seb/hermes-agent
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(read): extract notebook and office documents (#37082)

Browse Source 
Add stdlib-only extraction for `.ipynb`, `.docx`, and `.xlsx` in read_file with lazy integration and malformed-document fallback.
This commit is contained in:
Teknium
2026-06-13 14:42:51 -07:00
committed by GitHub
parent 2b67e96aec
commit 817f392311
3 changed files with 590 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/file_tools.py
+47 -1
View File
@@ -760,6 +760,52 @@ def read_file_tool(path: str, offset: int = 1, limit: int = 500, task_id: str =
_resolved = _resolve_path_for_task(path, task_id)
# ── Structured-document extraction ────────────────────────────
# Try before the binary-extension guard so .docx/.xlsx can render as text.
# Malformed documents fall through to the normal path/binary guard.
from tools.read_extract import ExtractionError, extract_document_text, is_extractable_document
if is_extractable_document(str(_resolved)):
try:
extracted_text = extract_document_text(str(_resolved))
except ExtractionError:
logger.debug("document extraction failed for %s", path, exc_info=True)
else:
file_ops = _get_file_ops(task_id)
lines = extracted_text.splitlines()
total_lines = len(lines)
end_line = offset + limit - 1
page_text = "\n".join(lines[offset - 1:end_line])
result_dict = {
"content": file_ops._add_line_numbers(page_text, offset) if page_text else "",
"total_lines": total_lines,
"file_size": os.path.getsize(_resolved),
"truncated": total_lines > end_line,
"extracted_document": True,
}
if result_dict["truncated"]:
result_dict["hint"] = (
f"Use offset={end_line + 1} to continue reading "
f"(showing {offset}-{min(end_line, total_lines)} of {total_lines} lines)"
)
content_len = len(result_dict["content"])
max_chars = _get_max_read_chars()
if content_len > max_chars:
return json.dumps({
"error": (
f"Read produced {content_len:,} characters which exceeds "
f"the safety limit ({max_chars:,} chars). "
"Use offset and limit to read a smaller range. "
f"The document has {total_lines} lines of extracted text."
),
"path": path,
"total_lines": total_lines,
"file_size": result_dict["file_size"],
}, ensure_ascii=False)
if result_dict["content"]:
result_dict["content"] = redact_sensitive_text(result_dict["content"], code_file=True)
return json.dumps(result_dict, ensure_ascii=False)
# ── Binary file guard ─────────────────────────────────────────
# Block binary files by extension (no I/O).
if has_binary_extension(str(_resolved)):
@@ -1427,7 +1473,7 @@ def _check_file_reqs():
READ_FILE_SCHEMA = {
"name": "read_file",
"description": "Read a text file with line numbers and pagination. Use this instead of cat/head/tail in terminal. Output format: 'LINE_NUM|CONTENT'. Suggests similar filenames if not found. Use offset and limit for large files. Reads exceeding ~100K characters are rejected; use offset and limit to read specific sections of large files. NOTE: Cannot read images or binary files — use vision_analyze for images.",
"description": "Read a text file with line numbers and pagination. Use this instead of cat/head/tail in terminal. Output format: 'LINE_NUM|CONTENT'. Suggests similar filenames if not found. Use offset and limit for large files. Reads exceeding ~100K characters are rejected; use offset and limit to read specific sections of large files. Jupyter notebooks (.ipynb), Word documents (.docx), and Excel workbooks (.xlsx) are auto-extracted to readable text. NOTE: Cannot read images or other binary files — use vision_analyze for images.",
"parameters": {
"type": "object",
"properties": {