Add kimi-agent: kimi-code CLI wrapped as a LiteLLM model

Runs the kimi-code coding agent in its own container, exposed as an
OpenAI-compatible model ("kimi-agent") that LiteLLM/Open WebUI can call
directly. Backed by the user's own Kimi/Moonshot subscription via
`kimi login`, not the pay-per-token API. Mount is scoped to a dedicated
~/kimi-workspace directory rather than the full home dir.

openai/docker-compose.yml

@@ -32,6 +32,14 @@ services:
       - langfuse
     restart: always
 
+  kimi-agent:
+    build: ./kimi-agent
+    container_name: kimi-agent
+    volumes:
+      - /home/alvis/kimi-workspace:/workspace
+      - kimi-agent-home:/root/.kimi-code
+    restart: unless-stopped
+
   langfuse-db:
     image: postgres:16-alpine
     container_name: langfuse-db
@@ -112,3 +120,6 @@ services:
     extra_hosts:
       - "host.docker.internal:host-gateway"
     restart: unless-stopped
+
+volumes:
+  kimi-agent-home: