Skip to content

fix(provider): preserve image input for custom openai-compatible models#29386

Open
SpencerJung wants to merge 2 commits into
anomalyco:devfrom
SpencerJung:fix/26780-ollama-images
Open

fix(provider): preserve image input for custom openai-compatible models#29386
SpencerJung wants to merge 2 commits into
anomalyco:devfrom
SpencerJung:fix/26780-ollama-images

Conversation

@SpencerJung
Copy link
Copy Markdown

Fixes #26780

Preserve image input content in OpenAI-compatible provider models by correctly mapping image content through the provider pipeline.

Verification

  • LSP diagnostics clean on changed files

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

[Bug] Images silently discarded with local Ollama vision models + TUI lacks drag-and-drop

1 participant