Block a user
/no_think is honoured on chat/completions but ignored on /v1/responses
Measured: with no working control, reasoning expands to fill any budget
This issue's third point — populate incomplete_details — is no longer
the cosmetic half. Three runs today against…
Prefix-cache reuse looks low on long agentic contexts — 2068 tokens reused against a 42K prompt
Prefix cache savings are invisible:
cached_tokens is never reported, so every client shows 0% cache hit
A streamed turn logs nothing when it ends, so it cannot be diagnosed afterwards
Streams go silent for the whole prefill, so clients drop them as dead — and an abandoned request keeps the pool lock
Correction — the diagnosis above is wrong, and the real cause is on the wire
The issue body describes a permanent cuMemAllocAsync wedge. It is not
that. I took a single eu-stack…