docs: refresh qwen video generation refs

docs/concepts/features.md

@@ -20,7 +20,7 @@ title: "Features"
     Multi-agent routing with isolated sessions.
   </Card>
   <Card title="Media" icon="image">
-    Images, audio, and documents in and out.
+    Images, audio, video, documents, and image/video generation.
   </Card>
   <Card title="Apps and UI" icon="monitor">
     Web Control UI and macOS companion app.
@@ -57,6 +57,7 @@ title: "Features"
 **Media:**
 
 - Images, audio, video, and documents in and out
+- Shared image generation and video generation capability surfaces
 - Voice note transcription
 - Text-to-speech with multiple providers
 

docs/concepts/model-providers.md

@@ -141,8 +141,10 @@ Current bundled examples:
 - `byteplus`, `cloudflare-ai-gateway`, `huggingface`, `kimi`,
   `nvidia`, `qianfan`, `stepfun`, `synthetic`, `together`, `venice`,
   `vercel-ai-gateway`, and `volcengine`: plugin-owned catalogs only
-- `qwen`: plugin-owned catalogs for text models plus shared media-understanding
-  and video-generation provider registrations for its multimodal surfaces
+- `qwen`: plugin-owned catalogs for text models plus shared
+  media-understanding and video-generation provider registrations for its
+  multimodal surfaces; Qwen video generation uses the Standard DashScope video
+  endpoints with bundled Wan models such as `wan2.6-t2v` and `wan2.7-r2v`
 - `minimax`: plugin-owned catalogs, hybrid Anthropic/OpenAI replay-policy
   selection, and usage auth/snapshot logic
 - `xiaomi`: plugin-owned catalogs plus usage auth/snapshot logic

docs/gateway/configuration-reference.md

@@ -988,8 +988,9 @@ Time format in system prompt. Default: `auto` (OS preference).
   - 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.
 - `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` or another registered video-generation provider/model.
+  - Typical values: `qwen/wan2.6-t2v`, `qwen/wan2.6-i2v`, `qwen/wan2.6-r2v`, `qwen/wan2.6-r2v-flash`, or `qwen/wan2.7-r2v`.
   - 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 }`).
   - Used by the `pdf` tool for model routing.
   - If omitted, the PDF tool falls back to `imageModel`, then to the resolved session/default model.

docs/providers/qwen.md

@@ -80,7 +80,12 @@ Cloud surface, not just coding/text models.
 The `qwen` extension now also exposes:
 
 - Video understanding via `qwen-vl-max-latest`
-- Wan video generation via models such as `wan2.6-t2v`, `wan2.6-i2v`, and `wan2.6-r2v`
+- Wan video generation via:
+  - `wan2.6-t2v` (default)
+  - `wan2.6-i2v`
+  - `wan2.6-r2v`
+  - `wan2.6-r2v-flash`
+  - `wan2.7-r2v`
 
 These multimodal surfaces use the **Standard** DashScope endpoints, not the
 Coding Plan endpoints.
@@ -88,6 +93,16 @@ Coding Plan endpoints.
 - Global/Intl Standard base URL: `https://dashscope-intl.aliyuncs.com/compatible-mode/v1`
 - China Standard base URL: `https://dashscope.aliyuncs.com/compatible-mode/v1`
 
+For video generation, OpenClaw maps the configured Qwen region to the matching
+DashScope AIGC host before submitting the job:
+
+- Global/Intl: `https://dashscope-intl.aliyuncs.com`
+- China: `https://dashscope.aliyuncs.com`
+
+That means a normal `models.providers.qwen.baseUrl` pointing at either the
+Coding Plan or Standard Qwen hosts still keeps video generation on the correct
+regional DashScope video endpoint.
+
 For video generation, set a default model explicitly:
 
 ```json5
@@ -100,5 +115,13 @@ For video generation, set a default model explicitly:
 }
 ```
 
+Current bundled Qwen video-generation limits:
+
+- Up to **1** output video per request
+- Up to **1** input image
+- Up to **4** input videos
+- Up to **10 seconds** duration
+- Supports `size`, `aspectRatio`, `resolution`, `audio`, and `watermark`
+
 See [Qwen / Model Studio](/providers/qwen_modelstudio) for endpoint-level detail
 and compatibility notes.