mostlyright-data 0.29.8__tar.gz → 0.29.9__tar.gz

{mostlyright_data-0.29.8 → mostlyright_data-0.29.9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mostlyright-data
-Version: 0.29.8
+Version: 0.29.9
 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-0.29.8 → mostlyright_data-0.29.9}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "mostlyright-data"
-version = "0.29.8"
+version = "0.29.9"
 description = "Mostly Right hosted CLI for reviewed datasets"
 readme = "README.md"
 requires-python = ">=3.11"

{mostlyright_data-0.29.8 → mostlyright_data-0.29.9}/src/mostlyright/data_harness/thin/recipe.py

@@ -80,11 +80,9 @@ SHOW_SCHEMA = f"{THIN_SCHEMA_PREFIX}-recipe-read.v1"
 READINESS_SCHEMA = f"{THIN_SCHEMA_PREFIX}-recipe-readiness.v1"
 PROPOSE_SCHEMA = f"{THIN_SCHEMA_PREFIX}-recipe-propose.v1"
 
-#: The bound on the document. The same number the authoring lane bounded one of its six documents
-#: by -- four times the contract's own 262144-byte ceiling on a canonical recipe -- rather than a
-#: second number chosen here, because this document is those six documents in one and the ceiling
-#: it has to clear is the canonical form's.
-MAX_DOCUMENT_BYTES = 4 * 262_144
+#: A plain input file may occupy up to Studio's 2 MiB body ceiling. Before submission,
+#: the complete canonical UTF-8 request envelope must also fit that ceiling.
+MAX_DOCUMENT_BYTES = v4.MAX_RECIPE_REQUEST_BYTES
 
 #: ``recipe.schema.json#/$defs/recipe_document``'s required members, in the order the schema lists
 #: them. Checked here before the network, for the reason every early refusal in this client
@@ -1187,6 +1185,9 @@ def register(
     """
 
     document = read_document(Path(args.target))
+    # UUIDs have fixed wire length. Refuse an oversized envelope before credentials,
+    # capability reads or delegation writes; the actual client checks it again.
+    v4.recipe_registration_body(document, "00000000-0000-0000-0000-000000000000")
     # New grammar must be refused as unserved before local lint can diagnose its shape.
     keyless = any(
         capability == "keyless_window" for _, capability in recipe_explain.gated_grammar(document)

{mostlyright_data-0.29.8 → mostlyright_data-0.29.9}/src/mostlyright/data_harness/thin/recipe_explain.py

@@ -39,6 +39,7 @@ from mostlyright.data_harness.thin.transport import ThinLaneError
 from mostlyright.data_harness.thin.v4 import (
     EXPLAIN_AND_FORECAST_REQUEST_VERSION,
     StudioV4Client,
+    check_recipe_request_size,
     identifier,
 )
 
@@ -1231,17 +1232,18 @@ def explain_document_at_studio(
     nothing, which is what makes it safe to ask before a registration.
     """
 
+    body = {
+        "schema_version": ROUTES_REQUEST_VERSION,
+        "workspace_id": str(client.session.workspace_id),
+        "document": dict(document),
+    }
+    check_recipe_request_size(body)
     try:
-        # The one inherited `_call` (thin/v4.py): the route rides the same transport, byte
-        # ceiling and refusal translation as every other V4 call.
+        # The one inherited `_call` carries the ordinary response ceiling.
         answer = client._call(
             "POST",
             EXPLAIN_REFRESH_PATH,
-            body={
-                "schema_version": ROUTES_REQUEST_VERSION,
-                "workspace_id": str(client.session.workspace_id),
-                "document": dict(document),
-            },
+            body=body,
             expected=(200,),
         )
     except ThinLaneError as refusal:

{mostlyright_data-0.29.8 → mostlyright_data-0.29.9}/src/mostlyright/data_harness/thin/v4.py

@@ -39,6 +39,7 @@ from collections.abc import Mapping
 from typing import Any
 from uuid import UUID
 
+from mostlyright.data_harness.canonical import canonical_json_bytes
 from mostlyright.data_harness.thin.runs import StudioApiClient
 from mostlyright.data_harness.thin.transport import ThinLaneError
 
@@ -915,6 +916,35 @@ def identifier(value: str, field: str) -> str:
         raise ThinLaneError("THIN_REQUEST_INVALID", f"{value!r} is not a {field}") from error
 
