crashlabs/huskies
0
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 37 Wiki Activity

Converted all external tool calling to async

Browse Source
This commit is contained in:
Timmy
2026-06-29 16:59:54 +01:00
parent 75f41088b1
commit feb35ddd10
49 changed files with 482 additions and 496 deletions
Download Patch File Download Diff File Expand all files Collapse all files
server/src/agents/pool/auto_assign/watchdog/mod.rs
+19 -17
View File
@@ -25,8 +25,8 @@ pub(crate) use limits::{count_turns_in_log, resolve_session_log};
impl AgentPool {
/// Run a single watchdog pass synchronously (test helper).
#[cfg(test)]
pub fn run_watchdog_once(&self) {
check_orphaned_agents(&self.agents);
pub async fn run_watchdog_once(&self) {
check_orphaned_agents(&self.agents).await;
}
/// Run one watchdog pass: detect orphans, enforce limits, kill offenders.
@@ -39,21 +39,22 @@ impl AgentPool {
/// `retry_count` is incremented and the story stays in `2_current/` for
/// re-attempt. This prevents the original kill-respawn loop (bug 646)
/// while restoring the `max_retries` semantic for turn/budget overruns.
pub fn run_watchdog_pass(&self, project_root: Option<&Path>) -> usize {
let orphaned = check_orphaned_agents(&self.agents);
pub async fn run_watchdog_pass(&self, project_root: Option<&Path>) -> usize {
let orphaned = check_orphaned_agents(&self.agents).await;
if let Some(root) = project_root {
let terminated = check_agent_limits(&self.agents, root);
let terminated = check_agent_limits(&self.agents, root).await;
let config = ProjectConfig::load(root).unwrap_or_default();
for (key, reason) in &terminated {
// Step 1: snapshot the agent's worktree path so we can find every
// process running in it (claude + any subprocesses). This must
// happen BEFORE we mutate the agent record so we can read the
// worktree info safely.
let worktree_path = self.agents.lock().ok().and_then(|lock| {
let worktree_path = {
let lock = self.agents.lock().await;
lock.get(key)
.and_then(|a| a.worktree_info.as_ref().map(|wt| wt.path.clone()))
});
};
// Step 2: SIGKILL every process running in the worktree and
// BLOCK until verified gone. The previous mechanism — portable_pty's
@@ -85,23 +86,24 @@ impl AgentPool {
"[watchdog] No worktree path recorded for '{key}'; cannot tree-kill, \
falling back to portable_pty SIGHUP (likely no-op for claude-code)."
);
self.kill_child_for_key(key);
self.kill_child_for_key(key).await;
}
// Step 3: NOW update the agent record. The process is verified
// gone (or we logged that SIGKILL didn't take effect, which is
// exceptional), so flipping status away from Running can no
// longer open a window for a concurrent spawn.
if let Ok(mut lock) = self.agents.lock()
&& let Some(agent) = lock.get_mut(key)
{
agent.status = AgentStatus::Failed;
agent.termination_reason = Some(reason.clone());
if let Some(handle) = agent.task_handle.take() {
// Best-effort abort of the outer tokio task. The PTY
// blocking thread already returned (claude is dead),
// so this is bookkeeping rather than load-bearing.
handle.abort();
let mut lock = self.agents.lock().await;
if let Some(agent) = lock.get_mut(key) {
agent.status = AgentStatus::Failed;
agent.termination_reason = Some(reason.clone());
if let Some(handle) = agent.task_handle.take() {
// Best-effort abort of the outer tokio task. The PTY
// blocking thread already returned (claude is dead),
// so this is bookkeeping rather than load-bearing.
handle.abort();
}
}
}