mirror of
https://github.com/Memo-2023/mana-monorepo.git
synced 2026-05-14 18:41:08 +02:00
infra(phase 2g): mana-research → GPU-Box
Web-Research-Orchestrator (16+ search-/LLM-providers) auf die GPU-Box verlagert. Cross-LAN für mana-auth/mana-credits/mana-llm/mana-search/ postgres/redis (192.168.178.131). research.mana.how routet jetzt zum mana-gpu-server-Tunnel (CF config v29). Mini-Container-Count 42 → 41. PUBLIC_MANA_RESEARCH_URL in mana-app-web auf https-URL umgestellt — Mini-Container können 192.168.178.11 nicht direkt erreichen (Colima-NAT), daher Cross-LAN-Bridge via Cloudflare-Tunnel wie bei mana-ai. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Till JS
parent
521ae52a62
commit
c84742005b
7 changed files with 80 additions and 63 deletions
|
|
@ -148,8 +148,6 @@ ingress:
|
|||
service: http://localhost:3063
|
||||
- hostname: events.mana.how
|
||||
service: http://localhost:3065
|
||||
- hostname: research.mana.how
|
||||
service: http://localhost:3068
|
||||
- hostname: cards-api.mana.how
|
||||
service: http://localhost:3072
|
||||
- hostname: feedback.mana.how
|
||||
|
|
|
|||
|
|
@ -343,66 +343,10 @@ services:
|
|||
retries: 3
|
||||
start_period: 15s
|
||||
|
||||
mana-research:
|
||||
build:
|
||||
context: .
|
||||
dockerfile: services/mana-research/Dockerfile
|
||||
image: mana-research:local
|
||||
container_name: mana-research
|
||||
restart: always
|
||||
# Tier-3 right-size 2026-04-28: live RSS ~57 MiB, 4× headroom is enough.
|
||||
mem_limit: 128m
|
||||
depends_on:
|
||||
postgres:
|
||||
condition: service_healthy
|
||||
redis:
|
||||
condition: service_started
|
||||
mana-credits:
|
||||
condition: service_healthy
|
||||
mana-search:
|
||||
condition: service_started
|
||||
environment:
|
||||
TZ: Europe/Berlin
|
||||
NODE_ENV: production
|
||||
PORT: 3068
|
||||
DATABASE_URL: postgresql://postgres:${POSTGRES_PASSWORD:-mana123}@postgres:5432/mana_platform
|
||||
# Redis requires auth (see redis service `--requirepass`). Without the
|
||||
# password here the cache layer degrades to every-request-missing with
|
||||
# NOAUTH log spam. Cache misses are not fatal (the executor just
|
||||
# proxies straight to the upstream provider), but the log noise
|
||||
# drowns out real errors in grafana/glitchtip.
|
||||
REDIS_URL: redis://:${REDIS_PASSWORD:-redis123}@redis:6379
|
||||
MANA_AUTH_URL: http://mana-auth:3001
|
||||
MANA_LLM_URL: http://mana-llm:3025
|
||||
MANA_CREDITS_URL: http://mana-credits:3002
|
||||
MANA_SEARCH_URL: http://mana-search:3021
|
||||
MANA_SERVICE_KEY: ${MANA_SERVICE_KEY}
|
||||
CACHE_TTL_SECONDS: 3600
|
||||
BRAVE_API_KEY: ${BRAVE_API_KEY:-}
|
||||
TAVILY_API_KEY: ${TAVILY_API_KEY:-}
|
||||
EXA_API_KEY: ${EXA_API_KEY:-}
|
||||
SERPER_API_KEY: ${SERPER_API_KEY:-}
|
||||
JINA_API_KEY: ${JINA_API_KEY:-}
|
||||
FIRECRAWL_API_KEY: ${FIRECRAWL_API_KEY:-}
|
||||
SCRAPINGBEE_API_KEY: ${SCRAPINGBEE_API_KEY:-}
|
||||
PERPLEXITY_API_KEY: ${PERPLEXITY_API_KEY:-}
|
||||
ANTHROPIC_API_KEY: ${ANTHROPIC_API_KEY:-}
|
||||
OPENAI_API_KEY: ${OPENAI_API_KEY:-}
|
||||
GOOGLE_GENAI_API_KEY: ${GOOGLE_GENAI_API_KEY:-}
|
||||
CORS_ORIGINS: https://mana.how,https://chat.mana.how,https://research.mana.how
|
||||
ports:
|
||||
- "3068:3068"
|
||||
healthcheck:
|
||||
test: ["CMD", "bun", "-e", "fetch('http://127.0.0.1:3068/health').then(r=>process.exit(r.ok?0:1)).catch(()=>process.exit(1))"]
|
||||
interval: 120s
|
||||
timeout: 10s
|
||||
retries: 3
|
||||
start_period: 15s
|
||||
labels:
|
||||
- "traefik.enable=true"
|
||||
- "traefik.http.routers.mana-research.rule=Host(`research.mana.how`)"
|
||||
- "traefik.http.routers.mana-research.tls=true"
|
||||
- "traefik.http.services.mana-research.loadbalancer.server.port=3068"
