tinybird 4.6.10.dev0__tar.gz → 4.6.11__tar.gz

{tinybird-4.6.10.dev0 → tinybird-4.6.11}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: tinybird
-Version: 4.6.10.dev0
+Version: 4.6.11
 Summary: Tinybird Command Line Tool
 Home-page: https://www.tinybird.co/docs/forward/commands
 Author: Tinybird
@@ -52,6 +52,16 @@ The Tinybird command-line tool allows you to use all the Tinybird functionality
 Changelog
 ----------
 
+4.6.11
+********
+
+- `Added` `tb datasource sample` support for DynamoDB connectors.
+
+4.6.10
+********
+
+- `Removed` `tinybird.bi_stats_rt` from `tb logs` sources. The BI Connector `bi_stats` / `bi_stats_rt` service datasources are deprecated.
+
 4.6.9
 *******
 

{tinybird-4.6.10.dev0 → tinybird-4.6.11}/tinybird/ch_utils/engine.py

@@ -121,6 +121,12 @@ class TableDetails:
     def is_mergetree_family(self) -> bool:
         return self.engine is not None and "mergetree" in self.engine.lower()
 
+    def is_view(self) -> bool:
+        return self.original_engine == "View"
+
+    def is_merge_final_engine(self) -> bool:
+        return self.original_engine == "MergeFinal"
+
     def supports_alter_add_column(self) -> bool:
         return self.is_mergetree_family() or (self.engine is not None and self.engine.lower() == "null")
 

{tinybird-4.6.10.dev0 → tinybird-4.6.11}/tinybird/datafile/common.py

@@ -221,8 +221,6 @@ INTERNAL_TABLES: Tuple[str, ...] = (
     "kafka_ops_log",
     "datasources_storage",
     "endpoint_errors",
-    "bi_stats_rt",
-    "bi_stats",
 )
 
 PREVIEW_CONNECTOR_SERVICES = ["s3", "s3_iamrole", "gcs"]
@@ -1725,7 +1723,9 @@ def parse(
 
         parser_state.current_node["indexes"] = indexes
 
-    def assign_var(v: str, allowed_values: Optional[set[str]] = None) -> Callable[[VarArg(str), KwArg(Any)], None]:
+    def assign_var(
+        v: str, allowed_values: Optional[set[str]] = None, lowercase: bool = False
+    ) -> Callable[[VarArg(str), KwArg(Any)], None]:
         @multiline_not_supported
         def _f(*args: str, **kwargs: Any):
             s = _unquote((" ".join(args)).strip())
@@ -1736,6 +1736,8 @@ def parse(
                     lineno=kwargs["lineno"],
                     pos=1,
                 )
+            if lowercase:
+                val = val.lower()
             parser_state.current_node[v.lower()] = val
 
         return _f
@@ -2048,7 +2050,9 @@ def parse(
             "import_schedule": assign_var("import_schedule"),
             "import_strategy": import_strategy_deprecated,  # Deprecated, always append
             "import_bucket_uri": assign_var("import_bucket_uri"),
-            "import_format": assign_var("import_format"),
+            # Lowercase: format checks and executor routing downstream expect
+            # lowercase values (ANALYTICS-A8M)
+            "import_format": assign_var("import_format", lowercase=True),
             "import_from_timestamp": assign_var("import_from_timestamp"),
             "import_service": import_service_deprecated,  # Deprecated
             "import_external_datasource": import_external_datasource_deprecated,  # Deprecated, BQ and SFK

{tinybird-4.6.10.dev0 → tinybird-4.6.11}/tinybird/service_datasources.py

@@ -244,49 +244,6 @@ def get_tinybird_service_datasources() -> List[Dict[str, Any]]:
                 {"name": "rows_quarantine", "type": "SimpleAggregateFunction(max, UInt64)"},
             ],
         },
-        {
-            "name": "tinybird.bi_stats_rt",
-            "description": "Contains information about all requests to your BI Connector interface in real time.",
-            "dateColumn": "start_datetime",
-            "engine": {
-                "engine": "MergeTree",
-                "sorting_key": "cityHash64(query_normalized), start_datetime",
-                "ttl": "start_datetime + toIntervalDay(7)",
-            },
-            "columns": [
-                {"name": "start_datetime", "type": "DateTime"},
-                {"name": "query", "type": "String"},
-                {"name": "query_normalized", "type": "String"},
-                {"name": "error_code", "type": "Int32"},
-                {"name": "error", "type": "Nullable(String)"},
-                {"name": "duration", "type": "UInt64"},
-                {"name": "read_rows", "type": "UInt64"},
-                {"name": "read_bytes", "type": "UInt64"},
-                {"name": "result_rows", "type": "UInt64"},
-                {"name": "result_bytes", "type": "UInt64"},
-            ],
-        },
-        {
-            "name": "tinybird.bi_stats",
-            "description": "Aggregates the stats in tinybird.bi_stats_rt by day.",
-            "dateColumn": "date",
-            "engine": {"engine": "MergeTree", "sorting_key": "cityHash64(query_normalized), start_datetime"},
-            "columns": [
-                {"name": "date", "type": "Date"},
-                {"name": "query_normalized", "type": "String"},
-                {"name": "view_count", "type": "UInt64"},
-                {"name": "error_count", "type": "UInt64"},
-                {"name": "avg_duration_state", "type": "AggregateFunction(avg, Float32)"},
-                {
-                    "name": "quantile_timing_state",
-                    "type": "AggregateFunction(quantilesTiming(0.9, 0.95, 0.99), Float64)",
-                },
-                {"name": "read_bytes_sum", "type": "UInt64"},
-                {"name": "read_rows_sum", "type": "UInt64"},
-                {"name": "avg_result_rows_state", "type": "AggregateFunction(avg, Float32)"},
-                {"name": "avg_result_bytes_state", "type": "AggregateFunction(avg, Float32)"},
-            ],
-        },
         {
             "name": "tinybird.sinks_ops_log",
             "description": "Contains information about your Sink pipes.",
@@ -483,6 +440,7 @@ def get_tinybird_service_datasources() -> List[Dict[str, Any]]:
                 {"name": "error_code", "type": "Int16"},
                 {"name": "error", "type": "String"},
                 {"name": "fix_suggestion", "type": "String"},
+                {"name": "fix_suggestion_ai", "type": "String"},
                 {"name": "run_validation", "type": "DateTime"},
             ],
         },
@@ -798,51 +756,6 @@ def get_organization_service_datasources() -> List[Dict[str, Any]]:
                 {"name": "token_name", "type": "String"},
             ],
         },
-        {
-            "name": "organization.bi_stats_rt",
-            "description": "Contains information about all requests to the BI Connector interface for the whole Organization in real time.",
-            "dateColumn": "start_datetime",
-            "engine": {
-                "engine": "MergeTree",
-                "sorting_key": "cityHash64(query_normalized), start_datetime",
-                "ttl": "start_datetime + toIntervalDay(7)",
-            },
-            "columns": [
-                {"name": "database", "type": "String"},
-                {"name": "start_datetime", "type": "DateTime"},
-                {"name": "query", "type": "String"},
-                {"name": "query_normalized", "type": "String"},
-                {"name": "error_code", "type": "Int32"},
-                {"name": "error", "type": "Nullable(String)"},
-                {"name": "duration", "type": "UInt64"},
-                {"name": "read_rows", "type": "UInt64"},
-                {"name": "read_bytes", "type": "UInt64"},
-                {"name": "result_rows", "type": "UInt64"},
-                {"name": "result_bytes", "type": "UInt64"},
-            ],
-        },
-        {
-            "name": "organization.bi_stats",
-            "description": "Aggregates the stats in organization.bi_stats_rt by day.",
-            "dateColumn": "date",
-            "engine": {"engine": "MergeTree", "sorting_key": "database, cityHash64(query_normalized), date"},
-            "columns": [
-                {"name": "database", "type": "String"},
-                {"name": "date", "type": "Date"},
-                {"name": "query_normalized", "type": "String"},
-                {"name": "view_count", "type": "UInt64"},
-                {"name": "error_count", "type": "UInt64"},
-                {"name": "avg_duration_state", "type": "AggregateFunction(avg, Float32)"},
-                {
-                    "name": "quantile_timing_state",
-                    "type": "AggregateFunction(quantilesTiming(0.9, 0.95, 0.99), Float64)",
-                },
-                {"name": "read_bytes_sum", "type": "UInt64"},
-                {"name": "read_rows_sum", "type": "UInt64"},
-                {"name": "avg_result_rows_state", "type": "AggregateFunction(avg, Float32)"},
-                {"name": "avg_result_bytes_state", "type": "AggregateFunction(avg, Float32)"},
-            ],
-        },
         {
             "name": "organization.metrics_logs",
             "description": "Metrics of your organization's dedicated clusters",

