From 832b184af611b66df2709699ab42ea0f37423d9f Mon Sep 17 00:00:00 2001 From: agent-zero Date: Fri, 11 Sep 2026 15:05:00 -0400 Subject: [PATCH] fix(litellm): upgrade contract refs 1.90.0-rc.1 -> 1.99.1 and correct redis role - 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. --- infrastructure-control.prose.md | 6 +++--- infrastructure-update.prose.md | 2 +- litellm-health.prose.md | 2 +- litellm-self-heal.prose.md | 7 ++++--- 4 files changed, 9 insertions(+), 8 deletions(-) diff --git a/infrastructure-control.prose.md b/infrastructure-control.prose.md index cbbdbc0..52c8281 100644 --- a/infrastructure-control.prose.md +++ b/infrastructure-control.prose.md @@ -199,14 +199,14 @@ description: > ### Ecosystem B: CT 116 syslog-api (192.168.68.116) -11 containers in inference-harness stack (verified live 2026-09-11): +11 containers in inference-harness stack (verified live 2026-09-11; LiteLLM upgraded 1.90.0-rc.1 -> 1.99.1): | Container | Image | Port | Role | |-----------|-------|------|------| -| harness-litellm | ghcr.io/docker.litellm.ai/berriai/litellm:1.90.0-rc.1 | :4000→:4000 | API proxy, key mgmt, fallbacks | +| harness-litellm | ghcr.io/docker.litellm.ai/berriai/litellm:1.99.1 | :4000→:4000 | API proxy, key mgmt, fallbacks | | harness-nginx | nginx:alpine | :80 | Entrypoint, /v1→LiteLLM, /dashboard/ | | harness-postgres | postgres:16-alpine | :5432 | LiteLLM DB (keys, spend, config) | -| harness-redis | redis:7-alpine | :6379 | Router slots, circuit breakers | +| harness-redis | redis:7-alpine | :6379 | LiteLLM cache + rate-limit state | | harness-dashboard | inference-harness-dashboard | :3000 | SyslogAI Harness UI | | harness-grafana | grafana/grafana | :3000→:3001 (direct LAN, not behind nginx) | GPU + Proxmox + Docker dashboards | | harness-prometheus | prom/prometheus | :9090 | Metrics scraper, 6 jobs | diff --git a/infrastructure-update.prose.md b/infrastructure-update.prose.md index 7913034..f1411c6 100644 --- a/infrastructure-update.prose.md +++ b/infrastructure-update.prose.md @@ -206,7 +206,7 @@ mcp_servers: | Key | MCP Access | |-----|-----------| | Master key | ✅ Full — 90 tools (vault-injected) | -| Agent keys (mumuni, tanko, etc.) | ❌ Per-key grants not supported in v1.90.0-rc.1 | +| Agent keys (mumuni, tanko, etc.) | ❌ Per-key grants not supported in v1.99.1 | ### Known Limitations - Per-key MCP server grants not functional — only master key has access diff --git a/litellm-health.prose.md b/litellm-health.prose.md index dad97bf..15555b3 100644 --- a/litellm-health.prose.md +++ b/litellm-health.prose.md @@ -100,7 +100,7 @@ Request → nginx:80 → LiteLLM:4000 → GPU(llama-server, parallel 2) | Container | Image | Port | Health Check | |-----------|-------|------|-------------| -| harness-litellm | ghcr.io/docker.litellm.ai/berriai/litellm:1.90.0-rc.1 | :4000→:4000 | /health/liveliness | +| harness-litellm | ghcr.io/docker.litellm.ai/berriai/litellm:1.99.1 | :4000→:4000 | /health/liveliness | | harness-nginx | nginx:alpine | :80 | HTTP 200 on /health | | harness-postgres | postgres:16-alpine | :5432 | pg_isready | | harness-redis | redis:7-alpine | :6379 | PING | diff --git a/litellm-self-heal.prose.md b/litellm-self-heal.prose.md index 70ee7d3..7524458 100644 --- a/litellm-self-heal.prose.md +++ b/litellm-self-heal.prose.md @@ -98,7 +98,7 @@ Preferred implementation: uncap shared pool, add capped alias for crew-only. | Container | Image | Port | Health Check | |-----------|-------|------|-------------| -| harness-litellm | ghcr.io/docker.litellm.ai/berriai/litellm:1.90.0-rc.1 | :4000→:4000 | /health/liveliness | +| harness-litellm | ghcr.io/docker.litellm.ai/berriai/litellm:1.99.1 | :4000→:4000 | /health/liveliness | | harness-nginx | nginx:alpine | :80 | HTTP 200 on /health | | harness-postgres | postgres:16-alpine | :5432 | pg_isready | | harness-redis | redis:7-alpine | :6379 | PING | @@ -215,8 +215,9 @@ Fix → generate keys in LiteLLM via /key/generate → update /etc/environment o Escalate → if SSH access unavailable, send Zulip DM ### Rule 9: Stale Active Counter in Redis — DEPRECATED -Router no longer in path so Redis active counters are unused. Rule retained -for reference but inactive. If Redis issues occur, check harness-redis container. +Router no longer in path so router active-slot counters are unused. Rule retained +for reference but inactive. `harness-redis` now serves only LiteLLM cache and +rate-limit state; check the container if cache errors appear. --- ---