litellm/tests/integration/cost_calculation
devin-ai-integration[bot] ad263b01f4
test(integration): chain a proxy-issued previous_response_id in the cost suite (#42396)
The gpt-5.6-responses_previous_response_id case sent a literal id the proxy never issued, which the Responses id security hook refuses with a 403 at production defaults. The case now primes a response through the proxy and chains the id it hands back, so the harness drops allow_unmanaged_response_ids and the security hook stays exercised

Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
2026-09-21 20:36:53 -07:00
..
assertions.py test(integration): tighten batch and realtime cost assertions 2026-09-20 01:29:46 +00:00
conftest.py test(integration): wait for the batch retrieval row and drop the failed-only output file 2026-09-20 01:46:23 +00:00
cost_tracking_case.py test(integration): chain a proxy-issued previous_response_id in the cost suite (#42396) 2026-09-21 20:36:53 -07:00
cost_tracking_cases.json test(integration): chain a proxy-issued previous_response_id in the cost suite (#42396) 2026-09-21 20:36:53 -07:00
test_batch_realtime_cost.py test(integration): wait for the batch retrieval row and drop the failed-only output file 2026-09-20 01:46:23 +00:00
test_cost_tracking.py test(integration): chain a proxy-issued previous_response_id in the cost suite (#42396) 2026-09-21 20:36:53 -07:00