fix: enable thinking mode for DeepSeek V3.1 on Fireworks AI

[roomote]

Related GitHub Issue

Closes: #10071

Description

This PR attempts to address Issue #10071 by enabling thinking mode support for DeepSeek V3.1 on the Fireworks AI provider.

Changes:

• Added supportsReasoningBinary: true flag to the deepseek-v3p1 model definition in the Fireworks provider configuration
• Updated corresponding test to verify the new flag is present

How it works:
When the model has supportsReasoningBinary: true and the user enables reasoning in the API options, the provider will pass thinking: { type: "enabled" } parameter to the Fireworks API, which triggers the reasoning/thinking mode for DeepSeek V3.1.

Feedback and guidance are welcome.

Test Procedure

1. Ran Fireworks provider tests: cd src && npx vitest run api/providers/__tests__/fireworks.spec.ts - All 25 tests passed
2. Ran type checking: cd packages/types && npx tsc --noEmit - No type errors
3. Lint checks passed during commit

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.

Documentation Updates

• No documentation updates are required.

Additional Notes

This is an automated PR created by Roomote. The fix adds the supportsReasoningBinary capability flag to DeepSeek V3.1 model based on user confirmation that Fireworks documentation supports thinking/reasoning mode for this model via API parameter.

[roomote]

Rooviewer   See task on Roo Cloud

Review complete. No issues found.

The PR correctly adds supportsReasoningBinary: true to the DeepSeek V3.1 model configuration. This enables thinking mode when users have reasoning enabled in their settings. The change is minimal, type-safe, and properly tested.

_{Mention @roomote in a comment to request specific changes to this pull request or fix all unresolved issues.}