Status: REPROVADO | Passou: 10/11 | Gerado em: 2026-05-30T16:45:58.362350
| Teste | Status | ms | Evidências | |
|---|---|---|---|---|
| ✅ | 01_backend_health | HTTP 200 | 31 | evidencias/20260530_164528/logs/01_backend_health_curl.logevidencias/20260530_164528/json/01_backend_health.json |
| ✅ | 02_env_and_repository_config | HTTP 200; missing=[] | 22 | evidencias/20260530_164528/logs/02_debug_env_curl.logevidencias/20260530_164528/json/02_debug_env.jsonevidencias/20260530_164528/json/02_local_env_detected.json |
| ✅ | 03_database_persistence_check | Banco não é SQLite local ou arquivo não encontrado; validação marcada como informativa | 2 | evidencias/20260530_164528/json/03_database_paths.json |
| ✅ | 04_mcp_tools_list | HTTP 200; tools=8 | 21 | evidencias/20260530_164528/logs/04_mcp_tools_curl.logevidencias/20260530_164528/json/04_mcp_tools.json |
| ✅ | 05_mcp_direct_tool_calls | tools_tested=2 | 129 | evidencias/20260530_164528/logs/05_mcp_call_consultar_fatura_curl.logevidencias/20260530_164528/json/05_mcp_call_consultar_fatura.jsonevidencias/20260530_164528/logs/05_mcp_call_consultar_pedido_curl.logevidencias/20260530_164528/json/05_mcp_call_consultar_pedido.json |
| ✅ | 06_router_or_supervisor_decisions | scenarios=3 | 52 | evidencias/20260530_164528/logs/06_debug_route_billing_curl.logevidencias/20260530_164528/json/06_debug_route_billing.jsonevidencias/20260530_164528/logs/06_debug_route_retail_order_curl.logevidencias/20260530_164528/json/06_debug_route_retail_order.jsonevidencias/20260530_164528/logs/06_debug_route_product_curl.logevidencias/20260530_164528/json/06_debug_route_product.json |
| ❌ | 07_gateway_e2e_mcp_memory_checkpoint | gateway=False; memory=True; checkpoint=True | 14890 | evidencias/20260530_164528/logs/07_gateway_message_1_curl.logevidencias/20260530_164528/json/07_gateway_message_1.jsonevidencias/20260530_164528/logs/07_gateway_message_2_curl.logevidencias/20260530_164528/json/07_gateway_message_2.jsonevidencias/20260530_164528/logs/07_gateway_message_3_curl.logevidencias/20260530_164528/json/07_gateway_message_3.jsonevidencias/20260530_164528/logs/07_session_messages_curl.logevidencias/20260530_164528/logs/07_session_checkpoint_curl.log |
| ✅ | 08_guardrails_behavior | Ao menos um cenário indicou comportamento de guardrail; revisar evidência | 14273 | evidencias/20260530_164528/logs/08_guardrails_prompt_injection_curl.logevidencias/20260530_164528/json/08_guardrails_prompt_injection.jsonevidencias/20260530_164528/logs/08_guardrails_pii_mask_curl.logevidencias/20260530_164528/json/08_guardrails_pii_mask.json |
| ✅ | 09_langfuse_trace_check | Langfuse desabilitado no .env; validação informativa | 2 | evidencias/20260530_164528/json/09_langfuse_config.json |
| ✅ | 10_frontend_health | HTTP 200 | 18 | evidencias/20260530_164528/logs/10_frontend_curl.logevidencias/20260530_164528/logs/10_frontend_html.log |
| ✅ | 11_basic_load_test | 10/10 OK; rps=238.96 | 43 | evidencias/20260530_164528/json/11_load_summary.json |