Increase default stall watchdog timeout from 10 minutes to 30 minutes

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Bryan Helmkamp 2026-03-08 09:52:07 -04:00
parent 3dce68d664
commit 59634a3936
5 changed files with 7 additions and 7 deletions

View file

@ -421,7 +421,7 @@ impl Graph {
.map_or(3, |v| v as usize)
}
/// Graph-level `stall_timeout`. Defaults to 600s. Returns `None` when set to zero (disabled).
/// Graph-level `stall_timeout`. Defaults to 1800s. Returns `None` when set to zero (disabled).
pub fn stall_timeout(&self) -> Option<Duration> {
match self
.attrs
@ -430,7 +430,7 @@ impl Graph {
{
Some(d) if d.is_zero() => None,
Some(d) => Some(d),
None => Some(Duration::from_secs(600)),
None => Some(Duration::from_secs(1800)),
}
}
@ -732,7 +732,7 @@ mod tests {
#[test]
fn graph_stall_timeout_default() {
let g = Graph::new("empty");
assert_eq!(g.stall_timeout(), Some(Duration::from_secs(600)));
assert_eq!(g.stall_timeout(), Some(Duration::from_secs(1800)));
}
#[test]

View file

@ -12406,7 +12406,7 @@ impl Handler for SlowTestHandler {
#[tokio::test]
async fn e2e_stall_watchdog_with_explicit_timeout_override() {
// A short stall_timeout of 50ms should trigger faster than the default 600s.
// A short stall_timeout of 50ms should trigger faster than the default 1800s.
// This tests that the graph attribute is actually respected.
let dot = r#"digraph StallOverrideTest {
graph [goal="Test stall override", stall_timeout="50ms", default_max_retry=0]

View file

@ -252,7 +252,7 @@ Arc runs a background watchdog that monitors event activity. If no events are em
| Setting | Default |
|---|---|
| `stall_timeout` | 600 seconds (10 minutes) |
| `stall_timeout` | 1800 seconds (30 minutes) |
| Set to `0` | Disables the watchdog |
```dot title="example.dot"

View file

@ -183,7 +183,7 @@ See [Private repositories](#private-repositories) above. You need a GitHub App c
### Stall watchdog kills the run
Long-running commands in Daytona sandboxes may trigger the 600-second stall watchdog if they don't produce events. For workflows with long-running operations, increase the `stall_timeout` in the workflow graph:
Long-running commands in Daytona sandboxes may trigger the 1800-second stall watchdog if they don't produce events. For workflows with long-running operations, increase the `stall_timeout` in the workflow graph:
```dot
digraph Example {

View file

@ -82,7 +82,7 @@ rankdir=LR
| `default_fidelity` | String | Default [fidelity level](/execution/context) for all nodes |
| `default_thread` | String | Default thread ID for all nodes |
| `max_node_visits` | Integer | Max visits per node across the run (0 = unlimited) |
| `stall_timeout` | Duration | Timeout for stalled workflows (default: `600s`, 0 = disabled) |
| `stall_timeout` | Duration | Timeout for stalled workflows (default: `1800s`, 0 = disabled) |
### Node defaults