Conversation
Add a new provider that works with OpenAI-compatible backends lacking
server-side tool-call support (e.g. vLLM without --enable-auto-tool-choice).
Instead of passing `tools` in the API request, CherryProvider:
- Injects tool definitions into the system prompt
- Instructs the model to emit <tool_use> XML blocks in plain text
- Converts structured tool_calls/role="tool" history back to text on
subsequent turns so the backend never sees unsupported fields
The existing StreamProcessor already parses <tool_use> blocks, so no
downstream changes are needed.
Registration: built-in ("cherry") and dynamic via npm="@ai-sdk/cherry"
in flocks.json.
Made-with: Cursor
xiami762
approved these changes
Apr 16, 2026
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
feat(provider): add Cherry Provider for client-side tool calling
Add a new provider that works with OpenAI-compatible backends lacking
server-side tool-call support (e.g. vLLM without --enable-auto-tool-choice).
Instead of passing
toolsin the API request, CherryProvider:- Injects tool definitions into the system prompt
- Instructs the model to emit <tool_use> XML blocks in plain text
- Converts structured tool_calls/role="tool" history back to text on
subsequent turns so the backend never sees unsupported fields