fix(startup): thread-exhaustion resilience — cap workers, never panic
Port of upstream grok-build 0.2.113/0.2.114 fixes, extended to Kigi's startup order. - kigi-tty-utils runtime module: worker-cap policy (8 max) — tokio's per-core default pins 100+ thread slots on many-core shared hosts against RLIMIT_NPROC / pids.max, and later spawns die with EAGAIN. - kigi-bin builds the main runtime with capped workers and reports an out-of-threads host with a diagnostic + exit(1) instead of a panic. - The pre-runtime optimization threads (HTTP warmup, early model prefetch) spawn recoverably and degrade — their panic would have preempted the runtime's own diagnostic. - The per-session actor thread and its runtime report spawn/build failure through the existing acp::Error / AgentBuildError boundaries (new RuntimeBuild variant) instead of panicking the agent host. - fsnotify's watcher thread spawn maps into FsNotifyError::WatcherStart so callers degrade instead of crashing. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01KSy9S31pZNWXtRZNVJ1sDf
This commit is contained in:
1 parent
bf93091416
commit
97de661554
8 files changed
+144
-17
No files matched your search
@@ -971,7 +971,7 @@ pub(crate) fn start_with_timeout(
|
||||
|
||||
let progress_for_thread = progress.clone();
|
||||
|
||||
let thread = std::thread::spawn(move || {
|
||||
let watcher_loop = move || {
|
||||
let update_stage = |stage: &'static str| {
|
||||
if let Ok(mut p) = progress_for_thread.lock() {
|
||||
p.set_stage(stage);
|
||||
@@ -1351,7 +1351,13 @@ pub(crate) fn start_with_timeout(
|
||||
let _ = ready_tx.send(Err(Box::new(e)));
|
||||
}
|
||||
}
|
||||
});
|
||||
};
|
||||
// Recoverable spawn: a host out of threads must surface as an error the
|
||||
// caller can degrade on, not a `std::thread::spawn` panic.
|
||||
let thread = std::thread::Builder::new()
|
||||
.name("fsnotify-watcher".into())
|
||||
.spawn(watcher_loop)
|
||||
.map_err(|e| crate::FsNotifyError::WatcherStart(Box::new(e)))?;
|
||||
|
||||
// Wait for watcher to be ready (with timeout)
|
||||
if let Ok(mut p) = progress.lock() {
|
||||
|
||||
Reference in new issue
Block a user