9c31b5d622
May 19, 2026: Full harness update
Abiba2026-05-19 15:03:34 +00:00
4f032b035c
Mumuni review action items: health checks for all containers, version pinning, 503+Retry-After on all-GPU saturation
Abiba (pi)2026-05-17 09:05:27 +00:00
8f3b0c6647
Router: health check verifies actual llama.cpp endpoint, gpu_decr negative guard, AMD sidecar fixed (sysfs fallback)
Abiba (pi)2026-05-17 01:52:28 +00:00
9817fe2ef2
Dashboard: clean rebuild with Queue Status ring chart, GPU slot indicators, organized layout (GPU/Queue+Model+Agent/Usage/Live)
Abiba (pi)2026-05-16 21:05:19 +00:00
654cdff718
Dashboard: GPU slot indicators show active/max concurrent requests. Koonimo API key added. Real-time queuing visibility.
Abiba (pi)2026-05-16 20:43:22 +00:00
bf90e57c5f
Load-aware routing: tracks active GPU requests in Redis, distributes overflow when MoE saturated. 6 concurrent requests now spread across all 3 GPUs instead of queuing on one.
Abiba (pi)2026-05-16 20:23:32 +00:00
2db2796e53
Dashboard: rename to SyslogAI Harness, GPU bar now shows utilization instead of VRAM
Abiba (pi)2026-05-16 19:26:46 +00:00
ec0f9fac63
Fix: clean_unicode now uses chr()-based replacements + ASCII strip to prevent bash heredoc corruption. Emoji and all non-ASCII now fully stripped.
Abiba (pi)2026-05-16 19:12:58 +00:00