feat(inference): add Prime mode for text and video

packages/cli/README.md

@@ -112,15 +112,16 @@ irm https://bailian.aliyun.com/cli/install.ps1 | iex
 
 Once installed, just describe your task to your AI Agent — no need to assemble commands by hand.
 
-| Scenario                 | What to say to your Agent                                                         |
-| ------------------------ | --------------------------------------------------------------------------------- |
-| Managed Agent            | "Create a Managed Agent that can generate short-film storyboards and videos."     |
-| Image & video generation | "Generate an image of a cat in a spacesuit on Mars, then turn it into a video."   |
-| Speech recognition       | "Transcribe this audio; if proper nouns are wrong, add hot words and try again."  |
-| Usage & quota            | "Show my recent model usage, free-tier quota, and rate limits."                   |
-| Monitoring & alerts      | "Show my model call stats, failures and logs, and create an alert rule."          |
-| Model selection          | "Recommend a model for image understanding and customer support."                 |
-| About Bailian CLI        | "Tell me what Bailian CLI can do for me, and suggest how to use it for my needs." |
+| Scenario                 | What to say to your Agent                                                                                                             |
+| ------------------------ | ------------------------------------------------------------------------------------------------------------------------------------- |
+| Managed Agent            | "Create a Managed Agent that can generate short-film storyboards and videos."                                                         |
+| Image & video generation | "Generate an image of a cat in a spacesuit on Mars, then turn it into a video."                                                       |
+| Speech recognition       | "Transcribe this audio; if proper nouns are wrong, add hot words and try again."                                                      |
+| Usage & quota            | "Show my recent model usage, free-tier quota, and rate limits."                                                                       |
+| Monitoring & alerts      | "Show my model call stats, failures and logs, and create an alert rule."                                                              |
+| Throughput reservations  | "List my throughput reservations and capacity instances, then scale, renew or release capacity and wait for the operation to finish." |
+| Model selection          | "Recommend a model for image understanding and customer support."                                                                     |
+| About Bailian CLI        | "Tell me what Bailian CLI can do for me, and suggest how to use it for my needs."                                                     |
 
 > More examples and scenarios: [Aliyun Model Studio CLI Site](https://bailian.console.aliyun.com/cli?source_channel=cli_github&)
 

packages/cli/README.zh.md

@@ -111,15 +111,16 @@ irm https://bailian.aliyun.com/cli/install.ps1 | iex
 
 安装完成后，直接在 AI Agent 中描述你的任务，无需手动拼接命令。
 
-| 场景             | 可以这样对 Agent 说                                                     |
-| ---------------- | ----------------------------------------------------------------------- |
-| Managed Agent    | “帮我创建一个能够生成短片分镜和视频的 Managed Agent。”                  |
-| 图片和视频生成   | “生成一张穿着太空服的猫站在火星上的图片，再把它制作成一段视频。”        |
-| 语音识别         | “把这段音频转写成文字，专有名词识别不准的话帮我加上热词再试。”          |
-| 用量与额度       | “查看最近的模型用量、免费额度和限流情况。”                              |
-| 监控与告警       | “查看我的模型调用统计、失败明细和调用日志，并创建一条告警规则。”        |
-| 模型选型         | “推荐一个适合图片理解和智能客服的模型。”                                |
-| 了解 Bailian CLI | “介绍一下 Bailian CLI 能帮我完成哪些任务，并根据我的需求推荐使用方式。” |
+| 场景             | 可以这样对 Agent 说                                                          |
+| ---------------- | ---------------------------------------------------------------------------- |
+| Managed Agent    | “帮我创建一个能够生成短片分镜和视频的 Managed Agent。”                       |
+| 图片和视频生成   | “生成一张穿着太空服的猫站在火星上的图片，再把它制作成一段视频。”             |
+| 语音识别         | “把这段音频转写成文字，专有名词识别不准的话帮我加上热词再试。”               |
+| 用量与额度       | “查看最近的模型用量、免费额度和限流情况。”                                   |
+| 监控与告警       | “查看我的模型调用统计、失败明细和调用日志，并创建一条告警规则。”             |
+| 吞吐预留         | “查看我的吞吐预留及容量实例，并对容量进行扩缩、续订或释放，再等待操作完成。” |
+| 模型选型         | “推荐一个适合图片理解和智能客服的模型。”                                     |
+| 了解 Bailian CLI | “介绍一下 Bailian CLI 能帮我完成哪些任务，并根据我的需求推荐使用方式。”      |
 
