Ensure that the function call results respect the previous LLM context.

This commit is contained in:
Filipi Fuchter
2025-11-18 11:37:57 -03:00
parent 6481094638
commit a510b276e6
2 changed files with 54 additions and 25 deletions

View File

@@ -66,6 +66,11 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
### Fixed
- Fixed a race condition where, if the LLM received instructions to both produce
text and invoke a function call at the same time, the context would not be
updated before the function call result arrived, causing the bot to repeat
itself.
- Fixed an issue in the `Runner` where, when using `SmallWebRTCTransport`, the
`request_data` was not being passed to the `SmallWebRTCRunnerArguments` body.