Add dedicated Hermes compression model

platform/hermes/config.yaml

@@ -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

platform/hermes/install-profiles.sh

@@ -35,6 +35,14 @@ create_profile() {
   docker exec "$HERMES_CONTAINER" hermes -p "$name" config set compression.target_ratio 0.35
   docker exec "$HERMES_CONTAINER" hermes -p "$name" config set compression.protect_last_n 12
   docker exec "$HERMES_CONTAINER" hermes -p "$name" config set compression.protect_first_n 0
+  docker exec "$HERMES_CONTAINER" hermes -p "$name" config set auxiliary.compression.provider openai-api
+  docker exec "$HERMES_CONTAINER" hermes -p "$name" config set auxiliary.compression.model qwen-compression
+  docker exec "$HERMES_CONTAINER" hermes -p "$name" config set auxiliary.compression.base_url http://192.168.1.212:8099/v1
+  docker exec "$HERMES_CONTAINER" hermes -p "$name" config set auxiliary.compression.api_key local
+  docker exec "$HERMES_CONTAINER" hermes -p "$name" config set auxiliary.compression.reasoning_effort none
+  docker exec "$HERMES_CONTAINER" hermes -p "$name" config set auxiliary.compression.extra_body \
+    '{"chat_template_kwargs":{"enable_thinking":false}}'
+  docker exec "$HERMES_CONTAINER" hermes -p "$name" config set auxiliary.compression.timeout 600
   docker exec "$HERMES_CONTAINER" hermes -p "$name" config set platform_toolsets.cli \
     '["web","terminal","file","skills","todo","memory","vision","tts"]'
   [[ $(docker exec "$HERMES_CONTAINER" hermes -p "$name" config get model.default) == "$model" ]] || \