mirror of
https://github.com/Routstr/routstr-core.git
synced 2026-08-11 19:57:32 +00:00
Jeroen UbbinkandClaude Fable 5
cbdbe4b899
Every statement and branch of the topup path (recieve_token, swap_to_primary_mint and its helpers, credit_balance) is now covered, including the previously untested mint-failure/recovery block: recovery must never credit proofs the wallet does not hold, and post-melt failures must propagate unwrapped since the foreign proofs are already spent. On testing internals: orchestration and side effects are tested only through the public functions, with mocks at the external mint boundary (the cashu Wallet object) — no internal code is ever mocked. The two pure leaf helpers (_melt_insufficient_shortfall, _net_minted_amount) are tested directly instead: their input spaces (seven error formats across mint implementations, sat/msat conversions both ways) would cost ~30 lines of quote/melt mock choreography per case through the swap loop, for the same assertion a parametrize row makes. The same-mint branch of _calculate_swap_amount is unreachable from public callers today; its test documents the contract for the planned pre-flight fee estimation, which will call it directly. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Routstr Payment Proxy
Routstr is a decentralized protocol for permissionless, private, and censorship-resistant AI inference. It combines Nostr for discovery and Cashu for private Bitcoin micropayments.
This repo contains Routstr Core: a FastAPI-based reverse proxy that sits in front of OpenAI-compatible APIs and handles pay-per-request billing.
Start Here
- Overview: https://docs.routstr.com/overview/
- Provider Guide: https://docs.routstr.com/provider/quickstart/
- User Guide: https://docs.routstr.com/user-guide/introduction/
Basic Usage
If you are a user/developer, you just point an OpenAI-compatible SDK at a Routstr node and pay with a Cashu token.
OpenAI SDK
from openai import OpenAI
client = OpenAI(
base_url="https://api.routstr.com/v1",
api_key="cashuBo2FteCJodHRwczovL21...",
)
response = client.chat.completions.create(
model="gpt-5-nano",
messages=[{"role": "user", "content": "hello"}],
)
print(response.choices[0].message.content)
cURL
curl https://api.routstr.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "x-cashu: cashuBo2FteCJodHRwczovL21..." \
-d '{
"model": "gpt-5-nano",
"messages": [{"role": "user", "content": "hello"}]
}'
Quick Start (Docker)
If you are a node runner, start a Routstr Core instance using Docker Compose:
-
Prepare your
.env:ADMIN_PASSWORD=mysecretpassword NAME="My AI Node" DESCRIPTION="Fast access to models" NSEC=yournsec RECEIVE_LN_ADDRESS=yourname@wallet.com -
Start the services:
docker compose up -d -
Configure: Open http://localhost:8000/admin/ to connect your AI providers and set pricing.
For full instructions, see the Provider Quick Start Guide.
Development
make setup
cp .env.example .env
fastapi run routstr