Use minimal reasoning for responsive Hermes chats

2026-08-25 18:26:31 +02:00
parent a9bd832c71
commit 57afdd4f15
3 changed files with 3 additions and 3 deletions
@@ -59,7 +59,7 @@ agent:
  # 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"
+  reasoning_effort: "minimal"
  gateway_timeout: 3600
  session_stall_timeout: 600
  tool_loop_guardrails:
@@ -28,7 +28,7 @@ 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 8192
  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 minimal
  docker exec "$HERMES_CONTAINER" hermes -p "$name" config set auxiliary.title_generation.enabled false
  docker exec "$HERMES_CONTAINER" hermes -p "$name" config set compression.threshold_tokens 60000
  docker exec "$HERMES_CONTAINER" hermes -p "$name" config set compression.protect_last_n 8