@tangle-network/agent-eval 0.208.2 → 0.210.0
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 +26 -0
- package/README.md +1 -1
- package/dist/adapters/http.d.ts +2 -2
- package/dist/{agent-profile-CEhxR_I3.d.ts → agent-profile-BGyt2z8U.d.ts} +3 -3
- package/dist/{agent-profile-CEhxR_I3.d.ts.map → agent-profile-BGyt2z8U.d.ts.map} +1 -1
- package/dist/{agent-profile-cell-BHcB-mZX.d.ts → agent-profile-cell-BNp-Js9F.d.ts} +2 -3
- package/dist/agent-profile-cell-BNp-Js9F.d.ts.map +1 -0
- package/dist/{agent-profile-cell-DcFW4vOc.js → agent-profile-cell-BYc0bxsL.js} +2 -2
- package/dist/agent-profile-cell-BYc0bxsL.js.map +1 -0
- package/dist/analyst/index.d.ts +12 -12
- package/dist/analyst/index.js +5 -5
- package/dist/{analyze-runs-GZ0VSwui.js → analyze-runs-3xpby3p2.js} +6 -6
- package/dist/analyze-runs-3xpby3p2.js.map +1 -0
- package/dist/{analyze-runs-CTJyUplR.d.ts → analyze-runs-BlslTkOJ.d.ts} +4 -4
- package/dist/{analyze-runs-CTJyUplR.d.ts.map → analyze-runs-BlslTkOJ.d.ts.map} +1 -1
- package/dist/{benchmark-command-BC265T1r.js → benchmark-command-S8tCtkxh.js} +6 -6
- package/dist/{benchmark-command-BC265T1r.js.map → benchmark-command-S8tCtkxh.js.map} +1 -1
- package/dist/benchmarks/index.d.ts +5 -7
- package/dist/benchmarks/index.d.ts.map +1 -1
- package/dist/benchmarks/index.js +3 -3
- package/dist/builder-eval/index.js +1 -1
- package/dist/campaign/index.d.ts +6 -6
- package/dist/campaign/index.js +10 -10
- package/dist/{campaign-evidence-DW3Krxov.js → campaign-evidence-OcUciD-N.js} +4 -4
- package/dist/campaign-evidence-OcUciD-N.js.map +1 -0
- package/dist/{campaign-C5pjR-Qn.js → campaign-wvvJA1ps.js} +14 -14
- package/dist/{campaign-C5pjR-Qn.js.map → campaign-wvvJA1ps.js.map} +1 -1
- package/dist/claude-jsonl-dZir12m6.js +86 -0
- package/dist/claude-jsonl-dZir12m6.js.map +1 -0
- package/dist/cli.js +7 -7
- package/dist/contract/index.d.ts +10 -10
- package/dist/contract/index.js +92 -16
- package/dist/contract/index.js.map +1 -1
- package/dist/counterfactual-DtMWvn7D.js.map +1 -1
- package/dist/{default-registry-DZFWY2_E.d.ts → default-registry-Crk3QEy1.d.ts} +6 -6
- package/dist/{default-registry-DZFWY2_E.d.ts.map → default-registry-Crk3QEy1.d.ts.map} +1 -1
- package/dist/{default-registry-DX5R7_n9.js → default-registry-DF4Yp7HQ.js} +2 -2
- package/dist/{default-registry-DX5R7_n9.js.map → default-registry-DF4Yp7HQ.js.map} +1 -1
- package/dist/{define-agent-eval-C8zBSbsc.d.ts → define-agent-eval-B_zZY2AZ.d.ts} +7 -7
- package/dist/{define-agent-eval-C8zBSbsc.d.ts.map → define-agent-eval-B_zZY2AZ.d.ts.map} +1 -1
- package/dist/{define-agent-eval-BjKXcDQp.js → define-agent-eval-CoXXDCMu.js} +7 -7
- package/dist/{define-agent-eval-BjKXcDQp.js.map → define-agent-eval-CoXXDCMu.js.map} +1 -1
- package/dist/diagnosis/index.d.ts +2 -5
- package/dist/diagnosis/index.d.ts.map +1 -1
- package/dist/diagnosis/index.js +2 -26
- package/dist/diagnosis/index.js.map +1 -1
- package/dist/{dspy-rlm-engine-sHwdSxK3.js → dspy-rlm-engine-BpaKVKJA.js} +2 -2
- package/dist/{dspy-rlm-engine-sHwdSxK3.js.map → dspy-rlm-engine-BpaKVKJA.js.map} +1 -1
- package/dist/{engine-DProXJ7A.d.ts → engine-D-YZ32ZJ.d.ts} +5 -12
- package/dist/engine-D-YZ32ZJ.d.ts.map +1 -0
- package/dist/{eval-campaign-DU_p8qVt.js → eval-campaign-4byTtqrf.js} +4 -4
- package/dist/{eval-campaign-DU_p8qVt.js.map → eval-campaign-4byTtqrf.js.map} +1 -1
- package/dist/evaluation.d.ts +2 -2
- package/dist/{exact-types-Cq6xXNVR.d.ts → exact-types-DjhfZglz.d.ts} +2 -2
- package/dist/{exact-types-Cq6xXNVR.d.ts.map → exact-types-DjhfZglz.d.ts.map} +1 -1
- package/dist/experiment/index.d.ts +2 -2
- package/dist/experiment/index.js +8 -8
- package/dist/{feedback-trajectory-C6Z8PRoF.d.ts → feedback-trajectory-CX01700m.d.ts} +3 -3
- package/dist/{feedback-trajectory-C6Z8PRoF.d.ts.map → feedback-trajectory-CX01700m.d.ts.map} +1 -1
- package/dist/hosted/index.js +1 -1
- package/dist/{index-CbBfavbT.d.ts → index-D0_l25We.d.ts} +21 -42
- package/dist/{index-CbBfavbT.d.ts.map → index-D0_l25We.d.ts.map} +1 -1
- package/dist/{index-nwNoS582.d.ts → index-DnZdBxCL.d.ts} +14 -11
- package/dist/{index-nwNoS582.d.ts.map → index-DnZdBxCL.d.ts.map} +1 -1
- package/dist/{index-DkucR0KJ.d.ts → index-UxNTvn-w.d.ts} +6 -6
- package/dist/{index-DkucR0KJ.d.ts.map → index-UxNTvn-w.d.ts.map} +1 -1
- package/dist/{index-Bzto04CY.d.ts → index-xnhRdqik.d.ts} +9 -20
- package/dist/{index-Bzto04CY.d.ts.map → index-xnhRdqik.d.ts.map} +1 -1
- package/dist/index.d.ts +28 -37
- package/dist/index.d.ts.map +1 -1
- package/dist/index.js +28 -90
- package/dist/index.js.map +1 -1
- package/dist/judge-gate-C59znGmR.js +638 -0
- package/dist/judge-gate-C59znGmR.js.map +1 -0
- package/dist/judge-gate-D2hCppem.d.ts +439 -0
- package/dist/judge-gate-D2hCppem.d.ts.map +1 -0
- package/dist/{kind-factory-Cn1lbsAd.js → kind-factory-ivTx6koH.js} +2 -11
- package/dist/{kind-factory-Cn1lbsAd.js.map → kind-factory-ivTx6koH.js.map} +1 -1
- package/dist/{llm-judge-HLWASwUJ.js → llm-judge-Tr7MBUnf.js} +9 -9
- package/dist/llm-judge-Tr7MBUnf.js.map +1 -0
- package/dist/{matrix-Cqkk7eYI.d.ts → matrix-jHTsHEkR.d.ts} +2 -2
- package/dist/{matrix-Cqkk7eYI.d.ts.map → matrix-jHTsHEkR.d.ts.map} +1 -1
- package/dist/meta-eval/index.d.ts +3 -133
- package/dist/meta-eval/index.d.ts.map +1 -1
- package/dist/meta-eval/index.js +3 -276
- package/dist/meta-eval/index.js.map +1 -1
- package/dist/{mint-C1W8w5wo.d.ts → mint-CDy-brUR.d.ts} +2 -2
- package/dist/{mint-C1W8w5wo.d.ts.map → mint-CDy-brUR.d.ts.map} +1 -1
- package/dist/{mint-CWG-s2mI.js → mint-Csor1BLJ.js} +2 -2
- package/dist/{mint-CWG-s2mI.js.map → mint-Csor1BLJ.js.map} +1 -1
- package/dist/multishot/golden/index.d.ts +1 -1
- package/dist/multishot/index.d.ts +2 -2
- package/dist/openapi.json +1 -1
- package/dist/{paired-arms-CgWT7sHy.js → paired-arms-DzKn0TfY.js} +3 -5
- package/dist/{paired-arms-CgWT7sHy.js.map → paired-arms-DzKn0TfY.js.map} +1 -1
- package/dist/{paired-binary-b2L3WKqr.js → paired-binary-Q36bhn2R.js} +13 -9
- package/dist/paired-binary-Q36bhn2R.js.map +1 -0
- package/dist/{paired-promotion-decision-2deJ7sDX.js → paired-promotion-decision-BN6IQTiu.js} +2 -2
- package/dist/{paired-promotion-decision-2deJ7sDX.js.map → paired-promotion-decision-BN6IQTiu.js.map} +1 -1
- package/dist/pipelines/index.d.ts +1 -1
- package/dist/pipelines/index.js +2 -2
- package/dist/{prime-protocol-Csr9kcOM.d.ts → prime-protocol-B7et3tI7.d.ts} +2 -2
- package/dist/{prime-protocol-Csr9kcOM.d.ts.map → prime-protocol-B7et3tI7.d.ts.map} +1 -1
- package/dist/{produced-state-Bzlh09oj.js → produced-state-CKybuR9F.js} +3 -3
- package/dist/produced-state-CKybuR9F.js.map +1 -0
- package/dist/profile-cell.d.ts +2 -2
- package/dist/profile-cell.js +2 -2
- package/dist/{promotion-policy-CCmyEH_c.js → promotion-policy-CWW35UWq.js} +3 -3
- package/dist/{promotion-policy-CCmyEH_c.js.map → promotion-policy-CWW35UWq.js.map} +1 -1
- package/dist/{query-DlV0pdx4.js → query-B1D1qp2Z.js} +2 -2
- package/dist/{query-DlV0pdx4.js.map → query-B1D1qp2Z.js.map} +1 -1
- package/dist/{query-DBUQhehH.d.ts → query-DK1nWcmp.d.ts} +2 -3
- package/dist/{query-DBUQhehH.d.ts.map → query-DK1nWcmp.d.ts.map} +1 -1
- package/dist/{registry-DMkmhBQ5.d.ts → registry-BL7H33tj.d.ts} +3 -3
- package/dist/{registry-DMkmhBQ5.d.ts.map → registry-BL7H33tj.d.ts.map} +1 -1
- package/dist/{release-confidence-CkoXFx9I.d.ts → release-confidence-C4kI7lQi.d.ts} +4 -12
- package/dist/release-confidence-C4kI7lQi.d.ts.map +1 -0
- package/dist/{release-confidence-CiFg1EPq.js → release-confidence-Dbe9AS_X.js} +2 -2
- package/dist/{release-confidence-CiFg1EPq.js.map → release-confidence-Dbe9AS_X.js.map} +1 -1
- package/dist/{report-command-pXtxg5YK.js → report-command-CtIIsQKP.js} +3 -28
- package/dist/{report-command-pXtxg5YK.js.map → report-command-CtIIsQKP.js.map} +1 -1
- package/dist/reporting.d.ts +3 -3
