Skip to content

Your lightweight open-source personal agent.

fix(files): honor Unicode byte-order marks

Zihan Xu394b4f2cc3f2
diff --git a/nanobot/agent/tools/filesystem.py b/nanobot/agent/tools/filesystem.py
index 7a2ae142f..6f680bb05 100644
--- a/nanobot/agent/tools/filesystem.py
+++ b/nanobot/agent/tools/filesystem.py
@@ -348,28 +348,32 @@ class ReadFileTool(_FsTool):
fp, offset=offset, limit=limit, content_hash=content_hash,
):
return f"[File unchanged since last read: {path}]"
- try:
- text_content = raw.decode("utf-8")
- except UnicodeDecodeError:
- # Match the former eager extractor for known text formats while
- # keeping arbitrary binary files on the guarded error path.
- from nanobot.utils.document import _is_text_extension
-
- if _is_text_extension(fp.suffix.lower()):
- text_content = raw.decode("latin-1")
- else:
- mime = detect_image_mime(raw) or mimetypes.guess_type(path)[0]
- if mime and mime.startswith("image/"):
- return build_image_content_blocks(
- raw,
- mime,
- str(fp),
- f"(Image file: {path})",
+ from nanobot.utils.document import _decode_bom_text
+
+ text_content = _decode_bom_text(raw)
+ if text_content is None:
+ try:
+ text_content = raw.decode("utf-8")
+ except UnicodeDecodeError:
+ # Match the former eager extractor for known text formats while
+ # keeping arbitrary binary files on the guarded error path.
+ from nanobot.utils.document import _is_text_extension
+
+ if _is_text_extension(fp.suffix.lower()):
+ text_content = raw.decode("latin-1")
+ else:
+ mime = detect_image_mime(raw) or mimetypes.guess_type(path)[0]
+ if mime and mime.startswith("image/"):
+ return build_image_content_blocks(
+ raw,
+ mime,
+ str(fp),
+ f"(Image file: {path})",
+ )
+ return ToolResult.error(
+ f"Error: Cannot read binary file {path} (MIME: {mime or 'unknown'}). "
+ "Only supported text files and images can be read."
)
- return ToolResult.error(
- f"Error: Cannot read binary file {path} (MIME: {mime or 'unknown'}). "
- "Only supported text files and images can be read."
- )
# Normalize CRLF -> LF before line-splitting. Primarily a Windows
# concern (git checkouts with autocrlf, editors saving CRLF) but