fix/decommission-router-20260911
master
- harness-litellm pinned tag updated to 1.99.1 in infrastructure-control, litellm-health, litellm-self-heal container tables - infrastructure-update MCP per-key limitation note now cites v1.99.1 - harness-redis role corrected: dead 'Router slots, circuit breakers' -> 'LiteLLM cache + rate-limit state' (router decommissioned 2026-09-11) - litellm-self-heal Rule 9 wording clarified for cache/rate-limit only Live verification 2026-09-11: harness-litellm healthy, /health 200/200, 7 models, 46 keys, prisma migrations 127 -> 157.
Router container, image, and config are purged on CT 116 (verified: no container, no image, inference-harness-router:latest removed, :9000 free, 11 containers healthy, 7 models, live syslog-auto completion OK). Updates: - gpu-fleet.prose.md: topology diagram rebuilt without the router tier - gpu-monitor / gpu-self-heal / litellm-health / litellm-self-heal: router steps dropped - infrastructure-control.prose.md: container inventory + litellm row corrected - scripts/daily-infra-report.py, scripts/prose-ai-review.sh: host-scoped checks Verified: 40/40 anchors matched uniquely, 0 U+FFFD across changed files, daily-infra-report.py compiles, no stray harness-router references remain.