mostlyright-data 0.29.4__tar.gz → 0.29.6__tar.gz

{mostlyright_data-0.29.4 → mostlyright_data-0.29.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mostlyright-data
-Version: 0.29.4
+Version: 0.29.6
 Summary: Mostly Right hosted CLI for reviewed datasets
 Project-URL: Homepage, https://mostlyright.md/
 Project-URL: Documentation, https://mostlyright.md/docs/guides/cli/

{mostlyright_data-0.29.4 → mostlyright_data-0.29.6}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "mostlyright-data"
-version = "0.29.4"
+version = "0.29.6"
 description = "Mostly Right hosted CLI for reviewed datasets"
 readme = "README.md"
 requires-python = ">=3.11"

{mostlyright_data-0.29.4 → mostlyright_data-0.29.6}/skills/mr-data-build/references/5-draft-one-recipe-document-one-call.md

@@ -455,11 +455,12 @@ from the accepted subset — `Cel`, `ug/m3`, `km/h`, `hPa`, `{count}` and the re
 out in [Units](https://mostlyright.md/docs/reference/units/). Write the code rather than a name:
 `ug/m3` composes and `microgram_per_cubic_meter` does not.
 
-**Nothing resolves the code, so there is no `UNIT_*` refusal to lean on.** The recipe schema bounds
-the length of `unit` and nothing else; registration checks only that `units[].column` names a
-declared column and answers `422 RECIPE_DOCUMENT_INCOHERENT` at `/units/N/column` when it does not;
-the run never reads `units` at all. A code outside the subset therefore costs nothing at build time
-and costs every reader afterwards, and a column declared in metres that holds feet is caught by
+**Registration resolves the code and reads no data.** The recipe schema bounds the length of
+`unit`; registration then checks that `units[].column` names a declared column, answering
+`422 RECIPE_DOCUMENT_INCOHERENT` at `/units/N/column` when it does not, and resolves each
+`units[].unit` against the subset, answering the same code at `/units/N/unit` when it cannot.
+`mr-data recipe` does not resolve the code locally, so that refusal arrives from registration. The
+run does not read `units`, so a column declared in metres that holds feet is caught by
 nothing. Convert in the statement, then declare the unit of what the column ends up holding. Leave a
 column out of `units` rather than declare something approximate — a density, a rate, anything whose
 unit is genuinely new. `none` is not a unit and does not become one. Remember that the two

{mostlyright_data-0.29.4 → mostlyright_data-0.29.6}/skills/mr-data-build/references/making-a-table-incremental.md

@@ -105,8 +105,9 @@ Studio records the answer as one classification per source:
 | a `window` carrying a `request` | `window` | `acquire_incremental` |
 | none of those | `resync_only` | `resync_required` |
 
-The rows are in Studio's precedence order, and the first match wins. A source that states both
-`closed: true` and a request window is `closed`, and its window is never read. One `resync_only`
+The rows are in Studio's precedence order, and the first match wins. A source may not state both
+`closed: true` and a request window: registration refuses that pair with
+`422 RECIPE_DOCUMENT_INCOHERENT` at `/sources/N/closed`. One `resync_only`
 source makes the whole table resync-only, however truthful its siblings are. Say which sources you
 left `resync_only` and why, because a recipe that never asked the question registers the same way
 as one that did.

{mostlyright_data-0.29.4 → mostlyright_data-0.29.6}/src/mostlyright/data_harness/thin/session.py

@@ -75,6 +75,9 @@ CLOUD_DATASETS_LIST_PATH = "/api/cli/datasets"
 # Projection repair after a Studio metadata write, without a publication mutation.
 CLOUD_DATASET_IDENTITY_PATH = "/api/cli/datasets/{dataset_id}/identity"
 
+# Shared UI/CLI archive orchestration, including public projection withdrawal.
+CLOUD_DATASET_ARCHIVE_PATH = "/api/cli/datasets/{dataset_id}/archive"
+
 #: The one Cloud address a Dataset has. ``mostlyright-cloud`` serves it at this route with
 #: section suffixes, and a run has no page of its own: its evidence lives on this page's Harness
 #: card, so a receipt names its run with :func:`run_dashboard_url` as a query member here rather
@@ -687,6 +690,7 @@ __all__ = [
     "CLOUD_APPROVAL_DASHBOARD_PATH",
     "CLOUD_DATASETS_LIST_PATH",
     "CLOUD_DATASET_ACCESS_PATH",
+    "CLOUD_DATASET_ARCHIVE_PATH",
     "CLOUD_DATASET_DASHBOARD_PATH",
     "CLOUD_DATASET_RESOLVED_SCHEMA",
     "CLOUD_DATASET_RESOLVE_PATH",

