mirror of
https://github.com/jmcorgan/fips.git
synced 2026-10-06 03:28:24 +00:00
Johnathan Corgan
eadc3257d8
show_peers, and the peer row the tick publishes for the control socket to serve, printed a peer's connectivity from a state stored on the active peer. That state starts at connected on promotion and nothing outside the tests ever changes it, so every peer read connected for as long as it stayed in the peer map, including one that had stopped answering and was waiting out its link-dead timeout. Both render sites now derive the value from how long the peer has been silent: connected while its idle time is at or below heartbeat_interval_secs, floored at one second, and stale above it. That is the rule discovery already applies when deciding whether to re-dial an active peer on the path it already has, so the rule moves to one helper on Node that the re-dial gate and both renders call. stale was already one of the field's values, so the set of values a client can see does not grow, and the response shape is unchanged. The stored state and its other readers are left as they are. The open-discovery tutorial described reconnecting and disconnected values that never occur, and the advertise-your-node tutorial said a new peer would read active, which the field never reports. Both now describe what the field reports. The new tests insert peers last heard from at chosen times and read show_peers both on the loop and from the tick-published snapshot. Under the default 10 s interval a peer silent for 15 s reads stale and one heard from just now reads connected; with a 30 s interval a peer silent for 15 s still reads connected, so the threshold is the configured interval and not a fixed ten seconds. Both failed on the unfixed code, which reported the silent peer as connected. A third test pins the boundary: connected at exactly the interval, stale one millisecond past it, and a zero interval floored at one second. Restoring the stored read at either render site alone fails both show_peers tests on that render, making the comparison inclusive fails the boundary test, and a fixed ten-second threshold fails the configured-interval and boundary tests.