Skip to content

Enhancements/tests and coverage - #10

Merged
Aaryanverma merged 7 commits into
mainfrom
enhancements/tests_and_coverage
Jun 20, 2026
Merged

Aaryanverma merged 7 commits into
mainfrom
enhancements/tests_and_coverage

Conversation

@Aaryanverma

Copy link
Copy Markdown
Collaborator

No description provided.

- Added extensive tests for document extraction from various input types including dicts, custom objects, and lists in `test_infra.py`.
- Improved LLM parameter extraction tests to validate overrides and defaults.
- Enhanced metric logging tests to ensure proper categorization and handling when MLflow is disabled.
- Implemented additional tests for async trust score calculations and response generation in `test_trustifai.py`.
- Introduced validation checks for missing context attributes in the Trustifai core logic.
- Updated embedding computation to handle missing embeddings more effectively.
- Enhanced reasoning graph construction to ensure nodes and edges are created correctly based on trust score metrics.
- Improved handling of unsupported spans in the LLM-based evidence strategy, including detailed reasoning for decisions.
- Refactored online metrics to inherit from `BaseMetric` for consistency.
- Updated visualizer to correctly position nodes based on their types.
Bumped litellm version to fix vulnerability raised by github bot.
@Aaryanverma
Aaryanverma merged commit 3aedea6 into main Jun 20, 2026
4 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant