add ack_until: bulk-ack inbox messages by id + surface msg ids in wake prompts and recv (closes #2125)

This commit is contained in:
damocles 2026-07-02 11:45:12 +02:00 committed by mara
commit 34374fd10a
8 changed files with 221 additions and 16 deletions

View file

@ -751,6 +751,38 @@ impl Broker {
Ok(u64::try_from(n).unwrap_or(0))
}
/// Bulk-ack every message addressed to `recipient` with row id
/// `<= up_to` that isn't acked yet — pending AND delivered rows
/// alike. The agent-facing triage tool behind `AckUntil`: after a
/// redelivered flood the agent acks everything up to the highest id
/// it has seen instead of re-popping each row. Recipient-scoped by
/// the WHERE clause, so an agent can never touch another agent's
/// rows. Also drains the in-memory `unacked_ids` / `requeued_ids`
/// bookkeeping below the cutoff so a later `ack_turn` doesn't
/// re-update rows this call already closed and a stale redelivery
/// tag doesn't outlive its row. Returns the number of rows newly
/// acked.
///
/// # Errors
///
/// Propagates sqlite errors from the `UPDATE`.
pub fn ack_until(&self, recipient: &str, up_to: i64) -> Result<u64> {
// Same lock order as `recv` / `ack_turn` / `requeue_inflight`:
// `inflight` FIRST, then `conn`.
let mut inflight = self.inflight.lock().unwrap();
if let Some(state) = inflight.get_mut(recipient) {
state.unacked_ids.retain(|&id| id > up_to);
state.requeued_ids.retain(|&id| id > up_to);
}
let conn = self.conn.lock().unwrap();
let n = conn.execute(
"UPDATE messages SET acked_at = ?1
WHERE recipient = ?2 AND id <= ?3 AND acked_at IS NULL",
params![now_unix(), recipient, up_to],
)?;
Ok(u64::try_from(n).unwrap_or(0))
}
/// Resurface every message the broker previously handed to this
/// recipient that never got `acked_at` set. Used by the harness at
/// boot to recover from the crashed-mid-turn / OOM-killed /
@ -1304,6 +1336,61 @@ mod tests {
assert!(pop_one(broker, "b").is_none());
}
/// Bulk triage: three queued messages, agent acks up to the second
/// id — the first two never deliver again, the third still pops.
#[test]
fn ack_until_acks_only_rows_at_or_below_cutoff() {
let h = open_broker();
let broker = &h.broker;
broker.send(&msg("a", "b", "one")).unwrap();
broker.send(&msg("a", "b", "two")).unwrap();
broker.send(&msg("a", "b", "three")).unwrap();
// Pop the first two so we know their ids (FIFO).
let d1 = pop_one(broker, "b").expect("popped one");
let d2 = pop_one(broker, "b").expect("popped two");
assert_eq!(broker.ack_until("b", d2.id).unwrap(), 2);
// The cutoff also drained the in-memory unacked list, so a
// turn-level ack right after finds nothing left to do.
assert_eq!(broker.ack_turn("b").unwrap(), 0);
// A restart-style requeue finds nothing below the cutoff …
assert_eq!(broker.requeue_inflight("b").unwrap(), 0);
// … and the third message (id above the cutoff) still pops.
let d3 = pop_one(broker, "b").expect("third still pending");
assert_eq!(d3.message.body, "three");
assert!(d1.id < d2.id && d2.id < d3.id);
}
/// Pending (never-delivered) rows below the cutoff are acked too —
/// that's the whole point for a stale backlog the agent never
/// popped individually.
#[test]
fn ack_until_covers_pending_rows() {
let h = open_broker();
let broker = &h.broker;
broker.send(&msg("a", "b", "stale-1")).unwrap();
broker.send(&msg("a", "b", "stale-2")).unwrap();
// Learn the highest id by peeking via recent_for (non-mutating).
let rows = broker.recent_for("b", 10).unwrap();
let max_id = rows.iter().map(|r| r.id).max().expect("rows");
assert_eq!(broker.ack_until("b", max_id).unwrap(), 2);
assert!(pop_one(broker, "b").is_none(), "backlog cleared");
}
/// Recipient scoping: acking b's inbox never touches c's rows,
/// even when c's ids fall below the cutoff.
#[test]
fn ack_until_is_recipient_scoped() {
let h = open_broker();
let broker = &h.broker;
broker.send(&msg("a", "c", "for-c")).unwrap();
broker.send(&msg("a", "b", "for-b")).unwrap();
let rows = broker.recent_for("b", 10).unwrap();
let max_id = rows.iter().map(|r| r.id).max().expect("rows");
assert_eq!(broker.ack_until("b", max_id).unwrap(), 1);
let d = pop_one(broker, "c").expect("c's message untouched");
assert_eq!(d.message.body, "for-c");
}
/// Crash-recovery: send → recv → (no ack) → `requeue_inflight`
/// resets `delivered_at` + tags the next pop as redelivered. After
/// that `ack_turn` closes it out cleanly.

View file

@ -237,6 +237,7 @@ pub(crate) async fn dispatch_shared(
}
hive_sh4re::Request::CreateRepo { repo } => handle_create_repo(agent, repo).await,
hive_sh4re::Request::AckTurn => handle_ack_turn(coord, agent),
hive_sh4re::Request::AckUntil { up_to } => handle_ack_until(coord, agent, *up_to),
hive_sh4re::Request::RequeueInflight => handle_requeue_inflight(coord, agent),
hive_sh4re::Request::GracefulStopComplete => {
// Harness drained + is exiting: clear the fence so the
@ -483,6 +484,17 @@ fn handle_ack_turn(coord: &Arc<Coordinator>, agent: &str) -> hive_sh4re::Respons
}
}
/// `AckUntil` — bulk-ack every message addressed to `agent` with row
/// id `<= up_to` (the agent-side backlog-triage escape hatch).
fn handle_ack_until(coord: &Arc<Coordinator>, agent: &str, up_to: i64) -> hive_sh4re::Response {
match coord.broker.ack_until(agent, up_to) {
Ok(count) => hive_sh4re::Response::Acked { count },
Err(e) => hive_sh4re::Response::Err {
message: format!("{e:#}"),
},
}
}
/// `RequeueInflight` — resurface `agent`'s unacked in-flight messages
/// (crash recovery on harness boot).
fn handle_requeue_inflight(coord: &Arc<Coordinator>, agent: &str) -> hive_sh4re::Response {