diff --git a/backend/open_webui/socket/main.py b/backend/open_webui/socket/main.py
index 7a585830a9..7229601f53 100644
--- a/backend/open_webui/socket/main.py
+++ b/backend/open_webui/socket/main.py
@@ -185,12 +185,19 @@ RESUME_STREAM_TTL_REFRESH_EVERY = 64
 # Replay read timeout: looser since a resume is user-blocking anyway
 # and silent timeout here is worse than a brief extra wait. Both
 # configurable for infra where Redis isn't colocated.
-RESUME_STREAM_REDIS_TIMEOUT_SEC = float(
-    os.environ.get('RESUME_STREAM_REDIS_TIMEOUT_SEC', '0.1')
-)
-RESUME_STREAM_READ_TIMEOUT_SEC = float(
-    os.environ.get('RESUME_STREAM_READ_TIMEOUT_SEC', '1.0')
-)
+def _float_env(name: str, default: float) -> float:
+    val = os.environ.get(name)
+    if val is None or val == '':
+        return default
+    try:
+        return float(val)
+    except (TypeError, ValueError):
+        log.warning(f'Invalid {name}={val!r}; using default {default}')
+        return default
+
+
+RESUME_STREAM_REDIS_TIMEOUT_SEC = _float_env('RESUME_STREAM_REDIS_TIMEOUT_SEC', 0.1)
+RESUME_STREAM_READ_TIMEOUT_SEC = _float_env('RESUME_STREAM_READ_TIMEOUT_SEC', 1.0)
 
 # Module-level circuit breaker for the streaming hot path. After N
 # consecutive Redis failures/timeouts, short-circuit seq/log calls for
diff --git a/src/lib/components/chat/Chat.svelte b/src/lib/components/chat/Chat.svelte
index 0e9a331646..e2ef682f50 100644
--- a/src/lib/components/chat/Chat.svelte
+++ b/src/lib/components/chat/Chat.svelte
@@ -1544,6 +1544,15 @@
 					taskIds = taskRes.task_ids;
 				}
 
+				// Request resume BEFORE marking messages done. The
+				// interrupted-generation heuristic below flips `done=true`
+				// when getTaskIdsByChatId returns empty/null, which can
+				// happen on API failure too; asking for resume first lets
+				// us recover when the stream is actually still alive.
+				// Server replies empty if no log exists, so a spurious
+				// request costs one round trip.
+				requestResumeForAllInProgress();
+
 				// If no active tasks and current message is incomplete, generation was interrupted
 				const currentMessage = history.currentId ? history.messages[history.currentId] : null;
 				if (
@@ -1555,13 +1564,6 @@
 					currentMessage.done = true;
 				}
 
-				// Resume any in-flight streams. Not gated on taskIds —
-				// that call can fail or race and is not authoritative;
-				// requestResumeForAllInProgress already filters to
-				// unfinished assistants and the server no-ops when no
-				// log exists.
-				requestResumeForAllInProgress();
-
 				await tick();
 
 				return true;