diff --git a/40-inventory/hosts.yml b/40-inventory/hosts.yml index b046c55..ab0050e 100644 --- a/40-inventory/hosts.yml +++ b/40-inventory/hosts.yml @@ -142,6 +142,33 @@ status: active type: server user: bserv + notes: 'AI services deployed 2026-09-20 (owner-approved): (1) Ollama 0.34.2, systemd + override /etc/systemd/system/ollama.service.d/override.conf: OLLAMA_HOST=0.0.0.0:11434, + FLASH_ATTENTION=1, KV_CACHE_TYPE=q8_0, CONTEXT_LENGTH=49152, MAX_LOADED_MODELS=1, + KEEP_ALIVE=-1; model qwen3.5:2b-q4_K_M (1.9GB, vision, 201 langs), use think:false + in requests; ~13 tok/s. (2) whisper.cpp built from /opt/whisper.cpp with CUDA + sm_50 (required gcc-10 host compiler fix for nvcc 11.5); systemd unit whisper-server.service: + whisper-server --host 0.0.0.0 --port 8008 -m models/ggml-large-v3-turbo-q5_0.bin + -t 4 -l auto -fa --vad -vm models/ggml-silero-v5.1.2.bin; HTTP POST /inference + multipart file=@; auto language detect, ru/uk verified. VRAM budget: ollama 2726MiB + + whisper ~855MiB = 3581/4096 MiB resident. Driver upgraded 535->580 live (rmmod/modprobe, + no reboot, 26 VMs unaffected). OOM fallback ladder: turbo->small q5_1, KV q8_0->q4_0, + ctx 48K->32K.' + ram_gb: 120 + gpu: NVIDIA Quadro K1200 (GM107GL, Maxwell sm_50, 4GB GDDR5, driver 580.178.04 non-open, + CUDA 13.0 runtime); secondary AMD ES1000 embedded (server display only) + active_services: + - ollama.service + - whisper-server.service + - libvirtd + - ssh.service + listening_ports: + tcp: + - 22 + - 111 + - 2049 + - 8008 + - 11434 - id: gnexus-creds-host addresses: lan: @@ -321,3 +348,35 @@ status: active type: vps user: ubuntu +- id: gntasks + active_services: + - navi.service + - docker.service + - containerd.service + - ssh.service + addresses: + lan: + - 192.168.1.179 + docs: ../10-systems/hosts/gntasks.md + environment: home + hostname: gntasks + last_reviewed: '2026-09-21' + listening_ports: + tcp: + - 22 + - 5432 + - 8099 + name: gntasks + notes: 'Navi instance ayame (profile navi_code, instance_id 1606fff0-5abc-468c-af57-6c3c316494ac) + deployed 2026-09-21 from deploy branch (e276b1e). navi.service on port 8099, repo + /home/ubuntu/navi-1. Postgres (navi) docker on 127.0.0.1:5432. Hive announce to + http://192.168.1.168:8087 confirmed (announce_ok). Ollama backend via OLLAMA_HOST/OLLAMA_API_KEY + in .env; embeddings via 192.168.1.168:11434 (embed.ok=true). ufw inactive. Credentials: + gnexus-creds secret e4e28fe1-c9ac-4bb9-a462-0d57bce13692 (SSH=sudo=root password).' + os: Ubuntu 22.04.5 LTS + owner: gmikcon + purpose: Navi agent instance (ayame, navi_code) in home LAN + source_of_truth: ssh-host-and-owner-confirmed + status: active + type: vps + user: ubuntu diff --git a/40-inventory/services.yml b/40-inventory/services.yml index 64f957d..5394cc1 100644 --- a/40-inventory/services.yml +++ b/40-inventory/services.yml @@ -216,3 +216,47 @@ tls: terminates on internal-proxy-vps (.226), separate Let's Encrypt certificate CN=bugtrail.gnexus.space (expires 2026-12-17) type: web-app +- id: gntranscribe + criticality: medium + description: 'Telegram bot @gntranscribe_bot: forwards voice/audio/video to whisper-server + (bserv-host 192.168.1.130:8008) and returns transcripts. asyncio queue (max 20), + single worker, optional chat_id whitelist via ALLOWED_CHAT_IDS in .env, commands + /start /help /id /status. python-telegram-bot 21.10.' + docs: ../10-systems/bots/gntranscribe.md + host: tgbots-vm + last_reviewed: '2026-09-20' + name: GNtranscribe + path: /home/ubuntu/bots/GNtranscribe + ports: [] + runbook: '' + source_of_truth: live_system + status: active + systemd_unit: gntranscribe.service + type: telegram-bot + upstream: http://192.168.1.130:8008/inference +- id: gntodo + criticality: medium + deployed_at: '2026-09-21' + description: 'GNexus Tasks (gntodo): personal task manager with projects, recurring + tasks, XP/garden rewards. Docker compose stack (postgres:17 + FastAPI api + nginx + web SPA) in /srv/gntodo on gntasks host. SSO via gnexus-auth (OAuth + signed webhook), + per-user MCP tokens (Settings → MCP tokens), multi-tenant since ac8aefb (ТЗ 0.34). + MCP endpoint https://tasks.gnexus.space/mcp/ (streamable HTTP, Bearer per-user + token).' + docs: ../10-systems/hosts/gntasks.md + domains: + - tasks-gnexus-space + health_endpoint: /api/health + host: gntasks + internal_upstream: http://192.168.1.179:8135 + last_reviewed: '2026-09-22' + name: GNexus Tasks (gntodo) + ports: + - 8135 + public_url: https://tasks.gnexus.space/ + repository: https://git.gnexus.space/git/root/gnexus-tasks.git + source_of_truth: ssh-host-and-live-verified + status: active + tls: terminates on internal-proxy-vps (.226), separate Let's Encrypt certificate + CN=tasks.gnexus.space (expires 2026-12-20) + type: web-app