vinzenz/hyperhive
vinzenz/hyperhive
Watch
0
0
Fork
You've already forked hyperhive
 0
Code Activity

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

Browse source 
`/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
Download patch file Download diff file Expand all files Collapse all files

13
hive-agent/src/main.rs
View file

@ -662,6 +662,9 @@ async fn serve_loop<S: Surface>(
// The durable agent session, built once and reused for every turn +
// idle compaction below (it's effectively stateless).
let session = turn::make_session(&bus)?;
if let Some(canceller) = hive_runtime::Runtime::canceller(&session) {
bus.set_turn_canceller(canceller);
}
// Tracks the last observed pause state so the transitions get logged
// once each instead of twelve lines a minute while parked.
let mut was_paused = false;
@ -1040,9 +1043,13 @@ async fn handle_turn_error_recovery<S: Surface>(
S::requeue_inflight(socket).await;
bus.emit_status("online");
}
if matches!(outcome, Err(turn::TurnError::ApiStall)) {
// Idle watchdog killed claude on a suspected API stall. Park briefly to
// let the API recover, then requeue — same shape as the rate-limit path.
if matches!(
outcome,
Err(turn::TurnError::ApiStall | turn::TurnError::AgentStall(_))
) {
// Idle watchdog stopped the turn on a suspected API stall. Park briefly
// to let the API recover, then requeue — same shape as the rate-limit
// path.
let secs = turn::stall_sleep_secs();
bus.emit_status("api_stall");
bus.emit(LiveEvent::Note {