github/OpenHands
1
0
Fork 0
mirror of https://github.com/OpenHands/OpenHands.git synced 2025-12-26 05:48:36 +08:00
Code Issues Packages Projects Releases Wiki Activity

Simplify max_output_tokens handling in LLM classes (#9296)

Browse Source 
Co-authored-by: openhands <openhands@all-hands.dev>
This commit is contained in:
Graham Neubig 2025-06-23 06:48:45 -04:00 committed by GitHub
parent 8b90d610c6
commit 1e33624951
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 4 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
openhands/llm/llm.py
View File

@ -163,6 +163,7 @@ 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
@ -486,26 +487,6 @@ 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 = (

6
tests/unit/test_llm.py
View File

@ -132,7 +132,7 @@ def test_llm_init_with_model_info(mock_get_model_info, default_config):
llm = LLM(default_config)
llm.init_model_info()
assert llm.config.max_input_tokens == 8000
assert llm.config.max_output_tokens == 2000
assert llm.config.max_output_tokens is None
@patch('openhands.llm.llm.litellm.get_model_info')
@ -141,7 +141,7 @@ def test_llm_init_without_model_info(mock_get_model_info, default_config):
llm = LLM(default_config)
llm.init_model_info()
assert llm.config.max_input_tokens == 4096
assert llm.config.max_output_tokens == 4096
assert llm.config.max_output_tokens is None
def test_llm_init_with_custom_config():
@ -260,7 +260,7 @@ def test_llm_init_with_openrouter_model(mock_get_model_info, default_config):
llm = LLM(default_config)
llm.init_model_info()
assert llm.config.max_input_tokens == 7000
assert llm.config.max_output_tokens == 1500
assert llm.config.max_output_tokens is None
mock_get_model_info.assert_called_once_with('openrouter:gpt-4o-mini')