[BFCL] Omit Reasoning Content from Chat History for Function-Calling Models #1064
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
CharlieJCJ
approved these changes
Jun 13, 2025
TheFloatingString
added a commit
to TheFloatingString/gorilla-fork
that referenced
this pull request
Jun 20, 2025
* origin: [BFCL] Fix prompt concatenation bug in Qwen template (ShishirPatil#1068) [BFCL] Multi-turn TravelAPI book_flight() Fix (ShishirPatil#966) _get_item() can not handle the "." directory in path string (ShishirPatil#1060) Add support for llama-3.1-nemotron-ultra-253b-v1 to BFCL (ShishirPatil#1032) [BFCL] Omit Reasoning Content from Chat History for Function-Calling Models (ShishirPatil#1064) [BFCL] Add support for Ling-Lite-V1.5 (ShishirPatil#1056) [BFCL] Added support for DeepSeek-R1-0528 and DeepSeek-V3-0324 (ShishirPatil#1063) [BFCL] Add type hinting (ShishirPatil#1058)
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Outdated suggestions cannot be applied.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.
OpenAI models do not return reasoning content within API responses. However, other models using the OpenAI-compatible interface, such as DeepSeek, include reasoning details in their responses.
These reasoning contents are typically not intended for inclusion in subsequent chat turns. This PR addresses this behavior by updating the handler to store any available reasoning content into response_data (primarily for local result logging), while ensuring that reasoning content does not propagate into the chat history.
This approach has previously been implemented for prompt-based models. This PR extends that logic to also support function-calling models.