aminghadersohi commented on code in PR #40961:
URL: https://github.com/apache/superset/pull/40961#discussion_r3501655693
##########
superset/mcp_service/dashboard/schemas.py:
##########
@@ -1717,3 +1732,225 @@ def dashboard_layout_serializer(dashboard: "Dashboard")
-> DashboardLayout:
has_layout=bool(position_json_str),
)
)
+
+
+# Per-dataset caps keep responses small enough for LLM context: wide
+# datasets can have hundreds of columns, which would dwarf the fields an
+# agent actually needs to configure native filters.
+MAX_DASHBOARD_DATASET_COLUMNS: int = 100
+MAX_DASHBOARD_DATASET_METRICS: int = 50
+
+
+class DashboardDatasetColumn(BaseModel):
+ """Lean column representation for dashboard dataset context."""
+
+ column_name: str = Field(..., description="Column name")
+ verbose_name: str | None = Field(None, description="Verbose (display)
name")
+ type: str | None = Field(None, description="Column data type")
+ is_dttm: bool | None = Field(None, description="Is datetime column")
+
+
+class DashboardDatasetMetric(BaseModel):
+ """Lean metric representation for dashboard dataset context."""
+
+ metric_name: str = Field(..., description="Saved metric name")
+ verbose_name: str | None = Field(None, description="Verbose (display)
name")
+ expression: str | None = Field(None, description="SQL expression")
+
+
+class DashboardDatasetDatabaseInfo(BaseModel):
+ """Database connection summary for a dashboard dataset."""
+
+ id: int | None = Field(None, description="Database ID")
+ name: str | None = Field(None, description="Database name")
+ backend: str | None = Field(None, description="Database backend (engine)")
+
+
+class DashboardDatasetSummary(BaseModel):
+ """A dataset used by a dashboard's charts, with columns and metrics."""
+
+ id: int | None = Field(None, description="Dataset ID")
+ uuid: str | None = Field(None, description="Dataset UUID")
+ table_name: str | None = Field(None, description="Table name")
+ schema_name: str | None = Field(None, description="Schema name")
+ database: DashboardDatasetDatabaseInfo | None = Field(
+ None, description="Database the dataset belongs to"
+ )
+ chart_count: int = Field(
+ 0, description="Number of charts on the dashboard using this dataset"
+ )
+ columns: List[DashboardDatasetColumn] = Field(
+ default_factory=list, description="Dataset columns"
+ )
+ metrics: List[DashboardDatasetMetric] = Field(
+ default_factory=list, description="Dataset metrics"
+ )
+ total_column_count: int = Field(
+ 0, description="Total number of columns on the dataset"
+ )
+ total_metric_count: int = Field(
+ 0, description="Total number of metrics on the dataset"
+ )
+ columns_truncated: bool = Field(
+ False,
+ description=(
+ "True when the columns list was truncated to keep the response
small"
+ ),
+ )
+ metrics_truncated: bool = Field(
+ False,
+ description=(
+ "True when the metrics list was truncated to keep the response
small"
+ ),
+ )
+
+ @model_serializer(mode="wrap")
+ def _rename_schema_field(self, serializer: Any, info: Any) -> Dict[str,
Any]:
+ """Serialize 'schema_name' as 'schema' to match API conventions."""
+ data = serializer(self)
+ if "schema_name" in data:
+ data["schema"] = data.pop("schema_name")
+ return data
+
Review Comment:
Fixed — added `alias="schema"` to `DashboardDatasetSummary.schema_name` and
`ConfigDict(populate_by_name=True)` to the class, mirroring the exact same
pattern already used in `DatasetInfo` (dataset/schemas.py:137,184). Without the
alias, `model_json_schema()` advertised `schema_name` while the
`@model_serializer` output `schema`, creating a contract mismatch. Now both the
advertised schema and runtime payload agree on `schema`.
##########
tests/unit_tests/mcp_service/dashboard/tool/test_get_dashboard_datasets.py:
##########
@@ -0,0 +1,387 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements. See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership. The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License. You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied. See the License for the
+# specific language governing permissions and limitations
+# under the License.
+
+"""Unit tests for the MCP get_dashboard_datasets tool."""
