32fcf914ed
* feat(agent_utils.py): add get_model_token_limit function to retrieve token limits for models based on provider and model name feat(models_tokens.py): create models_tokens module to store token limits for various models and providers test(agent_utils.py): implement unit tests for get_model_token_limit and create_agent functions to ensure correct behavior and error handling * test: Add unit tests for token limiting and agent creation functionality * fix: Correct indentation and add missing test function for error handling * fix: Update test assertion to use messages_modifier instead of state_modifier * feat(agent_utils.py): add limit_tokens function to manage message token limits and preserve system message fix(agent_utils.py): update get_model_token_limit to handle exceptions and return None on error fix(ciayn_agent.py): set default max_tokens to DEFAULT_TOKEN_LIMIT in CiaynAgent initialization feat(models_tokens.py): define DEFAULT_TOKEN_LIMIT for consistent token limit management across agents style(agent_utils.py): improve code formatting and consistency in function definitions and comments style(agent_utils.py): refactor imports for better organization and readability fix(test_agent_utils.py): correct test assertion to use state_modifier instead of messages_modifier for create_agent function * refactor(agent_utils.py): improve docstring clarity and formatting for limit_tokens function to enhance readability refactor(test_agent_utils.py): format test assertions for consistency and readability in agent creation tests * feat: Update limit_tokens function to support Dict type for state parameter * feat: Update limit_tokens to handle both list and dict input types * refactor: Extract duplicate token trimming logic into helper function * refactor: Rename and update message trimming functions for clarity * refactor: Extract agent kwargs logic into a helper method for reuse * refactor: Rename _build_agent_kwargs to build_agent_kwargs for clarity * fix: Ensure state_modifier is passed correctly for agent creation * test: Add tests for create_agent token limiting configuration * refactor: Simplify CiaynAgent instantiation to only use max_tokens parameter * refactor: Remove is_react_agent parameter from build_agent_kwargs function * test: Fix test assertions for state_modifier in agent creation tests * fix: Update agent creation to handle checkpointer and simplify tests * test: Remove unnecessary assertions from agent creation test * feat: Implement token limiting configuration for create_agent function * refactor: Remove unused model info and token limit retrieval code * test: Fix assertion errors in agent creation tests and update state_modifier handling * test: Remove commented-out code and clarify assertions in tests * test: Fix assertion in test_create_agent_anthropic_token_limiting_disabled * feat(main.py): add --limit-tokens argument to control token limiting in agent state fix(main.py): include limit_tokens in configuration to ensure proper state management * test: Refactor agent creation tests for improved readability and consistency * test: Modify error handling in create_agent test to use side_effect on get_model_token_limit * test: Improve error handling in create_agent test to verify fallback behavior * test: Trigger exception on get_model_token_limit in error handling test * refactor(agent_utils.py): remove unused config parameter from create_agent function to simplify the function signature fix(agent_utils.py): ensure config is always retrieved from _global_memory with a default value to prevent potential errors test(tests/test_agent_utils.py): remove outdated test for create_agent error handling to clean up the test suite * feat: Add debug print for agent_kwargs in create_agent function * refactor: Replace lambda with inner function for state_modifier in agent_utils * refactor: Simplify limit_tokens function to return only message sequences * feat: Add debug print statements to show token trimming details in trim_messages * PAIN * feat(main.py): add debug print statement for args.chat to assist in troubleshooting chat mode feat(agent_utils.py): implement estimate_messages_tokens function to calculate total tokens in messages refactor(agent_utils.py): replace token counting logic in trim_messages_with_removal with estimate_messages_tokens for clarity refactor(agent_utils.py): modify state_modifier to accept model and max_tokens parameters for better flexibility refactor(agent_utils.py): update build_agent_kwargs to pass model to state_modifier for improved functionality * feat: Add .direnvrc to manage Python virtual environment activation * refactor: Update state_modifier to handle first message token count and trim messages * chore: remove unused .direnvrc file to clean up project structure feat: add .envrc to .gitignore to prevent environment configuration file from being tracked fix: update help text for --disable-limit-tokens argument for clarity refactor: clean up imports in agent_utils.py for better readability refactor: remove unused functions and comments in agent_utils.py to streamline code test: add unit tests for state_modifier function to ensure correct message trimming behavior * refactor: Remove commented-out code in create_agent function * feat: Add is_anthropic_claude method to check provider and model name * fix: Correct search/replace block to match existing lines in agent_utils.py * fix(main.py): update help text for --disable-limit-tokens argument to clarify it applies to react agents refactor(agent_utils.py): streamline token limit retrieval and improve readability by removing redundant checks and restructuring code refactor(agent_utils.py): modify build_agent_kwargs to use is_anthropic_claude for clarity and maintainability * test: Update tests to pass config argument to get_model_token_limit() * refactor(agent_utils.py): remove unnecessary print statements and improve function signatures for clarity refactor(agent_utils.py): consolidate provider and model_name retrieval into config parameter for better maintainability * test: Remove redundant token limiting tests from agent creation logic * test: Refactor test_state_modifier to use mock_messages fixture * test(tests): update test description for clarity on state_modifier behavior and use mock_messages for assertions to ensure consistency * refactor(agent_utils.py): simplify token limit retrieval by removing unnecessary variable initialization and defaulting to None in get method * chore(main.py): remove debug print statement for args.chat to clean up output |
||
|---|---|---|
| .. | ||
| agents | ||
| console | ||
| proc | ||
| tests | ||
| text | ||
| tools | ||
| __init__.py | ||
| __main__.py | ||
| __version__.py | ||
| agent_utils.py | ||
| config.py | ||
| dependencies.py | ||
| env.py | ||
| exceptions.py | ||
| file_listing.py | ||
| llm.py | ||
| logging_config.py | ||
| models_tokens.py | ||
| project_info.py | ||
| project_state.py | ||
| prompts.py | ||
| provider_strategy.py | ||
| tool_configs.py | ||