Capability heuristic: no fabricated vision for gpt-oss; detect open vision families - #6
Merged
Merged
Conversation
…amilies 'gpt' as a substring granted .vision to Ollama Cloud's TEXT-ONLY gpt-oss models — they appeared in Naseem's vision-model picker and would silently fail to see. gpt-oss now keeps tools/reasoning, loses vision. Conversely, real multimodal open families (qwen-vl, llava, llama3.2-vision, pixtral, moondream, minicpm-v) served via OpenAI-compatible hosts gain vision — previously they were missed entirely (fail-closed everywhere). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Live inconsistency (Naseem, 2026-08-30): the vision-model picker filters on advertised capabilities, but the OpenAI-format heuristic grants
.visionto any id containing "gpt" — so Ollama Cloud's text-onlygpt-oss:120b/20bshowed up as pickable vision models (which would silently see nothing), while genuinely multimodal open models (qwen3-vl,llava,llama3.2-vision) got no vision flag at all.gpt-oss→ tools + structured output + reasoning, NO vision/imageInputisKnownVisionFamily(vision/-vl/llava/pixtral/moondream/minicpm-v) → vision on OpenAI-compatible hostsNew test with 10 assertions; full suite 57/57 green.
🤖 Generated with Claude Code