secure endpoint

feat: reactive request-correction retry for recoverable upstream 400s

routstr/payment/models.py

@@ -3,7 +3,7 @@ import json
 import random
 
 import httpx
-from fastapi import APIRouter, Depends
+from fastapi import APIRouter, Depends, HTTPException, Request
 from pydantic import BaseModel as V2BaseModel
 from pydantic.v1 import BaseModel
 from sqlmodel.ext.asyncio.session import AsyncSession
@@ -17,6 +17,24 @@ logger = get_logger(__name__)
 
 models_router = APIRouter()
 
+_MODEL_TEST_ENDPOINT_PATHS = {
+    "chat-completions": "chat/completions",
+    "completions": "completions",
+    "embeddings": "embeddings",
+    "responses": "responses",
+}
+
+# Cap the caller-supplied test payload to avoid forwarding oversized bodies
+# upstream on the operator's credentials.
+_MODEL_TEST_MAX_REQUEST_BYTES = 64 * 1024
+
+
+async def _require_admin_api(request: Request) -> None:
+    """Require admin auth without creating an import-time cycle with core.admin."""
+    from ..core.admin import require_admin_api
+
+    await require_admin_api(request)
+
 
 class Architecture(BaseModel):
     modality: str
@@ -418,7 +436,9 @@ class ModelTestRequest(V2BaseModel):
     request_data: dict
 
 
-@models_router.post("/api/models/test")
+@models_router.post(
+    "/api/models/test", dependencies=[Depends(_require_admin_api)]
+)
 async def test_model(
     payload: ModelTestRequest,
     session: AsyncSession = Depends(get_session),
@@ -446,16 +466,35 @@ async def test_model(
             "status_code": 404,
         }
 
-    base_url = provider.base_url.rstrip("/")
-    if payload.endpoint_type == "chat-completions":
-        url = f"{base_url}/chat/completions"
-    else:
-        url = f"{base_url}/{payload.endpoint_type}"
+    endpoint_path = _MODEL_TEST_ENDPOINT_PATHS.get(payload.endpoint_type)
+    if endpoint_path is None:
+        raise HTTPException(status_code=400, detail="Unsupported endpoint_type")
 
     actual_model_id = model_row.forwarded_model_id or model_row.id
     request_data = dict(payload.request_data)
     request_data["model"] = actual_model_id
 
+    try:
+        request_size = len(json.dumps(request_data).encode("utf-8"))
+    except (TypeError, ValueError):
+        raise HTTPException(status_code=400, detail="Invalid request_data")
+    if request_size > _MODEL_TEST_MAX_REQUEST_BYTES:
+        raise HTTPException(status_code=413, detail="request_data too large")
+
+    base_url = provider.base_url.rstrip("/")
+    url = f"{base_url}/{endpoint_path}"
+
+    logger.info(
+        "admin model test",
+        extra={
+            "model_id": payload.model_id,
+            "forwarded_model_id": actual_model_id,
+            "endpoint_type": payload.endpoint_type,
+            "upstream_provider_id": model_row.upstream_provider_id,
+            "request_bytes": request_size,
+        },
+    )
+
     headers = {
         "Content-Type": "application/json",
         "Authorization": f"Bearer {provider.api_key}",

routstr/proxy.py

@@ -28,6 +28,7 @@ from .payment.helpers import (
 from .payment.models import Model
 from .upstream import BaseUpstreamProvider
 from .upstream.helpers import init_upstreams
+from .upstream.request_correction import correct_request, extract_error_message
 
 logger = get_logger(__name__)
 proxy_router = APIRouter()
@@ -352,50 +353,86 @@ async def proxy(
     if request_body_dict:
         await pay_for_request(key, max_cost_for_model, session)
 
