mirror of
https://github.com/ruvnet/ruflo.git
synced 2026-09-14 14:01:28 +08:00
ruv
b03c097be1
Keying the registry cache by path broke #2968's fixture. That test installs a fake registry through __setMemoryBridgeRegistryForTests and then calls bridgeStoreEntry with its own temp dbPath, so an override installed under the two keys the seam could guess was never consulted: the call resolved a third path, missed the cache, and tried a real init instead of the fake. A test seam means 'use this registry', not 'use it if the caller passes the path I assumed'. It is now a separate override that getRegistry() returns first, kept deliberately outside the path cache so the two concerns cannot collide again. Verified: #2968 and the #3196 identity tests pass together, and the bridge dbPath, durability, purge and row-visibility suites are unchanged. Co-Authored-By: RuFlo <ruv@ruv.net> Claude-Session: https://claude.ai/code/session_013u4pmL9ZUAXb6usVQgNo67