feat: InferenceEngine chat/chat_structured 全流程 + 文档补丁(补丁1/2/3)
This commit is contained in:
@@ -133,7 +133,7 @@ models:
|
||||
timeout_sec: 90
|
||||
|
||||
llm_calls:
|
||||
token_estimation: tiktoken # tiktoken | approximate
|
||||
token_estimation: tiktoken # tiktoken | approximate;tiktoken 缺失自动回落 approximate(内置估算器)
|
||||
max_context_tokens: 32000 # 上下文窗口上限
|
||||
truncation_policy: # 超限裁剪策略(runtime §2.6)
|
||||
priority:
|
||||
|
||||
Reference in New Issue
Block a user