Commit Graph

70 Commits

Author SHA1 Message Date
AI Christianson be0b566edb fix ERROR - Error getting expert guidance for planning: module 'ra_aid.agent_utils' has no attribute 'process_thinking_content' 2025-03-13 07:11:32 -04:00
AI Christianson ae9cf5021b record trajectory at all steps 2025-03-11 11:01:05 -04:00
AI Christianson 5d899d3d13 trajectory 2025-03-11 08:56:12 -04:00
AI Christianson 909825bf1b refactor: extract get_most_recent_id 2025-03-10 19:37:39 -04:00
AI Christianson a18998be0d add project info to reasoning assist prompts 2025-03-10 18:01:56 -04:00
AI Christianson b5e4c64042 improve prompts; make list_directory more resilient 2025-03-10 16:41:09 -04:00
AI Christianson e81421a95a improve prompts 2025-03-10 15:30:22 -04:00
AI Christianson c98c107ce3 use expert model for reasoning assisted mode 2025-03-10 14:58:47 -04:00
AI Christianson 51fa86b5c4 refactor: extract run_task_implementation_agent 2025-03-10 14:44:34 -04:00
AI Christianson d8dcc8ca86 refactor: extract run_planning_agent 2025-03-10 14:19:06 -04:00
AI Christianson 4f2c36b958 refactor: extract research agent 2025-03-10 13:33:00 -04:00
AI Christianson 77856bfa0c set agent_should_exit in gc agents 2025-03-07 10:35:02 -05:00
AI Christianson 5bd8c76a22 config repository 2025-03-04 21:01:08 -05:00
AI Christianson 035544c77a research notes repo 2025-03-03 22:31:51 -05:00
AI Christianson 5202d2e7f3 use context vars for human input repo 2025-03-03 17:58:55 -05:00
AI Christianson 36e4004db0 use context vars for key facts repo 2025-03-03 16:58:03 -05:00
AI Christianson 9a69bb173e do not gc key facts/snippets associated with current human input 2025-03-02 20:27:52 -05:00
AI Christianson d4353b1824 localize delete_key_snippets with gc agent 2025-03-02 19:56:42 -05:00
AI Christianson 332cbec826 key snippet gc 2025-03-02 19:41:48 -05:00
AI Christianson 8819f463a1 fix output 2025-03-02 15:28:32 -05:00
AI Christianson 7ec6535eef gc fixups 2025-03-02 15:18:16 -05:00
AI Christianson 2418506d7e gc status panels 2025-03-02 15:04:25 -05:00
AI Christianson 1855cc3252 cleaner -> gc 2025-03-02 14:44:39 -05:00
AI Christianson 14c9bdfdc7 key facts gc 2025-03-02 14:37:42 -05:00
AI Christianson 17ab6d2a50 refactor: agents/ -> agent_backends/ 2025-03-02 14:16:15 -05:00
AI Christianson fd1025f74c refactor prompts 2025-03-02 13:47:39 -05:00
Ariel Frischer 81354df48b fix(ciayn_agent.py): correct spelling of "execute" in error message for clarity
refactor(ciayn_agent.py): improve error handling by chaining exceptions for better debugging
docs(output.py): update docstring to include agent_type parameter for clarity on agent behavior
2025-02-14 14:45:33 -08:00
Ariel Frischer f65918cfd3 refactor(ciayn_agent.py): remove unused variables tool_failure_current_provider and tool_failure_current_model to clean up the code and improve readability 2025-02-14 14:11:33 -08:00
Ariel Frischer 27400d6225 feat(ciayn_agent.py): add fallback_fixed_msg to inform users about fallback tool handling
fix(ciayn_agent.py): ensure error message is logged in chat history when fallback response is empty
2025-02-14 13:54:06 -08:00
Ariel Frischer f3a5ce6d8e chore(ciayn_agent.py): remove debug logging for extracted tool call to clean up logs and reduce verbosity 2025-02-14 13:50:43 -08:00
Ariel Frischer 0df5d43333 feat(main.py): import models_params and set default temperature for models that support it to improve user experience
fix(ciayn_agent.py): update fallback tool error messages to use FallbackToolExecutionError for better error handling
fix(config.py): remove unnecessary blank line to maintain code style consistency
fix(fallback_handler.py): raise FallbackToolExecutionError for better error clarity when tools are not found
fix(llm.py): set default temperature to 0.7 and notify user when not provided for models that support it
test(test_llm.py): update tests to check for default temperature behavior and improve error messages for unsupported providers
2025-02-14 13:50:32 -08:00
