fix: disable prompt caching and responses API in litellm

- Add LITELLM_DROP_PARAMS environment variable
- Disable cache in litellm_settings
- Attempt to disable responses API endpoint
- Remove invalid supports_prompt_caching parameter

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

ai/compose.yaml

@@ -98,6 +98,7 @@ services:
       ANTHROPIC_API_KEY: ${ANTHROPIC_API_KEY}
       LITELLM_MASTER_KEY: ${AI_LITELLM_API_KEY}
       DATABASE_URL: postgresql://${AI_DB_USER}:${AI_DB_PASSWORD}@ai_postgres:5432/litellm
+      LITELLM_DROP_PARAMS: "true"
     volumes:
       - ./litellm-config.yaml:/app/litellm-config.yaml:ro
     command: ["--config", "/app/litellm-config.yaml", "--host", "0.0.0.0", "--port", "4000", "--detailed_debug", "--drop_params"]

ai/litellm-config.yaml

@@ -8,8 +8,6 @@ model_list:
     litellm_params:
       model: anthropic/claude-sonnet-4-5-20250929
       api_key: os.environ/ANTHROPIC_API_KEY
-      drop_params: true
-      supports_prompt_caching: false
 
   - model_name: claude-3-5-sonnet
     litellm_params:
@@ -29,6 +27,8 @@ model_list:
 litellm_settings:
   drop_params: true
   set_verbose: true
+  # Disable prompt caching features
+  cache: false
 
 router_settings:
   allowed_fails: 0
@@ -39,3 +39,5 @@ default_litellm_params:
 
 general_settings:
   disable_responses_id_security: true
+  # Explicitly disable responses API endpoint
+  disable_responses_api: true