Compare commits

..

1 Commits

Author SHA1 Message Date
故璃 fd96fd664c feat(quota): split --delete into a dedicated quota delete command
The destructive --delete flag sat on "quota update", but the --yes
high-risk confirmation guards command paths rather than individual flags.
Promote it to its own "quota delete" command with a --yes guardrail, and
reduce "quota update" to QPM/TPM updates only.
2026-09-01 17:35:46 +08:00
27 changed files with 279 additions and 358 deletions
-10
View File
@@ -6,16 +6,6 @@ The format follows [Keep a Changelog](https://keepachangelog.com/en/1.1.0/), and
[中文版](CHANGELOG.zh.md) · [README](README.md) · [Contributing](CONTRIBUTING.md)
## [1.18.2] - 2026-09-01
### Changed
- **Confirmation before deleting or clearing resources** — `bl finetune delete`, `bl deploy delete`, `bl dataset delete`, and `bl quota update --delete` now ask for confirmation; pass `--yes` for non-interactive use.
### Fixed
- **Skill installation reliability** — `bl skill init` now retries transient network failures, and completed Skill updates are no longer reported as failed when backup cleanup is blocked.
## [1.18.1] - 2026-08-28
### Removed
-10
View File
@@ -6,16 +6,6 @@
[English](CHANGELOG.md) · [README](README.zh.md) · [参与贡献](CONTRIBUTING.zh.md)
## [1.18.2] - 2026-09-01
### 变更
- **删除与清除操作增加确认** —— `bl finetune delete``bl deploy delete``bl dataset delete``bl quota update --delete` 现在会在执行前要求确认;非交互场景请传入 `--yes`
### 修复
- **Skill 安装可靠性** —— `bl skill init` 现在会重试临时性网络故障;备份清理受阻时,已完成的 Skill 更新不再被误报为失败。
## [1.18.1] - 2026-08-28
### 已移除
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "bailian-cli",
"version": "1.18.2",
"version": "1.18.1",
"description": "CLI for Aliyun Model Studio (DashScope) AI Platform.",
"keywords": [
"agent",
+2 -12
View File
@@ -181,13 +181,7 @@ function atomicSwap(tmpDir, catalogDir) {
if (existsSync(backup) && !existsSync(catalogDir)) renameSync(backup, catalogDir);
throw err;
}
// Best-effort cleanup (symmetric with core skills/extract.ts): the swap already
// succeeded, so a backup deletion failure must not fail the pre-download
try {
if (existsSync(backup)) rmSync(backup, { recursive: true, force: true });
} catch {
/* keep the backup on disk rather than report a completed swap as failed */
}
if (existsSync(backup)) rmSync(backup, { recursive: true, force: true });
}
async function main() {
@@ -220,11 +214,7 @@ async function main() {
}
atomicSwap(tmpDir, catalogDir);
} catch (err) {
try {
if (existsSync(tmpDir)) rmSync(tmpDir, { recursive: true, force: true });
} catch {
/* cleanup must not mask the original error */
}
if (existsSync(tmpDir)) rmSync(tmpDir, { recursive: true, force: true });
throw err;
}
+2
View File
@@ -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,
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "bailian-cli-commands",
"version": "1.18.2",
"version": "1.18.1",
"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": {
@@ -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`);
},
});
+15 -53
View File
@@ -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)}`);
+1
View File
@@ -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";
+25 -15
View File
@@ -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 () => {
@@ -68,7 +73,7 @@ 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",
@@ -76,28 +81,33 @@ describe("e2e: quota", () => {
"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: quotaDashScope", () => {
test("quota list 文本输出正常退出", async () => {
const { stderr, exitCode } = await runCommandE2e(QUOTA_ROUTES, [
@@ -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",
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "bailian-cli-core",
"version": "1.18.2",
"version": "1.18.1",
"description": "Core SDK for bailian-cli. See https://www.npmjs.com/package/bailian-cli for usage.",
"homepage": "https://bailian.console.aliyun.com/cli",
"bugs": {
+1 -4
View File
@@ -37,8 +37,6 @@ const MODELS_FILE = "models.jsonl";
const THROTTLE_MS = 12 * 60 * 60 * 1000; // 12h
/** Tighter than the interactive default: the silent channel must not stall `bl advisor recommend` */
const INDEX_TIMEOUT_MS = 3000;
/** No retries on the silent channel: a failed sync simply tries again on the next recommend */
const FETCH_ATTEMPTS = 1;
interface SyncState {
lastChecked: number;
@@ -110,7 +108,7 @@ function wikiLockNeedsBackfill(contentHash: string): boolean {
