Files
arys 1dcfaf46cf 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.
2026-08-30 14:19:23 +05:00

433 lines
14 KiB
Python

from __future__ import annotations
import json
from fastapi import Depends, FastAPI, HTTPException
from sqlalchemy import select, text
from services.routing_service import engine as routing_engine
from services.shared.core import Role, new_id, utc_now_iso
from services.shared.db import engine, get_session
from services.shared.models import (
AgentCreate,
AgentPoolOut,
AgentStatusUpdateIn,
EscalationOut,
HealthResponse,
QueueCreate,
QueueOut,
RoutingAgentReserveIn,
RoutingAgentReserveOut,
RoutingAgentStatusIn,
)
from services.shared.security import require_roles
from services.shared.sql_init import init_sql_schema
from services.shared.sql_models import AgentRow, EscalationRow, IvrSessionRow, Queue, RoutingCounter
app = FastAPI(title="routing-service", version="1.1.0")
init_sql_schema()
_AGENTS = {
"voice": ["operator_a", "operator_b", "operator_c"],
"telegram": ["operator_t1", "operator_t2"],
"webchat": ["operator_w1"],
"email": ["operator_e1"],
}
def _db_backend_name() -> str:
return engine.url.get_backend_name()
def _next_agent_index(session, *, channel: str, agent_count: int) -> int:
if _db_backend_name() != "postgresql":
counter = session.execute(
select(RoutingCounter).where(RoutingCounter.channel == channel)
).scalar_one_or_none()
if not counter:
counter = RoutingCounter(channel=channel, counter=0)
session.add(counter)
session.flush()
idx = counter.counter % agent_count
counter.counter += 1
return idx
counter_value = session.execute(
text(
"""
INSERT INTO routing_counters(channel, counter)
VALUES (:channel, 1)
ON CONFLICT (channel)
DO UPDATE SET counter = routing_counters.counter + 1
RETURNING counter
"""
),
{"channel": channel},
).scalar_one()
return (int(counter_value) - 1) % agent_count
def _parse_rules_json(raw_rules_json: str | None) -> list[dict]:
if not raw_rules_json:
return []
try:
data = json.loads(raw_rules_json)
except (TypeError, json.JSONDecodeError):
return []
if isinstance(data, list):
return [item for item in data if isinstance(item, dict)]
if isinstance(data, dict):
nested_rules = data.get("rules")
if isinstance(nested_rules, list):
return [item for item in nested_rules if isinstance(item, dict)]
if data:
return [data]
return []
return []
def _to_out(row: Queue) -> QueueOut:
return QueueOut(
queue_id=row.queue_id,
name=row.name,
description=row.description,
rules=_parse_rules_json(row.rules_json),
created_at=row.created_at,
)
@app.get("/health", response_model=HealthResponse)
def health() -> HealthResponse:
return HealthResponse(status="ok", service="routing-service", version="v1.1")
@app.post("/queues", response_model=QueueOut)
def create_queue(payload: QueueCreate, _: dict = Depends(require_roles(Role.ADMIN, Role.SUPERVISOR))) -> QueueOut:
session = get_session()
try:
row = Queue(
queue_id=new_id("que"),
name=payload.name,
description=payload.description,
rules_json=json.dumps([r.model_dump() for r in payload.rules], ensure_ascii=False),
created_at=utc_now_iso(),
)
session.add(row)
session.commit()
session.refresh(row)
return _to_out(row)
finally:
session.close()
@app.get("/queues", response_model=list[QueueOut])
def list_queues(
_: dict = Depends(require_roles(Role.ADMIN, Role.SUPERVISOR)),
) -> list[QueueOut]:
session = get_session()
try:
rows = session.execute(select(Queue).order_by(Queue.id.desc())).scalars().all()
return [_to_out(r) for r in rows]
finally:
session.close()
@app.patch("/queues/{queue_id}/rules", response_model=QueueOut)
def update_rules(
queue_id: str,
payload: QueueCreate,
_: dict = Depends(require_roles(Role.ADMIN, Role.SUPERVISOR)),
