Merge remote-tracking branch 'origin/main' into feat/support-agent-sandbox

api/controllers/console/app/workflow_app_log.py

@@ -11,7 +11,10 @@ from controllers.console.app.wraps import get_app_model
 from controllers.console.wraps import account_initialization_required, setup_required
 from core.workflow.enums import WorkflowExecutionStatus
 from extensions.ext_database import db
-from fields.workflow_app_log_fields import build_workflow_app_log_pagination_model
+from fields.workflow_app_log_fields import (
+    build_workflow_app_log_pagination_model,
+    build_workflow_archived_log_pagination_model,
+)
 from libs.login import login_required
 from models import App
 from models.model import AppMode
@@ -61,6 +64,7 @@ console_ns.schema_model(
 
 # Register model for flask_restx to avoid dict type issues in Swagger
 workflow_app_log_pagination_model = build_workflow_app_log_pagination_model(console_ns)
+workflow_archived_log_pagination_model = build_workflow_archived_log_pagination_model(console_ns)
 
 
 @console_ns.route("/apps/<uuid:app_id>/workflow-app-logs")
@@ -99,3 +103,33 @@ class WorkflowAppLogApi(Resource):
             )
 
             return workflow_app_log_pagination
+
+
+@console_ns.route("/apps/<uuid:app_id>/workflow-archived-logs")
+class WorkflowArchivedLogApi(Resource):
+    @console_ns.doc("get_workflow_archived_logs")
+    @console_ns.doc(description="Get workflow archived execution logs")
+    @console_ns.doc(params={"app_id": "Application ID"})
+    @console_ns.expect(console_ns.models[WorkflowAppLogQuery.__name__])
+    @console_ns.response(200, "Workflow archived logs retrieved successfully", workflow_archived_log_pagination_model)
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @get_app_model(mode=[AppMode.WORKFLOW])
+    @marshal_with(workflow_archived_log_pagination_model)
+    def get(self, app_model: App):
+        """
+        Get workflow archived logs
+        """
+        args = WorkflowAppLogQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+
+        workflow_app_service = WorkflowAppService()
+        with Session(db.engine) as session:
+            workflow_app_log_pagination = workflow_app_service.get_paginate_workflow_archive_logs(
+                session=session,
+                app_model=app_model,
+                page=args.page,
+                limit=args.limit,
+            )
+
+            return workflow_app_log_pagination

api/controllers/console/app/workflow_run.py

@@ -1,12 +1,15 @@
+from datetime import UTC, datetime, timedelta
 from typing import Literal, cast
 
 from flask import request
 from flask_restx import Resource, fields, marshal_with
 from pydantic import BaseModel, Field, field_validator
+from sqlalchemy import select
 
 from controllers.console import console_ns
 from controllers.console.app.wraps import get_app_model
 from controllers.console.wraps import account_initialization_required, setup_required
+from extensions.ext_database import db
 from fields.end_user_fields import simple_end_user_fields
 from fields.member_fields import simple_account_fields
 from fields.workflow_run_fields import (
@@ -19,14 +22,17 @@ from fields.workflow_run_fields import (
     workflow_run_node_execution_list_fields,
     workflow_run_pagination_fields,
 )
+from libs.archive_storage import ArchiveStorageNotConfiguredError, get_archive_storage
 from libs.custom_inputs import time_duration
 from libs.helper import uuid_value
 from libs.login import current_user, login_required
-from models import Account, App, AppMode, EndUser, WorkflowRunTriggeredFrom
+from models import Account, App, AppMode, EndUser, WorkflowArchiveLog, WorkflowRunTriggeredFrom
+from services.retention.workflow_run.constants import ARCHIVE_BUNDLE_NAME
 from services.workflow_run_service import WorkflowRunService
 
 # Workflow run status choices for filtering
 WORKFLOW_RUN_STATUS_CHOICES = ["running", "succeeded", "failed", "stopped", "partial-succeeded"]
+EXPORT_SIGNED_URL_EXPIRE_SECONDS = 3600
 
 # Register models for flask_restx to avoid dict type issues in Swagger
 # Register in dependency order: base models first, then dependent models
@@ -93,6 +99,15 @@ workflow_run_node_execution_list_model = console_ns.model(
     "WorkflowRunNodeExecutionList", workflow_run_node_execution_list_fields_copy
 )
 
