Files
agents-marketplace/deploy/mainnet/docker-compose.supplier-qwen38-chat.yml
david e8261d9500 feat(deploy): swap retired Hetzner suppliers for Qwen3.8-27B pair
Hetzner Inference dropped Kimi-K2.7-Code, GLM-5.2-NVFP4 and
DeepSeek-V4-Flash-0731 from /v1/models; the 6 suppliers serving them are
deregistered (adverts retired on-chain 2026-08-21, containers removed):

  kimi-code          3f37082166faf2b2220e6476235bae8723af9a3434a6aaf60277366ff1f62bfb
  kimi-code-chat     3d1b43645c00bdb7b429f29ced798bc4af206c9dc56074e955d84b603b64f50c
  glm                bf3ee48addb32e2b0726066f1806b9d84ad64b86c7d41d379abd4b439c522696
  glm-chat           b910327023edb6a3f31696b7feaa9448a151c671c2ff303c4c3dd5a07d03c6b5
  ds-flash-htz       61dd30deb1cd3d6c3f73792bda46ecea6890735237d8329ade2b8449d298f24e
  ds-flash-htz-chat  348a278c81a2bf664ea65705a6245df31e81f64c0ffa6e04a59b248fcdae3d9f

New qwen38 + qwen38-chat suppliers serve Hetzner's new Qwen3.8-27B
(ctx 262144; ping + tools round-trip verified 2026-08-21), reusing the
retired kimi-code / kimi-code-chat wallets. Adverts:

  qwen38       bb8a7078098dc5e60b3f97b040e38f05e6cca662497d4bea471e1dff19c1e1ae#0
  qwen38-chat  31e3a6e258ceaa0d1eaabe61fa3fbe3abcbbb400a7b885e05c8dbcdcf4924eda#0
2026-08-21 13:46:03 +02:00

104 lines
5.0 KiB
YAML

# deploy/mainnet/docker-compose.supplier-qwen38-chat.yml — Supplier — MAINNET
# (Hetzner Inference / Qwen3.8-27B — MULTI-TURN CHAT capability `llm.chat.v1`)
#
# The chat-session sibling of docker-compose.supplier-qwen38.yml. Same
# image, same Hetzner backend (Qwen3.8-27B), but CAPABILITY_KIND=chat-session so
# it mounts /v1/chat/{start,message,end} (escrow bookends, off-chain streaming
# turns) instead of the one-off /v1/chat/completions route.
#
# A SEPARATE process/advert from the one-off supplier on purpose: the chat
# session holds the supplier's single-slot lock for the whole conversation
# (minutes), which would starve one-off traffic if co-hosted.
#
# One of the Hetzner-backed suppliers (models x {one-off, chat-session});
# fleet runbook: docs/HETZNER_SETUP.md. Wallet reused from the retired
# kimi-code-chat supplier (Hetzner dropped Kimi-K2.7-Code on 2026-08; advert
# retired 2026-08-21, tx 3d1b43645c00bdb7b429f29ced798bc4af206c9dc56074e955d84b603b64f50c).
#
# Pre-flight:
# 1. DNS: mp-suppliers-qwen38-chat.vector.apexfusion.org → host
# (individual DNS-only A record → 91.98.147.172; NO wildcard exists —
# letsencrypt HTTP-01 issuance needs the unproxied direct record)
# 2. supplier/.env.qwen38-chat 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
# The advert must be posted with --capability-id llm.chat.v1 and a large
# --max-processing-ms (~1800000) so Claim+Submit both land before deliver_by.
# 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-qwen38-chat
services:
supplier:
build:
context: ../..
dockerfile: supplier/Dockerfile
container_name: marketplace-mainnet-supplier-qwen38-chat
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.qwen38-chat
required: false
environment:
# Multi-turn chat session capability (mounts /v1/chat/{start,message,end}).
CAPABILITY_KIND: chat-session
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; mirror the one-off compose.
OPENAI_TIMEOUT_MS: "300000"
# Idle end (supplier Submits the transcript): single-slot suppliers must
# free up quickly (the gateway transparently reopens a session on the
# next turn). Mirrors the kimi-chat fleet.
CHAT_IDLE_TIMEOUT_MS: "900000"
CHAT_SETTLE_MODE: ticket
MAX_CHAT_SESSIONS: "8"
PORT: "8080"
# Enable LiveOgmiosProvider so Claim/Submit actually broadcast.
LIVE_CHAIN: "1"
# NETWORK_ID and OGMIOS_URL intentionally not pinned here — they MUST
# come from the operator-provided supplier/.env.qwen38-chat 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-qwen38-chat-mainnet.entrypoints=web"
- "traefik.http.routers.mp-suppliers-qwen38-chat-mainnet.rule=Host(`mp-suppliers-qwen38-chat.vector.apexfusion.org`)"
- "traefik.http.routers.mp-suppliers-qwen38-chat-mainnet.middlewares=mp-suppliers-qwen38-chat-mainnet-https"
- "traefik.http.middlewares.mp-suppliers-qwen38-chat-mainnet-https.redirectscheme.scheme=https"
- "traefik.http.middlewares.mp-suppliers-qwen38-chat-mainnet-https.redirectscheme.permanent=true"
- "traefik.http.routers.mp-suppliers-qwen38-chat-mainnet-tls.entrypoints=websecure"
- "traefik.http.routers.mp-suppliers-qwen38-chat-mainnet-tls.rule=Host(`mp-suppliers-qwen38-chat.vector.apexfusion.org`)"
- "traefik.http.routers.mp-suppliers-qwen38-chat-mainnet-tls.tls.certresolver=letsencrypt"
- "traefik.http.services.mp-suppliers-qwen38-chat-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