bailian-cli 0.1.2 → 1.0.0

package/skill/reference/video.md

@@ -0,0 +1,207 @@
+# `bl video` commands
+
+> Auto-generated from `packages/cli/src/commands/catalog.ts`. Do not edit by hand.
+> Regenerate: `pnpm --filter bailian-cli run generate:reference` (runs automatically on `build`).
+
+Index: [index.md](index.md)
+
+## Commands in this group
+
+| Command | Description |
+| --- | --- |
+| `bl video download` | Download a completed video by task ID |
+| `bl video edit` | Edit a video with happyhorse-1.0-video-edit (style transfer, object replacement, etc.) |
+| `bl video generate` | Generate a video from text or image (happyhorse-1.0-t2v / happyhorse-1.0-i2v / wan2.6-t2v) |
+| `bl video ref` | Reference-to-video generation (happyhorse-1.0-r2v / wan2.6-r2v): multi-subject, multi-shot with voice |
+| `bl video task get` | Query async task status |
+
+## Command details
+
+### `bl video download`
+
+| Field | Value |
+| --- | --- |
+| **Name** | `video download` |
+| **Description** | Download a completed video by task ID |
+| **Usage** | `bl video download --task-id <id> --out <path>` |
+
+#### Options
+
+| Flag | Type | Required | Description |
+| --- | --- | --- | --- |
+| `--task-id <id>` | string | no | Task ID to download from |
+| `--out <path>` | string | no | Output file path |
+
+#### Examples
+
+```bash
+bl video download --task-id 3b256896-xxxx --out video.mp4
+```
+
+```bash
+bl video download --task-id 3b256896-xxxx --out video.mp4 --quiet
+```
+
+### `bl video edit`
+
+| Field | Value |
+| --- | --- |
+| **Name** | `video edit` |
+| **Description** | Edit a video with happyhorse-1.0-video-edit (style transfer, object replacement, etc.) |
+| **Usage** | `bl video edit --video <url> --prompt <text> [flags]` |
+| **API docs** | [/best-practice/wanx/video-edit](https://help.aliyun.com/zh/model-studio/best-practice/wanx/video-edit) |
+
+#### Options
+
+| Flag | Type | Required | Description |
+| --- | --- | --- | --- |
+| `--model <model>` | string | no | Model ID (default: happyhorse-1.0-video-edit) |
+| `--video <url>` | string | yes | Input video URL or local file (mp4/mov, 2-10s) |
+| `--prompt <text>` | string | no | Edit instruction (e.g. "将画面转换为黏土风格") |
+| `--ref-image <url>` | string | no | Reference image URL (up to 4, comma-separated) |
+| `--negative-prompt <text>` | string | no | Negative prompt to exclude unwanted content |
+| `--resolution <res>` | string | no | Resolution: 720P or 1080P (default: 1080P) |
+| `--ratio <ratio>` | string | no | Aspect ratio (16:9, 9:16, 1:1, 4:3, 3:4) |
+| `--duration <seconds>` | number | no | Output video duration in seconds (2-10) |
+| `--audio-setting <mode>` | string | no | Audio: auto (default) or origin (keep original) |
+| `--prompt-extend` | boolean | no | Enable prompt intelligent rewriting (default: true) |
+| `--no-prompt-extend` | boolean | no | Disable prompt intelligent rewriting |
+| `--watermark` | boolean | no | Add "AI生成" watermark |
+| `--seed <n>` | number | no | Random seed for reproducible generation |
+| `--download <path>` | string | no | Save video to file on completion |
+| `--no-wait` | boolean | no | Return task ID immediately without waiting |
+| `--async` | boolean | no | Return task ID immediately (agent/CI mode, same as --no-wait) |
+| `--poll-interval <seconds>` | number | no | Polling interval when waiting (default: 15) |
+
+#### Examples
+
+```bash
+bl video edit --video https://example.com/input.mp4 --prompt "将整个画面转换为黏土风格"
+```
+
+```bash
+bl video edit --video https://example.com/input.mp4 --prompt "替换衣服为图片中的款式" --ref-image https://example.com/clothes.png
+```
+
+```bash
+bl video edit --video https://example.com/input.mp4 --prompt "Convert to anime style" --resolution 720P --download output.mp4
+```
+
+### `bl video generate`
+
+| Field | Value |
+| --- | --- |
