bailian-cli-core 1.3.3 → 1.4.0

package/dist/index.d.mts

@@ -604,7 +604,6 @@ interface ConfigFile {
   api_key?: string;
   /** OAuth-style token from `bl auth login --console` callback; sent as `Authorization: Bearer …` */
   access_token?: string;
-  region?: Region;
   base_url?: string;
   output?: "text" | "json";
   output_dir?: string;
@@ -617,7 +616,9 @@ interface ConfigFile {
   access_key_id?: string;
   access_key_secret?: string;
   workspace_id?: string;
-  console_gateway_url?: string;
+  console_site?: "domestic" | "international";
+  console_region?: string;
+  console_switch_agent?: number;
   telemetry?: boolean;
 }
 declare function parseConfigFile(raw: unknown): ConfigFile;
@@ -630,9 +631,7 @@ interface Config {
   /** `access_token` in config file (console login). */
   fileAccessToken?: string;
   fileApiKey?: string;
-  fileRegion?: Region;
   configPath?: string;
-  region: Region;
   baseUrl: string;
   output: "text" | "json";
   outputDir?: string;
@@ -645,7 +644,9 @@ interface Config {
   accessKeyId?: string;
   accessKeySecret?: string;
   workspaceId?: string;
-  consoleGatewayUrl: string;
+  consoleSite?: "domestic" | "international";
+  consoleRegion?: string;
+  consoleSwitchAgent?: number;
   verbose: boolean;
   quiet: boolean;
   noColor: boolean;
@@ -792,23 +793,36 @@ interface ServerSentEvent {
 declare function parseSSE(response: Response): AsyncGenerator<ServerSentEvent>;
 //#endregion
 //#region src/console/gateway.d.ts
+type ConsoleSite = "domestic" | "international";
+/** Resolved console gateway settings (same defaults as {@link callConsoleGateway}). */
+declare function effectiveConsoleGatewayConfig(config: Config): {
+  consoleRegion: string;
+  consoleSite: ConsoleSite;
+  consoleSwitchAgent?: number;
+};
 interface ConsoleGatewayRequest {
   /** Console API name, e.g. zeldaEasy.broadscope-bailian.freeTrial.queryFreeTierQuota */
   api: string;
   data: Record<string, unknown>;
-  /** Console region (default: cn-beijing), distinct from DashScope `config.region`. */
+  /** Console region (e.g. cn-beijing, ap-southeast-1). Falls back to config.consoleRegion, then "cn-beijing". */
   region?: string;
+  /** Console site. Falls back to config.consoleSite, then "domestic". */
+  site?: ConsoleSite;
+  /** Switch-agent UID for delegated access. Falls back to config.consoleSwitchAgent. */
+  switchAgent?: number;
 }
 /**
  * Invoke a Bailian **console** OpenAPI via the CLI gateway (`/cli/api.json`).
  * `token` is the console `access_token` (from `bl auth login --console`); when
  * omitted the request is sent without an Authorization header, which works for
  * public console APIs that don't require a login session.
+ *
+ * Gateway URL and action are resolved from `region + site` via {@link REGION_GATEWAYS}.
+ * Each parameter falls back to the corresponding config value, then to a hardcoded default.
  */
 declare function callConsoleGateway(config: Config, token: string | undefined, {
   api,
-  data,
-  region
+  data
 }: ConsoleGatewayRequest): Promise<unknown>;
 //#endregion
 //#region src/console/models.d.ts
@@ -818,7 +832,6 @@ interface ModelListParams {
   name?: string;
   providers?: string[];
   capabilities?: string[];
-  region?: string;
 }
 interface ModelListResult {
   total: number;
@@ -840,6 +853,9 @@ interface GlobalFlags {
   help: boolean;
   nonInteractive: boolean;
   async: boolean;
+  consoleRegion?: string;
+  consoleSite?: string;
+  consoleSwitchAgent?: number;
   [key: string]: unknown;
 }
 //#endregion
@@ -903,6 +919,7 @@ interface Command {
   usage?: string;
   options?: OptionDef[];
   examples?: string[];
+  skipDefaultApiKeySetup?: boolean;
   notes?: string[];
   execute: (config: Config, flags: GlobalFlags) => Promise<void>;
 }
@@ -912,6 +929,7 @@ interface CommandSpec {
   usage?: string;
   options?: OptionDef[];
   examples?: string[];
+  skipDefaultApiKeySetup?: boolean;
   notes?: string[];
   run: (config: Config, flags: GlobalFlags) => Promise<void>;
 }
@@ -1009,7 +1027,6 @@ interface TrackingEvent {
   httpStatus?: number;
   requestId?: string;
   cliVersion: string;
-  region: string;
   nodeVersion: string;
   os: string;
   authMethod?: string;
@@ -1025,7 +1042,6 @@ declare function createTrackingEvent(opts: {
     requestId?: string;
   };
   cliVersion: string;
-  region: string;
   authMethod?: string;
   params?: Record<string, unknown>;
 }): TrackingEvent;
@@ -1235,4 +1251,4 @@ interface ModelSource {
   load(): Promise<ModelProfile[]>;
 }
 //#endregion
-export { AkSignConfig, type ApiErrorBody, AppCompletionRequest, AppCompletionResponse, AppStreamChunk, AuthMethod, BAILIAN_HOST, BailianError, Budget, Budgets, CHANNEL, CONSOLE_GATEWAY_NO_TOKEN_MESSAGE, Capabilities, Capability, ChatChoice, ChatMessage, ChatMessageContent, ChatRequest, ChatResponse, ChatTool, Command, CommandSpec, Complexities, Complexity, Config, ConfigFile, ConsoleGatewayRequest, ContextNeed, ContextNeeds, DOCS_HOSTS, DashScopeASRRequest, DashScopeASRTaskResult, DashScopeAsyncResponse, DashScopeImageRequest, DashScopeImageSyncResponse, DashScopeKnowledgeRetrieveRequest, DashScopeKnowledgeRetrieveResponse, DashScopeTTSRequest, DashScopeTTSResponse, DashScopeTTSStreamChunk, DashScopeTaskResponse, DashScopeVideoEditRequest, DashScopeVideoRefRequest, DashScopeVideoRequest, ExitCode, Feature, Features, GLOBAL_OPTIONS, GetModelsOptions, GlobalFlags, IntentProfile, IntentSegment, KnowledgeRetrieveRequest, KnowledgeRetrieveResponse, McpClient, McpTool, McpToolResult, MemoryAddRequest, MemoryAddResponse, MemoryMessage, MemoryNode, MemoryNodeListResponse, MemoryNodeUpdateRequest, MemorySearchRequest, MemorySearchResponse, Modalities, Modality, ModelCategories, ModelCategory, ModelListParams, ModelListResult, ModelPreference, ModelPrice, ModelProfile, ModelSource, OptionDef, OutputFormat, PipelineResult, PipelineStep, PreferenceMode, ProfileAttribute, ProfileSchemaCreateRequest, ProfileSchemaCreateResponse, QpmLimit, QualityPreference, QualityPreferences, REGIONS, RecommendOptions, RecommendResult, RecommendedModel, Region, RequestOpts, ResolvedCredential, SOURCE_CONFIG, ScoredCandidate, ServerSentEvent, SingleResult, StreamChoice, StreamChunk, TAGS, TrackingEvent, UserProfileResponse, analyzeIntent, appCompletionEndpoint, bailianMcpUrl, buildDocLink, callConsoleGateway, chatEndpoint, clearApiKey, createTrackingEvent, defineCommand, detectOutputFormat, ensureConfigDir, fetchModelList, flushTelemetry, formatErrorJson, formatJson, formatOutput, formatText, generateFilename, generateToolSchema, getConfigDir, getConfigPath, getCredentialsPath, getModels, imageEndpoint, imageSyncEndpoint, isCI, isInteractive, isLocalFile, isSemanticAvailable, knowledgeRetrieveEndpoint, loadApiKeyFromConfig, loadConfig, localSink, mapApiError, maskToken, mcpWebSearchEndpoint, memoryAddEndpoint, memoryListEndpoint, memoryNodeEndpoint, memorySearchEndpoint, parseBooleanValue, parseConfigFile, parseOptionalBooleanValue, parseSSE, profileSchemaEndpoint, rankModels, readConfigFile, recallCandidates, recallSemantic, remoteSink, request, requestJson, resolveBooleanFlag, resolveConsoleGatewayCredential, resolveCredential, resolveFileUrl, resolveOutputDir, resolveWatermark, saveApiKeyToConfig, signRequest, speechRecognizeEndpoint, speechSynthesizeEndpoint, stripUndefined, taskEndpoint, trackCommandExecution, trackingHeaders, uploadFile, userProfileEndpoint, videoGenerateEndpoint, writeConfigFile };
+export { AkSignConfig, type ApiErrorBody, AppCompletionRequest, AppCompletionResponse, AppStreamChunk, AuthMethod, BAILIAN_HOST, BailianError, Budget, Budgets, CHANNEL, CONSOLE_GATEWAY_NO_TOKEN_MESSAGE, Capabilities, Capability, ChatChoice, ChatMessage, ChatMessageContent, ChatRequest, ChatResponse, ChatTool, Command, CommandSpec, Complexities, Complexity, Config, ConfigFile, ConsoleGatewayRequest, ConsoleSite, ContextNeed, ContextNeeds, DOCS_HOSTS, DashScopeASRRequest, DashScopeASRTaskResult, DashScopeAsyncResponse, DashScopeImageRequest, DashScopeImageSyncResponse, DashScopeKnowledgeRetrieveRequest, DashScopeKnowledgeRetrieveResponse, DashScopeTTSRequest, DashScopeTTSResponse, DashScopeTTSStreamChunk, DashScopeTaskResponse, DashScopeVideoEditRequest, DashScopeVideoRefRequest, DashScopeVideoRequest, ExitCode, Feature, Features, GLOBAL_OPTIONS, GetModelsOptions, GlobalFlags, IntentProfile, IntentSegment, KnowledgeRetrieveRequest, KnowledgeRetrieveResponse, McpClient, McpTool, McpToolResult, MemoryAddRequest, MemoryAddResponse, MemoryMessage, MemoryNode, MemoryNodeListResponse, MemoryNodeUpdateRequest, MemorySearchRequest, MemorySearchResponse, Modalities, Modality, ModelCategories, ModelCategory, ModelListParams, ModelListResult, ModelPreference, ModelPrice, ModelProfile, ModelSource, OptionDef, OutputFormat, PipelineResult, PipelineStep, PreferenceMode, ProfileAttribute, ProfileSchemaCreateRequest, ProfileSchemaCreateResponse, QpmLimit, QualityPreference, QualityPreferences, REGIONS, RecommendOptions, RecommendResult, RecommendedModel, Region, RequestOpts, ResolvedCredential, SOURCE_CONFIG, ScoredCandidate, ServerSentEvent, SingleResult, StreamChoice, StreamChunk, TAGS, TrackingEvent, UserProfileResponse, analyzeIntent, appCompletionEndpoint, bailianMcpUrl, buildDocLink, callConsoleGateway, chatEndpoint, clearApiKey, createTrackingEvent, defineCommand, detectOutputFormat, effectiveConsoleGatewayConfig, ensureConfigDir, fetchModelList, flushTelemetry, formatErrorJson, formatJson, formatOutput, formatText, generateFilename, generateToolSchema, getConfigDir, getConfigPath, getCredentialsPath, getModels, imageEndpoint, imageSyncEndpoint, isCI, isInteractive, isLocalFile, isSemanticAvailable, knowledgeRetrieveEndpoint, loadApiKeyFromConfig, loadConfig, localSink, mapApiError, maskToken, mcpWebSearchEndpoint, memoryAddEndpoint, memoryListEndpoint, memoryNodeEndpoint, memorySearchEndpoint, parseBooleanValue, parseConfigFile, parseOptionalBooleanValue, parseSSE, profileSchemaEndpoint, rankModels, readConfigFile, recallCandidates, recallSemantic, remoteSink, request, requestJson, resolveBooleanFlag, resolveConsoleGatewayCredential, resolveCredential, resolveFileUrl, resolveOutputDir, resolveWatermark, saveApiKeyToConfig, signRequest, speechRecognizeEndpoint, speechSynthesizeEndpoint, stripUndefined, taskEndpoint, trackCommandExecution, trackingHeaders, uploadFile, userProfileEndpoint, videoGenerateEndpoint, writeConfigFile };

package/dist/index.mjs

@@ -108,15 +108,11 @@ const DOCS_HOSTS = {
 	intl: "https://help.aliyun.com/zh/model-studio"
 };
 const BAILIAN_HOST = "https://bailian.cn-beijing.aliyuncs.com";
-const VALID_REGIONS = new Set([
-	"cn",
-	"us",
-	"intl"
-]);
 const VALID_OUTPUTS = new Set(["text", "json"]);
+const VALID_CONSOLE_SITES = new Set(["domestic", "international"]);
 /**
-* A syntactically valid absolute http(s) URL. Used to validate `base_url` and
-* `console_gateway_url` from the config file: the credential-bearing client
+* A syntactically valid absolute http(s) URL. Used to validate `base_url`
+* from the config file: the credential-bearing client
 * sends the Bearer token to these origins, so a bare `startsWith("http")` check
 * (which also accepts e.g. "httpfoo://…") is too loose.
 */
@@ -135,7 +131,6 @@ function parseConfigFile(raw) {
 	if (typeof obj.api_key === "string") out.api_key = obj.api_key;
 	if (typeof obj.access_token === "string" && obj.access_token.length > 0) out.access_token = obj.access_token;
 	else if (typeof obj.accessToken === "string" && obj.accessToken.length > 0) out.access_token = obj.accessToken;
-	if (typeof obj.region === "string" && VALID_REGIONS.has(obj.region)) out.region = obj.region;
 	if (typeof obj.base_url === "string" && isHttpUrl(obj.base_url)) out.base_url = obj.base_url;
 	if (typeof obj.output === "string" && VALID_OUTPUTS.has(obj.output)) out.output = obj.output;
 	if (typeof obj.output_dir === "string" && obj.output_dir.length > 0) out.output_dir = obj.output_dir;
@@ -148,7 +143,9 @@ function parseConfigFile(raw) {
 	if (typeof obj.access_key_id === "string" && obj.access_key_id.length > 0) out.access_key_id = obj.access_key_id;
 	if (typeof obj.access_key_secret === "string" && obj.access_key_secret.length > 0) out.access_key_secret = obj.access_key_secret;
 	if (typeof obj.workspace_id === "string" && obj.workspace_id.length > 0) out.workspace_id = obj.workspace_id;
-	if (typeof obj.console_gateway_url === "string" && isHttpUrl(obj.console_gateway_url)) out.console_gateway_url = obj.console_gateway_url;
+	if (typeof obj.console_site === "string" && VALID_CONSOLE_SITES.has(obj.console_site)) out.console_site = obj.console_site;
+	if (typeof obj.console_region === "string" && obj.console_region.length > 0) out.console_region = obj.console_region;
+	if (typeof obj.console_switch_agent === "number" && obj.console_switch_agent > 0) out.console_switch_agent = obj.console_switch_agent;
 	if (typeof obj.telemetry === "boolean") out.telemetry = obj.telemetry;
 	return out;
 }
@@ -232,10 +229,7 @@ function loadConfig(flags) {
 	const fileApiKey = file.api_key;
 	const accessTokenEnv = process.env.DASHSCOPE_ACCESS_TOKEN?.trim() || void 0;
 	const fileAccessToken = file.access_token?.trim() || void 0;
-	const explicitRegion = flags.region || process.env.DASHSCOPE_REGION || void 0;
-	const cachedRegion = file.region;
-	const region = explicitRegion || cachedRegion || "cn";
-	const baseUrl = flags.baseUrl || process.env.DASHSCOPE_BASE_URL || file.base_url || REGIONS[region] || REGIONS.cn;
+	const baseUrl = flags.baseUrl || file.base_url || process.env.DASHSCOPE_BASE_URL || REGIONS.cn;
 	const output = detectOutputFormat(flags.output || process.env.DASHSCOPE_OUTPUT || file.output);
 	const envTimeout = process.env.DASHSCOPE_TIMEOUT ? Number(process.env.DASHSCOPE_TIMEOUT) : void 0;
 	const validEnvTimeout = envTimeout !== void 0 && Number.isFinite(envTimeout) && envTimeout > 0 ? envTimeout : void 0;
@@ -246,9 +240,7 @@ function loadConfig(flags) {
 		accessTokenEnv,
 		fileAccessToken,
 		fileApiKey,
-		fileRegion: file.region,
 		configPath: getConfigPath(),
-		region,
 		baseUrl,
 		output,
 		outputDir: file.output_dir || void 0,
@@ -261,7 +253,9 @@ function loadConfig(flags) {
 		accessKeyId: process.env.ALIBABA_CLOUD_ACCESS_KEY_ID || file.access_key_id || void 0,
 		accessKeySecret: process.env.ALIBABA_CLOUD_ACCESS_KEY_SECRET || file.access_key_secret || void 0,
 		workspaceId: process.env.BAILIAN_WORKSPACE_ID || file.workspace_id || void 0,
-		consoleGatewayUrl: process.env.BAILIAN_CONSOLE_GATEWAY_URL || file.console_gateway_url || "https://bailian-cs.console.aliyun.com",
+		consoleSite: flags.consoleSite || file.console_site || void 0,
+		consoleRegion: flags.consoleRegion || file.console_region || void 0,
+		consoleSwitchAgent: flags.consoleSwitchAgent || file.console_switch_agent || void 0,
 		verbose: flags.verbose || process.env.DASHSCOPE_VERBOSE === "1",
 		quiet: flags.quiet || false,
 		noColor: flags.noColor || process.env.NO_COLOR !== void 0 || !process.stdout.isTTY,
@@ -722,9 +716,47 @@ async function* parseSSE(response) {
 }
 //#endregion
 //#region src/console/gateway.ts
-const GATEWAY_ACTION = "BroadScopeAspnGateway";
 const GATEWAY_PRODUCT = "sfm_bailian";
-function buildGatewayParams(api, data) {
+const REGION_GATEWAYS = {
+	"cn-beijing": {
+		domestic: {
+			csGateway: "bailian-cs.console.aliyun.com",
+			action: "BroadScopeAspnGateway"
+		},
+		international: {
+			csGateway: "bailian-cs.console.alibabacloud.com",
+			action: "BroadScopeAspnGateway"
+		}
+	},
+	"ap-southeast-1": {
+		domestic: {
+			csGateway: "modelstudio-cs.console.aliyun.com",
+			action: "IntlBroadScopeAspnGateway"
+		},
+		international: {
+			csGateway: "bailian-singapore-cs.alibabacloud.com",
+			action: "IntlBroadScopeAspnGateway"
+		}
+	}
+};
+function resolveGateway(region, site) {
+	return REGION_GATEWAYS[region]?.[site] ?? REGION_GATEWAYS["cn-beijing"][site];
+}
+/** Resolved console gateway settings (same defaults as {@link callConsoleGateway}). */
+function effectiveConsoleGatewayConfig(config) {
+	const consoleRegion = config.consoleRegion ?? "cn-beijing";
+	const consoleSite = config.consoleSite ?? "domestic";
+	const consoleSwitchAgent = config.consoleSwitchAgent;
+	return consoleSwitchAgent != null ? {
+		consoleRegion,
+		consoleSite,
+		consoleSwitchAgent
+	} : {
+		consoleRegion,
+		consoleSite
+	};
+}
+function buildGatewayParams(api, data, switchAgent) {
 	return JSON.stringify({
 		Api: api,
 		V: "1.0",
@@ -735,6 +767,7 @@ function buildGatewayParams(api, data) {
 				console: "ONE_CONSOLE",
 				productCode: "p_efm",
 				consoleSite: "BAILIAN_ALIYUN",
+				...switchAgent != null ? { switchAgent } : {},
 				...typeof data.cornerstoneParam === "object" && data.cornerstoneParam !== null ? data.cornerstoneParam : {}
 			}
 		}
@@ -745,21 +778,27 @@ function buildGatewayParams(api, data) {
 * `token` is the console `access_token` (from `bl auth login --console`); when
 * omitted the request is sent without an Authorization header, which works for
 * public console APIs that don't require a login session.
+*
+* Gateway URL and action are resolved from `region + site` via {@link REGION_GATEWAYS}.
+* Each parameter falls back to the corresponding config value, then to a hardcoded default.
 */
-async function callConsoleGateway(config, token, { api, data, region = "cn-beijing" }) {
-	const params = buildGatewayParams(api, data);
+async function callConsoleGateway(config, token, { api, data }) {
+	const { consoleRegion: effectiveRegion, consoleSite: effectiveSite, consoleSwitchAgent: effectiveSwitchAgent } = effectiveConsoleGatewayConfig(config);
+	const resolved = resolveGateway(effectiveRegion, effectiveSite);
+	const gatewayBase = `https://${resolved.csGateway}`;
+	const action = resolved.action;
+	const params = buildGatewayParams(api, data, effectiveSwitchAgent);
 	const body = new URLSearchParams({
 		params,
-		region
+		region: effectiveRegion
 	});
 	const timeoutMs = config.timeout * 1e3;
-	const gatewayBase = config.consoleGatewayUrl;
 	const headers = {
 		Accept: "*/*",
 		"Content-Type": "application/x-www-form-urlencoded"
 	};
 	if (token) headers.Authorization = `Bearer ${token}`;
-	const res = await fetch(`${gatewayBase}/cli/api.json?action=${GATEWAY_ACTION}&product=${GATEWAY_PRODUCT}&api=${encodeURIComponent(api)}`, {
+	const res = await fetch(`${gatewayBase}/cli/api.json?action=${action}&product=${GATEWAY_PRODUCT}&api=${encodeURIComponent(api)}`, {
 		method: "POST",
 		headers,
 		body: body.toString(),
@@ -771,14 +810,19 @@ async function callConsoleGateway(config, token, { api, data, region = "cn-beiji
 	}
 	const json = await res.json();
 	const innerData = json.data;
-	if (innerData?.success === false && innerData.errorCode) throw new BailianError(`Console gateway error: ${innerData.errorCode}`, ExitCode.GENERAL, typeof innerData.errorMsg === "string" ? innerData.errorMsg : void 0);
+	if (innerData?.success === false && innerData.errorCode) {
+		const errorCode = String(innerData.errorCode);
+		const notLogined = errorCode.includes("NotLogined");
+		const errorMsg = typeof innerData.errorMsg === "string" ? innerData.errorMsg : void 0;
+		throw new BailianError(notLogined ? "Console session is not logged in or has expired." : `Console gateway error: ${errorCode}`, notLogined ? ExitCode.AUTH : ExitCode.GENERAL, notLogined ? "Run `bl auth login --console` to sign in or refresh your console session." : errorMsg && errorMsg !== errorCode ? errorMsg : void 0);
+	}
 	return json;
 }
 //#endregion
 //#region src/console/models.ts
 const MODEL_LIST_API = "zeldaHttp.dashscopeModel./zelda/api/v1/modelCenter/listFoundationModels";
 async function fetchModelList(config, token, params = {}) {
-	const { pageNo = 1, pageSize = 50, name = "", providers = [], capabilities = [], region = "cn-beijing" } = params;
+	const { pageNo = 1, pageSize = 50, name = "", providers = [], capabilities = [] } = params;
 	const result = await callConsoleGateway(config, token, {
 		api: MODEL_LIST_API,
 		data: { input: {
@@ -791,8 +835,7 @@ async function fetchModelList(config, token, params = {}) {
 			group: true,
 			capabilities,
 			contextWindows: []
-		} },
-		region
+		} }
 	});
 	const responseData = result?.data?.DataV2?.data ?? result?.data ?? {};
 	const total = responseData?.data?.total ?? responseData?.total ?? 0;
@@ -921,6 +964,7 @@ function defineCommand(spec) {
 		usage: spec.usage,
 		options: spec.options,
 		examples: spec.examples,
+		skipDefaultApiKeySetup: spec.skipDefaultApiKeySetup,
 		notes: spec.notes,
 		execute: (config, flags) => spec.run(config, flags)
 	};
@@ -931,10 +975,6 @@ const GLOBAL_OPTIONS = [
 		flag: "--api-key <key>",
 		description: "API key"
 	},
-	{
-		flag: "--region <region>",
-		description: "API region: cn (default), us, intl"
-	},
 	{
 		flag: "--base-url <url>",
 		description: "API base URL"
@@ -973,6 +1013,19 @@ const GLOBAL_OPTIONS = [
 		description: "Run N parallel requests (default: 1)",
 		type: "number"
 	},
+	{
+		flag: "--console-region <region>",
+		description: "Console gateway region (e.g. cn-beijing, ap-southeast-1)"
+	},
+	{
+		flag: "--console-site <site>",
+		description: "Console site: domestic, international"
+	},
+	{
+		flag: "--console-switch-agent <uid>",
+		description: "Switch agent UID for delegated access",
+		type: "number"
+	},
 	{
 		flag: "--help",
 		description: "Show help"
@@ -1151,7 +1204,6 @@ function createTrackingEvent(opts) {
 		durationMs: opts.durationMs,
 		success: opts.success,
 		cliVersion: opts.cliVersion,
-		region: opts.region,
 		nodeVersion: process.version,
 		os: process.platform
 	};
@@ -2058,7 +2110,6 @@ const GLOBAL_FLAG_KEYS = new Set([
 	"help",
 	"nonInteractive",
 	"async",
-	"region",
 	"console"
 ]);
 /**
@@ -2156,7 +2207,6 @@ async function trackCommandExecution(config, commandPath, flags, fn) {
 				requestId
 			},
 			cliVersion: config.clientVersion ?? "unknown",
-			region: config.region,
 			authMethod,
 			params: extractParams(flags)
 		});
@@ -2360,197 +2410,182 @@ const ModelCategories = {
 };
 //#endregion
 //#region src/advisor/constants/prompts.ts
-const INTENT_MODEL = "qwen-turbo";
+const INTENT_MODEL = "qwen-flash";
 const RANKING_MODEL = "qwen3.6-flash";
-const RANKING_MODEL_FAST = "qwen-turbo";
-const INTENT_SYSTEM_PROMPT = `你是一个意图分析器。根据用户的需求描述，先理解用户场景，再提取结构化信息。
-
-## 分析步骤
-1. 用一句话总结用户的核心需求（taskSummary），要体现具体场景而非泛泛描述
-2. 推断场景特征（scenarioHints），例如：["需要低延迟","面向C端用户","高并发","对话式交互","离线批处理","需要精准度"]
-3. 基于场景特征推断 budget 和 qualityPreference
-   - 只在用户明确表达或场景强烈暗示时偏离默认值
-   - 用户明确说"低成本"、"便宜"、"省钱" → budget:"low"
-   - 用户明确说"最好的"、"高精度"、"不计成本" → qualityPreference:"flagship"
-   - 场景本身有强约束时才推断：如"日均百万请求的客服" → budget:"low"（高并发=成本敏感）
-   - 其他情况保持 budget:"medium", qualityPreference:"balanced"
-4. 提取模态、能力、特性等结构化字段
-
-## 示例
-
-用户: "做一个低成本高并发的在线客服"
-→ budget:"low", qualityPreference:"cost-optimized"（用户明确说了低成本）
+const RANKING_MODEL_FAST = "qwen-flash";
+const INTENT_SYSTEM_PROMPT = `You are an intent analyzer. Given the user's requirement, understand the scenario first, then extract structured information.
 
-用户: "法律合同审查，要求高精准度"
-→ budget:"medium", qualityPreference:"flagship"（用户明确要求高精准度，但没提预算）
+CRITICAL: You MUST respond entirely in English. Do not use any Chinese characters anywhere in your response. All text fields (taskSummary, scenarioHints) must be in English.
 
-用户: "我要做一个能理解图片的客服机器人"
-→ budget:"medium", qualityPreference:"balanced"（用户没提成本和质量要求，不过度推断）
+## Analysis Steps
+1. Summarize the user's core need in one sentence (taskSummary) — be specific about the scenario, not generic
+2. Infer scenario hints (scenarioHints), e.g.: ["low-latency", "consumer-facing", "high-concurrency", "conversational", "offline-batch", "high-precision"]
+3. Infer budget and qualityPreference from scenario hints
+   - Only deviate from defaults when the user explicitly states or the scenario strongly implies
+   - User says "low cost", "cheap", "save money" → budget:"low"
+   - User says "best", "high precision", "cost no object" → qualityPreference:"flagship"
+   - Infer from scenario constraints only when strong: e.g. "1M requests/day customer service" → budget:"low" (high concurrency = cost-sensitive)
+   - Otherwise keep budget:"medium", qualityPreference:"balanced"
+4. Extract modalities, capabilities, features etc.
 
-用户: "帮我选一个写代码的模型"
-→ budget:"medium", qualityPreference:"balanced"（通用需求，无明确倾向）
+## Model preference detection
+Analyze whether the user mentioned specific models, model families, or vendors:
+- No models/families/vendors mentioned → mode:"unconstrained", no targets
+- User scoped the range (e.g. "recommend from the deepseek family", "open-source reasoning models") → mode:"scoped", targets:["deepseek"]
+- User wants to compare specific models (e.g. "compare wan2.6 and wan2.7", "is qwen-max good for legal analysis") → mode:"comparison", targets:["wan2.6","wan2.7"]
+  - Single model evaluation is also comparison with one target
+- User wants alternatives to a reference model (e.g. "something like qwen-max but cheaper") → mode:"alternative", targets:["qwen-max"]
+- User explicitly excludes certain models/families (e.g. "good models besides qwen") → excludes:["qwen"], mode determined by other signals
+- targets should capture the model/family names as the user wrote them
 
-用户: "预算有限，做个简单的文本摘要功能"
-→ budget:"low", qualityPreference:"cost-optimized"（用户说了预算有限）
-
-用户: "企业级知识库问答，准确率是第一优先级"
-→ budget:"high", qualityPreference:"flagship"（企业级+准确率第一=愿投入高成本）
+## Output fields
+- taskSummary: one-sentence scenario understanding (must be specific, never generic like "user wants AI")
+- scenarioHints: array of inferred scenario features
+- complexity: "single" or "pipeline"
+- segments: only for pipeline, each with step/inputModality/outputModality/requiredCapabilities
+  - step must describe the specific problem this step solves in the user's task, no numbered or generic modal labels
+  - segments must form a modality chain: each step's inputModality should cover the previous step's outputModality
+- inputModality: user input modalities ["Text","Image","Video","Audio"]
+- outputModality: expected output modalities
+- requiredCapabilities: capability codes (use strictly from the list, don't invent):
+  TG=Text Generation, Reasoning=Reasoning, VU=Vision Understanding, IG=Image Generation, VG=Video Generation,
+  TTS=Text-to-Speech, ASR=Speech-to-Text, Realtime-ASR=Realtime Speech-to-Text,
+  Realtime-Text-to-Speech=Realtime Text-to-Speech, Realtime-Audio-Translate=Realtime Audio Translation,
+  Realtime-Omni=Realtime Omni-modal, Multimodal-Omni=Multimodal Omni, ME=Multimodal Embedding,
+  TR=Translation, 3D-generation=3D Generation
+- requiredFeatures: required features (function-calling, web-search, structured-outputs, prefix-completion)
+- budget: "low"/"medium"/"high"
+- contextNeed: "standard"/"large"/"extra-large"
+- qualityPreference: "flagship"/"balanced"/"cost-optimized"
+- modelPreference: { mode, targets?, excludes? }
 
-用户: "个人学习项目，试试AI生成图片"
-→ budget:"low", qualityPreference:"cost-optimized"（个人学习=成本敏感）
+Output only JSON, no other text.`;
+const SINGLE_SYSTEM_PROMPT = `You are a model recommendation advisor for Alibaba Cloud Model Studio. From the candidate models below, select the best recommendations.
 
-用户: "做一个Agent自动根据用户意图生成动画片"
-→ budget:"medium", qualityPreference:"balanced"（复杂pipeline，但没明确成本/质量约束）
+CRITICAL: You MUST respond entirely in English. Do not use any Chinese characters anywhere in your response. Every field — reason, highlights, step, summary — must be written in English.
 
-## 模型偏好识别
-分析用户是否提到了特定的模型、模型系列或厂商，据此判断推荐模式：
-- 用户未提到任何模型/系列/厂商 → mode:"unconstrained"，不填 targets
-- 用户限定了范围（如"deepseek系列哪个好"、"通义千问的模型推荐"、"开源的推理模型"） → mode:"scoped"，targets:["deepseek"] 或 ["通义千问"]
-- 用户要对比特定模型（如"wan2.6和wan2.7哪个好"、"qwen-max和deepseek-v3对比"、"qwen-max适合做法律分析吗"） → mode:"comparison"，targets:["wan2.6","wan2.7"]
-  - 单模型评估也算 comparison，targets 只填一个
-- 用户以某模型为参照找替代（如"有没有类似qwen-max但更便宜的"） → mode:"alternative"，targets:["qwen-max"]
-- 用户明确排除某些模型/系列（如"除了qwen还有什么好的"） → excludes:["qwen"]，mode 根据其他条件判断
-- targets 填写用户原文中的模型/系列名称，保持原文写法
+## Background
+The system has pre-filtered candidate models based on intent analysis. Your job is to rank and pick from these candidates.
+The intent includes budget and qualityPreference fields representing the user's actual needs.
 
-## 输出字段
-- taskSummary: 一句话场景理解（必须具体，禁止"用户想用AI做某事"这种废话）
-- scenarioHints: 推断的场景特征数组
-- complexity: "single"（单一模型可完成）或 "pipeline"（需要多个模型协同）
-- segments: 仅 pipeline 时填写，每步包含 step/inputModality/outputModality/requiredCapabilities。
-  - step 必须是一句话描述该步骤在用户任务中解决的具体问题，例如"解析天气预报数据，生成适合视频制作的场景描述文本"，禁止用编号或泛化的模态标签
-  - segments 必须形成模态链路：每步的 inputModality 应包含上一步的 outputModality，确保上下游数据可以衔接
-- inputModality: 用户输入涉及的模态 ["Text","Image","Video","Audio"]
-- outputModality: 期望输出的模态
-- requiredCapabilities: 需要的能力。可选代码（必须严格使用，不要自创）：
-  TG=文本生成, Reasoning=推理, VU=视觉理解, IG=图像生成, VG=视频生成,
-  TTS=语音合成, ASR=语音识别, Realtime-ASR=实时语音识别,
-  Realtime-Text-to-Speech=实时语音合成, Realtime-Audio-Translate=实时音频翻译,
-  Realtime-Omni=实时全模态, Multimodal-Omni=全模态, ME=多模态嵌入,
-  TR=翻译, 3D-generation=3D生成
-- requiredFeatures: 需要的特性 (function-calling, web-search, structured-outputs, prefix-completion)
-- budget: "low"/"medium"/"high"（基于场景推断，不要默认 medium）
-- contextNeed: "standard"/"large"/"extra-large"
-- qualityPreference: "flagship"/"balanced"/"cost-optimized"（基于场景推断，不要默认 balanced）
-- modelPreference: { mode, targets?, excludes? }（见上方"模型偏好识别"）
+## Recommendation Strategy
 
-只输出 JSON，不要有其他文字。`;
-const SINGLE_SYSTEM_PROMPT = `你是阿里云百炼平台的模型推荐顾问。从以下候选模型中选出最佳推荐。
+Recommend 3 models at different tiers, but ordering must reflect the user's true needs:
 
-## 背景
-系统已根据用户意图预筛选了候选模型，你只需从中精选并排序。
-意图分析中包含 budget 和 qualityPreference 字段，这代表了用户的实际需求层次。
+- #1 (Best Pick): Based on budget and qualityPreference, pick the best-fitting tier and put its top model first
+- #2 (Runner-Up): A worthy consideration from another tier, explaining tradeoffs vs #1
+- #3 (Alternative): A third-perspective choice, explaining scenario differences
 
-## 推荐策略
+Key principles:
+- budget:"low" / qualityPreference:"cost-optimized" → #1 should be the best value model, not a flagship
+- budget:"high" / qualityPreference:"flagship" → #1 should be the most capable flagship model
+- budget:"medium" / qualityPreference:"balanced" → #1 should be the best all-around match
 
-推荐 3 个不同档次的模型，但排序必须反映用户的真实需求：
+Each recommendation must explain why the model fits (or as an alternative, why it's worth considering), with reasoning tied to the user's specific needs.
 
-- 推荐 #1（最佳推荐）：根据 budget 和 qualityPreference 判断哪个档次最适合用户，把那个档次的最佳模型放在第一位
-- 推荐 #2（次优选择）：另一个档次中值得考虑的模型，说明与 #1 相比的 tradeoff
-- 推荐 #3（备选参考）：第三个视角的选择，说明适用场景差异
+## Rules
+- Only recommend models from the candidate list — never recommend outside it
+- No generic reasons ("powerful", "good performance", "effective"). Each reason must describe how the model solves a specific aspect of the user's task
+- All three recommendations must have distinct reasoning angles, not duplicate reasons
+- When pricing is available: factor in budget, put the most budget-friendly option first
+- When family info is available: avoid recommending multiple models from the same family, prefer stable versions
+- When version tags are available: prefer stable/latest versions unless the user explicitly needs a specific version
+- Models without enriched fields: rank by capability and description — don't penalize for missing info
+- If no model fits, return an empty array
+- If you believe the task actually requires multi-model collaboration (pipeline), you may output type:"pipeline" format
+- Output strict JSON, no other text
 
-关键原则：
-- budget:"low" / qualityPreference:"cost-optimized" → 推荐 #1 应该是性价比最高的模型，而非旗舰模型
-- budget:"high" / qualityPreference:"flagship" → 推荐 #1 应该是能力最强的旗舰模型
-- budget:"medium" / qualityPreference:"balanced" → 推荐 #1 应该是综合匹配度最高的模型，不预设档次偏好
+## Output Format
 
-每个推荐都必须说明该模型为什么适合（或作为备选为什么值得考虑），理由必须关联用户的具体需求。
+Single task:
+{"type":"single","recommendations":[{"model":"model ID","reason":"recommendation reason","highlights":["key highlights"]}]}
 
-## 规则
-- 只能推荐候选列表中的模型，严禁推荐列表外的模型
-- 严禁使用泛泛的推荐理由（如"性能强大"、"综合能力好"、"效果不错"），每条 reason 必须说明该模型解决用户任务中的什么具体问题
-- 三个推荐的理由不允许雷同，每个必须从不同维度论证
-- 有定价信息时：结合 budget 字段权衡，把最符合用户预算的放在最前面
-- 有家族信息时：避免推荐同一家族的多个模型，优先推荐稳定版本
-- 有版本标签时：优先推荐 stable/latest 版本，除非用户明确需要特定版本
-- 没有增强字段的模型：按能力和描述排序即可，不因缺少信息而降权
-- 如果没有合适的模型，返回空数组
-- 如果你认为该需求实际需要多模型协同完成（pipeline），可以输出 type:"pipeline" 格式
-- 输出严格 JSON，不要输出其他内容
+Pipeline (only when confident multi-model is needed):
+{"type":"pipeline","summary":"one-line solution description","steps":[{"step":"step description","recommendations":[{"model":"model ID","reason":"reason for choosing","highlights":["highlights"]}]}]}`;
+const PIPELINE_SYSTEM_PROMPT = `You are a model recommendation advisor for Alibaba Cloud Model Studio. The user's need has been decomposed into multi-step pipeline. Select the best model for each step.
 
-## 输出格式
+CRITICAL: You MUST respond entirely in English. Do not use any Chinese characters anywhere in your response. Every field — reason, highlights, step, summary — must be written in English.
 
-单一任务：
-{"type":"single","recommendations":[{"model":"模型ID","reason":"推荐理由","highlights":["亮点"]}]}
+## Background
+The system has pre-filtered candidate models for each step's requirements.
+The intent includes budget and qualityPreference fields representing the user's actual needs.
 
-复合任务（仅当你确信需要多模型协同时）：
-{"type":"pipeline","summary":"一句话方案描述","steps":[{"step":"步骤描述","recommendations":[{"model":"模型ID","reason":"选择理由","highlights":["亮点"]}]}]}`;
-const PIPELINE_SYSTEM_PROMPT = `你是阿里云百炼平台的模型推荐顾问。用户需求已被拆解为多步骤流水线，请为每步选出最佳模型。
+## Recommendation Strategy
 
-## 背景
-系统已根据各步骤需求预筛选了候选模型。
-意图分析中包含 budget 和 qualityPreference 字段，这代表了用户的实际需求层次。
+Recommend 3 models at different tiers per step, ordering by user needs:
 
-## 推荐策略
+- #1 (Best Pick): Based on budget and qualityPreference, pick the best-fitting tier and put its top model first
+- #2 (Runner-Up): A worthy consideration from another tier, explaining tradeoffs
+- #3 (Alternative): A third-perspective choice
 
-每步推荐 3 个不同档次的模型，但排序必须反映用户的真实需求：
+Key principles:
+- budget:"low" / qualityPreference:"cost-optimized" → #1 should be the best value model
+- budget:"high" / qualityPreference:"flagship" → #1 should be the most capable flagship model
+- budget:"medium" / qualityPreference:"balanced" → #1 should be the best all-around match
 
-- 推荐 #1（最佳推荐）：根据 budget 和 qualityPreference 判断哪个档次最适合用户，把那个档次的最佳模型放在第一位
-- 推荐 #2（次优选择）：另一个档次中值得考虑的模型，说明 tradeoff
-- 推荐 #3（备选参考）：第三个视角的选择，说明适用场景差异
+## Rules
+- Only recommend models from the candidate list
+- Each step recommends multiple models sorted by priority, each with brief reason and key highlights
+- The "step" field must describe the specific problem this step solves in the user's task — no numbered or generic modal labels (e.g. "Output: Text")
+- No generic reasons. Each reason must describe how the model solves a specific aspect of the user's task at this step
+- When pricing is available: factor in budget, put the most budget-friendly option first
+- When family info is available: avoid using different tiers of the same family in adjacent steps unless truly needed
+- Models without enriched fields: rank by capability and description — don't penalize for missing info
+- Adjacent steps must be modality-compatible: the previous step's output modalities must be supported as input modalities by the next step
+- If you believe the task can be done with a single model, output type:"single" format
+- Output strict JSON
 
-关键原则：
-- budget:"low" / qualityPreference:"cost-optimized" → 推荐 #1 应该是性价比最高的模型
-- budget:"high" / qualityPreference:"flagship" → 推荐 #1 应该是能力最强的旗舰模型
-- budget:"medium" / qualityPreference:"balanced" → 推荐 #1 应该是综合匹配度最高的模型
+## Output Format
 
-## 规则
-- 只能推荐候选列表中的模型
-- 每步推荐多个模型，按优先级排序，每个推荐给出简短理由和关键亮点
-- step 字段必须用一句话描述该步骤在用户任务中解决的具体问题，禁止用编号或泛化的模态标签（如"输出: Text"）
-- 严禁使用泛泛的推荐理由，每条 reason 必须说明该模型在这一步解决用户任务中的什么具体问题
-- 有定价信息时：结合 budget 字段权衡，把最符合用户预算的放在最前面
-- 有家族信息时：避免在相邻步骤使用同一家族的不同规格模型，除非确实需要
-- 没有增强字段的模型：按能力和描述排序即可，不因缺少信息而降权
-- 相邻步骤的模型必须模态兼容：上一步模型的输出模态必须被下一步模型的输入模态支持
-- 如果你认为该需求其实单模型可以完成，可以输出 type:"single" 格式
-- 输出严格 JSON
+{"type":"pipeline","summary":"one-line solution description","steps":[{"step":"specific problem this step solves in the user's task","recommendations":[{"model":"model ID","reason":"how this model solves the specific problem at this step","highlights":["highlights"]}]}]}
 
-## 输出格式
+Or (if single model suffices):
+{"type":"single","recommendations":[{"model":"model ID","reason":"recommendation reason","highlights":
+["key highlights"]}]}`;
+const COMPARISON_SYSTEM_PROMPT = `You are a model comparison advisor for Alibaba Cloud Model Studio. The user wants to compare specific models — analyze them against the use case.
 
-{"type":"pipeline","summary":"一句话方案描述","steps":[{"step":"该步骤在用户任务中解决的具体问题","recommendations":[{"model":"模型ID","reason":"该模型如何解决这一步的具体问题","highlights":["亮点"]}]}]}
+CRITICAL: You MUST respond entirely in English. Do not use any Chinese characters anywhere in your response. Every field — reason, highlights — must be written in English.
 
-或者（如果你认为单模型即可）：
-{"type":"single","recommendations":[{"model":"模型ID","reason":"推荐理由","highlights":["亮点"]}]}`;
-const COMPARISON_SYSTEM_PROMPT = `你是阿里云百炼平台的模型对比顾问。用户想对比特定模型，请根据使用场景进行对比分析。
+## Background
+The user specified models to compare. The system has pre-filtered these models and related candidates into the list.
+The intent's modelPreference.targets are the models to compare.
 
-## 背景
-用户指定了要对比的模型，系统已将这些模型和相关候选预筛选到列表中。
-意图分析中的 modelPreference.targets 是用户要对比的模型。
+## Comparison Strategy
+- All user-specified models must appear in the results, sorted by suitability
+- Each model's reason must be comparative: describe strengths and weaknesses relative to other models being compared
+- If candidates contain better fits than what the user specified, they can be additionally recommended, but user-specified models take priority
+- Single-model evaluation (one target): evaluate if the model fits, and recommend better alternatives
 
-## 对比策略
-- 用户指定的模型必须全部出现在推荐结果中，按适合程度排序
-- 每个模型的 reason 必须是对比性的，说明该模型相对于其他对比模型的优势和劣势
-- 如果候选中有比用户指定的更合适的模型，可以额外推荐，但用户指定的必须优先包含
-- 单模型评估场景（targets 只有一个）：评估该模型是否适合用户需求，同时推荐更优的替代
+## Rules
+- Only recommend models from the candidate list
+- reason must include comparative perspective: how this model is better/worse compared to others
+- highlights should emphasize differentiating characteristics
+- Output strict JSON
 
-## 规则
-- 只能推荐候选列表中的模型
-- reason 必须包含对比视角：该模型相比其他模型在哪些方面更好/更差
-- highlights 突出各模型的差异化特点
-- 输出严格 JSON，不要输出其他内容
+## Output Format
+{"type":"single","recommendations":[{"model":"model ID","reason":"comparative analysis","highlights":["differentiators"]}]}`;
+const ALTERNATIVE_SYSTEM_PROMPT = `You are a model alternative advisor for Alibaba Cloud Model Studio. The user has a reference model and wants to find alternatives.
 
-## 输出格式
-{"type":"single","recommendations":[{"model":"模型ID","reason":"对比分析理由","highlights":["差异化亮点"]}]}`;
-const ALTERNATIVE_SYSTEM_PROMPT = `你是阿里云百炼平台的模型替代顾问。用户以某个模型为参照，寻找替代方案。
+CRITICAL: You MUST respond entirely in English. Do not use any Chinese characters anywhere in your response. Every field — reason, highlights — must be written in English.
 
-## 背景
-用户以某个模型为参照点，想找到在特定维度上更优的替代方案（如更便宜、更快、更强）。
-意图分析中的 modelPreference.targets 是参照模型。
+## Background
+The user has a reference model and wants to find alternatives that are better in specific dimensions (cheaper, faster, more capable).
+The intent's modelPreference.targets is the reference model.
 
-## 替代策略
-- 推荐 #1：如果参照模型在候选中，先评估它是否满足用户需求，给出其基本定位
-- 推荐 #2~#3：推荐替代方案，reason 必须说明相比参照模型在用户关注维度上的 tradeoff
-- 关注用户提到的替代维度（如"更便宜"→重点对比定价，"更强"→重点对比能力）
+## Alternative Strategy
+- #1: If the reference model is in candidates, first evaluate if it meets the user's needs — give its positioning
+- #2~#3: Recommend alternatives. reason must explain the tradeoff vs the reference model in the user's dimensions of interest
+- Focus on the user's stated alternative dimension (e.g. "cheaper" → focus on pricing comparison, "better" → focus on capability comparison)
 
-## 规则
-- 只能推荐候选列表中的模型
-- 参照模型必须包含在结果中（如果在候选列表中）
-- 替代推荐的 reason 必须说明与参照模型的具体差异
-- 避免推荐和参照模型同系列的其他版本（除非确实有显著差异）
-- 输出严格 JSON，不要输出其他内容
+## Rules
+- Only recommend models from the candidate list
+- The reference model must be included in results if it's in the candidate list
+- Alternative recommendations must explain concrete differences from the reference model
+- Avoid recommending other versions from the same family unless there's a significant difference
+- Output strict JSON
 
-## 输出格式
-{"type":"single","recommendations":[{"model":"模型ID","reason":"替代分析理由","highlights":["差异化亮点"]}]}`;
+## Output Format
+{"type":"single","recommendations":[{"model":"model ID","reason":"alternative analysis","highlights":["differentiators"]}]}`;
 //#endregion
 //#region src/advisor/constants/defaults.ts
 const DEFAULT_INTENT = {
@@ -2845,19 +2880,19 @@ async function embedBatch(config, texts) {
 	})).data.sort((left, right) => left.index - right.index).map((item) => item.embedding);
 }
 const CAPABILITY_LABELS = {
-	TG: "文本生成",
-	Reasoning: "推理",
-	VU: "视觉理解",
-	IG: "图像生成",
-	VG: "视频生成",
-	TTS: "语音合成",
-	ASR: "语音识别"
+	TG: "Text Generation",
+	Reasoning: "Reasoning",
+	VU: "Vision Understanding",
+	IG: "Image Generation",
+	VG: "Video Generation",
+	TTS: "Text-to-Speech",
+	ASR: "Speech-to-Text"
 };
 const MODALITY_LABELS = {
-	Text: "文本",
-	Image: "图片/图像",
-	Video: "视频",
-	Audio: "音频/语音"
+	Text: "Text",
+	Image: "Image",
+	Video: "Video",
+	Audio: "Audio"
 };
 function loadGroupDescriptions() {
 	const groupsDir = join$1(skillDataDir(), "groups");
@@ -2879,12 +2914,12 @@ function buildModelText(model, descriptions) {
 		model.name,
 		model.model,
 		description,
-		caps ? `能力: ${caps}` : "",
-		inputMods ? `输入: ${inputMods}` : "",
-		outputMods ? `输出: ${outputMods}` : "",
-		model.features?.length ? `特性: ${model.features.join(", ")}` : "",
+		caps ? `Capabilities: ${caps}` : "",
+		inputMods ? `Input: ${inputMods}` : "",
+		outputMods ? `Output: ${outputMods}` : "",
+		model.features?.length ? `Features: ${model.features.join(", ")}` : "",
 		model.familyName || "",
-		model.category ? `定位: ${model.category}` : ""
+		model.category ? `Category: ${model.category}` : ""
 	].filter(Boolean).join(" | ");
 }
 async function buildAndCacheEmbeddings(config, models) {
@@ -3124,51 +3159,51 @@ function buildCandidatesContext(candidates) {
 	return candidates.map(({ model: profile }) => {
 		const parts = [
 			`ID: ${profile.model}`,
-			`名称: ${profile.name}`,
-			`描述: ${profile.shortDescription || profile.description}`,
-			`能力: ${profile.capabilities.join(", ")}`,
-			`特性: ${profile.features.join(", ")}`
+			`Name: ${profile.name}`,
+			`Description: ${profile.shortDescription || profile.description}`,
+			`Capabilities: ${profile.capabilities.join(", ")}`,
+			`Features: ${profile.features.join(", ")}`
 		];
-		if (profile.contextWindow) parts.push(`上下文窗口: ${profile.contextWindow}`);
-		if (profile.maxOutputTokens) parts.push(`最大输出: ${profile.maxOutputTokens}`);
-		if (profile.category) parts.push(`类别: ${profile.category}`);
+		if (profile.contextWindow) parts.push(`Context Window: ${profile.contextWindow}`);
+		if (profile.maxOutputTokens) parts.push(`Max Output: ${profile.maxOutputTokens}`);
+		if (profile.category) parts.push(`Category: ${profile.category}`);
 		const modality = profile.inferenceMetadata;
-		if (modality?.request_modality?.length) parts.push(`输入模态: ${modality.request_modality.join(", ")}`);
-		if (modality?.response_modality?.length) parts.push(`输出模态: ${modality.response_modality.join(", ")}`);
+		if (modality?.request_modality?.length) parts.push(`Input Modality: ${modality.request_modality.join(", ")}`);
+		if (modality?.response_modality?.length) parts.push(`Output Modality: ${modality.response_modality.join(", ")}`);
 		const prices = formatPrices(profile);
-		if (prices) parts.push(`定价: ${prices}`);
+		if (prices) parts.push(`Pricing: ${prices}`);
 		const qpm = formatQpm(profile);
 		if (qpm) parts.push(`QPM: ${qpm}`);
-		if (profile.versionTag) parts.push(`版本: ${profile.versionTag}`);
-		if (profile.openSource !== void 0) parts.push(`开源: ${profile.openSource ? "是" : "否"}`);
-		if (profile.family) parts.push(`家族: ${profile.family}`);
+		if (profile.versionTag) parts.push(`Version: ${profile.versionTag}`);
+		if (profile.openSource !== void 0) parts.push(`Open Source: ${profile.openSource ? "Yes" : "No"}`);
+		if (profile.family) parts.push(`Family: ${profile.family}`);
 		return parts.join(" | ");
 	}).join("\n");
 }
 function buildIntentContext(intent) {
 	const { taskSummary, scenarioHints, inputModality, outputModality, requiredCapabilities, requiredFeatures, budget, qualityPreference, contextNeed, segments, modelPreference } = intent;
 	const parts = [];
-	if (taskSummary) parts.push(`场景理解: ${taskSummary}`);
-	if (scenarioHints.length) parts.push(`场景特征: ${scenarioHints.join(", ")}`);
-	if (inputModality.length) parts.push(`输入模态: ${inputModality.join(", ")}`);
-	if (outputModality.length) parts.push(`输出模态: ${outputModality.join(", ")}`);
-	if (requiredCapabilities.length) parts.push(`所需能力: ${requiredCapabilities.join(", ")}`);
-	if (requiredFeatures.length) parts.push(`所需特性: ${requiredFeatures.join(", ")}`);
-	parts.push(`预算倾向: ${budget}`);
-	parts.push(`质量偏好: ${qualityPreference}`);
-	if (contextNeed !== ContextNeeds.Standard) parts.push(`上下文需求: ${contextNeed}`);
+	if (taskSummary) parts.push(`Task: ${taskSummary}`);
+	if (scenarioHints.length) parts.push(`Scenario: ${scenarioHints.join(", ")}`);
+	if (inputModality.length) parts.push(`Input: ${inputModality.join(", ")}`);
+	if (outputModality.length) parts.push(`Output: ${outputModality.join(", ")}`);
+	if (requiredCapabilities.length) parts.push(`Capabilities: ${requiredCapabilities.join(", ")}`);
+	if (requiredFeatures.length) parts.push(`Features: ${requiredFeatures.join(", ")}`);
+	parts.push(`Budget: ${budget}`);
+	parts.push(`Quality: ${qualityPreference}`);
+	if (contextNeed !== ContextNeeds.Standard) parts.push(`Context: ${contextNeed}`);
 	if (modelPreference && modelPreference.mode !== "unconstrained") {
-		parts.push(`模型偏好: ${modelPreference.mode}`);
-		if (modelPreference.targets?.length) parts.push(`目标模型: ${modelPreference.targets.join(", ")}`);
-		if (modelPreference.excludes?.length) parts.push(`排除模型: ${modelPreference.excludes.join(", ")}`);
+		parts.push(`Mode: ${modelPreference.mode}`);
+		if (modelPreference.targets?.length) parts.push(`Targets: ${modelPreference.targets.join(", ")}`);
+		if (modelPreference.excludes?.length) parts.push(`Excludes: ${modelPreference.excludes.join(", ")}`);
 	}
 	if (segments?.length) {
-		parts.push(`拆解步骤:`);
+		parts.push(`Pipeline Steps:`);
 		for (const seg of segments) {
-			const inMod = seg.inputModality.join(",") || "无";
-			const outMod = seg.outputModality.join(",") || "无";
-			const caps = seg.requiredCapabilities.join(",") || "无";
