diff --git a/agent/compose.yaml b/agent/compose.yaml index ab68989d..3e074cc2 100644 --- a/agent/compose.yaml +++ b/agent/compose.yaml @@ -113,7 +113,7 @@ services: - no-new-privileges:true read_only: true volumes: - - /apps/litellm/config.yaml:/app/config.yaml:ro + - ./litellm/config.yaml:/app/config.yaml:ro tmpfs: - /app/cache - /app/migrations diff --git a/agent/litellm/config.yaml b/agent/litellm/config.yaml new file mode 100644 index 00000000..69462f00 --- /dev/null +++ b/agent/litellm/config.yaml @@ -0,0 +1,83 @@ +general_settings: + store_model_in_db: true + +litellm_settings: + drop_params: true + request_timeout: 60 + json_logs: true + +model_list: + - model_name: cerebras/gemma-4-31b + litellm_params: + model: cerebras/gemma-4-31b + + - model_name: google/gemini-flash-lite-latest + litellm_params: + model: gemini/gemini-flash-lite-latest + + - model_name: google/gemma-4-31b-it + litellm_params: + model: gemini/gemma-4-31b-it + + - model_name: groq/gpt-oss-120b + litellm_params: + model: groq/openai/gpt-oss-120b + + - model_name: nous/hy3:free + litellm_params: + model: openai/tencent/hy3:free + litellm_credential_name: nous + + - model_name: opencode-zen/deepseek-v4-flash-free + litellm_params: + model: openai/deepseek-v4-flash-free + litellm_credential_name: opencode_zen + + - model_name: opencode-zen/mimo-v2.5-free + litellm_params: + model: openai/mimo-v2.5-free + litellm_credential_name: opencode_zen + + - model_name: openrouter/free + litellm_params: + model: openrouter/openrouter/free + + - model_name: smart-router + litellm_params: + model: auto_router/complexity_router + complexity_router_config: + tiers: + SIMPLE: opencode-zen/deepseek-v4-flash-free + MEDIUM: opencode-zen/deepseek-v4-flash-free + COMPLEX: nous/hy3:free + REASONING: nous/hy3:free + adaptive: true + session_affinity: true + complexity_router_default_model: nous/hy3:free + +credential_list: + - credential_name: nous + credential_values: + api_key: os.environ/NOUS_API_KEY + api_base: https://inference-api.nousresearch.com/v1 + credential_info: {} + + - credential_name: opencode_zen + credential_values: + api_key: os.environ/OPENCODE_ZEN_API_KEY + api_base: https://opencode.ai/zen/v1 + credential_info: {} + + - credential_name: opencode_go + credential_values: + api_key: os.environ/OPENCODE_GO_API_KEY + api_base: https://opencode.ai/zen/go/v1 + credential_info: {} + +# guardrails: +# - guardrail_name: headroom +# litellm_params: +# guardrail: headroom +# mode: pre_call +# api_base: http://headroom:8787 +# default_on: true