rename gateway-* → system-model-* + gateway-messaging, de-ollama, add system-model-explorer

- Rename gateway-provider → system-model-provider (generic :local provider, no hardcoded ollama)
- Rename gateway-llm → system-model (model-request dispatcher)
- Rename system-embedding-gateway → system-model-embedding
- Rename gateway-manager → gateway-messaging (public api renamed to messaging-*)
- Add system-model-explorer (model discovery via OpenRouter API, cached, per-slot recommendations)
- Fix skill loader export: replace prefix-matching with fbound/boundp-based export (20 skills now export)
- Add model-router to skill-loader exclusion list (loaded via CLI)
- De-ollama: remove hardcoded assumed-available patterns from provider pipeline
- Default cascade: cloud-only (openrouter, openai, groq, gemini, deepseek, nvidia, anthropic)
- Env example: add LOCAL_BASE_URL, fix cascade order
- All org files updated with architectural prose (literate programming)

org/system-model-router.org

@@ -171,7 +171,7 @@ Returns model name or :skip."
                           (t *model-cascade-chat*)))
                (entry (model-cascade-find
                        (or cascade '((:ollama . "qwen2.5:14b"))) backend)))
-          (if entry (cdr entry) :skip)))))
+          (if entry (cdr entry) nil)))))
 #+end_src
 
 ** Initialization