Files
LangBot/en/develop/plugin-runtime.mdx
T

96 lines
3.8 KiB
Plaintext

---
title: "Debugging Plugin Runtime, CLI, SDK"
---
<Info>
Plugin Runtime, CLI, SDK are open sourced at: https://github.com/langbot-app/langbot-plugin-sdk
</Info>
Since LangBot depends on entities defined in langbot-plugin-sdk, we recommend opening VS Code in a new directory, placing both LangBot and langbot-plugin-sdk (git clone https://github.com/langbot-app/langbot-plugin-sdk) as subdirectories within it. The directory structure should look like:
```bash
langbot-projects
├── LangBot
├── langbot-plugin-sdk
```
Enter the LangBot directory and install dependencies:
```bash
cd LangBot
uv sync --dev
```
At this point, uv will automatically create a virtual environment (.venv) for you. If your editor asks whether to use this virtual environment, please select `Yes`.
<img
width="600"
src="/images/zh/develop/confirm_venv.png"
/>
If the prompt does not appear, please manually set the Python interpreter path to the interpreter in the venv from the bottom-right corner.
Then open the terminal at the bottom of VS Code, which will automatically activate the venv.
Or you can manually activate this virtual environment:
```bash
# Please modify the command according to your .venv path
source .venv/bin/activate
```
## Start Plugin Runtime
```bash
uv run --no-sync lbp rt
```
Or start it via `python -m langbot_plugin.cli.__init__ rt`.
Plugin Runtime accepts the following parameters:
- `--debug-only`: Do not start plugins in the `data/plugins` directory, only allow loading plugins through debug connections.
- `--ws-debug-port`: Debug port to listen on, default is `5401`.
- `--ws-control-port`: Control port to listen on (for LangBot main program connection), default is `5400`.
- `-s`: Use `stdio` to accept control connections. **Use only in production environment**.
- `--skip-deps-check`: To ensure that all plugin dependencies are installed, the Runtime will check and install all installed plugin dependencies on every startup. Use this parameter to disable this check.
### Make LangBot Use Your Locally Modified langbot-plugin-sdk
If you have modified things like message entities or plugin data definitions, you need to update them in the LangBot environment to ensure data format compatibility during runtime.
In a **terminal with the LangBot directory's virtual environment (.venv) activated**, switch to the langbot-plugin-sdk directory and run:
```bash
uv pip install .
```
This will install your modified langbot-plugin-sdk into LangBot's environment.
### Make LangBot Connect to This Runtime
Configure `plugin.runtime_ws_url` to `ws://localhost:5400/control/ws` in LangBot's `data/config.yaml`.
```yaml
plugin:
runtime_ws_url: ws://localhost:5400/control/ws
```
And add the startup parameter `--standalone-runtime` when starting the LangBot main program (e.g., `uv run --no-sync main.py --standalone-runtime`). Make sure to include the `--no-sync` parameter in this command, which ensures that the local langbot-plugin-sdk you just synced will not be overwritten by the remote version.\
Restart LangBot, and it will connect to this runtime using WebSocket.
## langbot-plugin-sdk Architecture
This codebase contains the following:
- `langbot_plugin.api`: Plugin-related entities and API definitions.
- `langbot_plugin.assets`: Plugin templates.
- `langbot_plugin.cli`: Plugin development CLI tools.
- `langbot_plugin.entities`: Plugin system-related entities not defined in API.
- `langbot_plugin.runtime`: Plugin runtime and underlying communication (stdio and websocket) implementation.
## `lbp` CLI Tool
The CLI tool provides Runtime startup, plugin initialization, plugin component management, Marketplace interaction, and other functions.
For detailed program entry points, please see [`langbot_plugin.cli.__init__`](https://github.com/langbot-app/langbot-plugin-sdk/blob/main/src/langbot_plugin/cli/__init__.py).