 
+# Studio's API request-body middleware accepts at most 2 MiB. Bound the complete
+# UTF-8 wire envelope, not the recipe's character count or its formatted file size.
+MAX_RECIPE_REQUEST_BYTES = 2 * 1024 * 1024
+# A GET recipe includes the document plus identifiers and registration metadata.
+# Give that envelope 1 MiB headroom; ordinary JSON routes retain their 1 MiB cap.
+MAX_RECIPE_RESPONSE_BYTES = MAX_RECIPE_REQUEST_BYTES + 1024 * 1024
+
+
+def check_recipe_request_size(body: Mapping[str, Any]) -> None:
+    size = len(canonical_json_bytes(body))
+    if size > MAX_RECIPE_REQUEST_BYTES:
+        raise ThinLaneError(
+            "THIN_RECIPE_REQUEST_TOO_LARGE",
+            f"the serialized recipe request is {size} bytes; Studio accepts at most "
+            f"{MAX_RECIPE_REQUEST_BYTES} bytes including its request envelope. "
+            "Reduce the recipe before submitting it",
+        )
+
+
+def recipe_registration_body(document: Mapping[str, Any], workspace_id: str) -> dict[str, Any]:
+    body = {
+        "workspace_id": workspace_id,
+        "document": dict(document),
+        "require_category": True,
+    }
+    check_recipe_request_size(body)
+    return body
+
+
 class StudioV4Client(StudioApiClient):
     """The V4 routes, over the transport and the hardening :class:`StudioApiClient` already has.
 
@@ -993,11 +1023,7 @@ class StudioV4Client(StudioApiClient):
         return self._call(
             "POST",
             CREATE_RECIPE_PATH,
-            body={
-                "workspace_id": str(self.session.workspace_id),
-                "document": dict(document),
-                "require_category": True,
-            },
+            body=recipe_registration_body(document, str(self.session.workspace_id)),
             expected=(201,),
         )
 
@@ -1008,6 +1034,7 @@ class StudioV4Client(StudioApiClient):
             "GET",
             GET_RECIPE_PATH.format(recipe_id=identifier(recipe_id, "recipe identifier")),
             expected=(200,),
+            maximum=MAX_RECIPE_RESPONSE_BYTES,
         )
 
     def recipe_readiness(
@@ -1049,14 +1076,16 @@ class StudioV4Client(StudioApiClient):
     def explain_recipe_refresh(self, document: Mapping[str, Any]) -> dict[str, Any]:
         """Judge one unregistered recipe document for refresh, and read what this Studio serves."""
 
+        body = {
+            "schema_version": EXPLAIN_AND_FORECAST_REQUEST_VERSION,
+            "workspace_id": str(self.session.workspace_id),
+            "document": dict(document),
+        }
+        check_recipe_request_size(body)
         return self._call(
             "POST",
             EXPLAIN_RECIPE_REFRESH_PATH,
-            body={
-                "schema_version": EXPLAIN_AND_FORECAST_REQUEST_VERSION,
-                "workspace_id": str(self.session.workspace_id),
-                "document": dict(document),
-            },
+            body=body,
             expected=(200,),
         )
 

{mostlyright_data-0.29.8 → mostlyright_data-0.29.9}/src/mostlyright/data_harness/thin/v4_query.py

@@ -54,7 +54,6 @@ from mostlyright.data_harness.thin.session import (
 )
 from mostlyright.data_harness.thin.transport import ThinLaneError, UrlLibTransport
 from mostlyright.data_harness.thin.v4 import (
-    GET_RECIPE_PATH,
     GET_RUN_PATH,
     GET_RUN_QUERY_PATH,
     RUN_QUERY_PATH,
@@ -278,7 +277,7 @@ class StudioV4QueryClient(StudioV4Client):
     def recipe_source_ids(self, recipe_id: str) -> list[str]:
         """The sources a recipe registered, which a session opened for its dataset may probe."""
 
-        record = self._call("GET", GET_RECIPE_PATH.format(recipe_id=recipe_id), expected=(200,))
+        record = self.recipe(recipe_id)
         listed = record.get("source_ids")
         sources = (
             [item for item in listed if isinstance(item, str) and item]