litellm/tests/unit/proxy/utils
devin-ai-integration[bot] b1d0e45f8d
feat(policy-engine): stream detect-only post_call pipeline steps live when buffering is off (#45516)
* feat(policy-engine): stream detect-only post_call pipeline steps live when buffering is off

* fix(policy-engine): scan live pipeline streams a provider error cuts short and discard rewrites per step

A live detect-only pipeline now scans the chunks the client received when the provider fails mid-stream, then re-raises the error. Each step's rewrite is discarded right after the step, so later steps scan the text the client actually received.

* fix(proxy): keep a guardrail verdict recorded after a stream failure on the failure spend row

---------

Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
2026-10-09 15:46:51 -07:00
..
helpers fix(proxy): use budget reset window for projected spend alerts (#31942) 2026-10-08 12:02:40 -07:00
prisma_and_spend fix(proxy): accept team-scoped models by their public name on POST /fallback (#45455) 2026-10-08 22:38:38 +00:00
proxy_logging feat(policy-engine): stream detect-only post_call pipeline steps live when buffering is off (#45516) 2026-10-09 15:46:51 -07:00
__init__.py test(proxy): move utils, agent_endpoints and endpoint tests into tests/unit/proxy (#44006) 2026-10-01 11:06:42 -07:00