feat(anthropic_token_limiter.py): add get_model_name_from_chat_model function to extract model name from BaseChatModel instances
style(anthropic_token_limiter.py): format code for better readability and consistency in function definitions and logging messages
fix(anthropic_token_limiter): refactor get_model_token_limit to use the new get_provider_and_model_for_agent_type function for cleaner code
test(anthropic_token_limiter): add unit tests for get_provider_and_model_for_agent_type and adjust_claude_37_token_limit functions to ensure correctness and coverage
feat(agent_utils.py): add model detection utilities for Claude 3.7 models
fix(agent_utils.py): update get_model_token_limit to handle Claude 3.7 token limits correctly
test(model_detection.py): add unit tests for model detection utilities
chore(agent_utils.py): remove deprecated is_anthropic_claude function and related tests
style(agent_utils.py): format code for better readability and consistency
- Introduce a new `Session` model to store information about each program run, including command line arguments and environment details.
- Implement a `Trajectory` model to log significant events and errors during execution, enhancing debugging and monitoring capabilities.
- Update various repository classes to support session and trajectory management, allowing for better tracking of user interactions and system behavior.
- Modify existing functions to record relevant events in the trajectory, ensuring comprehensive logging of application activities.
- Enhance error handling by logging errors to the trajectory, providing insights into failures and system performance.
feat(vsc): add initial setup for VS Code extension "ra-aid" with essential files and configurations
chore(vsc): create tasks.json for managing build and watch tasks in VS Code
chore(vsc): add .vscodeignore to exclude unnecessary files from the extension package
docs(vsc): create CHANGELOG.md to document changes and updates for the extension
docs(vsc): add README.md with instructions and information about the extension
feat(vsc): include esbuild.js for building and bundling the extension
chore(vsc): add eslint.config.mjs for TypeScript linting configuration
chore(vsc): create package.json with dependencies and scripts for the extension
feat(vsc): implement extension logic in src/extension.ts with webview support
test(vsc): add initial test suite in extension.test.ts for extension functionality
chore(vsc): create tsconfig.json for TypeScript compiler options
docs(vsc): add vsc-extension-quickstart.md for guidance on extension development
chore(anthropic_message_utils.py): remove debug print statements to clean up code and improve readability
chore(anthropic_token_limiter.py): remove debug print statements and replace with logging for better monitoring
test(test_anthropic_token_limiter.py): update tests to verify correct behavior of sonnet_35_state_modifier without patching internal logic
chore(anthropic_token_limiter.py): remove import of fix_anthropic_message_content as it is no longer needed
test: add unit tests for has_tool_use and is_tool_pair functions to ensure correct functionality
test: enhance test coverage for anthropic_trim_messages with tool use scenarios to validate message handling
fix(anthropic_message_utils.py): add warning in docstring for anthropic_trim_messages function to indicate incomplete implementation and clarify behavior
fix(anthropic_message_utils.py): ensure consistent formatting in conditional statements and improve readability of logical checks
fix(agent_utils.py): remove debug print statement for max_input_tokens to clean up code
refactor(anthropic_token_limiter.py): update state_modifier to use anthropic_trim_messages for better token management and maintain message structure
feat(anthropic_token_limiter.py): add convert_message_to_litellm_format function to standardize message format for litellm
fix(anthropic_token_limiter.py): update wrapped_token_counter to handle only BaseMessage objects and improve token counting logic
chore(anthropic_token_limiter.py): add debug print statements to track token counts before and after trimming messages
feat(main.py): add DEFAULT_MODEL constant to centralize model configuration
feat(main.py): enhance logging and error handling for better debugging
feat(main.py): implement state_modifier for managing token limits in agent state
feat(anthropic_token_limiter.py): create utilities for handling token limits with Anthropic models
feat(output.py): add print_messages_compact function for debugging message output
test(anthropic_token_limiter.py): add unit tests for token limit utilities and state management
refactor(agent_utils.py): import run_research_agent and run_web_research_agent from their respective modules to streamline the code structure and enhance clarity
This commit introduces a new `Trajectory` model to the database, which tracks the sequence of actions taken by agents, including tool executions and their results. The addition of the `TrajectoryRepository` allows for storing and retrieving these trajectories, enabling better analysis of agent behavior and debugging of issues.
Additionally, the commit refactors existing code to utilize the new repository and model, improving the overall architecture and maintainability of the codebase. This change is essential for enhancing the capabilities of the agent system and providing a more robust framework for future development.
AI Christianson
Ariel Frischer
Andrew
Andrew I. Christianson
Will