fix: detect Ollama vision models from naming conventions - #345
Open
manavshrivastavagit wants to merge 1 commit into
Open
fix: detect Ollama vision models from naming conventions#345manavshrivastavagit wants to merge 1 commit into
manavshrivastavagit wants to merge 1 commit into
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Ollama vision models (e.g. qwen3-vl:8b, llava, bakllava) were unconditionally marked as vision: False in capabilities_for(), causing the agent to replace image attachments with a placeholder text.
Root cause
coworker/providers/capabilities.py set vision=False for every Ollama model regardless of actual vision capability.
Fix
Added a heuristic that inspects the model name for common vision-model naming patterns (-vl, vision, llava, bakllava, cogvlm, minicpm-v). Non-vision Ollama models (e.g. qwen2.5-coder) remain unaffected.
Closes #337