first commit

templates/agent_template_backend/app/agents/README.md

@@ -0,0 +1,15 @@
+# Agentes do Template Backend Enterprise
+
+Os arquivos desta pasta preservam a estrutura real esperada pelo workflow, mas
+não executam lógica de negócio pronta.
+
+Cada agente mostra:
+
+- como emitir IC;
+- como emitir NOC;
+- como emitir GRL;
+- como coletar MCP via `_collect_tool_context()`;
+- como recuperar RAG via `_retrieve_rag_context()`;
+- onde chamar LLM/cache.
+
+A implementação original do exemplo está comentada no fim de cada arquivo.

templates/agent_template_backend/app/agents/billing_agent.py

@@ -0,0 +1,98 @@
+from app.agents.prompting import apply_agent_profile_prompt
+from app.agents.runtime import AgentRuntimeMixin
+
+
+class BillingAgent(AgentRuntimeMixin):
+    name = "billingAgent"
+
+    def __init__(
+        self,
+        llm,
+        telemetry=None,
+        tool_router=None,
+        rag_service=None,
+        cache=None,
+        settings=None,
+        observer=None,
+        memory=None,
+        summary_memory=None,
+    ):
+        self.llm = llm
+        self.telemetry = telemetry
+        self.tool_router = tool_router
+        self.rag_service = rag_service
+        self.cache = cache
+        self.settings = settings
+        self.observer = observer
+        self.memory = memory
+        self.summary_memory = summary_memory
+
+    async def run(self, state):
+        await self._emit_ic(
+            "IC.BILLING_AGENT_STARTED",
+            state,
+            {"business_component": "faturas"},
+            component="agent.billing.start",
+        )
+
+        tool_context = await self._collect_tool_context(state)
+        if tool_context:
+            await self._emit_ic(
+                "IC.BILLING_MCP_CONTEXT_COLLECTED",
+                state,
+                {"tool_result_count": len(tool_context)},
+                component="agent.billing.mcp",
+            )
+
+        rag_context, rag_metadata = await self._retrieve_rag_context(state)
+        if rag_metadata.get("enabled"):
+            await self._emit_ic(
+                "IC.BILLING_RAG_CONTEXT_RETRIEVED",
+                state,
+                {
+                    "document_count": rag_metadata.get("document_count"),
+                    "graph_neighbors": rag_metadata.get("graph_neighbors"),
+                    "latency_ms": rag_metadata.get("latency_ms"),
+                },
+                component="agent.billing.rag",
+            )
+
+        # Prepara ConversationSummaryMemory antes de montar o prompt.
+        # O build_messages() do framework injeta resumo + últimas mensagens quando habilitado.
+        await self.prepare_memory_context(state)
+
+        messages = self.build_messages(
+            state,
+            system_prompt=apply_agent_profile_prompt(
+                state,
+                "Você é um agente especialista em faturas. Responda com clareza, objetividade e sem sugerir ações não solicitadas. Use dados MCP quando disponíveis.",
+            ),
+            mcp_results=tool_context,
+            rag_context=rag_context,
+            rag_metadata=rag_metadata,
+        )
+
+        answer = await self._invoke_llm_cached(state, "BillingAgent", messages)
+        result = {
+            "answer": f"[BillingAgent] {answer}",
+            "next_state": "BILLING_ACTIVE",
+            "mcp_results": tool_context,
+            "rag": rag_metadata,
+            "memory_context_metadata": state.get("memory_context_metadata"),
+        }
+
+        await self._emit_ic(
+            "IC.BILLING_AGENT_COMPLETED",
+            state,
+            {
+                "answer_chars": len(result.get("answer") or ""),
+                "has_mcp_results": bool(tool_context),
+                "rag_enabled": bool(rag_metadata.get("enabled")),
+                "memory_context": state.get("memory_context_metadata"),
+            },
+            component="agent.billing.completed",
+        )
+        return result
+
+    async def _collect_tool_context(self, state):
+        return await self._collect_mcp_context(state)

templates/agent_template_backend/app/agents/orders_agent.py

@@ -0,0 +1,98 @@
+from app.agents.prompting import apply_agent_profile_prompt
+from app.agents.runtime import AgentRuntimeMixin
+
+
+class OrdersAgent(AgentRuntimeMixin):
+    name = "orders_agent"
+
+    def __init__(
+        self,
+        llm,
+        telemetry=None,
+        tool_router=None,
+        rag_service=None,
+        cache=None,
+        settings=None,
+        observer=None,
+        memory=None,
+        summary_memory=None,
+    ):
+        self.llm = llm
+        self.telemetry = telemetry
+        self.tool_router = tool_router
+        self.rag_service = rag_service
+        self.cache = cache
+        self.settings = settings
+        self.observer = observer
+        self.memory = memory
+        self.summary_memory = summary_memory
+
+    async def run(self, state):
+        await self._emit_ic(
+            "IC.ORDERS_AGENT_STARTED",
+            state,
+            {"business_component": "pedidos"},
+            component="agent.orders.start",
+        )
+
+        tool_context = await self._collect_tool_context(state)
+        if tool_context:
+            await self._emit_ic(
+                "IC.ORDERS_MCP_CONTEXT_COLLECTED",
+                state,
+                {"tool_result_count": len(tool_context)},
+                component="agent.orders.mcp",
+            )
+
+        rag_context, rag_metadata = await self._retrieve_rag_context(state)
+        if rag_metadata.get("enabled"):
+            await self._emit_ic(
+                "IC.ORDERS_RAG_CONTEXT_RETRIEVED",
+                state,
+                {
+                    "document_count": rag_metadata.get("document_count"),
+                    "graph_neighbors": rag_metadata.get("graph_neighbors"),
+                    "latency_ms": rag_metadata.get("latency_ms"),
+                },
+                component="agent.orders.rag",
+            )
+
+        # Prepara ConversationSummaryMemory antes de montar o prompt.
+        # O build_messages() do framework injeta resumo + últimas mensagens quando habilitado.
+        await self.prepare_memory_context(state)
+
+        messages = self.build_messages(
+            state,
+            system_prompt=apply_agent_profile_prompt(
+                state,
+                "Você é um agente de pedidos de varejo. Use dados de tools quando disponíveis.",
+            ),
+            mcp_results=tool_context,
+            rag_context=rag_context,
+            rag_metadata=rag_metadata,
+        )
+
+        answer = await self._invoke_llm_cached(state, "OrdersAgent", messages)
+        result = {
+            "answer": f"[OrdersAgent] {answer}",
+            "next_state": "ORDER_ACTIVE",
+            "mcp_results": tool_context,
+            "rag": rag_metadata,
+            "memory_context_metadata": state.get("memory_context_metadata"),
+        }
+
+        await self._emit_ic(
+            "IC.ORDERS_AGENT_COMPLETED",
+            state,
+            {
+                "answer_chars": len(result.get("answer") or ""),
+                "has_mcp_results": bool(tool_context),
+                "rag_enabled": bool(rag_metadata.get("enabled")),
+                "memory_context": state.get("memory_context_metadata"),
+            },
+            component="agent.orders.completed",
+        )
+        return result
+
+    async def _collect_tool_context(self, state):
+        return await self._collect_mcp_context(state)

templates/agent_template_backend/app/agents/product_agent.py

@@ -0,0 +1,98 @@
+from app.agents.prompting import apply_agent_profile_prompt
+from app.agents.runtime import AgentRuntimeMixin
+
+
+class ProductAgent(AgentRuntimeMixin):
+    name = "productAgent"
+
+    def __init__(
+        self,
+        llm,
+        telemetry=None,
+        tool_router=None,
+        rag_service=None,
+        cache=None,
+        settings=None,
+        observer=None,
+        memory=None,
+        summary_memory=None,
+    ):
+        self.llm = llm
+        self.telemetry = telemetry
+        self.tool_router = tool_router
+        self.rag_service = rag_service
+        self.cache = cache
+        self.settings = settings
+        self.observer = observer
+        self.memory = memory
+        self.summary_memory = summary_memory
+
+    async def run(self, state):
+        await self._emit_ic(
+            "IC.PRODUCT_AGENT_STARTED",
+            state,
+            {"business_component": "produtos"},
+            component="agent.product.start",
+        )
+
+        tool_context = await self._collect_tool_context(state)
+        if tool_context:
+            await self._emit_ic(
+                "IC.PRODUCT_MCP_CONTEXT_COLLECTED",
+                state,
+                {"tool_result_count": len(tool_context)},
+                component="agent.product.mcp",
+            )
+
+        rag_context, rag_metadata = await self._retrieve_rag_context(state)
+        if rag_metadata.get("enabled"):
+            await self._emit_ic(
+                "IC.PRODUCT_RAG_CONTEXT_RETRIEVED",
+                state,
+                {
+                    "document_count": rag_metadata.get("document_count"),
+                    "graph_neighbors": rag_metadata.get("graph_neighbors"),
+                    "latency_ms": rag_metadata.get("latency_ms"),
+                },
+                component="agent.product.rag",
+            )
+
+        # Prepara ConversationSummaryMemory antes de montar o prompt.
+        # O build_messages() do framework injeta resumo + últimas mensagens quando habilitado.
+        await self.prepare_memory_context(state)
+
+        messages = self.build_messages(
+            state,
+            system_prompt=apply_agent_profile_prompt(
+                state,
+                "Você é um agente especialista em produtos, planos e serviços. Explique sem fazer oferta proativa e sem executar ações sem confirmação. Use dados MCP quando disponíveis.",
+            ),
+            mcp_results=tool_context,
+            rag_context=rag_context,
+            rag_metadata=rag_metadata,
+        )
+
+        answer = await self._invoke_llm_cached(state, "ProductAgent", messages)
+        result = {
+            "answer": f"[ProductAgent] {answer}",
+            "next_state": "PRODUCT_ACTIVE",
+            "mcp_results": tool_context,
+            "rag": rag_metadata,
+            "memory_context_metadata": state.get("memory_context_metadata"),
+        }
+
+        await self._emit_ic(
+            "IC.PRODUCT_AGENT_COMPLETED",
+            state,
+            {
+                "answer_chars": len(result.get("answer") or ""),
+                "has_mcp_results": bool(tool_context),
+                "rag_enabled": bool(rag_metadata.get("enabled")),
+                "memory_context": state.get("memory_context_metadata"),
+            },
+            component="agent.product.completed",
+        )
+        return result
+
+    async def _collect_tool_context(self, state):
+        return await self._collect_mcp_context(state)

