Watch
0
0
Fork
You've already forked hyperhive
0

hive-agent: dashboard Cancel and idle stalls for ACP agents

`/api/cancel` stopped a turn only by SIGINTing a child process whose argv0 is
`claude`, so on an ACP agent it reported "no claude process to interrupt"
and the turn ran on. The serve loop now stores the session's canceller on
the `Bus` when the runtime has one, and `/api/cancel` uses it: the agent is
sent `session/cancel`, and the next wake prompt carries the interrupted hint,
as for a signalled claude turn. Without a canceller (claude), the SIGINT path
is untouched.

An ACP turn stopped by the idle watchdog (`HIVE_TURN_IDLE_SECS`) becomes
`TurnError::AgentStall(note)`, handled like `ApiStall`: park for
`HIVE_STALL_SLEEP_SECS`, requeue, and record `api_stall`. The TurnEnd note
is the runtime's message (how long the agent was silent, whether it had to
be killed, and that a silently retried provider error such as HTTP 429
looks like this), not the claude-specific `ApiStall` text. A cancel the
agent ignores is a `Failed` turn.

Refs #4391
This commit is contained in:
atlas 2026-09-29 23:22:59 +02:00
commit 91e47732a6
7 changed files with 115 additions and 9 deletions

View file

@ -195,6 +195,12 @@ pub enum TurnError {
/// The serve loop parks for `stall_sleep_secs()` and requeues, like the
/// rate-limit path — NOT a crash.
ApiStall,
/// The ACP backend's idle watchdog stopped a turn that sent nothing for
/// `turn_idle_secs()`: the agent was sent `session/cancel`, and killed if
/// it ignored that. Carries what happened. An ACP agent retrying a failing
/// provider (e.g. HTTP 429) without reporting it ends up here. Handled
/// like [`Self::ApiStall`].
AgentStall(String),
/// A hard failure with no recovery — the serve loop escalates it to the
/// operator (`send_to_operator`).
Failed(anyhow::Error),
@ -565,6 +571,13 @@ pub fn emit_turn_end(bus: &Bus, outcome: &TurnOutcome) {
});
tracing::warn!("turn killed: API stall (idle watchdog)");
}
Err(TurnError::AgentStall(note)) => {
bus.emit(LiveEvent::TurnEnd {
ok: false,
note: Some(format!("{note} — parking + requeueing")),
});
tracing::warn!(note = %note, "ACP turn stopped by the idle watchdog");
}
Err(TurnError::Failed(e)) => {
let note = format!("{e:#}");
bus.emit(LiveEvent::TurnEnd {
@ -694,10 +707,15 @@ fn error_to_turn(err: hive_claude::Error) -> TurnOutcome {
}
/// [`error_to_turn`] for a runtime error: the claude backend's errors map as
/// above, every other runtime's as `Failed`.
/// above, the ACP idle watchdog's as `AgentStall`, everything else as
/// `Failed`.
fn runtime_error_to_turn(err: hive_runtime::Error) -> TurnOutcome {
use hive_runtime::{AcpError, Error};
match err {
hive_runtime::Error::Claude(err) => error_to_turn(err),
Error::Claude(err) => error_to_turn(err),
Error::Acp(err @ (AcpError::IdleTimeout { .. } | AcpError::IdleKilled { .. })) => {
Err(TurnError::AgentStall(err.to_string()))
}
other => Err(TurnError::Failed(other.into())),
}
}
@ -809,7 +827,10 @@ fn archive_session(bus: &Bus, session: &AgentSession) {
#[cfg(test)]
mod tests {
use super::{PermissionAsk, acp_permits, nonzero_or, parse_u64};
use super::{
PermissionAsk, TurnError, acp_permits, nonzero_or, parse_u64, runtime_error_to_turn,
};
use hive_runtime::{AcpError, Error};
#[test]
fn an_absent_or_blank_value_is_not_a_number() {
@ -909,4 +930,40 @@ mod tests {
assert!(acp_permits(&ask("fetch"), true));
assert!(!acp_permits(&ask("fetch"), false));
}
#[test]
fn a_stalled_acp_turn_parks_and_requeues_with_what_happened() {
for err in [
AcpError::IdleTimeout { silent_secs: 600 },
AcpError::IdleKilled {
silent_secs: 600,
grace_secs: 10,
},
] {
let expected = err.to_string();
match runtime_error_to_turn(Error::Acp(err)) {
Err(TurnError::AgentStall(note)) => assert_eq!(note, expected),
other => panic!("{expected}: {other:?}"),
}
}
}
#[test]
fn a_rate_limited_acp_turn_says_so_when_it_stalls() {
let Err(TurnError::AgentStall(note)) =
runtime_error_to_turn(Error::Acp(AcpError::IdleTimeout { silent_secs: 600 }))
else {
panic!("not a stall");
};
assert!(note.contains("600s"), "{note}");
assert!(note.contains("HTTP 429"), "{note}");
}
#[test]
fn a_cancel_the_agent_ignored_is_a_failure() {
assert!(matches!(
runtime_error_to_turn(Error::Acp(AcpError::CancelIgnored { grace_secs: 10 })),
Err(TurnError::Failed(_))
));
}
}