feat: update Token Plan defaults and support local image inputs

packages/commands/src/commands/auth/login-api-key.ts

@@ -20,6 +20,9 @@ interface ApiKeyLoginProfile {
   baseUrl: string;
   persistBaseUrl?: string;
   defaultTextModel?: string;
+  defaultVideoModel?: string;
+  defaultImageToVideoModel?: string;
+  defaultReferenceToVideoModel?: string;
   defaultImageModel?: string;
   persistPatch?: AuthPersistPatch;
 }
@@ -54,17 +57,18 @@ export async function validateAndPersistApiKey(
   const persistBaseUrl = profile.persistBaseUrl
     ? normalizeModelBaseUrl(profile.persistBaseUrl)
     : undefined;
+  const validationModel = profile.defaultTextModel || "qwen3.7-max";
   const requestOpts = {
     url: baseUrl + chatPath(),
     method: "POST",
     headers: { Authorization: `Bearer ${key}` },
     timeout: Math.min(deps.settings.timeout, 30),
     body: {
-      model: profile.defaultTextModel || "qwen3.7-max",
+      model: validationModel,
       messages: [{ role: "user", content: "hi" }],
       max_tokens: 1,
       stream: false,
-      enable_thinking: false,
+      enable_thinking: validationModel === "qwen3.8-max-preview",
     },
   };
 
@@ -88,6 +92,9 @@ export async function validateAndPersistApiKey(
     api_key: key,
     base_url: persistBaseUrl,
     default_text_model: profile.defaultTextModel,
+    default_video_model: profile.defaultVideoModel,
+    default_image_to_video_model: profile.defaultImageToVideoModel,
+    default_reference_to_video_model: profile.defaultReferenceToVideoModel,
     default_image_model: profile.defaultImageModel,
   });
 }

packages/commands/src/commands/auth/login.ts

@@ -150,6 +150,9 @@ export default defineCommand({
       baseUrl: resolvedBaseUrl,
       persistBaseUrl,
       defaultTextModel: profilePreset?.defaultTextModel,
+      defaultVideoModel: profilePreset?.defaultVideoModel,
+      defaultImageToVideoModel: profilePreset?.defaultImageToVideoModel,
+      defaultReferenceToVideoModel: profilePreset?.defaultReferenceToVideoModel,
       defaultImageModel: profilePreset?.defaultImageModel,
     });
   },

packages/commands/src/commands/config/shared.ts

@@ -13,6 +13,8 @@ export const VALID_KEYS = [
   "security_token",
   "default_text_model",
   "default_video_model",
+  "default_image_to_video_model",
+  "default_reference_to_video_model",
   "default_image_model",
   "default_speech_model",
   "default_omni_model",
@@ -41,6 +43,8 @@ export const KEY_ALIASES: Record<string, string> = {
   "security-token": "security_token",
   "default-text-model": "default_text_model",
   "default-video-model": "default_video_model",
+  "default-image-to-video-model": "default_image_to_video_model",
+  "default-reference-to-video-model": "default_reference_to_video_model",
   "default-image-model": "default_image_model",
   "default-speech-model": "default_speech_model",
   "default-omni-model": "default_omni_model",

packages/commands/src/commands/image/edit.ts

@@ -22,6 +22,7 @@ import {
   resolveWatermark,
   ASYNC_FLAG,
   CONCURRENT_FLAG,
+  redactDataUri,
 } from "bailian-cli-core";
 import { poll } from "bailian-cli-runtime";
 import { downloadFile } from "bailian-cli-runtime";
@@ -31,10 +32,15 @@ import { resolveImageSize } from "bailian-cli-runtime";
 import { join } from "path";
 import { BOOL_FLAG_PROMPT_EXTEND_CLI_TRUE, BOOL_FLAG_WATERMARK } from "bailian-cli-runtime";
 
-const SYNC_MODEL_PREFIXES = ["qwen-image-2.0", "qwen-image-max"];
+const SYNC_MODEL_PREFIXES = ["qwen-image-2.0", "qwen-image-max", "wan2.7-image"];
+const PROMPT_EXTEND_DEFAULT_PREFIXES = ["qwen-image-2.0", "qwen-image-max"];
 
 function isSyncModel(model: string): boolean {
-  return SYNC_MODEL_PREFIXES.some((p) => model.startsWith(p));
+  return SYNC_MODEL_PREFIXES.some((prefix) => model.startsWith(prefix));
+}
+
+function enablesPromptExtendByDefault(model: string): boolean {
+  return PROMPT_EXTEND_DEFAULT_PREFIXES.some((prefix) => model.startsWith(prefix));
 }
 
 const EDIT_FLAGS = {
@@ -98,7 +104,7 @@ const EDIT_FLAGS = {
 type EditFlags = ParsedFlags<typeof EDIT_FLAGS>;
 
 export default defineCommand({
-  description: "Edit an existing image with text instructions (Qwen-Image)",
+  description: "Edit an existing image with text instructions (Qwen-Image / Wan 2.7)",
   auth: "apiKey",
   usageArgs: "--image <url> --prompt <text> [flags]",
   flags: EDIT_FLAGS,
@@ -107,6 +113,7 @@ export default defineCommand({
     '--image https://example.com/logo.png --prompt "Change color to blue" --n 3',
     '--image ./a.png --image ./b.png --prompt "Merge two images into one collage"',
     '--image https://example.com/photo.png --prompt "Remove the person" --model qwen-image-2.0-pro',
+    '--image ./photo.png --prompt "Change the style" --model wan2.7-image',
     '--image ./photo.png --prompt "Replace the background with a beach" --watermark false',
   ],
   async run(ctx) {
@@ -125,13 +132,13 @@ export default defineCommand({
 
     // Auto-upload local files (resolve all images in parallel)
     const resolvedImages = await Promise.all(
-      rawImages.map((img) => ctx.client.uploadFile(img, model)),
+      rawImages.map((image) => ctx.client.resolveImageInput(image, model)),
     );
     const n = flags.n ?? 1;
 
     const promptExtend = resolveBooleanFlag(
       flags.promptExtend,
-      useSync ? true : undefined,
+      enablesPromptExtendByDefault(model) ? true : undefined,
       "prompt-extend",
     );
 
@@ -169,7 +176,18 @@ export default defineCommand({
     const format = detectOutputFormat(settings.output);
 
     if (settings.dryRun) {
-      emitResult({ request: body, mode: useSync ? "sync" : "async" }, format);
+      const previewBody = {
+        ...body,
+        input: {
+          messages: body.input.messages.map((message) => ({
+            ...message,
+            content: message.content.map((item) =>
+              item.image ? { ...item, image: redactDataUri(item.image) } : item,
+            ),
+          })),
+        },
+      };
+      emitResult({ request: previewBody, mode: useSync ? "sync" : "async" }, format);
       return;
     }
 

packages/commands/src/commands/image/generate.ts

@@ -31,11 +31,16 @@ import { BOOL_FLAG_PROMPT_EXTEND_IMAGE_GENERATE, BOOL_FLAG_WATERMARK } from "bai
 
 import { join } from "path";
 
-// qwen-image-2.0 series uses the sync multimodal-generation endpoint
-const SYNC_MODEL_PREFIXES = ["qwen-image-2.0", "qwen-image-max"];
+// Qwen-Image 2.0 and Wan 2.7 use the sync multimodal-generation endpoint.
+const SYNC_MODEL_PREFIXES = ["qwen-image-2.0", "qwen-image-max", "wan2.7-image"];
+const PROMPT_EXTEND_DEFAULT_PREFIXES = ["qwen-image-2.0", "qwen-image-max"];
 
 function isSyncModel(model: string): boolean {
-  return SYNC_MODEL_PREFIXES.some((p) => model.startsWith(p));
+  return SYNC_MODEL_PREFIXES.some((prefix) => model.startsWith(prefix));
+}
+
+function enablesPromptExtendByDefault(model: string): boolean {
+  return PROMPT_EXTEND_DEFAULT_PREFIXES.some((prefix) => model.startsWith(prefix));
 }
 
 const GENERATE_FLAGS = {
@@ -121,7 +126,7 @@ export default defineCommand({
 
     const promptExtend = resolveBooleanFlag(
       flags.promptExtend,
-      useSync ? true : undefined,
+      enablesPromptExtendByDefault(model) ? true : undefined,
       "prompt-extend",
     );
 

packages/commands/src/commands/video/generate.ts

@@ -13,6 +13,7 @@ import {
   resolveWatermark,
   ASYNC_FLAG,
   CONCURRENT_FLAG,
+  redactDataUri,
 } from "bailian-cli-core";
 import { poll } from "bailian-cli-runtime";
 import { downloadFile, formatBytes } from "bailian-cli-runtime";
@@ -103,16 +104,17 @@ export default defineCommand({
 
     const model =
       flags.model ||
-      settings.defaultVideoModel ||
-      (flags.image ? "happyhorse-1.1-i2v" : "happyhorse-1.1-t2v");
+      (flags.image
+        ? settings.defaultImageToVideoModel || "happyhorse-1.1-i2v"
+        : settings.defaultVideoModel || "happyhorse-1.1-t2v");
     const format = detectOutputFormat(settings.output);
 
     const imageUrl = flags.image;
 
     // Auto-upload local image file for i2v
     let resolvedImageUrl: string | undefined;
     if (imageUrl) {
-      resolvedImageUrl = await ctx.client.uploadFile(imageUrl, model);
+      resolvedImageUrl = await ctx.client.resolveImageInput(imageUrl, model);
     }
 
     const watermark = resolveWatermark(flags.watermark);
@@ -139,7 +141,16 @@ export default defineCommand({
     };
 
     if (settings.dryRun) {
-      emitResult({ request: body }, format);
+      const previewBody = resolvedImageUrl
+        ? {
+            ...body,
+            input: {
+              ...body.input,
+              media: [{ type: "first_frame" as const, url: redactDataUri(resolvedImageUrl) }],
+            },
+          }
+        : body;
+      emitResult({ request: previewBody }, format);
       return;
     }
 

packages/commands/src/commands/video/ref.ts

@@ -13,6 +13,7 @@ import {
   resolveWatermark,
   ASYNC_FLAG,
   CONCURRENT_FLAG,
+  redactDataUri,
 } from "bailian-cli-core";
 import { poll } from "bailian-cli-runtime";
 import { downloadFile, formatBytes } from "bailian-cli-runtime";
@@ -117,40 +118,40 @@ export default defineCommand({
     const imageVoices = flags.imageVoice || [];
     const videoVoices = flags.videoVoice || [];
 
-    const model = flags.model || "happyhorse-1.1-r2v";
+    const model = flags.model || settings.defaultReferenceToVideoModel || "happyhorse-1.1-r2v";
     const format = detectOutputFormat(settings.output);
 
     // --- Resolve file URLs (auto-upload local files) ---
     const media: DashScopeVideoRefRequest["input"]["media"] = [];
 
     // Add reference images
-    for (let i = 0; i < images.length; i++) {
-      const resolved = await ctx.client.uploadFile(images[i]!, model);
+    for (let imageIndex = 0; imageIndex < images.length; imageIndex++) {
+      const resolved = await ctx.client.resolveImageInput(images[imageIndex]!, model);
       const entry: DashScopeVideoRefRequest["input"]["media"][number] = {
         type: "reference_image",
         url: resolved,
       };
 
       // Pair voice by position
-      if (imageVoices[i]) {
-        const resolvedVoice = await ctx.client.uploadFile(imageVoices[i]!, model);
+      if (imageVoices[imageIndex]) {
+        const resolvedVoice = await ctx.client.uploadFile(imageVoices[imageIndex]!, model);
         entry.reference_voice = resolvedVoice;
       }
 
       media.push(entry);
     }
 
     // Add reference videos
-    for (let i = 0; i < refVideos.length; i++) {
-      const resolved = await ctx.client.uploadFile(refVideos[i]!, model);
+    for (let videoIndex = 0; videoIndex < refVideos.length; videoIndex++) {
+      const resolved = await ctx.client.uploadFile(refVideos[videoIndex]!, model);
       const entry: DashScopeVideoRefRequest["input"]["media"][number] = {
         type: "reference_video",
         url: resolved,
       };
 
       // Pair voice by position
-      if (videoVoices[i]) {
-        const resolvedVoice = await ctx.client.uploadFile(videoVoices[i]!, model);
+      if (videoVoices[videoIndex]) {
+        const resolvedVoice = await ctx.client.uploadFile(videoVoices[videoIndex]!, model);
         entry.reference_voice = resolvedVoice;
       }
 
@@ -178,7 +179,18 @@ export default defineCommand({
     };
 
     if (settings.dryRun) {
-      emitResult({ request: body }, format);
+      const previewBody = {
+        ...body,
+        input: {
+          ...body.input,
+          media: body.input.media.map((item) => ({
+            ...item,
+            url: redactDataUri(item.url),
+            reference_voice: item.reference_voice ? redactDataUri(item.reference_voice) : undefined,
+          })),
+        },
+      };
+      emitResult({ request: previewBody }, format);
       return;
     }
 
@@ -233,11 +245,11 @@ export default defineCommand({
     );
 
     const videos: Array<{ taskId: string; videoUrl: string }> = [];
-    for (let i = 0; i < results.length; i++) {
-      const result = results[i]!;
+    for (let resultIndex = 0; resultIndex < results.length; resultIndex++) {
+      const result = results[resultIndex]!;
       const videoUrl =
         result.output.video_url || (result.output.results && result.output.results[0]?.url);
-      if (videoUrl) videos.push({ taskId: taskIds[i]!, videoUrl });
+      if (videoUrl) videos.push({ taskId: taskIds[resultIndex]!, videoUrl });
     }
 
     if (videos.length === 0) {

packages/commands/src/commands/vision/describe.ts

@@ -8,18 +8,13 @@ import {
   BailianError,
   ExitCode,
   isLocalFile,
+  imageFileToDataUri,
+  redactDataUri,
 } from "bailian-cli-core";
 import { emitResult, emitBare } from "bailian-cli-runtime";
-import { readFileSync, existsSync } from "fs";
+import { existsSync, statSync } from "fs";
 import { extname } from "path";
 
-const IMAGE_MIME_TYPES: Record<string, string> = {
-  ".jpg": "image/jpeg",
-  ".jpeg": "image/jpeg",
-  ".png": "image/png",
-  ".webp": "image/webp",
-};
-
 const VIDEO_EXTENSIONS = new Set([".mp4", ".mov", ".avi", ".mkv", ".webm", ".flv", ".wmv"]);
 
 function isVideoInput(input: string): boolean {
@@ -35,18 +30,7 @@ async function toImageUrl(image: string): Promise<string> {
   if (image.startsWith("data:")) return image;
   if (image.startsWith("http://") || image.startsWith("https://")) return image;
   if (image.startsWith("oss://")) return image;
-
-  // Local file → data URI (for small files < 10MB, fallback)
-  if (!existsSync(image)) throw new BailianError(`File not found: ${image}`, ExitCode.USAGE);
-  const ext = extname(image).toLowerCase();
-  const mime = IMAGE_MIME_TYPES[ext];
-  if (!mime)
-    throw new BailianError(
-      `Unsupported image format "${ext}". Supported: jpg, jpeg, png, webp`,
-      ExitCode.USAGE,
-    );
-  const buf = readFileSync(image);
-  return `data:${mime};base64,${buf.toString("base64")}`;
+  return imageFileToDataUri(image);
 }
 
 export default defineCommand({
@@ -86,7 +70,10 @@ export default defineCommand({
     const { settings, flags } = ctx;
     let image = flags.image;
     const videoInputs = flags.video ?? [];
-    const model = flags.model || "qwen3-vl-plus";
+    const model =
+      flags.model ||
+      (ctx.client.usesTokenPlanEndpoint() ? settings.defaultTextModel : undefined) ||
+      "qwen3-vl-plus";
 
     // Auto-detect: if --image was given a video file, treat it as --video
     if (image && isVideoInput(image)) {
@@ -102,7 +89,14 @@ export default defineCommand({
 
     if (settings.dryRun) {
       emitResult(
-        { request: { prompt, image, video: videoInputs.length ? videoInputs : undefined, model } },
+        {
+          request: {
+            prompt,
+            image: image ? redactDataUri(image) : undefined,
+            video: videoInputs.length ? videoInputs.map(redactDataUri) : undefined,
+            model,
+          },
+        },
         format,
       );
       return;
@@ -132,10 +126,9 @@ export default defineCommand({
 
       let finalImageUrl = imageUrl;
       if (isLocalFile(image) && imageUrl.startsWith("data:")) {
-        const { statSync } = await import("fs");
         const fileSize = statSync(image).size;
         if (fileSize > 5 * 1024 * 1024) {
-          finalImageUrl = await ctx.client.uploadFile(image, model);
+          finalImageUrl = await ctx.client.resolveImageInput(image, model);
         }
       }