Skip to content

fix: bound web search result content #14470

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
Oxygen56 wants to merge 6 commits into
base: main
Choose a base branch
from
Open

fix: bound web search result content #14470

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
8454392
fix: bound web search result content
Oxygen56 Aug 8, 2026
5df6cce
[autofix.ci] apply automated fixes
autofix-ci[bot] Aug 8, 2026
65cbdeb
[autofix.ci] apply automated fixes (attempt 2/3)
autofix-ci[bot] Aug 8, 2026
23ba428
test: cover nonpositive web search limits
Oxygen56 Aug 8, 2026
cf37613
chore: resolve component index merge conflict
Oxygen56 Aug 8, 2026
26bfacc
chore: merge main into web search fix
Oxygen56 Aug 9, 2026
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
48 changes: 46 additions & 2 deletions src/backend/base/langflow/initial_setup/starter_projects/Content Aggregator.json
View file
Open in desktop

Large diffs are not rendered by default.

48 changes: 46 additions & 2 deletions src/backend/base/langflow/initial_setup/starter_projects/Deep Research Agent.json
View file
Open in desktop

Large diffs are not rendered by default.

48 changes: 46 additions & 2 deletions src/backend/base/langflow/initial_setup/starter_projects/Instagram Copywriter.json
View file
Open in desktop

Large diffs are not rendered by default.

48 changes: 46 additions & 2 deletions src/backend/base/langflow/initial_setup/starter_projects/Market Research.json
View file
Open in desktop

Large diffs are not rendered by default.

48 changes: 46 additions & 2 deletions src/backend/base/langflow/initial_setup/starter_projects/Price Deal Finder.json
View file
Open in desktop

Large diffs are not rendered by default.

48 changes: 46 additions & 2 deletions src/backend/base/langflow/initial_setup/starter_projects/Sequential Tasks Agents.json
View file
Open in desktop

Large diffs are not rendered by default.

48 changes: 46 additions & 2 deletions src/backend/base/langflow/initial_setup/starter_projects/Simple Agent.json
View file
Open in desktop

Large diffs are not rendered by default.

48 changes: 46 additions & 2 deletions src/backend/base/langflow/initial_setup/starter_projects/Social Media Agent.json
View file
Open in desktop

Large diffs are not rendered by default.

48 changes: 46 additions & 2 deletions src/backend/base/langflow/initial_setup/starter_projects/Travel Planning Agents.json
View file
Open in desktop

Large diffs are not rendered by default.

103 changes: 103 additions & 0 deletions src/backend/tests/unit/components/data_source/test_web_search.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,6 +21,8 @@ def default_kwargs(self):
return {
"search_mode": "Web",
"query": "OpenAI GPT-4",
"max_results": 5,
"max_content_length": 4000,
"timeout": 5,
}

Expand Down Expand Up @@ -123,6 +125,15 @@ def test_clean_html(self):
expected = "Title Paragraph"
assert component.clean_html(html) == expected

def test_web_search_limit_inputs(self):
"""Web search should expose conservative advanced limits."""
inputs = {input_.name: input_ for input_ in WebSearchComponent.inputs}

assert inputs["max_results"].value == 5
assert inputs["max_results"].advanced is True
assert inputs["max_content_length"].value == 4000
assert inputs["max_content_length"].advanced is True

def test_update_build_config_web_mode(self):
"""Test build config update for Web mode."""
component = WebSearchComponent()
Expand Down Expand Up @@ -187,6 +198,98 @@ def test_perform_web_search_success(self, mock_get, mock_safe_get):
assert result.iloc[0]["snippet"] == "Test snippet content"
assert "Page content" in result.iloc[0]["content"]

@patch.object(WebSearchComponent, "_safe_get_url")
@patch("lfx.components.data_source.web_search.requests.get")
def test_perform_web_search_limits_results_and_content(self, mock_get, mock_safe_get):
"""Web search should bound both fetched result count and returned page text."""
component = WebSearchComponent()
component.query = "test query"
component.max_results = 2
component.max_content_length = 12
component.timeout = 5

mock_response = Mock()
mock_response.text = """
<html>
<div class="result">
<a class="result__a" href="?uddg=https%3A%2F%2Fexample.com%2F1">First</a>
</div>
<div class="result">
<a class="result__a" href="?uddg=https%3A%2F%2Fexample.com%2F2">Second</a>
</div>
<div class="result">
<a class="result__a" href="?uddg=https%3A%2F%2Fexample.com%2F3">Third</a>
</div>
</html>
"""
mock_response.headers = {"content-type": "text/html"}
mock_response.raise_for_status.return_value = None
mock_get.return_value = mock_response

mock_page_response = Mock()
mock_page_response.text = "<html><body>abcdefghijklmnopqrstuvwxyz</body></html>"
mock_page_response.raise_for_status.return_value = None
mock_safe_get.return_value = mock_page_response

with patch("lfx.components.data_source.web_search.get_user_agent", return_value="test-agent"):
result = component.perform_web_search()

assert len(result) == 2
assert mock_safe_get.call_count == 2
assert result["content"].tolist() == ["abcdefghijkl", "abcdefghijkl"]
Comment on lines +201 to +239

@coderabbitai coderabbitai Bot Aug 8, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

🎯 Functional Correctness | 🟡 Minor | ⚡ Quick win

Test zero and negative limits.

The implementation clamps both limits to zero. This test only covers positive values. Add cases for max_results=0, max_results=-1, max_content_length=0, and max_content_length=-1. Assert that a zero result limit fetches no result pages and that a zero content limit returns empty content.

As per coding guidelines, backend tests must cover positive, negative, edge, and error cases.

🤖 Prompt for AI Agents 
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@src/backend/tests/unit/components/data_source/test_web_search.py` around
lines 201 - 239, Add test coverage around
test_perform_web_search_limits_and_content for zero and negative max_results and
max_content_length values. Verify max_results=0 and -1 fetch no result pages,
and max_content_length=0 and -1 return empty content, while preserving the
existing positive-limit assertions and mocks.

Source: Coding guidelines


@pytest.mark.parametrize(
("max_results", "max_content_length", "expected_result_count", "expected_content"),
[
(0, 12, 0, None),
(-1, 12, 0, None),
(1, 0, 1, ""),
(1, -1, 1, ""),
],
)
@patch.object(WebSearchComponent, "_safe_get_url")
@patch("lfx.components.data_source.web_search.requests.get")
def test_perform_web_search_clamps_nonpositive_limits(
self,
mock_get,
mock_safe_get,
max_results,
max_content_length,
expected_result_count,
expected_content,
):
"""Web search should clamp zero and negative limits to zero."""
component = WebSearchComponent()
component.query = "test query"
component.max_results = max_results
component.max_content_length = max_content_length
component.timeout = 5

mock_response = Mock()
mock_response.text = """
<html>
<div class="result">
<a class="result__a" href="?uddg=https%3A%2F%2Fexample.com%2F1">First</a>
</div>
</html>
"""
mock_response.headers = {"content-type": "text/html"}
mock_response.raise_for_status.return_value = None
mock_get.return_value = mock_response

mock_page_response = Mock()
mock_page_response.text = "<html><body>abcdefghijklmnopqrstuvwxyz</body></html>"
mock_page_response.raise_for_status.return_value = None
mock_safe_get.return_value = mock_page_response

with patch("lfx.components.data_source.web_search.get_user_agent", return_value="test-agent"):
result = component.perform_web_search()

assert len(result) == expected_result_count
assert mock_safe_get.call_count == expected_result_count
if expected_content is not None:
assert result["content"].tolist() == [expected_content]

@patch("lfx.components.data_source.web_search.requests.get")
def test_perform_web_search_no_results(self, mock_get):
"""Test web search with no results."""
Expand Down
Loading
Loading