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>

tools.py

@@ -124,6 +124,10 @@ def execute_tool(tool_name: str, tool_input: Dict[str, Any]) -> str:
         return f"Error executing {tool_name}: {str(e)}"
 
 
+# Maximum characters of tool output to return (prevents token explosion)
+_MAX_TOOL_OUTPUT = 5000
+
+
 def _read_file(file_path: str) -> str:
     """Read and return file contents."""
     path = Path(file_path)
@@ -132,6 +136,8 @@ def _read_file(file_path: str) -> str:
 
     try:
         content = path.read_text(encoding="utf-8")
+        if len(content) > _MAX_TOOL_OUTPUT:
+            content = content[:_MAX_TOOL_OUTPUT] + "\n... (file truncated)"
         return f"Content of {file_path}:\n\n{content}"
     except Exception as e:
         return f"Error reading file: {str(e)}"
@@ -210,9 +216,15 @@ def _run_command(command: str, working_dir: str) -> str:
 
         output = []
         if result.stdout:
-            output.append(f"STDOUT:\n{result.stdout}")
+            stdout = result.stdout
+            if len(stdout) > _MAX_TOOL_OUTPUT:
+                stdout = stdout[:_MAX_TOOL_OUTPUT] + "\n... (stdout truncated)"
+            output.append(f"STDOUT:\n{stdout}")
         if result.stderr:
-            output.append(f"STDERR:\n{result.stderr}")
+            stderr = result.stderr
+            if len(stderr) > _MAX_TOOL_OUTPUT:
+                stderr = stderr[:_MAX_TOOL_OUTPUT] + "\n... (stderr truncated)"
+            output.append(f"STDERR:\n{stderr}")
 
         status = f"Command exited with code {result.returncode}"
         if not output: