add lite_llm support

config.yaml

@@ -0,0 +1,20 @@
+litellm_settings:
+  drop_params: true  # This strips 'thinking', etc. before sending to Copilot
+  
+model_list:
+  - model_name: github_copilot/gpt-4
+    litellm_params:
+      model: github_copilot/gpt-4
+  - model_name: github_copilot/claude-sonnet-4.6
+    litellm_params:
+      model: github_copilot/claude-sonnet-4.6
+  - model_name: github_copilot/gpt-5.1-codex
+    model_info:
+      mode: responses
+    litellm_params:
+      model: github_copilot/gpt-5.1-codex
+  - model_name: github_copilot/text-embedding-ada-002
+    model_info:
+      mode: embedding
+    litellm_params:
+      model: github_copilot/text-embedding-ada-002

start_litllm.sh

@@ -0,0 +1 @@
+litellm --config config.yaml