+| **Name** | `video generate` |
+| **Description** | Generate a video from text or image (happyhorse-1.0-t2v / happyhorse-1.0-i2v / wan2.6-t2v) |
+| **Usage** | `bl video generate --prompt <text> [--image <url>] [flags]` |
+| **API docs** | [/best-practice/wanx/text-to-video](https://help.aliyun.com/zh/model-studio/best-practice/wanx/text-to-video) |
+
+#### Options
+
+| Flag | Type | Required | Description |
+| --- | --- | --- | --- |
+| `--model <model>` | string | no | Model ID (default: happyhorse-1.0-t2v, or happyhorse-1.0-i2v with --image) |
+| `--prompt <text>` | string | yes | Video description |
+| `--image <url>` | string | no | Input image URL for image-to-video generation |
+| `--negative-prompt <text>` | string | no | Negative prompt to exclude unwanted content |
+| `--resolution <res>` | string | no | Resolution (e.g. 1280*720, 960*960) |
+| `--ratio <ratio>` | string | no | Aspect ratio (e.g. 16:9, 1:1) |
+| `--duration <seconds>` | number | no | Video duration in seconds (default: 5) |
+| `--prompt-extend` | boolean | no | Automatically extend prompt for better results |
+| `--watermark` | boolean | no | Add watermark to generated video |
+| `--seed <n>` | number | no | Random seed for reproducible generation |
+| `--download <path>` | string | no | Save video to file on completion |
+| `--no-wait` | boolean | no | Return task ID immediately without waiting |
+| `--async` | boolean | no | Return task ID immediately (agent/CI mode, same as --no-wait) |
+| `--poll-interval <seconds>` | number | no | Polling interval when waiting (default: 5) |
+
+#### Examples
+
+```bash
+bl video generate --prompt "一个人在读书，静态镜头"
+```
+
+```bash
+bl video generate --prompt "Ocean waves at sunset." --download sunset.mp4
+```
+
+```bash
+bl video generate --image https://example.com/cat.png --prompt "让画面中的猫动起来"
+```
+
+```bash
+bl video generate --prompt "Mountain landscape" --resolution 1280*720 --duration 5
+```
+
+### `bl video ref`
+
+| Field | Value |
+| --- | --- |
+| **Name** | `video ref` |
+| **Description** | Reference-to-video generation (happyhorse-1.0-r2v / wan2.6-r2v): multi-subject, multi-shot with voice |
+| **Usage** | `bl video ref --prompt <text> --image <url>... [--ref-video <url>...] [flags]` |
+| **API docs** | [/best-practice/wanx/video-reference](https://help.aliyun.com/zh/model-studio/best-practice/wanx/video-reference) |
+
+#### Options
+
+| Flag | Type | Required | Description |
+| --- | --- | --- | --- |
+| `--model <model>` | string | no | Model ID (default: happyhorse-1.0-r2v) |
+| `--prompt <text>` | string | yes | Video description with reference markers (图1, 视频1, etc.) |
+| `--image <url>` | array | no | Reference image URL or local file (repeatable for multiple subjects) |
+| `--ref-video <url>` | array | no | Reference video URL or local file (repeatable) |
+| `--image-voice <url>` | array | no | Voice URL for corresponding image (pairs by position) |
+| `--video-voice <url>` | array | no | Voice URL for corresponding ref-video (pairs by position) |
+| `--resolution <res>` | string | no | Resolution: 720P or 1080P (default: 720P) |
+| `--ratio <ratio>` | string | no | Aspect ratio (16:9, 9:16, 1:1) |
+| `--duration <seconds>` | number | no | Video duration in seconds (2-10, default: 5) |
+| `--prompt-extend` | boolean | no | Enable prompt intelligent rewriting |
+| `--no-prompt-extend` | boolean | no | Disable prompt intelligent rewriting |
+| `--watermark` | boolean | no | Add watermark to generated video |
+| `--seed <n>` | number | no | Random seed for reproducible generation |
+| `--download <path>` | string | no | Save video to file on completion |
+| `--no-wait` | boolean | no | Return task ID immediately without waiting |
+| `--async` | boolean | no | Return task ID immediately (agent/CI mode, same as --no-wait) |