+    # Tracks request params already removed in response to upstream rejections,
+    # shared across providers so a stripped param stays stripped on failover and
+    # the reactive retry can never loop unboundedly.
+    already_stripped: set[str] = set()
+
     for i, upstream in enumerate(upstreams):
         headers = upstream.prepare_headers(dict(request.headers))
 
         try:
-            try:
-                if is_responses_api:
-                    response = await upstream.forward_responses_request(
-                        request,
-                        path,
-                        headers,
-                        request_body,
-                        key,
-                        max_cost_for_model,
-                        session,
-                        model_obj,
+            while True:
+                try:
+                    if is_responses_api:
+                        response = await upstream.forward_responses_request(
+                            request,
+                            path,
+                            headers,
+                            request_body,
+                            key,
+                            max_cost_for_model,
+                            session,
+                            model_obj,
+                        )
+                    else:
+                        response = await upstream.forward_request(
+                            request,
+                            path,
+                            headers,
+                            request_body,
+                            key,
+                            max_cost_for_model,
+                            session,
+                            model_obj,
+                        )
+                except UpstreamError:
+                    # Let the outer UpstreamError handler manage retry/revert
+                    raise
+                except Exception as e:
+                    # Unexpected error (not an upstream failure) — revert and propagate
+                    logger.error(
+                        "Unexpected error in upstream request, reverting payment",
+                        extra={
+                            "error": str(e),
+                            "error_type": type(e).__name__,
+                            "path": path,
+                            "key_hash": key.hashed_key[:8] + "...",
+                            "max_cost_for_model": max_cost_for_model,
+                        },
                     )
-                else:
-                    response = await upstream.forward_request(
-                        request,
-                        path,
-                        headers,
+                    await revert_pay_for_request(key, session, max_cost_for_model)
+                    raise
+
+                # Reactive recovery: some models reject one specific request
+                # param (e.g. newer Anthropic models deprecating `temperature`).
+                # When the upstream 400s naming such a param, strip it from the
+                # body and retry the SAME upstream. ``already_stripped`` bounds
+                # this to one retry per distinct param so it always terminates.
+                if response.status_code == 400:
+                    correction = correct_request(
                         request_body,
-                        key,
-                        max_cost_for_model,
-                        session,
-                        model_obj,
+                        extract_error_message(response),
+                        already_stripped,
                     )
-            except UpstreamError:
-                # Let the outer UpstreamError handler manage retry/revert
-                raise
-            except Exception as e:
-                # Unexpected error (not an upstream failure) — revert and propagate
-                logger.error(
-                    "Unexpected error in upstream request, reverting payment",
-                    extra={
-                        "error": str(e),
-                        "error_type": type(e).__name__,
-                        "path": path,
-                        "key_hash": key.hashed_key[:8] + "...",
-                        "max_cost_for_model": max_cost_for_model,
-                    },
-                )
-                await revert_pay_for_request(key, session, max_cost_for_model)
-                raise
+                    if correction is not None:
+                        request_body, bad_param = correction.body, correction.label
+                        already_stripped.add(bad_param)
+                        logger.warning(
+                            "Upstream %s rejected param '%s' for model=%s; "
+                            "stripping and retrying same upstream",
+                            upstream.provider_type,
+                            bad_param,
+                            model_id,
+                            extra={
+                                "provider": upstream.provider_type,
+                                "model": model_id,
+                                "stripped_param": bad_param,
+                                "path": path,
+                            },
+                        )
+                        continue
+                break
 
             if response.status_code != 200:
                 # Check if we should retry (502 Upstream Error or 429 Rate Limit)

routstr/upstream/request_correction.py

@@ -0,0 +1,142 @@
+"""Reactive request-correction layer.
+
+When an upstream rejects a request with a recoverable 4xx error, this layer
+tries to *fix* the request body and let the caller retry the same upstream
+instead of failing outright. It is provider-agnostic: correctors key off the
+upstream's own error wording, so the same recovery works across every provider.
+
+The layer is a small pipeline of :data:`Corrector` callables. Each corrector
+inspects the parsed request body and the upstream error message and either
+returns a corrected body (plus a short label identifying the fix) or declines
+by returning ``None``. Adding a new reactive fix means writing one corrector
+and adding it to :data:`DEFAULT_CORRECTORS` — no changes to the proxy loop.
+
+All corrections are immutable: a corrector never mutates the body it is given,
+it returns a new ``dict``. The proxy threads an ``applied`` set of fix labels
+through retries so each distinct fix is applied at most once, guaranteeing the
+retry loop always terminates.
+"""
+
+from __future__ import annotations
+
+import json
+import re
+from collections.abc import Callable, Sequence
+from dataclasses import dataclass
+
+from fastapi.responses import Response
+
+from ..core import get_logger
+
+logger = get_logger(__name__)
+
+
+# Matches upstream error text that names a single rejected request parameter,
+# e.g. "`temperature` is deprecated for this model." or
+# "parameter 'top_p' is not supported". Keys off the upstream's own wording so
+# a 400 about an unsupported sampling/option field can be recovered by stripping
+# that field and retrying the same upstream.
+_UNSUPPORTED_PARAM_RE = re.compile(
+    r"[`'\"]?(?P<param>[a-zA-Z_][a-zA-Z0-9_]*)[`'\"]?\s+is\s+"
+    r"(?:deprecated|not\s+supported|unsupported|no\s+longer\s+supported)",
+    re.IGNORECASE,
+)
+
+
+# A corrector inspects the parsed request body and the upstream error message
+# and returns ``(new_body_dict, label)`` for a fix it can apply, or ``None`` to
+# decline. ``label`` identifies the fix so it is applied at most once per request.
+Corrector = Callable[[dict, str], "tuple[dict, str] | None"]
+
+
+@dataclass(frozen=True)
+class Correction:
+    """A successful request correction ready to retry.
+
+    ``body`` is the corrected JSON body (encoded), ``label`` identifies the fix
+    that was applied (e.g. the stripped param name) so the caller can guard
+    against applying the same fix twice.
+    """
+
+    body: bytes
+    label: str
+
+
+def extract_error_message(response: Response) -> str:
+    """Best-effort extraction of an error message string from a proxy Response."""
+    body_bytes = getattr(response, "body", None)
+    if not body_bytes:
+        return ""
+    try:
+        data = json.loads(body_bytes)
+    except Exception:
+        return body_bytes.decode("utf-8", errors="ignore")[:500]
+    if isinstance(data, dict):
+        err = data.get("error")
+        if isinstance(err, dict):
+            msg = err.get("message") or err.get("detail")
+            if isinstance(msg, str):
+                return msg
+        elif isinstance(err, str):
+            return err
+        if isinstance(data.get("message"), str):
+            return data["message"]
+    return ""
+
+
+def strip_unsupported_param(
+    body: dict, error_message: str
+) -> tuple[dict, str] | None:
+    """Drop a top-level param the upstream named as unsupported/deprecated.
+
+    Returns ``(new_body, param)`` (a new dict, original untouched) when the
+    error names a top-level param present in the body, otherwise ``None``.
+    """
+    match = _UNSUPPORTED_PARAM_RE.search(error_message)
+    if not match:
+        return None
+    param = match.group("param")
+    if param not in body:
+        return None
+    new_body = {k: v for k, v in body.items() if k != param}
+    return new_body, param
+
+
+# Ordered pipeline of correctors tried on each recoverable rejection.
+DEFAULT_CORRECTORS: tuple[Corrector, ...] = (strip_unsupported_param,)
+
+
+def correct_request(
+    request_body: bytes,
+    error_message: str,
+    applied: set[str],
+    correctors: Sequence[Corrector] = DEFAULT_CORRECTORS,
+) -> Correction | None:
+    """Try to correct a rejected request body so it can be retried.
+
+    Runs each corrector in order against the parsed body and ``error_message``.
+    The first corrector that proposes a fix whose ``label`` is not already in
+    ``applied`` wins; its result is returned as a :class:`Correction`. Returns
+    ``None`` when nothing parses, nothing matches, or every proposed fix was
+    already applied — the caller then treats the response as a normal failure.
+
+    ``applied`` is read-only here; the caller records the returned ``label`` to
+    bound retries and guarantee forward progress.
+    """
+    if not request_body or not error_message:
+        return None
+    try:
+        data = json.loads(request_body)
+    except Exception:
+        return None
+    if not isinstance(data, dict):
+        return None
+    for corrector in correctors:
+        result = corrector(data, error_message)
+        if result is None:
+            continue
+        new_body, label = result
+        if label in applied:
+            continue
+        return Correction(body=json.dumps(new_body).encode(), label=label)
+    return None

tests/integration/test_model_test_endpoint_security.py

@@ -0,0 +1,224 @@
+import time
+from types import TracebackType
+from typing import Any
+from unittest.mock import patch
+
+import pytest
+from httpx import AsyncClient
+
+from routstr.core.admin import admin_sessions
+from routstr.core.db import ModelRow, UpstreamProviderRow
+
+
+@pytest.mark.integration
+@pytest.mark.asyncio
+async def test_model_test_endpoint_requires_admin_auth(
+    integration_client: AsyncClient,
+) -> None:
+    with patch("httpx.AsyncClient") as mock_async_client:
+        response = await integration_client.post(
+            "/api/models/test",
+            json={
+                "model_id": "model-a",
+                "endpoint_type": "chat-completions",
+                "request_data": {"messages": []},
+            },
+        )
+
+    assert response.status_code == 403
+    mock_async_client.assert_not_called()
+
+
+@pytest.mark.integration
+@pytest.mark.asyncio
+async def test_model_test_endpoint_rejects_unsupported_endpoint_type(
+    integration_client: AsyncClient,
+    integration_session: Any,
+) -> None:
+    admin_token = "test-admin-token-model-test"
+    admin_sessions[admin_token] = int(time.time()) + 3600
+    integration_client.headers["Authorization"] = f"Bearer {admin_token}"
+
+    provider = UpstreamProviderRow(
+        provider_type="custom",
+        base_url="https://api.example.com/v1",
+        api_key="sk-upstream-test",
+        enabled=True,
+        provider_fee=1.01,
+    )
+    integration_session.add(provider)
+    await integration_session.commit()
+    await integration_session.refresh(provider)
+    assert provider.id is not None
+
+    model = ModelRow(
+        id="model-a",
+        name="Model A",
+        created=1,
+        description="desc",
+        context_length=100,
+        architecture='{"modality": "text", "input_modalities": ["text"], "output_modalities": ["text"], "tokenizer": "tiktoken", "instruct_type": "chat"}',
+        pricing='{"prompt": 1.0, "completion": 1.0}',
+        upstream_provider_id=provider.id,
+        enabled=True,
+    )
+    integration_session.add(model)
+    await integration_session.commit()
+
+    try:
+        with patch("httpx.AsyncClient") as mock_async_client:
+            response = await integration_client.post(
+                "/api/models/test",
+                json={
+                    "model_id": "model-a",
+                    "endpoint_type": "../../abuse",
+                    "request_data": {"messages": []},
+                },
+            )
+
+        assert response.status_code == 400
+        assert response.json()["detail"] == "Unsupported endpoint_type"
+        mock_async_client.assert_not_called()
+    finally:
+        admin_sessions.pop(admin_token, None)
+
+
+@pytest.mark.integration
+@pytest.mark.asyncio
+async def test_model_test_endpoint_rejects_oversized_request_data(
+    integration_client: AsyncClient,
+    integration_session: Any,
+) -> None:
+    admin_token = "test-admin-token-model-test-oversized"
+    admin_sessions[admin_token] = int(time.time()) + 3600
+    integration_client.headers["Authorization"] = f"Bearer {admin_token}"
+
+    provider = UpstreamProviderRow(
+        provider_type="custom",
+        base_url="https://api.example.com/v1",
+        api_key="sk-upstream-test",
+        enabled=True,
+        provider_fee=1.01,
+    )
+    integration_session.add(provider)
+    await integration_session.commit()
+    await integration_session.refresh(provider)
+    assert provider.id is not None
+
+    model = ModelRow(
+        id="model-a",
+        name="Model A",
+        created=1,
+        description="desc",
+        context_length=100,
