From e8261d95002a733dc576a22595a71008334e6d52 Mon Sep 17 00:00:00 2001 From: david Date: Fri, 21 Aug 2026 13:46:03 +0200 Subject: [PATCH] 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 --- buyer/scripts/monitor-wallets.ts | 14 +++ .../docker-compose.supplier-ds-flash-htz.yml | 89 --------------- .../docker-compose.supplier-glm-chat.yml | 101 ------------------ .../mainnet/docker-compose.supplier-glm.yml | 89 --------------- ...docker-compose.supplier-kimi-code-chat.yml | 101 ------------------ ...> docker-compose.supplier-qwen38-chat.yml} | 44 ++++---- ...yml => docker-compose.supplier-qwen38.yml} | 40 +++---- docs/HETZNER_SETUP.md | 50 +++++---- 8 files changed, 87 insertions(+), 441 deletions(-) delete mode 100644 deploy/mainnet/docker-compose.supplier-ds-flash-htz.yml delete mode 100644 deploy/mainnet/docker-compose.supplier-glm-chat.yml delete mode 100644 deploy/mainnet/docker-compose.supplier-glm.yml delete mode 100644 deploy/mainnet/docker-compose.supplier-kimi-code-chat.yml rename deploy/mainnet/{docker-compose.supplier-ds-flash-htz-chat.yml => docker-compose.supplier-qwen38-chat.yml} (62%) rename deploy/mainnet/{docker-compose.supplier-kimi-code.yml => docker-compose.supplier-qwen38.yml} (61%) diff --git a/buyer/scripts/monitor-wallets.ts b/buyer/scripts/monitor-wallets.ts index ac10a7f..cca7e79 100644 --- a/buyer/scripts/monitor-wallets.ts +++ b/buyer/scripts/monitor-wallets.ts @@ -132,6 +132,20 @@ const OPERATOR_SOURCES: OperatorSource[] = [ keyVar: "SUPPLIER_PRIV_KEY_HEX", role: "supplier", }, + { + label: "supplier-qwen38@vector-marketplace", + host: "root@91.98.147.172", + envPath: "/root/agents-marketplace/supplier/.env.qwen38", + keyVar: "SUPPLIER_PRIV_KEY_HEX", + role: "supplier", + }, + { + label: "supplier-qwen38-chat@vector-marketplace", + host: "root@91.98.147.172", + envPath: "/root/agents-marketplace/supplier/.env.qwen38-chat", + keyVar: "SUPPLIER_PRIV_KEY_HEX", + role: "supplier", + }, { label: "supplier-local@inference-proxy", host: "inference-proxy", diff --git a/deploy/mainnet/docker-compose.supplier-ds-flash-htz.yml b/deploy/mainnet/docker-compose.supplier-ds-flash-htz.yml deleted file mode 100644 index 512fd1a..0000000 --- a/deploy/mainnet/docker-compose.supplier-ds-flash-htz.yml +++ /dev/null @@ -1,89 +0,0 @@ -# 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 -# (individual DNS-only A record → 91.98.147.172; NO wildcard exists — -# letsencrypt HTTP-01 issuance needs the unproxied direct record) -# 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 diff --git a/deploy/mainnet/docker-compose.supplier-glm-chat.yml b/deploy/mainnet/docker-compose.supplier-glm-chat.yml deleted file mode 100644 index 2112000..0000000 --- a/deploy/mainnet/docker-compose.supplier-glm-chat.yml +++ /dev/null @@ -1,101 +0,0 @@ -# deploy/mainnet/docker-compose.supplier-glm-chat.yml — Supplier — MAINNET -# (Hetzner Inference / GLM-5.2-NVFP4 — MULTI-TURN CHAT capability `llm.chat.v1`) -# -# The chat-session sibling of docker-compose.supplier-glm.yml. Same -# image, same Hetzner backend (GLM-5.2-NVFP4), 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-glm-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.glm-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-glm-chat - -services: - supplier: - build: - context: ../.. - dockerfile: supplier/Dockerfile - container_name: marketplace-mainnet-supplier-glm-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.glm-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.glm-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-glm-chat-mainnet.entrypoints=web" - - "traefik.http.routers.mp-suppliers-glm-chat-mainnet.rule=Host(`mp-suppliers-glm-chat.vector.apexfusion.org`)" - - "traefik.http.routers.mp-suppliers-glm-chat-mainnet.middlewares=mp-suppliers-glm-chat-mainnet-https" - - "traefik.http.middlewares.mp-suppliers-glm-chat-mainnet-https.redirectscheme.scheme=https" - - "traefik.http.middlewares.mp-suppliers-glm-chat-mainnet-https.redirectscheme.permanent=true" - - "traefik.http.routers.mp-suppliers-glm-chat-mainnet-tls.entrypoints=websecure" - - "traefik.http.routers.mp-suppliers-glm-chat-mainnet-tls.rule=Host(`mp-suppliers-glm-chat.vector.apexfusion.org`)" - - "traefik.http.routers.mp-suppliers-glm-chat-mainnet-tls.tls.certresolver=letsencrypt" - - "traefik.http.services.mp-suppliers-glm-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 