mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-09-14 02:42:24 +03:00
The eighteen commits main carries beyond the cycle branch, and what each one
became here:
already in release/v3.8.51 by its own PR (no-op, verified by content):
b090b601a5 / 026e1cadaa deps: nanoid 3.3.18 equal, dompurify 3.4.14 newer
918fba5e39 .gitignore: /_tasks already anchored
5f0a394091 #10026 hide health-check-excluded models — same helper, 5 call sites
c68cda7dfb #11075 shared passthrough providers — superseded by #11071/#11078
superseded, one piece kept:
ca23eed77c #10055 memoize models.dev pricing — the cycle memoizes on the
catalog cache version already; only the resetDbInstance() hook is
ported, wired to that memo
applied as-is:
8778ea7d18 stamp dist/BUILD_SHA before the npm provenance gate (#11721)
aa52351113 decouple the Bun image from the release manifest (#11724)
925feb27b8 let the bun digest artifact be absent (#11740)
b65ef333da size the install-upgrade gate to a measured run
0ce21232db #11845 converge install/upgrade schemas (migration renumbered in
the next commit: 163 collides with 163_radar_feed_cache_generated_at)
b7c07edad8 #11855 install-upgrade gate on disk, not tmpfs
8e2fb04329 #11864 drop *.nft.json from the npm tarball (413)
dea6bb8b6b #11877 publish npm from a hosted runner (provenance 422)
handled by the sync script that follows (CHANGELOG protocol):
b4ec7807ab Release v3.8.50 — squash of content this branch already carries
5458026c21 / c44c0a29e8 CHANGELOG aggregation, stats and top-25
applied separately (its own commit, ten files):
65e81158ab #11088 Ollama capability routing — a 5,094-file squash from a
stale base; only the Ollama files are the change
Every cherry-pick that touched a file this branch had also changed was
resolved by hand and re-run through the tests both sides own for it.
7 lines
1.7 KiB
JSON
7 lines
1.7 KiB
JSON
{
|
|
"_doc": "Tables that exist ONLY in databases upgraded from an older version. Two causes, and they call for different fixes: (a) residue whose CREATE left the migration set in some past cycle but survives where it already existed — allowlist it here; (b) a table created LAZILY at runtime with `CREATE TABLE IF NOT EXISTS` inside a feature code path — whether a database has it depends on whether that feature ran, so it diverges by TIMING and can show up on EITHER side. Fix (b) with a migration instead of an entry here (see src/lib/db/migrations/163_model_capabilities.sql); an allowlist entry only hides it in one direction. Either way, recorded so check-install-upgrade.mjs can still fail on a NEW divergence. The opposite direction (a table a clean install creates but an upgrade does not) is NEVER allowlisted: it means every existing user is missing structure the code expects.",
|
|
"residualTables": {
|
|
"cache_metrics": "Measured 2026-07-30 on a real 3.8.48 install upgraded to 3.8.49 (VPS .16, 165 MB database, 114 → 117 tables). Present in upgraded databases, absent from clean installs. Cause identified 2026-08-27: it is case (b) above — created lazily by `ensureCacheMetricsTable()` at src/lib/semanticCache.ts:34, never by a migration, so it appears only where the semantic cache has run. No code path referenced it during the upgrade (zero `no such table` in 150 log lines, both installs healthy). Left as an allowlist entry rather than promoted to a migration or dropped: unlike model_capabilities it did not block a release, and creating a table for a subsystem we cannot prove is live is not a change to make blind. Revisit when the cache subsystem is next touched."
|
|
}
|
|
}
|