28 lines
1.4 KiB
Markdown
28 lines
1.4 KiB
Markdown
**Background Vision Agent (Windows)**
|
|
|
|
- One-command setup/run: `powershell -ExecutionPolicy Bypass -File .\run.ps1`
|
|
- Requires Python 3.9+ and an `OPENAI_API_KEY` in your user environment.
|
|
- Runs hidden (uses `pythonw.exe`) and listens for global hotkeys.
|
|
|
|
**Hotkeys**
|
|
|
|
- Alt+Shift+1 — Capture active window (added to input buffer)
|
|
- Alt+Shift+2 — Send payload (buffered images + prompt) to OpenAI; save response
|
|
- Alt+Shift+3 — Action 3 (depends on mode)
|
|
- Mode 1: Type response char-by-char into current input field
|
|
- Mode 2: Clipboard mode: primes clipboard with first char; every Ctrl+V advances to next char
|
|
- Alt+Shift+4 — Reset program state (clears buffers and captured files)
|
|
- Alt+Shift+5 — Quit permanently (press 3x within 2 seconds); also deletes app data directory
|
|
- Alt+Shift+6 — Switch Action 3 mode (toggle between Mode 1 and Mode 2)
|
|
|
|
**Customize**
|
|
|
|
- Edit defaults in `bg_agent/config.py` (hotkeys, model, prompt, typing speed). The endpoint is hardcoded via the official OpenAI Python SDK.
|
|
- App data directory (captures, response, logs): `%LOCALAPPDATA%\BgVisionAgent`.
|
|
|
|
**Notes**
|
|
|
|
- Windows is supported now; code is structured to later add macOS/Linux window capture backends.
|
|
- No admin privileges are required. If a hotkey conflicts with another app, change it in `bg_agent/config.py`.
|
|
- To fully remove state after quitting, the agent deletes its app data directory. Source files and the virtual env remain unless manually removed.
|