feat(microsoft-foundry/gpt-5.6-luna): add new models [bot]

[models-bot]

Auto-generated by model-addition-agent for microsoft-foundry/gpt-5.6-luna.

---

Note

Low Risk
Adds static model metadata only; no application logic, auth, or routing changes.

Overview
Registers gpt-5.6-luna on Microsoft Foundry by adding a new provider model YAML (providers/microsoft-foundry/gpt-5.6-luna.yaml).

The entry marks the model as active, serverless, with chat and responses modes, text/image input, a 1.05M context window, 128k max output, tool/structured-output features including prompt caching, global token pricing, retirement 2028-01-11, and Azure catalog/blog sources.

^{Reviewed by Cursor Bugbot for commit 3330c42. Bugbot is set up for automated code reviews on this repo. Configure here.}

[github-actions]

/test-models

[cursor]

Cursor Bugbot has reviewed your changes using default effort and found 2 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 3330c42. Configure here.}

[cursor]

Missing reasoning effort override

Medium Severity

gpt-5.6-luna inherits reasoning_effort from default.yaml, which includes minimal and omits max. This model rejects minimal and accepts max, so the catalog advertises an invalid value and hides a supported effort tier.

 

^{Triggered by learned rule: Don't flag model-addition-agent stubs as incomplete}

^{Reviewed by Cursor Bugbot for commit 3330c42. Configure here.}

[cursor]

Missing thinking capability flag

Medium Severity

gpt-5.6-luna supports scalable reasoning but omits thinking. Catalog consumers that gate reasoning UI or routing on this flag will treat the alias as a non-reasoning model.

 

^{Reviewed by Cursor Bugbot for commit 3330c42. Configure here.}

[LordGameleo]

Approving: bot-generated model addition. Required check (Validate YAML files) is green; the gateway-test trigger failure is a CI infra issue, not a model validation failure.