Compare commits

...

9 Commits

29 changed files with 286 additions and 756 deletions

View File

@@ -68,10 +68,9 @@ lint:
@echo "✅ Linting complete"
type-check:
@echo "📝 Running type checks (basedpyright + mypy + ty)..."
@echo "📝 Running type checks (basedpyright + mypy)..."
@./dev/basedpyright-check $(PATH_TO_CHECK)
@uv --directory api run mypy --exclude-gitignore --exclude 'tests/' --exclude 'migrations/' --check-untyped-defs --disable-error-code=import-untyped .
@cd api && uv run ty check
@echo "✅ Type checks complete"
test:
@@ -132,7 +131,7 @@ help:
@echo " make format - Format code with ruff"
@echo " make check - Check code with ruff"
@echo " make lint - Format, fix, and lint code (ruff, imports, dotenv)"
@echo " make type-check - Run type checks (basedpyright, mypy, ty)"
@echo " make type-check - Run type checks (basedpyright, mypy)"
@echo " make test - Run backend unit tests (or TARGET_TESTS=./api/tests/<target_tests>)"
@echo ""
@echo "Docker Build Targets:"

File diff suppressed because one or more lines are too long

View File

@@ -192,8 +192,8 @@ class AnalyticdbVectorOpenAPI:
collection=self._collection_name,
metrics=self.config.metrics,
include_values=True,
vector=None, # ty: ignore [invalid-argument-type]
content=None, # ty: ignore [invalid-argument-type]
vector=None,
content=None,
top_k=1,
filter=f"ref_doc_id='{id}'",
)
@@ -211,7 +211,7 @@ class AnalyticdbVectorOpenAPI:
namespace=self.config.namespace,
namespace_password=self.config.namespace_password,
collection=self._collection_name,
collection_data=None, # ty: ignore [invalid-argument-type]
collection_data=None,
collection_data_filter=f"ref_doc_id IN {ids_str}",
)
self._client.delete_collection_data(request)
@@ -225,7 +225,7 @@ class AnalyticdbVectorOpenAPI:
namespace=self.config.namespace,
namespace_password=self.config.namespace_password,
collection=self._collection_name,
collection_data=None, # ty: ignore [invalid-argument-type]
collection_data=None,
collection_data_filter=f"metadata_ ->> '{key}' = '{value}'",
)
self._client.delete_collection_data(request)
@@ -249,7 +249,7 @@ class AnalyticdbVectorOpenAPI:
include_values=kwargs.pop("include_values", True),
metrics=self.config.metrics,
vector=query_vector,
content=None, # ty: ignore [invalid-argument-type]
content=None,
top_k=kwargs.get("top_k", 4),
filter=where_clause,
)
@@ -285,7 +285,7 @@ class AnalyticdbVectorOpenAPI:
collection=self._collection_name,
include_values=kwargs.pop("include_values", True),
metrics=self.config.metrics,
vector=None, # ty: ignore [invalid-argument-type]
vector=None,
content=query,
top_k=kwargs.get("top_k", 4),
filter=where_clause,

View File

@@ -306,7 +306,7 @@ class CouchbaseVector(BaseVector):
def search_by_full_text(self, query: str, **kwargs: Any) -> list[Document]:
top_k = kwargs.get("top_k", 4)
try:
CBrequest = search.SearchRequest.create(search.QueryStringQuery("text:" + query)) # ty: ignore [too-many-positional-arguments]
CBrequest = search.SearchRequest.create(search.QueryStringQuery("text:" + query))
search_iter = self._scope.search(
self._collection_name + "_search", CBrequest, SearchOptions(limit=top_k, fields=["*"])
)

