Handle MessageTooLarge error in router to prevent node crash

When a message exceeds gossipsub's 1 MiB limit, the resulting
RuntimeError("MessageTooLarge") was unhandled in _networking_publish,
causing the entire TaskGroup to fail and crash the node. Now catch
this error and log it, dropping the oversized message gracefully.

Fixes #1296

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

app/EXO/EXO/ExoProcessController.swift

@@ -126,11 +126,37 @@ final class ExoProcessController: ObservableObject {
             return
         }
         process.terminationHandler = nil
-        if process.isRunning {
-            process.terminate()
-        }
-        self.process = nil
         status = .stopped
+
+        guard process.isRunning else {
+            self.process = nil
+            return
+        }
+
+        let proc = process
+        self.process = nil
+
+        Task.detached {
+            proc.interrupt()
+
+            for _ in 0..<50 {
+                if !proc.isRunning { return }
+                try? await Task.sleep(nanoseconds: 100_000_000)
+            }
+
+            if proc.isRunning {
+                proc.terminate()
+            }
+
+            for _ in 0..<30 {
+                if !proc.isRunning { return }
+                try? await Task.sleep(nanoseconds: 100_000_000)
+            }
+
+            if proc.isRunning {
+                kill(proc.processIdentifier, SIGKILL)
+            }
+        }
     }
 
     func restart() {

pyproject.toml

@@ -132,7 +132,7 @@ markers = [
 env = [
   "EXO_TESTS=1"
 ]
-addopts = "-m 'not slow'"
+addopts = "-m 'not slow' --ignore=tests/start_distributed_test.py"
 filterwarnings = [
     "ignore:builtin type Swig:DeprecationWarning",
 ]

src/exo/download/coordinator.py

@@ -14,6 +14,7 @@ from exo.download.download_utils import (
     map_repo_download_progress_to_download_progress_data,
 )
 from exo.download.shard_downloader import ShardDownloader
+from exo.shared.constants import EXO_MODELS_DIR
 from exo.shared.models.model_cards import ModelId
 from exo.shared.types.commands import (
     CancelDownload,
@@ -63,6 +64,9 @@ class DownloadCoordinator:
         self.event_sender, self.event_receiver = channel[Event]()
         self.shard_downloader.on_progress(self._download_progress_callback)
 
+    def _model_dir(self, model_id: ModelId) -> str:
+        return str(EXO_MODELS_DIR / model_id.normalize())
+
     async def _download_progress_callback(
         self, callback_shard: ShardMetadata, progress: RepoDownloadProgress
     ) -> None:
@@ -74,6 +78,7 @@ class DownloadCoordinator:
                 shard_metadata=callback_shard,
                 node_id=self.node_id,
                 total_bytes=progress.total_bytes,
+                model_directory=self._model_dir(model_id),
             )
             self.download_status[model_id] = completed
             await self.event_sender.send(
@@ -93,6 +98,7 @@ class DownloadCoordinator:
                 download_progress=map_repo_download_progress_to_download_progress_data(
                     progress
                 ),
+                model_directory=self._model_dir(model_id),
             )
             self.download_status[model_id] = ongoing
             await self.event_sender.send(
@@ -170,7 +176,11 @@ class DownloadCoordinator:
                 return
 
         # Emit pending status
-        progress = DownloadPending(shard_metadata=shard, node_id=self.node_id)
+        progress = DownloadPending(
+            shard_metadata=shard,
+            node_id=self.node_id,
+            model_directory=self._model_dir(model_id),
+        )
         self.download_status[model_id] = progress
         await self.event_sender.send(NodeDownloadProgress(download_progress=progress))
 
