feat(azure-open-ai/gpt-5.6-terra-2026-07-09): add new models [bot]#1722
feat(azure-open-ai/gpt-5.6-terra-2026-07-09): add new models [bot]#1722models-bot[bot] wants to merge 2 commits into
Conversation
| mode: chat | ||
| model: gpt-5.6-terra-2026-07-09 | ||
| supportedModes: | ||
| - chat |
There was a problem hiding this comment.
Missing costs omits model
High Severity
The new gpt-5.6-terra-2026-07-09 entry defines only mode, model, and supportedModes, with no costs block. The unified JSON build skips models without pricing, so this ID never appears in ai-models.json or the gateway catalog after merge.
Reviewed by Cursor Bugbot for commit 1eda962. Configure here.
|
/test-models |
Gateway test results
|
There was a problem hiding this comment.
Cursor Bugbot has reviewed your changes using default effort and found 1 potential issue.
There are 2 total unresolved issues (including 1 from previous review).
❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.
Reviewed by Cursor Bugbot for commit 8e969de. Configure here.
| - low | ||
| - medium | ||
| - high | ||
| type: string |
There was a problem hiding this comment.
Incomplete reasoning effort values
Medium Severity
reasoning_effort supportedValues lists only none, low, medium, and high. The OpenAI gpt-5.6-terra definition and nearby Azure models like gpt-5.5-2026-04-24 also include xhigh, so clients that validate against this registry may reject valid Terra requests.
Reviewed by Cursor Bugbot for commit 8e969de. Configure here.


Auto-generated by model-addition-agent for
azure-open-ai/gpt-5.6-terra-2026-07-09.Note
Low Risk
Metadata-only addition with no runtime or auth changes; risk is limited to incorrect limits or capability flags in the new model config.
Overview
Adds a new provider catalog file for
gpt-5.6-terra-2026-07-09underazure-open-ai, registering the model as active with serverless provisioning and retirement 2027-07-09.The entry declares chat/responses modes, thinking enabled, text+image input, standard tool features (function calling, structured output), large context limits (~1.05M window), and a configurable
reasoning_effortparameter (none/low/medium/high, default medium).Reviewed by Cursor Bugbot for commit 8e969de. Bugbot is set up for automated code reviews on this repo. Configure here.