我仅在使用模拟器/谷歌助手时才收到此错误。当我在DialogFlow中使用Slack集成或测试时,它可以完美运行。
我检查了question的DialogFlow中的设置,但这不是我的问题。我检查了此question,但是因为我在网络挂钩中使用了 python ,所以我不确定是否能为我解决它。
我正在执行以下操作:
首先,用户调用通过Webhook连接到我的python代码的我的任何一个意图。将此称为intent1
。
第二,我检查代码中对response1
的响应(intent1
)。
第三,我通过跟踪事件response1
将intent2
发送到另一个意图event2
。
之所以这样做只是出于兴趣,是因为我允许多种类型的对话流。第一个是常见问题解答,第二个是定向对话。
我发回的JSON是:
"followupEventInput":{
"name":"EventName",
"parameters":{
"speech": str(speech)
}
}
EventName
是event2
。
speech
是response1
我还尝试将其添加到JSON中,但没有任何改变:
,"payload": {"google":{"expectUserResponse": False}}
模拟器中的调试显示:
{
"response": "",
"expectUserResponse": false,
"conversationToken": "GidzaW11bG...",
"audioResponse": "//NExAASWK...",
"debugInfo": {
"assistantToAgentDebug": {
"curlCommand": "curl -v 'https://api.api.ai/api/integrations/google?token=2b0fcc112a9b40c48f7a7182a29f6b2f' -H 'Content-Type: application/json;charset=UTF-8' -H 'Google-Actions-API-Version: 2' -H 'Authorization: eyJhbGciOiJSUzI1NiIsImtpZCI6IjQxMjlkYjJlYTE4NjBkMmU4NzFlZTQ4NTA2Mjg3ZmIwNWIwNGNhM2YifQ.eyJhdWQiOiJkbmFmaXQtZmFxIiwiZXhwIjoxNTMwODU5MzIzLCJpc3MiOiJodHRwczovL2FjY291bnRzLmdvb2dsZS5jb20iLCJqdGkiOiJiNDcwZjdhODYyYWJiMzI0NjRjNGY5MmU4MTQ1ZWU5NTFlYTA1MWY5IiwiaWF0IjoxNTMwODU5MjAzLCJuYmYiOjE1MzA4NTg5MDN9.XMAmItiH9SEo1I24T5xEPvSfP7dPX21AYHvVqZZReayNoR396ZQ1JdHZiY9rwGfp49qSwn2ea9EDkNVCQ-PK8NIKdTdxG-L0HuhY7r8nEMfzO4PjJKU6bI-Ry1OwL3A90WGK0l8rwJpByHSfA1gTsS7PU983yyR51PCJFkVnd2KQfX1ZKPIqpcEzKkCvexh9mwOx8cH6iVYuBzmHctH1FRLqhzzRb9zcx3Qq2mDFB8cVbl8SluXLyV4hBeKSeFe-HnkWEzqE3zvgIbAZha2rAOMb2xx1ta_M86hmwET4woAB-hBlR77cyNZV49Y5GmFrF5DozvQWEw1GNoRxcZCLhA' -A 'Mozilla/5.0 (compatible; Google-Cloud-Functions/2.1; +http://www.google.com/bot.html)' -X POST -d '{\"user\":{\"userId\":\"ABwppHEpW9IVOkzk8egeV0A0NHO5Ug4wqLj3ney3hdwx_iPW4cMeayYws8m-fzoFiYksk7JsnDmi-g\",\"locale\":\"en-US\",\"lastSeen\":\"2018-07-05T15:54:50Z\"},\"conversation\":{\"conversationId\":\"1530859188209\",\"type\":\"ACTIVE\",\"conversationToken\":\"[]\"},\"inputs\":[{\"intent\":\"actions.intent.TEXT\",\"rawInputs\":[{\"inputType\":\"KEYBOARD\",\"query\":\"what are the best recipes for oranges\"}],\"arguments\":[{\"name\":\"text\",\"rawText\":\"what are the best recipes for oranges\",\"textValue\":\"what are the best recipes for oranges\"}]}],\"surface\":{\"capabilities\":[{\"name\":\"actions.capability.MEDIA_RESPONSE_AUDIO\"},{\"name\":\"actions.capability.WEB_BROWSER\"},{\"name\":\"actions.capability.AUDIO_OUTPUT\"},{\"name\":\"actions.capability.SCREEN_OUTPUT\"}]},\"isInSandbox\":true,\"availableSurfaces\":[{\"capabilities\":[{\"name\":\"actions.capability.WEB_BROWSER\"},{\"name\":\"actions.capability.AUDIO_OUTPUT\"},{\"name\":\"actions.capability.SCREEN_OUTPUT\"}]}],\"requestType\":\"SIMULATOR\"}'",
"assistantToAgentJson": "{\"user\":{\"userId\":\"ABwppHEpW9IVOkzk8egeV0A0NHO5Ug4wqLj3ney3hdwx_iPW4cMeayYws8m-fzoFiYksk7JsnDmi-g\",\"locale\":\"en-US\",\"lastSeen\":\"2018-07-05T15:54:50Z\"},\"conversation\":{\"conversationId\":\"1530859188209\",\"type\":\"ACTIVE\",\"conversationToken\":\"[]\"},\"inputs\":[{\"intent\":\"actions.intent.TEXT\",\"rawInputs\":[{\"inputType\":\"KEYBOARD\",\"query\":\"what are the best recipes for oranges\"}],\"arguments\":[{\"name\":\"text\",\"rawText\":\"what are the best recipes for oranges\",\"textValue\":\"what are the best recipes for oranges\"}]}],\"surface\":{\"capabilities\":[{\"name\":\"actions.capability.MEDIA_RESPONSE_AUDIO\"},{\"name\":\"actions.capability.WEB_BROWSER\"},{\"name\":\"actions.capability.AUDIO_OUTPUT\"},{\"name\":\"actions.capability.SCREEN_OUTPUT\"}]},\"isInSandbox\":true,\"availableSurfaces\":[{\"capabilities\":[{\"name\":\"actions.capability.WEB_BROWSER\"},{\"name\":\"actions.capability.AUDIO_OUTPUT\"},{\"name\":\"actions.capability.SCREEN_OUTPUT\"}]}],\"requestType\":\"SIMULATOR\"}"
},
"agentToAssistantDebug": {
"agentToAssistantJson": "{\n \"responseMetadata\": {\n \"status\": {\n \"code\": 10,\n \"message\": \"Failed to parse Dialogflow response into AppResponse because of empty speech response\",\n \"details\": [{\n \"@type\": \"type.googleapis.com/google.protobuf.Value\",\n \"value\": \"{\\\"id\\\":\\\"63a2647e-43fc-4c36-9067-5c48b51626bb\\\",\\\"timestamp\\\":\\\"2018-07-06T06:40:04.014Z\\\",\\\"lang\\\":\\\"en-us\\\",\\\"result\\\":{},\\\"status\\\":{\\\"code\\\":200,\\\"errorType\\\":\\\"success\\\"},\\\"sessionId\\\":\\\"1530859188209\\\"}\"\n }]\n }\n }\n}"
},
"sharedDebugInfoList": [
{
"name": "ResponseValidation",
"debugInfo": "",
"subDebugEntryList": [
{
"name": "MalformedResponse",
"debugInfo": "'final_response' must be set.",
"subDebugEntryList": []
}
]
}
]
},
"visualResponse": {
"visualElementsList": [],
"suggestionsList": [],
"agentLogoUrl": ""
},
"clientError": 0,
"is3pResponse": 1
}
答案 0 :(得分:2)
agentToAssistantJson
字段的值包括消息“由于语音响应空而无法将Dialogflow响应解析为AppResponse”。正如它所暗示的那样,无论您发送的回复是什么,都缺少语音信息。
您没有指定Event2在做什么,它在发回什么东西或使用参数(如果有的话)在做什么,但是可能的问题是它没有发回任何东西。仅将语音作为参数并不起作用-参数只是信息,而不是答复。
尽管后续事件有一些用途,但大多数情况下它们并不是您真正想要的。如果您想用履行中的消息来答复-只需用消息来答复。