agentic-flow 1.7.3 → 1.7.4

package/scripts/test-agentdb.sh

@@ -0,0 +1,153 @@
+#!/bin/bash
+# AgentDB CLI Quick Test Script
+
+set -e
+
+echo "🧪 AgentDB CLI Testing Script"
+echo "=============================="
+echo ""
+
+# Set test database path
+export AGENTDB_PATH="./test-agentdb.db"
+
+# Clean up old test database
+if [ -f "$AGENTDB_PATH" ]; then
+  echo "🗑️  Removing old test database..."
+  rm "$AGENTDB_PATH"
+fi
+
+echo "📍 Current directory: $(pwd)"
+echo "💾 Database path: $AGENTDB_PATH"
+echo ""
+
+# Test 1: Help command
+echo "1️⃣  Testing help command..."
+echo ""
+node dist/agentdb/cli/agentdb-cli.js --help | head -20
+echo ""
+echo "✅ Help command works!"
+echo ""
+
+# Test 2: Store a successful episode
+echo "2️⃣  Storing a successful episode..."
+node dist/agentdb/cli/agentdb-cli.js reflexion store \
+  "test-session-1" \
+  "implement_authentication" \
+  0.95 \
+  true \
+  "Successfully implemented OAuth2 with JWT tokens" \
+  "User login requirement" \
+  "Working auth system with refresh tokens" \
+  1200 \
+  5000
+echo ""
+
+# Test 3: Store a failed episode
+echo "3️⃣  Storing a failed episode..."
+node dist/agentdb/cli/agentdb-cli.js reflexion store \
+  "test-session-1" \
+  "implement_authentication" \
+  0.35 \
+  false \
+  "Forgot to validate token expiration" \
+  "User login requirement" \
+  "Insecure auth system" \
+  800 \
+  3000
+echo ""
+
+# Test 4: Retrieve episodes
+echo "4️⃣  Retrieving episodes..."
+node dist/agentdb/cli/agentdb-cli.js reflexion retrieve \
+  "authentication" \
+  5 \
+  0.3
+echo ""
+
+# Test 5: Get critique summary
+echo "5️⃣  Getting critique summary (failures only)..."
+node dist/agentdb/cli/agentdb-cli.js reflexion critique-summary \
+  "authentication" \
+  true
+echo ""
+
+# Test 6: Create a skill
+echo "6️⃣  Creating a skill..."
+node dist/agentdb/cli/agentdb-cli.js skill create \
+  "jwt_authentication" \
+  "Generate and validate JWT tokens for user authentication" \
+  "function generateJWT(payload, secret) { return jwt.sign(payload, secret, { expiresIn: '1h' }); }"
+echo ""
+
+# Test 7: Search skills
+echo "7️⃣  Searching for skills..."
+node dist/agentdb/cli/agentdb-cli.js skill search \
+  "authentication" \
+  5
+echo ""
+
+# Test 8: Add a causal edge
+echo "8️⃣  Adding a causal edge..."
+node dist/agentdb/cli/agentdb-cli.js causal add-edge \
+  "add_unit_tests" \
+  "code_quality_score" \
+  0.25 \
+  0.95 \
+  100
+echo ""
+
+# Test 9: Create an experiment
+echo "9️⃣  Creating an A/B experiment..."
+node dist/agentdb/cli/agentdb-cli.js causal experiment create \
+  "test-coverage-vs-bugs" \
+  "test_coverage" \
+  "bug_rate"
+echo ""
+
+# Test 10: Add experiment observations
+echo "🔟 Adding experiment observations..."
+echo "   - Treatment group (high test coverage)..."
+node dist/agentdb/cli/agentdb-cli.js causal experiment add-observation \
+  1 \
+  true \
+  0.15 \
+  '{"coverage": 0.85, "lines": 5000}'
+echo "   - Control group (low test coverage)..."
+node dist/agentdb/cli/agentdb-cli.js causal experiment add-observation \
+  1 \
+  false \
+  0.35 \
+  '{"coverage": 0.45, "lines": 5000}'
+echo ""
+
+# Test 11: Calculate experiment uplift
+echo "1️⃣1️⃣  Calculating experiment uplift..."
+node dist/agentdb/cli/agentdb-cli.js causal experiment calculate 1
+echo ""
+
+# Test 12: Query causal edges
+echo "1️⃣2️⃣  Querying causal edges..."
+node dist/agentdb/cli/agentdb-cli.js causal query \
+  "" \
+  "" \
+  0.5 \
+  0.1 \
+  10
+echo ""
+
+# Test 13: Database stats
+echo "1️⃣3️⃣  Getting database statistics..."
+node dist/agentdb/cli/agentdb-cli.js db stats
+echo ""
+
+# Summary
+echo "=============================="
+echo "✅ All 13 tests completed successfully!"
+echo ""
+echo "📊 Test database created at: $AGENTDB_PATH"
+echo "📁 Size: $(du -h "$AGENTDB_PATH" | cut -f1)"
+echo ""
+echo "🔍 You can now explore the database or run individual commands:"
+echo "   node dist/agentdb/cli/agentdb-cli.js --help"
+echo "   AGENTDB_PATH=$AGENTDB_PATH node dist/agentdb/cli/agentdb-cli.js reflexion retrieve authentication 5"
+echo ""

package/.claude/skills/agentdb-memory-patterns/SKILL.md

@@ -1,166 +0,0 @@
----
-name: "AgentDB Memory Patterns"
-description: "Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful agents, chat systems, or intelligent assistants."
----
-
-# AgentDB Memory Patterns
-
-## What This Skill Does
-
-Provides memory management patterns for AI agents using AgentDB's persistent storage and ReasoningBank integration. Enables agents to remember conversations, learn from interactions, and maintain context across sessions.
-
-## Prerequisites
-
-- agentic-flow v1.5.11+ or agentdb v1.0.4+
-- Node.js 18+
-- Understanding of agent architectures
-
-## Quick Start
-
-```typescript
-import { AgentDB, MemoryManager } from 'agentdb';
-
-// Initialize memory system
-const memory = new MemoryManager({
-  agentId: 'assistant-001',
-  persist: true,
-  ttl: 3600 * 24 * 30 // 30 days
-});
-
-// Store interaction
-await memory.store({
-  role: 'user',
-  content: 'What is the capital of France?',
-  timestamp: Date.now()
-});
-
-await memory.store({
-  role: 'assistant',
-  content: 'The capital of France is Paris.',
-  timestamp: Date.now()
-});
-
-// Retrieve context
-const context = await memory.getRecentContext({ limit: 10 });
-```
-
-## Memory Patterns
-
-### 1. Session Memory
-```typescript
-class SessionMemory {
-  async storeMessage(role: string, content: string) {
-    return await db.storeMemory({
-      sessionId: this.sessionId,
-      role,
-      content,
-      timestamp: Date.now()
-    });
-  }
-
-  async getSessionHistory(limit = 20) {
-    return await db.query({
-      filters: { sessionId: this.sessionId },
-      orderBy: 'timestamp',
-      limit
-    });
-  }
-}
-```
-
-### 2. Long-Term Memory
-```typescript
-// Store important facts
-await db.storeFact({
-  category: 'user_preference',
-  key: 'language',
-  value: 'English',
-  confidence: 1.0,
-  source: 'explicit'
-});
-
-// Retrieve facts
-const prefs = await db.getFacts({
-  category: 'user_preference'
-});
-```
-
-### 3. Pattern Learning
-```typescript
-// Learn from successful interactions
-await db.storePattern({
-  trigger: 'user_asks_time',
-  response: 'provide_formatted_time',
-  success: true,
-  context: { timezone: 'UTC' }
-});
-
-// Apply learned patterns
-const pattern = await db.matchPattern(currentContext);
-```
-
-## Advanced Patterns
-
-### Hierarchical Memory
-```typescript
-// Organize memory in hierarchy
-await memory.organize({
-  immediate: recentMessages,    // Last 10 messages
-  shortTerm: sessionContext,    // Current session
-  longTerm: importantFacts,     // Persistent facts
-  semantic: embeddedKnowledge   // Vector search
-});
-```
-
-### Memory Consolidation
-```typescript
-// Periodically consolidate memories
-await memory.consolidate({
-  strategy: 'importance',       // Keep important memories
-  maxSize: 10000,              // Size limit
-  minScore: 0.5                // Relevance threshold
-});
-```
-
-## Integration with ReasoningBank
-
-```typescript
-import { ReasoningBank } from 'agentic-flow/reasoningbank';
-
-// Connect memory to reasoning
-const rb = new ReasoningBank({
-  memory: memory,
-  learningRate: 0.1
-});
-
-// Learn from outcomes
-await rb.recordOutcome({
-  task: 'summarize_document',
-  approach: 'extractive',
-  success: true,
-  metrics: { accuracy: 0.95 }
-});
-
-// Get optimal strategy
-const strategy = await rb.getOptimalStrategy('summarize_document');
-```
-
-## Best Practices
-
-1. **Prune regularly**: Remove outdated or low-value memories
-2. **Use TTL**: Set time-to-live for ephemeral data
-3. **Index metadata**: Enable fast filtering by sessionId, userId
-4. **Compress old data**: Archive infrequently accessed memories
-
-## Troubleshooting
-
-### Issue: Memory growing too large
-**Solution**: Enable auto-pruning or set TTL values
-
-### Issue: Context not relevant
-**Solution**: Use vector search for semantic memory retrieval
-
-## Learn More
-
-- Memory API: packages/agentdb/docs/memory-api.md
-- ReasoningBank: agentic-flow/src/reasoningbank/README.md

package/.claude/skills/agentdb-vector-search/SKILL.md

@@ -1,126 +0,0 @@
----
-name: "AgentDB Vector Search"
-description: "Implement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware querying. Use when building RAG systems, semantic search engines, or intelligent knowledge bases."
----
-
-# AgentDB Vector Search
-
-## What This Skill Does
-
-Implements vector-based semantic search using AgentDB's high-performance vector database with 150x-12,500x faster operations than traditional solutions. Enables similarity search, hybrid search (vector + metadata), and real-time embedding generation.
-
-## Prerequisites
-
-- agentic-flow v1.5.11+ or agentdb v1.0.4+
-- Node.js 18+
-- OpenAI API key (for embeddings) or custom embedding model
-
-## Quick Start
-
-```typescript
-import { AgentDB } from 'agentdb';
-
-// Initialize AgentDB with vector support
-const db = new AgentDB({
-  persist: true,
-  vectorDimensions: 1536, // OpenAI ada-002 dimensions
-  enableVectorIndex: true
-});
-
-// Store documents with vectors
-await db.storeMemory({
-  text: "The quantum computer achieved 100 qubits",
-  metadata: { category: "technology", date: "2025-01-15" },
-  embedding: await generateEmbedding(text) // Your embedding function
-});
-
-// Semantic search
-const results = await db.searchSimilar(
-  queryEmbedding,
-  { limit: 10, threshold: 0.7 }
-);
-```
-
-## Core Features
-
-### 1. Vector Storage
-```typescript
-// Store with automatic embedding
-await db.storeWithEmbedding({
-  content: "Your document text",
-  metadata: { source: "docs", page: 42 }
-});
-```
-
-### 2. Similarity Search
-```typescript
-// Find similar documents
-const similar = await db.findSimilar("quantum computing", {
-  limit: 5,
-  minScore: 0.75
-});
-```
-
-### 3. Hybrid Search (Vector + Metadata)
-```typescript
-// Combine vector similarity with metadata filtering
-const results = await db.hybridSearch({
-  query: "machine learning models",
-  filters: {
-    category: "research",
-    date: { $gte: "2024-01-01" }
-  },
-  limit: 20
-});
-```
-
-## Advanced Usage
-
-### RAG (Retrieval Augmented Generation)
-```typescript
-// Build RAG pipeline
-async function ragQuery(question: string) {
-  // 1. Get relevant context
-  const context = await db.searchSimilar(
-    await embed(question),
-    { limit: 5, threshold: 0.7 }
-  );
-
-  // 2. Generate answer with context
-  const prompt = `Context: ${context.map(c => c.text).join('\n')}
-Question: ${question}`;
-
-  return await llm.generate(prompt);
-}
-```
-
-### Batch Operations
-```typescript
-// Efficient batch storage
-await db.batchStore(documents.map(doc => ({
-  text: doc.content,
-  embedding: doc.vector,
-  metadata: doc.meta
-})));
-```
-
-## Performance Tips
-
-- **Indexing**: Enable vector index for 10-100x faster searches
-- **Batch Size**: Use batch operations for 1000+ documents
-- **Dimensions**: Match embedding model (1536 for OpenAI ada-002)
-- **Threshold**: Start at 0.7 for quality results
-
-## Troubleshooting
-
-### Issue: Slow search performance
-**Solution**: Enable vector index: `enableVectorIndex: true`
-
-### Issue: Poor relevance
-**Solution**: Adjust similarity threshold or use hybrid search
-
-## Learn More
-
-- AgentDB Docs: packages/agentdb/README.md
-- Vector DB API: packages/agentdb/docs/vector-api.md
-- Performance Guide: docs/agentdb/performance.md

