docs: document sampling passthrough and the empty thinking profiles

2026-07-31 21:41:34 -04:00
parent a5ebf72f17
commit 2958dc8231
5 changed files with 45 additions and 5 deletions
@@ -18,6 +18,10 @@ LLM__QWEN__1__TIMEOUT_S=120
 # LLM__QWEN__1__ENABLE_THINKING=true     # 三态: 缺省=不注入 / true=注入开启 / false=注入关闭
 # LLM__QWEN__1__MISSING_DONE=retry       # SSE 缺 [DONE]: retry(默认) | salvage
 # LLM__QWEN__1__TRUST_ENV=true           # false = 绕过本地代理(LAN 直连)
+# LLM__QWEN__1__EXTRA_BODY={"temperature":0}   # 本源恒定的采样参数(JSON 对象串)
+#   并入请求体,优先级低于 chat(overlay=...);受控实验固定解码用它,免得漏传
+#   禁用键 model/messages/stream/stream_options(会击穿治理),配了直接报错
+#   OCR/EMBED scope 不消费该键: 配了会被忽略并 warning(见 issue #4 决策 G)

 # ══ scope 级全局闸(跨源合计;0/缺省 = 不启用)══
 # LLM__GLOBAL__MAX_CONCURRENCY=8