From 37df57748e8e399ba1237fd7df1d1c999795a3c1 Mon Sep 17 00:00:00 2001
From: Ahmed Allam <ahmed39652003@gmail.com>
Date: Fri, 4 Sep 2026 17:08:15 +0000
Subject: [PATCH] fix(web_search): case-fold only scheme and host when matching
 fetched URLs

---
 strix/tools/web_search/tool.py |  7 ++++++-
 tests/test_web_search.py       | 12 ++++++++++++
 2 files changed, 18 insertions(+), 1 deletion(-)

diff --git a/strix/tools/web_search/tool.py b/strix/tools/web_search/tool.py
index aabaad40..9f1c4910 100644
--- a/strix/tools/web_search/tool.py
+++ b/strix/tools/web_search/tool.py
@@ -6,6 +6,7 @@ import asyncio
 import json
 import logging
 from typing import TYPE_CHECKING, Any, cast
+from urllib.parse import urlsplit, urlunsplit
 
 import requests
 from agents import RunContextWrapper, function_tool
@@ -133,7 +134,11 @@ def _exa_content(api_key: str, query: str, search_type: str, num_results: int) -
 
 
 def _normalize_url(url: str) -> str:
-    return url.strip().rstrip("/").lower()
+    """Canonical form for matching: case-fold scheme and host only, drop a trailing slash."""
+    parts = urlsplit(url.strip())
+    return urlunsplit(
+        (parts.scheme.lower(), parts.netloc.lower(), parts.path.rstrip("/"), parts.query, "")
+    )
 
 
 def _exa_page_text(api_key: str, urls: list[str]) -> tuple[str, set[str]]:
diff --git a/tests/test_web_search.py b/tests/test_web_search.py
index 49f4c418..7ec066b9 100644
--- a/tests/test_web_search.py
+++ b/tests/test_web_search.py
@@ -343,6 +343,18 @@ def test_do_get_contents_reports_urls_exa_did_not_return(
     assert "blocked.example" not in result["content"]
 
 
+def test_normalize_url_folds_only_scheme_and_host() -> None:
+    assert tool._normalize_url("HTTPS://Ex.Example/Path/") == tool._normalize_url(
+        "https://ex.example/Path"
+    )
+    assert tool._normalize_url("https://ex.example/Path") != tool._normalize_url(
+        "https://ex.example/path"
+    )
+    assert tool._normalize_url("https://ex.example/p?Q=A") != tool._normalize_url(
+        "https://ex.example/p?q=a"
+    )
+
+
 def test_do_get_contents_omits_the_warning_when_every_page_returns(
     monkeypatch: pytest.MonkeyPatch,
 ) -> None: