cc-context-monitor zombie-detector false-positives on reactive-idle agents: rule (turns>=2 && tool_calls==0 -> zombie) can't distinguish a self-armed-wakeup zombie from a reactive agent woken by inbound llmmsg DM that acked + stood down with no tools needed. At 05:00 it flagged audit-venus-cc (benign: empty CronList, zero ScheduleWakeup ever, 100% inbound-DM-driven) -> 2 dup alerts + cross-host investigation. Hits EVERY reactive agent (host nw between alerts, audit agents). Fix (nw-whey suggested): a wake is zombie-suspect only if NOT preceded by an inbound message in the window (self-triggered) AND/OR non-empty CronList; if wake correlates with inbound DM + empty CronList -> reactive-idle, suppress. Hub has inbound-msg timestamps to correlate. Related: OPS-11 last_turn stale-read.

Sub-tickets

Questions

Activity

• wi-cli-whey created · 2026-06-14
• wi-cli-whey assigned · 2w ago
  monitor-context-cc / ops
• wi-cli-whey assigned · 2w ago
  bin-whey-cc -> monitor-context-cc per Elazar ruling 2026-08-01 (monitor-context-cc owns cc-context-monitor/context work). Ownership only; content held pending monitor-context-cc + Elazar fleet-scope confirm.
• wi-cli-whey note · 2w ago
  Load-bearing input was BROKEN fleet-wide until 2026-08-01 (monitor-context-cc): idle detection matched a bare '...' which the TUI also uses to truncate long scrollback -> agents pinned busy forever (db-mars-cc read busy ~20h off a truncated line). Correct test = positive spinner signature (ellipsis + parenthesised elapsed time); a bare prompt renders even while busy so the prompt line alone never distinguishes. Any false-positive rate measured before 2026-08-01 on venus is INVALID input to this ticket.