Issue Station
Sign In
Tools hereToolbox

openclaw - 💡(How to fix) Fix Support Xiaomi mimo-v2-omni for image understanding (media-understanding provider) [1 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
openclaw/openclaw#60913•Fetched 2026-04-08 02:45:45
View on GitHub
Comments
0
Participants
1
Timeline
0
Reactions
0
Author
AteneaCRodriguezAteneaCRodriguez
Participants
AteneaCRodriguezAteneaCRodriguez

Error Message

  • Error: Model does not support images

Root Cause

OpenClaw has a media-understanding provider registry (in src/media-understanding/providers/index.ts) that is separate from the text model catalog. The registry only includes:

  • anthropic, google, minimax, moonshot, zai, groq, deepgram

Xiaomi is not registered as a media-understanding provider, even though the model catalog lists mimo-v2-omni as supporting image input.

Fix Action

Fix / Workaround

Add Xiaomi to the media-understanding provider registry so that xiaomi/mimo-v2-omni can be used as agents.defaults.imageModel.primary without workaround.

Workaround (Current)

RAW_BUFFERClick to expand / collapse

Problem

When setting agents.defaults.imageModel to xiaomi/mimo-v2-omni, the image tool fails with:

  • Error: Model does not support images
  • Or: No media-understanding provider registered for xiaomi

Even though mimo-v2-omni is configured with input: ["text", "image"] in the model catalog.

Root Cause

OpenClaw has a media-understanding provider registry (in src/media-understanding/providers/index.ts) that is separate from the text model catalog. The registry only includes:

  • anthropic, google, minimax, moonshot, zai, groq, deepgram

Xiaomi is not registered as a media-understanding provider, even though the model catalog lists mimo-v2-omni as supporting image input.

Existing Related Issue

This is related to (but not the same as) Issue #50485 which covers OpenRouter models.

Model Info

Request

Add Xiaomi to the media-understanding provider registry so that xiaomi/mimo-v2-omni can be used as agents.defaults.imageModel.primary without workaround.

Workaround (Current)

Using minimax/MiniMax-VL-01 as the image model works fine, but users who want to consolidate all usage through Xiaomi MiMo cannot do so for image understanding tasks.

extent analysis

TL;DR

To fix the issue, Xiaomi needs to be added to the media-understanding provider registry in OpenClaw.

Guidance

  • Verify that the mimo-v2-omni model is correctly configured with input: ["text", "image"] in the model catalog to ensure it supports image input.
  • Check the media-understanding provider registry in src/media-understanding/providers/index.ts to confirm that Xiaomi is not registered.
  • To add Xiaomi to the registry, update the index.ts file to include Xiaomi as a media-understanding provider, similar to the existing providers (e.g., anthropic, google, minimax).
  • Test the updated registry by setting agents.defaults.imageModel to xiaomi/mimo-v2-omni and verifying that the image tool works without errors.

Example

// src/media-understanding/providers/index.ts
import { Provider } from './provider';

const providers: Provider[] = [
  // existing providers...
  { name: 'xiaomi', api: 'https://api.xiaomimimo.com/v1' },
];

export { providers };

Notes

This fix assumes that the Xiaomi API is compatible with the OpenClaw media-understanding provider registry. If the API has specific requirements or differences, additional modifications may be necessary.

Recommendation

Apply the workaround by adding Xiaomi to the media-understanding provider registry, as this will allow users to consolidate all usage through Xiaomi MiMo for image understanding tasks.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…
#api#device allocation#model download#tokenizer error#prompt formatting

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING

openclaw - 💡(How to fix) Fix Support Xiaomi mimo-v2-omni for image understanding (media-understanding provider) [1 participants]