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(mixed-content): do not carve ISO-timestamped log rows as search results (#4463)

HetCreepabbade9b4c76
diff --git a/headroom/transforms/mixed_content.py b/headroom/transforms/mixed_content.py
index 9c0a398c8..e359ef485 100644
--- a/headroom/transforms/mixed_content.py
+++ b/headroom/transforms/mixed_content.py
@@ -7,6 +7,7 @@ import re
from dataclasses import dataclass
from .content_detector import ContentType, _is_search_result_line
+from .lossless_compaction import _TIMESTAMP_ROW_RE
@dataclass
@@ -45,7 +46,13 @@ def _is_search_line(line: str) -> bool:
Sharing it keeps the splitter carving the same lines the detector claims
(#3580); otherwise code in context lines would strand in PLAIN_TEXT
sections and reach the prose compressor.
+
+ Timestamped log rows (``2026-09-23T10:05:07Z ...``) match the legacy
+ pattern but are never grep output; the detector rejects them (#3736), so
+ the splitter must too or it hands them to the lossy search compressor.
"""
+ if _TIMESTAMP_ROW_RE.match(line):
+ return False
return bool(_SEARCH_RESULT_PATTERN.match(line)) or _is_search_result_line(line)
diff --git a/tests/test_mixed_content_sections.py b/tests/test_mixed_content_sections.py
index 3d80f75dd..822a530a4 100644
--- a/tests/test_mixed_content_sections.py
+++ b/tests/test_mixed_content_sections.py
@@ -98,3 +98,22 @@ def test_extract_json_block_ignores_delimiters_inside_strings():
assert end_line == 3
assert block == "\n".join(lines)
+
+
+def test_split_does_not_carve_timestamped_log_rows_as_search():
+ """Regression (#3736 residual): the detector rejects ISO-timestamped log
+ rows as search output; the splitter must not carve them either, while
+ real ``path:NN:content`` grep lines still carve.
+ """
+ logs = [
+ "2026-09-23T10:05:07Z worker-1 INFO request handled",
+ "2026-09-23T10:05:13Z worker-2 ERROR upstream timeout",
+ ]
+ content = "\n".join(["Intro text", "```python", "print('x')", "```", *logs])
+
+ assert ContentType.SEARCH_RESULTS not in [
+ section.content_type for section in split_into_sections(content)
+ ]
+
+ grep = "\n".join(["Intro text", "```python", "print('x')", "```", "src/app.py:10:print('x')"])
+ assert split_into_sections(grep)[-1].content_type == ContentType.SEARCH_RESULTS