New features: Route Stickness, Handoff, Clarification, Read-Only/Transactional, Long Term Memory

templates/agent_template_backend/app/agents/billing_agent.py

@@ -44,6 +44,36 @@ class BillingAgent(AgentRuntimeMixin):
                 component="agent.billing.mcp",
             )
 
+        state["mcp_results"] = tool_context
+        clarification_message = self.transaction_clarification_message(state)
+        if clarification_message:
+            return {
+                "answer": f"[{self.__class__.__name__}] {clarification_message}",
+                "next_state": state.get("next_state") or "COLLECTING_PARAMETERS",
+                "mcp_results": tool_context,
+                **self.transaction_state_patch(state),
+            }
+
+        confirmation_message = self.transaction_confirmation_message(state)
+        if confirmation_message:
+            result = {
+                "answer": f"[{self.__class__.__name__}] {confirmation_message}",
+                "next_state": state.get("next_state"),
+                "mcp_results": tool_context,
+                **self.transaction_state_patch(state),
+            }
+            return result
+
+        direct_answer = self.build_direct_mcp_answer(state, tool_context, agent_label="BillingAgent")
+        if direct_answer:
+            return {
+                "answer": direct_answer,
+                "next_state": state.get("next_state") or "ACTIVE",
+                "mcp_results": tool_context,
+                "rag": {"enabled": False, "skipped": True, "reason": "direct_mcp_answer"},
+                **self.transaction_state_patch(state),
+            }
+
         rag_context, rag_metadata = await self._retrieve_rag_context(state)
         if rag_metadata.get("enabled"):
             await self._emit_ic(
@@ -79,6 +109,7 @@ class BillingAgent(AgentRuntimeMixin):
             "mcp_results": tool_context,
             "rag": rag_metadata,
             "memory_context_metadata": state.get("memory_context_metadata"),
+            **self.transaction_state_patch(state),
         }
 
         await self._emit_ic(

templates/agent_template_backend/app/agents/orders_agent.py

@@ -44,6 +44,36 @@ class OrdersAgent(AgentRuntimeMixin):
                 component="agent.orders.mcp",
             )
 
+        state["mcp_results"] = tool_context
+        clarification_message = self.transaction_clarification_message(state)
+        if clarification_message:
+            return {
+                "answer": f"[{self.__class__.__name__}] {clarification_message}",
+                "next_state": state.get("next_state") or "COLLECTING_PARAMETERS",
+                "mcp_results": tool_context,
+                **self.transaction_state_patch(state),
+            }
+
+        confirmation_message = self.transaction_confirmation_message(state)
+        if confirmation_message:
+            result = {
+                "answer": f"[{self.__class__.__name__}] {confirmation_message}",
+                "next_state": state.get("next_state"),
+                "mcp_results": tool_context,
+                **self.transaction_state_patch(state),
+            }
+            return result
+
+        direct_answer = self.build_direct_mcp_answer(state, tool_context, agent_label="OrdersAgent")
+        if direct_answer:
+            return {
+                "answer": direct_answer,
+                "next_state": state.get("next_state") or "ACTIVE",
+                "mcp_results": tool_context,
+                "rag": {"enabled": False, "skipped": True, "reason": "direct_mcp_answer"},
+                **self.transaction_state_patch(state),
+            }
+
         rag_context, rag_metadata = await self._retrieve_rag_context(state)
         if rag_metadata.get("enabled"):
             await self._emit_ic(
@@ -79,6 +109,7 @@ class OrdersAgent(AgentRuntimeMixin):
             "mcp_results": tool_context,
             "rag": rag_metadata,
             "memory_context_metadata": state.get("memory_context_metadata"),
+            **self.transaction_state_patch(state),
         }
 
         await self._emit_ic(

templates/agent_template_backend/app/agents/product_agent.py

@@ -44,6 +44,36 @@ class ProductAgent(AgentRuntimeMixin):
                 component="agent.product.mcp",
             )
 
