atlas/home-voice-agent/conversation/summarization

Conversation Summarization & Pruning

Manages conversation history by summarizing long conversations and enforcing retention policies.

Features

• Automatic Summarization: Summarize conversations when they exceed size limits
• Message Pruning: Keep recent messages, summarize older ones
• Retention Policies: Automatic deletion of old conversations
• Privacy Controls: User can delete specific sessions

Usage

Summarization

from conversation.summarization.summarizer import get_summarizer

summarizer = get_summarizer()

# Check if summarization needed
messages = session.get_messages()
if summarizer.should_summarize(len(messages), total_tokens=5000):
    summary = summarizer.summarize(messages, agent_type="family")
    
    # Prune messages, keeping recent ones
    pruned = summarizer.prune_messages(
        messages,
        keep_recent=10,
        summary=summary
    )
    
    # Update session with pruned messages
    session.update_messages(pruned)

Retention

from conversation.summarization.retention import get_retention_manager

retention = get_retention_manager()

# List old sessions
old_sessions = retention.list_old_sessions()

# Delete specific session
retention.delete_session("session-123")

# Clean up old sessions (if auto_delete enabled)
deleted_count = retention.cleanup_old_sessions()

# Enforce maximum session limit
deleted_count = retention.enforce_max_sessions()

Configuration

Summarization Thresholds

• Max Messages: 20 messages (default)
• Max Tokens: 4000 tokens (default)
• Keep Recent: 10 messages when pruning

Retention Policy

• Max Age: 90 days (default)
• Max Sessions: 1000 sessions (default)
• Auto Delete: False (default) - manual cleanup required

Integration

With Session Manager

The session manager should check for summarization when:

• Adding new messages
• Retrieving session for use
• Before saving session

With LLM

Summarization uses LLM to create concise summaries that preserve:

• Important facts and information
• Decisions made or actions taken
• User preferences or requests
• Tasks or reminders created
• Key context for future conversations

Privacy

• Users can delete specific sessions
• Automatic cleanup respects retention policy
• Summaries preserve context but reduce verbosity
• No external storage - all local

Future Enhancements

• LLM integration for better summaries
• Semantic search over conversation history
• Export conversations before deletion
• Configurable retention per session type
• Conversation analytics