- package/dist/reporting.js +3 -3
- package/dist/{researcher-CZFZjj-u.d.ts → researcher-DuIJ9IaA.d.ts} +4 -4
- package/dist/{researcher-CZFZjj-u.d.ts.map → researcher-DuIJ9IaA.d.ts.map} +1 -1
- package/dist/{reward-hacking-Cyk-QHk9.d.ts → reward-hacking-C6Kp54Av.d.ts} +2 -2
- package/dist/{reward-hacking-Cyk-QHk9.d.ts.map → reward-hacking-C6Kp54Av.d.ts.map} +1 -1
- package/dist/reward-nw2xZGZG.js.map +1 -1
- package/dist/rl.d.ts +10 -29
- package/dist/rl.d.ts.map +1 -1
- package/dist/rl.js +7 -7
- package/dist/rl.js.map +1 -1
- package/dist/rollout/index.d.ts +3 -3
- package/dist/rollout/index.js +4 -4
- package/dist/{rollout-l9w3Gdvh.js → rollout-D9bKKBnZ.js} +30 -165
- package/dist/rollout-D9bKKBnZ.js.map +1 -0
- package/dist/{rubric-predictive-validity-DIUwJJ9Y.d.ts → rubric-predictive-validity-BiNNEjpG.d.ts} +2 -2
- package/dist/{rubric-predictive-validity-DIUwJJ9Y.d.ts.map → rubric-predictive-validity-BiNNEjpG.d.ts.map} +1 -1
- package/dist/{run-record-BRlM99rX.js → run-record-DlTZ_lqe.js} +3 -13
- package/dist/run-record-DlTZ_lqe.js.map +1 -0
- package/dist/{run-record-BB290Y9A.js → run-record-ES07wfz9.js} +2 -2
- package/dist/{run-record-BB290Y9A.js.map → run-record-ES07wfz9.js.map} +1 -1
- package/dist/{run-record-DF-fuu31.d.ts → run-record-p2AYTrCn.d.ts} +3 -7
- package/dist/run-record-p2AYTrCn.d.ts.map +1 -0
- package/dist/search/index.d.ts +2 -24
- package/dist/search/index.d.ts.map +1 -1
- package/dist/search/index.js +3 -3
- package/dist/{search-kernel-CIie6xig.js → search-kernel-BIXWM7YV.js} +4 -4
- package/dist/search-kernel-BIXWM7YV.js.map +1 -0
- package/dist/{search-kernel-uKdPVRAe.d.ts → search-kernel-ah2GESe3.d.ts} +3 -3
- package/dist/{search-kernel-uKdPVRAe.d.ts.map → search-kernel-ah2GESe3.d.ts.map} +1 -1
- package/dist/{search-ledger-CXQPwdWz.js → search-ledger-aMTNQn_m.js} +2 -2
- package/dist/{search-ledger-CXQPwdWz.js.map → search-ledger-aMTNQn_m.js.map} +1 -1
- package/dist/{search-shipper-DhhofkDX.js → search-shipper-DKXWuLnp.js} +2 -2
- package/dist/{search-shipper-DhhofkDX.js.map → search-shipper-DKXWuLnp.js.map} +1 -1
- package/dist/{search-summary-BV5uehLd.js → search-summary-nwrtXxC_.js} +3 -3
- package/dist/{search-summary-BV5uehLd.js.map → search-summary-nwrtXxC_.js.map} +1 -1
- package/dist/{semantic-concept-judge-D1wH-YKc.js → semantic-concept-judge-BQxZyXdN.js} +3 -3
- package/dist/{semantic-concept-judge-D1wH-YKc.js.map → semantic-concept-judge-BQxZyXdN.js.map} +1 -1
- package/dist/{sequential-DMqr3sni.js → sequential-D-1PPCmM.js} +3 -3
- package/dist/{sequential-DMqr3sni.js.map → sequential-D-1PPCmM.js.map} +1 -1
- package/dist/{skillopt-optimization-method-Dcnh5Pvr.js → skillopt-optimization-method-DujPOiwD.js} +5 -5
- package/dist/{skillopt-optimization-method-Dcnh5Pvr.js.map → skillopt-optimization-method-DujPOiwD.js.map} +1 -1
- package/dist/{statistical-heldout-BP6iEJvR.js → statistical-heldout-1Gbmex7v.js} +2 -2
- package/dist/{statistical-heldout-BP6iEJvR.js.map → statistical-heldout-1Gbmex7v.js.map} +1 -1
- package/dist/{statistical-heldout-DFKtp-Qm.d.ts → statistical-heldout-8RGPIeyo.d.ts} +17 -14
- package/dist/statistical-heldout-8RGPIeyo.d.ts.map +1 -0
- package/dist/{store-otlp-BA7G1Du-.js → store-otlp-__ebQ6Hn.js} +2 -2
- package/dist/{store-otlp-BA7G1Du-.js.map → store-otlp-__ebQ6Hn.js.map} +1 -1
- package/dist/{store-tool-spans-DKoVbE-w.js → store-tool-spans-TbRBuIM7.js} +3 -3
- package/dist/{store-tool-spans-DKoVbE-w.js.map → store-tool-spans-TbRBuIM7.js.map} +1 -1
- package/dist/{store-tool-spans-9YJNMP-z.d.ts → store-tool-spans-wQ9idsnn.d.ts} +5 -5
- package/dist/{store-tool-spans-9YJNMP-z.d.ts.map → store-tool-spans-wQ9idsnn.d.ts.map} +1 -1
- package/dist/{summary-report-DvvesgR_.d.ts → summary-report-CK0ueoJd.d.ts} +2 -2
- package/dist/{summary-report-DvvesgR_.d.ts.map → summary-report-CK0ueoJd.d.ts.map} +1 -1
- package/dist/{summary-report-fXurE2TR.js → summary-report-DtdRucM0.js} +3 -3
- package/dist/{summary-report-fXurE2TR.js.map → summary-report-DtdRucM0.js.map} +1 -1
- package/dist/supervisor-run/index.d.ts +0 -8
- package/dist/supervisor-run/index.d.ts.map +1 -1
- package/dist/supervisor-run/index.js +36 -71
- package/dist/supervisor-run/index.js.map +1 -1
- package/dist/{systemone-review-Bt4JcxMc.d.ts → systemone-review-BReh3mvm.d.ts} +2 -2
- package/dist/{systemone-review-Bt4JcxMc.d.ts.map → systemone-review-BReh3mvm.d.ts.map} +1 -1
- package/dist/systemone.d.ts +3 -3
- package/dist/{tool-groups-j19pmOfP.d.ts → tool-groups-v28A-ZAF.d.ts} +3 -3
- package/dist/tool-groups-v28A-ZAF.d.ts.map +1 -0
- package/dist/{tool-waste-x_E8h9Ih.js → tool-waste-BYt5rdt8.js} +2 -2
- package/dist/{tool-waste-x_E8h9Ih.js.map → tool-waste-BYt5rdt8.js.map} +1 -1
- package/dist/{tool-waste-DxlebQkx.d.ts → tool-waste-Wi4g6Ekb.d.ts} +2 -2
- package/dist/{tool-waste-DxlebQkx.d.ts.map → tool-waste-Wi4g6Ekb.d.ts.map} +1 -1
- package/dist/{trace-questions-dRvmsbTk.d.ts → trace-questions-C26UvI3D.d.ts} +3 -3
- package/dist/{trace-questions-dRvmsbTk.d.ts.map → trace-questions-C26UvI3D.d.ts.map} +1 -1
- package/dist/trace-repair/index.d.ts +2 -9
- package/dist/trace-repair/index.d.ts.map +1 -1
- package/dist/trace-repair/index.js +1 -1
- package/dist/traces.d.ts +6 -8
- package/dist/traces.d.ts.map +1 -1
- package/dist/traces.js +6 -6
- package/dist/trajectory-replay/index.d.ts +0 -2
- package/dist/trajectory-replay/index.d.ts.map +1 -1
- package/dist/trajectory-replay/index.js +1 -1
- package/dist/{tree-CJOXbVcv.js → tree-kc1d80yF.js} +5 -25
- package/dist/tree-kc1d80yF.js.map +1 -0
- package/dist/{types-CFCUZk0B.d.ts → types-Dv9sYwBB.d.ts} +4 -4
- package/dist/{types-CFCUZk0B.d.ts.map → types-Dv9sYwBB.d.ts.map} +1 -1
- package/dist/{types-DAPpAkd4.d.ts → types-KEkKkETv.d.ts} +2 -2
- package/dist/{types-DAPpAkd4.d.ts.map → types-KEkKkETv.d.ts.map} +1 -1
- package/dist/{types-BlSBUNRd.d.ts → types-tWFY6bON.d.ts} +3 -3
- package/dist/{types-BlSBUNRd.d.ts.map → types-tWFY6bON.d.ts.map} +1 -1
- package/dist/wire/index.d.ts +1 -1
- package/docs/concepts.md +13 -0
- package/docs/experiment.md +10 -0
- package/docs/public-api.md +399 -424
- package/docs/trace-analysis.md +3 -0
- package/package.json +6 -5
- package/dist/agent-profile-cell-BHcB-mZX.d.ts.map +0 -1
- package/dist/agent-profile-cell-DcFW4vOc.js.map +0 -1
- package/dist/analyze-runs-GZ0VSwui.js.map +0 -1
- package/dist/campaign-evidence-DW3Krxov.js.map +0 -1
- package/dist/claude-jsonl-CG3JUbTJ.js +0 -211
- package/dist/claude-jsonl-CG3JUbTJ.js.map +0 -1
- package/dist/engine-DProXJ7A.d.ts.map +0 -1
- package/dist/llm-judge-HLWASwUJ.js.map +0 -1
- package/dist/paired-binary-b2L3WKqr.js.map +0 -1
- package/dist/produced-state-Bzlh09oj.js.map +0 -1
- package/dist/release-confidence-CkoXFx9I.d.ts.map +0 -1
- package/dist/rollout-l9w3Gdvh.js.map +0 -1
- package/dist/run-record-BRlM99rX.js.map +0 -1
- package/dist/run-record-DF-fuu31.d.ts.map +0 -1
- package/dist/search-kernel-CIie6xig.js.map +0 -1
- package/dist/series-convergence-CjO2QdRW.js +0 -43
- package/dist/series-convergence-CjO2QdRW.js.map +0 -1
- package/dist/series-convergence-hEfKdoi-.d.ts +0 -126
- package/dist/series-convergence-hEfKdoi-.d.ts.map +0 -1
- package/dist/statistical-heldout-DFKtp-Qm.d.ts.map +0 -1
- package/dist/tool-groups-j19pmOfP.d.ts.map +0 -1
- package/dist/tree-CJOXbVcv.js.map +0 -1
|
@@ -3886,6 +3886,6 @@ function shellQuote(value) {
|
|
|
3886
3886
|
return `'${value.replaceAll("'", `'\\''`)}'`;
|
|
3887
3887
|
}
|
|
3888
3888
|
//#endregion
|
|
3889
|
-
export { ADMISSION_CONFIG_DEFAULTS, ADMISSION_EXCLUSION_MEANING, ADMISSION_EXCLUSION_ORDER, ADMISSION_STRATA, AdmissionDenominatorError, AdmissionIndependenceError, BLINDED_FIELDS, CONTROL_SCREENING_MODES, CREDIT_TERMS, ContinuationPolicyViolationError, ContinuationSymmetryError, DEGENERATE_STRATEGIES, DSPY_REPAIR_SIGNATURE, DSPY_REPAIR_TASK_TOKEN, MINI_SWE_SYSTEM_MESSAGE, NO_DECISIVE_FAILURE,
|
|
3889
|
+
export { ADMISSION_CONFIG_DEFAULTS, ADMISSION_EXCLUSION_MEANING, ADMISSION_EXCLUSION_ORDER, ADMISSION_STRATA, AdmissionDenominatorError, AdmissionIndependenceError, BLINDED_FIELDS, CONTROL_SCREENING_MODES, CREDIT_TERMS, ContinuationPolicyViolationError, ContinuationSymmetryError, DEGENERATE_STRATEGIES, DSPY_REPAIR_SIGNATURE, DSPY_REPAIR_TASK_TOKEN, MINI_SWE_SYSTEM_MESSAGE, NO_DECISIVE_FAILURE, NondeterministicOracleError, OUTPUT_ELISION_THRESHOLD, REPAIR_CONTRACT_LINES, REPAIR_QUESTION, REPAIR_REPAIR_CONTRACT_LINES, SCAFFOLD_INTERVENTION_BUDGET, SUBMIT_SENTINEL, SUITE_REWARD_UNIT, TB_REPAIR_ADMISSION_CRITERIA, TestOracleError, TestSuiteTamperedError, UncalibratedControlError, admissionArtifact, admitRow, admittedCount, admittedRowIds, askRepairArm, assertAnalystIndependent, assertArmSymmetry, assertChainReconciles, assertControlCalibrated, assertDenominatorIntact, assertDeterministicOracle, assertDspyRepairEngine, blindTrajectory, buildDenominatorChain, checkInterventionBudget, classifyActionPayload, continuationPolicyDigest, continuationSeed, controlCanRescue, countFunnel, createCompletionRepairArm, createDockerContinuationEnvironment, createDspyRepairArm, defineControlPolicy, definePinnedContinuationPolicy, deltaRepair, dockerRunArgs, dspyRepairInstructions, gradeRepairRow, injectedTestOracle, isRecordedTimeout, noOpInjectionStep, nodeProcessRunner, normalizeActionForComparison, oracleDeterminism, parseAction, parseAnalystResponse, parseTaskOracleRegistry, renderAdmissionReport, renderDeltaRepairReport, renderFormatErrorObservation, renderInstanceMessage, renderObservation, renderRepairTrajectory, renderTimeoutObservation, repairArmAsymmetries, repairArmPromptSha256, repairArmResponse, repairCredit, repairFinding, repairQuestionSha256, repairTaskDefinition, repairTaskPolicy, repairTrajectoryHeader, resolveAdmissionConfig, rolloutDigest, rolloutRecordedSteps, runAdmission, runContinuation, scanShellAction, stratumOf, submissionOf, taskOracleRegistry, testSuiteDigest, toRecordedSteps, totalCost, totalUsage };
|
|
3890
3890
|
|
|
3891
3891
|
//# sourceMappingURL=index.js.map
|
package/dist/traces.d.ts
CHANGED
|
@@ -1,16 +1,16 @@
|
|
|
1
1
|
import { c as ValidationError, o as LimitExceededError, r as CaptureIntegrityError, s as NotFoundError, t as AgentEvalError } from "./errors-DEE6u6ot.js";
|
|
2
2
|
import { C as ToolSpan, D as isToolSpan, E as isLlmSpan, S as TRACE_SCHEMA_VERSION, T as isJudgeSpan, _ as SandboxSpan, a as FAILURE_CLASSES, b as SpanKind, c as JudgeSpan, d as RetrievalSpan, f as Run, g as RunStatus, h as RunOutcome, i as EventKind, l as LlmSpan, m as RunLayer, n as BudgetLedgerEntry, o as FailureClass, p as RunCaptureReport, r as BudgetSpec, s as GenericSpan, t as Artifact, u as Message, v as Span, w as TraceEvent, x as SpanStatus, y as SpanBase } from "./schema-2g7trUwH.js";
|
|
3
|
-
import { a as RunRecord, c as RunSplitTag, d as RunTokenUsage, u as RunTerminalOutcome } from "./run-record-
|
|
4
|
-
import { A as DEFAULT_TRACE_ANALYST_BUDGETS, B as TraceAnalystSpan, C as BoundedTraceAnalysisStoreOptions, D as TRACE_ANALYSIS_LIMITS, E as SpanSourceReader, F as SearchTraceResult, G as ViewTraceOversized, H as TraceAnalystSpanStatus, I as SpanMatchRecord, K as ViewTraceResult, L as TRACE_ANALYST_TRUNCATION_MARKER_PREFIX, M as ErrorCluster, N as QueryTracesPage, O as TraceAnalysisStore, P as SearchSpanResult, R as TraceAnalystByteBudgets, S as createBoundedTraceAnalysisStore, T as ReadSpanSourceResult, U as TraceAnalystTraceSummary, V as TraceAnalystSpanKind, W as ViewSpansResult, j as DatasetOverview, k as TraceAnalysisStoreContext, w as ReadSpanSourceInput, z as TraceAnalystFilters } from "./types-
|
|
3
|
+
import { a as RunRecord, c as RunSplitTag, d as RunTokenUsage, u as RunTerminalOutcome } from "./run-record-p2AYTrCn.js";
|
|
4
|
+
import { A as DEFAULT_TRACE_ANALYST_BUDGETS, B as TraceAnalystSpan, C as BoundedTraceAnalysisStoreOptions, D as TRACE_ANALYSIS_LIMITS, E as SpanSourceReader, F as SearchTraceResult, G as ViewTraceOversized, H as TraceAnalystSpanStatus, I as SpanMatchRecord, K as ViewTraceResult, L as TRACE_ANALYST_TRUNCATION_MARKER_PREFIX, M as ErrorCluster, N as QueryTracesPage, O as TraceAnalysisStore, P as SearchSpanResult, R as TraceAnalystByteBudgets, S as createBoundedTraceAnalysisStore, T as ReadSpanSourceResult, U as TraceAnalystTraceSummary, V as TraceAnalystSpanKind, W as ViewSpansResult, j as DatasetOverview, k as TraceAnalysisStoreContext, w as ReadSpanSourceInput, z as TraceAnalystFilters } from "./types-KEkKkETv.js";
|
|
5
5
|
import { $ as NoopRawProviderSink, Q as InMemoryRawProviderSinkOptions, X as FileSystemRawProviderSinkOptions, Y as FileSystemRawProviderSink, Z as InMemoryRawProviderSink, at as defaultProviderRedactor, et as ProviderRedactor, it as RawProviderSinkFilter, nt as RawProviderEvent, ot as providerFromBaseUrl, rt as RawProviderSink, tt as RawProviderDirection } from "./types-Lub7o6bN.js";
|
|
6
6
|
import { a as RunFilter, i as InMemoryTraceStore, n as FileSystemTraceStore, o as SpanFilter, r as FileSystemTraceStoreOptions, s as TraceStore, t as EventFilter } from "./store-C4avFjIi.js";
|
|
7
|
-
import { _ as buildTraceAnalysisToolDescriptors, g as UNTRUSTED_TRACE_TEXT, h as TraceAnalysisToolDescriptor, m as TRACE_ANALYST_TOOL_NAMESPACE, p as BuildTraceAnalysisToolsOptions
|
|
7
|
+
import { _ as buildTraceAnalysisToolDescriptors, g as UNTRUSTED_TRACE_TEXT, h as TraceAnalysisToolDescriptor, m as TRACE_ANALYST_TOOL_NAMESPACE, p as BuildTraceAnalysisToolsOptions } from "./engine-D-YZ32ZJ.js";
|
|
8
8
|
import { a as SpanHandle, i as RunCompleteHookContext, n as CaptureWrite, o as TraceEmitter, r as RunCompleteHook, s as TraceEmitterOptions, t as CaptureErrorHandler } from "./emitter-HcCmFQl_.js";
|
|
9
9
|
import { S as shareAllowed, _ as emptyRedactionReport, a as RedactionFinding, b as redactForShare, c as SafetyCategory, d as ShareSafetyVerdict, f as assessShareSafety, g as detectPersonalData, h as detectCredential, i as RedactOptions, l as ShareSafetyFinding, m as combineVerdicts, n as REDACTION_PROFILES, o as RedactionProfile, p as classifyKey, r as REDACTION_VERSION, s as RedactionReport, t as AssessOptions, u as ShareSafetyStatus, v as normalizeKey, x as redactText, y as redact } from "./redact-Cveoq6fJ.js";
|
|
10
10
|
import { C as TOOL_LATENCY_MS, D as asNumber, E as applyLlmSpanOtlpAttributes, O as contextInputTokens, S as TOOL_ARGS_CAPTURED, T as TOOL_NAME_ATTR_KEYS, _ as LlmSpanOtlpInput, a as LLM_CACHE_WRITE_TOKEN_ATTR_KEYS, b as RUN_COST_ATTR_KEYS, c as LLM_COST_USD, d as LLM_MODEL_ATTR_KEYS, f as LLM_MODEL_NAME, g as LLM_REASONING_TOKEN_ATTR_KEYS, h as LLM_REASONING_TOKENS, i as LLM_CACHE_WRITE_TOKENS, k as firstNumberAttr, l as LLM_INPUT_TOKENS, m as LLM_OUTPUT_TOKEN_ATTR_KEYS, n as LLM_CACHED_TOKENS, o as LLM_CONTEXT_TOKENS, p as LLM_OUTPUT_TOKENS, r as LLM_CACHED_TOKEN_ATTR_KEYS, s as LLM_COST_ATTR_KEYS, t as INPUT_VALUE, u as LLM_INPUT_TOKEN_ATTR_KEYS, v as OPENINFERENCE_SPAN_KIND, w as TOOL_NAME, x as SPAN_KIND_ATTR_KEYS, y as OUTPUT_VALUE } from "./attribute-vocabulary-CcXqHODT.js";
|
|
11
|
-