) -> QueueOut:
session = get_session()
try:
row = session.execute(select(Queue).where(Queue.queue_id == queue_id)).scalar_one_or_none()
if not row:
raise HTTPException(status_code=404, detail="Queue not found")
row.name = payload.name
row.description = payload.description
row.rules_json = json.dumps([r.model_dump() for r in payload.rules], ensure_ascii=False)
session.commit()
return _to_out(row)
finally:
session.close()
@app.post("/queues/{queue_id}/route")
def route_interaction(
queue_id: str,
channel: str,
priority: int = 3,
ivr_session_id: str | None = None,
_: dict = Depends(require_roles(Role.ADMIN, Role.SUPERVISOR)),
) -> dict:
session = get_session()
try:
original_queue = session.execute(select(Queue).where(Queue.queue_id == queue_id)).scalar_one_or_none()
if not original_queue:
raise HTTPException(status_code=404, detail="Queue not found")
resolved_queue_id = queue_id
ivr_flow_id = None
ivr_outcome_code = None
if ivr_session_id:
ivr_session = session.execute(
select(IvrSessionRow).where(IvrSessionRow.session_id == ivr_session_id)
).scalar_one_or_none()
if not ivr_session:
raise HTTPException(status_code=404, detail="IVR session not found")
if ivr_session.status != "completed":
raise HTTPException(status_code=400, detail="IVR session is not completed")
if ivr_session.queue_id != queue_id:
raise HTTPException(status_code=400, detail="IVR session does not belong to the requested queue")
resolved_queue_id = ivr_session.resolved_queue_id or queue_id
ivr_flow_id = ivr_session.flow_id
ivr_outcome_code = ivr_session.outcome_code
queue = session.execute(select(Queue).where(Queue.queue_id == resolved_queue_id)).scalar_one_or_none()
if not queue:
raise HTTPException(status_code=404, detail="Queue not found")
agents = _AGENTS.get(channel)
if not agents:
raise HTTPException(status_code=400, detail="No agents for channel")
idx = _next_agent_index(session, channel=channel, agent_count=len(agents))
sla_seconds = 30
for rule in _parse_rules_json(queue.rules_json):
if rule.get("channel") == channel and int(rule.get("priority", 3)) == priority:
sla_seconds = int(rule.get("sla_seconds", 30))
break
session.commit()
response = {
"queue_id": resolved_queue_id,
"channel": channel,
"priority": priority,
"assignee": agents[idx],
"sla_seconds": sla_seconds,
}
if ivr_session_id:
response.update(
{
"original_queue_id": queue_id,
"resolved_queue_id": resolved_queue_id,
"ivr_flow_id": ivr_flow_id,
"ivr_outcome_code": ivr_outcome_code,
"ivr_session_id": ivr_session_id,
}
)
return response
finally:
session.close()
@app.delete("/queues/{queue_id}")
def delete_queue(
queue_id: str,
_: dict = Depends(require_roles(Role.ADMIN)),
) -> dict:
session = get_session()
try:
row = session.execute(select(Queue).where(Queue.queue_id == queue_id)).scalar_one_or_none()
if not row:
raise HTTPException(status_code=404, detail="Queue not found")
session.delete(row)
session.commit()
return {"queue_id": queue_id, "deleted": True}
finally:
session.close()
def _agent_to_out(row: AgentRow) -> AgentPoolOut:
return AgentPoolOut(
agent_id=row.agent_id,
tenant_ids=routing_engine.parse_list_json(row.tenant_ids_json),
extension=row.extension,
endpoint=row.endpoint,
display_name=row.display_name,
level=row.level,
skills=routing_engine.parse_list_json(row.skills_json),
status=row.status,
current_call_id=row.current_call_id,
max_concurrent_calls=row.max_concurrent_calls,
enabled=row.enabled,
calls_handled_count=row.calls_handled_count,
created_at=row.created_at,
updated_at=row.updated_at,
)
@app.post("/agents", response_model=AgentPoolOut)
def create_agent(
payload: AgentCreate,
_: dict = Depends(require_roles(Role.ADMIN, Role.SUPERVISOR)),
) -> AgentPoolOut:
session = get_session()
try:
now = utc_now_iso()
row = AgentRow(
agent_id=new_id("agt"),
tenant_ids_json=json.dumps(payload.tenant_ids, ensure_ascii=False),
extension=payload.extension,
endpoint=payload.endpoint,
display_name=payload.display_name,
level=payload.level,
skills_json=json.dumps(payload.skills, ensure_ascii=False),
status="OFFLINE",
max_concurrent_calls=payload.max_concurrent_calls,
enabled=payload.enabled,
created_at=now,
updated_at=now,
)
session.add(row)
session.commit()
session.refresh(row)
return _agent_to_out(row)
finally:
session.close()
@app.get("/agents", response_model=list[AgentPoolOut])
def list_agents(
level: str | None = None,
_: dict = Depends(require_roles(Role.ADMIN, Role.SUPERVISOR, Role.OPERATOR)),
) -> list[AgentPoolOut]:
session = get_session()
try:
stmt = select(AgentRow).order_by(AgentRow.id.desc())
if level:
stmt = stmt.where(AgentRow.level == level)
rows = session.execute(stmt).scalars().all()
return [_agent_to_out(r) for r in rows]
finally:
session.close()
@app.patch("/agents/{agent_id}/status", response_model=AgentPoolOut)
def update_agent_status(
agent_id: str,
payload: AgentStatusUpdateIn,
_: dict = Depends(require_roles(Role.ADMIN, Role.SUPERVISOR, Role.OPERATOR)),
) -> AgentPoolOut:
session = get_session()
try:
row = session.execute(select(AgentRow).where(AgentRow.agent_id == agent_id)).scalar_one_or_none()
if not row:
raise HTTPException(status_code=404, detail="Agent not found")
row.status = payload.status
if payload.status == "AVAILABLE":
row.current_call_id = None
row.updated_at = utc_now_iso()
session.commit()
return _agent_to_out(row)
finally:
session.close()
def _escalation_to_out(row: EscalationRow) -> EscalationOut:
return EscalationOut(
escalation_id=row.escalation_id,
call_id=row.call_id,
tenant_id=row.tenant_id,
from_level=row.from_level,
to_level=row.to_level,
reason_code=row.reason_code,
required_skills=routing_engine.parse_list_json(row.required_skills_json),
priority=row.priority,
topic=row.topic,
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,
)
@app.get("/escalations", response_model=list[EscalationOut])
def list_escalations(
status: str | None = None,
limit: int = 50,
_: dict = Depends(require_roles(Role.ADMIN, Role.SUPERVISOR)),
) -> list[EscalationOut]:
session = get_session()
try:
stmt = select(EscalationRow).order_by(EscalationRow.id.desc()).limit(max(1, min(limit, 200)))
if status:
stmt = stmt.where(EscalationRow.status == status)
rows = session.execute(stmt).scalars().all()
return [_escalation_to_out(r) for r in rows]
finally:
session.close()
@app.post("/internal/routing/reserve-agent", response_model=RoutingAgentReserveOut)
def reserve_agent_endpoint(
payload: RoutingAgentReserveIn,
_: dict = Depends(require_roles(Role.ADMIN)),
) -> RoutingAgentReserveOut:
session = get_session()
try:
agent = routing_engine.reserve_agent(
session,
call_id=payload.call_id,
level=payload.level,
tenant_id=payload.tenant_id,
required_skills=payload.required_skills,
exclude_agent_ids=payload.exclude_agent_ids,
)
if agent is None:
raise HTTPException(status_code=409, detail=f"No available {payload.level} agent")
return RoutingAgentReserveOut(
agent_id=agent.agent_id,
extension=agent.extension,
endpoint=agent.endpoint,
display_name=agent.display_name,
)
finally:
session.close()
@app.post("/internal/routing/release-agent")
def release_agent_endpoint(
payload: dict,
_: dict = Depends(require_roles(Role.ADMIN)),
) -> dict:
call_id = str(payload.get("call_id") or "").strip()
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:
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()