@tangle-network/agent-eval 0.120.2 → 0.120.4

package/dist/wire/index.js

@@ -0,0 +1,81 @@
+import {
+  BUILTIN_RUBRICS,
+  ErrorResponseSchema,
+  FailureModeSchema,
+  FeedbackAttemptSchema,
+  FeedbackIngestResponseSchema,
+  FeedbackLabelSchema,
+  FeedbackTrajectorySchema,
+  HealthResponseSchema,
+  JudgeRequestSchema,
+  JudgeResultSchema,
+  ListRubricsResponseSchema,
+  RubricDimensionSchema,
+  RubricInfoSchema,
+  RubricSchema,
+  TraceEventSchema,
+  TracesIngestRequestSchema,
+  TracesIngestResponseSchema,
+  VersionResponseSchema,
+  WIRE_VERSION,
+  WireError,
+  buildOpenApi,
+  createApp,
+  dispatchRpc,
+  getBuiltinRubric,
+  handleFeedbackIngest,
+  handleJudge,
+  handleListRubrics,
+  handleTracesIngest,
+  handleVersion,
+  hashRubric,
+  listBuiltinRubrics,
+  runRpcBatch,
+  runRpcOnce,
+  startServer,
+  startServerAsync
+} from "../chunk-NMN4WGSJ.js";
+import "../chunk-NJC7U437.js";
+import "../chunk-ZMXDQ4K7.js";
+import "../chunk-VI2UW6B6.js";
+import "../chunk-PC4UYEBM.js";
+import "../chunk-ONWEPEDO.js";
+import "../chunk-PZ5AY32C.js";
+export {
+  BUILTIN_RUBRICS,
+  ErrorResponseSchema,
+  FailureModeSchema,
+  FeedbackAttemptSchema,
+  FeedbackIngestResponseSchema,
+  FeedbackLabelSchema,
+  FeedbackTrajectorySchema,
+  HealthResponseSchema,
+  JudgeRequestSchema,
+  JudgeResultSchema,
+  ListRubricsResponseSchema,
+  RubricDimensionSchema,
+  RubricInfoSchema,
+  RubricSchema,
+  TraceEventSchema,
+  TracesIngestRequestSchema,
+  TracesIngestResponseSchema,
+  VersionResponseSchema,
+  WIRE_VERSION,
+  WireError,
+  buildOpenApi,
+  createApp,
+  dispatchRpc,
+  getBuiltinRubric,
+  handleFeedbackIngest,
+  handleJudge,
+  handleListRubrics,
+  handleTracesIngest,
+  handleVersion,
+  hashRubric,
+  listBuiltinRubrics,
+  runRpcBatch,
+  runRpcOnce,
+  startServer,
+  startServerAsync
+};
+//# sourceMappingURL=index.js.map

package/dist/wire/index.js.map

@@ -0,0 +1 @@
+{"version":3,"sources":[],"sourcesContent":[],"mappings":"","names":[]}

package/docs/eval-surface-map.md

@@ -12,7 +12,7 @@ composition point already exists (see Produced-state grading below).**
 | `runCampaign` | The measurement primitive. Run a dispatch over scenarios × seeds × reps, score each with judges, aggregate. Caller owns the dispatch. | `CampaignResult` |
 | `runEval` | The simplest preset over `runCampaign` — just score, no loop, no gate. The 80% "I want a scorecard" case. | `CampaignResult` |
 | `runProfileMatrix` | Factor the SAME scenarios across N agent **profiles** (models / prompt variants), with RunRecord stamping + a real-backend integrity guard. | `RunRecord[]` |
-| `runOptimization` | GENERATE: baseline → N generations of propose → measure → rank → promote. No release gate. | generations + winner |
+| `runOptimization` | GENERATE: measured or validated premeasured baseline → N generations of propose → measure → rank → promote. No release gate. | generations + winner |
 | `runImprovementLoop` | The release-gate shell around `runOptimization`: adds a held-out re-score + a promotion gate (+ optional auto-PR). | gate decision + winner |
 | `runEvalCampaign` | Inversion-of-control variant of `runCampaign` — the runner is handed a pre-wired trace/sink/emitter and integrity gating as a precondition. Use when you need full capture by construction. | `CampaignResult` + records |
 | `runAgentMatrix` | The bare N-axis cartesian scheduler with concurrency control. The layer beneath the eval surface — reach for it only when you need raw scheduling, not eval semantics. | cell results |

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@tangle-network/agent-eval",
-  "version": "0.120.2",
+  "version": "0.120.4",
   "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": {