Ariel Frischer d5e2e0a9a0 refactor(agent_utils.py, ciayn_agent.py): remove unused import cpm to clean up code and improve readability
style(tests): format code for better readability and consistency in test files
test(tests): update assertions and test cases for better clarity and maintainability
2025-02-14 13:04:41 -08:00
Ariel Frischer efec91579a refactor(ciayn_agent.py): remove unnecessary raise statement and debug log to clean up code 2025-02-13 20:09:47 -08:00
Ariel Frischer 15ce534f8f feat(agent_utils.py): add debug print for config to assist in troubleshooting
feat(ciayn_agent.py): pass config to CiaynAgent for improved functionality
fix(ciayn_agent.py): handle tool execution errors more gracefully with msg_list
feat(fallback_handler.py): enhance handle_failure method to utilize msg_list for better context
feat(fallback_handler.py): implement init_msg_list to manage message history effectively
test(test_fallback_handler.py): add unit tests for init_msg_list to ensure correct behavior
2025-02-13 20:09:21 -08:00
Ariel Frischer ac13ce746a feat(agent_utils.py): add cpm function import for enhanced logging in run_agent_with_retry
fix(agent_utils.py): set default value of fallback_handler to None in run_agent_with_retry
chore(ciayn_agent.py): comment out debug log for generated code to reduce verbosity
fix(fallback_handler.py): change fallback_enabled config key to experimental_fallback_handler for better clarity
refactor(test_ciayn_agent.py): update invoke method in DummyModel to return AIMessage instead of a custom Response class
test(test_ciayn_agent.py): comment out test_retry_logic_with_failure_recovery for future implementation and focus on existing tests
2025-02-13 17:57:27 -08:00
Ariel Frischer 2420dfbb4f refactor(agent_utils.py): extract fallback handler initialization into a separate function to improve code readability and maintainability
fix(ciayn_agent.py): reset fallback handler after executing tool to ensure proper state management
style(fallback_handler.py): format method signature for better readability
2025-02-13 16:53:22 -08:00
Ariel Frischer 63e48db9de feat(agent_utils.py): add _handle_fallback_response function to streamline fallback handling logic
refactor(agent_utils.py): extract fallback handling logic from run_agent_with_retry to improve code readability
fix(ciayn_agent.py): update stream method parameter name for consistency
chore(agents_alias.py): reorder import statements to follow best practices
style(fallback_handler.py): reorder exception imports for consistency and clarity
2025-02-13 16:47:31 -08:00
Ariel Frischer 115cde98b6 feat(agent_utils.py): add FallbackToolExecutionError exception to handle fallback tool execution failures
fix(ciayn_agent.py): improve error message template for tool call errors to provide clearer guidance
refactor(ciayn_agent.py): update comment for clarity regarding fallback tool invocation
fix(output.py): clarify that CiaynAgent handles tool execution errors internally
fix(fallback_handler.py): raise FallbackToolExecutionError for better error handling in fallback scenarios
2025-02-13 16:42:59 -08:00
Ariel Frischer e2cd51c66d feat(agent_utils.py): add SystemMessage import and improve logging messages for clarity
fix(agent_utils.py): handle fallback responses more effectively and ensure fallback handler is optional
refactor(ciayn_agent.py): streamline prompt building and extract tool call logic into a separate method
chore(ciayn_agent.py): remove commented-out code and improve fallback response handling
chore(exceptions.py): remove unused CiaynToolExecutionError class to clean up code
chore(fallback_handler.py): simplify fallback response handling logic
chore(logging_config.py): add debug print statement for logging handler usage
chore(prompts.py): update prompts for clarity and maintainability
2025-02-13 16:14:24 -08:00
Ariel Frischer 646d509c22 feat(agent_utils.py): add agent_type retrieval to enhance fallback handling logic
feat(ciayn_agent.py): implement chat_history in CiaynAgent for improved context management during tool execution
