mateo-berri c3071d1663 fix(spend): price non-finite provider costs on every route and drain parked NaN batches ... Perplexity, OpenRouter pass-through, and Responses streaming now treat a NaN or infinite reported cost as unreported, so the token price bills the request. A daily spend batch parked in the Redis buffer by an older version with a NaN spend now drains as 0 instead of failing every flush. The cost header never carries NaN or Infinity, and a set holding a non-finite float no longer breaks spend log JSON		2026-10-28 07:21:30 -07:00
..
chat	fix(openai): send chat completions through client.post so the SDK's per-message param transform stops holding the event loop (#46967)	2026-10-16 18:06:01 -07:00
embedding	fix(llms): sanitize trailing slashes in provider get_complete_url (#42887)	2026-10-15 02:59:46 -07:00
responses	test: add __init__.py to phase 12 unit test directories	2026-09-20 12:36:15 +00:00
search	fix(llms): sanitize trailing slashes in provider get_complete_url (#42887)	2026-10-15 02:59:46 -07:00
__init__.py	test: add __init__.py to intermediate phase 12 unit test directories	2026-09-20 12:37:21 +00:00
test_perplexity.py	test: migrate local_testing SDK and provider tests out of build_and_test (#45760)	2026-10-10 23:14:25 +00:00
test_perplexity_cost_calculator.py	fix(spend): price non-finite provider costs on every route and drain parked NaN batches	2026-10-28 07:21:30 -07:00
test_perplexity_integration.py	test: move tests/test_litellm/llms into tests/unit/llms (#43191)	2026-09-25 12:43:23 -07:00