import { A as scoreTraceInsightReadiness, B as OtlpSpan, C as describeTraceInsightScope, D as isTraceInsightAttribution, E as isTraceInsightArtifact, F as analyzeTraces, G as ExtractUsageFromSseOptions, H as CaptureFetchContext, I as OtlpFlatLine, J as extractUsage, K as ExtractedUsage, L as OTEL_AGENT_EVAL_SCOPE, M as AnalyzeTracesInput, N as AnalyzeTracesOptions, O as isTraceInsightEvidence, P as AnalyzeTracesResult, R as OtlpExport, S as defaultTraceInsightPanel, T as inferDomainKeywords, U as CaptureFetchOptions, V as exportRunAsOtlp, W as captureFetchToRawSink, X as extractUsageFromSse, Y as extractUsageFromResponse, _ as TraceInsightReadiness, a as SpanRecordsToTraceAnalysisStoreOptions, b as buildTraceInsightContext, c as spanRecordsToTraceAnalysisStore, d as TraceInsightEvidence, f as TraceInsightFinding, g as TraceInsightQuestion, h as TraceInsightQualityGate, i as OtlpFileTraceStoreOptions, j as tokenizeDomainWords, k as planTraceInsightQuestions, l as TraceInsightAttribution, m as TraceInsightPromptInput, n as toolSpansToTraceAnalysisStore, o as ToolSpansToTraceAnalysisStoreOptions, p as TraceInsightPanelRole, q as SseUsageMode, r as OtlpFileTraceStore, s as otlpTextToTraceAnalysisStore, t as ToolTraceMissingError, u as TraceInsightContext, v as TraceInsightSuite, w as domainEvidencePattern, x as buildTraceInsightPrompt, y as TraceInsightTask, z as OtlpResourceSpans } from "./store-tool-spans-
|
|
11
|
+
import { A as scoreTraceInsightReadiness, B as OtlpSpan, C as describeTraceInsightScope, D as isTraceInsightAttribution, E as isTraceInsightArtifact, F as analyzeTraces, G as ExtractUsageFromSseOptions, H as CaptureFetchContext, I as OtlpFlatLine, J as extractUsage, K as ExtractedUsage, L as OTEL_AGENT_EVAL_SCOPE, M as AnalyzeTracesInput, N as AnalyzeTracesOptions, O as isTraceInsightEvidence, P as AnalyzeTracesResult, R as OtlpExport, S as defaultTraceInsightPanel, T as inferDomainKeywords, U as CaptureFetchOptions, V as exportRunAsOtlp, W as captureFetchToRawSink, X as extractUsageFromSse, Y as extractUsageFromResponse, _ as TraceInsightReadiness, a as SpanRecordsToTraceAnalysisStoreOptions, b as buildTraceInsightContext, c as spanRecordsToTraceAnalysisStore, d as TraceInsightEvidence, f as TraceInsightFinding, g as TraceInsightQuestion, h as TraceInsightQualityGate, i as OtlpFileTraceStoreOptions, j as tokenizeDomainWords, k as planTraceInsightQuestions, l as TraceInsightAttribution, m as TraceInsightPromptInput, n as toolSpansToTraceAnalysisStore, o as ToolSpansToTraceAnalysisStoreOptions, p as TraceInsightPanelRole, q as SseUsageMode, r as OtlpFileTraceStore, s as otlpTextToTraceAnalysisStore, t as ToolTraceMissingError, u as TraceInsightContext, v as TraceInsightSuite, w as domainEvidencePattern, x as buildTraceInsightPrompt, y as TraceInsightTask, z as OtlpResourceSpans } from "./store-tool-spans-wQ9idsnn.js";
|
|
12
12
|
import { a as RunIntegrityReport, i as RunIntegrityIssueCode, n as RunIntegrityExpectations, o as assertRunCaptured, r as RunIntegrityIssue, s as throwIfRunIncomplete, t as RunIntegrityError } from "./integrity-zloavsM_.js";
|
|
13
|
-
import { a as groupBy, c as
|
|
13
|
+
import { a as groupBy, c as llmSpans, d as runsForScenario, f as toolSpans, i as argHash, l as runFailureClass, n as RunMetric, o as hasCapturedToolArgs, r as aggregateLlm, s as judgeSpans, t as RUN_METRICS, u as runMetricExtractor } from "./query-DK1nWcmp.js";
|
|
14
14
|
import { SpanKind as SpanKind$1 } from "@tangle-network/agent-trace-contract";
|
|
15
15
|
//#region src/trace-analyst/errors.d.ts
|
|
16
16
|
/** Invalid trace-tool arguments, including malformed filters and regexes. */
|
|
@@ -321,13 +321,11 @@ export declare function otlpToRunRecords(otlpJsonl: string, opts: OtlpToRunRecor
|
|
|
321
321
|
export declare function otlpRowsToRunRecords(rows: Iterable<object>, opts: OtlpToRunRecordsOptions): RunRecord[];
|
|
322
322
|
/** As {@link otlpToRunRecords} but returns the prompt/completion text too. */
|
|
323
323
|
export declare function otlpToTraceRunRecords(otlpJsonl: string, opts: OtlpToRunRecordsOptions): OtlpTraceRunRecord[];
|
|
324
|
-
/** Parsed-row counterpart to {@link otlpToTraceRunRecords}. */
|
|
325
|
-
export declare function otlpRowsToTraceRunRecords(rows: Iterable<object>, opts: OtlpToRunRecordsOptions): OtlpTraceRunRecord[];
|
|
326
324
|
//#endregion
|
|
327
325
|
//#region src/trace-analyst/prompts.d.ts
|
|
328
326
|
/** General policy for recursive, evidence-backed trace analysis. */
|
|
329
327
|
export declare const TRACE_ANALYST_ACTOR_DESCRIPTION = "Answer the question by inspecting the OTLP trace dataset with the available tools.\n\n1. Call getDatasetOverview first. Use its real trace ids and dataset size to plan the investigation.\n2. Narrow with queryTraces and countTraces before scanning large payloads.\n3. For a small trace, use viewTrace. For a large trace, use searchTrace and then viewSpans or searchSpan.\n4. Never invent a trace id, span id, tool result, error, frequency, or final outcome.\n5. When a search reports has_more, refine the query before drawing a conclusion.\n6. Use llm_query only over evidence already loaded. A recursive query cannot inspect traces itself.\n7. Cite exact evidence URIs returned by the tools. Include a short exact excerpt when it supports the claim.\n8. Return no finding when the available evidence cannot support one.\n\nThe prose answer must directly answer the question and state important uncertainty.\nThe findings array contains only actionable or decision-relevant claims supported by inspected evidence.";
|
|
330
328
|
export declare const TRACE_ANALYST_ACTOR_DESCRIPTION_VERSION = "trace-analyst-research-v1-2026-07-30";
|
|
331
329
|
//#endregion
|
|
332
|
-
export { type AnalyzeTracesInput, type AnalyzeTracesOptions, type AnalyzeTracesResult, Artifact, AssessOptions, type BoundedTraceAnalysisStoreOptions, BudgetLedgerEntry, BudgetSpec, type BuildTraceAnalysisToolsOptions, CaptureErrorHandler, CaptureFetchContext, CaptureFetchOptions, CaptureWrite, DEFAULT_TRACE_ANALYST_BUDGETS, type DatasetOverview, type ErrorCluster, EventFilter, EventKind, ExtractUsageFromSseOptions, ExtractedUsage, FAILURE_CLASSES, FailureClass, FileSystemRawProviderSink, FileSystemRawProviderSinkOptions, FileSystemTraceStore, FileSystemTraceStoreOptions, type FlattenOtlpOptions, GenericSpan, INPUT_VALUE, InMemoryRawProviderSink, InMemoryRawProviderSinkOptions, InMemoryTraceStore, JudgeSpan, LLM_CACHED_TOKENS, LLM_CACHED_TOKEN_ATTR_KEYS, LLM_CACHE_WRITE_TOKENS, LLM_CACHE_WRITE_TOKEN_ATTR_KEYS, LLM_CONTEXT_TOKENS, LLM_COST_ATTR_KEYS, LLM_COST_USD, LLM_INPUT_TOKENS, LLM_INPUT_TOKEN_ATTR_KEYS, LLM_MODEL_ATTR_KEYS, LLM_MODEL_NAME, LLM_OUTPUT_TOKENS, LLM_OUTPUT_TOKEN_ATTR_KEYS, LLM_REASONING_TOKENS, LLM_REASONING_TOKEN_ATTR_KEYS, LlmSpan, LlmSpanOtlpInput, Message, NoopRawProviderSink, OPENINFERENCE_SPAN_KIND, OTEL_AGENT_EVAL_SCOPE, OUTPUT_VALUE, OtlpExport, OtlpFileTraceStore, type OtlpFileTraceStoreOptions, type OtlpFlatLine, OtlpResourceSpans, OtlpSpan, type OtlpToRunRecordsOptions, type OtlpTraceRunRecord, type ProjectedOtlpSpan, ProviderRedactor, type QueryTracesPage, REDACTION_PROFILES, REDACTION_VERSION, RUN_COST_ATTR_KEYS, RUN_METRICS, RawProviderDirection, RawProviderEvent, RawProviderSink, RawProviderSinkFilter, type ReadSpanSourceInput, type ReadSpanSourceResult, RedactOptions, RedactionFinding, RedactionProfile, RedactionReport, RetrievalSpan, Run, RunCaptureReport, RunCompleteHook, RunCompleteHookContext, RunFilter, RunIntegrityError, RunIntegrityExpectations, RunIntegrityIssue, RunIntegrityIssueCode, RunIntegrityReport, RunLayer, RunMetric, RunOutcome, RunStatus, SPAN_KIND_ATTR_KEYS, SafetyCategory, SandboxSpan, type SearchSpanResult, type SearchTraceResult, ShareSafetyFinding, ShareSafetyStatus, ShareSafetyVerdict, Span, SpanBase, SpanFilter, SpanHandle, SpanKind, type SpanMatchRecord, type SpanRecordsToTraceAnalysisStoreOptions, type SpanSourceReader, SpanStatus, SseUsageMode, TOOL_ARGS_CAPTURED, TOOL_LATENCY_MS, TOOL_NAME, TOOL_NAME_ATTR_KEYS, TRACE_ANALYSIS_LIMITS, TRACE_ANALYST_TOOL_NAMESPACE, TRACE_ANALYST_TRUNCATION_MARKER_PREFIX, TRACE_SCHEMA_VERSION, ToolSpan, type ToolSpansToTraceAnalysisStoreOptions, ToolTraceMissingError, type TraceAggregate, type TraceAnalysisStore, type TraceAnalysisStoreContext, type TraceAnalysisToolDescriptor, type TraceAnalystByteBudgets, type TraceAnalystFilters, type TraceAnalystHookOptions, type TraceAnalystSpan, type TraceAnalystSpanKind, type TraceAnalystSpanStatus, type TraceAnalystTraceSummary, TraceEmitter, TraceEmitterOptions, TraceEvent, type TraceInsightAttribution, type TraceInsightContext, type TraceInsightEvidence, type TraceInsightFinding, type TraceInsightPanelRole, type TraceInsightPromptInput, type TraceInsightQualityGate, type TraceInsightQuestion, type TraceInsightReadiness, type TraceInsightSuite, type TraceInsightTask, TraceStore, UNTRUSTED_TRACE_TEXT, type ViewSpansResult, type ViewTraceOversized, type ViewTraceResult, aggregateLlm, analyzeTraces, applyLlmSpanOtlpAttributes, argHash, asNumber, assertRunCaptured, assessShareSafety, buildTraceAnalysisToolDescriptors, buildTraceInsightContext, buildTraceInsightPrompt, captureFetchToRawSink, classifyKey, combineVerdicts, contextInputTokens, createBoundedTraceAnalysisStore, defaultProviderRedactor, defaultTraceInsightPanel, describeTraceInsightScope, detectCredential, detectPersonalData, domainEvidencePattern, emptyRedactionReport, exportRunAsOtlp, extractUsage, extractUsageFromResponse, extractUsageFromSse, firstNumberAttr, groupBy, hasCapturedToolArgs, inferDomainKeywords, isJudgeSpan, isLlmSpan,
