litellm/tests/unit/batches
joshua-berri be4f3d36ce
feat(accounting): capture request usage through the durable meter (#49133)
* feat(accounting): capture request usage through the durable meter

* fix(accounting): preserve native Google usage compatibility

* fix(accounting): preserve prepared usage observation on failure

* fix(accounting): exclude sync acknowledgement policy rejections from capture

* test(accounting): verify capture races and failure isolation

* fix(accounting): preserve request support with sync acknowledgements

* fix(accounting): normalize usage metadata before queue admission

* fix(accounting): preserve prior attempt links on successful fallback

* fix(accounting): preserve attempt evidence through retries and failures

* fix(accounting): depend on prior receipts without resubmitting usage

* fix(accounting): preserve pricing inputs and resolved capture attribution

* fix(accounting): persist batch usage within capture bounds

* test(accounting): cover batch dependency failure and backpressure

* fix(accounting): isolate batch persistence and preserve trusted attribution

* fix(accounting): share byte admission across batch producers and writes

* fix(accounting): reserve batch snapshot reads before admission

* fix(accounting): compact repeated batch observations without losing requests

---------

Co-authored-by: Joshua Valluru <326636767+joshua-berri@users.noreply.github.com>
2026-10-31 07:32:25 -07:00
..
__init__.py test: add __init__.py to migrated tests/unit packages 2026-09-20 11:53:49 +00:00
test_batch_line_items.py fix(batches): apply the Vertex regional endpoint uplift to batch cost (#47466) 2026-10-20 01:51:51 +00:00
test_batch_utils.py feat(accounting): capture request usage through the durable meter (#49133) 2026-10-31 07:32:25 -07:00
test_main.py fix(hosted_vllm): accept the vLLM production-stack router's file and batch objects (#49068) 2026-10-30 23:11:34 -07:00
test_responses_batch_cost.py test: migrate wave 1 phase 1 legacy tests to tests/unit 2026-09-20 09:17:57 +00:00