admin/dify
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

refactor:Decouple Domain Models from Direct Database Access (#27316)

Browse Source 
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
This commit is contained in:
heyszt
2025-10-28 09:59:30 +08:00
committed by GitHub
parent 341b3ae7c9
commit 543c5236e7
7 changed files with 595 additions and 264 deletions
Download Patch File Download Diff File Expand all files Collapse all files

154
api/repositories/api_workflow_run_repository.py
View File

@@ -28,7 +28,7 @@ Example:
runs = repo.get_paginated_workflow_runs(
tenant_id="tenant-123",
app_id="app-456",
triggered_from="debugging",
triggered_from=WorkflowRunTriggeredFrom.DEBUGGING,
limit=20
)
```
@@ -40,7 +40,14 @@ from typing import Protocol
from core.workflow.repositories.workflow_execution_repository import WorkflowExecutionRepository
from libs.infinite_scroll_pagination import InfiniteScrollPagination
from models.enums import WorkflowRunTriggeredFrom
from models.workflow import WorkflowRun
from repositories.types import (
AverageInteractionStats,
DailyRunsStats,
DailyTerminalsStats,
DailyTokenCostStats,
)
class APIWorkflowRunRepository(WorkflowExecutionRepository, Protocol):
@@ -56,7 +63,7 @@ class APIWorkflowRunRepository(WorkflowExecutionRepository, Protocol):
self,
tenant_id: str,
app_id: str,
triggered_from: str,
triggered_from: WorkflowRunTriggeredFrom | Sequence[WorkflowRunTriggeredFrom],
limit: int = 20,
last_id: str | None = None,
status: str | None = None,
@@ -71,7 +78,7 @@ class APIWorkflowRunRepository(WorkflowExecutionRepository, Protocol):
Args:
tenant_id: Tenant identifier for multi-tenant isolation
app_id: Application identifier
triggered_from: Filter by trigger source (e.g., "debugging", "app-run")
triggered_from: Filter by trigger source(s) (e.g., "debugging", "app-run", or list of values)
limit: Maximum number of records to return (default: 20)
last_id: Cursor for pagination - ID of the last record from previous page
status: Optional filter by status (e.g., "running", "succeeded", "failed")
@@ -109,6 +116,31 @@ class APIWorkflowRunRepository(WorkflowExecutionRepository, Protocol):
"""
...
def get_workflow_run_by_id_without_tenant(
self,
run_id: str,
) -> WorkflowRun | None:
"""
Get a specific workflow run by ID without tenant/app context.
Retrieves a single workflow run using only the run ID, without
requiring tenant_id or app_id. This method is intended for internal
system operations like tracing and monitoring where the tenant context
is not available upfront.
Args:
run_id: Workflow run identifier
Returns:
WorkflowRun object if found, None otherwise
Note:
This method bypasses tenant isolation checks and should only be used
in trusted system contexts like ops trace collection. For user-facing
operations, use get_workflow_run_by_id() with proper tenant isolation.
"""
...
def get_workflow_runs_count(
self,
tenant_id: str,
@@ -218,3 +250,119 @@ class APIWorkflowRunRepository(WorkflowExecutionRepository, Protocol):
and ensure proper data retention policies are followed.
"""
...
def get_daily_runs_statistics(
self,
tenant_id: str,
app_id: str,
triggered_from: str,
start_date: datetime | None = None,
end_date: datetime | None = None,
timezone: str = "UTC",
) -> list[DailyRunsStats]:
"""
Get daily runs statistics.
Retrieves daily workflow runs count grouped by date for a specific app
and trigger source. Used for workflow statistics dashboard.
Args:
tenant_id: Tenant identifier for multi-tenant isolation
app_id: Application identifier
triggered_from: Filter by trigger source (e.g., "app-run")
start_date: Optional start date filter
end_date: Optional end date filter
timezone: Timezone for date grouping (default: "UTC")
Returns:
List of dictionaries containing date and runs count:
[{"date": "2024-01-01", "runs": 10}, ...]
"""
...
def get_daily_terminals_statistics(
self,
tenant_id: str,
app_id: str,
triggered_from: str,
start_date: datetime | None = None,
end_date: datetime | None = None,
timezone: str = "UTC",
) -> list[DailyTerminalsStats]:
"""
Get daily terminals statistics.
Retrieves daily unique terminal count grouped by date for a specific app
and trigger source. Used for workflow statistics dashboard.
Args:
tenant_id: Tenant identifier for multi-tenant isolation
app_id: Application identifier
triggered_from: Filter by trigger source (e.g., "app-run")
start_date: Optional start date filter
end_date: Optional end date filter
timezone: Timezone for date grouping (default: "UTC")
Returns:
List of dictionaries containing date and terminal count:
[{"date": "2024-01-01", "terminal_count": 5}, ...]
"""
...
def get_daily_token_cost_statistics(
self,
tenant_id: str,
app_id: str,
triggered_from: str,
start_date: datetime | None = None,
end_date: datetime | None = None,
timezone: str = "UTC",
) -> list[DailyTokenCostStats]:
"""
Get daily token cost statistics.