@@ -184,6 +194,7 @@ class DownloadCoordinator:
                 shard_metadata=shard,
                 node_id=self.node_id,
                 total_bytes=initial_progress.total_bytes,
+                model_directory=self._model_dir(model_id),
             )
             self.download_status[model_id] = completed
             await self.event_sender.send(
@@ -206,6 +217,7 @@ class DownloadCoordinator:
             download_progress=map_repo_download_progress_to_download_progress_data(
                 initial_progress
             ),
+            model_directory=self._model_dir(model_id),
         )
         self.download_status[model_id] = status
         self.event_sender.send_nowait(NodeDownloadProgress(download_progress=status))
@@ -219,6 +231,7 @@ class DownloadCoordinator:
                     shard_metadata=shard,
                     node_id=self.node_id,
                     error_message=str(e),
+                    model_directory=self._model_dir(model_id),
                 )
                 self.download_status[model_id] = failed
                 await self.event_sender.send(
@@ -253,6 +266,7 @@ class DownloadCoordinator:
             pending = DownloadPending(
                 shard_metadata=current_status.shard_metadata,
                 node_id=self.node_id,
+                model_directory=self._model_dir(model_id),
             )
             await self.event_sender.send(
                 NodeDownloadProgress(download_progress=pending)
@@ -295,11 +309,18 @@ class DownloadCoordinator:
                             node_id=self.node_id,
                             shard_metadata=progress.shard,
                             total_bytes=progress.total_bytes,
+                            model_directory=self._model_dir(
+                                progress.shard.model_card.model_id
+                            ),
                         )
                     elif progress.status in ["in_progress", "not_started"]:
                         if progress.downloaded_bytes_this_session.in_bytes == 0:
                             status = DownloadPending(
-                                node_id=self.node_id, shard_metadata=progress.shard
+                                node_id=self.node_id,
+                                shard_metadata=progress.shard,
+                                model_directory=self._model_dir(
+                                    progress.shard.model_card.model_id
+                                ),
                             )
                         else:
                             status = DownloadOngoing(
@@ -308,6 +329,9 @@ class DownloadCoordinator:
                                 download_progress=map_repo_download_progress_to_download_progress_data(
                                     progress
                                 ),
+                                model_directory=self._model_dir(
+                                    progress.shard.model_card.model_id
+                                ),
                             )
                     else:
                         continue

src/exo/main.py

@@ -136,6 +136,8 @@ class Node:
 
     async def run(self):
         async with self._tg as tg:
+            signal.signal(signal.SIGINT, lambda _, __: self.shutdown())
+            signal.signal(signal.SIGTERM, lambda _, __: self.shutdown())
             tg.start_soon(self.router.run)
             tg.start_soon(self.election.run)
             if self.download_coordinator:
@@ -147,8 +149,6 @@ class Node:
             if self.api:
                 tg.start_soon(self.api.run)
             tg.start_soon(self._elect_loop)
-            signal.signal(signal.SIGINT, lambda _, __: self.shutdown())
-            signal.signal(signal.SIGTERM, lambda _, __: self.shutdown())
 
     def shutdown(self):
         # if this is our second call to shutdown, just sys.exit

src/exo/routing/router.py

@@ -211,6 +211,14 @@ class Router:
                     pass
                 except AllQueuesFullError:
                     logger.warning(f"All peer queues full, dropping message on {topic}")
+                except RuntimeError as e:
+                    if "MessageTooLarge" in str(e):
+                        logger.error(
+                            f"Message too large for gossipsub on topic {topic} "
+                            f"({len(data)} bytes), dropping message"
+                        )
+                    else:
+                        raise
 
 
 def get_node_id_keypair(

src/exo/shared/apply.py

@@ -218,11 +218,6 @@ def apply_node_timed_out(event: NodeTimedOut, state: State) -> State:
         key: value for key, value in state.downloads.items() if key != event.node_id
     }
     # Clean up all granular node mappings
-    node_identities = {
-        key: value
-        for key, value in state.node_identities.items()
-        if key != event.node_id
-    }
     node_memory = {
         key: value for key, value in state.node_memory.items() if key != event.node_id
     }
@@ -263,7 +258,6 @@ def apply_node_timed_out(event: NodeTimedOut, state: State) -> State:
             "downloads": downloads,
             "topology": topology,
             "last_seen": last_seen,
-            "node_identities": node_identities,
             "node_memory": node_memory,
             "node_disk": node_disk,
             "node_system": node_system,

src/exo/shared/types/worker/downloads.py

@@ -26,6 +26,7 @@ class DownloadProgressData(CamelCaseModel):
 class BaseDownloadProgress(TaggedModel):
     node_id: NodeId
     shard_metadata: ShardMetadata
+    model_directory: str = ""
 
 
 class DownloadPending(BaseDownloadProgress):