Harden and demote experimental Hermes compressor

2026-08-26 01:40:38 +02:00
parent 99285fe81a
commit aaadc57c07
7 changed files with 52 additions and 40 deletions
@@ -86,7 +86,7 @@ compression:
  threshold: 0.82
  target_ratio: 0.35
  tail_mode: "lean"
-  protect_last_n: 12
+  protect_last_n: 20
  protect_first_n: 0
  proactive_prune_tokens: 50000
  proactive_prune_min_result_chars: 4000
@@ -99,16 +99,6 @@ auxiliary:
  # actual chat, so keep the original timestamp/session id instead.
  title_generation:
    enabled: false
-  compression:
-    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