Add UCX history schema and table for storing UCX's artifact

src/databricks/labs/ucx/progress/install.py

@@ -1,12 +1,43 @@
 import logging
+from dataclasses import dataclass
 
 from databricks.labs.lsql.backends import SqlBackend
 from databricks.labs.lsql.deployment import SchemaDeployer
+
+from databricks.labs.ucx.__about__ import __version__
 from databricks.labs.ucx.progress.workflow_runs import WorkflowRun
 
+
 logger = logging.getLogger(__name__)
 
 
+@dataclass(frozen=True, kw_only=True)
+class Historical:
+    workspace_id: int
+    """The identifier of the workspace where this historical record was generated."""
+
+    job_run_id: int
+    """The identifier of the job run that generated this historical record."""
+
+    object_type: str
+    """The inventory table for which this historical record was generated."""
+
+    object_id: list[str]
+    """The type-specific identifier for the corresponding inventory record."""
+
+    data: dict[str, str]
+    """Type-specific JSON-encoded data of the inventory record."""
+
+    failures: list[str]
+    """The list of problems associated with the object that this inventory record covers."""
+
+    owner: str
+    """The identity that has ownership of the object."""
+
+    ucx_version: str = __version__
+    """The UCX semantic version."""
+
+
 class ProgressTrackingInstallation:
     """Install resources for UCX's progress tracking."""
 
@@ -19,4 +50,5 @@ def __init__(self, sql_backend: SqlBackend, ucx_catalog: str) -> None:
     def run(self) -> None:
         self._schema_deployer.deploy_schema()
         self._schema_deployer.deploy_table("workflow_runs", WorkflowRun)
+        self._schema_deployer.deploy_table("historical", Historical)
         logger.info("Installation completed successfully!")

tests/integration/progress/test_install.py

@@ -1,7 +1,11 @@
-def test_progress_tracking_installer_creates_workflow_runs_table(az_cli_ctx) -> None:
+import pytest
+
+
+@pytest.mark.parametrize("table_name", ["workflow_runs", "historical"])
+def test_progress_tracking_installer_creates_table(az_cli_ctx, table_name) -> None:
     az_cli_ctx.progress_tracking_installation.run()
     query = (
         f"SELECT 1 FROM tables WHERE table_catalog = '{az_cli_ctx.config.ucx_catalog}' "
-        "AND table_schema = 'multiworkspace' AND table_name = 'workflow_runs'"
+        f"AND table_schema = 'multiworkspace' AND table_name = '{table_name}'"
     )
     assert any(az_cli_ctx.sql_backend.fetch(query, catalog="system", schema="information_schema"))

tests/unit/progress/test_install.py

@@ -7,8 +7,8 @@ def test_progress_tracking_installation_run_creates_progress_tracking_schema(moc
     assert "CREATE SCHEMA IF NOT EXISTS ucx.multiworkspace" in mock_backend.queries[0]
 
 
-def test_progress_tracking_installation_run_creates_workflow_runs_table(mock_backend) -> None:
+def test_progress_tracking_installation_run_creates_tables(mock_backend) -> None:
     installation = ProgressTrackingInstallation(mock_backend, "ucx")
     installation.run()
     # Dataclass to schema conversion is tested within the lsql package
-    assert any("CREATE TABLE IF NOT EXISTS" in query for query in mock_backend.queries)
+    assert sum("CREATE TABLE IF NOT EXISTS" in query for query in mock_backend.queries) == 2