Retrieves daily total token count grouped by date for a specific app
and trigger source. Used for workflow statistics dashboard.
Args:
tenant_id: Tenant identifier for multi-tenant isolation
app_id: Application identifier
triggered_from: Filter by trigger source (e.g., "app-run")
start_date: Optional start date filter
end_date: Optional end date filter
timezone: Timezone for date grouping (default: "UTC")
Returns:
List of dictionaries containing date and token count:
[{"date": "2024-01-01", "token_count": 1000}, ...]
"""
...
def get_average_app_interaction_statistics(
self,
tenant_id: str,
app_id: str,
triggered_from: str,
start_date: datetime | None = None,
end_date: datetime | None = None,
timezone: str = "UTC",
) -> list[AverageInteractionStats]:
"""
Get average app interaction statistics.
Retrieves daily average interactions per user grouped by date for a specific app
and trigger source. Used for workflow statistics dashboard.
Args:
tenant_id: Tenant identifier for multi-tenant isolation
app_id: Application identifier
triggered_from: Filter by trigger source (e.g., "app-run")
start_date: Optional start date filter
end_date: Optional end date filter
timezone: Timezone for date grouping (default: "UTC")
Returns:
List of dictionaries containing date and average interactions:
[{"date": "2024-01-01", "interactions": 2.5}, ...]
"""
...

241
api/repositories/sqlalchemy_api_workflow_run_repository.py
View File

@@ -22,16 +22,25 @@ Implementation Notes:
import logging
from collections.abc import Sequence
from datetime import datetime
from typing import cast
from decimal import Decimal
from typing import Any, cast
import sqlalchemy as sa
from sqlalchemy import delete, func, select
from sqlalchemy.engine import CursorResult
from sqlalchemy.orm import Session, sessionmaker
from libs.infinite_scroll_pagination import InfiniteScrollPagination
from libs.time_parser import get_time_threshold
from models.enums import WorkflowRunTriggeredFrom
from models.workflow import WorkflowRun
from repositories.api_workflow_run_repository import APIWorkflowRunRepository
from repositories.types import (
AverageInteractionStats,
DailyRunsStats,
DailyTerminalsStats,
DailyTokenCostStats,
)
logger = logging.getLogger(__name__)
@@ -61,7 +70,7 @@ class DifyAPISQLAlchemyWorkflowRunRepository(APIWorkflowRunRepository):
self,
tenant_id: str,
app_id: str,
triggered_from: str,
triggered_from: WorkflowRunTriggeredFrom | Sequence[WorkflowRunTriggeredFrom],
limit: int = 20,
last_id: str | None = None,
status: str | None = None,
@@ -78,9 +87,14 @@ class DifyAPISQLAlchemyWorkflowRunRepository(APIWorkflowRunRepository):
base_stmt = select(WorkflowRun).where(
WorkflowRun.tenant_id == tenant_id,
WorkflowRun.app_id == app_id,
WorkflowRun.triggered_from == triggered_from,
)
# Handle triggered_from values
if isinstance(triggered_from, WorkflowRunTriggeredFrom):
triggered_from = [triggered_from]
if triggered_from:
base_stmt = base_stmt.where(WorkflowRun.triggered_from.in_(triggered_from))
# Add optional status filter
if status:
base_stmt = base_stmt.where(WorkflowRun.status == status)
@@ -126,6 +140,17 @@ class DifyAPISQLAlchemyWorkflowRunRepository(APIWorkflowRunRepository):
)
return session.scalar(stmt)
def get_workflow_run_by_id_without_tenant(
self,
run_id: str,
) -> WorkflowRun | None:
"""
Get a specific workflow run by ID without tenant/app context.
"""
with self._session_maker() as session:
stmt = select(WorkflowRun).where(WorkflowRun.id == run_id)
return session.scalar(stmt)
def get_workflow_runs_count(
self,
tenant_id: str,
@@ -275,3 +300,213 @@ class DifyAPISQLAlchemyWorkflowRunRepository(APIWorkflowRunRepository):
logger.info("Total deleted %s workflow runs for app %s", total_deleted, app_id)
return total_deleted
def get_daily_runs_statistics(
self,
tenant_id: str,
app_id: str,
triggered_from: str,
start_date: datetime | None = None,
end_date: datetime | None = None,
timezone: str = "UTC",
) -> list[DailyRunsStats]:
"""
Get daily runs statistics using raw SQL for optimal performance.
"""
sql_query = """SELECT
DATE(DATE_TRUNC('day', created_at AT TIME ZONE 'UTC' AT TIME ZONE :tz )) AS date,
COUNT(id) AS runs
FROM
workflow_runs
WHERE
tenant_id = :tenant_id
AND app_id = :app_id
AND triggered_from = :triggered_from"""
arg_dict: dict[str, Any] = {
"tz": timezone,
"tenant_id": tenant_id,
"app_id": app_id,
"triggered_from": triggered_from,
}
if start_date:
sql_query += " AND created_at >= :start_date"
arg_dict["start_date"] = start_date
if end_date:
sql_query += " AND created_at < :end_date"
arg_dict["end_date"] = end_date
sql_query += " GROUP BY date ORDER BY date"
response_data = []
with self._session_maker() as session:
rs = session.execute(sa.text(sql_query), arg_dict)
for row in rs:
response_data.append({"date": str(row.date), "runs": row.runs})
return cast(list[DailyRunsStats], response_data)
def get_daily_terminals_statistics(
self,
tenant_id: str,
app_id: str,
triggered_from: str,
start_date: datetime | None = None,
end_date: datetime | None = None,
timezone: str = "UTC",
) -> list[DailyTerminalsStats]:
"""
Get daily terminals statistics using raw SQL for optimal performance.
