name: "CodeDebugCollab_Flow" description: "ToDO: add description" max_rounds: 2 # ToDo: To increase to 4 input_interface: - "problem_description" - "input_description" - "output_description" - "io_examples_and_explanation" - "public_tests_individual_io" output_interface: - "code" subflows_config: CodeGenerator: _target_: .CF_Code.instantiate_from_default_config name: "CodeGenerator" model_name: "gpt-4" human_message_prompt_template: _target_: langchain.PromptTemplate template: |2- {{testing_results_summary}} {{code_feedback}} Consider the problem statement, the last proposed solution, its issue and the provided feedback. Return a corrected version of the code that solves the original problem and resolves the issue, without any explanation, in the following format: ```python {{code_placeholder}} ``` input_variables: - code_feedback - testing_results_summary partial_variables: code_placeholder: "{{python_code}}" input_interface_initialized: - "code_feedback" - "testing_results_summary" CodeDebugCritic: _target_: .CF_CodeDebugCritic.instantiate_from_default_config topology: # ~~~ Code Generator ~~~ - goal: "Generate/refine a solution." ### Input Interface input_interface: _target_: flows.interfaces.KeyInterface additional_transformations: - _target_: flows.data_transformations.KeyMatchInput ### Flow Specification flow: CodeGenerator ### Output Interface output_interface: _target_: flows.interfaces.KeyInterface additional_transformations: - _target_: flows.data_transformations.RegexFirstOccurrenceExtractor regex: '(?<=```python)([\s\S]*?)(?=```)' regex_fallback: '(?<=```)([\s\S]*?)(?=```)' input_key: "api_output" output_key: "code" strip: True assert_unique: True keys_to_select: - "code" reset: false # ~~~ Code Critic Grounded in Tests ~~~ - goal: "" ### Input Interface input_interface: _target_: flows.interfaces.KeyInterface additional_transformations: - _target_: flows.data_transformations.KeyMatchInput ### Flow Specification flow: CodeDebugCritic reset: true