feat(quota): split --delete into a dedicated quota delete command

packages/cli/src/commands.ts

@@ -85,6 +85,7 @@ import {
   workspaceList,
   quotaList,
   quotaUpdate,
+  quotaDelete,
   quotaHistory,
   quotaCheck,
   permissionList,
@@ -246,6 +247,7 @@ export const commands: Record<string, AnyCommand> = {
   "workspace list": workspaceList,
   "quota list": quotaList,
   "quota update": quotaUpdate,
+  "quota delete": quotaDelete,
   "quota history": quotaHistory,
   "quota check": quotaCheck,
   "permission list": permissionList,

packages/commands/src/commands/quota/delete.ts

@@ -0,0 +1,71 @@
+import { defineCommand, detectOutputFormat, modelsLimitsPath } from "bailian-cli-core";
+import { emitResult, confirmDangerousAction } from "bailian-cli-runtime";
+
+export default defineCommand({
+  description: {
+    "en-US": "Clear all custom rate limits (QPM/TPM) for a model",
+    "zh-CN": "清除模型的所有自定义限流配置（QPM/TPM）",
+  },
+  auth: "apiKey",
+  usageArgs: "--model <model> [--yes]",
+  flags: {
+    model: {
+      type: "string",
+      valueHint: "<model>",
+      description: { "en-US": "Model name (required)", "zh-CN": "模型名称（必填）" },
+      required: true,
+    },
+    yes: {
+      type: "switch",
+      description: {
+        "en-US": "Skip the confirmation prompt",
+        "zh-CN": "跳过确认提示",
+      },
+    },
+  },
+  exampleArgs: ["--model qwen-plus", "--model qwen-plus --yes", "--model qwen-plus --output json"],
+  notes: [
+    {
+      "en-US":
+        "Irreversible — the server-side OVERLAY is reset to defaults, so your custom QPM/TPM configuration is permanently removed.",
+      "zh-CN":
+        "该操作不可撤销——服务端 OVERLAY 会重置为默认值，你的自定义 QPM/TPM 配置将被永久删除。",
+    },
+    {
+      "en-US": "Requires confirmation; pass --yes to skip the prompt in scripts.",
+      "zh-CN": "需要确认；脚本中可加 --yes 跳过交互提示。",
+    },
+  ],
+  async run(ctx) {
+    const { settings, flags } = ctx;
+    const modelName = flags.model;
+    const format = detectOutputFormat(settings.output);
+
+    const body = { models: [{ model: modelName, operation_type: "DELETE" }] };
+
+    if (settings.dryRun) {
+      emitResult(
+        { endpoint: ctx.client.url(modelsLimitsPath()), method: "POST", request: body },
+        format,
+      );
+      return;
+    }
+
+    await confirmDangerousAction(
+      `Clear all custom rate limits for model ${modelName}.\nYour custom QPM/TPM configuration will be removed.`,
+      flags.yes ?? false,
+    );
+
+    const result = await ctx.client.requestJson<{ request_id?: string }>({
+      path: modelsLimitsPath(),
+      method: "POST",
+      body,
+    });
+
+    if (format === "json") {
+      emitResult({ model: modelName, ...result }, format);
+      return;
+    }
+    process.stdout.write(`Rate limits cleared for "${modelName}".\n`);
+  },
+});

packages/commands/src/commands/quota/update.ts

@@ -1,16 +1,16 @@
 import { defineCommand, detectOutputFormat, modelsLimitsPath } from "bailian-cli-core";
-import { emitResult, confirmDangerousAction } from "bailian-cli-runtime";
+import { emitResult } from "bailian-cli-runtime";
 import { formatNumber } from "../shared/format.ts";
 
 const MINUTE_SECONDS = 60;
 
