fix(paired): bound arbiter interventions to stop infinite arbiter loop

The owner↔reviewer↔arbiter loop could repeat forever: when the arbiter
ruled PROCEED/REVISE/RESET it reset round_trip_count to 0, and nothing
tracked how many times the arbiter had already intervened. A re-deadlock
re-invoked the arbiter without bound.

Add a persistent arbiter_intervention_count (new column + migration 020)
that survives the round-trip reset, and a configurable cap
ARBITER_MAX_INTERVENTIONS (default 1). Once the arbiter has intervened
that many times and the loop still deadlocks, requestArbiterOrEscalate
escalates straight to the user instead of re-invoking the arbiter.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

src/paired-execution-context.ts

@@ -145,6 +145,7 @@ function createActiveTaskForRoom(args: {
     finalize_step_done_count: 0,
     task_done_then_user_reopen_count: 0,
     empty_step_done_streak: 0,
+    arbiter_intervention_count: 0,
     status: 'active',
     arbiter_verdict: null,
     arbiter_requested_at: null,
@@ -494,6 +495,7 @@ export function preparePairedExecutionContext(args: {
                   owner_failure_count: 0,
                   owner_step_done_streak: 0,
                   empty_step_done_streak: 0,
+                  arbiter_intervention_count: 0,
                 }
               : {}),
           },
@@ -510,6 +512,7 @@ export function preparePairedExecutionContext(args: {
                   owner_failure_count: 0,
                   owner_step_done_streak: 0,
                   empty_step_done_streak: 0,
+                  arbiter_intervention_count: 0,
                 }
               : {}),
           },