Merge pull request #24 from WqyJh/v2

Migrate to Realtime API GA

Author: WqyJh

.github/workflows/coverage.yml

@@ -10,21 +10,17 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
       - name: Setup Go
-        uses: actions/setup-go@v5
+        uses: actions/setup-go@v6
         with:
-          go-version: "1.19"
+          go-version: "1.24"
       - name: Run vet
         run: |
           go vet .
-      - name: Run golangci-lint
-        uses: golangci/golangci-lint-action@v6
-        with:
-          version: latest
       - name: Run tests
         run: make cov
       - name: Upload coverage reports to Codecov
-        uses: codecov/codecov-action@v4
+        uses: codecov/codecov-action@v5
         env:
           CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}

.github/workflows/go-test.yml

@@ -10,19 +10,19 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        go-version: ["1.20", "1.22", "1.23", "1.24"]
+        go-version: ["1.23", "1.24", "1.25"]
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
       - name: Setup Go ${{ matrix.go-version }}
-        uses: actions/setup-go@v5
+        uses: actions/setup-go@v6
         with:
           go-version: ${{ matrix.go-version }}
       - name: Run vet
         run: |
           go vet .
       - name: Run golangci-lint
-        uses: golangci/golangci-lint-action@v4
+        uses: golangci/golangci-lint-action@v8
         with:
           version: latest
       - name: Run tests

.github/workflows/release-drafter.yml

@@ -10,6 +10,6 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@v5
       - name: Release
         uses: softprops/action-gh-release@v2

.golangci.bck.yml

@@ -1,22 +1,45 @@
 # OpenAI Realtime API SDK for Golang
 
-[![Go Reference](https://pkg.go.dev/badge/github.com/WqyJh/go-openai-realtime.svg)](https://pkg.go.dev/github.com/WqyJh/go-openai-realtime)
-[![Go Report Card](https://goreportcard.com/badge/github.com/WqyJh/go-openai-realtime)](https://goreportcard.com/report/github.com/WqyJh/go-openai-realtime)
+[![Go Reference](https://pkg.go.dev/badge/github.com/WqyJh/go-openai-realtime/v2.svg)](https://pkg.go.dev/github.com/WqyJh/go-openai-realtime/v2)
+[![Go Report Card](https://goreportcard.com/badge/github.com/WqyJh/go-openai-realtime/v2)](https://goreportcard.com/report/github.com/WqyJh/go-openai-realtime/v2)
 [![codecov](https://codecov.io/gh/WqyJh/go-openai-realtime/branch/main/graph/badge.svg?token=bCbIfHLIsW)](https://codecov.io/gh/WqyJh/go-openai-realtime)
 
-This library provides unofficial Go clients for [OpenAI Realtime API](https://platform.openai.com/docs/api-reference/realtime). We support all 9 client events and 28 server events.
+This library provides unofficial Go clients for [OpenAI Realtime API](https://platform.openai.com/docs/api-reference/realtime). We support all 11 client events and 40 server events (except for 3 WebRTC-Only events).
+
+[Model Support](https://platform.openai.com/docs/models/gpt-realtime):
+
+- gpt-realtime
+- gpt-realtime-2025-08-28
+- gpt-realtime-mini
+- gpt-realtime-mini-2025-10-06
+- gpt-4o-realtime-preview (shutdown date 2026-02-27)
+- gpt-4o-realtime-preview-2024-10-01 (shutdown date 2025-10-10)
+- gpt-4o-realtime-preview-2024-12-17 (shutdown date 2026-02-27)
+- gpt-4o-realtime-preview-2025-06-03 (shutdown date 2026-02-27)
+- gpt-4o-mini-realtime-preview
+- gpt-4o-mini-realtime-preview-2024-12-17
+
+
+## Migration
+
+OpenAI Realtime API GA was officially released on 2025-08-28, and it is not fully compatible with the Beta version.To address these breaking changes, 
+we need to develop a v2 version of go-openai-realtime.For details, refer to the [Beta to GA Migration Guide](https://platform.openai.com/docs/guides/realtime#beta-to-ga-migration).
+
+Please use `github.com/WqyJh/go-openai-realtime/v2` instead of `github.com/WqyJh/go-openai-realtime`, and update your code to adapt to the new API specifications.
+
+Note that the Realtime API Beta and Realtime Preview Models (e.g., gpt-4o-realtime-preview) will be shut down on 2026-02-27. After this date, 
+you will no longer be able to use these services or the v1 version of go-openai-realtime.
+
+The old v1 version of go-openai-realtime is available at [v1 branch](https://github.com/WqyJh/go-openai-realtime/tree/v1).
 
-[Model Support](https://platform.openai.com/docs/models/gpt-4o-realtime):
-- gpt-4o-realtime-preview
-- gpt-4o-realtime-preview-2024-10-01
 
 ## Installation
 
 ```bash
-go get github.com/WqyJh/go-openai-realtime
+go get github.com/WqyJh/go-openai-realtime/v2
 ```
 
-Currently, go-openai-realtime requires Go version 1.19 or greater.
+Currently, go-openai-realtime requires Go version 1.22 or greater.
 
 ## Usage
 
@@ -32,7 +55,7 @@ import (
 	"log"
 	"os"
 
-	openairt "github.com/WqyJh/go-openai-realtime"
+	openairt "github.com/WqyJh/go-openai-realtime/v2"
 )
 
 func main() {
@@ -52,8 +75,8 @@ Switch to another websocket dialer [gorilla/websocket](https://github.com/gorill
 
 ```go
 import (
-	openairt "github.com/WqyJh/go-openai-realtime"
-	gorilla "github.com/WqyJh/go-openai-realtime/contrib/ws-gorilla"
+	openairt "github.com/WqyJh/go-openai-realtime/v2"
+	gorilla "github.com/WqyJh/go-openai-realtime/v2/contrib/ws-gorilla"
 )
 
 func main() {
@@ -74,14 +97,16 @@ func main() {
 ```go
 
 import (
-	openairt "github.com/WqyJh/go-openai-realtime"
+	openairt "github.com/WqyJh/go-openai-realtime/v2"
 )
 
 func main() {
     err = conn.SendMessage(ctx, &openairt.SessionUpdateEvent{
-        Session: openairt.ClientSession{
-            Modalities: []openairt.Modality{openairt.ModalityText},
-        },
+        Session: openairt.SessionUnion{
+			Realtime: &openairt.RealtimeSession{
+				OutputModalities: []openairt.Modality{openairt.ModalityText},
+			},
+		},
     })
 }
 ```
@@ -138,8 +163,8 @@ Based on the event type, you can get the event data by type assertion.
 	// Teletype response
 	responseDeltaHandler := func(ctx context.Context, event openairt.ServerEvent) {
 		switch event.ServerEventType() {
-		case openairt.ServerEventTypeResponseTextDelta:
-			fmt.Printf(event.(openairt.ResponseTextDeltaEvent).Delta)
+		case openairt.ServerEventTypeResponseOutputTextDelta:
+			fmt.Printf(event.(openairt.ResponseOutputTextDeltaEvent).Delta)
 		}
 	}
 ```

.golangci.yml

@@ -9,65 +9,35 @@ import (
 	"net/http"
 )
 
-type CreateSessionRequest struct {
-	ClientSession
-
-	// The Realtime model used for this session.
-	Model string `json:"model"`
-}
-
 type ClientSecret struct {
 	// Ephemeral key usable in client environments to authenticate connections to the Realtime API. Use this in client-side environments rather than a standard API token, which should only be used server-side.
 	Value string `json:"value"`
 	// Timestamp for when the token expires. Currently, all tokens expire after one minute.
 	ExpiresAt int64 `json:"expires_at"`
 }
 
