• Stefy Lanza (nextime / spora )'s avatar
    front: live it/s on the synthesized task (measure throughput from the relayed SSE stream) · be9950a5
    Stefy Lanza (nextime / spora ) authored
    The Tasks page lost the it/s indicator under load: when the engine is too busy to
    report its own task, the front showed a synthetic in-flight task with rate 0. Now
    the front counts SSE "data:" events (~one token each for chat/text) as it relays
    the stream and publishes step + rate (tokens/s, refreshed ~2×/s) onto the in-flight
    metadata, so the synthesized task shows a live it/s even while the engine can't
    answer its own /admin/api/tasks. Only for streaming 200 responses; the engine's
    real task (with its own rate) still wins via the (engine,model) dedup when reachable.
    Co-Authored-By: 's avatarClaude Opus 4.8 <noreply@anthropic.com>
    be9950a5
app.py 51.4 KB