+| `--poll-interval <seconds>` | number | no | Polling interval when waiting (default: 15) |
+
+#### Examples
+
+```bash
+bl video ref --prompt "图1在草地上奔跑" --image person.jpg
+```
+
+```bash
+bl video ref --prompt "视频1在弹吉他，图1走过来" --ref-video scene.mp4 --image person.jpg
+```
+
+```bash
+bl video ref --prompt "图1说话" --image person.jpg --image-voice voice.mp3 --resolution 1080P
+```
+
+```bash
+bl video ref --prompt "图1和图2在对话" --image a.jpg --image b.jpg --image-voice va.mp3 --image-voice vb.mp3
+```
+
+### `bl video task get`
+
+| Field | Value |
+| --- | --- |
+| **Name** | `video task get` |
+| **Description** | Query async task status |
+| **Usage** | `bl video task get --task-id <id>` |
+
+#### Options
+
+| Flag | Type | Required | Description |
+| --- | --- | --- | --- |
+| `--task-id <id>` | string | no | Async task ID |
+
+#### Examples
+
+```bash
+bl video task get --task-id 3b256896-3e70-xxxx-xxxx-xxxxxxxxxxxx
+```
+
+```bash
+bl video task get --task-id 3b256896-3e70-xxxx --output json
+```

package/skill/reference/vision.md

@@ -0,0 +1,53 @@
+# `bl vision` commands
+
+> Auto-generated from `packages/cli/src/commands/catalog.ts`. Do not edit by hand.
+> Regenerate: `pnpm --filter bailian-cli run generate:reference` (runs automatically on `build`).
+
+Index: [index.md](index.md)
+
+## Commands in this group
+
+| Command | Description |
+| --- | --- |
+| `bl vision describe` | Describe an image or video using Qwen-VL |
+
+## Command details
+
+### `bl vision describe`
+
+| Field | Value |
+| --- | --- |
+| **Name** | `vision describe` |
+| **Description** | Describe an image or video using Qwen-VL |
+| **Usage** | `bl vision describe --image <path-or-url> [--video <url>] [--prompt <text>]` |
+
+#### Options
+
+| Flag | Type | Required | Description |
+| --- | --- | --- | --- |
+| `--image <path-or-url>` | string | no | Local image path or URL |
+| `--video <url>` | array | no | Video file URL or local path (mp4/mov/avi/mkv/webm) |
+| `--prompt <text>` | string | no | Question about the content (default: auto-detected) |
+| `--model <model>` | string | no | Vision model (default: qwen-vl-max) |
+
+#### Examples
+
+```bash
+bl vision describe --image photo.jpg
+```
+
+```bash
+bl vision describe --image https://example.com/photo.jpg --prompt "这只狗是什么品种？"
+```
+
+```bash
+bl vision describe --video https://example.com/video.mp4 --prompt "总结视频内容"
+```
+
+```bash
+bl vision describe --video ./local-video.mp4
+```
+
+```bash
+bl vision describe --image photo.png --prompt "Extract the text" --model qwen-vl-plus
+```

package/README.md

@@ -1,291 +0,0 @@
-<div align="center">
-
-<img src="https://img.alicdn.com/imgextra/i1/O1CN01RSQFUD1jN5IBzHORt_!!6000000004535-2-tps-2440-521.png" alt="Bailian CLI" width="420" />
-
-# >_ Bailian CLI
-
-**The official command-line interface for Alibaba Cloud Bailian (DashScope) AI Platform**
-
-[![npm version](https://img.shields.io/npm/v/bailian-cli?color=0969da&label=npm)](https://www.npmjs.com/package/bailian-cli)
-[![Node.js](https://img.shields.io/badge/node-%3E%3D18-brightgreen)](https://nodejs.org)
-[![TypeScript](https://img.shields.io/badge/TypeScript-strict-3178c6)](https://www.typescriptlang.org)
-[![License](https://img.shields.io/badge/license-Apache%202.0-blue)](LICENSE)
-
-[中文文档](README_CN.md) · [API Documentation](https://help.aliyun.com/zh/model-studio/) · [Get API Key](https://bailian.console.aliyun.com/cn-beijing/?source_channel=aliway&tab=app#/api-key)
-
----
-
-*Chat with Qwen, generate images & videos, understand images, call agents,*
-*manage memory, search the web — all from your terminal.*
-
-*Built for AI Agents. Every command works as a structured tool call.*
-
-</div>
-
-## Installation
-
-```bash
-npm install -g bailian-cli
-```
-
-After installation, both `bailian` and `bl` (short alias) are available.
-
-## Quick Start
-
-```bash
-# Authenticate
-bl auth login --api-key sk-xxxxx
-
-# Chat with Qwen
-bl text chat --message "What is DashScope?"
-
-# Multimodal chat (text + image + audio + video)
-bl omni --message "Describe this image" --image ./photo.jpg
-
-# Generate an image
-bl image generate --prompt "A cat in a spacesuit" --out-dir ./images/
-
-# Generate a video from local image
-bl video generate --image ./cat.png --prompt "Make the cat move" --download cat.mp4
-```
-
-## Features
-
-> **Local File Support**: All commands accepting file URLs also accept local file paths — files are auto-uploaded. Just pass `./photo.png` instead of a URL.
-
-<table>
-<tr><td>
-
-| Category | Commands | Default Model |
-|:---------|:---------|:--------------|
-| **Text** | `text chat` | qwen3.6-plus |
-| **Omni** | `omni` (text+image+audio+video) | qwen3.5-omni-plus |
-| **Image** | `image generate` | qwen-image-2.0 |
-| | `image edit` (multi-image merge) | qwen-image-2.0 |
-| **Video** | `video generate` (text/image-to-video) | happyhorse-1.0-t2v / happyhorse-1.0-i2v |
-| | `video edit` (style transfer) | happyhorse-1.0-video-edit |
-| | `video task get` / `video download` | — |
-
-</td></tr>
-<tr><td>
-
-| Category | Commands | Default Model |
-|:---------|:---------|:--------------|
-| **Vision** | `vision describe` | qwen-vl-max |
-| **Speech** | `speech synthesize` (TTS) | cosyvoice-v3-flash |
-| | `speech recognize` (ASR) | fun-asr |
-| **File** | `file upload` (to temp OSS) | — |
-| **App** | `app call` (agents / workflows) | — |
-| **Memory** | `memory add/search/list/update/delete` | — |
-| **Knowledge** | `knowledge retrieve` (RAG) | — |
-| **Search** | `search web` | — |
-
-</td></tr>
-</table>
-
-## Usage Examples
-
-### Text Chat
-
-```bash
-# Simple chat
-bl text chat --message "Explain quantum computing"
-
-# Multi-turn conversation
-bl text chat --message "Hello" --message "assistant:Hi!" --message "How are you?"
-
-# With system prompt
-bl text chat --system "You are a coding assistant." --message "Write fizzbuzz in Python"
-
-# Enable thinking mode (qwen3 / qwq)
-bl text chat --model qwq-plus --message "Solve 1+1" --enable-thinking
-```
-
-### Omni Multimodal
-
-```bash
-# Describe an image
-bl omni --message "What's in this photo?" --image ./photo.jpg
-
-# Understand audio
-bl omni --message "Transcribe this audio" --audio ./recording.wav
-
-# Generate speech output
-bl omni --message "Read this aloud" --audio-out greeting.wav
-```
-
-### Image Generation & Editing
-
-```bash
-# Generate images
-bl image generate --prompt "Mountain landscape" --size 16:9
-
-# Generate multiple images
-bl image generate --prompt "Logo design" --n 3 --out-dir ./generated/
-
-# Edit an image (local file auto-uploaded)
-bl image edit --image ./photo.png --prompt "Change background to beach"
-
-# Multi-image merge
-bl image edit --image ./a.png --image ./b.png --prompt "Combine into a collage"
-```
-
-### Video Generation & Editing
-
-```bash
-# Text to video
-bl video generate --prompt "A person reading a book" --download output.mp4
-
-# Image to video (local file auto-uploaded)
-bl video generate --image ./cat.png --prompt "Make the cat move" --ratio 3:4
-
-# Edit a video (style transfer)
-bl video edit --video ./input.mp4 --prompt "Convert to clay style"
-```
-
-### Speech
-
-```bash
-# List available voices
-bl speech synthesize --list-voices --model cosyvoice-v3-flash
-
-# Text-to-speech
-bl speech synthesize --text "Hello world" --voice longyumi_v3 --out speech.wav
-
-# Stream to audio player (macOS)
-bl speech synthesize --text "你好" --voice longyumi_v3 --stream | afplay -
-
-# Speech-to-text (local file auto-uploaded)
-bl speech recognize --url ./meeting.mp3
-```
-
-### File Upload, App, Memory & Knowledge
-
-```bash
-# Upload a local file to DashScope temp storage
-bl file upload --file ./photo.png --model qwen-vl-max
-
-# Call a Bailian application
-bl app call --app-id <APP_ID> --prompt "Hello" --stream
-
-# Memory management
-bl memory add --user-id user1 --content "User prefers Python"
-bl memory search --user-id user1 --query "programming language"
-
-# Knowledge base retrieval (requires AK/SK)
-bl knowledge retrieve --index-id <INDEX_ID> --query "search text"
-
-# Web search
-bl search web --query "latest TypeScript features" --count 5
-```
-
-## Authentication
-
-### DashScope API Key
-
-Required for most commands. Get your key from the [DashScope Console](https://bailian.console.aliyun.com/cn-beijing/?source_channel=aliway&tab=app#/api-key).
-
-```bash
-# Option 1: Environment variable
-export DASHSCOPE_API_KEY=sk-xxxxx
-
-# Option 2: Login command (persisted to ~/.bailian/config.json)
-bl auth login --api-key sk-xxxxx
-
-# Option 3: Per-command flag
-bl text chat --api-key sk-xxxxx --message "Hello"
-```
-
-### Alibaba Cloud AK/SK (Knowledge Base only)
-
-Required for `knowledge retrieve`. Get your AccessKey from [RAM Console](https://ram.console.aliyun.com/manage/ak).
-
-```bash
-export ALIBABA_CLOUD_ACCESS_KEY_ID=LTAI5t...
-export ALIBABA_CLOUD_ACCESS_KEY_SECRET=...
-export BAILIAN_WORKSPACE_ID=ws-...
-```
-
-## Configuration
-
-```bash
-# View current config
-bl config show
-
-# Set defaults
-bl config set --key region --value us
-bl config set --key default_text_model --value qwen-turbo
-bl config set --key timeout --value 600
-
-# Export MCP-compatible JSON Schema for all commands
-bl config export-schema
-
-# Self-update to latest version
-bl update
-```
-
-Config file location: `~/.bailian/config.json`
-
-## Global Flags
-
-| Flag | Description |
-|:-----|:------------|
-| `--api-key <key>` | API key (overrides all other auth) |
-| `--region <region>` | API region: `cn` (default), `us`, `intl` |
-| `--output <format>` | Output format: `text`, `json` |
-| `--quiet` | Suppress non-essential output |
-| `--verbose` | Print HTTP request/response details |
-| `--dry-run` | Show what would happen without executing |
-| `--no-color` | Disable ANSI colors and spinners |
-| `--timeout <seconds>` | Request timeout (default: 300) |
-| `--non-interactive` | Disable interactive prompts (CI mode) |
-
-## Project Structure
-
-```
-src/
-├── main.ts              # CLI entry point
-├── registry.ts          # Command registry (30 commands)
-├── args.ts              # Argument parsing
-├── command.ts           # Command interface & global options
-├── auth/                # Authentication (credentials, resolver, setup)
-├── client/              # HTTP client (AK signing, endpoints, streaming)
-├── commands/            # Command implementations
-│   ├── auth/            #   login, status, logout
-│   ├── text/            #   chat
-│   ├── omni/            #   multimodal chat
-│   ├── image/           #   generate, edit
-│   ├── video/           #   generate, edit, task-get, download
-│   ├── vision/          #   describe
-│   ├── speech/          #   synthesize, recognize
-│   ├── file/            #   upload
-│   ├── app/             #   call
-│   ├── memory/          #   add, search, list, update, delete, profile
-│   ├── knowledge/       #   retrieve
-│   ├── search/          #   web
-│   └── config/          #   show, set, export-schema
-├── config/              # Config loading & schema (Zod)
-├── errors/              # Error handling hierarchy
-├── output/              # Formatters (text, json, progress, status-bar)
-├── polling/             # Async task polling
-├── update/              # Self-update checker
-└── utils/               # Utilities (fs, token, env, prompt)
-```
-
-## Links
-
-| Resource | URL |
-|:---------|:----|
-| DashScope API Docs | https://help.aliyun.com/zh/model-studio/ |
-| Qwen Model List | https://help.aliyun.com/zh/model-studio/getting-started/models |
-| Bailian Console | https://bailian.console.aliyun.com/ |
-| Get API Key | https://bailian.console.aliyun.com/cn-beijing/?source_channel=aliway&tab=app#/api-key |
-| Get AccessKey | https://ram.console.aliyun.com/manage/ak |
-
-<div align="center">
-
----
-
-Made with `>_` by the Bailian team
-
-</div>

package/scripts/preuninstall.js

@@ -1,69 +0,0 @@
-#!/usr/bin/env node
-
-/**
- * Preuninstall script: remove SKILL.md from all AI coding tools on uninstall.
- */
-
-import { existsSync, rmSync, openSync, writeSync, closeSync } from 'fs';
-import { join } from 'path';
-import { homedir } from 'os';
-
-const home = homedir();
-
-// Write directly to /dev/tty to bypass npm output suppression
-let ttyFd;
-try {
-  ttyFd = openSync('/dev/tty', 'w');
-} catch {
-  ttyFd = null;
-}
-
-function ttyPrint(msg) {
-  if (ttyFd != null) {
-    writeSync(ttyFd, msg + '\n');
-  }
-}
-
-const dotDirTargets = [
-  '.qoder',
-  '.claude',
-  '.cline',
-  '.qwen',
-  '.cursor',
-  '.windsurf',
-  '.trae',
-  '.qoderwork',
-  '.kiro',
-];
-
-const customTargets = [
-  { root: join(home, 'Library', 'Application Support', 'iDingTalk', 'wukong'), label: 'Wukong' },
-];
-
-const targets = [
-  ...dotDirTargets.map(d => ({ root: join(home, d), label: d })),
-  ...customTargets,
-];
-
-let removed = 0;
-
-for (const { root, label } of targets) {
-  try {
-    const skillDir = join(root, 'skills', 'bailian-cli');
-    if (!existsSync(skillDir)) continue;
-
-    rmSync(skillDir, { recursive: true });
-    removed++;
-    ttyPrint(`  \u2717 ${label}`);
-  } catch {
-    // Silent fail — don't block npm uninstall
-  }
-}
-
-if (removed > 0) {
-  ttyPrint(`Bailian CLI skill removed from ${removed} AI coding tool(s).`);
-}
-
-if (ttyFd != null) {
-  closeSync(ttyFd);
-}