github/OpenHands
1
1
Fork 0
mirror of https://github.com/All-Hands-AI/OpenHands.git synced 2026-01-09 14:57:59 -05:00
Code Issues Packages Projects Releases Wiki Activity

Revert "Simplify max_output_tokens handling in LLM classes" (#9364)

Browse Source
This commit is contained in:
Xingyao Wang
2025-06-25 16:01:23 -04:00
committed by GitHub
parent e9027e2ae8
commit 8e4a8a65f8
2 changed files with 23 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
openhands/llm/llm.py
View File

@@ -163,7 +163,6 @@ class LLM(RetryMixin, DebugMixin):
'temperature': self.config.temperature,
'max_completion_tokens': self.config.max_output_tokens,
}
if self.config.top_k is not None:
# openai doesn't expose top_k
# litellm will handle it a bit differently than the openai-compatible params
@@ -493,6 +492,26 @@ class LLM(RetryMixin, DebugMixin):
# Safe fallback for any potentially viable model
self.config.max_input_tokens = 4096
if self.config.max_output_tokens is None:
# Safe default for any potentially viable model
self.config.max_output_tokens = 4096
if self.model_info is not None:
# max_output_tokens has precedence over max_tokens, if either exists.
# litellm has models with both, one or none of these 2 parameters!
if 'max_output_tokens' in self.model_info and isinstance(
self.model_info['max_output_tokens'], int
):
self.config.max_output_tokens = self.model_info['max_output_tokens']
elif 'max_tokens' in self.model_info and isinstance(
self.model_info['max_tokens'], int
):
self.config.max_output_tokens = self.model_info['max_tokens']
if any(
model in self.config.model
for model in ['claude-3-7-sonnet', 'claude-3.7-sonnet']
):
self.config.max_output_tokens = 64000 # litellm set max to 128k, but that requires a header to be set
# Initialize function calling capability
# Check if model name is in our supported list
model_name_supported = (