Add API usage tracking and dynamic task reloading

Features:
- Usage tracking system (usage_tracker.py)
  - Tracks input/output tokens per API call
  - Calculates costs with support for cache pricing
  - Stores data in usage_data.json (gitignored)
  - Integrated into llm_interface.py

- Dynamic task scheduler reloading
  - Auto-detects YAML changes every 60s
  - No restart needed for new tasks
  - reload_tasks() method for manual refresh

- Example cost tracking scheduled task
  - Daily API usage report
  - Budget tracking ($5/month target)
  - Disabled by default in scheduled_tasks.yaml

Improvements:
- Fixed tool_use/tool_result pair splitting bug (CRITICAL)
- Added thread safety to agent.chat()
- Fixed N+1 query problem in hybrid search
- Optimized database batch queries
- Added conversation history pruning (50 messages max)

Updated .gitignore:
- Exclude user profiles (memory_workspace/users/*.md)
- Exclude usage data (usage_data.json)
- Exclude vector index (vectors.usearch)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>

test_agent_hybrid.py

@@ -0,0 +1,36 @@
+"""Test agent with hybrid search."""
+
+from agent import Agent
+
+print("Initializing agent with hybrid search...")
+agent = Agent(provider="claude")
+
+print("\n" + "="*60)
+print("TESTING AGENT MEMORY RECALL WITH HYBRID SEARCH")
+print("="*60)
+
+# Test 1: Semantic query - ask about cost in different words
+print("\n1. Testing semantic recall: 'How can I save money on API calls?'")
+print("-" * 60)
+response = agent.chat("How can I save money on API calls?", username="alice")
+print(response)
+
+# Test 2: Ask about birthday (semantic search should find personal info)
+print("\n" + "="*60)
+print("2. Testing semantic recall: 'What's my birthday?'")
+print("-" * 60)
+response = agent.chat("What's my birthday?", username="alice")
+print(response)
+
+# Test 3: Ask about specific technical detail
+print("\n" + "="*60)
+print("3. Testing keyword recall: 'What search technology are we using?'")
+print("-" * 60)
+response = agent.chat("What search technology are we using?", username="alice")
+print(response)
+
+print("\n" + "="*60)
+print("Test complete!")
+print("="*60)
+
+agent.shutdown()