 > 更多案例与使用场景：[阿里云百炼 CLI 官方主页](https://bailian.console.aliyun.com/cli?source_channel=cli_github&)
 

packages/commands/src/commands/shared/prime.ts

@@ -0,0 +1,63 @@
+import {
+  BailianError,
+  ExitCode,
+  workspaceMaaSBaseUrl,
+  type Client,
+  type FlagsDef,
+} from "bailian-cli-core";
+
+export const PRIME_FLAGS = {
+  prime: {
+    type: "switch",
+    description: {
+      "en-US": "Use Prime mode with a workspace-scoped endpoint",
+      "zh-CN": "使用工作空间专属 Endpoint 的 Prime 模式",
+    },
+  },
+  workspaceId: {
+    type: "string",
+    valueHint: "<id>",
+    description: {
+      "en-US": "Workspace ID for the default Prime endpoint (or set BAILIAN_WORKSPACE_ID)",
+      "zh-CN": "默认 Prime Endpoint 使用的 Workspace ID（也可设置 BAILIAN_WORKSPACE_ID）",
+    },
+  },
+} satisfies FlagsDef;
+
+interface PrimeFlags {
+  prime: boolean;
+  workspaceId?: string;
+  model?: string;
+}
+
+export function validatePrimeFlags(flags: PrimeFlags): string | undefined {
+  if (flags.workspaceId && !flags.prime) {
+    return "--workspace-id requires --prime.";
+  }
+  if (flags.prime && !flags.model) {
+    return "--prime requires an explicit --model.";
+  }
+  return undefined;
+}
+
+export function resolvePrimeEndpoint(
+  ctx: {
+    flags: Pick<PrimeFlags, "workspaceId">;
+    settings: { workspaceId?: string };
+    identity: { binName: string };
+    client: Pick<Client, "url">;
+  },
+  path: string,
+): string {
+  return ctx.client.url(path, () => {
+    const workspaceId = ctx.flags.workspaceId || ctx.settings.workspaceId;
+    if (!workspaceId) {
+      throw new BailianError(
+        "Workspace ID is required for the default Prime endpoint.",
+        ExitCode.USAGE,
+        `Pass --workspace-id, set BAILIAN_WORKSPACE_ID env, or configure: ${ctx.identity.binName} config set workspace_id <id>. You can also override the endpoint with --base-url.`,
+      );
+    }
+    return workspaceMaaSBaseUrl(workspaceId);
+  });
+}

packages/commands/src/commands/text/chat.ts

@@ -22,6 +22,7 @@ import {
   inspectResponsesStreamEvent,
   extractResponsesText,
 } from "./responses.ts";
+import { PRIME_FLAGS, resolvePrimeEndpoint, validatePrimeFlags } from "../shared/prime.ts";
 
 const CHAT_FLAGS = {
   api: {
@@ -107,6 +108,7 @@ const CHAT_FLAGS = {
       "zh-CN": "思考过程最大 Token 数（默认：4096）",
     },
   },
+  ...PRIME_FLAGS,
 } satisfies FlagsDef;
 type ChatFlags = ParsedFlags<typeof CHAT_FLAGS>;
 
@@ -187,11 +189,33 @@ export default defineCommand({
       "en-US": '--model qwq-plus --message "Solve 1+1" --enable-thinking',
       "zh-CN": '--model qwq-plus --message "计算 1+1" --enable-thinking',
     },
+    {
+      "en-US": '--prime --workspace-id <id> --model glm-5.3-prime --message "Explain this code"',
+      "zh-CN": '--prime --workspace-id <id> --model glm-5.3-prime --message "解释这段代码"',
+    },
+  ],
+  notes: [
+    {
+      "en-US":
+        "Prime mode requires an explicit model and currently supports only the Chat Completions API.",
+      "zh-CN": "Prime 模式必须显式指定模型，且当前仅支持 Chat Completions API。",
+    },
+    {
+      "en-US":
+        "Prime endpoint: configured --base-url, DASHSCOPE_BASE_URL, or profile base_url takes precedence; otherwise workspace is resolved from --workspace-id, BAILIAN_WORKSPACE_ID, then config workspace_id.",
+      "zh-CN":
+        "Prime Endpoint：已配置的 --base-url、DASHSCOPE_BASE_URL 或 Profile base_url 优先；否则按 --workspace-id、BAILIAN_WORKSPACE_ID、配置项 workspace_id 解析工作空间。",
+    },
   ],
   validate: (flags) => {
     if (!flags.message && !flags.messagesFile) {
       return "Provide --message or --messages-file.";
     }
+    const primeValidation = validatePrimeFlags(flags);
+    if (primeValidation) return primeValidation;
+    if (flags.prime && flags.api === "responses") {
+      return "--prime currently supports only --api chat.";
+    }
     if (flags.api === "responses" && flags.thinkingBudget !== undefined) {
       return "--thinking-budget is not supported by the Responses API.";
     }
@@ -240,6 +264,12 @@ export default defineCommand({
       }
     }
 
+    const requestPath = flags.prime
+      ? resolvePrimeEndpoint(ctx, chatPath())
+      : api === "responses"
+        ? responsesPath()
+        : chatPath();
+
     if (flags.tool) {
       const tools = flags.tool.map((toolValue) => {
         try {
@@ -253,13 +283,16 @@ export default defineCommand({
     }
 
     if (settings.dryRun) {
-      emitResult({ request: body }, format);
+      emitResult(
+        flags.prime ? { endpoint: requestPath, request: body } : { request: body },
+        format,
+      );
       return;
     }
 
     if (shouldStream) {
       const responseStream = await ctx.client.request({
-        path: api === "responses" ? responsesPath() : chatPath(),
+        path: requestPath,
         method: "POST",
         body,
         stream: true,
@@ -336,7 +369,7 @@ export default defineCommand({
       }
     } else if (api === "responses") {
       const response = await ctx.client.requestJson<ResponsesResponse>({
-        path: responsesPath(),
+        path: requestPath,
         method: "POST",
         body,
       });
@@ -350,7 +383,7 @@ export default defineCommand({
       }
     } else {
       const response = await ctx.client.requestJson<ChatResponse>({
-        path: chatPath(),
+        path: requestPath,
         method: "POST",
         body,
       });

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

@@ -21,6 +21,7 @@ import { downloadFile, formatBytes } from "bailian-cli-runtime";
 import { runConcurrent, getConcurrency } from "bailian-cli-runtime";
 import { emitResult, emitBare } from "bailian-cli-runtime";
 import { BOOL_FLAG_PROMPT_EXTEND_API_DEFAULT, BOOL_FLAG_WATERMARK } from "bailian-cli-runtime";
+import { PRIME_FLAGS, resolvePrimeEndpoint, validatePrimeFlags } from "../shared/prime.ts";
 
 export default defineCommand({
   description: {
@@ -128,6 +129,7 @@ export default defineCommand({
           "参考文件 URL 或本地路径，用于文件生视频（仅 wan3.0-video；与 --image/--last-frame 互斥）",
       },
     },
+    ...PRIME_FLAGS,
     ...ASYNC_FLAG,
     ...CONCURRENT_FLAG,
     pollInterval: {
@@ -160,7 +162,25 @@ export default defineCommand({
       "en-US": '--prompt "A cat playing with a ball" --watermark false',
       "zh-CN": '--prompt "一只正在玩球的猫" --watermark false',
     },
+    {
+      "en-US":
+        '--prime --workspace-id <id> --model wan3.0-video-prime --prompt "Ocean waves at sunset"',
+      "zh-CN": '--prime --workspace-id <id> --model wan3.0-video-prime --prompt "日落时的海浪"',
+    },
   ],
+  notes: [
+    {
+      "en-US": "Prime mode requires an explicit model.",
+      "zh-CN": "Prime 模式必须显式指定模型。",
+    },
+    {
+      "en-US":
+        "Prime endpoint: configured --base-url, DASHSCOPE_BASE_URL, or profile base_url takes precedence; otherwise workspace is resolved from --workspace-id, BAILIAN_WORKSPACE_ID, then config workspace_id.",
+      "zh-CN":
+        "Prime Endpoint：已配置的 --base-url、DASHSCOPE_BASE_URL 或 Profile base_url 优先；否则按 --workspace-id、BAILIAN_WORKSPACE_ID、配置项 workspace_id 解析工作空间。",
+    },
+  ],
+  validate: validatePrimeFlags,
   async run(ctx) {
     const { settings, flags } = ctx;
     const prompt = flags.prompt;
@@ -211,6 +231,9 @@ export default defineCommand({
     const watermark = resolveWatermark(flags.watermark, settings.watermark);
     const promptExtend = resolveBooleanFlag(flags.promptExtend, undefined, "prompt-extend");
 
