OpenClawAndroid
diff --git a/‎CHANGELOG.md‎
Lines changed: 1 addition & 0 deletions b/‎CHANGELOG.md‎
Lines changed: 1 addition & 0 deletions
diff --git a/‎docs/.generated/plugin-sdk-api-baseline.sha256‎
Lines changed: 2 additions & 2 deletions b/‎docs/.generated/plugin-sdk-api-baseline.sha256‎
Lines changed: 2 additions & 2 deletions
diff --git a/‎docs/tools/video-generation.md‎
Lines changed: 98 additions & 77 deletions b/‎docs/tools/video-generation.md‎
Lines changed: 98 additions & 77 deletions
diff --git a/‎extensions/byteplus/video-generation-provider.test.ts‎
Lines changed: 80 additions & 23 deletions b/‎extensions/byteplus/video-generation-provider.test.ts‎
Lines changed: 80 additions & 23 deletions
diff --git a/‎extensions/byteplus/video-generation-provider.ts‎
Lines changed: 40 additions & 4 deletions b/‎extensions/byteplus/video-generation-provider.ts‎
Lines changed: 40 additions & 4 deletions
diff --git a/‎src/agents/tools/video-generate-tool.actions.ts‎
Lines changed: 30 additions & 0 deletions b/‎src/agents/tools/video-generate-tool.actions.ts‎
Lines changed: 30 additions & 0 deletions
@@ -158,6 +158,7 @@ Docs: https://docs.openclaw.ai
 - QA/lab: add character-vibes evaluation reports with model selection and parallel runs so live QA can compare candidate behavior faster.
 - Plugins/provider-auth: let provider manifests declare `providerAuthAliases` so provider variants can share env vars, auth profiles, config-backed auth, and API-key onboarding choices without core-specific wiring.
 - iOS: pin release versioning to an explicit CalVer in `apps/ios/version.json`, keep TestFlight iteration on the same short version until maintainers intentionally promote the next gateway version, and add the documented `pnpm ios:version:pin -- --from-gateway` workflow for release trains. (#63001) Thanks @ngutman.
+- Tools/video_generate: extend the tool and the Plugin SDK with `providerOptions` (vendor-specific options forwarded as a JSON object), `inputAudios` / `audioRef` / `audioRefs` reference audio inputs, per-asset semantic role hints (`imageRoles` / `videoRoles` / `audioRoles`) using a typed `VideoGenerationAssetRole` union, a new `"adaptive"` aspect-ratio sentinel, and `maxInputAudios` provider capability declarations. Providers opt into `providerOptions` by declaring a typed `capabilities.providerOptions` schema (`{ seed: "number", draft: "boolean", ... }`); unknown keys and type mismatches cause the runtime fallback loop to skip the candidate with a visible warning and an `attempts` entry, so vendor-specific options never silently reach the wrong provider. Also raises the in-tool image input cap to 9 and updates the docs table to list all new parameters. (#61987) Thanks @xieyongliang.
 
 ### Fixes
 
 
@@ -1,2 +1,2 @@
-ee16273fa5ad8c5408e9dad8d96fde86dfa666ef8eb44840b78135814ff97173  plugin-sdk-api-baseline.json
-2bd0d5edf23e6a889d6bedb74d0d06411dd7750dac6ebf24971c789f8a69253a  plugin-sdk-api-baseline.jsonl
+7a9bb7a5e4b243e2123af94301ba363d57eddab2baa6378d16cd37a1cb8a55f7  plugin-sdk-api-baseline.json
+2bdca027d5fda72399479569927cd34d18b56b242e4b12ac45e7c2352e551c77  plugin-sdk-api-baseline.jsonl
@@ -14,31 +14,35 @@ beforeAll(async () => {
 
 installProviderHttpMockCleanup();
 
+function mockSuccessfulBytePlusTask(params?: { model?: string }) {
+  postJsonRequestMock.mockResolvedValue({
+    response: {
+      json: async () => ({
+        id: "task_123",
+      }),
+    },
+    release: vi.fn(async () => {}),
+  });
+  fetchWithTimeoutMock
+    .mockResolvedValueOnce({
+      json: async () => ({
+        id: "task_123",
+        status: "succeeded",
+        content: {
+          video_url: "https://example.com/byteplus.mp4",
+        },
+        model: params?.model ?? "seedance-1-0-lite-t2v-250428",
+      }),
+    })
+    .mockResolvedValueOnce({
+      headers: new Headers({ "content-type": "video/mp4" }),
+      arrayBuffer: async () => Buffer.from("mp4-bytes"),
+    });
+}
+
 describe("byteplus video generation provider", () => {
   it("creates a content-generation task, polls, and downloads the video", async () => {
-    postJsonRequestMock.mockResolvedValue({
-      response: {
-        json: async () => ({
-          id: "task_123",
-        }),
-      },
-      release: vi.fn(async () => {}),
-    });
-    fetchWithTimeoutMock
-      .mockResolvedValueOnce({
-        json: async () => ({
-          id: "task_123",
-          status: "succeeded",
-          content: {
-            video_url: "https://example.com/byteplus.mp4",
-          },
-          model: "seedance-1-0-lite-t2v-250428",
-        }),
-      })
-      .mockResolvedValueOnce({
-        headers: new Headers({ "content-type": "video/mp4" }),
-        arrayBuffer: async () => Buffer.from("mp4-bytes"),
-      });
+    mockSuccessfulBytePlusTask();
 
