Eight new mainnet suppliers backed by Hetzner's OpenAI-compatible inference API (https://inference.hetzner.com/api). Pure configuration — the LLM_BACKEND=openai path is reused unchanged, following the HuggingFace-router precedent: kimi-code[-chat] Kimi-K2.7-Code (ctx 262144) glm[-chat] GLM-5.2-NVFP4 (ctx 512000) ds-flash-htz[-chat] DeepSeek-V4-Flash-0731 (ctx 512000) qwen35b[-chat] Qwen/Qwen3.6-35B-A3B-FP8 (ctx 262144) Uniform 0.2 AP3X per job, default 1 AP3X bonds, no upstream max_tokens (advert cap = model context length), 300s SLA (1800s for chat sessions). All four models smoke-tested for non-empty content and tools round-trip. Runbook: docs/HETZNER_SETUP.md. Adverts, wallets, and host env files are operator steps after merge; first `up -d` is manual (CD skips projects with no running containers). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
89 lines
4.1 KiB
YAML
89 lines
4.1 KiB
YAML
# deploy/mainnet/docker-compose.supplier-ds-flash-htz.yml — Supplier — MAINNET
|
||
# (Hetzner Inference / DeepSeek-V4-Flash-0731 — one-off `llm.text.generate.v1`)
|
||
#
|
||
# Hetzner-backed supplier. LLM_BACKEND=openai pointed directly at Hetzner's
|
||
# hosted inference API (OpenAI-compatible at https://inference.hetzner.com/api).
|
||
# No local proxy container — reachable over public HTTPS.
|
||
#
|
||
# One of 8 Hetzner-backed suppliers (4 models x {one-off, chat-session});
|
||
# fleet runbook: docs/HETZNER_SETUP.md.
|
||
#
|
||
# Pre-flight:
|
||
# 1. DNS: mp-suppliers-ds-flash-htz.vector.apexfusion.org → host
|
||
# (wildcard *.vector.apexfusion.org already in place via Cloudflare)
|
||
# 2. supplier/.env.ds-flash-htz written on host (chmod 600) with at minimum:
|
||
# SUPPLIER_PRIV_KEY_HEX, SUPPLIER_ADDRESS, SUPPLIER_PKH,
|
||
# SUPPLIER_PUB_KEY_HEX, OPENAI_API_KEY, OGMIOS_URL, NETWORK_ID=1,
|
||
# VECTOR_ZERO_TIME_MS, ESCROW_REF_UTXO, ADVERT_REF_UTXO, ADVERT_REF,
|
||
# LIVE_CHAIN=1
|
||
# 3. Networks already exist (created by the canonical supplier compose):
|
||
# docker network create marketplace-mainnet-net # one-shot
|
||
# # traefik-net is created by the Traefik project
|
||
|
||
name: marketplace-mainnet-supplier-ds-flash-htz
|
||
|
||
services:
|
||
supplier:
|
||
build:
|
||
context: ../..
|
||
dockerfile: supplier/Dockerfile
|
||
container_name: marketplace-mainnet-supplier-ds-flash-htz
|
||
restart: unless-stopped
|
||
env_file:
|
||
# Self-contained env for this Hetzner-backed variant. Holds this
|
||
# supplier's distinct SUPPLIER_PRIV_KEY_HEX (+ derived wallet vars),
|
||
# ADVERT_REF, the shared Hetzner OPENAI_API_KEY, and the shared mainnet
|
||
# plumbing duplicated in full (NETWORK_ID, OGMIOS_URL, VECTOR_ZERO_TIME_MS,
|
||
# ref-script UTxOs, LIVE_CHAIN). No env_file ordering / override magic.
|
||
- path: ../../supplier/.env.ds-flash-htz
|
||
required: false
|
||
environment:
|
||
LLM_BACKEND: openai
|
||
# No /v1 suffix — supplier/src/openai.ts appends /v1/chat/completions
|
||
# (Hetzner serves at https://inference.hetzner.com/api/v1/...).
|
||
OPENAI_BASE_URL: https://inference.hetzner.com/api
|
||
# Reasoning-style models can be slow; matches the advert's
|
||
# max_processing_ms (300000).
|
||
OPENAI_TIMEOUT_MS: "300000"
|
||
# OPENAI_MAX_TOKENS intentionally unset: no max_tokens forwarded upstream,
|
||
# the provider grants context − prompt. Advert cap = model context length.
|
||
PORT: "8080"
|
||
# Enable LiveOgmiosProvider so submitTx/awaitTx actually broadcast.
|
||
LIVE_CHAIN: "1"
|
||
# NETWORK_ID and OGMIOS_URL intentionally not pinned here — they MUST
|
||
# come from the operator-provided supplier/.env.ds-flash-htz on a mainnet host.
|
||
healthcheck:
|
||
test: ["CMD-SHELL", "wget -qO- http://localhost:8080/healthz >/dev/null || exit 1"]
|
||
interval: 20s
|
||
timeout: 5s
|
||
retries: 3
|
||
start_period: 15s
|
||
networks:
|
||
- marketplace-mainnet-net
|
||
- traefik-net
|
||
labels:
|
||
- "traefik.enable=true"
|
||
- "traefik.docker.network=traefik-net"
|
||
- "traefik.http.routers.mp-suppliers-ds-flash-htz-mainnet.entrypoints=web"
|
||
- "traefik.http.routers.mp-suppliers-ds-flash-htz-mainnet.rule=Host(`mp-suppliers-ds-flash-htz.vector.apexfusion.org`)"
|
||
- "traefik.http.routers.mp-suppliers-ds-flash-htz-mainnet.middlewares=mp-suppliers-ds-flash-htz-mainnet-https"
|
||
- "traefik.http.middlewares.mp-suppliers-ds-flash-htz-mainnet-https.redirectscheme.scheme=https"
|
||
- "traefik.http.middlewares.mp-suppliers-ds-flash-htz-mainnet-https.redirectscheme.permanent=true"
|
||
- "traefik.http.routers.mp-suppliers-ds-flash-htz-mainnet-tls.entrypoints=websecure"
|
||
- "traefik.http.routers.mp-suppliers-ds-flash-htz-mainnet-tls.rule=Host(`mp-suppliers-ds-flash-htz.vector.apexfusion.org`)"
|
||
- "traefik.http.routers.mp-suppliers-ds-flash-htz-mainnet-tls.tls.certresolver=letsencrypt"
|
||
- "traefik.http.services.mp-suppliers-ds-flash-htz-mainnet.loadbalancer.server.port=8080"
|
||
logging:
|
||
driver: json-file
|
||
options:
|
||
max-size: "10m"
|
||
max-file: "3"
|
||
|
||
networks:
|
||
marketplace-mainnet-net:
|
||
external: true
|
||
name: marketplace-mainnet-net
|
||
traefik-net:
|
||
external: true
|
||
name: traefik-net
|