"""
sql_query = """SELECT
DATE(DATE_TRUNC('day', created_at AT TIME ZONE 'UTC' AT TIME ZONE :tz )) AS date,
COUNT(DISTINCT created_by) AS terminal_count
FROM
workflow_runs
WHERE
tenant_id = :tenant_id
AND app_id = :app_id
AND triggered_from = :triggered_from"""
arg_dict: dict[str, Any] = {
"tz": timezone,
"tenant_id": tenant_id,
"app_id": app_id,
"triggered_from": triggered_from,
}
if start_date:
sql_query += " AND created_at >= :start_date"
arg_dict["start_date"] = start_date
if end_date:
sql_query += " AND created_at < :end_date"
arg_dict["end_date"] = end_date
sql_query += " GROUP BY date ORDER BY date"
response_data = []
with self._session_maker() as session:
rs = session.execute(sa.text(sql_query), arg_dict)
for row in rs:
response_data.append({"date": str(row.date), "terminal_count": row.terminal_count})
return cast(list[DailyTerminalsStats], response_data)
def get_daily_token_cost_statistics(
self,
tenant_id: str,
app_id: str,
triggered_from: str,
start_date: datetime | None = None,
end_date: datetime | None = None,
timezone: str = "UTC",
) -> list[DailyTokenCostStats]:
"""
Get daily token cost statistics using raw SQL for optimal performance.
"""
sql_query = """SELECT
DATE(DATE_TRUNC('day', created_at AT TIME ZONE 'UTC' AT TIME ZONE :tz )) AS date,
SUM(total_tokens) AS token_count
FROM
workflow_runs
WHERE
tenant_id = :tenant_id
AND app_id = :app_id
AND triggered_from = :triggered_from"""
arg_dict: dict[str, Any] = {
"tz": timezone,
"tenant_id": tenant_id,
"app_id": app_id,
"triggered_from": triggered_from,
}
if start_date:
sql_query += " AND created_at >= :start_date"
arg_dict["start_date"] = start_date
if end_date:
sql_query += " AND created_at < :end_date"
arg_dict["end_date"] = end_date
sql_query += " GROUP BY date ORDER BY date"
response_data = []
with self._session_maker() as session:
rs = session.execute(sa.text(sql_query), arg_dict)
for row in rs:
response_data.append(
{
"date": str(row.date),
"token_count": row.token_count,
}
)
return cast(list[DailyTokenCostStats], response_data)
def get_average_app_interaction_statistics(
self,
tenant_id: str,
app_id: str,
triggered_from: str,
start_date: datetime | None = None,
end_date: datetime | None = None,
timezone: str = "UTC",
) -> list[AverageInteractionStats]:
"""
Get average app interaction statistics using raw SQL for optimal performance.
"""
sql_query = """SELECT
AVG(sub.interactions) AS interactions,
sub.date
FROM
(
SELECT
DATE(DATE_TRUNC('day', c.created_at AT TIME ZONE 'UTC' AT TIME ZONE :tz )) AS date,
c.created_by,
COUNT(c.id) AS interactions
FROM
workflow_runs c
WHERE
c.tenant_id = :tenant_id
AND c.app_id = :app_id
AND c.triggered_from = :triggered_from
{{start}}
{{end}}
GROUP BY
date, c.created_by
) sub
GROUP BY
sub.date"""
arg_dict: dict[str, Any] = {
"tz": timezone,
"tenant_id": tenant_id,
"app_id": app_id,
"triggered_from": triggered_from,
}
if start_date:
sql_query = sql_query.replace("{{start}}", " AND c.created_at >= :start_date")
arg_dict["start_date"] = start_date
else:
sql_query = sql_query.replace("{{start}}", "")
if end_date:
sql_query = sql_query.replace("{{end}}", " AND c.created_at < :end_date")
arg_dict["end_date"] = end_date
else:
sql_query = sql_query.replace("{{end}}", "")
response_data = []
with self._session_maker() as session:
rs = session.execute(sa.text(sql_query), arg_dict)
for row in rs:
response_data.append(
{"date": str(row.date), "interactions": float(row.interactions.quantize(Decimal("0.01")))}
)
return cast(list[AverageInteractionStats], response_data)

21
api/repositories/types.py Normal file
View File

@@ -0,0 +1,21 @@
from typing import TypedDict
class DailyRunsStats(TypedDict):
date: str
runs: int
class DailyTerminalsStats(TypedDict):
date: str
terminal_count: int
class DailyTokenCostStats(TypedDict):
date: str
token_count: int
class AverageInteractionStats(TypedDict):
date: str
interactions: float