     const provider = buildBytePlusVideoGenerationProvider();
     const result = await provider.generateVideo({
@@ -60,4 +64,57 @@ describe("byteplus video generation provider", () => {
       }),
     );
   });
+
+  it("switches t2v image requests to i2v models and lowercases resolution", async () => {
+    mockSuccessfulBytePlusTask({ model: "seedance-1-0-lite-i2v-250428" });
+
+    const provider = buildBytePlusVideoGenerationProvider();
+    await provider.generateVideo({
+      provider: "byteplus",
+      model: "seedance-1-0-lite-t2v-250428",
+      prompt: "Animate this still image",
+      resolution: "720P",
+      inputImages: [{ url: "https://example.com/first-frame.png" }],
+      cfg: {},
+    });
+
+    const request = postJsonRequestMock.mock.calls[0]?.[0] as { body?: Record<string, unknown> };
+    expect(request.body).toMatchObject({
+      model: "seedance-1-0-lite-i2v-250428",
+      resolution: "720p",
+      content: [
+        { type: "text", text: "Animate this still image" },
+        {
+          type: "image_url",
+          image_url: { url: "https://example.com/first-frame.png" },
+          role: "first_frame",
+        },
+      ],
+    });
+  });
+
+  it("maps declared providerOptions into the request body", async () => {
+    mockSuccessfulBytePlusTask({ model: "seedance-1-0-pro-250528" });
+
+    const provider = buildBytePlusVideoGenerationProvider();
+    await provider.generateVideo({
+      provider: "byteplus",
+      model: "seedance-1-0-pro-250528",
+      prompt: "A cinematic lobster montage",
+      providerOptions: {
+        seed: 42,
+        draft: true,
+        camera_fixed: false,
+      },
+      cfg: {},
+    });
+
+    const request = postJsonRequestMock.mock.calls[0]?.[0] as { body?: Record<string, unknown> };
+    expect(request.body).toMatchObject({
+      model: "seedance-1-0-pro-250528",
+      seed: 42,
+      resolution: "480p",
+      camera_fixed: false,
+    });
+  });
 });
@@ -141,6 +141,11 @@ export function buildBytePlusVideoGenerationProvider(): VideoGenerationProvider
         agentDir,
       }),
     capabilities: {
+      providerOptions: {
+        seed: "number",
+        draft: "boolean",
+        camera_fixed: "boolean",
+      },
       generate: {
         maxVideos: 1,
         maxDurationSeconds: 12,
@@ -191,6 +196,17 @@ export function buildBytePlusVideoGenerationProvider(): VideoGenerationProvider
           capability: "video",
           transport: "http",
         });
+      // Seedance 1.0 has separate T2V and I2V model IDs (e.g. seedance-1-0-lite-t2v-250428 vs
+      // seedance-1-0-lite-i2v-250428). When input images are provided with a T2V model, auto-
+      // switch to the corresponding I2V variant so the API does not reject with task_type mismatch.
+      // 1.5 Pro uses a single model ID for both modes and is unaffected by this substitution.
+      const hasInputImages = (req.inputImages?.length ?? 0) > 0;
+      const requestedModel = normalizeOptionalString(req.model) || DEFAULT_BYTEPLUS_VIDEO_MODEL;
+      const resolvedModel =
+        hasInputImages && requestedModel.includes("-t2v-")
+          ? requestedModel.replace("-t2v-", "-i2v-")
+          : requestedModel;
+
       const content: Array<Record<string, unknown>> = [{ type: "text", text: req.prompt }];
       const imageUrl = resolveBytePlusImageUrl(req);
       if (imageUrl) {
@@ -201,15 +217,18 @@ export function buildBytePlusVideoGenerationProvider(): VideoGenerationProvider
         });
       }
       const body: Record<string, unknown> = {
-        model: normalizeOptionalString(req.model) || DEFAULT_BYTEPLUS_VIDEO_MODEL,
+        model: resolvedModel,
         content,
       };
       const aspectRatio = normalizeOptionalString(req.aspectRatio);
       if (aspectRatio) {
         body.ratio = aspectRatio;
       }
-      if (req.resolution) {
-        body.resolution = req.resolution;
+      // Seedance API requires lowercase resolution values (e.g. "480p", "720p"); uppercase
+      // variants like "480P" are rejected with InvalidParameter.
+      const resolution = normalizeOptionalString(req.resolution)?.toLowerCase();
+      if (resolution) {
+        body.resolution = resolution;
       }
       if (typeof req.durationSeconds === "number" && Number.isFinite(req.durationSeconds)) {
         body.duration = Math.max(1, Math.round(req.durationSeconds));
@@ -221,6 +240,23 @@ export function buildBytePlusVideoGenerationProvider(): VideoGenerationProvider
         body.watermark = req.watermark;
       }
 
