fix: type the generate request as the fields generation uses

api.oas3.yaml

@@ -376,6 +376,9 @@ components:
       $ref: "./schemas/serve/transfer.yaml#/Transfer"
 
     # Generation schemas
+    GenerationAsset:
+      $ref: "./schemas/generationasset.yaml#/GenerationAsset"
+
     GenerationModel:
       $ref: "./schemas/generationmodel.yaml#/GenerationModel"
 

paths/generate.yaml

@@ -90,8 +90,10 @@
           schema:
             type: string
       requestBody:
+        required: true
         description: >-
-          A prompt-bearing image, video or audio asset to generate.
+          The asset to generate and, for models that generate to a duration, the length of
+          the clip it fills.
         content:
           application/json:
             example:
@@ -103,10 +105,7 @@
               type: object
               properties:
                 asset:
-                  oneOf:
-                    - $ref: "../schemas/imageasset.yaml#/ImageAsset"
-                    - $ref: "../schemas/videoasset.yaml#/VideoAsset"
-                    - $ref: "../schemas/audioasset.yaml#/AudioAsset"
+                  $ref: "../schemas/generationasset.yaml#/GenerationAsset"
                 length:
                   description: >-
                     The length, in seconds, of the clip the asset fills. A model that

schemas/generationasset.yaml

@@ -0,0 +1,40 @@
+    GenerationAsset:
+      description: An image, video or audio asset to generate from a text prompt.
+      type: object
+      properties:
+        type:
+          description: The kind of asset to generate.
+          type: string
+          enum: ['image', 'video', 'audio']
+          example: image
+        prompt:
+          description: >-
+            A description of the asset to generate. For text-to-speech models it is the
+            text spoken.
+          type: string
+          minLength: 1
+          maxLength: 4000
+          pattern: '\S'
+          example: A lighthouse on a rocky coast at sunset, cinematic lighting
+        model:
+          description: >-
+            The generation model. Defaults to `nano-banana-2` for images,
+            `seedance-2.0-text-to-video` for video and `elevenlabs-multilingual-v2` for
+            audio. `GET /models` lists the models for each type.
+          type: string
+          example: nano-banana-2
+        options:
+          description: >-
+            Settings for the chosen `model`. `GET /models` lists the options each model
+            accepts; omitted options use the model's defaults and unknown or invalid
+            options are rejected. A starting image for video goes in `startSrc`
+            (`inputSrc` on the original image-to-video models) and a speech voice in
+            `voice`.
+          type: object
+          additionalProperties: true
+          example:
+            aspectRatio: '16:9'
+      additionalProperties: false
+      required:
+        - type
+        - prompt