Merge branch 'main' into feat/end-user-oauth

api/core/workflow/graph_engine/event_management/event_manager.py

@@ -2,6 +2,7 @@
 Unified event manager for collecting and emitting events.
 """
 
+import logging
 import threading
 import time
 from collections.abc import Generator
@@ -12,6 +13,8 @@ from core.workflow.graph_events import GraphEngineEvent
 
 from ..layers.base import GraphEngineLayer
 
+_logger = logging.getLogger(__name__)
+
 
 @final
 class ReadWriteLock:
@@ -180,5 +183,4 @@ class EventManager:
             try:
                 layer.on_event(event)
             except Exception:
-                # Silently ignore layer errors during collection
-                pass
+                _logger.exception("Error in layer on_event, layer_type=%s", type(layer))

api/core/workflow/graph_engine/manager.py

@@ -6,12 +6,15 @@ using the new Redis command channel, without requiring user permission checks.
 Supports stop, pause, and resume operations.
 """
 
+import logging
 from typing import final
 
 from core.workflow.graph_engine.command_channels.redis_channel import RedisChannel
 from core.workflow.graph_engine.entities.commands import AbortCommand, GraphEngineCommand, PauseCommand
 from extensions.ext_redis import redis_client
 
+logger = logging.getLogger(__name__)
+
 
 @final
 class GraphEngineManager:
@@ -57,4 +60,4 @@ class GraphEngineManager:
         except Exception:
             # Silently fail if Redis is unavailable
             # The legacy control mechanisms will still work
-            pass
+            logger.exception("Failed to send graph engine command %s for task %s", command.__class__.__name__, task_id)

api/core/workflow/nodes/document_extractor/node.py

@@ -7,7 +7,7 @@ import tempfile
 from collections.abc import Mapping, Sequence
 from typing import Any
 
-import chardet
+import charset_normalizer
 import docx
 import pandas as pd
 import pypandoc
@@ -228,9 +228,12 @@ def _extract_text_by_file_extension(*, file_content: bytes, file_extension: str)
 
 def _extract_text_from_plain_text(file_content: bytes) -> str:
     try:
-        # Detect encoding using chardet
-        result = chardet.detect(file_content)
-        encoding = result["encoding"]
+        # Detect encoding using charset_normalizer
+        result = charset_normalizer.from_bytes(file_content, cp_isolation=["utf_8", "latin_1", "cp1252"]).best()
+        if result:
+            encoding = result.encoding
+        else:
+            encoding = "utf-8"
 
         # Fallback to utf-8 if detection fails
         if not encoding:
@@ -247,9 +250,12 @@ def _extract_text_from_plain_text(file_content: bytes) -> str:
 
 def _extract_text_from_json(file_content: bytes) -> str:
     try:
-        # Detect encoding using chardet
-        result = chardet.detect(file_content)
-        encoding = result["encoding"]
+        # Detect encoding using charset_normalizer
+        result = charset_normalizer.from_bytes(file_content).best()
+        if result:
+            encoding = result.encoding
+        else:
+            encoding = "utf-8"
 
         # Fallback to utf-8 if detection fails
         if not encoding:
@@ -269,9 +275,12 @@ def _extract_text_from_json(file_content: bytes) -> str:
 def _extract_text_from_yaml(file_content: bytes) -> str:
     """Extract the content from yaml file"""
     try:
-        # Detect encoding using chardet
-        result = chardet.detect(file_content)
-        encoding = result["encoding"]
+        # Detect encoding using charset_normalizer
+        result = charset_normalizer.from_bytes(file_content).best()
+        if result:
+            encoding = result.encoding
+        else:
+            encoding = "utf-8"
 
         # Fallback to utf-8 if detection fails
         if not encoding:
@@ -424,9 +433,12 @@ def _extract_text_from_file(file: File):
 
 def _extract_text_from_csv(file_content: bytes) -> str:
     try:
-        # Detect encoding using chardet
-        result = chardet.detect(file_content)
-        encoding = result["encoding"]
+        # Detect encoding using charset_normalizer
+        result = charset_normalizer.from_bytes(file_content).best()
+        if result:
+            encoding = result.encoding
+        else:
+            encoding = "utf-8"
 
         # Fallback to utf-8 if detection fails
         if not encoding:

api/core/workflow/nodes/node_factory.py

@@ -64,7 +64,10 @@ class DifyNodeFactory(NodeFactory):
         if not node_mapping:
             raise ValueError(f"No class mapping found for node type: {node_type}")
 
-        node_class = node_mapping.get(LATEST_VERSION)
+        latest_node_class = node_mapping.get(LATEST_VERSION)
+        node_version = str(node_data.get("version", "1"))
+        matched_node_class = node_mapping.get(node_version)
+        node_class = matched_node_class or latest_node_class
         if not node_class:
             raise ValueError(f"No latest version class found for node type: {node_type}")