LiteLLM: drop unsupported params instead of erroring (fixes Hermes routing)

Hermes sends provider-agnostic params like reasoning_effort that OpenRouter's
auto model doesn't accept, causing a 400 on every request until this was
set. Also documents (in a follow-up, not this commit) that getting Hermes to
actually use this gateway needed live 'hermes config set' calls on the
running container (providers.litellm.{api,api_key}, model.provider=litellm,
model.default=auto) — that state lives in the hermes-data volume, not git,
so it isn't reproduced automatically by a fresh deploy. See README.

litellm-config.yaml

@@ -24,6 +24,11 @@ model_list:
     litellm_params:
       model: anthropic/claude-sonnet-5
 
+litellm_settings:
+  # Callers (Hermes included) send provider-specific params like reasoning_effort that
+  # not every routed model/provider accepts — drop unsupported ones instead of erroring.
+  drop_params: true
+
 general_settings:
   forward_client_headers_to_llm_api: true
   master_key: os.environ/LITELLM_MASTER_KEY