refactor(agent): move document media logic out of AgentLoop into document.py

Extract is_image_file() and reference_non_image_attachments() from
AgentLoop private static methods into nanobot/utils/document.py where
they belong alongside extract_documents(). Simplify config lookup by
removing dead isinstance(dict) branch.
This commit is contained in:
chengyongru
2026-05-29 15:31:03 +08:00
committed by Xubin Ren
parent ec4f9e9857
commit 672fabe5be
3 changed files with 54 additions and 51 deletions
+41 -5
View File
@@ -7,7 +7,6 @@ from loguru import logger
from nanobot.utils.helpers import detect_image_mime
# Supported file extensions for text extraction
SUPPORTED_EXTENSIONS: set[str] = {
# Document formats
@@ -232,6 +231,46 @@ def _is_text_extension(ext: str) -> bool:
_MAX_EXTRACT_FILE_SIZE = 50 * 1024 * 1024 # 50 MB
def is_image_file(path: str) -> bool:
"""Check whether *path* looks like an image file.
Uses magic-byte detection (reads first 16 bytes) with a ``mimetypes``
extension-based fallback.
"""
p = Path(path)
mime: str | None = None
if p.is_file():
try:
with p.open("rb") as f:
mime = detect_image_mime(f.read(16))
except OSError:
mime = None
if not mime:
mime = mimetypes.guess_type(path)[0]
return bool(mime and mime.startswith("image/"))
def reference_non_image_attachments(
content: str, media: list[str],
) -> tuple[str, list[str]]:
"""Separate images from non-image attachments without reading file content.
Image paths are preserved for downstream vision-block construction.
Non-image paths are appended as ``[Attachment: path]`` references.
"""
image_paths: list[str] = []
attachment_refs: list[str] = []
for path in media:
if is_image_file(path):
image_paths.append(path)
else:
attachment_refs.append(f"[Attachment: {path}]")
if attachment_refs:
suffix = "\n".join(attachment_refs)
content = f"{content}\n\n{suffix}" if content else suffix
return content, image_paths
def extract_documents(
text: str,
media_paths: list[str],
@@ -267,10 +306,7 @@ def extract_documents(
)
continue
with open(p, "rb") as f:
header = f.read(16)
mime = detect_image_mime(header) or mimetypes.guess_type(path_str)[0]
if mime and mime.startswith("image/"):
if is_image_file(path_str):
image_paths.append(path_str)
else:
extracted = extract_text(p)