Add dedicated Hermes compression model

2026-08-26 00:45:32 +02:00
parent e872829b11
commit 43d9903d13
8 changed files with 120 additions and 3 deletions
@@ -100,9 +100,15 @@ auxiliary:
  title_generation:
    enabled: false
  compression:
-    provider: "main"
-    model: ""
+    provider: "openai-api"
+    model: "qwen-compression"
+    base_url: "http://192.168.1.212:8099/v1"
+    api_key: "local"
    reasoning_effort: "none"
+    extra_body:
+      chat_template_kwargs:
+        enable_thinking: false
+    timeout: 600

 # The full hermes-cli preset injects several large, overlapping schemas on
 # every turn. Athena already exposes browsing, orchestration and host services