/** Fetch skills/index.json via the shared registry client and extract the wiki skill entry; returns null on any failure */
async function fetchIndexEntry(): Promise<SkillIndexEntry | null> {
try {
const index = await fetchSkillsIndex(INDEX_TIMEOUT_MS, FETCH_ATTEMPTS);
const index = await fetchSkillsIndex(INDEX_TIMEOUT_MS);
return index.skills[WIKI_SKILL_NAME] ?? null;
} catch {
return null;
@@ -162,7 +160,6 @@ export async function maybeSyncWikiData(): Promise<boolean> {
entry,
detectInstalledAgents(),
previousLinks,
FETCH_ATTEMPTS,
);
recordWikiInLock(record.lockEntry);
} catch {
+1 -8
View File
@@ -100,12 +100,5 @@ export function atomicSwap(tmpDir: string, destDir: string): void {
if (existsSync(backup) && !existsSync(destDir)) renameSync(backup, destDir);
throw err;
}
// Best-effort cleanup: the swap already succeeded, so a backup deletion failure
// (permissions, host safe-delete guards on large dirs) must not fail the install;
// leftover .old-* dirs are inert (skill status scans ignore them)
try {
if (existsSync(backup)) rmSync(backup, { recursive: true, force: true });
} catch {
/* keep the backup on disk rather than report a completed install as failed */
}
if (existsSync(backup)) rmSync(backup, { recursive: true, force: true });
}
+4 -17
View File
@@ -61,22 +61,12 @@ export async function installSkillFromBuffer(
atomicSwap(tmpDir, dest);
return { name, path: dest, meta };
} finally {
// Best-effort cleanup: on failure paths this must not mask the original error,
// and on success the dir is already renamed away (existsSync → false)
try {
if (existsSync(tmpDir)) rmSync(tmpDir, { recursive: true, force: true });
} catch {
/* leave the temp dir rather than hide the real error */
}
if (existsSync(tmpDir)) rmSync(tmpDir, { recursive: true, force: true });
}
}
/** Install a single skill by index entry (download + validate + write to disk) */
export async function installSkill(
name: string,
entry: SkillIndexEntry,
downloadAttempts?: number,
): Promise<InstalledSkill> {
export async function installSkill(name: string, entry: SkillIndexEntry): Promise<InstalledSkill> {
if (entry.compression && entry.compression !== "tar.br") {
throw new BailianError(
`Skill ${name} uses unsupported compression format: ${entry.compression}`,
@@ -84,7 +74,7 @@ export async function installSkill(
"Upgrade bailian-cli to the latest version and retry",
);
}
const buffer = await downloadSkillAsset(name, entry, downloadAttempts);
const buffer = await downloadSkillAsset(name, entry);
return installSkillFromBuffer(name, buffer, entry.contentHash);
}
@@ -126,17 +116,14 @@ export interface SkillInstallRecord {
* entry (batch writeSkillLock for commands, best-effort upsertSkillLockEntry for silent channels).
* recordedLinks = the skill's previously recorded fan-out paths from the lock; lets the
* fan-out replace copy-fallback artifacts and keeps unvisited paths reclaimable.
* downloadAttempts = registry fetch attempts (undefined → interactive default; silent
* background channels pass 1 to fail fast instead of stalling the host command).
*/
export async function installSkillWithFanout(
name: string,
entry: SkillIndexEntry,
agents: AgentTarget[] = detectInstalledAgents(),
recordedLinks: string[] = [],
downloadAttempts?: number,
): Promise<SkillInstallRecord> {
await installSkill(name, entry, downloadAttempts);
await installSkill(name, entry);
const fanout = fanOutSkillToAgents(name, agents, recordedLinks);
return {
lockEntry: buildSkillLockEntry(entry, fanout.links),
+74 -95
View File
@@ -1,6 +1,5 @@
import { BailianError } from "../errors/base.ts";
import { ExitCode } from "../errors/codes.ts";
import { withRetry } from "../utils/retry.ts";
import type { SkillIndexEntry, SkillsIndex } from "./types.ts";
/**
@@ -10,10 +9,8 @@ import type { SkillIndexEntry, SkillsIndex } from "./types.ts";
*/
const DEFAULT_REGISTRY_BASE_URL = "https://bailian-wiki.oss-cn-hangzhou.aliyuncs.com/skills";
const INDEX_TIMEOUT_MS = 30_000;
const INDEX_TIMEOUT_MS = 10_000;
const ASSET_TIMEOUT_MS = 120_000;
/** Interactive channels retry transient failures; silent background channels pass 1 to fail fast */
const DEFAULT_ATTEMPTS = 3;
export function getSkillRegistryBaseUrl(): string {
const override = process.env.BAILIAN_SKILL_REGISTRY_URL?.trim();
@@ -23,64 +20,55 @@ export function getSkillRegistryBaseUrl(): string {
/**
* Fetch the remote skill index. No local caching — the diff comparison is always
* "live remote index vs local skill-lock.json".
