Skip to content

Commit b81aef6

Browse files
quantstruct-botquantstruct-bot
committed
Add changelog
1 parent a10322a commit b81aef6

18 files changed

+85
-0
lines changed

‎fern/changelog/2025-03-28.mdx‎

Lines changed: 15 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,15 @@
1+
1. **New Slack and Google Calendar Tools Added**: You can now use the built-in [Slack tool](https://docs.vapi.ai/tools/slack) to send messages and use the [Google Calendar tool](https://docs.vapi.ai/tools/google-calendar) to check calendar availability directly from your assistant, with full CRUD operations available via the [`/tool` API endpoint](https://docs.vapi.ai/api-reference/tools/list). You can authenticate the [Slack tool](https://dashboard.vapi.ai/keys#:~:text=Slack) and the [Google Calendar tool](https://dashboard.vapi.ai/keys#:~:text=Google%20Calendar) using OAuth2 from the [Vapi provider keys page](https://dashboard.vapi.ai/keys).
2+
3+
<Frame caption="Slack Tool">
4+
<img src="../static/images/changelog/slack-tool.png" alt="Slack Tool" />
5+
</Frame>
6+
7+
<Frame caption="Google Calendar Tool">
8+
<img src="../static/images/changelog/google-calendar-tool.png" alt="Google Calendar Tool" />
9+
</Frame>
10+
11+
2. **Select LLM Model in Workflow Nodes**: You can now select and update which LLM model you want to use within workflow nodes, allowing more precise control over the assistant's behavior in different workflow nodes and easier configuration updates.
12+
13+
4. **Enhanced Call Monitoring and Reporting**: We've improved call monitoring with conversation turn tracking, millisecond-precision timestamps, and provided more detailed call end reasons. These enhancements make it easier to track conversation flow, perform precise time calculations, and diagnose specific call termination issues like server overloads or database errors.
14+
15+
5. **Enable Background Denoising**: You can now filter out background noise during calls by setting `Assistant.backgroundDenoisingEnabled` to `true`.

‎fern/changelog/2025-03-29.mdx‎

Lines changed: 9 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,9 @@
1+
1. **Updated `Call.endedReason` with New Prefix** The `endedReason` codes now include a prefix `call.in-progress.error-`, standardizing error codes across schemas. This change requires you to update your code to use the new prefixed enum values when handling call termination reasons.
2+
3+
The following specific `endedReason` values have been updated:
4+
5+
| Old Value | New Value |
6+
| --- | --- |
7+
| `pipeline-no-available-llm-model` | `call.in-progress.error-pipeline-no-available-llm-model` |
8+
| `assistant-did-not-receive-customer-audio` | `call.in-progress.error-assistant-did-not-receive-customer-audio` |
9+
| `sip-telephony-provider-failed-to-connect-call` | `call.in-progress.error-sip-telephony-provider-failed-to-connect-call` |

‎fern/changelog/2025-03-30.mdx‎

Lines changed: 5 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,5 @@
1+
1. **TestSuiteRunTestAttempt now accepts `callId` and `metadata`**: You can now include a `callId` and `metadata` when creating a test suite run attempt, allowing you to reference calls by ID and attach session-related information.
2+
3+
2. **`call` property in [TestSuiteRunTestAttempt](https://api.vapi.ai/api#:~:text=TestSuiteRunTestAttemptMetadata) is no longer required**: It's now optional to include the full `call` object in a test attempt, providing flexibility for cases where call details are unnecessary or already known.
4+
5+
3. **Attach Metadata to Test Suite Run Attempts**: You can now attach [metadata](https://api.vapi.ai/api#:~:text=TestSuiteRunTestAttemptMetadata) like `sessionId` to test attempts for better tracking and analysis.

‎fern/changelog/2025-04-01.mdx‎

Lines changed: 8 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,8 @@
1+
1. **Introducing `SmsSendTool` for SMS messaging support**: Developers can now create and manage tools of type `sms` using the new `SmsSendTool` schema, enabling assistants to send SMS messages via defined servers. This allows integration of SMS sending capabilities into applications, enhancing communication options.
2+
3+
2. **`sms` type added to discriminator mappings**: The `sms` tool type is now recognized in API endpoints, ensuring that `SmsSendTool`s are correctly processed during create, read, update, and delete operations. This enables seamless handling of SMS tools within existing API workflows.
4+
The `sms` tool type is now recognized in API endpoints, ensuring that `SmsSendTool`s are correctly processed during create, read, update, and delete operations. This enables seamless handling of SMS tools within existing API workflows.
5+
6+
3. **New configuration options for voice and transcriber settings**: The `autoMode` property has been added to `ElevenLabsVoice` schemas, letting developers control automatic voice settings. Additionally, `confidenceThreshold` has been introduced in transcriber schemas, allowing developers to set thresholds to discard low-confidence transcriptions and improve accuracy.
7+
8+
4. **Enhanced speed control in `CartesiaExperimentalControls`**: The `speed` property now accepts both predefined speeds (`'slowest'`, `'slow'`, `'normal'`, `'fast'`, `'fastest'`) and numeric values between -1 and 1. This provides developers with more precise control over speed settings for better customization.