|
||||
# mana-research moved to GPU-Box on 2026-05-07 (Phase 2g). Source-of-truth
|
||||
# is now mana-monorepo/infrastructure/docker-compose.gpu-box.yml. DNS for
|
||||
# research.mana.how points at the mana-gpu-server tunnel; cross-LAN to
|
||||
# mana-credits + mana-search + postgres + redis on 192.168.178.131.
|
||||
|
||||
mana-events:
|
||||
build:
|
||||
|
|
@ -930,7 +874,7 @@ services:
|
|||
# internal docker-network URL. Without this pair, the SSR-
|
||||
# injected window.__PUBLIC_MANA_RESEARCH_URL__ is empty string
|
||||
# and research fetches fall back to the current origin (404).
|
||||
PUBLIC_MANA_RESEARCH_URL: http://mana-research:3068
|
||||
PUBLIC_MANA_RESEARCH_URL: https://research.mana.how
|
||||
PUBLIC_MANA_RESEARCH_URL_CLIENT: https://research.mana.how
|
||||
# mana-analytics — public-feedback hub. Browser hits the
|
||||
# /api/v1/(public/)feedback/* endpoints directly; SSR uses the
|
||||
|
|
|
|||
|
|
@ -300,6 +300,7 @@ scrape_configs:
|
|||
- https://memoro-api.mana.how/health
|
||||
- https://memoro-audio.mana.how/health
|
||||
- https://mana-ai.mana.how/health
|
||||
- https://research.mana.how/health
|
||||
# who.mana.how API on /api/decks — root is 404 by design (Phaser-Cantina mounts at /cantina)
|
||||
- https://who-api.mana.how/api/decks
|
||||
# Verein backoffice (mana e.V. Plattform); only /health returns 200, root is auth-walled
|
||||
|
|
|
|||
|
|
@ -18,6 +18,7 @@ Production-Hot-Path bleibt unverändert auf dem Mini.
|
|||
| Phase 2d — Glitchtip mit dediziertem DB-Stack | ✅ | 4 Container neu (mana-mon-glitchtip + worker + dedizierte glitchtip-postgres + glitchtip-redis). Mini-Postgres scheiterte bei `logs.0001_initial`-Partition-Creation mit OS-level "Permission denied" (macOS-Docker-Storage-Quirk auf externer SSD). Auf der GPU-Box mit Linux-ext4 saubere 333-Tabellen-Migration. Worker enqueuet UND finished Tasks → DB-Writes funktional (vorher hingen sie ewig). Public-Hostname `glitchtip.mana.how` → mana-gpu-server-Tunnel (config v23). |
|
||||
| Phase 2e — Status-Page auf GPU-Box | ✅ | 2 Container neu (`mana-mon-status-gen` + `mana-mon-status-nginx`). Sparse `/srv/mana/source` mit `mana-source-pull.timer` (stündlich) hostet das `generate-status-page.sh` und `mana-apps.ts`. status-gen schreibt in das Docker-Volume `status-output`, das status-nginx auf `:8090` ausliefert. Public-Hostname `status.mana.how` → mana-gpu-server-Tunnel (config v25). Bonus: behebt den Inode-Stale-Bind-Mount-Bug, der auf dem Mini bei jedem CD-`git checkout -f` die Status-Page kaputt machte. `vm.mana.how` (Phase-2c-Workaround für Mini→GPU-VM-Routing) wurde wieder aus dem Tunnel entfernt — VM ist nicht mehr public. |
|
||||
| Phase 2f — drei weitere Hilfsdienste verlagert | ✅ | (1) **verdaccio** (npm.mana.how, was im mana-platform-Repo): Volume tar-stream + Config-bundle in mana-monorepo (`infrastructure/verdaccio/config.yaml`). (2) **news-ingester** (Bun-Background-Tick): Cross-LAN-DB zur Mini-Postgres. Cross-arch-Limit aufgedeckt — `docker save\|load` zwischen Mini (arm64) und GPU-Box (x86_64) wirft `exec format error`, daher nativer Build mit GPU-Box-eigenem Dockerfile in `infrastructure/news-ingester/` der `@mana/shared-rss` als `file:`-ref vendored. (3) **mana-ai** (AI Mission Runner): Cross-LAN für mana-api/mana-llm/mana-research, RSA-Key-Sync (`MANA_AI_PRIVATE_KEY_PEM`), `mana-ai.mana.how` zum GPU-Tunnel (config v28). Bonus: AI Mission Runner sitzt jetzt im selben docker-network wie gpu-llm/gpu-ollama — künftige direct-LLM-Pfade ohne Cloudflare-Round-Trip. Mini Container 44 → 42. |
