Merge branch 'main' into feat/coding-plan-usage

Add MCP classic SSE auto-fallback for Bailian and --url

.gitignore

@@ -52,6 +52,3 @@ packages/cli/scene/**/outputs/
 
 # Local scratch / plan drafts (never commit)
 .scratch/
-
-# pnpm pack output
-*.tgz

packages/cli/package.json

@@ -1,6 +1,6 @@
 {
   "name": "bailian-cli",
-  "version": "1.14.2",
+  "version": "1.14.3",
   "description": "CLI for Aliyun Model Studio (DashScope) AI Platform.",
   "keywords": [
     "agent",

packages/cli/src/commands.ts

@@ -30,10 +30,6 @@ import {
   memoryDelete,
   memoryProfileCreate,
   memoryProfileGet,
-  memoryProfileList,
-  memoryProfileDetail,
-  memoryProfileUpdate,
-  memoryProfileDelete,
   knowledgeRetrieve,
   knowledgeSearch,
   knowledgeChat,
@@ -49,6 +45,8 @@ import {
   usageFreetier,
   usageStats,
   usageSummary,
+  usageTokenPlan,
+  usageCodingPlan,
   pipelineRun,
   pipelineValidate,
   advisorRecommend,
@@ -88,8 +86,6 @@ import {
   tokenPlanCreateKey,
   tokenPlanAssignSeats,
   tokenPlanAddMember,
-  tokenPlanPersonalUsage,
-  tokenPlanPersonalKey,
   workspaceInit,
   pluginInstall,
   pluginLink,
@@ -104,7 +100,6 @@ import {
   managedAgentValidate,
   managedAgentPlan,
   managedAgentApply,
-  managedAgentRun,
   managedAgentDestroy,
   managedAgentStateList,
   managedAgentStateShow,
@@ -156,10 +151,6 @@ export const commands: Record<string, AnyCommand> = {
   "memory delete": memoryDelete,
   "memory profile create": memoryProfileCreate,
   "memory profile get": memoryProfileGet,
-  "memory profile list": memoryProfileList,
-  "memory profile detail": memoryProfileDetail,
-  "memory profile update": memoryProfileUpdate,
-  "memory profile delete": memoryProfileDelete,
   "knowledge retrieve": knowledgeRetrieve,
   "knowledge search": knowledgeSearch,
   "knowledge chat": knowledgeChat,
@@ -175,6 +166,8 @@ export const commands: Record<string, AnyCommand> = {
   "usage freetier": usageFreetier,
   "usage stats": usageStats,
   "usage summary": usageSummary,
+  "usage token-plan": usageTokenPlan,
+  "usage coding-plan": usageCodingPlan,
   "pipeline run": pipelineRun,
   "pipeline validate": pipelineValidate,
   "advisor recommend": advisorRecommend,
@@ -214,8 +207,6 @@ export const commands: Record<string, AnyCommand> = {
   "token-plan create-key": tokenPlanCreateKey,
   "token-plan assign-seats": tokenPlanAssignSeats,
   "token-plan add-member": tokenPlanAddMember,
-  "token-plan personal-usage": tokenPlanPersonalUsage,
-  "token-plan personal-key": tokenPlanPersonalKey,
   "workspace init": workspaceInit,
   "plugin install": pluginInstall,
   "plugin link": pluginLink,
@@ -230,7 +221,6 @@ export const commands: Record<string, AnyCommand> = {
   "managed-agent validate": managedAgentValidate,
   "managed-agent plan": managedAgentPlan,
   "managed-agent apply": managedAgentApply,
-  "managed-agent run": managedAgentRun,
   "managed-agent destroy": managedAgentDestroy,
   "managed-agent state list": managedAgentStateList,
   "managed-agent state show": managedAgentStateShow,

packages/cli/tests/e2e/registry.smoke.e2e.test.ts

@@ -7,10 +7,15 @@ const commandPaths = Object.keys(commands).sort();
 const groupPaths = deriveGroupPaths(commandPaths);
 
 describe("e2e: bl registry smoke", () => {
-  test("根帮助展示 bl 与全局 flag", async () => {
+  test("根帮助展示 bl、逐命令鉴权域与全局 flag", async () => {
     const { stderr, exitCode } = await runCli(["--help"]);
     expect(exitCode, stderr).toBe(0);
     expect(stderr).toMatch(/\bbl\b/i);
+    expect(stderr).not.toMatch(/COMMAND\s+AUTH\s+DESCRIPTION/);
+    expect(stderr).toMatch(/app call\s+\[API Key\]\s+Call a Bailian application/);
+    expect(stderr).toMatch(/app list\s+\[Console\]\s+List Bailian applications/);
+    expect(stderr).toMatch(/token-plan create-key\s+\[AK\/SK\]\s+Create a Token Plan API key/);
+    expect(stderr).toMatch(/config show\s+\[No Auth\]\s+Display current configuration/);
     expect(stderr).toMatch(/--base-url/);
     expect(stderr).toMatch(/--console-region/);
     expect(stderr).toMatch(/--console-site/);
@@ -18,6 +23,24 @@ describe("e2e: bl registry smoke", () => {
     expect(stderr).not.toMatch(/^\s*--region\s/m);
   });
 
+  test("分组帮助按叶子命令展示不同鉴权域", async () => {
+    const { stderr, exitCode } = await runCli(["app", "--help"]);
+    expect(exitCode, stderr).toBe(0);
+    expect(stderr).toMatch(/app call\s+\[API Key\]\s+Call a Bailian application/);
+    expect(stderr).toMatch(/app list\s+\[Console\]\s+List Bailian applications/);
+  });
+
+  test.each([
+    [["text", "chat"], "API Key"],
+    [["app", "list"], "Console"],
+    [["token-plan", "list-seats"], "AK/SK"],
+    [["config", "show"], "No Auth"],
+  ] as const)("%s --help 明确展示鉴权域 %s", async (commandPath, authLabel) => {
+    const { stderr, exitCode } = await runCli([...commandPath, "--help"]);
+    expect(exitCode, stderr).toBe(0);
+    expect(stderr).toContain(`Authentication: ${authLabel}`);
+  });
+
   test("quota check --help:Flags 含 console 域鉴权 flag,Global Flags 全量列出", async () => {
     const { stderr, exitCode } = await runCli(["quota", "check", "--help"]);
     expect(exitCode, stderr).toBe(0);

packages/commands/package.json

@@ -1,6 +1,6 @@
 {
   "name": "bailian-cli-commands",
-  "version": "1.14.2",
+  "version": "1.14.3",
   "description": "Command library for bailian-cli products (knowledge, memory, media, …). See https://www.npmjs.com/package/bailian-cli for usage.",
   "homepage": "https://bailian.console.aliyun.com/cli",
   "bugs": {

packages/commands/src/commands/console/call.ts

@@ -25,7 +25,7 @@ export default defineCommand({
     },
   },
   exampleArgs: [
-    `--api zeldaEasy.broadscope-bailian.freeTrial.queryFreeTierQuota --data '{"queryFreeTierQuotaRequest":{"models":["qwen3-max"]}}'`,
+    `--api zeldaEasy.bailian-commerce.freeTrial.queryFreeTierQuota --data '{"queryFreeTierQuotaRequest":{"models":["qwen3-max"]}}'`,
     `--api some.api.name --data '{"key":"value"}' --console-region cn-beijing`,
   ],
   async run(ctx) {

packages/commands/src/commands/managed-agent/_engine/credentials.ts

@@ -50,7 +50,6 @@ export interface CredentialHost {
  */
 export const CREDENTIALS_NOTE = [
   "Bailian credentials come from bl's auth chain: --api-key > DASHSCOPE_API_KEY > `bl auth login` (active config profile).",
-  "The agentstudio endpoint is workspace-scoped: the base URL is composed from the workspace id (agents.yaml workspace_id > $BAILIAN_WORKSPACE_ID > bl's configured workspace_id) as https://{workspace}.cn-beijing.maas.aliyuncs.com/api/v1/agentstudio, and the key must belong to that workspace.",
   "Other providers read the env vars referenced in agents.yaml (e.g. ${ANTHROPIC_API_KEY}), including .env and ~/.agents/config.json.",
   "Resolved credentials are injected into the SDK in-memory and cleared from the environment; they never persist in process env.",
 ];
@@ -86,19 +85,13 @@ export function prepareProviderEnv(): void {
  * the block references them and the interpolated value is empty (a literal in
  * agents.yaml is respected).
  *
- * `base_url` is composed from the workspace when one is known — block
- * `workspace_id` (agents.yaml literal or interpolated `${BAILIAN_WORKSPACE_ID}`)
- * first, then bl's configured `workspace_id` — because agentstudio is served
- * only on the workspace-scoped host; the bare model-domain origin 404s it
- * (managed-agents API overview: `https://{workspace_id}.cn-beijing.maas.
- * aliyuncs.com/api/v1/agentstudio`, region cn-beijing only). Only with no
- * workspace at all does the model-domain origin get {@link AGENTSTUDIO_API_PATH}
- * suffixed. A value already ending in the suffix is left as-is. base_url is
- * filled even without a credential — `client.baseUrl` is readable
- * credential-less — so offline commands (which skip the credential assert)
- * still satisfy the SDK's "workspace_id or base_url" schema. With no
- * credential the `api_key` is left untouched: online commands reject it via
- * {@link assertProviderCredentials}.
+ * `base_url` carries {@link AGENTSTUDIO_API_PATH} because the SDK appends resource
+ * paths onto it verbatim; a value already ending in the suffix is left as-is.
+ * It is filled even without a credential — `client.baseUrl` is readable
+ * credential-less (defaults to the CLI's model-domain base URL) — so offline
+ * commands (which skip the credential assert) still satisfy the SDK's
+ * "workspace_id or base_url" schema. With no credential the `api_key` is left
+ * untouched: online commands reject it via {@link assertProviderCredentials}.
  */
 export function injectProviderCredentials(
   providers: Record<string, unknown>,
@@ -110,27 +103,16 @@ export function injectProviderCredentials(
 
   const cred = host.client.exportApiCredential();
   if (cred) block.api_key = cred.token;
-  if ("workspace_id" in block && !block.workspace_id) {
-    // agents.yaml interpolation already replaced `${BAILIAN_WORKSPACE_ID}` in
-    // file-based flows; the inline runtime passes an object config that never
-    // interpolates, so read the env var here too (prepareProviderEnv
-    // placeholders it to "" when unset). bl's configured workspace_id is the
-    // last resort.
-    block.workspace_id =
-      process.env.BAILIAN_WORKSPACE_ID?.trim() || host.settings.workspaceId || "";
-  }
   if ("base_url" in block && !block.base_url) {
-    const workspaceId = typeof block.workspace_id === "string" ? block.workspace_id.trim() : "";
-    if (workspaceId) {
-      block.base_url = `https://${workspaceId}.cn-beijing.maas.aliyuncs.com${AGENTSTUDIO_API_PATH}`;
-    } else {
-      // Defensive normalization: the auth chain already normalizes base_url to
-      // an origin, but never let a trailing slash produce "//api/v1/agentstudio".
-      const origin = host.client.baseUrl.replace(/\/+$/, "");
-      block.base_url = origin.endsWith(AGENTSTUDIO_API_PATH)
-        ? origin
-        : `${origin}${AGENTSTUDIO_API_PATH}`;
-    }
+    // Defensive normalization: the auth chain already normalizes base_url to
+    // an origin, but never let a trailing slash produce "//api/v1/agentstudio".
+    const origin = host.client.baseUrl.replace(/\/+$/, "");
+    block.base_url = origin.endsWith(AGENTSTUDIO_API_PATH)
+      ? origin
+      : `${origin}${AGENTSTUDIO_API_PATH}`;
+  }
+  if ("workspace_id" in block && !block.workspace_id && host.settings.workspaceId) {
+    block.workspace_id = host.settings.workspaceId;
   }
 }
 

packages/commands/src/commands/managed-agent/_engine/inline-runtime.ts

@@ -1,124 +0,0 @@
-import { mkdirSync } from "node:fs";
-import { dirname, join } from "node:path";
-import {
-  type BackendRuntimeInput,
-  LocalFileStateBackend,
-  resolveProjectConfigFromObject,
-} from "@openagentpack/sdk";
-import { getConfigDir } from "bailian-cli-core";
-import {
-  assertProviderCredentials,
-  type CredentialHost,
-  injectProviderCredentials,
-  normalizeInterpolatedProviderBlocks,
-  prepareProviderEnv,
-  scrubCredentialEnv,
-} from "./credentials.ts";
-import { type HostContext, installSdkTransport } from "./transport.ts";
-
-/** Default agent identity `bl managed-agent run` materializes and reuses. */
-export const DEFAULT_INLINE_AGENT = "dsh-remote-runner";
-
-/** Default model for the materialized agent. */
-export const DEFAULT_INLINE_MODEL = "qwen3.8-max";
-
-/** Default role when the caller supplies no `--instructions`. */
-export const DEFAULT_INLINE_INSTRUCTIONS = "You are a helpful assistant. Complete the task.";
-
-/** Environment name declared in the inline config; one cloud env per agent. */
-const INLINE_ENVIRONMENT = "cloud";
-
-export interface InlineAgentOptions {
-  agentName: string;
-  instructions: string;
-  model: string;
-  /** Override the persisted state location (defaults under the bl config dir). */
-  statePath?: string;
-}
-
-/**
- * Slugify an agent name into a filesystem- and project-id-safe token. The state
- * for each distinct agent lives in its own directory so repeat runs reuse the
- * same materialized remote agent.
- */
-function slugify(agentName: string): string {
-  const slug = agentName
-    .toLowerCase()
-    .replace(/[^a-z0-9._-]+/g, "-")
-    .replace(/^-+|-+$/g, "");
-  return slug.length > 0 ? slug : "agent";
-}
-
-/** Where a materialized agent's state is persisted (not the user's cwd). */
-export function inlineStatePath(agentName: string): string {
-  return join(getConfigDir(), "managed-agent", slugify(agentName), "state.json");
-}
-
-/**
- * The minimal in-memory project config that materializes into one cloud agent.
- * `providers.bailian` carries empty `api_key`/`base_url`/`workspace_id`
- * placeholders so {@link injectProviderCredentials} fills them from bl's auth
- * chain and workspace sources (it only writes fields the block already
- * declares). `workspace_id` lets injection compose the workspace-scoped
- * agentstudio host instead of the model-domain origin.
- */
-export function buildInlineConfig(opts: InlineAgentOptions): Record<string, unknown> {
-  return {
-    version: "1",
-    providers: {
-      bailian: { api_key: "", base_url: "", workspace_id: "" },
-    },
-    defaults: { provider: "bailian" },
-    environments: {
-      [INLINE_ENVIRONMENT]: {
-        description: "Bailian CLI cloud environment",
-        config: { type: "cloud", networking: { type: "unrestricted" } },
-      },
-    },
-    agents: {
-      [opts.agentName]: {
-        description: opts.agentName,
-        model: opts.model,
-        instructions: opts.instructions,
-        environment: INLINE_ENVIRONMENT,
-        provider: "bailian",
-      },
-    },
-  };
-}
-
-/**
- * Build the `BackendRuntimeInput` shared by ensure (`syncAgentResourcesWith
- * StateBackend`) and run (`readProjectRuntime` + `startSessionRun`). Mirrors the
- * credential spine of {@link buildAgentRuntime} but sources config from an
- * in-memory object instead of a file, so no `agents.yaml` or `apply` is required.
- */
-export async function buildInlineBackendInput(
-  host: HostContext & CredentialHost,
-  opts: InlineAgentOptions,
-): Promise<BackendRuntimeInput> {
-  installSdkTransport(host);
-  prepareProviderEnv();
-
-  const rawConfig = buildInlineConfig(opts);
-  const { config, projectName } = await resolveProjectConfigFromObject(rawConfig, {
-    projectName: slugify(opts.agentName),
-  });
-
-  normalizeInterpolatedProviderBlocks(config.providers);
-  injectProviderCredentials(config.providers, host);
-  scrubCredentialEnv();
-  assertProviderCredentials(config.providers);
-
-  const statePath = opts.statePath ?? inlineStatePath(opts.agentName);
-  mkdirSync(dirname(statePath), { recursive: true });
-  const stateBackend = new LocalFileStateBackend({ statePath });
-
-  return {
-    projectName,
-    config,
-    stateBackend,
-    stateScope: { projectId: slugify(opts.agentName) },
-    providers: config.providers,
-  };
-}

packages/commands/src/commands/managed-agent/run.ts

@@ -1,137 +0,0 @@
-import {
-  BailianError,
-  defineCommand,
-  detectOutputFormat,
-  ExitCode,
-  type FlagsDef,
-} from "bailian-cli-core";
-import { emitResult } from "bailian-cli-runtime";
-import {
-  readProjectRuntime,
-  startSessionRun,
-  startSessionRunPolling,
-  syncAgentResourcesWithStateBackend,
-} from "@openagentpack/sdk";
-import { CREDENTIALS_NOTE } from "./_engine/config-loader.ts";
-import { withStdoutProtected } from "./_engine/console-capture.ts";
-import { withAgentErrors } from "./_engine/errors.ts";
-import {
-  buildInlineBackendInput,
-  DEFAULT_INLINE_AGENT,
-  DEFAULT_INLINE_INSTRUCTIONS,
-  DEFAULT_INLINE_MODEL,
-} from "./_engine/inline-runtime.ts";
-import { renderCollectedEvents, streamAndRenderEvents } from "./_engine/session-render.ts";
-
-const RUN_FLAGS = {
-  prompt: {
-    type: "string",
-    valueHint: "<text>",
-    description: "Task to run (required)",
-    required: true,
-  },
-  instructions: {
-    type: "string",
-    valueHint: "<text>",
-    description: "Role/system instructions for the remote agent (default: generic assistant)",
-  },
-  model: {
-    type: "string",
-    valueHint: "<id>",
-    description: `Model for the remote agent (default: ${DEFAULT_INLINE_MODEL})`,
-  },
-  agent: {
-    type: "string",
-    valueHint: "<name>",
-    description: `Agent identity to create/reuse (default: ${DEFAULT_INLINE_AGENT})`,
-  },
-  noStream: {
-    type: "switch",
-    description: "Use polling instead of SSE streaming",
-  },
-} satisfies FlagsDef;
-
-export default defineCommand({
-  description: "Provision (if needed) a cloud agent and run a task in one step",
-  auth: "apiKey",
-  usageArgs: "--prompt <text> [--instructions <text>] [--model <id>] [--agent <name>]",
-  flags: RUN_FLAGS,
-  exampleArgs: [
-    '--prompt "Summarize the latest AI news"',
-    '--prompt "Audit this dependency tree" --instructions "You are a security expert" --model qwen3.8-max',
-  ],
-  notes: [
-    ...CREDENTIALS_NOTE,
-    "Unlike `apply`, this creates/updates the cloud agent + environment on demand without --yes. The first run provisions cloud resources (may incur cost and take longer to start); later runs with the same --agent reuse them.",
-  ],
-  async run(ctx) {
-    const { settings, flags } = ctx;
-    const format = detectOutputFormat(settings.output);
-    const asJson = format === "json";
-
-    const agentName = flags.agent ?? DEFAULT_INLINE_AGENT;
-    const model = flags.model ?? DEFAULT_INLINE_MODEL;
-    const instructions = flags.instructions ?? DEFAULT_INLINE_INSTRUCTIONS;
-
-    if (settings.dryRun) {
-      emitResult(
-        {
-          would_run: {
-            prompt: flags.prompt,
-            agent: agentName,
-            model,
-            instructions,
-            mode: flags.noStream ? "polling" : "streaming",
-          },
-        },
-        format,
-      );
-      return;
-    }
-
-    await withAgentErrors(() =>
-      withStdoutProtected(async () => {
-        const input = await buildInlineBackendInput(ctx, { agentName, instructions, model });
-
-        // Ensure the remote agent + its cloud environment exist. Idempotent:
-        // a repeat run with the same agent name reuses the materialized state.
-        if (!asJson) process.stderr.write(`Ensuring cloud agent "${agentName}"…\n`);
-        const sync = await syncAgentResourcesWithStateBackend(input, agentName, {
-          policy: "force",
-          quiet: true,
-        });
-        if (sync.status !== "completed") {
-          const detail =
-            sync.error ??
-            sync.diagnostics.find((diag) => diag.severity === "error")?.message ??
-            `provisioning ended with status "${sync.status}"`;
-          throw new BailianError(
-            `Failed to provision cloud agent "${agentName}": ${detail}`,
-            ExitCode.GENERAL,
-          );
-        }
-
-        // Run the task inside a runtime bound to the just-materialized state.
-        await readProjectRuntime(input, async (runtime) => {
-          if (flags.noStream) {
-            const run = await startSessionRunPolling(runtime, flags.prompt, { agent: agentName });
-            if (!asJson) process.stderr.write(`Session created: ${run.session.id}\n`);
-            renderCollectedEvents(run, asJson, {
-              session_id: run.session.id,
-              provider: run.provider,
-              agent: run.agentName,
-            });
-          } else {
-            const run = await startSessionRun(runtime, flags.prompt, { agent: agentName });
-            if (!asJson) process.stderr.write(`Session created: ${run.session.id}\n`);
-            await streamAndRenderEvents(run.events, asJson, {
-              session_id: run.session.id,
-              provider: run.provider,
-              agent: run.agentName,
-            });
-          }
-        });
-      }),
-    );
-  },
-});

packages/commands/src/commands/mcp/activate-hint.ts

@@ -1,11 +1,11 @@
-import { BailianError } from "bailian-cli-core";
+import { BailianError, isStreamableHttpUnsupported } from "bailian-cli-core";
 import { mcpMarketplaceDetailPage } from "bailian-cli-runtime";
 
 /** Detect MCP-not-activated / invalid 404 errors (CLI-wrapped server message). */
 export function isMcpNotActivated(error: unknown): boolean {
   if (!(error instanceof BailianError)) return false;
   const message = error.message;
-  if (!/MCP request failed:\s*404\b/i.test(message)) return false;
+  if (!/^MCP request failed:\s*404\b/i.test(message)) return false;
   return /未开通|MCP不存在|MCP_IS_INVALID/i.test(message);
 }
 
@@ -26,14 +26,28 @@ export function mcpActivateHint(serverCode: string): string {
 /**
  * For not-activated errors, keep the original message / exitCode and append a hint only.
  * Do not replace the server error message.
+ * WebSearch + 405 streamableHttp: do not fall back; attach a re-activate / upgrade hint.
  */
 export function rethrowWithMcpActivateHint(error: unknown, serverCode: string): never {
-  if (isMcpNotActivated(error) && error instanceof BailianError && !error.hint) {
+  if (!(error instanceof BailianError) || error.hint) {
+    throw error;
+  }
+
+  if (isMcpNotActivated(error)) {
     throw new BailianError(error.message, error.exitCode, mcpActivateHint(serverCode), {
       cause: error,
       api: error.api,
       rawResponse: error.rawResponse,
     });
   }
+
+  if (serverCode === "WebSearch" && isStreamableHttpUnsupported(error)) {
+    throw new BailianError(error.message, error.exitCode, mcpActivateHint(serverCode), {
+      cause: error,
+      api: error.api,
+      rawResponse: error.rawResponse,
+    });
+  }
+
   throw error;
 }

packages/commands/src/commands/mcp/call.ts

@@ -36,7 +36,8 @@ const CALL_FLAGS = {
   url: {
     type: "string",
     valueHint: "<url>",
-    description: "Override the MCP endpoint URL (for non-Bailian servers)",
+    description:
+      "Override the MCP endpoint URL (non-Bailian). Tries Streamable HTTP first, then classic SSE on the same URL.",
   },
 } satisfies FlagsDef;
 type CallFlags = ParsedFlags<typeof CALL_FLAGS>;
@@ -114,14 +115,14 @@ export default defineCommand({
     const { serverCode, toolName } = parseTarget(flags.target);
     const toolArgs = buildToolArgs(flags);
 
-    const url = flags.url || ctx.client.url(bailianMcpPath(serverCode));
+    const previewUrl = flags.url || ctx.client.url(bailianMcpPath(serverCode));
     const format = detectOutputFormat(settings.output);
 
     if (settings.dryRun) {
       emitResult(
         {
           server: serverCode,
-          url,
+          url: previewUrl,
           tool: toolName,
           arguments: toolArgs,
         },
@@ -130,13 +131,14 @@ export default defineCommand({
       return;
     }
 
-    const client = ctx.client.mcp(url);
+    let client: { close?(): void } | undefined;
     try {
-      await client.initialize();
-      const result = await client.callTool(toolName, toolArgs);
+      const connected = await ctx.client.connectBailianMcp(serverCode, flags.url);
+      client = connected.client;
+      const result = await connected.client.callTool(toolName, toolArgs);
 
       if (result.isError) {
-        const errText = result.content.map((c) => c.text || "").join("\n");
+        const errText = result.content.map((contentItem) => contentItem.text || "").join("\n");
         throw new BailianError(`Tool error: ${errText}`);
       }
 
@@ -146,6 +148,8 @@ export default defineCommand({
         rethrowWithMcpActivateHint(error, serverCode);
       }
       throw error;
+    } finally {
+      client?.close?.();
     }
   },
 });

packages/commands/src/commands/mcp/tools.ts

@@ -16,7 +16,8 @@ export default defineCommand({
     url: {
       type: "string",
       valueHint: "<url>",
-      description: "Override the MCP endpoint URL (for non-Bailian servers)",
+      description:
+        "Override the MCP endpoint URL (non-Bailian). Tries Streamable HTTP first, then classic SSE on the same URL.",
     },
   },
   exampleArgs: [
@@ -28,24 +29,27 @@ export default defineCommand({
     const { settings, flags } = ctx;
     const code = flags.server;
 
-    const url = flags.url || ctx.client.url(bailianMcpPath(code));
+    const previewUrl = flags.url || ctx.client.url(bailianMcpPath(code));
     const format = detectOutputFormat(settings.output);
 
     if (settings.dryRun) {
-      emitResult({ server: code, url, action: "tools/list" }, format);
+      emitResult({ server: code, url: previewUrl, action: "tools/list" }, format);
       return;
     }
 
-    const client = ctx.client.mcp(url);
+    let client: { close?(): void } | undefined;
     try {
-      await client.initialize();
-      const tools = await client.listTools();
-      emitResult({ server: code, url, tools }, format);
+      const connected = await ctx.client.connectBailianMcp(code, flags.url);
+      client = connected.client;
+      const tools = await connected.client.listTools();
+      emitResult({ server: code, url: connected.url, tools }, format);
     } catch (error) {
       if (!flags.url) {
         rethrowWithMcpActivateHint(error, code);
       }
       throw error;
+    } finally {
+      client?.close?.();
     }
   },
 });

packages/commands/src/commands/memory/add.ts

@@ -28,16 +28,6 @@ const ADD_FLAGS = {
     valueHint: "<id>",
     description: "Memory library ID (isolate memory space)",
   },
-  projectId: {
-    type: "string",
-    valueHint: "<id>",
-    description: "Memory extraction rule ID (defaults to the library's default rule)",
-  },
-  metaData: {
-    type: "string",
-    valueHint: "<json>",
-    description: 'Custom metadata JSON object: {"location":"Beijing"}',
-  },
 } satisfies FlagsDef;
 type AddFlags = ParsedFlags<typeof ADD_FLAGS>;
 
@@ -50,7 +40,6 @@ export default defineCommand({
     '--user-id user1 --content "The user likes Python programming"',
     '--user-id user1 --messages \'[{"role":"user","content":"I like traveling"}]\'',
     '--user-id user1 --content "Lives in Beijing" --profile-schema schema_xxx',
-    '--user-id user1 --content "Lives in Beijing" --meta-data \'{"source":"onboarding"}\'',
   ],
   validate: (f: AddFlags) =>
     !f.messages && !f.content ? "Provide --messages or --content." : undefined,
@@ -74,15 +63,6 @@ export default defineCommand({
 
     if (flags.profileSchema) body.profile_schema = flags.profileSchema;
     if (flags.memoryLibraryId) body.memory_library_id = flags.memoryLibraryId;
-    if (flags.projectId) body.project_id = flags.projectId;
-
-    if (flags.metaData) {
-      try {
-        body.meta_data = JSON.parse(flags.metaData);
-      } catch {
-        throw new UsageError("--meta-data must be valid JSON object");
-      }
-    }
 
     const format = detectOutputFormat(settings.output);
 
@@ -98,14 +78,8 @@ export default defineCommand({
     });
 
     if (settings.quiet || format === "text") {
-      const nodes = response.memory_nodes ?? [];
-      if (nodes.length === 0) {
-        emitBare("No memory fragments were extracted.");
-      } else {
-        for (const node of nodes) {
-          emitBare(`[${node.event ?? "ADD"}] ${node.memory_node_id} ${node.content}`);
-        }
-      }
+      const ids = response.memory_ids?.join(", ") || "none";
+      emitBare(`Memory added. IDs: ${ids}`);
     } else {
       emitResult(response, format);
     }

packages/commands/src/commands/memory/list.ts

@@ -24,11 +24,6 @@ export default defineCommand({
     },
     page: { type: "number", valueHint: "<n>", description: "Page number (default: 1)" },
     memoryLibraryId: { type: "string", valueHint: "<id>", description: "Memory library ID" },
-    projectId: {
-      type: "string",
-      valueHint: "<id>",
-      description: "Memory extraction rule ID (defaults to the library's default rule)",
-    },
   },
   exampleArgs: ["--user-id user1", "--user-id user1 --page-size 20 --page 2"],
   async run(ctx) {
@@ -41,7 +36,6 @@ export default defineCommand({
     if (flags.pageSize !== undefined) params.set("page_size", String(flags.pageSize));
     if (flags.page !== undefined) params.set("page_num", String(flags.page));
     if (flags.memoryLibraryId) params.set("memory_library_id", flags.memoryLibraryId);
-    if (flags.projectId) params.set("project_id", flags.projectId);
 
     const path = `${memoryListPath()}?${params.toString()}`;
 

packages/commands/src/commands/memory/profile-delete.ts

@@ -1,44 +0,0 @@
-import { defineCommand, profileSchemaItemPath, detectOutputFormat } from "bailian-cli-core";
-import { emitResult, emitBare } from "bailian-cli-runtime";
-
-export default defineCommand({
-  description: "Delete a profile schema",
-  auth: "apiKey",
-  usageArgs: "--schema-id <id> [flags]",
-  flags: {
-    schemaId: {
-      type: "string",
-      valueHint: "<id>",
-      description: "Profile schema ID (required)",
-      required: true,
-    },
-    memoryLibraryId: { type: "string", valueHint: "<id>", description: "Memory library ID" },
-  },
-  exampleArgs: ["--schema-id schema_xxx"],
-  async run(ctx) {
-    const { settings, flags } = ctx;
-    const format = detectOutputFormat(settings.output);
-
-    const params = new URLSearchParams();
-    if (flags.memoryLibraryId) params.set("memory_library_id", flags.memoryLibraryId);
-    const query = params.toString();
-    const base = profileSchemaItemPath(flags.schemaId);
-    const path = query ? `${base}?${query}` : base;
-
-    if (settings.dryRun) {
-      emitResult({ endpoint: ctx.client.url(path), method: "DELETE" }, format);
-      return;
-    }
-
-    const response = await ctx.client.requestJson<{ request_id: string }>({
-      path,
-      method: "DELETE",
-    });
-
-    if (settings.quiet || format === "text") {
-      emitBare(`Profile schema ${flags.schemaId} deleted.`);
-    } else {
-      emitResult(response, format);
-    }
-  },
-});

packages/commands/src/commands/memory/profile-detail.ts

@@ -1,52 +0,0 @@
-import {
-  defineCommand,
-  profileSchemaItemPath,
-  detectOutputFormat,
-  type ProfileSchemaGetResponse,
-} from "bailian-cli-core";
-import { emitResult, emitBare } from "bailian-cli-runtime";
-
-export default defineCommand({
-  description: "Show a profile schema and its attribute IDs",
-  auth: "apiKey",
-  usageArgs: "--schema-id <id> [flags]",
-  flags: {
-    schemaId: {
-      type: "string",
-      valueHint: "<id>",
-      description: "Profile schema ID (required)",
-      required: true,
-    },
-    memoryLibraryId: { type: "string", valueHint: "<id>", description: "Memory library ID" },
-  },
-  exampleArgs: ["--schema-id schema_xxx"],
-  async run(ctx) {
-    const { settings, flags } = ctx;
-    const format = detectOutputFormat(settings.output);
-
-    const params = new URLSearchParams();
-    if (flags.memoryLibraryId) params.set("memory_library_id", flags.memoryLibraryId);
-    const query = params.toString();
-    const base = profileSchemaItemPath(flags.schemaId);
-    const path = query ? `${base}?${query}` : base;
-
-    if (settings.dryRun) {
-      emitResult({ endpoint: ctx.client.url(path), method: "GET" }, format);
-      return;
-    }
-
-    const response = await ctx.client.requestJson<ProfileSchemaGetResponse>({
-      path,
-      method: "GET",
-    });
-
-    if (settings.quiet || format === "text") {
-      emitBare(`${response.name}${response.description ? ` — ${response.description}` : ""}`);
-      for (const attribute of response.attributes ?? []) {
-        emitBare(`  [${attribute.attribute_id}] ${attribute.name}`);
-      }
-    } else {
-      emitResult(response, format);
-    }
-  },
-});

packages/commands/src/commands/memory/profile-list.ts

@@ -1,55 +0,0 @@
-import {
-  defineCommand,
-  profileSchemaPath,
-  detectOutputFormat,
-  type ProfileSchemaListResponse,
-} from "bailian-cli-core";
-import { emitResult, emitBare } from "bailian-cli-runtime";
-
-export default defineCommand({
-  description: "List profile schemas",
-  auth: "apiKey",
-  usageArgs: "[flags]",
-  flags: {
-    memoryLibraryId: { type: "string", valueHint: "<id>", description: "Memory library ID" },
-    pageSize: { type: "number", valueHint: "<n>", description: "Results per page (default: 10)" },
-    page: { type: "number", valueHint: "<n>", description: "Page number (default: 1)" },
-  },
-  exampleArgs: ["", "--page-size 20 --page 2"],
-  async run(ctx) {
-    const { settings, flags } = ctx;
-    const format = detectOutputFormat(settings.output);
-
-    const params = new URLSearchParams();
-    if (flags.memoryLibraryId) params.set("memory_library_id", flags.memoryLibraryId);
-    if (flags.pageSize !== undefined) params.set("page_size", String(flags.pageSize));
-    if (flags.page !== undefined) params.set("page_num", String(flags.page));
-
-    const query = params.toString();
-    const path = query ? `${profileSchemaPath()}?${query}` : profileSchemaPath();
-
-    if (settings.dryRun) {
-      emitResult({ endpoint: ctx.client.url(path), method: "GET" }, format);
-      return;
-    }
-
-    const response = await ctx.client.requestJson<ProfileSchemaListResponse>({
-      path,
-      method: "GET",
-    });
-
-    if (settings.quiet || format === "text") {
-      const schemas = response.profile_schemas ?? [];
-      if (schemas.length === 0) {
-        emitBare("No profile schemas found.");
-      } else {
-        for (const schema of schemas) {
-          emitBare(`[${schema.profile_schema_id}] ${schema.name}`);
-        }
-        if (response.total !== undefined) emitBare(`\nTotal: ${response.total}`);
-      }
-    } else {
-      emitResult(response, format);
-    }
-  },
-});

packages/commands/src/commands/memory/profile-update.ts

@@ -1,81 +0,0 @@
-import {
-  defineCommand,
-  UsageError,
-  profileSchemaItemPath,
-  detectOutputFormat,
-  type ProfileSchemaUpdateRequest,
-} from "bailian-cli-core";
-import { emitResult, emitBare } from "bailian-cli-runtime";
-import type { FlagsDef, ParsedFlags } from "bailian-cli-core";
-
-const UPDATE_FLAGS = {
-  schemaId: {
-    type: "string",
-    valueHint: "<id>",
-    description: "Profile schema ID (required)",
-    required: true,
-  },
-  name: { type: "string", valueHint: "<name>", description: "New schema name" },
-  description: { type: "string", valueHint: "<text>", description: "New schema description" },
-  attributeOps: {
-    type: "string",
-    valueHint: "<json>",
-    description:
-      'Attribute operations JSON array: [{"op":"add","name":"plan"},{"op":"delete","attribute_id":"attr_1"}]',
-  },
-  memoryLibraryId: { type: "string", valueHint: "<id>", description: "Memory library ID" },
-} satisfies FlagsDef;
-type UpdateFlags = ParsedFlags<typeof UPDATE_FLAGS>;
-
-export default defineCommand({
-  description: "Update a profile schema's name, description, or attributes",
-  auth: "apiKey",
-  usageArgs: "--schema-id <id> [--name <name>] [--attribute-ops <json>] [flags]",
-  flags: UPDATE_FLAGS,
-  notes: ["Attribute IDs for update/delete operations come from `memory profile detail`."],
-  exampleArgs: [
-    '--schema-id schema_xxx --name "user_basic_v2"',
-    '--schema-id schema_xxx --attribute-ops \'[{"op":"add","name":"plan","description":"subscription plan"}]\'',
-    '--schema-id schema_xxx --attribute-ops \'[{"op":"delete","attribute_id":"attr_1"}]\'',
-  ],
-  validate: (f: UpdateFlags) =>
-    !f.name && !f.description && !f.attributeOps
-      ? "Provide --name, --description, or --attribute-ops."
-      : undefined,
-  async run(ctx) {
-    const { settings, flags } = ctx;
-    const format = detectOutputFormat(settings.output);
-
-    const body: ProfileSchemaUpdateRequest = {};
-    if (flags.name) body.name = flags.name;
-    if (flags.description) body.description = flags.description;
-    if (flags.memoryLibraryId) body.memory_library_id = flags.memoryLibraryId;
-
-    if (flags.attributeOps) {
-      try {
-        body.attributes_operations = JSON.parse(flags.attributeOps);
-      } catch {
-        throw new UsageError("--attribute-ops must be valid JSON array");
-      }
-    }
-
-    const path = profileSchemaItemPath(flags.schemaId);
-
-    if (settings.dryRun) {
-      emitResult({ endpoint: ctx.client.url(path), method: "PATCH", request: body }, format);
-      return;
-    }
-
-    const response = await ctx.client.requestJson<{ request_id: string }>({
-      path,
-      method: "PATCH",
-      body,
-    });
-
-    if (settings.quiet || format === "text") {
-      emitBare(`Profile schema ${flags.schemaId} updated.`);
-    } else {
-      emitResult(response, format);
-    }
-  },
-});

packages/commands/src/commands/memory/search.ts

@@ -24,38 +24,6 @@ const SEARCH_FLAGS = {
     description: "Number of results to return (default: 10)",
   },
   memoryLibraryId: { type: "string", valueHint: "<id>", description: "Memory library ID" },
-  projectIds: {
-    type: "array",
-    valueHint: "<id>",
-    description: "Memory extraction rule ID for hybrid retrieval (repeatable)",
-  },
-  minScore: {
-    type: "number",
-    valueHint: "<n>",
-    description: "Minimum similarity score, 0-1 (default: 0.3)",
-  },
-  enableRerank: {
-    type: "boolean",
-    valueHint: "<bool>",
-    description:
-      "Rerank results. Also selects the billing tier: false bills lite, true bills pro (~50x). (default: true)",
-  },
-  planVersion: {
-    type: "string",
-    valueHint: "<lite|pro>",
-    description:
-      "Documented billing tier. The service currently honors --enable-rerank instead, so prefer that flag",
-  },
-  enableJudge: {
-    type: "boolean",
-    valueHint: "<bool>",
-    description: "Enable the intent-discrimination callback (default: false)",
-  },
-  enableRewrite: {
-    type: "boolean",
-    valueHint: "<bool>",
-    description: "Enable query rewriting (default: false)",
-  },
 } satisfies FlagsDef;
 type SearchFlags = ParsedFlags<typeof SEARCH_FLAGS>;
 
@@ -67,7 +35,6 @@ export default defineCommand({
   exampleArgs: [
     '--user-id user1 --query "programming preferences"',
     '--user-id user1 --messages \'[{"role":"user","content":"recommend a book"}]\' --top-k 5',
-    '--user-id user1 --query "preferences" --enable-rerank false --min-score 0.5',
   ],
   validate: (f: SearchFlags) =>
     !f.query && !f.messages ? "Provide --query or --messages." : undefined,
@@ -94,21 +61,6 @@ export default defineCommand({
 
     if (flags.topK !== undefined) body.top_k = flags.topK;
     if (flags.memoryLibraryId) body.memory_library_id = flags.memoryLibraryId;
-    if (flags.projectIds && flags.projectIds.length > 0) body.project_ids = flags.projectIds;
-    if (flags.minScore !== undefined) body.min_score = flags.minScore;
-    if (flags.enableRerank !== undefined) body.enable_rerank = flags.enableRerank;
-    if (flags.enableJudge !== undefined) body.enable_judge = flags.enableJudge;
-    if (flags.enableRewrite !== undefined) body.enable_rewrite = flags.enableRewrite;
-
-    if (flags.planVersion) {
-      if (flags.planVersion !== "lite" && flags.planVersion !== "pro") {
-        throw new UsageError("--plan-version must be lite or pro");
-      }
-      body.plan_version = flags.planVersion;
-      // The service ignores plan_version on its own, so mirror the intent onto
-      // the flag it does honor unless the caller set that one explicitly.
-      if (flags.enableRerank === undefined) body.enable_rerank = flags.planVersion === "pro";
-    }
 
     const format = detectOutputFormat(settings.output);
 

packages/commands/src/commands/memory/update.ts

@@ -1,6 +1,5 @@
 import {
   defineCommand,
-  UsageError,
   memoryNodePath,
   detectOutputFormat,
   type MemoryNodeUpdateRequest,
@@ -35,16 +34,6 @@ export default defineCommand({
       valueHint: "<id>",
       description: "Memory library ID (non-default library)",
     },
-    timestamp: {
-      type: "number",
-      valueHint: "<unix-seconds>",
-      description: "When the remembered event happened (default: now)",
-    },
-    metaData: {
-      type: "string",
-      valueHint: "<json>",
-      description: 'Custom metadata JSON object, merged incrementally: {"source":"manual"}',
-    },
   },
   exampleArgs: ['--node-id node_xxx --user-id user1 --content "updated memory content"'],
   async run(ctx) {
@@ -58,15 +47,6 @@ export default defineCommand({
       custom_content: content,
     };
     if (flags.memoryLibraryId) body.memory_library_id = flags.memoryLibraryId;
-    if (flags.timestamp !== undefined) body.timestamp = flags.timestamp;
-
-    if (flags.metaData) {
-      try {
-        body.meta_data = JSON.parse(flags.metaData);
-      } catch {
-        throw new UsageError("--meta-data must be valid JSON object");
-      }
-    }
 
     const format = detectOutputFormat(settings.output);
 

packages/commands/src/commands/speech/recognize.ts

@@ -12,6 +12,13 @@ import {
   stripUndefined,
   taskPath,
   speechRecognizePath,
+  resolveAsrApi,
+  buildAsrFlashRequest,
+  buildAsyncAsrLanguageFields,
+  collectAsrTranscriptionItems,
+  extractAsrFlashText,
+  type AsrApiRoute,
+  type AsrFlashFamily,
   type OutputFormat,
   type FlagsDef,
   type ParsedFlags,
@@ -27,8 +34,18 @@ const RECOGNIZE_FLAGS = {
     description: "Audio file URL or local file path (repeatable, max 100)",
     required: true,
   },
-  model: { type: "string", valueHint: "<model>", description: "Model ID (default: fun-asr)" },
-  language: { type: "string", valueHint: "<lang>", description: "Language hint (e.g. zh, en, ja)" },
+  model: {
+    type: "string",
+    valueHint: "<model>",
+    description:
+      "Model ID (default: fun-asr). Async: fun-asr / *-filetrans / paraformer-*; sync: qwen3-asr-flash* / fun-asr-flash* / qwen-audio-*-asr-flash",
+  },
+  language: {
+    type: "string",
+    valueHint: "<lang>",
+    description:
+      "Language hint (e.g. zh, en, ja). Classic async/input-audio: language_hints; qwen3-filetrans: language; qwen3 sync: asr_options.language",
+  },
   diarization: { type: "switch", description: "Enable automatic speaker diarization" },
   speakerCount: {
     type: "number",
@@ -55,8 +72,33 @@ const RECOGNIZE_FLAGS = {
 } satisfies FlagsDef;
 type RecognizeFlags = ParsedFlags<typeof RECOGNIZE_FLAGS>;
 
+function assertSyncFlashFlagsAllowed(
+  flags: RecognizeFlags,
+  model: string,
+  flashFamily: AsrFlashFamily,
+): void {
+  const unsupported: string[] = [];
+  if (flags.diarization === true) unsupported.push("--diarization");
+  if (flags.speakerCount !== undefined) unsupported.push("--speaker-count");
+  // qwen3 sync Flash does not use vocabulary_id; input-audio Flash (fun-asr-flash* / qwen-audio-*-asr-flash) does
+  if (flashFamily === "qwen3" && flags.vocabularyId !== undefined) {
+    unsupported.push("--vocabulary-id");
+  }
+  if (flags.channelId !== undefined) unsupported.push("--channel-id");
+  if (flags.async === true) unsupported.push("--async");
+  if (flags.pollInterval !== undefined) unsupported.push("--poll-interval");
+
+  if (unsupported.length > 0) {
+    throw new BailianError(
+      `Model "${model}" uses sync Flash ASR and does not support: ${unsupported.join(", ")}.\n` +
+        `Hint: Use an async filetrans model (e.g. fun-asr, qwen3-asr-flash-filetrans) for those flags.`,
+      ExitCode.USAGE,
+    );
+  }
+}
+
 export default defineCommand({
-  description: "Recognize speech from audio files (FunAudio-ASR)",
+  description: "Recognize speech from audio files (FunAudio-ASR / Qwen-ASR Flash)",
   auth: "apiKey",
   usageArgs: "--url <audio-url> [flags]",
   flags: RECOGNIZE_FLAGS,
@@ -68,6 +110,7 @@ export default defineCommand({
     "--url https://example.com/audio.mp3 --vocabulary-id vocab-abc123",
     "--url https://example.com/audio.mp3 --out result.json",
     "--url https://example.com/audio.mp3 --async --quiet",
+    "--url https://example.com/audio.mp3 --model qwen-audio-3.0-asr-flash --language en",
   ],
   async run(ctx) {
     const { settings, flags } = ctx;
@@ -90,22 +133,70 @@ export default defineCommand({
     }
 
     const model = flags.model || "fun-asr";
+    const route = resolveAsrApi(model);
+    if (route.kind === "unsupported") {
+      throw new BailianError(
+        route.unsupportedReason ?? `Unsupported ASR model: ${model}`,
+        ExitCode.USAGE,
+      );
+    }
+
+    if (route.kind === "sync-flash") {
+      assertSyncFlashFlagsAllowed(flags, model, route.flashFamily!);
+      if (rawUrls.length !== 1) {
+        throw new BailianError(
+          `Model "${model}" is a sync Flash ASR model and accepts exactly one --url (got ${rawUrls.length}).\n` +
+            `Hint: Pass a single audio URL, or use an async filetrans model for batch files.`,
+          ExitCode.USAGE,
+        );
+      }
+    }
+    if (
+      route.kind === "async-filetrans" &&
+      route.asyncInputStyle === "file_url" &&
+      rawUrls.length !== 1
+    ) {
+      throw new BailianError(
+        `Model "${model}" accepts exactly one --url (got ${rawUrls.length}).\n` +
+          "Hint: qwen3-asr-flash-filetrans* requires a single file_url.",
+        ExitCode.USAGE,
+      );
+    }
+
     const format = detectOutputFormat(settings.output);
 
     // Auto-upload local files in parallel
-    const resolvedUrls = await Promise.all(rawUrls.map((u) => ctx.client.uploadFile(u, model)));
+    const resolvedUrls = await Promise.all(rawUrls.map((url) => ctx.client.uploadFile(url, model)));
+
+    if (route.kind === "sync-flash") {
+      await handleSyncFlashMode(
+        ctx.client,
+        settings,
+        flags,
+        format,
+        model,
+        route,
+        resolvedUrls[0]!,
+      );
+      return;
+    }
+
     const channelId = flags.channelId;
-    const language = flags.language;
     const vocabularyId = flags.vocabularyId;
+    const languageFields = buildAsyncAsrLanguageFields(
+      route.asyncLanguageStyle ?? "language_hints",
+      flags.language,
+    );
 
     const body: DashScopeASRRequest = {
       model,
-      input: {
-        file_urls: resolvedUrls,
-      },
+      input:
+        route.asyncInputStyle === "file_url"
+          ? { file_url: resolvedUrls[0]! }
+          : { file_urls: resolvedUrls },
       parameters: {
         channel_id: channelId !== undefined ? [channelId] : [0],
-        language_hints: language ? [language] : undefined,
+        ...languageFields,
         diarization_enabled: diarization ? true : undefined,
         speaker_count: speakerCount,
         vocabulary_id: vocabularyId,
@@ -116,7 +207,7 @@ export default defineCommand({
     stripUndefined(body.parameters as Record<string, unknown>);
 
     if (settings.dryRun) {
-      emitResult({ request: body, mode: "async" }, format);
+      emitResult({ request: body, mode: "async", path: speechRecognizePath() }, format);
       return;
     }
 
@@ -128,6 +219,55 @@ export default defineCommand({
   },
 });
 
+async function handleSyncFlashMode(
+  client: Client,
+  settings: Settings,
+  flags: RecognizeFlags,
+  format: OutputFormat,
+  model: string,
+  route: AsrApiRoute,
+  audioUrl: string,
+): Promise<void> {
+  const flashFamily = route.flashFamily as AsrFlashFamily;
+  const body = buildAsrFlashRequest({
+    model,
+    audioUrl,
+    language: flags.language,
+    vocabularyId: flags.vocabularyId,
+    flashFamily,
+  });
+
+  if (settings.dryRun) {
+    emitResult({ request: body, mode: "sync", path: route.path }, format);
+    return;
+  }
+
+  if (!settings.quiet) {
+    process.stderr.write(`[Model: ${model}] [Mode: sync] [Files: 1]\n`);
+  }
+
+  const response = await client.requestJson<Record<string, unknown>>({
+    path: route.path,
+    method: "POST",
+    headers: { "X-DashScope-SSE": "disable" },
+    body,
+  });
+
+  const text = extractAsrFlashText(response, flashFamily);
+  if (text) {
+    process.stdout.write(text.endsWith("\n") ? text : `${text}\n`);
+  } else {
+    emitBare(JSON.stringify(response));
+  }
+
+  if (flags.out) {
+    writeFileSync(flags.out, JSON.stringify(response, null, 2) + "\n");
+    if (!settings.quiet) {
+      process.stderr.write(`Full result saved to: ${flags.out}\n`);
+    }
+  }
+}
+
 async function handleAsyncMode(
   client: Client,
   settings: Settings,
@@ -160,16 +300,16 @@ async function handleAsyncMode(
     url: pollUrl,
     intervalSec: pollInterval,
     timeoutSec: settings.timeout,
-    isComplete: (d) => (d as DashScopeASRTaskResult).output.task_status === "SUCCEEDED",
-    isFailed: (d) => (d as DashScopeASRTaskResult).output.task_status === "FAILED",
-    getStatus: (d) => (d as DashScopeASRTaskResult).output.task_status,
-    getErrorMessage: (d) => {
-      const o = (d as DashScopeASRTaskResult).output;
-      return (o as unknown as Record<string, unknown>).message as string | undefined;
+    isComplete: (data) => (data as DashScopeASRTaskResult).output.task_status === "SUCCEEDED",
+    isFailed: (data) => (data as DashScopeASRTaskResult).output.task_status === "FAILED",
+    getStatus: (data) => (data as DashScopeASRTaskResult).output.task_status,
+    getErrorMessage: (data) => {
+      const output = (data as DashScopeASRTaskResult).output;
+      return (output as unknown as Record<string, unknown>).message as string | undefined;
     },
   });
 
-  const results = result.output.results ?? [];
+  const results = collectAsrTranscriptionItems(result.output);
 
   if (results.length === 0) {
     emitResult({ task_id: taskId, status: result.output.task_status }, format);
@@ -179,12 +319,14 @@ async function handleAsyncMode(
   // Collect all transcription data for --out
   const allTransData: Record<string, unknown>[] = [];
 
-  for (let i = 0; i < results.length; i++) {
-    const subResult = results[i]!;
+  for (let index = 0; index < results.length; index++) {
+    const subResult = results[index]!;
     const isMulti = fileCount > 1;
 
     if (isMulti) {
-      process.stdout.write(`=== [${i + 1}/${results.length}] ${subResult.file_url ?? ""} ===\n`);
+      process.stdout.write(
+        `=== [${index + 1}/${results.length}] ${subResult.file_url ?? ""} ===\n`,
+      );
     }
 
     if (subResult.subtask_status === "FAILED") {

packages/commands/src/commands/token-plan/personal-key.ts

@@ -1,18 +0,0 @@
-import { defineCommand, detectOutputFormat } from "bailian-cli-core";
-import { emitResult } from "bailian-cli-runtime";
-
-const GET_KEY_API = "zeldaHttp.apikeyMgr./tokenplan/personal/api/v2/api-keys/getKeyByUid";
-
-export default defineCommand({
-  description: "Get the personal-edition TokenPlan API key (masked) for the current account",
-  auth: "console",
-  usageArgs: "[flags]",
-  flags: {},
-  exampleArgs: [""],
-  async run(ctx) {
-    const { settings } = ctx;
-    const format = detectOutputFormat(settings.output);
-    const result = await ctx.client.console(GET_KEY_API, {});
-    emitResult(result, format);
-  },
-});

packages/commands/src/commands/token-plan/personal-usage.ts

@@ -1,62 +0,0 @@
-import { defineCommand, detectOutputFormat } from "bailian-cli-core";
-import { emitResult } from "bailian-cli-runtime";
-
-const USAGE_API = "zeldaHttp.apikeyMgr./tokenplan/personal/api/v2/usage";
-const SUBSCRIPTION_API = "zeldaHttp.apikeyMgr./tokenplan/personal/api/v2/subscription";
-const ADDON_API = "zeldaHttp.apikeyMgr./tokenplan/personal/api/v2/addon/summary";
-
-const COMMODITY_CN = "sfm_tokenplansolo_public_cn";
-const COMMODITY_INTL = "sfm_tokenplansolo_public_intl";
-const ADDON_CN = "sfm_tokenplansoloaddon_public_cn";
-const ADDON_INTL = "sfm_tokenplansoloaddon_public_intl";
-
-function nested(obj: Record<string, unknown>, key: string): Record<string, unknown> | undefined {
-  const val = obj[key];
-  return val && typeof val === "object" && !Array.isArray(val)
-    ? (val as Record<string, unknown>)
-    : undefined;
-}
-
-/** Unwrap the console gateway `data.DataV2.data.data` envelope to the business payload. */
-function extract(result: Record<string, unknown>): Record<string, unknown> {
-  const data = nested(result, "data");
-  if (!data) return result;
-  const dataV2 = nested(data, "DataV2");
-  if (dataV2) {
-    const inner = nested(dataV2, "data");
-    const innerData = inner ? nested(inner, "data") : undefined;
-    return innerData ?? inner ?? dataV2;
-  }
-  return nested(data, "data") ?? data;
-}
-
-export default defineCommand({
-  description:
-    "Query personal-edition TokenPlan usage (5h/1w percentage, subscription, addon credits)",
-  auth: "console",
-  usageArgs: "[flags]",
-  flags: {},
-  exampleArgs: [""],
-  async run(ctx) {
-    const { settings } = ctx;
-    const format = detectOutputFormat(settings.output);
-    const intl = settings.consoleSite === "international";
-
-    const [usage, subscription, addon] = await Promise.all([
-      ctx.client.console(USAGE_API, {}),
-      ctx.client.console(SUBSCRIPTION_API, {
-        queryInstanceInfoRequest: { commodityCode: intl ? COMMODITY_INTL : COMMODITY_CN },
-      }),
-      ctx.client.console(ADDON_API, { commodityCode: intl ? ADDON_INTL : ADDON_CN }),
-    ]);
-
-    emitResult(
-      {
-        usage: extract(usage as Record<string, unknown>),
-        subscription: extract(subscription as Record<string, unknown>),
-        addonSummary: extract(addon as Record<string, unknown>),
-      },
-      format,
-    );
-  },
-});

packages/commands/src/commands/usage/coding-plan.ts

@@ -0,0 +1,132 @@
+import { defineCommand, detectOutputFormat, unwrapResponse } from "bailian-cli-core";
+import { emitResult } from "bailian-cli-runtime";
+import { printQuotaBox, readNumber, type QuotaSection } from "./quota-box.ts";
+import { formatNumber } from "./shared.ts";
+
+const CODING_PLAN_USAGE_API =
+  "zeldaEasy.broadscope-bailian.codingPlan.queryCodingPlanInstanceInfoV2";
+
+const COMMODITY_CODES: Record<string, string> = {
+  domestic: "sfm_codingplan_public_cn",
+  international: "sfm_codingplan_public_intl",
+};
+
+interface CodingPlanWindow {
+  usedQuota?: number;
+  totalQuota?: number;
+  /** Usage ratio in [0, 1]; absent when the window has no positive total or no used value. */
+  percentage?: number;
+  resetTime?: number;
+}
+
+interface CodingPlanUsage {
+  instanceType?: string;
+  per5Hour: CodingPlanWindow;
+  perWeek: CodingPlanWindow;
+  perBillMonth: CodingPlanWindow;
+}
+
+function readWindow(
+  quotaInfo: Record<string, unknown> | undefined,
+  fieldPrefix: string,
+): CodingPlanWindow {
+  const window: CodingPlanWindow = {};
+  if (!quotaInfo) return window;
+
+  const usedQuota = readNumber(quotaInfo[`${fieldPrefix}UsedQuota`]);
+  if (usedQuota !== undefined) window.usedQuota = usedQuota;
+  const totalQuota = readNumber(quotaInfo[`${fieldPrefix}TotalQuota`]);
+  if (totalQuota !== undefined) window.totalQuota = totalQuota;
+  const resetTime = readNumber(quotaInfo[`${fieldPrefix}QuotaNextRefreshTime`]);
+  if (resetTime !== undefined) window.resetTime = resetTime;
+
+  // Console rule: the usage rate only exists with a positive total and a used value.
+  if (usedQuota !== undefined && totalQuota !== undefined && totalQuota > 0) {
+    window.percentage = usedQuota / totalQuota;
+  }
+  return window;
+}
+
+/** Pick the first VALID instance's quota info, mirroring the Coding Plan console. */
+function readUsage(result: unknown): CodingPlanUsage | undefined {
+  const response = unwrapResponse(result as Record<string, unknown>);
+  const instances = Array.isArray(response.codingPlanInstanceInfos)
+    ? (response.codingPlanInstanceInfos as Record<string, unknown>[])
+    : [];
+  const validInstance = instances.find((instance) => instance.status === "VALID");
+  if (!validInstance) return undefined;
+
+  const quotaInfo = validInstance.codingPlanQuotaInfo as Record<string, unknown> | undefined;
+  const usage: CodingPlanUsage = {
+    per5Hour: readWindow(quotaInfo, "per5Hour"),
+    perWeek: readWindow(quotaInfo, "perWeek"),
+    perBillMonth: readWindow(quotaInfo, "perBillMonth"),
+  };
+  if (typeof validInstance.instanceType === "string" && validInstance.instanceType) {
+    usage.instanceType = validInstance.instanceType;
+  }
+  return usage;
+}
+
+function toSection(label: string, window: CodingPlanWindow): QuotaSection {
+  const section: QuotaSection = {
+    label,
+    emptyMessage: "No quota data for this window; verify in the Bailian Coding Plan console.",
+    percentage: window.percentage,
+    resetTime: window.resetTime,
+  };
+  if (window.usedQuota !== undefined && window.totalQuota !== undefined) {
+    section.detail = `Used: ${formatNumber(window.usedQuota)} / ${formatNumber(window.totalQuota)}`;
+  }
+  return section;
+}
+
+function printView(usage: CodingPlanUsage, generatedAt: number): void {
+  const planSuffix = usage.instanceType ? ` (${usage.instanceType})` : "";
+  printQuotaBox(
+    `Coding Plan Usage${planSuffix}`,
+    [
+      toSection("5-hour quota", usage.per5Hour),
+      toSection("1-week quota", usage.perWeek),
+      toSection("Monthly quota", usage.perBillMonth),
+    ],
+    generatedAt,
+  );
+}
+
+export default defineCommand({
+  description: "Show Coding Plan quota usage",
+  auth: "console",
+  usageArgs: "[flags]",
+  exampleArgs: ["", "--output json"],
+  async run(ctx) {
+    const { settings } = ctx;
+    const format = detectOutputFormat(settings.output);
+    const requestData = {
+      queryCodingPlanInstanceInfoRequest: {
+        commodityCode: COMMODITY_CODES[settings.consoleSite ?? "domestic"],
+        onlyLatestOne: true,
+      },
+    };
+
+    if (settings.dryRun) {
+      emitResult({ api: CODING_PLAN_USAGE_API, data: requestData }, format);
+      return;
+    }
+
+    const result = await ctx.client.console(CODING_PLAN_USAGE_API, requestData);
+    const usage = readUsage(result);
+
+    if (format === "json") {
+      emitResult(usage ?? {}, format);
+      return;
+    }
+
+    if (!usage) {
+      process.stdout.write("No active Coding Plan subscription found.\n");
+      return;
+    }
+
+    printView(usage, Date.now());
+  },
+});

packages/commands/src/commands/usage/freetier.ts

@@ -1,95 +1,22 @@
-import { defineCommand, detectOutputFormat, fetchModelList, type Client } from "bailian-cli-core";
+import { defineCommand, detectOutputFormat, unwrapResponse } from "bailian-cli-core";
 import { emitResult } from "bailian-cli-runtime";
+import {
+  FREE_TIER_API,
+  FREE_TIER_ONLY_STATUS_API,
+  extractFreeTierOnlyStatuses,
+  extractQuotas,
+  fetchAllModels,
+  pollFreeTierBatch,
+} from "./shared.ts";
 
-const ACTIVATE_API = "zeldaEasy.broadscope-bailian.freeTrial.batchActivateFreeTierOnly";
-const DEACTIVATE_API = "zeldaEasy.broadscope-bailian.freeTrial.batchDeactivateFreeTierOnly";
-const FREE_TIER_API = "zeldaEasy.broadscope-bailian.freeTrial.queryFreeTierQuota";
-const FREE_TIER_ONLY_STATUS_API = "zeldaEasy.broadscope-bailian.freeTrial.queryFreeTierOnlyStatus";
-
-interface FreeTierQuota {
-  model: string;
-  quotaTotal: number;
-  quotaInitTotal: number;
-}
-
-interface FreeTierOnlyStatus {
-  model: string;
-  freeTierOnly: boolean;
-}
+const ACTIVATE_API = "zeldaEasy.bailian-commerce.freeTrial.batchActivateFreeTierOnly";
+const DEACTIVATE_API = "zeldaEasy.bailian-commerce.freeTrial.batchDeactivateFreeTierOnly";
 
 interface BatchResultFailure {
   failureModelId: string;
   errorCode: string;
 }
 
-function getNestedRecord(
-  obj: Record<string, unknown>,
-  key: string,
-): Record<string, unknown> | undefined {
-  const val = obj[key];
-  if (val && typeof val === "object" && !Array.isArray(val)) return val as Record<string, unknown>;
-  return undefined;
-}
-
-function extractResponseData(result: Record<string, unknown>): Record<string, unknown> {
-  const data = getNestedRecord(result, "data");
-  if (!data) return result;
-
-  const dataV2 = getNestedRecord(data, "DataV2");
-  if (dataV2) {
-    const inner = getNestedRecord(dataV2, "data");
-    const innerData = inner ? getNestedRecord(inner, "data") : undefined;
-    return innerData ?? inner ?? dataV2;
-  }
-
-  const direct = getNestedRecord(data, "data");
-  return direct ?? data;
-}
-
-const POLL_INTERVAL_MS = 500;
-const MAX_POLLS = 20;
-
-async function pollUntilDone(
-  client: Client,
-  api: string,
-  requestKey: string,
-  models: string[],
-): Promise<unknown> {
-  let nextTaskId: string | undefined;
-
-  for (let attempt = 0; attempt < MAX_POLLS; attempt++) {
-    const requestData = {
-      [requestKey]: nextTaskId ? { taskId: nextTaskId } : { models },
-    };
-
-    const raw = await client.console(api, requestData);
-
-    const resp = extractResponseData(raw as Record<string, unknown>);
-    if (resp.taskId && Object.keys(resp).length === 1) {
-      nextTaskId = resp.taskId as string;
-      await new Promise((resolve) => setTimeout(resolve, POLL_INTERVAL_MS));
-      continue;
-    }
-    return raw;
-  }
-  return null;
-}
-
-async function fetchAllModelNames(client: Client): Promise<string[]> {
-  const allModels: Record<string, unknown>[] = [];
-  let page = 1;
-  while (true) {
-    const result = await fetchModelList((api, data) => client.console(api, data), {
-      pageNo: page,
-      pageSize: 50,
-    });
-    allModels.push(...result.models);
-    if (allModels.length >= result.total) break;
-    page++;
-  }
-  return allModels.map((item) => item.model as string).filter(Boolean);
-}
-
 export default defineCommand({
   description:
     "Enable or disable auto-stop for free-tier models. Enables by default; use --off to disable",
@@ -161,7 +88,7 @@ export default defineCommand({
     }
 
     if (!modelFlag) {
-      models = await fetchAllModelNames(ctx.client);
+      models = (await fetchAllModels(ctx.client)).map((model) => model.name);
     }
 
     if (off) {
@@ -172,12 +99,10 @@ export default defineCommand({
         }),
       ]);
 
-      const quotaData = extractResponseData(quotaResult as Record<string, unknown>);
-      const quotas = (quotaData.freeTierQuotas ?? []) as FreeTierQuota[];
+      const quotas = extractQuotas(quotaResult);
       const quotaMap = new Map(quotas.map((quota) => [quota.model, quota]));
 
-      const stopData = extractResponseData(stopResult as Record<string, unknown>);
-      const stopStatuses = (stopData.freeTierOnlyStatuses ?? []) as FreeTierOnlyStatus[];
+      const stopStatuses = extractFreeTierOnlyStatuses(stopResult);
       const stopMap = new Map(stopStatuses.map((status) => [status.model, status.freeTierOnly]));
 
       for (const name of models) {
@@ -192,7 +117,7 @@ export default defineCommand({
           );
           continue;
         }
-        await pollUntilDone(ctx.client, api, requestKey, [name]);
+        await pollFreeTierBatch(ctx.client, api, requestKey, [name]);
         process.stdout.write(`Disabled auto-stop for "${name}".\n`);
       }
       return;
@@ -200,13 +125,13 @@ export default defineCommand({
 
     const jsonResults: unknown[] = [];
     for (const name of models) {
-      const result = await pollUntilDone(ctx.client, api, requestKey, [name]);
+      const result = await pollFreeTierBatch(ctx.client, api, requestKey, [name]);
       if (format === "json") {
         jsonResults.push(result);
         continue;
       }
       if (result) {
-        const resultData = extractResponseData(result as Record<string, unknown>);
+        const resultData = unwrapResponse(result as Record<string, unknown>);
         const failureModels = (resultData.failureModels as BatchResultFailure[]) ?? [];
         if (failureModels.length > 0) {
           process.stderr.write(

packages/commands/src/commands/usage/quota-box.ts

@@ -0,0 +1,91 @@
+import {
+  ansi,
+  displayWidth,
+  renderGauge,
+  type GaugeCell,
+  type TextStyle,
+} from "bailian-cli-runtime";
+import { formatDateTime } from "./shared.ts";
+
+const BOX_WIDTH = 76;
+
+/** One quota window rendered inside the box: a label + usage ratio + reset time. */
+export interface QuotaSection {
+  label: string;
+  /** Shown instead of the gauge when the usage ratio is absent. */
+  emptyMessage: string;
+  /** Usage ratio in [0, 1]; absent means no data (possibly unlimited). */
+  percentage?: number;
+  resetTime?: number;
+  /** Optional dim line under the gauge, e.g. "Used: 38 / 100". */
+  detail?: string;
+}
+
+/** Accept only finite numbers; anything else counts as absent (possibly unlimited). */
+export function readNumber(value: unknown): number | undefined {
+  return typeof value === "number" && Number.isFinite(value) ? value : undefined;
+}
+
+/** Match the `usage free` gauge label style: 0.1% precision, no trailing zeros. */
+function formatPercentage(ratio: number): string {
+  const percent = Math.round(ratio * 1000) / 10;
+  return `${Number.isInteger(percent) ? percent : percent.toFixed(1)}%`;
+}
+
+function formatRemainingTime(resetTime: number, now: number): string {
+  const remainingMs = Math.max(0, resetTime - now);
+  const totalMinutes = Math.floor(remainingMs / 60_000);
+  if (totalMinutes === 0) return "now";
+
+  const days = Math.floor(totalMinutes / (24 * 60));
+  const hours = Math.floor((totalMinutes % (24 * 60)) / 60);
+  const minutes = totalMinutes % 60;
+  const parts: string[] = [];
+  if (days > 0) parts.push(`${days}d`);
+  if (hours > 0) parts.push(`${hours}h`);
+  if (minutes > 0 || parts.length === 0) parts.push(`${minutes}m`);
+  return parts.join(" ");
+}
+
+/** Print a bordered quota box with a title line and one gauge per section. */
+export function printQuotaBox(title: string, sections: QuotaSection[], generatedAt: number): void {
+  const color = ansi(process.stdout);
+  const writeLine = (text = "", style?: TextStyle) => {
+    const padding = Math.max(0, BOX_WIDTH - displayWidth(` ${text}`));
+    process.stdout.write(`│ ${style ? style(text) : text}${" ".repeat(padding)}│\n`);
+  };
+  // Pre-colored gauge cell: pad from the plain variant so ANSI escapes never shift the border.
+  const writeGaugeLine = (cell: GaugeCell) => {
+    const padding = Math.max(0, BOX_WIDTH - displayWidth(` ${cell.plain}`));
+    process.stdout.write(`│ ${cell.colored}${" ".repeat(padding)}│\n`);
+  };
+  const writeQuota = (section: QuotaSection) => {
+    writeLine(section.label, color.bold);
+    if (section.percentage === undefined) {
+      writeLine(section.emptyMessage, color.dim);
+      return;
+    }
+
+    const gaugeLabel = `${formatPercentage(section.percentage)} used`;
+    writeGaugeLine(renderGauge(section.percentage * 100, gaugeLabel));
+    if (section.detail) {
+      writeLine(section.detail, color.dim);
+    }
+    if (section.resetTime === undefined) {
+      writeLine("Resets: not applicable (no usage yet)", color.dim);
+      return;
+    }
+
+    const resetText = `Resets: ${formatDateTime(section.resetTime)}  (in ${formatRemainingTime(section.resetTime, generatedAt)})`;
+    writeLine(resetText, color.dim);
+  };
+
+  process.stdout.write(`┌${"─".repeat(BOX_WIDTH)}┐\n`);
+  writeLine(title, color.cyan);
+  writeLine(`Generated at: ${formatDateTime(generatedAt)} (local time)`, color.dim);
+  for (const section of sections) {
+    process.stdout.write(`├${"─".repeat(BOX_WIDTH)}┤\n`);
+    writeQuota(section);
+  }
+  process.stdout.write(`└${"─".repeat(BOX_WIDTH)}┘\n`);
+}

packages/commands/src/commands/usage/shared.ts

@@ -24,6 +24,14 @@ export function formatDate(ts: number): string {
   return `${year}-${month}-${day}`;
 }
 
+export function formatDateTime(ts: number): string {
+  const date = new Date(ts);
+  const hour = String(date.getHours()).padStart(2, "0");
+  const minute = String(date.getMinutes()).padStart(2, "0");
+  const second = String(date.getSeconds()).padStart(2, "0");
+  return `${formatDate(ts)} ${hour}:${minute}:${second}`;
+}
+
 export function requireWorkspaceId(settings: Settings, binName: string): string {
   if (settings.workspaceId) return settings.workspaceId;
 
@@ -102,9 +110,9 @@ export async function fetchAllModels(client: Client): Promise<ModelInfo[]> {
 // Free-tier quota
 // ---------------------------------------------------------------------------
 
-export const FREE_TIER_API = "zeldaEasy.broadscope-bailian.freeTrial.queryFreeTierQuota";
+export const FREE_TIER_API = "zeldaEasy.bailian-commerce.freeTrial.queryFreeTierQuota";
 export const FREE_TIER_ONLY_STATUS_API =
-  "zeldaEasy.broadscope-bailian.freeTrial.queryFreeTierOnlyStatus";
+  "zeldaEasy.bailian-commerce.freeTrial.queryFreeTierOnlyStatus";
 
 export interface FreeTierQuota {
   model: string;
@@ -257,22 +265,27 @@ export interface ListStatisticResponse {
 }
 
 const POLL_INTERVAL_MS = 500;
-const MAX_POLLS = 30;
+const DEFAULT_MAX_POLLS = 30;
 
-export async function pollTelemetryApi(
+/**
+ * Poll a console API until it returns a terminal (non task-id) response.
+ * The gateway answers an async request with a bare `{taskId}` envelope; the
+ * caller re-issues with that id until real data arrives or the budget runs out.
+ * `buildRequest` shapes each attempt (initial call vs. taskId follow-up) so the
+ * same loop serves every request-wrapper convention (telemetry `reqDTO`,
+ * free-tier batch `…Request`).
+ */
+export async function pollConsoleUntilDone(
   client: Client,
   api: string,
-  reqDTO: Record<string, unknown>,
+  buildRequest: (taskId: string | undefined) => Record<string, unknown>,
+  maxPolls = DEFAULT_MAX_POLLS,
 ): Promise<unknown> {
   let nextTaskId: string | undefined;
 
-  for (let attempt = 0; attempt < MAX_POLLS; attempt++) {
-    const requestData = nextTaskId
-      ? { reqDTO: { ...reqDTO, asyncTaskId: nextTaskId } }
-      : { reqDTO };
-
-    const raw = await client.console(api, requestData);
-    const resp = extractResponseData(raw as Record<string, unknown>);
+  for (let attempt = 0; attempt < maxPolls; attempt++) {
+    const raw = await client.console(api, buildRequest(nextTaskId));
+    const resp = unwrapResponse(raw as Record<string, unknown>);
 
     if (resp.taskId && Object.keys(resp).length === 1) {
       nextTaskId = resp.taskId as string;
@@ -284,6 +297,32 @@ export async function pollTelemetryApi(
   return null;
 }
 
+/** Telemetry APIs wrap the payload in `reqDTO` and echo the task id as `asyncTaskId`. */
+export async function pollTelemetryApi(
+  client: Client,
+  api: string,
+  reqDTO: Record<string, unknown>,
+): Promise<unknown> {
+  return pollConsoleUntilDone(client, api, (taskId) =>
+    taskId ? { reqDTO: { ...reqDTO, asyncTaskId: taskId } } : { reqDTO },
+  );
+}
+
+/** Free-tier batch activate/deactivate wrap the payload in `requestKey` and echo `taskId`. */
+export async function pollFreeTierBatch(
+  client: Client,
+  api: string,
+  requestKey: string,
+  models: string[],
+): Promise<unknown> {
+  return pollConsoleUntilDone(
+    client,
+    api,
+    (taskId) => ({ [requestKey]: taskId ? { taskId } : { models } }),
+    20,
+  );
+}
+
 export function extractOverviewData(result: unknown): OverviewStatistic | undefined {
   const resp = extractResponseData(result as Record<string, unknown>);
   if (resp.callSuccessCount !== undefined || resp.usages !== undefined) {

packages/commands/src/commands/usage/stats.ts

@@ -1,176 +1,26 @@
-import {
-  defineCommand,
-  BailianError,
-  ExitCode,
-  detectOutputFormat,
-  type Settings,
-  type Client,
-} from "bailian-cli-core";
+import { defineCommand, BailianError, ExitCode, detectOutputFormat } from "bailian-cli-core";
 import { ansi, emitResult } from "bailian-cli-runtime";
 import { displayWidth, padEnd } from "bailian-cli-runtime";
-
-const OVERVIEW_API = "zeldaEasy.bailian-telemetry.model.getModelUsageStatistic";
-const LIST_API = "zeldaEasy.bailian-telemetry.model.listModelUsageStatisticData";
-
-interface UsageItem {
-  key: string;
-  value: number;
-  unit: string;
-}
-
-interface OverviewStatistic {
-  callCount: number;
-  modelCount: number;
-  callSuccessCount: number;
-  usages: UsageItem[];
-}
-
-interface ModelStatisticItem {
-  model: string;
-  callSuccessCount: number;
-  usages?: UsageItem[];
-  usage?: Record<string, number | undefined>;
-}
-
-interface ListStatisticResponse {
-  list: ModelStatisticItem[];
-  totalCount: number;
-  maxResults: number;
-}
-
-function getNestedRecord(
-  obj: Record<string, unknown>,
-  key: string,
-): Record<string, unknown> | undefined {
-  const val = obj[key];
-  if (val && typeof val === "object" && !Array.isArray(val)) return val as Record<string, unknown>;
-  return undefined;
-}
-
-function extractResponseData(result: Record<string, unknown>): Record<string, unknown> {
-  const data = getNestedRecord(result, "data");
-  if (!data) return result;
-
-  const dataV2 = getNestedRecord(data, "DataV2");
-  if (dataV2) {
-    const inner = getNestedRecord(dataV2, "data");
-    const innerData = inner ? getNestedRecord(inner, "data") : undefined;
-    return innerData ?? inner ?? dataV2;
-  }
-
-  const direct = getNestedRecord(data, "data");
-  return direct ?? data;
-}
-
-const POLL_INTERVAL_MS = 500;
-const MAX_POLLS = 30;
-
-async function pollTelemetryApi(
-  client: Client,
-  api: string,
-  reqDTO: Record<string, unknown>,
-): Promise<unknown> {
-  let nextTaskId: string | undefined;
-
-  for (let attempt = 0; attempt < MAX_POLLS; attempt++) {
-    const requestData = nextTaskId
-      ? { reqDTO: { ...reqDTO, asyncTaskId: nextTaskId } }
-      : { reqDTO };
-
-    const raw = await client.console(api, requestData);
-
-    const resp = extractResponseData(raw as Record<string, unknown>);
-
-    if (resp.taskId && Object.keys(resp).length === 1) {
-      nextTaskId = resp.taskId as string;
-      await new Promise((resolve) => setTimeout(resolve, POLL_INTERVAL_MS));
-      continue;
-    }
-
-    return raw;
-  }
-  return null;
-}
-
-function requireWorkspaceId(settings: Settings, binName: string): string {
-  if (settings.workspaceId) return settings.workspaceId;
-
-  throw new BailianError(
-    `workspace-id is required. Set via --workspace-id, BAILIAN_WORKSPACE_ID, or \`${binName} config set workspace_id <id>\`.`,
-    ExitCode.GENERAL,
-    `Run \`${binName} workspace list\` to view available workspaces.`,
-  );
-}
-
-function formatNumber(num: number): string {
-  return num.toLocaleString("en-US");
-}
-
-function formatDate(ts: number): string {
-  const date = new Date(ts);
-  const year = date.getFullYear();
-  const month = String(date.getMonth() + 1).padStart(2, "0");
-  const day = String(date.getDate()).padStart(2, "0");
-  return `${year}-${month}-${day}`;
-}
-
-function extractOverviewData(result: unknown): OverviewStatistic | undefined {
-  const resp = extractResponseData(result as Record<string, unknown>);
-  if (resp.callSuccessCount !== undefined || resp.usages !== undefined) {
-    return resp as unknown as OverviewStatistic;
-  }
-  return undefined;
-}
-
-function extractListData(result: unknown): ListStatisticResponse {
-  const resp = extractResponseData(result as Record<string, unknown>);
-  const list = (resp.list as ModelStatisticItem[]) ?? [];
-  const totalCount = (resp.totalCount as number) ?? 0;
-  const maxResults = (resp.maxResults as number) ?? 0;
-  return { list, totalCount, maxResults };
-}
-
-function resolveUsageMap(item: ModelStatisticItem): Record<string, number> {
-  const out: Record<string, number> = {};
-  if (item.usages && Array.isArray(item.usages)) {
-    for (const entry of item.usages) {
-      if (entry.key && entry.value != null) {
-        out[entry.key] = entry.value;
-      }
-    }
-  }
-  if (item.usage && typeof item.usage === "object") {
-    for (const [key, val] of Object.entries(item.usage)) {
-      if (val != null) out[key] = val;
-    }
-  }
-  return out;
-}
+import {
+  LIST_API,
+  OVERVIEW_API,
+  USAGE_KEY_LABELS,
+  extractListData,
+  extractOverviewData,
+  formatDate,
+  formatNumber,
+  pollTelemetryApi,
+  requireWorkspaceId,
+  resolveUsageMap,
+  type ModelStatisticItem,
+  type OverviewStatistic,
+} from "./shared.ts";
 
 interface UsageLabel {
   en: string;
   unit?: string;
 }
 
-const USAGE_KEY_LABELS: Record<string, UsageLabel> = {
-  total_token: { en: "Total Tokens", unit: "tokens" },
-  input_token: { en: "Input Tokens", unit: "tokens" },
-  output_token: { en: "Output Tokens", unit: "tokens" },
-  input_token_cache: { en: "Cached Tokens", unit: "tokens" },
-  input_token_cache_read: { en: "Cache Read", unit: "tokens" },
-  input_token_cache_creation: { en: "Cache Creation", unit: "tokens" },
-  thinking_input_token: { en: "Thinking Input", unit: "tokens" },
-  thinking_output_token: { en: "Thinking Output", unit: "tokens" },
-  text_input_token: { en: "Text Input", unit: "tokens" },
-  purein_text_output_token: { en: "Text Output", unit: "tokens" },
-  embedding_token: { en: "Embedding", unit: "tokens" },
-  image_number: { en: "Images", unit: "images" },
-  video_duration: { en: "Video Duration", unit: "sec" },
-  content_duration: { en: "Audio Duration", unit: "sec" },
-  tts_text_number: { en: "TTS Chars", unit: "chars" },
-  total_token_avg: { en: "Avg Tokens/Req" },
-};
-
 function formatLabel(label: UsageLabel): string {
   const unitSuffix = label.unit ? ` [${label.unit}]` : "";
   return `${label.en}${unitSuffix}`;

packages/commands/src/commands/usage/token-plan.ts

@@ -0,0 +1,77 @@
+import { defineCommand, detectOutputFormat, unwrapResponse } from "bailian-cli-core";
+import { emitResult } from "bailian-cli-runtime";
+import { printQuotaBox, readNumber } from "./quota-box.ts";
+
+const TOKEN_PLAN_USAGE_API = "zeldaHttp.apikeyMgr./tokenplan/personal/api/v2/usage";
+
+interface TokenPlanUsage {
+  per5HourPercentage?: number;
+  per5HourResetTime?: number;
+  per1WeekPercentage?: number;
+  per1WeekResetTime?: number;
+}
+
+function readUsage(result: unknown): TokenPlanUsage {
+  const response = unwrapResponse(result as Record<string, unknown>);
+  const usage: TokenPlanUsage = {};
+
+  const per5HourPercentage = readNumber(response.per5HourPercentage);
+  if (per5HourPercentage !== undefined) usage.per5HourPercentage = per5HourPercentage;
+  const per5HourResetTime = readNumber(response.per5HourResetTime);
+  if (per5HourResetTime !== undefined) usage.per5HourResetTime = per5HourResetTime;
+  const per1WeekPercentage = readNumber(response.per1WeekPercentage);
+  if (per1WeekPercentage !== undefined) usage.per1WeekPercentage = per1WeekPercentage;
+  const per1WeekResetTime = readNumber(response.per1WeekResetTime);
+  if (per1WeekResetTime !== undefined) usage.per1WeekResetTime = per1WeekResetTime;
+
+  return usage;
+}
+
+function printView(usage: TokenPlanUsage, generatedAt: number): void {
+  printQuotaBox(
+    "Token Plan Usage",
+    [
+      {
+        label: "5-hour quota",
+        emptyMessage:
+          "The 5-hour limit may be unlimited; verify in the Bailian Token Plan console.",
+        percentage: usage.per5HourPercentage,
+        resetTime: usage.per5HourResetTime,
+      },
+      {
+        label: "1-week quota",
+        emptyMessage:
+          "The 1-week limit may be unlimited; verify in the Bailian Token Plan console.",
+        percentage: usage.per1WeekPercentage,
+        resetTime: usage.per1WeekResetTime,
+      },
+    ],
+    generatedAt,
+  );
+}
+
+export default defineCommand({
+  description: "Show Token Plan quota usage",
+  auth: "console",
+  usageArgs: "[flags]",
+  exampleArgs: ["", "--output json"],
+  async run(ctx) {
+    const { settings } = ctx;
+    const format = detectOutputFormat(settings.output);
+
+    if (settings.dryRun) {
+      emitResult({ api: TOKEN_PLAN_USAGE_API, data: {} }, format);
+      return;
+    }
+
+    const result = await ctx.client.console(TOKEN_PLAN_USAGE_API, {});
+    const usage = readUsage(result);
+
+    if (format === "json") {
+      emitResult(usage, format);
+      return;
+    }
+
+    printView(usage, Date.now());
+  },
+});

packages/commands/src/index.ts

@@ -33,10 +33,6 @@ export { default as memoryUpdate } from "./commands/memory/update.ts";
 export { default as memoryDelete } from "./commands/memory/delete.ts";
 export { default as memoryProfileCreate } from "./commands/memory/profile-create.ts";
 export { default as memoryProfileGet } from "./commands/memory/profile-get.ts";
-export { default as memoryProfileList } from "./commands/memory/profile-list.ts";
-export { default as memoryProfileDetail } from "./commands/memory/profile-detail.ts";
-export { default as memoryProfileUpdate } from "./commands/memory/profile-update.ts";
-export { default as memoryProfileDelete } from "./commands/memory/profile-delete.ts";
 export { default as knowledgeRetrieve } from "./commands/knowledge/retrieve.ts";
 export { default as knowledgeSearch } from "./commands/knowledge/search.ts";
 export { default as knowledgeChat } from "./commands/knowledge/chat.ts";
@@ -52,6 +48,8 @@ export { default as usageFree } from "./commands/usage/free.ts";
 export { default as usageFreetier } from "./commands/usage/freetier.ts";
 export { default as usageStats } from "./commands/usage/stats.ts";
 export { default as usageSummary } from "./commands/usage/summary.ts";
+export { default as usageTokenPlan } from "./commands/usage/token-plan.ts";
+export { default as usageCodingPlan } from "./commands/usage/coding-plan.ts";
 export { default as pipelineRun } from "./commands/pipeline/run.ts";
 export { default as pipelineValidate } from "./commands/pipeline/validate.ts";
 export { default as advisorRecommend } from "./commands/advisor/recommend.ts";
@@ -95,13 +93,10 @@ export { default as tokenPlanListSeats } from "./commands/token-plan/list-seats.
 export { default as tokenPlanCreateKey } from "./commands/token-plan/create-key.ts";
 export { default as tokenPlanAssignSeats } from "./commands/token-plan/assign-seats.ts";
 export { default as tokenPlanAddMember } from "./commands/token-plan/add-member.ts";
-export { default as tokenPlanPersonalUsage } from "./commands/token-plan/personal-usage.ts";
-export { default as tokenPlanPersonalKey } from "./commands/token-plan/personal-key.ts";
 export { default as managedAgentInit } from "./commands/managed-agent/init.ts";
 export { default as managedAgentValidate } from "./commands/managed-agent/validate.ts";
 export { default as managedAgentPlan } from "./commands/managed-agent/plan.ts";
 export { default as managedAgentApply } from "./commands/managed-agent/apply.ts";
-export { default as managedAgentRun } from "./commands/managed-agent/run.ts";
 export { default as managedAgentDestroy } from "./commands/managed-agent/destroy.ts";
 export { default as managedAgentStateList } from "./commands/managed-agent/state-list.ts";
 export { default as managedAgentStateShow } from "./commands/managed-agent/state-show.ts";

packages/commands/tests/coding-plan-usage.test.ts

@@ -0,0 +1,213 @@
+import { afterEach, describe, expect, test, vi } from "vite-plus/test";
+import codingPlanUsage from "../src/commands/usage/coding-plan.ts";
+
+const originalNoColor = process.env.NO_COLOR;
+const originalForceColor = process.env.FORCE_COLOR;
+const originalIsTty = Object.getOwnPropertyDescriptor(process.stdout, "isTTY");
+
+afterEach(() => {
+  if (originalNoColor === undefined) delete process.env.NO_COLOR;
+  else process.env.NO_COLOR = originalNoColor;
+  if (originalForceColor === undefined) delete process.env.FORCE_COLOR;
+  else process.env.FORCE_COLOR = originalForceColor;
+  if (originalIsTty) Object.defineProperty(process.stdout, "isTTY", originalIsTty);
+  else delete (process.stdout as { isTTY?: boolean }).isTTY;
+  vi.restoreAllMocks();
+});
+
+function captureStdout(): string[] {
+  const output: string[] = [];
+  vi.spyOn(process.stdout, "write").mockImplementation((chunk) => {
+    output.push(String(chunk));
+    return true;
+  });
+  return output;
+}
+
+async function runCodingPlan(response: Record<string, unknown>, output?: string): Promise<void> {
+  await codingPlanUsage.run({
+    client: { console: vi.fn().mockResolvedValue(response) },
+    flags: {},
+    settings: { dryRun: false, output },
+  } as never);
+}
+
+function wrapResponse(data: Record<string, unknown>): Record<string, unknown> {
+  return {
+    data: {
+      DataV2: {
+        data: {
+          data,
+        },
+      },
+    },
+  };
+}
+
+function makeInstanceResponse(
+  quotaInfo: Record<string, unknown>,
+  overrides: Record<string, unknown> = {},
+): Record<string, unknown> {
+  return wrapResponse({
+    codingPlanInstanceInfos: [
+      { status: "VALID", instanceType: "pro", codingPlanQuotaInfo: quotaInfo, ...overrides },
+    ],
+  });
+}
+
+const FULL_QUOTA_INFO = {
+  per5HourUsedQuota: 38,
+  per5HourTotalQuota: 100,
+  per5HourQuotaNextRefreshTime: 1_786_000_000_000,
+  perWeekUsedQuota: 500,
+  perWeekTotalQuota: 1000,
+  perWeekQuotaNextRefreshTime: 1_786_100_000_000,
+  perBillMonthUsedQuota: 950,
+  perBillMonthTotalQuota: 1000,
+  perBillMonthQuotaNextRefreshTime: 1_786_200_000_000,
+};
+
+describe("usage coding-plan view", () => {
+  test("renders the three quota windows with usage rates and used/total details", async () => {
+    const output = captureStdout();
+
+    await runCodingPlan(makeInstanceResponse(FULL_QUOTA_INFO));
+
+    const renderedOutput = output.join("");
+    expect(renderedOutput).toContain("Coding Plan Usage (pro)");
+    expect(renderedOutput).toContain("5-hour quota");
+    expect(renderedOutput).toContain("1-week quota");
+    expect(renderedOutput).toContain("Monthly quota");
+    expect(renderedOutput).toContain("38% used");
+    expect(renderedOutput).toContain("50% used");
+    expect(renderedOutput).toContain("95% used");
+    expect(renderedOutput).toContain("Used: 38 / 100");
+    expect(renderedOutput).toContain("Used: 950 / 1,000");
+  });
+
+  test("skips non-VALID instances when picking quota info", async () => {
+    const output = captureStdout();
+
+    await runCodingPlan(
+      wrapResponse({
+        codingPlanInstanceInfos: [
+          {
+            status: "EXPIRED",
+            codingPlanQuotaInfo: { per5HourUsedQuota: 1, per5HourTotalQuota: 2 },
+          },
+          { status: "VALID", codingPlanQuotaInfo: FULL_QUOTA_INFO },
+        ],
+      }),
+    );
+
+    expect(output.join("")).toContain("38% used");
+  });
+
+  test("renders windows without a positive total as missing quota data", async () => {
+    const output = captureStdout();
+
+    await runCodingPlan(
+      makeInstanceResponse({
+        per5HourUsedQuota: 38,
+        per5HourTotalQuota: 0,
+        perWeekUsedQuota: 500,
+        perBillMonthUsedQuota: "not-a-number",
+        perBillMonthTotalQuota: 1000,
+      }),
+    );
+
+    const renderedOutput = output.join("");
+    const emptyMessageCount = renderedOutput.split(
+      "No quota data for this window; verify in the Bailian Coding Plan console.",
+    ).length;
+    expect(emptyMessageCount - 1).toBe(3);
+  });
+
+  test("reports when there is no active subscription", async () => {
+    const output = captureStdout();
+
+    await runCodingPlan(wrapResponse({ codingPlanInstanceInfos: [] }));
+
+    expect(output.join("")).toContain("No active Coding Plan subscription found.");
+  });
+
+  test("renders the gauge in the usage-free style: brand fill and proportional cells", async () => {
+    delete process.env.NO_COLOR;
+    process.env.FORCE_COLOR = "3";
+    Object.defineProperty(process.stdout, "isTTY", { configurable: true, value: true });
+    const output = captureStdout();
+
+    await runCodingPlan(makeInstanceResponse(FULL_QUOTA_INFO));
+
+    // Brand-cyan fill cell, same as the `usage free` gauge column
+    expect(output.join("")).toContain("\u001B[38;2;0;150;160m\u2588");
+  });
+
+  test("fills gauge cells proportionally to the usage rate", async () => {
+    process.env.NO_COLOR = "1";
+    const output = captureStdout();
+
+    await runCodingPlan(makeInstanceResponse(FULL_QUOTA_INFO));
+
+    const renderedOutput = output.join("");
+    // 95% of the default 20-cell gauge → 19 filled cells + 1 track space
+    expect(renderedOutput).toContain(`${"\u2588".repeat(19)} `);
+    expect(renderedOutput).not.toContain("\u2588".repeat(20));
+  });
+});
+
+describe("usage coding-plan json", () => {
+  test("outputs the three windows with used/total/percentage/resetTime", async () => {
+    const output = captureStdout();
+
+    await runCodingPlan(makeInstanceResponse(FULL_QUOTA_INFO), "json");
+
+    expect(JSON.parse(output.join(""))).toEqual({
+      instanceType: "pro",
+      per5Hour: {
+        usedQuota: 38,
+        totalQuota: 100,
+        percentage: 0.38,
+        resetTime: 1_786_000_000_000,
+      },
+      perWeek: {
+        usedQuota: 500,
+        totalQuota: 1000,
+        percentage: 0.5,
+        resetTime: 1_786_100_000_000,
+      },
+      perBillMonth: {
+        usedQuota: 950,
+        totalQuota: 1000,
+        percentage: 0.95,
+        resetTime: 1_786_200_000_000,
+      },
+    });
+  });
+
+  test("returns an empty JSON object when no VALID instance exists", async () => {
+    const output = captureStdout();
+
+    await runCodingPlan(wrapResponse({}), "json");
+
+    expect(output.join("").trim()).toBe("{}");
+  });
+
+  test("omits non-numeric quota fields from the JSON output", async () => {
+    const output = captureStdout();
+
+    await runCodingPlan(
+      makeInstanceResponse(
+        { per5HourUsedQuota: "not-a-number", per5HourTotalQuota: 100 },
+        { instanceType: undefined },
+      ),
+      "json",
+    );
+
+    expect(JSON.parse(output.join(""))).toEqual({
+      per5Hour: { totalQuota: 100 },
+      perWeek: {},
+      perBillMonth: {},
+    });
+  });
+});

packages/commands/tests/credentials-bridge.test.ts

@@ -124,8 +124,7 @@ test("inject:已带后缀且尾斜杠的 base_url 去斜杠后原样保留", ()
   expect(providers.bailian.base_url).toBe("https://x.maas.aliyuncs.com/api/v1/agentstudio");
 });
 
-test("inject:workspace_id 引用且为空时按 env > settings 填充;有字面量则保留", () => {
-  delete process.env.BAILIAN_WORKSPACE_ID;
+test("inject:workspace_id 引用且为空时用 settings 填充;有字面量则保留", () => {
   const empty = { bailian: { api_key: "", workspace_id: "" } };
   injectProviderCredentials(
     empty,
@@ -133,16 +132,6 @@ test("inject:workspace_id 引用且为空时按 env > settings 填充;有字面
   );
   expect(empty.bailian.workspace_id).toBe("ws-settings");
 
-  // 内联运行时(对象配置)不做 ${} 插值,env 变量在此补读。
-  process.env.BAILIAN_WORKSPACE_ID = "ws-env";
-  const fromEnv = { bailian: { api_key: "", workspace_id: "" } };
-  injectProviderCredentials(
-    fromEnv,
-    makeHost({ apiCred: bailianCred(), workspaceId: "ws-settings" }),
-  );
-  expect(fromEnv.bailian.workspace_id).toBe("ws-env");
-  delete process.env.BAILIAN_WORKSPACE_ID;
-
   const literal = { bailian: { api_key: "", workspace_id: "ws-yaml" } };
   injectProviderCredentials(
     literal,
@@ -151,37 +140,6 @@ test("inject:workspace_id 引用且为空时按 env > settings 填充;有字面
   expect(literal.bailian.workspace_id).toBe("ws-yaml");
 });
 
-test("inject:workspace 已知时 base_url 拼工作空间主机,而非模型域 origin", () => {
-  // agents.yaml 字面量 workspace_id + 空 base_url。
-  const literal = { bailian: { api_key: "", base_url: "", workspace_id: "ws-yaml" } };
-  injectProviderCredentials(literal, makeHost({ apiCred: bailianCred() }));
-  expect(literal.bailian.base_url).toBe(
-    "https://ws-yaml.cn-beijing.maas.aliyuncs.com/api/v1/agentstudio",
-  );
-
-  // 内联块:workspace_id 由 settings 填充后同样走工作空间主机。
-  const inline = { bailian: { api_key: "", base_url: "", workspace_id: "" } };
-  injectProviderCredentials(
-    inline,
-    makeHost({ apiCred: bailianCred(), workspaceId: "ws-settings" }),
-  );
-  expect(inline.bailian.workspace_id).toBe("ws-settings");
-  expect(inline.bailian.base_url).toBe(
-    "https://ws-settings.cn-beijing.maas.aliyuncs.com/api/v1/agentstudio",
-  );
-
-  // 显式 base_url 字面量永远优先于拼装。
-  const explicit = {
-    bailian: {
-      api_key: "",
-      base_url: "https://custom.example.com/api/v1/agentstudio",
-      workspace_id: "ws-yaml",
-    },
-  };
-  injectProviderCredentials(explicit, makeHost({ apiCred: bailianCred() }));
-  expect(explicit.bailian.base_url).toBe("https://custom.example.com/api/v1/agentstudio");
-});
-
 test("inject:无凭证时 api_key 保持不变,base_url 仍用 client 默认域名补齐(离线/范围外 schema 可用)", () => {
   const providers = { bailian: { api_key: "", base_url: "" } };
   injectProviderCredentials(providers, makeHost({}));

packages/commands/tests/e2e/speech-recognize.e2e.test.ts

@@ -1,4 +1,6 @@
 import { readFileSync } from "node:fs";
+import http from "node:http";
+import type { AddressInfo } from "node:net";
 import { join } from "node:path";
 import { describe, expect, test } from "vite-plus/test";
 import {
@@ -16,6 +18,37 @@ import { SPEECH_ROUTES } from "./topic-routes.ts";
  */
 
 describe("e2e: speech recognize", () => {
+  async function runRecognizeDryRun(args: string[]) {
+    const { stdout, stderr, exitCode } = await runCommandE2e(SPEECH_ROUTES, [
+      "speech",
+      "recognize",
+      ...args,
+      "--dry-run",
+      "--output",
+      "json",
+      "--quiet",
+    ]);
+    expect(exitCode, stderr).toBe(0);
+    return parseStdoutJson<{
+      mode?: string;
+      path?: string;
+      request?: {
+        model?: string;
+        parameters?: {
+          format?: string;
+          language_hints?: string[];
+          language?: string;
+          vocabulary_id?: string;
+        };
+        input?: {
+          file_url?: string;
+          file_urls?: string[];
+          messages?: Array<{ content?: Array<{ type?: string }> }>;
+        };
+      };
+    }>(stdout);
+  }
+
   test("speech recognize --help 正常退出", async () => {
     const { stderr, exitCode } = await runCommandE2e(SPEECH_ROUTES, [
       "speech",
@@ -25,6 +58,217 @@ describe("e2e: speech recognize", () => {
     expect(exitCode, stderr).toBe(0);
     expect(stderr).toMatch(/recognize|--url|model|audio/i);
   });
+
+  test("speech recognize sync-flash dry-run 走 multimodal-generation", async () => {
+    const body = await runRecognizeDryRun([
+      "--model",
+      "qwen-audio-3.0-asr-flash",
+      "--url",
+      "https://dashscope.oss-cn-beijing.aliyuncs.com/samples/audio/paraformer/hello_world_female2.wav",
+      "--language",
+      "en",
+      "--vocabulary-id",
+      "vocab-e2e",
+    ]);
+    expect(body.mode).toBe("sync");
+    expect(body.path).toBe("/api/v1/services/aigc/multimodal-generation/generation");
+    expect(body.request?.model).toBe("qwen-audio-3.0-asr-flash");
+    expect(body.request?.parameters?.format).toBe("wav");
+    expect(body.request?.parameters?.language_hints).toEqual(["en"]);
+    expect(body.request?.parameters?.vocabulary_id).toBe("vocab-e2e");
+    expect(body.request?.input?.messages?.[0]?.content?.[0]?.type).toBe("input_audio");
+  });
+
+  test("speech recognize qwen3 filetrans dry-run 使用 file_url 与 language", async () => {
+    const body = await runRecognizeDryRun([
+      "--model",
+      "qwen3-asr-flash-filetrans",
+      "--url",
+      "https://dashscope.oss-cn-beijing.aliyuncs.com/samples/audio/paraformer/hello_world_female2.wav",
+      "--language",
+      "zh",
+    ]);
+    expect(body.mode).toBe("async");
+    expect(body.path).toBe("/api/v1/services/audio/asr/transcription");
+    expect(body.request?.input?.file_url?.startsWith("https://")).toBe(true);
+    expect(body.request?.input?.file_urls).toBeUndefined();
+    expect(body.request?.parameters?.language).toBe("zh");
+    expect(body.request?.parameters?.language_hints).toBeUndefined();
+  });
+
+  test("speech recognize realtime 模型报用法错误", async () => {
+    // Use --dry-run to skip auth so CI without API keys still hits USAGE(2)
+    const { stderr, exitCode } = await runCommandE2e(SPEECH_ROUTES, [
+      "speech",
+      "recognize",
+      "--model",
+      "qwen3-asr-flash-realtime",
+      "--url",
+      "https://example.com/a.wav",
+      "--dry-run",
+      "--quiet",
+    ]);
+    expect(exitCode).toBe(2);
+    expect(stderr).toMatch(/realtime|WebSocket|unsupported/i);
+  });
+
+  test("speech recognize flash 真实请求走 sync endpoint 并落盘 --out", async () => {
+    let requestPath = "";
+    let requestBody: Record<string, unknown> = {};
+    let sseHeader: string | undefined;
+    const server = http.createServer((request, response) => {
+      const chunks: Buffer[] = [];
+      request.on("data", (chunk: Buffer) => chunks.push(chunk));
+      request.on("end", () => {
+        requestPath = request.url ?? "";
+        requestBody = JSON.parse(Buffer.concat(chunks).toString("utf8")) as Record<string, unknown>;
+        sseHeader = request.headers["x-dashscope-sse"] as string | undefined;
+        response.writeHead(200, { "Content-Type": "application/json" });
+        response.end(
+          JSON.stringify({
+            output: { text: "flash recognition works" },
+            request_id: "request-146",
+          }),
+        );
+      });
+    });
+    await new Promise<void>((resolve) => server.listen(0, "127.0.0.1", resolve));
+    const address = server.address() as AddressInfo;
+    const outDir = makeE2eOutputDir("speech-recognize-flash-sync");
+    const outPath = join(outDir, "result.json");
+
+    try {
+      const { stdout, stderr, exitCode } = await runCommandE2e(SPEECH_ROUTES, [
+        "speech",
+        "recognize",
+        "--model",
+        "fun-asr-flash-2026-06-15",
+        "--url",
+        "https://example.com/sample.wav",
+        "--api-key",
+        "sk-e2e-placeholder",
+        "--base-url",
+        `http://127.0.0.1:${address.port}`,
+        "--out",
+        outPath,
+        "--quiet",
+      ]);
+
+      expect(exitCode, stderr).toBe(0);
+      expect(stdout).toContain("flash recognition works");
+      expect(requestPath).toBe("/api/v1/services/aigc/multimodal-generation/generation");
+      expect(sseHeader).toBe("disable");
+      expect(requestBody).toMatchObject({
+        model: "fun-asr-flash-2026-06-15",
+        parameters: { format: "wav" },
+      });
+      expect(JSON.parse(readFileSync(outPath, "utf8"))).toMatchObject({
+        output: { text: "flash recognition works" },
+        request_id: "request-146",
+      });
+    } finally {
+      await new Promise<void>((resolve) => server.close(() => resolve()));
+    }
+  });
+
+  test("speech recognize flash 多 --url 在发请求前报用法错误", async () => {
+    const { stderr, exitCode } = await runCommandE2e(SPEECH_ROUTES, [
+      "speech",
+      "recognize",
+      "--model",
+      "qwen-audio-3.0-asr-flash",
+      "--url",
+      "https://example.com/a.wav",
+      "--url",
+      "https://example.com/b.wav",
+      "--dry-run",
+      "--quiet",
+    ]);
+
+    expect(exitCode).toBe(2);
+    expect(stderr).toMatch(/exactly one --url|sync Flash/i);
+  });
+
+  test("speech recognize qwen3-filetrans 轮询成功后下载 result.transcription_url", async () => {
+    const server = http.createServer((request, response) => {
+      const url = request.url ?? "";
+      const chunks: Buffer[] = [];
+      request.on("data", (chunk: Buffer) => chunks.push(chunk));
+      request.on("end", () => {
+        response.writeHead(200, { "Content-Type": "application/json" });
+        if (url.startsWith("/api/v1/services/audio/asr/transcription")) {
+          response.end(
+            JSON.stringify({
+              output: { task_id: "task-qwen3", task_status: "PENDING" },
+              request_id: "req-submit",
+            }),
+          );
+          return;
+        }
+        if (url.startsWith("/api/v1/tasks/")) {
+          const address = server.address() as AddressInfo;
+          response.end(
+            JSON.stringify({
+              output: {
+                task_id: "task-qwen3",
+                task_status: "SUCCEEDED",
+                result: {
+                  transcription_url: `http://127.0.0.1:${address.port}/transcription.json`,
+                },
+              },
+              request_id: "req-poll",
+            }),
+          );
+          return;
+        }
+        if (url.startsWith("/transcription.json")) {
+          response.end(
+            JSON.stringify({
+              file_url: "https://example.com/a.wav",
+              transcripts: [{ text: "你好世界", sentences: [{ text: "你好世界" }] }],
+            }),
+          );
+          return;
+        }
+        response.writeHead(404);
+        response.end(JSON.stringify({ message: `unexpected path: ${url}` }));
+      });
+    });
+    await new Promise<void>((resolve) => server.listen(0, "127.0.0.1", resolve));
+    const address = server.address() as AddressInfo;
+    const outDir = makeE2eOutputDir("speech-recognize-qwen3-filetrans");
+    const outPath = join(outDir, "result.json");
+
+    try {
+      const { stdout, stderr, exitCode } = await runCommandE2e(SPEECH_ROUTES, [
+        "speech",
+        "recognize",
+        "--model",
+        "qwen3-asr-flash-filetrans",
+        "--url",
+        "https://example.com/a.wav",
+        "--language",
+        "zh",
+        "--api-key",
+        "sk-e2e-placeholder",
+        "--base-url",
+        `http://127.0.0.1:${address.port}`,
+        "--poll-interval",
+        "1",
+        "--out",
+        outPath,
+        "--quiet",
+      ]);
+
+      expect(exitCode, stderr).toBe(0);
+      expect(stdout).toContain("你好世界");
+      expect(JSON.parse(readFileSync(outPath, "utf8"))).toMatchObject({
+        transcripts: [{ text: "你好世界" }],
+      });
+    } finally {
+      await new Promise<void>((resolve) => server.close(() => resolve()));
+    }
+  });
 });
 
 describe.skipIf(!isBailianE2EMediaEnabled() || !isDashScopeE2EReady())(

packages/commands/tests/e2e/topic-routes.ts

@@ -33,10 +33,6 @@ export const MEMORY_ROUTES: E2eRouteExports = {
   "memory delete": "memoryDelete",
   "memory profile create": "memoryProfileCreate",
   "memory profile get": "memoryProfileGet",
-  "memory profile list": "memoryProfileList",
-  "memory profile detail": "memoryProfileDetail",
-  "memory profile update": "memoryProfileUpdate",
-  "memory profile delete": "memoryProfileDelete",
 };
 
 export const KNOWLEDGE_ROUTES: E2eRouteExports = {
@@ -113,6 +109,8 @@ export const USAGE_ROUTES: E2eRouteExports = {
   "usage free": "usageFree",
   "usage freetier": "usageFreetier",
   "usage stats": "usageStats",
+  "usage token-plan": "usageTokenPlan",
+  "usage coding-plan": "usageCodingPlan",
 };
 
 export const DEPLOY_ROUTES: E2eRouteExports = {
@@ -162,8 +160,6 @@ export const TOKEN_PLAN_ROUTES: E2eRouteExports = {
   "token-plan create-key": "tokenPlanCreateKey",
   "token-plan assign-seats": "tokenPlanAssignSeats",
   "token-plan add-member": "tokenPlanAddMember",
-  "token-plan personal-usage": "tokenPlanPersonalUsage",
-  "token-plan personal-key": "tokenPlanPersonalKey",
 };
 
 export const SKILL_ROUTES: E2eRouteExports = {
@@ -179,7 +175,6 @@ export const MANAGED_AGENT_ROUTES: E2eRouteExports = {
   "managed-agent validate": "managedAgentValidate",
   "managed-agent plan": "managedAgentPlan",
   "managed-agent apply": "managedAgentApply",
-  "managed-agent run": "managedAgentRun",
   "managed-agent destroy": "managedAgentDestroy",
   "managed-agent state list": "managedAgentStateList",
   "managed-agent state rm": "managedAgentStateRm",

packages/commands/tests/e2e/usage-coding-plan.e2e.test.ts

@@ -0,0 +1,80 @@
+import { describe, expect, test } from "vite-plus/test";
+import {
+  isConsoleAuthFailure,
+  isConsoleE2EReady,
+  parseStdoutJson,
+  runCommandE2e,
+} from "./helpers.ts";
+import { USAGE_ROUTES } from "./topic-routes.ts";
+
+describe("e2e: usage coding-plan", () => {
+  test("usage coding-plan --help 正常退出", async () => {
+    const { stderr, exitCode } = await runCommandE2e(USAGE_ROUTES, [
+      "usage",
+      "coding-plan",
+      "--help",
+    ]);
+    expect(exitCode, stderr).toBe(0);
+    expect(stderr).toMatch(/Coding Plan|quota/i);
+  });
+
+  test("usage coding-plan --help 包含 --output json 示例", async () => {
+    const { stderr, exitCode } = await runCommandE2e(USAGE_ROUTES, [
+      "usage",
+      "coding-plan",
+      "--help",
+    ]);
+    expect(exitCode, stderr).toBe(0);
+    expect(stderr).toContain("bl usage coding-plan --output json");
+  });
+});
+
+describe.skipIf(!isConsoleE2EReady())("e2e: usage coding-plan（Console）", () => {
+  test("usage coding-plan --dry-run 输出网关请求计划", async () => {
+    const { stdout, stderr, exitCode } = await runCommandE2e(USAGE_ROUTES, [
+      "usage",
+      "coding-plan",
+      "--dry-run",
+      "--output",
+      "json",
+    ]);
+    expect(exitCode, stderr).toBe(0);
+    const data = parseStdoutJson<{
+      api?: string;
+      data?: { queryCodingPlanInstanceInfoRequest?: Record<string, unknown> };
+    }>(stdout);
+    expect(data.api).toBe("zeldaEasy.broadscope-bailian.codingPlan.queryCodingPlanInstanceInfoV2");
+    expect(data.data?.queryCodingPlanInstanceInfoRequest).toEqual({
+      commodityCode: "sfm_codingplan_public_cn",
+      onlyLatestOne: true,
+    });
+  });
+
+  test("usage coding-plan --output json 返回窗口结构", async () => {
+    const result = await runCommandE2e(USAGE_ROUTES, ["usage", "coding-plan", "--output", "json"]);
+    if (isConsoleAuthFailure(result)) return;
+    expect(result.exitCode, result.stderr).toBe(0);
+    const data = parseStdoutJson<{
+      per5Hour?: { percentage?: number };
+      perWeek?: { percentage?: number };
+      perBillMonth?: { percentage?: number };
+    }>(result.stdout);
+    // 无有效订阅返回 {}；有订阅时三个窗口必须存在
+    if (Object.keys(data).length > 0) {
+      expect(data.per5Hour).toBeTypeOf("object");
+      expect(data.perWeek).toBeTypeOf("object");
+      expect(data.perBillMonth).toBeTypeOf("object");
+    }
+  });
+
+  test("usage coding-plan 默认渲染生成时间与额度窗口或无订阅提示", async () => {
+    const result = await runCommandE2e(USAGE_ROUTES, ["usage", "coding-plan"]);
+    if (isConsoleAuthFailure(result)) return;
+    expect(result.exitCode, result.stderr).toBe(0);
+    if (result.stdout.includes("No active Coding Plan subscription found.")) return;
+    expect(result.stdout).toContain("Generated at:");
+    expect(result.stdout).toContain("5-hour quota");
+    expect(result.stdout).toContain("1-week quota");
+    expect(result.stdout).toContain("Monthly quota");
+  });
+});

packages/commands/tests/e2e/usage-token-plan.e2e.test.ts

@@ -0,0 +1,76 @@
+import { describe, expect, test } from "vite-plus/test";
+import {
+  isConsoleAuthFailure,
+  isConsoleE2EReady,
+  parseStdoutJson,
+  runCommandE2e,
+} from "./helpers.ts";
+import { USAGE_ROUTES } from "./topic-routes.ts";
+
+describe("e2e: usage token-plan", () => {
+  test("usage token-plan --help 正常退出", async () => {
+    const { stderr, exitCode } = await runCommandE2e(USAGE_ROUTES, [
+      "usage",
+      "token-plan",
+      "--help",
+    ]);
+    expect(exitCode, stderr).toBe(0);
+    expect(stderr).toMatch(/Token Plan|quota/i);
+  });
+
+  test("usage token-plan --help 包含 --output json 示例", async () => {
+    const { stderr, exitCode } = await runCommandE2e(USAGE_ROUTES, [
+      "usage",
+      "token-plan",
+      "--help",
+    ]);
+    expect(exitCode, stderr).toBe(0);
+    expect(stderr).toContain("bl usage token-plan --output json");
+  });
+});
+
+describe.skipIf(!isConsoleE2EReady())("e2e: usage token-plan（Console）", () => {
+  test("usage token-plan --dry-run 输出网关请求计划", async () => {
+    const { stdout, stderr, exitCode } = await runCommandE2e(USAGE_ROUTES, [
+      "usage",
+      "token-plan",
+      "--dry-run",
+      "--output",
+      "json",
+    ]);
+    expect(exitCode, stderr).toBe(0);
+    const data = parseStdoutJson<{ api?: string; data?: Record<string, unknown> }>(stdout);
+    expect(data.api).toBe("zeldaHttp.apikeyMgr./tokenplan/personal/api/v2/usage");
+    expect(data.data).toEqual({});
+  });
+
+  test("usage token-plan --output json 返回可用的额度字段", async () => {
+    const result = await runCommandE2e(USAGE_ROUTES, ["usage", "token-plan", "--output", "json"]);
+    if (isConsoleAuthFailure(result)) return;
+    expect(result.exitCode, result.stderr).toBe(0);
+    const data = parseStdoutJson<{
+      per5HourPercentage?: number;
+      per5HourResetTime?: number;
+      per1WeekPercentage?: number;
+      per1WeekResetTime?: number;
+    }>(result.stdout);
+    const fields = [
+      data.per5HourPercentage,
+      data.per5HourResetTime,
+      data.per1WeekPercentage,
+      data.per1WeekResetTime,
+    ];
+    for (const field of fields) {
+      if (field !== undefined) expect(field).toBeTypeOf("number");
+    }
+  });
+
+  test("usage token-plan 默认渲染生成时间与两个额度窗口", async () => {
+    const result = await runCommandE2e(USAGE_ROUTES, ["usage", "token-plan"]);
+    if (isConsoleAuthFailure(result)) return;
+    expect(result.exitCode, result.stderr).toBe(0);
+    expect(result.stdout).toContain("Generated at:");
+    expect(result.stdout).toContain("5-hour quota");
+    expect(result.stdout).toContain("1-week quota");
+  });
+});

packages/commands/tests/mcp-activate-hint.test.ts

@@ -26,6 +26,12 @@ describe("mcp-activate-hint", () => {
       false,
     );
     expect(isMcpNotActivated(new Error("MCP不存在或未开通"))).toBe(false);
+    // Nested wrapper phrase must not match (anchored at start).
+    expect(
+      isMcpNotActivated(
+        new BailianError("MCP error (-32000): MCP request failed: 404 Not Found - 未开通"),
+      ),
+    ).toBe(false);
   });
 
   test("hint 含对应 server 的 MCP 广场深链", () => {
@@ -38,6 +44,36 @@ describe("mcp-activate-hint", () => {
     expect(mcpActivateHint("WebSearch")).toMatch(/SSE|Streamable HTTP/i);
   });
 
+  test("WebSearch + 405 streamableHttp 补重开通 hint", () => {
+    const original = new BailianError(
+      "MCP request failed: 405 Method Not Allowed - current mcp not support streamableHttp",
+      ExitCode.GENERAL,
+    );
+    try {
+      rethrowWithMcpActivateHint(original, "WebSearch");
+      expect.unreachable("should throw");
+    } catch (error) {
+      expect(error).toBeInstanceOf(BailianError);
+      const wrapped = error as BailianError;
+      expect(wrapped.message).toBe(original.message);
+      expect(wrapped.hint).toMatch(/SSE|Streamable HTTP|Activate|re-activate/i);
+      expect(wrapped.hint).toContain(mcpMarketplaceDetailPage("WebSearch"));
+    }
+  });
+
+  test("非 WebSearch 的 405 streamableHttp 不补 hint（由 fallback 处理）", () => {
+    const original = new BailianError(
+      "MCP request failed: 405 Method Not Allowed - current mcp not support streamableHttp",
+      ExitCode.GENERAL,
+    );
+    try {
+      rethrowWithMcpActivateHint(original, "WebParser");
+      expect.unreachable("should throw");
+    } catch (error) {
+      expect(error).toBe(original);
+    }
+  });
+
   test("rethrow 保留原 message，补 hint", () => {
     const serverCode = "market-cmapi00073529";
     const original = new BailianError(

packages/commands/tests/token-plan-usage.test.ts

@@ -0,0 +1,195 @@
+import { afterEach, describe, expect, test, vi } from "vite-plus/test";
+import tokenPlanUsage from "../src/commands/usage/token-plan.ts";
+
+const originalNoColor = process.env.NO_COLOR;
+const originalForceColor = process.env.FORCE_COLOR;
+const originalIsTty = Object.getOwnPropertyDescriptor(process.stdout, "isTTY");
+
+afterEach(() => {
+  if (originalNoColor === undefined) delete process.env.NO_COLOR;
+  else process.env.NO_COLOR = originalNoColor;
+  if (originalForceColor === undefined) delete process.env.FORCE_COLOR;
+  else process.env.FORCE_COLOR = originalForceColor;
+  if (originalIsTty) Object.defineProperty(process.stdout, "isTTY", originalIsTty);
+  else delete (process.stdout as { isTTY?: boolean }).isTTY;
+  vi.restoreAllMocks();
+});
+
+function captureStdout(): string[] {
+  const output: string[] = [];
+  vi.spyOn(process.stdout, "write").mockImplementation((chunk) => {
+    output.push(String(chunk));
+    return true;
+  });
+  return output;
+}
+
+async function runTokenPlan(response: Record<string, unknown>, output?: string): Promise<void> {
+  await tokenPlanUsage.run({
+    client: { console: vi.fn().mockResolvedValue(response) },
+    flags: {},
+    settings: { dryRun: false, output },
+  } as never);
+}
+
+function makeUsageResponse(
+  per5HourPercentage?: number,
+  per1WeekPercentage = per5HourPercentage,
+): Record<string, unknown> {
+  const usage: Record<string, number> = {};
+  if (per5HourPercentage !== undefined) {
+    usage.per5HourPercentage = per5HourPercentage;
+    if (per5HourPercentage !== 0) usage.per5HourResetTime = 1_786_000_000_000;
+  }
+  if (per1WeekPercentage !== undefined) {
+    usage.per1WeekPercentage = per1WeekPercentage;
+    if (per1WeekPercentage !== 0) usage.per1WeekResetTime = 1_786_100_000_000;
+  }
+
+  return wrapResponse(usage);
+}
+
+function wrapResponse(usage: Record<string, unknown>): Record<string, unknown> {
+  return {
+    data: {
+      DataV2: {
+        data: {
+          data: usage,
+        },
+      },
+    },
+  };
+}
+
+describe("usage token-plan view", () => {
+  test("renders the gauge with the usage-free brand fill color", async () => {
+    delete process.env.NO_COLOR;
+    process.env.FORCE_COLOR = "3";
+    Object.defineProperty(process.stdout, "isTTY", { configurable: true, value: true });
+    const output = captureStdout();
+
+    await runTokenPlan(makeUsageResponse(0.5));
+
+    // Brand-cyan fill cell, same as the `usage free` gauge column
+    expect(output.join("")).toContain("\u001B[38;2;0;150;160m\u2588");
+  });
+
+  test("renders proportional gauge cells with a transparent track", async () => {
+    process.env.NO_COLOR = "1";
+    const output = captureStdout();
+
+    await runTokenPlan(makeUsageResponse(0.5));
+
+    const renderedOutput = output.join("");
+    // 50% of the default 20-cell gauge → 10 filled cells + 10 track spaces
+    expect(renderedOutput).toContain(`${"\u2588".repeat(10)}${" ".repeat(10)}`);
+    expect(renderedOutput).not.toContain("\u2588".repeat(11));
+  });
+
+  test("accepts missing reset times when the quota usage is zero", async () => {
+    const output = captureStdout();
+
+    await runTokenPlan(makeUsageResponse(0));
+
+    expect(output.join("")).toContain("Resets: not applicable (no usage yet)");
+  });
+
+  test("allows one unused quota window without masking another reset time", async () => {
+    const output = captureStdout();
+
+    await runTokenPlan(makeUsageResponse(0, 0.5));
+
+    const renderedOutput = output.join("");
+    expect(renderedOutput).toContain("Resets: not applicable (no usage yet)");
+    expect(renderedOutput).toMatch(/Resets: \d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}/);
+  });
+
+  test("renders missing quota windows as possibly unlimited", async () => {
+    const output = captureStdout();
+
+    await runTokenPlan(makeUsageResponse());
+
+    const renderedOutput = output.join("");
+    expect(renderedOutput).toContain(
+      "The 5-hour limit may be unlimited; verify in the Bailian Token Plan console.",
+    );
+    expect(renderedOutput).toContain(
+      "The 1-week limit may be unlimited; verify in the Bailian Token Plan console.",
+    );
+  });
+
+  test("renders only the missing quota window as possibly unlimited", async () => {
+    const output = captureStdout();
+
+    await runTokenPlan(makeUsageResponse(undefined, 0.5));
+
+    const renderedOutput = output.join("");
+    expect(renderedOutput).toContain(
+      "The 5-hour limit may be unlimited; verify in the Bailian Token Plan console.",
+    );
+    expect(renderedOutput).not.toContain(
+      "The 1-week limit may be unlimited; verify in the Bailian Token Plan console.",
+    );
+    expect(renderedOutput).toMatch(/Resets: \d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}/);
+  });
+
+  test("renders a window with a missing percentage as possibly unlimited even when its reset time is present", async () => {
+    const output = captureStdout();
+
+    await runTokenPlan(wrapResponse({ per5HourResetTime: 1_786_000_000_000 }));
+
+    expect(output.join("")).toContain(
+      "The 5-hour limit may be unlimited; verify in the Bailian Token Plan console.",
+    );
+  });
+
+  test("treats non-numeric quota fields as absent instead of failing", async () => {
+    const output = captureStdout();
+
+    await runTokenPlan(
+      wrapResponse({ per5HourPercentage: "not-a-number", per1WeekPercentage: Number.NaN }),
+    );
+
+    const renderedOutput = output.join("");
+    expect(renderedOutput).toContain(
+      "The 5-hour limit may be unlimited; verify in the Bailian Token Plan console.",
+    );
+    expect(renderedOutput).toContain(
+      "The 1-week limit may be unlimited; verify in the Bailian Token Plan console.",
+    );
+  });
+});
+
+describe("usage token-plan json", () => {
+  test("outputs the four core usage fields with --output json", async () => {
+    const output = captureStdout();
+
+    await runTokenPlan(makeUsageResponse(0.5, 0.25), "json");
+
+    expect(JSON.parse(output.join(""))).toEqual({
+      per5HourPercentage: 0.5,
+      per5HourResetTime: 1_786_000_000_000,
+      per1WeekPercentage: 0.25,
+      per1WeekResetTime: 1_786_100_000_000,
+    });
+  });
+
+  test("returns an empty JSON object when no quota fields are available", async () => {
+    const output = captureStdout();
+
+    await runTokenPlan(makeUsageResponse(), "json");
+
+    expect(output.join("").trim()).toBe("{}");
+  });
+
+  test("omits non-numeric quota fields from the JSON output", async () => {
+    const output = captureStdout();
+
+    await runTokenPlan(
+      wrapResponse({ per5HourPercentage: "not-a-number", per1WeekPercentage: 0 }),
+      "json",
+    );
+
+    expect(JSON.parse(output.join(""))).toEqual({ per1WeekPercentage: 0 });
+  });
+});

packages/core/package.json

@@ -1,6 +1,6 @@
 {
   "name": "bailian-cli-core",
-  "version": "1.14.2",
+  "version": "1.14.3",
   "description": "Core SDK for bailian-cli. See https://www.npmjs.com/package/bailian-cli for usage.",
   "homepage": "https://bailian.console.aliyun.com/cli",
   "bugs": {

packages/core/src/client/asr-routes.ts

@@ -0,0 +1,327 @@
+import { imageSyncPath, speechRecognizePath } from "./endpoints.ts";
+
+/**
+ * DashScope ASR APIs differ by model family:
+ *
+ * - async file transcription (`.../audio/asr/transcription`):
+ *   fun-asr*, paraformer* (non-realtime), *-filetrans, sensevoice*
+ *   language via `parameters.language_hints`
+ * - sync multimodal (`.../aigc/multimodal-generation/generation`):
+ *   - qwen3: `{ content: [{ audio }] }` + optional `asr_options.language`
+ *     (qwen3-asr-flash*)
+ *   - input-audio: `{ type: input_audio, input_audio.data }` +
+ *     `format`/`sample_rate` + optional `language_hints`
+ *     (fun-asr-flash*, qwen-audio-*-asr-flash*)
+ * - realtime / streaming: WebSocket — not supported by `speech recognize`
+ */
+
+export type AsrApiKind = "async-filetrans" | "sync-flash" | "unsupported";
+
+/** Sync-flash request body shape differs by Flash protocol family. */
+export type AsrFlashFamily = "qwen3" | "input-audio";
+
+export interface AsrApiRoute {
+  kind: AsrApiKind;
+  path: string;
+  /** True when the call is synchronous (no X-DashScope-Async / task poll). */
+  useSync: boolean;
+  /**
+   * Async transcription request input style.
+   * - `file_urls`: classic async models (fun-asr / paraformer / qwen-audio filetrans...)
+   * - `file_url`: qwen3-asr-flash-filetrans family
+   */
+  asyncInputStyle?: "file_urls" | "file_url";
+  /**
+   * Async transcription language field style.
+   * - `language_hints`: fun-asr / paraformer / qwen-audio filetrans...
+   * - `language`: qwen3-asr-flash-filetrans*
+   */
+  asyncLanguageStyle?: "language_hints" | "language";
+  flashFamily?: AsrFlashFamily;
+  /** Human-readable reason when kind is unsupported. */
+  unsupportedReason?: string;
+}
+
+function isRealtimeOrStreaming(model: string): boolean {
+  return /realtime|streaming/i.test(model);
+}
+
+function isFiletransModel(model: string): boolean {
+  return /filetrans/i.test(model);
+}
+
+function isQwen3FiletransModel(model: string): boolean {
+  return /^qwen3-asr-flash-filetrans(?:-|$)/i.test(model);
+}
+
+const INPUT_AUDIO_FLASH_PREFIXES = ["fun-asr-flash", "qwen-audio"] as const;
+
+/**
+ * Fun-ASR-Flash / Qwen-Audio-*-ASR-Flash share the input_audio + format protocol.
+ * Examples: fun-asr-flash-2026-06-15, qwen-audio-3.0-asr-flash
+ */
+function isInputAudioFlashModel(model: string): boolean {
+  if (isRealtimeOrStreaming(model) || isFiletransModel(model)) return false;
+  if (model.startsWith(INPUT_AUDIO_FLASH_PREFIXES[0])) return true;
+  if (model.startsWith(INPUT_AUDIO_FLASH_PREFIXES[1]) && /asr-flash/i.test(model)) return true;
+  return false;
+}
+
+/**
+ * Qwen3-ASR-Flash sync models use content.audio + asr_options.
+ * Examples: qwen3-asr-flash, qwen3-asr-flash-2025-09-08, qwen3-asr-flash-us
+ */
+function isQwen3AsrFlashModel(model: string): boolean {
+  if (!/^qwen3-asr-flash(?:-|$)/i.test(model)) return false;
+  if (isFiletransModel(model) || isRealtimeOrStreaming(model)) return false;
+  if (isInputAudioFlashModel(model)) return false;
+  return true;
+}
+
+/**
+ * Resolve which DashScope ASR API a model should use for file recognition.
+ * Unknown models default to async-filetrans (preserves existing CLI behavior).
+ */
+export function resolveAsrApi(model: string): AsrApiRoute {
+  if (isRealtimeOrStreaming(model)) {
+    return {
+      kind: "unsupported",
+      path: "",
+      useSync: false,
+      unsupportedReason:
+        `Model "${model}" is a realtime/streaming ASR model and requires a WebSocket API. ` +
+        `Use an async filetrans model (e.g. fun-asr, qwen3-asr-flash-filetrans) or a sync flash model ` +
+        `(e.g. qwen3-asr-flash, qwen-audio-3.0-asr-flash) with this command.`,
+    };
+  }
+
+  if (isFiletransModel(model)) {
+    const isQwen3Filetrans = isQwen3FiletransModel(model);
+    return {
+      kind: "async-filetrans",
+      path: speechRecognizePath(),
+      useSync: false,
+      asyncInputStyle: isQwen3Filetrans ? "file_url" : "file_urls",
+      asyncLanguageStyle: isQwen3Filetrans ? "language" : "language_hints",
+    };
+  }
+
+  if (isInputAudioFlashModel(model)) {
+    return {
+      kind: "sync-flash",
+      path: imageSyncPath(),
+      useSync: true,
+      flashFamily: "input-audio",
+    };
+  }
+
+  if (isQwen3AsrFlashModel(model)) {
+    return {
+      kind: "sync-flash",
+      path: imageSyncPath(),
+      useSync: true,
+      flashFamily: "qwen3",
+    };
+  }
+
+  // fun-asr / paraformer / sensevoice / unknown → keep legacy async path
+  return {
+    kind: "async-filetrans",
+    path: speechRecognizePath(),
+    useSync: false,
+    asyncInputStyle: "file_urls",
+    asyncLanguageStyle: "language_hints",
+  };
+}
+
+/** Infer audio container hint for input-audio Flash `parameters.format`. */
+export function inferAudioFormatHint(audioUrl: string): string {
+  // data URI: data:audio/mpeg;base64,... → mp3; data:audio/x-wav;... → wav
+  const dataType = /^data:audio\/([^;,]+)/i.exec(audioUrl)?.[1]?.toLowerCase();
+  if (dataType) {
+    if (dataType === "mpeg") return "mp3";
+    if (dataType === "x-wav" || dataType === "wave") return "wav";
+    return dataType;
+  }
+
+  const pathPart = audioUrl.split(/[?#]/, 1)[0] ?? audioUrl;
+  const match = pathPart.match(/\.([a-zA-Z0-9]+)$/);
+  const extension = match?.[1]?.toLowerCase();
+  if (!extension) return "wav";
+  if (extension === "mpeg") return "mp3";
+  return extension;
+}
+
+export interface BuildAsrFlashRequestOpts {
+  model: string;
+  audioUrl: string;
+  language?: string;
+  /** Precompiled hotword vocabulary ID; supported for input-audio Flash (fun-asr-flash* / qwen-audio-*-asr-flash). */
+  vocabularyId?: string;
+  flashFamily: AsrFlashFamily;
+}
+
+/**
+ * Build language fields for async ASR routes.
+ * qwen3-asr-flash-filetrans* → `language`; other async models → `language_hints`.
+ */
+export function buildAsyncAsrLanguageFields(
+  languageStyle: "language_hints" | "language",
+  language?: string,
+): { language_hints?: string[]; language?: string } {
+  if (!language) return {};
+  if (languageStyle === "language") {
+    return { language };
+  }
+  return { language_hints: [language] };
+}
+
+/** Build a sync multimodal ASR request body for Flash models. */
+export function buildAsrFlashRequest(opts: BuildAsrFlashRequestOpts): Record<string, unknown> {
+  const { model, audioUrl, language, vocabularyId, flashFamily } = opts;
+
+  if (flashFamily === "input-audio") {
+    // Match official Qwen-Audio / Fun-ASR-Flash docs: language_hints + vocabulary_id
+    const parameters: Record<string, unknown> = {
+      format: inferAudioFormatHint(audioUrl),
+      sample_rate: "16000",
+    };
+    if (language) {
+      parameters.language_hints = [language];
+    }
+    if (vocabularyId) {
+      parameters.vocabulary_id = vocabularyId;
+    }
+    return {
+      model,
+      input: {
+        messages: [
+          {
+            role: "user",
+            content: [
+              {
+                type: "input_audio",
+                input_audio: { data: audioUrl },
+              },
+            ],
+          },
+        ],
+      },
+      parameters,
+    };
+  }
+
+  const asrOptions: Record<string, unknown> = {};
+  if (language) {
+    asrOptions.language = language;
+  }
+
+  const parameters: Record<string, unknown> = {};
+  if (Object.keys(asrOptions).length > 0) {
+    parameters.asr_options = asrOptions;
+  }
+
+  const body: Record<string, unknown> = {
+    model,
+    input: {
+      messages: [
+        {
+          role: "user",
+          content: [{ audio: audioUrl }],
+        },
+      ],
+    },
+  };
+  if (Object.keys(parameters).length > 0) {
+    body.parameters = parameters;
+  }
+  return body;
+}
+
+/**
+ * Extract recognition text from a sync Flash ASR response.
+ * Qwen3 uses choices[].message.content; input-audio Flash uses output.text /
+ * output.sentence.text / output.output.sentence.text.
+ */
+export function extractAsrFlashText(
+  response: Record<string, unknown>,
+  flashFamily: AsrFlashFamily,
+): string {
+  const output = response.output as Record<string, unknown> | undefined;
+  if (!output) return "";
+
+  if (flashFamily === "input-audio") {
+    if (typeof output.text === "string" && output.text.length > 0) {
+      return output.text;
+    }
+    const topSentence = output.sentence as Record<string, unknown> | undefined;
+    if (typeof topSentence?.text === "string" && topSentence.text.length > 0) {
+      return topSentence.text;
+    }
+    const nested = output.output as Record<string, unknown> | undefined;
+    const nestedSentence = nested?.sentence as Record<string, unknown> | undefined;
+    if (typeof nestedSentence?.text === "string") {
+      return nestedSentence.text;
+    }
+    return "";
+  }
+
+  const choices = output.choices as Array<Record<string, unknown>> | undefined;
+  if (!choices?.length) return "";
+
+  const texts: string[] = [];
+  for (const choice of choices) {
+    const message = choice.message as Record<string, unknown> | undefined;
+    if (!message) continue;
+    const content = message.content;
+    if (typeof content === "string") {
+      texts.push(content);
+      continue;
+    }
+    if (!Array.isArray(content)) continue;
+    for (const item of content) {
+      if (typeof item === "string") {
+        texts.push(item);
+        continue;
+      }
+      if (item && typeof item === "object") {
+        const record = item as Record<string, unknown>;
+        if (typeof record.text === "string") {
+          texts.push(record.text);
+        }
+      }
+    }
+  }
+  return texts.join("");
+}
+
+/**
+ * Normalize async ASR task transcription items:
+ * - classic models: `output.results[]`
+ * - qwen3-asr-flash-filetrans*: `output.result.transcription_url`
+ */
+export function collectAsrTranscriptionItems(output: {
+  results?: Array<{
+    file_url?: string;
+    transcription_url?: string;
+    subtask_status?: string;
+    code?: string;
+    message?: string;
+  }>;
+  result?: { transcription_url?: string };
+}): Array<{
+  file_url?: string;
+  transcription_url?: string;
+  subtask_status?: string;
+  code?: string;
+  message?: string;
+}> {
+  if (output.results && output.results.length > 0) {
+    return output.results;
+  }
+  const transcriptionUrl = output.result?.transcription_url;
+  if (typeof transcriptionUrl === "string" && transcriptionUrl.length > 0) {
+    return [{ transcription_url: transcriptionUrl, subtask_status: "SUCCEEDED" }];
+  }
+  return [];
+}

packages/core/src/client/client.ts

@@ -5,7 +5,13 @@ import { ExitCode } from "../errors/codes.ts";
 import { request, requestJson, type HttpDeps, type RequestOpts } from "./http.ts";
 import { buildAcsCanonicalQuery, signAcsRequest, type AcsQueryParams } from "./acs.ts";
 import { imageFileToDataUri, isLocalFile, resolveFileUrl } from "../files/upload.ts";
-import { McpClient } from "./mcp.ts";
+import {
+  bailianMcpPath,
+  bailianMcpSsePath,
+  connectBailianMcpWithFallback,
+  McpClient,
+  type McpConnectedClient,
+} from "./mcp.ts";
 import { callConsoleGateway } from "../console/gateway.ts";
 import { refreshAccessToken } from "../auth/refresh-token.ts";
 import { maskToken } from "../utils/token.ts";
@@ -164,6 +170,25 @@ export class Client {
     return new McpClient(this.http, url, this.deps.apiCred?.token);
   }
 
+  /**
+   * Connect to a Bailian MCP: try Streamable HTTP, then SSE on 405 (except WebSearch).
+   * `urlOverride` maps to `--url`: Streamable first, then classic SSE on the same URL (405/404).
+   */
+  connectBailianMcp(
+    serverCode: string,
+    urlOverride?: string,
+  ): Promise<{ client: McpConnectedClient; url: string }> {
+    this.requireApi();
+    return connectBailianMcpWithFallback({
+      deps: this.http,
+      authToken: this.deps.apiCred?.token,
+      httpUrl: this.url(bailianMcpPath(serverCode)),
+      sseUrl: this.url(bailianMcpSsePath(serverCode)),
+      serverCode,
+      urlOverride,
+    });
+  }
+
   async console<T>(api: string, data: Record<string, unknown>): Promise<T> {
     if (!this.deps.consoleCred) {
       throw new BailianError("This command needs a console access token.", ExitCode.AUTH);

packages/core/src/client/endpoints.ts

@@ -75,11 +75,7 @@ export function profileSchemaPath(): string {
 }
 
 export function userProfilePath(schemaId: string): string {
-  return `/api/v2/apps/memory/profile_schemas/${encodeURIComponent(schemaId)}/user_profile`;
-}
-
-export function profileSchemaItemPath(schemaId: string): string {
-  return `/api/v2/apps/memory/profile_schemas/${encodeURIComponent(schemaId)}`;
+  return `/api/v2/apps/memory/profile_schemas/${encodeURIComponent(schemaId)}/profiles`;
 }
 
 // ---- Knowledge Base Retrieve (DashScope) ----

packages/core/src/client/index.ts

@@ -13,7 +13,6 @@ export {
   memoryNodePath,
   memorySearchPath,
   mcpWebSearchPath,
-  profileSchemaItemPath,
   profileSchemaPath,
   speechRecognizePath,
   speechSynthesizePath,
@@ -35,6 +34,18 @@ export {
   type ImageInputStyle,
   type ImageSizeProfile,
 } from "./image-routes.ts";
+export {
+  buildAsrFlashRequest,
+  buildAsyncAsrLanguageFields,
+  collectAsrTranscriptionItems,
+  extractAsrFlashText,
+  inferAudioFormatHint,
+  resolveAsrApi,
+  type AsrApiKind,
+  type AsrApiRoute,
+  type AsrFlashFamily,
+  type BuildAsrFlashRequestOpts,
+} from "./asr-routes.ts";
 export { CHANNEL, sourceConfig, trackingHeaders, type TrackingIdentity } from "./headers.ts";
 export type { HttpDeps, RequestOpts } from "./http.ts";
 export { request, requestJson } from "./http.ts";
@@ -58,7 +69,19 @@ export {
   type AcsQueryParams,
   type AcsSignConfig,
 } from "./acs.ts";
-export type { McpTool, McpToolResult } from "./mcp.ts";
-export { McpClient, bailianMcpPath } from "./mcp.ts";
+export type {
+  McpTool,
+  McpToolResult,
+  McpConnectedClient,
+  ConnectBailianMcpOptions,
+} from "./mcp.ts";
+export {
+  McpClient,
+  bailianMcpPath,
+  bailianMcpSsePath,
+  isStreamableHttpUnsupported,
+  isUrlOverrideSseFallbackCandidate,
+  connectBailianMcpWithFallback,
+} from "./mcp.ts";
 export type { ServerSentEvent } from "./stream.ts";
 export { parseSSE } from "./stream.ts";

packages/core/src/client/mcp-sse.ts

@@ -0,0 +1,474 @@
+/**
+ * MCP classic HTTP+SSE client (protocol 2024-11-05 transport).
+ *
+ * Flow: GET /sse → endpoint event → POST JSON-RPC to message URL;
+ * responses arrive as SSE `message` events matched by JSON-RPC id.
+ */
+
+import { BailianError } from "../errors/base.ts";
+import { ExitCode } from "../errors/codes.ts";
+import type { HttpDeps } from "./http.ts";
+import { trackingHeaders } from "./headers.ts";
+import type { McpTool, McpToolResult } from "./mcp.ts";
+import { parseSSE } from "./stream.ts";
+
+interface JsonRpcResponse {
+  jsonrpc: "2.0";
+  id?: number | string | null;
+  result?: unknown;
+  error?: { code: number; message: string; data?: unknown };
+}
+
+type PendingResolver = {
+  resolve: (value: JsonRpcResponse) => void;
+  reject: (reason: unknown) => void;
+};
+
+/** Match JSON-RPC ids with string keys (number or string echo from server). */
+function pendingKey(id: number | string): string {
+  return String(id);
+}
+
+export class McpSseClient {
+  private sseUrl: string;
+  private messageUrl: string | undefined;
+  private nextId = 1;
+  private deps: HttpDeps;
+  private authToken: string | undefined;
+  private abortController: AbortController | undefined;
+  private pending = new Map<string, PendingResolver>();
+  private endpointReady: Promise<void>;
+  private resolveEndpoint: (() => void) | undefined;
+  private rejectEndpoint: ((reason: unknown) => void) | undefined;
+  private closed = false;
+  /** Set when the SSE GET ends without an intentional close(); later RPCs fail fast. */
+  private streamEnded = false;
+
+  constructor(deps: HttpDeps, sseUrl: string, authToken?: string) {
+    this.deps = deps;
+    this.sseUrl = sseUrl;
+    this.authToken = authToken;
+    this.endpointReady = new Promise<void>((resolve, reject) => {
+      this.resolveEndpoint = resolve;
+      this.rejectEndpoint = reject;
+    });
+  }
+
+  /** Open the SSE session and run initialize / notifications/initialized. */
+  async initialize(): Promise<void> {
+    if (!this.authToken) {
+      throw new BailianError("This command needs a model-domain API key.", ExitCode.AUTH);
+    }
+
+    await this.openSse();
+
+    const result = await this.rpc("initialize", {
+      protocolVersion: "2025-03-26",
+      capabilities: {},
+      clientInfo: {
+        name: this.deps.identity.clientName,
+        version: this.deps.identity.version,
+      },
+    });
+
+    if (this.deps.settings.verbose) {
+      console.error(`[MCP SSE] Session initialized`);
+      console.error(`[MCP SSE] Server: ${JSON.stringify(result)}`);
+    }
+
+    await this.notify("notifications/initialized");
+  }
+
+  async listTools(): Promise<McpTool[]> {
+    const result = (await this.rpc("tools/list")) as { tools: McpTool[] };
+    return result.tools || [];
+  }
+
+  async callTool(name: string, args: Record<string, unknown>): Promise<McpToolResult> {
+    const result = (await this.rpc("tools/call", { name, arguments: args })) as McpToolResult;
+    return result;
+  }
+
+  /** Abort the hanging GET /sse so the CLI process can exit. */
+  close(): void {
+    if (this.closed) return;
+    this.closed = true;
+    this.abortController?.abort();
+    this.failPending(new BailianError("MCP SSE session closed.", ExitCode.GENERAL));
+    this.messageUrl = undefined;
+  }
+
+  private failPending(reason: unknown): void {
+    for (const [, waiter] of this.pending) {
+      waiter.reject(reason);
+    }
+    this.pending.clear();
+  }
+
+  private markStreamEnded(reason: BailianError): void {
+    this.streamEnded = true;
+    this.messageUrl = undefined;
+    this.failPending(reason);
+  }
+
+  private async openSse(): Promise<void> {
+    if (this.abortController) return;
+
+    // One abortController for header/error-body wait; clear timer before the long-lived stream.
+    this.abortController = new AbortController();
+    const timeoutMs = this.deps.settings.timeout * 1000;
+    let headerTimedOut = false;
+    const headerTimer = setTimeout(() => {
+      headerTimedOut = true;
+      this.abortController?.abort();
+    }, timeoutMs);
+
+    const headers: Record<string, string> = {
+      Accept: "text/event-stream",
+      "User-Agent": `${this.deps.identity.clientName}/${this.deps.identity.version}`,
+      ...trackingHeaders(this.deps.identity),
+    };
+    if (this.authToken) {
+      headers["Authorization"] = `Bearer ${this.authToken}`;
+    }
+
+    if (this.deps.settings.verbose) {
+      console.error(`> GET ${this.sseUrl}`);
+    }
+
+    let response: Response;
+    try {
+      response = await fetch(this.sseUrl, {
+        method: "GET",
+        headers,
+        signal: this.abortController.signal,
+      });
+    } catch (error) {
+      clearTimeout(headerTimer);
+      // Allow a later initialize() to openSse again on this instance.
+      this.abortController = undefined;
+      if (this.closed) {
+        throw new BailianError("MCP SSE session closed.", ExitCode.GENERAL);
+      }
+      if (headerTimedOut) {
+        throw new BailianError("MCP SSE timed out waiting for response headers.", ExitCode.TIMEOUT);
+      }
+      // Rethrow fetch failures so runtime can surface errno (e.g. ENOTFOUND) in JSON/text.
+      throw error;
+    }
+
+    if (this.deps.settings.verbose) {
+      console.error(`< ${response.status} ${response.statusText}`);
+    }
+
+    if (!response.ok) {
+      // Keep headerTimer until error body is read (or times out).
+      let errMsg = `MCP request failed: ${response.status} ${response.statusText}`;
+      try {
+        const errBody = await response.text();
+        if (errBody) errMsg += ` - ${errBody.slice(0, 500)}`;
+      } catch (error) {
+        clearTimeout(headerTimer);
+        this.abortController = undefined;
+        if (this.closed) {
+          throw new BailianError("MCP SSE session closed.", ExitCode.GENERAL);
+        }
+        if (headerTimedOut) {
+          throw new BailianError(
+            "MCP SSE timed out reading error response body.",
+            ExitCode.TIMEOUT,
+          );
+        }
+        throw new BailianError(errMsg, ExitCode.GENERAL, undefined, { cause: error });
+      }
+      clearTimeout(headerTimer);
+      this.abortController = undefined;
+      // Do not rejectEndpoint — openSse never awaits endpointReady on this path.
+      throw new BailianError(errMsg, ExitCode.GENERAL);
+    }
+
+    clearTimeout(headerTimer);
+
+    void this.consumeSse(response).catch((error) => {
+      if (this.closed) return;
+      const reason =
+        error instanceof BailianError
+          ? error
+          : new BailianError(
+              `MCP SSE stream failed: ${error instanceof Error ? error.message : String(error)}`,
+              ExitCode.GENERAL,
+            );
+      this.rejectEndpoint?.(reason);
+      // consumeSse already markStreamEnded on a clean end; cover parse/read failures here.
+      if (!this.streamEnded) {
+        this.markStreamEnded(reason);
+      }
+    });
+
+    const endpointTimeout = cancellableTimeoutReject(
+      timeoutMs,
+      "MCP SSE timed out waiting for endpoint event.",
+    );
+    try {
+      await Promise.race([this.endpointReady, endpointTimeout.promise]);
+    } finally {
+      endpointTimeout.cancel();
+    }
+  }
+
+  private async consumeSse(response: Response): Promise<void> {
+    for await (const event of parseSSE(response)) {
+      if (this.closed) break;
+
+      // Spec requires event: endpoint; ignore unnamed events so JSON is not treated as a URL.
+      if (event.event === "endpoint") {
+        const raw = event.data.trim();
+        if (!raw) continue;
+        // Only accept same-origin message URLs so we never forward the Bearer token cross-origin.
+        this.messageUrl = resolveSameOriginMessageUrl(this.sseUrl, raw);
+        this.resolveEndpoint?.();
+        this.resolveEndpoint = undefined;
+        this.rejectEndpoint = undefined;
+        continue;
+      }
+
+      // Omitted SSE event type defaults to "message".
+      if (event.event === "message" || event.event === undefined) {
+        let payload: JsonRpcResponse;
+        try {
+          payload = JSON.parse(event.data) as JsonRpcResponse;
+        } catch {
+          continue;
+        }
+        if (typeof payload.id !== "number" && typeof payload.id !== "string") continue;
+        const key = pendingKey(payload.id);
+        const waiter = this.pending.get(key);
+        if (!waiter) continue;
+        this.pending.delete(key);
+        waiter.resolve(payload);
+      }
+    }
+
+    if (this.closed) return;
+
+    if (!this.messageUrl) {
+      const error = new BailianError(
+        "MCP SSE stream ended before endpoint event.",
+        ExitCode.GENERAL,
+      );
+      this.rejectEndpoint?.(error);
+      throw error;
+    }
+
+    // After endpoint: mark dead and wake pending; don't throw (avoid unhandledRejection).
+    this.markStreamEnded(new BailianError("MCP SSE stream ended unexpectedly.", ExitCode.GENERAL));
+  }
+
+  private async rpc(method: string, params?: Record<string, unknown>): Promise<unknown> {
+    if (this.closed || this.streamEnded) {
+      throw new BailianError("MCP SSE stream ended unexpectedly.", ExitCode.GENERAL);
+    }
+
+    const id = this.nextId++;
+    const key = pendingKey(id);
+    const body = {
+      jsonrpc: "2.0" as const,
+      id,
+      method,
+      ...(params ? { params } : {}),
+    };
+
+    const timeoutMs = this.deps.settings.timeout * 1000;
+    const responsePromise = new Promise<JsonRpcResponse>((resolve, reject) => {
+      this.pending.set(key, { resolve, reject });
+    });
+    // Stream may end and reject pending before Promise.race; attach catch to avoid unhandledRejection.
+    void responsePromise.catch(() => undefined);
+    const responseTimeout = cancellableTimeoutReject(
+      timeoutMs,
+      `MCP SSE timed out waiting for response to ${method}.`,
+    );
+
+    try {
+      await this.postMessage(body);
+      if (this.closed || this.streamEnded) {
+        throw new BailianError("MCP SSE stream ended unexpectedly.", ExitCode.GENERAL);
+      }
+      const data = await Promise.race([responsePromise, responseTimeout.promise]);
+      if (data.error) {
+        throw new BailianError(
+          `MCP error (${data.error.code}): ${data.error.message}`,
+          ExitCode.GENERAL,
+        );
+      }
+      return data.result;
+    } catch (error) {
+      this.pending.delete(key);
+      throw error;
+    } finally {
+      responseTimeout.cancel();
+    }
+  }
+
+  private async notify(method: string, params?: Record<string, unknown>): Promise<void> {
+    const body = {
+      jsonrpc: "2.0" as const,
+      method,
+      ...(params ? { params } : {}),
+    };
+    await this.postMessage(body);
+  }
+
+  private async postMessage(body: unknown): Promise<void> {
+    if (this.closed || this.streamEnded) {
+      throw new BailianError("MCP SSE stream ended unexpectedly.", ExitCode.GENERAL);
+    }
+    if (!this.messageUrl) {
+      throw new BailianError("MCP SSE message endpoint is not ready.", ExitCode.GENERAL);
+    }
+
+    const headers: Record<string, string> = {
+      "Content-Type": "application/json",
+      Accept: "application/json, text/event-stream",
+      "User-Agent": `${this.deps.identity.clientName}/${this.deps.identity.version}`,
+      ...trackingHeaders(this.deps.identity),
+    };
+    // Bearer is only sent to a messageUrl that already passed the same-origin check.
+    if (this.authToken) {
+      headers["Authorization"] = `Bearer ${this.authToken}`;
+    }
+
+    if (this.deps.settings.verbose) {
+      console.error(`> POST ${this.messageUrl}`);
+      console.error(`> Method: ${(body as { method?: string }).method}`);
+    }
+
+    const timeoutMs = this.deps.settings.timeout * 1000;
+    // Combine per-RPC timeout with session abort so close() cancels in-flight POSTs.
+    const requestSignal = createLinkedAbortSignal(timeoutMs, this.abortController?.signal);
+    let res: Response;
+    try {
+      try {
+        res = await fetch(this.messageUrl, {
+          method: "POST",
+          headers,
+          body: JSON.stringify(body),
+          signal: requestSignal.signal,
+        });
+      } catch (error) {
+        if (this.closed) {
+          throw new BailianError("MCP SSE session closed.", ExitCode.GENERAL);
+        }
+        throw error;
+      }
+
+      if (this.deps.settings.verbose) {
+        console.error(`< ${res.status} ${res.statusText}`);
+      }
+
+      if (!res.ok) {
+        // Keep signal until error body is read (same class of bug as GET openSse).
+        let errMsg = `MCP request failed: ${res.status} ${res.statusText}`;
+        try {
+          const errBody = await res.text();
+          if (errBody) errMsg += ` - ${errBody.slice(0, 500)}`;
+        } catch (error) {
+          if (this.closed) {
+            throw new BailianError("MCP SSE session closed.", ExitCode.GENERAL);
+          }
+          if (requestSignal.timedOut) {
+            throw new BailianError(
+              "MCP SSE timed out reading error response body.",
+              ExitCode.TIMEOUT,
+            );
+          }
+          throw new BailianError(errMsg, ExitCode.GENERAL, undefined, { cause: error });
+        }
+        throw new BailianError(errMsg, ExitCode.GENERAL);
+      }
+    } finally {
+      requestSignal.cleanup();
+    }
+  }
+}
+
+/** Resolve the SSE endpoint data to an absolute URL and require same origin as sseUrl. */
+export function resolveSameOriginMessageUrl(sseUrl: string, endpointData: string): string {
+  let resolved: URL;
+  let base: URL;
+  try {
+    base = new URL(sseUrl);
+    resolved = new URL(endpointData, sseUrl);
+  } catch {
+    throw new BailianError(
+      `MCP SSE endpoint is not a valid URL: ${endpointData}`,
+      ExitCode.GENERAL,
+    );
+  }
+  if (resolved.origin !== base.origin) {
+    throw new BailianError(
+      `MCP SSE endpoint origin mismatch: expected ${base.origin}, got ${resolved.origin}`,
+      ExitCode.GENERAL,
+    );
+  }
+  return resolved.toString();
+}
+
+/**
+ * Cancellable timeout rejection: after Promise.race settles, call cancel()
+ * to clear the timer and avoid unhandledRejection.
+ */
+function cancellableTimeoutReject(
+  timeoutMs: number,
+  message: string,
+): { promise: Promise<never>; cancel: () => void } {
+  let timer: ReturnType<typeof setTimeout> | undefined;
+  const promise = new Promise<never>((_, reject) => {
+    timer = setTimeout(() => {
+      timer = undefined;
+      reject(new BailianError(message, ExitCode.TIMEOUT));
+    }, timeoutMs);
+  });
+  // Swallow late rejects after cancel to avoid unhandledRejection.
+  void promise.catch(() => undefined);
+
+  return {
+    promise,
+    cancel: () => {
+      if (timer !== undefined) {
+        clearTimeout(timer);
+        timer = undefined;
+      }
+    },
+  };
+}
+
+/** Timeout + optional parent abort without AbortSignal.any (Node 18). */
+function createLinkedAbortSignal(
+  timeoutMs: number,
+  parentSignal?: AbortSignal,
+): { signal: AbortSignal; cleanup: () => void; timedOut: boolean } {
+  const controller = new AbortController();
+  const state = { timedOut: false };
+  const timeout = setTimeout(() => {
+    state.timedOut = true;
+    controller.abort();
+  }, timeoutMs);
+  const abortFromParent = () => controller.abort(parentSignal?.reason);
+  const cleanup = () => {
+    clearTimeout(timeout);
+    parentSignal?.removeEventListener("abort", abortFromParent);
+  };
+
+  if (parentSignal?.aborted) abortFromParent();
+  else parentSignal?.addEventListener("abort", abortFromParent, { once: true });
+  controller.signal.addEventListener("abort", cleanup, { once: true });
+
+  return {
+    signal: controller.signal,
+    cleanup,
+    get timedOut() {
+      return state.timedOut;
+    },
+  };
+}

packages/core/src/client/mcp.ts

@@ -15,6 +15,8 @@ import { BailianError } from "../errors/base.ts";
 import { ExitCode } from "../errors/codes.ts";
 import type { HttpDeps } from "./http.ts";
 import { trackingHeaders } from "./headers.ts";
+import { McpSseClient } from "./mcp-sse.ts";
+import { parseSSE } from "./stream.ts";
 
 // ---- JSON-RPC 2.0 Types ----
 
@@ -27,7 +29,7 @@ interface JsonRpcRequest {
 
 interface JsonRpcResponse {
   jsonrpc: "2.0";
-  id: number;
+  id?: number | string | null;
   result?: unknown;
   error?: { code: number; message: string; data?: unknown };
 }
@@ -61,6 +63,101 @@ export function bailianMcpPath(serverCode: string): string {
   return `/api/v1/mcps/${serverCode}/mcp`;
 }
 
+/** Classic SSE path: `/api/v1/mcps/<serverCode>/sse`. */
+export function bailianMcpSsePath(serverCode: string): string {
+  return `/api/v1/mcps/${serverCode}/sse`;
+}
+
+/**
+ * True when Streamable HTTP is unsupported and classic SSE fallback should be tried.
+ * Anchored to HTTP wrapper text only (not JSON-RPC / nested copies). Bailian 404 excluded.
+ */
+export function isStreamableHttpUnsupported(error: unknown): boolean {
+  if (!(error instanceof BailianError)) return false;
+  return /^MCP request failed:\s*405\b/i.test(error.message);
+}
+
+/**
+ * SSE fallback for `--url` (official backwards-compat: same URL, HTTP 405/404 then GET SSE).
+ */
+export function isUrlOverrideSseFallbackCandidate(error: unknown): boolean {
+  if (!(error instanceof BailianError)) return false;
+  return /^MCP request failed:\s*(405|404)\b/i.test(error.message);
+}
+
+export type McpConnectedClient = {
+  initialize(): Promise<void>;
+  listTools(): Promise<McpTool[]>;
+  callTool(name: string, args: Record<string, unknown>): Promise<McpToolResult>;
+  close?(): void;
+};
+
+export type ConnectBailianMcpOptions = {
+  deps: HttpDeps;
+  authToken: string | undefined;
+  /** Full Streamable HTTP URL (/mcp). */
+  httpUrl: string;
+  /** Full classic SSE URL (/sse). */
+  sseUrl: string;
+  serverCode: string;
+  /**
+   * Explicit `--url` override: try Streamable on that URL first;
+   * on 405/404 fall back to classic SSE on the same URL.
+   */
+  urlOverride?: string;
+};
+
+/**
+ * Connect via Streamable HTTP first; on 405 (except WebSearch), fall back to SSE.
+ * `--url` uses the same URL for Streamable then classic SSE (official backwards-compat).
+ * For WebSearch, rethrow the original error so commands can attach a re-activate hint.
+ */
+export async function connectBailianMcpWithFallback(
+  options: ConnectBailianMcpOptions,
+): Promise<{ client: McpConnectedClient; url: string }> {
+  const { deps, authToken, httpUrl, sseUrl, serverCode, urlOverride } = options;
+
+  if (urlOverride) {
+    const httpClient = new McpClient(deps, urlOverride, authToken);
+    try {
+      await httpClient.initialize();
+      return { client: httpClient, url: urlOverride };
+    } catch (error) {
+      if (!isUrlOverrideSseFallbackCandidate(error)) {
+        throw error;
+      }
+    }
+
+    const sseClient = new McpSseClient(deps, urlOverride, authToken);
+    try {
+      await sseClient.initialize();
+      return { client: sseClient, url: urlOverride };
+    } catch (error) {
+      sseClient.close();
+      throw error;
+    }
+  }
+
+  const httpClient = new McpClient(deps, httpUrl, authToken);
+  try {
+    await httpClient.initialize();
+    return { client: httpClient, url: httpUrl };
+  } catch (error) {
+    if (!isStreamableHttpUnsupported(error) || serverCode === "WebSearch") {
+      throw error;
+    }
+  }
+
+  const sseClient = new McpSseClient(deps, sseUrl, authToken);
+  try {
+    await sseClient.initialize();
+    return { client: sseClient, url: sseUrl };
+  } catch (error) {
+    sseClient.close();
+    throw error;
+  }
+}
+
 // ---- MCP Client ----
 
 export class McpClient {
@@ -121,7 +218,7 @@ export class McpClient {
     };
 
     const response = await this.send(body);
-    const data = (await response.json()) as JsonRpcResponse;
+    const data = await this.readJsonRpcResponse(response, id);
 
     if (data.error) {
       throw new BailianError(
@@ -143,6 +240,44 @@ export class McpClient {
     await this.send(body);
   }
 
+  /**
+   * Read a JSON-RPC response by Content-Type: application/json or text/event-stream.
+   */
+  private async readJsonRpcResponse(
+    response: Response,
+    expectedId: number,
+  ): Promise<JsonRpcResponse> {
+    const contentType = response.headers.get("content-type") || "";
+    if (contentType.includes("text/event-stream")) {
+      return await this.readJsonRpcFromSse(response, expectedId);
+    }
+
+    return (await response.json()) as JsonRpcResponse;
+  }
+
+  private async readJsonRpcFromSse(
+    response: Response,
+    expectedId: number,
+  ): Promise<JsonRpcResponse> {
+    const expectedKey = String(expectedId);
+    for await (const event of parseSSE(response)) {
+      if (event.event && event.event !== "message") continue;
+      let payload: JsonRpcResponse;
+      try {
+        payload = JSON.parse(event.data) as JsonRpcResponse;
+      } catch {
+        continue;
+      }
+      if (payload.id == null) continue;
+      if (String(payload.id) !== expectedKey) continue;
+      return payload;
+    }
+    throw new BailianError(
+      "MCP SSE response stream ended without a matching JSON-RPC response.",
+      ExitCode.GENERAL,
+    );
+  }
+
   private async send(body: unknown): Promise<Response> {
     const headers: Record<string, string> = {
       "Content-Type": "application/json",

packages/core/src/client/stream.ts

@@ -7,6 +7,71 @@ export interface ServerSentEvent {
   id?: string;
 }
 
+/** Normalize CRLF/CR to LF; hold a trailing `\r` so a split CRLF is not double-broken. */
+function takeNormalizedSseLines(buffer: string): { lines: string[]; rest: string } {
+  let text = buffer;
+  let holdTrailingCr = false;
+  if (text.endsWith("\r")) {
+    holdTrailingCr = true;
+    text = text.slice(0, -1);
+  }
+
+  text = text.replace(/\r\n/g, "\n").replace(/\r/g, "\n");
+  const parts = text.split("\n");
+  const incomplete = parts.pop() ?? "";
+  return {
+    lines: parts,
+    rest: holdTrailingCr ? `${incomplete}\r` : incomplete,
+  };
+}
+
+function applySseLine(
+  line: string,
+  event: Partial<ServerSentEvent>,
+  maxBuffer: number,
+): { event: Partial<ServerSentEvent>; completed?: ServerSentEvent } {
+  if (line === "") {
+    if (event.data === undefined) {
+      return { event: {} };
+    }
+    return {
+      event: {},
+      completed: { data: event.data, event: event.event, id: event.id },
+    };
+  }
+
+  if (line.startsWith(":")) {
+    return { event };
+  }
+
+  const colonIndex = line.indexOf(":");
+  if (colonIndex === -1) {
+    return { event };
+  }
+
+  const field = line.slice(0, colonIndex);
+  const fieldValue = line.slice(colonIndex + 1).trimStart();
+  const nextEvent: Partial<ServerSentEvent> = { ...event };
+
+  switch (field) {
+    case "data":
+      nextEvent.data =
+        nextEvent.data !== undefined ? `${nextEvent.data}\n${fieldValue}` : fieldValue;
+      if (nextEvent.data.length > maxBuffer) {
+        throw new BailianError("SSE event exceeded the maximum buffer size.", ExitCode.GENERAL);
+      }
+      break;
+    case "event":
+      nextEvent.event = fieldValue;
+      break;
+    case "id":
+      nextEvent.id = fieldValue;
+      break;
+  }
+
+  return { event: nextEvent };
+}
+
 export async function* parseSSE(response: Response): AsyncGenerator<ServerSentEvent> {
   const reader = response.body?.getReader();
   if (!reader) return;
@@ -14,69 +79,55 @@ export async function* parseSSE(response: Response): AsyncGenerator<ServerSentEv
   const decoder = new TextDecoder();
   let buffer = "";
 
-  // Guard against a hostile or malfunctioning stream that never emits a newline
-  // (or builds a single absurdly large event): bound the in-memory buffer so the
-  // parser cannot be driven to exhaust process memory.
   const MAX_SSE_BUFFER = 16 * 1024 * 1024; // 16 MiB
 
   try {
+    // Keep partial event fields across chunks.
+    let event: Partial<ServerSentEvent> = {};
+
     while (true) {
       const { done, value } = await reader.read();
-      if (done) break;
+      if (done) {
+        // EOF: treat any held `\r` as a line ending.
+        if (buffer.length > 0) {
+          const finalText = buffer.replace(/\r\n/g, "\n").replace(/\r/g, "\n");
+          const parts = finalText.split("\n");
+          buffer = parts.pop() ?? "";
+          for (const line of parts) {
+            const applied = applySseLine(line, event, MAX_SSE_BUFFER);
+            event = applied.event;
+            if (applied.completed) {
+              yield applied.completed;
+            }
+          }
+        }
+        break;
+      }
 
       buffer += decoder.decode(value, { stream: true });
       if (buffer.length > MAX_SSE_BUFFER) {
         throw new BailianError("SSE stream exceeded the maximum buffer size.", ExitCode.GENERAL);
       }
 
-      const lines = buffer.split("\n");
-      buffer = lines.pop() || "";
-
-      let event: Partial<ServerSentEvent> = {};
+      const { lines, rest } = takeNormalizedSseLines(buffer);
+      buffer = rest;
 
       for (const line of lines) {
-        if (line === "") {
-          if (event.data !== undefined) {
-            yield { data: event.data, event: event.event, id: event.id };
-          }
-          event = {};
-          continue;
-        }
-
-        if (line.startsWith(":")) continue; // comment
-
-        const colonIndex = line.indexOf(":");
-        if (colonIndex === -1) continue;
-
-        const field = line.slice(0, colonIndex);
-        const value = line.slice(colonIndex + 1).trimStart();
-
-        switch (field) {
-          case "data":
-            event.data = event.data !== undefined ? `${event.data}\n${value}` : value;
-            if (event.data.length > MAX_SSE_BUFFER) {
-              throw new BailianError(
-                "SSE event exceeded the maximum buffer size.",
-                ExitCode.GENERAL,
-              );
-            }
-            break;
-          case "event":
-            event.event = value;
-            break;
-          case "id":
-            event.id = value;
-            break;
+        const applied = applySseLine(line, event, MAX_SSE_BUFFER);
+        event = applied.event;
+        if (applied.completed) {
+          yield applied.completed;
         }
       }
     }
 
-    // Flush remaining
-    if (buffer.trim() && buffer.includes("data:")) {
-      const colonIndex = buffer.indexOf(":");
-      if (colonIndex !== -1) {
-        yield { data: buffer.slice(colonIndex + 1).trimStart() };
-      }
+    // Legacy EOF flush: apply trailing field line and dispatch with event/id intact.
+    if (buffer.length > 0) {
+      const applied = applySseLine(buffer, event, MAX_SSE_BUFFER);
+      event = applied.event;
+    }
+    if (event.data !== undefined) {
+      yield { data: event.data, event: event.event, id: event.id };
     }
   } finally {
     reader.releaseLock();

packages/core/src/config/loader.ts

@@ -199,15 +199,7 @@ export function buildSources(flags: Partial<SourceFlags>): ResolutionSources {
   const raw = readRawConfigObject();
   const configExplicit = flags.config !== undefined;
   const activeConfigName = readStoredActiveConfigName(raw, !configExplicit);
-  // Config selection: --config flag > BAILIAN_CONFIG env > persisted active_config.
-  // The env lets a host (e.g. dsh) pin a named profile for all child `bl`
-  // calls without rewriting --config or the user's active_config.
-  const envConfig = process.env.BAILIAN_CONFIG;
-  const configName = configExplicit
-    ? normalizeConfigName(flags.config)
-    : envConfig
-      ? normalizeConfigName(envConfig)
-      : activeConfigName;
+  const configName = configExplicit ? normalizeConfigName(flags.config) : activeConfigName;
   return {
     flags,
     file: parseConfigFile(readRawConfigBlock(raw, configName)),

packages/core/src/console/gateway.ts

@@ -58,7 +58,7 @@ export function effectiveConsoleGatewayConfig(
 }
 
 export interface ConsoleGatewayRequest {
-  /** Console API name, e.g. zeldaEasy.broadscope-bailian.freeTrial.queryFreeTierQuota */
+  /** Console API name, e.g. zeldaEasy.bailian-commerce.freeTrial.queryFreeTierQuota */
   api: string;
   data: Record<string, unknown>;
 }

packages/core/src/types/api.ts

@@ -305,22 +305,11 @@ export interface MemoryAddRequest {
   custom_content?: string;
   profile_schema?: string;
   memory_library_id?: string;
-  project_id?: string;
-  meta_data?: Record<string, unknown>;
-}
-
-/** 变更的记忆片段;`event` 为 ADD / UPDATE / DELETE。 */
-export interface MemoryAddNode {
-  memory_node_id: string;
-  content: string;
-  event?: string;
-  /** 仅 `event` 为 UPDATE 时有效。 */
-  old_content?: string;
 }
 
 export interface MemoryAddResponse {
   request_id: string;
-  memory_nodes?: MemoryAddNode[];
+  memory_ids?: string[];
 }
 
 export interface MemorySearchRequest {
@@ -329,17 +318,6 @@ export interface MemorySearchRequest {
   query?: string;
   top_k?: number;
   memory_library_id?: string;
-  project_ids?: string[];
-  min_score?: number;
-  /**
-   * 计费档位的**有效**开关。服务端当前忽略单独传入的 `plan_version`,
-   * 只有 `enable_rerank: false` 才会按 lite 计费(pro 约为 lite 的 50 倍)。
-   */
-  enable_rerank?: boolean;
-  /** 文档所述的档位字段;当前服务端未按文档生效,与 `enable_rerank` 一起传。 */
-  plan_version?: "lite" | "pro";
-  enable_judge?: boolean;
-  enable_rewrite?: boolean;
 }
 
 export interface MemoryNode {
@@ -347,19 +325,13 @@ export interface MemoryNode {
   content: string;
   user_id?: string;
   meta_data?: Record<string, unknown>;
-  project_id?: string;
-  /** 秒级 Unix 时间戳。 */
-  created_at?: number;
-  /** 秒级 Unix 时间戳。 */
-  updated_at?: number;
-  timestamp?: number;
+  created_at?: string;
+  updated_at?: string;
 }
 
 export interface MemorySearchResponse {
   request_id: string;
   memory_nodes: MemoryNode[];
-  /** 本次检索实际计费的档位。 */
-  billing_plan?: string;
 }
 
 export interface MemoryNodeListResponse {
@@ -375,18 +347,13 @@ export interface MemoryNodeUpdateRequest {
   custom_content: string;
   /** 非默认记忆库时必填（与控制台记忆库 ID 一致） */
   memory_library_id?: string;
-  /** 记忆片段对应事件发生时的秒级 Unix 时间戳。 */
-  timestamp?: number;
-  /** 增量更新。 */
-  meta_data?: Record<string, unknown>;
 }
 
 // ---- Memory Profile (DashScope v2) ----
 
 export interface ProfileAttribute {
   name: string;
-  description?: string;
-  default_value?: string;
+  description: string;
   value?: string;
 }
 
@@ -394,8 +361,6 @@ export interface ProfileSchemaCreateRequest {
   name: string;
   description?: string;
   attributes: ProfileAttribute[];
-  memory_library_id?: string;
-  plan_version?: "lite" | "pro";
 }
 
 export interface ProfileSchemaCreateResponse {
@@ -403,52 +368,12 @@ export interface ProfileSchemaCreateResponse {
   profile_schema_id: string;
 }
 
-export interface ProfileSchemaSummary {
-  profile_schema_id: string;
-  name: string;
-  description?: string;
-}
-
-export interface ProfileSchemaListResponse {
-  request_id: string;
-  profile_schemas: ProfileSchemaSummary[];
-  total?: number;
-}
-
-/** 画像模板详情;`attributes[].attribute_id` 是更新/删除属性时的定位键。 */
-export interface ProfileSchemaGetResponse {
-  request_id: string;
-  name: string;
-  description?: string;
-  attributes: Array<ProfileAttribute & { attribute_id: string }>;
-}
-
-export interface ProfileSchemaAttributeOperation {
-  op: "add" | "update" | "delete";
-  /** `update` / `delete` 必填。 */
-  attribute_id?: string;
-  /** `add` 必填。 */
-  name?: string;
-  description?: string;
-  default_value?: string | null;
-}
-
-export interface ProfileSchemaUpdateRequest {
-  name?: string;
-  description?: string;
-  memory_library_id?: string;
-  attributes_operations?: ProfileSchemaAttributeOperation[];
-}
-
-/**
- * 用户画像。服务端返回的是模板名称/描述与属性值,不回传 schema_id / user_id。
- */
 export interface UserProfileResponse {
   request_id: string;
   profile: {
-    schema_name?: string;
-    schema_description?: string;
-    attributes: Array<{ id: string; name: string; value?: string }>;
+    schema_id: string;
+    user_id: string;
+    attributes: ProfileAttribute[];
   };
 }
 
@@ -608,33 +533,46 @@ export interface DashScopeTTSStreamChunk {
 export interface DashScopeASRRequest {
   model: string;
   input: {
-    file_urls: string[];
+    file_urls?: string[];
+    file_url?: string;
   };
   parameters?: {
     channel_id?: number[];
+    /** Classic async models (fun-asr / paraformer / qwen-audio filetrans, etc.) */
     language_hints?: string[];
+    /** qwen3-asr-flash-filetrans* uses singular `language` */
+    language?: string;
     diarization_enabled?: boolean;
     speaker_count?: number;
     vocabulary_id?: string;
   };
 }
 
+export interface DashScopeASRTranscriptionItem {
+  file_url?: string;
+  transcription_url?: string;
+  subtask_status?: string;
+  code?: string;
+  message?: string;
+}
+
 export interface DashScopeASRTaskResult {
   output: {
     task_id: string;
     task_status: "PENDING" | "RUNNING" | "SUCCEEDED" | "FAILED" | "UNKNOWN";
-    results?: Array<{
-      file_url?: string;
+    /** Multi-file async results (fun-asr / paraformer / qwen-audio filetrans, etc.) */
+    results?: DashScopeASRTranscriptionItem[];
+    /** Singular result returned by qwen3-asr-flash-filetrans* on success */
+    result?: {
       transcription_url?: string;
-      subtask_status?: string;
-      code?: string;
-      message?: string;
-    }>;
+    };
     task_metrics?: {
       TOTAL: number;
       SUCCEEDED: number;
       FAILED: number;
     };
+    code?: string;
+    message?: string;
   };
   usage?: Record<string, unknown>;
   request_id: string;

packages/core/src/types/index.ts

@@ -48,6 +48,7 @@ export type {
   ChatTool,
   DashScopeASRRequest,
   DashScopeASRTaskResult,
+  DashScopeASRTranscriptionItem,
   DashScopeAsyncResponse,
   DashScopeImageRequest,
   DashScopeImageSyncResponse,

packages/core/tests/asr-routes.test.ts

@@ -0,0 +1,213 @@
+import { expect, test } from "vite-plus/test";
+import {
+  buildAsrFlashRequest,
+  buildAsyncAsrLanguageFields,
+  collectAsrTranscriptionItems,
+  extractAsrFlashText,
+  inferAudioFormatHint,
+  resolveAsrApi,
+} from "../src/client/asr-routes.ts";
+
+test("resolveAsrApi routes model families correctly", () => {
+  const cases = [
+    {
+      model: "fun-asr",
+      expected: {
+        kind: "async-filetrans",
+        useSync: false,
+        path: "/api/v1/services/audio/asr/transcription",
+        asyncInputStyle: "file_urls",
+      },
+    },
+    {
+      model: "qwen3-asr-flash-filetrans-2025-11-17",
+      expected: {
+        kind: "async-filetrans",
+        useSync: false,
+        path: "/api/v1/services/audio/asr/transcription",
+        asyncInputStyle: "file_url",
+        asyncLanguageStyle: "language",
+      },
+    },
+    {
+      model: "qwen-audio-3.0-asr-flash-filetrans",
+      expected: {
+        kind: "async-filetrans",
+        useSync: false,
+        asyncInputStyle: "file_urls",
+        asyncLanguageStyle: "language_hints",
+      },
+    },
+    {
+      model: "qwen3-asr-flash-us",
+      expected: {
+        kind: "sync-flash",
+        useSync: true,
+        flashFamily: "qwen3",
+        path: "/api/v1/services/aigc/multimodal-generation/generation",
+      },
+    },
+    {
+      model: "qwen-audio-3.0-asr-flash",
+      expected: {
+        kind: "sync-flash",
+        useSync: true,
+        flashFamily: "input-audio",
+      },
+    },
+    {
+      model: "qwen3-asr-flash-realtime",
+      expected: {
+        kind: "unsupported",
+      },
+    },
+    {
+      model: "foo-asr-flash",
+      expected: {
+        kind: "async-filetrans",
+        useSync: false,
+        path: "/api/v1/services/audio/asr/transcription",
+        asyncInputStyle: "file_urls",
+      },
+    },
+  ] as const;
+
+  for (const { model, expected } of cases) {
+    const route = resolveAsrApi(model);
+    expect(route, model).toMatchObject(expected);
+    if (expected.kind === "unsupported") {
+      expect(route.unsupportedReason, model).toMatch(/realtime|streaming|WebSocket/i);
+    }
+  }
+});
+
+test("unknown models default to async-filetrans for backward compatibility", () => {
+  expect(resolveAsrApi("custom-asr-model")).toMatchObject({
+    kind: "async-filetrans",
+    useSync: false,
+  });
+});
+
+test("inferAudioFormatHint reads extension from url", () => {
+  expect(inferAudioFormatHint("https://example.com/a.mp3")).toBe("mp3");
+  expect(inferAudioFormatHint("oss://bucket/path/file.WAV")).toBe("wav");
+  expect(inferAudioFormatHint("https://example.com/a.mpeg?x=1")).toBe("mp3");
+  expect(inferAudioFormatHint("https://example.com/noext")).toBe("wav");
+  expect(inferAudioFormatHint("data:audio/mpeg;base64,AAA")).toBe("mp3");
+  expect(inferAudioFormatHint("data:audio/x-wav;base64,AAA")).toBe("wav");
+  expect(inferAudioFormatHint("data:audio/ogg;codecs=opus;base64,AAA")).toBe("ogg");
+});
+
+test("buildAsrFlashRequest shapes qwen3 and input-audio bodies", () => {
+  expect(
+    buildAsrFlashRequest({
+      model: "qwen3-asr-flash",
+      audioUrl: "https://example.com/a.mp3",
+      language: "en",
+      flashFamily: "qwen3",
+    }),
+  ).toEqual({
+    model: "qwen3-asr-flash",
+    input: {
+      messages: [{ role: "user", content: [{ audio: "https://example.com/a.mp3" }] }],
+    },
+    parameters: { asr_options: { language: "en" } },
+  });
+
+  expect(
+    buildAsrFlashRequest({
+      model: "qwen-audio-3.0-asr-flash",
+      audioUrl: "https://example.com/a.wav",
+      language: "en",
+      vocabularyId: "vocab-abc",
+      flashFamily: "input-audio",
+    }),
+  ).toEqual({
+    model: "qwen-audio-3.0-asr-flash",
+    input: {
+      messages: [
+        {
+          role: "user",
+          content: [{ type: "input_audio", input_audio: { data: "https://example.com/a.wav" } }],
+        },
+      ],
+    },
+    parameters: {
+      format: "wav",
+      sample_rate: "16000",
+      language_hints: ["en"],
+      vocabulary_id: "vocab-abc",
+    },
+  });
+});
+
+test("buildAsyncAsrLanguageFields maps language by async style", () => {
+  expect(buildAsyncAsrLanguageFields("language_hints", "zh")).toEqual({
+    language_hints: ["zh"],
+  });
+  expect(buildAsyncAsrLanguageFields("language", "zh")).toEqual({ language: "zh" });
+  expect(buildAsyncAsrLanguageFields("language", undefined)).toEqual({});
+});
+
+test("extractAsrFlashText reads qwen3 choices and input-audio text fields", () => {
+  expect(
+    extractAsrFlashText(
+      {
+        output: {
+          choices: [{ message: { content: [{ text: "你好" }] } }],
+        },
+      },
+      "qwen3",
+    ),
+  ).toBe("你好");
+
+  expect(
+    extractAsrFlashText(
+      {
+        output: {
+          text: "Hello World",
+          output: { sentence: { text: "ignored when text present" } },
+        },
+      },
+      "input-audio",
+    ),
+  ).toBe("Hello World");
+
+  expect(
+    extractAsrFlashText(
+      {
+        output: {
+          sentence: { text: "top-level sentence" },
+        },
+      },
+      "input-audio",
+    ),
+  ).toBe("top-level sentence");
+
+  expect(
+    extractAsrFlashText(
+      {
+        output: {
+          output: { sentence: { text: "nested sentence" } },
+        },
+      },
+      "input-audio",
+    ),
+  ).toBe("nested sentence");
+});
+
+test("collectAsrTranscriptionItems prefers results[] then singular result", () => {
+  expect(
+    collectAsrTranscriptionItems({
+      results: [{ transcription_url: "https://example.com/a.json", file_url: "https://a.wav" }],
+    }),
+  ).toEqual([{ transcription_url: "https://example.com/a.json", file_url: "https://a.wav" }]);
+
+  expect(
+    collectAsrTranscriptionItems({
+      result: { transcription_url: "https://example.com/qwen3.json" },
+    }),
+  ).toEqual([{ transcription_url: "https://example.com/qwen3.json", subtask_status: "SUCCEEDED" }]);
+
+  expect(collectAsrTranscriptionItems({})).toEqual([]);
+});

packages/core/tests/mcp.test.ts

@@ -0,0 +1,736 @@
+import { expect, test } from "vite-plus/test";
+import type { Identity, Settings } from "../src/index.ts";
+import {
+  BailianError,
+  bailianMcpPath,
+  bailianMcpSsePath,
+  connectBailianMcpWithFallback,
+  isStreamableHttpUnsupported,
+  isUrlOverrideSseFallbackCandidate,
+  McpClient,
+} from "../src/index.ts";
+import { McpSseClient, resolveSameOriginMessageUrl } from "../src/client/mcp-sse.ts";
+
+function testDeps(overrides?: Partial<Settings>): { identity: Identity; settings: Settings } {
+  return {
+    identity: {
+      binName: "bl",
+      version: "0.0.0-test",
+      npmPackage: "bailian-cli",
+      clientName: "bailian-cli",
+    },
+    settings: {
+      output: "json",
+      outputExplicit: true,
+      timeout: 5,
+      verbose: false,
+      quiet: true,
+      dryRun: false,
+      telemetry: true,
+      ...overrides,
+    },
+  };
+}
+
+function jsonRpcResult(id: number | string, result: unknown): string {
+  return `event:message\ndata:${JSON.stringify({ jsonrpc: "2.0", id, result })}\n\n`;
+}
+
+function requestUrl(input: string | URL | Request): string {
+  if (typeof input === "string") return input;
+  if (input instanceof URL) return input.href;
+  return input.url;
+}
+
+test("bailianMcp 路径与 isStreamableHttpUnsupported", () => {
+  expect(bailianMcpPath("WebParser")).toBe("/api/v1/mcps/WebParser/mcp");
+  expect(bailianMcpSsePath("WebParser")).toBe("/api/v1/mcps/WebParser/sse");
+
+  expect(
+    isStreamableHttpUnsupported(
+      new BailianError(
+        "MCP request failed: 405 Method Not Allowed - current mcp not support streamableHttp",
+      ),
+    ),
+  ).toBe(true);
+  expect(
+    isStreamableHttpUnsupported(new BailianError("MCP request failed: 405 Method Not Allowed")),
+  ).toBe(true);
+  expect(isStreamableHttpUnsupported(new BailianError("MCP request failed: 404 Not Found"))).toBe(
+    false,
+  );
+  expect(isStreamableHttpUnsupported(new Error("405 streamableHttp"))).toBe(false);
+  // JSON-RPC business 405 must not trigger HTTP transport fallback
+  expect(isStreamableHttpUnsupported(new BailianError("MCP error (405): Method Not Allowed"))).toBe(
+    false,
+  );
+  // Nested wrapper phrase in a JSON-RPC message must not trigger fallback.
+  expect(
+    isStreamableHttpUnsupported(
+      new BailianError("MCP error (-32000): MCP request failed: 405 Method Not Allowed"),
+    ),
+  ).toBe(false);
+
+  expect(
+    isUrlOverrideSseFallbackCandidate(new BailianError("MCP request failed: 404 Not Found")),
+  ).toBe(true);
+  expect(
+    isUrlOverrideSseFallbackCandidate(
+      new BailianError("MCP request failed: 405 Method Not Allowed"),
+    ),
+  ).toBe(true);
+  expect(isUrlOverrideSseFallbackCandidate(new BailianError("MCP error (404): not found"))).toBe(
+    false,
+  );
+  expect(
+    isUrlOverrideSseFallbackCandidate(
+      new BailianError("MCP error (-32000): MCP request failed: 404 Not Found"),
+    ),
+  ).toBe(false);
+});
+
+test("resolveSameOriginMessageUrl：同源通过、跨域拒绝", () => {
+  expect(
+    resolveSameOriginMessageUrl(
+      "https://example.test/api/v1/mcps/WebParser/sse",
+      "/api/v1/mcps/WebParser/message?sessionId=x",
+    ),
+  ).toBe("https://example.test/api/v1/mcps/WebParser/message?sessionId=x");
+
+  expect(() =>
+    resolveSameOriginMessageUrl(
+      "https://example.test/api/v1/mcps/WebParser/sse",
+      "https://evil.example/steal",
+    ),
+  ).toThrow(/origin mismatch/i);
+});
+
+test("connectBailianMcpWithFallback：成功走 Streamable；405 降级 SSE", async () => {
+  const originalFetch = globalThis.fetch;
+
+  // Streamable success path
+  globalThis.fetch = async (input, init) => {
+    const body = typeof init?.body === "string" ? JSON.parse(init.body) : {};
+    if (requestUrl(input).includes("/sse")) {
+      return new Response("should not hit sse", { status: 500 });
+    }
+    if (body.method === "notifications/initialized") {
+      return new Response(null, { status: 200 });
+    }
+    return new Response(JSON.stringify({ jsonrpc: "2.0", id: body.id, result: {} }), {
+      status: 200,
+    });
+  };
+
+  try {
+    const connected = await connectBailianMcpWithFallback({
+      deps: testDeps(),
+      authToken: "sk-test",
+      httpUrl: "https://example.test/api/v1/mcps/WebParser/mcp",
+      sseUrl: "https://example.test/api/v1/mcps/WebParser/sse",
+      serverCode: "WebParser",
+    });
+    expect(connected.url).toContain("/mcp");
+  } finally {
+    globalThis.fetch = originalFetch;
+  }
+
+  // Bare HTTP 405 (no streamableHttp body text) → SSE
+  let sseController: ReadableStreamDefaultController<Uint8Array> | undefined;
+  const encoder = new TextEncoder();
+  const urls: string[] = [];
+
+  globalThis.fetch = async (input, init) => {
+    const url = requestUrl(input);
+    urls.push(`${init?.method ?? "GET"} ${url}`);
+
+    if (url.endsWith("/mcp")) {
+      return new Response("Method Not Allowed", {
+        status: 405,
+        statusText: "Method Not Allowed",
+      });
+    }
+
+    if (url.endsWith("/sse") && (init?.method ?? "GET") === "GET") {
+      const stream = new ReadableStream<Uint8Array>({
+        start(controller) {
+          sseController = controller;
+          controller.enqueue(
+            encoder.encode(
+              "event:endpoint\ndata:/api/v1/mcps/WebParser/message?sessionId=test-session\n\n",
+            ),
+          );
+        },
+      });
+      return new Response(stream, {
+        status: 200,
+        headers: { "Content-Type": "text/event-stream" },
+      });
+    }
+
+    if (url.includes("/message")) {
+      const body = typeof init?.body === "string" ? JSON.parse(init.body) : {};
+      queueMicrotask(() => {
+        if (body.id != null && sseController) {
+          sseController.enqueue(encoder.encode(jsonRpcResult(body.id, {})));
+        }
+      });
+      return new Response(null, { status: 200 });
+    }
+
+    return new Response("unexpected", { status: 500 });
+  };
+
+  try {
+    const connected = await connectBailianMcpWithFallback({
+      deps: testDeps(),
+      authToken: "sk-test",
+      httpUrl: "https://example.test/api/v1/mcps/WebParser/mcp",
+      sseUrl: "https://example.test/api/v1/mcps/WebParser/sse",
+      serverCode: "WebParser",
+    });
+    expect(connected.url).toContain("/sse");
+    expect(urls.some((entry) => entry.includes("GET ") && entry.includes("/sse"))).toBe(true);
+    connected.client.close?.();
+  } finally {
+    globalThis.fetch = originalFetch;
+  }
+});
+
+test("connectBailianMcpWithFallback：WebSearch 不降级；urlOverride 同 URL 降级 SSE；404 不降级 Bailian 路径", async () => {
+  const originalFetch = globalThis.fetch;
+  const urls: string[] = [];
+
+  globalThis.fetch = async (input) => {
+    urls.push(requestUrl(input));
+    return new Response("current mcp not support streamableHttp", {
+      status: 405,
+      statusText: "Method Not Allowed",
+    });
+  };
+
+  try {
+    await expect(
+      connectBailianMcpWithFallback({
+        deps: testDeps(),
+        authToken: "sk-test",
+        httpUrl: "https://example.test/api/v1/mcps/WebSearch/mcp",
+        sseUrl: "https://example.test/api/v1/mcps/WebSearch/sse",
+        serverCode: "WebSearch",
+      }),
+    ).rejects.toBeInstanceOf(BailianError);
+    expect(urls.some((url) => url.includes("/sse"))).toBe(false);
+  } finally {
+    globalThis.fetch = originalFetch;
+  }
+
+  // urlOverride: after POST 405, fall back with GET SSE on the same URL
+  urls.length = 0;
+  let sseController: ReadableStreamDefaultController<Uint8Array> | undefined;
+  const encoder = new TextEncoder();
+  const overrideUrl = "https://custom.example/mcp";
+
+  globalThis.fetch = async (input, init) => {
+    const url = requestUrl(input);
+    const method = init?.method ?? "GET";
+    urls.push(`${method} ${url}`);
+
+    if (method === "POST" && url === overrideUrl) {
+      return new Response("Method Not Allowed", {
+        status: 405,
+        statusText: "Method Not Allowed",
+      });
+    }
+
+    if (method === "GET" && url === overrideUrl) {
+      const stream = new ReadableStream<Uint8Array>({
+        start(controller) {
+          sseController = controller;
+          controller.enqueue(encoder.encode("event:endpoint\ndata:/message?sessionId=x\n\n"));
+        },
+      });
+      return new Response(stream, {
+        status: 200,
+        headers: { "Content-Type": "text/event-stream" },
+      });
+    }
+
+    if (url.includes("/message")) {
+      const body = typeof init?.body === "string" ? JSON.parse(init.body) : {};
+      queueMicrotask(() => {
+        if (body.id != null && sseController) {
+          sseController.enqueue(encoder.encode(jsonRpcResult(body.id, {})));
+        }
+      });
+      return new Response(null, { status: 200 });
+    }
+
+    return new Response("unexpected", { status: 500 });
+  };
+
+  try {
+    const connected = await connectBailianMcpWithFallback({
+      deps: testDeps(),
+      authToken: "sk-test",
+      httpUrl: "https://example.test/api/v1/mcps/WebParser/mcp",
+      sseUrl: "https://example.test/api/v1/mcps/WebParser/sse",
+      serverCode: "WebParser",
+      urlOverride: overrideUrl,
+    });
+    expect(connected.url).toBe(overrideUrl);
+    expect(urls.some((entry) => entry.startsWith(`GET ${overrideUrl}`))).toBe(true);
+    connected.client.close?.();
+  } finally {
+    globalThis.fetch = originalFetch;
+  }
+
+  globalThis.fetch = async () =>
+    new Response("MCP不存在或未开通", { status: 404, statusText: "Not Found" });
+
+  try {
+    await expect(
+      connectBailianMcpWithFallback({
+        deps: testDeps(),
+        authToken: "sk-test",
+        httpUrl: "https://example.test/api/v1/mcps/WebParser/mcp",
+        sseUrl: "https://example.test/api/v1/mcps/WebParser/sse",
+        serverCode: "WebParser",
+      }),
+    ).rejects.toMatchObject({ message: expect.stringContaining("404") });
+  } finally {
+    globalThis.fetch = originalFetch;
+  }
+});
+
+test("McpSseClient：流结束后立刻失败 pending（不干等到 timeout）", async () => {
+  const originalFetch = globalThis.fetch;
+  const encoder = new TextEncoder();
+
+  globalThis.fetch = async (input, init) => {
+    const url = requestUrl(input);
+    if ((init?.method ?? "GET") === "GET" || url.endsWith("/sse")) {
+      // Close the stream immediately after the endpoint event
+      const stream = new ReadableStream<Uint8Array>({
+        start(controller) {
+          controller.enqueue(
+            encoder.encode("event:endpoint\ndata:/api/v1/mcps/WebParser/message?sessionId=x\n\n"),
+          );
+          controller.close();
+        },
+      });
+      return new Response(stream, {
+        status: 200,
+        headers: { "Content-Type": "text/event-stream" },
+      });
+    }
+    return new Response(null, { status: 200 });
+  };
+
+  try {
+    const client = new McpSseClient(
+      testDeps({ timeout: 5 }),
+      "https://example.test/sse",
+      "sk-test",
+    );
+    const started = Date.now();
+    await expect(client.initialize()).rejects.toThrow(/stream ended unexpectedly/i);
+    expect(Date.now() - started).toBeLessThan(2000);
+    client.close();
+  } finally {
+    globalThis.fetch = originalFetch;
+  }
+});
+
+test("McpSseClient：string JSON-RPC id 可匹配；仅认 event:endpoint", async () => {
+  const originalFetch = globalThis.fetch;
+  let sseController: ReadableStreamDefaultController<Uint8Array> | undefined;
+  const encoder = new TextEncoder();
+
+  globalThis.fetch = async (input, init) => {
+    const url = requestUrl(input);
+    if ((init?.method ?? "GET") === "GET" || url.endsWith("/sse")) {
+      const stream = new ReadableStream<Uint8Array>({
+        start(controller) {
+          sseController = controller;
+          // Untyped events must not be treated as endpoint
+          controller.enqueue(
+            encoder.encode(`data:${JSON.stringify({ jsonrpc: "2.0", id: 99, result: {} })}\n\n`),
+          );
+          controller.enqueue(
+            encoder.encode("event:endpoint\ndata:/api/v1/mcps/WebParser/message?sessionId=x\n\n"),
+          );
+        },
+      });
+      return new Response(stream, {
+        status: 200,
+        headers: { "Content-Type": "text/event-stream" },
+      });
+    }
+
+    if (url.includes("/message")) {
+      const body = typeof init?.body === "string" ? JSON.parse(init.body) : {};
+      queueMicrotask(() => {
+        if (body.id != null && sseController) {
+          // Echo id as a string
+          sseController.enqueue(encoder.encode(jsonRpcResult(String(body.id), {})));
+        }
+      });
+      return new Response(null, { status: 200 });
+    }
+
+    return new Response("unexpected", { status: 500 });
+  };
+
+  try {
+    const client = new McpSseClient(testDeps(), "https://example.test/sse", "sk-test");
+    await client.initialize();
+    client.close();
+  } finally {
+    globalThis.fetch = originalFetch;
+  }
+});
+
+test("McpClient：支持 text/event-stream 响应体", async () => {
+  const originalFetch = globalThis.fetch;
+
+  globalThis.fetch = async (_input, init) => {
+    const body = typeof init?.body === "string" ? JSON.parse(init.body) : {};
+    if (body.method === "notifications/initialized") {
+      return new Response(null, { status: 202 });
+    }
+    const sse = `event: message\ndata: ${JSON.stringify({
+      jsonrpc: "2.0",
+      id: body.id,
+      result: {
+        protocolVersion: "2025-03-26",
+        capabilities: {},
+        serverInfo: { name: "x", version: "0" },
+      },
+    })}\n\n`;
+    return new Response(sse, {
+      status: 200,
+      headers: { "Content-Type": "text/event-stream" },
+    });
+  };
+
+  try {
+    const client = new McpClient(testDeps(), "https://example.test/mcp", "sk-test");
+    await client.initialize();
+  } finally {
+    globalThis.fetch = originalFetch;
+  }
+});
+
+test("McpSseClient.close 可中止挂起 GET", async () => {
+  const originalFetch = globalThis.fetch;
+  let aborted = false;
+
+  globalThis.fetch = async (_input, init) => {
+    const signal = init?.signal;
+    if (signal) {
+      signal.addEventListener("abort", () => {
+        aborted = true;
+      });
+    }
+    const stream = new ReadableStream<Uint8Array>({
+      start(controller) {
+        controller.enqueue(
+          new TextEncoder().encode(
+            "event:endpoint\ndata:/api/v1/mcps/WebParser/message?sessionId=x\n\n",
+          ),
+        );
+      },
+    });
+    return new Response(stream, {
+      status: 200,
+      headers: { "Content-Type": "text/event-stream" },
+    });
+  };
+
+  try {
+    const client = new McpSseClient(testDeps(), "https://example.test/sse", "sk-test");
+    const initPromise = client.initialize().catch(() => undefined);
+    await new Promise((resolve) => setTimeout(resolve, 20));
+    client.close();
+    await initPromise;
+    expect(aborted).toBe(true);
+  } finally {
+    globalThis.fetch = originalFetch;
+  }
+});
+
+test("McpSseClient：等待响应头受 --timeout 约束", async () => {
+  const originalFetch = globalThis.fetch;
+
+  globalThis.fetch = async (_input, init) => {
+    const signal = init?.signal;
+    return new Promise((_resolve, reject) => {
+      if (!signal) {
+        reject(new Error("missing signal"));
+        return;
+      }
+      if (signal.aborted) {
+        reject(new DOMException("This operation was aborted.", "AbortError"));
+        return;
+      }
+      signal.addEventListener(
+        "abort",
+        () => reject(new DOMException("This operation was aborted.", "AbortError")),
+        { once: true },
+      );
+    });
+  };
+
+  try {
+    const client = new McpSseClient(
+      testDeps({ timeout: 1 }),
+      "https://example.test/sse",
+      "sk-test",
+    );
+    const started = Date.now();
+    await expect(client.initialize()).rejects.toThrow(/timed out waiting for response headers/i);
+    expect(Date.now() - started).toBeLessThan(2500);
+    client.close();
+  } finally {
+    globalThis.fetch = originalFetch;
+  }
+});
+
+test("McpSseClient：非 2xx 不产生 unhandledRejection", async () => {
+  const originalFetch = globalThis.fetch;
+  const unhandled: unknown[] = [];
+  const onUnhandled = (reason: unknown) => {
+    unhandled.push(reason);
+  };
+  process.on("unhandledRejection", onUnhandled);
+
+  globalThis.fetch = async () =>
+    new Response("boom", { status: 500, statusText: "Internal Server Error" });
+
+  try {
+    const client = new McpSseClient(testDeps(), "https://example.test/sse", "sk-test");
+    await expect(client.initialize()).rejects.toThrow(/MCP request failed:\s*500/i);
+    await new Promise((resolve) => setTimeout(resolve, 30));
+    expect(unhandled).toEqual([]);
+    client.close();
+  } finally {
+    process.off("unhandledRejection", onUnhandled);
+    globalThis.fetch = originalFetch;
+  }
+});
+
+test("McpSseClient：非 2xx 读 body 仍受 --timeout 约束", async () => {
+  const originalFetch = globalThis.fetch;
+
+  globalThis.fetch = async (_input, init) => {
+    const signal = init?.signal;
+    return {
+      ok: false,
+      status: 500,
+      statusText: "Internal Server Error",
+      async text() {
+        return new Promise<string>((_resolve, reject) => {
+          if (!signal) {
+            reject(new Error("missing signal"));
+            return;
+          }
+          if (signal.aborted) {
+            reject(new DOMException("This operation was aborted.", "AbortError"));
+            return;
+          }
+          signal.addEventListener(
+            "abort",
+            () => reject(new DOMException("This operation was aborted.", "AbortError")),
+            { once: true },
+          );
+        });
+      },
+    } as Response;
+  };
+
+  try {
+    const client = new McpSseClient(
+      testDeps({ timeout: 1 }),
+      "https://example.test/sse",
+      "sk-test",
+    );
+    const started = Date.now();
+    await expect(client.initialize()).rejects.toThrow(/timed out reading error response body/i);
+    expect(Date.now() - started).toBeLessThan(2500);
+    client.close();
+  } finally {
+    globalThis.fetch = originalFetch;
+  }
+});
+
+test("McpSseClient：fetch 失败抛出原始 TypeError（保留 ENOTFOUND）", async () => {
+  const originalFetch = globalThis.fetch;
+  const root = Object.assign(new Error("getaddrinfo ENOTFOUND example.test"), {
+    code: "ENOTFOUND",
+  });
+  const fetchFailed = new TypeError("fetch failed", { cause: root });
+
+  globalThis.fetch = async () => {
+    throw fetchFailed;
+  };
+
+  try {
+    const client = new McpSseClient(testDeps(), "https://example.test/sse", "sk-test");
+    const error = await client.initialize().catch((reason: unknown) => reason);
+    expect(error).toBe(fetchFailed);
+    expect((error as TypeError & { cause?: NodeJS.ErrnoException }).cause?.code).toBe("ENOTFOUND");
+    client.close();
+  } finally {
+    globalThis.fetch = originalFetch;
+  }
+});
+
+test("McpSseClient：fetch 失败后同实例可重新 openSse", async () => {
+  const originalFetch = globalThis.fetch;
+  let attempt = 0;
+  let sseController: ReadableStreamDefaultController<Uint8Array> | undefined;
+  const encoder = new TextEncoder();
+
+  globalThis.fetch = async (input, init) => {
+    const url = requestUrl(input);
+    const method = init?.method ?? "GET";
+    if (method === "GET" || url.endsWith("/sse")) {
+      attempt += 1;
+      if (attempt === 1) {
+        throw new TypeError("fetch failed");
+      }
+      const stream = new ReadableStream<Uint8Array>({
+        start(controller) {
+          sseController = controller;
+          controller.enqueue(encoder.encode("event: endpoint\ndata: /message\n\n"));
+        },
+      });
+      return new Response(stream, {
+        status: 200,
+        headers: { "Content-Type": "text/event-stream" },
+      });
+    }
+    const body = typeof init?.body === "string" ? JSON.parse(init.body) : {};
+    queueMicrotask(() => {
+      if (body.id != null && sseController) {
+        sseController.enqueue(encoder.encode(jsonRpcResult(body.id, {})));
+      }
+    });
+    return new Response("{}", { status: 200, headers: { "Content-Type": "application/json" } });
+  };
+
+  try {
+    const client = new McpSseClient(testDeps(), "https://example.test/sse", "sk-test");
+    await expect(client.initialize()).rejects.toThrow(/fetch failed/i);
+    await client.initialize();
+    client.close();
+  } finally {
+    globalThis.fetch = originalFetch;
+  }
+});
+
+test("McpSseClient：close 可中止进行中的 POST", async () => {
+  const originalFetch = globalThis.fetch;
+  let postAborted = false;
+  const encoder = new TextEncoder();
+
+  globalThis.fetch = async (input, init) => {
+    const url = requestUrl(input);
+    const method = init?.method ?? "GET";
+    if (method === "GET" || url.endsWith("/sse")) {
+      const stream = new ReadableStream<Uint8Array>({
+        start(controller) {
+          controller.enqueue(encoder.encode("event: endpoint\ndata: /message\n\n"));
+        },
+      });
+      return new Response(stream, {
+        status: 200,
+        headers: { "Content-Type": "text/event-stream" },
+      });
+    }
+
+    const signal = init?.signal;
+    return new Promise((_resolve, reject) => {
+      if (!signal) {
+        reject(new Error("missing signal"));
+        return;
+      }
+      const onAbort = () => {
+        postAborted = true;
+        reject(new DOMException("This operation was aborted.", "AbortError"));
+      };
+      if (signal.aborted) {
+        onAbort();
+        return;
+      }
+      signal.addEventListener("abort", onAbort, { once: true });
+    });
+  };
+
+  try {
+    const client = new McpSseClient(
+      testDeps({ timeout: 5 }),
+      "https://example.test/sse",
+      "sk-test",
+    );
+    const initPromise = client.initialize();
+    await new Promise((resolve) => setTimeout(resolve, 30));
+    client.close();
+    await expect(initPromise).rejects.toThrow(/session closed|aborted/i);
+    expect(postAborted).toBe(true);
+  } finally {
+    globalThis.fetch = originalFetch;
+  }
+});
+
+test("McpSseClient：POST 非 2xx 读 body 仍受 --timeout 约束", async () => {
+  const originalFetch = globalThis.fetch;
+  const encoder = new TextEncoder();
+
+  globalThis.fetch = async (input, init) => {
+    const url = requestUrl(input);
+    const method = init?.method ?? "GET";
+    if (method === "GET" || url.endsWith("/sse")) {
+      const stream = new ReadableStream<Uint8Array>({
+        start(controller) {
+          controller.enqueue(encoder.encode("event: endpoint\ndata: /message\n\n"));
+        },
+      });
+      return new Response(stream, {
+        status: 200,
+        headers: { "Content-Type": "text/event-stream" },
+      });
+    }
+
+    const signal = init?.signal;
+    const body = new ReadableStream<Uint8Array>({
+      start(controller) {
+        if (!signal) return;
+        const onAbort = () => {
+          try {
+            controller.error(new DOMException("This operation was aborted.", "AbortError"));
+          } catch {
+            /* ignore */
+          }
+        };
+        if (signal.aborted) onAbort();
+        else signal.addEventListener("abort", onAbort, { once: true });
+      },
+    });
+    return new Response(body, { status: 500, statusText: "Internal Server Error" });
+  };
+
+  try {
+    const client = new McpSseClient(
+      testDeps({ timeout: 1 }),
+      "https://example.test/sse",
+      "sk-test",
+    );
+    const started = Date.now();
+    await expect(client.initialize()).rejects.toThrow(/timed out reading error response body/i);
+    expect(Date.now() - started).toBeLessThan(2500);
+    client.close();
+  } finally {
+    globalThis.fetch = originalFetch;
+  }
+});