+      // Forward declared providerOptions: seed, draft, camerafixed.
+      // draft=true forces 480p resolution for faster generation.
+      const opts = req.providerOptions ?? {};
+      const seed = typeof opts.seed === "number" ? opts.seed : undefined;
+      const draft = opts.draft === true;
+      // Official JSON body field is camera_fixed (with underscore).
+      const cameraFixed = typeof opts.camera_fixed === "boolean" ? opts.camera_fixed : undefined;
+      if (seed != null) {
+        body.seed = seed;
+      }
+      if (draft && !body.resolution) {
+        body.resolution = "480p";
+      }
+      if (cameraFixed != null) {
+        body.camera_fixed = cameraFixed;
+      }
+
       const { response, release } = await postJsonRequest({
         url: `${baseUrl}/contents/generations/tasks`,
         headers,
@@ -255,7 +291,7 @@ export function buildBytePlusVideoGenerationProvider(): VideoGenerationProvider
         });
         return {
           videos: [video],
-          model: completed.model ?? req.model ?? DEFAULT_BYTEPLUS_VIDEO_MODEL,
+          model: completed.model ?? resolvedModel,
           metadata: {
             taskId,
             status: completed.status,
 
@@ -21,11 +21,36 @@ function summarizeVideoGenerationCapabilities(
   const generate = provider.capabilities.generate;
   const imageToVideo = provider.capabilities.imageToVideo;
   const videoToVideo = provider.capabilities.videoToVideo;
+  // providerOptions may be declared at the mode level (generate) or at the flat
+  // provider-capabilities level. The runtime checks both; surface the union so
+  // the agent sees a single merged view of which opaque keys each provider
+  // actually accepts.
+  const declaredProviderOptions: Record<string, string> = {};
+  for (const [key, type] of Object.entries(provider.capabilities.providerOptions ?? {})) {
+    declaredProviderOptions[key] = type;
+  }
+  for (const [key, type] of Object.entries(generate?.providerOptions ?? {})) {
+    declaredProviderOptions[key] = type;
+  }
+  for (const [key, type] of Object.entries(imageToVideo?.providerOptions ?? {})) {
+    declaredProviderOptions[key] = type;
+  }
+  for (const [key, type] of Object.entries(videoToVideo?.providerOptions ?? {})) {
+    declaredProviderOptions[key] = type;
+  }
+  const maxInputAudios =
+    generate?.maxInputAudios ??
+    imageToVideo?.maxInputAudios ??
+    videoToVideo?.maxInputAudios ??
+    provider.capabilities.maxInputAudios;
   const capabilities = [
     supportedModes.length > 0 ? `modes=${supportedModes.join("/")}` : null,
     generate?.maxVideos ? `maxVideos=${generate.maxVideos}` : null,
     imageToVideo?.maxInputImages ? `maxInputImages=${imageToVideo.maxInputImages}` : null,
     videoToVideo?.maxInputVideos ? `maxInputVideos=${videoToVideo.maxInputVideos}` : null,
+    typeof maxInputAudios === "number" && maxInputAudios > 0
+      ? `maxInputAudios=${maxInputAudios}`
+      : null,
     generate?.maxDurationSeconds ? `maxDurationSeconds=${generate.maxDurationSeconds}` : null,
     generate?.supportedDurationSeconds?.length
       ? `supportedDurationSeconds=${generate.supportedDurationSeconds.join("/")}`
@@ -41,6 +66,11 @@ function summarizeVideoGenerationCapabilities(
     generate?.supportsSize ? "size" : null,
     generate?.supportsAudio ? "audio" : null,
     generate?.supportsWatermark ? "watermark" : null,
+    Object.keys(declaredProviderOptions).length > 0
+      ? `providerOptions={${Object.entries(declaredProviderOptions)
+          .map(([key, type]) => `${key}:${type}`)
+          .join(", ")}}`
+      : null,
   ]
     .filter((entry): entry is string => Boolean(entry))
     .join(", ");