{mostlyright_data-0.29.4 → mostlyright_data-0.29.6}/src/mostlyright/data_harness/thin/v4.py

@@ -147,8 +147,8 @@ 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 = "bf6312e73ba81725f9146dd6c8b10ff47ae57d1822ba695991aec03931d17d4d"
-PINNED_V4_CONTRACT_VERSION = "4.26.0"
+PINNED_V4_OPENAPI_SOURCE_SHA256 = "1f30e109b81f6aa55c00c8999fd877b6678b7e0bea617707d26e7a040380f98b"
+PINNED_V4_CONTRACT_VERSION = "4.27.0"
 
 #: The ``schema_version`` every command body that predates 4.14.0 stamps: ``dataset activity``,
 #: ``table rename``, ``table archive`` and ``dataset archive``. It is the number the 0.25 line

{mostlyright_data-0.29.4 → mostlyright_data-0.29.6}/src/mostlyright/data_harness/thin/v4_datasets.py

@@ -127,6 +127,7 @@ from mostlyright.data_harness.thin.narrative import (
 from mostlyright.data_harness.thin.runs import new_idempotency_key
 from mostlyright.data_harness.thin.session import (
     CLOUD_DATASET_ACCESS_PATH,
+    CLOUD_DATASET_ARCHIVE_PATH,
     CLOUD_DATASET_IDENTITY_PATH,
     CLOUD_DATASET_RESOLVE_PATH,
     CLOUD_DATASET_RESOLVED_SCHEMA,
@@ -149,7 +150,6 @@ from mostlyright.data_harness.thin.stream import RunEventStream
 from mostlyright.data_harness.thin.transport import ThinLaneError, Transport, UrlLibTransport
 from mostlyright.data_harness.thin.v4 import (
     ARCHIVE_DATASET_PATH,
-    COMMAND_REQUEST_VERSION_FLOOR,
     CREATE_DATASET_PATH,
     DATASET_CURRENT_STATE_PATH,
     DATASET_EVENT_HISTORY_PATH,
@@ -448,6 +448,14 @@ class CloudDatasetAccessClient(CloudClient):
     credential header and the refusal folding to drift.
     """
 
+    def archive_dataset(self, dataset_id: str, confirmation_name: str) -> dict[str, Any]:
+        return self.call(
+            "POST",
+            CLOUD_DATASET_ARCHIVE_PATH.format(dataset_id=dataset_id),
+            act="archive this dataset and withdraw its public listings",
+            body={"confirmation_name": confirmation_name},
+        )
+
     def sync_dataset_identity(self, dataset_id: str) -> dict[str, Any]:
         """Carry Studio's current metadata into Cloud's existing public projection."""
 
@@ -458,7 +466,6 @@ class CloudDatasetAccessClient(CloudClient):
             body={},
         )
 
-
     def list_datasets(self, *, limit: int | None = None) -> dict[str, Any]:
         """Name every dataset this workspace holds, most recently updated first.
 