-type CreateSessionResponse struct {
-	ServerSession
+type ExpiresAfter struct {
+	// The anchor point for the client secret expiration, meaning that seconds will be added to the created_at time of the client secret to produce an expiration timestamp. Only created_at is currently supported.
+	Anchor string `json:"anchor,omitempty"`
 
-	// Ephemeral key returned by the API.
-	ClientSecret ClientSecret `json:"client_secret"`
+	// The number of seconds from the anchor point to the expiration. Select a value between 10 and 7200 (2 hours). This default to 600 seconds (10 minutes) if not specified.
+	Seconds int `json:"seconds,omitempty"`
 }
 
-// CreateTranscriptionSessionRequest is the request for creating a transcription session.
-type CreateTranscriptionSessionRequest struct {
-	// The set of items to include in the transcription.
-	Include []string `json:"include,omitempty"`
-	// The format of input audio. Options are "pcm16", "g711_ulaw", or "g711_alaw".
-	InputAudioFormat AudioFormat `json:"input_audio_format,omitempty"`
-	// Configuration for input audio noise reduction.
-	InputAudioNoiseReduction *InputAudioNoiseReduction `json:"input_audio_noise_reduction,omitempty"`
-	// Configuration for input audio transcription.
-	InputAudioTranscription *InputAudioTranscription `json:"input_audio_transcription,omitempty"`
-
-	// Attention: Keep this field empty! It's shocking that this field is documented but not supported.
-	// You may get error of "Unknown parameter: 'modalities'." if this field is not empty.
-	// Issue reported: https://community.openai.com/t/unknown-parameter-modalities-when-creating-transcriptionsessions/1150141/6
-	// Docs: https://platform.openai.com/docs/api-reference/realtime-sessions/create-transcription#realtime-sessions-create-transcription-modalities
-	// The set of modalities the model can respond with. To disable audio, set this to ["text"].
-	Modalities []Modality `json:"modalities,omitempty"`
-
-	// Configuration for turn detection.
-	TurnDetection *ClientTurnDetection `json:"turn_detection,omitempty"`
+type CreateClientSecretRequest struct {
+	// Configuration for the client secret expiration. Expiration refers to the time after which a client secret will no longer be valid for creating sessions. The session itself may continue after that time once started. A secret can be used to create multiple sessions until it expires.
+	ExpiresAfter *ExpiresAfter `json:"expires_after,omitempty"`
+
+	// Session configuration to use for the client secret. Choose either a realtime session or a transcription session.
+	Session *SessionUnion `json:"session,omitempty"`
 }
 
-// CreateTranscriptionSessionResponse is the response from creating a transcription session.
-type CreateTranscriptionSessionResponse struct {
-	// The unique ID of the session.
-	ID string `json:"id"`
-	// The object type, must be "realtime.transcription_session".
-	Object string `json:"object"`
-	// The format of input audio.
-	InputAudioFormat AudioFormat `json:"input_audio_format,omitempty"`
-	// Configuration of the transcription model.
-	InputAudioTranscription *InputAudioTranscription `json:"input_audio_transcription,omitempty"`
-	// The set of modalities.
-	Modalities []Modality `json:"modalities,omitempty"`
-	// Configuration for turn detection.
-	TurnDetection *ServerTurnDetection `json:"turn_detection,omitempty"`
+type CreateClientSecretResponse struct {
 	// Ephemeral key returned by the API.
-	ClientSecret ClientSecret `json:"client_secret"`
+	ClientSecret
+
+	// Session configuration to use for the client secret. Choose either a realtime session or a transcription session.
+	Session *SessionUnion `json:"session,omitempty"`
 }
 
 type OpenAIError struct {
@@ -84,7 +54,7 @@ type ErrorResponse struct { //nolint:errname // this is a http error response
 }
 
 func (e *ErrorResponse) Error() string {
-	return e.OpenAIError.Message
+	return e.Message
 }
 
 type httpOption struct {