packages/core/tests/stream.test.ts

@@ -0,0 +1,79 @@
+import { expect, test } from "vite-plus/test";
+import { parseSSE } from "../src/client/stream.ts";
+
+async function collectEvents(
+  chunks: string[],
+): Promise<Array<{ data: string; event?: string; id?: string }>> {
+  const encoder = new TextEncoder();
+  const stream = new ReadableStream<Uint8Array>({
+    start(controller) {
+      for (const chunk of chunks) {
+        controller.enqueue(encoder.encode(chunk));
+      }
+      controller.close();
+    },
+  });
+  const response = new Response(stream, {
+    headers: { "Content-Type": "text/event-stream" },
+  });
+  const events: Array<{ data: string; event?: string; id?: string }> = [];
+  for await (const event of parseSSE(response)) {
+    events.push(event);
+  }
+  return events;
+}
+
+test("parseSSE：单 chunk 完整事件保持原行为", async () => {
+  const events = await collectEvents([
+    'event: message\ndata: {"ok":true}\nid: 1\n\ndata: plain\n\n',
+  ]);
+  expect(events).toEqual([{ data: '{"ok":true}', event: "message", id: "1" }, { data: "plain" }]);
+});
+
+test("parseSSE：多行 data 与注释保持原行为", async () => {
+  const events = await collectEvents([": keep-alive\ndata: line1\ndata: line2\n\n"]);
+  expect(events).toEqual([{ data: "line1\nline2" }]);
+});
+
+test("parseSSE：跨 chunk 保留 event 类型", async () => {
+  const events = await collectEvents(["event: endpoint\n", "data: /message?sessionId=abc\n\n"]);
+  expect(events).toEqual([{ data: "/message?sessionId=abc", event: "endpoint" }]);
+});
+
+test("parseSSE：跨 chunk 保留 id，且多事件连续正确", async () => {
+  const events = await collectEvents([
+    "id: a\nevent: message\n",
+    'data: {"n":1}\n\n',
+    "event: message\ndata: ",
+    '{"n":2}\n\n',
+  ]);
+  expect(events).toEqual([
+    { data: '{"n":1}', event: "message", id: "a" },
+    { data: '{"n":2}', event: "message" },
+  ]);
+});
+
+test("parseSSE：CRLF 行尾可解析 endpoint", async () => {
+  const events = await collectEvents(["event: endpoint\r\ndata: /message\r\n\r\n"]);
+  expect(events).toEqual([{ data: "/message", event: "endpoint" }]);
+});
+
+test("parseSSE：纯 CR 行尾可解析 endpoint", async () => {
+  const events = await collectEvents(["event: endpoint\rdata: /message\r\r"]);
+  expect(events).toEqual([{ data: "/message", event: "endpoint" }]);
+});
+
+test("parseSSE：跨 chunk 的 CRLF（\\r|\\n）不丢事件", async () => {
+  const events = await collectEvents(["event: endpoint\r", "\ndata: /message\r\n\r\n"]);
+  expect(events).toEqual([{ data: "/message", event: "endpoint" }]);
+});
+
+test("parseSSE：EOF without blank line keeps event type", async () => {
+  const events = await collectEvents(["event: endpoint\ndata: /message"]);
+  expect(events).toEqual([{ data: "/message", event: "endpoint" }]);
+});
+
+test("parseSSE：EOF data-only flush keeps prior behavior", async () => {
+  const events = await collectEvents(["data: plain"]);
+  expect(events).toEqual([{ data: "plain" }]);
+});

packages/dsh/.gitignore

@@ -1,4 +0,0 @@
-# build artifacts (regenerated by `pnpm build`)
-client.bundle.js
-dist/
-*.tgz

packages/dsh/README.md

@@ -1,232 +0,0 @@
-# bailian-cli-dsh
-
-把阿里云百炼（Model Studio）的能力接入 [DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness)（`dsh`）的 profile bundle。
-
-本包提供两项能力：
-
-| 能力               | 说明                                                                                                                  |
-| ------------------ | --------------------------------------------------------------------------------------------------------------------- |
-| **Bailian 设置页** | 通用的百炼凭证配置（AK/SK 存入 `dsh` bl profile + DashScope API Key）+ TokenPlan 用量展示 + 记忆库配置 + 新会话欢迎页 |
-| **跨会话长期记忆** | 自动检索注入 + 自动落库，模型可主动 search/add/list。按量计费，默认停用                                               |
-
----
-
-## 1. 前置条件
-
-- Node ≥ 22.19（`dsh` 的要求）
-- `bl`（用量展示通过子进程调用 `bl console call`）
-
-  ```sh
-  npm install -g bailian-cli
-  ```
-
-- **阿里云 AK/SK**（AccessKey ID + AccessKey Secret）—— 用于控制台鉴权，查询用量信息。在 webui 设置页填入即可，无需环境变量。
-- **DashScope API Key**（`sk-` 前缀，按量付费）—— 用于记忆库等 DashScope API 调用。在设置页「凭证配置」填入，与 AK/SK 并列为通用凭证。
-
-  获取方式：[阿里云控制台 → AccessKey 管理](https://ram.console.aliyun.com/manage/ak)
-
----
-
-## 2. 安装到 `web` profile
-
-`npx @deepseek-ai/dsh web` 是 `dsh --profile web` 的别名，配置目录是 `~/.dsh/profiles/web/`。
-
-```sh
-pnpm -F bailian-cli-dsh build   # vp pack（host）+ esbuild（client.bundle.js）
-cd packages/dsh && pnpm pack
-
-npx @deepseek-ai/dsh plugin --profile web add /absolute/path/to/bailian-cli-dsh-<version>.tgz
-```
-
-确认 bailian 行都在：
-
-```sh
-npx @deepseek-ai/dsh --profile web --dump-config | grep -E 'bailian'
-```
-
-启动：
-
-```sh
-npx @deepseek-ai/dsh web
-```
-
-Web UI 在 http://127.0.0.1:3080。
-
----
-
-## 3. Bailian 设置页 + 欢迎页
-
-安装并重启后：
-
-- **Settings → Bailian**：通用设置页（凭证配置 / TokenPlan 用量 / 记忆库）。
-- **新会话欢迎页**：每个新会话（blank）在输入框上方显示「百炼 Agent」欢迎页（Tab + 功能卡片），发出第一条消息后自动隐藏。
-
-### 凭证配置（通用）
-
-1. 在「凭证配置」区填入 **AccessKey ID** 和 **AccessKey Secret**
-2. 点击 **「保存凭证」**
-
-Host 会执行 `bl auth login --open-api --config dsh`，将 AK/SK 和新生成的 access_token 存入 bl 的 `dsh` 专属 profile。**所有后续百炼插件共用此凭证**，无需重复配置。
-
-### TokenPlan 用量
-
-1. 选择区域和站点
-2. 点击 **「查询用量」**
-
-Host 执行 `bl console call --config dsh` 调用 3 个个人版控制台接口，返回：
-
-- **用量百分比** —— 5 小时窗口 / 1 周窗口的用量百分比和重置时间
-- **套餐信息** —— 套餐类型（基础版/标准版/高级版）、状态、剩余天数、到期时间、自动续费
-- **额外用量包** —— Credits 总量、剩余量、生效中数量
-
-### 凭证解析优先级
-
-凭证保存到 bl 的 `dsh` profile 后，所有百炼插件通过 `--config dsh` 读取。行内 config 的 `accessKeyId`/`accessKeySecret` 作为兜底（未通过 UI 保存时自动使用）。
-
-### 行内配置（可选）
-
-如果不想在 UI 里每次输入，可以在 profile 的 `cordis.patch.yml` 里固化凭证：
-
-```yaml
-- id: bailian-tokenplan-usage
-  config:
-    # accessKeyId / accessKeySecret: 兜底凭证（未通过 UI 保存时使用）
-    # consoleRegion: cn-beijing
-    # consoleSite: domestic
-    # profile: dsh  # 默认用 dsh 专属 profile
-```
-
-配置后 UI 表单会留空，但点击「查询用量」会使用行内凭证。
-
----
-
-## 4. 跨会话长期记忆
-
-默认停用（按量计费）。在 `cordis.patch.yml` 中设 `disabled: false` 启用，然后在设置页配置 API Key 和参数。
-
-### 功能
-
-- **自动检索注入**：新会话首轮，用用户消息搜索记忆，将结果注入上下文（`autoInject`，默认开启）
-- **自动落库**：每轮结束，将该轮新消息发送到记忆库 add API（`autoPersist`，默认开启）
-- **模型工具**：`bailian_memory_search`（检索）、`bailian_memory_add`（存储）、`bailian_memory_list`（浏览）
-
-### 触发机制
-
-| 时机       | 触发方式                                                  |
-| ---------- | --------------------------------------------------------- |
-| 新会话首轮 | 自动检索记忆注入上下文（`agent/pre-step` 事件）           |
-| 对话中     | 模型主动调用 `bailian_memory_search`/`bailian_memory_add` |
-| 轮次结束   | 自动落库新消息（`agent/turn-stopping` 事件）              |
-
-### 凭证与配置
-
-- **API Key**：DashScope 按量付费 Key（`sk-`），在设置页「凭证配置」填入
-- **Base URL**：默认 `https://dashscope.aliyuncs.com/api/v2/apps/memory/`
-- **User ID**：记忆归属 ID，默认读系统用户名
-- **Plan Version**：`lite`（便宜，关闭 rerank）或 `pro`（开启 rerank，约 50 倍成本）。注意：实际计费由 `enable_rerank` 控制
-- **Top K**：检索返回数量（1-100，默认 10）
-- **Memory Library ID**：记忆库 ID，留空用默认
-
-### 计费
-
-- Add：120 QPM
-- Search：300 QPM（Lite ¥0.00002/次，Pro ¥0.001/次）
-- 总计不超过 3000 QPM
-
-### 启用
-
-```yaml
-- id: bailian-memory
-  disabled: false
-  config:
-    baseUrl: "https://dashscope.aliyuncs.com/api/v2/apps/memory/"
-    planVersion: "lite"
-    topK: 10
-    autoInject: true
-    autoPersist: true
-```
-
-启用后在设置页「记忆库」section 配置 API Key 和参数。
-
-> 记忆库调用 DashScope memory v2 API（非 `bl memory`），因为 v2 API 暴露了 `min_score`、`enable_rerank`、`plan_version`、`memory_library_id` 等参数 `bl memory` 不支持。
-
-## 5. 验证
-
-```sh
-# 配置合成
-npx @deepseek-ai/dsh --profile web --dump-config | grep bailian
-
-# bl 就绪
-bl auth status
-```
-
-启动后验证：
-
-- **欢迎页**：新开一个会话，输入框上方出现「百炼 Agent」欢迎页
-- **凭证配置**：打开 Settings → Bailian → 填入 AK/SK → 保存凭证
-- **用量展示**：同页面选择区域 → 查询用量
-- **记忆库**：启用 `bailian-memory` 后，同页面配置 API Key
-
----
-
-## 6. 常见问题
-
-| 现象                                  | 原因                                                                                                                               |
-| ------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------- |
-| 用量查询报 `bl auth login failed`     | AK/SK 无效或无权限；确认 AK 有百炼控制台访问权限                                                                                   |
-| 用量查询报 `NotLogined` 或 token 过期 | bl 的 access token 已过期；Host 会自动通过 AK/SK 刷新，确认 AK/SK 正确                                                             |
-| 用量查询报 `bl console call failed`   | 控制台接口调用失败；检查 region/site 是否匹配你的账号                                                                              |
-| 用量查询报 `Workspace.NotAuthorised`  | bl 用了其他 profile 的旧 access_token；Host 默认用 `--config dsh` 专属 profile 隔离，首次 login 会生成新 token                     |
-| 工具报找不到 `bl`                     | `bl` 不在 PATH：`npm install -g bailian-cli`                                                                                       |
-| 设置页/欢迎页看不到 Bailian           | 需**重启 `dsh web`**（bundle 在启动时加载）；确认 `dump-config` 有 `bailian-client` 行，且 `client.bundle.js` 为 ModuleLoader 格式 |
-| 启动报 `invalid plugin ... apply`     | 包根 `dist/index.mjs` 必须导出 `apply`（no-op 插件）；重新 `pnpm build` 再装                                                       |
-
----
-
-## 7. 卸载
-
-```sh
-npx @deepseek-ai/dsh plugin --profile web remove bailian-cli-dsh
-```
-
----
-
-## 架构说明
-
-### Host 半
-
-- `src/tokenplan-usage/index.ts` —— 凭证 + TokenPlan 用量。`inject: ['subprocess']`，所有 bl 命令带 `--config dsh` 隔离凭证。两个 webServer 路由：
-  - `POST /bailian/credentials` — 保存 AK/SK（`bl auth login --open-api --config dsh`，生成新 token）
-  - `POST /bailian/tokenplan/usage` — 查询用量（`bl console call --config dsh`，3 个个人版接口）
-- `src/memory/index.ts` —— 记忆库（默认停用）。直接调 DashScope memory v2 API，注册 tools + auto-inject/persist。路由 `/bailian/memory/config`、`/bailian/memory/status`。
-- `src/index.ts` —— 包根 no-op 插件，供 `bailian-client` 行加载（该行只为了让 client-modules 服务浏览器 bundle）。
-
-> 路由用 `/bailian/*` 而非 `/api/*`：`/api` 前缀被 dsh 的 RPC 网关（apiProxy）占用，自定义路由会被遮蔽。
-
-调用链路：**AK/SK → `bl auth login --open-api --config dsh`（存入 dsh profile）→ `bl console call --config dsh`（读 dsh profile token → 控制台网关）→ 个人版 TokenPlan 接口**
-
-### Client 半（`src/client.ts`）
-
-- 唯一的浏览器源码，构建为 DSH ModuleLoader 格式（见下）。
-- 注册 `settings.section`（id: `bailian`，label: `Bailian`），渲染通用百炼设置页（凭证配置 / TokenPlan 用量 / 记忆库）。
-- 注册 `conversation.input.dock`（id: `bailian-welcome`）：当 `session.blank === true`（新会话）渲染「百炼 Agent」欢迎页（Tab + 功能卡片），开始对话后自动隐藏。
-- 通过 `fetch('/bailian/*')` 调 Host 路由。
-
-### Client 构建（ModuleLoader 格式）
-
-DSH 浏览器只加载 `window.__ModuleLoader__.load({ id, factory })` 格式的 bundle（`require('react')` 由浏览器 ModuleLoader 提供）。vite-plus 产出裸 ES module，格式不对，所以 client 单独用 esbuild 构建：
-
-- `scripts/build-client.mjs` —— 把 `src/client.ts` 构建为 CJS + browser + `react` external，包上 ModuleLoader banner/footer，输出 `client.bundle.js`。
-- `package.json` 的 `build` = `vp pack && node scripts/build-client.mjs`。
-- `package.json` 的 `exports["./client"]` 与 `dsh.client: { platform: "web" }` 指向 `client.bundle.js`，被 client-modules 扫描并服务。
-- `cordis.patch.yml` 的 `bailian-client` 行 `name` 必须是**包根**（`bailian-cli-dsh`，无子路径），client-modules 才能 `require.resolve("<name>/package.json")` 识别 `dsh.client`。
-
-改 client UI 只需编辑 `src/client.ts`，`pnpm build` 自动重新生成 `client.bundle.js`。
-
-### 共享模块（`src/shared/`）
-
-- `bl.ts` —— `bl` 子进程调用封装（env 转发、stdout/stderr 收集、JSON 解析）
-- `credentials.ts` —— TokenPlan / 按量付费 Key 分类工具
-- `http.ts` —— DashScope HTTP 客户端
-
-这些模块来自早期版本（vision / image / managed-agent / RAG / memory 工具），已移除工具实现但保留共享逻辑作为参考。

packages/dsh/cordis.patch.yml

@@ -1,53 +0,0 @@
-# bailian-cli-dsh — Aliyun Model Studio (Bailian) as a dsh profile bundle.
-#
-# Inserts Bailian plugin rows: TokenPlan usage display + cross-session memory.
-# Every inserted id is `bailian-`-prefixed so a user profile can address,
-# reconfigure, or disable any single capability without touching the others.
-# Remember that a later patch REPLACES a row's whole `config` rather than
-# merging into it, so restate the complete config when overriding.
-
-- insert:
-    # Client-only row: name is the package ROOT (no subpath) so client-modules
-    # can resolve "<name>/package.json" and detect the dsh.client declaration.
-    # Its node half (dist/index.mjs) is a no-op; the row exists to serve the
-    # browser bundle (client.bundle.js) that renders the Bailian settings page
-    # and the new-session welcome page.
-    - id: bailian-client
-      name: bailian-cli-dsh
-
-    # TokenPlan usage display (dual-face: Host provides two webServer routes,
-    # Client renders a general "Bailian" settings.section page). All bl commands
-    # use `--config dsh` to isolate credentials in a dedicated bl profile.
-    #
-    # Two routes:
-    #   POST /api/bailian/credentials — saves AK/SK to dsh profile
-    #     (bl auth login --open-api --config dsh). Generates fresh access_token.
-    #   POST /api/bailian/tokenplan/usage — fetches personal-edition usage
-    #     using the dsh profile (no AK/SK in body; credentials already saved).
-    #
-    # Users configure AK/SK once on the settings page; all future Bailian
-    # plugins reuse the same dsh profile credentials.
-    #
-    # Config fields:
-    #   accessKeyId / accessKeySecret: fallback when not provided via UI.
-    #   consoleRegion: default region (cn-beijing).
-    #   consoleSite: domestic | international (default: domestic).
-    #   profile: bl config profile name (default: dsh).
-    - id: bailian-tokenplan-usage
-      name: bailian-cli-dsh/tokenplan-usage
-      config: {}
-
-    # Disabled by default: memory add/search are billed per call. Enable in
-    # the profile patch and configure API Key + parameters on the Bailian
-    # settings page. Calls DashScope memory v2 API directly (not bl memory)
-    # for full parameter control (min_score, enable_rerank, plan_version,
-    # memory_library_id, enable_judge, enable_rewrite).
-    - id: bailian-memory
-      name: bailian-cli-dsh/memory
-      disabled: true
-      config:
-        baseUrl: "https://dashscope.aliyuncs.com/api/v2/apps/memory/"
-        planVersion: "lite"
-        topK: 10
-        autoInject: true
-        autoPersist: true

packages/dsh/package.json

@@ -1,102 +0,0 @@
-{
-  "name": "bailian-cli-dsh",
-  "version": "1.14.2",
-  "description": "Aliyun Model Studio (Bailian) plugin bundle for DeepSeek Harness (dsh): TokenPlan LLM provider and personal-edition TokenPlan usage display in the webui.",
-  "homepage": "https://bailian.console.aliyun.com/cli",
-  "bugs": {
-    "url": "https://github.com/modelstudioai/cli/issues"
-  },
-  "license": "Apache-2.0",
-  "author": "Aliyun Model Studio",
-  "repository": {
-    "type": "git",
-    "url": "git+https://github.com/modelstudioai/cli.git",
-    "directory": "packages/dsh"
-  },
-  "files": [
-    "README.md",
-    "dist",
-    "client.bundle.js",
-    "cordis.patch.yml"
-  ],
-  "type": "module",
-  "types": "./dist/index.d.mts",
-  "exports": {
-    ".": {
-      "types": "./src/index.ts",
-      "default": "./dist/index.mjs"
-    },
-    "./tokenplan-usage": {
-      "types": "./src/tokenplan-usage/index.ts",
-      "default": "./dist/tokenplan-usage/index.mjs"
-    },
-    "./memory": {
-      "types": "./src/memory/index.ts",
-      "default": "./dist/memory/index.mjs"
-    },
-    "./client": "./client.bundle.js",
-    "./cordis.patch.yml": "./cordis.patch.yml",
-    "./package.json": "./package.json"
-  },
-  "publishConfig": {
-    "access": "public",
-    "exports": {
-      ".": "./dist/index.mjs",
-      "./tokenplan-usage": "./dist/tokenplan-usage/index.mjs",
-      "./memory": "./dist/memory/index.mjs",
-      "./client": "./client.bundle.js",
-      "./cordis.patch.yml": "./cordis.patch.yml",
-      "./package.json": "./package.json"
-    },
-    "registry": "https://registry.npmjs.org/"
-  },
-  "scripts": {
-    "build": "vp pack && node scripts/build-client.mjs",
-    "dev": "vp pack --watch",
-    "test": "vp test",
-    "check": "vp check"
-  },
-  "dependencies": {
-    "@deepseek-ai/schemastery": "^3.18.1"
-  },
-  "devDependencies": {
-    "@deepseek-ai/cordis": "^4.0.1",
-    "@deepseek-ai/dsh-agent": "^0.1.0-rc.6",
-    "@deepseek-ai/dsh-attachment": "^0.1.0-rc.6",
-    "@deepseek-ai/dsh-fs": "^0.1.0-rc.6",
-    "@deepseek-ai/dsh-launch-environment": "^0.1.0-rc.6",
-    "@deepseek-ai/dsh-llm": "^0.1.0-rc.6",
-    "@deepseek-ai/dsh-session": "^0.1.0-rc.6",
-    "@deepseek-ai/dsh-subagent": "^0.1.0-rc.6",
-    "@deepseek-ai/dsh-subprocess": "^0.1.0-rc.6",
-    "@deepseek-ai/dsh-tools": "^0.1.0-rc.6",
-    "@deepseek-ai/dsh-web": "^0.1.0-rc.6",
-    "@types/node": "catalog:",
-    "typescript": "^6.0.2",
-    "vite-plus": "catalog:"
-  },
-  "peerDependencies": {
-    "@deepseek-ai/cordis": "^4.0.1",
-    "@deepseek-ai/dsh-agent": "^0.1.0-rc.6",
-    "@deepseek-ai/dsh-attachment": "^0.1.0-rc.6",
-    "@deepseek-ai/dsh-fs": "^0.1.0-rc.6",
-    "@deepseek-ai/dsh-launch-environment": "^0.1.0-rc.6",
-    "@deepseek-ai/dsh-llm": "^0.1.0-rc.6",
-    "@deepseek-ai/dsh-session": "^0.1.0-rc.6",
-    "@deepseek-ai/dsh-subagent": "^0.1.0-rc.6",
-    "@deepseek-ai/dsh-subprocess": "^0.1.0-rc.6",
-    "@deepseek-ai/dsh-tools": "^0.1.0-rc.6",
-    "@deepseek-ai/dsh-web": "^0.1.0-rc.6"
-  },
-  "engines": {
-    "node": ">=22.19.0"
-  },
-  "dsh": {
-    "bundle": {
-      "patch": "./cordis.patch.yml"
-    },
-    "client": {
-      "platform": "web"
-    }
-  }
-}

packages/dsh/scripts/build-client.mjs

@@ -1,44 +0,0 @@
-/**
- * Build the browser client bundle in the DSH ModuleLoader closure format.
- *
- * The DSH web shell only loads client plugins that call
- * `window.__ModuleLoader__.load({ id, factory })`, resolving externals (react)
- * through the injected `require`. vite-plus emits plain ESM (wrong format), so
- * the client is built separately with esbuild: CJS + browser platform + react
- * external, wrapped in the ModuleLoader banner/footer.
- *
- * Run after `vp pack` (see package.json "build").
- */
-import { spawnSync } from "node:child_process";
-import { fileURLToPath } from "node:url";
-import { dirname, join } from "node:path";
-
-const pkgDir = dirname(dirname(fileURLToPath(import.meta.url)));
-const esbuild = join(pkgDir, "node_modules", ".bin", "esbuild");
-
-const banner =
-  'window.__ModuleLoader__.load({ id: "bailian-cli-dsh", factory: (require) => { ' +
-  "var module = { exports: {} }; var exports = module.exports;";
-const footer = "return module.exports; } });";
-
-const result = spawnSync(
-  esbuild,
-  [
-    "src/client.ts",
-    "--bundle",
-    "--format=cjs",
-    "--platform=browser",
-    "--external:react",
-    `--banner:js=${banner}`,
-    `--footer:js=${footer}`,
-    "--outfile=client.bundle.js",
-  ],
-  { cwd: pkgDir, stdio: "inherit" },
-);
-
-if (result.status !== 0) {
-  // Throw rather than process.exit: an uncaught top-level error still yields a
-  // non-zero exit (so `pnpm build` fails), and it carries esbuild's own status.
-  throw new Error(`build-client: esbuild failed with status ${result.status ?? "unknown"}`);
-}
-console.log("build-client: client.bundle.js (ModuleLoader format) written");

packages/dsh/src/features.ts

@@ -1,132 +0,0 @@
-/**
- * Bailian feature registry — single source of truth mapping a welcome-page
- * card to a **bailian-cli command**. The console-API knowledge lives in
- * bailian-cli (packages/commands); this bundle only shells out to `bl`, so a
- * feature added there is reusable here for free.
- *
- * Each entry is exposed two ways by the Host:
- * 1. a **model tool** `bailian_<id>` (natural-language entry: the LLM reads
- *    `intent` and calls the tool when the user asks in plain language);
- * 2. the **generic route** `POST /bailian/console { featureId }` (card-click
- *    entry: the client renders `summarize`/`data`).
- *
- * Adding a feature = (a) add a `bl` command in bailian-cli, (b) add one record
- * here. Tool + card come for free.
- *
- * Browser-safe (no node imports) so both the vite host build and the esbuild
- * client bundle can import it.
- *
- * @module bailian-cli-dsh/features
- */
-
-export interface BailianFeature {
-  /** Stable id; tool name is `bailian_<id>`. */
-  id: string;
-  /** Card title (matched against welcome cards). */
-  title: string;
-  /** Card description. */
-  desc: string;
-  /** Tool description: tells the LLM which user utterances should use it. */
-  intent: string;
-  /** Natural-language query sent into the conversation when the card is clicked. */
-  query: string;
-  /** `bl` command args (without `--output`); the Host appends `--output json`. */
-  argv: string[];
-  /** Args appended when the user supplies no params (e.g. ["--all"]). */
-  defaultArgs?: string[];
-  /** Optional params the LLM (or UI) may supply; mapped to bl flags. */
-  paramFlags?: FeatureParam[];
-  /** Human/LLM summary of the command's JSON output. */
-  summarize: (data: any) => string;
-}
-
-export interface FeatureParam {
-  /** Tool parameter name (LLM fills it). */
-  name: string;
-  /** bl flag it maps to (e.g. --model). */
-  flag: string;
-  type: "string" | "number" | "boolean";
-  description: string;
-}
-
-function pick(obj: any, ...keys: string[]): any {
-  for (const k of keys) if (obj && obj[k] !== undefined && obj[k] !== null) return obj[k];
-  return undefined;
-}
-function pct(v: any): string {
-  if (v === undefined || v === null) return "—";
-  const n = (typeof v === "number" ? v : Number(v)) * 100;
-  return (isNaN(n) ? 0 : n).toFixed(1) + "%";
-}
-
-export const FEATURES: BailianFeature[] = [
-  {
-    id: "free-tier",
-    title: "免费额度一键防护",
-    desc: "查询免费额度用量，一键开启「用完即停」，额度耗尽自动停止调用，不再产生意外扣费",
-    intent:
-      "查询百炼免费额度用量与『用完即停』防护状态。当用户提到免费额度、额度耗尽、意外扣费、用完即停、额度防护时使用。",
-    query: "帮我查看百炼免费额度用量，并告诉我怎么开启「用完即停」防护",
-    argv: ["usage", "freetier"],
-    defaultArgs: ["--all"],
-    paramFlags: [
-      {
-        name: "models",
-        flag: "--model",
-        type: "string",
-        description:
-          "逗号分隔的模型列表；不填则查询全部（--all）。若用户只关心特定模型且未说明，可先用 AskUserQuestion 询问。",
-      },
-    ],
-    summarize: (d) => {
-      if (!d || typeof d !== "object") return "未获取到免费额度数据。";
-      const list = pick(d, "quotas", "quotaList", "models", "list");
-      if (Array.isArray(list)) {
-        const lines = list.slice(0, 8).map((m: any) => {
-          const model = pick(m, "model", "modelName", "modelId") ?? "?";
-          const total = pick(m, "quotaTotal", "totalQuota", "total");
-          const used = pick(m, "quotaUsed", "usedQuota", "used");
-          const on = pick(m, "freeTierOnly");
-          return `- ${model}: 已用 ${used ?? "?"} / 共 ${total ?? "?"}${on !== undefined ? `，用完即停 ${on ? "开" : "关"}` : ""}`;
-        });
-        return lines.length
-          ? `免费额度:\n${lines.join("\n")}`
-          : "免费额度: " + JSON.stringify(d).slice(0, 300);
-      }
-      return "免费额度: " + JSON.stringify(d).slice(0, 300);
-    },
-  },
-  {
-    id: "usage",
-    title: "模型用量统计",
-    desc: "各模型/TokenPlan 的用量与百分比一次查清，自动生成用量分析",
-    intent:
-      "查询百炼 TokenPlan 个人版用量（5 小时/1 周窗口百分比、重置时间、套餐、用量包）。当用户问用量、用了多少、额度百分比、TokenPlan 使用情况时使用。",
-    query: "帮我查询百炼 TokenPlan 个人版用量（5 小时/1 周窗口、套餐与用量包）",
-    argv: ["token-plan", "personal-usage"],
-    summarize: (d) => {
-      if (!d || typeof d !== "object") return "未获取到用量数据。";
-      const u = d.usage ?? d;
-      const parts: string[] = [];
-      if (u.per5HourPercentage !== undefined)
-        parts.push(`5 小时窗口已用 ${pct(u.per5HourPercentage)}`);
-      if (u.per1WeekPercentage !== undefined)
-        parts.push(`1 周窗口已用 ${pct(u.per1WeekPercentage)}`);
-      const sub = d.subscription;
-      if (sub && sub.remainingDays !== undefined) parts.push(`套餐剩余 ${sub.remainingDays} 天`);
-      const add = d.addonSummary;
-      if (add && add.remainingCredits !== undefined)
-        parts.push(`用量包剩余 ${add.remainingCredits}/${add.totalCredits}`);
-      return parts.length
-        ? `TokenPlan 用量: ${parts.join("；")}`
-        : "用量: " + JSON.stringify(d).slice(0, 300);
-    },
-  },
-];
-
-export function featureById(id: string): BailianFeature | undefined {
-  return FEATURES.find((f) => f.id === id);
-}
-export function featureByTitle(title: string): BailianFeature | undefined {
-  return FEATURES.find((f) => f.title === title);
-}

packages/dsh/src/index.ts

@@ -1,20 +0,0 @@
-/**
- * bailian-cli-dsh — Aliyun Model Studio capabilities as a DeepSeek Harness
- * profile bundle. The package's substance is `cordis.patch.yml`, declared by
- * the `dsh.bundle.patch` manifest field and resolved by the profile composer.
- *
- * This root module is the no-op node half loaded by the `bailian-client` row
- * (whose purpose is to make `client-modules` serve the browser bundle
- * `client.bundle.js`). Cordis requires every row to resolve to a plugin with
- * an `apply` method, so this exports a minimal one. The real Host logic lives
- * in `./tokenplan-usage` and `./memory`; the browser UI lives in
- * `client.bundle.js`.
- *
- * @module bailian-cli-dsh
- */
-
-/** Cordis plugin name used by loader diagnostics. */
-export const name = "bailian-cli-dsh";
-
-/** No-op: this row exists only to serve the client bundle. */
-export function apply(): void {}

packages/dsh/src/memory/index.ts

@@ -1,621 +0,0 @@
-/**
- * `bailian-cli-dsh/memory` (Host half): cross-session long-term memory backed
- * by Bailian's hosted memory library (DashScope memory v2 API).
- *
- * Provides:
- * - Two model tools: `bailian_memory_search` (recall) + `bailian_memory_add`
- *   (store), plus `bailian_memory_list` (browse).
- * - Auto-inject: on the first turn of each session (or every turn if
- *   configured), search memory and inject relevant facts into context.
- * - Auto-persist: when a turn closes, send new user/assistant messages to
- *   the add API so future sessions can recall them.
- * - webServer routes for the Client settings page to configure memory
- *   parameters (apiKey, baseUrl, userId, planVersion, etc.).
- *
- * Calls go straight to DashScope rather than through `bl memory`, because
- * the v2 API exposes retrieval controls (`min_score`, `plan_version`,
- * `enable_rerank`, `memory_library_id`, `enable_judge`, `enable_rewrite`)
- * the CLI does not surface.
- *
- * BILLING: add and search are charged per call. `pro` costs ~50x `lite` per
- * search. The `enable_rerank` flag is what actually selects the billing tier
- * (verified: sending `plan_version: lite` alone still bills `pro`).
- *
- * @module bailian-cli-dsh/memory
- */
-import { userInfo } from "node:os";
-import type { Context } from "@deepseek-ai/cordis";
-import type { Agent, PreStepDecision } from "@deepseek-ai/dsh-agent";
-import type {} from "@deepseek-ai/dsh-agent";
-import type { ContentBlock, Message } from "@deepseek-ai/dsh-llm";
-import { createUserMessage } from "@deepseek-ai/dsh-llm";
-import { defineTool } from "@deepseek-ai/dsh-tools";
-import z from "@deepseek-ai/schemastery";
-import type { IncomingMessage, ServerResponse } from "node:http";
-import { isTokenPlanKey, tokenPlanKeyRejection } from "../shared/credentials.ts";
-import { dashScopeFetch } from "../shared/http.ts";
-
-/** Cordis plugin name used by loader diagnostics. */
-export const name = "bailian-memory";
-
-/** Seams this plugin registers into. */
-export const inject = ["tools", "agents", "webServer"];
-
-export interface Config {
-  /** DashScope API key (pay-as-you-go sk-ws-). Falls back to $DASHSCOPE_API_KEY. */
-  apiKey?: string;
-  /** Memory API base URL (default: https://dashscope.aliyuncs.com/api/v2/apps/memory/). */
-  baseUrl?: string;
-  /** Memory entity id. Falls back to $BAILIAN_MEMORY_USER_ID, then OS user. */
-  userId?: string;
-  /** Memory library id; defaults to the account default. */
-  memoryLibraryId?: string;
-  /** Memory extraction rule id. */
-  projectId?: string;
-  /** Profile template id; omitting skips profile extraction (and its cost). */
-  profileSchema?: string;
-  /** Search strategy; pro enables rerank at ~50x the cost. */
-  planVersion?: "lite" | "pro";
-  topK?: number;
-  minScore?: number;
-  /** Retrieve relevant memories and inject into the conversation. */
-  autoInject?: boolean;
-  /** Retrieve every turn instead of once per session. */
-  injectEveryTurn?: boolean;
-  /** Persist each turn's new messages when the turn closes. */
-  autoPersist?: boolean;
-}
-
-export const Config: z<Config> = z.object({
-  apiKey: z.string().role("secret").description("Pay-as-you-go DashScope API key (sk-)."),
-  baseUrl: z.string().description("Memory API base URL."),
-  userId: z.string().description("Memory entity id owning these memories."),
-  memoryLibraryId: z.string().description("Memory library id."),
-  projectId: z.string().description("Memory extraction rule id."),
-  profileSchema: z.string().description("Profile template id; enables profile extraction."),
-  planVersion: z.union(["lite", "pro"] as const).description("Search strategy; pro ~50x cost."),
-  topK: z.natural().description("Maximum memories to recall (1-100)."),
-  minScore: z.number().description("Minimum similarity score, 0-1."),
-  autoInject: z.boolean().description("Inject recalled memories automatically."),
-  injectEveryTurn: z.boolean().description("Retrieve every turn instead of once per session."),
-  autoPersist: z.boolean().description("Persist new messages when a turn closes."),
-});
-
-const DEFAULT_BASE_URL = "https://dashscope.aliyuncs.com/api/v2/apps/memory/";
-const DEFAULT_TOP_K = 10;
-const DEFAULT_PLAN_VERSION = "lite";
-
-const CONFIG_ROUTE = "/bailian/memory/config";
-const STATUS_ROUTE = "/bailian/memory/status";
-
-interface MemoryNode {
-  memory_node_id?: string;
-  content?: string;
-  event?: string;
-  old_content?: string;
-  created_at?: number;
-  updated_at?: number;
-  meta_data?: Record<string, unknown>;
-}
-
-interface MemoryResponse {
-  request_id?: string;
-  memory_nodes?: readonly MemoryNode[];
-  total?: number;
-  page_num?: number;
-  page_size?: number;
-  billing_plan?: string;
-}
-
-interface ChatTurn {
-  role: "user" | "assistant";
-  content: string;
-}
-
-/** Mutable runtime config — updated via webServer route, initialized from Cordis config. */
-interface MemoryRuntimeConfig {
-  apiKey: string | undefined;
-  baseUrl: string;
-  userId: string;
-  memoryLibraryId: string | undefined;
-  projectId: string | undefined;
-  profileSchema: string | undefined;
-  planVersion: "lite" | "pro";
-  topK: number;
-  minScore: number | undefined;
-  autoInject: boolean;
-  injectEveryTurn: boolean;
-  autoPersist: boolean;
-}
-
-/** Resolution order: explicit config, then env, then OS user. */
-function resolveUserId(ctx: Context, config: Config): string {
-  if (config.userId !== undefined && config.userId.length > 0) return config.userId;
-  const fromEnv = ctx.get("launchEnvironment")?.get("BAILIAN_MEMORY_USER_ID")?.value;
-  if (fromEnv !== undefined && fromEnv.length > 0) return fromEnv;
-  return userInfo().username;
-}
-
-function textOf(content: readonly ContentBlock[]): string {
-  return content
-    .filter((block): block is Extract<ContentBlock, { type: "text" }> => block.type === "text")
-    .map((block) => block.text)
-    .join("\n")
-    .trim();
-}
-
-/** Plain user/assistant exchanges; tool traffic and injected context are not memories. */
-function conversationTurns(messages: readonly Message[]): ChatTurn[] {
-  const turns: ChatTurn[] = [];
-  for (const message of messages) {
-    if (message.role !== "user" && message.role !== "assistant") continue;
-    if (message.role === "user" && message.source.kind !== "user") continue;
-    const text = textOf(message.content);
-    if (text.length > 0) turns.push({ role: message.role, content: text });
-  }
-  return turns;
-}
-
-/** Read a UTF-8 POST body up to a size limit. */
-function readJsonBody(req: IncomingMessage, maxBytes: number = 16384): Promise<unknown> {
-  return new Promise((resolve, reject) => {
-    const chunks: Buffer[] = [];
-    let total = 0;
-    req.on("data", (chunk: Buffer) => {
-      total += chunk.length;
-      if (total > maxBytes) {
-        req.destroy();
-        reject(new Error("body too large"));
-        return;
-      }
-      chunks.push(chunk);
-    });
-    req.on("end", () => {
-      const text = Buffer.concat(chunks).toString("utf8");
-      if (text.length === 0) return resolve({});
-      try {
-        resolve(JSON.parse(text));
-      } catch {
-        reject(new Error("invalid JSON"));
-      }
-    });
-    req.on("error", reject);
-  });
-}
-
-function sendJson(res: ServerResponse, status: number, data: unknown): void {
-  res.statusCode = status;
-  res.setHeader("Content-Type", "application/json; charset=utf-8");
-  res.end(JSON.stringify(data));
-}
-
-class MemoryClient {
-  constructor(
-    private readonly apiKey: string,
-    private readonly baseUrl: string,
-    private readonly cfg: MemoryRuntimeConfig,
-    private readonly userId: string,
-  ) {}
-
-  private shared(): Record<string, unknown> {
-    return {
-      user_id: this.userId,
-      ...(this.cfg.memoryLibraryId !== undefined
-        ? { memory_library_id: this.cfg.memoryLibraryId }
-        : {}),
-    };
-  }
-
-  async add(
-    messages: readonly ChatTurn[],
-    signal: AbortSignal | undefined,
-    overrides?: { customContent?: string; metaData?: Record<string, unknown> },
-  ): Promise<MemoryResponse> {
-    return dashScopeFetch<MemoryResponse>({
-      url: `${this.baseUrl}add`,
-      method: "POST",
-      apiKey: this.apiKey,
-      signal,
-      body: {
-        ...this.shared(),
-        ...(overrides?.customContent !== undefined
-          ? { custom_content: overrides.customContent }
-          : { messages }),
-        ...(this.cfg.projectId !== undefined ? { project_id: this.cfg.projectId } : {}),
-        ...(this.cfg.profileSchema !== undefined ? { profile_schema: this.cfg.profileSchema } : {}),
-        ...(overrides?.metaData !== undefined ? { meta_data: overrides.metaData } : {}),
-      },
-    });
-  }
-
-  async search(
-    messages: readonly ChatTurn[],
-    signal: AbortSignal | undefined,
-    overrides?: { topK?: number; minScore?: number; planVersion?: "lite" | "pro" },
-  ): Promise<MemoryResponse> {
-    const planVersion = overrides?.planVersion ?? this.cfg.planVersion ?? DEFAULT_PLAN_VERSION;
-    return dashScopeFetch<MemoryResponse>({
-      url: `${this.baseUrl}memory_nodes/search`,
-      method: "POST",
-      apiKey: this.apiKey,
-      signal,
-      body: {
-        ...this.shared(),
-        messages,
-        top_k: overrides?.topK ?? this.cfg.topK ?? DEFAULT_TOP_K,
-        ...((overrides?.minScore ?? this.cfg.minScore) !== undefined
-          ? { min_score: overrides?.minScore ?? this.cfg.minScore }
-          : {}),
-        // enable_rerank is what actually selects the billing tier (verified:
-        // plan_version alone still bills pro). Send both for safety.
-        enable_rerank: planVersion === "pro",
-        plan_version: planVersion,
-        ...(this.cfg.projectId !== undefined ? { project_ids: [this.cfg.projectId] } : {}),
-      },
-    });
-  }
-
-  async list(
-    signal: AbortSignal | undefined,
-    overrides?: { pageNum?: number; pageSize?: number },
-  ): Promise<MemoryResponse> {
-    const params = new URLSearchParams({
-      user_id: this.userId,
-      page_num: String(overrides?.pageNum ?? 1),
-      page_size: String(overrides?.pageSize ?? 10),
-      ...(this.cfg.memoryLibraryId !== undefined
-        ? { memory_library_id: this.cfg.memoryLibraryId }
-        : {}),
-    });
-    return dashScopeFetch<MemoryResponse>({
-      url: `${this.baseUrl}memory_nodes?${params.toString()}`,
-      method: "GET",
-      apiKey: this.apiKey,
-      signal,
-    });
-  }
-}
-
-function formatMemories(nodes: readonly MemoryNode[]): string {
-  const items = nodes
-    .map((node) => node.content?.trim())
-    .filter((content): content is string => content !== undefined && content.length > 0);
-  if (items.length === 0) return "";
-  return `What you remember about this user from earlier sessions:\n${items.map((item) => `- ${item}`).join("\n")}`;
-}
-
-/** Register model tools for deliberate memory operations. */
-function registerTools(ctx: Context, client: () => MemoryClient | undefined): void {
-  ctx.tools.register(
-    defineTool({
-      name: "bailian_memory_search",
-      description:
-        "Recall facts stored about this user in earlier sessions. Use when the user refers to prior context, preferences, or decisions you have no record of in this session.",
-      parameters: {
-        query: { type: "string", required: true, description: "What to recall." },
-        top_k: { type: "integer", description: "Maximum memories to return (1-100)." },
-        min_score: { type: "number", description: "Minimum similarity score, 0-1." },
-      },
-      output: {
-        schema: {
-          type: "object",
-          additionalProperties: false,
-          properties: {
-            memories: {
-              type: "array",
-              required: true,
-              items: {
-                type: "object",
-                additionalProperties: false,
-                properties: {
-                  id: { type: "string", required: true },
-                  content: { type: "string", required: true },
-                },
-              },
-            },
-          },
-        },
-        render: (_args, value) => [
-          {
-            type: "text",
-            text:
-              value.memories.length === 0
-                ? "No relevant memories."
-                : value.memories.map((m: any) => `- ${m.content}`).join("\n"),
-          },
-        ],
-      },
-      isConcurrencySafe: () => true,
-      async execute(args, exec) {
-        const mem = client();
-        if (mem === undefined)
-          throw new Error(
-            "bailian-memory: not configured. Set apiKey in the Bailian settings page or config.",
-          );
-        const result = await mem.search([{ role: "user", content: args.query }], exec.signal, {
-          ...(args.top_k !== undefined ? { topK: args.top_k } : {}),
-          ...(args.min_score !== undefined ? { minScore: args.min_score } : {}),
-        });
-        return {
-          memories: (result.memory_nodes ?? []).map((node) => ({
-            id: node.memory_node_id ?? "",
-            content: node.content ?? "",
-          })),
-        };
-      },
-    }),
-  );
-
-  ctx.tools.register(
-    defineTool({
-      name: "bailian_memory_add",
-      description:
-        "Store a durable fact about this user so later sessions can recall it. Use for stable preferences, decisions, and context — not for transient task state.",
-      parameters: {
-        content: { type: "string", required: true, description: "The fact to remember." },
-      },
-      output: {
-        schema: {
-          type: "object",
-          additionalProperties: false,
-          properties: { stored: { type: "integer", required: true } },
-        },
-        render: (_args, value) => [
-          { type: "text", text: `Stored ${value.stored} memory fragment(s).` },
-        ],
-      },
-      async execute(args, exec) {
-        const mem = client();
-        if (mem === undefined)
-          throw new Error(
-            "bailian-memory: not configured. Set apiKey in the Bailian settings page or config.",
-          );
-        const result = await mem.add([], exec.signal, { customContent: args.content });
-        return { stored: (result.memory_nodes ?? []).length };
-      },
-    }),
-  );
-
-  ctx.tools.register(
-    defineTool({
-      name: "bailian_memory_list",
-      description:
-        "List all stored memory fragments for this user. Use to review what the system already knows.",
-      parameters: {
-        page_size: { type: "integer", description: "Results per page (default 10)." },
-        page_num: { type: "integer", description: "Page number, starting from 1." },
-      },
-      output: {
-        schema: {
-          type: "object",
-          additionalProperties: false,
-          properties: {
-            memories: {
-              type: "array",
-              required: true,
-              items: {
-                type: "object",
-                additionalProperties: false,
-                properties: {
-                  id: { type: "string", required: true },
-                  content: { type: "string", required: true },
-                },
-              },
-            },
-            total: { type: "integer", required: true },
-          },
-        },
-        render: (_args, value) => [
-          {
-            type: "text",
-            text: `${value.total} memory fragment(s):\n${value.memories.map((m: any) => `- ${m.content}`).join("\n")}`,
-          },
-        ],
-      },
-      isConcurrencySafe: () => true,
-      async execute(args, exec) {
-        const mem = client();
-        if (mem === undefined) throw new Error("bailian-memory: not configured.");
-        const result = await mem.list(exec.signal, {
-          ...(args.page_size !== undefined ? { pageSize: args.page_size } : {}),
-          ...(args.page_num !== undefined ? { pageNum: args.page_num } : {}),
-        });
-        return {
-          memories: (result.memory_nodes ?? []).map((node) => ({
-            id: node.memory_node_id ?? "",
-            content: node.content ?? "",
-          })),
-          total: result.total ?? 0,
-        };
-      },
-    }),
-  );
-}
-
-/** Auto-inject (search on first turn) + auto-persist (add on turn end). */
-function registerAutoBehavior(
-  ctx: Context,
-  client: () => MemoryClient | undefined,
-  cfg: () => MemoryRuntimeConfig,
-): void {
-  const injectedSessions = new WeakSet<Agent>();
-  const persistedCursor = new WeakMap<Agent, number>();
-
-  const currentCfg = cfg();
-
-  if (currentCfg.autoInject !== false) {
-    ctx.on(
-      "agent/pre-step",
-      async (
-        {
-          agent,
-          messages,
-          signal,
-        }: { agent: Agent; messages: readonly Message[]; signal: AbortSignal },
-        next: () => Promise<PreStepDecision>,
-      ) => {
-        const decision = await next();
-        if (decision.kind !== "enter") return decision;
-        if (injectedSessions.has(agent) && currentCfg.injectEveryTurn !== true) return decision;
-
-        const query = textOf(messages.flatMap((m) => m.content));
-        if (query.length === 0) return decision;
-
-        const mem = client();
-        if (mem === undefined) return decision;
-
-        let nodes: readonly MemoryNode[] = [];
-        try {
-          const result = await mem.search([{ role: "user", content: query }], signal);
-          nodes = result.memory_nodes ?? [];
-        } catch {
-          return decision;
-        }
-
-        injectedSessions.add(agent);
-        if (nodes.length === 0) return decision;
-
-        const text = formatMemories(nodes);
-        return {
-          ...decision,
-          messages: [
-            ...decision.messages,
-            createUserMessage({
-              content: [{ type: "text", text }],
-              source: {
-                kind: "plugin",
-                plugin: name,
-                form: "snapshot",
-                sections: [{ name, text }],
-              },
-            }),
-          ],
-        };
-      },
-      { prepend: true },
-    );
-  }
-
-  if (currentCfg.autoPersist !== false) {
-    ctx.on(
-      "agent/turn-stopping",
-      async ({ agent, signal }: { agent: Agent; signal: AbortSignal }) => {
-        const mem = client();
-        if (mem === undefined) return;
-
-        const turns = conversationTurns(agent.session.deriveMessages());
-        const cursor = persistedCursor.get(agent) ?? 0;
-        const newTurns = turns.slice(cursor);
-        if (newTurns.length === 0) return;
-
-        persistedCursor.set(agent, turns.length);
-        try {
-          await mem.add(newTurns, signal);
-        } catch {
-          persistedCursor.set(agent, cursor);
-        }
-      },
-    );
-  }
-}
-
-export function apply(ctx: Context, config: Config): void {
-  const webServer = ctx.get("webServer");
-
-  // Mutable runtime config — initialized from Cordis config, updatable via webServer route.
-  let runtime: MemoryRuntimeConfig = {
-    apiKey: config.apiKey,
-    baseUrl: config.baseUrl ?? DEFAULT_BASE_URL,
-    userId: resolveUserId(ctx, config),
-    memoryLibraryId: config.memoryLibraryId,
-    projectId: config.projectId,
-    profileSchema: config.profileSchema,
-    planVersion: config.planVersion ?? DEFAULT_PLAN_VERSION,
-    topK: config.topK ?? DEFAULT_TOP_K,
-    minScore: config.minScore,
-    autoInject: config.autoInject ?? true,
-    injectEveryTurn: config.injectEveryTurn ?? false,
-    autoPersist: config.autoPersist ?? true,
-  };
-
-  /** Build a MemoryClient from the current runtime config, or undefined if no API key. */
-  function buildClient(): MemoryClient | undefined {
-    if (runtime.apiKey === undefined || runtime.apiKey.length === 0) return undefined;
-    if (isTokenPlanKey(runtime.apiKey)) {
-      throw new Error(tokenPlanKeyRejection(name, "the memory API"));
-    }
-    return new MemoryClient(runtime.apiKey, runtime.baseUrl, runtime, runtime.userId);
-  }
-
-  // Register tools + auto behavior.
-  registerTools(ctx, buildClient);
-  registerAutoBehavior(ctx, buildClient, () => runtime);
-
-  // webServer routes for the Client settings page.
-  if (webServer !== undefined) {
-    ctx.effect(() =>
-      webServer.register({
-        kind: "exact",
-        path: STATUS_ROUTE,
-        handler: async (_req: IncomingMessage, res: ServerResponse) => {
-          sendJson(res, 200, {
-            configured: runtime.apiKey !== undefined && runtime.apiKey.length > 0,
-            userId: runtime.userId,
-            baseUrl: runtime.baseUrl,
-            planVersion: runtime.planVersion,
-            topK: runtime.topK,
-            autoInject: runtime.autoInject,
-            injectEveryTurn: runtime.injectEveryTurn,
-            autoPersist: runtime.autoPersist,
-            memoryLibraryId: runtime.memoryLibraryId,
-          });
-        },
-      }),
-    );
-
-    ctx.effect(() =>
-      webServer.register({
-        kind: "exact",
-        path: CONFIG_ROUTE,
-        handler: async (req: IncomingMessage, res: ServerResponse) => {
-          if (req.method !== "POST") {
-            sendJson(res, 405, { error: "use POST" });
-            return;
-          }
-          let body: Record<string, unknown>;
-          try {
-            body = (await readJsonBody(req)) as Record<string, unknown>;
-          } catch (error) {
-            sendJson(res, 400, { error: error instanceof Error ? error.message : "bad request" });
-            return;
-          }
-
-          // Update mutable fields from the request body.
-          if (typeof body.apiKey === "string") runtime.apiKey = body.apiKey || undefined;
-          if (typeof body.baseUrl === "string" && body.baseUrl.length > 0)
-            runtime.baseUrl = body.baseUrl;
-          if (typeof body.userId === "string" && body.userId.length > 0)
-            runtime.userId = body.userId;
-          if (typeof body.memoryLibraryId === "string")
-            runtime.memoryLibraryId = body.memoryLibraryId || undefined;
-          if (typeof body.projectId === "string") runtime.projectId = body.projectId || undefined;
-          if (typeof body.profileSchema === "string")
-            runtime.profileSchema = body.profileSchema || undefined;
-          if (body.planVersion === "lite" || body.planVersion === "pro")
-            runtime.planVersion = body.planVersion;
-          if (typeof body.topK === "number") runtime.topK = body.topK;
-          if (typeof body.minScore === "number") runtime.minScore = body.minScore;
-          if (typeof body.autoInject === "boolean") runtime.autoInject = body.autoInject;
-          if (typeof body.injectEveryTurn === "boolean")
-            runtime.injectEveryTurn = body.injectEveryTurn;
-          if (typeof body.autoPersist === "boolean") runtime.autoPersist = body.autoPersist;
-
-          sendJson(res, 200, {
-            ok: true,
-            configured: runtime.apiKey !== undefined && runtime.apiKey.length > 0,
-          });
-        },
-      }),
-    );
-  }
-}

