From 02a3de7c0e941279d86efb94638ccc4157f9c502 Mon Sep 17 00:00:00 2001
From: "Molecule AI Dev Engineer A (Kimi)"
 <dev-engineer-a-kimi@agents.moleculesai.app>
Date: Wed, 27 May 2026 09:45:31 +0000
Subject: [PATCH] fix(workspace-server): replace time.After with time.NewTimer
 to prevent goroutine leaks

Inside loops, time.After creates a new timer goroutine each iteration
that cannot be GC'd until it fires. In long-running loops (supervisor
restart backoff, Telegram polling, restart-context polling, CP stop
retry) this leaks goroutines proportional to iteration count.

Replace with time.NewTimer + timer.Stop() on ctx cancellation so the
timer is cleaned up immediately when the goroutine exits.

Affected files:
- supervised/supervised.go (RunWithRecover backoff)
- channels/telegram.go (429 retry + poll error sleep)
- handlers/restart_context.go (online + heartbeat polling)
- handlers/workspace_restart.go (cpStop retry backoff)

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
---
 workspace-server/internal/channels/telegram.go       | 12 ++++++++----
 .../internal/handlers/restart_context.go             |  8 ++++++--
 .../internal/handlers/workspace_restart.go           |  4 +++-
 workspace-server/internal/supervised/supervised.go   |  4 +++-
 4 files changed, 20 insertions(+), 8 deletions(-)

diff --git a/workspace-server/internal/channels/telegram.go b/workspace-server/internal/channels/telegram.go
index 778afa5c0..3d323057c 100644
--- a/workspace-server/internal/channels/telegram.go
+++ b/workspace-server/internal/channels/telegram.go
@@ -482,12 +482,14 @@ func (t *TelegramAdapter) StartPolling(ctx context.Context, config map[string]in
 				if apiErr.Code == 429 {
 					retryAfter := time.Duration(apiErr.RetryAfter) * time.Second
 					log.Printf("Channels: Telegram poll rate-limited, sleeping %s", retryAfter)
+					timer := time.NewTimer(retryAfter)
 					select {
 					case <-ctx.Done():
+						timer.Stop()
 						return nil
-					case <-time.After(retryAfter):
-						continue
+					case <-timer.C:
 					}
+					continue
 				}
 				if apiErr.Code == 401 {
 					invalidateBot(token)
@@ -495,12 +497,14 @@ func (t *TelegramAdapter) StartPolling(ctx context.Context, config map[string]in
 				}
 			}
 			log.Printf("Channels: Telegram poll error: %v", err)
+			timer := time.NewTimer(telegramPollInterval)
 			select {
 			case <-ctx.Done():
+				timer.Stop()
 				return nil
-			case <-time.After(telegramPollInterval):
-				continue
+			case <-timer.C:
 			}
+			continue
 		}
 
 		for _, update := range updates {
diff --git a/workspace-server/internal/handlers/restart_context.go b/workspace-server/internal/handlers/restart_context.go
index d84141976..d0bfad617 100644
--- a/workspace-server/internal/handlers/restart_context.go
+++ b/workspace-server/internal/handlers/restart_context.go
@@ -177,10 +177,12 @@ func waitForWorkspaceOnline(ctx context.Context, workspaceID string, timeout tim
 		).Scan(&status); err == nil && status == "online" {
 			return true
 		}
+		timer := time.NewTimer(restartContextOnlinePollInterval)
 		select {
 		case <-ctx.Done():
+			timer.Stop()
 			return false
-		case <-time.After(restartContextOnlinePollInterval):
+		case <-timer.C:
 		}
 	}
 	return false
@@ -213,10 +215,12 @@ func waitForFreshHeartbeat(ctx context.Context, workspaceID string, restartStart
 			lastHB.Valid && lastHB.Time.After(restartStartTs) {
 			return true
 		}
+		timer := time.NewTimer(restartContextOnlinePollInterval)
 		select {
 		case <-ctx.Done():
+			timer.Stop()
 			return false
-		case <-time.After(restartContextOnlinePollInterval):
+		case <-timer.C:
 		}
 	}
 	return false
diff --git a/workspace-server/internal/handlers/workspace_restart.go b/workspace-server/internal/handlers/workspace_restart.go
index 5d9122648..8bae4ef61 100644
--- a/workspace-server/internal/handlers/workspace_restart.go
+++ b/workspace-server/internal/handlers/workspace_restart.go
@@ -763,12 +763,14 @@ func (h *WorkspaceHandler) cpStopWithRetryErr(ctx context.Context, workspaceID,
 		}
 		// Sleep with ctx awareness so a cancelled ctx exits early instead
 		// of stalling the goroutine through the remaining backoff.
+		timer := time.NewTimer(delay)
 		select {
 		case <-ctx.Done():
+			timer.Stop()
 			log.Printf("%s: cpProv.Stop(%s) abandoned mid-retry: ctx cancelled (last_err=%v)",
 				source, workspaceID, lastErr)
 			return ctx.Err()
-		case <-time.After(delay):
+		case <-timer.C:
 		}
 		delay *= 2
 	}
diff --git a/workspace-server/internal/supervised/supervised.go b/workspace-server/internal/supervised/supervised.go
index 8de84258f..e9c6a40f3 100644
--- a/workspace-server/internal/supervised/supervised.go
+++ b/workspace-server/internal/supervised/supervised.go
@@ -60,10 +60,12 @@ func RunWithRecover(ctx context.Context, name string, fn func(context.Context))
 		}
 
 		// Panic → back off and restart.
+		timer := time.NewTimer(backoff)
 		select {
 		case <-ctx.Done():
+			timer.Stop()
 			return
-		case <-time.After(backoff):
+		case <-timer.C:
 		}
 		if backoff < maxBackoff {
 			backoff *= 2
-- 
2.52.0