feat(skill-learning): produce replay eval reports

app-instance/backend/beaver/skills/learning/pipeline.py

@@ -8,6 +8,7 @@ from beaver.engine.providers import ProviderBundle
 from beaver.memory.skills import SkillDraftEvalReport, SkillDraftSafetyReport, SkillLearningCandidate, SkillLearningStore
 from beaver.skills.drafts import DraftService
 from beaver.skills.learning.eval import SkillDraftEvaluator
+from beaver.skills.learning.replay import ReplayRunner
 from beaver.skills.learning.service import SkillLearningService
 from beaver.skills.learning.safety import SkillDraftSafetyChecker
 from beaver.skills.publisher import SkillPublisher
@@ -285,11 +286,17 @@ class SkillLearningPipelineService:
         draft_id: str,
         *,
         provider_bundle: ProviderBundle | None,
+        replay_runner: ReplayRunner | None = None,
     ) -> SkillDraftEvalReport:
         draft = self.get_draft(skill_name, draft_id)
         candidate = self.get_candidate(candidate_id)
         evaluator = self.evaluator or SkillDraftEvaluator(self.learning_service.run_store)
-        report = await evaluator.evaluate(candidate=candidate, draft=draft, provider_bundle=provider_bundle)
+        report = await evaluator.evaluate(
+            candidate=candidate,
+            draft=draft,
+            provider_bundle=provider_bundle,
+            replay_runner=replay_runner,
+        )
         self.learning_store.write_eval_report(report)
         if report.status == "skipped_provider_unavailable":
             status = "draft_ready"