|
||||
| Phase 2g — mana-research auslagern | ✅ | Web-Research-Orchestrator mit 16+ Search-/LLM-Providern. Nativer Build via workspace-Dockerfile (sparse-checkout `services/mana-research` + `packages/{shared-research,shared-types,shared-hono,shared-logger}`). Cross-LAN zu mana-auth/mana-credits/mana-llm/mana-search/postgres/redis (alle auf 192.168.178.131); Redis-Auth via `REDIS_PASSWORD` aus Mini's `.env.macmini` übernommen. `research.mana.how` zum GPU-Tunnel umgebogen via Cloudflare-API (config v29). Beide `PUBLIC_MANA_RESEARCH_URL`-Vars in mana-app-web auf https-URL umgestellt — gleicher Cross-LAN-Bridge-Pattern wie mana-ai (Mini-Container können 192.168.178.11 nicht direkt erreichen, daher Tunnel-Roundtrip). Mini Container 42 → 41. |
|
||||
| Phase 3 — Daten-Migration | n/a | Alle migrierten Apps lesen Mini-Postgres direkt — keine separate Datenmigration |
|
||||
| Phase 4 — Cloudflare-Cutover | ✅ | API-Approach via `cert.pem` apiToken: PUT `/accounts/.../cfd_tunnel/.../configurations` für GPU-Tunnel, dann `cloudflared tunnel route dns --overwrite-dns`. Kein Dashboard-Klick nötig. 3 Hostnames live (grafana/git/stats) |
|
||||
| Phase 5 — Mini-Compose aufräumen | ✅ | 3 Blöcke in `cloudflared-config.yml` auskommentiert (Backup angelegt), cloudflared neu geladen, Mini-Container `mana-mon-grafana` + `mana-mon-umami` gestoppt (nicht entfernt — Rollback bleibt möglich) |
|
||||
|
|
|
|||
|
|
@ -34,3 +34,22 @@ GLITCHTIP_ADMIN_PASSWORD=
|
|||
# in mana-auth's MANA_AI_PUBLIC_KEY_PEM auf dem Mini steht).
|
||||
MANA_SERVICE_KEY=
|
||||
MANA_AI_PRIVATE_KEY_PEM=
|
||||
|
||||
# ─── Redis-Mini Auth (für Cross-LAN-Cache von mana-research, Phase 2g) ───
|
||||
# Identisch mit mana-monorepo/.env.macmini REDIS_PASSWORD.
|
||||
REDIS_PASSWORD=
|
||||
|
||||
# ─── mana-research (Web-Research-Orchestrator, Phase 2g) ─────
|
||||
# 16 Search-/LLM-Provider — alle optional, leer lassen wenn ungenutzt.
|
||||
# Aktuell aktiv im Live-Betrieb: GOOGLE_GENAI_API_KEY (von Mini übernommen).
|
||||
GOOGLE_GENAI_API_KEY=
|
||||
ANTHROPIC_API_KEY=
|
||||
OPENAI_API_KEY=
|
||||
PERPLEXITY_API_KEY=
|
||||
EXA_API_KEY=
|
||||
TAVILY_API_KEY=
|
||||
BRAVE_API_KEY=
|
||||
SERPER_API_KEY=
|
||||
JINA_API_KEY=
|
||||
FIRECRAWL_API_KEY=
|
||||
SCRAPINGBEE_API_KEY=
|
||||
|
|
|
|||
|
|
@ -21,6 +21,10 @@ Hilfsdienste vom Mini abgegeben — siehe [`docs/PLAN_OPTION_C.md`](../docs/PLAN
|
|||
| `gpu-node-exporter`, `gpu-cadvisor`, `gpu-promtail` | (intern) | Self-Monitoring (Phase 2c) |
|
||||
| `glitchtip` + worker + dedizierte postgres + redis | `:8020` → `glitchtip.mana.how` | Error-Tracking mit eigenem DB-Stack (Phase 2d) |
|
||||
| `status-page-gen`, `status-nginx` | `:8090` → `status.mana.how` | Status-Seite (Phase 2e) |
|
||||
| `verdaccio` | `:4873` → `npm.mana.how` | Private @mana/* npm-Registry (Phase 2f-1) |
|
||||
| `news-ingester` | (intern) | RSS-Crawl + News-Ingestion (Phase 2f-2) |
|
||||
| `mana-ai` | `:3067` → `mana-ai.mana.how` | AI Mission Runner (Phase 2f-3) |
|
||||
| `mana-research` | `:3068` → `research.mana.how` | Web-Research-Orchestrator (Phase 2g) |
|
||||
|
||||
Plus der bestehende `photon`-Container (Geocoder), der vor Phase 2 schon
|
||||
auf der Box existierte und unangetastet blieb.