templates/agent_template_backend/app/agents/prompting.py

@@ -0,0 +1,15 @@
+from __future__ import annotations
+
+
+def apply_agent_profile_prompt(state: dict, default_prompt: str) -> str:
+    """Adiciona o prefixo de prompt configurado para o agent_template selecionado.
+
+    Cada agent_id pode definir metadata.system_prefix em config/agents.yaml. Isso
+    mantém prompts isolados sem duplicar o código dos agentes especializados.
+    """
+    profile = state.get("agent_profile") or (state.get("context") or {}).get("agent_profile") or {}
+    metadata = profile.get("metadata") or {}
+    prefix = (metadata.get("system_prefix") or "").strip()
+    if not prefix:
+        return default_prompt
+    return f"{prefix}\n\n{default_prompt}"

templates/agent_template_backend/app/agents/runtime.py

@@ -0,0 +1,7 @@
+from __future__ import annotations
+
+# Compatibilidade local do template/backend.
+# A implementação oficial agora fica no framework para evitar duplicação entre agentes.
+from agent_framework.runtime import AgentRuntimeMixin, MessageBuilder, RuntimeContext
+
+__all__ = ["AgentRuntimeMixin", "MessageBuilder", "RuntimeContext"]

templates/agent_template_backend/app/agents/support_agent.py

@@ -0,0 +1,98 @@
+from app.agents.prompting import apply_agent_profile_prompt
+from app.agents.runtime import AgentRuntimeMixin
+
+
+class SupportAgent(AgentRuntimeMixin):
+    name = "support_agent"
+
+    def __init__(
+        self,
+        llm,
+        telemetry=None,
+        tool_router=None,
+        rag_service=None,
+        cache=None,
+        settings=None,
+        observer=None,
+        memory=None,
+        summary_memory=None,
+    ):
+        self.llm = llm
+        self.telemetry = telemetry
+        self.tool_router = tool_router
+        self.rag_service = rag_service
+        self.cache = cache
+        self.settings = settings
+        self.observer = observer
+        self.memory = memory
+        self.summary_memory = summary_memory
+
+    async def run(self, state):
+        await self._emit_ic(
+            "IC.SUPPORT_AGENT_STARTED",
+            state,
+            {"business_component": "suporte"},
+            component="agent.support.start",
+        )
+
+        tool_context = await self._collect_tool_context(state)
+        if tool_context:
+            await self._emit_ic(
+                "IC.SUPPORT_MCP_CONTEXT_COLLECTED",
+                state,
+                {"tool_result_count": len(tool_context)},
+                component="agent.support.mcp",
+            )
+
+        rag_context, rag_metadata = await self._retrieve_rag_context(state)
+        if rag_metadata.get("enabled"):
+            await self._emit_ic(
+                "IC.SUPPORT_RAG_CONTEXT_RETRIEVED",
+                state,
+                {
+                    "document_count": rag_metadata.get("document_count"),
+                    "graph_neighbors": rag_metadata.get("graph_neighbors"),
+                    "latency_ms": rag_metadata.get("latency_ms"),
+                },
+                component="agent.support.rag",
+            )
+
+        # Prepara ConversationSummaryMemory antes de montar o prompt.
+        # O build_messages() do framework injeta resumo + últimas mensagens quando habilitado.
+        await self.prepare_memory_context(state)
+
+        messages = self.build_messages(
+            state,
+            system_prompt=apply_agent_profile_prompt(
+                state,
+                "Você é um agente de suporte de varejo para troca, devolução e garantia.",
+            ),
+            mcp_results=tool_context,
+            rag_context=rag_context,
+            rag_metadata=rag_metadata,
+        )
+
+        answer = await self._invoke_llm_cached(state, "SupportAgent", messages)
+        result = {
+            "answer": f"[SupportAgent] {answer}",
+            "next_state": "SUPPORT_ACTIVE",
+            "mcp_results": tool_context,
+            "rag": rag_metadata,
+            "memory_context_metadata": state.get("memory_context_metadata"),
+        }
+
+        await self._emit_ic(
+            "IC.SUPPORT_AGENT_COMPLETED",
+            state,
+            {
+                "answer_chars": len(result.get("answer") or ""),
+                "has_mcp_results": bool(tool_context),
+                "rag_enabled": bool(rag_metadata.get("enabled")),
+                "memory_context": state.get("memory_context_metadata"),
+            },
+            component="agent.support.completed",
+        )
+        return result
+
+    async def _collect_tool_context(self, state):
+        return await self._collect_mcp_context(state)

templates/agent_template_backend/app/examples/__init__.py

@@ -0,0 +1 @@
+"""Exemplos de uso do template backend enterprise."""

templates/agent_template_backend/app/examples/grl_examples.py

@@ -0,0 +1,37 @@
+"""Exemplos de GRL.
+
+GRL representa eventos de guardrails. Em regra, GRL.001..GRL.009 são emitidos
+pelo pipeline de guardrails e pelo OutputSupervisor do framework. Use emissão
+manual apenas para validações customizadas do agente.
+"""
+
+from typing import Any
+
+
+async def exemplo_guardrail_observado(observer: Any, state: dict[str, Any], rail_code: str, reason: str) -> None:
+    await observer.emit_grl(
+        "OBSERVE",
+        {
+            "session_id": state.get("conversation_key") or state.get("session_id"),
+            "tenant_id": state.get("tenant_id"),
+            "agent_id": state.get("agent_id"),
+            "rail_code": rail_code,
+            "reason": reason,
+        },
+        component="examples.grl",
+    )
+
+
+async def exemplo_guardrail_block(observer: Any, state: dict[str, Any], rail_code: str, reason: str) -> None:
+    await observer.emit_grl(
+        "004",
+        {
+            "session_id": state.get("conversation_key") or state.get("session_id"),
+            "tenant_id": state.get("tenant_id"),
+            "agent_id": state.get("agent_id"),
+            "rail_code": rail_code,
+            "reason": reason,
+            "action": "block",
+        },
+        component="examples.grl",
+    )

templates/agent_template_backend/app/examples/ic_examples.py

@@ -0,0 +1,34 @@
+"""Exemplos de IC - Item de Controle.
+
+ICs representam eventos de negócio. Eles alimentam Informacional, Curadoria,
+analytics, BigQuery ou qualquer publisher configurado no framework.
+"""
+
+from typing import Any
+
+
+async def exemplo_fatura_consultada(observer: Any, state: dict[str, Any], invoice_id: str) -> None:
+    await observer.emit_ic(
+        "IC.FATURA_CONSULTADA",
+        {
+            "session_id": state.get("conversation_key") or state.get("session_id"),
+            "tenant_id": state.get("tenant_id"),
+            "agent_id": state.get("agent_id"),
+            "invoice_id": invoice_id,
+        },
+        component="examples.ic",
+    )
+
+
+async def exemplo_acao_concluida(observer: Any, state: dict[str, Any], action_name: str, ok: bool) -> None:
+    await observer.emit_ic(
+        "IC.ACAO_CONCLUIDA",
+        {
+            "session_id": state.get("conversation_key") or state.get("session_id"),
+            "tenant_id": state.get("tenant_id"),
+            "agent_id": state.get("agent_id"),
+            "action_name": action_name,
+            "ok": ok,
+        },
+        component="examples.ic",
+    )

templates/agent_template_backend/app/examples/mcp_examples.py

@@ -0,0 +1,43 @@
+"""Exemplos de MCP + IC.
+
+O AgentRuntimeMixin já possui _collect_mcp_context(), mas este arquivo mostra o
+padrão para chamadas explícitas ao tool_router quando necessário.
+"""
+
+from typing import Any
+
+
+async def exemplo_chamada_mcp(tool_router: Any, observer: Any, state: dict[str, Any], tool_name: str, payload: dict[str, Any]) -> Any:
+    session_id = state.get("conversation_key") or state.get("session_id")
+
+    await observer.emit_ic(
+        "IC.MCP_TOOL_CALLED",
+        {
+            "session_id": session_id,
+            "tenant_id": state.get("tenant_id"),
+            "agent_id": state.get("agent_id"),
+            "tool_name": tool_name,
+        },
+        component="examples.mcp",
+    )
+
+    result = await tool_router.call(
+        tool_name,
+        payload,
+        business_context=(state.get("context") or {}).get("business_context") or {},
+        original_context=state.get("context") or {},
+    )
+
+    await observer.emit_ic(
+        "IC.TOOL_CALLED",
+        {
+            "session_id": session_id,
+            "tenant_id": state.get("tenant_id"),
+            "agent_id": state.get("agent_id"),
+            "tool_name": tool_name,
+            "ok": getattr(result, "ok", None),
+        },
+        component="examples.mcp",
+    )
+
+    return result

templates/agent_template_backend/app/examples/noc_examples.py

@@ -0,0 +1,37 @@
+"""Exemplos de NOC.
+
+NOC representa telemetria operacional. O workflow do template já emite NOC.001,
+NOC.005 e NOC.006. Estes exemplos mostram eventos adicionais que a squad pode
+emitir em pontos críticos.
+"""
+
+from typing import Any
+
+
+async def exemplo_api_invalida(observer: Any, state: dict[str, Any], api_url: str, status_code: int, latency_ms: int) -> None:
+    await observer.emit_noc(
+        "002",
+        {
+            "session_id": state.get("conversation_key") or state.get("session_id"),
+            "tenant_id": state.get("tenant_id"),
+            "agent_id": state.get("agent_id"),
+            "apiUrl": api_url,
+            "statusCode": status_code,
+            "latencyMs": latency_ms,
+        },
+        component="examples.noc",
+    )
+
+
+async def exemplo_latencia_banco(observer: Any, state: dict[str, Any], resource_name: str, latency_ms: int) -> None:
+    await observer.emit_noc(
+        "003",
+        {
+            "session_id": state.get("conversation_key") or state.get("session_id"),
+            "tenant_id": state.get("tenant_id"),
+            "agent_id": state.get("agent_id"),
+            "resourceName": resource_name,
+            "latencyMs": latency_ms,
+        },
+        component="examples.noc",
+    )

templates/agent_template_backend/app/examples/observer_examples.py

@@ -0,0 +1,28 @@
+"""Resumo prático do Observer corporativo.
+
+Use este arquivo como cola rápida para IC, NOC e GRL.
+"""
+
+from typing import Any
+
+
+async def emitir_eventos_basicos(observer: Any, state: dict[str, Any]) -> None:
+    session_id = state.get("conversation_key") or state.get("session_id")
+
+    await observer.emit_ic(
+        "IC.EXEMPLO_NEGOCIO",
+        {"session_id": session_id, "agent_id": state.get("agent_id")},
+        component="examples.observer",
+    )
+
+    await observer.emit_noc(
+        "EXEMPLO_OPERACIONAL",
+        {"session_id": session_id, "agent_id": state.get("agent_id")},
+        component="examples.observer",
+    )
+
+    await observer.emit_grl(
+        "OBSERVE",
+        {"session_id": session_id, "agent_id": state.get("agent_id"), "rail_code": "CUSTOM"},
+        component="examples.observer",
+    )

templates/agent_template_backend/app/main.py

@@ -0,0 +1,476 @@
+from __future__ import annotations
+
+import logging
+from uuid import uuid4
+import time
+
+from fastapi import FastAPI, HTTPException, Request
+from fastapi.middleware.cors import CORSMiddleware
+from fastapi.responses import StreamingResponse
+from pydantic import BaseModel
+
+from agent_framework.channels.base import ChannelResponse
+from agent_framework.channels.gateway import ChannelGateway
+from agent_framework.config.agent_registry import AgentProfileRegistry
+from agent_framework.config.settings import settings
+from agent_framework.analytics.factory import create_analytics_publisher
+from agent_framework.observer import configure as configure_global_observer
+from agent_framework.llm.providers import create_llm
+from agent_framework.memory.message_history import create_memory
+from agent_framework.memory.summary_memory import create_conversation_summary_memory
+from agent_framework.mcp.tool_router import create_mcp_tool_router
+from agent_framework.models.identity import AgentIdentity
+from agent_framework.identity import IdentityResolver, BusinessContext
+from agent_framework.models.session import ChatMessage, SessionContext
+from agent_framework.observability.telemetry import Telemetry
+from agent_framework.observability.context import set_observability_context, clear_observability_context
+from agent_framework.repositories.session_repository import create_session_repository
+from agent_framework.checkpoints.checkpoint_repository import create_checkpoint_repository
+from agent_framework.cache.cache import create_cache
+from agent_framework.billing.usage_repository import create_usage_repository
+from agent_framework.sse.events import SSEHub
+from app.workflows.agent_graph import AgentWorkflow
+from app.observability.telemetry_observer import TelemetryBackedAgentObserver
+
+logging.basicConfig(level=settings.LOG_LEVEL)
+logger = logging.getLogger("agent_template_backend")
+
+app = FastAPI(title="Agent Template Backend FIRST-ready")
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=[o.strip() for o in settings.CORS_ORIGINS.split(",")],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+telemetry = Telemetry(settings)
+usage_repository = create_usage_repository(settings)
+llm = create_llm(settings, telemetry=telemetry, usage_repository=usage_repository)
+memory = create_memory(settings)
+summary_memory = create_conversation_summary_memory(settings, message_history=memory, llm=llm, telemetry=telemetry)
+sessions = create_session_repository(settings)
+checkpoints = create_checkpoint_repository(settings)
+cache = create_cache(settings, telemetry=telemetry)
+gateway = ChannelGateway(input_mode=settings.FRAMEWORK_CHANNEL_INPUT_MODE)
+analytics = create_analytics_publisher(settings)
+observer = TelemetryBackedAgentObserver(telemetry=telemetry)
+configure_global_observer({
+    "enabled": getattr(settings, "ENABLE_ANALYTICS", False),
+    "providers": getattr(settings, "ANALYTICS_PROVIDERS", "oci_streaming"),
+    "topic_path": getattr(settings, "GCP_PUBSUB_TOPIC_PATH", None) or getattr(settings, "AGENT_PUBSUB_TOPIC", None),
+})
+tool_router = create_mcp_tool_router(settings, telemetry=telemetry)
+identity_resolver = IdentityResolver.from_yaml(settings.IDENTITY_CONFIG_PATH)
+agent_profiles = AgentProfileRegistry(settings)
+sse_hub = SSEHub(settings, telemetry=telemetry)
+workflow = AgentWorkflow(llm, memory, telemetry, analytics, settings, observer=observer, tool_router=tool_router, summary_memory=summary_memory)
+
+logger.info("LLM provider carregado: %s", llm.__class__.__name__)
+logger.info("Langfuse habilitado: %s host=%s", telemetry.is_enabled(), settings.LANGFUSE_HOST)
+logger.info("Analytics habilitado: %s providers=%s", getattr(settings, "ENABLE_ANALYTICS", False), getattr(settings, "ANALYTICS_PROVIDERS", ""))
+logger.info("Agentes disponíveis: %s", [p.agent_id for p in agent_profiles.list_profiles()])
+logger.info("Framework channel input mode: %s", gateway.input_mode)
+
+@app.middleware("http")
+async def observability_context_middleware(request: Request, call_next):
+    request_id = request.headers.get("x-request-id") or str(uuid4())
+    set_observability_context(
+        request_id=request_id,
+        channel=request.headers.get("x-channel") or "http",
+        ura_call_id=request.headers.get("x-ura-call-id"),
+    )
+    started = time.time()
+    try:
+        response = await call_next(request)
+        response.headers["x-request-id"] = request_id
+        await telemetry.event("http.request.completed", {
+            "method": request.method,
+            "path": request.url.path,
+            "status_code": response.status_code,
+            "duration_ms": int((time.time() - started) * 1000),
+        }, kind="http")
+        return response
+    except Exception as exc:
+        await telemetry.event("http.request.failed", {
+            "method": request.method,
+            "path": request.url.path,
+            "error": str(exc),
+            "duration_ms": int((time.time() - started) * 1000),
+        }, kind="http")
+        raise
+
+
+class GatewayRequest(BaseModel):
+    channel: str = "web"
+    payload: dict
+    agent_id: str | None = None
+    tenant_id: str | None = None
+
+
+def _resolve_identity(req: GatewayRequest, msg) -> tuple[AgentIdentity, dict, BusinessContext, list[str]]:
+    payload = req.payload or {}
+    context = dict(msg.context or {})
+    tenant_id = req.tenant_id or payload.get("tenant_id") or context.get("tenant_id") or "default"
+    agent_id = req.agent_id or payload.get("agent_id") or context.get("agent_id") or agent_profiles.default_agent_id
+    profile = agent_profiles.get(agent_id)
+
+    # 1) Identidade técnica do framework: isola tenant/agente/sessão.
+    context.update({"tenant_id": tenant_id, "agent_id": profile.agent_id, "agent_profile": profile.__dict__})
+    identity = AgentIdentity.from_context(context, session_id=msg.session_id)
+
+    # 2) Identidade de negócio: chaves canônicas vindas do front/canal.
+    #    Estas chaves são estáveis na sessão e seguem até agentes e MCP Router.
+    previous_business_context = context.get("business_context") or context.get("identity") or {}
+    business_context = identity_resolver.resolve(
+        {**payload, **context},
+        session_id=identity.conversation_key(),
+        previous=previous_business_context,
+    )
+    missing_identity_keys = identity_resolver.validate(business_context)
+    context.update({
+        "business_context": business_context.model_dump(),
+        "business_keys": business_context.to_context_dict(),
+        "identity_missing": missing_identity_keys,
+        "conversation_key": identity.conversation_key(),
+        "original_session_id": msg.session_id,
+    })
+    return identity, context, business_context, missing_identity_keys
+
+
+async def _process_gateway_message(req: GatewayRequest, emit_sse: bool = False) -> dict:
+    try:
+        msg = await gateway.normalize(req.channel, req.payload)
+    except ValueError as exc:
+        raise HTTPException(status_code=422, detail=str(exc)) from exc
+    identity, normalized_context, business_context, missing_identity_keys = _resolve_identity(req, msg)
+    agent_session_id = identity.conversation_key()
+    message_id = (req.payload or {}).get("message_id") or str(uuid4())
+    set_observability_context(
+        session_id=agent_session_id,
+        user_id=msg.user_id,
+        tenant_id=identity.tenant_id,
+        agent_id=identity.agent_id,
+        channel=msg.channel,
+        message_id=message_id,
+        ura_call_id=(req.payload or {}).get("ura_call_id") or normalized_context.get("ura_call_id") or business_context.interaction_key,
+    )
+
+    stream = sse_hub.stream_for(agent_session_id)
+    async with stream.lock:
+        await sse_hub.emit(agent_session_id, "flow.start", {"session_id": agent_session_id, "message_id": message_id, "agent_id": identity.agent_id}) if emit_sse else None
+
+        session = await sessions.get(agent_session_id)
+        if not session:
+            context_fields = {
+                k: v
+                for k, v in normalized_context.items()
+                if k in SessionContext.model_fields
+                and k not in {"tenant_id", "agent_id", "session_id", "user_id", "channel", "channel_id"}
+            }
+            session = SessionContext(
+                tenant_id=identity.tenant_id,
+                agent_id=identity.agent_id,
+                session_id=agent_session_id,
+                user_id=msg.user_id,
+                channel=msg.channel,
+                channel_id=msg.channel_id,
+                **context_fields,
+            )
+
+        session.tenant_id = identity.tenant_id
+        session.agent_id = identity.agent_id
+        session.channel = msg.channel
+        session.channel_id = msg.channel_id or session.channel_id
+        await sessions.upsert(session)
+        session.metadata = {
+            **(session.metadata or {}),
+            "business_context": business_context.model_dump(),
+            "identity_missing": missing_identity_keys,
+            "original_context": normalized_context,
+        }
+        await sse_hub.emit(agent_session_id, "session.upserted", {"session_id": agent_session_id, "business_context": business_context.model_dump()}) if emit_sse else None
+
+        await memory.append(
+            agent_session_id,
+            ChatMessage(
+                role="user",
+                content=msg.text,
+                metadata={
+                    **normalized_context,
+                    "agent_id": identity.agent_id,
+                    "tenant_id": identity.tenant_id,
+                    "message_id": message_id,
+                    "business_context": business_context.model_dump(),
+                    "identity_missing": missing_identity_keys,
+                },
+            ),
+        )
+        await sse_hub.emit(agent_session_id, "message.received", {"session_id": agent_session_id, "role": "user"}) if emit_sse else None
+        history = [m.model_dump(mode="json") for m in await memory.list(agent_session_id)]
+
+        trace_input = {
+            "text": msg.text,
+            "channel": msg.channel,
+            "channel_id": msg.channel_id,
+            "tenant_id": identity.tenant_id,
+            "agent_id": identity.agent_id,
+            "conversation_key": agent_session_id,
+            "message_id": message_id,
+            "business_context": business_context.model_dump(),
+            "identity_missing": missing_identity_keys,
+        }
+
+        async with telemetry.span(
+            "agent.gateway_message",
+            session_id=agent_session_id,
+            user_id=session.user_id,
+            channel=msg.channel,
+            input=trace_input,
+            tags=["agent-template", msg.channel, f"agent:{identity.agent_id}", f"tenant:{identity.tenant_id}"],
+        ):
+            await telemetry.event("gateway.message.received", trace_input)
+            await sse_hub.emit(agent_session_id, "workflow.started", trace_input) if emit_sse else None
+            result = await workflow.ainvoke(
+                {
+                    "tenant_id": identity.tenant_id,
+                    "agent_id": identity.agent_id,
+                    "session_id": agent_session_id,
+                    "conversation_key": agent_session_id,
+                    "agent_profile": normalized_context["agent_profile"],
+                    "user_text": msg.text,
+                    "history": history,
+                    "context": {
+                        **normalized_context,
+                        "session": session.model_dump(mode="json"),
+                        "original_session_id": msg.session_id,
+                        "session_id": agent_session_id,
+                        "conversation_key": agent_session_id,
+                        "user_id": session.user_id,
+                        "channel": msg.channel,
+                        "message_id": message_id,
+                        "business_context": business_context.model_dump(),
+                        "business_keys": business_context.to_context_dict(),
+                        "identity_missing": missing_identity_keys,
+                    },
+                }
+            )
+
+        await checkpoints.put(agent_session_id, {"state": result, "message_id": message_id})
+        await sse_hub.emit(agent_session_id, "workflow.completed", {"session_id": agent_session_id, "route": result.get("route"), "intent": result.get("intent")}) if emit_sse else None
+
+        answer = result.get("final_answer") or result.get("answer") or ""
+        await memory.append(
+            agent_session_id,
+            ChatMessage(
+                role="assistant",
+                content=answer,
+                metadata={
+                    "tenant_id": identity.tenant_id,
+                    "agent_id": identity.agent_id,
+                    "message_id": f"assistant-{message_id}",
+                    "route": result.get("route"),
+                    "intent": result.get("intent"),
+                    "route_decision": result.get("route_decision"),
+                    "judges": result.get("judge_results"),
+                },
+            ),
+        )
+
+        await telemetry.event(
+            "gateway.message.responded",
+            {
+                "session_id": agent_session_id,
+                "tenant_id": identity.tenant_id,
+                "agent_id": identity.agent_id,
+                "route": result.get("route"),
+                "intent": result.get("intent"),
+                "answer_chars": len(answer),
+            },
+        )
+
+        response = ChannelResponse(
+            channel=msg.channel,
+            session_id=agent_session_id,
+            text=answer,
+            metadata={
+                "channel_id": msg.channel_id,
+                "tenant_id": identity.tenant_id,
+                "agent_id": identity.agent_id,
+                "original_session_id": msg.session_id,
+                "conversation_key": agent_session_id,
+                "message_id": message_id,
+                "route": result.get("route"),
+                "intent": result.get("intent"),
+                "route_decision": result.get("route_decision"),
+                "domain": result.get("domain"),
+                "mcp_tools": result.get("mcp_tools"),
+                "mcp_results": result.get("mcp_results"),
+                "business_context": business_context.model_dump(),
+                "identity_missing": missing_identity_keys,
+                "judges": result.get("judge_results"),
+                "guardrails": result.get("guardrail_decisions"),
+            },
+        )
+        rendered = await gateway.render(response)
+        await sse_hub.emit(agent_session_id, "message.responded", rendered) if emit_sse else None
+        await sse_hub.emit(agent_session_id, "flow.end", {"session_id": agent_session_id, "message_id": message_id}) if emit_sse else None
+        return rendered
+
+
+@app.get("/health")
+async def health():
+    return {
+        "status": "ok",
+        "llm_provider": settings.LLM_PROVIDER,
+        "llm_class": llm.__class__.__name__,
+        "langfuse_enabled": telemetry.is_enabled(),
+        "agents": [p.agent_id for p in agent_profiles.list_profiles()],
+        "default_agent_id": agent_profiles.default_agent_id,
+        "routing_mode": settings.ROUTING_MODE,
+        "sse_enabled": settings.ENABLE_SSE,
+        "session_repository": settings.SESSION_REPOSITORY_PROVIDER,
+        "memory_repository": settings.MEMORY_REPOSITORY_PROVIDER,
+        "checkpoint_repository": settings.CHECKPOINT_REPOSITORY_PROVIDER,
+        "usage_repository": settings.USAGE_REPOSITORY_PROVIDER,
+        "identity_config_path": settings.IDENTITY_CONFIG_PATH,
+        "mcp_parameter_mapping_path": settings.MCP_PARAMETER_MAPPING_PATH,
+        "framework_channel_input_mode": settings.FRAMEWORK_CHANNEL_INPUT_MODE,
+        "legacy_channel_gateway_mode": settings.CHANNEL_GATEWAY_MODE,
+    }
+
+
+@app.get("/agents")
+async def list_agents():
+    return {"default_agent_id": agent_profiles.default_agent_id, "agents": [p.__dict__ for p in agent_profiles.list_profiles()]}
+
+
+@app.get("/debug/env")
+async def debug_env():
+    return {
+        "APP_ENV": settings.APP_ENV,
+        "LLM_PROVIDER": settings.LLM_PROVIDER,
+        "ENABLE_LANGFUSE": settings.ENABLE_LANGFUSE,
+        "LANGFUSE_HOST": settings.LANGFUSE_HOST,
+        "TELEMETRY_ENABLED": telemetry.is_enabled(),
+        "SQLITE_DB_PATH": settings.SQLITE_DB_PATH,
+        "SESSION_REPOSITORY_PROVIDER": settings.SESSION_REPOSITORY_PROVIDER,
+        "MEMORY_REPOSITORY_PROVIDER": settings.MEMORY_REPOSITORY_PROVIDER,
+        "CHECKPOINT_REPOSITORY_PROVIDER": settings.CHECKPOINT_REPOSITORY_PROVIDER,
+        "AGENTS_CONFIG_PATH": settings.AGENTS_CONFIG_PATH,
+        "ROUTING_CONFIG_PATH": settings.ROUTING_CONFIG_PATH,
+        "ROUTING_MODE": settings.ROUTING_MODE,
+        "FRAMEWORK_CHANNEL_INPUT_MODE": settings.FRAMEWORK_CHANNEL_INPUT_MODE,
+        "CHANNEL_GATEWAY_MODE": settings.CHANNEL_GATEWAY_MODE,
+    }
+
+
+@app.get("/test-llm")
+async def test_llm():
+    async with telemetry.span("debug.test_llm", input={"message": "Diga apenas OK"}):
+        answer = await llm.ainvoke([
+            {"role": "system", "content": "Responda de forma curta."},
+            {"role": "user", "content": "Diga apenas OK"},
+        ])
+    telemetry.flush()
+    return {"provider": llm.__class__.__name__, "answer": answer}
+
+
+@app.post("/debug/route")
+async def debug_route(req: GatewayRequest):
+    msg = await gateway.normalize(req.channel, req.payload)
+    identity, context, business_context, missing_identity_keys = _resolve_identity(req, msg)
+    state = {
+        "tenant_id": identity.tenant_id,
+        "agent_id": identity.agent_id,
+        "session_id": msg.session_id or "debug-session",
+        "conversation_key": identity.conversation_key(),
+        "agent_profile": context["agent_profile"],
+        "user_text": msg.text,
+        "sanitized_input": msg.text,
+        "history": [],
+        "context": {**context, "session": context.get("session", {}), "channel": msg.channel, "business_context": business_context.model_dump()},
+    }
+    if settings.ROUTING_MODE == "supervisor":
+        plan = await workflow.supervisor.route_plan(state)
+        return {"mode": "supervisor", "route": "supervisor_agent", "agents": plan.agents, "intent": plan.intent, "confidence": plan.confidence, "reason": plan.reason, "metadata": plan.metadata}
+    decision = await workflow.router.route(state)
+    data = decision.model_dump(mode="json")
+    data["mode"] = "router"
+    return data
+
+
+
+
+@app.post("/debug/identity")
+async def debug_identity(req: GatewayRequest):
+    msg = await gateway.normalize(req.channel, req.payload)
+    identity, context, business_context, missing_identity_keys = _resolve_identity(req, msg)
+    return {
+        "technical_identity": {
+            "tenant_id": identity.tenant_id,
+            "agent_id": identity.agent_id,
+            "conversation_key": identity.conversation_key(),
+            "original_session_id": msg.session_id,
+        },
+        "business_context": business_context.model_dump(),
+        "identity_missing": missing_identity_keys,
+        "context_keys": sorted(context.keys()),
+    }
+
+@app.get("/debug/usage")
+async def debug_usage(tenant_id: str | None = None, session_id: str | None = None):
+    return await usage_repository.summarize(tenant_id=tenant_id, session_id=session_id)
+
+
+@app.get("/debug/mcp/tools")
+async def debug_mcp_tools():
+    return {"enabled": tool_router.enabled, "tools": tool_router.describe_tools()}
+
+
+@app.post("/debug/mcp/call/{tool_name}")
+async def debug_mcp_call(tool_name: str, arguments: dict | None = None):
+    arguments = arguments or {}
+    ctx = arguments.get("business_context") or arguments.get("identity") or {}
+    result = await tool_router.call(
+        tool_name,
+        arguments,
+        business_context=ctx,
+        original_context=arguments,
+    )
+    return result.model_dump(mode="json")
+
+
+@app.post("/gateway/message")
+async def gateway_message(req: GatewayRequest):
+    return await _process_gateway_message(req, emit_sse=False)
+
+
+@app.post("/gateway/message/sse")
+async def gateway_message_sse(req: GatewayRequest):
+    return await _process_gateway_message(req, emit_sse=True)
+
+
+@app.get("/gateway/events/{session_id}")
+async def gateway_events(session_id: str, request: Request):
+    last = request.headers.get("last-event-id") or request.query_params.get("last_event_id") or "0"
+    return StreamingResponse(
+        sse_hub.subscribe(session_id, int(last)),
+        media_type="text/event-stream",
+        headers={"Cache-Control": "no-cache", "Connection": "keep-alive", "X-Accel-Buffering": "no"},
+    )
+
+
+@app.get("/sessions/{session_id}/messages")
+async def get_session_messages(session_id: str, limit: int = 50):
+    return {"session_id": session_id, "messages": [m.model_dump(mode="json") for m in await memory.list(session_id, limit)]}
+
+
+@app.get("/sessions/{session_id}/checkpoint")
+async def get_session_checkpoint(session_id: str):
+    return {"session_id": session_id, "checkpoint": await checkpoints.get_latest(session_id)}
+
+
+@app.on_event("shutdown")
+async def shutdown():
+    telemetry.shutdown()

