@tangle-network/agent-eval 0.138.0 → 0.139.0

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@tangle-network/agent-eval",
-  "version": "0.138.0",
+  "version": "0.139.0",
   "description": "Evaluate and improve AI agents from runs, traces, judges, and feedback. Compare candidates, cluster failures, measure lift, and gate releases.",
   "homepage": "https://github.com/tangle-network/agent-eval#readme",
   "repository": {
@@ -167,7 +167,6 @@
   },
   "dependencies": {
     "@asteasolutions/zod-to-openapi": "^9.1.0",
-    "@ax-llm/ax": "^23.0.5",
     "@hono/node-server": "^2.0.12",
     "@tangle-network/agent-core": "0.4.28",
     "@tangle-network/agent-interface": "0.39.0",

package/dist/analyze-runs-CPYxfPWT.d.ts

@@ -1,72 +0,0 @@
-import { a as RunRecord } from "./run-record-DwHMk1Ai.js";
-import { n as AnalystRegistry } from "./registry-C4yJTza7.js";
-import { a as DatasetScenario } from "./dataset-v_Y5902-.js";
-import "./summary-report-BKinV4yD.js";
-import { o as InsightReport, r as ExecutionInsight, t as CostProvenanceSummary } from "./insight-report-CXd8VBDR.js";
-//#region src/contract/analyze-runs.d.ts
-interface AnalyzeRunsOptions {
-  /** The runs to analyze. */
-  runs: RunRecord[];
-  /** Which split to score against when reading composite from RunOutcome.
-   *  Default: holdout when ANY run has a `holdoutScore`, else search. */
-  split?: 'search' | 'holdout' | 'auto';
-  /** Pairwise analysis configuration. When both `baselineCandidateId` and
-   *  `candidateCandidateId` are present, lift is computed on paired
-   *  (experimentId, scenarioId, seed) identities shared between the two sides.
-   *  Unmatched rows remain visible in the lift result. */
-  baselineCandidateId?: string;
-  candidateCandidateId?: string;
-  /** Canary scenarios — checked against every run's raw output for
-   *  holdout contamination. */
-  canaryScenarios?: DatasetScenario[];
-  /** Analyst registry for failure clustering. When omitted, the
-   *  `failureClusters` section is left undefined. */
-  analyst?: AnalystRegistry;
-  /** Downstream outcome metric per run (e.g. engagement rate, approval
-   *  rate, downstream pass rate). When present, the report includes
-   *  `outcomeCorrelation` + a simple linear reward model fit. */
-  outcomeSignal?: {
-    metric: string;
-    valueByRunId: Record<string, number>;
-  };
-  /** Multi-rater feedback for inter-rater agreement. Each entry is one
-   *  rater's score for one run. Two or more raters → kappa + disagreement
-   *  triage list. */
-  raterScores?: Array<{
-    runId: string;
-    rater: string;
-    score: number;
-  }>;
-  /** Number of histogram bins for distributional summaries. Default 12. */
-  histogramBins?: number;
-  /** Decision threshold — the smallest composite lift the caller cares
-   *  about. Used by the recommendations engine to call ship vs hold.
-   *  Default 0.02. */
-  decisionThreshold?: number;
-  /** Optional prior-period runs. When set, the report includes
-   *  `priorPeriodComparison` with per-metric Welch-CI deltas and
-   *  recommendations fire on statistically significant regressions.
-   *  The two windows do NOT have to share scenarios — the comparison
-   *  is two-sample unpaired (the substrate's `lift` field uses paired
-   *  bootstrap on shared (experimentId, scenarioId, seed) identities; this is the
-   *  shape for "this week vs last week" rather than "candidate vs
-   *  baseline within a campaign"). */
-  baselineRuns?: RunRecord[];
-  /** Human-readable label for the baseline window, e.g. "vs prior 7
-   *  days", "vs v3.1 release". Surfaces in recommendations + UI. */
-  baselineLabel?: string;
-}
-interface SummarizeExecutionOptions {
-  runs: RunRecord[];
-  histogramBins?: number;
-}
-interface ExecutionReport {
-  execution: ExecutionInsight;
-  costProvenance: CostProvenanceSummary;
-}
-/** Summarize runtime facts without interpreting task quality or promotion readiness. */
-declare function summarizeExecution(opts: SummarizeExecutionOptions): ExecutionReport;
-declare function analyzeRuns(opts: AnalyzeRunsOptions): Promise<InsightReport>;
-//#endregion
-export { summarizeExecution as a, analyzeRuns as i, ExecutionReport as n, SummarizeExecutionOptions as r, AnalyzeRunsOptions as t };
-//# sourceMappingURL=analyze-runs-CPYxfPWT.d.ts.map

package/dist/analyze-runs-CPYxfPWT.d.ts.map

@@ -1 +0,0 @@
-{"version":3,"file":"analyze-runs-CPYxfPWT.d.ts","names":[],"sources":["../src/contract/analyze-runs.ts"],"mappings":";;;;;;UAoEiB;;EAEf,MAAM;;;EAGN;;;;;EAKA;EACA;;;EAGA,kBAAkB;;;EAGlB,UAAU;;;;EAIV;IACE;IACA,cAAc;;;;;EAKhB,cAAc;IAAQ;IAAe;IAAe;;;EAEpD;;;;EAIA;;;;;;;;;EASA,eAAe;;;EAGf;;UAGe;EACf,MAAM;EACN;;UAGe;EACf,WAAW;EACX,gBAAgB;;;iBAIF,mBAAmB,MAAM,4BAA4B;iBAgB/C,YAAY,MAAM,qBAAqB,QAAQ"}