From 92d3a1d87de637efd57acfd31dd8068f5ee0848c Mon Sep 17 00:00:00 2001 From: yassin Date: Sun, 20 Sep 2026 06:10:16 +0000 Subject: [PATCH] test(proxy): expect 422 for per-model budget rejections on cursor route Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- .../proxy/response_api_endpoints/test_endpoints.py | 6 +++--- tests/test_litellm/proxy/test_proxy_server.py | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/tests/test_litellm/proxy/response_api_endpoints/test_endpoints.py b/tests/test_litellm/proxy/response_api_endpoints/test_endpoints.py index f7abb209015..4153bf7d7ee 100644 --- a/tests/test_litellm/proxy/response_api_endpoints/test_endpoints.py +++ b/tests/test_litellm/proxy/response_api_endpoints/test_endpoints.py @@ -2099,7 +2099,7 @@ class TestCursorVariantPerModelBudgetEnforcement: response = _post_cursor_with_real_auth(valid_token, attrs, request_model="claude-opus-5-thinking-high") - assert response.status_code == 429, response.text + assert response.status_code == 422, response.text error = response.json()["error"] assert error["type"] == "budget_exceeded" assert "exceeded budget for model=claude-opus-5" in error["message"] @@ -2110,8 +2110,8 @@ class TestCursorVariantPerModelBudgetEnforcement: base_response = _post_cursor_with_real_auth(valid_token, attrs, request_model="claude-opus-5") alias_response = _post_cursor_with_real_auth(valid_token, attrs, request_model="claude-opus-5-fast") - assert base_response.status_code == 429, base_response.text - assert alias_response.status_code == 429, alias_response.text + assert base_response.status_code == 422, base_response.text + assert alias_response.status_code == 422, alias_response.text assert alias_response.json() == base_response.json() diff --git a/tests/test_litellm/proxy/test_proxy_server.py b/tests/test_litellm/proxy/test_proxy_server.py index f71f9c20f3b..950a6cc3c40 100644 --- a/tests/test_litellm/proxy/test_proxy_server.py +++ b/tests/test_litellm/proxy/test_proxy_server.py @@ -10872,7 +10872,7 @@ async def test_realtime_session_rejected_in_pre_call_releases_the_budget_reserva """A rate-limit or guardrail rejection happens before route_request, so the relay never runs and no success log can own the reservation. The endpoint must release it on that exit too, or the key stays pinned at the reserved - amount and its next requests 429 with budget_exceeded while /key/info shows + amount and its next requests 422 with budget_exceeded while /key/info shows spend 0 (reproduced live with rpm_limit=1). The client still gets the pre-call error event and the 1011 close it got before.""" reservation: Final = {"reserved_cost": 0.55, "input_cost": 0.0, "finalized": False, "entries": []}