Skip to content

feat: add MiniMax image generation - #137

Open
octo-patch wants to merge 3 commits into
deer-flow:mainfrom
octo-patch:octo/20260812-text-to-image-tool-recvrXMSgZmI4e
Open

feat: add MiniMax image generation#137
octo-patch wants to merge 3 commits into
deer-flow:mainfrom
octo-patch:octo/20260812-text-to-image-tool-recvrXMSgZmI4e

Conversation

@octo-patch

Copy link
Copy Markdown
Contributor

Reason: The built-in image-generation tool does not support MiniMax models or either official regional endpoint.

This change adds the MiniMax image model catalog, provider-backed global and China endpoint selection, native request and response handling, model availability settings, and the generate_minimax_image built-in tool. The focused adapter tests cover global URL responses, China endpoint base64 responses, and provider errors.

Checks:

  • git diff --check
  • bun test packages/runtime/tests/models/minimax-image-generation.test.ts
  • bun run check:changed

@foreleven

Copy link
Copy Markdown
Collaborator

Hi @octo-patch, this PR currently has merge conflicts with main. Could you please update the branch with the latest main and resolve the conflicts? Thanks!

@octo-patch

Copy link
Copy Markdown
Contributor Author

Thanks for flagging this. I merged the latest main into this branch and resolved the single conflict in packages/runtime/src/tools/built-in/media.ts, keeping both the image-saving helpers from main and the MiniMax numeric-argument validation helper. I ran the runtime test suite (105 pass), tsc --noEmit on the root, runtime, ui, desktop and server projects, and eslint on the touched files. The branch is conflict-free now and CI is green.

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.

2 participants