b0c83ca985
Some checks failed
CI / typecheck + vitest (Node 20) (push) Has been cancelled
The PR #12 runbook and compose pre-flight headers claimed a wildcard *.vector.apexfusion.org record covers new supplier hosts. It does not: each mp-suppliers-* host is an individual DNS-only A record to 91.98.147.172, and on-box Let's Encrypt HTTP-01 issuance requires the record to be unproxied. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
102 lines
4.9 KiB
YAML
102 lines
4.9 KiB
YAML
# deploy/mainnet/docker-compose.supplier-kimi-code-chat.yml — Supplier — MAINNET
|
|
# (Hetzner Inference / Kimi-K2.7-Code — MULTI-TURN CHAT capability `llm.chat.v1`)
|
|
#
|
|
# The chat-session sibling of docker-compose.supplier-kimi-code.yml. Same
|
|
# image, same Hetzner backend (Kimi-K2.7-Code), 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 8 Hetzner-backed suppliers (4 models x {one-off, chat-session});
|
|
# fleet runbook: docs/HETZNER_SETUP.md.
|
|
#
|
|
# Pre-flight:
|
|
# 1. DNS: mp-suppliers-kimi-code-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.kimi-code-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-kimi-code-chat
|
|
|
|
services:
|
|
supplier:
|
|
build:
|
|
context: ../..
|
|
dockerfile: supplier/Dockerfile
|
|
container_name: marketplace-mainnet-supplier-kimi-code-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.kimi-code-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.kimi-code-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-kimi-code-chat-mainnet.entrypoints=web"
|
|
- "traefik.http.routers.mp-suppliers-kimi-code-chat-mainnet.rule=Host(`mp-suppliers-kimi-code-chat.vector.apexfusion.org`)"
|
|
- "traefik.http.routers.mp-suppliers-kimi-code-chat-mainnet.middlewares=mp-suppliers-kimi-code-chat-mainnet-https"
|
|
- "traefik.http.middlewares.mp-suppliers-kimi-code-chat-mainnet-https.redirectscheme.scheme=https"
|
|
- "traefik.http.middlewares.mp-suppliers-kimi-code-chat-mainnet-https.redirectscheme.permanent=true"
|
|
- "traefik.http.routers.mp-suppliers-kimi-code-chat-mainnet-tls.entrypoints=websecure"
|
|
- "traefik.http.routers.mp-suppliers-kimi-code-chat-mainnet-tls.rule=Host(`mp-suppliers-kimi-code-chat.vector.apexfusion.org`)"
|
|
- "traefik.http.routers.mp-suppliers-kimi-code-chat-mainnet-tls.tls.certresolver=letsencrypt"
|
|
- "traefik.http.services.mp-suppliers-kimi-code-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
|