packages/dsh/src/shared/bl.ts

@@ -1,161 +0,0 @@
-/**
- * Shared `bl` invocation for the plugins that delegate to the Bailian CLI
- * rather than calling DashScope directly — the ones whose CLI implementation
- * carries real substance (async task polling, artifact download, SSE session
- * streaming, `agents.yaml` resolution) that a plugin should not restate.
- * @module bailian-cli-dsh/shared/bl
- */
-import type { Context } from "@deepseek-ai/cordis";
-import type { SubprocessSpawnSpec } from "@deepseek-ai/dsh-subprocess";
-import { launchEnvironmentOf } from "@deepseek-ai/dsh-launch-environment";
-
-const DEFAULT_STDOUT_MAX_BYTES = 4 * 1024 * 1024;
-const DEFAULT_STDERR_MAX_BYTES = 64 * 1024;
-const DEFAULT_GRACE_MS = 5_000;
-
-/**
- * Environment names `bl` reads for credentials, endpoint routing, and profile
- * selection. `scrubbedParentEnv()` strips credential-shaped names from every
- * harness child, so the key would never reach `bl` unless forwarded here.
- */
-const FORWARDED_ENV_NAMES = [
-  "DASHSCOPE_API_KEY",
-  "DASHSCOPE_BASE_URL",
-  "DASHSCOPE_TIMEOUT",
-  "BAILIAN_WORKSPACE_ID",
-  "BAILIAN_CONFIG_DIR",
-  "ALIBABA_CLOUD_ACCESS_KEY_ID",
-  "ALIBABA_CLOUD_ACCESS_KEY_SECRET",
-  "ALIBABA_CLOUD_SECURITY_TOKEN",
-] as const;
-
-/** A `bl` invocation that exited non-zero or produced unreadable output. */
-export class BlError extends Error {
-  constructor(
-    message: string,
-    readonly detail: { argv: readonly string[]; exitCode: number | null; stderr: string },
-    options?: { cause?: unknown },
-  ) {
-    super(message, options);
-    this.name = "BlError";
-  }
-}
-
-export interface RunBlOptions {
-  /** Working directory for the child; callers pass the session cwd. */
-  cwd: string;
-  signal: AbortSignal;
-  /** Extra entries layered after the forwarded Bailian names. */
-  env?: NodeJS.ProcessEnv;
-  stdoutMaxBytes?: number;
-  graceMs?: number;
-}
-
-export interface BlOutcome {
-  stdout: string;
-  stderr: string;
-  exitCode: number | null;
-  terminatedBy: NodeJS.Signals | null;
-}
-
-function abortError(): DOMException {
-  return new DOMException("bl invocation aborted", "AbortError");
-}
-
-function forwardedEnv(ctx: Context, extra: NodeJS.ProcessEnv | undefined): NodeJS.ProcessEnv {
-  const launchEnvironment = launchEnvironmentOf(ctx);
-  const env: NodeJS.ProcessEnv = {};
-  for (const name of FORWARDED_ENV_NAMES) {
-    const entry = launchEnvironment.get(name);
-    if (entry !== undefined) env[name] = entry.value;
-  }
-  return { ...env, ...extra };
-}
-
-/**
- * Run `bl` to completion and collect its output.
- * @throws {BlError} when the executable cannot be resolved.
- * @throws {DOMException} `AbortError` when the caller's signal fires.
- */
-export async function runBl(
-  ctx: Context,
-  argv: readonly string[],
-  options: RunBlOptions,
-): Promise<BlOutcome> {
-  if (options.signal.aborted) throw abortError();
-
-  const env = forwardedEnv(ctx, options.env);
-  let executable: string;
-  try {
-    executable = await ctx.subprocess.resolveExecutable(
-      "bl",
-      env as Readonly<Record<string, string>>,
-      options.signal,
-    );
-  } catch (error) {
-    throw new BlError(
-      "the `bl` executable was not found on PATH; install it with `npm install -g bailian-cli`",
-      { argv, exitCode: null, stderr: "" },
-      { cause: error },
-    );
-  }
-
-  const spec: SubprocessSpawnSpec = {
-    argv: [executable, ...argv],
-    cwd: options.cwd,
-    stdio: {
-      stdin: "ignore",
-      stdout: { maxBytes: options.stdoutMaxBytes ?? DEFAULT_STDOUT_MAX_BYTES },
-      stderr: { maxBytes: DEFAULT_STDERR_MAX_BYTES },
-    },
-    graceMs: options.graceMs ?? DEFAULT_GRACE_MS,
-    signal: options.signal,
-    env,
-  };
-
-  const handle = ctx.subprocess.spawn(spec);
-  if (options.signal.aborted) throw abortError();
-
-  const outcome = await handle.done;
-  if (options.signal.aborted) throw abortError();
-
-  return {
-    stdout: handle.collected.stdout?.readFrom(0).text ?? "",
-    stderr: handle.collected.stderr?.readFrom(0).text ?? "",
-    exitCode: outcome.exitCode,
-    terminatedBy: outcome.signal,
-  };
-}
-
-/**
- * Run `bl … --output json` and parse stdout.
- * @throws {BlError} on non-zero exit or unparseable stdout.
- */
-export async function runBlJson<T>(
-  ctx: Context,
-  argv: readonly string[],
-  options: RunBlOptions,
-): Promise<T> {
-  const withJson = [...argv, "--output", "json"];
-  const outcome = await runBl(ctx, withJson, options);
-
-  if (outcome.exitCode !== 0) {
-    // bl passes service errors through verbatim; surface them unchanged.
-    const reason = outcome.stderr.trim() || outcome.stdout.trim() || "no diagnostics on stderr";
-    throw new BlError(`bl ${argv.join(" ")} failed: ${reason}`, {
-      argv: withJson,
-      exitCode: outcome.exitCode,
-      stderr: outcome.stderr,
-    });
-  }
-
-  try {
-    return JSON.parse(outcome.stdout) as T;
-  } catch (error) {
-    throw new BlError(
-      `bl ${argv.join(" ")} did not emit JSON on stdout`,
-      { argv: withJson, exitCode: outcome.exitCode, stderr: outcome.stderr },
-      { cause: error },
-    );
-  }
-}

packages/dsh/src/shared/credentials.ts

@@ -1,93 +0,0 @@
-/**
- * Pure credential classification and pairing shared by the plugins that call
- * pay-as-you-go DashScope APIs directly (memory, knowledge base) or through
- * `bl managed-agent` (agentstudio). No runtime imports — this module is safe
- * to load from tests and its rules are locked by `tests/credentials.test.ts`.
- *
- * TokenPlan keys (`sk-sp-`) and pay-as-you-go keys (`sk-ws-`) are not
- * interchangeable: the TokenPlan gateway 401s a pay-as-you-go key, and the
- * service APIs this package calls 401 or 404 a TokenPlan key. The LLM
- * provider row keeps its TokenPlan key under a dedicated env name
- * (`BAILIAN_TOKENPLAN_API_KEY`); every other plugin needs a pay-as-you-go key
- * and rejects a TokenPlan one up front instead of failing at request time.
- *
- * @module bailian-cli-dsh/shared/credentials
- */
-
-/**
- * Standard DashScope model-domain endpoint. It serves the model APIs plus the
- * memory v2 and knowledge indices the plugins call directly — but NOT
- * `/api/v1/agentstudio`, which lives on the workspace-scoped host.
- */
-export const DASHSCOPE_DEFAULT_BASE_URL = "https://dashscope.aliyuncs.com";
-
-/** Key prefix that marks a TokenPlan key (which service APIs reject). */
-export const TOKEN_PLAN_KEY_PREFIX = "sk-sp-";
-
-/** Whether a key is shaped like a TokenPlan key (which service APIs reject). */
-export function isTokenPlanKey(apiKey: string): boolean {
-  return apiKey.startsWith(TOKEN_PLAN_KEY_PREFIX);
-}
-
-/**
- * Whether a base URL points at the TokenPlan gateway. That gateway serves the
- * model-inference routes only — none of the service APIs this package calls,
- * including `/api/v1/agentstudio`, so requests to it 404.
- */
-export function isTokenPlanEndpoint(baseUrl: string): boolean {
-  try {
-    return new URL(baseUrl).hostname.startsWith("token-plan.");
-  } catch {
-    // An unparseable URL fails the request later with its own diagnostics;
-    // this check only classifies well-formed endpoints.
-    return false;
-  }
-}
-
-/**
- * The standard error wording every plugin uses when it resolves a TokenPlan
- * key, so all three surfaces fail with one recognizable, actionable message.
- */
-export function tokenPlanKeyRejection(plugin: string, capability: string): string {
-  return (
-    `${plugin}: the resolved API key is a TokenPlan key (${TOKEN_PLAN_KEY_PREFIX}…), which ` +
-    `${capability} rejects. Use a pay-as-you-go key (sk-ws-): set \`apiKey\` in this row's ` +
-    "config or $DASHSCOPE_API_KEY. TokenPlan keys belong on $BAILIAN_TOKENPLAN_API_KEY, " +
-    "which only the `bailian-tokenplan` LLM provider reads."
-  );
-}
-
-/**
- * Build the `--api-key` / `--base-url` flags handed to `bl managed-agent run`.
- * Each resolved half ships independently:
- *
- * - A resolved key becomes `--api-key`, overriding bl's auth chain so an
- *   active TokenPlan profile cannot substitute its own key.
- * - A resolved endpoint becomes `--base-url`, overriding the ACTIVE PROFILE's
- *   base_url — the half that fixes the classic `Bailian API 404`, where a
- *   TokenPlan (or bare model-domain) origin does not serve
- *   `/api/v1/agentstudio`.
- *
- * There is deliberately NO fallback endpoint: agentstudio is only served on
- * the workspace-scoped host (see {@link workspaceEndpoint}), and an unknown
- * workspace is a configuration gap, not a defaultable value. Unresolved halves
- * emit nothing and bl's own auth chain decides them.
- */
-export function credentialFlags(apiKey: string | undefined, baseUrl: string | undefined): string[] {
-  const flags: string[] = [];
-  if (baseUrl !== undefined && baseUrl.length > 0) flags.push("--base-url", baseUrl);
-  if (apiKey !== undefined && apiKey.length > 0) flags.push("--api-key", apiKey);
-  return flags;
-}
-
-/**
- * Compose the workspace-scoped agentstudio host for a workspace id. The
- * managed-agent API is served only from
- * `https://{workspace}.cn-beijing.maas.aliyuncs.com/api/v1/agentstudio`
- * (bl/the SDK append the resource path onto this origin); the plain
- * dashscope origin 404s it, and a key only unlocks its own workspace's host
- * (a mismatched one 403s `Endpoint.AccessDenied`).
- */
-export function workspaceEndpoint(workspaceId: string): string {
-  return `https://${workspaceId}.cn-beijing.maas.aliyuncs.com`;
-}

packages/dsh/src/shared/http.ts

@@ -1,101 +0,0 @@
-/**
- * Direct DashScope HTTP for the plugins whose CLI counterpart does not expose
- * the full parameter surface (long-term memory, knowledge-base retrieval).
- * Service errors pass through verbatim — this layer classifies nothing.
- * @module bailian-cli-dsh/shared/http
- */
-import type { Context } from "@deepseek-ai/cordis";
-import { launchEnvironmentOf } from "@deepseek-ai/dsh-launch-environment";
-import { DASHSCOPE_DEFAULT_BASE_URL } from "./credentials.ts";
-
-export { DASHSCOPE_DEFAULT_BASE_URL } from "./credentials.ts";
-
-/** A non-2xx DashScope response, carrying the server's own wording. */
-export class DashScopeError extends Error {
-  constructor(
-    message: string,
-    readonly detail: { status: number; code?: string; requestId?: string },
-    options?: { cause?: unknown },
-  ) {
-    super(message, options);
-    this.name = "DashScopeError";
-  }
-}
-
-/**
- * Resolve the DashScope key: explicit row config first, then the launch
- * environment (process env, project `.env`, harness-home `.env`). Callers
- * that get `undefined` decide their own failure mode — opt-in plugins reject
- * at boot, the managed-agent tool falls through to bl's own auth chain.
- */
-export function resolveApiKey(ctx: Context, explicit?: string): string | undefined {
-  if (explicit !== undefined && explicit.length > 0) return explicit;
-  const entry = launchEnvironmentOf(ctx).get("DASHSCOPE_API_KEY");
-  return entry !== undefined && entry.value.length > 0 ? entry.value : undefined;
-}
-
-export function resolveBaseUrl(ctx: Context, explicit?: string): string {
-  if (explicit !== undefined && explicit.length > 0) return explicit;
-  const entry = launchEnvironmentOf(ctx).get("DASHSCOPE_BASE_URL");
-  return entry !== undefined && entry.value.length > 0 ? entry.value : DASHSCOPE_DEFAULT_BASE_URL;
-}
-
-export interface DashScopeRequest {
-  url: string;
-  method: "GET" | "POST" | "PATCH" | "DELETE";
-  apiKey: string;
-  body?: unknown;
-  signal?: AbortSignal | undefined;
-}
-
-interface DashScopeErrorBody {
-  code?: string;
-  message?: string;
-  request_id?: string;
-  error?: { code?: string; message?: string };
-}
-
-/**
- * Issue one DashScope request and parse its JSON body.
- * @throws {DashScopeError} on a non-2xx response or an unreadable body.
- */
-export async function dashScopeFetch<T>(request: DashScopeRequest): Promise<T> {
-  const response = await fetch(request.url, {
-    method: request.method,
-    headers: {
-      Authorization: `Bearer ${request.apiKey}`,
-      "Content-Type": "application/json",
-    },
-    ...(request.body !== undefined ? { body: JSON.stringify(request.body) } : {}),
-    ...(request.signal !== undefined ? { signal: request.signal } : {}),
-    redirect: "error",
-  });
-
-  const text = await response.text();
-
-  if (!response.ok) {
-    let parsed: DashScopeErrorBody = {};
-    try {
-      parsed = JSON.parse(text) as DashScopeErrorBody;
-    } catch {
-      // A non-JSON error body is still worth surfacing as-is.
-    }
-    const code = parsed.code ?? parsed.error?.code;
-    const message = parsed.message ?? parsed.error?.message ?? text.trim();
-    throw new DashScopeError(message.length > 0 ? message : `HTTP ${response.status}`, {
-      status: response.status,
-      ...(code !== undefined ? { code } : {}),
-      ...(parsed.request_id !== undefined ? { requestId: parsed.request_id } : {}),
-    });
-  }
-
-  try {
-    return JSON.parse(text) as T;
-  } catch (error) {
-    throw new DashScopeError(
-      "DashScope returned a non-JSON success body",
-      { status: response.status },
-      { cause: error },
-    );
-  }
-}

packages/dsh/src/tokenplan-usage/index.ts

@@ -1,423 +0,0 @@
-/**
- * `bailian-cli-dsh/tokenplan-usage` (Host half): provides two webServer
- * routes for the Client's "Bailian" settings page:
- *
- * 1. `POST /api/bailian/credentials` — saves AK/SK to the dedicated `dsh`
- *    bl profile via `bl auth login --open-api --config dsh`. This generates
- *    a fresh access_token and stores AK/SK + token in the profile. All
- *    subsequent console calls read this profile.
- *
- * 2. `POST /api/bailian/tokenplan/usage` — fetches personal-edition
- *    TokenPlan usage (3 console APIs) using the `dsh` profile credentials.
- *    Takes only `{ region, site }`; AK/SK are already saved in the profile.
- *
- * Configuration UX: users save AK/SK once on the settings page. All future
- * Bailian plugins reuse the same `dsh` profile credentials.
- *
- * @module bailian-cli-dsh/tokenplan-usage
- */
-import type { Context } from "@deepseek-ai/cordis";
-import type { IncomingMessage, ServerResponse } from "node:http";
-import { runBl } from "../shared/bl.ts";
-import { defineTool } from "@deepseek-ai/dsh-tools";
-import type { JsonValue } from "@deepseek-ai/dsh-session";
-import { FEATURES, featureById, type FeatureParam } from "../features.ts";
-import z from "@deepseek-ai/schemastery";
-
-/** Cordis plugin name used by loader diagnostics. */
-export const name = "bailian-tokenplan-usage";
-
-/** Hard deps: bl via subprocess; routes need webServer; feature tools need tools. */
-export const inject = ["subprocess", "webServer", "tools"];
-
-export interface Config {
-  /** Alibaba Cloud Access Key ID. Fallback when not provided via UI. */
-  accessKeyId?: string;
-  /** Alibaba Cloud Access Key Secret. Fallback when not provided via UI. */
-  accessKeySecret?: string;
-  /** Console gateway region (default: cn-beijing). */
-  consoleRegion?: string;
-  /** Console site: domestic or international (default: domestic). */
-  consoleSite?: "domestic" | "international";
-  /** Dedicated bl config profile name (default: dsh). */
-  profile?: string;
-}
-
-export const Config = z.object({
-  accessKeyId: z.string().description("Alibaba Cloud Access Key ID (fallback)."),
-  accessKeySecret: z.string().description("Alibaba Cloud Access Key Secret (fallback)."),
-  consoleRegion: z.string().description("Console gateway region (default: cn-beijing)."),
-  consoleSite: z.string().description("Console site: domestic or international."),
-  profile: z.string().description("Dedicated bl config profile name (default: dsh)."),
-});
-
-/** Personal-edition console API names (from bailian-tokenplan frontend). */
-const PERSONAL_USAGE_API = "zeldaHttp.apikeyMgr./tokenplan/personal/api/v2/usage";
-const PERSONAL_SUBSCRIPTION_API = "zeldaHttp.apikeyMgr./tokenplan/personal/api/v2/subscription";
-const PERSONAL_ADDON_SUMMARY_API = "zeldaHttp.apikeyMgr./tokenplan/personal/api/v2/addon/summary";
-
-const PERSONAL_SUB_COMMODITY_CN = "sfm_tokenplansolo_public_cn";
-const PERSONAL_SUB_COMMODITY_INTL = "sfm_tokenplansolo_public_intl";
-const PERSONAL_ADDON_COMMODITY_CN = "sfm_tokenplansoloaddon_public_cn";
-const PERSONAL_ADDON_COMMODITY_INTL = "sfm_tokenplansoloaddon_public_intl";
-
-const CREDENTIALS_ROUTE = "/bailian/credentials";
-const USAGE_ROUTE = "/bailian/tokenplan/usage";
-const CONSOLE_ROUTE = "/bailian/console";
-const BL_LOGIN_TIMEOUT_MS = 30_000;
-const BL_CALL_TIMEOUT_MS = 90_000;
-const BL_LOGIN_GRACE_MS = 20_000;
-const BL_CALL_GRACE_MS = 60_000;
-const DEFAULT_PROFILE = "dsh";
-
-interface FetchResult {
-  usage: unknown;
-  subscription: unknown;
-  addonSummary: unknown;
-  errors: Array<{ api: string; message: string }>;
-}
-
-/** Extract the business payload from a console gateway response. */
-function extractData(response: unknown): unknown {
-  if (response === null || typeof response !== "object") return response;
-  const outer = (response as Record<string, unknown>).data;
-  if (outer !== null && typeof outer === "object") {
-    const dataV2 = (outer as Record<string, unknown>).DataV2;
-    if (dataV2 !== null && typeof dataV2 === "object") {
-      const inner = (dataV2 as Record<string, unknown>).data;
-      if (inner !== null && typeof inner === "object") {
-        const payload = (inner as Record<string, unknown>).data;
-        if (payload !== undefined) return payload;
-        return inner;
-      }
-    }
-    const fallback = (outer as Record<string, unknown>).data;
-    if (fallback !== undefined) return fallback;
-  }
-  return response;
-}
-
-/** Read a UTF-8 POST body up to a size limit. */
-function readJsonBody(req: IncomingMessage, maxBytes: number = 8192): Promise<unknown> {
-  return new Promise((resolve, reject) => {
-    const chunks: Buffer[] = [];
-    let total = 0;
-    req.on("data", (chunk: Buffer) => {
-      total += chunk.length;
-      if (total > maxBytes) {
-        req.destroy();
-        reject(new Error("request body too large"));
-        return;
-      }
-      chunks.push(chunk);
-    });
-    req.on("end", () => {
-      const text = Buffer.concat(chunks).toString("utf8");
-      if (text.length === 0) return resolve({});
-      try {
-        resolve(JSON.parse(text));
-      } catch {
-        reject(new Error("invalid JSON body"));
-      }
-    });
-    req.on("error", reject);
-  });
-}
-
-/** Send a JSON response with a status code. */
-function sendJson(res: ServerResponse, status: number, data: unknown): void {
-  res.statusCode = status;
-  res.setHeader("Content-Type", "application/json; charset=utf-8");
-  res.end(JSON.stringify(data));
-}
-
-export function apply(ctx: Context, config: Config): void {
-  const webServer = ctx.get("webServer");
-  if (webServer === undefined) return;
-
-  const profile = config.profile || DEFAULT_PROFILE;
-
-  /** Save AK/SK to the dsh profile (bl auth login --open-api --config dsh). */
-  async function saveCredentials(accessKeyId: string, accessKeySecret: string): Promise<void> {
-    const loginArgs = [
-      "auth",
-      "login",
-      "--open-api",
-      "--config",
-      profile,
-      "--access-key-id",
-      accessKeyId,
-      "--access-key-secret",
-      accessKeySecret,
-    ];
-    const loginOutcome = await runBl(ctx, loginArgs, {
-      cwd: process.cwd(),
-      signal: AbortSignal.timeout(BL_LOGIN_TIMEOUT_MS),
-      graceMs: BL_LOGIN_GRACE_MS,
-    });
-    if (loginOutcome.exitCode !== 0) {
-      const reason =
-        loginOutcome.stderr.trim() || loginOutcome.stdout.trim() || `exit ${loginOutcome.exitCode}`;
-      throw new Error(`bl auth login failed: ${reason}`);
-    }
-  }
-
-  /** Call a console API using the dsh profile (credentials already saved). */
-  async function consoleCall(
-    region: string,
-    site: string,
-    api: string,
-    data: Record<string, unknown>,
-  ): Promise<unknown> {
-    const callArgs = [
-      "console",
-      "call",
-      "--config",
-      profile,
-      "--api",
-      api,
-      "--data",
-      JSON.stringify(data),
-      "--console-region",
-      region,
-      "--console-site",
-      site,
-      "--output",
-      "json",
-    ];
-    const callOutcome = await runBl(ctx, callArgs, {
-      cwd: process.cwd(),
-      signal: AbortSignal.timeout(BL_CALL_TIMEOUT_MS),
-      graceMs: BL_CALL_GRACE_MS,
-    });
-    if (callOutcome.exitCode !== 0) {
-      const reason =
-        callOutcome.stderr.trim() || callOutcome.stdout.trim() || `exit ${callOutcome.exitCode}`;
-      throw new Error(`bl console call failed (${api}): ${reason}`);
-    }
-    try {
-      return JSON.parse(callOutcome.stdout);
-    } catch {
-      return { raw: callOutcome.stdout };
-    }
-  }
-
-  /** Fetch all personal-edition TokenPlan usage (3 console calls). */
-  async function fetchUsage(region: string, site: string): Promise<FetchResult> {
-    const isIntl = site === "international";
-    const subCommodity = isIntl ? PERSONAL_SUB_COMMODITY_INTL : PERSONAL_SUB_COMMODITY_CN;
-    const addonCommodity = isIntl ? PERSONAL_ADDON_COMMODITY_INTL : PERSONAL_ADDON_COMMODITY_CN;
-
-    const errors: Array<{ api: string; message: string }> = [];
-    let usage = null;
-    let subscription = null;
-    let addonSummary = null;
-
-    try {
-      usage = extractData(await consoleCall(region, site, PERSONAL_USAGE_API, {}));
-    } catch (error) {
-      errors.push({
-        api: "usage",
-        message: error instanceof Error ? error.message : String(error),
-      });
-    }
-    try {
-      subscription = extractData(
-        await consoleCall(region, site, PERSONAL_SUBSCRIPTION_API, {
-          queryInstanceInfoRequest: { commodityCode: subCommodity },
-        }),
-      );
-    } catch (error) {
-      errors.push({
-        api: "subscription",
-        message: error instanceof Error ? error.message : String(error),
-      });
-    }
-    try {
-      addonSummary = extractData(
-        await consoleCall(region, site, PERSONAL_ADDON_SUMMARY_API, {
-          commodityCode: addonCommodity,
-        }),
-      );
-    } catch (error) {
-      errors.push({
-        api: "addonSummary",
-        message: error instanceof Error ? error.message : String(error),
-      });
-    }
-
-    return { usage, subscription, addonSummary, errors };
-  }
-
-  // Route 1: Save credentials to the dsh bl profile.
-  ctx.effect(() =>
-    webServer.register({
-      kind: "exact",
-      path: CREDENTIALS_ROUTE,
-      handler: async (req: IncomingMessage, res: ServerResponse) => {
-        if (req.method !== "POST") {
-          sendJson(res, 405, { error: "method not allowed, use POST" });
-          return;
-        }
-        let body: Record<string, unknown>;
-        try {
-          body = (await readJsonBody(req)) as Record<string, unknown>;
-        } catch (error) {
-          sendJson(res, 400, { error: error instanceof Error ? error.message : "bad request" });
-          return;
-        }
-        const accessKeyId = (body.accessKeyId as string) || config.accessKeyId;
-        const accessKeySecret = (body.accessKeySecret as string) || config.accessKeySecret;
-        if (!accessKeyId || !accessKeySecret) {
-          sendJson(res, 400, { error: "accessKeyId and accessKeySecret are required." });
-          return;
-        }
-        try {
-          await saveCredentials(accessKeyId, accessKeySecret);
-          sendJson(res, 200, { ok: true, profile });
-        } catch (error) {
-          sendJson(res, 500, { error: error instanceof Error ? error.message : "internal error" });
-        }
-      },
-    }),
-  );
-
-  // Route 2: Fetch TokenPlan usage using the dsh profile credentials.
-  ctx.effect(() =>
-    webServer.register({
-      kind: "exact",
-      path: USAGE_ROUTE,
-      handler: async (req: IncomingMessage, res: ServerResponse) => {
-        if (req.method !== "POST") {
-          sendJson(res, 405, { error: "method not allowed, use POST" });
-          return;
-        }
-        let body: Record<string, unknown>;
-        try {
-          body = (await readJsonBody(req)) as Record<string, unknown>;
-        } catch (error) {
-          sendJson(res, 400, { error: error instanceof Error ? error.message : "bad request" });
-          return;
-        }
-        // If AK/SK are provided in the body, save them first (auto-provision).
-        const bodyKeyId = (body.accessKeyId as string) || undefined;
-        const bodyKeySecret = (body.accessKeySecret as string) || undefined;
-        if (bodyKeyId && bodyKeySecret) {
-          try {
-            await saveCredentials(bodyKeyId, bodyKeySecret);
-          } catch (error) {
-            sendJson(res, 500, {
-              error: error instanceof Error ? error.message : "credential save failed",
-            });
-            return;
-          }
-        }
-        const region = (body.region as string) || config.consoleRegion || "cn-beijing";
-        const site = (body.site as string) || config.consoleSite || "domestic";
-        try {
-          const result = await fetchUsage(region, site);
-          sendJson(res, 200, result);
-        } catch (error) {
-          sendJson(res, 500, { error: error instanceof Error ? error.message : "internal error" });
-        }
-      },
-    }),
-  );
-
-  // ── Feature layer: reuse bailian-cli commands as model tools + a generic route ──
-
-  /** Run a feature's `bl` command with the dsh profile; returns parsed JSON. */
-  async function invokeFeature(
-    feature: (typeof FEATURES)[number],
-    params?: Record<string, unknown>,
-  ): Promise<JsonValue> {
-    const extra: string[] = [];
-    for (const pf of feature.paramFlags ?? []) {
-      const val = params?.[pf.name];
-      if (val !== undefined && val !== null && val !== "") extra.push(pf.flag, String(val));
-    }
-    if (extra.length === 0 && feature.defaultArgs) extra.push(...feature.defaultArgs);
-    const args = [...feature.argv, ...extra, "--config", profile, "--output", "json"];
-    const outcome = await runBl(ctx, args, {
-      cwd: process.cwd(),
-      signal: AbortSignal.timeout(BL_CALL_TIMEOUT_MS),
-      graceMs: BL_CALL_GRACE_MS,
-    });
-    if (outcome.exitCode !== 0) {
-      const reason = outcome.stderr.trim() || outcome.stdout.trim() || `exit ${outcome.exitCode}`;
-      throw new Error(`bl ${feature.argv.join(" ")} failed: ${reason}`);
-    }
-    try {
-      return JSON.parse(outcome.stdout);
-    } catch {
-      return { raw: outcome.stdout };
-    }
-  }
-
-  // Natural-language entry: one model tool per feature.
-  const tools = ctx.get("tools");
-  if (tools !== undefined) {
-    for (const feature of FEATURES) {
-      // Keep FeatureParam's literal `type` union: widening it to `string`
-      // makes the map unassignable to ParameterSchemaSpec.
-      const parameters: Record<string, { type: FeatureParam["type"]; description: string }> = {};
-      for (const pf of feature.paramFlags ?? []) {
-        parameters[pf.name] = { type: pf.type, description: pf.description };
-      }
-      ctx.effect(() =>
-        tools.register(
-          defineTool({
-            name: `bailian_${feature.id}`,
-            description: `${feature.title}。${feature.intent}`,
-            parameters,
-            output: {
-              schema: { type: "object", additionalProperties: true },
-              render: (_a, value) => [
-                { type: "text", text: String((value as any).summary ?? JSON.stringify(value)) },
-              ],
-            },
-            async execute(args) {
-              const data = await invokeFeature(feature, args as Record<string, unknown>);
-              return { summary: feature.summarize(data), data };
-            },
-          }),
-        ),
-      );
-    }
-  }
-
-  // Card-click entry: generic route dispatching to a feature by id.
-  ctx.effect(() =>
-    webServer.register({
-      kind: "exact",
-      path: CONSOLE_ROUTE,
-      handler: async (req: IncomingMessage, res: ServerResponse) => {
-        if (req.method !== "POST") {
-          sendJson(res, 405, { error: "method not allowed, use POST" });
-          return;
-        }
-        let body: Record<string, unknown>;
-        try {
-          body = (await readJsonBody(req)) as Record<string, unknown>;
-        } catch (error) {
-          sendJson(res, 400, { error: error instanceof Error ? error.message : "bad request" });
-          return;
-        }
-        const feature = featureById(String(body.featureId ?? ""));
-        if (feature === undefined) {
-          sendJson(res, 400, { error: `unknown featureId: ${String(body.featureId)}` });
-          return;
-        }
-        try {
-          const data = await invokeFeature(
-            feature,
-            body.params as Record<string, unknown> | undefined,
-          );
-          sendJson(res, 200, { summary: feature.summarize(data), data });
-        } catch (error) {
-          sendJson(res, 500, { error: error instanceof Error ? error.message : "internal error" });
-        }
-      },
-    }),
-  );
-}

packages/dsh/tests/credentials.test.ts

@@ -1,59 +0,0 @@
-import { expect, test } from "vite-plus/test";
-import {
-  credentialFlags,
-  DASHSCOPE_DEFAULT_BASE_URL,
-  isTokenPlanEndpoint,
-  isTokenPlanKey,
-  workspaceEndpoint,
-} from "../src/shared/credentials.ts";
-
-// 行为锁定:两类 Key(sk-sp- TokenPlan / sk-ws- 按量付费)不可混用。
-// TokenPlan 网关 401 按量付费 Key,TokenPlan 网关只提供模型推理,不提供
-// 服务 API。managed-agent 的凭证两半独立下发:解析出 key 就显式
-// --api-key(不让 bl 用活动 profile 的 key),解析出端点就显式 --base-url
-// (不让 bl 用活动 profile 的端点)。agentstudio 只在工作空间前缀主机上提供,
-// 因此绝不存在"默认端点"——工作空间未知就是配置缺口,该报错而不是猜。
-// 这些共享函数来自早期版本(vision / image / managed-agent 等工具),
-// 工具已移除但凭证分类逻辑保留作为参考。
-
-test("isTokenPlanKey classifies by prefix", () => {
-  expect(isTokenPlanKey("sk-sp-abc123")).toBe(true);
-  expect(isTokenPlanKey("sk-ws-abc123")).toBe(false);
-  expect(isTokenPlanKey("")).toBe(false);
-});
-
-test("isTokenPlanEndpoint classifies the gateway host", () => {
-  expect(isTokenPlanEndpoint("https://token-plan.cn-beijing.maas.aliyuncs.com")).toBe(true);
-  expect(
-    isTokenPlanEndpoint("https://token-plan.cn-beijing.maas.aliyuncs.com/compatible-mode/v1"),
-  ).toBe(true);
-  expect(isTokenPlanEndpoint(DASHSCOPE_DEFAULT_BASE_URL)).toBe(false);
-  expect(isTokenPlanEndpoint(workspaceEndpoint("llm-x"))).toBe(false);
-  // 不可解析的 URL 交给后续请求自己报错,这里只做形状分类。
-  expect(isTokenPlanEndpoint("not a url")).toBe(false);
-});
-
-test("workspaceEndpoint composes the workspace-scoped agentstudio host", () => {
-  expect(workspaceEndpoint("llm-kpgesh4vqzf5gzv9")).toBe(
-    "https://llm-kpgesh4vqzf5gzv9.cn-beijing.maas.aliyuncs.com",
-  );
-  expect(workspaceEndpoint("ws_abc")).toBe("https://ws_abc.cn-beijing.maas.aliyuncs.com");
-});
-
-test("credentialFlags: each resolved half ships independently, no defaults", () => {
-  expect(credentialFlags(undefined, undefined)).toEqual([]);
-  expect(credentialFlags("", "")).toEqual([]);
-  // 只有 key:端点留给 bl 解析,绝不塞一个会 404 的默认主机。
-  expect(credentialFlags("sk-ws-abc", undefined)).toEqual(["--api-key", "sk-ws-abc"]);
-  // 只有端点:也下发,key 留给 bl 的 auth chain。
-  expect(credentialFlags(undefined, "https://ws.example.com")).toEqual([
-    "--base-url",
-    "https://ws.example.com",
-  ]);
-  expect(credentialFlags("sk-ws-abc", "https://ws.example.com")).toEqual([
-    "--base-url",
-    "https://ws.example.com",
-    "--api-key",
-    "sk-ws-abc",
-  ]);
-});

packages/dsh/tsconfig.json

@@ -1,20 +0,0 @@
-{
-  "compilerOptions": {
-    "target": "esnext",
-    "lib": ["es2023"],
-    "moduleDetection": "force",
-    "module": "nodenext",
-    "moduleResolution": "nodenext",
-    "resolveJsonModule": true,
-    "types": ["node"],
-    "strict": true,
-    "noUnusedLocals": true,
-    "declaration": true,
-    "noEmit": true,
-    "allowImportingTsExtensions": true,
-    "esModuleInterop": true,
-    "isolatedModules": true,
-    "verbatimModuleSyntax": true,
-    "skipLibCheck": true
-  }
-}

packages/dsh/vite.config.ts

@@ -1,18 +0,0 @@
-import { defineConfig } from "vite-plus";
-
-export default defineConfig({
-  pack: {
-    entry: ["src/index.ts", "src/tokenplan-usage/index.ts", "src/memory/index.ts"],
-    minify: true,
-    dts: {
-      tsgo: true,
-    },
-  },
-  lint: {
-    options: {
-      typeAware: true,
-      typeCheck: true,
-    },
-  },
-  fmt: {},
-});

packages/kscli/package.json

@@ -1,6 +1,6 @@
 {
   "name": "knowledge-studio-cli",
-  "version": "1.14.2",
+  "version": "1.14.3",
   "description": "Lightweight RAG CLI for Aliyun Model Studio — focused on knowledge-base retrieval.",
   "keywords": [
     "alibaba-cloud",

packages/runtime/package.json

@@ -1,6 +1,6 @@
 {
   "name": "bailian-cli-runtime",
-  "version": "1.14.2",
+  "version": "1.14.3",
   "description": "Runtime framework for bailian-cli (createCli, registry, args, output, pipeline). See https://www.npmjs.com/package/bailian-cli for usage.",
   "homepage": "https://bailian.console.aliyun.com/cli",
   "bugs": {

packages/runtime/src/error-handler.ts

@@ -78,11 +78,12 @@ function fromFetchFailed(err: TypeError): BailianError {
   if (causeMsg && causeMsg !== code) detailParts.push(causeMsg);
   const detail = detailParts.length > 0 ? detailParts.join(": ") : "unknown cause";
 
+  // Prefer the errno (ENOTFOUND, …) so JSON toJSON() exposes cause.code for agents.
   return new BailianError(
     `Network request failed: ${detail}`,
     ExitCode.NETWORK,
     pickNetworkHint(code),
-    { cause: err },
+    { cause: cause ?? err },
   );
 }
 

packages/runtime/src/index.ts

@@ -42,7 +42,13 @@ export {
 // Output facilities consumed by commands
 export { emitResult, emitBare, emitRequestId } from "./output/output.ts";
 export { formatTable } from "./output/table.ts";
-export { renderBoxTable, type BoxTableOptions, type BarColumn } from "./output/box-table.ts";
+export {
+  renderBoxTable,
+  renderGauge,
+  type BoxTableOptions,
+  type BarColumn,
+  type GaugeCell,
+} from "./output/box-table.ts";
 export { createSpinner, createProgressBar } from "./output/progress.ts";
 export { printWelcomeBanner, printQuickStart } from "./output/banner.ts";
 export { maybeShowStatusBar } from "./output/status-bar.ts";

packages/runtime/src/output/box-table.ts

@@ -136,6 +136,26 @@ interface RenderedCell {
   colored: string;
 }
 
+/** A standalone gauge cell (bar + label) for non-table layouts, e.g. the usage quota box. */
+export interface GaugeCell {
+  plain: string;
+  colored: string;
+}
+
+/**
+ * Render a single gauge cell in the `usage free` table style: brand-cyan fill,
+ * transparent track, and a light-blue label after the bar. `percent` is 0-100;
+ * null renders an empty gauge with a neutral label.
+ */
+export function renderGauge(
+  percent: number | null,
+  label: string,
+  width: number = DEFAULT_BAR_WIDTH,
+  out: NodeJS.WriteStream = process.stdout,
+): GaugeCell {
+  return buildBarCell(percent, label, width, colorLevel(out));
+}
+
 function buildBarCell(
   percent: number | null,
   label: string,

packages/runtime/src/pipeline/steps/bl-api.ts

@@ -10,6 +10,11 @@ import {
   taskPath,
   speechSynthesizePath,
   speechRecognizePath,
+  resolveAsrApi,
+  buildAsrFlashRequest,
+  buildAsyncAsrLanguageFields,
+  collectAsrTranscriptionItems,
+  extractAsrFlashText,
   stripUndefined,
   resolveBooleanFlag,
   resolveWatermark,
@@ -23,6 +28,7 @@ import {
   type DashScopeTTSRequest,
   type DashScopeTTSResponse,
   type DashScopeASRRequest,
+  type DashScopeASRTaskResult,
   type ChatMessageContent,
   isLocalFile,
 } from "bailian-cli-core";
@@ -573,27 +579,103 @@ export async function speechRecognize(
     });
   }
 
+  const model = input.model || "fun-asr";
+  const route = resolveAsrApi(model);
+  if (route.kind === "unsupported") {
+    throw new PipelineError(
+      "invalid_input",
+      route.unsupportedReason ?? `Unsupported ASR model: ${model}`,
+      {
+        step: "speech/recognize",
+      },
+    );
+  }
+
+  if (route.kind === "sync-flash") {
+    if (rawUrls.length !== 1) {
+      throw new PipelineError(
+        "invalid_input",
+        `Model "${model}" is a sync Flash ASR model and accepts exactly one url (got ${rawUrls.length})`,
+        { step: "speech/recognize" },
+      );
+    }
+    const unsupportedFlags: string[] = [];
+    if (input.diarization) unsupportedFlags.push("diarization");
+    if (input["speaker-count"] !== undefined) unsupportedFlags.push("speaker-count");
+    // input-audio Flash supports vocabulary_id; qwen3 sync Flash does not
+    if (route.flashFamily === "qwen3" && input["vocabulary-id"] !== undefined) {
+      unsupportedFlags.push("vocabulary-id");
+    }
+    if (input["channel-id"] !== undefined) unsupportedFlags.push("channel-id");
+    if (unsupportedFlags.length > 0) {
+      throw new PipelineError(
+        "invalid_input",
+        `Model "${model}" uses sync Flash ASR and does not support: ${unsupportedFlags.join(", ")}`,
+        { step: "speech/recognize" },
+      );
+    }
+  }
+  if (
+    route.kind === "async-filetrans" &&
+    route.asyncInputStyle === "file_url" &&
+    rawUrls.length !== 1
+  ) {
+    throw new PipelineError(
+      "invalid_input",
+      `Model "${model}" accepts exactly one url (got ${rawUrls.length})`,
+      { step: "speech/recognize" },
+    );
+  }
+
   // Resolve local files to upload URLs
   const fileUrls: string[] = [];
-  for (const u of rawUrls) {
-    if (isLocalFile(u)) {
+  for (const audioUrl of rawUrls) {
+    if (isLocalFile(audioUrl)) {
       fileUrls.push(
-        await env.client.uploadFile(u, input.model || "fun-asr", {
+        await env.client.uploadFile(audioUrl, model, {
           signal: ctx.signal,
         }),
       );
     } else {
-      fileUrls.push(u);
+      fileUrls.push(audioUrl);
     }
   }
 
-  const model = input.model || "fun-asr";
+  if (route.kind === "sync-flash") {
+    const flashFamily = route.flashFamily!;
+    const body = buildAsrFlashRequest({
+      model,
+      audioUrl: fileUrls[0]!,
+      language: input.language,
+      vocabularyId: input["vocabulary-id"],
+      flashFamily,
+    });
+    const response = await env.client.requestJson<Record<string, unknown>>({
+      path: route.path,
+      method: "POST",
+      headers: { "X-DashScope-SSE": "disable" },
+      body,
+      signal: ctx.signal,
+    });
+    return {
+      text: extractAsrFlashText(response, flashFamily),
+      model,
+      mode: "sync",
+      raw: response,
+    };
+  }
+
+  const languageFields = buildAsyncAsrLanguageFields(
+    route.asyncLanguageStyle ?? "language_hints",
+    input.language,
+  );
   const body: DashScopeASRRequest = {
     model,
-    input: { file_urls: fileUrls },
+    input:
+      route.asyncInputStyle === "file_url" ? { file_url: fileUrls[0]! } : { file_urls: fileUrls },
     parameters: {
       channel_id: input["channel-id"] !== undefined ? [input["channel-id"]] : undefined,
-      language_hints: input.language ? [input.language] : undefined,
+      ...languageFields,
       diarization_enabled: input.diarization,
       speaker_count: input["speaker-count"],
       vocabulary_id: input["vocabulary-id"],
@@ -601,9 +683,8 @@ export async function speechRecognize(
   };
   stripUndefined(body.parameters as Record<string, unknown>);
 
-  const url = speechRecognizePath();
   const asyncResp = await env.client.requestJson<DashScopeAsyncResponse>({
-    path: url,
+    path: speechRecognizePath(),
     method: "POST",
     body,
     async: true,
@@ -614,7 +695,65 @@ export async function speechRecognize(
   const pollIntervalMs = (input["poll-interval"] ?? 2) * 1000;
   const timeoutMs = (ctx.timeoutSeconds ?? 300) * 1000;
 
-  return await pollTaskWithOptions(env, taskId, pollIntervalMs, timeoutMs, ctx);
+  // ASR polling reads original output, avoids generic flatten (avoids transcription_url polluting media urls)
+  const asrTask = await pollAsrTaskWithOptions(env, taskId, pollIntervalMs, timeoutMs, ctx);
+  const transcriptionItems = collectAsrTranscriptionItems(asrTask.output);
+
+  const base: Record<string, unknown> = {
+    task_id: asrTask.output.task_id,
+    task_status: asrTask.output.task_status,
+    request_id: asrTask.request_id,
+    mode: "async",
+    model,
+  };
+  if (asrTask.output.results) base.results = asrTask.output.results;
+  if (asrTask.output.result) {
+    base.result = asrTask.output.result;
+    if (typeof asrTask.output.result.transcription_url === "string") {
+      base.transcription_url = asrTask.output.result.transcription_url;
+    }
+  }
+  if (asrTask.output.task_metrics) base.task_metrics = asrTask.output.task_metrics;
+  if (asrTask.usage) base.usage = asrTask.usage;
+
+  if (transcriptionItems.length === 0) {
+    return base;
+  }
+
+  const texts: string[] = [];
+  const transcripts: Record<string, unknown>[] = [];
+  for (const item of transcriptionItems) {
+    if (!item.transcription_url) continue;
+    const transRes = await fetch(item.transcription_url, { signal: ctx.signal });
+    if (!transRes.ok) {
+      throw new PipelineError(
+        "async_task_failed",
+        `Failed to download transcription: HTTP ${transRes.status}`,
+        { step: "speech/recognize", details: { taskId, url: item.transcription_url } },
+      );
+    }
+    const transData = (await transRes.json()) as Record<string, unknown>;
+    transcripts.push(transData);
+    const transcriptList = transData.transcripts as
+      | Array<{ text?: string; sentences?: Array<{ text?: string }> }>
+      | undefined;
+    if (!transcriptList?.length) continue;
+    for (const transcript of transcriptList) {
+      if (transcript.sentences?.length) {
+        for (const sentence of transcript.sentences) {
+          if (sentence.text) texts.push(sentence.text);
+        }
+      } else if (transcript.text) {
+        texts.push(transcript.text);
+      }
+    }
+  }
+
+  return {
+    ...base,
+    text: texts.join("\n"),
+    transcripts,
+  };
 }
 
 // --- Shared: task polling ---
@@ -640,7 +779,7 @@ function flattenTaskResponse(resp: DashScopeTaskResponse): Record<string, unknow
     if (urls.length > 0) flat.urls = urls;
   }
   if (output.results) {
-    const urls = output.results.map((r) => r.url).filter(Boolean);
+    const urls = output.results.map((item) => item.url).filter(Boolean);
     if (urls.length > 0 && !flat.urls) flat.urls = urls;
   }
   if (output.task_metrics) flat.task_metrics = output.task_metrics;
@@ -658,13 +797,13 @@ async function pollTask(
   return await pollTaskWithOptions(env, taskId, pollIntervalMs, timeoutMs, ctx);
 }
 
-async function pollTaskWithOptions(
+async function pollUntilSucceeded(
   env: PipelineEnv,
   taskId: string,
   pollIntervalMs: number,
   timeoutMs: number,
   ctx?: StepContext,
-): Promise<Record<string, unknown>> {
+): Promise<DashScopeTaskResponse> {
   const started = Date.now();
   let attempt = 0;
 
@@ -687,7 +826,7 @@ async function pollTaskWithOptions(
     const status = result.output.task_status;
 
     if (status === "SUCCEEDED") {
-      return flattenTaskResponse(result);
+      return result;
     }
 
     if (status === "FAILED") {
@@ -718,6 +857,33 @@ async function pollTaskWithOptions(
   }
 }
 
+async function pollTaskWithOptions(
+  env: PipelineEnv,
+  taskId: string,
+  pollIntervalMs: number,
+  timeoutMs: number,
+  ctx?: StepContext,
+): Promise<Record<string, unknown>> {
+  return flattenTaskResponse(await pollUntilSucceeded(env, taskId, pollIntervalMs, timeoutMs, ctx));
+}
+
+/** ASR task polling: preserve original output (includes results[] / result.transcription_url). */
+async function pollAsrTaskWithOptions(
+  env: PipelineEnv,
+  taskId: string,
+  pollIntervalMs: number,
+  timeoutMs: number,
+  ctx?: StepContext,
+): Promise<DashScopeASRTaskResult> {
+  return (await pollUntilSucceeded(
+    env,
+    taskId,
+    pollIntervalMs,
+    timeoutMs,
+    ctx,
+  )) as DashScopeASRTaskResult;
+}
+
 function delay(ms: number, signal?: AbortSignal): Promise<void> {
   if (!signal) return new Promise((resolve) => setTimeout(resolve, ms));
   return new Promise((resolve, reject) => {

packages/runtime/src/registry.ts

@@ -25,6 +25,13 @@ interface CommandNode {
   children: Map<string, CommandNode>;
 }
 
+const AUTH_LABELS = {
+  apiKey: "API Key",
+  console: "Console",
+  openapi: "AK/SK",
+  none: "No Auth",
+} satisfies Record<AuthRequirement, string>;
+
 /**
  * What a command path resolves to in the registry. The single judgement that
  * feeds `resolve()` — no scattered `isGroupPath` + throwing `resolve`.
@@ -157,14 +164,37 @@ export class CommandRegistry {
     };
   }
 
-  private buildResourceLines(a: (s: string) => string, d: (s: string) => string): string {
-    const entries: Array<{ path: string; desc: string }> = [];
+  private buildCommandLines(
+    entries: Array<{ path: string; auth: AuthRequirement; desc: string }>,
+    accent: (text: string) => string,
+    dim: (text: string) => string,
+  ): string {
+    const maxPathLength = Math.max(...entries.map((entry) => entry.path.length));
+    const maxAuthLength = Math.max(
+      ...entries.map((entry) => `[${AUTH_LABELS[entry.auth]}]`.length),
+    );
+    const rows = entries.map((entry) => {
+      const authLabel = `[${AUTH_LABELS[entry.auth]}]`;
+      return `  ${accent(entry.path.padEnd(maxPathLength + 2))} ${accent(authLabel.padEnd(maxAuthLength + 2))} ${dim(entry.desc)}`;
+    });
+    return rows.join("\n");
+  }
+
+  private buildResourceLines(
+    accent: (text: string) => string,
+    dim: (text: string) => string,
+  ): string {
+    const entries: Array<{ path: string; auth: AuthRequirement; desc: string }> = [];
 
     const collect = (node: CommandNode, prefix: string) => {
       for (const [name, child] of node.children) {
         const fullPath = prefix ? `${prefix} ${name}` : name;
         if (child.command) {
-          entries.push({ path: fullPath, desc: child.command.description });
+          entries.push({
+            path: fullPath,
+            auth: child.command.auth,
+            desc: child.command.description,
+          });
         }
         if (child.children.size > 0) {
           collect(child, fullPath);
@@ -173,8 +203,7 @@ export class CommandRegistry {
     };
     collect(this.root, "");
 
-    const maxLen = Math.max(...entries.map((e) => e.path.length));
-    return entries.map((e) => `  ${a(e.path.padEnd(maxLen + 2))} ${d(e.desc)}`).join("\n");
+    return this.buildCommandLines(entries, accent, dim);
   }
 
   private buildFlagLines(
@@ -341,6 +370,7 @@ ${authFlagSections ? `${authFlagSections}\n\n` : ""}${b("Getting Help:")}
 
     out.write(`\n${cmd.description}\n`);
     out.write(`${b("Usage:")} ${prefix}${cmd.usageArgs ? ` ${cmd.usageArgs}` : ""}\n`);
+    out.write(`${b("Authentication:")} ${a(AUTH_LABELS[cmd.auth])}\n`);
     const flagEntries = [
       ...Object.entries(cmd.flags ?? {}),
       ...Object.entries(credentialFlagDefs(cmd)),
@@ -373,18 +403,25 @@ ${authFlagSections ? `${authFlagSections}\n\n` : ""}${b("Getting Help:")}
   }
 
   private printChildren(node: CommandNode, prefix: string, out: NodeJS.WriteStream): void {
-    const entries: Array<{ fullName: string; description: string }> = [];
-    const collect = (n: CommandNode, p: string) => {
-      for (const [name, child] of n.children) {
+    const entries: Array<{ path: string; auth: AuthRequirement; desc: string }> = [];
+    const collect = (currentNode: CommandNode, currentPath: string) => {
+      for (const [name, child] of currentNode.children) {
         if (child.command)
-          entries.push({ fullName: `${p} ${name}`, description: child.command.description });
-        if (child.children.size > 0) collect(child, `${p} ${name}`);
+          entries.push({
+            path: `${currentPath} ${name}`,
+            auth: child.command.auth,
+            desc: child.command.description,
+          });
+        if (child.children.size > 0) collect(child, `${currentPath} ${name}`);
       }
     };
     collect(node, prefix);
-    const maxLen = Math.max(...entries.map((e) => e.fullName.length));
-    for (const { fullName, description } of entries) {
-      out.write(`  ${this.accent(fullName.padEnd(maxLen), out)}  ${this.dim(description, out)}\n`);
-    }
+    out.write(
+      this.buildCommandLines(
+        entries,
+        (text) => this.accent(text, out),
+        (text) => this.dim(text, out),
+      ) + "\n",
+    );
   }
 }

packages/runtime/tests/error-handler.test.ts

@@ -0,0 +1,85 @@
+import { ExitCode } from "bailian-cli-core";
+import { expect, test } from "vite-plus/test";
+import { handleError } from "../src/error-handler.ts";
+
+test("handleError: fetch failed JSON includes cause.code from errno", () => {
+  const previousOutput = process.env.DASHSCOPE_OUTPUT;
+  process.env.DASHSCOPE_OUTPUT = "json";
+
+  let stderr = "";
+  const originalWrite = process.stderr.write.bind(process.stderr);
+  const originalExit = process.exit;
+  process.stderr.write = ((chunk: string | Uint8Array) => {
+    stderr += String(chunk);
+    return true;
+  }) as typeof process.stderr.write;
+  process.exit = ((code?: number) => {
+    throw new Error(`process.exit:${code ?? 0}`);
+  }) as typeof process.exit;
+
+  const root = Object.assign(new Error("getaddrinfo ENOTFOUND example.invalid"), {
+    code: "ENOTFOUND",
+  });
+  const fetchFailed = new TypeError("fetch failed", { cause: root });
+
+  try {
+    expect(() => handleError(fetchFailed, "bl")).toThrow(
+      new RegExp(`process\\.exit:${ExitCode.NETWORK}`),
+    );
+    const payload = JSON.parse(stderr.trim()) as {
+      error: { code: number; message: string; cause?: { message: string; code?: string } };
+    };
+    expect(payload.error.code).toBe(ExitCode.NETWORK);
+    expect(payload.error.message).toMatch(/ENOTFOUND/);
+    expect(payload.error.cause).toEqual({
+      message: root.message,
+      code: "ENOTFOUND",
+    });
+  } finally {
+    process.stderr.write = originalWrite;
+    process.exit = originalExit;
+    if (previousOutput === undefined) {
+      delete process.env.DASHSCOPE_OUTPUT;
+    } else {
+      process.env.DASHSCOPE_OUTPUT = previousOutput;
+    }
+  }
+});
+
+test("handleError: fetch failed without nested cause still maps to NETWORK", () => {
+  const previousOutput = process.env.DASHSCOPE_OUTPUT;
+  process.env.DASHSCOPE_OUTPUT = "json";
+
+  let stderr = "";
+  const originalWrite = process.stderr.write.bind(process.stderr);
+  const originalExit = process.exit;
+  process.stderr.write = ((chunk: string | Uint8Array) => {
+    stderr += String(chunk);
+    return true;
+  }) as typeof process.stderr.write;
+  process.exit = ((code?: number) => {
+    throw new Error(`process.exit:${code ?? 0}`);
+  }) as typeof process.exit;
+
+  const fetchFailed = new TypeError("fetch failed");
+
+  try {
+    expect(() => handleError(fetchFailed, "bl")).toThrow(
+      new RegExp(`process\\.exit:${ExitCode.NETWORK}`),
+    );
+    const payload = JSON.parse(stderr.trim()) as {
+      error: { code: number; message: string; cause?: { message: string; code?: string } };
+    };
+    expect(payload.error.code).toBe(ExitCode.NETWORK);
+    expect(payload.error.message).toMatch(/unknown cause/);
+    expect(payload.error.cause).toEqual({ message: "fetch failed" });
+  } finally {
+    process.stderr.write = originalWrite;
+    process.exit = originalExit;
+    if (previousOutput === undefined) {
+      delete process.env.DASHSCOPE_OUTPUT;
+    } else {
+      process.env.DASHSCOPE_OUTPUT = previousOutput;
+    }
+  }
+});

packages/runtime/tests/speech-recognize-pipeline.test.ts

@@ -0,0 +1,184 @@
+import { expect, test } from "vite-plus/test";
+import type { Client } from "bailian-cli-core";
+import { PipelineError } from "../src/pipeline/errors.ts";
+import type { PipelineEnv } from "../src/pipeline/bl-config.ts";
+import { speechRecognize } from "../src/pipeline/steps/bl-api.ts";
+import type { StepContext } from "../src/pipeline/types.ts";
+
+type CapturedRequest = {
+  path?: string;
+  method?: string;
+  headers?: Record<string, string>;
+  body?: Record<string, unknown>;
+  async?: boolean;
+};
+
+function makeEnv(requestJsonImpl?: (opts: CapturedRequest) => Promise<unknown>): {
+  env: PipelineEnv;
+  captured: CapturedRequest[];
+} {
+  const captured: CapturedRequest[] = [];
+  const client = {
+    uploadFile: async (source: string) => source,
+    requestJson: async (opts: CapturedRequest) => {
+      captured.push(opts);
+      if (requestJsonImpl) return requestJsonImpl(opts);
+      return { output: { text: "ok" } };
+    },
+  } as unknown as Client;
+
+  return {
+    env: {
+      client,
+      settings: { quiet: true, output: "json" } as PipelineEnv["settings"],
+    },
+    captured,
+  };
+}
+
+function makeCtx(): StepContext {
+  return { dryRun: false, signal: new AbortController().signal };
+}
+
+test("pipeline speechRecognize routes input-audio flash to sync multimodal endpoint", async () => {
+  const { env, captured } = makeEnv();
+  const result = (await speechRecognize(
+    env,
+    {
+      url: "https://example.com/a.wav",
+      model: "qwen-audio-3.0-asr-flash",
+      language: "en",
+      "vocabulary-id": "vocab-1",
+    },
+    makeCtx(),
+  )) as { mode?: string; text?: string };
+
+  expect(result.mode).toBe("sync");
+  expect(result.text).toBe("ok");
+  expect(captured).toHaveLength(1);
+  expect(captured[0]?.path).toBe("/api/v1/services/aigc/multimodal-generation/generation");
+  expect(captured[0]?.headers?.["X-DashScope-SSE"]).toBe("disable");
+  expect(captured[0]?.body).toMatchObject({
+    model: "qwen-audio-3.0-asr-flash",
+    parameters: {
+      format: "wav",
+      language_hints: ["en"],
+      vocabulary_id: "vocab-1",
+    },
+  });
+});
+
+test("pipeline speechRecognize maps qwen3-filetrans language to parameters.language", async () => {
+  const { env, captured } = makeEnv(async (opts) => {
+    if (opts.async || opts.method === "POST") {
+      return { output: { task_id: "task-1", task_status: "PENDING" } };
+    }
+    return {
+      output: { task_id: "task-1", task_status: "SUCCEEDED", results: [] },
+      request_id: "r1",
+    };
+  });
+
+  await speechRecognize(
+    env,
+    {
+      url: "https://example.com/a.wav",
+      model: "qwen3-asr-flash-filetrans",
+      language: "zh",
+      "poll-interval": 0,
+    },
+    makeCtx(),
+  );
+
+  expect(captured[0]?.path).toBe("/api/v1/services/audio/asr/transcription");
+  expect(captured[0]?.async).toBe(true);
+  expect(captured[0]?.body).toMatchObject({
+    model: "qwen3-asr-flash-filetrans",
+    input: { file_url: "https://example.com/a.wav" },
+    parameters: { language: "zh" },
+  });
+  expect(
+    (captured[0]?.body?.parameters as Record<string, unknown> | undefined)?.language_hints,
+  ).toBeUndefined();
+});
+
+test("pipeline speechRecognize rejects realtime models before requesting", async () => {
+  const { env, captured } = makeEnv();
+  await expect(
+    speechRecognize(
+      env,
+      { url: "https://example.com/a.wav", model: "qwen3-asr-flash-realtime" },
+      makeCtx(),
+    ),
+  ).rejects.toBeInstanceOf(PipelineError);
+  expect(captured).toHaveLength(0);
+});
+
+test("pipeline speechRecognize rejects multiple urls for sync flash", async () => {
+  const { env, captured } = makeEnv();
+  await expect(
+    speechRecognize(
+      env,
+      {
+        url: ["https://example.com/a.wav", "https://example.com/b.wav"],
+        model: "fun-asr-flash-2026-06-15",
+      },
+      makeCtx(),
+    ),
+  ).rejects.toBeInstanceOf(PipelineError);
+  expect(captured).toHaveLength(0);
+});
+
+test("pipeline speechRecognize downloads qwen3 singular result.transcription_url", async () => {
+  const originalFetch = globalThis.fetch;
+  const transcriptionUrl = "https://example.com/transcription.json";
+  globalThis.fetch = (async (input: RequestInfo | URL) => {
+    const url = typeof input === "string" ? input : input instanceof URL ? input.href : input.url;
+    expect(url).toBe(transcriptionUrl);
+    return new Response(
+      JSON.stringify({
+        transcripts: [{ text: "pipeline hello", sentences: [{ text: "pipeline hello" }] }],
+      }),
+      { status: 200, headers: { "Content-Type": "application/json" } },
+    );
+  }) as typeof fetch;
+
+  try {
+    const { env, captured } = makeEnv(async (opts) => {
+      if (opts.async || opts.method === "POST") {
+        return { output: { task_id: "task-1", task_status: "PENDING" } };
+      }
+      return {
+        output: {
+          task_id: "task-1",
+          task_status: "SUCCEEDED",
+          result: { transcription_url: transcriptionUrl },
+        },
+        request_id: "r1",
+      };
+    });
+
+    const result = (await speechRecognize(
+      env,
+      {
+        url: "https://example.com/a.wav",
+        model: "qwen3-asr-flash-filetrans",
+        "poll-interval": 0,
+      },
+      makeCtx(),
+    )) as {
+      mode?: string;
+      text?: string;
+      transcription_url?: string;
+      result?: { transcription_url?: string };
+    };
+
+    expect(captured[0]?.async).toBe(true);
+    expect(result.mode).toBe("async");
+    expect(result.text).toBe("pipeline hello");
+    expect(result.transcription_url).toBe(transcriptionUrl);
+    expect(result.result?.transcription_url).toBe(transcriptionUrl);
+  } finally {
+    globalThis.fetch = originalFetch;
+  }
+});

pnpm-workspace.yaml

@@ -24,10 +24,6 @@ catalogMode: prefer
 overrides:
   vite: "catalog:"
   vitest: "catalog:"
-# The @deepseek-ai/dsh-* rc line (used only by bailian-cli-dsh) peers on
-# packages that were never published: dsh-type-meta, dsh-environment,
-# dsh-tasks. Auto-installing peers therefore 404s the whole workspace.
-autoInstallPeers: false
 peerDependencyRules:
   allowAny:
     - vite

skills/bailian-cli/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: bailian-cli
 metadata:
-  version: "1.14.2"
+  version: "1.14.3"
   requires:
     bins: ["bl"]
 description: >-
@@ -71,6 +71,8 @@ Use this table only after the decision table in [`bailian-protocol`](../bailian-
 | Bailian pipeline workflow (a step in a bl flow)  | `bl pipeline run` / `validate`                | JSON/YAML workflow definitions                                                   |
 | Bailian rate limits / quota                      | `bl quota list` / `check` / `request`         | Console auth; class 2 — ask which product first if unnamed                       |
 | Bailian free tier / usage stats                  | `bl usage free` / `stats` / `freetier`        | Console auth; class 2 — ask which product first if unnamed                       |
+| Bailian Token Plan quota usage                   | `bl usage token-plan`                         | Console auth; class 2 — ask which product first if unnamed                       |
+| Bailian Coding Plan quota usage                  | `bl usage coding-plan`                        | Console auth; class 2 — ask which product first if unnamed                       |
 | Console API (advanced)                           | `bl console call`                             | Console auth                                                                     |
 | Bailian workspace listing                        | `bl workspace list`                           | Console auth                                                                     |
 | Image / video / speech / omni / vision           | → skill `bailian-gen`                         | Fallback: `bl image\|video\|speech\|omni\|vision --help`                         |

skills/bailian-cli/reference/advisor.md

@@ -7,19 +7,20 @@ Index: [index.md](index.md)
 
 ## Commands in this group
 
-| Command                | Description                                                                                    |
-| ---------------------- | ---------------------------------------------------------------------------------------------- |
-| `bl advisor recommend` | Recommend the best models for your use case (intent analysis → candidate recall → LLM ranking) |
+| Command                | Authentication | Description                                                                                    |
+| ---------------------- | -------------- | ---------------------------------------------------------------------------------------------- |
+| `bl advisor recommend` | API Key        | Recommend the best models for your use case (intent analysis → candidate recall → LLM ranking) |
 
 ## Command details
 
 ### `bl advisor recommend`
 
-| Field           | Value                                                                                          |
-| --------------- | ---------------------------------------------------------------------------------------------- |
-| **Name**        | `advisor recommend`                                                                            |
-| **Description** | Recommend the best models for your use case (intent analysis → candidate recall → LLM ranking) |
-| **Usage**       | `bl advisor recommend --message <text> [flags]`                                                |
+| Field              | Value                                                                                          |
+| ------------------ | ---------------------------------------------------------------------------------------------- |
+| **Name**           | `advisor recommend`                                                                            |
+| **Description**    | Recommend the best models for your use case (intent analysis → candidate recall → LLM ranking) |
+| **Authentication** | API Key                                                                                        |
+| **Usage**          | `bl advisor recommend --message <text> [flags]`                                                |
 
 #### Flags
 

skills/bailian-cli/reference/app.md

@@ -7,20 +7,21 @@ Index: [index.md](index.md)
 
 ## Commands in this group
 
-| Command       | Description                                    |
-| ------------- | ---------------------------------------------- |
-| `bl app call` | Call a Bailian application (agent or workflow) |
-| `bl app list` | List Bailian applications                      |
+| Command       | Authentication | Description                                    |
+| ------------- | -------------- | ---------------------------------------------- |
+| `bl app call` | API Key        | Call a Bailian application (agent or workflow) |
+| `bl app list` | Console        | List Bailian applications                      |
 
 ## Command details
 
 ### `bl app call`
 
-| Field           | Value                                               |
-| --------------- | --------------------------------------------------- |
-| **Name**        | `app call`                                          |
-| **Description** | Call a Bailian application (agent or workflow)      |
-| **Usage**       | `bl app call --app-id <id> --prompt <text> [flags]` |
+| Field              | Value                                               |
+| ------------------ | --------------------------------------------------- |
+| **Name**           | `app call`                                          |
+| **Description**    | Call a Bailian application (agent or workflow)      |
+| **Authentication** | API Key                                             |
+| **Usage**          | `bl app call --app-id <id> --prompt <text> [flags]` |
 
 #### Flags
 
@@ -67,11 +68,12 @@ bl app call --app-id abc123 --prompt "Start" --biz-params '{"key":"value"}'
 
 ### `bl app list`
 
-| Field           | Value                     |
-| --------------- | ------------------------- |
-| **Name**        | `app list`                |
-| **Description** | List Bailian applications |
-| **Usage**       | `bl app list [flags]`     |
+| Field              | Value                     |
+| ------------------ | ------------------------- |
+| **Name**           | `app list`                |
+| **Description**    | List Bailian applications |
+| **Authentication** | Console                   |
+| **Usage**          | `bl app list [flags]`     |
 
 #### Flags
 

skills/bailian-cli/reference/auth.md

@@ -7,22 +7,23 @@ Index: [index.md](index.md)
 
 ## Commands in this group
 
-| Command                         | Description                                                                                  |
-| ------------------------------- | -------------------------------------------------------------------------------------------- |
-| `bl auth generate-access-token` | Generate a CLI access token using OpenAPI AK/SK                                              |
-| `bl auth login`                 | Authenticate with API key, console browser login, or OpenAPI AK/SK (credentials can coexist) |
-| `bl auth logout`                | Clear stored credentials; full logout also clears the model Base URL                         |
-| `bl auth status`                | Show current authentication state                                                            |
+| Command                         | Authentication | Description                                                                                  |
+| ------------------------------- | -------------- | -------------------------------------------------------------------------------------------- |
+| `bl auth generate-access-token` | No Auth        | Generate a CLI access token using OpenAPI AK/SK                                              |
+| `bl auth login`                 | No Auth        | Authenticate with API key, console browser login, or OpenAPI AK/SK (credentials can coexist) |
+| `bl auth logout`                | No Auth        | Clear stored credentials; full logout also clears the model Base URL                         |
+| `bl auth status`                | No Auth        | Show current authentication state                                                            |
 
 ## Command details
 
 ### `bl auth generate-access-token`
 
-| Field           | Value                                                                                                      |
-| --------------- | ---------------------------------------------------------------------------------------------------------- |
-| **Name**        | `auth generate-access-token`                                                                               |
-| **Description** | Generate a CLI access token using OpenAPI AK/SK                                                            |
-| **Usage**       | `bl auth generate-access-token --access-key-id <id> --access-key-secret <secret> --security-token <token>` |
+| Field              | Value                                                                                                      |
+| ------------------ | ---------------------------------------------------------------------------------------------------------- |
+| **Name**           | `auth generate-access-token`                                                                               |
+| **Description**    | Generate a CLI access token using OpenAPI AK/SK                                                            |
+| **Authentication** | No Auth                                                                                                    |
+| **Usage**          | `bl auth generate-access-token --access-key-id <id> --access-key-secret <secret> --security-token <token>` |
 
 #### Flags
 
@@ -40,11 +41,12 @@ bl auth generate-access-token --access-key-id LTAIxxxxx --access-key-secret xxxx
 
 ### `bl auth login`
 
-| Field           | Value                                                                                                        |
-| --------------- | ------------------------------------------------------------------------------------------------------------ |
-| **Name**        | `auth login`                                                                                                 |
-| **Description** | Authenticate with API key, console browser login, or OpenAPI AK/SK (credentials can coexist)                 |
-| **Usage**       | `bl auth login --api-key <key> \| --console \| --open-api --access-key-id <id> --access-key-secret <secret>` |
+| Field              | Value                                                                                                        |
+| ------------------ | ------------------------------------------------------------------------------------------------------------ |
+| **Name**           | `auth login`                                                                                                 |
+| **Description**    | Authenticate with API key, console browser login, or OpenAPI AK/SK (credentials can coexist)                 |
+| **Authentication** | No Auth                                                                                                      |
+| **Usage**          | `bl auth login --api-key <key> \| --console \| --open-api --access-key-id <id> --access-key-secret <secret>` |
 
 #### Flags
 
@@ -78,11 +80,12 @@ bl auth login --open-api --access-key-id LTAIxxxxx --access-key-secret xxxxx
 
 ### `bl auth logout`
 
-| Field           | Value                                                                |
-| --------------- | -------------------------------------------------------------------- |
-| **Name**        | `auth logout`                                                        |
-| **Description** | Clear stored credentials; full logout also clears the model Base URL |
-| **Usage**       | `bl auth logout [--console \| --open-api] [--dry-run]`               |
+| Field              | Value                                                                |
+| ------------------ | -------------------------------------------------------------------- |
+| **Name**           | `auth logout`                                                        |
+| **Description**    | Clear stored credentials; full logout also clears the model Base URL |
+| **Authentication** | No Auth                                                              |
+| **Usage**          | `bl auth logout [--console \| --open-api] [--dry-run]`               |
 
 #### Flags
 
@@ -111,11 +114,12 @@ bl auth logout --dry-run
 
 ### `bl auth status`
 
-| Field           | Value                             |
-| --------------- | --------------------------------- |
-| **Name**        | `auth status`                     |
-| **Description** | Show current authentication state |
-| **Usage**       | `bl auth status`                  |
+| Field              | Value                             |
+| ------------------ | --------------------------------- |
+| **Name**           | `auth status`                     |
+| **Description**    | Show current authentication state |
+| **Authentication** | No Auth                           |
+| **Usage**          | `bl auth status`                  |
 
 #### Flags
 

skills/bailian-cli/reference/config.md

@@ -7,24 +7,25 @@ Index: [index.md](index.md)
 
 ## Commands in this group
 
-| Command           | Description                                      |
-| ----------------- | ------------------------------------------------ |
-| `bl config agent` | Configure a coding agent to use DashScope API    |
-| `bl config list`  | List config profiles and show the active profile |
-| `bl config set`   | Set a config value                               |
-| `bl config show`  | Display current configuration                    |
-| `bl config ui`    | Open a local web UI to manage config profiles    |
-| `bl config use`   | Set the active config profile                    |
+| Command           | Authentication | Description                                      |
+| ----------------- | -------------- | ------------------------------------------------ |
+| `bl config agent` | No Auth        | Configure a coding agent to use DashScope API    |
+| `bl config list`  | No Auth        | List config profiles and show the active profile |
+| `bl config set`   | No Auth        | Set a config value                               |
+| `bl config show`  | No Auth        | Display current configuration                    |
+| `bl config ui`    | No Auth        | Open a local web UI to manage config profiles    |
+| `bl config use`   | No Auth        | Set the active config profile                    |
 
 ## Command details
 
 ### `bl config agent`
 
-| Field           | Value                                                                                                                         |
-| --------------- | ----------------------------------------------------------------------------------------------------------------------------- |
-| **Name**        | `config agent`                                                                                                                |
-| **Description** | Configure a coding agent to use DashScope API                                                                                 |
-| **Usage**       | `bl config agent --agent <name> (--base-url <url> \| --region <region>) (--api-key <key> \| --key <encoded>) --model <model>` |
+| Field              | Value                                                                                                                         |
+| ------------------ | ----------------------------------------------------------------------------------------------------------------------------- |
+| **Name**           | `config agent`                                                                                                                |
+| **Description**    | Configure a coding agent to use DashScope API                                                                                 |
+| **Authentication** | No Auth                                                                                                                       |
+| **Usage**          | `bl config agent --agent <name> (--base-url <url> \| --region <region>) (--api-key <key> \| --key <encoded>) --model <model>` |
 
 #### Flags
 
@@ -55,11 +56,12 @@ bl config agent --agent codex --base-url https://dashscope.aliyuncs.com/compatib
 
 ### `bl config list`
 
-| Field           | Value                                            |
-| --------------- | ------------------------------------------------ |
-| **Name**        | `config list`                                    |
-| **Description** | List config profiles and show the active profile |
-| **Usage**       | `bl config list`                                 |
+| Field              | Value                                            |
+| ------------------ | ------------------------------------------------ |
+| **Name**           | `config list`                                    |
+| **Description**    | List config profiles and show the active profile |
+| **Authentication** | No Auth                                          |
+| **Usage**          | `bl config list`                                 |
 
 #### Flags
 
@@ -77,11 +79,12 @@ bl config list --output json
 
 ### `bl config set`
 
-| Field           | Value                                       |
-| --------------- | ------------------------------------------- |
-| **Name**        | `config set`                                |
-| **Description** | Set a config value                          |
-| **Usage**       | `bl config set --key <key> --value <value>` |
+| Field              | Value                                       |
+| ------------------ | ------------------------------------------- |
+| **Name**           | `config set`                                |
+| **Description**    | Set a config value                          |
+| **Authentication** | No Auth                                     |
+| **Usage**          | `bl config set --key <key> --value <value>` |
 
 #### Flags
 
@@ -106,11 +109,12 @@ bl config set --key base_url --value https://dashscope.aliyuncs.com
 
 ### `bl config show`
 
-| Field           | Value                         |
-| --------------- | ----------------------------- |
-| **Name**        | `config show`                 |
-| **Description** | Display current configuration |
-| **Usage**       | `bl config show`              |
+| Field              | Value                         |
+| ------------------ | ----------------------------- |
+| **Name**           | `config show`                 |
+| **Description**    | Display current configuration |
+| **Authentication** | No Auth                       |
+| **Usage**          | `bl config show`              |
 
 #### Flags
 
@@ -128,11 +132,12 @@ bl config show --output json
 
 ### `bl config ui`
 
-| Field           | Value                                         |
-| --------------- | --------------------------------------------- |
-| **Name**        | `config ui`                                   |
-| **Description** | Open a local web UI to manage config profiles |
-| **Usage**       | `bl config ui [--port <port>] [--no-open]`    |
+| Field              | Value                                         |
+| ------------------ | --------------------------------------------- |
+| **Name**           | `config ui`                                   |
+| **Description**    | Open a local web UI to manage config profiles |
+| **Authentication** | No Auth                                       |
+| **Usage**          | `bl config ui [--port <port>] [--no-open]`    |
 
 #### Flags
 
@@ -157,11 +162,12 @@ bl config ui --no-open
 
 ### `bl config use`
 
-| Field           | Value                         |
-| --------------- | ----------------------------- |
-| **Name**        | `config use`                  |
-| **Description** | Set the active config profile |
-| **Usage**       | `bl config use --name <name>` |
+| Field              | Value                         |
+| ------------------ | ----------------------------- |
+| **Name**           | `config use`                  |
+| **Description**    | Set the active config profile |
+| **Authentication** | No Auth                       |
+| **Usage**          | `bl config use --name <name>` |
 
 #### Flags
 

skills/bailian-cli/reference/console.md

@@ -7,19 +7,20 @@ Index: [index.md](index.md)
 
 ## Commands in this group
 
-| Command           | Description                                    |
-| ----------------- | ---------------------------------------------- |
-| `bl console call` | Call a Bailian console API via the CLI gateway |
+| Command           | Authentication | Description                                    |
+| ----------------- | -------------- | ---------------------------------------------- |
+| `bl console call` | Console        | Call a Bailian console API via the CLI gateway |
 
 ## Command details
 
 ### `bl console call`
 
-| Field           | Value                                               |
-| --------------- | --------------------------------------------------- |
-| **Name**        | `console call`                                      |
-| **Description** | Call a Bailian console API via the CLI gateway      |
-| **Usage**       | `bl console call --api <api> --data <json> [flags]` |
+| Field              | Value                                               |
+| ------------------ | --------------------------------------------------- |
+| **Name**           | `console call`                                      |
+| **Description**    | Call a Bailian console API via the CLI gateway      |
+| **Authentication** | Console                                             |
+| **Usage**          | `bl console call --api <api> --data <json> [flags]` |
 
 #### Flags
 
@@ -35,7 +36,7 @@ Index: [index.md](index.md)
 #### Examples
 
 ```bash
-bl console call --api zeldaEasy.broadscope-bailian.freeTrial.queryFreeTierQuota --data '{"queryFreeTierQuotaRequest":{"models":["qwen3-max"]}}'
+bl console call --api zeldaEasy.bailian-commerce.freeTrial.queryFreeTierQuota --data '{"queryFreeTierQuotaRequest":{"models":["qwen3-max"]}}'
 ```
 
 ```bash

skills/bailian-cli/reference/file.md

@@ -7,19 +7,20 @@ Index: [index.md](index.md)
 
 ## Commands in this group
 
-| Command          | Description                                              |
-| ---------------- | -------------------------------------------------------- |
-| `bl file upload` | Upload a local file to DashScope temporary storage (48h) |
+| Command          | Authentication | Description                                              |
+| ---------------- | -------------- | -------------------------------------------------------- |
+| `bl file upload` | API Key        | Upload a local file to DashScope temporary storage (48h) |
 
 ## Command details
 
 ### `bl file upload`
 
-| Field           | Value                                                    |
-| --------------- | -------------------------------------------------------- |
-| **Name**        | `file upload`                                            |
-| **Description** | Upload a local file to DashScope temporary storage (48h) |
-| **Usage**       | `bl file upload --file <path> --model <model>`           |
+| Field              | Value                                                    |
+| ------------------ | -------------------------------------------------------- |
+| **Name**           | `file upload`                                            |
+| **Description**    | Upload a local file to DashScope temporary storage (48h) |
+| **Authentication** | API Key                                                  |
+| **Usage**          | `bl file upload --file <path> --model <model>`           |
 
 #### Flags
 

skills/bailian-cli/reference/index.md

@@ -9,96 +9,92 @@ Use this index for the skill-scoped quick index and global flags.
 
 ## Quick index
 
-| Command                         | Description                                                                                    | Detail                         |
-| ------------------------------- | ---------------------------------------------------------------------------------------------- | ------------------------------ |
-| `bl advisor recommend`          | Recommend the best models for your use case (intent analysis → candidate recall → LLM ranking) | [advisor.md](advisor.md)       |
-| `bl app call`                   | Call a Bailian application (agent or workflow)                                                 | [app.md](app.md)               |
-| `bl app list`                   | List Bailian applications                                                                      | [app.md](app.md)               |
-| `bl auth generate-access-token` | Generate a CLI access token using OpenAPI AK/SK                                                | [auth.md](auth.md)             |
-| `bl auth login`                 | Authenticate with API key, console browser login, or OpenAPI AK/SK (credentials can coexist)   | [auth.md](auth.md)             |
-| `bl auth logout`                | Clear stored credentials; full logout also clears the model Base URL                           | [auth.md](auth.md)             |
-| `bl auth status`                | Show current authentication state                                                              | [auth.md](auth.md)             |
-| `bl config agent`               | Configure a coding agent to use DashScope API                                                  | [config.md](config.md)         |
-| `bl config list`                | List config profiles and show the active profile                                               | [config.md](config.md)         |
-| `bl config set`                 | Set a config value                                                                             | [config.md](config.md)         |
-| `bl config show`                | Display current configuration                                                                  | [config.md](config.md)         |
-| `bl config ui`                  | Open a local web UI to manage config profiles                                                  | [config.md](config.md)         |
-| `bl config use`                 | Set the active config profile                                                                  | [config.md](config.md)         |
-| `bl console call`               | Call a Bailian console API via the CLI gateway                                                 | [console.md](console.md)       |
-| `bl file upload`                | Upload a local file to DashScope temporary storage (48h)                                       | [file.md](file.md)             |
-| `bl knowledge chat`             | Chat with a Bailian knowledge base (RAG Q&A with streaming)                                    | [knowledge.md](knowledge.md)   |
-| `bl knowledge retrieve`         | Retrieve from a Bailian knowledge base (deprecated, use `search` instead)                      | [knowledge.md](knowledge.md)   |
-| `bl knowledge search`           | Search a Bailian knowledge base (RAG semantic retrieval)                                       | [knowledge.md](knowledge.md)   |
-| `bl mcp call`                   | Call a tool on an MCP server (tools/call)                                                      | [mcp.md](mcp.md)               |
-| `bl mcp list`                   | List MCP servers activated under your Bailian account                                          | [mcp.md](mcp.md)               |
-| `bl mcp tools`                  | List tools exposed by an MCP server (tools/list)                                               | [mcp.md](mcp.md)               |
-| `bl memory add`                 | Add memory from messages or custom content                                                     | [memory.md](memory.md)         |
-| `bl memory delete`              | Delete a memory node                                                                           | [memory.md](memory.md)         |
-| `bl memory list`                | List memory nodes for a user                                                                   | [memory.md](memory.md)         |
-| `bl memory profile create`      | Create a user profile schema for memory profiling                                              | [memory.md](memory.md)         |
-| `bl memory profile delete`      | Delete a profile schema                                                                        | [memory.md](memory.md)         |
-| `bl memory profile detail`      | Show a profile schema and its attribute IDs                                                    | [memory.md](memory.md)         |
-| `bl memory profile get`         | Get user profile by schema ID and user ID                                                      | [memory.md](memory.md)         |
-| `bl memory profile list`        | List profile schemas                                                                           | [memory.md](memory.md)         |
-| `bl memory profile update`      | Update a profile schema's name, description, or attributes                                     | [memory.md](memory.md)         |
-| `bl memory search`              | Search memory nodes by query or messages                                                       | [memory.md](memory.md)         |
-| `bl memory update`              | Update a memory node content                                                                   | [memory.md](memory.md)         |
-| `bl model list`                 | Browse model families or show detailed model info in the Bailian model marketplace             | [model.md](model.md)           |
-| `bl pipeline run`               | Run a pipeline workflow definition                                                             | [pipeline.md](pipeline.md)     |
-| `bl pipeline validate`          | Validate a pipeline definition without executing                                               | [pipeline.md](pipeline.md)     |
-| `bl plugin install`             | Install or upgrade an allowlisted Command Pack                                                 | [plugin.md](plugin.md)         |
-| `bl plugin link`                | Link an allowlisted local Command Pack for development                                         | [plugin.md](plugin.md)         |
-| `bl plugin list`                | List installed Command Packs and their load status                                             | [plugin.md](plugin.md)         |
-| `bl plugin remove`              | Remove an installed Command Pack                                                               | [plugin.md](plugin.md)         |
-| `bl quota check`                | Check current usage against rate limits                                                        | [quota.md](quota.md)           |
-| `bl quota history`              | View quota change history                                                                      | [quota.md](quota.md)           |
-| `bl quota list`                 | View model RPM/TPM rate limits                                                                 | [quota.md](quota.md)           |
-| `bl quota request`              | Request a temporary quota increase                                                             | [quota.md](quota.md)           |
-| `bl search web`                 | Search the web using DashScope MCP WebSearch service                                           | [search.md](search.md)         |
-| `bl skill add`                  | Install skills from the Bailian skill registry into local agents                               | [skill.md](skill.md)           |
-| `bl skill init`                 | Install all bailian-\* skills (one-shot bootstrap for new environments)                        | [skill.md](skill.md)           |
-| `bl skill list`                 | List registry skills and diff against local installs                                           | [skill.md](skill.md)           |
-| `bl skill remove`               | Remove locally installed skills (registry is untouched)                                        | [skill.md](skill.md)           |
-| `bl skill update`               | Update installed skills to the latest registry versions                                        | [skill.md](skill.md)           |
-| `bl text chat`                  | Send a chat completion (OpenAI compatible, DashScope)                                          | [text.md](text.md)             |
-| `bl token-plan add-member`      | Add a member to a Token Plan organization                                                      | [token-plan.md](token-plan.md) |
-| `bl token-plan assign-seats`    | Batch assign Token Plan seats to members                                                       | [token-plan.md](token-plan.md) |
-| `bl token-plan create-key`      | Create a Token Plan API key for a seat                                                         | [token-plan.md](token-plan.md) |
-| `bl token-plan list-seats`      | List Token Plan subscription seat details                                                      | [token-plan.md](token-plan.md) |
-| `bl token-plan personal-key`    | Get the personal-edition TokenPlan API key (masked) for the current account                    | [token-plan.md](token-plan.md) |
-| `bl token-plan personal-usage`  | Query personal-edition TokenPlan usage (5h/1w percentage, subscription, addon credits)         | [token-plan.md](token-plan.md) |
-| `bl update`                     | Update the CLI to the latest or a specified version                                            | [update.md](update.md)         |
-| `bl usage free`                 | Query free-tier quota for models (all models if --model is omitted)                            | [usage.md](usage.md)           |
-| `bl usage freetier`             | Enable or disable auto-stop for free-tier models. Enables by default; use --off to disable     | [usage.md](usage.md)           |
-| `bl usage stats`                | Query model usage statistics                                                                   | [usage.md](usage.md)           |
-| `bl usage summary`              | Show a unified usage summary: free-tier quota and recent usage overview                        | [usage.md](usage.md)           |
-| `bl workspace init`             | Initialize Bailian workspace and activate postpaid services                                    | [workspace.md](workspace.md)   |
-| `bl workspace list`             | List all workspaces                                                                            | [workspace.md](workspace.md)   |
+| Command                         | Authentication | Description                                                                                    | Detail                         |
+| ------------------------------- | -------------- | ---------------------------------------------------------------------------------------------- | ------------------------------ |
+| `bl advisor recommend`          | API Key        | Recommend the best models for your use case (intent analysis → candidate recall → LLM ranking) | [advisor.md](advisor.md)       |
+| `bl app call`                   | API Key        | Call a Bailian application (agent or workflow)                                                 | [app.md](app.md)               |
+| `bl app list`                   | Console        | List Bailian applications                                                                      | [app.md](app.md)               |
+| `bl auth generate-access-token` | No Auth        | Generate a CLI access token using OpenAPI AK/SK                                                | [auth.md](auth.md)             |
+| `bl auth login`                 | No Auth        | Authenticate with API key, console browser login, or OpenAPI AK/SK (credentials can coexist)   | [auth.md](auth.md)             |
+| `bl auth logout`                | No Auth        | Clear stored credentials; full logout also clears the model Base URL                           | [auth.md](auth.md)             |
+| `bl auth status`                | No Auth        | Show current authentication state                                                              | [auth.md](auth.md)             |
+| `bl config agent`               | No Auth        | Configure a coding agent to use DashScope API                                                  | [config.md](config.md)         |
+| `bl config list`                | No Auth        | List config profiles and show the active profile                                               | [config.md](config.md)         |
+| `bl config set`                 | No Auth        | Set a config value                                                                             | [config.md](config.md)         |
+| `bl config show`                | No Auth        | Display current configuration                                                                  | [config.md](config.md)         |
+| `bl config ui`                  | No Auth        | Open a local web UI to manage config profiles                                                  | [config.md](config.md)         |
+| `bl config use`                 | No Auth        | Set the active config profile                                                                  | [config.md](config.md)         |
+| `bl console call`               | Console        | Call a Bailian console API via the CLI gateway                                                 | [console.md](console.md)       |
+| `bl file upload`                | API Key        | Upload a local file to DashScope temporary storage (48h)                                       | [file.md](file.md)             |
+| `bl knowledge chat`             | API Key        | Chat with a Bailian knowledge base (RAG Q&A with streaming)                                    | [knowledge.md](knowledge.md)   |
+| `bl knowledge retrieve`         | API Key        | Retrieve from a Bailian knowledge base (deprecated, use `search` instead)                      | [knowledge.md](knowledge.md)   |
+| `bl knowledge search`           | API Key        | Search a Bailian knowledge base (RAG semantic retrieval)                                       | [knowledge.md](knowledge.md)   |
+| `bl mcp call`                   | API Key        | Call a tool on an MCP server (tools/call)                                                      | [mcp.md](mcp.md)               |
+| `bl mcp list`                   | Console        | List MCP servers activated under your Bailian account                                          | [mcp.md](mcp.md)               |
+| `bl mcp tools`                  | API Key        | List tools exposed by an MCP server (tools/list)                                               | [mcp.md](mcp.md)               |
+| `bl memory add`                 | API Key        | Add memory from messages or custom content                                                     | [memory.md](memory.md)         |
+| `bl memory delete`              | API Key        | Delete a memory node                                                                           | [memory.md](memory.md)         |
+| `bl memory list`                | API Key        | List memory nodes for a user                                                                   | [memory.md](memory.md)         |
+| `bl memory profile create`      | API Key        | Create a user profile schema for memory profiling                                              | [memory.md](memory.md)         |
+| `bl memory profile get`         | API Key        | Get user profile by schema ID and user ID                                                      | [memory.md](memory.md)         |
+| `bl memory search`              | API Key        | Search memory nodes by query or messages                                                       | [memory.md](memory.md)         |
+| `bl memory update`              | API Key        | Update a memory node content                                                                   | [memory.md](memory.md)         |
+| `bl model list`                 | Console        | Browse model families or show detailed model info in the Bailian model marketplace             | [model.md](model.md)           |
+| `bl pipeline run`               | No Auth        | Run a pipeline workflow definition                                                             | [pipeline.md](pipeline.md)     |
+| `bl pipeline validate`          | No Auth        | Validate a pipeline definition without executing                                               | [pipeline.md](pipeline.md)     |
+| `bl plugin install`             | No Auth        | Install or upgrade an allowlisted Command Pack                                                 | [plugin.md](plugin.md)         |
+| `bl plugin link`                | No Auth        | Link an allowlisted local Command Pack for development                                         | [plugin.md](plugin.md)         |
+| `bl plugin list`                | No Auth        | List installed Command Packs and their load status                                             | [plugin.md](plugin.md)         |
+| `bl plugin remove`              | No Auth        | Remove an installed Command Pack                                                               | [plugin.md](plugin.md)         |
+| `bl quota check`                | Console        | Check current usage against rate limits                                                        | [quota.md](quota.md)           |
+| `bl quota history`              | Console        | View quota change history                                                                      | [quota.md](quota.md)           |
+| `bl quota list`                 | Console        | View model RPM/TPM rate limits                                                                 | [quota.md](quota.md)           |
+| `bl quota request`              | Console        | Request a temporary quota increase                                                             | [quota.md](quota.md)           |
+| `bl search web`                 | API Key        | Search the web using DashScope MCP WebSearch service                                           | [search.md](search.md)         |
+| `bl skill add`                  | No Auth        | Install skills from the Bailian skill registry into local agents                               | [skill.md](skill.md)           |
+| `bl skill init`                 | No Auth        | Install all bailian-\* skills (one-shot bootstrap for new environments)                        | [skill.md](skill.md)           |
+| `bl skill list`                 | No Auth        | List registry skills and diff against local installs                                           | [skill.md](skill.md)           |
+| `bl skill remove`               | No Auth        | Remove locally installed skills (registry is untouched)                                        | [skill.md](skill.md)           |
+| `bl skill update`               | No Auth        | Update installed skills to the latest registry versions                                        | [skill.md](skill.md)           |
+| `bl text chat`                  | API Key        | Send a chat completion (OpenAI compatible, DashScope)                                          | [text.md](text.md)             |
+| `bl token-plan add-member`      | AK/SK          | Add a member to a Token Plan organization                                                      | [token-plan.md](token-plan.md) |
+| `bl token-plan assign-seats`    | AK/SK          | Batch assign Token Plan seats to members                                                       | [token-plan.md](token-plan.md) |
+| `bl token-plan create-key`      | AK/SK          | Create a Token Plan API key for a seat                                                         | [token-plan.md](token-plan.md) |
+| `bl token-plan list-seats`      | AK/SK          | List Token Plan subscription seat details                                                      | [token-plan.md](token-plan.md) |
+| `bl update`                     | No Auth        | Update the CLI to the latest or a specified version                                            | [update.md](update.md)         |
+| `bl usage coding-plan`          | Console        | Show Coding Plan quota usage                                                                   | [usage.md](usage.md)           |
+| `bl usage free`                 | Console        | Query free-tier quota for models (all models if --model is omitted)                            | [usage.md](usage.md)           |
+| `bl usage freetier`             | Console        | Enable or disable auto-stop for free-tier models. Enables by default; use --off to disable     | [usage.md](usage.md)           |
+| `bl usage stats`                | Console        | Query model usage statistics                                                                   | [usage.md](usage.md)           |
+| `bl usage summary`              | Console        | Show a unified usage summary: free-tier quota and recent usage overview                        | [usage.md](usage.md)           |
+| `bl usage token-plan`           | Console        | Show Token Plan quota usage                                                                    | [usage.md](usage.md)           |
+| `bl workspace init`             | No Auth        | Initialize Bailian workspace and activate postpaid services                                    | [workspace.md](workspace.md)   |
+| `bl workspace list`             | Console        | List all workspaces                                                                            | [workspace.md](workspace.md)   |
 
 ## By group
 
-| Group        | Commands                                                                                                                                           | Reference                      |
-| ------------ | -------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------ |
-| `advisor`    | `recommend`                                                                                                                                        | [advisor.md](advisor.md)       |
-| `app`        | `call`, `list`                                                                                                                                     | [app.md](app.md)               |
-| `auth`       | `generate-access-token`, `login`, `logout`, `status`                                                                                               | [auth.md](auth.md)             |
-| `config`     | `agent`, `list`, `set`, `show`, `ui`, `use`                                                                                                        | [config.md](config.md)         |
-| `console`    | `call`                                                                                                                                             | [console.md](console.md)       |
-| `file`       | `upload`                                                                                                                                           | [file.md](file.md)             |
-| `knowledge`  | `chat`, `retrieve`, `search`                                                                                                                       | [knowledge.md](knowledge.md)   |
-| `mcp`        | `call`, `list`, `tools`                                                                                                                            | [mcp.md](mcp.md)               |
-| `memory`     | `add`, `delete`, `list`, `profile create`, `profile delete`, `profile detail`, `profile get`, `profile list`, `profile update`, `search`, `update` | [memory.md](memory.md)         |
-| `model`      | `list`                                                                                                                                             | [model.md](model.md)           |
-| `pipeline`   | `run`, `validate`                                                                                                                                  | [pipeline.md](pipeline.md)     |
-| `plugin`     | `install`, `link`, `list`, `remove`                                                                                                                | [plugin.md](plugin.md)         |
-| `quota`      | `check`, `history`, `list`, `request`                                                                                                              | [quota.md](quota.md)           |
-| `search`     | `web`                                                                                                                                              | [search.md](search.md)         |
-| `skill`      | `add`, `init`, `list`, `remove`, `update`                                                                                                          | [skill.md](skill.md)           |
-| `text`       | `chat`                                                                                                                                             | [text.md](text.md)             |
-| `token-plan` | `add-member`, `assign-seats`, `create-key`, `list-seats`, `personal-key`, `personal-usage`                                                         | [token-plan.md](token-plan.md) |
-| `update`     | `(root)`                                                                                                                                           | [update.md](update.md)         |
-| `usage`      | `free`, `freetier`, `stats`, `summary`                                                                                                             | [usage.md](usage.md)           |
-| `workspace`  | `init`, `list`                                                                                                                                     | [workspace.md](workspace.md)   |
+| Group        | Commands                                                                     | Reference                      |
+| ------------ | ---------------------------------------------------------------------------- | ------------------------------ |
+| `advisor`    | `recommend`                                                                  | [advisor.md](advisor.md)       |
+| `app`        | `call`, `list`                                                               | [app.md](app.md)               |
+| `auth`       | `generate-access-token`, `login`, `logout`, `status`                         | [auth.md](auth.md)             |
+| `config`     | `agent`, `list`, `set`, `show`, `ui`, `use`                                  | [config.md](config.md)         |
+| `console`    | `call`                                                                       | [console.md](console.md)       |
+| `file`       | `upload`                                                                     | [file.md](file.md)             |
+| `knowledge`  | `chat`, `retrieve`, `search`                                                 | [knowledge.md](knowledge.md)   |
+| `mcp`        | `call`, `list`, `tools`                                                      | [mcp.md](mcp.md)               |
+| `memory`     | `add`, `delete`, `list`, `profile create`, `profile get`, `search`, `update` | [memory.md](memory.md)         |
+| `model`      | `list`                                                                       | [model.md](model.md)           |
+| `pipeline`   | `run`, `validate`                                                            | [pipeline.md](pipeline.md)     |
+| `plugin`     | `install`, `link`, `list`, `remove`                                          | [plugin.md](plugin.md)         |
+| `quota`      | `check`, `history`, `list`, `request`                                        | [quota.md](quota.md)           |
+| `search`     | `web`                                                                        | [search.md](search.md)         |
+| `skill`      | `add`, `init`, `list`, `remove`, `update`                                    | [skill.md](skill.md)           |
+| `text`       | `chat`                                                                       | [text.md](text.md)             |
+| `token-plan` | `add-member`, `assign-seats`, `create-key`, `list-seats`                     | [token-plan.md](token-plan.md) |
+| `update`     | `(root)`                                                                     | [update.md](update.md)         |
+| `usage`      | `coding-plan`, `free`, `freetier`, `stats`, `summary`, `token-plan`          | [usage.md](usage.md)           |
+| `workspace`  | `init`, `list`                                                               | [workspace.md](workspace.md)   |
 
 ## Global flags
 

skills/bailian-cli/reference/knowledge.md

@@ -7,21 +7,22 @@ Index: [index.md](index.md)
 
 ## Commands in this group
 
-| Command                 | Description                                                               |
-| ----------------------- | ------------------------------------------------------------------------- |
-| `bl knowledge chat`     | Chat with a Bailian knowledge base (RAG Q&A with streaming)               |
-| `bl knowledge retrieve` | Retrieve from a Bailian knowledge base (deprecated, use `search` instead) |
-| `bl knowledge search`   | Search a Bailian knowledge base (RAG semantic retrieval)                  |
+| Command                 | Authentication | Description                                                               |
+| ----------------------- | -------------- | ------------------------------------------------------------------------- |
+| `bl knowledge chat`     | API Key        | Chat with a Bailian knowledge base (RAG Q&A with streaming)               |
+| `bl knowledge retrieve` | API Key        | Retrieve from a Bailian knowledge base (deprecated, use `search` instead) |
+| `bl knowledge search`   | API Key        | Search a Bailian knowledge base (RAG semantic retrieval)                  |
 
 ## Command details
 
 ### `bl knowledge chat`
 
-| Field           | Value                                                        |
-| --------------- | ------------------------------------------------------------ |
-| **Name**        | `knowledge chat`                                             |
-| **Description** | Chat with a Bailian knowledge base (RAG Q&A with streaming)  |
-| **Usage**       | `bl knowledge chat --message <text> --agent-id <id> [flags]` |
+| Field              | Value                                                        |
+| ------------------ | ------------------------------------------------------------ |
+| **Name**           | `knowledge chat`                                             |
+| **Description**    | Chat with a Bailian knowledge base (RAG Q&A with streaming)  |
+| **Authentication** | API Key                                                      |
+| **Usage**          | `bl knowledge chat --message <text> --agent-id <id> [flags]` |
 
 #### Flags
 
@@ -57,11 +58,12 @@ bl knowledge chat --message "Describe these images" --image https://example.com/
 
 ### `bl knowledge retrieve`
 
-| Field           | Value                                                                     |
-| --------------- | ------------------------------------------------------------------------- |
-| **Name**        | `knowledge retrieve`                                                      |
-| **Description** | Retrieve from a Bailian knowledge base (deprecated, use `search` instead) |
-| **Usage**       | `bl knowledge retrieve --index-id <id> --query <text> [flags]`            |
+| Field              | Value                                                                     |
+| ------------------ | ------------------------------------------------------------------------- |
+| **Name**           | `knowledge retrieve`                                                      |
+| **Description**    | Retrieve from a Bailian knowledge base (deprecated, use `search` instead) |
+| **Authentication** | API Key                                                                   |
+| **Usage**          | `bl knowledge retrieve --index-id <id> --query <text> [flags]`            |
 
 #### Flags
 
@@ -92,11 +94,12 @@ bl knowledge retrieve --index-id idx_xxx --query "RAG retrieval" --rerank --rera
 
 ### `bl knowledge search`
 
-| Field           | Value                                                        |
-| --------------- | ------------------------------------------------------------ |
-| **Name**        | `knowledge search`                                           |
-| **Description** | Search a Bailian knowledge base (RAG semantic retrieval)     |
-| **Usage**       | `bl knowledge search --query <text> --agent-id <id> [flags]` |
+| Field              | Value                                                        |
+| ------------------ | ------------------------------------------------------------ |
+| **Name**           | `knowledge search`                                           |
+| **Description**    | Search a Bailian knowledge base (RAG semantic retrieval)     |
+| **Authentication** | API Key                                                      |
+| **Usage**          | `bl knowledge search --query <text> --agent-id <id> [flags]` |
 
 #### Flags
 

skills/bailian-cli/reference/mcp.md

@@ -7,33 +7,34 @@ Index: [index.md](index.md)
 
 ## Commands in this group
 
-| Command        | Description                                           |
-| -------------- | ----------------------------------------------------- |
-| `bl mcp call`  | Call a tool on an MCP server (tools/call)             |
-| `bl mcp list`  | List MCP servers activated under your Bailian account |
-| `bl mcp tools` | List tools exposed by an MCP server (tools/list)      |
+| Command        | Authentication | Description                                           |
+| -------------- | -------------- | ----------------------------------------------------- |
+| `bl mcp call`  | API Key        | Call a tool on an MCP server (tools/call)             |
+| `bl mcp list`  | Console        | List MCP servers activated under your Bailian account |
+| `bl mcp tools` | API Key        | List tools exposed by an MCP server (tools/list)      |
 
 ## Command details
 
 ### `bl mcp call`
 
-| Field           | Value                                                                               |
-| --------------- | ----------------------------------------------------------------------------------- |
-| **Name**        | `mcp call`                                                                          |
-| **Description** | Call a tool on an MCP server (tools/call)                                           |
-| **Usage**       | `bl mcp call --target <server.tool> [--arg k=v ...] [--json '{...}'] [--url <url>]` |
+| Field              | Value                                                                               |
+| ------------------ | ----------------------------------------------------------------------------------- |
+| **Name**           | `mcp call`                                                                          |
+| **Description**    | Call a tool on an MCP server (tools/call)                                           |
+| **Authentication** | API Key                                                                             |
+| **Usage**          | `bl mcp call --target <server.tool> [--arg k=v ...] [--json '{...}'] [--url <url>]` |
 
 #### Flags
 
-| Flag                     | Type   | Required | Description                                                                              |
-| ------------------------ | ------ | -------- | ---------------------------------------------------------------------------------------- |
-| `--target <server.tool>` | string | yes      | Server code and tool name joined by a dot, e.g. market-cmapi00073529.SmartStockSelection |
-| `--arg <kv>`             | array  | no       | Tool argument (repeatable). Values parsed as JSON if possible, else string.              |
-| `--json <obj>`           | string | no       | Full arguments object as JSON; merged with --arg (arg wins).                             |
-| `--query <text>`         | string | no       | Shortcut for --arg query=<text> (mirrors many DashScope MCP tools).                      |
-| `--url <url>`            | string | no       | Override the MCP endpoint URL (for non-Bailian servers)                                  |
-| `--api-key <key>`        | string | no       | API key                                                                                  |
-| `--base-url <url>`       | string | no       | API base URL                                                                             |
+| Flag                     | Type   | Required | Description                                                                                                 |
+| ------------------------ | ------ | -------- | ----------------------------------------------------------------------------------------------------------- |
+| `--target <server.tool>` | string | yes      | Server code and tool name joined by a dot, e.g. market-cmapi00073529.SmartStockSelection                    |
+| `--arg <kv>`             | array  | no       | Tool argument (repeatable). Values parsed as JSON if possible, else string.                                 |
+| `--json <obj>`           | string | no       | Full arguments object as JSON; merged with --arg (arg wins).                                                |
+| `--query <text>`         | string | no       | Shortcut for --arg query=<text> (mirrors many DashScope MCP tools).                                         |
+| `--url <url>`            | string | no       | Override the MCP endpoint URL (non-Bailian). Tries Streamable HTTP first, then classic SSE on the same URL. |
+| `--api-key <key>`        | string | no       | API key                                                                                                     |
+| `--base-url <url>`       | string | no       | API base URL                                                                                                |
 
 #### Examples
 
@@ -51,11 +52,12 @@ bl mcp call --target market-cmapi00073529.SmartFundSelection --arg riskLevel=R3
 
 ### `bl mcp list`
 
-| Field           | Value                                                 |
-| --------------- | ----------------------------------------------------- |
-| **Name**        | `mcp list`                                            |
-| **Description** | List MCP servers activated under your Bailian account |
-| **Usage**       | `bl mcp list [flags]`                                 |
+| Field              | Value                                                 |
+| ------------------ | ----------------------------------------------------- |
+| **Name**           | `mcp list`                                            |
+| **Description**    | List MCP servers activated under your Bailian account |
+| **Authentication** | Console                                               |
+| **Usage**          | `bl mcp list [flags]`                                 |
 
 #### Flags
 
@@ -86,20 +88,21 @@ bl mcp list --output json
 
 ### `bl mcp tools`
 
-| Field           | Value                                            |
-| --------------- | ------------------------------------------------ |
-| **Name**        | `mcp tools`                                      |
-| **Description** | List tools exposed by an MCP server (tools/list) |
-| **Usage**       | `bl mcp tools --server <code> [--url <url>]`     |
+| Field              | Value                                            |
+| ------------------ | ------------------------------------------------ |
+| **Name**           | `mcp tools`                                      |
+| **Description**    | List tools exposed by an MCP server (tools/list) |
+| **Authentication** | API Key                                          |
+| **Usage**          | `bl mcp tools --server <code> [--url <url>]`     |
 
 #### Flags
 
-| Flag               | Type   | Required | Description                                             |
-| ------------------ | ------ | -------- | ------------------------------------------------------- |
-| `--server <code>`  | string | yes      | Server code from `mcp list` (e.g. market-cmapi00073529) |
-| `--url <url>`      | string | no       | Override the MCP endpoint URL (for non-Bailian servers) |
-| `--api-key <key>`  | string | no       | API key                                                 |
-| `--base-url <url>` | string | no       | API base URL                                            |
+| Flag               | Type   | Required | Description                                                                                                 |
+| ------------------ | ------ | -------- | ----------------------------------------------------------------------------------------------------------- |
+| `--server <code>`  | string | yes      | Server code from `mcp list` (e.g. market-cmapi00073529)                                                     |
+| `--url <url>`      | string | no       | Override the MCP endpoint URL (non-Bailian). Tries Streamable HTTP first, then classic SSE on the same URL. |
+| `--api-key <key>`  | string | no       | API key                                                                                                     |
+| `--base-url <url>` | string | no       | API base URL                                                                                                |
 
 #### Examples
 

skills/bailian-cli/reference/memory.md

@@ -7,43 +7,38 @@ Index: [index.md](index.md)
 
 ## Commands in this group
 
-| Command                    | Description                                                |
-| -------------------------- | ---------------------------------------------------------- |
-| `bl memory add`            | Add memory from messages or custom content                 |
-| `bl memory delete`         | Delete a memory node                                       |
-| `bl memory list`           | List memory nodes for a user                               |
-| `bl memory profile create` | Create a user profile schema for memory profiling          |
-| `bl memory profile delete` | Delete a profile schema                                    |
-| `bl memory profile detail` | Show a profile schema and its attribute IDs                |
-| `bl memory profile get`    | Get user profile by schema ID and user ID                  |
-| `bl memory profile list`   | List profile schemas                                       |
-| `bl memory profile update` | Update a profile schema's name, description, or attributes |
-| `bl memory search`         | Search memory nodes by query or messages                   |
-| `bl memory update`         | Update a memory node content                               |
+| Command                    | Authentication | Description                                       |
+| -------------------------- | -------------- | ------------------------------------------------- |
+| `bl memory add`            | API Key        | Add memory from messages or custom content        |
+| `bl memory delete`         | API Key        | Delete a memory node                              |
+| `bl memory list`           | API Key        | List memory nodes for a user                      |
+| `bl memory profile create` | API Key        | Create a user profile schema for memory profiling |
+| `bl memory profile get`    | API Key        | Get user profile by schema ID and user ID         |
+| `bl memory search`         | API Key        | Search memory nodes by query or messages          |
+| `bl memory update`         | API Key        | Update a memory node content                      |
 
 ## Command details
 
 ### `bl memory add`
 
-| Field           | Value                                                                         |
-| --------------- | ----------------------------------------------------------------------------- |
-| **Name**        | `memory add`                                                                  |
-| **Description** | Add memory from messages or custom content                                    |
-| **Usage**       | `bl memory add --user-id <id> [--messages <json>] [--content <text>] [flags]` |
+| Field              | Value                                                                         |
+| ------------------ | ----------------------------------------------------------------------------- |
+| **Name**           | `memory add`                                                                  |
+| **Description**    | Add memory from messages or custom content                                    |
+| **Authentication** | API Key                                                                       |
+| **Usage**          | `bl memory add --user-id <id> [--messages <json>] [--content <text>] [flags]` |
 
 #### Flags
 
-| Flag                       | Type   | Required | Description                                                        |
-| -------------------------- | ------ | -------- | ------------------------------------------------------------------ |
-| `--user-id <id>`           | string | yes      | User ID (required)                                                 |
-| `--messages <json>`        | string | no       | Messages JSON array: [{"role":"user","content":"..."},...]         |
-| `--content <text>`         | string | no       | Custom content text to memorize                                    |
-| `--profile-schema <id>`    | string | no       | Profile schema ID for user profiling                               |
-| `--memory-library-id <id>` | string | no       | Memory library ID (isolate memory space)                           |
-| `--project-id <id>`        | string | no       | Memory extraction rule ID (defaults to the library's default rule) |
-| `--meta-data <json>`       | string | no       | Custom metadata JSON object: {"location":"Beijing"}                |
-| `--api-key <key>`          | string | no       | API key                                                            |
-| `--base-url <url>`         | string | no       | API base URL                                                       |
+| Flag                       | Type   | Required | Description                                                |
+| -------------------------- | ------ | -------- | ---------------------------------------------------------- |
+| `--user-id <id>`           | string | yes      | User ID (required)                                         |
+| `--messages <json>`        | string | no       | Messages JSON array: [{"role":"user","content":"..."},...] |
+| `--content <text>`         | string | no       | Custom content text to memorize                            |
+| `--profile-schema <id>`    | string | no       | Profile schema ID for user profiling                       |
+| `--memory-library-id <id>` | string | no       | Memory library ID (isolate memory space)                   |
+| `--api-key <key>`          | string | no       | API key                                                    |
+| `--base-url <url>`         | string | no       | API base URL                                               |
 
 #### Examples
 
@@ -59,17 +54,14 @@ bl memory add --user-id user1 --messages '[{"role":"user","content":"I like trav
 bl memory add --user-id user1 --content "Lives in Beijing" --profile-schema schema_xxx
 ```
 
-```bash
-bl memory add --user-id user1 --content "Lives in Beijing" --meta-data '{"source":"onboarding"}'
-```
-
 ### `bl memory delete`
 
-| Field           | Value                                            |
-| --------------- | ------------------------------------------------ |
-| **Name**        | `memory delete`                                  |
-| **Description** | Delete a memory node                             |
-| **Usage**       | `bl memory delete --node-id <id> --user-id <id>` |
+| Field              | Value                                            |
+| ------------------ | ------------------------------------------------ |
+| **Name**           | `memory delete`                                  |
+| **Description**    | Delete a memory node                             |
+| **Authentication** | API Key                                          |
+| **Usage**          | `bl memory delete --node-id <id> --user-id <id>` |
 
 #### Flags
 
@@ -89,23 +81,23 @@ bl memory delete --node-id node_xxx --user-id user1
 
 ### `bl memory list`
 
-| Field           | Value                                   |
-| --------------- | --------------------------------------- |
-| **Name**        | `memory list`                           |
-| **Description** | List memory nodes for a user            |
-| **Usage**       | `bl memory list --user-id <id> [flags]` |
+| Field              | Value                                   |
+| ------------------ | --------------------------------------- |
+| **Name**           | `memory list`                           |
+| **Description**    | List memory nodes for a user            |
+| **Authentication** | API Key                                 |
+| **Usage**          | `bl memory list --user-id <id> [flags]` |
 
 #### Flags
 
-| Flag                       | Type   | Required | Description                                                        |
-| -------------------------- | ------ | -------- | ------------------------------------------------------------------ |
-| `--user-id <id>`           | string | yes      | User ID (required)                                                 |
-| `--page-size <n>`          | number | no       | Results per page (default: 10)                                     |
-| `--page <n>`               | number | no       | Page number (default: 1)                                           |
-| `--memory-library-id <id>` | string | no       | Memory library ID                                                  |
-| `--project-id <id>`        | string | no       | Memory extraction rule ID (defaults to the library's default rule) |
-| `--api-key <key>`          | string | no       | API key                                                            |
-| `--base-url <url>`         | string | no       | API base URL                                                       |
+| Flag                       | Type   | Required | Description                    |
+| -------------------------- | ------ | -------- | ------------------------------ |
+| `--user-id <id>`           | string | yes      | User ID (required)             |
+| `--page-size <n>`          | number | no       | Results per page (default: 10) |
+| `--page <n>`               | number | no       | Page number (default: 1)       |
+| `--memory-library-id <id>` | string | no       | Memory library ID              |
+| `--api-key <key>`          | string | no       | API key                        |
+| `--base-url <url>`         | string | no       | API base URL                   |
 
 #### Examples
 
@@ -119,11 +111,12 @@ bl memory list --user-id user1 --page-size 20 --page 2
 
 ### `bl memory profile create`
 
-| Field           | Value                                                                |
-| --------------- | -------------------------------------------------------------------- |
-| **Name**        | `memory profile create`                                              |
-| **Description** | Create a user profile schema for memory profiling                    |
-| **Usage**       | `bl memory profile create --name <name> --attributes <json> [flags]` |
+| Field              | Value                                                                |
+| ------------------ | -------------------------------------------------------------------- |
+| **Name**           | `memory profile create`                                              |
+| **Description**    | Create a user profile schema for memory profiling                    |
+| **Authentication** | API Key                                                              |
+| **Usage**          | `bl memory profile create --name <name> --attributes <json> [flags]` |
 
 #### Flags
 
@@ -141,59 +134,14 @@ bl memory list --user-id user1 --page-size 20 --page 2
 bl memory profile create --name "user_basic" --attributes '[{"name":"age","description":"age"},{"name":"hobby","description":"hobby"}]'
 ```
 
-### `bl memory profile delete`
-
-| Field           | Value                                               |
-| --------------- | --------------------------------------------------- |
-| **Name**        | `memory profile delete`                             |
-| **Description** | Delete a profile schema                             |
-| **Usage**       | `bl memory profile delete --schema-id <id> [flags]` |
-
-#### Flags
-
-| Flag                       | Type   | Required | Description                  |
-| -------------------------- | ------ | -------- | ---------------------------- |
-| `--schema-id <id>`         | string | yes      | Profile schema ID (required) |
-| `--memory-library-id <id>` | string | no       | Memory library ID            |
-| `--api-key <key>`          | string | no       | API key                      |
-| `--base-url <url>`         | string | no       | API base URL                 |
-
-#### Examples
-
-```bash
-bl memory profile delete --schema-id schema_xxx
-```
-
-### `bl memory profile detail`
-
-| Field           | Value                                               |
-| --------------- | --------------------------------------------------- |
-| **Name**        | `memory profile detail`                             |
-| **Description** | Show a profile schema and its attribute IDs         |
-| **Usage**       | `bl memory profile detail --schema-id <id> [flags]` |
-
-#### Flags
-
-| Flag                       | Type   | Required | Description                  |
-| -------------------------- | ------ | -------- | ---------------------------- |
-| `--schema-id <id>`         | string | yes      | Profile schema ID (required) |
-| `--memory-library-id <id>` | string | no       | Memory library ID            |
-| `--api-key <key>`          | string | no       | API key                      |
-| `--base-url <url>`         | string | no       | API base URL                 |
-
-#### Examples
-
-```bash
-bl memory profile detail --schema-id schema_xxx
-```
-
 ### `bl memory profile get`
 
-| Field           | Value                                                   |
-| --------------- | ------------------------------------------------------- |
-| **Name**        | `memory profile get`                                    |
-| **Description** | Get user profile by schema ID and user ID               |
-| **Usage**       | `bl memory profile get --schema-id <id> --user-id <id>` |
+| Field              | Value                                                   |
+| ------------------ | ------------------------------------------------------- |
+| **Name**           | `memory profile get`                                    |
+| **Description**    | Get user profile by schema ID and user ID               |
+| **Authentication** | API Key                                                 |
+| **Usage**          | `bl memory profile get --schema-id <id> --user-id <id>` |
 
 #### Flags
 
@@ -210,97 +158,26 @@ bl memory profile detail --schema-id schema_xxx
 bl memory profile get --schema-id schema_xxx --user-id user1
 ```
 
-### `bl memory profile list`
-
-| Field           | Value                            |
-| --------------- | -------------------------------- |
-| **Name**        | `memory profile list`            |
-| **Description** | List profile schemas             |
-| **Usage**       | `bl memory profile list [flags]` |
-
-#### Flags
-
-| Flag                       | Type   | Required | Description                    |
-| -------------------------- | ------ | -------- | ------------------------------ |
-| `--memory-library-id <id>` | string | no       | Memory library ID              |
-| `--page-size <n>`          | number | no       | Results per page (default: 10) |
-| `--page <n>`               | number | no       | Page number (default: 1)       |
-| `--api-key <key>`          | string | no       | API key                        |
-| `--base-url <url>`         | string | no       | API base URL                   |
-
-#### Examples
-
-```bash
-bl memory profile list
-```
-
-```bash
-bl memory profile list --page-size 20 --page 2
-```
-
-### `bl memory profile update`
-
-| Field           | Value                                                                                        |
-| --------------- | -------------------------------------------------------------------------------------------- |
-| **Name**        | `memory profile update`                                                                      |
-| **Description** | Update a profile schema's name, description, or attributes                                   |
-| **Usage**       | `bl memory profile update --schema-id <id> [--name <name>] [--attribute-ops <json>] [flags]` |
-
-#### Flags
-
-| Flag                       | Type   | Required | Description                                                                                           |
-| -------------------------- | ------ | -------- | ----------------------------------------------------------------------------------------------------- |
-| `--schema-id <id>`         | string | yes      | Profile schema ID (required)                                                                          |
-| `--name <name>`            | string | no       | New schema name                                                                                       |
-| `--description <text>`     | string | no       | New schema description                                                                                |
-| `--attribute-ops <json>`   | string | no       | Attribute operations JSON array: [{"op":"add","name":"plan"},{"op":"delete","attribute_id":"attr_1"}] |
-| `--memory-library-id <id>` | string | no       | Memory library ID                                                                                     |
-| `--api-key <key>`          | string | no       | API key                                                                                               |
-| `--base-url <url>`         | string | no       | API base URL                                                                                          |
-
-#### Notes
-
-- Attribute IDs for update/delete operations come from `memory profile detail`.
-
-#### Examples
-
-```bash
-bl memory profile update --schema-id schema_xxx --name "user_basic_v2"
-```
-
-```bash
-bl memory profile update --schema-id schema_xxx --attribute-ops '[{"op":"add","name":"plan","description":"subscription plan"}]'
-```
-
-```bash
-bl memory profile update --schema-id schema_xxx --attribute-ops '[{"op":"delete","attribute_id":"attr_1"}]'
-```
-
 ### `bl memory search`
 
-| Field           | Value                                                      |
-| --------------- | ---------------------------------------------------------- |
-| **Name**        | `memory search`                                            |
-| **Description** | Search memory nodes by query or messages                   |
-| **Usage**       | `bl memory search --user-id <id> [--query <text>] [flags]` |
+| Field              | Value                                                      |
+| ------------------ | ---------------------------------------------------------- |
+| **Name**           | `memory search`                                            |
+| **Description**    | Search memory nodes by query or messages                   |
+| **Authentication** | API Key                                                    |
+| **Usage**          | `bl memory search --user-id <id> [--query <text>] [flags]` |
 
 #### Flags
 
-| Flag                         | Type    | Required | Description                                                                                             |
-| ---------------------------- | ------- | -------- | ------------------------------------------------------------------------------------------------------- |
-| `--user-id <id>`             | string  | yes      | User ID (required)                                                                                      |
-| `--query <text>`             | string  | no       | Search query text                                                                                       |
-| `--messages <json>`          | string  | no       | Messages JSON array for context-based search                                                            |
-| `--top-k <n>`                | number  | no       | Number of results to return (default: 10)                                                               |
-| `--memory-library-id <id>`   | string  | no       | Memory library ID                                                                                       |
-| `--project-ids <id>`         | array   | no       | Memory extraction rule ID for hybrid retrieval (repeatable)                                             |
-| `--min-score <n>`            | number  | no       | Minimum similarity score, 0-1 (default: 0.3)                                                            |
-| `--enable-rerank <bool>`     | boolean | no       | Rerank results. Also selects the billing tier: false bills lite, true bills pro (~50x). (default: true) |
-| `--plan-version <lite\|pro>` | string  | no       | Documented billing tier. The service currently honors --enable-rerank instead, so prefer that flag      |
-| `--enable-judge <bool>`      | boolean | no       | Enable the intent-discrimination callback (default: false)                                              |
-| `--enable-rewrite <bool>`    | boolean | no       | Enable query rewriting (default: false)                                                                 |
-| `--api-key <key>`            | string  | no       | API key                                                                                                 |
-| `--base-url <url>`           | string  | no       | API base URL                                                                                            |
+| Flag                       | Type   | Required | Description                                  |
+| -------------------------- | ------ | -------- | -------------------------------------------- |
+| `--user-id <id>`           | string | yes      | User ID (required)                           |
+| `--query <text>`           | string | no       | Search query text                            |
+| `--messages <json>`        | string | no       | Messages JSON array for context-based search |
+| `--top-k <n>`              | number | no       | Number of results to return (default: 10)    |
+| `--memory-library-id <id>` | string | no       | Memory library ID                            |
+| `--api-key <key>`          | string | no       | API key                                      |
+| `--base-url <url>`         | string | no       | API base URL                                 |
 
 #### Examples
 
@@ -312,30 +189,25 @@ bl memory search --user-id user1 --query "programming preferences"
 bl memory search --user-id user1 --messages '[{"role":"user","content":"recommend a book"}]' --top-k 5
 ```
 
-```bash
-bl memory search --user-id user1 --query "preferences" --enable-rerank false --min-score 0.5
-```
-
 ### `bl memory update`
 
-| Field           | Value                                                             |
-| --------------- | ----------------------------------------------------------------- |
-| **Name**        | `memory update`                                                   |
-| **Description** | Update a memory node content                                      |
-| **Usage**       | `bl memory update --node-id <id> --user-id <id> --content <text>` |
+| Field              | Value                                                             |
+| ------------------ | ----------------------------------------------------------------- |
+| **Name**           | `memory update`                                                   |
+| **Description**    | Update a memory node content                                      |
+| **Authentication** | API Key                                                           |
+| **Usage**          | `bl memory update --node-id <id> --user-id <id> --content <text>` |
 
 #### Flags
 
-| Flag                         | Type   | Required | Description                                                            |
-| ---------------------------- | ------ | -------- | ---------------------------------------------------------------------- |
-| `--node-id <id>`             | string | yes      | Memory node ID (required)                                              |
-| `--user-id <id>`             | string | yes      | User ID (required)                                                     |
-| `--content <text>`           | string | yes      | New content for the memory node (required)                             |
-| `--memory-library-id <id>`   | string | no       | Memory library ID (non-default library)                                |
-| `--timestamp <unix-seconds>` | number | no       | When the remembered event happened (default: now)                      |
-| `--meta-data <json>`         | string | no       | Custom metadata JSON object, merged incrementally: {"source":"manual"} |
-| `--api-key <key>`            | string | no       | API key                                                                |
-| `--base-url <url>`           | string | no       | API base URL                                                           |
+| Flag                       | Type   | Required | Description                                |
+| -------------------------- | ------ | -------- | ------------------------------------------ |
+| `--node-id <id>`           | string | yes      | Memory node ID (required)                  |
+| `--user-id <id>`           | string | yes      | User ID (required)                         |
+| `--content <text>`         | string | yes      | New content for the memory node (required) |
+| `--memory-library-id <id>` | string | no       | Memory library ID (non-default library)    |
+| `--api-key <key>`          | string | no       | API key                                    |
+| `--base-url <url>`         | string | no       | API base URL                               |
 
 #### Examples
 

skills/bailian-cli/reference/model.md

@@ -7,19 +7,20 @@ Index: [index.md](index.md)
 
 ## Commands in this group
 
-| Command         | Description                                                                        |
-| --------------- | ---------------------------------------------------------------------------------- |
-| `bl model list` | Browse model families or show detailed model info in the Bailian model marketplace |
+| Command         | Authentication | Description                                                                        |
+| --------------- | -------------- | ---------------------------------------------------------------------------------- |
+| `bl model list` | Console        | Browse model families or show detailed model info in the Bailian model marketplace |
 
 ## Command details
 
 ### `bl model list`
 
-| Field           | Value                                                                                                                           |
-| --------------- | ------------------------------------------------------------------------------------------------------------------------------- |
-| **Name**        | `model list`                                                                                                                    |
-| **Description** | Browse model families or show detailed model info in the Bailian model marketplace                                              |
-| **Usage**       | `bl model list [--model <model>] [--page <n>] [--page-size <n>] [--provider <p>] [--capability <c>] [--feature <f>] [--enrich]` |
+| Field              | Value                                                                                                                           |
+| ------------------ | ------------------------------------------------------------------------------------------------------------------------------- |
+| **Name**           | `model list`                                                                                                                    |
+| **Description**    | Browse model families or show detailed model info in the Bailian model marketplace                                              |
+| **Authentication** | Console                                                                                                                         |
+| **Usage**          | `bl model list [--model <model>] [--page <n>] [--page-size <n>] [--provider <p>] [--capability <c>] [--feature <f>] [--enrich]` |
 
 #### Flags
 

skills/bailian-cli/reference/pipeline.md

@@ -7,20 +7,21 @@ Index: [index.md](index.md)
 
 ## Commands in this group
 
-| Command                | Description                                      |
-| ---------------------- | ------------------------------------------------ |
-| `bl pipeline run`      | Run a pipeline workflow definition               |
-| `bl pipeline validate` | Validate a pipeline definition without executing |
+| Command                | Authentication | Description                                      |
+| ---------------------- | -------------- | ------------------------------------------------ |
+| `bl pipeline run`      | No Auth        | Run a pipeline workflow definition               |
+| `bl pipeline validate` | No Auth        | Validate a pipeline definition without executing |
 
 ## Command details
 
 ### `bl pipeline run`
 
-| Field           | Value                                   |
-| --------------- | --------------------------------------- |
-| **Name**        | `pipeline run`                          |
-| **Description** | Run a pipeline workflow definition      |
-| **Usage**       | `bl pipeline run --file <path> [flags]` |
+| Field              | Value                                   |
+| ------------------ | --------------------------------------- |
+| **Name**           | `pipeline run`                          |
+| **Description**    | Run a pipeline workflow definition      |
+| **Authentication** | No Auth                                 |
+| **Usage**          | `bl pipeline run --file <path> [flags]` |
 
 #### Flags
 
@@ -57,11 +58,12 @@ bl pipeline run --file workflow.yaml --output json
 
 ### `bl pipeline validate`
 
-| Field           | Value                                            |
-| --------------- | ------------------------------------------------ |
-| **Name**        | `pipeline validate`                              |
-| **Description** | Validate a pipeline definition without executing |
-| **Usage**       | `bl pipeline validate --file <path>`             |
+| Field              | Value                                            |
+| ------------------ | ------------------------------------------------ |
+| **Name**           | `pipeline validate`                              |
+| **Description**    | Validate a pipeline definition without executing |
+| **Authentication** | No Auth                                          |
+| **Usage**          | `bl pipeline validate --file <path>`             |
 
 #### Flags
 

skills/bailian-cli/reference/plugin.md

@@ -7,22 +7,23 @@ Index: [index.md](index.md)
 
 ## Commands in this group
 
-| Command             | Description                                            |
-| ------------------- | ------------------------------------------------------ |
-| `bl plugin install` | Install or upgrade an allowlisted Command Pack         |
-| `bl plugin link`    | Link an allowlisted local Command Pack for development |
-| `bl plugin list`    | List installed Command Packs and their load status     |
-| `bl plugin remove`  | Remove an installed Command Pack                       |
+| Command             | Authentication | Description                                            |
+| ------------------- | -------------- | ------------------------------------------------------ |
+| `bl plugin install` | No Auth        | Install or upgrade an allowlisted Command Pack         |
+| `bl plugin link`    | No Auth        | Link an allowlisted local Command Pack for development |
+| `bl plugin list`    | No Auth        | List installed Command Packs and their load status     |
+| `bl plugin remove`  | No Auth        | Remove an installed Command Pack                       |
 
 ## Command details
 
 ### `bl plugin install`
 
-| Field           | Value                                          |
-| --------------- | ---------------------------------------------- |
-| **Name**        | `plugin install`                               |
-| **Description** | Install or upgrade an allowlisted Command Pack |
-| **Usage**       | `bl plugin install --package <name[@version]>` |
+| Field              | Value                                          |
+| ------------------ | ---------------------------------------------- |
+| **Name**           | `plugin install`                               |
+| **Description**    | Install or upgrade an allowlisted Command Pack |
+| **Authentication** | No Auth                                        |
+| **Usage**          | `bl plugin install --package <name[@version]>` |
 
 #### Flags
 
@@ -42,11 +43,12 @@ bl plugin install --package @ali/bailian-plugin-agent@beta
 
 ### `bl plugin link`
 
-| Field           | Value                                                  |
-| --------------- | ------------------------------------------------------ |
-| **Name**        | `plugin link`                                          |
-| **Description** | Link an allowlisted local Command Pack for development |
-| **Usage**       | `bl plugin link --path <directory>`                    |
+| Field              | Value                                                  |
+| ------------------ | ------------------------------------------------------ |
+| **Name**           | `plugin link`                                          |
+| **Description**    | Link an allowlisted local Command Pack for development |
+| **Authentication** | No Auth                                                |
+| **Usage**          | `bl plugin link --path <directory>`                    |
 
 #### Flags
 
@@ -62,11 +64,12 @@ bl plugin link --path ../bailian-plugin-agent
 
 ### `bl plugin list`
 
-| Field           | Value                                              |
-| --------------- | -------------------------------------------------- |
-| **Name**        | `plugin list`                                      |
-| **Description** | List installed Command Packs and their load status |
-| **Usage**       | `bl plugin list`                                   |
+| Field              | Value                                              |
+| ------------------ | -------------------------------------------------- |
+| **Name**           | `plugin list`                                      |
+| **Description**    | List installed Command Packs and their load status |
+| **Authentication** | No Auth                                            |
+| **Usage**          | `bl plugin list`                                   |
 
 #### Flags
 
@@ -84,11 +87,12 @@ bl plugin list --output json
 
 ### `bl plugin remove`
 
-| Field           | Value                               |
-| --------------- | ----------------------------------- |
-| **Name**        | `plugin remove`                     |
-| **Description** | Remove an installed Command Pack    |
-| **Usage**       | `bl plugin remove --name <package>` |
+| Field              | Value                               |
+| ------------------ | ----------------------------------- |
+| **Name**           | `plugin remove`                     |
+| **Description**    | Remove an installed Command Pack    |
+| **Authentication** | No Auth                             |
+| **Usage**          | `bl plugin remove --name <package>` |
 
 #### Flags
 

skills/bailian-cli/reference/quota.md

@@ -7,22 +7,23 @@ Index: [index.md](index.md)
 
 ## Commands in this group
 
-| Command            | Description                             |
-| ------------------ | --------------------------------------- |
-| `bl quota check`   | Check current usage against rate limits |
-| `bl quota history` | View quota change history               |
-| `bl quota list`    | View model RPM/TPM rate limits          |
-| `bl quota request` | Request a temporary quota increase      |
+| Command            | Authentication | Description                             |
+| ------------------ | -------------- | --------------------------------------- |
+| `bl quota check`   | Console        | Check current usage against rate limits |
+| `bl quota history` | Console        | View quota change history               |
+| `bl quota list`    | Console        | View model RPM/TPM rate limits          |
+| `bl quota request` | Console        | Request a temporary quota increase      |
 
 ## Command details
 
 ### `bl quota check`
 
-| Field           | Value                                      |
-| --------------- | ------------------------------------------ |
-| **Name**        | `quota check`                              |
-| **Description** | Check current usage against rate limits    |
-| **Usage**       | `bl quota check [--model <model>] [flags]` |
+| Field              | Value                                      |
+| ------------------ | ------------------------------------------ |
+| **Name**           | `quota check`                              |
+| **Description**    | Check current usage against rate limits    |
+| **Authentication** | Console                                    |
+| **Usage**          | `bl quota check [--model <model>] [flags]` |
 
 #### Flags
 
@@ -59,11 +60,12 @@ bl quota check --output json
 
 ### `bl quota history`
 
-| Field           | Value                      |
-| --------------- | -------------------------- |
-| **Name**        | `quota history`            |
-| **Description** | View quota change history  |
-| **Usage**       | `bl quota history [flags]` |
+| Field              | Value                      |
+| ------------------ | -------------------------- |
+| **Name**           | `quota history`            |
+| **Description**    | View quota change history  |
+| **Authentication** | Console                    |
+| **Usage**          | `bl quota history [flags]` |
 
 #### Flags
 
@@ -101,11 +103,12 @@ bl quota history --output json
 
 ### `bl quota list`
 
-| Field           | Value                                     |
-| --------------- | ----------------------------------------- |
-| **Name**        | `quota list`                              |
-| **Description** | View model RPM/TPM rate limits            |
-| **Usage**       | `bl quota list [--model <model>] [flags]` |
+| Field              | Value                                     |
+| ------------------ | ----------------------------------------- |
+| **Name**           | `quota list`                              |
+| **Description**    | View model RPM/TPM rate limits            |
+| **Authentication** | Console                                   |
+| **Usage**          | `bl quota list [--model <model>] [flags]` |
 
 #### Flags
 
@@ -137,11 +140,12 @@ bl quota list --output json
 
 ### `bl quota request`
 
-| Field           | Value                                                    |
-| --------------- | -------------------------------------------------------- |
-| **Name**        | `quota request`                                          |
-| **Description** | Request a temporary quota increase                       |
-| **Usage**       | `bl quota request --model <model> --tpm <value> [flags]` |
+| Field              | Value                                                    |
+| ------------------ | -------------------------------------------------------- |
+| **Name**           | `quota request`                                          |
+| **Description**    | Request a temporary quota increase                       |
+| **Authentication** | Console                                                  |
+| **Usage**          | `bl quota request --model <model> --tpm <value> [flags]` |
 
 #### Flags
 

skills/bailian-cli/reference/search.md

@@ -7,19 +7,20 @@ Index: [index.md](index.md)
 
 ## Commands in this group
 
-| Command         | Description                                          |
-| --------------- | ---------------------------------------------------- |
-| `bl search web` | Search the web using DashScope MCP WebSearch service |
+| Command         | Authentication | Description                                          |
+| --------------- | -------------- | ---------------------------------------------------- |
+| `bl search web` | API Key        | Search the web using DashScope MCP WebSearch service |
 
 ## Command details
 
 ### `bl search web`
 
-| Field           | Value                                                |
-| --------------- | ---------------------------------------------------- |
-| **Name**        | `search web`                                         |
-| **Description** | Search the web using DashScope MCP WebSearch service |
-| **Usage**       | `bl search web --query <text> [flags]`               |
+| Field              | Value                                                |
+| ------------------ | ---------------------------------------------------- |
+| **Name**           | `search web`                                         |
+| **Description**    | Search the web using DashScope MCP WebSearch service |
+| **Authentication** | API Key                                              |
+| **Usage**          | `bl search web --query <text> [flags]`               |
 
 #### Flags
 

skills/bailian-cli/reference/skill.md

@@ -7,23 +7,24 @@ Index: [index.md](index.md)
 
 ## Commands in this group
 
-| Command           | Description                                                             |
-| ----------------- | ----------------------------------------------------------------------- |
-| `bl skill add`    | Install skills from the Bailian skill registry into local agents        |
-| `bl skill init`   | Install all bailian-\* skills (one-shot bootstrap for new environments) |
-| `bl skill list`   | List registry skills and diff against local installs                    |
-| `bl skill remove` | Remove locally installed skills (registry is untouched)                 |
-| `bl skill update` | Update installed skills to the latest registry versions                 |
+| Command           | Authentication | Description                                                             |
+| ----------------- | -------------- | ----------------------------------------------------------------------- |
+| `bl skill add`    | No Auth        | Install skills from the Bailian skill registry into local agents        |
+| `bl skill init`   | No Auth        | Install all bailian-\* skills (one-shot bootstrap for new environments) |
+| `bl skill list`   | No Auth        | List registry skills and diff against local installs                    |
+| `bl skill remove` | No Auth        | Remove locally installed skills (registry is untouched)                 |
+| `bl skill update` | No Auth        | Update installed skills to the latest registry versions                 |
 
 ## Command details
 
 ### `bl skill add`
 
-| Field           | Value                                                            |
-| --------------- | ---------------------------------------------------------------- |
-| **Name**        | `skill add`                                                      |
-| **Description** | Install skills from the Bailian skill registry into local agents |
-| **Usage**       | `bl skill add --all \| --name <name,...>`                        |
+| Field              | Value                                                            |
+| ------------------ | ---------------------------------------------------------------- |
+| **Name**           | `skill add`                                                      |
+| **Description**    | Install skills from the Bailian skill registry into local agents |
+| **Authentication** | No Auth                                                          |
+| **Usage**          | `bl skill add --all \| --name <name,...>`                        |
 
 #### Flags
 
@@ -44,11 +45,12 @@ bl skill add --name spark-video,bailian-model-recommend
 
 ### `bl skill init`
 
-| Field           | Value                                                                   |
-| --------------- | ----------------------------------------------------------------------- |
-| **Name**        | `skill init`                                                            |
-| **Description** | Install all bailian-\* skills (one-shot bootstrap for new environments) |
-| **Usage**       | `bl skill init`                                                         |
+| Field              | Value                                                                   |
+| ------------------ | ----------------------------------------------------------------------- |
+| **Name**           | `skill init`                                                            |
+| **Description**    | Install all bailian-\* skills (one-shot bootstrap for new environments) |
+| **Authentication** | No Auth                                                                 |
+| **Usage**          | `bl skill init`                                                         |
 
 #### Flags
 
@@ -67,11 +69,12 @@ bl skill init
 
 ### `bl skill list`
 
-| Field           | Value                                                |
-| --------------- | ---------------------------------------------------- |
-| **Name**        | `skill list`                                         |
-| **Description** | List registry skills and diff against local installs |
-| **Usage**       | `bl skill list`                                      |
+| Field              | Value                                                |
+| ------------------ | ---------------------------------------------------- |
+| **Name**           | `skill list`                                         |
+| **Description**    | List registry skills and diff against local installs |
+| **Authentication** | No Auth                                              |
+| **Usage**          | `bl skill list`                                      |
 
 #### Flags
 
@@ -93,11 +96,12 @@ bl skill list --output json
 
 ### `bl skill remove`
 
-| Field           | Value                                                   |
-| --------------- | ------------------------------------------------------- |
-| **Name**        | `skill remove`                                          |
-| **Description** | Remove locally installed skills (registry is untouched) |
-| **Usage**       | `bl skill remove --name <all\|name,...>`                |
+| Field              | Value                                                   |
+| ------------------ | ------------------------------------------------------- |
+| **Name**           | `skill remove`                                          |
+| **Description**    | Remove locally installed skills (registry is untouched) |
+| **Authentication** | No Auth                                                 |
+| **Usage**          | `bl skill remove --name <all\|name,...>`                |
 
 #### Flags
 
@@ -117,11 +121,12 @@ bl skill remove --name all
 
 ### `bl skill update`
 
-| Field           | Value                                                   |
-| --------------- | ------------------------------------------------------- |
-| **Name**        | `skill update`                                          |
-| **Description** | Update installed skills to the latest registry versions |
-| **Usage**       | `bl skill update [--all] [--name <name,...>]`           |
+| Field              | Value                                                   |
+| ------------------ | ------------------------------------------------------- |
+| **Name**           | `skill update`                                          |
+| **Description**    | Update installed skills to the latest registry versions |
+| **Authentication** | No Auth                                                 |
+| **Usage**          | `bl skill update [--all] [--name <name,...>]`           |
 
 #### Flags
 

skills/bailian-cli/reference/text.md

@@ -7,19 +7,20 @@ Index: [index.md](index.md)
 
 ## Commands in this group
 
-| Command        | Description                                           |
-| -------------- | ----------------------------------------------------- |
-| `bl text chat` | Send a chat completion (OpenAI compatible, DashScope) |
+| Command        | Authentication | Description                                           |
+| -------------- | -------------- | ----------------------------------------------------- |
+| `bl text chat` | API Key        | Send a chat completion (OpenAI compatible, DashScope) |
 
 ## Command details
 
 ### `bl text chat`
 
-| Field           | Value                                                 |
-| --------------- | ----------------------------------------------------- |
-| **Name**        | `text chat`                                           |
-| **Description** | Send a chat completion (OpenAI compatible, DashScope) |
-| **Usage**       | `bl text chat --message <text> [flags]`               |
+| Field              | Value                                                 |
+| ------------------ | ----------------------------------------------------- |
+| **Name**           | `text chat`                                           |
+| **Description**    | Send a chat completion (OpenAI compatible, DashScope) |
+| **Authentication** | API Key                                               |
+| **Usage**          | `bl text chat --message <text> [flags]`               |
 
 #### Flags
 

skills/bailian-cli/reference/token-plan.md

@@ -7,24 +7,23 @@ Index: [index.md](index.md)
 
 ## Commands in this group
 
-| Command                        | Description                                                                            |
-| ------------------------------ | -------------------------------------------------------------------------------------- |
-| `bl token-plan add-member`     | Add a member to a Token Plan organization                                              |
-| `bl token-plan assign-seats`   | Batch assign Token Plan seats to members                                               |
-| `bl token-plan create-key`     | Create a Token Plan API key for a seat                                                 |
-| `bl token-plan list-seats`     | List Token Plan subscription seat details                                              |
-| `bl token-plan personal-key`   | Get the personal-edition TokenPlan API key (masked) for the current account            |
-| `bl token-plan personal-usage` | Query personal-edition TokenPlan usage (5h/1w percentage, subscription, addon credits) |
+| Command                      | Authentication | Description                               |
+| ---------------------------- | -------------- | ----------------------------------------- |
+| `bl token-plan add-member`   | AK/SK          | Add a member to a Token Plan organization |
+| `bl token-plan assign-seats` | AK/SK          | Batch assign Token Plan seats to members  |
+| `bl token-plan create-key`   | AK/SK          | Create a Token Plan API key for a seat    |
+| `bl token-plan list-seats`   | AK/SK          | List Token Plan subscription seat details |
 
 ## Command details
 
 ### `bl token-plan add-member`
 
-| Field           | Value                                                                  |
-| --------------- | ---------------------------------------------------------------------- |
-| **Name**        | `token-plan add-member`                                                |
-| **Description** | Add a member to a Token Plan organization                              |
-| **Usage**       | `bl token-plan add-member --account-name <name> --org-id <id> [flags]` |
+| Field              | Value                                                                  |
+| ------------------ | ---------------------------------------------------------------------- |
+| **Name**           | `token-plan add-member`                                                |
+| **Description**    | Add a member to a Token Plan organization                              |
+| **Authentication** | AK/SK                                                                  |
+| **Usage**          | `bl token-plan add-member --account-name <name> --org-id <id> [flags]` |
 
 #### Flags
 
@@ -56,11 +55,12 @@ bl token-plan add-member --account-name member1 --org-id org_123 --spec-type sta
 
 ### `bl token-plan assign-seats`
 
-| Field           | Value                                                                                         |
-| --------------- | --------------------------------------------------------------------------------------------- |
-| **Name**        | `token-plan assign-seats`                                                                     |
-| **Description** | Batch assign Token Plan seats to members                                                      |
-| **Usage**       | `bl token-plan assign-seats --workspace-id <id> --seat-type <type> --account-id <id> [flags]` |
+| Field              | Value                                                                                         |
+| ------------------ | --------------------------------------------------------------------------------------------- |
+| **Name**           | `token-plan assign-seats`                                                                     |
+| **Description**    | Batch assign Token Plan seats to members                                                      |
+| **Authentication** | AK/SK                                                                                         |
+| **Usage**          | `bl token-plan assign-seats --workspace-id <id> --seat-type <type> --account-id <id> [flags]` |
 
 #### Flags
 
@@ -88,11 +88,12 @@ bl token-plan assign-seats --workspace-id ws_456 --seat-type pro --account-id ac
 
 ### `bl token-plan create-key`
 
-| Field           | Value                                                                    |
-| --------------- | ------------------------------------------------------------------------ |
-| **Name**        | `token-plan create-key`                                                  |
-| **Description** | Create a Token Plan API key for a seat                                   |
-| **Usage**       | `bl token-plan create-key --account-id <id> --workspace-id <id> [flags]` |
+| Field              | Value                                                                    |
+| ------------------ | ------------------------------------------------------------------------ |
+| **Name**           | `token-plan create-key`                                                  |
+| **Description**    | Create a Token Plan API key for a seat                                   |
+| **Authentication** | AK/SK                                                                    |
+| **Usage**          | `bl token-plan create-key --account-id <id> --workspace-id <id> [flags]` |
 
 #### Flags
 
@@ -119,11 +120,12 @@ bl token-plan create-key --account-id acc_123 --workspace-id ws_456 --descriptio
 
 ### `bl token-plan list-seats`
 
-| Field           | Value                                     |
-| --------------- | ----------------------------------------- |
-| **Name**        | `token-plan list-seats`                   |
-| **Description** | List Token Plan subscription seat details |
-| **Usage**       | `bl token-plan list-seats [flags]`        |
+| Field              | Value                                     |
+| ------------------ | ----------------------------------------- |
+| **Name**           | `token-plan list-seats`                   |
+| **Description**    | List Token Plan subscription seat details |
+| **Authentication** | AK/SK                                     |
+| **Usage**          | `bl token-plan list-seats [flags]`        |
 
 #### Flags
 
@@ -155,49 +157,3 @@ bl token-plan list-seats --page-size 20 --status NORMAL
 ```bash
 bl token-plan list-seats --query-assigned true --seat-type standard
 ```
-
-### `bl token-plan personal-key`
-
-| Field           | Value                                                                       |
-| --------------- | --------------------------------------------------------------------------- |
-| **Name**        | `token-plan personal-key`                                                   |
-| **Description** | Get the personal-edition TokenPlan API key (masked) for the current account |
-| **Usage**       | `bl token-plan personal-key [flags]`                                        |
-
-#### Flags
-
-| Flag                           | Type   | Required | Description                                              |
-| ------------------------------ | ------ | -------- | -------------------------------------------------------- |
-| `--console-region <region>`    | string | no       | Console gateway region (e.g. cn-beijing, ap-southeast-1) |
-| `--console-site <site>`        | string | no       | Console site: domestic, international                    |
-| `--console-switch-agent <uid>` | number | no       | Switch agent UID for delegated access                    |
-| `--workspace-id <id>`          | string | no       | Workspace ID (env: BAILIAN_WORKSPACE_ID)                 |
-
-#### Examples
-
-```bash
-bl token-plan personal-key
-```
-
-### `bl token-plan personal-usage`
-
-| Field           | Value                                                                                  |
-| --------------- | -------------------------------------------------------------------------------------- |
-| **Name**        | `token-plan personal-usage`                                                            |
-| **Description** | Query personal-edition TokenPlan usage (5h/1w percentage, subscription, addon credits) |
-| **Usage**       | `bl token-plan personal-usage [flags]`                                                 |
-
-#### Flags
-
-| Flag                           | Type   | Required | Description                                              |
-| ------------------------------ | ------ | -------- | -------------------------------------------------------- |
-| `--console-region <region>`    | string | no       | Console gateway region (e.g. cn-beijing, ap-southeast-1) |
-| `--console-site <site>`        | string | no       | Console site: domestic, international                    |
-| `--console-switch-agent <uid>` | number | no       | Switch agent UID for delegated access                    |
-| `--workspace-id <id>`          | string | no       | Workspace ID (env: BAILIAN_WORKSPACE_ID)                 |
-
-#### Examples
-
-```bash
-bl token-plan personal-usage
-```

skills/bailian-cli/reference/update.md

@@ -7,19 +7,20 @@ Index: [index.md](index.md)
 
 ## Commands in this group
 
-| Command     | Description                                         |
-| ----------- | --------------------------------------------------- |
-| `bl update` | Update the CLI to the latest or a specified version |
+| Command     | Authentication | Description                                         |
+| ----------- | -------------- | --------------------------------------------------- |
+| `bl update` | No Auth        | Update the CLI to the latest or a specified version |
 
 ## Command details
 
 ### `bl update`
 
-| Field           | Value                                               |
-| --------------- | --------------------------------------------------- |
-| **Name**        | `update`                                            |
-| **Description** | Update the CLI to the latest or a specified version |
-| **Usage**       | `bl update [--to <version>]`                        |
+| Field              | Value                                               |
+| ------------------ | --------------------------------------------------- |
+| **Name**           | `update`                                            |
+| **Description**    | Update the CLI to the latest or a specified version |
+| **Authentication** | No Auth                                             |
+| **Usage**          | `bl update [--to <version>]`                        |
 
 #### Flags