 export default defineCommand({
   description: {
-    "en-US": "Update model rate limits (QPM/TPM), or clear them with --delete",
-    "zh-CN": "更新模型限流配置（QPM/TPM），或使用 --delete 清除配置",
+    "en-US": "Update model rate limits (QPM/TPM)",
+    "zh-CN": "更新模型限流配置（QPM/TPM）",
   },
   auth: "apiKey",
-  usageArgs: "--model <model> [--rpm <n>] [--tpm <n>] [--delete] [--yes]",
+  usageArgs: "--model <model> [--rpm <n>] [--tpm <n>]",
   flags: {
     model: {
       type: "string",
@@ -34,38 +34,18 @@ export default defineCommand({
         "zh-CN": "每分钟最大 Token 数（TPM）",
       },
     },
-    delete: {
-      type: "switch",
-      description: {
-        "en-US": "Clear all custom rate limits for the model",
-        "zh-CN": "清除该模型的所有自定义限流配置",
-      },
-    },
-    yes: {
-      type: "switch",
-      description: {
-        "en-US": "Skip the confirmation prompt for --delete",
-        "zh-CN": "使用 --delete 时跳过确认提示",
-      },
-    },
   },
   exampleArgs: [
     "--model qwen-plus --rpm 60 --tpm 100000",
     "--model qwen3-max --tpm 500000",
-    "--model qwen-plus --delete",
-    "--model qwen-plus --delete --yes",
     "--model qwen-plus --rpm 60 --output json",
   ],
   notes: [
     {
       "en-US":
-        "Fields you omit keep their current values (server-side OVERLAY merge); --delete clears all custom limits.",
+        'Fields you omit keep their current values (server-side OVERLAY merge). Clear all custom limits with the "quota delete" command instead.',
       "zh-CN":
-        "未指定的字段将保留当前值（服务端 OVERLAY 合并）；--delete 会清除所有自定义限流配置。",
-    },
-    {
-      "en-US": "--delete requires confirmation; pass --yes to skip the prompt in scripts.",
-      "zh-CN": "--delete 需要确认；脚本中可加 --yes 跳过交互提示。",
+        "未指定的字段将保留当前值（服务端 OVERLAY 合并）。清除全部自定义限流配置请改用 “quota delete” 命令。",
     },
     {
       "en-US":
@@ -74,10 +54,8 @@ export default defineCommand({
     },
   ],
   validate: (flags) => {
-    if (flags.delete && (flags.rpm !== undefined || flags.tpm !== undefined))
-      return "--delete cannot be combined with --rpm/--tpm.";
-    if (!flags.delete && flags.rpm === undefined && flags.tpm === undefined)
-      return "one of --rpm / --tpm / --delete is required.";
+    if (flags.rpm === undefined && flags.tpm === undefined)
+      return "one of --rpm / --tpm is required.";
     if (flags.rpm !== undefined && flags.rpm < 0) return "--rpm must be a non-negative number.";
     if (flags.tpm !== undefined && flags.tpm < 0) return "--tpm must be a non-negative number.";
     return undefined;
@@ -88,17 +66,13 @@ export default defineCommand({
     const format = detectOutputFormat(settings.output);
 
     const entry: Record<string, unknown> = { model: modelName };
-    if (flags.delete) {
-      entry.operation_type = "DELETE";
-    } else {
-      if (flags.rpm !== undefined) {
-        entry.request_limit = flags.rpm;
-        entry.request_limit_period = MINUTE_SECONDS;
-      }
-      if (flags.tpm !== undefined) {
-        entry.usage_limit = flags.tpm;
-        entry.usage_limit_period = MINUTE_SECONDS;
-      }
+    if (flags.rpm !== undefined) {
+      entry.request_limit = flags.rpm;
+      entry.request_limit_period = MINUTE_SECONDS;
+    }
+    if (flags.tpm !== undefined) {
+      entry.usage_limit = flags.tpm;
+      entry.usage_limit_period = MINUTE_SECONDS;
     }
     const body = { models: [entry] };
 
@@ -110,13 +84,6 @@ export default defineCommand({
       return;
     }
 
-    if (flags.delete) {
-      await confirmDangerousAction(
-        `Clear all custom rate limits for model ${modelName}.\nYour custom QPM/TPM configuration will be removed.`,
-        flags.yes ?? false,
-      );
-    }
-
     const result = await ctx.client.requestJson<{ request_id?: string }>({
       path: modelsLimitsPath(),
       method: "POST",
@@ -127,11 +94,6 @@ export default defineCommand({
       emitResult({ model: modelName, ...result }, format);
       return;
     }
-
-    if (flags.delete) {
-      process.stdout.write(`Rate limits cleared for "${modelName}".\n`);
-      return;
-    }
     const parts: string[] = [];
     if (flags.rpm !== undefined) parts.push(`QPM ${formatNumber(flags.rpm)}`);
     if (flags.tpm !== undefined) parts.push(`TPM ${formatNumber(flags.tpm)}`);

packages/commands/src/index.ts

@@ -88,6 +88,7 @@ export { default as modelList } from "./commands/model/list.ts";
 export { default as workspaceList } from "./commands/workspace/list.ts";
 export { default as quotaList } from "./commands/quota/list.ts";
 export { default as quotaUpdate } from "./commands/quota/update.ts";
+export { default as quotaDelete } from "./commands/quota/delete.ts";
 export { default as quotaHistory } from "./commands/quota/history.ts";
 export { default as quotaCheck } from "./commands/quota/check.ts";
 export { default as permissionList } from "./commands/permission/list.ts";

packages/commands/tests/e2e/quota.e2e.test.ts

@@ -31,15 +31,20 @@ describe("e2e: quota", () => {
     expect(stderr).toContain("--model");
     expect(stderr).toContain("--rpm");
     expect(stderr).toContain("--tpm");
-    expect(stderr).toContain("--delete");
+  });
+
+  test("quota delete --help 正常退出", async () => {
+    const { stderr, exitCode } = await runCommandHelp(QUOTA_ROUTES, ["quota", "delete", "--help"]);
+    expect(exitCode, stderr).toBe(0);
+    expect(stderr).toContain("--model");
     expect(stderr).toContain("--yes");
+    expect(stderr).toContain("bl quota delete --model qwen-plus");
   });
 
   test("quota request 作为 quota update 的兼容别名可用", async () => {
     const { stderr, exitCode } = await runCommandHelp(QUOTA_ROUTES, ["quota", "request", "--help"]);
     expect(exitCode, stderr).toBe(0);
     expect(stderr).toContain("--rpm");
-    expect(stderr).toContain("--delete");
   });
 
   test("quota history --help 正常退出", async () => {
@@ -68,36 +73,41 @@ describe("e2e: quota", () => {
     expect(stderr).toContain("at least 1 minute");
   });
 
-  test("quota update 缺少 --rpm/--tpm/--delete 报用法错误", async () => {
+  test("quota update 缺少 --rpm/--tpm 报用法错误", async () => {
     const { stderr, exitCode } = await runCommandE2e(QUOTA_ROUTES, [
       "quota",
       "update",
       "--model",
       "qwen-plus",
     ]);
     expect(exitCode).toBe(2);
-    expect(stderr).toContain("one of --rpm / --tpm / --delete");
+    expect(stderr).toContain("one of --rpm / --tpm");
   });
 
-  test("quota update --delete 与 --rpm 互斥", async () => {
+  test("quota update 不再接受 --delete", async () => {
     const { stderr, exitCode } = await runCommandE2e(QUOTA_ROUTES, [
       "quota",
       "update",
       "--model",
       "qwen-plus",
       "--delete",
-      "--rpm",
-      "60",
     ]);
     expect(exitCode).toBe(2);
-    expect(stderr).toContain("cannot be combined");
+    expect(stderr).toContain("Unknown flag");
   });
 
-  test("quota update --delete 非 TTY 无 --yes 报 USAGE (2)", async () => {
+  test("quota delete 缺少 --model 报用法错误", async () => {
+    // 裸 `quota delete`（无任何 flag）会渲染 help 并正常退出，需带 flag 触发必填校验
+    const { stderr, exitCode } = await runCommandE2e(QUOTA_ROUTES, ["quota", "delete", "--yes"]);
+    expect(exitCode).toBe(2);
+    expect(stderr).toContain("Missing required flag: --model");
+  });
+
+  test("quota delete 非 TTY 无 --yes 报 USAGE (2)", async () => {
     // 注入假 key 让 apiKey 鉴权通过；确认门在发任何网络请求前触发
     const { stderr, exitCode } = await runCommandE2e(
       QUOTA_ROUTES,
-      ["quota", "update", "--model", "qwen-plus", "--delete"],
+      ["quota", "delete", "--model", "qwen-plus"],
       { DASHSCOPE_API_KEY: "sk-e2e-quota-delete" },
     );
     expect(exitCode).toBe(2);
@@ -196,13 +206,12 @@ describe("e2e: quota", () => {
     expect(entry?.usage_limit_period).toBe(60);
   });
 
