Skip to main content

LLM-driven A-share (Shanghai/Shenzhen main board) stock screening CLI

Project description

DeepTrade

本地运行的 A 股(沪深主板)选股 CLI 工具:tushare 行情 + OpenAI 兼容 LLM(DeepSeek / Qwen / Kimi …)+ DuckDB 单机仓库 + 插件式 CLI 框架。

tests python license

✨ 主要特性

  • 轻量本地化:单文件 DuckDB + uv,一条命令跑完,无需服务进程或容器。
  • 纯透传式插件 CLI:框架命令面封闭——只管 init / config / plugin / data;其余命令一律按 deeptrade <plugin_id> <argv...> 透传给插件,插件自管 --help、子命令、参数、持久化。新增插件类型(皮肤、新数据源、回测、IM 渠道……)零框架改动。
  • 数据隔离(Plan A):每个插件在自己的 migrations 里声明并拥有自己的表(含 tushare 派生数据),框架不持有任何业务表。tushare_sync_state / tushare_calls / llm_calls 都按 plugin_id 维度隔离。
  • 顶层通知 APIfrom deeptrade import notify, notification_session 一行发推送;框架根据已安装的 channel 插件自动路由,无 channel 时自动 noop。
  • 多 LLM Provider 共存llm.providers 字典化配置,多个 OpenAI 兼容服务并存;插件通过 LLMManager.get_client(name=...) 按名取用,单次 run 内可调多家。
  • LLM 强约束:JSON 模式 + Pydantic 双层校验;永远不传 tools / function calls。
  • 盘中数据隔离--allow-intraday 模式下同步的不完整数据写入 data_completeness='intraday',日终模式严格拒绝命中。

🚀 5 分钟上手

安装

# 推荐
uv sync --all-extras
uv run pre-commit install

# 兜底(无 uv)
python -m venv .venv && source .venv/bin/activate  # Windows: .\.venv\Scripts\activate
pip install -e ".[dev]"

初始化与配置

deeptrade init                            # 建库 + 应用 core migrations
deeptrade config set-tushare              # 交互式输入 tushare token
deeptrade config set-llm                  # 交互式增/改/删 LLM provider(deepseek / qwen / kimi …)
deeptrade config list-llm                 # 列出已配置且可用的 provider
deeptrade config test-llm                 # 对所有 provider 做连通性自检(也可加 <name> 单测)
deeptrade config show                     # 表格展示当前配置(密钥脱敏)

安装内置插件并运行

# 安装一个 strategy 插件 + 一个 channel 插件
deeptrade plugin install ./deeptrade/strategies_builtin/limit_up_board -y
deeptrade plugin install ./deeptrade/channels_builtin/stdout -y

deeptrade plugin list                     # 查看已安装

# 运行打板策略(CLI 由插件自管,--help 由插件渲染)
deeptrade limit-up-board --help
deeptrade limit-up-board run              # 默认日终模式
deeptrade limit-up-board run --allow-intraday --force-sync

# 运行成交量异动策略(三模式)
deeptrade volume-anomaly screen           # 异动筛选 → upsert va_watchlist
deeptrade volume-anomaly analyze          # LLM 主升浪启动预测
deeptrade volume-anomaly prune --days 30  # 剔除追踪 ≥30 日的标的

# 推送链路自检
deeptrade stdout-channel test

报告产出在 ~/.deeptrade/reports/<run_id>/

📦 命令矩阵

框架命令(封闭集合)

命令 用途
deeptrade --version / -V 显示版本
deeptrade --help / -h 框架命令清单(枚举插件子命令)
deeptrade init [--no-prompts] 建库 + 应用 core migrations
deeptrade config {show, set, set-tushare, set-llm, list-llm, test-llm} 全局配置
deeptrade plugin install <path> [-y] 本地路径安装(绝不联网)
deeptrade plugin list / info <id> 列表 / 详情
deeptrade plugin enable <id> / disable <id> 启 / 停
deeptrade plugin uninstall <id> [--purge] 卸载(--purge 才 DROP 表)
deeptrade plugin upgrade <path> 升级(增量 migrations)
deeptrade data sync ... (暂停用,下版本恢复)

保留字(不可作为 plugin_id):init / config / plugin / data

插件命令(按 plugin_id 透传,插件自管)

命令 来源
deeptrade limit-up-board {run, sync, history, report} 内建打板策略插件
deeptrade volume-anomaly {screen, analyze, prune, history, report} 内建成交量异动插件
deeptrade stdout-channel {test, log} 内建 stdout 通知插件
deeptrade <你的-plugin-id> ... 你自己写的任何插件

任意插件子命令的 --help 都由插件自身渲染——框架不感知动词语义。

🧱 架构

┌──────────────────────── deeptrade CLI (custom click.Group) ────────────────────────┐
│                                                                                    │
│  framework commands (closed):                                                      │
│      init │ config │ plugin │ data                                                 │
│                                                                                    │
│  plugin pass-through (open):                                                       │
│      <plugin_id>  ──argv──→  Plugin.dispatch(argv) → int  (plugin owns the rest)   │
└──────────────────────────────────┬─────────────────────────────────────────────────┘
                                   │
            ┌──────────────────────┼──────────────────────────┐
            ▼                      ▼                          ▼
   ┌─────────────────┐   ┌──────────────────┐    ┌────────────────────┐
   │ Core services    │   │ deeptrade.notify │    │  Plugins (any type)│
   │ DuckDB · Config │   │ → routes to all  │    │  • metadata        │
   │ Tushare · LLM   │   │   enabled        │    │  • validate_static │
   │ Notifier        │   │   channel plugins│    │  • dispatch(argv)  │
   └─────────────────┘   └──────────────────┘    │  (channel: + push) │
                                                  └────────────────────┘

设计决策见 docs/plugin_cli_dispatch_evaluation.md

📖 文档

⚖️ 免责声明

本工具仅用于策略研究、数据整理与候选标的分析,不构成投资建议不进行自动交易。所有 LLM 输出基于提交的结构化数据,不引用任何外部信息源;用户应自行核验候选标的的最新状态后再做决策。

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

deeptrade_quant-0.0.2.tar.gz (208.1 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

deeptrade_quant-0.0.2-py3-none-any.whl (207.7 kB view details)

Uploaded Python 3

File details

Details for the file deeptrade_quant-0.0.2.tar.gz.

File metadata

  • Download URL: deeptrade_quant-0.0.2.tar.gz
  • Upload date:
  • Size: 208.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for deeptrade_quant-0.0.2.tar.gz
Algorithm Hash digest
SHA256 bd68b458993a7b56f6abc57a55362c5123b6312cb97760c086418b383ff32b04
MD5 ce0ec4409c13f2deb2cdcb817d27a01a
BLAKE2b-256 d1ef52b2c352bd5234edde36226b4a13c4b25ee2195d08f8228b3b3833e8fe4c

See more details on using hashes here.

Provenance

The following attestation bundles were made for deeptrade_quant-0.0.2.tar.gz:

Publisher: release.yml on ty19880929/DeepTrade

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file deeptrade_quant-0.0.2-py3-none-any.whl.

File metadata

  • Download URL: deeptrade_quant-0.0.2-py3-none-any.whl
  • Upload date:
  • Size: 207.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for deeptrade_quant-0.0.2-py3-none-any.whl
Algorithm Hash digest
SHA256 568852951bc02bc94b467b39e1b6579633ab0fe0cc24228a4a0a2d33abc8ca15
MD5 f2800219ea051fef5af011cd65fc44c3
BLAKE2b-256 0ab7314e6f4215b559915f4f1c0d64e9d2f1997b89ed1da784921f21719784c7

See more details on using hashes here.

Provenance

The following attestation bundles were made for deeptrade_quant-0.0.2-py3-none-any.whl:

Publisher: release.yml on ty19880929/DeepTrade

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page