Skip to content

worker: Allow runner to go back to LOADING post-start #3743

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
victorges merged 3 commits into from
Sep 22, 2025
Merged

worker: Allow runner to go back to LOADING post-start #3743

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
2790ce5
worker: Allow runner to go back to LOADING post-start
victorges Sep 19, 2025
3ed0a38
Fix loadingStartTime typing
victorges Sep 19, 2025
78fd117
Update ai/worker/docker.go
victorges Sep 22, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
24 changes: 13 additions & 11 deletions ai/worker/docker.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -570,8 +570,8 @@ func (m *DockerManager) watchContainer(rc *RunnerContainer) {
defer ticker.Stop()

slog.Info("Watching container", slog.String("container", rc.Name))
var loadingStartTime time.Time
failures := 0
loadingStartTime := time.Now()
for {
if failures >= maxHealthCheckFailures {
slog.Error("Container health check failed too many times", slog.String("container", rc.Name))
Expand Down Expand Up @@ -641,17 +641,19 @@ func (m *DockerManager) watchContainer(rc *RunnerContainer) {
}
fallthrough
case OK:
failures = 0
failures, loadingStartTime = 0, time.Time{}
continue
case "LOADING": // TODO: Use enum when ai-runner SDK is updated
if !isBorrowed {
slog.Info("Container is loading, removing from pool", slog.String("container", rc.Name))
failures = 0
loadingStartTime = time.Now()

m.mu.Lock()
m.borrowContainerLocked(context.Background(), rc)
m.mu.Unlock()
case LOADING:
if loadingStartTime.IsZero() {
failures, loadingStartTime = 0, time.Now()

if !isBorrowed {
slog.Info("Container is loading, removing from pool", slog.String("container", rc.Name))

m.mu.Lock()
m.borrowContainerLocked(context.Background(), rc)
m.mu.Unlock()
}
}
if loadingTime := time.Since(loadingStartTime); loadingTime > containerTimeout {
failures++
Expand Down
Loading