[gemini] feat: Add Claude API fallback tier to cascade.py (#980) (#1119)

Co-authored-by: Google Gemini <gemini@hermes.local>
Co-committed-by: Google Gemini <gemini@hermes.local>

config/providers.yaml

@@ -22,6 +22,7 @@ providers:
     type: ollama
     enabled: true
     priority: 1
+    tier: local
     url: "http://localhost:11434"
     models:
       # Text + Tools models
@@ -97,6 +98,7 @@ providers:
     type: vllm_mlx
     enabled: false  # Enable when vllm-mlx server is running
     priority: 2
+    tier: local
     base_url: "http://localhost:8000/v1"
     models:
       - name: Qwen/Qwen2.5-14B-Instruct-MLX
@@ -112,6 +114,7 @@ providers:
     type: openai
     enabled: false  # Enable by setting OPENAI_API_KEY
     priority: 3
+    tier: standard_cloud
     api_key: "${OPENAI_API_KEY}"  # Loaded from environment
     base_url: null  # Use default OpenAI endpoint
     models:
@@ -128,6 +131,7 @@ providers:
     type: anthropic
     enabled: false  # Enable by setting ANTHROPIC_API_KEY
     priority: 4
+    tier: frontier
     api_key: "${ANTHROPIC_API_KEY}"
     models:
       - name: claude-3-haiku-20240307