Skip to content

fix(llmcore): include temperature when provider required clamping #94

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
shaun0927 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

fix(llmcore): include temperature when provider required clamping #94

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 4 additions & 3 deletions llmcore.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -256,8 +256,9 @@ def _openai_stream(api_base, api_key, messages, model, api_mode='chat_completion
max_retries=0, connect_timeout=10, read_timeout=300, proxies=None):
"""Shared OpenAI-compatible streaming request with retry. Yields text chunks, returns list[content_block]."""
ml = model.lower()
if 'kimi' in ml or 'moonshot' in ml: temperature = 1
elif 'minimax' in ml: temperature = max(0.01, min(temperature, 1.0)) # MiniMax requires temp in (0, 1]
_force_temp = False
if 'kimi' in ml or 'moonshot' in ml: temperature, _force_temp = 1, True
elif 'minimax' in ml: temperature, _force_temp = max(0.01, min(temperature, 1.0)), True # MiniMax requires temp in (0, 1]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json", "Accept": "text/event-stream"}
if api_mode == "responses":
url = auto_make_url(api_base, "responses")
Expand All @@ -267,7 +268,7 @@ def _openai_stream(api_base, api_key, messages, model, api_mode='chat_completion
url = auto_make_url(api_base, "chat/completions")
_stamp_oai_cache_markers(messages, model)
payload = {"model": model, "messages": messages, "stream": True, "stream_options": {"include_usage": True}}
if temperature != 1: payload["temperature"] = temperature
if _force_temp or temperature != 1: payload["temperature"] = temperature
if max_tokens: payload["max_tokens"] = max_tokens
if reasoning_effort: payload["reasoning_effort"] = reasoning_effort
if tools:
Expand Down