Issue Station
Sign In
Tools hereToolbox

openclaw - 💡(How to fix) Fix Bug: image tool cannot resolve configured models (Unknown model)

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…

The image analysis tool fails with Unknown model errors for all configured multimodal models, even though they are properly defined in openclaw.json and models.json.

Error Message

  1. Observe error: Unknown model: <provider>/<model-id>

Root Cause

The image analysis tool fails with Unknown model errors for all configured multimodal models, even though they are properly defined in openclaw.json and models.json.

Code Example

"imageModel": {
  "primary": "xiaomi/mimo-v2-omni"
}
RAW_BUFFERClick to expand / collapse

Description

The image analysis tool fails with Unknown model errors for all configured multimodal models, even though they are properly defined in openclaw.json and models.json.

Steps to Reproduce

  1. Configure a multimodal model (e.g., xiaomi/mimo-v2-omni or zai/glm-4.6v-flash) in agents.defaults.imageModel
  2. Ensure the model is defined in models.providers with input: ["text", "image"]
  3. Send an image and attempt to analyze it with the image tool
  4. Observe error: Unknown model: <provider>/<model-id>

Expected Behavior

The image tool should resolve the model from the configuration and use it for image analysis.

Actual Behavior

All configured models return Unknown model errors:

  • xiaomi/mimo-v2-omni (configured as imageModel.primary)
  • xiaomi/mimo-v2.5 (main session model)
  • zai/glm-4.6v-flash (previously used for vision)

Configuration

"imageModel": {
  "primary": "xiaomi/mimo-v2-omni"
}

The model is defined in models.providers.xiaomi.models with input: ["text", "image"].

Environment

  • OpenClaw version: 2026.4.12 (1c0672b)
  • OS: Windows 10 (x64)
  • Node.js: v24.14.0

Notes

This appears to be a bug in how the image tool resolves model IDs from the configuration. The main session model works fine, but the image tool's model resolution path seems different.

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…
#callback error#memory management#API rate limit#retriever error#indexing error

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 Bug: image tool cannot resolve configured models (Unknown model)