openclaw - 💡(How to fix) Fix [Bug]: Feishu image: Media Understanding not triggered, model receives `[image data removed]` instead of image [1 participants]

TL;DR

The issue might be resolved by verifying the Media Understanding trigger configuration and ensuring it is properly integrated with the minimax model.

Guidance

• Check the Media Understanding configuration to ensure it is enabled and correctly set up to process image files downloaded to /tmp/openclaw/media/inbound/.
• Verify that the integration between Media Understanding and the minimax model is correct, allowing the model to receive the actual image content instead of the placeholder text.
• Review the provider/routing chain (openclaw->Gateway->minimax) to ensure that the image data is being passed correctly through each component.
• Investigate if there are any version-specific issues with OpenClaw (2026.04.15) that might be causing the problem.

Example

No code snippet is provided due to the lack of specific technical details in the issue.

Notes

The provided information does not include logs, screenshots, or detailed setup information, which might be necessary for a more accurate diagnosis. The issue might be specific to the integration between OpenClaw, Media Understanding, and the minimax model.

Recommendation

Apply workaround: Verify and adjust the Media Understanding configuration and its integration with the minimax model, as this seems to be the most likely cause of the issue, given the information provided.