@laiye-adp/agentic-doc-parse-and-extract-cli 1.11.0-beta.4

package/README.md

@@ -0,0 +1,214 @@
+# ADP CLI
+
+Official command-line tool for [Laiye ADP (Agentic Document Processing)](https://adp-global.laiye.com/) — document parsing and intelligent field extraction.
+
+[English](README.md) | [简体中文](README.zh.md)
+
+## Features
+
+- **Document Parsing** — Turn any type of document into structured data (Markdown or JSON)
+- **Invoice/Receipt/Purchase Order Extraction** — Extract key information and line items from invoices, receipts, purchase orders and more
+- **Custom Document Extraction** — Extract custom fields from any type of document
+- **Batch Processing** — Concurrently process multiple documents in a folder or from URLs, with per-file result output
+- **Sync/Async** — Support both sync and async processing modes
+- **Two-Phase Async** — `--async --no-wait` submits tasks and outputs task-id list; `query --file` resumes from where you left off
+- **Reliability** — Automatic retry with exponential backoff (`--retry`), fine-grained exit codes
+- **Cross Platform** — Windows / Linux / macOS, static binaries with no dependencies
+
+## Supported Formats
+
+`.jpg` `.jpeg` `.png` `.bmp` `.tiff` `.tif` `.pdf` `.doc` `.docx` `.xls` `.xlsx` `.ppt` `.pptx` (max 50MB per file)
+
+## Install
+
+```bash
+# npm (recommended)
+npm install -g @laiye-adp/agentic-doc-parse-and-extract-cli
+
+# Linux / macOS
+curl -fsSL https://raw.githubusercontent.com/laiye-ai/adp-cli/main/scripts/adp-init.sh | bash
+
+# Windows (PowerShell)
+irm https://raw.githubusercontent.com/laiye-ai/adp-cli/main/scripts/adp-init.ps1 | iex
+```
+
+Or download a prebuilt binary from [GitHub Releases](https://github.com/laiye-ai/adp-cli/releases).
+
+## Configure
+
+Get an API key at [https://adp-global.laiye.com/](https://adp-global.laiye.com/) (new users get 100 free credits per month).
+
+```bash
+adp config set --api-key <your-api-key>
+adp config set --api-base-url https://adp-global.laiye.com
+adp config get
+```
+
+## Quick Examples
+
+```bash
+# List available apps
+adp app-id list
+
+# Parse a local document
+adp parse local ./invoice.pdf --app-id <app-id>
+
+# Extract key fields
+adp extract local ./invoice.pdf --app-id <app-id>
+
+# Parse a directory in async mode
+adp parse local ./documents/ --app-id <app-id> --async
+
+# Process a remote URL
+adp extract url https://example.com/file.pdf --app-id <app-id>
+
+# Query an async task
+adp parse query <task-id>
+
+# Two-phase async (submit + query separately, resumable)
+adp extract local ./documents/ --app-id <app-id> --async --no-wait --export tasks.json
+adp extract query --watch --file tasks.json
+
+# Auto retry on failure (up to 2 retries)
+adp parse local ./documents/ --app-id <app-id> --retry 2
+
+# Check remaining credits
+adp credit
+```
+
+## Commands
+
+> AI agents should call `adp schema` for the machine-readable, authoritative command spec. The table below is a human-friendly summary.
+
+| Command | Description |
+|---|---|
+| `adp version` | Print version |
+| `adp config set` | Set API key / base URL |
+| `adp config get` | Show current config |
+| `adp config clear` | Clear config |
+| `adp app-id list` | List available apps |
+| `adp app-id cache` | Read app list from local cache |
+| `adp parse local <path>` | Parse local file/directory |
+| `adp parse url <url>` | Parse remote file (URL list file supported) |
+| `adp parse base64 <data>` | Parse Base64-encoded content |
+| `adp parse query <task-id...>` | Query async parse tasks (supports multiple IDs or `--file`) |
+| `adp extract local <path>` | Extract from local file/directory |
+| `adp extract url <url>` | Extract from remote file |
+| `adp extract base64 <data>` | Extract from Base64-encoded content |
+| `adp extract query <task-id...>` | Query async extract tasks (supports multiple IDs or `--file`) |
+| `adp custom-app create` | Create a custom extraction app |
+| `adp custom-app update` | Update custom app config |
+| `adp custom-app get-config` | Show app config |
+| `adp custom-app delete` | Delete a custom app |
+| `adp custom-app delete-version` | Delete a specific config version |
+| `adp custom-app ai-generate` | AI-recommend extraction fields |
+| `adp credit` | Show remaining credits |
+| `adp schema` | Output command schema (for AI agents) |
+
+## Flags
+
+| Flag | Description |
+|---|---|
+| `--json` | Output JSON |
+| `--quiet` | Quiet mode, output result only |
+| `--lang <en\|zh>` | Interface language |
+| `--app-id` | App ID (required for parse / extract) |
+| `--async` | Async mode |
+| `--no-wait` | Submit tasks only, do not wait for results (use with `--async`) |
+| `--export <path>` | Export result to file (single file) or directory (batch) |
+| `--timeout <seconds>` | Timeout (default 900s) |
+| `--concurrency <n>` | Concurrent workers (free: max 1, paid: max 2) |
+| `--retry <n>` | Retries for retryable errors (default 0) |
+| `--file <path>` | Read task IDs from JSON file (output of `--no-wait`, query only) |
+
+## Async Workflow
+
+For large files or batch jobs, submit with `--async` and the CLI returns a `task-id`. Poll for results with `parse query` / `extract query`:
+
+```bash
+adp parse local ./big.pdf --app-id <app-id> --async
+# returns a task-id
+
+adp parse query <task-id>
+```
+
+### Two-Phase Async (`--no-wait`)
+
+By default, `--async` submits and polls until completion — ideal for AI agents. For resumable workflows, use two-phase mode:
+
+**Phase 1: Submit tasks**
+
+```bash
+adp extract local ./documents/ --app-id <app-id> --async --no-wait --export tasks.json
+```
+
+Output is a JSON array with task IDs:
+
+```json
+[
+  {"path": "invoice.pdf", "task_id": "task_abc123"},
+  {"path": "contract.pdf", "task_id": "task_def456"}
+]
+```
+
+**Phase 2: Query results**
+
+```bash
+adp extract query --watch --file tasks.json
+adp extract query --watch --file tasks.json --export ./results/
+```
+
+Even if the CLI crashes mid-way, task IDs in `tasks.json` are preserved — resume anytime with `query --file`.
+
+## Batch Processing
+
+When processing multiple files/URLs, the CLI writes each result to a separate file:
+
+```
+adp_results_20250417_153020/
+├── _summary.json              # Summary (total, success, failed, per-file status)
+├── invoice_01.pdf.json        # Successful result
+├── contract_02.docx.json
+└── report_03.pdf.error.json   # Error details
+```
+
+- `--export <dir>` — specify output directory
+- Without `--export` — auto-creates `adp_results_<timestamp>/`
+- Single file — outputs to stdout or the `--export` file path
+
+## Exit Codes
+
+| Code | Meaning |
+|------|---------|
+| `0` | All success |
+| `1` | All failed / system error |
+| `2` | Parameter error |
+| `3` | Resource not found |
+| `4` | Permission denied |
+| `5` | Conflict |
+| `6` | Partial failure (some tasks failed in batch) |
+
+## Environment Variables
+
+| Variable | Description |
+|---|---|
+| `ADP_API_KEY` | API key (overrides config file) |
+| `ADP_API_BASE_URL` | Service URL |
+| `ADP_LANG` | Interface language (`en` / `zh`) |
+| `ADP_LOG_LEVEL` | Log level (`debug` / `info` / `warn` / `error`) |
+
+## Config Storage
+
+- Config dir: `~/.adp/`
+- Config file: `~/.adp/config.json`
+- Encrypted API key: `~/.adp/key.enc` (AES-256-GCM)
+- App cache: `~/.adp/app_cache.json`
+- Version check cache: `~/.adp/version_check.json` (refreshed every 24h)
+
+## License
+
+Commercial license — see [license.md](license.md). Free for non-commercial use (personal learning, research, teaching, open-source community). Commercial use requires written authorization from Laiye Technology. Contact: global_product@laiye.com
+
+## Contributing
+
+Build all platforms with `make build-all VERSION=v1.0.0`. Run E2E tests with `bash tests/test.sh`.

package/README.zh.md

@@ -0,0 +1,214 @@
+# ADP CLI
+
+来也科技 [ADP（Agentic Document Processing）](https://adp.laiye.com/) 产品的官方命令行工具 —— 文档解析与智能字段抽取。
+
+[English](README.md) | [简体中文](README.zh.md)
+
+## 功能
+
+- **文档解析** — 将文档转换为结构化文本（Markdown 或 JSON）
+- **发票/订单抽取** — 从发票、收据、采购订单等文档中抽取关键字段和表格
+- **自定义文档抽取** — 从任意类型的文档中抽取自定义字段或表格
+- **批量处理** — 并发处理文件夹或 URL 列表中的多个文档，每个文件单独输出结果
+- **同步/异步** — 支持同步和异步两种模式
+- **两阶段异步** — `--async --no-wait` 仅提交任务并输出 task-id 列表；`query --file` 从中断处恢复查询
+- **可靠性** — 自动重试与指数退避（`--retry`），细粒度退出码
+- **跨平台** — Windows / Linux / macOS，静态二进制无依赖
+
+## 支持的文件格式
+
+`.jpg` `.jpeg` `.png` `.bmp` `.tiff` `.tif` `.pdf` `.doc` `.docx` `.xls` `.xlsx` `.ppt` `.pptx`（单文件最大 50MB）
+
+## 安装
+
+```bash
+# npm（推荐）
+npm install -g @laiye-adp/agentic-doc-parse-and-extract-cli
+
+# Linux / macOS
+curl -fsSL https://raw.githubusercontent.com/laiye-ai/adp-cli/main/scripts/adp-init.sh | bash
+
+# Windows（PowerShell）
+irm https://raw.githubusercontent.com/laiye-ai/adp-cli/main/scripts/adp-init.ps1 | iex
+```
+
+或从 [GitHub Releases](https://github.com/laiye-ai/adp-cli/releases) 下载预编译二进制。
+
+## 配置
+
+访问 [https://adp.laiye.com/](https://adp.laiye.com/) 注册并获取 API Key（新用户每月 100 免费积分）。
+
+```bash
+adp config set --api-key <your-api-key>
+adp config set --api-base-url https://adp.laiye.com
+adp config get
+```
+
+## 快速示例
+
+```bash
+# 查看可用应用
+adp app-id list
+
+# 解析本地文档
+adp parse local ./invoice.pdf --app-id <app-id>
+
+# 抽取关键字段
+adp extract local ./invoice.pdf --app-id <app-id>
+
+# 异步解析目录
+adp parse local ./documents/ --app-id <app-id> --async
+
+# 处理远程 URL
+adp extract url https://example.com/file.pdf --app-id <app-id>
+
+# 查询异步任务
+adp parse query <task-id>
+
+# 两阶段异步（分开提交和查询，支持断点续传）
+adp extract local ./documents/ --app-id <app-id> --async --no-wait --export tasks.json
+adp extract query --watch --file tasks.json
+
+# 失败自动重试（最多 2 次）
+adp parse local ./documents/ --app-id <app-id> --retry 2
+
+# 查看剩余积分
+adp credit
+```
+
+## 命令
+
+> AI Agent 应调用 `adp schema` 获取机器可读的权威命令规格。下表仅供人类速查。
+
+| 命令 | 说明 |
+|---|---|
+| `adp version` | 显示版本号 |
+| `adp config set` | 设置 API Key / 服务地址 |
+| `adp config get` | 查看当前配置 |
+| `adp config clear` | 清除配置 |
+| `adp app-id list` | 列出可用应用 |
+| `adp app-id cache` | 从本地缓存读取应用列表 |
+| `adp parse local <path>` | 解析本地文件/目录 |
+| `adp parse url <url>` | 解析远程文件（支持 URL 列表文件） |
+| `adp parse base64 <data>` | 解析 Base64 编码内容 |
+| `adp parse query <task-id...>` | 查询异步解析任务（支持多个 ID 或 `--file`） |
+| `adp extract local <path>` | 抽取本地文件/目录 |
+| `adp extract url <url>` | 抽取远程文件 |
+| `adp extract base64 <data>` | 抽取 Base64 编码内容 |
+| `adp extract query <task-id...>` | 查询异步抽取任务（支持多个 ID 或 `--file`） |
+| `adp custom-app create` | 创建自定义抽取应用 |
+| `adp custom-app update` | 更新自定义应用配置 |
+| `adp custom-app get-config` | 查看应用配置 |
+| `adp custom-app delete` | 删除自定义应用 |
+| `adp custom-app delete-version` | 删除指定配置版本 |
+| `adp custom-app ai-generate` | AI 推荐抽取字段 |
+| `adp credit` | 查看剩余积分 |
+| `adp schema` | 输出命令 Schema（供 AI Agent 使用） |
+
+## 参数
+
+| 参数 | 说明 |
+|---|---|
+| `--json` | 以 JSON 格式输出 |
+| `--quiet` | 静默模式，仅输出结果 |
+| `--lang <en\|zh>` | 指定界面语言 |
+| `--app-id` | 应用 ID（parse / extract 必填） |
+| `--async` | 异步模式 |
+| `--no-wait` | 仅提交任务，不等待结果（与 `--async` 配合使用） |
+| `--export <path>` | 导出结果到文件（单文件）或目录（批量） |
+| `--timeout <seconds>` | 超时时间（默认 900 秒） |
+| `--concurrency <n>` | 并发数（免费用户最大 1，付费用户最大 2） |
+| `--retry <n>` | 可重试错误的重试次数（默认 0） |
+| `--file <path>` | 从 JSON 文件读取任务 ID（`--no-wait` 的输出文件，仅 query 可用） |
+
+## 异步工作流
+
+处理大文件或批量任务时，使用 `--async` 提交任务，CLI 返回 `task-id`，再用 `parse query` / `extract query` 轮询结果：
+
+```bash
+adp parse local ./big.pdf --app-id <app-id> --async
+# 返回一个 task-id
+
+adp parse query <task-id>
+```
+
+### 两阶段异步（`--no-wait`）
+
+默认情况下，`--async` 会提交并轮询直到完成——适合 AI Agent 使用。对于可恢复的工作流，使用两阶段模式：
+
+**第一阶段：提交任务**
+
+```bash
+adp extract local ./documents/ --app-id <app-id> --async --no-wait --export tasks.json
+```
+
+输出为包含任务 ID 的 JSON 数组：
+
+```json
+[
+  {"path": "invoice.pdf", "task_id": "task_abc123"},
+  {"path": "contract.pdf", "task_id": "task_def456"}
+]
+```
+
+**第二阶段：查询结果**
+
+```bash
+adp extract query --watch --file tasks.json
+adp extract query --watch --file tasks.json --export ./results/
+```
+
+即使 CLI 中途崩溃，`tasks.json` 中的任务 ID 也会被保留——随时可用 `query --file` 恢复查询。
+
+## 批量处理
+
+处理多个文件/URL 时，CLI 会将每个结果写入单独的文件：
+
+```
+adp_results_20250417_153020/
+├── _summary.json              # 汇总（总数、成功、失败、每文件状态）
+├── invoice_01.pdf.json        # 成功结果
+├── contract_02.docx.json
+└── report_03.pdf.error.json   # 错误详情
+```
+
+- `--export <dir>` — 指定输出目录
+- 不加 `--export` — 自动创建 `adp_results_<timestamp>/`
+- 单文件 — 输出到 stdout 或 `--export` 指定的文件路径
+
+## 退出码
+
+| 退出码 | 含义 |
+|------|---------|
+| `0` | 全部成功 |
+| `1` | 全部失败 / 系统错误 |
+| `2` | 参数错误 |
+| `3` | 资源未找到 |
+| `4` | 权限不足 |
+| `5` | 冲突 |
+| `6` | 部分失败（批量中部分任务失败） |
+
+## 环境变量
+
+| 变量 | 说明 |
+|---|---|
+| `ADP_API_KEY` | API Key（优先于配置文件） |
+| `ADP_API_BASE_URL` | 服务地址 |
+| `ADP_LANG` | 界面语言（`en` / `zh`） |
+| `ADP_LOG_LEVEL` | 日志级别（`debug` / `info` / `warn` / `error`） |
+
+## 配置存储
+
+- 配置目录：`~/.adp/`
+- 配置文件：`~/.adp/config.json`
+- 加密的 API Key：`~/.adp/key.enc`（AES-256-GCM）
+- 应用缓存：`~/.adp/app_cache.json`
+- 版本检查缓存：`~/.adp/version_check.json`（每 24 小时刷新）
+
+## 许可证
+
+商业许可协议 —— 详见 [license.md](license.md)。非商业用途（个人学习、研究、教学、开源社区交流等）可免费使用。商业用途需获得来也科技书面授权。联系：global_product@laiye.com
+
+## 参与贡献
+
+跨平台构建：`make build-all VERSION=v1.0.0`。运行 E2E 测试：`bash tests/test.sh`。

package/license.md

@@ -0,0 +1,51 @@
+Commercial License Agreement
+
+Effective Date: [March 30, 2026]
+Copyright © 2026 [Laiye Technology (Beijing) Co., Ltd.] All rights reserved.
+
+This “Skill” (referring to the entirety including models, software, code, weights, documentation, data, and related derivative works, “the Product”) is developed and wholly owned by Laiye Technology (Beijing) Co., Ltd. (“Licensor”). The mentioned derivative works refer to new works created by modifying, integrating, fine-tuning, or further developing the Product. Subject to your (“Licensee” or “you”) compliance with the terms of this Agreement, the Licensor grants you a worldwide, royalty-free, non-exclusive license.
+
+1. Licensing
+
+1.1 Free Use and Distribution: The Licensor grants the Licensee a non-transferable, non-exclusive right to freely use, copy, publish, and distribute copies of the Product for non-commercial purposes. The aforementioned "non-commercial purposes" include, but are not limited to:
+Personal learning, research, teaching, and evaluation.
+Technical exchanges within academic institutions or open-source communities, non-profit projects.
+Integration or demonstration in non-commercial products or services.
+1.2 Commercial License:	Any activity intended to directly or indirectly obtain commercial benefits, revenue, or consideration (“Commercial Exploitation”) requires the explicit written authorization (i.e., a "Commercial License") from the Licensor. Commercial Exploitation includes, but is not limited to:
+Distributing the Product or derivative works thereof in forms such as sales, resale, licensing fees, subscription fees, or other charges.
+Providing the Product or derivative works thereof as a SaaS (Software as a Service) to third parties.
+Integrating the Product or derivative works thereof, as a core function, into software, hardware, or services intended for sale or lease.
+Any for-profit activity that utilizes the functionality or content of the Product to provide services to third parties.
+
+2. Reserved Rights and Ownership
+
+2.1	Ownership, intellectual property rights (including but not limited to copyright, patents, trademarks, trade secrets), and other related rights and interests in the Product (including all copies thereof) belong to the Licensor or its affiliates. This Agreement does not constitute any form of transfer of rights or sale of the Licensor's intellectual property.
+2.2	The Licensee may non-commercially distribute unmodified copies of the Product through channels such as open-source platforms, or engage in non-commercial further development, and distribution, provided that this Agreement, the copyright notice, and the original identification are fully retained.
+3. Distribution Conditions
+
+When the Licensee distributes or provides the Product, all of the following conditions must be met:
+Retention of Notices:	Prominently retain all copyright notices of the Product, the text of this License Agreement, and the disclaimer on distributed copies.
+No Misrepresentation:	Should not imply that the Licensor endorses your distribution version.
+
+4. Disclaimer of Warranties
+
+THE PRODUCT IS PROVIDED "AS IS", WITHOUT WARRANTIES OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO: THE LICENSOR DOES NOT WARRANT THAT THE PRODUCT IS FREE FROM ERRORS, BUGS, WILL OPERATE PROPERLY, OR IS SUITABLE FOR A PARTICULAR PURPOSE; THE LICENSOR DOES NOT WARRANT THAT USE OF THE PRODUCT WILL NOT INFRINGE UPON THIRD-PARTY RIGHTS; THE LICENSOR SHALL NOT BE LIABLE TO THE LICENSEE OR ANY THIRD PARTY FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, OR PUNITIVE DAMAGES ARISING FROM THE USE OF THE PRODUCT.
+
+5. Termination
+
+5.1	This Agreement becomes effective from the Licensee's first use of the Product and continues until terminated.
+5.2	If the Licensee violates the restrictions in Article 1 "License Grant" of this Agreement (e.g., unauthorized Commercial Exploitation), this Agreement will terminate automatically without prior notice.
+5.3	Upon termination, the Licensee must immediately cease using the Product and destroy all copies of the Product in its possession.
+
+6. Miscellaneous
+
+6.1	The formation, execution, interpretation, and dispute resolution of this Agreement shall be governed by the laws of the People's Republic of China.
+6.2	The Licensee shall not assign or transfer any of its rights or obligations under this Agreement without the Licensor's prior written consent.
+6.3	This Agreement constitutes the entire agreement between the parties concerning this license matter and supersedes any prior oral or written communications and agreements between the parties regarding this matter.
+6.4	Any dispute related to this Agreement shall be settled through friendly negotiation between the parties. If negotiation fails, either party has the right to submit the dispute to the competent court in the place where the Licensor is registered.
+
+For obtaining a Commercial License or if you have any questions, please contact:
+[global_product@laiye.com]
+
+
+The Product is licensed under the Commercial License Agreement.  For commercial use, please contact us to obtain authorization.

package/package.json

@@ -0,0 +1,49 @@
+{
+  "name": "@laiye-adp/agentic-doc-parse-and-extract-cli",
+  "version": "1.11.0-beta.4",
+  "description": "Official CLI for Laiye ADP (Agentic Document Processing) - document parsing and intelligent extraction",
+  "keywords": [
+    "adp",
+    "laiye",
+    "document",
+    "parsing",
+    "extraction",
+    "ocr",
+    "cli"
+  ],
+  "homepage": "https://github.com/laiye-ai/adp-cli",
+  "bugs": {
+    "url": "https://github.com/laiye-ai/adp-cli/issues"
+  },
+  "repository": {
+    "type": "git",
+    "url": "https://github.com/laiye-ai/adp-cli.git"
+  },
+  "license": "SEE LICENSE IN license.md",
+  "bin": {
+    "adp": "bin/adp"
+  },
+  "files": [
+    "bin/adp"
+  ],
+  "engines": {
+    "node": ">=14.0.0"
+  },
+  "os": [
+    "win32",
+    "linux",
+    "darwin"
+  ],
+  "cpu": [
+    "x64",
+    "arm64"
+  ],
+  "optionalDependencies": {
+    "@laiye-adp/adp-cli-linux-x64": "1.11.0-beta.4",
+    "@laiye-adp/adp-cli-linux-arm64": "1.11.0-beta.4",
+    "@laiye-adp/adp-cli-darwin-x64": "1.11.0-beta.4",
+    "@laiye-adp/adp-cli-darwin-arm64": "1.11.0-beta.4",
+    "@laiye-adp/adp-cli-win32-x64": "1.11.0-beta.4",
+    "@laiye-adp/adp-cli-win32-arm64": "1.11.0-beta.4"
+  }
+}