Disable reasoning by default across clients

platform/hermes/config.yaml

@@ -59,10 +59,9 @@ agent:
   # checkpoint in a fresh turn instead of receiving an effectively unlimited
   # 500-step budget.
   max_turns: 64
-  # Keep enough deliberation for tool choice while avoiding the provider's
-  # unbounded `auto` reasoning mode on ordinary turns. Users can still raise it
-  # per session with /reasoning.
-  reasoning_effort: "low"
+  # Ordinary turns run without hidden reasoning. Users can enable it explicitly
+  # per session with /reasoning medium or /reasoning high when a task needs it.
+  reasoning_effort: "none"
   gateway_timeout: 3600
   session_stall_timeout: 600
   tool_loop_guardrails:

platform/hermes/install-profiles.sh

@@ -31,7 +31,7 @@ create_profile() {
   # tuning. Enforce them on old profiles as well as newly cloned profiles.
   docker exec "$HERMES_CONTAINER" hermes -p "$name" config set model.max_tokens "$max_tokens"
   docker exec "$HERMES_CONTAINER" hermes -p "$name" config set agent.max_turns 64
-  docker exec "$HERMES_CONTAINER" hermes -p "$name" config set agent.reasoning_effort low
+  docker exec "$HERMES_CONTAINER" hermes -p "$name" config set agent.reasoning_effort none
   docker exec "$HERMES_CONTAINER" hermes -p "$name" config set display.show_reasoning false
   docker exec "$HERMES_CONTAINER" hermes -p "$name" config set auxiliary.title_generation.enabled false
   docker exec "$HERMES_CONTAINER" hermes -p "$name" config set web.search_backend keenable