fix(vision): add vertex_gemini to vision-capable providers #217
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
The vision capabilities detection was missing the "vertex_gemini" provider name, which is the actual name used in llm_client.rs when creating a Vertex Gemini bridge. This caused the image upload icon to not appear in the input area when using Gemini models via Vertex AI.
Refactor model dropdown to support hierarchical grouping with recursive rendering. Vertex Gemini models are now organized by version (3, 2.5, 2.0) and xAI Grok models are grouped into a Grok 4 Series submenu. Also adds Gemini 3 Pro/Flash Preview to the flat provider groups.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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
"vertex_gemini"to the list of providers that support vision capabilities inVisionCapabilities::detect()vertex_geminiprovider nameProblem
When using Gemini models via Vertex AI, the image upload icon was not appearing in the input area. This was because the vision capabilities detection checked for
"gemini"and"vertex_ai_gemini", but the actual provider name set inllm_client.rsis"vertex_gemini".Test plan
cargo test -p qbit-llm-providerspasses (28 tests)