA;;;;;;EAMA;;;;;;;EAOA;;UAGe;;EAEf;;EAEA;;UAGe;;EAEf;;EAEA;;EAEA;;EAEA;;;;;EAKA;;EAEA,qBAAqB;;UAGN;;;;;;EAMf;;EAEA;IAAe;IAAa;;;;;;;;iBAQd,4BACd,cAAc,uBACd,OAAM,mBACL;;;;;;iBA4Ca,kCACd,cAAc,uBACd,OAAM,mBACL;;;;;;;;;;;;;;;;;;;;;iBAwDa,aACd,cAAc,uBACd,OAAM,mBACL;;;;;;iBAuEa,qBACd,cAAc,uBACd,OAAM;EACH,KAAK;EAAmB,OAAO;EAAmB,IAAI;;;;UCtQ1C;EACf,UAAU;EACV;;EAEA;;EAEA;;EAEA;;EAEA;;;;;;EAMA,YAAY,QAAQ,0CAA0C;;;;;;cAOnD,wCAAwC;UAC3C;UACA;EAER,YAAY,MAAM;EAIZ,gBAAgB,MAAM,cAAc,QAAQ;EA0C5C,cAAc,UAAU,gBAAgB,QAAQ;EAmDhD,YAAY,SAAS,kBAAkB,UAAU,iBAAiB,QAAQ;EAS1E,eAAe,MAAM,iBAAiB,QAAQ;;;;;;EAiD9C,iBAAiB,MAAM,cAAc,QAAQ;;;;;;EAiBnD,UAAU,QAAQ;EAIlB,iBAAiB;;;;UCpLF,qBAAqB,WAAW,oBAAoB;;EAEnE,cAAc;;EAEd,mBAAmB;;EAEnB,eAAe;EACf;;EAEA;IACE;IACA;IACA;MAAS;MAAa;;;;;;;;;;;;;IAYtB;;;EAGF;IACE,MAAM;IACN,OAAO;IACP,MAAM;;;;;;;;;;;UAYO;EACf;;EAEA;;EAEA;;EAEA;;EAEA;;EAEA;;EAEA;;UAGe;EACf,UAAU;;EAEV,eAAe;IAAQ;IAAe,QAAQ;;;EAE9C,aAAa;;;;;EAKb,mBAAmB;;;;EAInB,eAAe;;EAEf,eAAe;;EAEf,oBAAoB;;EAEpB;IACE,MAAM;IACN,OAAO;IACP,MAAM;;;;;EAKR;;;;EAIA;;iBAGoB,cAAc,GAAG,MAAM,qBAAqB,KAAK,QAAQ;;;UCrI9D;;EAEf;;EAEA;;EAEA;;EAEA;;EAEA;;EAEA,WAAW;;EAEX;;;;;;;;;;iBAWc,qBACd,UAAU,gBACV,KAAK;EAAmB;IACvB;;;;;;;;iBAyBa,8BACd,QAAQ,oBACR,KAAK;EAAmB;EAAqB;GAC7C;EAAQ;IACP;;;;;;;KCnCS,oBAAoB,QAAQ,cAAc;;;;;cAMzC;;;;;;;;;;;;;;;;;;;;;;cAuCA,yBAAyB;;;;;;;;;iBAmDtB,aAAa,GAAG,wBAAwB,GAAG;;;;;;;iBAqC3C,cAAc,kBAAkB;;;iBAsBhC,YAAY,eAAe;UAU1B;;EAEf;;;EAGA;;EAEA;;UAGe;EACf;;EAEA;;EAEA,WAAW;;EAEX;;EAEA;;KAGU;UAEK;EACf,cAAc;;;;EAId;;;EAGA;;;EAGA,SAAS;;UAGM;;EAEf,WAAW;;EAEX;;;;;;;;iBASc,kBACd,WAAW,aACX,YAAY,aACZ,OAAM,qBACL;UAuHc;;;EAGf;;;EAGA;;UAGe;EACf;EACA;;EAEA;;;EAGA;;;;;;;;;iBAUc,cACd,WAAW,aACX,YAAY,aACZ,OAAM,kBACL;;;;;;;;;;;;;;;;;;;;;;;;;;;;;UC/Xc;;EAEf;;EAEA;;;;;EAKA;;;;;;EAMA;;UAGe;EACf;;EAEA;;EAEA;;EAEA;;EAEA;;UAGe;EACf,SAAS;;EAET;;EAEA;EACA;;;;;;;;;;;iBAYc,gBACd,UAAU,mBACV;EAAQ;EAAoB;EAAwB;IACnD;;;;;;;;;UA+Gc;;EAEf;;EAEA;;iBAGc,eACd,SAAS,qBACT,SAAS,iBACT,OAAM;EACH;EAAqB;;;;;;;;UA2BT;EACf,MAAM;IACJ;;IAEA;IACA;;;;;;EAMF;;iBAGc,0BACd,OAAO,iCACN;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;cChNU;;UAKI;EACf;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;;EAEA;EACA,KAAK;EACL;;UAGe;EACf;EACA;EACA;EACA;EACA;EACA;;UAGe;EACf;EACA,OAAO;;;UAIQ;EACf;EACA;EACA;EACA;EACA;EACA;EACA;EACA,kBAAkB;IAAQ;IAAkB;;;;UAI7B;EACf;EACA;EACA;;UAGe;EACf;;;EAGA;;EAEA;EACA;;;UAIe;EACf;EACA;EACA;EACA;EACA,mBAAmB;EACnB;EACA;IAAU;IAAyB;;;UAKpB;EACf;EACA;EACA;;EAEA;EACA;;KAGU;UAEK;EACf,SAAS;EACT;EACA;EACA;EACA;;UAGe;EACf,eAAe;;EAEf;EACA;EACA;EACA;IACE;IACA;IACA;IACA;IACA;IACA;;EAEF;;IAEE;;IAEA;;IAEA;;IAEA;IACA;;;EAGF;IACE;MAAU;MAAe;;IACzB,OAAO;;EAET;IACE;;IAEA;IACA;IACA;IACA;IACA;IACA;IACA;;;IAGA;IACA,wBAAwB;IACxB;IACA;IACA;IACA;;EAEF,KAAK;EACL;IACE;IACA;IACA;IACA;IACA;IACA;IACA;IACA;IACA;IACA;IACA;IACA;IACA;;;UAIa;EACf;EACA;;;;EAIA;EACA,KAAK,OAAO;EACZ,UAAU;IAAiB;IAAc;IAAoB;;;UAO9C;EACf,WAAW;EACX,OAAO;EACP,OAAO;EACP;EACA;EACA;EACA;EACA;EACA;EACA;EACA,SAAS;EACT;;;;;;iBAiEc,wBAAwB,MAAM,8BAA8B;iBA8I5D,0BAA0B,MAAM,uBAAuB;iBAwBvD,wBAAwB,MAAM;UAM7B;EACf;;EAEA;;UAGe;EACf;;EAEA;;EAEA,SAAS,eAAe;;EAExB;EACA;;UAGe;EACf,MAAM;EACN,SAAS;EACT;IACE;IACA;IACA;IACA;IACA,SAAS;MAAiB;MAAoB;MAAsB;;;;;;;;;iBAuExD,4BACd,QAAQ,yBACP"}
