atlan-application-sdk 0.1.1rc46__tar.gz → 0.1.1rc48__tar.gz

{atlan_application_sdk-0.1.1rc46 → atlan_application_sdk-0.1.1rc48}/.github/actions/trivy-container/action.yaml

@@ -23,7 +23,7 @@ runs:
       uses: docker/build-push-action@v6
       with:
         context: .
-        file: ./install/Dockerfile
+        file: ./Dockerfile
         push: false
         secrets: |
           "PRIVATE_REPO_ACCESS_TOKEN=${{ inputs.github-token }}"

atlan_application_sdk-0.1.1rc48/.github/release_notes.md

@@ -0,0 +1,7 @@
+## v0.1.1rc48 (September 26, 2025)
+
+Full Changelog: https://github.com/atlanhq/application-sdk/compare/v0.1.1rc47...v0.1.1rc48
+
+### Bug Fixes
+
+- Updated constants + Refactor for multidb logic (#736) (by @Abhishek Agrawal in [cd97be3](https://github.com/atlanhq/application-sdk/commit/cd97be3))

{atlan_application_sdk-0.1.1rc46 → atlan_application_sdk-0.1.1rc48}/.github/workflow-templates/trivy-container.yaml

@@ -47,7 +47,7 @@ jobs:
         uses: docker/build-push-action@v6
         with:
           context: .
-          file: ./install/Dockerfile
+          file: ./Dockerfile
           push: false
           secrets: |
             "PRIVATE_REPO_ACCESS_TOKEN=${{ secrets.PRIVATE_REPO_ACCESS_TOKEN }}"

{atlan_application_sdk-0.1.1rc46 → atlan_application_sdk-0.1.1rc48}/.github/workflows/scale-tests.yaml

@@ -69,7 +69,7 @@ jobs:
         uses: docker/build-push-action@v6
         with:
           context: .
-          file: ./install/Dockerfile
+          file: ./Dockerfile
           tags: test-sample:latest
           secrets: |
             PRIVATE_REPO_ACCESS_TOKEN=${{ secrets.ORG_PAT_GITHUB }}

{atlan_application_sdk-0.1.1rc46 → atlan_application_sdk-0.1.1rc48}/CHANGELOG.md

@@ -1,6 +1,26 @@
 # Changelog
 
 
+## v0.1.1rc48 (September 26, 2025)
+
+Full Changelog: https://github.com/atlanhq/application-sdk/compare/v0.1.1rc47...v0.1.1rc48
+
+### Bug Fixes
+
+- Updated constants + Refactor for multidb logic (#736) (by @Abhishek Agrawal in [cd97be3](https://github.com/atlanhq/application-sdk/commit/cd97be3))
+
+## v0.1.1rc47 (September 24, 2025)
+
+Full Changelog: https://github.com/atlanhq/application-sdk/compare/v0.1.1rc46...v0.1.1rc47
+
+### Bug Fixes
+
+- partition columns defaults for daft write_parquet (#728) (by @Nishchith Shetty in [7ed4949](https://github.com/atlanhq/application-sdk/commit/7ed4949))
+- Update ParquetOutput to handle file uploads correctly (#732) (by @Mustafa in [b4b2953](https://github.com/atlanhq/application-sdk/commit/b4b2953))
+- CI build path (#733) (by @Nishchith Shetty in [6d04006](https://github.com/atlanhq/application-sdk/commit/6d04006))
+
+
+
 ## v0.1.1rc46 (September 18, 2025)
 
 Full Changelog: https://github.com/atlanhq/application-sdk/compare/v0.1.1rc45...v0.1.1rc46

{atlan_application_sdk-0.1.1rc46 → atlan_application_sdk-0.1.1rc48}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: atlan-application-sdk
-Version: 0.1.1rc46
+Version: 0.1.1rc48
 Summary: Atlan Application SDK is a Python library for developing applications on the Atlan Platform
 Project-URL: Repository, https://github.com/atlanhq/application-sdk
 Project-URL: Documentation, https://github.com/atlanhq/application-sdk/README.md

{atlan_application_sdk-0.1.1rc46 → atlan_application_sdk-0.1.1rc48}/application_sdk/activities/metadata_extraction/sql.py

