From c8da0ab6c41ca756e5c1d67da6c1db3e02bedb68 Mon Sep 17 00:00:00 2001
From: Alex Blank <alexblank@fastmail.com>
Date: Sun, 24 May 2026 18:33:25 +0000
Subject: [PATCH] fix: retry start/restart on network errors

When Docker starts a container, it creates network interfaces which
triggers Chrome's ERR_NETWORK_CHANGED error, aborting the request.
The backend successfully starts the container but the frontend never
gets the response, showing 'failed to create session' even though
the session is up.

Fix: Add retry with exponential backoff for startInstance and
restartInstance when network errors occur (no HTTP response).
Retries up to 2 times with 1.5s delay between attempts.

Fixes: False 'failed to create session' errors when launching tools.
---
 apps/web/src/api/sessions.ts | 44 ++++++++++++++++++++++++++----------
 1 file changed, 32 insertions(+), 12 deletions(-)

diff --git a/apps/web/src/api/sessions.ts b/apps/web/src/api/sessions.ts
index 6fe0ae4..90bd206 100644
--- a/apps/web/src/api/sessions.ts
+++ b/apps/web/src/api/sessions.ts
@@ -71,13 +71,23 @@ export async function startInstance(
   projectId: string,
   repoId: string,
   instanceId: string,
-  configProfileId?: string
+  configProfileId?: string,
+  retries = 2
 ): Promise<{ status: string; url?: string }> {
-  const response = await apiClient.post(
-    `/projects/${projectId}/repositories/${repoId}/instances/${instanceId}/start`,
-    { config_profile_id: configProfileId }
-  );
-  return response.data;
+  try {
+    const response = await apiClient.post(
+      `/projects/${projectId}/repositories/${repoId}/instances/${instanceId}/start`,
+      { config_profile_id: configProfileId }
+    );
+    return response.data;
+  } catch (error: any) {
+    // Retry on network errors (e.g. Docker creating network interfaces)
+    if (retries > 0 && !error.response) {
+      await new Promise((r) => setTimeout(r, 1500));
+      return startInstance(projectId, repoId, instanceId, configProfileId, retries - 1);
+    }
+    throw error;
+  }
 }
 
 export async function stopInstance(
@@ -95,13 +105,23 @@ export async function restartInstance(
   projectId: string,
   repoId: string,
   instanceId: string,
-  configProfileId?: string
+  configProfileId?: string,
+  retries = 2
 ): Promise<{ status: string; url?: string }> {
-  const response = await apiClient.post(
-    `/projects/${projectId}/repositories/${repoId}/instances/${instanceId}/restart`,
-    { config_profile_id: configProfileId }
-  );
-  return response.data;
+  try {
+    const response = await apiClient.post(
+      `/projects/${projectId}/repositories/${repoId}/instances/${instanceId}/restart`,
+      { config_profile_id: configProfileId }
+    );
+    return response.data;
+  } catch (error: any) {
+    // Retry on network errors (e.g. Docker creating network interfaces)
+    if (retries > 0 && !error.response) {
+      await new Promise((r) => setTimeout(r, 1500));
+      return restartInstance(projectId, repoId, instanceId, configProfileId, retries - 1);
+    }
+    throw error;
+  }
 }
 
 export async function deleteInstance(