From d7b337d3060623f902c0553cd0358c57c50a2548 Mon Sep 17 00:00:00 2001 From: Test Date: Fri, 17 Jul 2026 12:48:46 +0200 Subject: [PATCH] Clarify validation before tool approval --- agent-framework/workflows/human-in-the-loop.md | 3 +++ 1 file changed, 3 insertions(+) diff --git a/agent-framework/workflows/human-in-the-loop.md b/agent-framework/workflows/human-in-the-loop.md index a2ba8fce..e2e0f935 100644 --- a/agent-framework/workflows/human-in-the-loop.md +++ b/agent-framework/workflows/human-in-the-loop.md @@ -304,6 +304,9 @@ The `RequestPort` pattern described above works with custom executors and `Workf Agents can use tools that require human approval before execution. When the agent attempts to call an approval-required tool, the workflow pauses and emits a `RequestInfoEvent` just like the `RequestPort` pattern, but the event payload contains a `ToolApprovalRequestContent` (C# and Go) or a `Content` with `type == "function_approval_request"` (Python) instead of a custom request type. +> [!IMPORTANT] +> Treat approval as scoped to the exact tool call in the request. Before sending an approval response, validate the requested function name and arguments against the application's allowlist and current authorization policy. If the call changes, require a new approval. + > [!TIP] > For complete examples with code, see: > - [Sequential orchestration with HITL](./orchestrations/sequential.md#sequential-orchestration-with-human-in-the-loop)