feat: no-answer retry, agent status machine, escalation events/timeline (ТЗ §13-15,22,25-27,37, AC-08,16-19)

Phase 2 of the L1->L2 routing engine (Phase 1: MR!4).

- ami_loop() now also captures native AMI DialEnd/Hangup frames (not
  only UserEvent), needed to detect that an escalated agent did not
  answer. No dialplan change required - Redirect already routes the
  client channel into an existing Dial()-based transfer context, so
  Asterisk emits these events on its own; the listener just wasn't
  reading them before.
- retry_escalation_no_answer(): on NOANSWER/BUSY/CANCEL/CHANUNAVAIL/
  CONGESTION, releases the non-answering agent, excludes it, and
  reserves+redirects to the next available agent via the routing
  engine's existing exclude_agent_ids support. Exhausted pool marks
  the escalation failed and leaves the call with the AI instead of
  dropping the client (ТЗ §32).
- Agent status now actually moves through
  RESERVED -> RINGING -> TALKING -> AFTER_CALL_WORK -> AVAILABLE
  instead of staying stuck on RESERVED for the whole call; a new
  acw_sweep_loop background thread (same pattern as the existing
  failed_retry_loop) times out AFTER_CALL_WORK back to AVAILABLE.
- escalations gains attempt_count/real_agent_id/attempted_agent_ids_json
  (migration 0033); fixes a latent bug where assigned_agent_id stored
  the SIP extension instead of the real agent_id despite routing-service
  already returning it in RoutingAgentReserveOut.
- Every transition now records an interaction timeline entry and
  publishes the ТЗ §25 event catalog (AgentReserved/AgentRinging/
  AgentNoAnswer/AgentConnected/TransferCompleted/TransferFailed)
  through the existing emit_voice_event/EventOutboxRow idempotent path.

Not in this MR (see plan): SLA config, Callback, L3 (needs real
technical agents from the business), metrics.

services/routing_service/app.py

@@ -18,6 +18,7 @@ from services.shared.models import (
     QueueOut,
     RoutingAgentReserveIn,
     RoutingAgentReserveOut,
+    RoutingAgentStatusIn,
 )
 from services.shared.security import require_roles
 from services.shared.sql_init import init_sql_schema
@@ -343,6 +344,7 @@ def _escalation_to_out(row: EscalationRow) -> EscalationOut:
         summary=row.summary,
         status=row.status,
         assigned_agent_id=row.assigned_agent_id,
+        attempt_count=row.attempt_count or 0,
         requested_at=row.requested_at,
         connected_at=row.connected_at,
         completed_at=row.completed_at,
@@ -399,11 +401,32 @@ def release_agent_endpoint(
     _: dict = Depends(require_roles(Role.ADMIN)),
 ) -> dict:
     call_id = str(payload.get("call_id") or "").strip()
-    if not call_id:
-        raise HTTPException(status_code=400, detail="call_id is required")
+    agent_id = str(payload.get("agent_id") or "").strip()
+    next_status = str(payload.get("next_status") or "AVAILABLE").strip() or "AVAILABLE"
+    if not call_id and not agent_id:
+        raise HTTPException(status_code=400, detail="call_id or agent_id is required")
     session = get_session()
     try:
-        agent = routing_engine.release_agent_by_call_id(session, call_id=call_id)
-        return {"call_id": call_id, "released_agent_id": agent.agent_id if agent else None}
+        if agent_id:
+            agent = routing_engine.release_agent_by_id(session, agent_id=agent_id, next_status=next_status)
+        else:
+            agent = routing_engine.release_agent_by_call_id(session, call_id=call_id)
+        return {"call_id": call_id or None, "released_agent_id": agent.agent_id if agent else None}
+    finally:
+        session.close()
+
+
+@app.patch("/internal/routing/agents/{agent_id}/status")
+def set_agent_status_endpoint(
+    agent_id: str,
+    payload: RoutingAgentStatusIn,
+    _: dict = Depends(require_roles(Role.ADMIN)),
+) -> dict:
+    session = get_session()
+    try:
+        agent = routing_engine.set_agent_status(session, agent_id=agent_id, status=payload.status)
+        if agent is None:
+            raise HTTPException(status_code=404, detail="Agent not found")
+        return {"agent_id": agent.agent_id, "status": agent.status}
     finally:
         session.close()

services/routing_service/engine.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 import json
+from datetime import datetime
 
 from sqlalchemy import select, text
 
@@ -117,6 +118,41 @@ def release_agent_by_call_id(session, *, call_id: str) -> AgentRow | None:
     return agent
 
 
+def set_agent_status(session, *, agent_id: str, status: str) -> AgentRow | None:
+    agent = session.execute(
+        select(AgentRow).where(AgentRow.agent_id == agent_id)
+    ).scalar_one_or_none()
+    if agent is None:
+        return None
+    agent.status = status
+    agent.updated_at = utc_now_iso()
+    session.commit()
+    return agent
+
+
+def sweep_after_call_work(session, *, older_than_seconds: int) -> list[AgentRow]:
+    cutoff = utc_now_iso()
+    rows = session.execute(
+        select(AgentRow).where(AgentRow.status == "AFTER_CALL_WORK")
+    ).scalars().all()
+    swept: list[AgentRow] = []
+    for agent in rows:
+        try:
+            age_seconds = (
+                datetime.fromisoformat(cutoff) - datetime.fromisoformat(str(agent.updated_at))
+            ).total_seconds()
+        except (TypeError, ValueError):
+            continue
+        if age_seconds >= older_than_seconds:
+            agent.status = "AVAILABLE"
+            agent.current_call_id = None
+            agent.updated_at = cutoff
+            swept.append(agent)
+    if swept:
+        session.commit()
+    return swept
+
+
 def release_agent_by_id(session, *, agent_id: str, next_status: str = "AVAILABLE") -> AgentRow | None:
     agent = session.execute(
         select(AgentRow).where(AgentRow.agent_id == agent_id)