mirror of
https://github.com/Routstr/routstr-core.git
synced 2026-08-09 02:54:37 +00:00
thefux
3e906605a0
Fixes three issues that caused per-mint rate-limit state to never recover: 1. _is_mint_rate_limited: remove substring matching on 'rate limit' / 'too many requests' in exception messages. Only HTTP 429 (httpx.HTTPStatusError) is now classified as a rate limit, preventing false positives (e.g. a 503 with 'database rate exceeded' in its body). 2. _run_probe: use apply_cooldown() instead of apply_rate_limit_cooldown() when a probe fails due to a rate limit. The probe is a recovery check, not a new request, so it should not escalate the exponential backoff counter (_consecutive_rate_limits). This prevents the cooldown from ratcheting 60s → 120s → 240s → ... → 7h on repeated probe failures. 3. classify_redemption_error: split the combined _is_mint_rate_limited || is_mint_connection_error check into two separate classifications: - mint_rate_limited / cashu_mint_rate_limited (503, retryable) - mint_unreachable / cashu_mint_unreachable (503, retryable) Callers (routstrd) can now distinguish temporary rate limits from permanent connection failures when deciding fallback strategy. Tests: 20 new tests covering strict 429 detection, classification priority, probe non-escalation, and cooldown reset behaviour.
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