Initial commit: Claude Code Project Tracker

Add comprehensive development intelligence system that tracks:
- Development sessions with automatic start/stop
- Full conversation history with semantic search
- Tool usage and file operation analytics
- Think time and engagement analysis
- Git activity correlation
- Learning pattern recognition
- Productivity insights and metrics

Features:
- FastAPI backend with SQLite database
- Modern web dashboard with interactive charts
- Claude Code hook integration for automatic tracking
- Comprehensive test suite with 100+ tests
- Complete API documentation (OpenAPI/Swagger)
- Privacy-first design with local data storage

🤖 Generated with [Claude Code](https://claude.ai/code)

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

app/models/conversation.py

@@ -0,0 +1,118 @@
+"""
+Conversation model for tracking dialogue between user and Claude.
+"""
+
+from datetime import datetime
+from typing import Optional, List, Dict, Any
+from sqlalchemy import String, Text, Integer, DateTime, JSON, ForeignKey
+from sqlalchemy.orm import Mapped, mapped_column, relationship
+from sqlalchemy.sql import func
+
+from .base import Base, TimestampMixin
+
+
+class Conversation(Base, TimestampMixin):
+    """
+    Represents a conversation exchange between user and Claude.
+    
+    Each conversation entry captures either a user prompt or Claude's response,
+    along with context about tools used and files affected.
+    """
+    
+    __tablename__ = "conversations"
+    
+    # Primary key
+    id: Mapped[int] = mapped_column(primary_key=True)
+    
+    # Foreign key to session
+    session_id: Mapped[int] = mapped_column(ForeignKey("sessions.id"), nullable=False, index=True)
+    
+    # Timing
+    timestamp: Mapped[datetime] = mapped_column(
+        DateTime(timezone=True),
+        nullable=False,
+        default=func.now(),
+        index=True
+    )
+    
+    # Conversation content
+    user_prompt: Mapped[Optional[str]] = mapped_column(Text, nullable=True)
+    claude_response: Mapped[Optional[str]] = mapped_column(Text, nullable=True)
+    
+    # Context and metadata
+    tools_used: Mapped[Optional[List[str]]] = mapped_column(JSON, nullable=True)
+    files_affected: Mapped[Optional[List[str]]] = mapped_column(JSON, nullable=True)
+    context: Mapped[Optional[Dict[str, Any]]] = mapped_column(JSON, nullable=True)
+    
+    # Token estimates for analysis
+    tokens_input: Mapped[Optional[int]] = mapped_column(Integer, nullable=True)
+    tokens_output: Mapped[Optional[int]] = mapped_column(Integer, nullable=True)
+    
+    # Exchange type for categorization
+    exchange_type: Mapped[str] = mapped_column(String(50), nullable=False)  # user_prompt, claude_response
+    
+    # Relationships
+    session: Mapped["Session"] = relationship("Session", back_populates="conversations")
+    
+    def __repr__(self) -> str:
+        content_preview = ""
+        if self.user_prompt:
+            content_preview = self.user_prompt[:50] + "..." if len(self.user_prompt) > 50 else self.user_prompt
+        elif self.claude_response:
+            content_preview = self.claude_response[:50] + "..." if len(self.claude_response) > 50 else self.claude_response
+            
+        return f"<Conversation(id={self.id}, type='{self.exchange_type}', content='{content_preview}')>"
+    
+    @property
+    def is_user_prompt(self) -> bool:
+        """Check if this is a user prompt."""
+        return self.exchange_type == "user_prompt"
+    
+    @property
+    def is_claude_response(self) -> bool:
+        """Check if this is a Claude response."""
+        return self.exchange_type == "claude_response"
+    
+    @property
+    def content_length(self) -> int:
+        """Get the total character length of the conversation content."""
+        user_length = len(self.user_prompt) if self.user_prompt else 0
+        claude_length = len(self.claude_response) if self.claude_response else 0
+        return user_length + claude_length
+    
+    @property
+    def estimated_tokens(self) -> int:
+        """Estimate total tokens in this conversation exchange."""
+        if self.tokens_input and self.tokens_output:
+            return self.tokens_input + self.tokens_output
+        
+        # Rough estimation: ~4 characters per token
+        return self.content_length // 4
+    
+    def get_intent_category(self) -> Optional[str]:
+        """Extract intent category from context if available."""
+        if self.context and "intent" in self.context:
+            return self.context["intent"]
+        return None
+    
+    def get_complexity_level(self) -> Optional[str]:
+        """Extract complexity level from context if available."""
+        if self.context and "complexity" in self.context:
+            return self.context["complexity"]
+        return None
+    
+    def has_file_operations(self) -> bool:
+        """Check if this conversation involved file operations."""
+        if not self.tools_used:
+            return False
+        
+        file_tools = {"Edit", "Write", "Read"}
+        return any(tool in file_tools for tool in self.tools_used)
+    
+    def has_code_execution(self) -> bool:
+        """Check if this conversation involved code execution."""
+        if not self.tools_used:
+            return False
+        
+        execution_tools = {"Bash", "Task"}
+        return any(tool in execution_tools for tool in self.tools_used)