+        architecture='{"modality": "text", "input_modalities": ["text"], "output_modalities": ["text"], "tokenizer": "tiktoken", "instruct_type": "chat"}',
+        pricing='{"prompt": 1.0, "completion": 1.0}',
+        upstream_provider_id=provider.id,
+        enabled=True,
+    )
+    integration_session.add(model)
+    await integration_session.commit()
+
+    oversized = "x" * (64 * 1024 + 1)
+
+    try:
+        with patch("httpx.AsyncClient") as mock_async_client:
+            response = await integration_client.post(
+                "/api/models/test",
+                json={
+                    "model_id": "model-a",
+                    "endpoint_type": "chat-completions",
+                    "request_data": {"blob": oversized},
+                },
+            )
+
+        assert response.status_code == 413
+        assert response.json()["detail"] == "request_data too large"
+        mock_async_client.assert_not_called()
+    finally:
+        admin_sessions.pop(admin_token, None)
+
+
+@pytest.mark.integration
+@pytest.mark.asyncio
+async def test_model_test_endpoint_admin_uses_allowed_upstream_path(
+    integration_client: AsyncClient,
+    integration_session: Any,
+) -> None:
+    admin_token = "test-admin-token-model-test-success"
+    admin_sessions[admin_token] = int(time.time()) + 3600
+    integration_client.headers["Authorization"] = f"Bearer {admin_token}"
+
+    provider = UpstreamProviderRow(
+        provider_type="custom",
+        base_url="https://api.example.com/v1",
+        api_key="sk-upstream-test",
+        enabled=True,
+        provider_fee=1.01,
+    )
+    integration_session.add(provider)
+    await integration_session.commit()
+    await integration_session.refresh(provider)
+    assert provider.id is not None
+
+    model = ModelRow(
+        id="model-a",
+        name="Model A",
+        created=1,
+        description="desc",
+        context_length=100,
+        architecture='{"modality": "text", "input_modalities": ["text"], "output_modalities": ["text"], "tokenizer": "tiktoken", "instruct_type": "chat"}',
+        pricing='{"prompt": 1.0, "completion": 1.0}',
+        upstream_provider_id=provider.id,
+        enabled=True,
+        forwarded_model_id="upstream-model-a",
+    )
+    integration_session.add(model)
+    await integration_session.commit()
+
+    class MockResponse:
+        status_code = 200
+        text = '{"ok": true}'
+
+        def json(self) -> dict[str, bool]:
+            return {"ok": True}
+
+    class MockAsyncClient:
+        async def __aenter__(self) -> "MockAsyncClient":
+            return self
+
+        async def __aexit__(
+            self,
+            exc_type: type[BaseException] | None,
+            exc: BaseException | None,
+            tb: TracebackType | None,
+        ) -> None:
+            return None
+
+        async def post(
+            self, url: str, json: dict[str, Any], headers: dict[str, str]
+        ) -> MockResponse:
+            assert url == "https://api.example.com/v1/chat/completions"
+            assert json["model"] == "upstream-model-a"
+            assert headers["Authorization"] == "Bearer sk-upstream-test"
+            return MockResponse()
+
+    try:
+        with patch("httpx.AsyncClient", return_value=MockAsyncClient()):
+            response = await integration_client.post(
+                "/api/models/test",
+                json={
+                    "model_id": "model-a",
+                    "endpoint_type": "chat-completions",
+                    "request_data": {"messages": []},
+                },
+            )
+
+        assert response.status_code == 200
+        assert response.json() == {
+            "success": True,
+            "data": {"ok": True},
+            "status_code": 200,
+        }
+    finally:
+        admin_sessions.pop(admin_token, None)

tests/unit/test_request_correction.py

@@ -0,0 +1,156 @@
+"""Unit tests for the reactive request-correction layer.
+
+Covers the recovery path that lets a request survive a 400 where the upstream
+names a single unsupported request param (e.g. newer Anthropic models
+deprecating ``temperature``): the param is stripped from the JSON body and the
+same upstream is retried, provider-agnostically, keyed off the error text.
+"""
+
+from __future__ import annotations
+
+import json
+
+from fastapi.responses import Response
+
+from routstr.upstream.request_correction import (
+    Correction,
+    correct_request,
+    extract_error_message,
+    strip_unsupported_param,
+)
+
+
+def _body(**kwargs: object) -> bytes:
+    return json.dumps(kwargs).encode()
+
+
+class TestCorrectRequest:
+    def test_strips_deprecated_temperature(self) -> None:
+        body = _body(model="claude-opus-4-8", temperature=1, messages=[])
+        result = correct_request(
+            body, "`temperature` is deprecated for this model.", set()
+        )
+        assert isinstance(result, Correction)
+        assert result.label == "temperature"
+        decoded = json.loads(result.body)
+        assert "temperature" not in decoded
+        assert decoded["model"] == "claude-opus-4-8"
+
+    def test_strips_not_supported_param(self) -> None:
+        body = _body(model="m", top_p=0.9, messages=[])
+        result = correct_request(body, "Parameter 'top_p' is not supported", set())
+        assert result is not None
+        assert result.label == "top_p"
+        assert "top_p" not in json.loads(result.body)
+
+    def test_returns_none_when_label_already_applied(self) -> None:
+        body = _body(model="m", temperature=1)
+        assert (
+            correct_request(body, "`temperature` is deprecated", {"temperature"})
+            is None
+        )
+
+    def test_returns_none_when_param_absent_from_body(self) -> None:
+        body = _body(model="m", messages=[])
+        assert correct_request(body, "`temperature` is deprecated", set()) is None
+
+    def test_returns_none_when_message_does_not_match(self) -> None:
+        body = _body(model="m", temperature=1)
+        assert correct_request(body, "Insufficient balance", set()) is None
+
+    def test_returns_none_on_empty_inputs(self) -> None:
+        assert correct_request(b"", "`temperature` is deprecated", set()) is None
+        assert correct_request(_body(temperature=1), "", set()) is None
+
+    def test_returns_none_on_non_object_body(self) -> None:
+        assert correct_request(b"[1, 2, 3]", "`temperature` is deprecated", set()) is None
+
+    def test_deprecated_model_name_is_not_stripped_as_param(self) -> None:
+        """A 'model is deprecated' error must not strip an unrelated body field.
+
+        The regex matches the ``<token> is deprecated`` wording, but the
+        ``param not in body`` guard means a deprecated *model* name (not a
+        request param) yields no correction rather than a false strip.
+        """
+        body = _body(model="gpt-3", temperature=1, messages=[])
+        assert correct_request(body, "`gpt-3` is deprecated, use gpt-4", set()) is None
+
+    def test_streaming_400_buffered_error_is_correctable(self) -> None:
+        """Streaming 400s funnel through a buffered JSON Response, so the same
+        correction path applies as for non-streaming requests."""
+        # Mirrors forward_upstream_error_response's buffered JSON envelope.
+        resp = Response(
+            content=json.dumps(
+                {"error": {"message": "`temperature` is deprecated for this model"}}
+            ).encode(),
+            status_code=400,
+        )
+        body = _body(model="claude-opus-4-8", temperature=1, messages=[])
+        result = correct_request(body, extract_error_message(resp), set())
+        assert isinstance(result, Correction)
+        assert result.label == "temperature"
+        assert "temperature" not in json.loads(result.body)
+
+
+class TestStripUnsupportedParam:
+    def test_does_not_mutate_input(self) -> None:
+        body = {"model": "m", "temperature": 1}
+        result = strip_unsupported_param(body, "`temperature` is deprecated")
+        assert result is not None
+        new_body, param = result
+        assert param == "temperature"
+        assert "temperature" not in new_body
+        # original untouched (immutability)
+        assert body == {"model": "m", "temperature": 1}
+
+    def test_declines_when_no_match(self) -> None:
+        assert strip_unsupported_param({"temperature": 1}, "nope") is None
+
+
+class TestExtractErrorMessage:
+    def test_extracts_nested_error_message(self) -> None:
+        resp = Response(
+            content=json.dumps(
+                {"error": {"message": "`temperature` is deprecated", "type": "x"}}
+            ).encode(),
+            status_code=400,
+        )
+        assert extract_error_message(resp) == "`temperature` is deprecated"
+
+    def test_extracts_string_error(self) -> None:
+        resp = Response(
+            content=json.dumps({"error": "bad request"}).encode(), status_code=400
+        )
+        assert extract_error_message(resp) == "bad request"
+
+    def test_extracts_top_level_message(self) -> None:
+        resp = Response(
+            content=json.dumps({"message": "nope"}).encode(), status_code=400
+        )
+        assert extract_error_message(resp) == "nope"
+
+    def test_empty_body_returns_empty_string(self) -> None:
+        assert extract_error_message(Response(status_code=400)) == ""
+
+    def test_non_json_body_returns_preview(self) -> None:
+        resp = Response(content=b"plain text error", status_code=400)
+        assert extract_error_message(resp) == "plain text error"
+
+
+class TestEndToEndChaining:
+    def test_two_distinct_params_corrected_sequentially(self) -> None:
+        """Simulates the proxy loop: each 400 fixes one param, set guards reuse."""
+        body = _body(model="m", temperature=1, top_p=0.5, messages=[])
+        applied: set[str] = set()
+
+        first = correct_request(body, "`temperature` is deprecated", applied)
+        assert first is not None
+        body, applied = first.body, applied | {first.label}
+
+        second = correct_request(body, "`top_p` is not supported", applied)
+        assert second is not None
+        body, applied = second.body, applied | {second.label}
+
+        decoded = json.loads(body)
+        assert "temperature" not in decoded and "top_p" not in decoded
+        assert applied == {"temperature", "top_p"}