|
|
330
|
+
export { type AnalyzeTracesInput, type AnalyzeTracesOptions, type AnalyzeTracesResult, Artifact, AssessOptions, type BoundedTraceAnalysisStoreOptions, BudgetLedgerEntry, BudgetSpec, type BuildTraceAnalysisToolsOptions, CaptureErrorHandler, CaptureFetchContext, CaptureFetchOptions, CaptureWrite, DEFAULT_TRACE_ANALYST_BUDGETS, type DatasetOverview, type ErrorCluster, EventFilter, EventKind, ExtractUsageFromSseOptions, ExtractedUsage, FAILURE_CLASSES, FailureClass, FileSystemRawProviderSink, FileSystemRawProviderSinkOptions, FileSystemTraceStore, FileSystemTraceStoreOptions, type FlattenOtlpOptions, GenericSpan, INPUT_VALUE, InMemoryRawProviderSink, InMemoryRawProviderSinkOptions, InMemoryTraceStore, JudgeSpan, LLM_CACHED_TOKENS, LLM_CACHED_TOKEN_ATTR_KEYS, LLM_CACHE_WRITE_TOKENS, LLM_CACHE_WRITE_TOKEN_ATTR_KEYS, LLM_CONTEXT_TOKENS, LLM_COST_ATTR_KEYS, LLM_COST_USD, LLM_INPUT_TOKENS, LLM_INPUT_TOKEN_ATTR_KEYS, LLM_MODEL_ATTR_KEYS, LLM_MODEL_NAME, LLM_OUTPUT_TOKENS, LLM_OUTPUT_TOKEN_ATTR_KEYS, LLM_REASONING_TOKENS, LLM_REASONING_TOKEN_ATTR_KEYS, LlmSpan, LlmSpanOtlpInput, Message, NoopRawProviderSink, OPENINFERENCE_SPAN_KIND, OTEL_AGENT_EVAL_SCOPE, OUTPUT_VALUE, OtlpExport, OtlpFileTraceStore, type OtlpFileTraceStoreOptions, type OtlpFlatLine, OtlpResourceSpans, OtlpSpan, type OtlpToRunRecordsOptions, type OtlpTraceRunRecord, type ProjectedOtlpSpan, ProviderRedactor, type QueryTracesPage, REDACTION_PROFILES, REDACTION_VERSION, RUN_COST_ATTR_KEYS, RUN_METRICS, RawProviderDirection, RawProviderEvent, RawProviderSink, RawProviderSinkFilter, type ReadSpanSourceInput, type ReadSpanSourceResult, RedactOptions, RedactionFinding, RedactionProfile, RedactionReport, RetrievalSpan, Run, RunCaptureReport, RunCompleteHook, RunCompleteHookContext, RunFilter, RunIntegrityError, RunIntegrityExpectations, RunIntegrityIssue, RunIntegrityIssueCode, RunIntegrityReport, RunLayer, RunMetric, RunOutcome, RunStatus, SPAN_KIND_ATTR_KEYS, SafetyCategory, SandboxSpan, type SearchSpanResult, type SearchTraceResult, ShareSafetyFinding, ShareSafetyStatus, ShareSafetyVerdict, Span, SpanBase, SpanFilter, SpanHandle, SpanKind, type SpanMatchRecord, type SpanRecordsToTraceAnalysisStoreOptions, type SpanSourceReader, SpanStatus, SseUsageMode, TOOL_ARGS_CAPTURED, TOOL_LATENCY_MS, TOOL_NAME, TOOL_NAME_ATTR_KEYS, TRACE_ANALYSIS_LIMITS, TRACE_ANALYST_TOOL_NAMESPACE, TRACE_ANALYST_TRUNCATION_MARKER_PREFIX, TRACE_SCHEMA_VERSION, ToolSpan, type ToolSpansToTraceAnalysisStoreOptions, ToolTraceMissingError, type TraceAggregate, type TraceAnalysisStore, type TraceAnalysisStoreContext, type TraceAnalysisToolDescriptor, type TraceAnalystByteBudgets, type TraceAnalystFilters, type TraceAnalystHookOptions, type TraceAnalystSpan, type TraceAnalystSpanKind, type TraceAnalystSpanStatus, type TraceAnalystTraceSummary, TraceEmitter, TraceEmitterOptions, TraceEvent, type TraceInsightAttribution, type TraceInsightContext, type TraceInsightEvidence, type TraceInsightFinding, type TraceInsightPanelRole, type TraceInsightPromptInput, type TraceInsightQualityGate, type TraceInsightQuestion, type TraceInsightReadiness, type TraceInsightSuite, type TraceInsightTask, TraceStore, UNTRUSTED_TRACE_TEXT, type ViewSpansResult, type ViewTraceOversized, type ViewTraceResult, aggregateLlm, analyzeTraces, applyLlmSpanOtlpAttributes, argHash, asNumber, assertRunCaptured, assessShareSafety, buildTraceAnalysisToolDescriptors, buildTraceInsightContext, buildTraceInsightPrompt, captureFetchToRawSink, classifyKey, combineVerdicts, contextInputTokens, createBoundedTraceAnalysisStore, defaultProviderRedactor, defaultTraceInsightPanel, describeTraceInsightScope, detectCredential, detectPersonalData, domainEvidencePattern, emptyRedactionReport, exportRunAsOtlp, extractUsage, extractUsageFromResponse, extractUsageFromSse, firstNumberAttr, groupBy, hasCapturedToolArgs, inferDomainKeywords, isJudgeSpan, isLlmSpan, isToolSpan, isTraceInsightArtifact, isTraceInsightAttribution, isTraceInsightEvidence, judgeSpans, llmSpans, normalizeKey, otlpTextToTraceAnalysisStore, planTraceInsightQuestions, providerFromBaseUrl, redact, redactForShare, redactText, runFailureClass, runMetricExtractor, runsForScenario, scoreTraceInsightReadiness, shareAllowed, spanRecordsToTraceAnalysisStore, throwIfRunIncomplete, tokenizeDomainWords, toolSpans, toolSpansToTraceAnalysisStore };
|
|
333
331
|
//# sourceMappingURL=traces.d.ts.map
|
package/dist/traces.d.ts.map
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"traces.d.ts","names":["SpanKind"],"sources":["../src/trace-analyst/errors.ts","../src/trace/otlp-attributes.ts","../src/trace/store-to-otlp.ts","../src/trace-analyst/hook.ts","../src/trace-analyst/otlp-flatten.ts","../src/trace-analyst/otlp-span.ts","../src/trace-analyst/otlp-to-run-records.ts","../src/trace-analyst/prompts.ts"],"mappings":";;;;;;;;;;;;;;;;qBASa,qCAAqC;WAC/B;;;qBAIN,gCAAgC;WAC1B;WACR;WACA;WACA;EAET,YAAY,mBAAmB,gBAAgB,eAAe;;;qBASnD,wCAAwC;WAClC;WACR;EAET,YAAY,mBAAmB,iBAAiB;IAAY;;;qBAMjD,8BAA8B;WACxB;WACR;EAET,YAAY;;qBAMD,+BAA+B;WACjC;WACA;WACA;EAET,YAAY,cAAc,oBAAoB;;qBAcnC,gCAAgC;WAClC;WACA;WACA;EAET,YAAY,cAAc,qBAAqB,qBAAqB;;qBAQzD,2BAA2B;WACrB;WACR;EAET,YAAY;;qBAMD,0BAA0B;WACpB;WACR;WACA;EAET,YAAY,kBAAkB;;;;YC1EpB,oBAAoB,KAC9B;wBAkBc,4BACd,YAAY,yBACZ,MAAM;;;;;;wBAWQ,iCAAiC,eAAeA;;;iBCjB/C;;EAEf;;EAEA;;EAEA;;;EAGA;;;;;;;;;;;;iBAae;;EAEf;;EAEA;;EAEA;;;;iBAKe;;;EAGf;;;EAGA,sBAAsB,KAAK,QAAQ;;EAEnC,iBAAiB,KAAK,QAAQ;;;;;;;;;;;wBAYhB,yBACd,iBAAiB,4BAA4B,oBAC7C,iBACA,OAAM,0BACL;;;UCxEc;;;;;;EAMf,SAAS,KAAK;IAAoC,SAAS;;;;;;;EAM3D;;;;;;EAMA,QAAQ,QAAQ,qBAAqB,KAAK,2BAA2B;;;;;EAKrE,aAAa,KAAK;;;;;;EAMlB,UAAU,QAAQ,qBAAqB,KAAK;;wBAM9B,0BAA0B,MAAM,0BAA0B;;;UCnCzD;;;;EAIf;;EAEA,UAAU,QAAQ;;wBA+DJ,0BACd,YAAY,YACZ,OAAM,qBACL;;;;;;;;;UC7Dc;EACf;EACA;EACA;EACA;EACA,MAAM;EACN;EACA;EACA;EACA,QAAQ;EACR;EACA;EACA;EACA;EACA;;EAEA,YAAY;;;;;;wBAOE,oBAAoB,KAAK,0BAA0B;;;;;;wBA2FnD,sBAAsB,KAAK,0BAA0B;wBAoBrD,YAAY,KAAK,yBAAyB;wBAK1C,SAAS;;wBAKT,gBACd,OAAO,yBACP;;;UChHe;;EAEf;;;EAGA;;;EAGA,WAAW;;EAEX;;EAEA;;EAEA;;EAEA;;;;;;;EAOA;;;;;;EAMA;;;;;;;;;EASA,wBAAwB;;;;;;;;;EASxB,iBAAiB,eAAe,MAAM;;;;;EAKtC,yBAAyB,kBAAkB;;;;;;UAO5B;EACf,QAAQ;;EAER;;EAEA;;;UAIe;EACf;;EAEA;;EAEA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA,YAAY;;EAEZ;EACA;EACA;EACA;EACA;;EAEA,iBAAiB;;;;;;;wBAeH,iBAAiB,mBAAmB,MAAM,0BAA0B;;;;;;wBASpE,qBACd,MAAM,kBACN,MAAM,0BACL;;wBAKa,sBACd,mBACA,MAAM,0BACL
|
|
1
|
+
{"version":3,"file":"traces.d.ts","names":["SpanKind"],"sources":["../src/trace-analyst/errors.ts","../src/trace/otlp-attributes.ts","../src/trace/store-to-otlp.ts","../src/trace-analyst/hook.ts","../src/trace-analyst/otlp-flatten.ts","../src/trace-analyst/otlp-span.ts","../src/trace-analyst/otlp-to-run-records.ts","../src/trace-analyst/prompts.ts"],"mappings":";;;;;;;;;;;;;;;;qBASa,qCAAqC;WAC/B;;;qBAIN,gCAAgC;WAC1B;WACR;WACA;WACA;EAET,YAAY,mBAAmB,gBAAgB,eAAe;;;qBASnD,wCAAwC;WAClC;WACR;EAET,YAAY,mBAAmB,iBAAiB;IAAY;;;qBAMjD,8BAA8B;WACxB;WACR;EAET,YAAY;;qBAMD,+BAA+B;WACjC;WACA;WACA;EAET,YAAY,cAAc,oBAAoB;;qBAcnC,gCAAgC;WAClC;WACA;WACA;EAET,YAAY,cAAc,qBAAqB,qBAAqB;;qBAQzD,2BAA2B;WACrB;WACR;EAET,YAAY;;qBAMD,0BAA0B;WACpB;WACR;WACA;EAET,YAAY,kBAAkB;;;;YC1EpB,oBAAoB,KAC9B;wBAkBc,4BACd,YAAY,yBACZ,MAAM;;;;;;wBAWQ,iCAAiC,eAAeA;;;iBCjB/C;;EAEf;;EAEA;;EAEA;;;EAGA;;;;;;;;;;;;iBAae;;EAEf;;EAEA;;EAEA;;;;iBAKe;;;EAGf;;;EAGA,sBAAsB,KAAK,QAAQ;;EAEnC,iBAAiB,KAAK,QAAQ;;;;;;;;;;;wBAYhB,yBACd,iBAAiB,4BAA4B,oBAC7C,iBACA,OAAM,0BACL;;;UCxEc;;;;;;EAMf,SAAS,KAAK;IAAoC,SAAS;;;;;;;EAM3D;;;;;;EAMA,QAAQ,QAAQ,qBAAqB,KAAK,2BAA2B;;;;;EAKrE,aAAa,KAAK;;;;;;EAMlB,UAAU,QAAQ,qBAAqB,KAAK;;wBAM9B,0BAA0B,MAAM,0BAA0B;;;UCnCzD;;;;EAIf;;EAEA,UAAU,QAAQ;;wBA+DJ,0BACd,YAAY,YACZ,OAAM,qBACL;;;;;;;;;UC7Dc;EACf;EACA;EACA;EACA;EACA,MAAM;EACN;EACA;EACA;EACA,QAAQ;EACR;EACA;EACA;EACA;EACA;;EAEA,YAAY;;;;;;wBAOE,oBAAoB,KAAK,0BAA0B;;;;;;wBA2FnD,sBAAsB,KAAK,0BAA0B;wBAoBrD,YAAY,KAAK,yBAAyB;wBAK1C,SAAS;;wBAKT,gBACd,OAAO,yBACP;;;UChHe;;EAEf;;;EAGA;;;EAGA,WAAW;;EAEX;;EAEA;;EAEA;;EAEA;;;;;;;EAOA;;;;;;EAMA;;;;;;;;;EASA,wBAAwB;;;;;;;;;EASxB,iBAAiB,eAAe,MAAM;;;;;EAKtC,yBAAyB,kBAAkB;;;;;;UAO5B;EACf,QAAQ;;EAER;;EAEA;;;UAIe;EACf;;EAEA;;EAEA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA,YAAY;;EAEZ;EACA;EACA;EACA;EACA;;EAEA,iBAAiB;;;;;;;wBAeH,iBAAiB,mBAAmB,MAAM,0BAA0B;;;;;;wBASpE,qBACd,MAAM,kBACN,MAAM,0BACL;;wBAKa,sBACd,mBACA,MAAM,0BACL;;;;qBCjMU;qBAcA"}
|
package/dist/traces.js
CHANGED
|
@@ -1,17 +1,17 @@
|
|
|
1
1
|
import { a as isToolSpan, i as isLlmSpan, n as TRACE_SCHEMA_VERSION, r as isJudgeSpan, t as FAILURE_CLASSES } from "./schema-CSf6qWgZ.js";
|
|
2
|
-
import { a as hasCapturedToolArgs, c as
|
|
3
|
-
import {
|
|
2
|
+
import { a as hasCapturedToolArgs, c as runFailureClass, d as toolSpans, i as groupBy, l as runMetricExtractor, n as aggregateLlm, o as judgeSpans, r as argHash, s as llmSpans, t as RUN_METRICS, u as runsForScenario } from "./query-B1D1qp2Z.js";
|
|
3
|
+
import { c as validateRunRecord, i as modelHasSnapshot } from "./run-record-DlTZ_lqe.js";
|
|
4
4
|
import { a as combineVerdicts, c as emptyRedactionReport, d as redactForShare, f as redactText, i as classifyKey, l as normalizeKey, n as REDACTION_VERSION, o as detectCredential, p as shareAllowed, r as assessShareSafety, s as detectPersonalData, t as REDACTION_PROFILES, u as redact } from "./redact-Dk1ZdJEm.js";
|
|
5
5
|
import { t as TraceEmitter } from "./emitter-DbMXUIVP.js";
|
|
6
|
-
import { A as
|
|
6
|
+
import { A as spanEpochMillis, C as TraceFileTooLargeError, D as extractOtlpAttributes, E as compareSpanTime, O as firstStringAttr, S as TraceFileMissingError, T as asString, _ as SpanNotFoundError, a as TRACE_ANALYST_TOOL_NAMESPACE, b as TraceAnalysisValidationError, g as TRACE_ANALYSIS_LIMITS, h as TRACE_ANALYST_TRUNCATION_MARKER_PREFIX, j as stringField, k as projectOtlpFlatLine, l as createBoundedTraceAnalysisStore, m as DEFAULT_TRACE_ANALYST_BUDGETS, o as UNTRUSTED_TRACE_TEXT, s as buildTraceAnalysisToolDescriptors, v as TraceAnalysisLimitError, w as TraceNotFoundError, x as TraceFileMalformedError, y as TraceAnalysisStoreContractError } from "./kind-factory-ivTx6koH.js";
|
|
7
7
|
import { INPUT_VALUE, LLM_CACHED_TOKENS, LLM_CACHED_TOKEN_ATTR_KEYS, LLM_CACHE_WRITE_TOKENS, LLM_CACHE_WRITE_TOKEN_ATTR_KEYS, LLM_CONTEXT_TOKENS, LLM_COST_ATTR_KEYS, LLM_COST_USD, LLM_INPUT_TOKENS, LLM_INPUT_TOKEN_ATTR_KEYS, LLM_MODEL_ATTR_KEYS, LLM_MODEL_NAME, LLM_OUTPUT_TOKENS, LLM_OUTPUT_TOKEN_ATTR_KEYS, LLM_REASONING_TOKENS, LLM_REASONING_TOKEN_ATTR_KEYS, OPENINFERENCE_SPAN_KIND, OUTPUT_VALUE, RUN_COST_ATTR_KEYS, SPAN_KIND_ATTR_KEYS, TOOL_ARGS_CAPTURED, TOOL_LATENCY_MS, TOOL_NAME, TOOL_NAME_ATTR_KEYS, applyLlmSpanOtlpAttributes, asNumber, contextInputTokens, firstNumberAttr } from "./trace-attributes.js";
|
|
8
8
|
import { n as extractUsageFromResponse, r as extractUsageFromSse, t as extractUsage } from "./extract-usage-BrnzRJ6H.js";
|
|
9
9
|
import { a as providerFromBaseUrl, i as defaultProviderRedactor, n as InMemoryRawProviderSink, r as NoopRawProviderSink, t as FileSystemRawProviderSink } from "./raw-provider-sink-rB2DYxr6.js";
|
|
10
|
-
import { C as spanIdForWire, S as exportRunAsOtlp, T as captureFetchToRawSink, _ as tokenizeDomainWords, a as spanStatusToOtlp, b as TRACE_ANALYST_ACTOR_DESCRIPTION_VERSION, c as defaultTraceInsightPanel, d as inferDomainKeywords, f as isTraceInsightArtifact, g as scoreTraceInsightReadiness, h as planTraceInsightQuestions, i as epochMillisToIso, l as describeTraceInsightScope, m as isTraceInsightEvidence, n as toolSpansToTraceAnalysisStore, o as buildTraceInsightContext, p as isTraceInsightAttribution, r as createOtlpFlatLine, s as buildTraceInsightPrompt, t as ToolTraceMissingError, u as domainEvidencePattern, v as analyzeTraces, w as traceIdForWire, x as OTEL_AGENT_EVAL_SCOPE, y as TRACE_ANALYST_ACTOR_DESCRIPTION } from "./store-tool-spans-
|
|
10
|
+
import { C as spanIdForWire, S as exportRunAsOtlp, T as captureFetchToRawSink, _ as tokenizeDomainWords, a as spanStatusToOtlp, b as TRACE_ANALYST_ACTOR_DESCRIPTION_VERSION, c as defaultTraceInsightPanel, d as inferDomainKeywords, f as isTraceInsightArtifact, g as scoreTraceInsightReadiness, h as planTraceInsightQuestions, i as epochMillisToIso, l as describeTraceInsightScope, m as isTraceInsightEvidence, n as toolSpansToTraceAnalysisStore, o as buildTraceInsightContext, p as isTraceInsightAttribution, r as createOtlpFlatLine, s as buildTraceInsightPrompt, t as ToolTraceMissingError, u as domainEvidencePattern, v as analyzeTraces, w as traceIdForWire, x as OTEL_AGENT_EVAL_SCOPE, y as TRACE_ANALYST_ACTOR_DESCRIPTION } from "./store-tool-spans-TbRBuIM7.js";
|
|
11
11
|
import { n as assertRunCaptured, r as throwIfRunIncomplete, t as RunIntegrityError } from "./integrity-BvnVARVl.js";
|
|
12
12
|
import { n as traceSpanKindToOpenInferenceKind, t as applyToolSpanOtlpAttributes } from "./otlp-attributes-D9ptWaIJ.js";
|
|
13
13
|
import { n as InMemoryTraceStore, t as FileSystemTraceStore } from "./store-BhNuLdJw.js";
|
|
14
|
-
import { a as spanRecordsToTraceAnalysisStore, i as otlpTextToTraceAnalysisStore, n as OtlpFileTraceStore } from "./store-otlp-
|
|
14
|
+
import { a as spanRecordsToTraceAnalysisStore, i as otlpTextToTraceAnalysisStore, n as OtlpFileTraceStore } from "./store-otlp-__ebQ6Hn.js";
|
|
15
15
|
import { i as summarizeTraceErrors, n as recordAggregateMeasurements, r as summarizeExecutionMeasurements, t as readTaskFailureLabels } from "./task-failure-attributes-DngaLdE4.js";
|
|
16
16
|
import { readFileSync, readdirSync, statSync, writeFileSync } from "node:fs";
|
|
17
17
|
import { join } from "node:path";
|
|
@@ -803,6 +803,6 @@ function ensureSnapshot(model, fallbackModel) {
|
|
|
803
803
|
return `${model}${fallbackModel.includes("@") ? fallbackModel.slice(fallbackModel.indexOf("@")) : "@otlp"}`;
|
|
804
804
|
}
|
|
805
805
|
//#endregion
|
|
806
|
-
export { DEFAULT_TRACE_ANALYST_BUDGETS, FAILURE_CLASSES, FileSystemRawProviderSink, FileSystemTraceStore, INPUT_VALUE, InMemoryRawProviderSink, InMemoryTraceStore, LLM_CACHED_TOKENS, LLM_CACHED_TOKEN_ATTR_KEYS, LLM_CACHE_WRITE_TOKENS, LLM_CACHE_WRITE_TOKEN_ATTR_KEYS, LLM_CONTEXT_TOKENS, LLM_COST_ATTR_KEYS, LLM_COST_USD, LLM_INPUT_TOKENS, LLM_INPUT_TOKEN_ATTR_KEYS, LLM_MODEL_ATTR_KEYS, LLM_MODEL_NAME, LLM_OUTPUT_TOKENS, LLM_OUTPUT_TOKEN_ATTR_KEYS, LLM_REASONING_TOKENS, LLM_REASONING_TOKEN_ATTR_KEYS, NoopRawProviderSink, OPENINFERENCE_SPAN_KIND, OTEL_AGENT_EVAL_SCOPE, OUTPUT_VALUE, OtlpFileTraceStore, REDACTION_PROFILES, REDACTION_VERSION, RUN_COST_ATTR_KEYS, RUN_METRICS, RunIntegrityError, SPAN_KIND_ATTR_KEYS, SpanNotFoundError, TOOL_ARGS_CAPTURED, TOOL_LATENCY_MS, TOOL_NAME, TOOL_NAME_ATTR_KEYS, TRACE_ANALYSIS_LIMITS, TRACE_ANALYST_ACTOR_DESCRIPTION, TRACE_ANALYST_ACTOR_DESCRIPTION_VERSION, TRACE_ANALYST_TOOL_NAMESPACE, TRACE_ANALYST_TRUNCATION_MARKER_PREFIX, TRACE_SCHEMA_VERSION, ToolTraceMissingError, TraceAnalysisLimitError, TraceAnalysisStoreContractError, TraceAnalysisValidationError, TraceEmitter, TraceFileMalformedError, TraceFileMissingError, TraceFileTooLargeError, TraceNotFoundError, UNTRUSTED_TRACE_TEXT, aggregateLlm, analyzeTraces, applyLlmSpanOtlpAttributes, applyToolSpanOtlpAttributes, argHash, asNumber, asString, assertRunCaptured, assessShareSafety, buildTraceAnalysisToolDescriptors, buildTraceInsightContext, buildTraceInsightPrompt, captureFetchToRawSink, classifyKey, combineVerdicts, contextInputTokens, convertTraceStoresToOtlp, createBoundedTraceAnalysisStore, defaultProviderRedactor, defaultTraceInsightPanel, describeTraceInsightScope, detectCredential, detectPersonalData, domainEvidencePattern, emptyRedactionReport, exportRunAsOtlp, extractOtlpAttributes, extractUsage, extractUsageFromResponse, extractUsageFromSse, firstNumberAttr, firstStringAttr, flattenOtlpExportToNdjson, groupBy, hasCapturedToolArgs, inferDomainKeywords, isJudgeSpan, isLlmSpan,
|
|
806
|
+
export { DEFAULT_TRACE_ANALYST_BUDGETS, FAILURE_CLASSES, FileSystemRawProviderSink, FileSystemTraceStore, INPUT_VALUE, InMemoryRawProviderSink, InMemoryTraceStore, LLM_CACHED_TOKENS, LLM_CACHED_TOKEN_ATTR_KEYS, LLM_CACHE_WRITE_TOKENS, LLM_CACHE_WRITE_TOKEN_ATTR_KEYS, LLM_CONTEXT_TOKENS, LLM_COST_ATTR_KEYS, LLM_COST_USD, LLM_INPUT_TOKENS, LLM_INPUT_TOKEN_ATTR_KEYS, LLM_MODEL_ATTR_KEYS, LLM_MODEL_NAME, LLM_OUTPUT_TOKENS, LLM_OUTPUT_TOKEN_ATTR_KEYS, LLM_REASONING_TOKENS, LLM_REASONING_TOKEN_ATTR_KEYS, NoopRawProviderSink, OPENINFERENCE_SPAN_KIND, OTEL_AGENT_EVAL_SCOPE, OUTPUT_VALUE, OtlpFileTraceStore, REDACTION_PROFILES, REDACTION_VERSION, RUN_COST_ATTR_KEYS, RUN_METRICS, RunIntegrityError, SPAN_KIND_ATTR_KEYS, SpanNotFoundError, TOOL_ARGS_CAPTURED, TOOL_LATENCY_MS, TOOL_NAME, TOOL_NAME_ATTR_KEYS, TRACE_ANALYSIS_LIMITS, TRACE_ANALYST_ACTOR_DESCRIPTION, TRACE_ANALYST_ACTOR_DESCRIPTION_VERSION, TRACE_ANALYST_TOOL_NAMESPACE, TRACE_ANALYST_TRUNCATION_MARKER_PREFIX, TRACE_SCHEMA_VERSION, ToolTraceMissingError, TraceAnalysisLimitError, TraceAnalysisStoreContractError, TraceAnalysisValidationError, TraceEmitter, TraceFileMalformedError, TraceFileMissingError, TraceFileTooLargeError, TraceNotFoundError, UNTRUSTED_TRACE_TEXT, aggregateLlm, analyzeTraces, applyLlmSpanOtlpAttributes, applyToolSpanOtlpAttributes, argHash, asNumber, asString, assertRunCaptured, assessShareSafety, buildTraceAnalysisToolDescriptors, buildTraceInsightContext, buildTraceInsightPrompt, captureFetchToRawSink, classifyKey, combineVerdicts, contextInputTokens, convertTraceStoresToOtlp, createBoundedTraceAnalysisStore, defaultProviderRedactor, defaultTraceInsightPanel, describeTraceInsightScope, detectCredential, detectPersonalData, domainEvidencePattern, emptyRedactionReport, exportRunAsOtlp, extractOtlpAttributes, extractUsage, extractUsageFromResponse, extractUsageFromSse, firstNumberAttr, firstStringAttr, flattenOtlpExportToNdjson, groupBy, hasCapturedToolArgs, inferDomainKeywords, isJudgeSpan, isLlmSpan, isToolSpan, isTraceInsightArtifact, isTraceInsightAttribution, isTraceInsightEvidence, judgeSpans, llmSpans, normalizeKey, otlpRowsToRunRecords, otlpTextToTraceAnalysisStore, otlpToRunRecords, otlpToTraceRunRecords, planTraceInsightQuestions, projectOtlpFlatLine, providerFromBaseUrl, redact, redactForShare, redactText, runFailureClass, runMetricExtractor, runsForScenario, scoreTraceInsightReadiness, shareAllowed, spanRecordsToTraceAnalysisStore, stringField, throwIfRunIncomplete, tokenizeDomainWords, toolSpans, toolSpansToTraceAnalysisStore, traceAnalystOnRunComplete, traceSpanKindToOpenInferenceKind };
|
|
807
807
|
|
|
808
808
|
//# sourceMappingURL=traces.js.map
|
|
@@ -50,7 +50,6 @@ interface LabelEntry {
|
|
|
50
50
|
readonly incorrect_step_ids?: readonly number[];
|
|
51
51
|
}[];
|
|
52
52
|
}
|
|
53
|
-
export declare function readLabelEntries(labelsPath: string): LabelEntry[];
|
|
54
53
|
export declare function goldIncorrectSteps(entry: LabelEntry): number[];
|
|
55
54
|
type ResourceResolution = {
|
|
56
55
|
readonly resolved: true;
|
|
@@ -457,7 +456,6 @@ interface ReplayBatchReport {
|
|
|
457
456
|
}
|
|
458
457
|
export declare function seededSample<T>(items: readonly T[], size: number, seed: number): Set<T>;
|
|
459
458
|
export declare function runReplayBatch(options: ReplayBatchOptions): Promise<ReplayBatchReport>;
|
|
460
|
-
export declare function renderBatchReport(report: ReplayBatchReport): string;
|
|
461
459
|
//#endregion
|
|
462
460
|
//#region src/trajectory-replay/verify.d.ts
|
|
463
461
|
interface IngestedTrajectory {
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"index.d.ts","names":[],"sources":["../../src/trajectory-replay/corpus.ts","../../src/trajectory-replay/exec.ts","../../src/trajectory-replay/fix.ts","../../src/trajectory-replay/fix-loop.ts","../../src/trajectory-replay/image-preparer.ts","../../src/trajectory-replay/batch.ts","../../src/trajectory-replay/verify.ts","../../src/trajectory-replay/findings.ts","../../src/trajectory-replay/wire.ts"],"mappings":";;;;;;UAyBiB;WACN;WACA;WACA;;;wBAIK,gBAAgB,gBAAgB;KAYpC;UAYK;WACN;WACA;WACA,QAAQ;WACR;;KAGC;;UAGK;WACN;WACA;WACA;WACA,gBAAgB;WAChB;WACA;WACA;WACA,WAAW;;WAEX;;UAGM,uBAAuB;;WAE7B;;;;WAIA;;WAEA;;WAEA;;UAGD;WACC;WACA;aAAuC;;;
|
|
1
|
+
{"version":3,"file":"index.d.ts","names":[],"sources":["../../src/trajectory-replay/corpus.ts","../../src/trajectory-replay/exec.ts","../../src/trajectory-replay/fix.ts","../../src/trajectory-replay/fix-loop.ts","../../src/trajectory-replay/image-preparer.ts","../../src/trajectory-replay/batch.ts","../../src/trajectory-replay/verify.ts","../../src/trajectory-replay/findings.ts","../../src/trajectory-replay/wire.ts"],"mappings":";;;;;;UAyBiB;WACN;WACA;WACA;;;wBAIK,gBAAgB,gBAAgB;KAYpC;UAYK;WACN;WACA;WACA,QAAQ;WACR;;KAGC;;UAGK;WACN;WACA;WACA;WACA,gBAAgB;WAChB;WACA;WACA;WACA,WAAW;;WAEX;;UAGM,uBAAuB;;WAE7B;;;;WAIA;;WAEA;;WAEA;;UAGD;WACC;WACA;aAAuC;;;wBAclC,mBAAmB,OAAO;KAuD9B;WACG;WAAyB,WAAW;;WACpC;WAA0B,QAAQ;WAAgC;;;;;;wBAMjE,qBAAqB,QAAQ,YAAY,iBAAiB;UAiEzD;WACN,YAAY;WACZ,UAAU;WACV;;;;;;;;;;wBAWK,yBAAyB,kBAAkB,eAAe;;;;;;;;;;;;UChPzD;EACf;EACA;EACA;;UAGe;EACf,KAAK,iBAAiB,oBAAoB,QAAQ;EAClD,SAAS;;UAGM;;EAEf,QAAQ,QAAQ;;;;;KAMN,4BAA4B,kBAAkB;;;;;;;wBAQ1C,kBAAkB,gBAAgB;;;UCrBjC;WACN;WACA;;KAGC;WACG;WAA0B;IAAS;IAAiB,OAAO;;;WAC3D;WAA2B;;UAEzB;EACf,SAAS,gBAAgB,eAAe,QAAQ;;UAGjC;WACN;WACA,gBAAgB;;WAEhB;;WAEA;;;wBAIK,SAAS,cAAc;wBAuCvB,eAAe,OAAO;EAAmB;EAAgB;;;UAiBxD;WACN;;WAEA;WACA;WACA;WACA;WACA;;;;;;;wBA4BK,oBACd,OAAO,gBACP,wBAAwB,oBACxB;EACG;EAAgB;;;wBAwBL,oBAAoB;;wBAMpB,kBAAkB;KAQtB;WACG;WAA0B;IAAS;IAAiB,OAAO;;;WAC3D;WAA2B;;wBAEpB,mBACpB,QAAQ,sBACR,OAAO,iBACN,QAAQ;;;;UCvJM;WACN;WACA;WACA;;WAEA;WACA;WACA;WACA;;;KAIC,kBAAkB,iBAAiB,oBAAoB,QAAQ;UAE1D;;WAEN;;WAEA;;WAEA;WACA,cAAc;;UAGR;WACN;WACA;WACA;WACA;aAAkB;aAA+B;;WACjD;WACA;WACA;WACA;WACA;WACA;WACA;WACA;WACA;WACA;;UAGM;WACN;WACA;WACA,mBAAmB;;WAEnB;WACA;;;WAGA;WACA;WACA;;;;WAIA;;wBAcW,WACpB,QAAQ,sBACR,OAAO,gBACP,UAAU,gBACV,SAAS,iBACR,QAAQ;;;;;;;;;;;;KCpFC;WAEG;WACA;IAAS;IAAsB;IAAiB;;;WAEhD;WAA2B;;UAEzB;EACf,OAAO,eAAe,cAAc,QAAQ;;UAG7B;WACN;WACA;;wBAGK,gBAAgB,eAAe;;;;;;;wBAW/B,oBAAoB,UAAS,6BAAkC;;;UCQ9D;WACN,kBAAkB;WAClB;;;;WAIA;;WAEA;WACA,YAAY;WACZ;;WAEA;WACA;;WAEA;WACA;;WAEA;;WAEA;;WAEA,WAAW;;WAEX,gBAAgB;WAChB,cAAc;;UAGR;;WAEN;WACA;WACA;WACA;;;WAGA,OAAO;WACP;WACA;WACA;WACA;WACA;WACA;;WAEA,mBAAmB;;;WAGnB;;UAGM;WACN;WACA;WACA;WACA;WACA;WACA;WACA;WACA;WACA;;WAEA;WACA;WACA;WACA;WACA;WACA;WACA;WACA;WACA;WACA;;WAEA;WACA;;;WAGA;WACA;WACA;WACA;;;WAGA;WACA,KAAK;WACL;;UAGM;WACN;WACA;IAAoB;IAAc;IAAoB;;WACtD;aACE;aACA;aACA;