Semantic Kernel Middleware (Python)
Guardrails, redaction, approval and telemetry in Semantic Kernel Python using kernel filters.
Verified against
semantic-kernel1.45.0 (checked 2026-11-19).
Semantic Kernel’s middleware mechanism is filters: async functions that wrap a step and call await next(context) to continue. There are three kinds:
| Filter type | Wraps | Typical uses |
|---|---|---|
FilterTypes.PROMPT_RENDERING | Rendering a prompt template, before it is sent | Redaction, prompt-injection checks, adding policy text (variables are already HTML-encoded by the template; see input encoding) |
FilterTypes.FUNCTION_INVOCATION | Every kernel function call (prompt or native) | Logging, timing, caching, input validation, output redaction |
FilterTypes.AUTO_FUNCTION_INVOCATION | Each function the model asks to call during function calling | Approval gates, blocking tools, stopping the tool loop |
Filters run for agents too, because agents invoke functions through their kernel.
Input guardrail on rendered prompts
Section titled “Input guardrail on rendered prompts”import refrom semantic_kernel import Kernelfrom semantic_kernel.filters import FilterTypes, PromptRenderContext
kernel = Kernel()SSN = re.compile(r"\b\d{3}-\d{2}-\d{4}\b")
@kernel.filter(FilterTypes.PROMPT_RENDERING)async def redact_prompt(context: PromptRenderContext, next): await next(context) # render first context.rendered_prompt = SSN.sub("***-**-****", context.rendered_prompt or "")Output redaction and timing on function calls
Section titled “Output redaction and timing on function calls”import time, loggingfrom semantic_kernel.filters import FunctionInvocationContextfrom semantic_kernel.functions import FunctionResult
log = logging.getLogger("sk")
@kernel.filter(FilterTypes.FUNCTION_INVOCATION)async def time_and_redact(context: FunctionInvocationContext, next): start = time.perf_counter() try: await next(context) finally: log.info("%s.%s took %.0f ms", context.function.plugin_name, context.function.name, (time.perf_counter() - start) * 1000) if context.result is not None: # Native functions return their own value; prompt functions return chat message # content objects — str() gives the text in both cases. context.result = FunctionResult( function=context.function.metadata, value=SSN.sub("***-**-****", str(context.result)), )To short-circuit — for example a cache hit — set context.result and return without calling next.
Approval gate for tool calls
Section titled “Approval gate for tool calls”from semantic_kernel.filters import AutoFunctionInvocationContext
SENSITIVE = {"delete_account", "send_payment"}
@kernel.filter(FilterTypes.AUTO_FUNCTION_INVOCATION)async def require_approval(context: AutoFunctionInvocationContext, next): if context.function.name in SENSITIVE and not await approved_by_human(context): context.function_result = FunctionResult( function=context.function.metadata, value="The user declined this action. Do not retry it.", ) return # skip the call; the model sees the message await next(context)
async def approved_by_human(context: AutoFunctionInvocationContext) -> bool: print(f"Approve {context.function.name}({dict(context.arguments or {})})? [y/N]") return input().strip().lower() == "y"Set context.terminate = True to stop the whole function-calling loop instead of just skipping one call.
Ordering and registration
Section titled “Ordering and registration”- Filters of the same type run in registration order, each wrapping the next (onion model).
kernel.add_filter(FilterTypes.FUNCTION_INVOCATION, fn)is the non-decorator form;kernel.remove_filter(...)removes one.- Build a fresh kernel per request (or per tenant) if filters carry request-specific state.
Telemetry
Section titled “Telemetry”Semantic Kernel emits OpenTelemetry spans for function invocations and model calls, and a duration histogram per function (Python has no token-usage metric; the production guide records usage from a filter). Configure a tracer provider and exporter as usual, then add attributes from a filter:
from opentelemetry import trace
@kernel.filter(FilterTypes.FUNCTION_INVOCATION)async def tag_span(context: FunctionInvocationContext, next): span = trace.get_current_span() span.set_attribute("app.tenant", (context.arguments or {}).get("tenant", "unknown")) await next(context)Set SEMANTICKERNEL_EXPERIMENTAL_GENAI_ENABLE_OTEL_DIAGNOSTICS=true to emit GenAI semantic-convention spans for model calls (..._SENSITIVE=true also records prompts and completions — development only).
Testing
Section titled “Testing”- Filters are plain async functions: call them directly with a hand-built context and a fake
next. - For integration tests, register the filters on a kernel whose chat service is a stub and assert on what reaches the service.
Revision history
Section titled “Revision history”| Date | Version | Changes |
|---|---|---|
| 2026-10-21 | 1.45.0 | Rewritten on the current filter API; redaction, timing and the approval gate run against a stub chat service. |