-  test("quota update --delete --dry-run 输出 DELETE 操作", async () => {
+  test("quota delete --dry-run 输出 DELETE 操作", async () => {
     const { stdout, stderr, exitCode } = await runCommandE2e(QUOTA_ROUTES, [
       "quota",
-      "update",
+      "delete",
       "--model",
       "qwen-plus",
-      "--delete",
       "--dry-run",
       "--output",
       "json",
@@ -211,6 +220,7 @@ describe("e2e: quota", () => {
     const data = parseStdoutJson<{
       request?: { models?: { model?: string; operation_type?: string }[] };
     }>(stdout);
+    expect(data.request?.models?.[0]?.model).toBe("qwen-plus");
     expect(data.request?.models?.[0]?.operation_type).toBe("DELETE");
   });
 
@@ -285,8 +295,8 @@ describe("e2e: quota", () => {
   });
 });
 
-// 真实调用 GET /api/v1/models/limits。quota update 只测 --dry-run——live POST
-// 会真实改写账号限流，不做 e2e。
+// 真实调用 GET /api/v1/models/limits。quota update / quota delete 只测
+// --dry-run——live POST 会真实改写账号限流，不做 e2e。
 describe.skipIf(!isDashScopeE2EReady())("e2e: quota（DashScope）", () => {
   test("quota list 文本输出正常退出", async () => {
     const { stderr, exitCode } = await runCommandE2e(QUOTA_ROUTES, [

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

@@ -103,6 +103,7 @@ export const ADVISOR_ROUTES: E2eRouteExports = {
 export const QUOTA_ROUTES: E2eRouteExports = {
   "quota list": "quotaList",
   "quota update": "quotaUpdate",
+  "quota delete": "quotaDelete",
   // Backward-compatible alias of "quota update".
   "quota request": "quotaUpdate",
   "quota history": "quotaHistory",

skills/bailian-cli/reference/index.md

@@ -81,9 +81,10 @@ Use this index for the skill-scoped quick index and global flags.
 | `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 delete`                | API Key        | Clear all custom rate limits (QPM/TPM) for a model                                               | [quota.md](quota.md)           |
 | `bl quota history`               | Console        | View quota change history                                                                        | [quota.md](quota.md)           |
 | `bl quota list`                  | API Key        | View model rate limits (QPM/TPM, account and workspace level)                                    | [quota.md](quota.md)           |
-| `bl quota update`                | API Key        | Update model rate limits (QPM/TPM), or clear them with --delete                                  | [quota.md](quota.md)           |
+| `bl quota update`                | API Key        | Update model rate limits (QPM/TPM)                                                               | [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)           |
@@ -122,7 +123,7 @@ Use this index for the skill-scoped quick index and global flags.
 | `permission` | `grant`, `list`, `revoke`                                                                                                                                                                                                                                                                                                                                                                                                                                                                   | [permission.md](permission.md) |
 | `pipeline`   | `run`, `validate`                                                                                                                                                                                                                                                                                                                                                                                                                                                                           | [pipeline.md](pipeline.md)     |
 | `plugin`     | `install`, `link`, `list`, `remove`                                                                                                                                                                                                                                                                                                                                                                                                                                                         | [plugin.md](plugin.md)         |
-| `quota`      | `check`, `history`, `list`, `update`                                                                                                                                                                                                                                                                                                                                                                                                                                                        | [quota.md](quota.md)           |
+| `quota`      | `check`, `delete`, `history`, `list`, `update`                                                                                                                                                                                                                                                                                                                                                                                                                                              | [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)             |