a hive-side pause holds against the swarm's declared state until an operator resumes
the harness writes the reason into the pause marker when it pauses itself and reports it as paused_by_hive in its turn-state header. swarm-controller declares such an agent paused (only if declared up) and shows the reason on the agents status row and the swarm ui card.
This commit is contained in:
parent
6470e2b109
commit
e5c55257f8
1 changed files with 517 additions and 26 deletions
|
|
@ -945,6 +945,14 @@ async fn drive_turn_and_wake_chain<S: Surface>(
|
|||
}
|
||||
}
|
||||
|
||||
/// The pause marker's content for an auto-pause after `streak` missed todo
|
||||
/// wakes. A non-empty marker is a pause by the harness itself, which the
|
||||
/// turn-state header reports as `paused_by_hive`; the operator's pause writes
|
||||
/// an empty one.
|
||||
fn todo_miss_pause_reason(streak: u32) -> String {
|
||||
format!("skipped get_loose_ends on {streak} consecutive todo wakes")
|
||||
}
|
||||
|
||||
/// Apply a finished turn's `todo_wake_checked` signal to the miss-streak:
|
||||
/// resets on a checked wake, increments (and auto-pauses at the threshold)
|
||||
/// on a missed one, no-ops for a non-todo-wake turn. Split out of
|
||||
|
|
@ -963,15 +971,19 @@ fn apply_todo_wake_checked(checked: Option<bool>, todo_miss_streak: &mut u32, bu
|
|||
);
|
||||
if streak >= TODO_MISS_PAUSE_THRESHOLD {
|
||||
tracing::warn!("todo-miss streak hit the threshold — pausing the turn loop");
|
||||
// Marker first: the Note triggers a turn-state header rebuild,
|
||||
// which reads the reason back out of this file.
|
||||
if let Err(e) =
|
||||
std::fs::write(paths::paused_marker(), todo_miss_pause_reason(streak))
|
||||
{
|
||||
tracing::warn!(error = ?e, "failed to write pause marker");
|
||||
}
|
||||
bus.emit(LiveEvent::Note {
|
||||
text: format!(
|
||||
"auto-paused: skipped get_loose_ends on {streak} \
|
||||
consecutive todo wakes — an operator needs to resume this agent"
|
||||
),
|
||||
});
|
||||
if let Err(e) = std::fs::write(paths::paused_marker(), "") {
|
||||
tracing::warn!(error = ?e, "failed to write pause marker");
|
||||
}
|
||||
// Fresh slate for whenever this agent gets resumed — see
|
||||
// `serve_loop`'s `was_paused` reset for the mirror side.
|
||||
*todo_miss_streak = 0;
|
||||
|
|
@ -1254,4 +1266,31 @@ mod tests {
|
|||
.await;
|
||||
assert!(matches!(woke, RecvOutcome::Empty));
|
||||
}
|
||||
|
||||
/// The third consecutive miss parks the agent with its reason in the
|
||||
/// marker; an earlier miss, or a wake that did call `get_loose_ends`,
|
||||
/// writes nothing.
|
||||
#[test]
|
||||
fn the_threshold_miss_writes_the_reason_into_the_pause_marker() {
|
||||
crate::paths::with_harness_dir(|| {
|
||||
let bus = crate::events::Bus::new();
|
||||
let mut streak = 0;
|
||||
for _ in 1..super::TODO_MISS_PAUSE_THRESHOLD {
|
||||
super::apply_todo_wake_checked(Some(false), &mut streak, &bus);
|
||||
assert!(
|
||||
!crate::paths::paused_marker().exists(),
|
||||
"below the threshold"
|
||||
);
|
||||
}
|
||||
super::apply_todo_wake_checked(Some(true), &mut streak, &bus);
|
||||
assert_eq!(streak, 0);
|
||||
for _ in 0..super::TODO_MISS_PAUSE_THRESHOLD {
|
||||
super::apply_todo_wake_checked(Some(false), &mut streak, &bus);
|
||||
}
|
||||
assert_eq!(
|
||||
std::fs::read_to_string(crate::paths::paused_marker()).unwrap(),
|
||||
super::todo_miss_pause_reason(super::TODO_MISS_PAUSE_THRESHOLD)
|
||||
);
|
||||
});
|
||||
}
|
||||
}
|
||||
|
|
|
|||
Loading…
Reference in a new issue