feat(azure-open-ai/gpt-chat-latest): add new models [bot] - #2433
feat(azure-open-ai/gpt-chat-latest): add new models [bot]#2433models-bot[bot] wants to merge 2 commits into
Conversation
![cursor[bot]](https://avatars.githubusercontent.com/in/1210556?s=60&v=4){kind=small}
|
/test-models |
There was a problem hiding this comment.
Cursor Bugbot has reviewed your changes using default effort and found 3 potential issues.
❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.
Reviewed by Cursor Bugbot for commit 9d7a653. Configure here.
| input: | ||
| - text | ||
| output: | ||
| - text |
There was a problem hiding this comment.
Missing image input modality
Medium Severity
modalities.input lists only text, but Azure's gpt-chat-latest catalog and related configs (openai/chat-latest, gpt-chat-latest-2026-05-05, gpt-chat-latest-2026-05-28, gpt-chat-latest-2026-06-24) all include image input. The registry will treat this multimodal model as text-only.
Reviewed by Cursor Bugbot for commit 9d7a653. Configure here.
| features: | ||
| - function_calling | ||
| - parallel_function_calling | ||
| - structured_output |
There was a problem hiding this comment.
Incomplete feature flags
Medium Severity
features omits system_messages, tool_choice, and prompt_caching, which are present on OpenAI chat-latest and all Azure gpt-chat-latest-* siblings. Feature detection will under-report capabilities for this alias.
Reviewed by Cursor Bugbot for commit 9d7a653. Configure here.
| context_window: 400000 | ||
| max_input_tokens: 272000 | ||
| max_output_tokens: 128000 | ||
| max_tokens: 128000 |
There was a problem hiding this comment.
Azure token limits mismatch
Medium Severity
limits use a 400000 context window and 272000 max input tokens, matching OpenAI chat-latest, but Azure Foundry documents gpt-chat-latest at a 200000 context window with 128000 max output. Request sizing based on these limits can exceed Azure's actual window.
Reviewed by Cursor Bugbot for commit 9d7a653. Configure here.
Auto-generated by model-addition-agent for
azure-open-ai/gpt-chat-latest.Note
Low Risk
Catalog-only YAML for a new preview model; no runtime, auth, or data-handling logic is changed.
Overview
Registers Azure OpenAI
gpt-chat-latestas a serverless preview chat model (retirement 2026-12-02).It supports chat and responses, thinking, function calling (including parallel), and structured output. Limits are a 400k context window, 272k max input, and 128k max output. Input/output are text-only, and
reasoning_effortis stripped from requests.Reviewed by Cursor Bugbot for commit 9d7a653. Bugbot is set up for automated code reviews on this repo. Configure here.