templates/agent_template_backend/app/observability/telemetry_observer.py

@@ -0,0 +1,84 @@
+from __future__ import annotations
+
+"""Observer adapter that emits IC/NOC/GRL through framework Telemetry only.
+
+This avoids a second Langfuse root trace created by AgentObserver ->
+AnalyticsPublisher while preserving the events inside the active request span.
+"""
+
+from datetime import datetime, timezone
+from typing import Any
+
+
+def _normalize_ic_code(code: str) -> str:
+    code = str(code or "UNKNOWN").strip()
+    return code if code.startswith(("IC.", "AGA.", "NOC.", "GRL.")) else f"IC.{code}"
+
+
+def _normalize_noc_code(code: str) -> str:
+    code = str(code or "UNKNOWN").strip()
+    return code if code.startswith("NOC.") else f"NOC.{code}"
+
+
+def _normalize_grl_code(code: str) -> str:
+    code = str(code or "UNKNOWN").strip()
+    return code if code.startswith("GRL.") else f"GRL.{code}"
+
+
+def _kind_for(event_type: str) -> str:
+    if event_type.startswith(("IC.", "AGA.")):
+        return "ic"
+    if event_type.startswith("NOC."):
+        return "noc"
+    if event_type.startswith("GRL."):
+        return "grl"
+    return "event"
+
+
+class TelemetryBackedAgentObserver:
+    """Drop-in subset of AgentObserver backed by Telemetry.event.
+
+    Do not publish through AnalyticsPublisher here. Analytics publishing may be
+    configured with a Langfuse provider, and that path creates an extra root
+    trace for business events such as IC.AGENT_COMPLETED/NOC.006. Telemetry.event
+    uses the active span/trace context, so these events appear inside the single
+    request trace.
+    """
+
+    def __init__(self, telemetry: Any, *, source: str = "agent_framework") -> None:
+        self.telemetry = telemetry
+        self.source = source
+
+    async def emit(
+        self,
+        event_type: str,
+        payload: dict[str, Any] | None = None,
+        *,
+        metadata: dict[str, Any] | None = None,
+        source: str | None = None,
+    ) -> dict[str, Any]:
+        body = dict(payload or {})
+        meta = dict(metadata or {})
+        body.setdefault("tag", event_type)
+        event = {
+            "eventType": event_type,
+            "source": source or self.source,
+            "eventDate": datetime.now(timezone.utc).isoformat(),
+            "body": body,
+            "metadata": meta,
+        }
+        try:
+            await self.telemetry.event(event_type, event, kind=_kind_for(event_type))
+        except TypeError:
+            # Compatibility with older Telemetry.event signatures.
+            await self.telemetry.event(event_type, event)
+        return event
+
+    async def emit_ic(self, code: str, payload: dict[str, Any] | None = None, **metadata: Any) -> dict[str, Any]:
+        return await self.emit(_normalize_ic_code(code), payload, metadata={**metadata, "ic": True})
+
+    async def emit_noc(self, code: str, payload: dict[str, Any] | None = None, **metadata: Any) -> dict[str, Any]:
+        return await self.emit(_normalize_noc_code(code), payload, metadata={**metadata, "noc": True})
+
+    async def emit_grl(self, code: str, payload: dict[str, Any] | None = None, **metadata: Any) -> dict[str, Any]:
+        return await self.emit(_normalize_grl_code(code), payload, metadata={**metadata, "grl": True})

templates/agent_template_backend/app/state.py

@@ -0,0 +1,34 @@
+from typing import Any, TypedDict
+
+
+class AgentState(TypedDict, total=False):
+    tenant_id: str
+    agent_id: str
+    session_id: str
+    conversation_key: str
+    agent_profile: dict[str, Any]
+    user_text: str
+    sanitized_input: str
+    route: str
+    intent: str
+    route_decision: dict[str, Any]
+    answer: str
+    final_answer: str
+    history: list[dict[str, Any]]
+    context: dict[str, Any]
+    guardrail_decisions: list[dict[str, Any]]
+    judge_results: list[dict[str, Any]]
+    next_state: str
+    domain: str
+    mcp_tools: list[str]
+    mcp_results: list[dict[str, Any]]
+    supervisor_plan: dict[str, Any]
+    supervisor_results: list[dict[str, Any]]
+    active_agent: str
+    blocked: bool
+    supervisor_action: str
+    supervisor_guidance: str
+    supervisor_attempt: int
+    supervisor_handover_reason: str
+    output_supervisor_results: list[dict[str, Any]]
+    output_guardrails_already_applied: bool

