feat(gateway-chat): persistent static-serve stack for the model-smoking web chat

Stands up tools/gateway-chat.html as a permanent URL on ana-docker (http://10.250.50.70:8091)
via a tiny nginx:alpine static container (no GPU, no DB). conf/index.html is a deployed
mirror of tools/gateway-chat.html (re-sync one-liner in README). Homepage tile + tnet per
convention. The enhanced tool (auto-discovers /v1/models, system prompts, streaming +
reasoning, image upload for vision) is now always-on for smoking new gateway models.
This commit is contained in:
vh
2026-06-19 12:32:51 -07:00
parent ef45f6d826
commit 740bcae45d
4 changed files with 291 additions and 0 deletions
+37
View File
@@ -0,0 +1,37 @@
# gateway-chat — persistent static-serve of the zero-dep web chat for SMOKING models on
# the LiteLLM gateway (auto-discovers /v1/models, system prompts, streaming +
# reasoning_content, image upload for vision models). Tiny nginx:alpine serving ONE file;
# no GPU, no DB. The served file is conf/index.html — a deployed mirror of the repo's
# tools/gateway-chat.html (re-sync on edit; see README).
#
# Tunables in .env.
name: gateway-chat
services:
gateway-chat:
image: ${GATEWAYCHAT_IMAGE:-nginx:alpine}
container_name: ${GATEWAYCHAT_CONTAINER_NAME:-gateway-chat}
restart: unless-stopped
ports:
- "${GATEWAYCHAT_PORT:-8091}:80"
volumes:
- /opt/docker/conf/gateway-chat/index.html:/usr/share/nginx/html/index.html:ro
healthcheck:
test: ["CMD-SHELL", "wget -qO /dev/null http://localhost/ || exit 1"]
interval: 30s
timeout: 5s
retries: 3
networks:
- tnet
labels:
- homepage.group=AI Systems
- homepage.name=Gateway Chat
- homepage.icon=mdi-chat-processing
- homepage.description=Light web chat for smoking LiteLLM gateway models (auto-discovery, system prompts, vision)
- homepage.href=http://10.250.50.70:${GATEWAYCHAT_PORT:-8091}
networks:
tnet:
name: traefik-net
external: true