mateo-berri 4c00a6e189 fix(batches): account a batch's cost once, from the first retrieve that sees it final ... Every retrieve of a batch through the proxy shares one spend row, the batch id plus the batch cost suffix, and spend log inserts skip duplicates. A poll that landed while the batch was still validating or in progress wrote that row at $0 and no later retrieve could overwrite it, and every completed retrieve after the first added the cost to the key, team, and user counters again with no new row to show for it. The cost callback now writes nothing for a batch retrieve until the batch is final, releasing the poll's budget reservation instead, and once it is final it charges only when no spend row for that batch is queued for flush or already stored. Batch cost rows are flushed to the database right away so a second instance sees them, and the logger prices a batch only once it is final, which also covers a failed batch that never produced an output file.		2026-09-05 16:35:32 -07:00
..
helpers	test: require a match= on broad pytest.raises, and drop duplicate parametrize cases (#37769)	2026-08-20 20:24:49 -07:00
prisma_and_spend	fix(batches): account a batch's cost once, from the first retrieve that sees it final	2026-09-05 16:35:32 -07:00
proxy_logging	Merge pull request #38440 from BerriAI/litellm_prompt_registry_env	2026-09-03 14:09:26 -07:00
__init__.py	test(proxy/utils): pin bottom-of-file helper behavior (#29509)	2026-06-02 17:45:19 -07:00