* Silent background channels (advisor sync) may pass a tighter timeout and attempts=1
* than the interactive defaults.
* Silent background channels (advisor sync) may pass a tighter timeout than the interactive default.
*/
export async function fetchSkillsIndex(
timeoutMs: number = INDEX_TIMEOUT_MS,
attempts: number = DEFAULT_ATTEMPTS,
): Promise<SkillsIndex> {
return withRetry(
async () => {
const url = `${getSkillRegistryBaseUrl()}/index.json`;
let res: Response;
try {
res = await fetch(url, { signal: AbortSignal.timeout(timeoutMs) });
} catch (err) {
throw new BailianError(
`Cannot access skill registry: ${url}`,
ExitCode.NETWORK,
"Check network connectivity; if using a private mirror, verify BAILIAN_SKILL_REGISTRY_URL configuration",
{ cause: err },
);
}
if (!res.ok) {
throw new BailianError(
`Skill registry returned HTTP ${res.status}: ${url}`,
ExitCode.NETWORK,
res.status === 404
? "Skill index not yet published or registry URL is incorrect; confirm the publisher has generated index.json"
: "Remote error, retry later",
);
}
let parsed: unknown;
try {
parsed = await res.json();
} catch (err) {
throw new BailianError(
"Skill index index.json is not valid JSON",
ExitCode.GENERAL,
"Remote may be in the middle of publishing, retry later",
{ cause: err },
);
}
const index = parsed as SkillsIndex;
if (
typeof index !== "object" ||
index === null ||
typeof index.skills !== "object" ||
index.skills === null
) {
throw new BailianError(
"Skill index index.json has invalid structure",
ExitCode.GENERAL,
"Retry later or contact the publisher",
);
}
return index;
},
{ attempts },
);
export async function fetchSkillsIndex(timeoutMs: number = INDEX_TIMEOUT_MS): Promise<SkillsIndex> {
const url = `${getSkillRegistryBaseUrl()}/index.json`;
let res: Response;
try {
res = await fetch(url, { signal: AbortSignal.timeout(timeoutMs) });
} catch (err) {
throw new BailianError(
`Cannot access skill registry: ${url}`,
ExitCode.NETWORK,
"Check network connectivity; if using a private mirror, verify BAILIAN_SKILL_REGISTRY_URL configuration",
{ cause: err },
);
}
if (!res.ok) {
throw new BailianError(
`Skill registry returned HTTP ${res.status}: ${url}`,
ExitCode.NETWORK,
res.status === 404
? "Skill index not yet published or registry URL is incorrect; confirm the publisher has generated index.json"
: "Remote error, retry later",
);
}
let parsed: unknown;
try {
parsed = await res.json();
} catch (err) {
throw new BailianError(
"Skill index index.json is not valid JSON",
ExitCode.GENERAL,
"Remote may be in the middle of publishing, retry later",
{ cause: err },
);
}
const index = parsed as SkillsIndex;
if (
typeof index !== "object" ||
index === null ||
typeof index.skills !== "object" ||
index.skills === null
) {
throw new BailianError(
"Skill index index.json has invalid structure",
ExitCode.GENERAL,
"Retry later or contact the publisher",
);
}
return index;
}
/**
@@ -96,38 +84,29 @@ export function resolveAssetFileName(entry?: SkillIndexEntry): string {
}
/** Download the tar.br archive for a single skill (one skill = one GET) */
export async function downloadSkillAsset(
name: string,
entry?: SkillIndexEntry,
attempts: number = DEFAULT_ATTEMPTS,
): Promise<Buffer> {
return withRetry(
async () => {
const url = `${getSkillRegistryBaseUrl()}/${name}/${resolveAssetFileName(entry)}`;
let res: Response;
try {
res = await fetch(url, { signal: AbortSignal.timeout(ASSET_TIMEOUT_MS) });
} catch (err) {
throw new BailianError(
`Failed to download skill ${name}: ${url}`,
ExitCode.NETWORK,
"Network error, retryable",
{
cause: err,
},
);
}
if (!res.ok) {
throw new BailianError(
`Failed to download skill ${name}: HTTP ${res.status}`,
ExitCode.NETWORK,
res.status === 404
? "index.json and skill object are temporarily inconsistent (publishing in progress), retry later"
: "Remote error, retry later",
);
}
return Buffer.from(await res.arrayBuffer());
},
{ attempts },
);
export async function downloadSkillAsset(name: string, entry?: SkillIndexEntry): Promise<Buffer> {
const url = `${getSkillRegistryBaseUrl()}/${name}/${resolveAssetFileName(entry)}`;
let res: Response;
