Heads up, MiMo users! 🧠
If you're using thinking mode in an agent loop — don't strip reasoning_content from assistant messages that have tool calls.
Without it → 400 error. Or worse, the model silently gets dumber.
Preserve the reasoning. Your agent will thank you. 🙏
Heads up, agent users!
If you're using Xiaomi MiMo with thinking mode:
When thinking mode is enabled in a multi-turn agent session and the conversation history contains a tool call, any assistant message with tool calls passed back in subsequent user turns must preserve its full reasoning_content field — otherwise the API will return a 400 error.
Without it, the model's context is incomplete, which can lead to weaker instruction-following, more hallucinations, and a visibly degraded user experience.
Missing reasoning = incomplete context = degraded reasoning quality.
Affected frameworks include TRAE, Cursor, Roo Code, Codex, GitHub Copilot CLI, Zed, AutoGen. We're actively working with the maintainers to push compatibility updates.
Affected models: MiMo-V2.5-Pro, MiMo-V2.5, MiMo-V2-Pro, MiMo-V2-Omni, MiMo-V2-Flash.
See docs(https://t.co/9v7oybaW26 )for more details.
Start with your assets.
• Listing photos (Zillow or your own)
• A photo of yourself or your agent character
Drop everything into GPT Image
Prompt:
"Create me a full character sheet and story board with the assets provided"
Xiaomi MiMo-V2.5 is now officially open-sourced!
MIT License, supporting commercial deployment, continued training, and fine-tuning - no additional authorization required.
Two models, both supporting a 1M-token context window :
• MiMo-V2.5-Pro: built for complex agent and coding tasks, ranking No.1 among open-source models on GDPVal-AA and ClawEval
• MiMo-V2.5: a native omni-modal model with strong agent capabilities
A model's value isn't measured by rankings alone — it's measured by the problems it solves.
Let's build with MiMo now!
🤗 Weights: https://t.co/w7wNtXj9Rm
📄 Blog: https://t.co/bPaaWMRI0g
Opus 4.7 is live in Claude Code today!
The model performs best if you treat it like an engineer you're delegating to, not a pair programmer you're guiding line by line. Here are three workflow shifts we recommend for this model 🧵
https://t.co/bD5JO1xDMS