|
package/dist/rl.js
CHANGED
|
@@ -1,18 +1,19 @@
|
|
|
1
1
|
import { s as ValidationError } from "./errors-Dngq5h35.js";
|
|
2
|
-
import { i as makeRng } from "./internal-
|
|
3
|
-
import {
|
|
4
|
-
import {
|
|
2
|
+
import { i as makeRng } from "./internal-BMFSR8Ns.js";
|
|
3
|
+
import { t as mulberry32 } from "./random-Dn5fPWkt.js";
|
|
4
|
+
import { o as benjaminiHochberg } from "./power-and-mde-B8F2RdcD.js";
|
|
5
|
+
import { l as wilcoxonSignedRank } from "./paired-arms-D4aeIHUy.js";
|
|
5
6
|
import { r as observedSplitScore, s as trainingScore } from "./reward-nw2xZGZG.js";
|
|
6
7
|
import { s as runTaskScore } from "./run-record-BC0ebuRP.js";
|
|
7
|
-
import { i as filterDeterministicallyRewarded, l as campaignCellToRunRecord, n as extractVerifiableReward, r as extractVerifiableRewardsFromRecords, t as detectRewardHacking } from "./reward-hacking-
|
|
8
|
+
import { i as filterDeterministicallyRewarded, l as campaignCellToRunRecord, n as extractVerifiableReward, r as extractVerifiableRewardsFromRecords, t as detectRewardHacking } from "./reward-hacking-O5zKDANP.js";
|
|
8
9
|
import { n as InMemoryTraceStore } from "./store-DNe_Uv1Q.js";
|
|
9
|
-
import { t as runEvalCampaign } from "./eval-campaign-
|
|
10
|
+
import { t as runEvalCampaign } from "./eval-campaign-BfohKmzx.js";
|
|
10
11
|
import { s as assertRewardGate } from "./schema-C1aaAxTf.js";
|
|
11
12
|
import { t as isSplitEligible } from "./exporters-Df7TgHFv.js";
|
|
12
13
|
import { t as mintRolloutRows } from "./mint-DfODW1KW.js";
|
|
13
14
|
import { t as evaluateInterimReleaseConfidence } from "./sequential-CzK5DarL.js";
|
|
14
|
-
import { t as rubricPredictiveValidity } from "./rubric-predictive-validity-
|
|
15
|
-
import { n as thompsonCurriculum, r as varianceBasedCurriculum, t as observationsFromRunRecords } from "./active-curriculum-
|
|
15
|
+
import { t as rubricPredictiveValidity } from "./rubric-predictive-validity-2D5Gw9z9.js";
|
|
16
|
+
import { n as thompsonCurriculum, r as varianceBasedCurriculum, t as observationsFromRunRecords } from "./active-curriculum-OjIWgrUJ.js";
|
|
16
17
|
import { n as InMemoryOutcomeStore, t as FileSystemOutcomeStore } from "./outcome-store-ChBKlTd_.js";
|
|
17
18
|
import { createHash } from "node:crypto";
|
|
18
19
|
import { appendFileSync, existsSync, mkdirSync, readFileSync } from "node:fs";
|
|
@@ -414,14 +415,7 @@ function renameVariables(identifiers, rename = (n, i) => `${n}_${(i % 26 + 10).t
|
|
|
414
415
|
* on the option labels, not order). Caller provides the section extractor.
|
|
415
416
|
*/
|
|
416
417
|
function shuffleOrder(shuffleSection, seed) {
|
|
417
|
-
|
|
418
|
-
const rng = () => {
|
|
419
|
-
s = s + 1831565813 >>> 0;
|
|
420
|
-
let t = s;
|
|
421
|
-
t = Math.imul(t ^ t >>> 15, t | 1);
|
|
422
|
-
t ^= t + Math.imul(t ^ t >>> 7, t | 61);
|
|
423
|
-
return ((t ^ t >>> 14) >>> 0) / 4294967296;
|
|
424
|
-
};
|
|
418
|
+
const rng = mulberry32(seed);
|
|
425
419
|
return {
|
|
426
420
|
kind: "shuffle_order",
|
|
427
421
|
apply(scenario) {
|