Skip to content

Commit a73aa38

Browse files
[fern-autoversion] feat!: remove exported types and enum values, add new tool variants and simulation concurrency endpoint
This release contains both breaking changes and new features. Several exported types and enum values have been removed, and existing interfaces have had required fields dropped. New tool union variants (Code, Ghl) and a simulation concurrency endpoint have been added. Key changes: - Removed exported types: `CreateTrieveCredentialDto`, `CreateTrieveKnowledgeBaseDto`, `TrieveKnowledgeBase`, `TrieveKnowledgeBaseImport`, `UpdateTrieveKnowledgeBaseDto`, `GhlToolType`, `UpdateCodeToolDtoType`, `ToolPinnedConflictResponseDtoError` - Removed `Duration` and `Cost` values from `EvalControllerGetRunsPaginatedRequestSortBy` and `GetEvalRunPaginatedDtoSortBy` enums; removed `error` field from `ToolPinnedConflictResponseDto` and `type` field from `GhlTool` and `UpdateCodeToolDto` - Added `Code` variant to `CreateToolsRequest` and `UpdateToolsRequestBody`; added `Ghl` variant to `CreateToolsResponse`, `DeleteToolsResponse`, `GetToolsResponse`, `ListToolsResponseItem`, and `UpdateToolsResponse` - Added `simulationControllerGetConcurrency()` method to `SimulationsClient` returning `SimulationConcurrencyResponse` - Renamed `StructuredOutputControllerRunResponseZero` to `StructuredOutputControllerRunResponseOne` 🌿 Generated with Fern
1 parent ed34cdc commit a73aa38

5 files changed

Lines changed: 48 additions & 5 deletions

File tree

‎.fern/metadata.json‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -16,5 +16,5 @@
1616
"invokedBy": "ci",
1717
"requestedVersion": "AUTO",
1818
"ciProvider": "unknown",
19-
"sdkVersion": "0.0.0-fern-placeholder"
19+
"sdkVersion": "3.0.0"
2020
}

‎changelog.md‎

Lines changed: 43 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1,3 +1,46 @@
1+
## [3.0.0] - 2026-10-09
2+
### Breaking Changes
3+
- **`Call.phoneNumber`** — type changed from `ImportTwilioPhoneNumberDto` to `TransientTwilioPhoneNumber`; update any code that constructs or reads this field to use `TransientTwilioPhoneNumber` instead.
4+
5+
### Added
6+
- **`AssemblyAiTranscriberSpeechModel.Universal36Pro`** and **`FallbackAssemblyAiTranscriberSpeechModel.Universal36Pro`** — new `universal-3-6-pro` speech model option for AssemblyAI transcribers.
7+
- **`agentContextAutoUpdateEnabled`** — new optional field on `AssemblyAiTranscriber` and `FallbackAssemblyAiTranscriber` that automatically sends the assistant's last spoken text as `agent_context` after each turn.
8+
- **`DeepgramVoiceModel.Flux`** / **`FallbackDeepgramVoiceModel.Flux`** — new Flux model option for Deepgram voices, with accompanying optional `speed` and `expressivity` fields on `DeepgramVoice` and `FallbackDeepgramVoice`.
9+
- **`squadVersion`** — new optional field on `Call` and `AssistantActivation` exposing the squad version governing the call or activation.
10+
11+
### Added
12+
- **`VapiClient.trafficAllocations`** — new `TrafficAllocationsClient` accessor for managing traffic allocation resources, exported via the `./trafficAllocations` package entry point.
13+
- **`OpenAiModel.speaker`**, **`OpenAiModel.reasoner`**, and **`OpenAiModel.serviceTier`** — new optional fields for configuring GPT-Live speaker, reasoner, and OpenAI service tier (fast/auto/default) on `OpenAiModel`.
14+
- **`ForbiddenError`** — new exported error class (HTTP 403) added to the errors surface.
15+
- **`RimeAiVoiceIdEnum`** and **`FallbackRimeAiVoiceIdEnum`** — seven new voice values added: `Clementine`, `Walnut`, `Eyre`, `Bancroft`, `Hesse`, `Beatty`, and `Godfrey`, covering the new mistv3 and coda Rime AI models.
16+
- **`UserMessage.confidence`** and **`UserMessage.confidenceSource`** — new optional fields exposing the transcriber's confidence score and its origin (`"provider"` or `"derived"`); `UserMessage.metadata` type narrowed to `UserMessageMetadata`.
17+
18+
### Changed
19+
- **`SimulationRunItemResults`** — adds optional `latencyEvaluations` field and updates `passed` to reflect latency expectations in addition to structured output evaluations.
20+
- **`CreateCallDto.squadVersion`** — new optional field for pinning a specific squad version on a call.
21+
- **`OpenAiVoiceId`** / **`FallbackOpenAiVoiceId`** — voice availability documentation updated to reflect new GPT-Live-only voices (quartz, ripple, vesper, willow, stone, gleam, meridian, bossa, tempo, beacon, delta, cinder).
22+
23+
### Added
24+
- **`TrafficAllocationsClient`** — new beta client (`client.trafficAllocations`) for managing assistant traffic splitting, with methods to list allocation history, create a new allocation, retrieve the latest allocation, and fetch a single allocation by ID.
25+
- **`modelDeprecations`** — new optional read-only field on **`Assistant`**, **`AssistantDraft`**, and **`AssistantVersion`** that surfaces deprecation and retirement notices for any models in use, including replacement recommendations.
26+
- **`ClientInboundMessageAppendContext`** and **`ClientInboundMessageAppendContextKind`** — new types enabling callers to append commentary, thinking, or instructions to an in-progress call via the `append-context` message variant on `ClientInboundMessageMessage`.
27+
- **New enum values** added to `CallEndedReason` (e.g. `CallStartSquadVersionErrorValidation`, `SipOutboundUnallocatedNumber`), `AssemblyAiTranscriberLanguageCodesItem` (13 new language codes), and `AnthropicBedrockModelFallbackModelsItem` (new Claude model variants).
28+
- **`AudioFormatFormat`** — new exported enum type representing supported audio formats (`pcm_s16le`, `mulaw`).
29+
30+
### Added
31+
- **`OpenAiReasoner`** and **`OpenAiSpeaker`** — new types for configuring GPT-Live real-time voice, including `gpt-live-1` and `gpt-6-luna` model values on `OpenAiModelModel`, and a new `OpenAiModelServiceTier` enum for fast/priority processing tiers.
32+
- **`LatencyExpectation`** and **`LatencyEvaluationResult`** — new types for simulation latency testing; `CreateScenarioDto` gains an optional `latencyExpectations` field to set per-metric ceilings (turn, model, voice) with configurable aggregation (mean, median, p95, max).
33+
- **`CreateTrafficAllocationTargetDto`**, **`GetTrafficAllocationLatestDto`**, and **`GetTrafficAllocationPaginatedDto`** — new types supporting assistant traffic splitting across published versions.
34+
- **`ClientMessageTranscript.confidence`** and **`ClientMessageTranscript.confidenceSource`** — new optional fields exposing the transcriber's confidence score and its origin (`provider` or `derived`), backed by the new `ClientMessageTranscriptConfidenceSource` enum.
35+
- **New enum values** across `DeepgramVoiceId` (36 voices), `FallbackDeepgramVoiceId` (36 voices), `FallbackOpenAiVoiceIdEnum` (17 voices), `ElevenLabsVoiceModel` / `FallbackElevenLabsVoiceModel` (`eleven_v4_turbo`), `FallbackRimeAiVoiceModel` (`coda`, `mistv3`), `FallbackAssemblyAiTranscriberLanguageCodesItem` (14 language codes), and `InviteUserDtoRoleZero` (`hipaa-special`).
36+
37+
### Added
38+
- **`TransientTwilioPhoneNumberFallbackDestination`** — new discriminated union type (`number` | `sip`) representing the fallback destination for inbound transient Twilio phone number calls.
39+
- **`TransientTwilioPhoneNumberHooksItem`** — new discriminated union type (`call.ringing` | `call.ending`) for lifecycle hooks on transient Twilio phone numbers.
40+
- **`UserMessageConfidenceSource`** — new enum (`"provider"` | `"derived"`) indicating whether a transcription confidence score came from the provider or was computed by Vapi.
41+
- **`UserMessageMetadata`** — new interface exposing word-level confidence scores and out-of-band message metadata on user messages.
42+
- **New enum values** added: `HipaaSpecial` to `UpdateUserRoleDtoRoleZero`, `SquadVersion` to `VersionPinReferenceSourceType`, and `Gpt6Luna` to `WorkflowOpenAiModelModel`.
43+
144
## [2.0.1] - 2026-08-26
245

346
## 2.0.0 - 2026-06-24

‎package.json‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
{
22
"name": "@vapi-ai/server-sdk",
3-
"version": "0.0.0-fern-placeholder",
3+
"version": "3.0.0",
44
"private": false,
55
"repository": {
66
"type": "git",

‎src/BaseClient.ts‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -52,8 +52,8 @@ export function normalizeClientOptions<T extends BaseClientOptions = BaseClientO
5252
{
5353
"X-Fern-Language": "JavaScript",
5454
"X-Fern-SDK-Name": "@vapi-ai/server-sdk",
55-
"X-Fern-SDK-Version": "0.0.0-fern-placeholder",
56-
"User-Agent": "@vapi-ai/server-sdk/0.0.0-fern-placeholder",
55+
"X-Fern-SDK-Version": "3.0.0",
56+
"User-Agent": "@vapi-ai/server-sdk/3.0.0",
5757
"X-Fern-Runtime": core.RUNTIME.type,
5858
"X-Fern-Runtime-Version": core.RUNTIME.version,
5959
},

‎src/version.ts‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1 +1 @@
1-
export const SDK_VERSION = "0.0.0-fern-placeholder";
1+
export const SDK_VERSION = "3.0.0";

0 commit comments

Comments
 (0)