Chore: Update magistral-medium-latest in mistral.ts

[ThomsenDrake]

Update magistral-medium-latest to reflect improvements with 2509 update (Magistral Medium 1.2)

This update expands token window to 128k and adds a visual encoder.

Related GitHub Issue

Closes: #8362

Description

Update magistral-medium-latest default config for Mistral AI API provider to reflect capabilities of Magistral Medium 1.2 released in September 2025

Test Procedure

N/A - Just an update to capability parameters

Pre-Submission Checklist

• Issue Linked: This PR is linked to an approved GitHub Issue (see "Related GitHub Issue" above).
• Scope: My changes are focused on the linked issue (one major feature/fix per PR).
• Self-Review: I have performed a thorough self-review of my code.
• Testing: New and/or updated tests have been added to cover my changes (if applicable).
• Documentation Impact: I have considered if my changes require documentation updates (see "Documentation Updates" section below).
• Contribution Guidelines: I have read and agree to the Contributor Guidelines.

Screenshots / Videos

N/A - Just an update to capability parameters

Documentation Updates

• No documentation updates are required.
• Yes, documentation updates are required. (Please describe what needs to be updated or link to a PR in the docs repository).

Get in Touch

vyndorialan

---

Important

Update magistral-medium-latest in mistral.ts to increase maxTokens and enable supportsImages.

• Behavior:
  • Update magistral-medium-latest in mistral.ts to increase maxTokens from 41,000 to 131,000.
  • Enable supportsImages for magistral-medium-latest in mistral.ts.

^{This description was created by for 8191f1a. You can customize this summary. It will automatically update as commits are pushed.}

[roomote]

I found some issues that need attention.

[roomote]

P1: contextWindow remains 41_000 for "magistral-medium-latest" while this PR/issue claim a 128k window. Please update this to match the provider’s documented context window (128_000 per issue) or 131_000 if we intentionally align with other entries here. Keeping maxTokens and contextWindow consistent avoids downstream logic relying on the smaller window.

Suggested change

	contextWindow: 41_000,
	contextWindow: 128_000,