@@ -528,7 +528,6 @@ class BaseSQLMetadataExtractionActivities(ActivitiesInterface):
             raise ValueError("SQL client engine not initialized")
 
         successful_databases: List[str] = []
-        failed_databases: List[str] = []
         dataframe_list: List[
             Union[AsyncIterator["pd.DataFrame"], Iterator["pd.DataFrame"]]
         ] = []
@@ -560,31 +559,23 @@ class BaseSQLMetadataExtractionActivities(ActivitiesInterface):
 
                 if success:
                     logger.info(f"Successfully processed database: {database_name}")
-                else:
-                    logger.warning(
-                        f"Failed to execute query for database: {database_name}"
-                    )
+
             except Exception as e:  # noqa: BLE001
-                logger.warning(
-                    f"Failed to process database '{database_name}': {str(e)}. Skipping to next database."
+                logger.error(
+                    f"Failed to process database '{database_name}': {str(e)}. Failing the workflow.",
+                    exc_info=True,
                 )
-                success, batched_iterator = False, None
+                raise
 
             if success:
                 successful_databases.append(database_name)
                 if not write_to_file and batched_iterator:
                     dataframe_list.append(batched_iterator)
-            else:
-                failed_databases.append(database_name)
 
         # Log results
         logger.info(
             f"Successfully processed {len(successful_databases)} databases: {successful_databases}"
         )
-        if failed_databases:
-            logger.warning(
-                f"Failed to process {len(failed_databases)} databases: {failed_databases}"
-            )
 
         # Finalize results
         return await self._finalize_multidb_results(

{atlan_application_sdk-0.1.1rc46 → atlan_application_sdk-0.1.1rc48}/application_sdk/constants.py

@@ -114,11 +114,13 @@ DEPLOYMENT_NAME_KEY = "deployment_name"
 # Workflow Constants
 #: Timeout duration for activity heartbeats
 HEARTBEAT_TIMEOUT = timedelta(
-    seconds=int(os.getenv("ATLAN_HEARTBEAT_TIMEOUT", 300))  # 5 minutes
+    seconds=int(os.getenv("ATLAN_HEARTBEAT_TIMEOUT_SECONDS", 300))  # 5 minutes
 )
 #: Maximum duration an activity can run before timing out
 START_TO_CLOSE_TIMEOUT = timedelta(
-    seconds=int(os.getenv("ATLAN_START_TO_CLOSE_TIMEOUT", 2 * 60 * 60))  # 2 hours
+    seconds=int(
+        os.getenv("ATLAN_START_TO_CLOSE_TIMEOUT_SECONDS", 2 * 60 * 60)
+    )  # 2 hours
 )
 
 # SQL Client Constants

{atlan_application_sdk-0.1.1rc46 → atlan_application_sdk-0.1.1rc48}/application_sdk/outputs/parquet.py

@@ -221,17 +221,19 @@ class ParquetOutput(Output):
             if row_count == 0:
                 return
 
+            file_paths = []
             # Use Daft's execution context for temporary configuration
             with daft.execution_config_ctx(
                 parquet_target_filesize=self.max_file_size_bytes,
                 default_morsel_size=morsel_size,
             ):
                 # Daft automatically handles file splitting and naming
-                dataframe.write_parquet(
+                result = dataframe.write_parquet(
                     root_dir=self.output_path,
                     write_mode=write_mode.value,
-                    partition_cols=partition_cols if partition_cols else [],
+                    partition_cols=partition_cols,
                 )
+                file_paths = result.to_pydict().get("path", [])
 
             # Update counters
             self.chunk_count += 1
@@ -266,12 +268,12 @@ class ParquetOutput(Output):
                     logger.info(
                         f"No files found under prefix {get_object_store_prefix(self.output_path)}: {str(e)}"
                     )
-
-            await ObjectStore.upload_prefix(
-                source=self.output_path,
-                destination=get_object_store_prefix(self.output_path),
-                retain_local_copy=self.retain_local_copy,
-            )
+            for path in file_paths:
+                await ObjectStore.upload_file(
+                    source=path,
+                    destination=get_object_store_prefix(path),
+                    retain_local_copy=self.retain_local_copy,
+                )
 
         except Exception as e:
             # Record metrics for failed write

{atlan_application_sdk-0.1.1rc46 → atlan_application_sdk-0.1.1rc48}/application_sdk/version.py

@@ -2,4 +2,4 @@
 Version information for the application_sdk package.
 """
 
-__version__ = "0.1.1rc46"
+__version__ = "0.1.1rc48"

{atlan_application_sdk-0.1.1rc46 → atlan_application_sdk-0.1.1rc48}/docs/docs/configuration.md

@@ -28,8 +28,8 @@ The Application SDK uses environment variables for configuration. These can be s
 | `ATLAN_WORKFLOW_UI_PORT` | Port number for the Temporal UI | `8233` | Port for Temporal Web UI |
 | `ATLAN_WORKFLOW_MAX_TIMEOUT_HOURS` | Maximum timeout duration for workflows (in hours) | `1` | Prevents runaway workflows from consuming resources |
 | `ATLAN_MAX_CONCURRENT_ACTIVITIES` | Maximum number of activities that can run concurrently | `5` | Controls resource usage and prevents overwhelming target systems |
-| `ATLAN_HEARTBEAT_TIMEOUT` | Timeout duration for activity heartbeats (in seconds) | `300` | Detects stuck activities and enables recovery |
-| `ATLAN_START_TO_CLOSE_TIMEOUT` | Maximum duration an activity can run before timing out (in seconds) | `7200` | Prevents activities from running indefinitely |
+| `ATLAN_HEARTBEAT_TIMEOUT_SECONDS` | Timeout duration for activity heartbeats (in seconds) | `300` | Detects stuck activities and enables recovery |
+| `ATLAN_START_TO_CLOSE_TIMEOUT_SECONDS` | Maximum duration an activity can run before timing out (in seconds) | `7200` | Prevents activities from running indefinitely |
 | `ATLAN_WORKFLOW_AUTH_ENABLED` | Whether to enable authentication for Temporal workflows | `false` | Used in production deployments with secure Temporal clusters |
 | `ATLAN_DEPLOYMENT_SECRET_PATH` | Path to deployment secrets in secret store | `ATLAN_DEPLOYMENT_SECRETS` | Contains authentication credentials for production |
 
@@ -139,7 +139,7 @@ For production deployments, consider these essential configurations:
 - `ATLAN_MAX_CONCURRENT_ACTIVITIES`: Adjust based on target system capacity
 - `DAPR_MAX_GRPC_MESSAGE_LENGTH`: Increase for large data processing
 - Batch sizes: Adjust `*_BATCH_SIZE` variables based on memory and performance requirements
-- Timeout values: Adjust `ATLAN_HEARTBEAT_TIMEOUT` and `ATLAN_START_TO_CLOSE_TIMEOUT` based on workload characteristics
+- Timeout values: Adjust `ATLAN_HEARTBEAT_TIMEOUT_SECONDS` and `ATLAN_START_TO_CLOSE_TIMEOUT_SECONDS` based on workload characteristics
 
 ### Observability Setup
 - Enable telemetry: Set `ATLAN_ENABLE_OTLP_*` variables to `true`

{atlan_application_sdk-0.1.1rc46 → atlan_application_sdk-0.1.1rc48}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "atlan-application-sdk"
-version = "0.1.1rc46"
+version = "0.1.1rc48"
 description = "Atlan Application SDK is a Python library for developing applications on the Atlan Platform"
 license = "Apache-2.0"
 authors = [

{atlan_application_sdk-0.1.1rc46 → atlan_application_sdk-0.1.1rc48}/tests/unit/outputs/test_parquet_output.py

@@ -300,7 +300,7 @@ class TestParquetOutputWriteDaftDataframe:
     async def test_write_daft_dataframe_success(self, base_output_path: str):
         """Test successful daft DataFrame writing."""
         with patch("daft.execution_config_ctx") as mock_ctx, patch(
-            "application_sdk.services.objectstore.ObjectStore.upload_prefix"
+            "application_sdk.services.objectstore.ObjectStore.upload_file"
         ) as mock_upload, patch(
             "application_sdk.outputs.parquet.get_object_store_prefix"
         ) as mock_prefix:
@@ -312,7 +312,9 @@ class TestParquetOutputWriteDaftDataframe:
             # Mock daft DataFrame
             mock_df = MagicMock()
             mock_df.count_rows.return_value = 1000
-            mock_df.write_parquet = MagicMock()
+            mock_result = MagicMock()
+            mock_result.to_pydict.return_value = {"path": ["test.parquet"]}
+            mock_df.write_parquet.return_value = mock_result
 
             parquet_output = ParquetOutput(
                 output_path=base_output_path,
@@ -327,7 +329,7 @@ class TestParquetOutputWriteDaftDataframe:
             mock_df.write_parquet.assert_called_once_with(
                 root_dir=parquet_output.output_path,
                 write_mode="append",  # Uses method default value "append"
-                partition_cols=[],  # Default empty list
+                partition_cols=None,
             )
 
             # Check that upload_prefix was called
@@ -339,7 +341,7 @@ class TestParquetOutputWriteDaftDataframe:
     ):
         """Test daft DataFrame writing with parameter overrides."""
         with patch("daft.execution_config_ctx") as mock_ctx, patch(
-            "application_sdk.services.objectstore.ObjectStore.upload_prefix"
+            "application_sdk.services.objectstore.ObjectStore.upload_file"
         ) as mock_upload, patch(
             "application_sdk.services.objectstore.ObjectStore.delete_prefix"
         ) as mock_delete, patch(
@@ -354,7 +356,9 @@ class TestParquetOutputWriteDaftDataframe:
             # Mock daft DataFrame
             mock_df = MagicMock()
             mock_df.count_rows.return_value = 500
-            mock_df.write_parquet = MagicMock()
+            mock_result = MagicMock()
+            mock_result.to_pydict.return_value = {"path": ["test.parquet"]}
+            mock_df.write_parquet.return_value = mock_result
 
