refactor(openai): centralize provider defaults

CHANGELOG.md

@@ -59,6 +59,7 @@ Docs: https://docs.openclaw.ai
 - Docs/plugins: add the community wecom plugin listing to the docs catalog. (#29905) Thanks @sliverp.
 - Models/GitHub Copilot: allow forward-compat dynamic model ids without code updates, while preserving configured provider and per-model overrides for those synthetic models. (#51325) Thanks @fuller-stack-dev.
 - Agents/compaction: notify users when followup auto-compaction starts and finishes, keeping those notices out of TTS and preserving reply threading for the real assistant reply. (#38805) Thanks @zidongdesign.
+- Models/OpenAI: switch the default OpenAI setup model to `openai/gpt-5.4`, keep Codex on `openai-codex/gpt-5.4`, and centralize OpenAI chat, image, TTS, transcription, and embedding defaults in one shared module so future default-model updates stay low-churn. Thanks @vincentkoc.
 
 ### Fixes
 

docs/start/wizard-cli-reference.md

@@ -149,7 +149,7 @@ What you set:
   <Accordion title="OpenAI API key">
     Uses `OPENAI_API_KEY` if present or prompts for a key, then stores the credential in auth profiles.
 
-    Sets `agents.defaults.model` to `openai/gpt-5.1-codex` when model is unset, `openai/*`, or `openai-codex/*`.
+    Sets `agents.defaults.model` to `openai/gpt-5.4` when model is unset, `openai/*`, or `openai-codex/*`.
 
   </Accordion>
   <Accordion title="xAI (Grok) API key">

extensions/openai/media-understanding-provider.ts

@@ -5,15 +5,15 @@ import {
   type AudioTranscriptionRequest,
   type MediaUnderstandingProvider,
 } from "openclaw/plugin-sdk/media-understanding";
+import { OPENAI_DEFAULT_AUDIO_TRANSCRIPTION_MODEL } from "../../src/providers/openai-defaults.js";
 
 export const DEFAULT_OPENAI_AUDIO_BASE_URL = "https://api.openai.com/v1";
-const DEFAULT_OPENAI_AUDIO_MODEL = "gpt-4o-mini-transcribe";
 
 export async function transcribeOpenAiAudio(params: AudioTranscriptionRequest) {
   return await transcribeOpenAiCompatibleAudio({
     ...params,
     defaultBaseUrl: DEFAULT_OPENAI_AUDIO_BASE_URL,
-    defaultModel: DEFAULT_OPENAI_AUDIO_MODEL,
+    defaultModel: OPENAI_DEFAULT_AUDIO_TRANSCRIPTION_MODEL,
   });
 }
 

extensions/openai/openai-codex-provider.ts

@@ -19,6 +19,7 @@ import {
 } from "openclaw/plugin-sdk/provider-models";
 import { createOpenAIAttributionHeadersWrapper } from "openclaw/plugin-sdk/provider-stream";
 import { fetchCodexUsage } from "openclaw/plugin-sdk/provider-usage";
+import { OPENAI_CODEX_DEFAULT_MODEL } from "../../src/providers/openai-defaults.js";
 import { buildOpenAICodexProvider } from "./openai-codex-catalog.js";
 import {
   cloneFirstTemplateModel,
@@ -38,7 +39,6 @@ const OPENAI_CODEX_GPT_53_SPARK_MODEL_ID = "gpt-5.3-codex-spark";
 const OPENAI_CODEX_GPT_53_SPARK_CONTEXT_TOKENS = 128_000;
 const OPENAI_CODEX_GPT_53_SPARK_MAX_TOKENS = 128_000;
 const OPENAI_CODEX_TEMPLATE_MODEL_IDS = ["gpt-5.2-codex"] as const;
-const OPENAI_CODEX_DEFAULT_MODEL = `${PROVIDER_ID}/${OPENAI_CODEX_GPT_54_MODEL_ID}`;
 const OPENAI_CODEX_XHIGH_MODEL_IDS = [
   OPENAI_CODEX_GPT_54_MODEL_ID,
   OPENAI_CODEX_GPT_53_MODEL_ID,

src/commands/openai-model-default.test.ts

@@ -112,7 +112,7 @@ describe("applyDefaultModelChoice", () => {
   });
 
   it("uses applyDefaultConfig path when setDefaultModel is true", async () => {
-    const defaultModel = "openai/gpt-5.1-codex";
+    const defaultModel = "openai/gpt-5.4";
     const applied = await applyDefaultModelChoice({
       config: {},
       setDefaultModel: true,

