scripts/artifacts.sh

@@ -100,13 +100,6 @@ fmt() {
   (cd "$ROOT" && TZ=UTC git show -s --format=%cd --date="format-local:$2" "$1")
 }
 
-# Leading zeros stripped so every segment is a plain integer — some version
-# validators reject `08`, and a leading zero buys nothing. `0000` (midnight)
-# must survive as `0`, not as the empty string.
-strip0() {
-  printf '%s' "$1" | sed -e 's/^0*//' -e 's/^$/0/'
-}
-
 # The IDENTITY of an artifact's content: the commit its shipped files last
 # changed in. This is what decides whether a build can be skipped.
 #
@@ -124,17 +117,32 @@ cmd_revision() {
   echo "$(newest "$1")" | cut -d' ' -f2 | cut -c1-12
 }
 
-# The ORDERING KEY: full precision, YYYY.M.D.HHMM. Used by the extension,
-# where the value is what Firefox compares to decide whether an update exists
-# — two same-day builds MUST be distinguishable or the second never reaches
-# anyone.
+# The VERSION: `YYYY.MM.DD.HHMM`, zero-padded, UTC. One shape across the whole
+# family (note #3127 §1, rule 148) — the number an instance reports about
+# itself, and, with a `v` in front, the release tag naming the same build.
+#
+# Zero-padded since 2026-08-28. This stripped leading zeros until then, on the
+# reasoning that every segment should read as a plain integer — which never
+# held, since comparison strips them on parse anyway. Padding costs nothing,
+# sorts lexically as well as numerically, and keeps this project emitting the
+# same string as its siblings: unpadded, a `2026.8.28.1432` here sits beside a
+# `2026.08.28.1432` there, two shapes one character apart. Two obviously
+# different formats are safer than two nearly identical ones.
+#
+# Comparison is numeric per dot-segment, so `08` and `8` are equal and nothing
+# already published is reordered by the change.
+#
+# HHMM is not decoration: it is what makes the value unique per build with no
+# lookup. A date alone collides on the second build of a day, and resolving
+# that needs a `.N` suffix, which needs asking the registry what already
+# exists — at which point two lanes derive different answers for one source
+# and the shared-signature property is lost.
 cmd_version() {
   sha=$(echo "$(newest "$1")" | cut -d' ' -f2)
-  printf '%s.%s.%s.%s\n' \
-    "$(fmt "$sha" %Y)" \
-    "$(strip0 "$(fmt "$sha" %m)")" \
-    "$(strip0 "$(fmt "$sha" %d)")" \
-    "$(strip0 "$(fmt "$sha" %H%M)")"
+  # One git call for the whole string rather than four and a sed. git's
+  # format-local takes the complete format, and doing it in pieces was only
+  # ever there to strip the padding between them.
+  fmt "$sha" '%Y.%m.%d.%H%M'
 }
 
 [ $# -ge 2 ] || usage

tests/test_artifact_identity.py

@@ -1,4 +1,10 @@
-"""`artifacts.sh revision` is what decides whether a build gets skipped.
+"""The two values `artifacts.sh` derives, and what each of them promises.
+
+`revision` decides whether a build gets skipped; `version` is what an instance
+reports about itself and what a release tag is named after. Neither has a
+consumer that would notice it going subtly wrong.
+
+## revision
 
 Milestone 318 step 3: each image carries its revision as an `fc.revision`
 label, and build.yml reads that label back off the moving channel tag. Equal
@@ -21,12 +27,20 @@ Both ways of getting it wrong are silent:
 This module owns the narrower claim: whatever the path sets say, the revision
 is genuinely the commit those paths last changed in.
 
+## version
+
+`YYYY.MM.DD.HHMM`, zero-padded, UTC — one shape across the family (note #3127
+§1, rule 148), so the string this project emits is the same string its siblings
+emit. Two nearly-identical formats are more dangerous than two obviously
+different ones, and the only thing keeping them identical is a test.
+
 The identity-TAG tests this file used to hold are gone with the tag. There is
 no longer a `CHANNELLED` list to drift (the channel is which tag you inspect),
 and no `identity` subcommand to refuse an unqualified call.
 """
 from __future__ import annotations
 
+import os
 import re
 import subprocess
 from pathlib import Path
@@ -40,6 +54,9 @@ ARTIFACTS = ("web", "ml", "agent", "extension")
 # 12 hex chars — the prefix build.yml stamps and compares.
 _REVISION = re.compile(r"^[0-9a-f]{12}$")
 
+# YYYY.MM.DD.HHMM, every segment zero-padded to its full width.
+_VERSION = re.compile(r"^\d{4}\.\d{2}\.\d{2}\.\d{4}$")
+
 
 # Everything here goes through artifacts.sh rather than importing a sibling
 # test module. That is the interface build.yml actually calls, so the tests
@@ -107,3 +124,43 @@ def test_revision_is_a_legal_label_value_and_is_stable(artifact):
     first = revision(artifact)
     assert _REVISION.match(first), f"{first!r} is not a 12-char hex revision"
     assert first == revision(artifact), "revision is not stable across calls"
+
+
+@pytest.mark.parametrize("artifact", ARTIFACTS)
+def test_version_is_zero_padded_calver(artifact):
+    """The family shape, pinned.
+
+    Padding was stripped until 2026-08-28 on the reasoning that each segment
+    should read as a plain integer — which never held, since comparison strips
+    leading zeros on parse anyway. What it did do was make this project emit
+    `2026.8.28.1432` while a sibling emitted `2026.08.28.1432`: two shapes one
+    character apart, which is the hard kind of difference to notice.
+
+    Also catches the midnight case. A `%H%M` of `0322` must survive as `0322`;
+    the old strip-leading-zeros helper turned it into `322`, silently changing
+    a four-digit field into three.
+    """
+    value = artifacts("version", artifact).strip()
+    assert _VERSION.match(value), (
+        f"{artifact} derives {value!r}, which is not zero-padded "
+        f"YYYY.MM.DD.HHMM. Note #3127 §1 and rule 148 both specify the padded "
+        f"form, and a release tag is this string with a `v` in front."
+    )
+
+
+@pytest.mark.parametrize("artifact", ARTIFACTS)
+def test_version_and_revision_describe_the_same_commit(artifact):
+    """They are derived independently and must not be able to disagree.
+
+    A build reports the version and skips on the revision, so a divergence
+    would mean an instance naming one commit while carrying another's bytes —
+    unfalsifiable from outside, since both values look perfectly well-formed.
+    """
+    sha = newest_by_commit_time(artifact)
+    stamped = subprocess.run(
+        ["git", "show", "-s", "--format=%cd", "--date=format-local:%Y.%m.%d.%H%M", sha],
+        capture_output=True, text=True, check=True, cwd=ROOT,
+        env={"TZ": "UTC", "PATH": os.environ.get("PATH", "")},
+    ).stdout.strip()
+    assert artifacts("version", artifact).strip() == stamped
+    assert sha.startswith(revision(artifact))