From 88124450b433bd0ca63be310c26d8db5f8bb93d1 Mon Sep 17 00:00:00 2001
From: "google-labs-jules[bot]"
 <161369871+google-labs-jules[bot]@users.noreply.github.com>
Date: Fri, 7 Aug 2026 11:01:40 +0000
Subject: [PATCH] perf(resolver): short-circuit quality score checks

Co-authored-by: d-oit <6849456+d-oit@users.noreply.github.com>
---
 .../do-web-doc-resolver/scripts/quality.py       | 16 ++++++++++++----
 scripts/quality.py                               | 16 ++++++++++++----
 tests/test_content_clean.py                      |  2 +-
 3 files changed, 25 insertions(+), 9 deletions(-)

diff --git a/.agents/skills/do-web-doc-resolver/scripts/quality.py b/.agents/skills/do-web-doc-resolver/scripts/quality.py
index de6fc171..b7150095 100644
--- a/.agents/skills/do-web-doc-resolver/scripts/quality.py
+++ b/.agents/skills/do-web-doc-resolver/scripts/quality.py
@@ -86,8 +86,12 @@ def _check_jargon(text_lower: str) -> bool:
         "transform",
         "supercharge",
     ]
-    jargon_count = sum(text_lower.count(signal) for signal in jargon_signals)
-    return jargon_count > THRESHOLD_JARGON
+    jargon_count = 0
+    for signal in jargon_signals:
+        jargon_count += text_lower.count(signal)
+        if jargon_count > THRESHOLD_JARGON:
+            return True
+    return False
 
 
 def _check_frontmatter(text: str) -> bool:
@@ -115,8 +119,12 @@ def _check_anchors(text: str) -> bool:
 def _compute_noise(text_lower: str) -> bool:
     """Detect noisy signals like cookie/subscribe prompts."""
     noisy_signals = ["cookie", "subscribe", "javascript", "log in", "sign up"]
-    noise_count = sum(text_lower.count(signal) for signal in noisy_signals)
-    return noise_count > THRESHOLD_NOISE
+    noise_count = 0
+    for signal in noisy_signals:
+        noise_count += text_lower.count(signal)
+        if noise_count > THRESHOLD_NOISE:
+            return True
+    return False
 
 
 def is_bot_challenge(content: str) -> bool:
diff --git a/scripts/quality.py b/scripts/quality.py
index 9ee6b6ff..ff8db32f 100644
--- a/scripts/quality.py
+++ b/scripts/quality.py
@@ -86,8 +86,12 @@ def _check_jargon(text_lower: str) -> bool:
         "transform",
         "supercharge",
     ]
-    jargon_count = sum(text_lower.count(signal) for signal in jargon_signals)
-    return jargon_count > THRESHOLD_JARGON
+    jargon_count = 0
+    for signal in jargon_signals:
+        jargon_count += text_lower.count(signal)
+        if jargon_count > THRESHOLD_JARGON:
+            return True
+    return False
 
 
 def _check_frontmatter(text: str) -> bool:
@@ -115,8 +119,12 @@ def _check_anchors(text: str) -> bool:
 def _compute_noise(text_lower: str) -> bool:
     """Detect noisy signals like cookie/subscribe prompts."""
     noisy_signals = ["cookie", "subscribe", "javascript", "log in", "sign up"]
-    noise_count = sum(text_lower.count(signal) for signal in noisy_signals)
-    return noise_count > THRESHOLD_NOISE
+    noise_count = 0
+    for signal in noisy_signals:
+        noise_count += text_lower.count(signal)
+        if noise_count > THRESHOLD_NOISE:
+            return True
+    return False
 
 
 def is_bot_challenge(content: str) -> bool:
diff --git a/tests/test_content_clean.py b/tests/test_content_clean.py
index eccf3a2c..981a500f 100644
--- a/tests/test_content_clean.py
+++ b/tests/test_content_clean.py
@@ -8,7 +8,7 @@
   <h1>API Reference</h1>
   <p>The <code>resolve_url</code> function accepts a URL and returns resolved content.</p>
   <p>It supports multiple providers including jina, firecrawl, and direct fetch.</p>
-  <p>To use this module, make sure you have the proper API keys set up in your environment. Detailed usage instructions can be found in the main documentation. Web Doc Resolver is designed to be highly extensible and customizable for your specific RAG pipeline needs.</p>
+  <p>This is additional description text designed to make the main content segment much longer than two hundred characters. This is needed so that the content cleaning utility does not fall back to raw HTML tag stripping, which would keep footer items like the secondary notices.</p>
 </main>
 <footer>Cookie Policy Privacy Terms</footer>
 </body></html>