mostlyright-data 0.21.1__tar.gz → 0.21.2__tar.gz

{mostlyright_data-0.21.1 → mostlyright_data-0.21.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mostlyright-data
-Version: 0.21.1
+Version: 0.21.2
 Summary: Mostly Right hosted CLI for reviewed datasets
 Project-URL: Homepage, https://mostlyright.md/
 Project-URL: Documentation, https://mostlyright.md/docs/guides/cli/
@@ -135,6 +135,7 @@ worker executables or image publisher.
 - [Aggregate a stream into bars](https://mostlyright.md/docs/recipes/stream-to-bars/)
 - [Use a public dataset](https://mostlyright.md/docs/guides/use-public-datasets/)
 - [Certified document extraction](docs/DOCUMENT-EXTRACTION.md)
+- [Use a table to drive a stream's market roster](docs/TABLE-DRIVEN-DISCOVERY.md)
 
 Use `mr-data --help` for the full command list and options. Commands that support
 `--json` write one JSON object.

{mostlyright_data-0.21.1 → mostlyright_data-0.21.2}/README.md

@@ -123,6 +123,7 @@ worker executables or image publisher.
 - [Aggregate a stream into bars](https://mostlyright.md/docs/recipes/stream-to-bars/)
 - [Use a public dataset](https://mostlyright.md/docs/guides/use-public-datasets/)
 - [Certified document extraction](docs/DOCUMENT-EXTRACTION.md)
+- [Use a table to drive a stream's market roster](docs/TABLE-DRIVEN-DISCOVERY.md)
 
 Use `mr-data --help` for the full command list and options. Commands that support
 `--json` write one JSON object.

{mostlyright_data-0.21.1 → mostlyright_data-0.21.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "mostlyright-data"
-version = "0.21.1"
+version = "0.21.2"
 description = "Mostly Right hosted CLI for reviewed datasets"
 readme = "README.md"
 requires-python = ">=3.11"

{mostlyright_data-0.21.1 → mostlyright_data-0.21.2}/src/mostlyright/data_harness/thin/stream_venue.py

@@ -202,6 +202,20 @@ RESOURCE_MEMBERS: tuple[str, ...] = (
     "event_shape_descriptor",
     "bookmark",
     "expected_watermark",
+    "table_discovery",
+)
+
+# Only the public dependency summary is rendered. An API adding transport or snapshot fields
+# beneath this object must not make signed sessions or private source rows appear in CLI output.
+TABLE_DISCOVERY_MEMBERS: tuple[str, ...] = (
+    "table_id",
+    "table_version_id",
+    "resolution_id",
+    "status",
+    "source_completed_at",
+    "freshness_checked_at",
+    "freshness_deadline_at",
+    "last_error_code",
 )
 
 #: The members one registered document is rendered under, spelled the way Studio spells them.
@@ -705,7 +719,18 @@ def resource(record: Mapping[str, Any], *, id_member: str) -> dict[str, Any]:
     rendered: dict[str, Any] = {id_member: record.get(id_member)}
     for member in RESOURCE_MEMBERS:
         if member in record:
-            rendered[member] = record[member]
+            if member == "table_discovery":
+                summary = record[member]
+                if isinstance(summary, Mapping):
+                    selected = {
+                        name: value
+                        for name in TABLE_DISCOVERY_MEMBERS
+                        if isinstance(value := summary.get(name), str) and 0 < len(value) <= 256
+                    }
+                    if "table_id" in selected and "status" in selected:
+                        rendered[member] = selected
+            else:
+                rendered[member] = record[member]
     return rendered
 
 

{mostlyright_data-0.21.1 → mostlyright_data-0.21.2}/src/mostlyright/data_harness/thin/v4.py

@@ -54,16 +54,16 @@ from mostlyright.data_harness.thin.transport import ThinLaneError
 #: WHY A LATER NUMBER IS SAFE TO SEND, AND AGAINST WHICH STUDIO. Studio's ``common.schema.json``
 #: gives command bodies ``request_schema_version`` -- deliberately wider than the ``4.0.0``
 #: envelope constant every V4 RESPONSE still stamps -- and the pinned copy of it admits ``4.0.0``,
-#: ``4.1.0``, ``4.2.0``, ``4.3.0``, ``4.4.0``, ``4.5.0`` and ``4.6.0``. Every command this module
-#: sends binds
+#: ``4.1.0``, ``4.2.0``, ``4.3.0``, ``4.4.0``, ``4.5.0``, ``4.6.0`` and ``4.7.0``. Every command
+#: this module sends binds
 #: that wider definition
 #: (``test_every_command_this_client_stamps_binds_the_wide_request_version``), so a body carrying
 #: this number is accepted by a Studio AT OR AFTER THE PINNED COMMIT.
 #:
 #: ⚠ AND NOT BY ONE BEFORE IT. Studio validates the body against that enum at request time, so
 #: this number is a DEPLOY ORDERING and not just a pin: ``4.2.0`` entered the enum in studio#531,
-#: ``4.3.0`` in studio#533, ``4.4.0`` in studio#552, ``4.5.0`` in studio#644 and ``4.6.0`` in
-#: studio#659, and a release of
+#: ``4.3.0`` in studio#533, ``4.4.0`` in studio#552, ``4.5.0`` in studio#644, ``4.6.0`` in
+#: studio#659 and ``4.7.0`` in Studio's legacy-normalization lane, and a release of
 #: this package that reaches a Studio older than those turns four commands -- ``dataset activity``,
 #: ``table rename``, ``table archive`` and ``dataset archive`` -- into ``422``s that used to be
 #: accepted. That is the whole reason this constant may only be raised in the ``make repin`` commit
@@ -92,6 +92,12 @@ from mostlyright.data_harness.thin.transport import ThinLaneError
 #: repinned against those bytes stamps it on every command it sends, which is why the enum in
 #: ``common.schema.json`` had to admit it and why the deploy ordering above covers it too.
 #:
+#: ⚠ ``4.7.0`` ADDS THE PUBLIC REQUEST/CANCEL SURFACE FOR STUDIO'S SOURCE-FREE LEGACY
+#: NORMALIZER. It is deliberately recorded in ``UNUSED_STUDIO_PATHS``: choosing the two legacy
+#: predecessor coordinates is Studio's recovery flow, and the thin client neither holds nor
+#: lists those reader inputs. The pin still rises because ordinary command bodies stamp the exact
+#: version Studio's common request grammar now declares.
+#:
 #: ⚠ AND THE WORKER SIDE OF THAT DELETION IS A DEPLOY ORDERING OF ITS OWN, in the OPPOSITE
 #: direction from the one above. ``run_execution_v4``'s job parser compares an EXACT field set, and
 #: ``source_collection_protocol``, ``source_collection`` and ``source_collection_inputs`` are no
@@ -99,8 +105,8 @@ from mostlyright.data_harness.thin.transport import ThinLaneError
 #: ``JOB_INVALID`` outright, which in production was every refresh a collection epoch was offered
 #: for rather than only the collection runs. This package must not reach a Studio older than the
 #: commit it pins; ``docs/V4-WORKER-PROTOCOL.md`` states it beside the layout's own ordering rule.
-PINNED_V4_OPENAPI_SOURCE_SHA256 = "b88ef1ea9535232f331bb1337d6a9d0def27e4759fb0a2f46085e481dabc395d"
-PINNED_V4_CONTRACT_VERSION = "4.6.0"
+PINNED_V4_OPENAPI_SOURCE_SHA256 = "2a83dda60e84c166f95ea18af747985bfeeb5887cb48d2c72d4335e83720dc37"
+PINNED_V4_CONTRACT_VERSION = "4.7.0"
 
 # --------------------------------------------------------------------------------------------
 # The routes
@@ -612,7 +618,7 @@ DECLARED_V4_PATHS: frozenset[str] = frozenset(
         # authentication alone -- see `CATALOG_SEARCH_PATH` for why a `workspace_id` would state
         # an isolation the answer does not have -- and the document version it arrived in,
         # `4.5.0`, was the pinned version when this route was promoted (the pin has since
-        # moved on to `4.6.0`). `thin/v4_catalog.py` was
+        # moved on to `4.7.0`). `thin/v4_catalog.py` was
         # written against the frozen cross-repo contract while Studio built its half, for the
         # reason the dataset surface was: a 422 is measured against a shape.
         CATALOG_SEARCH_PATH,