-			parts.push(`  - ${seg.step} (输入: ${inMod} → 输出: ${outMod}, 能力: ${caps})`);
+			const inMod = seg.inputModality.join(",") || "none";
+			const outMod = seg.outputModality.join(",") || "none";
+			const caps = seg.requiredCapabilities.join(",") || "none";
+			parts.push(`  - ${seg.step} (Input: ${inMod} → Output: ${outMod}, Capabilities: ${caps})`);
 		}
 	}
 	return parts.join("\n");
@@ -3214,7 +3249,7 @@ function validatePipelineCompatibility(steps, modelMap) {
 		const warnings = [];
 		for (const rec of currStep.recommendations) {
 			const accepts = modelMap.get(rec.model)?.inferenceMetadata?.request_modality ?? [];
-			if (!accepts.some((mod) => prevOutputs.has(mod)) && accepts.length > 0) warnings.push(`${rec.name} 的输入模态 [${accepts.join(", ")}] 可能不兼容上一步的输出模态 [${[...prevOutputs].join(", ")}]`);
+			if (!accepts.some((mod) => prevOutputs.has(mod)) && accepts.length > 0) warnings.push(`${rec.name}'s input modalities [${accepts.join(", ")}] may not be compatible with the previous step's output modalities [${[...prevOutputs].join(", ")}]`);
 		}
 		if (warnings.length > 0) currStep.warnings = warnings;
 	}
@@ -3227,11 +3262,11 @@ async function rankModels(config, candidates, intent, userInput, top, options) {
 	if (preferenceMode === "comparison") systemPrompt = COMPARISON_SYSTEM_PROMPT;
 	else if (preferenceMode === "alternative") systemPrompt = ALTERNATIVE_SYSTEM_PROMPT;
 	else if (preferenceMode === "scoped") {
-		const scopeNote = intent.modelPreference?.targets?.length ? `\n\n## 范围限定\n用户明确要求在以下范围内推荐：${intent.modelPreference.targets.join("、")}。请优先从匹配该范围的模型中选择。` : "";
+		const scopeNote = intent.modelPreference?.targets?.length ? `\n\n## Scope Restriction\nThe user explicitly requested recommendations from: ${intent.modelPreference.targets.join(", ")}. Prioritize models within this scope.` : "";
 		systemPrompt = (intent.complexity === Complexities.Pipeline ? PIPELINE_SYSTEM_PROMPT : SINGLE_SYSTEM_PROMPT) + scopeNote;
 	} else systemPrompt = intent.complexity === Complexities.Pipeline ? PIPELINE_SYSTEM_PROMPT : SINGLE_SYSTEM_PROMPT;
 	const useThinkingModel = options?.enableThinking ?? false;
-	const userMessage = intent.complexity === Complexities.Pipeline ? `意图分析结果：\n${intentContext}\n\n候选模型列表：\n${candidatesContext}\n\n用户原始需求：${userInput}\n\n请为流水线各步骤各推荐最多 ${top} 个模型。` : `意图分析结果：\n${intentContext}\n\n候选模型列表：\n${candidatesContext}\n\n用户原始需求：${userInput}\n\n请推荐最多 ${top} 个模型。`;
+	const userMessage = intent.complexity === Complexities.Pipeline ? `Intent Analysis:\n${intentContext}\n\nCandidate Models:\n${candidatesContext}\n\nUser Request: ${userInput}\n\nRecommend up to ${top} models for each pipeline step. Respond in English only.` : `Intent Analysis:\n${intentContext}\n\nCandidate Models:\n${candidatesContext}\n\nUser Request: ${userInput}\n\nRecommend up to ${top} models. Respond in English only.`;
 	const body = {
 		model: useThinkingModel ? RANKING_MODEL : RANKING_MODEL_FAST,
 		messages: [{
@@ -3316,4 +3351,4 @@ async function rankModels(config, candidates, intent, userInput, top, options) {
 	};
 }
 //#endregion
-export { BAILIAN_HOST, BailianError, Budgets, CHANNEL, CONSOLE_GATEWAY_NO_TOKEN_MESSAGE, Capabilities, Complexities, ContextNeeds, DOCS_HOSTS, ExitCode, Features, GLOBAL_OPTIONS, McpClient, Modalities, ModelCategories, QualityPreferences, REGIONS, SOURCE_CONFIG, TAGS, analyzeIntent, appCompletionEndpoint, bailianMcpUrl, buildDocLink, callConsoleGateway, chatEndpoint, clearApiKey, createTrackingEvent, defineCommand, detectOutputFormat, ensureConfigDir, fetchModelList, flushTelemetry, formatErrorJson, formatJson, formatOutput, formatText, generateFilename, generateToolSchema, getConfigDir, getConfigPath, getCredentialsPath, getModels, imageEndpoint, imageSyncEndpoint, isCI, isInteractive, isLocalFile, isSemanticAvailable, knowledgeRetrieveEndpoint, loadApiKeyFromConfig, loadConfig, localSink, mapApiError, maskToken, mcpWebSearchEndpoint, memoryAddEndpoint, memoryListEndpoint, memoryNodeEndpoint, memorySearchEndpoint, parseBooleanValue, parseConfigFile, parseOptionalBooleanValue, parseSSE, profileSchemaEndpoint, rankModels, readConfigFile, recallCandidates, recallSemantic, remoteSink, request, requestJson, resolveBooleanFlag, resolveConsoleGatewayCredential, resolveCredential, resolveFileUrl, resolveOutputDir, resolveWatermark, saveApiKeyToConfig, signRequest, speechRecognizeEndpoint, speechSynthesizeEndpoint, stripUndefined, taskEndpoint, trackCommandExecution, trackingHeaders, uploadFile, userProfileEndpoint, videoGenerateEndpoint, writeConfigFile };
+export { BAILIAN_HOST, BailianError, Budgets, CHANNEL, CONSOLE_GATEWAY_NO_TOKEN_MESSAGE, Capabilities, Complexities, ContextNeeds, DOCS_HOSTS, ExitCode, Features, GLOBAL_OPTIONS, McpClient, Modalities, ModelCategories, QualityPreferences, REGIONS, SOURCE_CONFIG, TAGS, analyzeIntent, appCompletionEndpoint, bailianMcpUrl, buildDocLink, callConsoleGateway, chatEndpoint, clearApiKey, createTrackingEvent, defineCommand, detectOutputFormat, effectiveConsoleGatewayConfig, ensureConfigDir, fetchModelList, flushTelemetry, formatErrorJson, formatJson, formatOutput, formatText, generateFilename, generateToolSchema, getConfigDir, getConfigPath, getCredentialsPath, getModels, imageEndpoint, imageSyncEndpoint, isCI, isInteractive, isLocalFile, isSemanticAvailable, knowledgeRetrieveEndpoint, loadApiKeyFromConfig, loadConfig, localSink, mapApiError, maskToken, mcpWebSearchEndpoint, memoryAddEndpoint, memoryListEndpoint, memoryNodeEndpoint, memorySearchEndpoint, parseBooleanValue, parseConfigFile, parseOptionalBooleanValue, parseSSE, profileSchemaEndpoint, rankModels, readConfigFile, recallCandidates, recallSemantic, remoteSink, request, requestJson, resolveBooleanFlag, resolveConsoleGatewayCredential, resolveCredential, resolveFileUrl, resolveOutputDir, resolveWatermark, saveApiKeyToConfig, signRequest, speechRecognizeEndpoint, speechSynthesizeEndpoint, stripUndefined, taskEndpoint, trackCommandExecution, trackingHeaders, uploadFile, userProfileEndpoint, videoGenerateEndpoint, writeConfigFile };

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "bailian-cli-core",
-  "version": "1.3.3",
+  "version": "1.4.0",
   "description": "Core SDK for bailian-cli. See https://www.npmjs.com/package/bailian-cli for usage.",
   "homepage": "https://bailian.console.aliyun.com/cli",
   "bugs": {