package/.claude/skills/agentic-flow/agentdb-memory-patterns/SKILL.md

@@ -1,166 +0,0 @@
----
-name: "AgentDB Memory Patterns"
-description: "Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful agents, chat systems, or intelligent assistants."
----
-
-# AgentDB Memory Patterns
-
-## What This Skill Does
-
-Provides memory management patterns for AI agents using AgentDB's persistent storage and ReasoningBank integration. Enables agents to remember conversations, learn from interactions, and maintain context across sessions.
-
-## Prerequisites
-
-- agentic-flow v1.5.11+ or agentdb v1.0.4+
-- Node.js 18+
-- Understanding of agent architectures
-
-## Quick Start
-
-```typescript
-import { AgentDB, MemoryManager } from 'agentdb';
-
-// Initialize memory system
-const memory = new MemoryManager({
-  agentId: 'assistant-001',
-  persist: true,
-  ttl: 3600 * 24 * 30 // 30 days
-});
-
-// Store interaction
-await memory.store({
-  role: 'user',
-  content: 'What is the capital of France?',
-  timestamp: Date.now()
-});
-
-await memory.store({
-  role: 'assistant',
-  content: 'The capital of France is Paris.',
-  timestamp: Date.now()
-});
-
-// Retrieve context
-const context = await memory.getRecentContext({ limit: 10 });
-```
-
-## Memory Patterns
-
-### 1. Session Memory
-```typescript
-class SessionMemory {
-  async storeMessage(role: string, content: string) {
-    return await db.storeMemory({
-      sessionId: this.sessionId,
-      role,
-      content,
-      timestamp: Date.now()
-    });
-  }
-
-  async getSessionHistory(limit = 20) {
-    return await db.query({
-      filters: { sessionId: this.sessionId },
-      orderBy: 'timestamp',
-      limit
-    });
-  }
-}
-```
-
-### 2. Long-Term Memory
-```typescript
-// Store important facts
-await db.storeFact({
-  category: 'user_preference',
-  key: 'language',
-  value: 'English',
-  confidence: 1.0,
-  source: 'explicit'
-});
-
-// Retrieve facts
-const prefs = await db.getFacts({
-  category: 'user_preference'
-});
-```
-
-### 3. Pattern Learning
-```typescript
-// Learn from successful interactions
-await db.storePattern({
-  trigger: 'user_asks_time',
-  response: 'provide_formatted_time',
-  success: true,
-  context: { timezone: 'UTC' }
-});
-
-// Apply learned patterns
-const pattern = await db.matchPattern(currentContext);
-```
-
-## Advanced Patterns
-
-### Hierarchical Memory
-```typescript
-// Organize memory in hierarchy
-await memory.organize({
-  immediate: recentMessages,    // Last 10 messages
-  shortTerm: sessionContext,    // Current session
-  longTerm: importantFacts,     // Persistent facts
-  semantic: embeddedKnowledge   // Vector search
-});
-```
-
-### Memory Consolidation
-```typescript
-// Periodically consolidate memories
-await memory.consolidate({
-  strategy: 'importance',       // Keep important memories
-  maxSize: 10000,              // Size limit
-  minScore: 0.5                // Relevance threshold
-});
-```
-
-## Integration with ReasoningBank
-
-```typescript
-import { ReasoningBank } from 'agentic-flow/reasoningbank';
-
-// Connect memory to reasoning
-const rb = new ReasoningBank({
-  memory: memory,
-  learningRate: 0.1
-});
-
-// Learn from outcomes
-await rb.recordOutcome({
-  task: 'summarize_document',
-  approach: 'extractive',
-  success: true,
-  metrics: { accuracy: 0.95 }
-});
-
-// Get optimal strategy
-const strategy = await rb.getOptimalStrategy('summarize_document');
-```
-
-## Best Practices
-
-1. **Prune regularly**: Remove outdated or low-value memories
-2. **Use TTL**: Set time-to-live for ephemeral data
-3. **Index metadata**: Enable fast filtering by sessionId, userId
-4. **Compress old data**: Archive infrequently accessed memories
-
-## Troubleshooting
-
-### Issue: Memory growing too large
-**Solution**: Enable auto-pruning or set TTL values
-
-### Issue: Context not relevant
-**Solution**: Use vector search for semantic memory retrieval
-
-## Learn More
-
-- Memory API: packages/agentdb/docs/memory-api.md
-- ReasoningBank: agentic-flow/src/reasoningbank/README.md