View File

@@ -33,6 +33,18 @@ class SortOrder(StrEnum):
class MyScaleVector(BaseVector):
_METADATA_KEY_WHITELIST = {
"annotation_id",
"app_id",
"batch",
"dataset_id",
"doc_hash",
"doc_id",
"document_id",
"lang",
"source",
}
def __init__(self, collection_name: str, config: MyScaleConfig, metric: str = "Cosine"):
super().__init__(collection_name)
self._config = config
@@ -45,10 +57,17 @@ class MyScaleVector(BaseVector):
password=config.password,
)
self._client.command("SET allow_experimental_object_type=1")
self._qualified_table = f"{self._config.database}.{self._collection_name}"
def get_type(self) -> str:
return VectorType.MYSCALE
@classmethod
def _validate_metadata_key(cls, key: str) -> str:
if key not in cls._METADATA_KEY_WHITELIST:
raise ValueError(f"Unsupported metadata key: {key!r}")
return key
def create(self, texts: list[Document], embeddings: list[list[float]], **kwargs):
dimension = len(embeddings[0])
self._create_collection(dimension)
@@ -59,7 +78,7 @@ class MyScaleVector(BaseVector):
self._client.command(f"CREATE DATABASE IF NOT EXISTS {self._config.database}")
fts_params = f"('{self._config.fts_params}')" if self._config.fts_params else ""
sql = f"""
CREATE TABLE IF NOT EXISTS {self._config.database}.{self._collection_name}(
CREATE TABLE IF NOT EXISTS {self._qualified_table}(
id String,
text String,
vector Array(Float32),
@@ -74,73 +93,103 @@ class MyScaleVector(BaseVector):
def add_texts(self, documents: list[Document], embeddings: list[list[float]], **kwargs):
ids = []
columns = ["id", "text", "vector", "metadata"]
values = []
rows = []
for i, doc in enumerate(documents):
if doc.metadata is not None:
doc_id = doc.metadata.get("doc_id", str(uuid.uuid4()))
row = (
doc_id,
self.escape_str(doc.page_content),
embeddings[i],
json.dumps(doc.metadata) if doc.metadata else {},
rows.append(
(
doc_id,
doc.page_content,
embeddings[i],
json.dumps(doc.metadata or {}),
)
)
values.append(str(row))
ids.append(doc_id)
sql = f"""
INSERT INTO {self._config.database}.{self._collection_name}
({",".join(columns)}) VALUES {",".join(values)}
"""
self._client.command(sql)
if rows:
self._client.insert(self._qualified_table, rows, column_names=columns)
return ids
@staticmethod
def escape_str(value: Any) -> str:
return "".join(" " if c in {"\\", "'"} else c for c in str(value))
def text_exists(self, id: str) -> bool:
results = self._client.query(f"SELECT id FROM {self._config.database}.{self._collection_name} WHERE id='{id}'")
results = self._client.query(
f"SELECT id FROM {self._qualified_table} WHERE id = %(id)s LIMIT 1",
parameters={"id": id},
)
return results.row_count > 0
def delete_by_ids(self, ids: list[str]):
if not ids:
return
placeholders, params = self._build_in_params("id", ids)
self._client.command(
f"DELETE FROM {self._config.database}.{self._collection_name} WHERE id IN {str(tuple(ids))}"
f"DELETE FROM {self._qualified_table} WHERE id IN ({placeholders})",
parameters=params,
)
def get_ids_by_metadata_field(self, key: str, value: str):
safe_key = self._validate_metadata_key(key)
rows = self._client.query(
f"SELECT DISTINCT id FROM {self._config.database}.{self._collection_name} WHERE metadata.{key}='{value}'"
f"SELECT DISTINCT id FROM {self._qualified_table} WHERE metadata.{safe_key} = %(value)s",
parameters={"value": value},
).result_rows
return [row[0] for row in rows]
def delete_by_metadata_field(self, key: str, value: str):
safe_key = self._validate_metadata_key(key)
self._client.command(
f"DELETE FROM {self._config.database}.{self._collection_name} WHERE metadata.{key}='{value}'"
f"DELETE FROM {self._qualified_table} WHERE metadata.{safe_key} = %(value)s",
parameters={"value": value},
)
def search_by_vector(self, query_vector: list[float], **kwargs: Any) -> list[Document]:
return self._search(f"distance(vector, {str(query_vector)})", self._vec_order, **kwargs)
return self._search(
"distance(vector, %(query_vector)s)",
self._vec_order,
parameters={"query_vector": query_vector},
**kwargs,
)
def search_by_full_text(self, query: str, **kwargs: Any) -> list[Document]:
return self._search(f"TextSearch('enable_nlq=false')(text, '{query}')", SortOrder.DESC, **kwargs)
return self._search(
"TextSearch('enable_nlq=false')(text, %(query)s)",
SortOrder.DESC,
parameters={"query": query},
**kwargs,
)
def _search(self, dist: str, order: SortOrder, **kwargs: Any) -> list[Document]:
@staticmethod
def _build_in_params(prefix: str, values: list[str]) -> tuple[str, dict[str, str]]:
params: dict[str, str] = {}
placeholders = []
for i, value in enumerate(values):
name = f"{prefix}_{i}"
placeholders.append(f"%({name})s")
params[name] = value
return ", ".join(placeholders), params
def _search(
self,
dist: str,
order: SortOrder,
parameters: dict[str, Any] | None = None,
**kwargs: Any,
) -> list[Document]:
top_k = kwargs.get("top_k", 4)
if not isinstance(top_k, int) or top_k <= 0:
raise ValueError("top_k must be a positive integer")
score_threshold = float(kwargs.get("score_threshold") or 0.0)
where_str = (
f"WHERE dist < {1 - score_threshold}"
if self._metric.upper() == "COSINE" and order == SortOrder.ASC and score_threshold > 0.0
else ""
)
where_clauses = []
if self._metric.upper() == "COSINE" and order == SortOrder.ASC and score_threshold > 0.0:
where_clauses.append(f"dist < {1 - score_threshold}")
document_ids_filter = kwargs.get("document_ids_filter")
query_params = dict(parameters or {})
if document_ids_filter:
document_ids = ", ".join(f"'{id}'" for id in document_ids_filter)
where_str = f"{where_str} AND metadata['document_id'] in ({document_ids})"
placeholders, params = self._build_in_params("document_id", document_ids_filter)
where_clauses.append(f"metadata['document_id'] IN ({placeholders})")
query_params.update(params)
where_str = f"WHERE {' AND '.join(where_clauses)}" if where_clauses else ""
sql = f"""
SELECT text, vector, metadata, {dist} as dist FROM {self._config.database}.{self._collection_name}
SELECT text, vector, metadata, {dist} as dist FROM {self._qualified_table}
{where_str} ORDER BY dist {order.value} LIMIT {top_k}
"""
try:
@@ -150,14 +199,14 @@ class MyScaleVector(BaseVector):
vector=r["vector"],
metadata=r["metadata"],
)
for r in self._client.query(sql).named_results()
for r in self._client.query(sql, parameters=query_params).named_results()
]
except Exception:
logger.exception("Vector search operation failed")
return []
def delete(self):
self._client.command(f"DROP TABLE IF EXISTS {self._config.database}.{self._collection_name}")
self._client.command(f"DROP TABLE IF EXISTS {self._qualified_table}")
class MyScaleVectorFactory(AbstractVectorFactory):

View File

@@ -9,7 +9,6 @@ from __future__ import annotations
import logging
import queue
import threading
from collections.abc import Generator
from typing import TYPE_CHECKING, cast, final
@@ -77,13 +76,10 @@ class GraphEngine:
config: GraphEngineConfig = _DEFAULT_CONFIG,
) -> None:
"""Initialize the graph engine with all subsystems and dependencies."""
# stop event
self._stop_event = threading.Event()
# Bind runtime state to current workflow context
self._graph = graph
self._graph_runtime_state = graph_runtime_state
self._graph_runtime_state.stop_event = self._stop_event
self._graph_runtime_state.configure(graph=cast("GraphProtocol", graph))
self._command_channel = command_channel
self._config = config
@@ -163,7 +159,6 @@ class GraphEngine:
layers=self._layers,
execution_context=execution_context,
config=self._config,
stop_event=self._stop_event,
)
# === Orchestration ===
@@ -194,7 +189,6 @@ class GraphEngine:
event_handler=self._event_handler_registry,
execution_coordinator=self._execution_coordinator,
event_emitter=self._event_manager,
stop_event=self._stop_event,
)
# === Validation ===
@@ -314,7 +308,6 @@ class GraphEngine:
def _start_execution(self, *, resume: bool = False) -> None:
"""Start execution subsystems."""
self._stop_event.clear()
paused_nodes: list[str] = []
deferred_nodes: list[str] = []
if resume:
@@ -348,7 +341,6 @@ class GraphEngine:
def _stop_execution(self) -> None:
"""Stop execution subsystems."""
self._stop_event.set()
self._dispatcher.stop()
self._worker_pool.stop()
# Don't mark complete here as the dispatcher already does it

View File

@@ -44,7 +44,6 @@ class Dispatcher:
event_queue: queue.Queue[GraphNodeEventBase],
event_handler: "EventHandler",
execution_coordinator: ExecutionCoordinator,
stop_event: threading.Event,
event_emitter: EventManager | None = None,
) -> None:
"""
@@ -62,7 +61,7 @@ class Dispatcher:
self._event_emitter = event_emitter
self._thread: threading.Thread | None = None
self._stop_event = stop_event
self._stop_event = threading.Event()
self._start_time: float | None = None
def start(self) -> None:
@@ -70,12 +69,14 @@ class Dispatcher:
if self._thread and self._thread.is_alive():
return
self._stop_event.clear()
self._start_time = time.time()
self._thread = threading.Thread(target=self._dispatcher_loop, name="GraphDispatcher", daemon=True)
self._thread.start()
def stop(self) -> None:
"""Stop the dispatcher thread."""
self._stop_event.set()
if self._thread and self._thread.is_alive():
self._thread.join(timeout=2.0)

View File

@@ -42,7 +42,6 @@ class Worker(threading.Thread):
event_queue: queue.Queue[GraphNodeEventBase],
graph: Graph,
layers: Sequence[GraphEngineLayer],
stop_event: threading.Event,
worker_id: int = 0,
execution_context: IExecutionContext | None = None,
) -> None:
@@ -63,16 +62,13 @@ class Worker(threading.Thread):
self._graph = graph
self._worker_id = worker_id
self._execution_context = execution_context
self._stop_event = stop_event
self._stop_event = threading.Event()
self._layers = layers if layers is not None else []
self._last_task_time = time.time()
def stop(self) -> None:
"""Worker is controlled via shared stop_event from GraphEngine.
This method is a no-op retained for backward compatibility.
"""
pass
"""Signal the worker to stop processing."""
self._stop_event.set()
@property
def is_idle(self) -> bool:

View File

@@ -37,7 +37,6 @@ class WorkerPool:
event_queue: queue.Queue[GraphNodeEventBase],
graph: Graph,
layers: list[GraphEngineLayer],
stop_event: threading.Event,
config: GraphEngineConfig,
execution_context: IExecutionContext | None = None,
) -> None:
@@ -64,7 +63,6 @@ class WorkerPool:
self._worker_counter = 0
self._lock = threading.RLock()
self._running = False
self._stop_event = stop_event
# No longer tracking worker states with callbacks to avoid lock contention
@@ -135,7 +133,6 @@ class WorkerPool:
layers=self._layers,
worker_id=worker_id,
execution_context=self._execution_context,
stop_event=self._stop_event,
)
worker.start()

View File

@@ -302,10 +302,6 @@ class Node(Generic[NodeDataT]):
"""
raise NotImplementedError
def _should_stop(self) -> bool:
"""Check if execution should be stopped."""
return self.graph_runtime_state.stop_event.is_set()
def run(self) -> Generator[GraphNodeEventBase, None, None]:
execution_id = self.ensure_execution_id()
self._start_at = naive_utc_now()
@@ -374,21 +370,6 @@ class Node(Generic[NodeDataT]):
yield event
else:
yield event
if self._should_stop():
error_message = "Execution cancelled"
yield NodeRunFailedEvent(
id=self.execution_id,
node_id=self._node_id,
node_type=self.node_type,
start_at=self._start_at,
node_run_result=NodeRunResult(
status=WorkflowNodeExecutionStatus.FAILED,
error=error_message,
),
error=error_message,
)
return
except Exception as e:
logger.exception("Node %s failed to run", self._node_id)
result = NodeRunResult(

View File

@@ -2,7 +2,6 @@ from __future__ import annotations
import importlib
import json
import threading
from collections.abc import Mapping, Sequence
from copy import deepcopy
from dataclasses import dataclass
@@ -219,8 +218,6 @@ class GraphRuntimeState:
self._pending_graph_node_states: dict[str, NodeState] | None = None
self._pending_graph_edge_states: dict[str, NodeState] | None = None
self.stop_event: threading.Event = threading.Event()
if graph is not None:
self.attach_graph(graph)

View File

@@ -116,7 +116,6 @@ dev = [
"dotenv-linter~=0.5.0",
"faker~=38.2.0",
"lxml-stubs~=0.5.1",
"ty>=0.0.14",
"basedpyright~=1.31.0",
"ruff~=0.14.0",
"pytest~=8.3.2",

View File

@@ -180,6 +180,14 @@ class ConversationService:
@classmethod
def delete(cls, app_model: App, conversation_id: str, user: Union[Account, EndUser] | None):
"""
Delete a conversation only if it belongs to the given user and app context.
Raises:
ConversationNotExistsError: When the conversation is not visible to the current user.
"""
conversation = cls.get_conversation(app_model, conversation_id, user)
try:
logger.info(
"Initiating conversation deletion for app_name %s, conversation_id: %s",
@@ -187,10 +195,10 @@ class ConversationService:
conversation_id,
)
db.session.query(Conversation).where(Conversation.id == conversation_id).delete(synchronize_session=False)
db.session.delete(conversation)
db.session.commit()
delete_conversation_related_data.delay(conversation_id)
delete_conversation_related_data.delay(conversation.id)
except Exception as e:
db.session.rollback()

View File

@@ -1,3 +1,4 @@
import json
import logging
import time
@@ -125,7 +126,7 @@ def document_indexing_sync_task(dataset_id: str, document_id: str):
data_source_info = document.data_source_info_dict
data_source_info["last_edited_time"] = last_edited_time
document.data_source_info = data_source_info
document.data_source_info = json.dumps(data_source_info)
document.indexing_status = "parsing"
document.processing_started_at = naive_utc_now()

View File

@@ -1034,3 +1034,34 @@ class TestConversationServiceExport:
# Step 2: Async cleanup task triggered
# The Celery task will handle cleanup of messages, annotations, etc.
mock_delete_task.delay.assert_called_once_with(conversation_id)
@patch("services.conversation_service.delete_conversation_related_data")
def test_delete_conversation_not_owned_by_account(self, mock_delete_task, db_session_with_containers):
"""
Test deletion is denied when conversation belongs to a different account.
"""
# Arrange
app_model, owner_account = ConversationServiceIntegrationTestDataFactory.create_app_and_account(
db_session_with_containers
)
_, other_account = ConversationServiceIntegrationTestDataFactory.create_app_and_account(
db_session_with_containers
)
conversation = ConversationServiceIntegrationTestDataFactory.create_conversation(
db_session_with_containers,
app_model,
owner_account,
)
# Act & Assert
with pytest.raises(ConversationNotExistsError):
ConversationService.delete(
app_model=app_model,
conversation_id=conversation.id,
user=other_account,
)
# Verify no deletion and no async cleanup trigger
not_deleted = db_session_with_containers.scalar(select(Conversation).where(Conversation.id == conversation.id))
assert not_deleted is not None
mock_delete_task.delay.assert_not_called()

View File

@@ -12,8 +12,6 @@ from unittest.mock import Mock, patch
from uuid import uuid4
import pytest
from psycopg2.extensions import register_adapter
from psycopg2.extras import Json
from core.indexing_runner import DocumentIsPausedError, IndexingRunner
from models import Account, Tenant, TenantAccountJoin, TenantAccountRole
@@ -21,12 +19,6 @@ from models.dataset import Dataset, Document, DocumentSegment
from tasks.document_indexing_sync_task import document_indexing_sync_task
@pytest.fixture(autouse=True)
def _register_dict_adapter_for_psycopg2():
"""Align test DB adapter behavior with dict payloads used in task update flow."""
register_adapter(dict, Json)
class DocumentIndexingSyncTaskTestDataFactory:
"""Create real DB entities for document indexing sync integration tests."""

View File

@@ -0,0 +1,32 @@
from unittest.mock import MagicMock, patch
from core.rag.datasource.vdb.myscale.myscale_vector import MyScaleConfig, MyScaleVector
@patch("core.rag.datasource.vdb.myscale.myscale_vector.get_client")
def test_search_by_vector_uses_parameterized_query(mock_get_client):
mock_client = MagicMock()
mock_get_client.return_value = mock_client
vector = MyScaleVector(
collection_name="test_collection",
config=MyScaleConfig(
host="localhost",
port=8123,
user="default",
password="",
database="dify",
fts_params="",
),
)
vector._search = MagicMock(return_value=[])
query_vector = [0.1, 0.2, 0.3]
vector.search_by_vector(query_vector, top_k=5)
vector._search.assert_called_once_with(
"distance(vector, %(query_vector)s)",
vector._vec_order,
parameters={"query_vector": query_vector},
top_k=5,
)