@@ -1838,75 +1845,46 @@ def write(
 
 
 def archive(
-    args: argparse.Namespace, *, client: StudioV4DatasetClient | None = None
+    args: argparse.Namespace, *, client: CloudDatasetAccessClient | None = None
 ) -> dict[str, Any]:
-    """``mr-data dataset archive DATASET_ID --confirm-name TITLE``: retire the page, free the name.
-
-    ⚠ THE TYPED TITLE IS COMPARED HERE AS WELL AS BY STUDIO, WHICH IS THE OPPOSITE CHOICE FROM
-    ``mr-data table archive`` AND THE REASON IS THAT THE READ IS ALREADY HAPPENING. This write is
-    fenced on the dataset's version, so the page has to be read before it can be sent; the title
-    arrives in the same body, the comparison costs nothing, and the fence is what makes it safe --
-    a title that changed after the read moves the version, and the conditional refuses. Where a
-    read would have to be bought only to give a second opinion, this lane does not buy it.
-
-    ⚠ AND IT IS NOT A DELETION. Runs, artifacts, versions and the decision record all stay. What
-    the command ends is the page's claim on its title and its place in the workspace's listing.
-    """
-
+    """Use the UI's Cloud archive ceremony; a Studio-only tombstone is incomplete."""
     dataset_id = identifier(getattr(args, "dataset_id", None) or "", "dataset identifier")
     confirmation = getattr(args, "confirm_name", None)
     if not isinstance(confirmation, str) or not confirmation.strip():
         raise ThinLaneError(
             "THIN_REQUEST_INVALID",
             "mr-data dataset archive needs the dataset's current title typed out: "
-            f"--confirm-name TITLE. mr-data dataset show {dataset_id} prints the title Studio "
-            "holds",
+            "--confirm-name TITLE",
         )
     stated = confirmation.strip()
-    selected = client or _client(args)
-    record = selected.dataset(dataset_id)
-    version = _version(record)
-    held = record.get("name")
-    if isinstance(held, str) and held.strip() != stated:
+    if client is None:
+        credentials = resolve_cloud_credentials()
+        require_device_key(credentials)
+        selected = CloudDatasetAccessClient(credentials)
+    elif isinstance(client, CloudDatasetAccessClient):
+        selected = client
+    else:
         raise ThinLaneError(
-            "THIN_CONFIRMATION_MISMATCH",
-            f"this dataset is called {held!r} and --confirm-name said {stated!r}. Archiving "
-            "releases the title, so the title is what confirms it: type the one on the page, or "
-            "check you have the dataset you meant",
-        )
-    try:
-        archived = selected.archive_dataset(
-            dataset_id,
-            body={
-                "schema_version": COMMAND_REQUEST_VERSION_FLOOR,
-                "workspace_id": str(selected.session.workspace_id),
-                "confirmation_name": stated,
-            },
-            expected_version=version,
+            "THIN_REQUEST_INVALID", "dataset archive requires the Cloud archive client"
         )
-    except ThinLaneError as refusal:
-        if not stale_version(refusal):
-            raise
-        # ⚠ NAMED, AND NOT RETRIED, WHICH IS THE ONE PLACE THIS DIFFERS FROM `write` AND `rename`.
-        # Those two replay at the new version because what they write does not depend on what
-        # changed underneath them. This does: the title typed to confirm the archive is exactly
-        # what a racing `dataset set` may have just rewritten, so a silent retry could archive a
-        # page under a title that is no longer its own. What it gets instead is the same sentence
-        # the other two end on, because it is the same thing that happened.
+    answer = selected.archive_dataset(dataset_id, stated)
+    if (
+        answer.get("schema_version") != "mostlyright-dataset-archive.v1"
+        or answer.get("status") != "dataset_archived"
+        or answer.get("dataset_id") != dataset_id
+        or answer.get("name") != stated
+    ):
         raise ThinLaneError(
-            "THIN_DATASET_VERSION_CONFLICT",
-            f"the dataset moved between the read at version {version} and this archive; somebody "
-            f"else is editing it. Read it with mr-data dataset show {dataset_id}, check the title "
-            "is still the one you typed, and archive again",
-        ) from refusal
+            "THIN_RESPONSE_INVALID",
+            "Cloud did not confirm this dataset's complete archive",
+        )
     return {
         "schema_version": ARCHIVE_SCHEMA,
         "status": "dataset_archived",
         "lane": "hosted",
-        "dataset_id": _dataset_id(archived, verb="archive") if archived else dataset_id,
+        "dataset_id": dataset_id,
         "name": stated,
-        "version": archived.get("version"),
-        "dashboard_url": dataset_dashboard_url(selected.session.cloud_url, dataset_id),
+        "dashboard_url": dataset_dashboard_url(selected.cloud_url, dataset_id),
         "note": (
             f"The dataset is retired and the title {stated!r} is free for another one. Nothing "
             "built was deleted: every run, artifact, version and decision cell stays where it is."
@@ -2488,7 +2466,6 @@ def watch(
     }
 
 
-
 def listing(
     args: argparse.Namespace, *, client: CloudDatasetAccessClient | None = None
 ) -> dict[str, Any]: