Clarifying current vs relevant evidence

[jamesbraza]

This PR clears up some fuzziness in our evidence accounting:

• Separating out current vs relevant evidence
• Clarifying in gen_answer that it needs relevant evidence
• Including the 'current question' for Best evidence message, to make it clear

[dosubot]

Related Documentation

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

^{How did I do? Any feedback?}  

[Copilot]

Pull Request Overview

This PR clarifies the distinction between current evidence and relevant evidence in the system's evidence accounting, improving transparency in status reporting and tool descriptions.

• Separates evidence counting into total evidence count vs relevant evidence count
• Updates tool descriptions to clarify that gen_answer uses relevant evidence specifically
• Enhances status messages to include the target question for better context

Reviewed Changes

Copilot reviewed 3 out of 3 changed files in this pull request and generated 1 comment.

File	Description
src/paperqa/agents/tools.py	Updates status formatting, adds relevant evidence parameter, and clarifies gen_answer tool description
src/paperqa/agents/env.py	Extends clinical trial status function with relevant evidence count parameter
tests/test_agents.py	Updates test assertions to include the new relevant evidence count parameter

---

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

[jamesbraza]

Closing in favor of #1113, let's just ditch irrelevant contexts instead of carting them around