litellm: route all homelab LLM load to Anvil/Ollama by default

Per-model api_base/api_key overrides in the template (default stays
Meridian's local port). All standard aliases (claude-*, gpt-*) now point
at Anvil's Ollama (mini/haiku-class -> llama3.1:8b, rest -> llama3.3:70b).
Claude/Max reachable only via new *-max escape-hatch aliases.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

roles/litellm/templates/litellm-config.yaml.j2

@@ -1,16 +1,18 @@
 # {{ ansible_managed }}
 #
-# LiteLLM proxy config. Routes OpenAI-shaped requests to Meridian's
-# /v1/messages (Anthropic format). Meridian (same host, :3456) ignores the
-# upstream API key, so we pass a placeholder.
+# LiteLLM proxy config. Routes OpenAI-shaped requests to backends:
+#   - Claude models → Meridian's /v1/messages (same host, :3456), which
+#     ignores the upstream API key (placeholder passed below).
+#   - Local models  → Anvil's Ollama (openai/ provider, OpenAI-compatible
+#     endpoint at http://192.168.1.150:11434). Set per-model api_base in vars.
 
 model_list:
 {% for m in litellm_models %}
   - model_name: {{ m.name }}
     litellm_params:
       model: {{ m.backend }}
-      api_base: http://127.0.0.1:{{ meridian_port }}
-      api_key: placeholder-meridian-ignores-this
+      api_base: {{ m.api_base | default('http://127.0.0.1:' ~ meridian_port) }}
+      api_key: {{ m.api_key | default('placeholder-meridian-ignores-this') }}
 {% endfor %}
 
 general_settings: