Skip to content

armgit / ruflo

Public Imported from GitHub
0

🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated

Checkpoint: File edits

rUvb05d6c419393
diff --git a/v3/@claude-flow/cli/src/ruvector/q-learning-router.ts b/v3/@claude-flow/cli/src/ruvector/q-learning-router.ts
index 049472af7c..fd9d965a13 100644
--- a/v3/@claude-flow/cli/src/ruvector/q-learning-router.ts
+++ b/v3/@claude-flow/cli/src/ruvector/q-learning-router.ts
@@ -627,7 +627,7 @@ export class QLearningRouter {
}
/**
- * Reset the router
+ * Reset the router (clears all learned data)
*/
reset(): void {
this.qTable.clear();
@@ -635,6 +635,20 @@ export class QLearningRouter {
this.stepCount = 0;
this.updateCount = 0;
this.avgTDError = 0;
+
+ // Reset replay buffer
+ this.replayBuffer = [];
+ this.replayBufferIdx = 0;
+ this.totalExperiences = 0;
+
+ // Reset cache
+ this.routeCache.clear();
+ this.cacheOrder = [];
+ this.cacheHits = 0;
+ this.cacheMisses = 0;
+
+ // Reset feature hash cache
+ this.featureHashCache.clear();
}
/**