+    const requestPath = isKf2v && !isWan30 ? image2videoPath() : videoGeneratePath();
+    const submitPath = flags.prime ? resolvePrimeEndpoint(ctx, requestPath) : requestPath;
+
     const body: DashScopeVideoRequest = {
       model,
       input: {
@@ -286,7 +309,10 @@ export default defineCommand({
           },
         };
       }
-      emitResult({ request: previewBody }, format);
+      emitResult(
+        flags.prime ? { endpoint: submitPath, request: previewBody } : { request: previewBody },
+        format,
+      );
       return;
     }
 
@@ -298,15 +324,15 @@ export default defineCommand({
       settings,
       () =>
         ctx.client.requestJson<DashScopeAsyncResponse>({
-          path: isKf2v && !isWan30 ? image2videoPath() : videoGeneratePath(),
+          path: submitPath,
           method: "POST",
           body,
           async: true,
         }),
       "tasks",
     );
 
-    const taskIds = responses.map((r) => r.output.task_id);
+    const taskIds = responses.map((response) => response.output.task_id);
 
     if (!settings.quiet) {
       process.stderr.write(`[Model: ${model}]\n`);
@@ -322,17 +348,19 @@ export default defineCommand({
     const pollInterval = flags.pollInterval ?? 5;
 
     const pollPromises = taskIds.map((taskId) => {
-      const pollUrl = ctx.client.url(taskPath(taskId));
+      const pollUrl = flags.prime
+        ? resolvePrimeEndpoint(ctx, taskPath(taskId))
+        : ctx.client.url(taskPath(taskId));
       return poll<DashScopeTaskResponse>(ctx.client, settings, {
         url: pollUrl,
         intervalSec: pollInterval,
         timeoutSec: settings.timeout,
-        isComplete: (d) => (d as DashScopeTaskResponse).output.task_status === "SUCCEEDED",
-        isFailed: (d) => (d as DashScopeTaskResponse).output.task_status === "FAILED",
-        getStatus: (d) => (d as DashScopeTaskResponse).output.task_status,
-        getErrorMessage: (d) => {
-          const o = (d as DashScopeTaskResponse).output;
-          return o.message || o.code || undefined;
+        isComplete: (data) => (data as DashScopeTaskResponse).output.task_status === "SUCCEEDED",
+        isFailed: (data) => (data as DashScopeTaskResponse).output.task_status === "FAILED",
+        getStatus: (data) => (data as DashScopeTaskResponse).output.task_status,
+        getErrorMessage: (data) => {
+          const output = (data as DashScopeTaskResponse).output;
+          return output.message || output.code || undefined;
         },
       });
     });
@@ -341,12 +369,11 @@ export default defineCommand({
 
     // Collect video URLs from all results
     const videos: Array<{ taskId: string; videoUrl: string }> = [];
-    for (let i = 0; i < results.length; i++) {
-      const result = results[i]!;
+    for (const [resultIndex, result] of results.entries()) {
       const videoUrl =
         result.output.video_url || (result.output.results && result.output.results[0]?.url);
       if (videoUrl) {
-        videos.push({ taskId: taskIds[i]!, videoUrl });
+        videos.push({ taskId: taskIds[resultIndex]!, videoUrl });
       }
     }