templates/agent_template_backend/app/workflows/agent_graph.py

@@ -0,0 +1,705 @@
+from agent_framework.checkpoints.langgraph_saver import create_langgraph_checkpointer
+from langgraph.graph import END, START, StateGraph
+
+from agent_framework.guardrails.pipeline import GuardrailPipeline
+from agent_framework.guardrails.output_supervisor import OutputSupervisor
+from agent_framework.guardrails.rail_action import RailAction
+from agent_framework.guardrails.rail_result import RailResult
+from agent_framework.judges.judge import JudgePipeline
+from agent_framework.routing.enterprise_router import EnterpriseRouter
+from agent_framework.supervisor.supervisor import Supervisor
+from agent_framework.observability.workflow_events import WorkflowTelemetry
+from agent_framework.observability.guardrail_events import GuardrailTelemetry
+from agent_framework.observability.judge_events import JudgeTelemetry
+from agent_framework.observability.langgraph_telemetry import LangGraphDeepTelemetry
+from agent_framework.observability.observer import AgentObserver
+from app.agents.billing_agent import BillingAgent
+from app.agents.product_agent import ProductAgent
+from app.agents.orders_agent import OrdersAgent
+from app.agents.support_agent import SupportAgent
+from app.state import AgentState
+from agent_framework.rag.rag_service import RagService
+from agent_framework.rag.embedding_provider import create_embedding_provider
+from agent_framework.cache.cache import create_cache
+
+
+class LegacyOutputGuardrailRail:
+    """Adapter: reutiliza GuardrailPipeline.run_output dentro do OutputSupervisor novo.
+
+    O framework antigo retornava decisões allowed=True/False. O OutputSupervisor
+    corporativo trabalha com RailAction (allow/sanitize/retry/block/handover).
+    Este adapter evita reescrever todos os rails agora e mantém compatibilidade.
+    """
+
+    code = "LEGACY_OUTPUT_GUARDRAILS"
+
+    def __init__(self, pipeline: GuardrailPipeline):
+        self.pipeline = pipeline
+
+    async def evaluate(self, candidate: str, context: dict):
+        final, decisions = await self.pipeline.run_output(candidate, context)
+        serialized = [d.model_dump() for d in decisions]
+
+        blocked = [d for d in decisions if not getattr(d, "allowed", True)]
+        if blocked:
+            first = blocked[0]
+            code = (getattr(first, "code", "") or "").upper()
+            action = RailAction.RETRY if code in {"REVPREC", "CMP", "SCO", "GND"} else RailAction.BLOCK
+            return RailResult(
+                code=code or self.code,
+                action=action,
+                reason=getattr(first, "reason", "Resposta bloqueada por guardrail de saída"),
+                guidance=getattr(first, "reason", "Regerar resposta seguindo as políticas de saída."),
+                sanitized_text=final,
+                metadata={"legacy_decisions": serialized},
+            )
+
+        if final != candidate:
+            return RailResult(
+                code=self.code,
+                action=RailAction.SANITIZE,
+                reason="Resposta sanitizada por guardrail de saída legado.",
+                sanitized_text=final,
+                metadata={"legacy_decisions": serialized},
+            )
+
+        return RailResult(
+            code=self.code,
+            action=RailAction.ALLOW,
+            reason="Resposta aprovada pelos guardrails de saída legados.",
+            sanitized_text=final,
+            metadata={"legacy_decisions": serialized},
+        )
+
+
+class AgentWorkflow:
+    """Workflow principal com dois modos de roteamento.
+
+    Modos suportados por configuração:
+      ROUTING_MODE=router
+        input_guardrails -> routing_decision/EnterpriseRouter -> 1 agente -> output_guardrails
+
+      ROUTING_MODE=supervisor
+        input_guardrails -> routing_decision/Supervisor -> supervisor_agent -> N agentes -> consolidação
+
+    Em ambos os modos, memória/checkpoint/session usam tenant_id:agent_id:session_id.
+    """
+
+    def __init__(self, llm, memory, telemetry, analytics, settings, observer: AgentObserver | None = None, tool_router=None, summary_memory=None):
+        self.llm = llm
+        self.memory = memory
+        self.telemetry = telemetry
+        self.analytics = analytics
+        self.observer = observer or AgentObserver(analytics=analytics)
+        self.settings = settings
+        self.tool_router = tool_router
+        self.summary_memory = summary_memory
+        self.guardrails = GuardrailPipeline(
+            observer=self.observer,
+            enable_parallel=bool(getattr(settings, "ENABLE_PARALLEL_GUARDRAILS", True)),
+            fail_fast=bool(getattr(settings, "GUARDRAILS_FAIL_FAST", True)),
+        )
+        self.output_supervisor_engine = OutputSupervisor(
+            rails=[LegacyOutputGuardrailRail(self.guardrails)],
+            observer=self.observer,
+            max_retries=int(getattr(settings, "OUTPUT_SUPERVISOR_MAX_RETRIES", 3)),
+            enable_parallel=bool(getattr(settings, "ENABLE_PARALLEL_GUARDRAILS", True)),
+            fail_fast=bool(getattr(settings, "GUARDRAILS_FAIL_FAST", True)),
+        )
+        self.judges = JudgePipeline()
+        self.supervisor = Supervisor()
+        self.workflow_telemetry = WorkflowTelemetry(telemetry)
+        self.guardrail_telemetry = GuardrailTelemetry(telemetry)
+        self.judge_telemetry = JudgeTelemetry(telemetry)
+        self.langgraph_telemetry = LangGraphDeepTelemetry(telemetry)
+        self.cache = create_cache(settings)
+        self.embedding_provider = create_embedding_provider(settings)
+        self.rag_service = RagService(settings, embedding_provider=self.embedding_provider, telemetry=telemetry)
+        self.router = EnterpriseRouter(settings, llm=llm, telemetry=telemetry)
+        agent_kwargs = {"telemetry": telemetry, "tool_router": getattr(self, "tool_router", None), "rag_service": self.rag_service, "cache": self.cache, "settings": settings, "observer": self.observer, "memory": memory, "summary_memory": summary_memory}
+        self.billing = BillingAgent(llm, **agent_kwargs)
+        self.product = ProductAgent(llm, **agent_kwargs)
+        self.orders = OrdersAgent(llm, **agent_kwargs)
+        self.support = SupportAgent(llm, **agent_kwargs)
+        self.graph = self._build_graph()
+
+    def _node(self, name, fn):
+        async def _wrapped(state):
+            async with self.langgraph_telemetry.node(name, state):
+                return await fn(state)
+        return _wrapped
+
+    def _build_graph(self):
+        builder = StateGraph(AgentState)
+        builder.add_node("input_guardrails", self._node("input_guardrails", self.input_guardrails))
+        builder.add_node("routing_decision", self._node("routing_decision", self.routing_decision))
+        builder.add_node("billing_agent", self._node("billing_agent", self.billing_agent))
+        builder.add_node("product_agent", self._node("product_agent", self.product_agent))
+        builder.add_node("orders_agent", self._node("orders_agent", self.orders_agent))
+        builder.add_node("support_agent", self._node("support_agent", self.support_agent))
+        builder.add_node("handoff", self._node("handoff", self.handoff))
+        builder.add_node("supervisor_agent", self._node("supervisor_agent", self.supervisor_agent))
+        builder.add_node("output_supervisor", self._node("output_supervisor", self.output_supervisor))
+        builder.add_node("output_guardrails", self._node("output_guardrails", self.output_guardrails))
+        builder.add_node("judge", self._node("judge", self.judge))
+        builder.add_node("supervisor_review", self._node("supervisor_review", self.supervisor_review))
+        builder.add_node("persist", self._node("persist", self.persist))
+
+        builder.add_edge(START, "input_guardrails")
+        builder.add_conditional_edges(
+            "input_guardrails",
+            self._after_input_guardrails,
+            {"blocked": "persist", "continue": "routing_decision"},
+        )
+        builder.add_conditional_edges(
+            "routing_decision",
+            lambda s: s.get("route", "billing_agent"),
+            {
+                "billing_agent": "billing_agent",
+                "product_agent": "product_agent",
+                "orders_agent": "orders_agent",
+                "support_agent": "support_agent",
+                "handoff": "handoff",
+                "supervisor_agent": "supervisor_agent",
+            },
+        )
+        builder.add_edge("billing_agent", "output_supervisor")
+        builder.add_edge("product_agent", "output_supervisor")
+        builder.add_edge("orders_agent", "output_supervisor")
+        builder.add_edge("support_agent", "output_supervisor")
+        builder.add_edge("handoff", "output_supervisor")
+        builder.add_edge("supervisor_agent", "output_supervisor")
+        builder.add_edge("output_supervisor", "output_guardrails")
+        builder.add_edge("output_guardrails", "judge")
+        builder.add_edge("judge", "supervisor_review")
+        builder.add_edge("supervisor_review", "persist")
+        builder.add_edge("persist", END)
+
+        return builder.compile(checkpointer=create_langgraph_checkpointer(self.settings))
+
+    def _after_input_guardrails(self, state):
+        return "blocked" if state.get("blocked") else "continue"
+
+    async def input_guardrails(self, state):
+        async with self.telemetry.span(
+            "workflow.input_guardrails",
+            session_id=state.get("conversation_key") or state.get("session_id"),
+            input=state.get("user_text"),
+        ):
+            history_texts = [m.get("content", "") for m in state.get("history", [])]
+            await self.observer.emit_grl(
+                "001",
+                {
+                    "session_id": state.get("conversation_key") or state.get("session_id"),
+                    "tenant_id": state.get("tenant_id"),
+                    "agent_id": state.get("agent_id"),
+                    "phase": "input",
+                },
+                component="workflow.input_guardrails.start",
+            )
+            sanitized, decisions = await self.guardrails.run_input(
+                state["user_text"],
+                {
+                    **(state.get("context") or {}),
+                    "history_texts": history_texts,
+                    "tenant_id": state.get("tenant_id"),
+                    "agent_id": state.get("agent_id"),
+                    "agent_profile": state.get("agent_profile") or {},
+                },
+            )
+            for _decision in decisions:
+                await self.guardrail_telemetry.evaluated("input", _decision)
+                await self.observer.emit_grl(
+                    "002" if _decision.allowed else "004",
+                    {
+                        "session_id": state.get("conversation_key") or state.get("session_id"),
+                        "tenant_id": state.get("tenant_id"),
+                        "agent_id": state.get("agent_id"),
+                        "phase": "input",
+                        "rail_code": getattr(_decision, "code", None),
+                        "allowed": bool(_decision.allowed),
+                        "reason": getattr(_decision, "reason", None),
+                    },
+                    component="workflow.input_guardrails.decision",
+                )
+                if not _decision.allowed:
+                    await self.guardrail_telemetry.blocked("input", _decision)
+            await self.telemetry.event(
+                "guardrails.input.completed",
+                {
+                    "session_id": state.get("conversation_key") or state.get("session_id"),
+                    "tenant_id": state.get("tenant_id"),
+                    "agent_id": state.get("agent_id"),
+                    "decisions": [d.model_dump() for d in decisions],
+                },
+            )
+            await self.observer.emit_grl(
+                "009",
+                {
+                    "session_id": state.get("conversation_key") or state.get("session_id"),
+                    "tenant_id": state.get("tenant_id"),
+                    "agent_id": state.get("agent_id"),
+                    "phase": "input",
+                    "blocked": any(not d.allowed for d in decisions),
+                    "decision_count": len(decisions),
+                },
+                component="workflow.input_guardrails.final",
+            )
+            if any(not d.allowed for d in decisions):
+                return {
+                    "sanitized_input": sanitized,
+                    "answer": "Não consegui seguir com essa mensagem por regra de segurança.",
+                    "final_answer": "Não consegui seguir com essa mensagem por regra de segurança.",
+                    "guardrail_decisions": [d.model_dump() for d in decisions],
+                    "route": "blocked",
+                    "blocked": True,
+                }
+            return {
+                "sanitized_input": sanitized,
+                "guardrail_decisions": [d.model_dump() for d in decisions],
+                "blocked": False,
+            }
+
+    async def routing_decision(self, state):
+        mode = getattr(self.settings, "ROUTING_MODE", "router")
+        async with self.telemetry.span(
+            "workflow.routing_decision",
+            session_id=state.get("conversation_key") or state.get("session_id"),
+            input={
+                "mode": mode,
+                "text": state.get("sanitized_input") or state.get("user_text"),
+                "previous_state": state.get("next_state"),
+            },
+        ):
+            if mode == "supervisor":
+                plan = await self.supervisor.route_plan(state)
+                await self.langgraph_telemetry.edge("routing_decision", "supervisor_agent", state, {"method": "supervisor", "intent": plan.intent, "confidence": plan.confidence})
+                return {
+                    "route": "supervisor_agent",
+                    "intent": plan.intent,
+                    "supervisor_plan": {
+                        "agents": plan.agents,
+                        "intent": plan.intent,
+                        "confidence": plan.confidence,
+                        "reason": plan.reason,
+                        "metadata": plan.metadata,
+                    },
+                    "route_decision": {
+                        "route": "supervisor_agent",
+                        "agent": "supervisor",
+                        "intent": plan.intent,
+                        "confidence": plan.confidence,
+                        "reason": plan.reason,
+                        "method": "supervisor",
+                        "metadata": plan.metadata,
+                    },
+                }
+
+            decision = await self.router.route(state)
+            await self.langgraph_telemetry.edge("routing_decision", decision.route, state, {"method": getattr(decision, "method", None), "intent": decision.intent, "confidence": decision.confidence})
+            await self.observer.emit_ic(
+                "ROUTE_SELECTED",
+                {
+                    "session_id": state.get("conversation_key") or state.get("session_id"),
+                    "tenant_id": state.get("tenant_id"),
+                    "agent_id": state.get("agent_id"),
+                    "route": decision.route,
+                    "intent": decision.intent,
+                    "confidence": decision.confidence,
+                    "method": getattr(decision, "method", None),
+                },
+                component="workflow.routing_decision",
+            )
+            return {
+                "route": decision.route,
+                "intent": decision.intent,
+                "route_decision": decision.model_dump(mode="json"),
+                "domain": decision.domain,
+                "mcp_tools": decision.mcp_tools,
+                "next_state": decision.next_state,
+            }
+
+    async def billing_agent(self, state):
+        async with self.langgraph_telemetry.node("billing_agent", state):
+            async with self.telemetry.span(
+                "workflow.agent.billing",
+                session_id=state.get("conversation_key") or state.get("session_id"),
+                input={"intent": state.get("intent")},
+            ):
+                return await self.billing.run(state)
+
+    async def product_agent(self, state):
+        async with self.langgraph_telemetry.node("product_agent", state):
+            async with self.telemetry.span(
+                "workflow.agent.product",
+                session_id=state.get("conversation_key") or state.get("session_id"),
+                input={"intent": state.get("intent")},
+            ):
+                return await self.product.run(state)
+
+    async def orders_agent(self, state):
+        async with self.langgraph_telemetry.node("orders_agent", state):
+            async with self.telemetry.span(
+                    "workflow.agent.orders",
+                    session_id=state.get("conversation_key") or state.get("session_id"),
+                    input={"intent": state.get("intent")},
+            ):
+                return await self.orders.run(state)
+
+
+    async def support_agent(self, state):
+        async with self.langgraph_telemetry.node("support_agent", state):
+            async with self.telemetry.span(
+                    "workflow.agent.support",
+                    session_id=state.get("conversation_key") or state.get("session_id"),
+                    input={"intent": state.get("intent")},
+            ):
+                return await self.support.run(state)
+
+    async def supervisor_agent(self, state):
+        """Executa um ou mais agentes no modo supervisor e consolida a resposta.
+
+        Este nó mantém o desenho de supervisor sem obrigar o restante do workflow
+        a conhecer quantos agentes foram acionados. Cada execução especializada
+        recebe o mesmo estado, mas com route/active_agent atualizados.
+        """
+        plan = state.get("supervisor_plan") or {}
+        agents = plan.get("agents") or ["billing_agent"]
+        handlers = {
+            "billing_agent": self.billing.run,
+            "product_agent": self.product.run,
+            "orders_agent": self.orders.run,
+            "support_agent": self.support.run,
+        }
+        partials = []
+        mcp_results = []
+        async with self.telemetry.span(
+            "workflow.supervisor_agent",
+            session_id=state.get("conversation_key") or state.get("session_id"),
+            input={"agents": agents, "intent": state.get("intent")},
+        ):
+            for agent_name in agents:
+                handler = handlers.get(agent_name)
+                if handler is None:
+                    continue
+                child_state = {**state, "route": agent_name, "active_agent": agent_name}
+                result = await handler(child_state)
+                partials.append({"agent": agent_name, "answer": result.get("answer", "")})
+                mcp_results.extend(result.get("mcp_results") or [])
+
+        if len(partials) == 1:
+            answer = partials[0]["answer"]
+        else:
+            joined = "\n\n".join(f"{p['agent']}: {p['answer']}" for p in partials)
+            answer = (
+                "[Supervisor] Consolidação de múltiplos agentes acionados.\n"
+                f"{joined}"
+            )
+        return {
+            "answer": answer,
+            "supervisor_results": partials,
+            "mcp_results": mcp_results,
+            "next_state": "SUPERVISOR_ACTIVE",
+        }
+
+    async def handoff(self, state):
+        async with self.telemetry.span("workflow.handoff", session_id=state.get("session_id")):
+            target = (state.get("route_decision") or {}).get("metadata", {}).get("target_agent")
+            answer = (
+                "Vou redirecionar sua solicitação para o especialista correto. "
+                f"Destino sugerido: {target or 'agente especializado'}."
+            )
+            return {"answer": answer}
+
+    async def output_supervisor(self, state):
+        """Valida a resposta candidata com o OutputSupervisor corporativo.
+
+        Este nó não substitui o roteador/supervisor multiagente. Ele roda após o
+        agente gerar `answer` e antes dos judges/persistência, produzindo campos
+        supervisor_* no state e eventos GRL.001..GRL.009 via AgentObserver.
+        """
+        if not bool(getattr(self.settings, "ENABLE_OUTPUT_SUPERVISOR", True)):
+            return {
+                "output_guardrails_already_applied": False,
+                "supervisor_action": "disabled",
+                "supervisor_attempt": int(state.get("supervisor_attempt", 0)),
+            }
+
+        candidate = state.get("answer") or ""
+        context = {
+            **(state.get("context") or {}),
+            "tenant_id": state.get("tenant_id"),
+            "agent_id": state.get("agent_id"),
+            "session_id": state.get("conversation_key") or state.get("session_id"),
+            "route": state.get("route"),
+            "intent": state.get("intent"),
+            "supervisor_attempt": int(state.get("supervisor_attempt", 0)),
+        }
+        async with self.telemetry.span(
+            "workflow.output_supervisor",
+            session_id=state.get("conversation_key") or state.get("session_id"),
+            input=candidate,
+        ):
+            decision = await self.output_supervisor_engine.evaluate(candidate, context)
+            action = decision.action.value
+            await self.telemetry.event(
+                "output_supervisor.completed",
+                {
+                    "session_id": context["session_id"],
+                    "tenant_id": state.get("tenant_id"),
+                    "agent_id": state.get("agent_id"),
+                    "action": action,
+                    "approved": decision.approved,
+                    "guidance": decision.guidance,
+                },
+            )
+
+            await self.observer.emit_ic(
+                "IC.OUTPUT_SUPERVISOR_COMPLETED",
+                {
+                    "session_id": context["session_id"],
+                    "tenant_id": state.get("tenant_id"),
+                    "agent_id": state.get("agent_id"),
+                    "route": state.get("route"),
+                    "intent": state.get("intent"),
+                    "action": action,
+                    "approved": decision.approved,
+                    "result_count": len(decision.results),
+                },
+                component="workflow.output_supervisor",
+            )
+
+            if decision.action in {RailAction.ALLOW, RailAction.SANITIZE, RailAction.OBSERVE}:
+                final_answer = decision.candidate
+            elif decision.action == RailAction.HANDOVER:
+                final_answer = "Vou encaminhar seu atendimento para continuidade com um especialista."
+            else:
+                final_answer = decision.fallback_message
+
+            return {
+                "answer": final_answer,
+                "final_answer": final_answer,
+                "supervisor_action": action,
+                "supervisor_guidance": decision.guidance,
+                "supervisor_attempt": int(state.get("supervisor_attempt", 0)) + (1 if decision.action == RailAction.RETRY else 0),
+                "supervisor_handover_reason": decision.handover_reason,
+                "output_supervisor_results": [
+                    {
+                        "code": r.code,
+                        "action": r.action.value,
+                        "reason": r.reason,
+                        "guidance": r.guidance,
+                        "metadata": r.metadata,
+                    }
+                    for r in decision.results
+                ],
+                "output_guardrails_already_applied": True,
+                "guardrail_decisions": state.get("guardrail_decisions", [])
+                + [item for r in decision.results for item in (r.metadata or {}).get("legacy_decisions", [])],
+            }
+
+    async def output_guardrails(self, state):
+        if state.get("output_guardrails_already_applied"):
+            return {"final_answer": state.get("final_answer") or state.get("answer") or ""}
+
+        async with self.telemetry.span(
+            "workflow.output_guardrails",
+            session_id=state.get("conversation_key") or state.get("session_id"),
+            input=state.get("answer"),
+        ):
+            await self.observer.emit_grl(
+                "001",
+                {
+                    "session_id": state.get("conversation_key") or state.get("session_id"),
+                    "tenant_id": state.get("tenant_id"),
+                    "agent_id": state.get("agent_id"),
+                    "phase": "output",
+                    "route": state.get("route"),
+                    "intent": state.get("intent"),
+                },
+                component="workflow.output_guardrails.start",
+            )
+            final, decisions = await self.guardrails.run_output(
+                state["answer"], state.get("context", {})
+            )
+            for _decision in decisions:
+                await self.guardrail_telemetry.evaluated("output", _decision)
+                await self.observer.emit_grl(
+                    "002" if _decision.allowed else "004",
+                    {
+                        "session_id": state.get("conversation_key") or state.get("session_id"),
+                        "tenant_id": state.get("tenant_id"),
+                        "agent_id": state.get("agent_id"),
+                        "phase": "output",
+                        "rail_code": getattr(_decision, "code", None),
+                        "allowed": bool(_decision.allowed),
+                        "reason": getattr(_decision, "reason", None),
+                    },
+                    component="workflow.output_guardrails.decision",
+                )
+                if not _decision.allowed:
+                    await self.guardrail_telemetry.blocked("output", _decision)
+            await self.telemetry.event(
+                "guardrails.output.completed",
+                {
+                    "session_id": state.get("conversation_key") or state.get("session_id"),
+                    "tenant_id": state.get("tenant_id"),
+                    "agent_id": state.get("agent_id"),
+                    "decisions": [d.model_dump() for d in decisions],
+                },
+            )
+            await self.observer.emit_grl(
+                "009",
+                {
+                    "session_id": state.get("conversation_key") or state.get("session_id"),
+                    "tenant_id": state.get("tenant_id"),
+                    "agent_id": state.get("agent_id"),
+                    "phase": "output",
+                    "blocked": any(not d.allowed for d in decisions),
+                    "decision_count": len(decisions),
+                },
+                component="workflow.output_guardrails.final",
+            )
+            return {
+                "final_answer": final,
+                "guardrail_decisions": state.get("guardrail_decisions", [])
+                + [d.model_dump() for d in decisions],
+            }
+
+    async def judge(self, state):
+        async with self.telemetry.span(
+            "workflow.judge",
+            session_id=state.get("conversation_key") or state.get("session_id"),
+            input={"question": state.get("user_text"), "answer": state.get("final_answer")},
+        ):
+            results = await self.judges.evaluate_all(
+                state["user_text"], state["final_answer"], state.get("context", {})
+            )
+            for _result in results:
+                await self.judge_telemetry.evaluated(_result)
+            await self.telemetry.event(
+                "judges.completed",
+                {
+                    "session_id": state.get("conversation_key") or state.get("session_id"),
+                    "tenant_id": state.get("tenant_id"),
+                    "agent_id": state.get("agent_id"),
+                    "results": [r.model_dump() for r in results],
+                },
+            )
+            return {"judge_results": [r.model_dump() for r in results]}
+
+    async def supervisor_review(self, state):
+        async with self.telemetry.span(
+            "workflow.supervisor_review",
+            session_id=state.get("conversation_key") or state.get("session_id"),
+            input=state.get("final_answer"),
+        ):
+            ok, answer = await self.supervisor.review(
+                state["final_answer"], state.get("context", {})
+            )
+            await self.telemetry.event(
+                "supervisor.review.completed",
+                {"session_id": state.get("session_id"), "approved": ok},
+            )
+            return {"final_answer": answer if ok else answer}
+
+    async def persist(self, state):
+        async with self.telemetry.span(
+            "workflow.persist",
+            session_id=state.get("conversation_key") or state.get("session_id"),
+            input={"route": state.get("route"), "intent": state.get("intent")},
+        ):
+            await self.observer.emit_ic(
+                "AGENT_COMPLETED",
+                {
+                    "session_id": state.get("conversation_key") or state["session_id"],
+                    "tenant_id": state.get("tenant_id"),
+                    "agent_id": state.get("agent_id"),
+                    "route": state.get("route"),
+                    "intent": state.get("intent"),
+                    "route_decision": state.get("route_decision"),
+                    "judges": state.get("judge_results", []),
+                    "mcp_tools": state.get("mcp_tools", []),
+                    "mcp_results": state.get("mcp_results", []),
+                },
+            )
+
+            await self.observer.emit_noc(
+                "006",
+                {
+                    "session_id": state.get("conversation_key") or state["session_id"],
+                    "tenant_id": state.get("tenant_id"),
+                    "agent_id": state.get("agent_id"),
+                    "route": state.get("route"),
+                    "intent": state.get("intent"),
+                    "answer_chars": len(state.get("final_answer") or ""),
+                },
+                component="workflow.persist",
+            )
+
+            await self.telemetry.event(
+                "agent.completed",
+                {
+                    "session_id": state.get("conversation_key") or state["session_id"],
+                    "tenant_id": state.get("tenant_id"),
+                    "agent_id": state.get("agent_id"),
+                    "route": state.get("route"),
+                    "intent": state.get("intent"),
+                    "answer_chars": len(state.get("final_answer") or ""),
+                },
+            )
+            return state
+
+    async def ainvoke(self, state):
+        thread_id = state.get("conversation_key") or state["session_id"]
+        config = {"configurable": {"thread_id": thread_id}}
+        async with self.telemetry.span(
+            "workflow.langgraph.ainvoke",
+            session_id=state.get("conversation_key") or state.get("session_id"),
+            user_id=state.get("context", {}).get("user_id"),
+            input={"user_text": state.get("user_text")},
+            tags=["langgraph", "agent-workflow", f"routing-mode:{getattr(self.settings, 'ROUTING_MODE', 'router')}",],
+        ):
+            await self.workflow_telemetry.started("agent_workflow", state)
+            await self.observer.emit_noc(
+                "001",
+                {
+                    "session_id": state.get("conversation_key") or state.get("session_id"),
+                    "tenant_id": state.get("tenant_id"),
+                    "agent_id": state.get("agent_id"),
+                    "channel_id": (state.get("context") or {}).get("channel"),
+                    "message_id": (state.get("context") or {}).get("message_id"),
+                    "ura_call_id": (state.get("context") or {}).get("ura_call_id"),
+                },
+                component="workflow.ainvoke",
+            )
+            await self.observer.emit_ic(
+                "AGENT_STARTED",
+                {
+                    "session_id": state.get("conversation_key") or state.get("session_id"),
+                    "tenant_id": state.get("tenant_id"),
+                    "agent_id": state.get("agent_id"),
+                    "channel_id": (state.get("context") or {}).get("channel"),
+                    "message_id": (state.get("context") or {}).get("message_id"),
+                    "user_text_chars": len(state.get("user_text") or ""),
+                },
+                component="workflow.ainvoke",
+            )
+            try:
+                result = await self.graph.ainvoke(state, config=config)
+                await self.workflow_telemetry.completed("agent_workflow", result)
+                return result
+            except Exception as exc:
+                await self.workflow_telemetry.failed("agent_workflow", exc)
+                await self.observer.emit_noc(
+                    "005",
+                    {
+                        "session_id": state.get("conversation_key") or state.get("session_id"),
+                        "tenant_id": state.get("tenant_id"),
+                        "agent_id": state.get("agent_id"),
+                        "error": str(exc),
+                        "exception_type": exc.__class__.__name__,
+                    },
+                    component="workflow.ainvoke",
+                )
+                raise