@tangle-network/agent-runtime 0.74.0 → 0.75.1

package/dist/intelligence.d.ts

@@ -1,4 +1,4 @@
-import { c as LoopTraceEvent } from './types-YimN9PQP.js';
+import { c as LoopTraceEvent } from './types-B-jWSfcu.js';
 import { AgentProfileMcpServer } from '@tangle-network/agent-interface';
 import { T as ToolSpec } from './router-client-C7kp_ECN.js';
 import '@tangle-network/agent-eval';

package/dist/lifecycle.d.ts

@@ -632,9 +632,10 @@ declare function runLifecycle(opts: RunLifecycleOptions): Promise<RunLifecycleRe
  *      reflection over the trace produces the first draft.
  *
  *   2. REFINE — take the distilled draft and improve its wording/structure. The
- *      production `refine` wraps agent-eval's skill optimizer (`runSkillOpt`).
- *      Refinement is optional: with no `refine`, the distilled draft IS the
- *      candidate.
+ *      production `refine` drives agent-eval's `skillOptProposer` (the uniform
+ *      skill-surface proposer factory from `@tangle-network/agent-eval/campaign`,
+ *      the same source as `gepaProposer` for the prompt surface). Refinement is
+ *      optional: with no `refine`, the distilled draft IS the candidate.
  *
  * Both steps are INJECTED seams, not hardcoded engines — per the §1.5 law, the
  * generator AUTHORS a profile piece; it does not embed a specific LLM loop. That
@@ -661,8 +662,8 @@ interface SkillDraft {
 type DistillSkills = (ctx: GenerateContext) => Promise<SkillDraft[]> | SkillDraft[];
 /**
  * REFINE — improve ONE distilled draft (wording, structure, examples). The
- * production implementation wraps `runSkillOpt`. Returns the refined draft; when
- * omitted from `skillGenerator`, the distilled draft is used as-is.
+ * production implementation drives `skillOptProposer`. Returns the refined draft;
+ * when omitted from `skillGenerator`, the distilled draft is used as-is.
  */
 type RefineSkill = (draft: SkillDraft) => Promise<SkillDraft> | SkillDraft;
 interface SkillGeneratorOptions {
@@ -676,10 +677,10 @@ interface SkillGeneratorOptions {
  * from history, then (optionally) refines them, and emits each as a `skill`
  * artifact carrying an inline `SKILL.md` resource ref.
  *
- * @example Production wiring (distill = LLM reflection, refine = skillOpt):
+ * @example Production wiring (distill = LLM reflection, refine = skillOptProposer):
  *   skillGenerator({
  *     distill: reflectiveDistill,   // creates the draft from traces
- *     refine: skillOptRefine,       // optimizes the draft
+ *     refine: skillOptRefine,       // optimizes the draft via skillOptProposer
  *   })
  */
 declare function skillGenerator(opts: SkillGeneratorOptions): CandidateGenerator<'skill'>;

package/dist/lifecycle.js

@@ -279,9 +279,9 @@ function recordsOf(runs, arm, artifactId) {
 // src/lifecycle/prompt-generator.ts
 import { callLlmJson } from "@tangle-network/agent-eval";
 import {
+  gepaProposer,
   isProposedCandidate
 } from "@tangle-network/agent-eval/campaign";
-import { gepaProposer } from "@tangle-network/agent-eval/contract";
 function promptGenerator(opts) {
   if (!opts.refine && !opts.authorDiverseSeeds) {
     throw new TypeError(