From 84badc36eabd2b6c241813e654696ea844358176 Mon Sep 17 00:00:00 2001 From: Bryant Date: Wed, 26 Mar 2025 18:31:30 +1100 Subject: [PATCH 1/5] update --- fern/calls/call-ended-reason.mdx | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fern/calls/call-ended-reason.mdx b/fern/calls/call-ended-reason.mdx index ae20ba440..5f2873342 100644 --- a/fern/calls/call-ended-reason.mdx +++ b/fern/calls/call-ended-reason.mdx @@ -30,8 +30,8 @@ Object](/api-reference/calls/get-call)). These relate to issues within the AI processing pipeline or the Large Language Models (LLMs) used for understanding and generating text: -- **pipeline-error-\***: Various error codes indicate specific failures within the processing pipeline, such as function execution, LLM responses, or external service integration. Examples include OpenAI, Azure OpenAI, Together AI, and several other LLMs or voice providers. -- **pipeline-error-first-message-failed:** The system failed to deliver the first message. This issue usually occurs when you add your own provider key in the voice section. It may be due to exceeding your subscription or quota limit. +- **call.in-progress.error-vapifault-\***: Various error codes indicate specific failures within the processing pipeline, such as function execution, LLM responses, or external service integration. Examples include OpenAI, Azure OpenAI, Together AI, and several other LLMs or voice providers. +- **pipeline-error-\***: Similar to **call.in-progress.error-vapifault-\***. However, these error codes are surfaced when you are using your own provider keys. - **pipeline-no-available-llm-model**: No suitable LLM was available to process the request. #### **Phone Calls and Connectivity** From 585d1d49e57d019e58895ad5f2ab45c156efe785 Mon Sep 17 00:00:00 2001 From: Bryant Date: Fri, 28 Mar 2025 19:13:48 +1100 Subject: [PATCH 2/5] update --- fern/calls/call-ended-reason.mdx | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fern/calls/call-ended-reason.mdx b/fern/calls/call-ended-reason.mdx index 5f2873342..2fbc7e484 100644 --- a/fern/calls/call-ended-reason.mdx +++ b/fern/calls/call-ended-reason.mdx @@ -4,7 +4,6 @@ subtitle: A guide to understanding all call "Ended Reason" types & errors. slug: calls/call-ended-reason --- - This guide will discuss all possible `endedReason`s for a call. You can find these under the **"Ended Reason"** section of your [call @@ -31,6 +30,7 @@ Object](/api-reference/calls/get-call)). These relate to issues within the AI processing pipeline or the Large Language Models (LLMs) used for understanding and generating text: - **call.in-progress.error-vapifault-\***: Various error codes indicate specific failures within the processing pipeline, such as function execution, LLM responses, or external service integration. Examples include OpenAI, Azure OpenAI, Together AI, and several other LLMs or voice providers. +- **call.in-progress.error-providerfault-\***: Similar to **call.in-progress.error-vapifault-\***. However, these error codes are surfaced when Vapi receives an error that has occured on the provider's side. Examples include internal server errors, or service unavailability. - **pipeline-error-\***: Similar to **call.in-progress.error-vapifault-\***. However, these error codes are surfaced when you are using your own provider keys. - **pipeline-no-available-llm-model**: No suitable LLM was available to process the request. @@ -45,6 +45,7 @@ These relate to issues within the AI processing pipeline or the Large Language M - **vonage-disconnected**: The call was disconnected by Vonage, another call management service. - **vonage-failed-to-connect-call**: Vonage failed to establish the call connection. - **vonage-rejected**: The call was rejected by Vonage due to an issue or configuration problem. +- **sip-telephony-provider-failed-to-connect-call**: The SIP telephony provider failed to establish the call connection. #### **Other Reasons** From 56d4275d848e2127adb9b5a3e6dca9ab6aa94ab6 Mon Sep 17 00:00:00 2001 From: Bryant Date: Sat, 29 Mar 2025 14:52:18 +1100 Subject: [PATCH 3/5] assistant-ended-call-after-message-spoken --- fern/calls/call-ended-reason.mdx | 1 + 1 file changed, 1 insertion(+) diff --git a/fern/calls/call-ended-reason.mdx b/fern/calls/call-ended-reason.mdx index 2fbc7e484..3e26b2644 100644 --- a/fern/calls/call-ended-reason.mdx +++ b/fern/calls/call-ended-reason.mdx @@ -13,6 +13,7 @@ Object](/api-reference/calls/get-call)). #### **Assistant-Related** - **assistant-ended-call**: The assistant intentionally ended the call based on the user's response. +- **assistant-ended-call-after-message-spoken**: The assistant intentionally ended the call after speaking a pre-defined message. - **assistant-error**: This general error occurs within the assistant's logic or processing due to bugs, misconfigurations, or unexpected inputs. - **assistant-forwarded-call**: The assistant successfully transferred the call to another number or service. - **assistant-join-timed-out**: The assistant failed to join the call within the expected timeframe. From 12f065ced6174aab6f67a146cf441684a0880acf Mon Sep 17 00:00:00 2001 From: Bryant Date: Sat, 29 Mar 2025 14:59:19 +1100 Subject: [PATCH 4/5] update --- fern/calls/call-ended-reason.mdx | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fern/calls/call-ended-reason.mdx b/fern/calls/call-ended-reason.mdx index 3e26b2644..354072e07 100644 --- a/fern/calls/call-ended-reason.mdx +++ b/fern/calls/call-ended-reason.mdx @@ -41,12 +41,13 @@ These relate to issues within the AI processing pipeline or the Large Language M - **customer-ended-call**: The customer(end human user) ended the call for both inbound and outbound calls. - **customer-did-not-answer**: The customer didn't answer the call. If you're looking to build a usecase where you need the bot to talk to automated IVRs, set `assistant.voicemailDetectionEnabled=false`. - **customer-did-not-give-microphone-permission**: The user didn't grant the necessary microphone access for the call. +- **assistant-did-not-receive-customer-audio**: Similar to **customer-did-not-give-microphone-permission**, but more generalized to situations where no customer audio was received. - **phone-call-provider-closed-websocket**: The connection with the call provider was unexpectedly closed. - **twilio-failed-to-connect-call**: The Twilio service, responsible for managing calls, failed to establish a connection. - **vonage-disconnected**: The call was disconnected by Vonage, another call management service. - **vonage-failed-to-connect-call**: Vonage failed to establish the call connection. - **vonage-rejected**: The call was rejected by Vonage due to an issue or configuration problem. -- **sip-telephony-provider-failed-to-connect-call**: The SIP telephony provider failed to establish the call connection. +- **sip-telephony-provider-failed-to-connect-call**: The SIP telephony provider failed to establish the call connection. Previously **sip-gateway-failed-to-connect-call**. #### **Other Reasons** From 23b7872d80777c5673e473088bfee418a121212d Mon Sep 17 00:00:00 2001 From: Bryant Date: Sat, 29 Mar 2025 14:59:57 +1100 Subject: [PATCH 5/5] update --- fern/calls/call-ended-reason.mdx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fern/calls/call-ended-reason.mdx b/fern/calls/call-ended-reason.mdx index 354072e07..e4524765f 100644 --- a/fern/calls/call-ended-reason.mdx +++ b/fern/calls/call-ended-reason.mdx @@ -33,7 +33,7 @@ These relate to issues within the AI processing pipeline or the Large Language M - **call.in-progress.error-vapifault-\***: Various error codes indicate specific failures within the processing pipeline, such as function execution, LLM responses, or external service integration. Examples include OpenAI, Azure OpenAI, Together AI, and several other LLMs or voice providers. - **call.in-progress.error-providerfault-\***: Similar to **call.in-progress.error-vapifault-\***. However, these error codes are surfaced when Vapi receives an error that has occured on the provider's side. Examples include internal server errors, or service unavailability. - **pipeline-error-\***: Similar to **call.in-progress.error-vapifault-\***. However, these error codes are surfaced when you are using your own provider keys. -- **pipeline-no-available-llm-model**: No suitable LLM was available to process the request. +- **pipeline-no-available-llm-model**: No suitable LLM was available to process the request. Previously **pipeline-no-available-model**. #### **Phone Calls and Connectivity**