View File

@@ -3,7 +3,6 @@
from __future__ import annotations
import queue
import threading
from unittest import mock
from core.workflow.entities.pause_reason import SchedulingPause
@@ -37,7 +36,6 @@ def test_dispatcher_should_consume_remains_events_after_pause():
event_queue=event_queue,
event_handler=event_handler,
execution_coordinator=execution_coordinator,
stop_event=threading.Event(),
)
dispatcher._dispatcher_loop()
assert event_queue.empty()
@@ -98,7 +96,6 @@ def _run_dispatcher_for_event(event) -> int:
event_queue=event_queue,
event_handler=event_handler,
execution_coordinator=coordinator,
stop_event=threading.Event(),
)
dispatcher._dispatcher_loop()
@@ -184,7 +181,6 @@ def test_dispatcher_drain_event_queue():
event_queue=event_queue,
event_handler=event_handler,
execution_coordinator=coordinator,
stop_event=threading.Event(),
)
dispatcher._dispatcher_loop()

View File

@@ -1,5 +1,4 @@
import queue
import threading
from datetime import datetime
from core.workflow.enums import NodeType, WorkflowNodeExecutionStatus
@@ -65,7 +64,6 @@ def test_dispatcher_drains_events_when_paused() -> None:
event_handler=handler,
execution_coordinator=coordinator,
event_emitter=None,
stop_event=threading.Event(),
)
dispatcher._dispatcher_loop()

