mirror of
https://github.com/jmcorgan/fips.git
synced 2026-10-06 11:38:24 +00:00
can_send read a connectivity state that nothing outside the tests ever changed after a peer was promoted, so every route, probe and shutdown filter on it kept every peer. The filters go: find_next_hop's direct-peer and tree fallback steps, the probe next-hop preview and its direct-peer flag, the disconnect broadcast at shutdown, and the send-eligibility read on the routing seam, which the candidate selection no longer consults. Node::sendable_peers and Node::sendable_peer_count keep their signatures and still return every peer. The routing seam test that marked a peer reconnecting to keep it out of the candidate set is removed: once no peer in the map can be marked down, removal from the map is what keeps a dead link out of routing, as it already was in the daemon. No behaviour change.