Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.nanny.run/llms.txt

Use this file to discover all available pages before exploring further.

​
What it does

@nanny_tool and #[nanny::tool] govern tool calls that go through your Rust or Python code. But some tools make HTTP requests without any decorator — LLM client libraries, database drivers, third-party SDKs, HTTP-based MCP tools. Those calls bypass @nanny_tool entirely. HTTP proxy mode fills that gap. When enabled, the governance server acts as an HTTP CONNECT proxy. Your agent sets standard proxy environment variables. All outbound HTTP and HTTPS traffic from the agent — regardless of which library or function makes the call — routes through the server. The server checks each request against an allowlist before forwarding it. A request to a host not on the allowlist gets a 403 Forbidden and the governance server emits a ToolDenied event in the NDJSON log. This covers the outbound HTTP surface without any code changes to your agent.

​
Enable proxy mode

nanny init generates a nanny.toml with a [proxy] section already present but commented out. To activate proxy mode, uncomment allowed_hosts and add the hosts your agent needs to reach: 
[proxy]
allowed_hosts = ["api.openai.com", "api.groq.com", "*.anthropic.com"]
Proxy mode is active only when allowed_hosts is non-empty. Leaving it commented out — or setting an empty list — disables proxy mode entirely. The governance server validates this list at startup. If --proxy is passed but allowed_hosts is empty, the server refuses to start with a clear error.

​
Configure your agent

Add the standard proxy variables to your agent project’s .env file: 
# .env
HTTP_PROXY=http://127.0.0.1:62669
HTTPS_PROXY=http://127.0.0.1:62669
Most HTTP client libraries — Python’s httpx, requests, aiohttp; Node’s fetch; curl — respect these variables automatically. No code changes needed. Most agent frameworks load .env on startup; if yours doesn’t, pass the variables inline: 
HTTP_PROXY=http://127.0.0.1:62669 HTTPS_PROXY=http://127.0.0.1:62669 nanny run
For HTTPS traffic, the proxy uses HTTP CONNECT tunneling: the client sends a CONNECT request to the proxy, the proxy opens a TCP tunnel to the target, and the TLS handshake happens inside the tunnel between the client and the target server. The proxy sees the hostname and port but not the decrypted content of HTTPS requests.

​
Host allowlist rules

​
Exact hostnames

allowed_hosts = ["api.openai.com", "api.anthropic.com"]
Matches only the exact hostname. api.openai.com does not match beta.openai.com.

​
Wildcard subdomains

allowed_hosts = ["*.openai.com", "*.anthropic.com"]
*.openai.com matches api.openai.com, beta.openai.com, platform.openai.com — any single subdomain level. It does not match openai.com itself (no wildcard prefix) and does not match api.us.openai.com (wildcards are single-level only).

​
Combining both

allowed_hosts = [
  "api.openai.com",       # exact — this specific API endpoint
  "*.anthropic.com",      # wildcard — any Anthropic subdomain
  "api.groq.com",         # exact — Groq API
]

​
What is always blocked

Some address ranges are blocked regardless of your allowed_hosts list:
RangeBlocked because
Loopback (127.x.x.x, ::1)localhost services
Link-local (169.254.x.x)cloud metadata endpoints (AWS, GCP, Azure)
RFC-1918 private ranges (10.x.x.x, 172.16–31.x.x, 192.168.x.x)internal network services

​
The event log

Every proxied request produces an event in the NDJSON log: Allowed request: 
{"event":"ToolAllowed","ts":1711234567120,"tool":"http_proxy","target":"api.openai.com:443"}
Denied request (not in allowlist): 
{"event":"ToolDenied","ts":1711234567320,"tool":"http_proxy","target":"malicious.example.com:443"}
{"event":"ExecutionStopped","ts":1711234567321,"reason":"ToolDenied","steps":3,"cost_spent":30,"elapsed_ms":1250}
A proxy denial is a hard stop — the same outcome as any other ToolDenied event. The agent process exits immediately.

​
Cost accounting and HTTPS content

Two things to be aware of when combining proxy mode with the rest of Nanny:
  • Cost accounting requires @nanny_tool. Proxy requests are logged as events but not charged against your cost budget. For cost-tracked HTTP calls, decorate the function with @nanny_tool or use nanny::http_get.
  • HTTPS content is not inspected. The proxy allows or denies by hostname. It cannot read request or response bodies inside HTTPS tunnels.

​
Example: LLM client with proxy

Most LLM client libraries pick up HTTP_PROXY and HTTPS_PROXY automatically. Here’s a complete example with the OpenAI Python client: 
import os
from openai import OpenAI

# The client picks up HTTP_PROXY / HTTPS_PROXY from the environment.
# No code changes needed — just set the env vars before starting your agent.
client = OpenAI()

response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "Hello"}],
)
nanny.toml: 
[proxy]
allowed_hosts = ["api.openai.com"]
If your agent tries to call any other API host, it gets a 403 and the execution stops.