mateo-berri f89a3693ba fix(responses): resolve previous_response_id for a just-written turn ... The session lookup reads spend logs straight out of the database, so a follow-up sent seconds after the turn it chains off found nothing while the row was still queued in the worker that served it, and the conversation was dropped without an error. Responses calls now ask the spend-log writer to flush on its next pass instead of waiting out its poll interval, and the lookup gives a just-finished turn a short second chance. Replaying a session also accepted `input` only as a string or a single dict, so the standard list shape dropped every user turn and left the model with assistant messages alone.		2026-08-22 11:46:24 -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(responses): resolve previous_response_id for a just-written turn	2026-08-22 11:46:24 -07:00
proxy_logging	fix(guardrails): run policy pipelines when the caller sends its own metadata (/v1/messages, Claude Code) (#36889)	2026-08-21 13:04:04 -07:00
__init__.py	test(proxy/utils): pin bottom-of-file helper behavior (#29509)	2026-06-02 17:45:19 -07:00