Switch OpenRouter tests to gpt-4o-mini

[Aaron1011]

This fixes the stop-sequences tests, as it looks like OpenRouter has broken stop sequences for gpt-4.1-mini

---

Important

Switches OpenRouter tests to use gpt-4o-mini model to fix stop-sequence issues.

• Behavior:
  • Switches model in OpenRouter tests from gpt-4.1-mini to gpt-4o-mini to fix stop-sequence issues.
• Code Changes:
  • Updates model_name in openrouter.rs for multiple E2ETestProvider instances.
  • Updates model configurations in tensorzero.toml to use gpt-4o-mini instead of gpt-4.1-mini.

^{This description was created by for d568d7b. You can customize this summary. It will automatically update as commits are pushed.}

[Copilot]

Pull Request Overview

This PR switches OpenRouter test configurations from using gpt-4.1-mini to gpt-4o-mini to fix broken stop sequence functionality. The change addresses an issue where OpenRouter's implementation of stop sequences is not working properly with the gpt-4.1-mini model.

• Updates model configurations in the test TOML file to use gpt-4o-mini instead of gpt-4.1-mini
• Updates corresponding test provider configurations in Rust test files
• Maintains all existing test functionality while switching to a more reliable model

Reviewed Changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated no comments.

File	Description
tensorzero-core/tests/e2e/tensorzero.toml	Updates model names and references from gpt-4.1-mini to gpt-4o-mini across all OpenRouter configurations
tensorzero-core/tests/e2e/providers/openrouter.rs	Updates test provider model names to match the new gpt-4o-mini configuration

---

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