Merge branch 'dhk-1' of http://192.168.0.200/knowledge-base-bj/deerflow-server into dhk-1
This commit is contained in:
commit
8f6e08eb2f
102 files changed
+6816
-6016
No files matched your search
+16
@@ -18,6 +18,12 @@ logger = logging.getLogger(__name__)
|
||||
|
||||
_OUTLINE_PREVIEW_LINES = 5
|
||||
|
||||
# Image files are understood via the `view_image` tool (which routes to the
|
||||
# configured vision model), never by reading their bytes. Listing them with the
|
||||
# generic read_file/grep guidance made the agent try to parse image binaries
|
||||
# with bash/python, which fails and wastes turns.
|
||||
_IMAGE_EXTENSIONS = {".jpg", ".jpeg", ".png", ".webp", ".gif", ".bmp"}
|
||||
|
||||
|
||||
def _extract_outline_for_file(file_path: Path) -> tuple[list[dict], list[str]]:
|
||||
"""Return the document outline and fallback preview for *file_path*.
|
||||
@@ -88,6 +94,16 @@ class UploadsMiddleware(AgentMiddleware[UploadsMiddlewareState]):
|
||||
size_str = f"{size_kb:.1f} KB" if size_kb < 1024 else f"{size_kb / 1024:.1f} MB"
|
||||
lines.append(f"- {file['filename']} ({size_str})")
|
||||
lines.append(f" Path: {file['path']}")
|
||||
|
||||
# Images must be understood through the vision model, not by reading bytes.
|
||||
extension = str(file.get("extension") or Path(file["filename"]).suffix).lower()
|
||||
if extension in _IMAGE_EXTENSIONS:
|
||||
lines.append(f" This is an image. To understand it, call the `view_image` tool with image_path='{file['path']}' (optionally pass a `question`).")
|
||||
lines.append(" The configured vision model will analyze it and return a description — trust that result.")
|
||||
lines.append(" Do NOT read, open, or parse the image with read_file, grep, bash, python, PIL, or any byte-level inspection; those cannot interpret image content.")
|
||||
lines.append("")
|
||||
return
|
||||
|
||||
outline = file.get("outline") or []
|
||||
if outline:
|
||||
truncated = outline[-1].get("truncated", False)
|
||||
|
||||
+6
@@ -139,6 +139,12 @@ class ViewImageMiddleware(AgentMiddleware[ViewImageMiddlewareState]):
|
||||
if not messages:
|
||||
return False
|
||||
|
||||
# Nothing to inject when no image data was captured (e.g. delegated
|
||||
# recognition handled the image in the tool and stored no base64).
|
||||
# Avoids injecting a useless "No images have been viewed." message.
|
||||
if not state.get("viewed_images"):
|
||||
return False
|
||||
|
||||
# Get the last assistant message
|
||||
last_assistant_msg = self._get_last_assistant_message(messages)
|
||||
if not last_assistant_msg:
|
||||
|
||||
Reference in new issue
Block a user