Yuneng Jiang 5445297da9 [Fix] Stabilize flaky spend accuracy tests with local ground truth ...

Replace the calibration step (one request + 10-minute poll) with an
independent ground truth computed from response usage via
litellm.cost_per_token. All N requests are made up front, so a single
dropped Redis write no longer kills the test.

Add /health/readiness checks at test start and on poll timeout so the
failure message surfaces proxy state (db, cache) instead of "calibration
timed out".

Set PROXY_BATCH_WRITE_AT=2 in the spend tracking CI job to shorten the
scheduler flush window.

2026-04-22 13:45:00 -07:00

..

test_ocr_spend_tracking.py

style: run black formatter on files from main merge

2026-04-17 13:02:59 -07:00

test_spend_accuracy_tests.py

[Fix] Stabilize flaky spend accuracy tests with local ground truth

2026-04-22 13:45:00 -07:00