@tangle-network/agent-eval 0.145.4 → 0.145.6

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.
Files changed (67) hide show
  1. package/CHANGELOG.md +17 -0
  2. package/README.md +5 -0
  3. package/dist/analyst/index.d.ts +5 -5
  4. package/dist/analyst/index.js +1 -1
  5. package/dist/{benchmark-command-BANo4dTm.js → benchmark-command-DspwA7cv.js} +2 -2
  6. package/dist/{benchmark-command-BANo4dTm.js.map → benchmark-command-DspwA7cv.js.map} +1 -1
  7. package/dist/benchmarks/index.d.ts +4 -4
  8. package/dist/benchmarks/index.js +2 -2
  9. package/dist/campaign/index.d.ts +6 -6
  10. package/dist/campaign/index.js +3 -3
  11. package/dist/{campaign-FY23WYzZ.js → campaign-jTOvqnse.js} +4 -4
  12. package/dist/{campaign-FY23WYzZ.js.map → campaign-jTOvqnse.js.map} +1 -1
  13. package/dist/cli.js +1 -1
  14. package/dist/{client-KUbGulm_.d.ts → client-DCVe0CwG.d.ts} +2 -2
  15. package/dist/{client-KUbGulm_.d.ts.map → client-DCVe0CwG.d.ts.map} +1 -1
  16. package/dist/contract/index.d.ts +8 -8
  17. package/dist/contract/index.js +3 -3
  18. package/dist/{default-registry-Di6HP6pG.d.ts → default-registry-CgzxnJsj.d.ts} +3 -3
  19. package/dist/{default-registry-Di6HP6pG.d.ts.map → default-registry-CgzxnJsj.d.ts.map} +1 -1
  20. package/dist/{define-agent-eval-xaceIpPS.js → define-agent-eval-CViDh2P9.js} +2 -2
  21. package/dist/{define-agent-eval-xaceIpPS.js.map → define-agent-eval-CViDh2P9.js.map} +1 -1
  22. package/dist/{define-agent-eval-DcAcC1yQ.d.ts → define-agent-eval-DLhZ8IHi.d.ts} +4 -4
  23. package/dist/{define-agent-eval-DcAcC1yQ.d.ts.map → define-agent-eval-DLhZ8IHi.d.ts.map} +1 -1
  24. package/dist/{engine-otFpE2gF.d.ts → engine-FRZ3RLvT.d.ts} +2 -2
  25. package/dist/{engine-otFpE2gF.d.ts.map → engine-FRZ3RLvT.d.ts.map} +1 -1
  26. package/dist/experiment/index.d.ts +2 -2
  27. package/dist/hosted/index.d.ts +2 -2
  28. package/dist/{index-Dytg99g1.d.ts → index-DF3ynqmJ.d.ts} +6 -6
  29. package/dist/{index-Dytg99g1.d.ts.map → index-DF3ynqmJ.d.ts.map} +1 -1
  30. package/dist/{index-BWDrSVfw.d.ts → index-PgqfwhsM.d.ts} +3 -3
  31. package/dist/{index-BWDrSVfw.d.ts.map → index-PgqfwhsM.d.ts.map} +1 -1
  32. package/dist/index.d.ts +8 -8
  33. package/dist/index.js +3 -3
  34. package/dist/{llm-judge-BPKBdQTp.js → llm-judge-DuYa4SEA.js} +2 -1
  35. package/dist/llm-judge-DuYa4SEA.js.map +1 -0
  36. package/dist/multishot/index.d.ts +1 -1
  37. package/dist/openapi.json +1 -1
  38. package/dist/{produced-state-B_-TW9o0.js → produced-state-D6j7qy1Q.js} +2 -2
  39. package/dist/{produced-state-B_-TW9o0.js.map → produced-state-D6j7qy1Q.js.map} +1 -1
  40. package/dist/{promotion-policy-D0nPhkSy.d.ts → promotion-policy-CsMZJOB-.d.ts} +2 -2
  41. package/dist/{promotion-policy-D0nPhkSy.d.ts.map → promotion-policy-CsMZJOB-.d.ts.map} +1 -1
  42. package/dist/{provenance-C_ln89b0.d.ts → provenance-8L-_4xiL.d.ts} +3 -3
  43. package/dist/{provenance-C_ln89b0.d.ts.map → provenance-8L-_4xiL.d.ts.map} +1 -1
  44. package/dist/rl.d.ts +1 -1
  45. package/dist/{skillopt-optimization-method-CxrOjp1S.js → skillopt-optimization-method-BTls2l-Z.js} +26 -3
  46. package/dist/skillopt-optimization-method-BTls2l-Z.js.map +1 -0
  47. package/dist/{skillopt-optimization-method-CkySQ0ca.d.ts → skillopt-optimization-method-CFDSzD-7.d.ts} +10 -3
  48. package/dist/skillopt-optimization-method-CFDSzD-7.d.ts.map +1 -0
  49. package/dist/{statistical-heldout-DC7cHtFD.d.ts → statistical-heldout-C4De2tRI.d.ts} +2 -2
  50. package/dist/{statistical-heldout-DC7cHtFD.d.ts.map → statistical-heldout-C4De2tRI.d.ts.map} +1 -1