+        state["mcp_results"] = tool_context
+        clarification_message = self.transaction_clarification_message(state)
+        if clarification_message:
+            return {
+                "answer": f"[{self.__class__.__name__}] {clarification_message}",
+                "next_state": state.get("next_state") or "COLLECTING_PARAMETERS",
+                "mcp_results": tool_context,
+                **self.transaction_state_patch(state),
+            }
+
+        confirmation_message = self.transaction_confirmation_message(state)
+        if confirmation_message:
+            result = {
+                "answer": f"[{self.__class__.__name__}] {confirmation_message}",
+                "next_state": state.get("next_state"),
+                "mcp_results": tool_context,
+                **self.transaction_state_patch(state),
+            }
+            return result
+
+        direct_answer = self.build_direct_mcp_answer(state, tool_context, agent_label="ProductAgent")
+        if direct_answer:
+            return {
+                "answer": direct_answer,
+                "next_state": state.get("next_state") or "ACTIVE",
+                "mcp_results": tool_context,
+                "rag": {"enabled": False, "skipped": True, "reason": "direct_mcp_answer"},
+                **self.transaction_state_patch(state),
+            }
+
         rag_context, rag_metadata = await self._retrieve_rag_context(state)
         if rag_metadata.get("enabled"):
             await self._emit_ic(
@@ -79,6 +109,7 @@ class ProductAgent(AgentRuntimeMixin):
             "mcp_results": tool_context,
             "rag": rag_metadata,
             "memory_context_metadata": state.get("memory_context_metadata"),
+            **self.transaction_state_patch(state),
         }
 
         await self._emit_ic(

templates/agent_template_backend/app/agents/support_agent.py

@@ -44,6 +44,36 @@ class SupportAgent(AgentRuntimeMixin):
                 component="agent.support.mcp",
             )
 
+        state["mcp_results"] = tool_context
+        clarification_message = self.transaction_clarification_message(state)
+        if clarification_message:
+            return {
+                "answer": f"[{self.__class__.__name__}] {clarification_message}",
+                "next_state": state.get("next_state") or "COLLECTING_PARAMETERS",
+                "mcp_results": tool_context,
+                **self.transaction_state_patch(state),
+            }
+
+        confirmation_message = self.transaction_confirmation_message(state)
+        if confirmation_message:
+            result = {
+                "answer": f"[{self.__class__.__name__}] {confirmation_message}",
+                "next_state": state.get("next_state"),
+                "mcp_results": tool_context,
+                **self.transaction_state_patch(state),
+            }
+            return result
+
+        direct_answer = self.build_direct_mcp_answer(state, tool_context, agent_label="SupportAgent")
+        if direct_answer:
+            return {
+                "answer": direct_answer,
+                "next_state": state.get("next_state") or "ACTIVE",
+                "mcp_results": tool_context,
+                "rag": {"enabled": False, "skipped": True, "reason": "direct_mcp_answer"},
+                **self.transaction_state_patch(state),
+            }
+
         rag_context, rag_metadata = await self._retrieve_rag_context(state)
         if rag_metadata.get("enabled"):
             await self._emit_ic(
@@ -79,6 +109,7 @@ class SupportAgent(AgentRuntimeMixin):
             "mcp_results": tool_context,
             "rag": rag_metadata,
             "memory_context_metadata": state.get("memory_context_metadata"),
+            **self.transaction_state_patch(state),
         }
 
