Problem
When a vision-capable model (e.g. qwen3-vl-plus) is selected via /model, the agent does not pass image input directly to the model as multimodal content. Instead it falls back to external image-understanding tools (the understand-image skill, which calls the MiniMax understand_image MCP tool).
If that external tool is unavailable (MCP server not connected), the agent cannot read the image at all — despite running on a native vision model.
Repro
- Register a vision model (
astra admin model ...), e.g. qwen3-vl-plus
- Select it via
/model
- Provide a local image path and ask the agent to read/describe the image
- Observe: the agent does NOT pass the image bytes to the model; it attempts
understand_image (external MCP) instead
Expected
When the active model is vision-capable, the agent should pass image input natively as multimodal content to the model, without requiring an external image tool.
Actual
Image input is not routed to the vision model. The agent depends on external image tools; when they are unavailable, image reading fails entirely.
Environment
- astra 0.1.0
- model: qwen3-vl-plus (high)
- input: local image file path
Related
Problem
When a vision-capable model (e.g.
qwen3-vl-plus) is selected via/model, the agent does not pass image input directly to the model as multimodal content. Instead it falls back to external image-understanding tools (theunderstand-imageskill, which calls the MiniMaxunderstand_imageMCP tool).If that external tool is unavailable (MCP server not connected), the agent cannot read the image at all — despite running on a native vision model.
Repro
astra admin model ...), e.g.qwen3-vl-plus/modelunderstand_image(external MCP) insteadExpected
When the active model is vision-capable, the agent should pass image input natively as multimodal content to the model, without requiring an external image tool.
Actual
Image input is not routed to the vision model. The agent depends on external image tools; when they are unavailable, image reading fails entirely.
Environment
Related