Executed in Session 0014.0 (= legacy "Session N"), 2026-05-28. The
session-protocol naming convention switched from alphabetical letters
(SESSION-A through SESSION-M, plus SESSION-M.1/M.2/M.3 subsessions) to
zero-padded 4-digit session numbers with a subagent ordinal suffix
(SESSION-0001.0 through SESSION-0013.0, plus SESSION-0013.1/.2/.3).
Rationale: alphabetical ordering breaks down after Z (does AA sort
before B in a filesystem? a glob?), and the convention doesn't
generalize to deeper structure. The numeric form addresses both, and
the explicit `.0` for the main driver transcript makes the parent-vs-
subagent distinction visible at first glance.
Mapping (all 16 transcripts):
A → 0001.0
B → 0002.0
C → 0003.0
D → 0004.0
E → 0005.0
F → 0006.0
G → 0007.0
H → 0008.0
I → 0009.0
J → 0010.0
K → 0011.0
L → 0012.0
M → 0013.0
M.1 → 0013.1
M.2 → 0013.2
M.3 → 0013.3
This commit uses `git mv` for each rename so Gitea's rename detection
records each as a file-was-renamed event rather than file-was-deleted-
and-recreated. The transcript bodies are NOT rewritten — they still
read "Session I" / "Session M.1" / etc. internally; the body's session
reference and the filename's numeric form are both authoritative.
Readers map back via the table above.
External references to the old paths
(e.g. wiggleverse/ohm-session-history/SESSION-I-TRANSCRIPT-…md) will
404 after this rename. The audit trail is in this git log; readers
who care can trace. No redirect tombstones were added.
The publish-transcript.sh validator was extended to accept both the
numeric form (binding from 0014.0 onward) AND the legacy letter form
(so renamed-old-files remain re-publishable if their content is later
corrected). See ohm-infra/scripts/publish-transcript.sh and
ohm-infra/SESSION-PROTOCOL.md §1 (binding spec) for the new
convention.
Session 0014.0 is the first session to ship under the new naming
end-to-end.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Ben Stull