diff --git a/deploy/mainnet/docker-compose.supplier-glm.yml b/deploy/mainnet/docker-compose.supplier-glm.yml deleted file mode 100644 index 4a846cb..0000000 --- a/deploy/mainnet/docker-compose.supplier-glm.yml +++ /dev/null @@ -1,89 +0,0 @@ -# deploy/mainnet/docker-compose.supplier-glm.yml — Supplier — MAINNET -# (Hetzner Inference / GLM-5.2-NVFP4 — 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-glm.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.glm 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-glm - -services: - supplier: - build: - context: ../.. - dockerfile: supplier/Dockerfile - container_name: marketplace-mainnet-supplier-glm - 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.glm - 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.glm 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-glm-mainnet.entrypoints=web" - - "traefik.http.routers.mp-suppliers-glm-mainnet.rule=Host(`mp-suppliers-glm.vector.apexfusion.org`)" - - "traefik.http.routers.mp-suppliers-glm-mainnet.middlewares=mp-suppliers-glm-mainnet-https" - - "traefik.http.middlewares.mp-suppliers-glm-mainnet-https.redirectscheme.scheme=https" - - "traefik.http.middlewares.mp-suppliers-glm-mainnet-https.redirectscheme.permanent=true" - - "traefik.http.routers.mp-suppliers-glm-mainnet-tls.entrypoints=websecure" - - "traefik.http.routers.mp-suppliers-glm-mainnet-tls.rule=Host(`mp-suppliers-glm.vector.apexfusion.org`)" - - "traefik.http.routers.mp-suppliers-glm-mainnet-tls.tls.certresolver=letsencrypt" - - "traefik.http.services.mp-suppliers-glm-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 diff --git a/deploy/mainnet/docker-compose.supplier-kimi-code-chat.yml b/deploy/mainnet/docker-compose.supplier-kimi-code-chat.yml deleted file mode 100644 index 040e7c3..0000000 --- a/deploy/mainnet/docker-compose.supplier-kimi-code-chat.yml +++ /dev/null @@ -1,101 +0,0 @@ -# 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 diff --git a/deploy/mainnet/docker-compose.supplier-ds-flash-htz-chat.yml b/deploy/mainnet/docker-compose.supplier-qwen38-chat.yml similarity index 62% rename from deploy/mainnet/docker-compose.supplier-ds-flash-htz-chat.yml rename to deploy/mainnet/docker-compose.supplier-qwen38-chat.yml index d967bc4..3839b4f 100644 --- a/deploy/mainnet/docker-compose.supplier-ds-flash-htz-chat.yml +++ b/deploy/mainnet/docker-compose.supplier-qwen38-chat.yml @@ -1,8 +1,8 @@ -# deploy/mainnet/docker-compose.supplier-ds-flash-htz-chat.yml — Supplier — MAINNET -# (Hetzner Inference / DeepSeek-V4-Flash-0731 — MULTI-TURN CHAT capability `llm.chat.v1`) +# 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-ds-flash-htz.yml. Same -# image, same Hetzner backend (DeepSeek-V4-Flash-0731), but CAPABILITY_KIND=chat-session so +# 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. # @@ -10,14 +10,16 @@ # 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. +# 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-ds-flash-htz-chat.vector.apexfusion.org → host +# 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.ds-flash-htz-chat written on host (chmod 600) with at minimum: +# 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, @@ -28,14 +30,14 @@ # docker network create marketplace-mainnet-net # one-shot # # traefik-net is created by the Traefik project -name: marketplace-mainnet-supplier-ds-flash-htz-chat +name: marketplace-mainnet-supplier-qwen38-chat services: supplier: build: context: ../.. dockerfile: supplier/Dockerfile - container_name: marketplace-mainnet-supplier-ds-flash-htz-chat + container_name: marketplace-mainnet-supplier-qwen38-chat restart: unless-stopped env_file: # Self-contained env for this Hetzner-backed variant. Holds this @@ -43,7 +45,7 @@ services: # 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-chat + - path: ../../supplier/.env.qwen38-chat required: false environment: # Multi-turn chat session capability (mounts /v1/chat/{start,message,end}). @@ -64,7 +66,7 @@ services: # 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.ds-flash-htz-chat on a mainnet host. + # 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 @@ -77,15 +79,15 @@ services: labels: - "traefik.enable=true" - "traefik.docker.network=traefik-net" - - "traefik.http.routers.mp-suppliers-ds-flash-htz-chat-mainnet.entrypoints=web" - - "traefik.http.routers.mp-suppliers-ds-flash-htz-chat-mainnet.rule=Host(`mp-suppliers-ds-flash-htz-chat.vector.apexfusion.org`)" - - "traefik.http.routers.mp-suppliers-ds-flash-htz-chat-mainnet.middlewares=mp-suppliers-ds-flash-htz-chat-mainnet-https" - - "traefik.http.middlewares.mp-suppliers-ds-flash-htz-chat-mainnet-https.redirectscheme.scheme=https" - - "traefik.http.middlewares.mp-suppliers-ds-flash-htz-chat-mainnet-https.redirectscheme.permanent=true" - - "traefik.http.routers.mp-suppliers-ds-flash-htz-chat-mainnet-tls.entrypoints=websecure" - - "traefik.http.routers.mp-suppliers-ds-flash-htz-chat-mainnet-tls.rule=Host(`mp-suppliers-ds-flash-htz-chat.vector.apexfusion.org`)" - - "traefik.http.routers.mp-suppliers-ds-flash-htz-chat-mainnet-tls.tls.certresolver=letsencrypt" - - "traefik.http.services.mp-suppliers-ds-flash-htz-chat-mainnet.loadbalancer.server.port=8080" + - "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: diff --git a/deploy/mainnet/docker-compose.supplier-kimi-code.yml b/deploy/mainnet/docker-compose.supplier-qwen38.yml similarity index 61% rename from deploy/mainnet/docker-compose.supplier-kimi-code.yml rename to deploy/mainnet/docker-compose.supplier-qwen38.yml index 9cc0327..e6a44ef 100644 --- a/deploy/mainnet/docker-compose.supplier-kimi-code.yml +++ b/deploy/mainnet/docker-compose.supplier-qwen38.yml @@ -1,18 +1,20 @@ -# deploy/mainnet/docker-compose.supplier-kimi-code.yml — Supplier — MAINNET -# (Hetzner Inference / Kimi-K2.7-Code — one-off `llm.text.generate.v1`) +# deploy/mainnet/docker-compose.supplier-qwen38.yml — Supplier — MAINNET +# (Hetzner Inference / Qwen3.8-27B — 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. +# 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 supplier (Hetzner dropped Kimi-K2.7-Code on 2026-08; advert +# retired 2026-08-21, tx 3f37082166faf2b2220e6476235bae8723af9a3434a6aaf60277366ff1f62bfb). # # Pre-flight: -# 1. DNS: mp-suppliers-kimi-code.vector.apexfusion.org → host +# 1. DNS: mp-suppliers-qwen38.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 written on host (chmod 600) with at minimum: +# 2. supplier/.env.qwen38 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, @@ -21,14 +23,14 @@ # docker network create marketplace-mainnet-net # one-shot # # traefik-net is created by the Traefik project -name: marketplace-mainnet-supplier-kimi-code +name: marketplace-mainnet-supplier-qwen38 services: supplier: build: context: ../.. dockerfile: supplier/Dockerfile - container_name: marketplace-mainnet-supplier-kimi-code + container_name: marketplace-mainnet-supplier-qwen38 restart: unless-stopped env_file: # Self-contained env for this Hetzner-backed variant. Holds this @@ -36,7 +38,7 @@ services: # 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 + - path: ../../supplier/.env.qwen38 required: false environment: LLM_BACKEND: openai @@ -52,7 +54,7 @@ services: # 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.kimi-code on a mainnet host. + # come from the operator-provided supplier/.env.qwen38 on a mainnet host. healthcheck: test: ["CMD-SHELL", "wget -qO- http://localhost:8080/healthz >/dev/null || exit 1"] interval: 20s @@ -65,15 +67,15 @@ services: labels: - "traefik.enable=true" - "traefik.docker.network=traefik-net" - - "traefik.http.routers.mp-suppliers-kimi-code-mainnet.entrypoints=web" - - "traefik.http.routers.mp-suppliers-kimi-code-mainnet.rule=Host(`mp-suppliers-kimi-code.vector.apexfusion.org`)" - - "traefik.http.routers.mp-suppliers-kimi-code-mainnet.middlewares=mp-suppliers-kimi-code-mainnet-https" - - "traefik.http.middlewares.mp-suppliers-kimi-code-mainnet-https.redirectscheme.scheme=https" - - "traefik.http.middlewares.mp-suppliers-kimi-code-mainnet-https.redirectscheme.permanent=true" - - "traefik.http.routers.mp-suppliers-kimi-code-mainnet-tls.entrypoints=websecure" - - "traefik.http.routers.mp-suppliers-kimi-code-mainnet-tls.rule=Host(`mp-suppliers-kimi-code.vector.apexfusion.org`)" - - "traefik.http.routers.mp-suppliers-kimi-code-mainnet-tls.tls.certresolver=letsencrypt" - - "traefik.http.services.mp-suppliers-kimi-code-mainnet.loadbalancer.server.port=8080" + - "traefik.http.routers.mp-suppliers-qwen38-mainnet.entrypoints=web" + - "traefik.http.routers.mp-suppliers-qwen38-mainnet.rule=Host(`mp-suppliers-qwen38.vector.apexfusion.org`)" + - "traefik.http.routers.mp-suppliers-qwen38-mainnet.middlewares=mp-suppliers-qwen38-mainnet-https" + - "traefik.http.middlewares.mp-suppliers-qwen38-mainnet-https.redirectscheme.scheme=https" + - "traefik.http.middlewares.mp-suppliers-qwen38-mainnet-https.redirectscheme.permanent=true" + - "traefik.http.routers.mp-suppliers-qwen38-mainnet-tls.entrypoints=websecure" + - "traefik.http.routers.mp-suppliers-qwen38-mainnet-tls.rule=Host(`mp-suppliers-qwen38.vector.apexfusion.org`)" + - "traefik.http.routers.mp-suppliers-qwen38-mainnet-tls.tls.certresolver=letsencrypt" + - "traefik.http.services.mp-suppliers-qwen38-mainnet.loadbalancer.server.port=8080" logging: driver: json-file options: diff --git a/docs/HETZNER_SETUP.md b/docs/HETZNER_SETUP.md index 97373a9..729cd8b 100644 --- a/docs/HETZNER_SETUP.md +++ b/docs/HETZNER_SETUP.md @@ -1,8 +1,13 @@ # Hetzner Inference Supplier Fleet — Setup Runbook -> **Status:** shipped. Configures 8 mainnet supplier nodes that use **Hetzner -> Inference** (`https://inference.hetzner.com`) as their **compute backend** for -> bonded inference work commissioned on Vector. Config only — no code changes. +> **Status:** shipped; fleet trimmed 2026-08-21. Hetzner retired +> `Kimi-K2.7-Code`, `GLM-5.2-NVFP4`, and `DeepSeek-V4-Flash-0731` from +> Inference (gone from `/v1/models`), so the 6 suppliers serving them were +> deregistered (adverts retired on-chain, containers removed). `Qwen3.8-27B` +> was added in their place, reusing the retired kimi-code wallets. Configures +> mainnet supplier nodes that use **Hetzner Inference** +> (`https://inference.hetzner.com`) as their **compute backend** for bonded +> inference work commissioned on Vector. Config only — no code changes. --- @@ -15,19 +20,21 @@ upstream client (`supplier/src/openai.ts`) already speaks plain This is the same pattern as the DeepSeek-direct and OpenRouter suppliers, and the direct sibling of `docs/HUGGINGFACE_ROUTER_SETUP.md`. -One supplier per (model × capability) — 4 models, both the one-off +One supplier per (model × capability) — both the one-off `llm.text.generate.v1` and the multi-turn `llm.chat.v1` capability: | Supplier name | Model (on-chain + API param, verbatim) | Capability | Advert max_output_tokens | |---|---|---|---| -| `kimi-code` | `Kimi-K2.7-Code` | `llm.text.generate.v1` | 262144 | -| `kimi-code-chat` | `Kimi-K2.7-Code` | `llm.chat.v1` | 262144 | -| `glm` | `GLM-5.2-NVFP4` | `llm.text.generate.v1` | 512000 | -| `glm-chat` | `GLM-5.2-NVFP4` | `llm.chat.v1` | 