add DeepSeek V3.2 and MiniMax M2.1 models to NVIDIA provider

[starfield17]

Add support for DeepSeek V3.2 and MiniMax M2.1 models in the NVIDIA provider to expand available AI model options with enhanced reasoning capabilities. Rationale This PR addresses the feature request to add additional advanced models within the NVIDIA provider ecosystem. Users need more choices for reasoning and tool calling capabilities, and these two models provide:

• Enhanced reasoning capabilities through advanced model architectures
• Tool calling support for interactive AI workflows
• Diverse model families (deepseek-v3 and minimax) for different use cases
• Open weights availability for research and development Changes
• Modified packages/opencode/test/tool/fixtures/models-api.json
• Added complete model configurations with cost, context limits, and capabilities
• JSON format validated successfully
• Followed existing configuration patterns and schemas Models Details DeepSeek V3.2
• Model ID: nvidia/deepseek-ai/deepseek-v3.2
• Context: 163,840 tokens
• Output: 65,536 tokens
• Cost: $0.28 input / $0.4 output
• Features: reasoning, tool_call, temperature
• Open Weights: true
• Family: deepseek-v3 MiniMax M2.1
• Model ID: nvidia/minimaxai/minimax-m2.1
• Context: 204,800 tokens
• Output: 131,072 tokens
• Cost: $0.3 input / $1.2 output
• Features: reasoning, tool_call, temperature, interleaved reasoning
• Open Weights: true
• Family: minimax
• Special: interleaved: { field: "reasoning_details" } Testing
• JSON syntax validated ✓
• Model configurations match existing patterns ✓
• All required fields included ✓
• Configuration follows provider schema requirements ✓ Impact This PR enhances the NVIDIA provider's model offerings by providing users access to two additional advanced AI models with reasoning and tool calling capabilities, expanding the ecosystem's functionality and model diversity. Related Issues This PR addresses the need for additional model support within the NVIDIA provider as mentioned in the community discussions about expanding available AI models.

[github-actions[bot]]

This issue might be a duplicate of existing issues. Please check:

• #7997: Feature Request: Add MiniMax AI Model Support (including M2.1-lightning) - requests MiniMax M2.1 support
• #7953: [FEATURE]: Please add the new GLM 4.7 and MiniMax M2.1 models to Nvidia - specifically requests adding MiniMax M2.1 to NVIDIA provider

Feel free to ignore if none of these address your specific case.