澄潭
澄潭
> Should this model mapping config be set in a provider level or route level? provider&route level, like this match config: ingress: - ai-route-dashscope.internal service: - llm-dashscope.internal.dns
Yes, can we change the current target model input box to a "Model Mapping" button? After clicking, the key-value pairs can be configured in a pop-up window.
@lexburner 可以支持的，你看上面的配置就是可以实现匹配不同的服务，然后针对不同模型做不同映射 --- @lexburner can support it. You see, the above configuration can be used to match different services, and then different mappings are made for different models
It is suggested to add this goal: enhance the security of doAfterVmCallActions, as the current mechanism may lead to unexpected calls on the Host side, resulting in envoy crash(refer to...
cc @WeixinX
OnHttpStreamingBody 的流式机制目前没有支持pause/resume，如果需要等待处理完再return，目前只能用非流式的方式
https://github.com/alibaba/higress/blob/9e6bd6d2cc9a5445d6a44731c5a33579b882a938/plugins/wasm-go/pkg/wrapper/plugin_wrapper.go#L566-L573 关键在这段地方，需要支持状态判断，然后根据特定状态返回types.ActionPause
这块机制 @rinfx 在实现中了
看抓包是网关关闭了连接之后，客户端还再发消息，导致RST 你到higress容器里执行一下 curl localhost:15000/logging?level=trace -X POST 然后再复现一下问题，再看日志中有无相关线索。
We will support this feature in July.