512000 | -| `ds-flash-htz` | `DeepSeek-V4-Flash-0731` | `llm.text.generate.v1` | 512000 | -| `ds-flash-htz-chat` | `DeepSeek-V4-Flash-0731` | `llm.chat.v1` | 512000 | | `qwen35b` | `Qwen/Qwen3.6-35B-A3B-FP8` | `llm.text.generate.v1` | 262144 | | `qwen35b-chat` | `Qwen/Qwen3.6-35B-A3B-FP8` | `llm.chat.v1` | 262144 | +| `qwen38` | `Qwen3.8-27B` | `llm.text.generate.v1` | 262144 | +| `qwen38-chat` | `Qwen3.8-27B` | `llm.chat.v1` | 262144 | + +Deregistered 2026-08-21 (models dropped by Hetzner): `kimi-code`, +`kimi-code-chat` (`Kimi-K2.7-Code`), `glm`, `glm-chat` (`GLM-5.2-NVFP4`), +`ds-flash-htz`, `ds-flash-htz-chat` (`DeepSeek-V4-Flash-0731`). The qwen38 +pair reuses the kimi-code / kimi-code-chat wallets; the other four wallets +still hold funds and their env files remain on the host. Shared advert parameters: price **200000 lovelace (0.2 AP3X)** flat per job, bonds **1000000 lovelace (1 AP3X)** both sides, `max_processing_ms` **300000** @@ -36,18 +43,18 @@ for one-off / **1800000** for chat (the session spans the whole conversation). forwarded upstream (`OPENAI_MAX_TOKENS` unset), so the advert value only gates what buyers may request. -Names follow the brand-by-model convention; `ds-flash-htz` carries a `-htz` -suffix only because `deepseek-flash-*` was already taken by the OpenRouter -fleet serving `deepseek/deepseek-v4-flash`. +Names follow the brand-by-model convention; the retired `ds-flash-htz` +carried a `-htz` suffix only because `deepseek-flash-*` was already taken by +the OpenRouter fleet serving `deepseek/deepseek-v4-flash`. ## 2. Prerequisites 1. A Hetzner account with Inference access and an API key (usage-based billing to you as the node operator — the flat 0.2 AP3X job price is a business - choice, not cost-derived). One key is shared by all 8 suppliers; Hetzner + choice, not cost-derived). One key is shared by all suppliers; Hetzner rate limits apply to the aggregate. -2. Eight funded supplier wallets (50 AP3X each recommended; bonds are 1 AP3X - per in-flight job and returned on completion). +2. One funded supplier wallet per supplier (50 AP3X each recommended; bonds + are 1 AP3X per in-flight job and returned on completion). 3. The usual mainnet supplier deploy prerequisites (`deploy/README.md`). 4. **DNS**: one A record per supplier — `mp-suppliers-.vector.apexfusion.org` → `91.98.147.172`, **DNS-only/unproxied**. There is NO wildcard for @@ -58,24 +65,25 @@ fleet serving `deepseek/deepseek-v4-flash`. ## 3. Verify the backend before spending on-chain -The four model ids come from `GET https://inference.hetzner.com/api/v1/models` +The model ids come from `GET https://inference.hetzner.com/api/v1/models` +(this list changes — Hetzner retires models; re-check before any advert) and are sent **verbatim** as the upstream `model` param (the runtime uses `advert.model`). Before posting adverts, smoke-test each model: ```bash curl -sS -X POST https://inference.hetzner.com/api/v1/chat/completions \ -H "Authorization: Bearer $HETZNER_KEY" -H "Content-Type: application/json" \ - -d '{"model":"GLM-5.2-NVFP4","messages":[{"role":"user","content":"ping"}]}' \ + -d '{"model":"Qwen3.8-27B","messages":[{"role":"user","content":"ping"}]}' \ | jq '.choices[0].message.content' ``` `choices[0].message.content` must be a non-empty string with **no `max_tokens` sent** (matches runtime config) — the supplier throws `openai_malformed` otherwise and forfeits its 1 AP3X bond per failed job. For chat suppliers also -verify a `tools`/`tool_choice` round-trip. All four models passed both checks -on 2026-08-11. +verify a `tools`/`tool_choice` round-trip. The original four models passed +both checks on 2026-08-11; `Qwen3.8-27B` passed both on 2026-08-21. -## 4. Per-supplier bring-up (repeat ×8) +## 4. Per-supplier bring-up (repeat per supplier) ```bash # 1. wallet — prints privateKeyHex, publicKeyHex, pubKeyHash, address