+workflow_run_export_fields = console_ns.model(
+    "WorkflowRunExport",
+    {
+        "status": fields.String(description="Export status: success/failed"),
+        "presigned_url": fields.String(description="Pre-signed URL for download", required=False),
+        "presigned_url_expires_at": fields.String(description="Pre-signed URL expiration time", required=False),
+    },
+)
+
 DEFAULT_REF_TEMPLATE_SWAGGER_2_0 = "#/definitions/{model}"
 
 
@@ -181,6 +196,56 @@ class AdvancedChatAppWorkflowRunListApi(Resource):
         return result
 
 
+@console_ns.route("/apps/<uuid:app_id>/workflow-runs/<uuid:run_id>/export")
+class WorkflowRunExportApi(Resource):
+    @console_ns.doc("get_workflow_run_export_url")
+    @console_ns.doc(description="Generate a download URL for an archived workflow run.")
+    @console_ns.doc(params={"app_id": "Application ID", "run_id": "Workflow run ID"})
+    @console_ns.response(200, "Export URL generated", workflow_run_export_fields)
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @get_app_model()
+    def get(self, app_model: App, run_id: str):
+        tenant_id = str(app_model.tenant_id)
+        app_id = str(app_model.id)
+        run_id_str = str(run_id)
+
+        run_created_at = db.session.scalar(
+            select(WorkflowArchiveLog.run_created_at)
+            .where(
+                WorkflowArchiveLog.tenant_id == tenant_id,
+                WorkflowArchiveLog.app_id == app_id,
+                WorkflowArchiveLog.workflow_run_id == run_id_str,
+            )
+            .limit(1)
+        )
+        if not run_created_at:
+            return {"code": "archive_log_not_found", "message": "workflow run archive not found"}, 404
+
+        prefix = (
+            f"{tenant_id}/app_id={app_id}/year={run_created_at.strftime('%Y')}/"
+            f"month={run_created_at.strftime('%m')}/workflow_run_id={run_id_str}"
+        )
+        archive_key = f"{prefix}/{ARCHIVE_BUNDLE_NAME}"
+
+        try:
+            archive_storage = get_archive_storage()
+        except ArchiveStorageNotConfiguredError as e:
+            return {"code": "archive_storage_not_configured", "message": str(e)}, 500
+
+        presigned_url = archive_storage.generate_presigned_url(
+            archive_key,
+            expires_in=EXPORT_SIGNED_URL_EXPIRE_SECONDS,
+        )
+        expires_at = datetime.now(UTC) + timedelta(seconds=EXPORT_SIGNED_URL_EXPIRE_SECONDS)
+        return {
+            "status": "success",
+            "presigned_url": presigned_url,
+            "presigned_url_expires_at": expires_at.isoformat(),
+        }, 200
+
+
 @console_ns.route("/apps/<uuid:app_id>/advanced-chat/workflow-runs/count")
 class AdvancedChatAppWorkflowRunCountApi(Resource):
     @console_ns.doc("get_advanced_chat_workflow_runs_count")

api/controllers/console/feature.py

@@ -1,6 +1,7 @@
 from flask_restx import Resource, fields
+from werkzeug.exceptions import Unauthorized
 
-from libs.login import current_account_with_tenant, login_required
+from libs.login import current_account_with_tenant, current_user, login_required
 from services.feature_service import FeatureService
 
 from . import console_ns
@@ -48,4 +49,12 @@ class SystemFeatureApi(Resource):
 
         Only non-sensitive configuration data should be returned by this endpoint.
         """
-        return FeatureService.get_system_features().model_dump()
+        # NOTE(QuantumGhost): ideally we should access `current_user.is_authenticated`
+        # without a try-catch. However, due to the implementation of user loader (the `load_user_from_request`
+        # in api/extensions/ext_login.py), accessing `current_user.is_authenticated` will
+        # raise `Unauthorized` exception if authentication token is not provided.
+        try:
+            is_authenticated = current_user.is_authenticated
+        except Unauthorized:
+            is_authenticated = False
+        return FeatureService.get_system_features(is_authenticated=is_authenticated).model_dump()

api/controllers/web/feature.py

@@ -17,5 +17,15 @@ class SystemFeatureApi(Resource):
 
         Returns:
             dict: System feature configuration object
+
+        This endpoint is akin to the `SystemFeatureApi` endpoint in api/controllers/console/feature.py,
+        except it is intended for use by the web app, instead of the console dashboard.
+
+        NOTE: This endpoint is unauthenticated by design, as it provides system features
+        data required for webapp initialization.
+
+        Authentication would create circular dependency (can't authenticate without webapp loading).
+
+        Only non-sensitive configuration data should be returned by this endpoint.
         """
         return FeatureService.get_system_features().model_dump()