-
Notifications
You must be signed in to change notification settings - Fork 105
Fix tests for Azure OpenAI models, add GPT-4.1-nano #286
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.
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
Changes from all commits
File filter
Filter by extension
Conversations
Jump to
Diff view
Diff view
There are no files selected for viewing
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -44,6 +44,13 @@ | |
| temperature=1, # gpt-5 supports temperature of 1 only | ||
| vision_support=True, | ||
| ), | ||
| "openai/gpt-4.1-nano-2025-04-14": OpenAIModelArgs( | ||
| model_name="gpt-4.1-nano-2025-04-14", | ||
| max_total_tokens=128_000, | ||
| max_input_tokens=128_000, | ||
| max_new_tokens=16_384, | ||
| vision_support=True, | ||
| ), | ||
| "openai/gpt-4.1-mini-2025-04-14": OpenAIModelArgs( | ||
| model_name="gpt-4.1-mini-2025-04-14", | ||
| max_total_tokens=128_000, | ||
|
|
@@ -160,6 +167,13 @@ | |
| max_new_tokens=16_384, | ||
| vision_support=True, | ||
| ), | ||
| "azure/gpt-4.1-nano-2025-04-14": AzureModelArgs( | ||
| model_name="gpt-4.1-nano", | ||
| max_total_tokens=128_000, | ||
| max_input_tokens=128_000, | ||
| max_new_tokens=16_384, | ||
| vision_support=True, | ||
| ), | ||
|
Comment on lines
+170
to
+176
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Token Limit Configuration Inconsistency
Tell me moreWhat is the issue?The max_input_tokens plus max_new_tokens exceeds max_total_tokens. The sum (144,384) is greater than the maximum allowed (128,000). Why this mattersThis configuration could lead to runtime errors when the model attempts to generate responses that approach the token limits, as the combined input and output tokens cannot exceed max_total_tokens. Suggested change ∙ Feature PreviewAdjust the token limits to ensure max_input_tokens + max_new_tokens <= max_total_tokens. A possible fix: "azure/gpt-4.1-nano-2025-04-14": AzureModelArgs(
model_name="gpt-4.1-nano",
max_total_tokens=128_000,
max_input_tokens=111_616, # 128_000 - 16_384
max_new_tokens=16_384,
vision_support=True,
),Provide feedback to improve future suggestions💬 Looking for more details? Reply to this comment to chat with Korbit. |
||
| "azure/gpt-5-2025-08-07": AzureModelArgs( | ||
| model_name="gpt-5", | ||
| max_total_tokens=400_000, | ||
|
|
||
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Incorrect Log Level for Deprecation Warning
Tell me more
What is the issue?
Using INFO level for a deprecation warning is incorrect. Deprecation warnings should use WARNING level to ensure visibility.
Why this matters
Deprecation messages may be missed if logging is set to WARNING or higher, making it harder to identify and update deprecated code usage.
Suggested change ∙ Feature Preview
Provide feedback to improve future suggestions
💬 Looking for more details? Reply to this comment to chat with Korbit.