After attempting cluster B (4 surgical agent-session fixes), even the
first commit conflicted because of structural namespace divergence
(gsd_*→sf_* rename, @sf-run/*→@singularity-forge/* rename, prior
pi-mono direct cherry-picks). The conflicts are real semantic
divergence, not noise.
Conclusion: sf is a fork; we do not periodically sync from
gsd-build/gsd-2. Pretending we still track upstream means weeks of
merge work for diminishing return.
BUILD_PLAN.md adds an explicit "Upstream stance" section documenting
the fork posture and the rationale for the three irreversible naming
choices.
UPSTREAM_CHERRY_PICK_CANDIDATES.md is reframed as a reference list,
not an action plan. The clusters and SHAs remain useful as an
intelligence source — port specific fixes by hand when one bites us;
do not run automated cherry-picks against the list.
Pi-mono SDK syncs continue separately — that path doesn't have the
same divergence problem.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
The origin↔upstream divergence is 4,589 commits. This file picks the
high-leverage subset (~70 commits across 16 topical clusters) worth
considering for cherry-pick. Recommended order at the bottom.
Each cluster lists candidate SHAs with one-line context and effort
estimates. Total estimated work if all clusters A-N are taken: ~10-15
hours plus conflict resolution. Cluster O (UnitContextManifest /
Composer rewrite, ~15 commits) is deferred — likely conflicts heavily
with our work and should be revisited during v3 schema reconciliation.
Cluster P (memories table cutover, 1 commit) is flagged as READ FIRST
because it's upstream's answer to what BUILD_PLAN calls Singularity
Memory integration; reading it may change the recommended integration
path.
This is a candidate list for human decision, not an action plan.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
