loom-kernel 2.1.1__tar.gz → 2.1.2__tar.gz

{loom_kernel-2.1.1 → loom_kernel-2.1.2}/.github/workflows/release.yml

@@ -20,7 +20,7 @@ jobs:
   release:
     permissions:
       contents: write
-    uses: the-reacher-data/loom-actions/.github/workflows/release-on-label.yml@28ac23a8f40757a8e162ba9d4fdc847a69d13c1e # v1.2.2
+    uses: the-reacher-data/loom-actions/.github/workflows/release-on-label.yml@017878a375d4728129792fee009296635884b6d3 # v1.2.3
     with:
       build-distribution: true
       package-name: loom-kernel

{loom_kernel-2.1.1 → loom_kernel-2.1.2}/CHANGELOG.md

@@ -4,6 +4,17 @@
 
 ### prefect
 
+- **prefect:** a correlation id renders its datetime's UTC instant instead of
+  its wall clock. `strftime` printed the local reading and dropped the
+  offset, so `2026-06-03T00:00+02:00` and `2026-06-03T00:00Z` — two instants
+  two hours apart — produced the same id, and therefore the same manifest
+  store key: the second run opened the first one's manifest and could treat
+  processes it never ran as done. A naive value still means UTC and is
+  unaffected by the machine's zone. The id of a run whose `correlation_field`
+  carries a non-UTC offset changes (`2026-06-03T00:00+02:00` now keys
+  `20260602T220000`), so do not upgrade across a run you intend to resume
+  from its manifest.
+
 - **prefect:** `backfill_flow` resumes from a `start_from` submitted as a
   string. A flow's run parameters are not validated against its signature
   (`validate_parameters=False`), so `start_from` reached the chunk algebra

{loom_kernel-2.1.1 → loom_kernel-2.1.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: loom-kernel
-Version: 2.1.1
+Version: 2.1.2
 Summary: Loom Python project
 License-File: LICENSE
 Classifier: Typing :: Typed

{loom_kernel-2.1.1 → loom_kernel-2.1.2}/src/loom/prefect/flow/_run_name.py

@@ -14,6 +14,8 @@ _COMPACT_TIMESTAMP_FMT = "%Y%m%dT%H%M%S"
 
 
 def _render_value(value: Any) -> str:
+    if isinstance(value, datetime) and value.tzinfo is not None:
+        return value.astimezone(UTC).strftime(_COMPACT_TIMESTAMP_FMT)
     if isinstance(value, datetime | date):
         return value.strftime(_COMPACT_TIMESTAMP_FMT)
     return str(value)
@@ -61,9 +63,10 @@ def compute_correlation_id(
     """Return a stable correlation id for a flow run.
 
     Falls back to ``"<flow_name>-<random>"`` when no ``correlation_field``
-    is configured. Datetimes are rendered compactly so the value remains
-    safe to use in S3 keys, filesystem paths and the manifest store's
-    correlation_id validator.
+    is configured. A datetime is rendered compactly, by its UTC instant, so
+    the value remains safe to use in S3 keys, filesystem paths and the
+    manifest store's correlation_id validator, and so two different instants
+    never share an id.
 
     Args:
         flow_name: Logical ETL name.

{loom_kernel-2.1.1 → loom_kernel-2.1.2}/tests/unit/prefect/test_etl_flow.py

@@ -4,6 +4,7 @@ from __future__ import annotations
 
 import inspect
 import textwrap
+import time
 from datetime import UTC, date, datetime, timedelta, timezone
 from pathlib import Path
 
@@ -317,15 +318,14 @@ def test_aware_datetime_with_offset_passes_through() -> None:
     assert out["updated_at_from"].utcoffset() == timedelta(hours=2)
 
 
-def test_correlation_id_of_an_offset_bearing_string_uses_the_compact_form() -> None:
-    # The coercion feeds the correlation id as well as the params struct, so an
-    # offset-bearing string now keys the manifest store the way a naive one
-    # always did.
+def test_correlation_id_of_an_offset_bearing_string_uses_its_utc_instant() -> None:
+    # The coercion feeds the correlation id as well as the params struct, so the
+    # string keys the manifest store by the instant it names, not by its wall clock.
     resolved = _normalize_datetime_fields(
         {"updated_at_from": "2026-06-03T00:00:00+02:00"},
         _SampleParams,
     )
-    assert compute_correlation_id("etl", "updated_at_from", resolved) == "etl-20260603T000000"
+    assert compute_correlation_id("etl", "updated_at_from", resolved) == "etl-20260602T220000"
 
 
 def test_a_date_on_a_datetime_field_becomes_its_midnight_in_utc() -> None:
@@ -343,6 +343,33 @@ def test_a_date_field_keeps_its_date(tmp_path: Path) -> None:
     assert out["day"] == date(2026, 6, 3)
 
 
+def test_correlation_id_of_two_offsets_distinguishes_the_instants() -> None:
+    madrid = timezone(timedelta(hours=2))
+    at_madrid = {"updated_at_from": datetime(2026, 6, 3, 0, 0, tzinfo=madrid)}
+    at_utc = {"updated_at_from": datetime(2026, 6, 3, 0, 0, tzinfo=UTC)}
+    assert compute_correlation_id("etl", "updated_at_from", at_madrid) == "etl-20260602T220000"
+    assert compute_correlation_id("etl", "updated_at_from", at_utc) == "etl-20260603T000000"
+
+
+def test_correlation_id_of_a_date_keeps_its_day() -> None:
+    resolved = {"updated_at_from": date(2026, 6, 3)}
+    assert compute_correlation_id("etl", "updated_at_from", resolved) == "etl-20260603T000000"
+
+
+def test_correlation_id_of_a_naive_datetime_ignores_the_local_zone(
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    # A naive value means UTC here, so the machine's zone must not shift it.
+    monkeypatch.setenv("TZ", "America/New_York")
+    time.tzset()
+    try:
+        resolved = {"updated_at_from": datetime(2026, 6, 3, 0, 0)}
+        assert compute_correlation_id("etl", "updated_at_from", resolved) == "etl-20260603T000000"
+    finally:
+        monkeypatch.undo()
+        time.tzset()
+
+
 def test_non_datetime_fields_untouched() -> None:
     out = _normalize_datetime_fields(
         {"updated_at_from": None, "label": "hello", "count": 42},