  51. package/dist/{store-tool-spans-DbDLOBOb.d.ts → store-tool-spans-CggeC1LB.d.ts} +3 -3
  52. package/dist/{store-tool-spans-DbDLOBOb.d.ts.map → store-tool-spans-CggeC1LB.d.ts.map} +1 -1
  53. package/dist/{tool-groups-Cteb03Ps.d.ts → tool-groups-BdcoEgtV.d.ts} +2 -2
  54. package/dist/tool-groups-BdcoEgtV.d.ts.map +1 -0
  55. package/dist/trace-repair/index.d.ts +1 -1
  56. package/dist/traces.d.ts +2 -2
  57. package/dist/{types-BEPZc6eo.d.ts → types-BRsxjg7z.d.ts} +2 -2
  58. package/dist/{types-BEPZc6eo.d.ts.map → types-BRsxjg7z.d.ts.map} +1 -1
  59. package/dist/{types-BZ59Ahr8.d.ts → types-BxLccGMf.d.ts} +3 -1
  60. package/dist/types-BxLccGMf.d.ts.map +1 -0
  61. package/docs/distributed-driver.md +6 -0
  62. package/package.json +1 -1
  63. package/dist/llm-judge-BPKBdQTp.js.map +0 -1
  64. package/dist/skillopt-optimization-method-CkySQ0ca.d.ts.map +0 -1
  65. package/dist/skillopt-optimization-method-CxrOjp1S.js.map +0 -1
  66. package/dist/tool-groups-Cteb03Ps.d.ts.map +0 -1
  67. package/dist/types-BZ59Ahr8.d.ts.map +0 -1
@@ -3,8 +3,8 @@ import { c as CostLedgerHandle } from "./cost-ledger-DbQdN3nO.js";
3
3
  import { S as ToolSpan } from "./schema-BtVldJ3T.js";
4
4
  import { s as TraceStore } from "./store-CT9YIIve.js";
5
5
  import { A as SearchSpanResult, B as ViewSpansResult, D as DatasetOverview, F as TraceAnalystFilters, H as ViewTraceResult, S as BoundedTraceAnalysisStoreOptions, T as TraceAnalysisStoreContext, f as AnalystUsageReceipt, i as AnalystFinding, j as SearchTraceResult, k as QueryTracesPage, w as TraceAnalysisStore } from "./types-DLQx4mKU.js";
6
- import { a as TraceAnalystLimits, i as TraceAnalysisEngineResult, n as TraceAnalysisEngine } from "./engine-otFpE2gF.js";
7
- import { t as TraceToolGroupName } from "./tool-groups-Cteb03Ps.js";
6
+ import { a as TraceAnalystLimits, i as TraceAnalysisEngineResult, n as TraceAnalysisEngine } from "./engine-FRZ3RLvT.js";
7
+ import { t as TraceToolGroupName } from "./tool-groups-BdcoEgtV.js";
8
8
  //#region src/trace/otel.d.ts
9
9
  declare const OTEL_AGENT_EVAL_SCOPE: {
10
10
  name: string;
@@ -339,4 +339,4 @@ declare class ToolTraceMissingError extends CaptureIntegrityError {
339
339
  declare function toolSpansToTraceAnalysisStore(spans: readonly ToolSpan[] | null | undefined, options?: ToolSpansToTraceAnalysisStoreOptions): TraceAnalysisStore;
340
340
  //#endregion
341
341
  export { createBoundedTraceAnalysisStore as A, OtlpSpan as B, scoreTraceInsightReadiness as C, AnalyzeTracesResult as D, AnalyzeTracesOptions as E, redactString as F, redactValue as I, OTEL_AGENT_EVAL_SCOPE as L, REDACTION_VERSION as M, RedactionReport as N, analyzeTraces as O, RedactionRule as P, OtlpExport as R, planTraceInsightQuestions as S, AnalyzeTracesInput as T, exportRunAsOtlp as V, buildTraceInsightPrompt as _, ToolSpansToTraceAnalysisStoreOptions as a, domainEvidencePattern as b, TraceInsightFinding as c, TraceInsightQualityGate as d, TraceInsightQuestion as f, buildTraceInsightContext as g, TraceInsightTask as h, OtlpFileTraceStoreOptions as i, DEFAULT_REDACTION_RULES as j, OtlpFlatLine as k, TraceInsightPanelRole as l, TraceInsightSuite as m, toolSpansToTraceAnalysisStore as n, otlpTextToTraceAnalysisStore as o, TraceInsightReadiness as p, OtlpFileTraceStore as r, TraceInsightContext as s, ToolTraceMissingError as t, TraceInsightPromptInput as u, defaultTraceInsightPanel as v, tokenizeDomainWords as w, inferDomainKeywords as x, describeTraceInsightScope as y, OtlpResourceSpans as z };
342
- //# sourceMappingURL=store-tool-spans-DbDLOBOb.d.ts.map
342
+ //# sourceMappingURL=store-tool-spans-CggeC1LB.d.ts.map
@@ -1 +1 @@
1
- {"version":3,"file":"store-tool-spans-DbDLOBOb.d.ts","names":[],"sources":["../src/trace/otel.ts","../src/trace/redact.ts","../src/trace-analyst/store-boundary.ts","../src/trace/otlp-flat.ts","../src/trace-analyst/analyst.ts","../src/trace-analyst/insights.ts","../src/trace-analyst/store-otlp.ts","../src/trace-analyst/store-tool-spans.ts"],"mappings":";;;;;;;;cAqBa;EAA0B;EAAoC;;UAE1D;EACf;EACA;EACA;EACA;EACA;EACA;EACA;EACA,YAAY;IACV;IACA;MAAS;MAAsB;MAAmB;MAAsB;;;EAE1E,SAAS;IAAQ;IAAsB;IAAc,aAAa;;EAClE;IAAW;IAAc;;;UAGV;EACf;IAAY,YAAY;;EACxB,YAAY;IAAQ,cAAc;IAAuB,OAAO;;;UAGjD;EACf,eAAe;;;iBAIK,gBACpB,OAAO,YACP,eACA,gBAAe,4CACd,QAAQ;;;;;;;;;;;;;;;;UCvCM;EACf;EACA,SAAS;;EAET;;UAGe;EACf;EACA,QAAQ;;;cAIG,yBAAyB;cAezB;;;;;iBAMG,aACd,eACA,QAAO;EACJ;EAAgB,QAAQ;;;;;;;iBAuBb,YACd,gBACA,QAAO,iBACP,SAAQ;EACL;EAAgB,QAAQ;;;;;iBCjDb,gCACd,QAAQ,oBACR,UAAS,mCACR;;;KC5BS;UAEK;EACf;EACA;EACA;EACA;EACA;EACA;EACA;EACA;IACE,MAAM;IACN;;EAEF;IAAY,YAAY;;EACxB,YAAY;EACZ,SAAS;IAAQ;IAAc;IAAuB,aAAa;;;;;UCNpD;EACf;EACA;EACA;EACA;;KAGU,sBAAsB;UAEjB;;EAEf,iBAAiB;;EAEjB,QAAQ;;EAER;;EAEA,YAAY;EACZ,SAAS,QAAQ;EACjB;EACA;EACA,aAAa;EACb;EACA,yBAAyB;EACzB,4BAA4B;EAC5B,eAAe,SAAS;EACxB,OAAO;EACP,OAAO,iBAAiB,SAAS;EACjC,SAAS;;;;;;;;iBASW,cACpB,OAAO,oBACP,SAAS,uBACR,QAAQ;;;UCtDM;EACf;EACA;EACA;EACA;EACA;EACA;EACA;EACA;;UAGe;EACf;EACA;EACA,OAAO;;UAGQ;EACf;EACA;EACA;EACA;EACA;;UAGe;EACf;EACA;EACA;;UAGe;EACf;EACA;EACA;;UAGe;EACf,OAAO;EACP,WAAW;EACX,QAAQ;EACR,SAAS;EACT;;UAGe;EACf,OAAO;EACP;EACA;EACA,WAAW;EACX,OAAO;EACP,UAAU;EACV,OAAO;EACP,QAAQ;;UAGO;EACf;EACA;EACA;EACA;EACA;;UAGe;EACf;EACA;EACA,OAAO;;iBA0BO,oBAAoB;iBAMpB,oBAAoB,OAAO;iBAuB3B,sBAAsB,qBAAqB;iBAS3C,0BAA0B,OAAO;iBAsBjC,0BAA0B,OAAO,0BAA0B;iBAsD3D,yBAAyB,OAAO,0BAA0B;iBAa1D,2BAA2B,SAAS,sBAAsB;iBA2D1D,4BAA4B;iBA6B5B,wBAAwB,OAAO;;;UC1K9B;;EAEf;;EAEA;;EAEA;;EAEA;;KAGG,gCAAgC;UAEpB,kCAAkC;;EAEjD;;;;;;;;EAQA;;uBAMa,kCAAkC;mBAC9B;mBACA;mBACA;mBACA;UACT;UACA;UACA;UACA;EAER,YAAY,MAAM;EAyBZ,SAAS,kBAAkB,UAAU,4BAA4B;EAOjE,SACJ;IAAQ;IAAkB;KAC1B,UAAU,4BACT;EAeG,YACJ,UAAU,qBACV,UAAU,4BACT,QAAQ;EAoDL,YACJ;IAAQ,UAAU;IAAqB;IAAe;KACtD,UAAU,4BACT,QAAQ;EAmBL,YACJ,UAAU,qBACV,UAAU,4BACT;EAMG,UACJ;IAAQ;IAAkB;KAC1B,UAAU,4BACT,QAAQ;EAuCL,UACJ;IAAQ;IAAkB;IAA6B;KACvD,UAAU,4BACT,QAAQ;EAsFL,YACJ;IAAQ;IAAkB;IAAuB;KACjD,UAAU,4BACT,QAAQ;EA4CL,WACJ;IAAQ;IAAkB;IAAiB;IAAuB;KAClE,UAAU,4BACT,QAAQ;;;EA6CL,cAAc,UAAU,4BAA4B;UAI5C;qBAmBK,WAAW,SAAS,cAAc,QAAQ;qBAE1C;UAEL;UAmBA;UAsHA;UA+DN;UAkBA;UAwDA;UAmBM;;cA+CH,2BAA2B;mBACrB;mBACA;EAEjB,YAAY,MAAM;;;YAYF,WAAW,SAAS,cAAc,QAAQ;YAkBhD;;;iBAwBI,6BACd,cACA,OAAM,uCACL;;;;cC/7BU,8BAA8B;EACzC;;;;;;iBASc,8BACd,gBAAgB,+BAChB,UAAS,uCACR"}
1
+ {"version":3,"file":"store-tool-spans-CggeC1LB.d.ts","names":[],"sources":["../src/trace/otel.ts","../src/trace/redact.ts","../src/trace-analyst/store-boundary.ts","../src/trace/otlp-flat.ts","../src/trace-analyst/analyst.ts","../src/trace-analyst/insights.ts","../src/trace-analyst/store-otlp.ts","../src/trace-analyst/store-tool-spans.ts"],"mappings":";;;;;;;;cAqBa;EAA0B;EAAoC;;UAE1D;EACf;EACA;EACA;EACA;EACA;EACA;EACA;EACA,YAAY;IACV;IACA;MAAS;MAAsB;MAAmB;MAAsB;;;EAE1E,SAAS;IAAQ;IAAsB;IAAc,aAAa;;EAClE;IAAW;IAAc;;;UAGV;EACf;IAAY,YAAY;;EACxB,YAAY;IAAQ,cAAc;IAAuB,OAAO;;;UAGjD;EACf,eAAe;;;iBAIK,gBACpB,OAAO,YACP,eACA,gBAAe,4CACd,QAAQ;;;;;;;;;;;;;;;;UCvCM;EACf;EACA,SAAS;;EAET;;UAGe;EACf;EACA,QAAQ;;;cAIG,yBAAyB;cAezB;;;;;iBAMG,aACd,eACA,QAAO;EACJ;EAAgB,QAAQ;;;;;;;iBAuBb,YACd,gBACA,QAAO,iBACP,SAAQ;EACL;EAAgB,QAAQ;;;;;iBCjDb,gCACd,QAAQ,oBACR,UAAS,mCACR;;;KC5BS;UAEK;EACf;EACA;EACA;EACA;EACA;EACA;EACA;EACA;IACE,MAAM;IACN;;EAEF;IAAY,YAAY;;EACxB,YAAY;EACZ,SAAS;IAAQ;IAAc;IAAuB,aAAa;;;;;UCNpD;EACf;EACA;EACA;EACA;;KAGU,sBAAsB;UAEjB;;EAEf,iBAAiB;;EAEjB,QAAQ;;EAER;;EAEA,YAAY;EACZ,SAAS,QAAQ;EACjB;EACA;EACA,aAAa;EACb;EACA,yBAAyB;EACzB,4BAA4B;EAC5B,eAAe,SAAS;EACxB,OAAO;EACP,OAAO,iBAAiB,SAAS;EACjC,SAAS;;;;;;;;iBASW,cACpB,OAAO,oBACP,SAAS,uBACR,QAAQ;;;UCtDM;EACf;EACA;EACA;EACA;EACA;EACA;EACA;EACA;;UAGe;EACf;EACA;EACA,OAAO;;UAGQ;EACf;EACA;EACA;EACA;EACA;;UAGe;EACf;EACA;EACA;;UAGe;EACf;EACA;EACA;;UAGe;EACf,OAAO;EACP,WAAW;EACX,QAAQ;EACR,SAAS;EACT;;UAGe;EACf,OAAO;EACP;EACA;EACA,WAAW;EACX,OAAO;EACP,UAAU;EACV,OAAO;EACP,QAAQ;;UAGO;EACf;EACA;EACA;EACA;EACA;;UAGe;EACf;EACA;EACA,OAAO;;iBA0BO,oBAAoB;iBAMpB,oBAAoB,OAAO;iBAuB3B,sBAAsB,qBAAqB;iBAS3C,0BAA0B,OAAO;iBAsBjC,0BAA0B,OAAO,0BAA0B;iBAsD3D,yBAAyB,OAAO,0BAA0B;iBAa1D,2BAA2B,SAAS,sBAAsB;iBA2D1D,4BAA4B;iBA6B5B,wBAAwB,OAAO;;;UC1K9B;;EAEf;;EAEA;;EAEA;;EAEA;;KAGG,gCAAgC;UAEpB,kCAAkC;;EAEjD;;;;;;;;EAQA;;uBAMa,kCAAkC;mBAC9B;mBACA;mBACA;mBACA;UACT;UACA;UACA;UACA;EAER,YAAY,MAAM;EAyBZ,SAAS,kBAAkB,UAAU,4BAA4B;EAOjE,SACJ;IAAQ;IAAkB;KAC1B,UAAU,4BACT;EAeG,YACJ,UAAU,qBACV,UAAU,4BACT,QAAQ;EAoDL,YACJ;IAAQ,UAAU;IAAqB;IAAe;KACtD,UAAU,4BACT,QAAQ;EAmBL,YACJ,UAAU,qBACV,UAAU,4BACT;EAMG,UACJ;IAAQ;IAAkB;KAC1B,UAAU,4BACT,QAAQ;EAuCL,UACJ;IAAQ;IAAkB;IAA6B;KACvD,UAAU,4BACT,QAAQ;EAsFL,YACJ;IAAQ;IAAkB;IAAuB;KACjD,UAAU,4BACT,QAAQ;EA4CL,WACJ;IAAQ;IAAkB;IAAiB;IAAuB;KAClE,UAAU,4BACT,QAAQ;;;EA6CL,cAAc,UAAU,4BAA4B;UAI5C;qBAmBK,WAAW,SAAS,cAAc,QAAQ;qBAE1C;UAEL;UAmBA;UAsHA;UA+DN;UAkBA;UAwDA;UAmBM;;cA+CH,2BAA2B;mBACrB;mBACA;EAEjB,YAAY,MAAM;;;YAYF,WAAW,SAAS,cAAc,QAAQ;YAkBhD;;;iBAwBI,6BACd,cACA,OAAM,uCACL;;;;cC/7BU,8BAA8B;EACzC;;;;;;iBASc,8BACd,gBAAgB,+BAChB,UAAS,uCACR"}
@@ -1,5 +1,5 @@
1
1
  import { w as TraceAnalysisStore } from "./types-DLQx4mKU.js";
2
- import { _ as TraceAnalysisToolDescriptor } from "./engine-otFpE2gF.js";
2
+ import { _ as TraceAnalysisToolDescriptor } from "./engine-FRZ3RLvT.js";
3
3
  //#region src/analyst/tool-groups.d.ts
4
4
  /** Named tool sets. Kinds pass `tools: TRACE_TOOL_GROUPS.failureForensics` etc. */
5
5
  type TraceToolGroupName =
@@ -25,4 +25,4 @@ type TraceToolGroupName =
25
25
  declare function buildTraceToolsForGroup(group: TraceToolGroupName, store: TraceAnalysisStore): TraceAnalysisToolDescriptor[];
26
26
  //#endregion
27
27
  export { buildTraceToolsForGroup as n, TraceToolGroupName as t };
28
- //# sourceMappingURL=tool-groups-Cteb03Ps.d.ts.map
28
+ //# sourceMappingURL=tool-groups-BdcoEgtV.d.ts.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"tool-groups-BdcoEgtV.d.ts","names":[],"sources":["../src/analyst/tool-groups.ts"],"mappings":";;;;KAmBY;;;;;;;;;;;;;;;;;;;;iBAgDI,wBACd,OAAO,oBACP,OAAO,qBACN"}
@@ -2,7 +2,7 @@ import { r as CaptureIntegrityError } from "../errors-DEE6u6ot.js";
2
2
  import { t as DefaultVerdict } from "../verdict-E4eRNf7-.js";
3
3
  import { b as CustomTokenPricing, c as CostLedgerHandle, p as CostProvenance } from "../cost-ledger-DbQdN3nO.js";
4
4
  import { u as RunTokenUsage } from "../run-record-CKiihE6f.js";
5
- import { a as TraceAnalystLimits, n as TraceAnalysisEngine } from "../engine-otFpE2gF.js";
5
+ import { a as TraceAnalystLimits, n as TraceAnalysisEngine } from "../engine-FRZ3RLvT.js";
6
6
  import { t as PrimeBridgeTransport } from "../prime-bridge-transport-6feEglLf.js";
7
7
  import { t as RecordedTrajectoryStep } from "../steps-BArUxhna.js";
8
8
  //#region src/trace-repair/mini-swe-scaffold.d.ts
package/dist/traces.d.ts CHANGED
@@ -6,12 +6,12 @@ import { $ as InMemoryRawProviderSinkOptions, Q as InMemoryRawProviderSink, X as
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-CT9YIIve.js";
7
7
  import { a as TraceEmitterOptions, i as TraceEmitter, n as RunCompleteHookContext, o as llmSpanFromProvider, r as SpanHandle, t as RunCompleteHook } from "./emitter-DGQGoLyj.js";
8
8
  import { a as RunIntegrityReport, i as RunIntegrityIssueCode, n as RunIntegrityExpectations, o as assertRunCaptured, r as RunIntegrityIssue, s as throwIfRunIncomplete, t as RunIntegrityError } from "./integrity-OrcI9Nau.js";
9
- import { A as createBoundedTraceAnalysisStore, B as OtlpSpan, C as scoreTraceInsightReadiness, D as AnalyzeTracesResult, E as AnalyzeTracesOptions, F as redactString, I as redactValue, L as OTEL_AGENT_EVAL_SCOPE, M as REDACTION_VERSION, N as RedactionReport, O as analyzeTraces, P as RedactionRule, R as OtlpExport, S as planTraceInsightQuestions, T as AnalyzeTracesInput, V as exportRunAsOtlp, _ as buildTraceInsightPrompt, a as ToolSpansToTraceAnalysisStoreOptions, b as domainEvidencePattern, c as TraceInsightFinding, d as TraceInsightQualityGate, f as TraceInsightQuestion, g as buildTraceInsightContext, h as TraceInsightTask, i as OtlpFileTraceStoreOptions, j as DEFAULT_REDACTION_RULES, k as OtlpFlatLine, l as TraceInsightPanelRole, m as TraceInsightSuite, n as toolSpansToTraceAnalysisStore, o as otlpTextToTraceAnalysisStore, p as TraceInsightReadiness, r as OtlpFileTraceStore, s as TraceInsightContext, t as ToolTraceMissingError, u as TraceInsightPromptInput, v as defaultTraceInsightPanel, w as tokenizeDomainWords, x as inferDomainKeywords, y as describeTraceInsightScope, z as OtlpResourceSpans } from "./store-tool-spans-DbDLOBOb.js";
9
+ import { A as createBoundedTraceAnalysisStore, B as OtlpSpan, C as scoreTraceInsightReadiness, D as AnalyzeTracesResult, E as AnalyzeTracesOptions, F as redactString, I as redactValue, L as OTEL_AGENT_EVAL_SCOPE, M as REDACTION_VERSION, N as RedactionReport, O as analyzeTraces, P as RedactionRule, R as OtlpExport, S as planTraceInsightQuestions, T as AnalyzeTracesInput, V as exportRunAsOtlp, _ as buildTraceInsightPrompt, a as ToolSpansToTraceAnalysisStoreOptions, b as domainEvidencePattern, c as TraceInsightFinding, d as TraceInsightQualityGate, f as TraceInsightQuestion, g as buildTraceInsightContext, h as TraceInsightTask, i as OtlpFileTraceStoreOptions, j as DEFAULT_REDACTION_RULES, k as OtlpFlatLine, l as TraceInsightPanelRole, m as TraceInsightSuite, n as toolSpansToTraceAnalysisStore, o as otlpTextToTraceAnalysisStore, p as TraceInsightReadiness, r as OtlpFileTraceStore, s as TraceInsightContext, t as ToolTraceMissingError, u as TraceInsightPromptInput, v as defaultTraceInsightPanel, w as tokenizeDomainWords, x as inferDomainKeywords, y as describeTraceInsightScope, z as OtlpResourceSpans } from "./store-tool-spans-CggeC1LB.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-DLJ6303h.js";
11
11
  import { a as judgeSpans, c as runsForScenario, i as hasCapturedToolArgs, l as toolSpans, n as argHash, o as llmSpans, r as groupBy, s as runFailureClass, t as aggregateLlm } from "./query-CJ_DX8vl.js";
12
12
  import "./index-Ba3YrbAL.js";
13
13
  import { A as SearchSpanResult, B as ViewSpansResult, C as TRACE_ANALYSIS_LIMITS, D as DatasetOverview, E as DEFAULT_TRACE_ANALYST_BUDGETS, F as TraceAnalystFilters, H as ViewTraceResult, I as TraceAnalystSpan, L as TraceAnalystSpanKind, M as SpanMatchRecord, N as TRACE_ANALYST_TRUNCATION_MARKER_PREFIX, O as ErrorCluster, P as TraceAnalystByteBudgets, R as TraceAnalystSpanStatus, S as BoundedTraceAnalysisStoreOptions, T as TraceAnalysisStoreContext, V as ViewTraceOversized, j as SearchTraceResult, k as QueryTracesPage, w as TraceAnalysisStore, z as TraceAnalystTraceSummary } from "./types-DLQx4mKU.js";
14
- import { _ as TraceAnalysisToolDescriptor, g as TRACE_ANALYST_TOOL_NAMESPACE, h as BuildTraceAnalysisToolsOptions, v as buildTraceAnalysisToolDescriptors, y as traceAnalystFunctionGroup } from "./engine-otFpE2gF.js";
14
+ import { _ as TraceAnalysisToolDescriptor, g as TRACE_ANALYST_TOOL_NAMESPACE, h as BuildTraceAnalysisToolsOptions, v as buildTraceAnalysisToolDescriptors, y as traceAnalystFunctionGroup } from "./engine-FRZ3RLvT.js";
15
15
  //#region src/trace/otlp-attributes.d.ts
16
16
  type ToolSpanOtlpInput = Pick<ToolSpan, 'toolName' | 'args' | 'argsCaptured' | 'result' | 'latencyMs'>;
17
17
  type OtlpSpanRole = 'AGENT' | 'CHAIN' | 'EVALUATOR' | 'GUARDRAIL' | 'LLM' | 'SPAN' | 'TOOL' | 'UNKNOWN';
@@ -1,5 +1,5 @@
1
1
  import { s as RunSplitTag } from "./run-record-CKiihE6f.js";
2
- import { R as Scenario, d as DispatchContext } from "./types-BZ59Ahr8.js";
2
+ import { R as Scenario, d as DispatchContext } from "./types-BxLccGMf.js";
3
3
  //#region src/benchmarks/types.d.ts
4
4
  type BenchmarkTaskKind = 'retrieval' | 'rag-answer' | 'hallucination' | 'kb-improvement' | 'routing' | 'custom';
5
5
  type BenchmarkFamily = 'beir' | 'mteb-retrieval' | 'msmarco' | 'trec-dl' | 'miracl' | 'lotte' | 'bright' | 'crag' | 'hotpotqa' | 'kilt' | 'ragtruth' | 'faithbench' | 'first-party' | 'custom';
@@ -90,4 +90,4 @@ declare const BENCHMARK_SPLIT_SEED = "agent-eval-v1";
90
90
  declare function deterministicSplit(itemId: string, seed?: string): RunSplitTag;
91
91
  //#endregion
92
92
  export { BenchmarkFamily as a, BenchmarkSource as c, BenchmarkEvaluation as i, BenchmarkTaskKind as l, BenchmarkAdapter as n, BenchmarkResponder as o, BenchmarkDatasetItem as r, BenchmarkScenario as s, BENCHMARK_SPLIT_SEED as t, deterministicSplit as u };
93
- //# sourceMappingURL=types-BEPZc6eo.d.ts.map
93
+ //# sourceMappingURL=types-BRsxjg7z.d.ts.map
@@ -1 +1 @@
1
- {"version":3,"file":"types-BEPZc6eo.d.ts","names":[],"sources":["../src/benchmarks/types.ts"],"mappings":";;;KASY;KAQA;UAgBK,qBAAqB;;;EAGpC;;EAEA,SAAS;;EAET,QAAQ;;EAER,SAAS;;EAET,WAAW;;EAEX;;EAEA,SAAS;EACT,WAAW;;UAGI;;;;EAIf;;EAEA;;EAEA,aAAa;;;EAGb,KAAK;EACL;;UAGe;EACf;EACA;EACA;EACA;EACA;;;UAQe,iBAAiB,kBAAkB,oBAAoB;;EAEtE;EACA,SAAS;EACT,WAAW;EACX;EACA,SAAS;EACT;;;;;EAKA,YAAY,OAAO,cAAc,QAAQ,qBAAqB;;EAE9D,SAAS,MAAM,qBAAqB,WAAW,UAAU,YAAY,QAAQ;;;;EAI7E,YAAY,iBAAiB;;UAGd,kBAAkB,4BAA4B;EAC7D;EACA;EACA,QAAQ;EACR,UAAU;EACV,UAAU;EACV,MAAM,qBAAqB;;KAGjB,mBAAmB,oBAAoB,uBAAuB;EACxE,UAAU,kBAAkB;EAC5B,MAAM,qBAAqB;EAC3B,SAAS;MACL,QAAQ,aAAa;;;cAoBd;;;;;;;;;iBAUG,mBACd,gBACA,gBACC"}
1
+ {"version":3,"file":"types-BRsxjg7z.d.ts","names":[],"sources":["../src/benchmarks/types.ts"],"mappings":";;;KASY;KAQA;UAgBK,qBAAqB;;;EAGpC;;EAEA,SAAS;;EAET,QAAQ;;EAER,SAAS;;EAET,WAAW;;EAEX;;EAEA,SAAS;EACT,WAAW;;UAGI;;;;EAIf;;EAEA;;EAEA,aAAa;;;EAGb,KAAK;EACL;;UAGe;EACf;EACA;EACA;EACA;EACA;;;UAQe,iBAAiB,kBAAkB,oBAAoB;;EAEtE;EACA,SAAS;EACT,WAAW;EACX;EACA,SAAS;EACT;;;;;EAKA,YAAY,OAAO,cAAc,QAAQ,qBAAqB;;EAE9D,SAAS,MAAM,qBAAqB,WAAW,UAAU,YAAY,QAAQ;;;;EAI7E,YAAY,iBAAiB;;UAGd,kBAAkB,4BAA4B;EAC7D;EACA;EACA,QAAQ;EACR,UAAU;EACV,UAAU;EACV,MAAM,qBAAqB;;KAGjB,mBAAmB,oBAAoB,uBAAuB;EACxE,UAAU,kBAAkB;EAC5B,MAAM,qBAAqB;EAC3B,SAAS;MACL,QAAQ,aAAa;;;cAoBd;;;;;;;;;iBAUG,mBACd,gBACA,gBACC"}
@@ -24,6 +24,8 @@ interface CampaignScenarioIdentity extends Pick<Scenario, 'id' | 'kind'> {
24
24
  * artifact root, the cost meter accumulates per cell. */
25
25
  interface DispatchContext {
26
26
  cellId: string;
27
+ /** Unique identity for this invocation of the campaign, including retries. */
28
+ runAttemptId: string;
27
29
  rep: number;
28
30
  generation?: number;
29
31
  seed: number;
@@ -624,4 +626,4 @@ interface CampaignResult<TArtifact = unknown, TScenario extends Scenario = Scena
624
626
  }
625
627
  //#endregion
626
628
  export { LabeledScenarioWrite as A, ScoredSurfaceOutcome as B, JudgeDimension as C, LabeledScenarioSampleArgs as D, LabeledScenarioRecord as E, ProposeContext as F, labelTrustRank as G, SurfaceProposer as H, ProposedCandidate as I, RedactionStatus as L, OptimizerConfig as M, ParetoParent as N, LabeledScenarioSource as O, ProposalTrackContext as P, Scenario as R, JudgeConfig as S, LabelTrust as T, TraceSpan as U, SessionScript as V, isProposedCandidate as W, GateDecision as _, CampaignResult as a, GenerationRecord as b, CampaignTraceWriter as c, DispatchContext as d, DispatchFn as f, GateContribution as g, GateContext as h, CampaignCostMeter as i, MutableSurface as j, LabeledScenarioStore as k, CodeSurface as l, GateCheckStatus as m, CampaignArtifactWriter as n, CampaignScenarioIdentity as o, Gate as p, CampaignCellResult as r, CampaignTokenUsage as s, CampaignAggregates as t, ComponentSurface as u, GateResult as v, JudgeScore as w, JudgeAggregate as x, GenerationCandidate as y, ScenarioAggregate as z };
627
- //# sourceMappingURL=types-BZ59Ahr8.d.ts.map
629
+ //# sourceMappingURL=types-BxLccGMf.d.ts.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"types-BxLccGMf.d.ts","names":[],"sources":["../src/campaign/types.ts"],"mappings":";;;;;;;UAgCiB;EACf;EACA;EACA;;;;;EAKA;;;UAIe,iCAAiC,KAAK;EACrD;;;;;UAMe;EACf;;EAEA;EACA;EACA;EACA;EACA,QAAQ;EACR,OAAO;EACP,WAAW;EACX,MAAM;;EAEN;;EAEA;;;;;;;;EAQA;;;;KAKU,WAAW,kBAAkB,UAAU,cACjD,UAAU,WACV,KAAK,oBACF,QAAQ;;;;UAOI,cAAc,WAAW;EACxC;EACA;EACA;;EAEA;;;EAGA,sBAAsB,UAAU,WAAW,sBAAsB,UAAU,cAAc;;UAK1E;;EAEf;;EAEA;;;;;;;;;UAUe,YAAY,WAAW,kBAAkB,WAAW;EACnE;EACA,YAAY;;;;EAIZ;;;EAGA,MAAM;IACJ,UAAU;IACV,UAAU;IACV,QAAQ;;IAER,aAAa;IACb;IACA,WAAW;MACT,aAAa,QAAQ;EACzB,aAAa,UAAU;;;;;;;;;;;UAYR;EACf,YAAY;EACZ;EACA;;EAEA,UAAU;;;;EAIV;;;EAGA;;EAEA;;EAEA,WAAW,eAAe;;;;;;;UAUX;WACN;;;WAGA;;WAEA;;WAEA;;WAEA;;WAEA;;WAEA;;;WAGA;aACE;aACA;aACA;;;WAGF;;;UAIM;WACN;WACA,YAAY,SAAS;;;;;;;;;;;KAYpB,0BAA0B,mBAAmB;;;;;;;UAQxC;EACf,SAAS;;EAET;;;;EAIA;;;;iBAKc,oBACd,OAAO,iBAAiB,oBACvB,SAAS;;;;;;;;;UAkBK;EACf,SAAS;EACT;;;EAGA,YAAY;;;EAGZ;;EAEA;EACA;EACA;;;UAIe;EACf;EACA;EACA;EACA;EACA;;;;;UAMe;;;EAGf;;EAEA;EACA;EACA;EACA,YAAY;;;;;EAKZ,WAAW;IAAQ;IAAoB;IAAmB;IAAgB;;EAC1E;IACE;IACA;;;;;UAMa,eAAe,YAAY;WACjC,gBAAgB;WAChB,SAAS,cAAc;WACvB,UAAU,cAAc;;WAExB;WACA;WACA,QAAQ;;WAER,QAAQ;;;WAGR,kBAAkB;;;WAGlB,mBAAmB;;;;WAInB;;;;;;;WAOA,gBAAgB,cAAc;;WAE9B,aAAa;WACb;;;;;;;;;;;;;;UAeM,gBAAgB,YAAY;EAC3C;;;;;EAKA,QAAQ,KAAK,eAAe,aAAa,QAAQ,MAAM,iBAAiB;;;EAGxE,QAAQ;IAAQ,SAAS,cAAc;;IAAwB;IAAe;;;UAG/D;EACf;EACA;EACA,mBAAmB,qBAAqB;;UAGzB,wBAAwB;EACvC,UAAU;;;KAMA;;KAGA;UAEK;EACf;EACA,QAAQ;EACR;;UAGe,YAAY,WAAW,kBAAkB;EACxD,oBAAoB,YAAY;EAChC,oBAAoB,YAAY;;EAEhC,aAAa,YAAY,eAAe;;;;;EAKxC,sBAAsB,YAAY,eAAe;;;;;;;EAOjD,yBAAyB,YAAY,eAAe;;;EAGpD,uBAAuB,YAAY;EACnC,WAAW;EACX;IAAQ;IAAmB;;;EAE3B,aAAa;EACb;EACA,QAAQ;;UAGO;EACf,UAAU;EACV;EACA,mBAAmB;EACnB;;;UAIe,KAAK,qBAAqB,kBAAkB,WAAW;EACtE;EACA,OAAO,KAAK,YAAY,WAAW,aAAa,QAAQ;;;;UAOzC;EACf,KAAK,cAAc,aAAa,0BAA0B;EAC1D,SAAS;;UAGM;EACf,IAAI,aAAa;EACjB,aAAa,aAAa;;;;UAKX;EACf,MAAM,cAAc,kBAAkB,aAAa;EACnD,UAAU,cAAc,iBAAiB;;;;;;KAO/B,qBAAqB;;;;;UAMhB;;EAEf,YAAY,GACV,OAAO,KAAK,iBAAiB;IAC3B,UAAU;MAEX,QAAQ,eAAe;;;;;KAQhB;KAOA;;;;;;;;;;;;;;;KAgBA;;iBASI,eAAe,OAAO;;;;UAOrB,qBAAqB,kBAAkB,WAAW,UAAU;EAC3E,UAAU;EACV,UAAU;EACV,aAAa,eAAe;EAC5B,QAAQ;EACR;EACA;EACA,iBAAiB;;;;;EAKjB,aAAa;;EAEb;;UAGe,sBAAsB,kBAAkB,WAAW,UAAU,6BACpE,qBAAqB,WAAW;;EAExC;;;EAGA;;UAGe;EACf;;EAEA;;;;EAIA;EACA;IACE;IACA,SAAS,wBAAwB;IACjC;IACA;;;;;IAKA,WAAW;;;UAIE;EACf,QAAQ,OAAO,uBAAuB;EACtC,OAAO,MAAM,4BAA4B,QAAQ;EACjD,QAAQ;IACN;IACA;IACA,UAAU;;;IAGV,SAAS,OAAO;;;UAMH,mBAAmB;;;EAGlC;EACA;EACA;EACA;EACA;EACA,UAAU;EACV,aAAa,eAAe;;;EAG5B;;EAEA,gBAAgB;;EAEhB;;;EAGA,YAAY;;;EAGZ;;;EAGA;EACA;EACA;EACA;;EAEA;;EAEA;EACA;;UAGe;EACf;EACA;EACA;EACA;;UAGe;EACf;EACA;EACA;;UAGe;EACf;EACA,YAAY;EACZ;;;;;;UAOe;EACf;;EAEA;;EAEA;;EAEA;;EAEA;;;EAGA;;;;EAIA;;;;EAIA;IACE;IACA;IACA,iBAAiB;MAAQ;MAAgB;;;;;EAI3C,YAAY;;;;;;;;;;EAUZ,WAAW;IAAQ;IAAoB;IAAmB;IAAgB;;;;EAG1E;;;;EAIA;;UAGe;EACf,SAAS,eAAe;EACxB,YAAY,eAAe;;EAE3B,MAAM;;EAEN;EACA;EACA;;EAEA;;EAEA;;EAEA;;EAEA;;UAGe,eAAe,qBAAqB,kBAAkB,WAAW;;EAEhF;;EAEA;EACA;;EAEA;EACA;EACA;EACA;EACA,OAAO,MAAM,mBAAmB;EAChC,YAAY;EACZ;IACE,aAAa;IACb;;EAEF,OAAO;EACP;EACA;EACA,iBAAiB;;;EAGjB,WAAW,MAAM,2BAA2B,KAAK"}
@@ -25,6 +25,7 @@ The implementation can be local, remote, sandboxed, or spread across a worker fl
25
25
  | Where | What |
26
26
  |---|---|
27
27
  | **`DispatchContext.placement?: string`** | Opaque placement key the substrate forwards to the Dispatch. |
28
+ | **`DispatchContext.runAttemptId: string`** | Unique identity for this campaign invocation, including failed retries. |
28
29
  | **`RunCampaignOptions.cellPlacement?(input) → string \| undefined`** | Strategy function the substrate calls per cell to compute the placement key. |
29
30
  | **`@tangle-network/agent-eval/adapters/http`** | `httpDispatch` (client) + `runDispatchServer` (server): wire shape for HTTP-based remote workers. |
30
31
 
@@ -33,6 +34,10 @@ install. The substrate doesn't strategy-pick; you provide the
33
34
  `cellPlacement` function, the substrate forwards its result, the
34
35
  Dispatch reads it. Clean seam, no policy baked in.
35
36
 
37
+ `runAttemptId` is not part of the cache key.
38
+ Completed cells remain reusable, while each failed retry receives a new attempt identity.
39
+ Keep this value in any worker workspace or receipt path that must not collide with another attempt.
40
+
36
41
  ## The three reference topologies
37
42
 
38
43
  ### 1. In-process (the default: what you already have)
@@ -136,6 +141,7 @@ round-robin, region-affinity from a previous run, scheduling table).
136
141
  | **Cancellation** | The coordinator's `AbortSignal` forwards into the HTTP request; server translates `AbortError` → `499` so client doesn't retry. |
137
142
  | **Timeouts** | Per-call `timeoutMs` on the client; server can layer its own. |
138
143
  | **Retries** | Idempotent retries on 5xx / 408 / 429 with exponential backoff + jitter. Coordinator aborts never retry. |
144
+ | **Attempt identity** | `runAttemptId` crosses the wire unchanged, so worker workspace names remain unique across failed retries. |
139
145
  | **Auth** | Bearer token on `Authorization`; pluggable via `auth: string \| () => string \| Promise<string>` for rotation/refresh. |
140
146
  | **Payload size** | Server enforces `maxBodyBytes` (default 10 MB). |
141
147
  | **Traces** | Both ends emit OTel: if both point at the same OTLP collector, you get a unified trace per cell. See `docs/adapters-observability.md`. |
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@tangle-network/agent-eval",
3
- "version": "0.145.4",
3
+ "version": "0.145.6",
4
4
  "description": "Evaluate and improve AI agents from runs, traces, judges, and feedback. Compare candidates, cluster failures, measure lift, and gate releases.",
5
5
  "homepage": "https://github.com/tangle-network/agent-eval#readme",
6
6
  "repository": {