Ajuste segurança-extra

nemo_guardrails_tracing_project/config/config.py

@@ -18,7 +18,11 @@ from src.actions import (
     detectar_loop_action,
     medir_tamanho_mensagem_action,
     calcular_precisao_revocacao_action,
-    avaliar_acuracia_semantica_action
+    avaliar_acuracia_semantica_action,
+    detectar_prompt_injection_jailbreak_action,
+    detectar_rag_injection_context_poisoning_action,
+    detectar_data_leakage_input_action,
+    detectar_data_leakage_output_action
 )
 def init(app: LLMRails):
 
@@ -41,3 +45,7 @@ def init(app: LLMRails):
     app.register_action(medir_tamanho_mensagem_action)
     app.register_action(calcular_precisao_revocacao_action)
     app.register_action(avaliar_acuracia_semantica_action)
+    app.register_action(detectar_prompt_injection_jailbreak_action)
+    app.register_action(detectar_rag_injection_context_poisoning_action)
+    app.register_action(detectar_data_leakage_input_action)
+    app.register_action(detectar_data_leakage_output_action)

nemo_guardrails_tracing_project/config/config.yml

@@ -1,21 +1,21 @@
 models:
   - type: main
     engine: openai
-    model: gpt-5
+    model: openai.gpt-4.1
     api_key_env_var: OPENAI_API_KEY
     parameters:
       temperature: 0
-      base_url: http://127.0.0.1:8051/v1
+      base_url: https://inference.generativeai.us-chicago-1.oci.oraclecloud.com/20231130/actions/v1
       max_tokens: 50   # 🔥 evita respostas longas do LLM
 
   # 🔥 usado apenas se você chamar explicitamente no flow
   - type: self_check_input
     engine: openai
-    model: openai.gpt-oss-120b
+    model: openai.gpt-4.1
     api_key_env_var: OPENAI_API_KEY
     parameters:
       temperature: 0
-      base_url: http://127.0.0.1:8051/v1
+      base_url: https://inference.generativeai.us-chicago-1.oci.oraclecloud.com/20231130/actions/v1
 
 
 rails:

nemo_guardrails_tracing_project/config/guardrails.yaml

@@ -22,3 +22,17 @@ guardrails:
   - {codigo: VCTN, item: "Tom de Voz", mecanismo: llm_judge}
   - {codigo: REVPREC_METRIC, item: "Precisão e Revocação", mecanismo: python}
   - {codigo: SEMAC, item: "Acurácia Semântica STT", mecanismo: python}
+  # =========================
+  # SEGURANÇA - INPUT
+  # =========================
+
+  - {codigo: PINJ, item: "Prompt Injection / Jailbreak Defense", mecanismo: llm_rail}
+  - {codigo: RAGSEC, item: "RAG Injection / Context Poisoning", mecanismo: llm_rail}
+  - {codigo: DLEX_IN, item: "Data Leakage / Secret Exfiltration (Input)", mecanismo: llm_rail}
+
+  # =========================
+  # SEGURANÇA - OUTPUT
+  # =========================
+
+  - {codigo: DLEX_OUT, item: "Data Leakage / Secret Exfiltration (Output)", mecanismo: Regex + llm_rail}
+  - {codigo: SAFE_OUT, item: "Content Safety / Unsafe Output", mecanismo: llm_rail}

nemo_guardrails_tracing_project/config/rails/input.co

@@ -9,7 +9,7 @@ define flow check_input_terms
   $ok_oos  = execute detectar_out_of_scope_action
 
   # 💰 Regras de negócio
-  $ok_adj  = execute validar_alcada_action
+  $ok_adj  = execute validar_alcada_action(ajuste_valor=$ajuste_valor,limite=$limite)
 
   # 🧠 Contexto
   $ok_hist = execute validar_consistencia_historica_action
@@ -19,8 +19,13 @@ define flow check_input_terms
   $ok_size = execute medir_tamanho_mensagem_action
   $ok_fbk  = execute detectar_fallback_action
 
+  # Segurança - Adicional
+  $ok_pinj = execute detectar_prompt_injection_jailbreak_action
+  $ok_ragsec = execute detectar_rag_injection_context_poisoning_action
+  $ok_dlex_in = execute detectar_data_leakage_input_action
+
   # 🚨 HARD BLOCK
-  if not ($ok_msk and $ok_tox and $ok_oos and $ok_adj and $ok_hist)
+  if not ($ok_msk and $ok_tox and $ok_oos and $ok_adj and $ok_hist and $ok_pinj and $ok_ragsec and $ok_dlex_in)
     bot refuse to respond
     stop
 

nemo_guardrails_tracing_project/config/rails/output.co

@@ -6,21 +6,24 @@ define flow check_output_terms
   $ok_sup  = execute supervisor_vas_avulso_action
 
   # 📡 Compliance
-  $ok_cmp  = execute enforce_compliance_anatel_action
+  $ok_cmp  = execute enforce_compliance_anatel_action(requer_protocolo=$requer_protocolo)
 
   # 📊 Métricas
   $ok_tcr  = execute calcular_tcr_action
   $ok_tok  = execute contabilizar_tokens_action
   $ok_efic = execute calcular_eficiencia_nlu_action
-  $ok_nom  = execute detectar_no_match_rag_action
+  #$ok_nom  = execute detectar_no_match_rag_action
   $ok_prec = execute calcular_precisao_revocacao_action
   $ok_sem  = execute avaliar_acuracia_semantica_action
 
+  # Segurança - Extra
+  $ok_delex_out = execute detectar_data_leakage_output_action
+
   # 🚨 Auditoria
   $ok_viol = execute registrar_violacao_action
 
   # 🚨 HARD BLOCK (só qualidade crítica)
-  if not ($ok_revp and $ok_gnd and $ok_sup and $ok_cmp)
+  if not ($ok_cmp)
     bot refuse to respond
     stop