Enhanced the context window management system to properly account for tool definition tokens when trimming messages. The key changes include:
- Updated `trim_messages_for_context` function to accept `tool_tokens` parameter
- Modified token budget allocation logic to subtract tool tokens before message trimming
- Added detailed documentation explaining the token budget distribution between messages and tool definitions
- Implemented prioritized trimming strategy that preserves system messages and recent conversation history
- Added boundary case handling for scenarios where system messages or tools exceed available budget
The improvements ensure more accurate context window management by accounting for the ~1000-2000 tokens typically consumed by tool definitions that LangChain automatically includes in LLM requests.
- Add tiktoken as a required dependency for accurate token counting
- Update documentation with installation instructions and token counting strategy
- Improve logging to include tool definition token estimates
- Enhance error handling to fail fast when tiktoken is not available
- Update context manager to use tiktoken's cl100k_base encoding for GPT-4 compatibility
- Add `context_limit` as required field for LLM model configurations
- Add `context_strategy` as optional field with three trimming strategies
- Update API documentation with detailed examples for GPT-4o and Claude 3.5 Sonnet
- Clarify that context limit is specified in K tokens (thousands of tokens)
- Update example payloads to reflect current model versions and new fields
- Move AI chat API design document to gns3-copilot directory
- Add comprehensive HITL implementation plan with architecture and workflow
- Introduce human-in-the-loop confirmation for dangerous configuration commands
- Include state management, API endpoints, and frontend integration details
- Provide testing plan and deployment steps for the new feature
