* added extra parameter for kickoff to return token usage count after result
* added output_token_usage to class and in full_output
* logger duplicated
* added more types
* added usage_metrics to full output instead
* added more to the description on full_output
* possible mispacing
* Sync with deep copy working now
* async working!!
* Clean up code for review
* Fix naming
---------
Co-authored-by: João Moura <joaomdmoura@gmail.com>
* fix: fix test actually running
* fix: fix test to not send request to openai
* fix: fix linting to remove cli files
* fix: exclude only files that breaks black
* fix: Fix all Ruff checkings on the code and Fix Test with repeated name
* fix: Change linter name on yml file
* feat: update pre-commit
* feat: remove need for isort on the code
* feat: add mypy as type checker, update code and add comment to reference
* feat: remove black linter
* feat: remove poetry to run the command
* feat: change logic to test mypy
* feat: update tests yml to try to fix the tests gh action
* feat: try to add just mypy to run on gh action
* feat: fix yml file
* feat: add comment to avoid issue on gh action
* feat: decouple pytest from the necessity of poetry install
* feat: change tests.yml to test different approach
* feat: change to poetry run
* fix: parameter field on yml file
* fix: update parameters to be on the pyproject
* fix: update pyproject to remove import untyped errors
* fix: fix test actually running
* fix: fix test to not send request to openai
* fix: fix linting to remove cli files
* fix: exclude only files that breaks black
* fix: Fix all Ruff checkings on the code and Fix Test with repeated name
* fix: Change linter name on yml file
* feat: update pre-commit
* feat: remove need for isort on the code
* feat: remove black linter
* feat: update tests yml to try to fix the tests gh action
* Update task.py: try to find json in task output using regex
Sometimes the model replies with a valid and additional text, let's try to extract and validate it first. It's cheaper than calling LLM for that.
* Update task.py
---------
Co-authored-by: João Moura <joaomdmoura@gmail.com>
This commit adds a conditional check to ensure that the output file directory exists before attempting to create it. This ensures that the code does not
fail in cases where the directory does not exist and needs to be created. The condition is added in the `_save_file` method of the `Task` class, ensuring
that the correct behavior is maintained for saving results to a file.
* tasks.py: don't call Converter when model response is valid
Try to convert the task output to the expected Pydantic model before sending it to Converter, maybe the model got it right.
* feature: human input per task
* Update executor.py
* Update executor.py
* Update executor.py
* Update executor.py
* Update executor.py
* feat: change human input for unit testing
added documentation and unit test
* Create test_agent_human_input.yaml
add yaml for test
---------
Co-authored-by: João Moura <joaomdmoura@gmail.com>