aACA,kBAAkB;;;aAGlB,qBAAqB;MAE1B;MAAyB;;;WAGtB;aACE;MAAqB;MAAmB;MAAqB;;aAC7D;MAAuB;MAAmB;MAAqB;;;;;aAI/D;eACE;eACA;eACA;eACA;;eAEA;eACA;eACA;eACA;;aAEF;MAAe;MAAmB;MAAqB;;;aAEvD;MACP;MACA;MACA;;;;aAIO;MACP;MACA;MACA;;;aAGO,gBAAgB;;WAElB;aACE;aACA;aACA;aACA;aACA;;;;aAIA;;WAEF;IAAqB;IAAgB;IAAgB;IAAgB;;WACrE;IAAyB;IAAgB;IAAgB;IAAe;;WACxE,gBAAgB;;wBAGX,aAAa,GAAG,gBAAgB,KAAK,cAAc,eAAe,IAAI;wBAkFhE,eAAe,SAAS,qBAAqB,QAAQ;;;UC1O1D;EACf;EACA;;;;;;;wBAQoB,yBACpB,OAAO,YACP,gBAAgB,0BAChB,iBACC,QAAQ;;KA6BC;;;;;UAMK;EACf;EACA,MAAM;;EAEN;EACA;;UAGe;EACf;;EAEA,mBAAmB;;EAEnB;EACA;EACA;;;EAGA;;EAEA;EACA;;;;qBAKW;;;;;wBAMG,mBACd,cACA,mCACA,qBACC;;wBAWa,sBACd,wBACA,mBAAmB,oBACnB,iBACC;UAwBc;EACf;EACA;EACA;EACA;EACA;;UAGe;EACf;EACA;;;EAGA;EACA,cAAc;;;;;;;;qBAsBH,uCAAuC;mBAK/B;mBACA;EALnB,YAAY;EACZ,SAAS;EAET,YACmB,SAAS,mBACT,SAAS;EAGtB,YAAY,KAAK,uBAAuB,SAAS,eAAe;;UAyEvD;EACf;EACA;;EAEA;;EAEA;EACA;EACA;EACA;;EAEA;EACA;EACA;;EAEA;;EAEA,SAAS;EACT,cAAc;;UAGC;EACf;EACA;EACA;EACA,QAAQ;;;;;;;;UASO,sBAAsB;EACrC;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA,mBAAmB;;EAEnB;EACA;EACA;EACA;EACA;EACA,MAAM;IAAqB;;EAC3B,OAAO;IAAqB;;EAC5B;IAAW;IAAgB;IAAuB;;EAClD;IAAU;IAAkB;IAAc;;;wBAUtB,aAAa,SAAS,sBAAsB,QAAQ;;;UC5TzD;WACN;WACA;WACA;WACA;WACA;WACA;aACE;aACA;aACA;;WAEF,WAAW,SAAS;;;;;;;;wBAWf,kBAAkB,SAAS;;wBAgB3B,oBAAoB,SAAS;;;;;;;;;;KAoBjC;WAEG;WACA;WACA;WACA;WACA;;WAGA;WACA,kBAAkB;WAClB,WAAW;;UAGT;WACN;WACA;;WAEA;WACA;;WAEA;WACA;WACA;;KAGC;WACG;WAA2B,UAAU;;WACrC;WAA4B;;;;;;;wBAiC3B,4BACd,SAAS,mBACT,QAAQ,sBACP;KAmFS;UAMK;WACN;WACA;WACA;;WAEA;WACA,UAAU;;WAEV;;WAEA;WACA;;WAEA;;;;;;;;UASM,0BAA0B;WAChC;WACA,wBAAwB;WACxB,QAAQ,SAAS,OAAO;;WAExB;;UAGM;WACN,QAAQ;;WAER;;WAEA;WACA;WACA;;WAEA,gBAAgB;;;WAGhB,kBAAkB;WAClB,cAAc;;;;;;;;wBAST,gBAAgB,SAAS,gBAAgB;;;;;;;wBAyGnC,eACpB,mBAAmB,qBACnB,SAAS,wBACR,QAAQ;;wBAwNK,8BAA8B,KAAK;;;;;;wBAmCnC,iBAAiB,eAAe;;;UCvoB/B;WACN;WACA;WACA;WACA;;;wBAMK,2BAA2B,kBAAkB;UAW5C;WACN;WACA;;UAGM;WACN,WAAW;WACX,SAAS;;WAET;;;;;;;;wBASK,yBACd,SAAS,sBACT,kBAAkB,eACjB;UAuCc;WACN,kBAAkB;WAClB;;WAEA,YAAY;;WAEZ;WACA;WACA;;WAEA,gBAAgB;WAChB,cAAc;;UAGR;WACN,YAAY;WACZ;WACA,SAAS;;;;;;;wBAQE,oBACpB,SAAS,sBACT,SAAS,uBACR,QAAQ"}
|
|
@@ -2154,6 +2154,6 @@ function readFindingsFile(path) {
|
|
|
2154
2154
|
return array;
|
|
2155
2155
|
}
|
|
2156
2156
|
//#endregion
|
|
2157
|
-
export { FORMAT_ERROR_OBSERVATION_PREFIX, PREFIX_DIVERGENCE_TOLERANCE_PCT, SUBMIT_ACTION_SIGNATURE, SandboxCounterfactualRunner, TIMEOUT_OBSERVATION_MARKER, assertReplayableTrajectory, buildFixPrompt, buildRetryFixPrompt, classifyObservation, classifyPrefixStep, classifyVerdict, clipText, countScriptCommands, decodeRecordedTurns, deriveFailureSignature, derivedImageTag, dockerImagePreparer, enumerateReplayableCases, extractFixCommand, finalRecordedOutcome, findingReplayStep, findingTrajectoryId, generateFixCommand, goldIncorrectSteps, ingestRecordedTrajectory, isElidedField, isRecordedTimeout, isSubmitAction, isSubmitOnlyAction, parseCorpusFlag, parseIncorrectStepsSubject, parseObservationOutput, parseRecordedReturncode, readFindingsFile,
|
|
2157
|
+
export { FORMAT_ERROR_OBSERVATION_PREFIX, PREFIX_DIVERGENCE_TOLERANCE_PCT, SUBMIT_ACTION_SIGNATURE, SandboxCounterfactualRunner, TIMEOUT_OBSERVATION_MARKER, assertReplayableTrajectory, buildFixPrompt, buildRetryFixPrompt, classifyObservation, classifyPrefixStep, classifyVerdict, clipText, countScriptCommands, decodeRecordedTurns, deriveFailureSignature, derivedImageTag, dockerImagePreparer, enumerateReplayableCases, extractFixCommand, finalRecordedOutcome, findingReplayStep, findingTrajectoryId, generateFixCommand, goldIncorrectSteps, ingestRecordedTrajectory, isElidedField, isRecordedTimeout, isSubmitAction, isSubmitOnlyAction, parseCorpusFlag, parseIncorrectStepsSubject, parseObservationOutput, parseRecordedReturncode, readFindingsFile, renderVerifiedFindingsSection, replayVerify, replayVerifyFinding, resolveCaseResources, resolveFindingInvocation, resolveFindingReplayability, runFixLoop, runReplayBatch, seededSample, summarizePrefixReplay, unreadableExitCount, verifyFindings, wrapActionForExec };
|
|
2158
2158
|
|
|
2159
2159
|
//# sourceMappingURL=index.js.map
|
|
@@ -3,9 +3,9 @@ import { a as medianInPlace, s as zQuantile } from "./internal-CRHwS9iz.js";
|
|
|
3
3
|
import { t as mulberry32 } from "./random-Dn5fPWkt.js";
|
|
4
4
|
import { r as holm } from "./multiplicity-D9cjmStq.js";
|
|
5
5
|
import { a as pairedSignTest, n as DECISION_PAIRED_DELTA_STATISTIC } from "./paired-tests-jbwPdSz5.js";
|
|
6
|
-
import { i as pairedDeltaTest, r as minimumPairsForPairedDeltaTest } from "./paired-promotion-decision-
|
|
7
|
-
import { E as seedFromDigest, O as paretoFrontier, T as searchPosterior, _ as INSUFFICIENT_FROM, a as searchPolicyView, d as verifySearchClaim, v as rankingSplit, w as searchEstimateMethod, x as estimateNode, y as summarizeSamples } from "./search-kernel-
|
|
8
|
-
import { f as searchUnitScores } from "./search-ledger-
|
|
6
|
+
import { i as pairedDeltaTest, r as minimumPairsForPairedDeltaTest } from "./paired-promotion-decision-BN6IQTiu.js";
|
|
7
|
+
import { E as seedFromDigest, O as paretoFrontier, T as searchPosterior, _ as INSUFFICIENT_FROM, a as searchPolicyView, d as verifySearchClaim, v as rankingSplit, w as searchEstimateMethod, x as estimateNode, y as summarizeSamples } from "./search-kernel-BIXWM7YV.js";
|
|
8
|
+
import { f as searchUnitScores } from "./search-ledger-aMTNQn_m.js";
|
|
9
9
|
import { defineInlineResource } from "@tangle-network/agent-interface";
|
|
10
10
|
//#region src/search/lenses/edit-credit.ts
|
|
11
11
|
/**
|
|
@@ -1359,26 +1359,6 @@ function lineageEdits() {
|
|
|
1359
1359
|
method: "edits between the two profiles along the recorded lineage: the fewest improve, debug or merge edges joining them (a re-proposal edge counts; a draft is written afresh, so its edge is no edit of its anchor)"
|
|
1360
1360
|
};
|
|
1361
1361
|
}
|
|
1362
|
-
/** Surfaces whose content digests differ: the edit distance between two
|
|
1363
|
-
* profiles at the granularity of their declared surfaces. */
|
|
1364
|
-
function surfaceDigestEdits() {
|
|
1365
|
-
return {
|
|
1366
|
-
kind: "distance",
|
|
1367
|
-
name: "surface-digest-edits",
|
|
1368
|
-
method: "declared surfaces whose content digests differ (a surface only one node has counts)",
|
|
1369
|
-
distance(a, b) {
|
|
1370
|
-
const left = new Map(a.surfaces.map((surface) => [surface.surfaceId, surface.artifact.sha256]));
|
|
1371
|
-
let count = 0;
|
|
1372
|
-
const seen = /* @__PURE__ */ new Set();
|
|
1373
|
-
for (const surface of b.surfaces) {
|
|
1374
|
-
seen.add(surface.surfaceId);
|
|
1375
|
-
if (left.get(surface.surfaceId) !== surface.artifact.sha256) count += 1;
|
|
1376
|
-
}
|
|
1377
|
-
for (const surfaceId of left.keys()) if (!seen.has(surfaceId)) count += 1;
|
|
1378
|
-
return count;
|
|
1379
|
-
}
|
|
1380
|
-
};
|
|
1381
|
-
}
|
|
1382
1362
|
/**
|
|
1383
1363
|
* Line edits between the surfaces' texts: for each declared surface, the
|
|
1384
1364
|
* fewest line insertions and deletions that turn one text into the other
|
|
@@ -4110,6 +4090,6 @@ function tree(state) {
|
|
|
4110
4090
|
};
|
|
4111
4091
|
}
|
|
4112
4092
|
//#endregion
|
|
4113
|
-
export {
|
|
4093
|
+
export { editCredit as C, front as S, surfaceTextEdits as _, skillCalibration as a, searchPlateau as b, metaSearch as c, renderMetaSearchText as d, searchPolicyGenome as f, lineageEdits as g, lineEditDistance as h, nextUnitExtension as i, metaSearchScore as l, landscape as m, taskMatrix as n, skillManifold as o, formatLandscape as p, formatSkillManifold as r, META_SEARCH_SCORE_SOURCE as s, tree as t, objectiveKey as u, vectorEmbedding as v, editCreditText as w, screenedNodes as x, draftOnPlateau as y };
|
|
4114
4094
|
|
|
4115
|
-
//# sourceMappingURL=tree-
|
|
4095
|
+
//# sourceMappingURL=tree-kc1d80yF.js.map
|