atropos/atroposlib/tests
Dakota 08e14cc745 feat: add minimum batch allocation support for environments
- Add min_batch_allocation parameter to ensure environments contribute minimum proportion to each batch
- Implement grab_batch_with_minimum_allocations function with proper scaling when allocations exceed 100%
- Add mixed-size group buffering to handle variable-sized data submissions
- Update server to use minimum allocation logic when any env has min_batch_allocation set
- Add comprehensive tests for minimum allocation scenarios
- Update documentation in API README and CONFIG.md
- Update example environments to demonstrate the feature

This feature allows critical environments to guarantee they contribute at least a specified proportion (0.0-1.0) to each training batch, ensuring important data sources are always represented during training.

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-07-07 08:50:28 -05:00
..
test_utils feat: add minimum batch allocation support for environments 2025-07-07 08:50:28 -05:00
api_test_utils.py Fix API to accept messages without reward field + comprehensive tests 2025-06-09 14:03:08 -05:00
conftest.py Add n kwarg being ignored workaround 2025-05-12 12:06:03 -05:00
README.md Fix API to accept messages without reward field + comprehensive tests 2025-06-09 14:03:08 -05:00
test_advantages.py Remove dependency on torch for default installation 2025-05-12 10:17:41 -05:00
test_api_legacy.py Fix API to accept messages without reward field + comprehensive tests 2025-06-09 14:03:08 -05:00
test_api_messages_handling.py Fix API to accept messages without reward field + comprehensive tests 2025-06-09 14:03:08 -05:00
test_api_messages_handling_README.md Fix API to accept messages without reward field + comprehensive tests 2025-06-09 14:03:08 -05:00
test_openai_api_workarounds.py Merge commit '71e7a5ca27' into add-support-for-custom-api-servers 2025-05-12 18:40:35 -05:00

Running Tests

This section contains instructions and guidelines for running the test suite. Please ensure all tests pass before submitting contributions.

We use pytest for our testing framework.

Simply run pytest from the main directory and you're good to go.