Files
PiCloud/crates/orchestrator-core/src/inbox.rs
MechaCat02 6b5da50a38 fix(orchestrator-core): F-Q-006 + F-Q-010 InboxRegistry expect on poison
InboxRegistry::register returned (Uuid, Receiver) even when the inner
Mutex was poisoned — `if let Ok(mut g) = self.inner.lock()` swallowed
the error, the sender was never inserted, the later deliver(id, …)
saw no entry and returned Abandoned, and the caller's `await rx`
blocked until the orchestrator's outer timeout.

Sister registries (RouteTable, AppDomainTable) already .expect()
panic on poison. Make InboxRegistry::{register, cancel, deliver} loud
in the same way.

A poisoned Mutex means a prior panic inside a critical section — the
process is unrecoverable; silently swallowing it just defers the
crash and corrupts the inbox protocol on the way.

AUDIT.md anchors: F-Q-006 (register), F-Q-010 (consistency policy).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-06-07 20:52:05 +02:00

146 lines
5.1 KiB
Rust

//! In-process `InboxRegistry` — the NATS-style request/reply
//! implementation for sync HTTP via the trigger outbox (design notes
//! §3).
//!
//! Workflow:
//! 1. Orchestrator allocates an `inbox_id`, calls
//! `registry.register()` to get a oneshot receiver.
//! 2. Orchestrator writes an outbox row with `reply_to = inbox_id`.
//! 3. Dispatcher picks the row, runs the script, calls
//! `registry.deliver(inbox_id, result)`.
//! 4. Orchestrator's `.await` on the receiver fires; it maps the
//! `InboxResult` back into an HTTP response.
//!
//! `Delivered` means the receiver was alive when delivery hit. If the
//! orchestrator timed out and dropped the receiver before delivery,
//! `Abandoned` comes back — the dispatcher writes an
//! `abandoned_executions` row (design notes §3 #9).
//!
//! Cluster mode (v1.3+) swaps this for a Postgres `LISTEN/NOTIFY`-
//! based resolver; the `InboxResolver` trait stays the same.
use std::collections::HashMap;
use std::sync::Mutex;
use async_trait::async_trait;
use picloud_shared::{InboxDeliveryOutcome, InboxResolver, InboxResult};
use tokio::sync::oneshot;
use uuid::Uuid;
pub struct InboxRegistry {
inner: Mutex<HashMap<Uuid, oneshot::Sender<InboxResult>>>,
}
impl InboxRegistry {
#[must_use]
pub fn new() -> Self {
Self {
inner: Mutex::new(HashMap::new()),
}
}
/// Allocate a new inbox id and register the sender side. The
/// caller awaits the returned `Receiver`; the dispatcher delivers
/// the outcome via `deliver(id, …)`.
///
/// F-Q-006: panic on poison — a poisoned mutex means a prior panic
/// inside the lock-holding code path, so the process is unrecoverable.
/// Silently swallowing it (the old behaviour) leaked a dead id: the
/// sender never got inserted, the later `deliver(id, …)` saw no
/// entry and returned Abandoned, and the caller's `await rx` blocked
/// until the orchestrator's outer timeout. Sister registries
/// (RouteTable, AppDomainTable) already `.expect()` here — settle
/// on the same loud policy.
#[must_use]
pub fn register(&self) -> (Uuid, oneshot::Receiver<InboxResult>) {
let id = Uuid::new_v4();
let (tx, rx) = oneshot::channel();
let mut g = self.inner.lock().expect("inbox registry poisoned");
g.insert(id, tx);
(id, rx)
}
/// Cancel a pending inbox (orchestrator timed out and gave up).
/// Drops the sender so any future `deliver` returns `Abandoned`.
/// Returns `true` if the receiver was still registered.
pub fn cancel(&self, id: Uuid) -> bool {
let mut g = self.inner.lock().expect("inbox registry poisoned");
g.remove(&id).is_some()
}
}
impl Default for InboxRegistry {
fn default() -> Self {
Self::new()
}
}
#[async_trait]
impl InboxResolver for InboxRegistry {
async fn deliver(&self, inbox_id: Uuid, result: InboxResult) -> InboxDeliveryOutcome {
// F-Q-006 + F-Q-010: panic on poison, matching the registry's
// register/cancel policy and the sister registries.
let mut g = self.inner.lock().expect("inbox registry poisoned");
let Some(tx) = g.remove(&inbox_id) else {
return InboxDeliveryOutcome::Abandoned;
};
// `send` returns Err iff the receiver was dropped — exactly
// the abandoned-execution case.
if tx.send(result).is_err() {
InboxDeliveryOutcome::Abandoned
} else {
InboxDeliveryOutcome::Delivered
}
}
}
#[cfg(test)]
mod tests {
use super::*;
use picloud_shared::ExecResponseSummary;
use std::collections::BTreeMap;
fn ok_result() -> InboxResult {
InboxResult::Success(ExecResponseSummary {
status_code: 200,
headers: BTreeMap::new(),
body: serde_json::json!({ "ok": true }),
})
}
#[tokio::test]
async fn register_then_deliver_resolves_receiver() {
let reg = InboxRegistry::new();
let (id, rx) = reg.register();
let outcome = reg.deliver(id, ok_result()).await;
assert_eq!(outcome, InboxDeliveryOutcome::Delivered);
let received = rx.await.expect("receiver should fire");
assert!(matches!(received, InboxResult::Success(_)));
}
#[tokio::test]
async fn deliver_to_unknown_id_is_abandoned() {
let reg = InboxRegistry::new();
let outcome = reg.deliver(Uuid::new_v4(), ok_result()).await;
assert_eq!(outcome, InboxDeliveryOutcome::Abandoned);
}
#[tokio::test]
async fn dropping_receiver_then_delivering_is_abandoned() {
let reg = InboxRegistry::new();
let (id, rx) = reg.register();
drop(rx);
let outcome = reg.deliver(id, ok_result()).await;
assert_eq!(outcome, InboxDeliveryOutcome::Abandoned);
}
#[tokio::test]
async fn cancel_removes_sender() {
let reg = InboxRegistry::new();
let (id, _rx) = reg.register();
assert!(reg.cancel(id));
let outcome = reg.deliver(id, ok_result()).await;
assert_eq!(outcome, InboxDeliveryOutcome::Abandoned);
}
}