New Feature: IGuardrailProvider interface for policy-based function invocation control
维护者通常 3 天内回复
还没有人认领这个 Issue。
评估
- 难度
- 5/5
- 预计耗时
- 一周以上
- 新手友好度
- 35/100
- Issue 类型
- 功能
- 描述清晰度
- 基本清楚
- 活跃度
- 冷清
- 领域
- ai, authorization, security
调研方向
从现有的 IAutoFunctionInvocationFilter 管道及其 .NET 和 Python 入口点开始,然后比较过滤器的注册方式,以及调用上下文和结果的表示方式。完成的标准是:为两种语言一致地定义 provider contract 和过滤器集成,包括允许、拒绝、取消和注册行为。
由索引模型根据 Issue 内容生成。
描述
Feature Request
Title: New Feature: IGuardrailProvider interface for policy-based function invocation control
Is your feature request related to a problem?
Enterprise deployments of Semantic Kernel agents need a standardized way to enforce authorization policies on function invocations -- deciding whether a tool call should proceed based on caller identity, resource scope, risk level, or organizational policy. Today this is achievable through IAutoFunctionInvocationFilter, but each team builds ad-hoc policy logic inside their filter implementations with no shared contract for pluggable policy providers.
This gap has been raised repeatedly:
- #1409 -- "Guardrails for C#" (2023, closed with TypeChat redirect, no guardrail interface shipped)
- #5436 -- "Filters use cases to be supported before making feature non-experimental" (explicitly lists "Function Call Approval" as a core requirement)
- #10951 -- "Agent Invocation Filter" (2025, requesting filters that wrap agent invocations "allowing for scenarios like guardrails etc." for both .NET and Python)
- #13556 -- "Governance Policy Filter for Semantic Kernel" (2026, proposed a governance layer, closed and redirected to microsoft/agent-governance-toolkit)
- #12294 -- Handoff orchestration triggering OpenAI jailbreak guardrails (demonstrates the practical need for pre-invocation policy checks)
Describe the solution you'd like
A thin IGuardrailProvider interface that plugs into the existing filter pipeline. It separates the policy decision (should this call proceed?) from the filter mechanics (intercepting the pipeline).
C# (.NET)
namespace Microsoft.SemanticKernel;
/// <summary>
/// Provides policy-based authorization decisions for function invocations.
/// Implementations are registered with the Kernel and consulted by a
/// built-in AutoFunctionInvocationFilter before each tool call.
/// </summary>
public interface IGuardrailProvider
{
/// <summary>
/// Evaluates whether a function invocation should proceed.
/// </summary>
Task<GuardrailDecision> EvaluateAsync(
GuardrailContext context,
CancellationToken cancellationToken = default);
}
public sealed class GuardrailContext
{
public KernelFunction Function { get; init; }
public KernelArguments Arguments { get; init; }
public AutoFunctionInvocationContext InvocationContext { get; init; }
/// <summary>Optional caller identity for multi-tenant scenarios.</summary>
public ClaimsPrincipal? Principal { get; init; }
}
public sealed class GuardrailDecision
{
public bool IsAllowed { get; init; }
public string? Reason { get; init; }
public static GuardrailDecision Allow() => new() { IsAllowed = true };
public static GuardrailDecision Deny(string reason) =>
new() { IsAllowed = false, Reason = reason };
}
Python
from abc import ABC, abstractmethod
from dataclasses import dataclass
from semantic_kernel.filters.auto_function_invocation.auto_function_invocation_context import (
AutoFunctionInvocationContext,
)
@dataclass
class GuardrailContext:
function_name: str
plugin_name: str
arguments: dict
invocation_context: AutoFunctionInvocationContext
principal: dict | None = None # Caller identity claims
@dataclass
class GuardrailDecision:
is_allowed: bool
reason: str | None = None
@staticmethod
def allow() -> "GuardrailDecision":
return GuardrailDecision(is_allowed=True)
@staticmethod
def deny(reason: str) -> "GuardrailDecision":
return GuardrailDecision(is_allowed=False, reason=reason)
class GuardrailProvider(ABC):
@abstractmethod
async def evaluate(self, context: GuardrailContext) -> GuardrailDecision:
"""Return whether this function invocation should proceed."""
...
Integration with existing filters
The provider does not replace filters -- it plugs into them. A built-in GuardrailAutoFunctionInvocationFilter consults registered providers:
public class GuardrailAutoFunctionInvocationFilter : IAutoFunctionInvocationFilter
{
private readonly IEnumerable<IGuardrailProvider> _providers;
public async Task OnAutoFunctionInvocationAsync(
AutoFunctionInvocationContext context,
Func<AutoFunctionInvocationContext, Task> next)
{
var guardrailContext = new GuardrailContext
{
Function = context.Function,
Arguments = context.Arguments,
InvocationContext = context
};
foreach (var provider in _providers)
{
var decision = await provider.EvaluateAsync(guardrailContext);
if (!decision.IsAllowed)
{
context.Result = new FunctionResult(context.Function,
$"Blocked by guardrail: {decision.Reason}");
return; // skip next -- do not invoke function
}
}
await next(context);
}
}
Registration
var kernel = Kernel.CreateBuilder()
.AddAzureOpenAIChatCompletion(...)
.Build();
kernel.AutoFunctionInvocationFilters.Add(
new GuardrailAutoFunctionInvocationFilter(
new MyOrgPolicyProvider(),
new AzureContentSafetyProvider()
));
Describe alternatives you've considered
- Raw
IAutoFunctionInvocationFilteronly -- Works today, but every team re-invents the allow/deny pattern. No shared contract means no ecosystem of pluggable providers. - External governance toolkit -- #13556 was redirected to microsoft/agent-governance-toolkit, but a lightweight in-kernel interface would enable third-party providers without requiring a separate toolkit dependency.
Why this fits Semantic Kernel's architecture
- Follows the existing filter pipeline pattern (
IAutoFunctionInvocationFilter,IFunctionInvocationFilter,IPromptRenderFilter) - Does not modify the filter contract -- composes on top of it
- Supports the "Function Call Approval" scenario explicitly called out in #5436
- Works for both .NET and Python with identical semantics
- Enables the agent-level guardrails requested in #10951
Additional context
A reference implementation of this provider pattern exists in APort Agent Guardrails, which enforces passport-based tool authorization policies for AI agents. The interface proposed here is deliberately provider-agnostic so that any policy backend (Azure Content Safety, OPA, custom rules, etc.) can plug in.
- 主要语言
- C#
- 星标
- 28.8k
- 派生
- 4.9k
- 平均合并
- 2 天 17 小时
- 30 天内合并 PR
- 48
环境准备
在浏览器里用你自己的 GitHub 账号启动这个项目的开发容器。
- 没有 Dockerfile 或 Docker Compose 文件
- 有 Pull Request 模板
- 阅读贡献指南
从这里开始
- 先读完整个 Issue,再读项目的贡献指南。
- 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
- Fork 仓库,在一个分支上完成修改。
- 提交 Pull Request,并在描述里引用这个 Issue 编号。
microsoft/semantic-kernel 的其他 Issue
-
Python: Bug: ChatMessageContent.from_element drops AudioContent and BinaryContent into raw TextContent可能已有人在做 @halcyon-past 今天认领。 未关闭
难度 2/5 1-3 小时 新手友好度 75/100
microsoft/semantic-kernel#14824 · 1 条评论 ·
维护者通常 3 天内回复
-
Python: Bug: Redis search returns None for every field that declares a storage_name, because RETURN lists the declared name可能已有人在做 @wasim-builds 于 9 天前认领。 未关闭python triage
难度 2/5 1-3 小时 新手友好度 78/100
microsoft/semantic-kernel#14753 · 1 条评论 ·
维护者通常 3 天内回复
-
.Net: gpt-image-1 is the default image model in the .NET OpenAI connector, and OpenAI shuts it down on October 23可能已有人在做 @nightcityblade 于 46 天前认领。 未关闭.NET triage
难度 2/5 1-3 小时 新手友好度 73/100
microsoft/semantic-kernel#14526 · 1 条评论 ·
维护者通常 3 天内回复
-
Python: VolatileMemoryStore.get_batch and get_nearest_matches ignore with_embeddings=False (deepcopy result is discarded)可能已有人在做 @VANDRANKI 于 48 天前认领。 未关闭python triage
难度 2/5 1-3 小时 新手友好度 84/100
microsoft/semantic-kernel#14522 ·
维护者通常 3 天内回复
-
.Net: Bug: BinaryContent does not decode the %xx escapes of a non-base64 data URI可能已有人在做 @Laurianti 于 48 天前认领。 未关闭.NET triage
难度 2/5 1-3 小时 新手友好度 76/100
microsoft/semantic-kernel#14518 ·
维护者通常 3 天内回复
查看 microsoft/semantic-kernel 的全部 Issue
相似的 Issue
-
难度 2/5 1-3 小时 新手友好度 75/100
维护者通常 1 天内回复
-
Support Flux ignore rules (drift detection ignore paths) in Microsoft.KubernetesConfiguration schema未关闭
难度 2/5 1-3 小时 新手友好度 65/100
Azure/azure-resource-manager-schemas#3921 ·
维护者通常 1 天内回复
-
text-align: justify is ignored in HTML to PDF conversion可能已有人在做 @PrzemyslawKlys 今天认领。 未关闭
难度 2/5 1-3 小时 新手友好度 82/100
维护者通常 1 天内回复
-
难度 1/5 1 小时以内 新手友好度 78/100
维护者通常 4 天内回复
-
难度 2/5 1-3 小时 新手友好度 75/100
asyncapi/modelina#2709 · 1 条评论 ·
维护者通常 1 天内回复