feat: add imageModel() method for image generation support (#366)

* feat: add imageModel() method for image generation support

Implements ImageModelV3 interface to enable image generation through
the AI SDK's generateImage() function. Uses OpenRouter's chat completions
endpoint with modalities: ['image', 'text'] to generate images.

Features:
- Supports aspectRatio parameter via image_config
- Supports seed parameter for reproducible generation
- Supports provider routing settings
- Returns warnings for unsupported features (n > 1, size)
- Throws UnsupportedFunctionalityError for image editing (files/mask)

Closes #317

Co-Authored-By: Robert Yeakel <robert.yeakel@openrouter.ai>

* fix: address PR review feedback

- Change zod import to 'zod/v4' for consistency with rest of codebase
- Add .passthrough() to schema for forward compatibility
- Throw NoContentGeneratedError when choices array is empty
- Add test for empty choices array edge case
- Rename test to clarify it tests 'no images in message' case

Co-Authored-By: Robert Yeakel <robert.yeakel@openrouter.ai>

* fix: use shared getBase64FromDataUrl and remove duplicate user field

- Use getBase64FromDataUrl from file-url-utils.ts instead of duplicating regex
- Remove duplicate user field from OpenRouterImageSettings (inherited from OpenRouterSharedSettings)

Co-Authored-By: Robert Yeakel <robert.yeakel@openrouter.ai>

* feat: add runtime providerOptions support to image model

- Extract providerOptions.openrouter and spread into request body
- Matches chat model behavior for consistency
- Add test for runtime providerOptions support

Co-Authored-By: Robert Yeakel <robert.yeakel@openrouter.ai>

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

Author: robert-j-y

.changeset/add-image-model.md

@@ -0,0 +1,29 @@
+---
+"@openrouter/ai-sdk-provider": minor
+---
+
+Add imageModel() method to OpenRouter provider for image generation support
+
+This adds the `imageModel()` method to the OpenRouter provider, enabling image generation through the AI SDK's `generateImage()` function. The implementation uses OpenRouter's chat completions endpoint with `modalities: ['image', 'text']` to generate images.
+
+Features:
+- Implements `ImageModelV3` interface from AI SDK
+- Supports `aspectRatio` parameter via `image_config`
+- Supports `seed` parameter for reproducible generation
+- Supports provider routing settings (order, allow_fallbacks, etc.)
+- Returns appropriate warnings for unsupported features (n > 1, size)
+- Throws `UnsupportedFunctionalityError` for image editing (files/mask parameters)
+
+Usage:
+```typescript
+import { createOpenRouter } from '@openrouter/ai-sdk-provider';
+import { generateImage } from 'ai';
+
+const openrouter = createOpenRouter();
+const { image } = await generateImage({
+  model: openrouter.imageModel('google/gemini-2.5-flash-image'),
+  prompt: 'A cat wearing a hat',
+  aspectRatio: '16:9',
+});
+```
+