try {
res = await fetch(url, { signal: AbortSignal.timeout(ASSET_TIMEOUT_MS) });
} catch (err) {
throw new BailianError(
`Failed to download skill ${name}: ${url}`,
ExitCode.NETWORK,
"Network error, retryable",
{
cause: err,
},
);
}
if (!res.ok) {
throw new BailianError(
`Failed to download skill ${name}: HTTP ${res.status}`,
ExitCode.NETWORK,
res.status === 404
? "index.json and skill object are temporarily inconsistent (publishing in progress), retry later"
: "Remote error, retry later",
);
}
return Buffer.from(await res.arrayBuffer());
}
+10 -90
View File
@@ -1,8 +1,8 @@
import { existsSync, lstatSync, mkdtempSync, readFileSync, readdirSync, rmSync } from "node:fs";
import { createHash } from "node:crypto";
import { tmpdir } from "node:os";
import { join } from "node:path";
import { brotliCompressSync } from "node:zlib";
import { existsSync, lstatSync, mkdtempSync, readFileSync, readdirSync, rmSync } from "fs";
import { createHash } from "crypto";
import { tmpdir } from "os";
import { join } from "path";
import { brotliCompressSync } from "zlib";
import tar from "tar-stream";
import { afterEach, expect, test, vi } from "vite-plus/test";
import { BailianError } from "../src/errors/base.ts";
@@ -10,18 +10,6 @@ import type { AgentTarget } from "../src/skills/agents.ts";
import { isSafeEntryName } from "../src/skills/extract.ts";
import { installSkillFromBuffer, installSkillWithFanout } from "../src/skills/installer.ts";
import { getSkillsDir } from "../src/skills/lock.ts";
import { downloadSkillAsset, fetchSkillsIndex } from "../src/skills/registry.ts";
/** rmSync wrapped in a spy so tests can simulate host deletion guards (e.g. safe-delete) */
const fsMocks = vi.hoisted(() => ({
rmSync: vi.fn(),
}));
vi.mock("node:fs", async (importOriginal) => {
const actual = await importOriginal<typeof import("node:fs")>();
fsMocks.rmSync.mockImplementation(actual.rmSync);
return { ...actual, rmSync: fsMocks.rmSync };
});
/** Run in an isolated temp config dir, restore env afterwards. */
async function inTempConfigDir(fn: () => Promise<void>): Promise<void> {
@@ -237,83 +225,15 @@ test("fanout install: downloads, links agents, and builds lock entry with merged
});
});
test("fanout install: download failure exhausts retries and leaves no canonical dir", async () => {
test("fanout install: download failure surfaces as BailianError and leaves no canonical dir", async () => {
await inTempConfigDir(async () => {
const fetchMock = vi.fn(async () => ({ ok: false, status: 404 }));
vi.stubGlobal("fetch", fetchMock);
vi.stubGlobal(
"fetch",
vi.fn(async () => ({ ok: false, status: 404 })),
);
await expect(
installSkillWithFanout("demo", { contentHash: "sha256:whatever" }, []),
).rejects.toThrow(BailianError);
expect(fetchMock).toHaveBeenCalledTimes(3);
expect(existsSync(join(getSkillsDir(), "demo"))).toBe(false);
});
});
// ---- host deletion guards (safe-delete): backup cleanup must not fail a completed install ----
const GUARD_ERROR =
'[safe-delete][SAFE_DELETE_BULK_CONFIRM_REQUIRED] {"count":1583,"threshold":500}';
test("installer: guard blocking backup deletion does not fail the install", async () => {
await inTempConfigDir(async () => {
await installSkillFromBuffer("demo", await buildTarBr({ "SKILL.md": VALID_SKILL_MD }));
fsMocks.rmSync.mockImplementationOnce(() => {
throw new Error(GUARD_ERROR);
});
const v2 = "---\nname: demo\ndescription: demo skill v2\n---\n";
const installed = await installSkillFromBuffer("demo", await buildTarBr({ "SKILL.md": v2 }));
expect(installed.name).toBe("demo");
expect(readFileSync(join(getSkillsDir(), "demo", "SKILL.md"), "utf-8")).toBe(v2);
// The blocked backup stays on disk but is inert (status scans ignore .old-*)
const leftovers = readdirSync(getSkillsDir()).filter((entry) => entry.startsWith("demo.old-"));
expect(leftovers).toHaveLength(1);
});
});
test("installer: temp cleanup failure does not mask the original error", async () => {
await inTempConfigDir(async () => {
fsMocks.rmSync.mockImplementationOnce(() => {
throw new Error(GUARD_ERROR);
});
const buf = await buildTarBr({ "SKILL.md": VALID_SKILL_MD, "../evil.txt": "pwned\n" });
await expect(installSkillFromBuffer("demo", buf)).rejects.toThrow(/unsafe tar entry/);
});
});
// ---- registry retry policy ----
test("registry: index fetch retries transient failures and succeeds", async () => {
const indexPayload = { skills: { demo: { contentHash: "sha256:abc" } } };
const fetchMock = vi.fn(async () => {
if (fetchMock.mock.calls.length < 3) throw new Error("network down");
return { ok: true, status: 200, json: async () => indexPayload };
});
vi.stubGlobal("fetch", fetchMock);
const index = await fetchSkillsIndex(1000);
expect(index.skills.demo.contentHash).toBe("sha256:abc");
expect(fetchMock).toHaveBeenCalledTimes(3);
});
test("registry: attempts=1 keeps the silent channel fail-fast", async () => {
const fetchMock = vi.fn(async () => {
throw new Error("network down");
});
vi.stubGlobal("fetch", fetchMock);
await expect(fetchSkillsIndex(1000, 1)).rejects.toThrow(BailianError);
expect(fetchMock).toHaveBeenCalledTimes(1);
});
test("registry: asset download retries transient HTTP errors", async () => {
const fetchMock = vi.fn(async () => {
if (fetchMock.mock.calls.length === 1) return { ok: false, status: 503 };
return {
ok: true,
status: 200,
arrayBuffer: async () => new Uint8Array([1, 2, 3]).buffer,
};
});
vi.stubGlobal("fetch", fetchMock);
const buffer = await downloadSkillAsset("demo");
expect([...buffer]).toEqual([1, 2, 3]);
expect(fetchMock).toHaveBeenCalledTimes(2);
});
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "knowledge-studio-cli",
"version": "1.18.2",
"version": "1.18.1",
"description": "Lightweight RAG CLI for Aliyun Model Studio — focused on knowledge-base retrieval.",
"keywords": [
"alibaba-cloud",
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "bailian-cli-runtime",
"version": "1.18.2",
"version": "1.18.1",
"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": {
+1 -1
View File
@@ -1,7 +1,7 @@
---
name: bailian-cli
metadata:
version: "1.18.2"
version: "1.18.1"
requires:
bins: ["bl"]
description: >-
+3 -2
View File
@@ -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) |
+58 -31
View File
@@ -7,12 +7,13 @@ Index: [index.md](index.md)
## Commands in this group
| Command | Authentication | Description |
| ------------------ | -------------- | --------------------------------------------------------------- |
| `bl quota check` | Console | Check current usage against rate limits |
| `bl quota history` | Console | View quota change history |
| `bl quota list` | API Key | View model rate limits (QPM/TPM, account and workspace level) |
| `bl quota update` | API Key | Update model rate limits (QPM/TPM), or clear them with --delete |
| Command | Authentication | Description |
| ------------------ | -------------- | ------------------------------------------------------------- |
| `bl quota check` | Console | Check current usage against rate limits |
| `bl quota delete` | API Key | Clear all custom rate limits (QPM/TPM) for a model |
| `bl quota history` | Console | View quota change history |
| `bl quota list` | API Key | View model rate limits (QPM/TPM, account and workspace level) |
| `bl quota update` | API Key | Update model rate limits (QPM/TPM) |
## Command details
@@ -58,6 +59,43 @@ bl quota check --model qwen3.6-plus,qwen-turbo
bl quota check --output json
```
### `bl quota delete`
| Field | Value |
| ------------------ | -------------------------------------------------- |
| **Name** | `quota delete` |
| **Description** | Clear all custom rate limits (QPM/TPM) for a model |
| **Authentication** | API Key |
| **Usage** | `bl quota delete --model <model> [--yes]` |
#### Flags
| Flag | Type | Required | Description |
| ------------------ | ------ | -------- | ---------------------------- |
| `--model <model>` | string | yes | Model name (required) |
| `--yes` | switch | no | Skip the confirmation prompt |
| `--api-key <key>` | string | no | API key |
| `--base-url <url>` | string | no | API base URL |
#### Notes
- Irreversible — the server-side OVERLAY is reset to defaults, so your custom QPM/TPM configuration is permanently removed.