         await self._emit_ic(

templates/agent_template_backend/app/main.py

@@ -291,6 +291,11 @@ async def _process_gateway_message(req: GatewayRequest, emit_sse: bool = False)
                     "conversation_key": agent_session_id,
                     "workflow_id": workflow_id,
                     "agent_profile": normalized_context["agent_profile"],
+                    # Chave estável de LTM. Nunca use session_id como identidade de longo prazo.
+                    "long_term_memory_subject_key": business_context.customer_key or session.user_id,
+                    "customer_key": business_context.customer_key,
+                    "user_id": session.user_id,
+                    "business_context": business_context.model_dump(),
                     "user_text": msg.text,
                     "history": history,
                     "context": {
@@ -365,6 +370,13 @@ async def _process_gateway_message(req: GatewayRequest, emit_sse: bool = False)
                     "identity_missing": missing_identity_keys,
                     "judges": result.get("judge_results"),
                     "guardrails": result.get("guardrail_decisions"),
+                    "long_term_memory": {
+                        "subject_key": business_context.customer_key or session.user_id,
+                        "loaded": result.get("long_term_memories", []),
+                        "context": result.get("long_term_memory_context", ""),
+                        "load_error": result.get("long_term_memory_load_error"),
+                        "write_result": result.get("long_term_memory_write_result", {}),
+                    },
                 },
             )
             rendered = await gateway.render(response)
@@ -387,6 +399,14 @@ async def health():
         "sse_enabled": settings.ENABLE_SSE,
         "session_repository": settings.SESSION_REPOSITORY_PROVIDER,
         "memory_repository": settings.MEMORY_REPOSITORY_PROVIDER,
+        "long_term_memory": {
+            "enabled": getattr(settings, "ENABLE_LONG_TERM_MEMORY", False),
+            "provider": getattr(settings, "LONG_TERM_MEMORY_PROVIDER", None),
+            "sqlite_path": getattr(settings, "LONG_TERM_MEMORY_SQLITE_PATH", None),
+            "table": getattr(settings, "LONG_TERM_MEMORY_TABLE", None),
+            "auto_extract": getattr(settings, "LONG_TERM_MEMORY_AUTO_EXTRACT", None),
+            "inject_context": getattr(settings, "LONG_TERM_MEMORY_INJECT_CONTEXT", None),
+        },
         "checkpoint_repository": settings.CHECKPOINT_REPOSITORY_PROVIDER,
         "usage_repository": settings.USAGE_REPOSITORY_PROVIDER,
         "identity_config_path": settings.IDENTITY_CONFIG_PATH,

templates/agent_template_backend/app/state.py

@@ -23,9 +23,22 @@ class AgentState(TypedDict, total=False):
     domain: str
     mcp_tools: list[str]
     mcp_results: list[dict[str, Any]]
+    available_mcp_tools: list[str]
+    selected_tool_call: dict[str, Any]
+    pending_tool_call: dict[str, Any]
+    transaction_status: str
+    confirmation_required: bool
+    confirmation_received: bool
+    tool_policy_result: dict[str, Any]
+    missing_parameters: list[str]
     supervisor_plan: dict[str, Any]
     supervisor_results: list[dict[str, Any]]
     active_agent: str
+    route_bypassed: bool
+    continuity_signal: dict[str, Any]
+    session_control: str
+    session_ended: bool
+    human_handoff_requested: bool
     blocked: bool
     supervisor_action: str
     supervisor_guidance: str
@@ -36,3 +49,5 @@ class AgentState(TypedDict, total=False):
     long_term_memories: list[dict[str, Any]]
     long_term_memory_context: str
     long_term_memory_write_result: dict[str, Any]
+    long_term_memory_subject_key: str
+    long_term_memory_load_error: str

templates/agent_template_backend/app/workflows/agent_graph.py

@@ -139,12 +139,15 @@ class AgentWorkflow:
     def _build_graph(self):
         builder = StateGraph(AgentState)
         builder.add_node("input_guardrails", self._node("input_guardrails", self.input_guardrails))
+        builder.add_node("load_long_term_memory", self._node("load_long_term_memory", self.load_long_term_memory))
         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("human_handoff", self._node("human_handoff", self.human_handoff))
+        builder.add_node("end_session", self._node("end_session", self.end_session))
         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))
@@ -157,8 +160,9 @@ class AgentWorkflow:
         builder.add_conditional_edges(
             "input_guardrails",
             self._after_input_guardrails,
-            {"blocked": "persist", "continue": "routing_decision"},
+            {"blocked": "persist", "continue": "load_long_term_memory"},
         )
+        builder.add_edge("load_long_term_memory", "routing_decision")
         builder.add_conditional_edges(
             "routing_decision",
             lambda s: s.get("route", "billing_agent"),
@@ -168,6 +172,8 @@ class AgentWorkflow:
                 "orders_agent": "orders_agent",
                 "support_agent": "support_agent",
                 "handoff": "handoff",
+                "human_handoff": "human_handoff",
+                "end_session": "end_session",
                 "supervisor_agent": "supervisor_agent",
             },
         )
@@ -176,6 +182,8 @@ class AgentWorkflow:
         builder.add_edge("orders_agent", "output_supervisor")
         builder.add_edge("support_agent", "output_supervisor")
         builder.add_edge("handoff", "output_supervisor")
+        builder.add_edge("human_handoff", "output_supervisor")
+        builder.add_edge("end_session", "output_supervisor")
         builder.add_edge("supervisor_agent", "output_supervisor")
         builder.add_edge("output_supervisor", "output_guardrails")
         builder.add_edge("output_guardrails", "judge")
@@ -190,6 +198,24 @@ class AgentWorkflow:
         return "blocked" if state.get("blocked") else "continue"
 
     async def input_guardrails(self, state):
+        if state.get("session_ended") is True:
+            answer = str(getattr(
+                self.settings,
+                "SESSION_ALREADY_ENDED_MESSAGE",
+                "Este atendimento já foi encerrado. Inicie uma nova sessão para continuar.",
+            ))
+            await self.telemetry.event(
+                "session.message.rejected_after_end",
+                {"session_id": state.get("conversation_key") or state.get("session_id")},
+            )
+            return {
+                "answer": answer,
+                "final_answer": answer,
+                "blocked": True,
+                "session_control": "END_SESSION",
+                "session_ended": True,
+                "next_state": "SESSION_ENDED",
+            }
         async with self.telemetry.span(
             "workflow.input_guardrails",
             session_id=state.get("conversation_key") or state.get("session_id"),
@@ -326,6 +352,17 @@ class AgentWorkflow:
                 "domain": decision.domain,
                 "mcp_tools": decision.mcp_tools,
                 "next_state": decision.next_state,
+                "active_agent": decision.agent,
+                "route_bypassed": decision.method == "continuity",
+                "session_control": (decision.metadata or {}).get("session_control", ""),
+                "human_handoff_requested": (decision.metadata or {}).get("session_control") == "HUMAN_HANDOFF",
+                "session_ended": (decision.metadata or {}).get("session_control") == "END_SESSION",
+                "continuity_signal": {
+                    "decision": (decision.metadata or {}).get("continuity_decision"),
+                    "confidence": decision.confidence if decision.method == "continuity" else None,
+                    "reason": decision.reason if decision.method == "continuity" else None,
+                    "profile": (decision.metadata or {}).get("continuity_profile"),
+                } if decision.method == "continuity" else {},
             }
 
     async def billing_agent(self, state):
@@ -415,6 +452,48 @@ class AgentWorkflow:
             )
             return {"answer": answer}
 
+    async def human_handoff(self, state):
+        session_id = state.get("conversation_key") or state.get("session_id")
+        async with self.telemetry.span("workflow.human_handoff", session_id=session_id):
+            answer = str(getattr(self.settings, "HUMAN_HANDOFF_MESSAGE", "Vou encaminhar seu atendimento para uma pessoa."))
+            await self.telemetry.event(
+                "session.human_handoff.requested",
+                {
+                    "session_id": session_id,
+                    "tenant_id": state.get("tenant_id"),
+                    "agent_id": state.get("agent_id"),
+                    "reason": (state.get("route_decision") or {}).get("reason"),
+                },
+            )
+            return {
+                "answer": answer,
+                "session_control": "HUMAN_HANDOFF",
+                "human_handoff_requested": True,
+                "session_ended": False,
+                "next_state": "HUMAN_HANDOFF_REQUESTED",
+            }
+
+    async def end_session(self, state):
+        session_id = state.get("conversation_key") or state.get("session_id")
+        async with self.telemetry.span("workflow.end_session", session_id=session_id):
+            answer = str(getattr(self.settings, "END_SESSION_MESSAGE", "Atendimento encerrado. Obrigado pelo contato."))
+            await self.telemetry.event(
+                "session.end.requested",
+                {
+                    "session_id": session_id,
+                    "tenant_id": state.get("tenant_id"),
+                    "agent_id": state.get("agent_id"),
+                    "reason": (state.get("route_decision") or {}).get("reason"),
+                },
+            )
+            return {
+                "answer": answer,
+                "session_control": "END_SESSION",
+                "session_ended": True,
+                "human_handoff_requested": False,
+                "next_state": "SESSION_ENDED",
+            }
+
     async def output_supervisor(self, state):
         """Valida a resposta candidata com o OutputSupervisor corporativo.
 
@@ -576,8 +655,34 @@ class AgentWorkflow:
             session_id=state.get("conversation_key") or state.get("session_id"),
             input={"question": state.get("user_text"), "answer": state.get("final_answer")},
         ):
+            judge_context = dict(state.get("context", {}) or {})
+            judge_context["mcp_results"] = state.get("mcp_results", [])
+            judge_context["evidence"] = state.get("mcp_results", []) or judge_context.get("evidence")
+            judge_context["route"] = state.get("route")
+            judge_context["intent"] = state.get("intent")
+            # Judge sampling must see the finalized transaction state. These
+            # fields are populated by the agent/tool runtime before this node.
+            for key in (
+                "transaction_status",
+                "confirmation_required",
+                "confirmation_received",
+                "tool_policy_result",
+                "selected_tool_call",
+                "pending_tool_call",
+            ):
+                judge_context[key] = state.get(key)
+            judge_context["transactional_tools"] = [
+                result.get("tool_name")
+                for result in state.get("mcp_results", [])
+                if isinstance(result, dict)
+                and (
+                    (result.get("metadata") or {}).get("operation_type") == "transactional"
+                    or result.get("awaiting_confirmation")
+                    or result.get("transaction_status")
+                )
+            ]
             results = await self.judges.evaluate_all(
-                state["user_text"], state["final_answer"], state.get("context", {})
+                state["user_text"], state["final_answer"], judge_context
             )
             for _result in results:
                 await self.judge_telemetry.evaluated(_result)
@@ -607,9 +712,78 @@ class AgentWorkflow:
             )
             return {"final_answer": answer if ok else answer}
 
+    async def load_long_term_memory(self, state):
+        """Carrega LTM antes do roteamento e mantém o resultado no estado.
+
+        A carga explícita evita depender apenas do agente selecionado para realizar
+        a recuperação e facilita o diagnóstico de identidade/namespace.
+        """
+        try:
+            memories = await self.long_term_memory_manager.load(state)
+            serialized = []
+            context_lines = []
+            for item in memories or []:
+                if hasattr(item, "model_dump"):
+                    data = item.model_dump(mode="json")
+                elif hasattr(item, "__dict__"):
+                    data = dict(item.__dict__)
+                elif isinstance(item, dict):
+                    data = dict(item)
+                else:
+                    data = {"value": str(item)}
+                serialized.append(data)
+                key = data.get("key") or data.get("memory_key") or data.get("category") or "memory"
+                value = data.get("value") or data.get("memory_value")
+                if value not in (None, ""):
+                    context_lines.append(f"- {key}: {value}")
+
+            return {
+                "long_term_memories": serialized,
+                "long_term_memory_context": "\n".join(context_lines),
+            }
+        except Exception as exc:
+            await self.telemetry.event(
+                "long_term_memory.load.failed",
+                {
+                    "session_id": state.get("conversation_key") or state.get("session_id"),
+                    "tenant_id": state.get("tenant_id"),
+                    "agent_id": state.get("agent_id"),
+                    "subject_key": state.get("long_term_memory_subject_key"),
+                    "error": str(exc),
+                },
+            )
+            return {
+                "long_term_memories": [],
+                "long_term_memory_context": "",
+                "long_term_memory_load_error": str(exc),
+            }
+
     async def persist_long_term_memory(self, state):
-        result = await self.long_term_memory_manager.persist_turn(state)
-        return {"long_term_memory_write_result": result}
+        try:
+            result = await self.long_term_memory_manager.persist_turn(state)
+            await self.telemetry.event(
+                "long_term_memory.persist.completed",
+                {
+                    "session_id": state.get("conversation_key") or state.get("session_id"),
+                    "tenant_id": state.get("tenant_id"),
+                    "agent_id": state.get("agent_id"),
+                    "subject_key": state.get("long_term_memory_subject_key"),
+                    "result": result,
+                },
+            )
+            return {"long_term_memory_write_result": result}
+        except Exception as exc:
+            await self.telemetry.event(
+                "long_term_memory.persist.failed",
+                {
+                    "session_id": state.get("conversation_key") or state.get("session_id"),
+                    "tenant_id": state.get("tenant_id"),
+                    "agent_id": state.get("agent_id"),
+                    "subject_key": state.get("long_term_memory_subject_key"),
+                    "error": str(exc),
+                },
+            )
+            return {"long_term_memory_write_result": {"saved": 0, "error": str(exc)}}
 
     async def persist(self, state):
         async with self.telemetry.span(