inference.LLM: add update_options for live model swaps#5757
Merged
Conversation
The model id was previously only settable at construction time, so demos that let a user pick a different LLM mid-session had to reach into `llm._opts.model`. Add a public `update_options(model=..., extra_kwargs=...)` method that mirrors `inference.STT.update_options` / `inference.TTS.update_options`. The new model id is read on the next `chat()` call, so the swap lands on the agent's next turn without recreating the LLM or losing the client connection pool.
|
Théo Monnom seems not to be a GitHub user. You need a GitHub account to be able to sign the CLA. If you have already a GitHub account, please add the email address used for this commit to your account. You have signed the CLA already but the status is still pending? Let us recheck it. |
longcw
approved these changes
May 18, 2026
Per Devin review on #5757: dict.update() merge semantics meant a key added via update_options could never be removed (even passing `{}` was a no-op). Replace the dict outright so callers can swap or clear the persistent kwargs cleanly. Consistent with the other update_options implementations in the codebase (OpenAI TTS, Cartesia, Mistral, …).
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
No description provided.