Add local Ollama as an AI Hub provider for claude-code

Ollama v0.14+ speaks the Anthropic Messages API natively, so the
registry drives it with a fixed 'ollama' token and runtime-listed
models: static_token skips secret storage everywhere keys resolve,
models_dynamic defers model validation to the live /api/tags list,
and the setup wizard installs the right GPU variant and starts the
service before listing local models. Doctor stops treating the
endpoint port as part of the hostname.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_019hLK3wsDuKVAC37GgDqg6H

cn/registry/ai-compatibility.json

@@ -21,6 +21,11 @@
         "level": "stable",
         "doc": "https://platform.minimax.io/docs/token-plan/claude-code",
         "adapter": true
+      },
+      "ollama": {
+        "level": "stable",
+        "doc": "https://docs.ollama.com/api/anthropic-compatibility",
+        "adapter": true
       }
     },
     "codex": {