Improve tool call APIs #363
Merged
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
github-actions
bot
added
the
CLA signed
mattjcly
reviewed
Jul 14, 2025
| @@ -424,6 +443,9 @@ export class LLMDynamicHandle extends DynamicHandle< | |||
| ) { | |||
| let finished = false; | |||
| let firstTokenTriggered = false; | |||
| let currentCallId = -1; | |||
There was a problem hiding this comment.
nit: could consider not using -1 as magic number
mattjcly
approved these changes
Jul 14, 2025
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.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.
Make changes to the tool call status reporting API so that:
toolCallIdis now available upon tool call request started (this is useful if one needs to use lmstudio-js as a OpenAI compatible endpoint proxy, as the toolCallId is required on the first fragment in OpenAI compatible endpoints.onToolCallRequestNameReceivedandonToolCallRequestArgumentFragmentGeneratedon both.actand.respondare now guaranteed to be called. If the underlying model doesn't support eager name reporting/arguments streaming, we will "fake" those events right beforeonToolCallRequestEndis called..respondto add acallIdparameter, as there might be multiple calls even within just one "round" of prediction. This is breaking change but we will not bump the major version because all the affects APIs were explicitly marked asexperimental.Fixes lmstudio-ai/lmstudio-bug-tracker#759 (LM Studio uses lmstudio.js internally)