Skip to content

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

fix(tests): skip HTML extractor tests when trafilatura not installed

Claude Code Bot9ff67fbd1b60
diff --git a/tests/test_evals/test_html_extraction_eval.py b/tests/test_evals/test_html_extraction_eval.py
index 4dcb56526..ef456f354 100644
--- a/tests/test_evals/test_html_extraction_eval.py
+++ b/tests/test_evals/test_html_extraction_eval.py
@@ -14,6 +14,9 @@ import os
import pytest
+# Skip entire module if trafilatura not installed
+pytest.importorskip("trafilatura")
+
from headroom.evals.html_extraction import (
HTMLEvalCase,
HTMLEvalResult,
diff --git a/tests/test_evals/test_html_oss_benchmarks.py b/tests/test_evals/test_html_oss_benchmarks.py
index be15f496a..3e6551f38 100644
--- a/tests/test_evals/test_html_oss_benchmarks.py
+++ b/tests/test_evals/test_html_oss_benchmarks.py
@@ -21,6 +21,9 @@ import os
import pytest
+# Skip entire module if trafilatura not installed
+pytest.importorskip("trafilatura")
+
class TestExtractionBenchmark:
"""Tests using Scrapinghub Article Extraction Benchmark.
diff --git a/tests/test_transforms/test_html_extractor.py b/tests/test_transforms/test_html_extractor.py
index bc281f178..b5416fa5c 100644
--- a/tests/test_transforms/test_html_extractor.py
+++ b/tests/test_transforms/test_html_extractor.py
@@ -7,6 +7,9 @@ and removes structural noise.
import pytest
+# Skip entire module if trafilatura not installed
+pytest.importorskip("trafilatura")
+
from headroom.transforms.html_extractor import (
HTMLExtractionResult,
HTMLExtractor,