Skip to content
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
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
2 changes: 2 additions & 0 deletions .github/workflows/nightly-bridge.yml

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

19 changes: 19 additions & 0 deletions tests/integration/test_nightly_bridge.py
Original file line number Diff line number Diff line change
Expand Up @@ -90,3 +90,22 @@ def test_nightly_llm_ready_standards():
assert "[ANCHOR: TECHNICAL_DETAILS]" in content
assert "[ANCHOR: COMPARISON]" in content
assert "[ANCHOR: CITATIONS]" in content


@pytest.mark.integration
def test_nightly_js_heavy_site_parsing():
"""Verify that JS-heavy sites have their content correctly parsed without unparsed code blocks."""
url = "https://react.dev/learn"

result = subprocess.run(
[CLI_PATH, "resolve", url, "--provider", "jina"],
capture_output=True,
text=True,
check=True,
)

content = result.stdout
assert len(content) > 500, "Content too short"
assert "React" in content
assert "<pre" not in content, "Found unparsed <pre> tag"
assert "<code>" not in content, "Found unparsed <code> tag"
3 changes: 3 additions & 0 deletions tests/test_content_clean.py
Original file line number Diff line number Diff line change
Expand Up @@ -8,6 +8,9 @@
<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 ensure high quality, the system filters out boilerplate, parses complex structures,
deduplicates headers, preserves nested lists, handles various character encodings, and
ensures the output matches 2026 LLM-ready standards with zero slop and maximum density.</p>
</main>
<footer>Cookie Policy Privacy Terms</footer>
</body></html>
Expand Down
22 changes: 11 additions & 11 deletions web/package-lock.json

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

6 changes: 3 additions & 3 deletions web/package.json
Original file line number Diff line number Diff line change
Expand Up @@ -43,7 +43,7 @@
"eslint-plugin-playwright": "^2.10.5",
"eslint-plugin-react-hooks": "^7.1.1",
"globals": "^17.7.0",
"postcss": "8.5.19",
"postcss": "8.5.25",
"tailwindcss": "^4.0.0",
"typescript": "6.0.3",
"vitest": "^4.1.10",
Expand All @@ -52,10 +52,10 @@
"overrides": {
"@ungap/structured-clone": "1.3.1",
"sharp": "0.35.3",
"brace-expansion": ">=1.1.16",
"brace-expansion": "^1.1.18 || ^2.1.4 || ^3.0.6 || ^5.0.9",
"axios": ">=1.18.0",
"next": {
"postcss": "8.5.19"
"postcss": "8.5.25"
}
}
}
Loading