- Requires confirmation; pass --yes to skip the prompt in scripts.
#### Examples
```bash
bl quota delete --model qwen-plus
```
```bash
bl quota delete --model qwen-plus --yes
```
```bash
bl quota delete --model qwen-plus --output json
```
### `bl quota history`
| Field | Value |
@@ -149,29 +187,26 @@ bl quota list --output json
### `bl quota update`
| Field | Value |
| ------------------ | ---------------------------------------------------------------------------- |
| **Name** | `quota update` |
| **Description** | Update model rate limits (QPM/TPM), or clear them with --delete |
| **Authentication** | API Key |
| **Usage** | `bl quota update --model <model> [--rpm <n>] [--tpm <n>] [--delete] [--yes]` |
| Field | Value |
| ------------------ | --------------------------------------------------------- |
| **Name** | `quota update` |
| **Description** | Update model rate limits (QPM/TPM) |
| **Authentication** | API Key |
| **Usage** | `bl quota update --model <model> [--rpm <n>] [--tpm <n>]` |
#### Flags
| Flag | Type | Required | Description |
| ------------------ | ------ | -------- | ------------------------------------------ |
| `--model <model>` | string | yes | Model name (required) |
| `--rpm <n>` | number | no | Max requests per minute (QPM) |
| `--tpm <n>` | number | no | Max tokens per minute (TPM) |
| `--delete` | switch | no | Clear all custom rate limits for the model |
| `--yes` | switch | no | Skip the confirmation prompt for --delete |
| `--api-key <key>` | string | no | API key |
| `--base-url <url>` | string | no | API base URL |
| Flag | Type | Required | Description |
| ------------------ | ------ | -------- | ----------------------------- |
| `--model <model>` | string | yes | Model name (required) |
| `--rpm <n>` | number | no | Max requests per minute (QPM) |
| `--tpm <n>` | number | no | Max tokens per minute (TPM) |
| `--api-key <key>` | string | no | API key |
| `--base-url <url>` | string | no | API base URL |
#### Notes
- Fields you omit keep their current values (server-side OVERLAY merge); --delete clears all custom limits.
- --delete requires confirmation; pass --yes to skip the prompt in scripts.
- Fields you omit keep their current values (server-side OVERLAY merge). Clear all custom limits with the "quota delete" command instead.
- Setting TPM without an existing QPM limit is rejected server-side — pass --rpm first or together.
#### Examples
@@ -184,14 +219,6 @@ bl quota update --model qwen-plus --rpm 60 --tpm 100000
bl quota update --model qwen3-max --tpm 500000
```
```bash
bl quota update --model qwen-plus --delete
```
```bash
bl quota update --model qwen-plus --delete --yes
```
```bash
bl quota update --model qwen-plus --rpm 60 --output json
```
+1 -1
View File
@@ -1,7 +1,7 @@
---
name: bailian-finetune
metadata:
version: "1.18.2"
version: "1.18.1"
requires:
bins: ["bl"]
description: >-
+1 -1
View File
@@ -1,7 +1,7 @@
---
name: bailian-gen
metadata:
version: "1.18.2"
version: "1.18.1"
requires:
bins: ["bl"]
description: >-
+1 -1
View File
@@ -1,7 +1,7 @@
---
name: bailian-managed-agent
metadata:
version: "1.18.2"
version: "1.18.1"
requires:
bins: ["bl"]
description: >-
+1 -1
View File
@@ -1,7 +1,7 @@
---
name: bailian-protocol
metadata:
version: "1.18.2"
version: "1.18.1"
requires:
bins: ["bl"]
description: >-
+1 -1
View File
@@ -1,7 +1,7 @@
---
name: bailian-web-search
metadata:
version: "1.18.2"
version: "1.18.1"
requires:
bins: ["bl"]
description: >-