refactor(ciayn_agent.py): streamline fallback response handling and logging for better clarity and maintainability
2025-02-13 00:24:31 -08:00
Ariel Frischer e508e4d1f2 feat(agent_utils.py): introduce get_agent_type function to determine agent type and improve code clarity
refactor(agent_utils.py): update _run_agent_stream to utilize agent type for output printing
fix(ciayn_agent.py): modify _execute_tool to handle BaseMessage and improve error reporting
feat(ciayn_agent.py): add extract_tool_name method to identify tool names from code
chore(agents_alias.py): create agents_alias module to avoid circular imports and define RAgents type
refactor(config.py): remove direct import of CiaynAgent and update RAgents definition
fix(output.py): update print_agent_output to accept agent type for better error handling
fix(exceptions.py): add CiaynToolExecutionError for distinguishing tool execution failures
refactor(fallback_handler.py): improve logging and error handling in fallback mechanism
2025-02-12 17:55:43 -08:00
Ariel Frischer 1388067769 refactor(agent_utils.py): refactor run_agent_with_retry function for better readability and maintainability by extracting helper functions
feat(agent_utils.py): add new helper functions for handling API errors and managing interrupt signals
fix(agent_utils.py): improve error handling in tool execution and retry logic
feat(fallback_handler.py): enhance fallback handling by binding tools correctly during retries
test(tests): add unit tests for new helper functions and refactored logic in agent_utils.py
2025-02-11 12:16:04 -08:00
Ariel Frischer 55abf6e5dd feat(fallback_handler): implement FallbackHandler class to manage tool failures and fallback logic
refactor(ciayn_agent): integrate FallbackHandler into CiaynAgent for improved failure handling
fix(agent_utils): add missing newline for better readability in run_agent_with_retry function
test(fallback_handler): add unit tests for FallbackHandler to ensure correct failure handling and fallback logic
2025-02-10 23:37:15 -08:00
Ariel Frischer d8ee4e04f4 feat(fallback): implement automatic fallback to alternative LLM models on consecutive failures to enhance user experience and prevent infinite error loops
refactor(ciayn_agent): restructure tool failure handling to track consecutive failures and fallback attempts more effectively
fix(logging): add pretty logging option for improved log readability
chore(config): define valid providers for LLM selection and update fallback model loading logic
test(ciayn_agent): add unit tests for fallback logic and tool failure handling to ensure reliability and correctness
2025-02-10 14:13:19 -08:00
Ariel Frischer 45b993cfd0 feat(issue): add LLM Tool Call Fallback Feature documentation to outline the new functionality for automatic fallback to alternative LLM models after consecutive failures
feat(ciayn_agent): implement fallback mechanism in CiaynAgent to handle tool call failures and switch to alternative models
feat(__main__): add command line arguments for fallback configuration in the main application
feat(llm): add validation for required environment variables for LLM providers and merge chat histories during fallback
fix(config): define default values for maximum tool failures in configuration
test(ciayn_agent): add unit tests for fallback logic and tool call execution with retries and error handling
test(llm): enhance tests for LLM initialization and environment variable validation
2025-02-09 22:07:23 -08:00
AI Christianson 5861f3a2bf Adjust token/bytes ratio to resolve errors on swebench-lite. 2025-02-08 08:07:37 -05:00
AI Christianson dd8b9c0d30 Improve prompts. 2025-01-31 17:45:47 -05:00
AI Christianson f7e02fc98e Refactor models_tokens to be models_params so we can track multiple parameters on a per-model basis. 2025-01-31 16:05:44 -05:00
AI Christianson e059ba3c49 Fix token estimation 2025-01-31 14:39:02 -05:00
Ariel Frischer 1b239f07bf
fix(ciayn_agent.py): convert list input to string to handle create-react-agent tool calls correctly (#66) 2025-01-29 17:42:59 -05:00