diff --git a/docs/edge/ar/guides/agents/secure-agent-design.mdx b/docs/edge/ar/guides/agents/secure-agent-design.mdx index 5b22372ff..80941c2c4 100644 --- a/docs/edge/ar/guides/agents/secure-agent-design.mdx +++ b/docs/edge/ar/guides/agents/secure-agent-design.mdx @@ -21,7 +21,7 @@ Human-in-the-loop (HITL) موافقة، وليس عنصر تحكم. يتوقف | --- | --- | | `HookAborted` في tool hook | يوقف استدعاء تلك الأداة فقط. يستمر الـ Agent. ويتلقى رسالة بأن الأداة حُظرت. | | Task `guardrail` | يرفض أو يعيد محاولة مخرج Task على مسار Task. | -| Task `human_input` | موافقة: يراجع الإجابة النهائية بعد تشغيل الأدوات على مسار Task. ولا يحظر الأدوات. ولا يتحقق ممن وافق. | +| Task `human_input` | يراجع الإجابة النهائية بعد تشغيل الأدوات على مسار Task. ولا يحظر الأدوات. | | `output_pydantic` / `output_json` | يلائم المخرج مع مخطط. ولا يتحقق من قواعد العمل. | | `Agent.guardrail` | يتحقق من المخرج على `agent.kickoff()` فقط. ولا يعمل أثناء تنفيذ Task في Crew. | @@ -104,7 +104,7 @@ researcher = Agent( | أدوات بأقل امتياز | `tools=[...]` على كل Agent | | حظر الاستدعاءات أو تقييدها | [Tool hooks](/ar/learn/tool-hooks) (`PRE_TOOL_CALL` + `HookAborted`) | | فحص استدعاءات النموذج | [LLM hooks](/ar/learn/llm-hooks) | -| موافقة بشرية | [HITL](/ar/learn/human-in-the-loop) / `request_human_input` — موافقة فقط. ليست عنصر تحكم. ولا تتحقق ممن وافق. استخدم tool hooks لحظر الاستدعاء. | +| موافقة بشرية | [HITL](/ar/learn/human-in-the-loop) / `request_human_input`. استخدم tool hooks لحظر الاستدعاء. | | فحوصات المخرج | [Task guardrails](/ar/concepts/tasks#task-guardrails) على مسار Task؛ `Agent.guardrail` على `kickoff()` | | شكل منظم | `output_pydantic` / `output_json` أو `response_format=` (الشكل فقط) | @@ -336,7 +336,7 @@ class SecureOutreachFlow(Flow[PipelineState]): تحقق من مخرجات Task قبل أن تستمر. - موافقة ومراجعة بعد التشغيل. ليست عنصر تحكم. ولا تتحقق ممن وافق. + مراجعة بشرية لمخرج Task واستدعاءات الأدوات. حدود التنفيذ والتفصيل وإعدادات الـ Agent. diff --git a/docs/edge/en/guides/agents/secure-agent-design.mdx b/docs/edge/en/guides/agents/secure-agent-design.mdx index fea72af26..ee910adef 100644 --- a/docs/edge/en/guides/agents/secure-agent-design.mdx +++ b/docs/edge/en/guides/agents/secure-agent-design.mdx @@ -21,7 +21,7 @@ This page covers threat model and execution-path behavior. For execution limits | --- | --- | | `HookAborted` in a tool hook | Stops that one tool call. The agent continues. It receives a message that the tool was blocked. | | Task `guardrail` | Rejects or retries Task output on the Task path. | -| Task `human_input` | Approval: reviews the final answer after tools ran on the Task path. It does not block tools. It does not check who approved. | +| Task `human_input` | Reviews the final answer after tools ran on the Task path. It does not block tools. | | `output_pydantic` / `output_json` | Fits output to a schema. It does not check business rules. | | `Agent.guardrail` | Checks output on `agent.kickoff()` only. It does not run on Crew Task execution. | @@ -104,7 +104,7 @@ Examples: | Least-privilege tools | `tools=[...]` on each agent | | Block or constrain calls | [Tool hooks](/en/learn/tool-hooks) (`PRE_TOOL_CALL` + `HookAborted`) | | Inspect model calls | [LLM hooks](/en/learn/llm-hooks) | -| Human approval | [HITL](/en/learn/human-in-the-loop) / `request_human_input` — approval only. Not a control. Does not check who approved. Use tool hooks to block the call. | +| Human approval | [HITL](/en/learn/human-in-the-loop) / `request_human_input`. Use tool hooks to block the call. | | Output checks | [Task guardrails](/en/concepts/tasks#task-guardrails) on the Task path; `Agent.guardrail` on `kickoff()` | | Structured shape | `output_pydantic` / `output_json` or `response_format=` (shape only) | @@ -336,7 +336,7 @@ See [Production Architecture](/en/concepts/production-architecture). Validate task outputs before they continue. - Approval and post-run review. Not a control. Does not check who approved. + Human review of task output and tool calls. Execution limits, verbosity, and agent settings. diff --git a/docs/edge/ko/guides/agents/secure-agent-design.mdx b/docs/edge/ko/guides/agents/secure-agent-design.mdx index 2dae8eda2..d8e50bda2 100644 --- a/docs/edge/ko/guides/agents/secure-agent-design.mdx +++ b/docs/edge/ko/guides/agents/secure-agent-design.mdx @@ -21,7 +21,7 @@ Human-in-the-loop (HITL)는 승인이지 통제가 아닙니다. 