             parquet_output = ParquetOutput(
                 output_path=base_output_path,
@@ -381,7 +385,7 @@ class TestParquetOutputWriteDaftDataframe:
     ):
         """Test daft DataFrame writing with default parameters (uses method default write_mode='append')."""
         with patch("daft.execution_config_ctx") as mock_ctx, patch(
-            "application_sdk.services.objectstore.ObjectStore.upload_prefix"
+            "application_sdk.services.objectstore.ObjectStore.upload_file"
         ) as mock_upload, patch(
             "application_sdk.outputs.parquet.get_object_store_prefix"
         ) as mock_prefix:
@@ -393,7 +397,9 @@ class TestParquetOutputWriteDaftDataframe:
             # Mock daft DataFrame
             mock_df = MagicMock()
             mock_df.count_rows.return_value = 500
-            mock_df.write_parquet = MagicMock()
+            mock_result = MagicMock()
+            mock_result.to_pydict.return_value = {"path": ["test.parquet"]}
+            mock_df.write_parquet.return_value = mock_result
 
             parquet_output = ParquetOutput(
                 output_path=base_output_path,
@@ -406,7 +412,7 @@ class TestParquetOutputWriteDaftDataframe:
             mock_df.write_parquet.assert_called_once_with(
                 root_dir=parquet_output.output_path,
                 write_mode="append",  # Uses method default value "append"
-                partition_cols=[],  # None converted to empty list
+                partition_cols=None,
             )
 
     @pytest.mark.asyncio
@@ -415,7 +421,7 @@ class TestParquetOutputWriteDaftDataframe:
     ):
         """Test that DAPR limit is properly configured."""
         with patch("daft.execution_config_ctx") as mock_ctx, patch(
-            "application_sdk.services.objectstore.ObjectStore.upload_prefix"
+            "application_sdk.services.objectstore.ObjectStore.upload_file"
         ) as mock_upload, patch(
             "application_sdk.outputs.parquet.get_object_store_prefix"
         ) as mock_prefix:
@@ -427,7 +433,9 @@ class TestParquetOutputWriteDaftDataframe:
             # Mock daft DataFrame
             mock_df = MagicMock()
             mock_df.count_rows.return_value = 1000
-            mock_df.write_parquet = MagicMock()
+            mock_result = MagicMock()
+            mock_result.to_pydict.return_value = {"path": ["test.parquet"]}
+            mock_df.write_parquet.return_value = mock_result
 
             parquet_output = ParquetOutput(output_path=base_output_path)
 
@@ -488,7 +496,7 @@ class TestParquetOutputMetrics:
     async def test_daft_write_metrics(self, base_output_path: str):
         """Test that metrics are recorded for daft DataFrame writes."""
         with patch("daft.execution_config_ctx") as mock_ctx, patch(
-            "application_sdk.services.objectstore.ObjectStore.upload_prefix"
+            "application_sdk.services.objectstore.ObjectStore.upload_file"
         ) as mock_upload, patch(
             "application_sdk.outputs.parquet.get_metrics"
         ) as mock_get_metrics, patch(
@@ -504,7 +512,9 @@ class TestParquetOutputMetrics:
             # Mock daft DataFrame
             mock_df = MagicMock()
             mock_df.count_rows.return_value = 1000
-            mock_df.write_parquet = MagicMock()
+            mock_result = MagicMock()
+            mock_result.to_pydict.return_value = {"path": ["test.parquet"]}
+            mock_df.write_parquet.return_value = mock_result
 
             parquet_output = ParquetOutput(output_path=base_output_path)
 

{atlan_application_sdk-0.1.1rc46 → atlan_application_sdk-0.1.1rc48}/uv.lock

@@ -140,7 +140,7 @@ wheels = [
 
 [[package]]
 name = "atlan-application-sdk"
-version = "0.1.1rc46"
+version = "0.1.1rc48"
 source = { editable = "." }
 dependencies = [
     { name = "aiohttp" },

atlan_application_sdk-0.1.1rc46/.github/release_notes.md

@@ -1,7 +0,0 @@
-## v0.1.1rc46 (September 18, 2025)
-
-Full Changelog: https://github.com/atlanhq/application-sdk/compare/v0.1.1rc45...v0.1.1rc46
-
-### Bug Fixes
-
-- Fix semaphore implementation to allow multiple batching without getting into max_concurrent_activities issue (#725) (by @Mustafa in [2a66f13](https://github.com/atlanhq/application-sdk/commit/2a66f13))