+
+from unittest.mock import Mock, patch
+
+import pytest
+from fastmcp import Client
+
+from superset.mcp_service.app import mcp
+from superset.mcp_service.utils.sanitization import (
+ LLM_CONTEXT_CLOSE_DELIMITER,
+ LLM_CONTEXT_OPEN_DELIMITER,
+)
+from superset.utils import json
+
+
+def _wrapped(value: str) -> str:
+ return
f"{LLM_CONTEXT_OPEN_DELIMITER}\n{value}\n{LLM_CONTEXT_CLOSE_DELIMITER}"
+
+
+def _build_column_mock(
+ name: str,
+ *,
+ verbose_name: str | None = None,
+ type_: str | None = "VARCHAR",
+ is_dttm: bool = False,
+) -> Mock:
+ column = Mock()
+ column.column_name = name
+ column.verbose_name = verbose_name
+ column.type = type_
+ column.is_dttm = is_dttm
+ return column
+
+
+def _build_metric_mock(
+ name: str,
+ *,
+ verbose_name: str | None = None,
+ expression: str | None = None,
+) -> Mock:
+ metric = Mock()
+ metric.metric_name = name
+ metric.verbose_name = verbose_name
+ metric.expression = expression
+ return metric
+
+
+def _build_database_mock(
+ *, database_id: int = 7, name: str = "examples", backend: str =
"postgresql"
+) -> Mock:
+ database = Mock()
+ database.id = database_id
+ database.database_name = name
+ database.backend = backend
+ return database
+
+
+def _build_datasource_mock(
+ *,
+ dataset_id: int,
+ uuid: str | None = None,
+ table_name: str = "my_table",
+ schema: str | None = "public",
+ database: Mock | None = None,
+ columns: list[Mock] | None = None,
+ metrics: list[Mock] | None = None,
+) -> Mock:
+ datasource = Mock()
+ datasource.id = dataset_id
+ datasource.uuid = uuid
+ datasource.table_name = table_name
+ datasource.schema = schema
+ datasource.database = database
+ datasource.columns = columns or []
+ datasource.metrics = metrics or []
+ return datasource
+
+
+def _build_slice_mock(datasource: Mock) -> Mock:
+ slc = Mock()
+ slc.datasource_id = datasource.id
+ slc.datasource = datasource
+ return slc
+
+
+def _build_dashboard_mock(
+ *,
+ dashboard_id: int = 1,
+ title: str = "Test Dashboard",
+ uuid: str | None = "dashboard-uuid-1",
+ slices: list[Mock] | None = None,
+) -> Mock:
+ dashboard = Mock()
+ dashboard.id = dashboard_id
+ dashboard.dashboard_title = title
+ dashboard.uuid = uuid
+ dashboard.slices = slices or []
+ return dashboard
+
+
[email protected]
+def mcp_server():
+ return mcp
+
+
[email protected](autouse=True)
+def mock_auth():
+ with patch("superset.mcp_service.auth.get_user_from_request") as
mock_get_user:
+ mock_user = Mock()
+ mock_user.id = 1
+ mock_user.username = "admin"
+ mock_get_user.return_value = mock_user
+ yield mock_get_user
+
+
[email protected](autouse=True)
+def mock_dataset_access():
+ with patch(
+ "superset.mcp_service.auth.has_dataset_access", return_value=True
+ ) as mock_access:
+ yield mock_access
+
+
[email protected](autouse=True)
+def allow_data_model_metadata():
+ """Keep tests in the metadata-allowed path unless a test overrides it."""
+ with patch(
+ "superset.mcp_service.dashboard.tool.get_dashboard_datasets."
