From 2aadb27ff322941f9029521f6e1f0e6ff5c0e0c5 Mon Sep 17 00:00:00 2001
From: Scott Severance <scott@scottseverance.net>
Date: Sat, 8 Aug 2026 16:17:23 +0000
Subject: [PATCH] feat(web): add timeout and error handling for socket timeouts

---
 agent/tools/web.py | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/agent/tools/web.py b/agent/tools/web.py
index 6213429..0b48325 100644
--- a/agent/tools/web.py
+++ b/agent/tools/web.py
@@ -1,6 +1,7 @@
 """Web tools: search and fetch for online operations."""
 
 import json
+import socket
 import urllib.request
 import urllib.parse
 import urllib.error
@@ -70,6 +71,8 @@ def execute(self, query: str, max_results: int = 5, **kw) -> ToolResult:
                 lines.append("")
 
             return ToolResult(True, "\n".join(lines))
+        except socket.timeout:
+            return ToolResult(False, "", f"Search timeout: server took too long to respond")
         except urllib.error.URLError as e:
             return ToolResult(False, "", f"Search failed (network error): {e}")
         except Exception as e:
@@ -167,6 +170,8 @@ def execute(self, url: str, max_length: int = 10000, **kw) -> ToolResult:
                 text = text[:max_length] + "\n\n... [content truncated]"
 
             return ToolResult(True, f"Content from {url}:\n\n{text}")
+        except socket.timeout:
+            return ToolResult(False, "", f"Fetch timeout: server took too long to respond")
         except urllib.error.HTTPError as e:
             return ToolResult(False, "", f"HTTP {e.code}: {e.reason}")
         except urllib.error.URLError as e:
@@ -180,7 +185,7 @@ def _html_to_text(self, html_content: str) -> str:
         text = re.sub(r"<script[^>]*>.*?</script>", "", html_content, flags=re.DOTALL)
         text = re.sub(r"<style[^>]*>.*?</style>", "", text, flags=re.DOTALL)
         # Convert common tags
-        text = re.sub(r"<br\s*/?>", "\n", text)
+        text = re.sub(r"<br\s*/?>\n", text)
         text = re.sub(r"</(p|div|h[1-6]|li|tr)>", "\n", text)
         text = re.sub(r"<h([1-6])[^>]*>", lambda m: "\n" + "#" * int(m.group(1)) + " ", text)
         text = re.sub(r"<li[^>]*>", "  - ", text)