fix(config): update model names to match LiteLLM host/name format

Replace ollama/ prefix with iguana/ and koala/ prefixes to match
actual model IDs exposed by LiteLLM on this cluster.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

config/models.yaml

@@ -1,25 +1,26 @@
 # Model selection — first entry per skill is used.
 # Override per-call by passing model in the MCP tool args.
+# Model names come from LiteLLM /v1/models (host/name format).
 
 default_chain:
-  - ollama/qwen3-coder-30b-tuned
+  - iguana/qwen3-coder-next
 
 skills:
   tdd:
     chain:
-      - ollama/qwen3-coder-30b-tuned
+      - koala/qwen3-coder-30b
   review:
     chain:
-      - ollama/devstral-tuned
+      - iguana/devstral
   debug:
     chain:
-      - ollama/deepseek-r1-tuned
+      - iguana/deepseek-r1-14b
   spec:
     chain:
-      - ollama/phi4
+      - koala/phi4-14b
   retrospective:
     chain:
-      - ollama/qwen3-coder-30b-tuned
+      - iguana/qwen3-coder-next
   trainer:
     chain:
-      - ollama/qwen3-coder-30b-tuned
+      - iguana/qwen3-coder-next