feat(subagents): add idle ttl cleanup and summary tool

docs/architecture/AGENT_DIAGRAM.md

@@ -137,7 +137,7 @@ Tool Calls (inside NativeAgent loop)
                  +---------------------------> AuditLogger (redacted)
 
 Subagent sessions (multi-turn child agents)
-  parent AgentOrchestrator -> subagent.* tools -> SubagentManager
+  parent AgentOrchestrator -> subagent.* tools -> SubagentManager (TTL cleanup)
   SubagentManager -> child AgentOrchestrator (session namespace: subagent:<parent>:<id>)
   child AgentOrchestrator -> NativeAgent/tool loop (same policy engine, recursion tools removed)
 

docs/architecture/GATEWAY_SESSIONS_AND_QUEUE.md

@@ -17,7 +17,7 @@ If you only want the protocol surface, see `docs/api/PROTOCOL.md`.
 - Backend routing outcomes are auditable via `backend.route` / `backend.success` / `backend.fallback`, which enables offline canary evaluation without changing gateway protocol methods.
 - Run lifecycle/cancel intent and reaction decisions are emitted to audit logs, and aggregated into `system.metrics` counters (runStates, cancelLatencyMs, reactions) for dashboards.
 - Reaction matching is deterministic (priority + cooldown + recursion guard) before intent/agent routing.
-- `subagent.*` tools create child orchestrators scoped to the parent conversation (`subagent:<parentSessionId>:<childId>`); this is tool-loop behavior, not a separate gateway RPC session lane.
+- `subagent.*` tools create child orchestrators scoped to the parent conversation (`subagent:<parentSessionId>:<childId>`) with idle TTL cleanup; this is tool-loop behavior, not a separate gateway RPC session lane.
 - Companion `node.*` registration is per WebSocket connection; reconnects must re-register capabilities before invoking node RPC methods.
 - Canvas artifacts are persisted per session under the gateway data directory for UI recovery across restarts.
 - TTS output is best-effort; synthesis failures fall back to text-only responses.