golem15/msd-core
3
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(#2949): exclude sentinel phase ids from stage-3 next-phase candidacy (#3070)

Browse Source 
* test(#2949): prove phase complete stage-3 admits 0.x backlog sentinels

Failing-first regression for #2949. cmdPhaseComplete's stage-3 lowest-outstanding
loop has no sentinel filter, so completing the last real phase with an unchecked
0.x backlog row present selects the sentinel as next_phase, corrupting STATE.md.
Row 1 asserts the 0.x sentinel is not selected; Row 2 guards the #2028 real-lower-
phase out-of-order behavior; Rows 3-4 cover STATE desync and the checked-sentinel
boundary.

* fix(#2949): exclude sentinel phase ids from stage-3 next-phase candidacy

cmdPhaseComplete's stage-3 lowest-outstanding-override loop (#2028) had no
sentinel filter, so completing the last real phase with an unchecked 0.x backlog
row present selected the sentinel as next_phase — comparePhaseNum("0.1","12")
=== -12 sorts it below every real phase — corrupting STATE.md and desyncing
current_phase from current_phase_name.

Add !isSentinelPhaseId(cbm[2]) to the stage-3 condition, reusing the existing
zero-caller predicate (SENTINEL_RANGES = [0, 999]) so both sentinel ranges are
excluded. A real lower-numbered outstanding phase is not a sentinel and is still
selected, preserving #2028's out-of-order-completion behavior.

Stage-3 only: PR #2815 (in-flight, #2786) covers stages 1-2; the two PRs touch
disjoint code.

* fix(#2949): compare next_phase numerically in Row 2 (handles padded/unpadded)

Row 2's assertion /09/.test(next_phase) failed because the CLI returns the
unpadded "9", not "09". Compare numerically (parseInt === 9) so the assertion
holds for either form.

* fix(#2949): mark Phase 11 complete in Row 1 so only the 0.x sentinel is unchecked

Row 1's fixture left Phase 11 unchecked, so completing Phase 12 correctly
selected Phase 11 as the real lower outstanding phase (is_last_phase=false) —
the assertion is_last_phase===true was wrong for that fixture, not the code.
Mark Phase 11 [x] so the ONLY unchecked lower row is the 0.x sentinel, which is
the actual #2949 scenario. Confirmed locally: with Phase 11 checked + the fix,
completing 12 yields is_last_phase=true, next_phase=null (sentinel excluded).

* chore(#2949): add changeset fragment

* chore(#2949): backfill changeset PR number 3070

---------

Co-authored-by: sim <sim@local>
This commit is contained in:
Tom Boucher
2026-08-04 23:58:49 -04:00
committed by GitHub
parent 8f75e27554
commit c97f5debb9
3 changed files with 219 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
src/phase.cts
View File

@@ -35,6 +35,7 @@ const {
phaseMarkdownRegexSource,
comparePhaseNum,
phaseTokenMatches,
isSentinelPhaseId,
OPTIONAL_PROJECT_CODE_PREFIX_SOURCE,
OPTIONAL_PHASE_TAG_SOURCE,
PHASE_NUMBER_TOKEN_SOURCE,
@@ -2574,7 +2575,14 @@ function cmdPhaseComplete(cwd: string, phaseNum: string, raw: boolean): void {
let lowestOutstanding: { num: string; name: string } | null = null;
while ((cbm = cbPattern.exec(milestoneScope)) !== null) {
const isChecked = cbm[1].toLowerCase() === 'x';
if (!isChecked && comparePhaseNum(cbm[2], phaseNum) < 0) {
// #2949: exclude sentinel-range phase ids (0.x backlog, 999.x) from candidacy.
// comparePhaseNum("0.1","12") === -12, so without this guard an unchecked 0.x
// backlog row sorts below every real phase and is wrongly selected as next_phase,
// corrupting STATE.md and desyncing current_phase from current_phase_name.
// isSentinelPhaseId covers both sentinel ranges (SENTINEL_RANGES = [0, 999]); a
// real lower-numbered outstanding phase (e.g. Phase 9) is NOT a sentinel and is
// still selected, preserving #2028's out-of-order-completion behavior.
if (!isChecked && !isSentinelPhaseId(cbm[2]) && comparePhaseNum(cbm[2], phaseNum) < 0) {
if (lowestOutstanding === null || comparePhaseNum(cbm[2], lowestOutstanding.num) < 0) {
lowestOutstanding = {
num: cbm[2],