docs: refresh video generation config refs

docs/concepts/models.md

@@ -30,7 +30,7 @@ Related:
   falls back to `agents.defaults.imageModel`, then the resolved session/default
   model.
 - `agents.defaults.imageGenerationModel` is used by the shared image-generation capability. If omitted, `image_generate` can still infer an auth-backed provider default. It tries the current default provider first, then the remaining registered image-generation providers in provider-id order. If you set a specific provider/model, also configure that provider's auth/API key.
-- `agents.defaults.videoGenerationModel` is used by the shared video-generation capability. If omitted, video-generation providers can still use their own default model selection; if you set a specific provider/model, configure that provider's auth/API key too.
+- `agents.defaults.videoGenerationModel` is used by the shared video-generation capability. Unlike image generation, this does not infer a provider default today. Set an explicit `provider/model` such as `qwen/wan2.6-t2v`, and configure that provider's auth/API key too.
 - Per-agent defaults can override `agents.defaults.model` via `agents.list[].model` plus bindings (see [/concepts/multi-agent](/concepts/multi-agent)).
 
 ## Quick model policy

docs/gateway/configuration-reference.md

@@ -989,6 +989,7 @@ Time format in system prompt. Default: `auto` (OS preference).
 - `videoGenerationModel`: accepts either a string (`"provider/model"`) or an object (`{ primary, fallbacks }`).
   - Used by the shared video-generation capability.
   - Typical values: `qwen/wan2.6-t2v`, `qwen/wan2.6-i2v`, `qwen/wan2.6-r2v`, `qwen/wan2.6-r2v-flash`, or `qwen/wan2.7-r2v`.
+  - Set this explicitly before using shared video generation. Unlike `imageGenerationModel`, the video-generation runtime does not infer a provider default yet.
   - If you select a provider/model directly, configure the matching provider auth/API key too.
   - The bundled Qwen video-generation provider currently supports up to 1 output video, 1 input image, 4 input videos, 10 seconds duration, and provider-level `size`, `aspectRatio`, `resolution`, `audio`, and `watermark` options.
 - `pdfModel`: accepts either a string (`"provider/model"`) or an object (`{ primary, fallbacks }`).

docs/reference/api-usage-costs.md

@@ -89,7 +89,22 @@ Inbound media can be summarized/transcribed before the reply runs. This uses mod
 
 See [Media understanding](/nodes/media-understanding).
 
-### 3) Memory embeddings + semantic search
+### 3) Image and video generation
+
+Shared generation capabilities can also spend provider keys:
+
+- Image generation: OpenAI / Google / fal / MiniMax
+- Video generation: Qwen
+
+Image generation can infer an auth-backed provider default when
+`agents.defaults.imageGenerationModel` is unset. Video generation currently
+requires an explicit `agents.defaults.videoGenerationModel` such as
+`qwen/wan2.6-t2v`.
+
+See [Image generation](/tools/image-generation), [Qwen Cloud](/providers/qwen),
+and [Models](/concepts/models).
+
+### 4) Memory embeddings + semantic search
 
 Semantic memory search uses **embedding APIs** when configured for remote providers:
 
@@ -104,7 +119,7 @@ You can keep it local with `memorySearch.provider = "local"` (no API usage).
 
 See [Memory](/concepts/memory).
 
-### 4) Web search tool
+### 5) Web search tool
 
 `web_search` may incur usage charges depending on your provider: