feat(mana-llm): add Google Gemini fallback provider with auto-routing

Add Google Gemini as a fallback provider that activates automatically
when Ollama is overloaded or unavailable, ensuring LLM requests always
succeed even under load.

New provider (src/providers/google.py):
- Full LLMProvider implementation using google-genai SDK
- Chat completions (streaming + non-streaming)
- Vision/multimodal support (base64 images)
- Embeddings via text-embedding-004
- Model mapping: Ollama models → Gemini equivalents
  (gemma3:4b → gemini-2.0-flash, llava:7b → gemini-2.0-flash, etc.)

Auto-fallback routing (src/providers/router.py):
- Concurrent request tracking for Ollama (OLLAMA_MAX_CONCURRENT=3)
- When Ollama concurrent > max: route to Google automatically
- When Ollama fails: retry on Google with model mapping
- Health check caching (5s TTL) to avoid hammering Ollama
- Non-Ollama providers (openrouter, groq, together) are never fallback-routed
- Fallback info included in /health endpoint response

New config (src/config.py):
- GOOGLE_API_KEY: enables Google provider
- GOOGLE_DEFAULT_MODEL: default gemini-2.0-flash
- AUTO_FALLBACK_ENABLED: toggle fallback (default: true)
- OLLAMA_MAX_CONCURRENT: concurrent request threshold (default: 3)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

docker-compose.macmini.yml

@@ -1779,6 +1779,10 @@ services:
       OPENROUTER_API_KEY: ${OPENROUTER_API_KEY:-}
       GROQ_API_KEY: ${GROQ_API_KEY:-}
       TOGETHER_API_KEY: ${TOGETHER_API_KEY:-}
+      GOOGLE_API_KEY: ${GOOGLE_API_KEY:-}
+      GOOGLE_DEFAULT_MODEL: gemini-2.0-flash
+      AUTO_FALLBACK_ENABLED: "true"
+      OLLAMA_MAX_CONCURRENT: 3
       CORS_ORIGINS: https://playground.mana.how,https://mana.how,https://chat.mana.how
     extra_hosts:
       - "host.docker.internal:host-gateway"