Generalizing tests for smarter LLMs

[jamesbraza]

This PR adjusts unit tests to also apply for Claude 4.5 Sonnet

[Copilot]

Pull Request Overview

This PR generalizes unit tests to accommodate Claude 4.5 Sonnet in addition to existing GPT models. The changes make test assertions more flexible to handle different LLM response formats and improve test clarity through better naming and fixed typos.

Key Changes

• Updated assertions to accept multiple valid response formats (e.g., "1.0mm", "1.0-mm", "1.0 mm")
• Fixed typo "What is is" → "What is" in multiple test queries
• Improved test data naming from generic "stub"/"special" to descriptive "positive"/"negative"

Reviewed Changes

Copilot reviewed 4 out of 6 changed files in this pull request and generated no comments.

File	Description
tests/test_paperqa.py	Replaced exact string matching with regex pattern, improved test data naming from stub/special to positive/negative, clarified comments, added context assertion
tests/test_configs.py	Extended LLM name check to accept both "gpt-" and "claude-" prefixes
tests/test_agents.py	Fixed duplicate word typo in test queries, increased context substring check from 20 to 30 characters
tests/conftest.py	Fixed duplicate word typo in test query fixture

---

_{Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.}

[dosubot]

Related Documentation

Checked 1 published document(s). No updates required.

^{How did I do? Any feedback?}