PromptReview Proxy (promptreview-proxy)
promptreview-proxy is a lightweight, local HTTP proxy forwarding server for the PromptReview VS Code Extension.
Features
- Local HTTP Proxying: Intercepts outbound LLM traffic from VS Code (
http.proxy). - Cloud Analytics Relay: Asynchronously logs prompt metadata to your API subdomain (
https://api.prompt-guard-ai.com/v1/prompts). - Dynamic Provider Routing: Forwards requests to target LLM providers (OpenAI, Anthropic, Groq, Ollama, etc.) and streams responses back to VS Code.
Quick Start
Installation
pip install promptreview-proxy
Usage
Run the proxy server from command line:
promptreview-proxy
Model routing
The VS Code model identifier is not necessarily an OpenAI API model name. The proxy sends LLM_DEFAULT_MODEL (default gpt-4o) unless an explicit alias is configured in LLM_MODEL_ROUTE_MAP.
For example, to route a VS Code model named Raptor to OpenAI's gpt-4o model:
export LLM_DEFAULT_MODEL=gpt-4o
export LLM_MODEL_ROUTE_MAP='{"raptor":"gpt-4o"}'
Or configure environment variables:
export PROXY_PORT=6767
export API_BASE_URL="https://api.prompt-guard-ai.com"
promptreview-proxy
1 maintainer
Release files for promptreview-proxy 0.1.10
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| promptreview_proxy-0.1.10-py3-none-any.whl | Python 3 | none | any | Details |
Release files / promptreview_proxy-0.1.10-py3-none-any.whl
| Download URL | promptreview_proxy-0.1.10-py3-none-any.whl |
|---|---|
| Size | 8.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
262da772366968e2eb87883b036bb9ab07e67266030809412ae6f7ad3deb1b84
|
|
BLAKE2b-256 checksum How to use checksums |
286057d21a2babf38519a158cd473de0811bcb63634cfd2186f063db03cb1383
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.7
|
