fix(#1329): restart hive-matrix-daemon after token write so new credential is picked up immediately

This commit is contained in:
damocles 2026-06-05 12:13:37 +02:00 committed by mara
commit f201f04d4e
4 changed files with 52 additions and 0 deletions

View file

@ -697,6 +697,15 @@ pub async fn ensure_user_for(
.await
.with_context(|| format!("matrix: write matrix-token for {name} via hive-priv"))?;
tracing::info!(%name, "matrix: provisioned access token");
// Kick the daemon so it picks up the new token without waiting for a
// full container restart — see docs/matrix.md::Provisioning flow.
if let Err(e) = crate::priv_client::restart_matrix_daemon(name).await {
tracing::warn!(%name, error = ?e, "matrix: could not restart hive-matrix-daemon (token written; daemon will reload on next container start)");
} else {
tracing::info!(%name, "matrix: restarted hive-matrix-daemon to pick up new token");
}
Ok(())
}

View file

@ -280,6 +280,17 @@ pub async fn write_agent_matrix_token(agent_name: &str, token: &str) -> Result<(
.await?)
}
/// Restart `hive-matrix-daemon.service` inside an agent container via
/// `systemctl --machine=h-<agent_name> restart hive-matrix-daemon.service`.
/// Non-fatal: callers should handle errors gracefully — if the container is
/// not running the restart will fail (the unit starts naturally on next boot).
pub async fn restart_matrix_daemon(agent_name: &str) -> Result<()> {
ok(call(&PrivRequest::RestartMatrixDaemon {
agent_name: agent_name.to_owned(),
})
.await?)
}
fn check(resp: PrivResponse) -> Result<(String, String)> {
if resp.ok {
Ok((resp.stdout, resp.stderr))

View file

@ -337,6 +337,28 @@ async fn exec(req: PrivRequest, writer: &mut OwnedWriteHalf) -> Result<(String,
validate_agent_name(agent_name)?;
write_agent_state_file(agent_name, "matrix-token", &format!("{token}\n"))
}
PrivRequest::RestartMatrixDaemon { ref agent_name } => {
validate_agent_name(agent_name)?;
let machine = format!("--machine=h-{agent_name}");
let unit = "hive-matrix-daemon.service";
let out = Command::new("systemctl")
.args([&machine, "restart", unit])
.output()
.await
.with_context(|| format!("systemctl restart {unit} in container h-{agent_name}"))?;
if !out.status.success() {
bail!(
"systemctl restart {unit} in h-{agent_name} exited {}: {}",
out.status,
String::from_utf8_lossy(&out.stderr).trim()
);
}
Ok((
String::from_utf8_lossy(&out.stdout).into_owned(),
String::from_utf8_lossy(&out.stderr).into_owned(),
))
}
}
}

View file

@ -189,6 +189,7 @@ pub enum PrivRequest {
DaemonReload,
/// Synchronise the nginx unit inside the `hive-gateway` container.
///
/// hive-priv queries `ActiveState` and dispatches:
/// - `active` → `systemctl reload nginx` (SIGHUP, zero-downtime)
/// - `failed` → `systemctl reset-failed nginx` + `systemctl start nginx`
@ -254,6 +255,15 @@ pub enum PrivRequest {
/// Token value. hive-priv appends a trailing newline before writing.
token: String,
},
/// Restart `hive-matrix-daemon.service` inside an agent container via
/// `systemctl --machine=h-<agent_name> restart hive-matrix-daemon.service`.
/// Used by hive-c0re to kick the daemon after a successful token write
/// so it picks up the new credential without a full container restart.
RestartMatrixDaemon {
/// Logical agent name (validated by `validate_agent_name`).
agent_name: String,
},
}
/// Response from the privileged helper.