[model] support minimax_m3

[Jintao-Huang]

No description provided.

[gemini-code-assist]

Code Review

This pull request adds support for the MiniMax-M3 VL multimodal model, introducing the MinimaxM3AgentTemplate for XML-based tool calling and the MinimaxM3VLTemplate for handling image and video inputs alongside thinking instructions. The code reviewer identified several issues and improvement opportunities: a bug in XML parsing where nested lists fail to parse correctly due to non-greedy regex matching, a type mismatch in token splitting where a list is passed instead of an integer, and redundant code including an unused _iter_tagged helper and an unnecessary _data_collator_mm_data method override.

Important

The consumer version of Gemini Code Assist on GitHub is being sunset. Starting June 18, 2026, new organization installations will be blocked, and all code review activity will officially cease on July 17, 2026.
For more details on the timeline and next steps, please review the Help Documentation.

[Jintao-Huang]

/gemini review

[gemini-code-assist]

Code Review

This pull request adds support for the MiniMax-M3 multimodal model and its corresponding agent template, including documentation updates, model registration, and architecture configuration. The feedback highlights several critical improvement opportunities: adding validation to prevent mismatches between media tokens and provided media in the template encoder, implementing a recursive helper function to safely replace placeholders in nested template prompts, and adding robust checks for malformed tool calls in the agent template.

Important

The consumer version of Gemini Code Assist on GitHub is being sunset. Starting June 18, 2026, new organization installations will be blocked, and all code review activity will officially cease on July 17, 2026.
For more details on the timeline and next steps, please review the Help Documentation.