사람이 수 | --- | --- | | tool hook의 `HookAborted` | 해당 도구 호출 하나만 중지합니다. 에이전트는 계속합니다. 도구가 차단되었다는 메시지를 받습니다. | | Task `guardrail` | Task 경로에서 Task 출력을 거부하거나 재시도합니다. | -| Task `human_input` | 승인: Task 경로에서 도구가 실행된 뒤 최종 답변을 검토합니다. 도구를 차단하지 않습니다. 누가 승인했는지는 검사하지 않습니다. | +| Task `human_input` | Task 경로에서 도구가 실행된 뒤 최종 답변을 검토합니다. 도구를 차단하지 않습니다. | | `output_pydantic` / `output_json` | 출력을 스키마에 맞춥니다. 비즈니스 규칙은 검사하지 않습니다. | | `Agent.guardrail` | `agent.kickoff()`에서만 출력을 검사합니다. Crew Task 실행에서는 실행되지 않습니다. | @@ -104,7 +104,7 @@ Crew와 Flow 입력에는 [execution boundary hooks](/ko/learn/execution-boundar | 최소 권한 도구 | 각 에이전트의 `tools=[...]` | | 호출 차단 또는 제한 | [Tool hooks](/ko/learn/tool-hooks) (`PRE_TOOL_CALL` + `HookAborted`) | | 모델 호출 검사 | [LLM hooks](/ko/learn/llm-hooks) | -| 사람 승인 | [HITL](/ko/learn/human-in-the-loop) / `request_human_input` — 승인만. 통제가 아닙니다. 누가 승인했는지는 검사하지 않습니다. 호출을 차단하려면 tool hooks를 사용하세요. | +| 사람 승인 | [HITL](/ko/learn/human-in-the-loop) / `request_human_input`. 호출을 차단하려면 tool hooks를 사용하세요. | | 출력 검사 | Task 경로의 [Task guardrails](/ko/concepts/tasks#task-guardrails); `kickoff()`의 `Agent.guardrail` | | 구조화된 형태 | `output_pydantic` / `output_json` 또는 `response_format=` (형태만) | @@ -336,7 +336,7 @@ class SecureOutreachFlow(Flow[PipelineState]): 계속하기 전에 Task 출력을 검증합니다. - 승인과 실행 후 검토. 통제가 아닙니다. 누가 승인했는지는 검사하지 않습니다. + Task 출력과 도구 호출에 대한 사람 검토. 실행 제한, verbose, 에이전트 설정. diff --git a/docs/edge/pt-BR/guides/agents/secure-agent-design.mdx b/docs/edge/pt-BR/guides/agents/secure-agent-design.mdx index 0c19c2cac..c5017f2e1 100644 --- a/docs/edge/pt-BR/guides/agents/secure-agent-design.mdx +++ b/docs/edge/pt-BR/guides/agents/secure-agent-design.mdx @@ -21,7 +21,7 @@ Esta página cobre o modelo de ameaça e o comportamento por caminho de execuç | --- | --- | | `HookAborted` em um tool hook | Interrompe aquela chamada de ferramenta. O agente continua. Ele recebe uma mensagem de que a ferramenta foi bloqueada. | | Task `guardrail` | Rejeita ou retenta a saída da Task no caminho da Task. | -| Task `human_input` | Aprovação: revisa a resposta final depois que as ferramentas rodaram no caminho da Task. Não bloqueia ferramentas. Não verifica quem aprovou. | +| Task `human_input` | Revisa a resposta final depois que as ferramentas rodaram no caminho da Task. Não bloqueia ferramentas. | | `output_pydantic` / `output_json` | Ajusta a saída a um schema. Não verifica regras de negócio. | | `Agent.guardrail` | Verifica a saída apenas em `agent.kickoff()`. Não roda na execução de Task do Crew. | @@ -104,7 +104,7 @@ Exemplos: | Ferramentas com menor privilégio | `tools=[...]` em cada agente | | Bloquear ou restringir chamadas | [Tool hooks](/pt-BR/learn/tool-hooks) (`PRE_TOOL_CALL` + `HookAborted`) | | Inspecionar chamadas do modelo | [LLM hooks](/pt-BR/learn/llm-hooks) | -| Aprovação humana | [HITL](/pt-BR/learn/human-in-the-loop) / `request_human_input` — só aprovação. Não é um controle. Não verifica quem aprovou. Use tool hooks para bloquear a chamada. | +| Aprovação humana | [HITL](/pt-BR/learn/human-in-the-loop) / `request_human_input`. Use tool hooks para bloquear a chamada. | | Checagens de saída | [Task guardrails](/pt-BR/concepts/tasks#task-guardrails) no caminho da Task; `Agent.guardrail` em `kickoff()` | | Forma estruturada | `output_pydantic` / `output_json` ou `response_format=` (apenas a forma) | @@ -336,7 +336,7 @@ Veja [Arquitetura de Produção](/pt-BR/concepts/production-architecture). Valide saídas de Task antes que elas continuem. - Aprovação e revisão após a execução. Não é um controle. Não verifica quem aprovou. + Revisão humana da saída da Task e das chamadas de ferramentas. Limites de execução, verbosidade e configurações do agente.