Set Hermes local model reasoning levels

dankclaw/hermes/config.yaml.example

@@ -40,6 +40,11 @@ auxiliary:
   profile_describer: {provider: custom, model: frank-default-small, base_url: http://192.168.0.235:7770/v1}
   curator: {provider: custom, model: frank-default-small, base_url: http://192.168.0.235:7770/v1}
 
+agent:
+  reasoning_overrides:
+    frank-default-large: medium
+    frank-default-small: medium
+
 dashboard:
   # basic_auth intentionally omitted; its password_hash remains live-only.
   font: atkinson-hyperlegible

docs/Dankclaw/Hermes.md

@@ -27,6 +27,9 @@ both containers. The tracked, sanitized configuration baseline is
 - The configured `dankserver-small` provider reaches `http://192.168.0.235:7770/v1`
   and exposes the `frank-default-small` alias. It is a named provider, so it can
   coexist with the existing `custom` provider for the large model.
+- Both local aliases have `agent.reasoning_overrides` set to `medium`. The
+  llama.cpp endpoints reject unsupported values such as `high` and `none`; the
+  active large endpoint advertises only `low`, `medium`, and `xhigh`.
 - The live `config.yaml` contains secrets and user state and is not committed;
   the tracked example is the sanitized backup of its non-secret settings.