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)

.env.example

@@ -19,21 +19,25 @@ DEEPSEEK_API_KEY="your_deepseek_key_here"
 NVIDIA_API_KEY="your_nvidia_nim_key_here"
 
 # Cascade order (first available provider wins)
-PROVIDER_CASCADE="openrouter,openai,anthropic,groq,gemini-api,ollama"
+# Default (if unset): openrouter,openai,anthropic,groq,gemini-api,deepseek,nvidia
+PROVIDER_CASCADE="openrouter,openai,anthropic,groq,gemini,deepseek"
 
 # =============================================================================
-# LOCAL LLM (Ollama - runs offline)
+# LOCAL LLM (generic OpenAI-compatible endpoint)
 # =============================================================================
+# Set this to the base URL of any local OpenAI-compatible server
+# (llama.cpp, Ollama, vLLM, LM Studio, etc.)
+LOCAL_BASE_URL="localhost:8080"
+
+# Ollama host (legacy: falls back to LOCAL_BASE_URL if not set)
 OLLAMA_HOST="localhost:11434"
 
-# llama.cpp backend (for local GGUF models)
-LLAMA_HOST="localhost:8080"
-
 # =============================================================================
 # VECTOR EMBEDDINGS (semantic search)
 # =============================================================================
-EMBEDDING_PROVIDER="ollama"  # "ollama" or "llama.cpp"
+EMBEDDING_PROVIDER="hashing"  # "hashing" (local, no deps), "local", or "openai"
 EMBEDDING_MODEL="nomic-embed-text"  # model name for embeddings
+EMBEDDING_BASE_URL="https://api.openai.com/v1"  # for :openai provider
 
 # =============================================================================
 # MESSAGING GATEWAYS (optional)