Watch
0
0
Fork
You've already forked hyperhive
0
hyperhive/hive-forge-notify/src/bin/hive-github-notify/main.rs
atlas cf763da178 hive-github-notify: pick up a rotated PAT without a restart
The poller read `<state>/github-token` once at start, so after a PAT
rotation it kept polling with the revoked token until the unit
restarted. It now re-reads the file on every tick, as
`hive-forge-notify` does: a different non-empty value rebuilds the
GitHub source, clears the own-login cache, and logs one info line. A
missing or empty file keeps the token in use.

A 401 from the notifications endpoint is now logged at warn, once per
token value; other non-2xx statuses stay at debug.

Part of #5017 (slice G).
2026-10-13 08:07:47 +02:00

301 lines
12 KiB
Rust

//! `hive-github-notify` binary — long-running per-agent **github.com**
//! notification poller. Same delivery path as its Forgejo sibling: unread
//! list, per-thread summary, todo upsert on the harness's in-agent socket,
//! mark read on the source.
//!
//! Takes no arguments. `HYPERHIVE_STATE_DIR` holds the PAT
//! (`github-token`, fetched from the swarm secret store by
//! `nix/agent-modules/github-token.nix` — see `docs/integrations/github.md`)
//! and `HIVE_AGENT_SOCKET` is the harness's todo socket.
//! Having a PAT *is* the opt-in: with no token the poller logs why and
//! exits 0, so deploying this unit to an agent that never gets one costs a
//! settled process rather than a restart loop. Once polling, it re-reads
//! `github-token` on every tick, so a rotated PAT takes effect on the next
//! poll without a restart.
//!
//! ⚠️ Reading the notification stream needs the **`notifications` scope**
//! on the PAT — a token minted for `gh` + `git push` usually carries `repo`
//! only, which is enough to push and open PRs but not to read (or mark
//! read) notifications. A PAT without it is not fatal: the poller logs the
//! refusal and stays quiet, so the symptom is silence rather than an error.
mod source;
use std::collections::HashMap;
use std::time::Duration;
use hive_forge_notify::notify::{
POLL_INTERVAL_SECS, TOKEN_RETRY_MAX, TOKEN_RETRY_SECS, poll_once, resolve_own_login,
};
use hive_forge_notify::{HTTP_TIMEOUT_SECS, agent_socket, init_tracing};
use source::GithubSource;
use tracing::{debug, info, warn};
#[tokio::main]
async fn main() {
init_tracing();
let socket = agent_socket();
info!(socket = %socket.display(), "hive-github-notify starting");
// Returns only when no PAT ever arrives; otherwise loops forever.
github_loop(hive_forge_notify::state_dir(), socket).await;
}
/// Waits for the PAT to appear: the agent's store fetch writes the token
/// out of band and it takes effect without a rebuild, so an agent that gains
/// a PAT mid-session starts getting notifications on the next tick rather
/// than after a restart. Gives up — returning, so the process exits 0
/// rather than restart-looping — when no PAT ever arrives, which is the
/// common case for an agent that has the unit but no account.
async fn github_loop(state_dir: String, socket: std::path::PathBuf) {
let token_path = format!("{state_dir}/github-token");
let mut attempts = 0u32;
let token = loop {
match tokio::fs::read_to_string(&token_path).await {
Ok(t) if !t.trim().is_empty() => break t.trim().to_owned(),
_ => debug!("forge_notify: no github token at {token_path} yet"),
}
attempts += 1;
if attempts >= TOKEN_RETRY_MAX {
debug!(
"forge_notify: no github token after {TOKEN_RETRY_MAX} retries — github disabled"
);
return;
}
tokio::time::sleep(Duration::from_secs(TOKEN_RETRY_SECS)).await;
};
let client = match reqwest::Client::builder()
.timeout(Duration::from_secs(HTTP_TIMEOUT_SECS))
.build()
{
Ok(c) => c,
Err(e) => {
warn!("forge_notify: failed to build github HTTP client: {e}");
return;
}
};
let mut pat = Pat::new(source::API_BASE, token_path, token);
let mut own_login = resolve_own_login(&client, &pat.source).await;
let mut delivered: HashMap<String, String> = HashMap::new();
// GitHub tells callers how often it is willing to be polled
// (`X-Poll-Interval`, 60s in practice) and rate-limits those who
// ignore it. Start at our own cadence and re-arm to whatever the
// server asks for — never faster than it wants, never slower than we
// need.
let mut cadence = POLL_INTERVAL_SECS;
let mut interval = tokio::time::interval(Duration::from_secs(cadence));
interval.set_missed_tick_behavior(tokio::time::MissedTickBehavior::Delay);
interval.tick().await;
info!("forge_notify: github polling started");
loop {
interval.tick().await;
let hint = poll_tick(&mut pat, &mut own_login, &client, &socket, &mut delivered).await;
if let Some(secs) = hint.filter(|s| *s > cadence) {
debug!(
secs,
"forge_notify: github asked for a slower poll — re-arming"
);
cadence = secs;
interval = tokio::time::interval(Duration::from_secs(cadence));
interval.set_missed_tick_behavior(tokio::time::MissedTickBehavior::Delay);
interval.tick().await;
}
}
}
/// One poll: pick up a rotated PAT, resolve the own login if it is not
/// known for the PAT in use, then poll. Returns the server's poll-interval
/// hint.
async fn poll_tick(
pat: &mut Pat,
own_login: &mut String,
client: &reqwest::Client,
socket: &std::path::Path,
delivered: &mut HashMap<String, String>,
) -> Option<u64> {
if pat.reread() {
info!("forge_notify: github token changed on disk; using the new one");
own_login.clear();
}
if own_login.is_empty() {
*own_login = resolve_own_login(client, &pat.source).await;
}
poll_once(&pat.source, client, socket, delivered, own_login).await
}
/// The PAT in use and the source built from it. The agent's store fetch
/// replaces `github-token` by atomic rename when the PAT rotates and never
/// deletes it, so a missing or empty file means "not readable right now"
/// and keeps the current token.
struct Pat {
api_base: String,
path: std::path::PathBuf,
token: String,
source: GithubSource,
}
impl Pat {
fn new(api_base: &str, path: impl Into<std::path::PathBuf>, token: String) -> Self {
let source = GithubSource::new(api_base, &token);
Self {
api_base: api_base.to_owned(),
path: path.into(),
token,
source,
}
}
/// Re-read the file and swap to its token if it differs. `true` when
/// the token changed.
fn reread(&mut self) -> bool {
match hive_forge_notify::read_first_token(std::slice::from_ref(&self.path)) {
Some(t) if t != self.token => {
self.source = GithubSource::new(&self.api_base, &t);
self.token = t;
true
}
_ => false,
}
}
}
#[cfg(test)]
mod tests {
use std::collections::HashMap;
use tokio::io::{AsyncReadExt as _, AsyncWriteExt as _};
use tokio::sync::mpsc;
use super::{Pat, poll_tick};
fn scratch(tag: &str) -> std::path::PathBuf {
let ts = std::time::SystemTime::now()
.duration_since(std::time::UNIX_EPOCH)
.map_or(0, |d| d.as_nanos());
let dir = std::env::temp_dir().join(format!("hive-github-notify-{tag}-{ts}"));
std::fs::create_dir_all(&dir).expect("create scratch dir");
dir
}
/// A stand-in for api.github.com on loopback. Answers `/user` with a
/// login and `/notifications` with an empty page, and reports each
/// request as `(path, Authorization header)`.
async fn stub() -> (String, mpsc::UnboundedReceiver<(String, String)>) {
let listener = tokio::net::TcpListener::bind("127.0.0.1:0")
.await
.expect("bind");
let base = format!("http://{}", listener.local_addr().expect("addr"));
let (tx, rx) = mpsc::unbounded_channel();
tokio::spawn(async move {
loop {
let (mut sock, _) = listener.accept().await.expect("accept");
let mut buf = Vec::new();
let mut chunk = [0u8; 1024];
while !buf.windows(4).any(|w| w == b"\r\n\r\n") {
let n = sock.read(&mut chunk).await.expect("read");
if n == 0 {
break;
}
buf.extend_from_slice(&chunk[..n]);
}
let head = String::from_utf8_lossy(&buf).into_owned();
let path = head
.split_whitespace()
.nth(1)
.unwrap_or_default()
.to_owned();
let auth = head
.lines()
.find_map(|l| {
let (k, v) = l.split_once(':')?;
k.eq_ignore_ascii_case("authorization")
.then(|| v.trim().to_owned())
})
.unwrap_or_default();
let body = if path.starts_with("/user") {
r#"{"login":"me"}"#
} else {
"[]"
};
let reply = format!(
"HTTP/1.1 200 OK\r\ncontent-type: application/json\r\n\
content-length: {}\r\nconnection: close\r\n\r\n{body}",
body.len()
);
let _ = sock.write_all(reply.as_bytes()).await;
let _ = tx.send((path, auth));
}
});
(base, rx)
}
/// Every request one tick made, in order.
fn drain(rx: &mut mpsc::UnboundedReceiver<(String, String)>) -> Vec<(String, String)> {
std::iter::from_fn(|| rx.try_recv().ok()).collect()
}
fn poll(path: &str) -> bool {
path.starts_with("/notifications")
}
#[tokio::test]
async fn a_rotated_token_is_sent_on_the_next_poll() {
let (base, mut rx) = stub().await;
let dir = scratch("rotate");
let path = dir.join("github-token");
std::fs::write(&path, "old\n").expect("write");
let mut pat = Pat::new(&base, &path, "old".to_owned());
let mut own_login = String::new();
let mut delivered = HashMap::new();
let client = reqwest::Client::new();
let socket = dir.join("no-socket");
poll_tick(&mut pat, &mut own_login, &client, &socket, &mut delivered).await;
let first = drain(&mut rx);
assert!(first.iter().any(|(p, a)| poll(p) && a == "Bearer old"));
assert_eq!(own_login, "me");
std::fs::write(&path, "new\n").expect("write");
poll_tick(&mut pat, &mut own_login, &client, &socket, &mut delivered).await;
let second = drain(&mut rx);
assert!(second.iter().all(|(_, a)| a == "Bearer new"), "{second:?}");
assert!(second.iter().any(|(p, _)| poll(p)), "{second:?}");
// The own login is resolved again, under the new token.
assert!(second.iter().any(|(p, _)| p == "/user"), "{second:?}");
let _ = std::fs::remove_dir_all(&dir);
}
#[tokio::test]
async fn an_empty_or_missing_file_keeps_the_token_in_use() {
let (base, mut rx) = stub().await;
let dir = scratch("keep");
let path = dir.join("github-token");
let mut pat = Pat::new(&base, &path, "old".to_owned());
let mut own_login = String::new();
let mut delivered = HashMap::new();
let client = reqwest::Client::new();
let socket = dir.join("no-socket");
std::fs::write(&path, "\n").expect("write");
poll_tick(&mut pat, &mut own_login, &client, &socket, &mut delivered).await;
let empty = drain(&mut rx);
assert!(empty.iter().any(|(p, _)| poll(p)), "{empty:?}");
assert!(empty.iter().all(|(_, a)| a == "Bearer old"), "{empty:?}");
std::fs::remove_file(&path).expect("remove");
poll_tick(&mut pat, &mut own_login, &client, &socket, &mut delivered).await;
let missing = drain(&mut rx);
assert!(missing.iter().any(|(p, _)| poll(p)), "{missing:?}");
assert!(
missing.iter().all(|(_, a)| a == "Bearer old"),
"{missing:?}"
);
let _ = std::fs::remove_dir_all(&dir);
}
}