src/image-generation/providers/openai.ts

@@ -1,8 +1,8 @@
 import { resolveApiKeyForProvider } from "../../agents/model-auth.js";
 import type { ImageGenerationProviderPlugin } from "../../plugins/types.js";
+import { OPENAI_DEFAULT_IMAGE_MODEL as DEFAULT_OPENAI_IMAGE_MODEL } from "../../providers/openai-defaults.js";
 
 const DEFAULT_OPENAI_IMAGE_BASE_URL = "https://api.openai.com/v1";
-const DEFAULT_OPENAI_IMAGE_MODEL = "gpt-image-1";
 const DEFAULT_OUTPUT_MIME = "image/png";
 const DEFAULT_SIZE = "1024x1024";
 const OPENAI_SUPPORTED_SIZES = ["1024x1024", "1024x1536", "1536x1024"] as const;

src/memory/embeddings-openai.ts

@@ -1,4 +1,5 @@
 import type { SsrFPolicy } from "../infra/net/ssrf.js";
+import { OPENAI_DEFAULT_EMBEDDING_MODEL } from "../providers/openai-defaults.js";
 import { normalizeEmbeddingModelWithPrefixes } from "./embeddings-model-normalize.js";
 import {
   createRemoteEmbeddingProvider,
@@ -13,7 +14,6 @@ export type OpenAiEmbeddingClient = {
   model: string;
 };
 
-export const DEFAULT_OPENAI_EMBEDDING_MODEL = "text-embedding-3-small";
 const DEFAULT_OPENAI_BASE_URL = "https://api.openai.com/v1";
 const OPENAI_MAX_INPUT_TOKENS: Record<string, number> = {
   "text-embedding-3-small": 8192,

src/plugins/provider-model-defaults.ts

@@ -1,9 +1,10 @@
 import type { OpenClawConfig } from "../config/config.js";
+import { OPENAI_DEFAULT_MODEL } from "../providers/openai-defaults.js";
 import { ensureModelAllowlistEntry } from "./provider-model-allowlist.js";
 import { applyAgentDefaultPrimaryModel } from "./provider-model-primary.js";
 
 export const GOOGLE_GEMINI_DEFAULT_MODEL = "google/gemini-3.1-pro-preview";
-export const OPENAI_DEFAULT_MODEL = "openai/gpt-5.1-codex";
+export { OPENAI_DEFAULT_MODEL } from "../providers/openai-defaults.js";
 export const OPENCODE_GO_DEFAULT_MODEL_REF = "opencode-go/kimi-k2.5";
 export const OPENCODE_ZEN_DEFAULT_MODEL = "opencode/claude-opus-4-6";
 

src/providers/openai-defaults.ts

@@ -0,0 +1,8 @@
+export const OPENAI_DEFAULT_MODEL = "openai/gpt-5.4";
+export const OPENAI_CODEX_DEFAULT_MODEL = "openai-codex/gpt-5.4";
+
+export const OPENAI_DEFAULT_IMAGE_MODEL = "gpt-image-1";
+export const OPENAI_DEFAULT_TTS_MODEL = "gpt-4o-mini-tts";
+export const OPENAI_DEFAULT_TTS_VOICE = "alloy";
+export const OPENAI_DEFAULT_AUDIO_TRANSCRIPTION_MODEL = "gpt-4o-mini-transcribe";
+export const OPENAI_DEFAULT_EMBEDDING_MODEL = "text-embedding-3-small";

src/tts/tts.ts

@@ -32,6 +32,10 @@ import {
   normalizeSpeechProviderId,
 } from "./provider-registry.js";
 import type { SpeechVoiceOption } from "./provider-types.js";
+import {
+  OPENAI_DEFAULT_TTS_MODEL as DEFAULT_OPENAI_MODEL,
+  OPENAI_DEFAULT_TTS_VOICE as DEFAULT_OPENAI_VOICE,
+} from "../providers/openai-defaults.js";
 import {
   DEFAULT_OPENAI_BASE_URL,
   isValidOpenAIModel,
@@ -54,8 +58,6 @@ const DEFAULT_MAX_TEXT_LENGTH = 4096;
 const DEFAULT_ELEVENLABS_BASE_URL = "https://api.elevenlabs.io";
 const DEFAULT_ELEVENLABS_VOICE_ID = "pMsXgVXv3BLzUgSXRplE";
 const DEFAULT_ELEVENLABS_MODEL_ID = "eleven_multilingual_v2";
-const DEFAULT_OPENAI_MODEL = "gpt-4o-mini-tts";
-const DEFAULT_OPENAI_VOICE = "alloy";
 const DEFAULT_EDGE_VOICE = "en-US-MichelleNeural";
 const DEFAULT_EDGE_LANG = "en-US";
 const DEFAULT_EDGE_OUTPUT_FORMAT = "audio-24khz-48kbitrate-mono-mp3";