‎fern/changelog/2025-04-02.mdx‎

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,3 @@
1+
1. **Introduction of `mcp` Tool Type**: Developers can now create and manage [MCP tools](https://api.vapi.ai/api#:~:text=McpTool), enabling customized interactions with specific tools, prompts, and resources in their applications. The new `mcp` tools can be configured using properties like `async`, `server`, `function`, and `messages` to control their behavior.
2+
3+
2. **Simplification of `Knowledge Base`**: The `model` property in the [`Knowledge Base`](https://api.vapi.ai/api#:~:text=KnowledgeBase) is now optional and changed from an object to a string, simplifying its use. You should update your Assistant configuration to treat `model` as a simple string identifier and adjust accordingly.

‎fern/changelog/2025-04-03.mdx‎

Lines changed: 5 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,5 @@
1+
1. **Introducing `SmsSendTool` for SMS messaging support**: You can now create and manage tools of type `sms` using the new [SMS Send Tool](https://api.vapi.ai/api#:~:text=SmsSendTool), allowing you to send SMS messages via defined servers. The `sms` tool type is also now recognized in API endpoints, ensuring that SMS send tools are correctly processed during CRUD operations.
2+
3+
2. **New configuration options for voice and transcriber settings**: The `autoMode` property has been added to [Eleven Labs Voice Settings](https://api.vapi.ai/api#:~:text=ElevenLabsVoice), letting developers control automatic voice settings. Additionally, `confidenceThreshold` has been introduced in transcriber settings, allowing developers to set thresholds to discard low-confidence transcriptions and improve accuracy.
4+
5+
3. **Enhanced speed control in `CartesiaExperimentalControls`**: The `speed` property now accepts both predefined speeds (`'slowest'`, `'slow'`, `'normal'`, `'fast'`, `'fastest'`) and numeric values between -1 and 1. This gives you more precise control over speed settings for better customization.

‎fern/changelog/2025-04-04.mdx‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+
1. **Addition of `assistantId` to `TargetPlan` settings**: You can now specify an `assistantId` when testing [target plans](https://api.vapi.ai/api#:~:text=TargetPlan), allowing you to test scenarios involving specific assistants directly.

‎fern/changelog/2025-04-05.mdx‎

Lines changed: 9 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,9 @@
1+
1. **Introducing `SmsSendTool` for SMS messaging support**: You can now create and send `sms` text messages using the new `[Send Text`](https://api.vapi.ai/api#:~:text=SmsSendTool) tool, enabling assistants to send SMS messages via defined servers.
2+
3+
<Frame caption="Send SMS with 'Send Text' tool">
4+
<img src="../static/images/changelog/sms-send-tool.png" alt="SmsSendTool" />
5+
</Frame>
6+
7+
2. **[Eleven Labs Voice](https://api.vapi.ai/api#:~:text=ElevenLabsVoice) Auto Mode and Confidence Threshold configuration options**: When using [`Eleven Labs Voice`](https://api.vapi.ai/api#:~:text=ElevenLabsVoice) in your Assistant, you can now configure `autoMode` (default: false) to automatically manage manage chunking strategies for long texts; Eleven Labs automatically determines the best way to process and generate audio, optimizing for latency and efficiency. Additionally, `confidenceThreshold` has been introduced in transcriber schemas, allowing developers to set thresholds to discard low-confidence transcriptions and improve accuracy.
8+
9+
3. **Changes to `CartesiaExperimentalControls` Speed property**: The `speed` property now accepts both predefined speeds (`'slowest'`, `'slow'`, `'normal'`, `'fast'`, `'fastest'`) and numeric values between -1 and 1. This simplifies the process of controlling the speed of the generated audio with Cartesia.

‎fern/changelog/2025-04-08.mdx‎

Lines changed: 7 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,7 @@
1+
1. **Simplified `transport` property in `Call` configuration**: You should now configure the `transport` property in [`Call`](https://api.vapi.ai/api#:~:text=Call) as an object when creating or updating a [`Call`](https://api.vapi.ai/api#:~:text=Call), since the separate `Transport` schema has been deprecated. This simplification makes it easier to work with transport details without referencing a separate transport configuration.
2+
3+
<Warning>
4+
The `Transport` schema is now deprecated and will be removed in a future release.
5+
</Warning>
6+
7+
2. **New call type `vapi.websocketCall`**: You can now make [phone calls over WebSockets](https://docs.vapi.ai/calls/websocket-transport) with Vapi. The `Call` schema now supports a new `type` value: `vapi.websocketCall`.

‎fern/changelog/2025-04-11.mdx‎

Lines changed: 9 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,9 @@
1+
1. **Updated AI Edge Condition with Prompt**: When defining an AI edge condition, the `matches` property has been renamed to `prompt`. The `prompt` allows you to provide a natural language condition (up to 1000 characters) that guides AI decision-making in workflows.
2+
3+
<Frame caption="Updated AI Edge Condition with Prompt">
4+
<img src="../static/images/changelog/ai-edge-condition-prompt.png" alt="AI Edge Condition with Prompt" />
5+
</Frame>
6+
7+
2. **Assistant Overrides per Customer**: You can now customize assistant settings for individual customers using `assistantOverrides` when [creating customers](https://api.vapi.ai/api#:~:text=CreateCustomerDTO). This enables personalized assistant interactions for each customer in batch calls.
8+
9+
3. **New Call Ended Reasons**: New error codes have been added to `endedReason` enums, providing more detailed insights into call terminations related to providers like Anthropic Bedrock and Vertex. This helps in better error handling and debugging of call issues.

0 commit comments

Comments
 (0)