|
||||
|
|
@ -81,6 +85,7 @@ Aktive Public-Hostnames (Stand 2026-05-07, config v28):
|
|||
| `photon.mana.how` | `:2322` | Photon Geocoder (cross-LAN-Workaround für mana-geocoding's Probe + privacy-local Provider) |
|
||||
| `npm.mana.how` | `:4873` | Verdaccio @mana/* npm-Registry (Phase 2f-1) |
|
||||
| `mana-ai.mana.how` | `:3067` | AI Mission Runner (Phase 2f-3) |
|
||||
| `research.mana.how` | `:3068` | Web-Research-Orchestrator (Phase 2g) |
|
||||
|
||||
API-Update (idempotent):
|
||||
|
||||
|
|
|
|||
|
|
@ -523,6 +523,55 @@ services:
|
|||
retries: 3
|
||||
start_period: 30s
|
||||
|
||||
# ============================================
|
||||
# Phase 2g — mana-research (Web Research Orchestrator, 2026-05-07)
|
||||
# 16+ search-providers + LLM-Pipeline. User-facing aber latenztolerant
|
||||
# (5-30s queries). Schreibt in mana_platform.research-Tabellen, nutzt
|
||||
# Redis-Cache + ruft mana-credits + mana-search auf. Geographische Nähe
|
||||
# zu gpu-llm/gpu-ollama wie bei mana-ai.
|
||||
# ============================================
|
||||
mana-research:
|
||||
build:
|
||||
context: /srv/mana/source
|
||||
dockerfile: services/mana-research/Dockerfile
|
||||
image: mana-research:gpu-box
|
||||
container_name: mana-research
|
||||
restart: unless-stopped
|
||||
environment:
|
||||
TZ: Europe/Berlin
|
||||
NODE_ENV: production
|
||||
PORT: 3068
|
||||
DATABASE_URL: postgresql://postgres:${POSTGRES_PASSWORD}@192.168.178.131:5432/mana_platform
|
||||
REDIS_URL: redis://:${REDIS_PASSWORD}@192.168.178.131:6379
|
||||
CACHE_TTL_SECONDS: '3600'
|
||||
CORS_ORIGINS: https://mana.how,https://chat.mana.how,https://research.mana.how
|
||||
# Cross-LAN service deps
|
||||
MANA_AUTH_URL: http://192.168.178.131:3001
|
||||
MANA_CREDITS_URL: http://192.168.178.131:3002
|
||||
MANA_LLM_URL: http://192.168.178.131:3025
|
||||
MANA_SEARCH_URL: http://192.168.178.131:3012
|
||||
MANA_SERVICE_KEY: ${MANA_SERVICE_KEY}
|
||||
# LLM + Search provider keys (most empty, only Google active currently)
|
||||
ANTHROPIC_API_KEY: ${ANTHROPIC_API_KEY:-}
|
||||
OPENAI_API_KEY: ${OPENAI_API_KEY:-}
|
||||
GOOGLE_GENAI_API_KEY: ${GOOGLE_GENAI_API_KEY:-}
|
||||
PERPLEXITY_API_KEY: ${PERPLEXITY_API_KEY:-}
|
||||
EXA_API_KEY: ${EXA_API_KEY:-}
|
||||
TAVILY_API_KEY: ${TAVILY_API_KEY:-}
|
||||
BRAVE_API_KEY: ${BRAVE_API_KEY:-}
|
||||
SERPER_API_KEY: ${SERPER_API_KEY:-}
|
||||
JINA_API_KEY: ${JINA_API_KEY:-}
|
||||
FIRECRAWL_API_KEY: ${FIRECRAWL_API_KEY:-}
|
||||
SCRAPINGBEE_API_KEY: ${SCRAPINGBEE_API_KEY:-}
|
||||
ports:
|
||||
- '3068:3068'
|
||||
healthcheck:
|
||||
test: ['CMD', 'bun', '-e', "fetch('http://localhost:3068/health').then(r => process.exit(r.ok ? 0 : 1)).catch(() => process.exit(1))"]
|
||||
interval: 60s
|
||||
timeout: 10s
|
||||
retries: 3
|
||||
start_period: 30s
|
||||
|
||||
# ============================================
|
||||
# Phase 2f-3 — mana-ai (AI Mission Runner, 2026-05-07)
|
||||
# Background tick-loop (60s default), queryt mana-api + mana-llm +
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue