youngkingdom/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-05-01 07:58:02 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'main' into feat/agent-node-v2

Browse Source
This commit is contained in:
Novice
2025-12-30 10:20:42 +08:00
parent 56c8221b3f faef04cdf7
commit ccabdbc83b
232 changed files with 18692 additions and 2696 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
api/core/workflow/enums.py
View File

@ -249,6 +249,7 @@ class WorkflowNodeExecutionMetadataKey(StrEnum):
DATASOURCE_INFO = "datasource_info"
LLM_CONTENT_SEQUENCE = "llm_content_sequence"
LLM_TRACE = "llm_trace"
COMPLETED_REASON = "completed_reason" # completed reason for loop node
class WorkflowNodeExecutionStatus(StrEnum):

5
api/core/workflow/nodes/http_request/executor.py
View File

@ -86,6 +86,11 @@ class Executor:
node_data.authorization.config.api_key = variable_pool.convert_template(
node_data.authorization.config.api_key
).text
# Validate that API key is not empty after template conversion
if not node_data.authorization.config.api_key or not node_data.authorization.config.api_key.strip():
raise AuthorizationConfigError(
"API key is required for authorization but was empty. Please provide a valid API key."
)
self.url = node_data.url
self.method = node_data.method

87
api/core/workflow/nodes/knowledge_retrieval/knowledge_retrieval_node.py
View File

@ -6,7 +6,7 @@ from collections import defaultdict
from collections.abc import Mapping, Sequence
from typing import TYPE_CHECKING, Any, cast
from sqlalchemy import and_, func, literal, or_, select
from sqlalchemy import and_, func, or_, select
from sqlalchemy.orm import sessionmaker
from core.app.app_config.entities import DatasetRetrieveConfigEntity
@ -460,7 +460,7 @@ class KnowledgeRetrievalNode(LLMUsageTrackingMixin, Node[KnowledgeRetrievalNodeD
if automatic_metadata_filters:
conditions = []
for sequence, filter in enumerate(automatic_metadata_filters):
self._process_metadata_filter_func(
DatasetRetrieval.process_metadata_filter_func(
sequence,
filter.get("condition", ""),
filter.get("metadata_name", ""),
@ -504,7 +504,7 @@ class KnowledgeRetrievalNode(LLMUsageTrackingMixin, Node[KnowledgeRetrievalNodeD
value=expected_value,
)
)
filters = self._process_metadata_filter_func(
filters = DatasetRetrieval.process_metadata_filter_func(
sequence,
condition.comparison_operator,
metadata_name,
@ -603,87 +603,6 @@ class KnowledgeRetrievalNode(LLMUsageTrackingMixin, Node[KnowledgeRetrievalNodeD
return [], usage
return automatic_metadata_filters, usage
def _process_metadata_filter_func(
self, sequence: int, condition: str, metadata_name: str, value: Any, filters: list[Any]
) -> list[Any]:
if value is None and condition not in ("empty", "not empty"):
return filters
json_field = Document.doc_metadata[metadata_name].as_string()
match condition:
case "contains":
filters.append(json_field.like(f"%{value}%"))
case "not contains":
filters.append(json_field.notlike(f"%{value}%"))
case "start with":
filters.append(json_field.like(f"{value}%"))
case "end with":
filters.append(json_field.like(f"%{value}"))
case "in":
if isinstance(value, str):
value_list = [v.strip() for v in value.split(",") if v.strip()]
elif isinstance(value, (list, tuple)):
value_list = [str(v) for v in value if v is not None]
else:
value_list = [str(value)] if value is not None else []
if not value_list:
filters.append(literal(False))
else:
filters.append(json_field.in_(value_list))
case "not in":
if isinstance(value, str):
value_list = [v.strip() for v in value.split(",") if v.strip()]
elif isinstance(value, (list, tuple)):
value_list = [str(v) for v in value if v is not None]
else:
value_list = [str(value)] if value is not None else []
if not value_list:
filters.append(literal(True))
else:
filters.append(json_field.notin_(value_list))
case "is" | "=":
if isinstance(value, str):
filters.append(json_field == value)
elif isinstance(value, (int, float)):
filters.append(Document.doc_metadata[metadata_name].as_float() == value)
case "is not" | "≠":
if isinstance(value, str):
filters.append(json_field != value)
elif isinstance(value, (int, float)):
filters.append(Document.doc_metadata[metadata_name].as_float() != value)
case "empty":
filters.append(Document.doc_metadata[metadata_name].is_(None))
case "not empty":
filters.append(Document.doc_metadata[metadata_name].isnot(None))
case "before" | "<":
filters.append(Document.doc_metadata[metadata_name].as_float() < value)
case "after" | ">":
filters.append(Document.doc_metadata[metadata_name].as_float() > value)
case "≤" | "<=":
filters.append(Document.doc_metadata[metadata_name].as_float() <= value)
case "≥" | ">=":
filters.append(Document.doc_metadata[metadata_name].as_float() >= value)
case _:
pass
return filters
@classmethod
def _extract_variable_selector_to_variable_mapping(
cls,

6
api/core/workflow/nodes/loop/entities.py
View File

@ -1,3 +1,4 @@
from enum import StrEnum
from typing import Annotated, Any, Literal
from pydantic import AfterValidator, BaseModel, Field, field_validator
@ -96,3 +97,8 @@ class LoopState(BaseLoopState):
Get current output.
"""
return self.current_output
class LoopCompletedReason(StrEnum):
LOOP_BREAK = "loop_break"
LOOP_COMPLETED = "loop_completed"

22
api/core/workflow/nodes/loop/loop_node.py
View File

@ -29,7 +29,7 @@ from core.workflow.node_events import (
)
from core.workflow.nodes.base import LLMUsageTrackingMixin
from core.workflow.nodes.base.node import Node
from core.workflow.nodes.loop.entities import LoopNodeData, LoopVariableData
from core.workflow.nodes.loop.entities import LoopCompletedReason, LoopNodeData, LoopVariableData
from core.workflow.utils.condition.processor import ConditionProcessor
from factories.variable_factory import TypeMismatchError, build_segment_with_type, segment_to_variable
from libs.datetime_utils import naive_utc_now
@ -96,6 +96,7 @@ class LoopNode(LLMUsageTrackingMixin, Node[LoopNodeData]):
loop_duration_map: dict[str, float] = {}
single_loop_variable_map: dict[str, dict[str, Any]] = {} # single loop variable output
loop_usage = LLMUsage.empty_usage()
loop_node_ids = self._extract_loop_node_ids_from_config(self.graph_config, self._node_id)
# Start Loop event
yield LoopStartedEvent(
@ -118,6 +119,8 @@ class LoopNode(LLMUsageTrackingMixin, Node[LoopNodeData]):
loop_count = 0
for i in range(loop_count):
# Clear stale variables from previous loop iterations to avoid streaming old values
self._clear_loop_subgraph_variables(loop_node_ids)
graph_engine = self._create_graph_engine(start_at=start_at, root_node_id=root_node_id)
loop_start_time = naive_utc_now()
@ -177,7 +180,11 @@ class LoopNode(LLMUsageTrackingMixin, Node[LoopNodeData]):
WorkflowNodeExecutionMetadataKey.TOTAL_TOKENS: loop_usage.total_tokens,
WorkflowNodeExecutionMetadataKey.TOTAL_PRICE: loop_usage.total_price,
WorkflowNodeExecutionMetadataKey.CURRENCY: loop_usage.currency,
"completed_reason": "loop_break" if reach_break_condition else "loop_completed",
WorkflowNodeExecutionMetadataKey.COMPLETED_REASON: (
LoopCompletedReason.LOOP_BREAK
if reach_break_condition
else LoopCompletedReason.LOOP_COMPLETED.value
),
WorkflowNodeExecutionMetadataKey.LOOP_DURATION_MAP: loop_duration_map,
WorkflowNodeExecutionMetadataKey.LOOP_VARIABLE_MAP: single_loop_variable_map,
},
@ -274,6 +281,17 @@ class LoopNode(LLMUsageTrackingMixin, Node[LoopNodeData]):
if WorkflowNodeExecutionMetadataKey.LOOP_ID not in current_metadata:
event.node_run_result.metadata = {**current_metadata, **loop_metadata}
def _clear_loop_subgraph_variables(self, loop_node_ids: set[str]) -> None:
"""
Remove variables produced by loop sub-graph nodes from previous iterations.
Keeping stale variables causes a freshly created response coordinator in the
next iteration to fall back to outdated values when no stream chunks exist.
"""
variable_pool = self.graph_runtime_state.variable_pool
for node_id in loop_node_ids:
variable_pool.remove([node_id])
@classmethod
def _extract_variable_selector_to_variable_mapping(
cls,

2
api/core/workflow/nodes/parameter_extractor/parameter_extractor_node.py
View File

@ -281,7 +281,7 @@ class ParameterExtractorNode(Node[ParameterExtractorNodeData]):
# handle invoke result
text = invoke_result.message.content or ""
text = invoke_result.message.get_text_content()
if not isinstance(text, str):
raise InvalidTextContentTypeError(f"Invalid text content type: {type(text)}. Expected str.")

21
api/core/workflow/nodes/start/start_node.py
View File

@ -1,3 +1,4 @@
import json
from typing import Any
from jsonschema import Draft7Validator, ValidationError
@ -42,15 +43,25 @@ class StartNode(Node[StartNodeData]):
if value is None and variable.required:
raise ValueError(f"{key} is required in input form")
if not isinstance(value, dict):
raise ValueError(f"{key} must be a JSON object")
schema = variable.json_schema
if not schema:
continue
if not value:
continue
try:
Draft7Validator(schema).validate(value)
json_schema = json.loads(schema)
except json.JSONDecodeError as e:
raise ValueError(f"{schema} must be a valid JSON object")
try:
json_value = json.loads(value)
except json.JSONDecodeError as e:
raise ValueError(f"{value} must be a valid JSON object")
try:
Draft7Validator(json_schema).validate(json_value)
except ValidationError as e:
raise ValueError(f"JSON object for '{key}' does not match schema: {e.message}")
node_inputs[key] = value
node_inputs[key] = json_value