mostlyright-data 0.21.3__tar.gz → 0.22.0__tar.gz

{mostlyright_data-0.21.3 → mostlyright_data-0.22.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mostlyright-data
-Version: 0.21.3
+Version: 0.22.0
 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-0.21.3 → mostlyright_data-0.22.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "mostlyright-data"
-version = "0.21.3"
+version = "0.22.0"
 description = "Mostly Right hosted CLI for reviewed datasets"
 readme = "README.md"
 requires-python = ">=3.11"

{mostlyright_data-0.21.3 → mostlyright_data-0.22.0}/skills/mr-data-build/SKILL.md

@@ -1867,8 +1867,10 @@ Write it as a source whose connector is that coordinate plus a `collection` memb
 
 - `collection.discovery` says how the corpus is LISTED — `json_api` with RFC 6901 pointers,
   `html_index` with the reader's closed selectors, `sitemap`, or an `explicit` member list — and
-  which pagination grammar the listing uses. The run follows only that grammar and never a link
-  found inside a detail page.
+  which pagination grammar the listing uses. `source_rows` instead names an upstream source and
+  its `url_column`, optionally `base_url_column`: acquisition runs upstream first, resolves and
+  deduplicates links, and preserves incomplete upstream coverage. Use only declared dependencies;
+  this is not arbitrary recursive crawling. It requires the matching Studio API/worker release.
 - `collection.pages` says what may be fetched and how much: `allowed_origins` (which must include
   the discovery address's own origin), `max_pages`, `max_fetches_per_run`, `concurrency` (1 or 2),
   `min_interval_seconds` as a whole number of seconds (one or more), `request_timeout_seconds`,
@@ -1877,7 +1879,8 @@ Write it as a source whose connector is that coordinate plus a `collection` memb
 - `limits.max_requests` is REQUIRED and bounds every request the run makes, discovery and detail
   pages together. `limits.max_source_bytes` bounds the fetched bytes; `limits.max_rows` clamps the
   merged relation.
-- The Reader pin is required, must be `html.web_extract`, and is the SAME settings for every page.
+- The Reader pin is required, must be `html.web_extract`, `html.tabular`, `json.tabular`, or
+  `xml.tabular`, and uses the same settings for every page.
 
 **`limits.max_requests` is charged per HTTP request, redirect hops and retries included** — a page
 that redirects once costs two. Registration only checks that
@@ -1888,6 +1891,10 @@ redirects are likely — trailing slashes, `http`→`https`, `www`, which is mos
 `limits.max_requests >= discovery.max_requests + 2 * max_fetches_per_run`. A budget larger than the
 corpus can absorb costs nothing.
 
+For a dependent graph, declare recipe-level `acquisition_limits` with `max_requests` and
+`max_source_bytes`. Every source must explicitly state both ceilings; their sums must fit the
+totals. Unused capacity does not transfer between sources.
+
 The relation the transform reads is the reader's columns plus `page_id`, `page_url`,
 `page_fetched_at`, `page_content_sha256`, `page_revision`, `page_discovered_at` and `page_ordinal`.
 Those names are reserved: a reader that declares one is a registration refusal. Select them in the
@@ -2024,6 +2031,7 @@ decoder. Zero matches and multiple matches both refuse.
 | `html.tabular@1.0.0` | Absolute record element path and relative text/attribute field selectors; fields are required unless `required: false`. |
 | `html.web_extract@1.0.0` | `mode: dom` with closed CSS-like record/field selectors, or `mode: json` with an inert JSON script selector and RFC 6901 field pointers. |
 | `html.web_extract@1.1.0` | Same settings as 1.0.0; extracted text follows DOM order, with one space at block-element boundaries and `<br>` and none between inline runs. |
+| `html.web_extract@1.2.0` | Same text as 1.1.0; bounded integer `:nth-child(N)` / `:nth-of-type(N)` and field `scope: ancestor` with `ancestor_selector`. Requires the corresponding deployed certification. |
 | `protobuf.tabular@1.0.0` | Digest-pinned base64 FileDescriptorSet, fully-qualified message type, `single` or `length_delimited` framing, and fields with an explicit repeated `explode` or `refuse` choice. |
 | `parquet.tabular@1.0.0` | Optional `columns` selects a bounded ordered Parquet projection. |
 | `xbrl.facts@1.0.0` | `document_kind` (`xbrl` or constrained XML `ixbrl`) and exact namespace/name fact projection; contexts, units, and metadata remain evidence fields, not joins. |

{mostlyright_data-0.21.3 → mostlyright_data-0.22.0}/src/mostlyright/data_harness/thin/v4.py

@@ -105,7 +105,7 @@ 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 = "2a83dda60e84c166f95ea18af747985bfeeb5887cb48d2c72d4335e83720dc37"
+PINNED_V4_OPENAPI_SOURCE_SHA256 = "2b854c3c4fae7c30a6219ee99ea814f80c57fbf0251ed22a0b66b002b598e6f7"
 PINNED_V4_CONTRACT_VERSION = "4.7.0"
 
 # --------------------------------------------------------------------------------------------