View File

@@ -1,550 +0,0 @@
"""
Unit tests for stop_event functionality in GraphEngine.
Tests the unified stop_event management by GraphEngine and its propagation
to WorkerPool, Worker, Dispatcher, and Nodes.
"""
import threading
import time
from unittest.mock import MagicMock, Mock, patch
from core.app.entities.app_invoke_entities import InvokeFrom
from core.workflow.entities.graph_init_params import GraphInitParams
from core.workflow.graph import Graph
from core.workflow.graph_engine import GraphEngine, GraphEngineConfig
from core.workflow.graph_engine.command_channels import InMemoryChannel
from core.workflow.graph_events import (
GraphRunStartedEvent,
GraphRunSucceededEvent,
NodeRunStartedEvent,
)
from core.workflow.nodes.answer.answer_node import AnswerNode
from core.workflow.nodes.start.start_node import StartNode
from core.workflow.runtime import GraphRuntimeState, VariablePool
from models.enums import UserFrom
class TestStopEventPropagation:
"""Test suite for stop_event propagation through GraphEngine components."""
def test_graph_engine_creates_stop_event(self):
"""Test that GraphEngine creates a stop_event on initialization."""
runtime_state = GraphRuntimeState(variable_pool=VariablePool(), start_at=time.perf_counter())
mock_graph = MagicMock(spec=Graph)
mock_graph.nodes = {}
mock_graph.edges = {}
mock_graph.root_node = MagicMock()
engine = GraphEngine(
workflow_id="test_workflow",
graph=mock_graph,
graph_runtime_state=runtime_state,
command_channel=InMemoryChannel(),
config=GraphEngineConfig(),
)
# Verify stop_event was created
assert engine._stop_event is not None
assert isinstance(engine._stop_event, threading.Event)
# Verify it was set in graph_runtime_state
assert runtime_state.stop_event is not None
assert runtime_state.stop_event is engine._stop_event
def test_stop_event_cleared_on_start(self):
"""Test that stop_event is cleared when execution starts."""
runtime_state = GraphRuntimeState(variable_pool=VariablePool(), start_at=time.perf_counter())
mock_graph = MagicMock(spec=Graph)
mock_graph.nodes = {}
mock_graph.edges = {}
mock_graph.root_node = MagicMock()
mock_graph.root_node.id = "start" # Set proper id
start_node = StartNode(
id="start",
config={"id": "start", "data": {"title": "start", "variables": []}},
graph_init_params=GraphInitParams(
tenant_id="test_tenant",
app_id="test_app",
workflow_id="test_workflow",
graph_config={},
user_id="test_user",
user_from=UserFrom.ACCOUNT,
invoke_from=InvokeFrom.DEBUGGER,
call_depth=0,
),
graph_runtime_state=runtime_state,
)
mock_graph.nodes["start"] = start_node
mock_graph.get_outgoing_edges = MagicMock(return_value=[])
mock_graph.get_incoming_edges = MagicMock(return_value=[])
engine = GraphEngine(
workflow_id="test_workflow",
graph=mock_graph,
graph_runtime_state=runtime_state,
command_channel=InMemoryChannel(),
config=GraphEngineConfig(),
)
# Set the stop_event before running
engine._stop_event.set()
assert engine._stop_event.is_set()
# Run the engine (should clear the stop_event)
events = list(engine.run())
# After running, stop_event should be set again (by _stop_execution)
# But during start it was cleared
assert any(isinstance(e, GraphRunStartedEvent) for e in events)
assert any(isinstance(e, GraphRunSucceededEvent) for e in events)
def test_stop_event_set_on_stop(self):
"""Test that stop_event is set when execution stops."""
runtime_state = GraphRuntimeState(variable_pool=VariablePool(), start_at=time.perf_counter())
mock_graph = MagicMock(spec=Graph)
mock_graph.nodes = {}
mock_graph.edges = {}
mock_graph.root_node = MagicMock()
mock_graph.root_node.id = "start" # Set proper id
start_node = StartNode(
id="start",
config={"id": "start", "data": {"title": "start", "variables": []}},
graph_init_params=GraphInitParams(
tenant_id="test_tenant",
app_id="test_app",
workflow_id="test_workflow",
graph_config={},
user_id="test_user",
user_from=UserFrom.ACCOUNT,
invoke_from=InvokeFrom.DEBUGGER,
call_depth=0,
),
graph_runtime_state=runtime_state,
)
mock_graph.nodes["start"] = start_node
mock_graph.get_outgoing_edges = MagicMock(return_value=[])
mock_graph.get_incoming_edges = MagicMock(return_value=[])
engine = GraphEngine(
workflow_id="test_workflow",
graph=mock_graph,
graph_runtime_state=runtime_state,
command_channel=InMemoryChannel(),
config=GraphEngineConfig(),
)
# Initially not set
assert not engine._stop_event.is_set()
# Run the engine
list(engine.run())
# After execution completes, stop_event should be set
assert engine._stop_event.is_set()
def test_stop_event_passed_to_worker_pool(self):
"""Test that stop_event is passed to WorkerPool."""
runtime_state = GraphRuntimeState(variable_pool=VariablePool(), start_at=time.perf_counter())
mock_graph = MagicMock(spec=Graph)
mock_graph.nodes = {}
mock_graph.edges = {}
mock_graph.root_node = MagicMock()
engine = GraphEngine(
workflow_id="test_workflow",
graph=mock_graph,
graph_runtime_state=runtime_state,
command_channel=InMemoryChannel(),
config=GraphEngineConfig(),
)
# Verify WorkerPool has the stop_event
assert engine._worker_pool._stop_event is not None
assert engine._worker_pool._stop_event is engine._stop_event
def test_stop_event_passed_to_dispatcher(self):
"""Test that stop_event is passed to Dispatcher."""
runtime_state = GraphRuntimeState(variable_pool=VariablePool(), start_at=time.perf_counter())
mock_graph = MagicMock(spec=Graph)
mock_graph.nodes = {}
mock_graph.edges = {}
mock_graph.root_node = MagicMock()
engine = GraphEngine(
workflow_id="test_workflow",
graph=mock_graph,
graph_runtime_state=runtime_state,
command_channel=InMemoryChannel(),
config=GraphEngineConfig(),
)
# Verify Dispatcher has the stop_event
assert engine._dispatcher._stop_event is not None
assert engine._dispatcher._stop_event is engine._stop_event
class TestNodeStopCheck:
"""Test suite for Node._should_stop() functionality."""
def test_node_should_stop_checks_runtime_state(self):
"""Test that Node._should_stop() checks GraphRuntimeState.stop_event."""
runtime_state = GraphRuntimeState(variable_pool=VariablePool(), start_at=time.perf_counter())
answer_node = AnswerNode(
id="answer",
config={"id": "answer", "data": {"title": "answer", "answer": "{{#start.result#}}"}},
graph_init_params=GraphInitParams(
tenant_id="test_tenant",
app_id="test_app",
workflow_id="test_workflow",
graph_config={},
user_id="test_user",
user_from=UserFrom.ACCOUNT,
invoke_from=InvokeFrom.DEBUGGER,
call_depth=0,
),
graph_runtime_state=runtime_state,
)
# Initially stop_event is not set
assert not answer_node._should_stop()
# Set the stop_event
runtime_state.stop_event.set()
# Now _should_stop should return True
assert answer_node._should_stop()
def test_node_run_checks_stop_event_between_yields(self):
"""Test that Node.run() checks stop_event between yielding events."""
runtime_state = GraphRuntimeState(variable_pool=VariablePool(), start_at=time.perf_counter())
# Create a simple node
answer_node = AnswerNode(
id="answer",
config={"id": "answer", "data": {"title": "answer", "answer": "hello"}},
graph_init_params=GraphInitParams(
tenant_id="test_tenant",
app_id="test_app",
workflow_id="test_workflow",
graph_config={},
user_id="test_user",
user_from=UserFrom.ACCOUNT,
invoke_from=InvokeFrom.DEBUGGER,
call_depth=0,
),
graph_runtime_state=runtime_state,
)
# Set stop_event BEFORE running the node
runtime_state.stop_event.set()
# Run the node - should yield start event then detect stop
# The node should check stop_event before processing
assert answer_node._should_stop(), "stop_event should be set"
# Run and collect events
events = list(answer_node.run())
# Since stop_event is set at the start, we should get:
# 1. NodeRunStartedEvent (always yielded first)
# 2. Either NodeRunFailedEvent (if detected early) or NodeRunSucceededEvent (if too fast)
assert len(events) >= 2
assert isinstance(events[0], NodeRunStartedEvent)
# Note: AnswerNode is very simple and might complete before stop check
# The important thing is that _should_stop() returns True when stop_event is set
assert answer_node._should_stop()
class TestStopEventIntegration:
"""Integration tests for stop_event in workflow execution."""
def test_simple_workflow_respects_stop_event(self):
"""Test that a simple workflow respects stop_event."""
runtime_state = GraphRuntimeState(variable_pool=VariablePool(), start_at=time.perf_counter())
mock_graph = MagicMock(spec=Graph)
mock_graph.nodes = {}
mock_graph.edges = {}
mock_graph.root_node = MagicMock()
mock_graph.root_node.id = "start"
# Create start and answer nodes
start_node = StartNode(
id="start",
config={"id": "start", "data": {"title": "start", "variables": []}},
graph_init_params=GraphInitParams(
tenant_id="test_tenant",
app_id="test_app",
workflow_id="test_workflow",
graph_config={},
user_id="test_user",
user_from=UserFrom.ACCOUNT,
invoke_from=InvokeFrom.DEBUGGER,
call_depth=0,
),
graph_runtime_state=runtime_state,
)
answer_node = AnswerNode(
id="answer",
config={"id": "answer", "data": {"title": "answer", "answer": "hello"}},
graph_init_params=GraphInitParams(
tenant_id="test_tenant",
app_id="test_app",
workflow_id="test_workflow",
graph_config={},
user_id="test_user",
user_from=UserFrom.ACCOUNT,
invoke_from=InvokeFrom.DEBUGGER,
call_depth=0,
),
graph_runtime_state=runtime_state,
)
mock_graph.nodes["start"] = start_node
mock_graph.nodes["answer"] = answer_node
mock_graph.get_outgoing_edges = MagicMock(return_value=[])
mock_graph.get_incoming_edges = MagicMock(return_value=[])
engine = GraphEngine(
workflow_id="test_workflow",
graph=mock_graph,
graph_runtime_state=runtime_state,
command_channel=InMemoryChannel(),
config=GraphEngineConfig(),
)
# Set stop_event before running
runtime_state.stop_event.set()
# Run the engine
events = list(engine.run())
# Should get started event but not succeeded (due to stop)
assert any(isinstance(e, GraphRunStartedEvent) for e in events)
# The workflow should still complete (start node runs quickly)
# but answer node might be cancelled depending on timing
def test_stop_event_with_concurrent_nodes(self):
"""Test stop_event behavior with multiple concurrent nodes."""
runtime_state = GraphRuntimeState(variable_pool=VariablePool(), start_at=time.perf_counter())
mock_graph = MagicMock(spec=Graph)
mock_graph.nodes = {}
mock_graph.edges = {}
mock_graph.root_node = MagicMock()
# Create multiple nodes
for i in range(3):
answer_node = AnswerNode(
id=f"answer_{i}",
config={"id": f"answer_{i}", "data": {"title": f"answer_{i}", "answer": f"test{i}"}},
graph_init_params=GraphInitParams(
tenant_id="test_tenant",
app_id="test_app",
workflow_id="test_workflow",
graph_config={},
user_id="test_user",
user_from=UserFrom.ACCOUNT,
invoke_from=InvokeFrom.DEBUGGER,
call_depth=0,
),
graph_runtime_state=runtime_state,
)
mock_graph.nodes[f"answer_{i}"] = answer_node
mock_graph.get_outgoing_edges = MagicMock(return_value=[])
mock_graph.get_incoming_edges = MagicMock(return_value=[])
engine = GraphEngine(
workflow_id="test_workflow",
graph=mock_graph,
graph_runtime_state=runtime_state,
command_channel=InMemoryChannel(),
config=GraphEngineConfig(),
)
# All nodes should share the same stop_event
for node in mock_graph.nodes.values():
assert node.graph_runtime_state.stop_event is runtime_state.stop_event
assert node.graph_runtime_state.stop_event is engine._stop_event
class TestStopEventTimeoutBehavior:
"""Test stop_event behavior with join timeouts."""
@patch("core.workflow.graph_engine.orchestration.dispatcher.threading.Thread", autospec=True)
def test_dispatcher_uses_shorter_timeout(self, mock_thread_cls: MagicMock):
"""Test that Dispatcher uses 2s timeout instead of 10s."""
runtime_state = GraphRuntimeState(variable_pool=VariablePool(), start_at=time.perf_counter())
mock_graph = MagicMock(spec=Graph)
mock_graph.nodes = {}
mock_graph.edges = {}
mock_graph.root_node = MagicMock()
engine = GraphEngine(
workflow_id="test_workflow",
graph=mock_graph,
graph_runtime_state=runtime_state,
command_channel=InMemoryChannel(),
config=GraphEngineConfig(),
)
dispatcher = engine._dispatcher
dispatcher.start() # This will create and start the mocked thread
mock_thread_instance = mock_thread_cls.return_value
mock_thread_instance.is_alive.return_value = True
dispatcher.stop()
mock_thread_instance.join.assert_called_once_with(timeout=2.0)
@patch("core.workflow.graph_engine.worker_management.worker_pool.Worker", autospec=True)
def test_worker_pool_uses_shorter_timeout(self, mock_worker_cls: MagicMock):
"""Test that WorkerPool uses 2s timeout instead of 10s."""
runtime_state = GraphRuntimeState(variable_pool=VariablePool(), start_at=time.perf_counter())
mock_graph = MagicMock(spec=Graph)
mock_graph.nodes = {}
mock_graph.edges = {}
mock_graph.root_node = MagicMock()
engine = GraphEngine(
workflow_id="test_workflow",
graph=mock_graph,
graph_runtime_state=runtime_state,
command_channel=InMemoryChannel(),
config=GraphEngineConfig(),
)
worker_pool = engine._worker_pool
worker_pool.start(initial_count=1) # Start with one worker
mock_worker_instance = mock_worker_cls.return_value
mock_worker_instance.is_alive.return_value = True
worker_pool.stop()
mock_worker_instance.join.assert_called_once_with(timeout=2.0)
class TestStopEventResumeBehavior:
"""Test stop_event behavior during workflow resume."""
def test_stop_event_cleared_on_resume(self):
"""Test that stop_event is cleared when resuming a paused workflow."""
runtime_state = GraphRuntimeState(variable_pool=VariablePool(), start_at=time.perf_counter())
mock_graph = MagicMock(spec=Graph)
mock_graph.nodes = {}
mock_graph.edges = {}
mock_graph.root_node = MagicMock()
mock_graph.root_node.id = "start" # Set proper id
start_node = StartNode(
id="start",
config={"id": "start", "data": {"title": "start", "variables": []}},
graph_init_params=GraphInitParams(
tenant_id="test_tenant",
app_id="test_app",
workflow_id="test_workflow",
graph_config={},
user_id="test_user",
user_from=UserFrom.ACCOUNT,
invoke_from=InvokeFrom.DEBUGGER,
call_depth=0,
),
graph_runtime_state=runtime_state,
)
mock_graph.nodes["start"] = start_node
mock_graph.get_outgoing_edges = MagicMock(return_value=[])
mock_graph.get_incoming_edges = MagicMock(return_value=[])
engine = GraphEngine(
workflow_id="test_workflow",
graph=mock_graph,
graph_runtime_state=runtime_state,
command_channel=InMemoryChannel(),
config=GraphEngineConfig(),
)
# Simulate a previous execution that set stop_event
engine._stop_event.set()
assert engine._stop_event.is_set()
# Run the engine (should clear stop_event in _start_execution)
events = list(engine.run())
# Execution should complete successfully
assert any(isinstance(e, GraphRunStartedEvent) for e in events)
assert any(isinstance(e, GraphRunSucceededEvent) for e in events)
class TestWorkerStopBehavior:
"""Test Worker behavior with shared stop_event."""
def test_worker_uses_shared_stop_event(self):
"""Test that Worker uses shared stop_event from GraphEngine."""
runtime_state = GraphRuntimeState(variable_pool=VariablePool(), start_at=time.perf_counter())
mock_graph = MagicMock(spec=Graph)
mock_graph.nodes = {}
mock_graph.edges = {}
mock_graph.root_node = MagicMock()
engine = GraphEngine(
workflow_id="test_workflow",
graph=mock_graph,
graph_runtime_state=runtime_state,
command_channel=InMemoryChannel(),
config=GraphEngineConfig(),
)
# Get the worker pool and check workers
worker_pool = engine._worker_pool
# Start the worker pool to create workers
worker_pool.start()
# Check that at least one worker was created
assert len(worker_pool._workers) > 0
# Verify workers use the shared stop_event
for worker in worker_pool._workers:
assert worker._stop_event is engine._stop_event
# Clean up
worker_pool.stop()
def test_worker_stop_is_noop(self):
"""Test that Worker.stop() is now a no-op."""
runtime_state = GraphRuntimeState(variable_pool=VariablePool(), start_at=time.perf_counter())
# Create a mock worker
from core.workflow.graph_engine.ready_queue import InMemoryReadyQueue
from core.workflow.graph_engine.worker import Worker
ready_queue = InMemoryReadyQueue()
event_queue = MagicMock()
# Create a proper mock graph with real dict
mock_graph = Mock(spec=Graph)
mock_graph.nodes = {} # Use real dict
stop_event = threading.Event()
worker = Worker(
ready_queue=ready_queue,
event_queue=event_queue,
graph=mock_graph,
layers=[],
stop_event=stop_event,
)
# Calling stop() should do nothing (no-op)
# and should NOT set the stop_event
worker.stop()
assert not stop_event.is_set()

View File

@@ -5,6 +5,7 @@ These tests intentionally stay in unit scope because they validate call argument
for external collaborators rather than SQL-backed state transitions.
"""
import json
import uuid
from unittest.mock import MagicMock, Mock, patch
@@ -196,3 +197,78 @@ class TestDocumentIndexingSyncTaskCollaboratorParams:
provider="notion_datasource",
plugin_id="langgenius/notion_datasource",
)
class TestDataSourceInfoSerialization:
"""Regression test: data_source_info must be written as a JSON string, not a raw dict.
See https://github.com/langgenius/dify/issues/32705
psycopg2 raises ``ProgrammingError: can't adapt type 'dict'`` when a Python
dict is passed directly to a text/LongText column.
"""
def test_data_source_info_serialized_as_json_string(
self,
mock_document,
mock_dataset,
dataset_id,
document_id,
):
"""data_source_info must be serialized with json.dumps before DB write."""
with (
patch("tasks.document_indexing_sync_task.session_factory") as mock_session_factory,
patch("tasks.document_indexing_sync_task.DatasourceProviderService") as mock_service_class,
patch("tasks.document_indexing_sync_task.NotionExtractor") as mock_extractor_class,
patch("tasks.document_indexing_sync_task.IndexProcessorFactory") as mock_ipf,
patch("tasks.document_indexing_sync_task.IndexingRunner") as mock_runner_class,
):
# External collaborators
mock_service = MagicMock()
mock_service.get_datasource_credentials.return_value = {"integration_secret": "token"}
mock_service_class.return_value = mock_service
mock_extractor = MagicMock()
# Return a *different* timestamp so the task enters the sync/update branch
mock_extractor.get_notion_last_edited_time.return_value = "2024-02-01T00:00:00Z"
mock_extractor_class.return_value = mock_extractor
mock_ip = MagicMock()
mock_ipf.return_value.init_index_processor.return_value = mock_ip
mock_runner = MagicMock()
mock_runner_class.return_value = mock_runner
# DB session mock — shared across all ``session_factory.create_session()`` calls
session = MagicMock()
session.scalars.return_value.all.return_value = []
# .where() path: session 1 reads document + dataset, session 2 reads dataset
session.query.return_value.where.return_value.first.side_effect = [
mock_document,
mock_dataset,
mock_dataset,
]
# .filter_by() path: session 3 (update), session 4 (indexing)
session.query.return_value.filter_by.return_value.first.side_effect = [
mock_document,
mock_document,
]
begin_cm = MagicMock()
begin_cm.__enter__.return_value = session
begin_cm.__exit__.return_value = False
session.begin.return_value = begin_cm
session_cm = MagicMock()
session_cm.__enter__.return_value = session
session_cm.__exit__.return_value = False
mock_session_factory.create_session.return_value = session_cm
# Act
document_indexing_sync_task(dataset_id, document_id)
# Assert: data_source_info must be a JSON *string*, not a dict
assert isinstance(mock_document.data_source_info, str), (
f"data_source_info should be a JSON string, got {type(mock_document.data_source_info).__name__}"
)
parsed = json.loads(mock_document.data_source_info)
assert parsed["last_edited_time"] == "2024-02-01T00:00:00Z"

View File

@@ -1,50 +0,0 @@
[src]
exclude = [
# deps groups (A1/A2/B/C/D/E)
# B: app runner + prompt
"core/prompt",
"core/app/apps/base_app_runner.py",
"core/app/apps/workflow_app_runner.py",
"core/agent",
"core/plugin",
# C: services/controllers/fields/libs
"services",
"controllers/inner_api",
"controllers/console/app",
"controllers/console/explore",
"controllers/console/datasets",
"controllers/console/workspace",
"controllers/service_api/wraps.py",
"fields/conversation_fields.py",
"libs/external_api.py",
# D: observability + integrations
"core/ops",
"extensions",
# E: vector DB integrations
"core/rag/datasource/vdb",
# non-producition or generated code
"migrations",
"tests",
# targeted ignores for current type-check errors
# TODO(QuantumGhost): suppress type errors in HITL related code.
# fix the type error later
"configs/middleware/cache/redis_pubsub_config.py",
"extensions/ext_redis.py",
"models/execution_extra_content.py",
"tasks/workflow_execution_tasks.py",
"core/workflow/nodes/base/node.py",
"services/human_input_delivery_test_service.py",
"core/app/apps/advanced_chat/app_generator.py",
"controllers/console/human_input_form.py",
"controllers/console/app/workflow_run.py",
"repositories/sqlalchemy_api_workflow_node_execution_repository.py",
"extensions/logstore/repositories/logstore_api_workflow_run_repository.py",
"controllers/web/workflow_events.py",
"tasks/app_generate/workflow_execute_task.py",
]
[rules]
deprecated = "ignore"
unused-ignore-comment = "ignore"
# possibly-missing-attribute = "ignore"

26
api/uv.lock generated
View File

@@ -1483,7 +1483,6 @@ dev = [
{ name = "scipy-stubs" },
{ name = "sseclient-py" },
{ name = "testcontainers" },
{ name = "ty" },
{ name = "types-aiofiles" },
{ name = "types-beautifulsoup4" },
{ name = "types-cachetools" },
@@ -1684,7 +1683,6 @@ dev = [
{ name = "scipy-stubs", specifier = ">=1.15.3.0" },
{ name = "sseclient-py", specifier = ">=1.8.0" },
{ name = "testcontainers", specifier = "~=4.13.2" },
{ name = "ty", specifier = ">=0.0.14" },
{ name = "types-aiofiles", specifier = "~=24.1.0" },
{ name = "types-beautifulsoup4", specifier = "~=4.12.0" },
{ name = "types-cachetools", specifier = "~=5.5.0" },
@@ -6278,30 +6276,6 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/70/26/2591b48412bde75e33bfd292034103ffe41743cacd03120e3242516cd143/transformers-4.56.2-py3-none-any.whl", hash = "sha256:79c03d0e85b26cb573c109ff9eafa96f3c8d4febfd8a0774e8bba32702dd6dde", size = 11608055, upload-time = "2025-09-19T15:16:23.736Z" },
]
[[package]]
name = "ty"
version = "0.0.14"
source = { registry = "https://pypi.org/simple" }
sdist = { url = "https://files.pythonhosted.org/packages/af/57/22c3d6bf95c2229120c49ffc2f0da8d9e8823755a1c3194da56e51f1cc31/ty-0.0.14.tar.gz", hash = "sha256:a691010565f59dd7f15cf324cdcd1d9065e010c77a04f887e1ea070ba34a7de2", size = 5036573, upload-time = "2026-01-27T00:57:31.427Z" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/99/cb/cc6d1d8de59beb17a41f9a614585f884ec2d95450306c173b3b7cc090d2e/ty-0.0.14-py3-none-linux_armv6l.whl", hash = "sha256:32cf2a7596e693094621d3ae568d7ee16707dce28c34d1762947874060fdddaa", size = 10034228, upload-time = "2026-01-27T00:57:53.133Z" },
{ url = "https://files.pythonhosted.org/packages/f3/96/dd42816a2075a8f31542296ae687483a8d047f86a6538dfba573223eaf9a/ty-0.0.14-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:f971bf9805f49ce8c0968ad53e29624d80b970b9eb597b7cbaba25d8a18ce9a2", size = 9939162, upload-time = "2026-01-27T00:57:43.857Z" },
{ url = "https://files.pythonhosted.org/packages/ff/b4/73c4859004e0f0a9eead9ecb67021438b2e8e5fdd8d03e7f5aca77623992/ty-0.0.14-py3-none-macosx_11_0_arm64.whl", hash = "sha256:45448b9e4806423523268bc15e9208c4f3f2ead7c344f615549d2e2354d6e924", size = 9418661, upload-time = "2026-01-27T00:58:03.411Z" },
{ url = "https://files.pythonhosted.org/packages/58/35/839c4551b94613db4afa20ee555dd4f33bfa7352d5da74c5fa416ffa0fd2/ty-0.0.14-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ee94a9b747ff40114085206bdb3205a631ef19a4d3fb89e302a88754cbbae54c", size = 9837872, upload-time = "2026-01-27T00:57:23.718Z" },
{ url = "https://files.pythonhosted.org/packages/41/2b/bbecf7e2faa20c04bebd35fc478668953ca50ee5847ce23e08acf20ea119/ty-0.0.14-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:6756715a3c33182e9ab8ffca2bb314d3c99b9c410b171736e145773ee0ae41c3", size = 9848819, upload-time = "2026-01-27T00:57:58.501Z" },
{ url = "https://files.pythonhosted.org/packages/be/60/3c0ba0f19c0f647ad9d2b5b5ac68c0f0b4dc899001bd53b3a7537fb247a2/ty-0.0.14-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:89d0038a2f698ba8b6fec5cf216a4e44e2f95e4a5095a8c0f57fe549f87087c2", size = 10324371, upload-time = "2026-01-27T00:57:29.291Z" },
{ url = "https://files.pythonhosted.org/packages/24/32/99d0a0b37d0397b0a989ffc2682493286aa3bc252b24004a6714368c2c3d/ty-0.0.14-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:2c64a83a2d669b77f50a4957039ca1450626fb474619f18f6f8a3eb885bf7544", size = 10865898, upload-time = "2026-01-27T00:57:33.542Z" },
{ url = "https://files.pythonhosted.org/packages/1a/88/30b583a9e0311bb474269cfa91db53350557ebec09002bfc3fb3fc364e8c/ty-0.0.14-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:242488bfb547ef080199f6fd81369ab9cb638a778bb161511d091ffd49c12129", size = 10555777, upload-time = "2026-01-27T00:58:05.853Z" },
{ url = "https://files.pythonhosted.org/packages/cd/a2/cb53fb6325dcf3d40f2b1d0457a25d55bfbae633c8e337bde8ec01a190eb/ty-0.0.14-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4790c3866f6c83a4f424fc7d09ebdb225c1f1131647ba8bdc6fcdc28f09ed0ff", size = 10412913, upload-time = "2026-01-27T00:57:38.834Z" },
{ url = "https://files.pythonhosted.org/packages/42/8f/f2f5202d725ed1e6a4e5ffaa32b190a1fe70c0b1a2503d38515da4130b4c/ty-0.0.14-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:950f320437f96d4ea9a2332bbfb5b68f1c1acd269ebfa4c09b6970cc1565bd9d", size = 9837608, upload-time = "2026-01-27T00:57:55.898Z" },
{ url = "https://files.pythonhosted.org/packages/f7/ba/59a2a0521640c489dafa2c546ae1f8465f92956fede18660653cce73b4c5/ty-0.0.14-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:4a0ec3ee70d83887f86925bbc1c56f4628bd58a0f47f6f32ddfe04e1f05466df", size = 9884324, upload-time = "2026-01-27T00:57:46.786Z" },
{ url = "https://files.pythonhosted.org/packages/03/95/8d2a49880f47b638743212f011088552ecc454dd7a665ddcbdabea25772a/ty-0.0.14-py3-none-musllinux_1_2_i686.whl", hash = "sha256:a1a4e6b6da0c58b34415955279eff754d6206b35af56a18bb70eb519d8d139ef", size = 10033537, upload-time = "2026-01-27T00:58:01.149Z" },
{ url = "https://files.pythonhosted.org/packages/e9/40/4523b36f2ce69f92ccf783855a9e0ebbbd0f0bb5cdce6211ee1737159ed3/ty-0.0.14-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:dc04384e874c5de4c5d743369c277c8aa73d1edea3c7fc646b2064b637db4db3", size = 10495910, upload-time = "2026-01-27T00:57:26.691Z" },
{ url = "https://files.pythonhosted.org/packages/08/d5/655beb51224d1bfd4f9ddc0bb209659bfe71ff141bcf05c418ab670698f0/ty-0.0.14-py3-none-win32.whl", hash = "sha256:b20e22cf54c66b3e37e87377635da412d9a552c9bf4ad9fc449fed8b2e19dad2", size = 9507626, upload-time = "2026-01-27T00:57:41.43Z" },
{ url = "https://files.pythonhosted.org/packages/b6/d9/c569c9961760e20e0a4bc008eeb1415754564304fd53997a371b7cf3f864/ty-0.0.14-py3-none-win_amd64.whl", hash = "sha256:e312ff9475522d1a33186657fe74d1ec98e4a13e016d66f5758a452c90ff6409", size = 10437980, upload-time = "2026-01-27T00:57:36.422Z" },
{ url = "https://files.pythonhosted.org/packages/ad/0c/186829654f5bfd9a028f6648e9caeb11271960a61de97484627d24443f91/ty-0.0.14-py3-none-win_arm64.whl", hash = "sha256:b6facdbe9b740cb2c15293a1d178e22ffc600653646452632541d01c36d5e378", size = 9885831, upload-time = "2026-01-27T00:57:49.747Z" },
]
[[package]]
name = "typer"
version = "0.20.0"

View File

@@ -149,7 +149,6 @@ services:
MARKETPLACE_URL: ${MARKETPLACE_URL:-https://marketplace.dify.ai}
TOP_K_MAX_VALUE: ${TOP_K_MAX_VALUE:-}
INDEXING_MAX_SEGMENTATION_TOKENS_LENGTH: ${INDEXING_MAX_SEGMENTATION_TOKENS_LENGTH:-}
PM2_INSTANCES: ${PM2_INSTANCES:-2}
LOOP_NODE_MAX_COUNT: ${LOOP_NODE_MAX_COUNT:-100}
MAX_TOOLS_NUM: ${MAX_TOOLS_NUM:-10}
MAX_PARALLEL_LIMIT: ${MAX_PARALLEL_LIMIT:-10}

View File

@@ -844,7 +844,6 @@ services:
MARKETPLACE_URL: ${MARKETPLACE_URL:-https://marketplace.dify.ai}
TOP_K_MAX_VALUE: ${TOP_K_MAX_VALUE:-}
INDEXING_MAX_SEGMENTATION_TOKENS_LENGTH: ${INDEXING_MAX_SEGMENTATION_TOKENS_LENGTH:-}
PM2_INSTANCES: ${PM2_INSTANCES:-2}
LOOP_NODE_MAX_COUNT: ${LOOP_NODE_MAX_COUNT:-100}
MAX_TOOLS_NUM: ${MAX_TOOLS_NUM:-10}
MAX_PARALLEL_LIMIT: ${MAX_PARALLEL_LIMIT:-10}

View File

@@ -50,24 +50,18 @@ ENV MARKETPLACE_API_URL=https://marketplace.dify.ai
ENV MARKETPLACE_URL=https://marketplace.dify.ai
ENV PORT=3000
ENV NEXT_TELEMETRY_DISABLED=1
ENV PM2_INSTANCES=2
# set timezone
ENV TZ=UTC
RUN ln -s /usr/share/zoneinfo/${TZ} /etc/localtime \
&& echo ${TZ} > /etc/timezone
# global runtime packages
RUN pnpm add -g pm2
# Create non-root user
ARG dify_uid=1001
RUN addgroup -S -g ${dify_uid} dify && \
adduser -S -u ${dify_uid} -G dify -s /bin/ash -h /home/dify dify && \
mkdir /app && \
mkdir /.pm2 && \
chown -R dify:dify /app /.pm2
chown -R dify:dify /app
WORKDIR /app/web

View File

@@ -89,8 +89,6 @@ If you want to customize the host and port:
pnpm run start --port=3001 --host=0.0.0.0
```
If you want to customize the number of instances launched by PM2, you can configure `PM2_INSTANCES` in `docker-compose.yaml` or `Dockerfile`.
## Storybook
This project uses [Storybook](https://storybook.js.org/) for UI component development.

View File

@@ -43,4 +43,4 @@ export NEXT_PUBLIC_MAX_PARALLEL_LIMIT=${MAX_PARALLEL_LIMIT}
export NEXT_PUBLIC_MAX_ITERATIONS_NUM=${MAX_ITERATIONS_NUM}
export NEXT_PUBLIC_MAX_TREE_DEPTH=${MAX_TREE_DEPTH}
pm2 start /app/web/server.js --name dify-web --cwd /app/web -i ${PM2_INSTANCES} --no-daemon
exec node /app/web/server.js

View File

@@ -1,11 +0,0 @@
{
"apps": [
{
"name": "dify-web",
"script": "/app/web/server.js",
"cwd": "/app/web",
"exec_mode": "cluster",
"instances": 2
}
]
}