+ "user_can_view_data_model_metadata",
+ return_value=True,
+ ) as mock_allow:
+ yield mock_allow
+
+
+@patch("superset.daos.dashboard.DashboardDAO.find_by_id")
[email protected]
+async def test_get_dashboard_datasets_multiple_datasets(mock_find, mcp_server):
+ sales = _build_datasource_mock(
+ dataset_id=10,
+ uuid="dataset-uuid-10",
+ table_name="sales",
+ schema="public",
+ database=_build_database_mock(),
+ columns=[
+ _build_column_mock("region", verbose_name="Region"),
+ _build_column_mock("order_date", type_="TIMESTAMP", is_dttm=True),
+ ],
+ metrics=[
+ _build_metric_mock(
+ "total_revenue",
+ verbose_name="Total Revenue",
+ expression="SUM(revenue)",
+ )
+ ],
+ )
+ customers = _build_datasource_mock(
+ dataset_id=20,
+ uuid="dataset-uuid-20",
+ table_name="customers",
+ schema="crm",
+ database=_build_database_mock(database_id=8, name="crm_db",
backend="mysql"),
+ columns=[_build_column_mock("customer_name")],
+ metrics=[],
+ )
+ mock_find.return_value = _build_dashboard_mock(
+ slices=[
+ _build_slice_mock(sales),
+ _build_slice_mock(sales),
+ _build_slice_mock(customers),
+ ]
+ )
+
+ async with Client(mcp_server) as client:
+ result = await client.call_tool(
+ "get_dashboard_datasets", {"request": {"identifier": 1}}
+ )
+ data = json.loads(result.content[0].text)
+
+ assert data["id"] == 1
+ assert data["dashboard_title"] == _wrapped("Test Dashboard")
+ assert data["uuid"] == "dashboard-uuid-1"
+ assert data["dataset_count"] == 2
+ assert data["inaccessible_dataset_count"] == 0
+ assert len(data["datasets"]) == 2
+
+ datasets_by_id = {d["id"]: d for d in data["datasets"]}
+ sales_data = datasets_by_id[10]
+ assert sales_data["uuid"] == "dataset-uuid-10"
+ assert sales_data["table_name"] == "sales"
+ assert sales_data["schema"] == "public"
+ assert sales_data["database"] == {
+ "id": 7,
+ "name": "examples",
+ "backend": "postgresql",
+ }
+ assert sales_data["chart_count"] == 2
+ assert sales_data["columns"] == [
+ {
+ "column_name": "region",
+ "verbose_name": _wrapped("Region"),
+ "type": "VARCHAR",
+ "is_dttm": False,
+ },
+ {
+ "column_name": "order_date",
+ "verbose_name": None,
+ "type": "TIMESTAMP",
+ "is_dttm": True,
+ },
+ ]
+ assert sales_data["metrics"] == [
+ {
+ "metric_name": "total_revenue",
+ "verbose_name": _wrapped("Total Revenue"),
+ "expression": _wrapped("SUM(revenue)"),
+ }
+ ]
+ assert sales_data["total_column_count"] == 2
+ assert sales_data["total_metric_count"] == 1
+ assert sales_data["columns_truncated"] is False
+ assert sales_data["metrics_truncated"] is False
+
+ customers_data = datasets_by_id[20]
+ assert customers_data["table_name"] == "customers"
+ assert customers_data["schema"] == "crm"
+ assert customers_data["chart_count"] == 1
+ assert customers_data["metrics"] == []
+
+
+@patch("superset.daos.dashboard.DashboardDAO.find_by_id")
[email protected]
+async def test_get_dashboard_datasets_by_slug(mock_find, mcp_server):
+ datasource = _build_datasource_mock(
+ dataset_id=10,
+ table_name="sales",
+ database=_build_database_mock(),
+ columns=[_build_column_mock("region")],
+ )
+ dashboard = _build_dashboard_mock(slices=[_build_slice_mock(datasource)])
+
+ def find_by_id(identifier, id_column=None, query_options=None):
+ if id_column == "slug" and identifier == "sales-dash":
+ return dashboard
+ return None
+
+ mock_find.side_effect = find_by_id
+
+ async with Client(mcp_server) as client:
+ result = await client.call_tool(
+ "get_dashboard_datasets", {"request": {"identifier": "sales-dash"}}
+ )
+ data = json.loads(result.content[0].text)
+
+ assert data["id"] == 1
+ assert data["dataset_count"] == 1
+ assert data["datasets"][0]["table_name"] == "sales"
+
+
+@patch("superset.daos.dashboard.DashboardDAO.find_by_id")
[email protected]
+async def test_get_dashboard_datasets_not_found(mock_find, mcp_server):
+ mock_find.return_value = None
+
+ async with Client(mcp_server) as client:
+ result = await client.call_tool(
+ "get_dashboard_datasets", {"request": {"identifier": 999}}
+ )
+ data = json.loads(result.content[0].text)
+
+ assert data["error_type"] == "not_found"
+
+
+@patch("superset.daos.dashboard.DashboardDAO.find_by_id")
[email protected]
+async def test_get_dashboard_datasets_metadata_restricted(
+ mock_find, mcp_server, allow_data_model_metadata
Review Comment:
Keeping test helpers and fixtures unannotated — same rationale as all
previous typing nits on this file (see resolved threads on this PR). Sibling
mcp_service test files follow the same convention, and mypy passes.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