{tinybird-4.6.10.dev0 → tinybird-4.6.11}/tinybird/tb/__cli__.py

@@ -4,5 +4,5 @@ __description__ = 'Tinybird Command Line Tool'
 __url__ = 'https://www.tinybird.co/docs/forward/commands'
 __author__ = 'Tinybird'
 __author_email__ = 'support@tinybird.co'
-__version__ = '4.6.10.dev0'
-__revision__ = 'fa1549d'
+__version__ = '4.6.11'
+__revision__ = '7bdea3d'

{tinybird-4.6.10.dev0 → tinybird-4.6.11}/tinybird/tb/client.py

@@ -546,20 +546,36 @@ class TinyB:
     def datasource_sync(self, datasource_id: str):
         return self._req(f"/v0/datasources/{datasource_id}/scheduling/runs", method="POST", data="")
 
-    def datasource_sample(self, datasource_name: str, max_files: int = 1) -> Dict[str, Any]:
-        """Start a sample import job for an S3/GCS connected datasource.
+    def datasource_sample(
+        self,
+        datasource_name: str,
+        max_files: int = 1,
+        rows: Optional[int] = None,
+        max_bytes: Optional[str] = None,
+        full_export: bool = False,
+    ) -> Dict[str, Any]:
+        """Start a sample import job for an S3/GCS/DynamoDB connected datasource.
 
         Args:
             datasource_name: Name of the datasource to import sample data into
-            max_files: Maximum number of files to import (default 1, max 10)
+            max_files: Maximum number of files to import for blob storage connectors (default 1, max 10)
+            rows: For DynamoDB, the maximum number of rows to scan and import (mutually exclusive with max_bytes)
+            max_bytes: For DynamoDB, the maximum approximate JSONEachRow bytes to import, capped by the server's
+                workspace limit (mutually exclusive with rows)
+            full_export: For DynamoDB, trigger a full PITR export instead of a bounded scan
 
         Returns:
             dict with job info including id, job_id, job_url, job, status
         """
+        payload: Dict[str, Any] = {"max_files": max_files, "full_export": full_export}
+        if rows is not None:
+            payload["rows"] = rows
+        if max_bytes is not None:
+            payload["max_bytes"] = max_bytes
         return self._req(
             f"/v0/datasources/{datasource_name}/sample",
             method="POST",
-            data=json.dumps({"max_files": max_files}),
+            data=json.dumps(payload),
         )
 
     def datasource_scheduling_state(self, datasource_id: str):

{tinybird-4.6.10.dev0 → tinybird-4.6.11}/tinybird/tb/modules/common.py

@@ -1614,6 +1614,7 @@ def run_aws_iamrole_connection_flow(
     connection_name: str,
     policy: str,
     local_unavailable: bool = False,
+    env: str = "local",
 ) -> Tuple[str, str, Optional[TinyB], Optional[TinyB]]:
     """
     Run the interactive AWS IAM Role connection flow for S3 or DynamoDB.
@@ -1628,6 +1629,9 @@ def run_aws_iamrole_connection_flow(
         connection_name: The name for the connection being created.
         policy: The access policy type ('read' or 'write').
         local_unavailable: If True, local environment is unavailable (e.g., missing AWS credentials).
+        env: The active target environment ('local' or 'cloud'). When not local, the
+            passed-in `client` is reused as the cloud client so secrets land in the
+            workspace the command targets (including branches).
 
     Returns:
         A tuple containing:
@@ -1736,12 +1740,15 @@ def run_aws_iamrole_connection_flow(
 
     if use_cloud:
         try:
-            cloud_client = TinyB(
-                token=config.get("token", ""),
-                host=config.get("host", ""),
-                staging=False,
-                request_from=getattr(client, "request_from", None),
-            )
+            if env != "local":
+                cloud_client = client
+            else:
+                cloud_client = TinyB(
+                    token=config.get("token", ""),
+                    host=config.get("host", ""),
+                    staging=False,
+                    request_from=getattr(client, "request_from", None),
+                )
         except Exception as e:
             click.echo(FeedbackManager.warning(message=f"Failed to initialize cloud client: {e}"))
             click.echo(FeedbackManager.warning(message="Continuing without cloud environment."))

{tinybird-4.6.10.dev0 → tinybird-4.6.11}/tinybird/tb/modules/connection_dynamodb.py

@@ -158,6 +158,7 @@ def connection_create_dynamodb(
         connection_name=connection_name,
         policy="read",
         local_unavailable=local_aws_unavailable,
+        env=env,
     )
 
     unique_suffix = uuid.uuid4().hex[:8]

{tinybird-4.6.10.dev0 → tinybird-4.6.11}/tinybird/tb/modules/connection_s3.py

@@ -363,6 +363,7 @@ def connection_create_s3(
         connection_name=connection_name,
         policy=access_type.lower(),
         local_unavailable=local_aws_unavailable,
+        env=env,
     )
     unique_suffix = uuid.uuid4().hex[:8]  # Use first 8 chars of a UUID for brevity
     secret_name = f"s3_role_arn_{connection_name}_{unique_suffix}"

{tinybird-4.6.10.dev0 → tinybird-4.6.11}/tinybird/tb/modules/datasource.py

@@ -862,20 +862,50 @@ def datasource_sync(ctx: Context, datasource_name: str, yes: bool):
     default=False,
     help="Wait for the import job to finish",
 )
+@click.option(
+    "--rows",
+    default=None,
+    type=int,
+    help="For DynamoDB, the maximum number of rows to scan and import (default 1500; mutually exclusive with --max-bytes)",
+)
+@click.option(
+    "--max-bytes",
+    default=None,
+    type=str,
+    help="For DynamoDB, the maximum approximate JSONEachRow bytes to import, e.g. 500MB (capped at 10GB by default; mutually exclusive with --rows)",
+)
+@click.option(
+    "--full-export",
+    is_flag=True,
+    default=False,
+    help="For DynamoDB, trigger a full PITR export instead of a bounded sample (mutually exclusive with --rows and --max-bytes)",
+)
 @click.pass_context
-def datasource_sample(ctx: Context, datasource_name: str, max_files: int, wait: bool) -> None:
-    """Import sample data from a datasource connected to an S3 or GCS bucket.
-
-    This command only works with datasources that have IMPORT_CONNECTION_NAME and
-    IMPORT_BUCKET_URI configured (i.e., datasources ingesting from S3 or GCS).
-    It imports a limited number of files from the bucket URI pattern, useful for
-    testing data pipelines in branches without importing the entire dataset.
+def datasource_sample(
+    ctx: Context,
+    datasource_name: str,
+    max_files: int,
+    wait: bool,
+    rows: Optional[int],
+    max_bytes: Optional[str],
+    full_export: bool,
+) -> None:
+    """Import sample data from a datasource connected to S3, GCS, or DynamoDB.
+
+    For S3 and GCS, this imports a limited number of files from the bucket URI
+    pattern. For DynamoDB, this scans and imports a bounded sample limited by
+    either --rows or --max-bytes (defaulting to 1500 rows), or --full-export to
+    trigger a PITR export of the whole table.
 
     By default, returns immediately with job info. Use --wait to block until complete.
 
     Examples:
         tb --branch=my_branch datasource sample my_s3_ds
         tb --branch=my_branch datasource sample my_s3_ds --max-files 3 --wait
+        tb --branch=my_branch datasource sample my_dynamodb_ds --wait
+        tb --branch=my_branch datasource sample my_dynamodb_ds --rows 100000 --wait
+        tb --branch=my_branch datasource sample my_dynamodb_ds --max-bytes 1GB --wait
+        tb --branch=my_branch datasource sample my_dynamodb_ds --full-export --wait
     """
     from tinybird.tb.modules.common import wait_job
     from tinybird.tb.modules.job_common import echo_job_url
@@ -884,10 +914,32 @@ def datasource_sample(ctx: Context, datasource_name: str, max_files: int, wait:
         client: TinyB = ctx.obj["client"]
         config = ctx.obj.get("config", {})
 
+        if rows is not None and max_bytes is not None:
+            raise CLIDatasourceException(
+                FeedbackManager.error(message="--rows and --max-bytes are mutually exclusive; pass only one.")
+            )
+
+        if full_export and (rows is not None or max_bytes is not None):
+            raise CLIDatasourceException(
+                FeedbackManager.error(message="--full-export cannot be combined with --rows or --max-bytes.")
+            )
+
+        if full_export:
+            click.echo(
+                FeedbackManager.warning(
+                    message=(
+                        "DynamoDB full export samples will import the whole table. "
+                        "Use --rows or --max-bytes without --full-export for a bounded sample."
+                    )
+                )
+            )
+
         click.echo(FeedbackManager.info(message=f"Starting sample import for {datasource_name}..."))
 
         # Start the job
-        result = client.datasource_sample(datasource_name, max_files=max_files)
+        result = client.datasource_sample(
+            datasource_name, max_files=max_files, rows=rows, max_bytes=max_bytes, full_export=full_export
+        )
 
         job_id = result.get("job_id") or result.get("id")
         if not job_id:

{tinybird-4.6.10.dev0 → tinybird-4.6.11}/tinybird/tb/modules/logs.py

@@ -21,7 +21,6 @@ from tinybird.tb.modules.feedback_manager import FeedbackManager
 
 LOG_SOURCES: Tuple[str, ...] = (
     "tinybird.pipe_stats_rt",
-    "tinybird.bi_stats_rt",
     "tinybird.block_log",
     "tinybird.datasources_ops_log",
     "tinybird.endpoint_errors",
@@ -39,7 +38,6 @@ DEFAULT_LOG_SOURCES: Tuple[str, ...] = (
 
 TIMESTAMP_COLUMNS: Dict[str, str] = {
     "tinybird.pipe_stats_rt": "start_datetime",
-    "tinybird.bi_stats_rt": "start_datetime",
     "tinybird.block_log": "timestamp",
     "tinybird.datasources_ops_log": "timestamp",
     "tinybird.endpoint_errors": "start_datetime",
@@ -61,16 +59,6 @@ RELEVANT_DETAIL_FIELDS: Dict[str, Tuple[str, ...]] = {
         "read_bytes",
         "result_rows",
     ),
-    "tinybird.bi_stats_rt": (
-        "query_normalized",
-        "error_code",
-        "error",
-        "duration",
-        "read_rows",
-        "read_bytes",
-        "result_rows",
-        "result_bytes",
-    ),
     "tinybird.block_log": (
         "datasource_name",
         "status",
@@ -207,7 +195,7 @@ _TEMPORAL_DETAIL_FIELDS = {
 _DURATION_DETAIL_FIELDS = {"duration", "elapsed_time", "processing_time"}
 _ROW_COUNT_DETAIL_FIELDS = {"rows", "read_rows", "written_rows", "result_rows", "quarantine_lines"}
 _BYTE_COUNT_DETAIL_FIELDS = {"bytes", "read_bytes", "result_bytes", "written_bytes"}
-_MILLISECOND_DURATION_SOURCES = {"tinybird.bi_stats_rt"}
+_MILLISECOND_DURATION_SOURCES: Set[str] = set()
 
 
 def _to_iso_utc(dt: datetime) -> str:

{tinybird-4.6.10.dev0 → tinybird-4.6.11}/tinybird.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: tinybird
-Version: 4.6.10.dev0
+Version: 4.6.11
 Summary: Tinybird Command Line Tool
 Home-page: https://www.tinybird.co/docs/forward/commands
 Author: Tinybird
@@ -52,6 +52,16 @@ The Tinybird command-line tool allows you to use all the Tinybird functionality
 Changelog
 ----------
 
+4.6.11
+********
+
+- `Added` `tb datasource sample` support for DynamoDB connectors.
+
+4.6.10
+********
+
+- `Removed` `tinybird.bi_stats_rt` from `tb logs` sources. The BI Connector `bi_stats` / `bi_stats_rt` service datasources are deprecated.
+
 4.6.9
 *******