feat(microsoft-foundry/MAI-Image-2.5-2026-06-02): add new models [bot]

[models-bot]

Auto-generated by model-addition-agent for microsoft-foundry/MAI-Image-2.5-2026-06-02.

---

Note

Low Risk
Adds a static provider model YAML with no application or runtime logic changes.

Overview
Adds a new Microsoft Foundry provider definition for MAI-Image-2.5-2026-06-02, a preview serverless image-generation model (text + image in, image out).

The YAML sets per-token and per-image-token pricing, a 131K context window, and marks the model as image mode only. It also lists standard chat/completion params to strip (temperature, stream, tools, etc.) so routing matches the MAI Image API surface.

^{Reviewed by Cursor Bugbot for commit 5113165. 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 1 potential issue.

^{❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.}

^{Reviewed by Cursor Bugbot for commit 5113165. Configure here.}

[cursor]

Incorrect MAI-Image context limits

Medium Severity

limits sets context_window to 131072 and max_output_tokens to 4096. Microsoft's MAI-Image-2.5 model card documents a 32K context length, so the catalog advertises a much larger window than the model accepts and can let over-limit prompts through.

 

^{Reviewed by Cursor Bugbot for commit 5113165. 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.