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

Merge PR #3462: fix(learning): create skills from validated task patterns

ruv580980a0fe80
diff --cc v3/@claude-flow/cli/src/memory/memory-bridge.ts
index 574bc7c9ca,52d50e096d..b37ed21356
--- a/v3/@claude-flow/cli/src/memory/memory-bridge.ts
+++ b/v3/@claude-flow/cli/src/memory/memory-bridge.ts
@@@ -19,9 -19,8 +19,10 @@@
import * as path from 'path';
import * as crypto from 'crypto';
+import { realpathSync } from 'node:fs';
import { createRequire } from 'node:module';
+import { AsyncLocalStorage } from 'node:async_hooks';
+ import { validateFeedbackPatterns } from './feedback-patterns.js';
// ===== Lazy registry cache, keyed by database path =====
@@@ -2493,7 -2421,7 +2496,8 @@@ export async function bridgeRecordFeedb
parentAgentId?: string;
depth?: number;
}): Promise<{ success: boolean; controller: string; updated: number } | null> {
+ if (!operationContext.getStore()?.active) return withBridgeOperation(() => bridgeRecordFeedback(options));
+ const patterns = validateFeedbackPatterns(options.patterns);
const registry = await getRegistry(options.dbPath);
if (!registry) return null;