Claude d37119be00 Drop dead relays from the subscription pool, not just reconnect backoff ...

The previous change only stopped the logger listener from scheduling
reconnects, but Quartz's relay pool is driven by the relays referenced in
active subscriptions. NotificationSubscription.updateFilter re-subscribed
every 30s with the full relay set, so the pool kept opening a socket to an
unreachable relay on every refresh.

Move the per-relay failure tracking into a shared RelayHealthTracker and
exclude dead relays from the subscription relay sets in updateFilter, so a
dead relay leaves the pool entirely and is no longer reconnected. Dead-relay
state is cleared on a successful connection, on every OS network change
(ConnectivityService), and on a manual reconnect (ReconnectReceiver), so
relays get a fresh chance to recover.

https://claude.ai/code/session_01SLv8ZEooFiXErAvpARtz2Y

2026-06-12 12:19:56 +00:00

..

release

add more event descriptions

2024-03-01 06:56:32 -03:00

schemas

Add Room schema export for database version 18

2026-03-30 16:53:08 +00:00

src

Drop dead relays from the subscription pool, not just reconnect backoff

2026-06-12 12:19:56 +00:00

.gitignore

init

2023-07-26 16:44:33 -03:00

build.gradle.kts

6.2.0

2026-06-01 11:05:58 -03:00

proguard-rules.pro

Add ProGuard rules to ignore missing java.lang.management references

2026-03-18 09:16:06 -03:00