Skip to content

Add socket timeout handling to web search and fetch tools #21

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
ssevera1 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Add socket timeout handling to web search and fetch tools #21

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 6 additions & 1 deletion agent/tools/web.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -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
Expand Down Expand Up @@ -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:
Expand Down Expand Up @@ -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:
Expand All @@ -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)
Expand Down
Loading