• Log actual tokens and elapsed time for all endpoints incl. streaming

    Ghost released this 2026-05-08 07:47:32 +00:00 | 20 commits to main since this release

    For streaming /v1/chat/completions: inject stream_options.include_usage,
    parse usage from SSE chunks, log actual ↑↓ tokens and wall time in the
    generator's finally block. Add elapsed time to all second log entries.

    Downloads