feat(litellm): front z.ai GLM cloud models through the gateway

Adds explicit gateway entries for the four z.ai GLM models (glm-5.1,
glm-5-turbo, glm-4.7, glm-4.5-air) routed to api.z.ai with Z_AI_API_KEY,
plus the compose env passthrough + .env.example doc. Explicit entries
win over the llama-swap wildcard (distinct IDs, no collision). Extends
the gateway's unified logging to cloud inference, not just local
vLLM/llama-swap.

Cost note: paid API — only gateway-keyed callers reach these, but calls
spend z.ai credits (documented in config + compose comments).

stacks/litellm/.env.example

@@ -30,6 +30,11 @@ POSTGRES_PASSWORD=
 # vllm stack's .env.
 VLLM_API_KEY=
 
+# Cloud-provider API keys fronted by the gateway (PAID — spend on use; only
+# gateway-keyed callers can reach them). z.ai GLM models
+# (glm-5.1 / glm-5-turbo / glm-4.7 / glm-4.5-air).
+Z_AI_API_KEY=
+
 # --- Langfuse-ready (leave blank for the lean first cut) ---
 # Fill these AND uncomment success/failure_callback in conf/config.yaml
 # to ship full traces to a Langfuse instance. That is the whole upgrade.