@ai-sdk/google 3.0.119 → 3.0.121

package/docs/15-google-generative-ai.mdx

@@ -1082,6 +1082,7 @@ The following Zod features are known to not work with Google Generative AI:
 
 | Model                                 | Image Input         | Object Generation   | Tool Usage          | Tool Streaming      | Google Search       | URL Context         |
 | ------------------------------------- | ------------------- | ------------------- | ------------------- | ------------------- | ------------------- | ------------------- |
+| `gemini-3.8-flash`                    | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
 | `gemini-3.7-flash`                    | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
 | `gemini-3.6-flash`                    | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
 | `gemini-3.5-flash`                    | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
@@ -1111,8 +1112,8 @@ The [Gemini Interactions API](https://ai.google.dev/gemini-api/docs/interactions
 (`POST /v1beta/interactions`) is a separate Google endpoint with server-side
 state, unified content blocks, first-class built-in tools, agent presets,
 managed agents that run in a sandboxed Linux environment, and native
-multimodal image output. It is reached via the `google.interactions(...)`
-factory:
+multimodal image and video output. It is reached via the
+`google.interactions(...)` factory:
 
 ```ts
 import { google } from '@ai-sdk/google';
@@ -1202,16 +1203,42 @@ The following optional provider options are available:
   Whether the model returns synthesized thought summaries on reasoning
   parts. Defaults to the API default.
 
-- **responseFormat** _Array\<\{ type: 'text' | 'image' | 'audio'; mimeType?: string; schema?: unknown; aspectRatio?: string; imageSize?: '1K' \| '2K' \| '4K' \| '512' \}\>_
+- **responseFormat** _Array\<ResponseFormatEntry\>_
 
   Output-format entries that map directly to the API's `response_format`
-  array. Use this for fine-grained control over image, audio, or non-JSON
-  text outputs (e.g. `aspectRatio` and `imageSize` for image generation).
+  array. Entries have the following shape:
+
+  ```ts
+  type ResponseFormatEntry =
+    | { type: 'text'; mimeType?: string; schema?: unknown }
+    | {
+        type: 'image';
+        mimeType?: string;
+        aspectRatio?: string;
+        imageSize?: '1K' | '2K' | '4K' | '512';
+      }
+    | { type: 'audio'; mimeType?: string }
+    | {
+        type: 'video';
+        aspectRatio?: '16:9' | '9:16';
+        resolution?: '360p' | '720p' | '1080p' | '4k';
+        duration?: string;
+        delivery?: 'inline' | 'uri';
+        gcsUri?: string;
+      };
+  ```
+
+  Use this for fine-grained control over image, audio, video, or non-JSON
+  text outputs. Video entries can control aspect ratio, resolution, duration,
+  and inline or URI delivery; set `gcsUri` when delivering to Google Cloud
+  Storage. Inline videos are returned in `result.files` by `generateText` and
+  emitted as `file` parts by `streamText`.
   The AI SDK call-level `responseFormat: { type: 'json', schema }` still
   drives JSON-mode automatically and prepends a matching text entry;
   entries listed here are appended.
 
-  `aspectRatio` accepts `1:1`, `2:3`, `3:2`, `3:4`, `4:3`, `4:5`, `5:4`,
+  For image entries, `aspectRatio` accepts `1:1`, `2:3`, `3:2`, `3:4`, `4:3`,
+  `4:5`, `5:4`,
   `9:16`, `16:9`, `21:9`, `1:8`, `8:1`, `1:4`, `4:1`.
 
 - **imageConfig** _\{ aspectRatio?: string; imageSize?: '1K' | '2K' | '4K' | '512' \}_ (deprecated)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@ai-sdk/google",
-  "version": "3.0.119",
+  "version": "3.0.121",
   "license": "Apache-2.0",
   "sideEffects": false,
   "main": "./dist/index.js",

package/src/google-generative-ai-options.ts

@@ -34,6 +34,7 @@ export type GoogleGenerativeAIModelId =
   | 'gemini-3.5-flash-lite'
   | 'gemini-3.6-flash'
   | 'gemini-3.7-flash'
+  | 'gemini-3.8-flash'
   // latest version
   // https://ai.google.dev/gemini-api/docs/models#latest
   | 'gemini-pro-latest'

package/src/interactions/google-interactions-language-model-options.ts

@@ -36,6 +36,7 @@ export type GoogleInteractionsModelId =
   | 'gemini-3.5-flash-lite'
   | 'gemini-3.6-flash'
   | 'gemini-3.7-flash'
+  | 'gemini-3.8-flash'
   | 'lyria-3-clip-preview'
   | 'lyria-3-pro-preview'
   | (string & {});
@@ -75,8 +76,8 @@ export const googleInteractionsLanguageModelOptions = lazySchema(() =>
 
       /**
        * Output-format entries that map directly to the API's `response_format`
-       * array. Use this to request image, audio, or non-JSON text outputs
-       * with full control over `mime_type`, `aspect_ratio`, and `image_size`.
+       * array. Use this to request image, audio, video, or non-JSON text
+       * outputs with modality-specific controls.
        *
        * Entries are sent in order. The AI SDK call-level `responseFormat: {
        * type: 'json', schema }` still drives JSON-mode and adds a matching
@@ -123,6 +124,16 @@ export const googleInteractionsLanguageModelOptions = lazySchema(() =>
                 mimeType: z.string().nullish(),
               })
               .loose(),
+            z
+              .object({
+                type: z.literal('video'),
+                aspectRatio: z.enum(['16:9', '9:16']).nullish(),
+                resolution: z.enum(['360p', '720p', '1080p', '4k']).nullish(),
+                duration: z.string().nullish(),
+                delivery: z.enum(['inline', 'uri']).nullish(),
+                gcsUri: z.string().nullish(),
+              })
+              .loose(),
           ]),
         )
         .nullish(),

package/src/interactions/google-interactions-language-model.ts

@@ -221,6 +221,17 @@ export class GoogleInteractionsLanguageModel implements LanguageModelV3 {
               mime_type: entry.mimeType ?? undefined,
             }),
           );
+        } else if (entry.type === 'video') {
+          responseFormatEntries.push(
+            pruneUndefined({
+              type: 'video' as const,
+              aspect_ratio: entry.aspectRatio ?? undefined,
+              resolution: entry.resolution ?? undefined,
+              duration: entry.duration ?? undefined,
+              delivery: entry.delivery ?? undefined,
+              gcs_uri: entry.gcsUri ?? undefined,
+            }),
+          );
         }
       }
     }

package/src/interactions/google-interactions-prompt.ts

@@ -434,6 +434,10 @@ export type GoogleInteractionsImageSize = '1K' | '2K' | '4K' | '512';
  *
  *   { type: 'image', mime_type, aspect_ratio?, image_size? }
  *     -- image generation. `mime_type` defaults to `image/png`.
+ *
+ *   { type: 'video', aspect_ratio?, resolution?, duration?, delivery?,
+ *     gcs_uri? }
+ *     -- video generation and delivery configuration.
  */
 export type GoogleInteractionsResponseFormatTextEntry = {
   type: 'text';
@@ -453,10 +457,20 @@ export type GoogleInteractionsResponseFormatAudioEntry = {
   mime_type?: string;
 };
 
+export type GoogleInteractionsResponseFormatVideoEntry = {
+  type: 'video';
+  aspect_ratio?: '16:9' | '9:16';
+  resolution?: '360p' | '720p' | '1080p' | '4k';
+  duration?: string;
+  delivery?: 'inline' | 'uri';
+  gcs_uri?: string;
+};
+
 export type GoogleInteractionsResponseFormatEntry =
   | GoogleInteractionsResponseFormatTextEntry
   | GoogleInteractionsResponseFormatImageEntry
-  | GoogleInteractionsResponseFormatAudioEntry;
+  | GoogleInteractionsResponseFormatAudioEntry
+  | GoogleInteractionsResponseFormatVideoEntry;
 
 export type GoogleInteractionsGenerationConfig = {
   temperature?: number;