feat(baseten): support top_p, presence_penalty, frequency_penalty#1217
Merged
toubatbrian merged 1 commit intolivekit:mainfrom Apr 9, 2026
Merged
feat(baseten): support top_p, presence_penalty, frequency_penalty#1217toubatbrian merged 1 commit intolivekit:mainfrom
toubatbrian merged 1 commit intolivekit:mainfrom
Conversation
Adds `topP`, `presencePenalty`, and `frequencyPenalty` to `BasetenLLMOptions`, forwarded to Baseten's OpenAI-compatible endpoint as `top_p`, `presence_penalty`, and `frequency_penalty` respectively. These are documented sampling parameters for Baseten inference. Also switches the existing `temperature` plumbing from a truthy check to `!== undefined` so that `temperature: 0` is preserved.
🦋 Changeset detectedLatest commit: d201fdd The changes in this PR will be included in the next version bump. This PR includes changesets to release 22 packages
Not sure what this means? Click here to learn what changesets are. Click here if you're a maintainer who wants to add another changeset to this PR |
![devin-ai-integration[bot]](https://avatars.githubusercontent.com/in/811515?s=60&v=4){kind=small}
|
|
toubatbrian
approved these changes
Apr 9, 2026
Merged
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
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Adds three documented Baseten sampling parameters to
BasetenLLMOptions:topP→ forwarded astop_ppresencePenalty→ forwarded aspresence_penaltyfrequencyPenalty→ forwarded asfrequency_penaltyThese mirror how
temperatureandmaxTokensare already plumbed through the plugin. Baseten's inference docs list all four as supported options.Details
BasetenLLMOptionsinplugins/baseten/src/types.tswith TSDoc.LLMOptionsinterface and into theextrasbag inOpenAILLM.chat()inplugins/baseten/src/llm.ts.LLMsubclass constructor passes the new fields intosuper({...}).temperatureplumbing from a truthy check to!== undefinedso thattemperature: 0is preserved (previously dropped silently).!== undefinedfor all three new fields so0is a valid value.Test plan
pnpm -w format:writecleanpnpm --filter @livekit/agents-plugin-baseten lintcleanpnpm --filter @livekit/agents-plugin-baseten... buildsucceedsBASETEN_API_KEY)