Files
msd-core/tests
Tom Boucher 2bc53baa03 fix(#2947): preserve preamble phase details when milestone section has none (#3084)
* test(#2947): milestone anchor must prefer heading with Phase details

Row 1 of the test matrix: the failing-first regression test. When the
phase-listing heading (## Phases) is NOT version-bearing but a later
version-bearing progress heading (### v9.0 phase progress) exists,
extractCurrentMilestone latches onto the progress heading and silently drops
the phases (phase_count: 0, exit 0). Five cases: the regression, the
version-bearing control (must keep working), the no-phase-details fallback,
the closed-vs-open preference, and an end-to-end roadmap.analyze check.

Reproduced locally against built lib + confirmed by maintainer triage (trek-e).
The one-word control (## Phases -> ## v9.0 Phases) restores phase_count: 2.

* fix(#2947): preserve preamble phase details when the milestone section has none

Root cause was one layer deeper than the issue title: the anchor selection
(selected = first non-closed version-bearing heading) is fine — the real
drop happens in the preamble strip. When the phase list lives under a
non-version-bearing ## Phases heading (the shipped greenfield template's own
shape) and the selected version-bearing heading is a LATER progress/notes
sub-heading with no ### Phase N: details of its own, the preamble strip
removed every phase-detail heading from the pre-milestone region (intended
to avoid duplication with a Phase Details section that does not exist here)
— silently dropping all phases (phase_count: 0, exit 0, empty stderr).

Fix: only strip preamble ### Phase N: headings when the selected milestone
section (currentSection) actually contains its own phase details. When it
does not, the preamble phases ARE this milestone's phases and must be
preserved. Falls back to today's behavior (strip) whenever the selected
section has phase details, so multi-milestone roadmaps with a dedicated
Phase Details section (#730) are unaffected.

Surgical: one conditional on the existing strip, no signature change, no
change to computeSectionEnd or the #730 Phase Details append. Blast radius
CRITICAL (84 upstream symbols) — the change is gated on currentSection's
content so every existing roadmap that currently resolves phases correctly
keeps doing so byte-identically.

* chore(#2947): add changeset fragment

* chore(#2947): backfill changeset PR number 3084

---------

Co-authored-by: sim <sim@local>
2026-08-05 13:10:52 -04:00
..