fix: separate Anthropic output and context limits
Direct Anthropic connections reused the configured context window as max_tokens, which could impose an unintended output value or send a provider-invalid request. Anthropic connections now expose an independent per-response maximum output setting, defaulting to 32K for the protocol-required field, while OpenAI direct requests remain without an added output token cap and direct tool rounds remain unmetered. Release note: Anthropic 直连模型现在可单独配置单次最大输出,不再复用上下文窗口;OpenAI 直连请求和工具调用轮次不增加额外配额。
This commit is contained in:
@@ -28,8 +28,8 @@ Linux x64 和 Linux arm64。
|
||||
导航及重定向仍经过 DNS 解析和目标地址固定。
|
||||
- 已实现回环过滤代理、下载和文件选择器阻止、权限拒绝、会话取消、
|
||||
空闲回收和应用退出清理。
|
||||
- 直连模型工具循环已提高到适合浏览器任务的有界上限,并包含重复调用和
|
||||
无进展保护。
|
||||
- 直连模型工具循环不设置工具次数或模型轮次配额;取消、请求超时、工具结果大小和
|
||||
累计输出边界继续防止失控执行。
|
||||
|
||||
### MCP
|
||||
|
||||
|
||||
Reference in New Issue
Block a user