fix(auth): preserve model_list and use gpt-5.2 for Codex API

Auth fixes:
- Fix OpenAI/Anthropic OAuth and token login to update ModelList
- Fix logout to clear AuthMethod in ModelList
- Add helper functions: isOpenAIModel, isAnthropicModel, isAntigravityModel
- Fix slice bounds panic in isAntigravityModel using strings.HasPrefix
- All auth operations now preserve existing model_list configuration

Factory provider fixes:
- Add OAuth support for openai protocol in CreateProviderFromConfig
- CodexAuthProvider is now used when auth_method is oauth/token

Default model updates:
- OpenAI login: set default model to gpt-5.2
- Anthropic login: set default model to claude-sonnet-4
- Antigravity login: set default model to gemini-flash (remove provider field)

Model changes:
- Change default OpenAI model from gpt-4o to gpt-5.2
- gpt-5.2 is compatible with Codex API (chatgpt.com backend)
- Update all README files, config examples, and migration code

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

README.fr.md

@@ -833,8 +833,8 @@ Cette conception permet également le **support multi-agent** avec une sélectio
 {
   "model_list": [
     {
-      "model_name": "gpt-4o",
+      "model_name": "gpt-5.2",
-      "model": "openai/gpt-4o",
+      "model": "openai/gpt-5.2",
       "api_key": "sk-your-openai-key"
     },
     {
@@ -850,7 +850,7 @@ Cette conception permet également le **support multi-agent** avec une sélectio
   ],
   "agents": {
     "defaults": {
-      "model": "gpt-4o"
+      "model": "gpt-5.2"
     }
   }
 }
@@ -861,8 +861,8 @@ Cette conception permet également le **support multi-agent** avec une sélectio
 **OpenAI**
 ```json
 {
-  "model_name": "gpt-4o",
+  "model_name": "gpt-5.2",
-  "model": "openai/gpt-4o",
+  "model": "openai/gpt-5.2",
   "api_key": "sk-..."
 }
 ```
@@ -894,14 +894,14 @@ Configurez plusieurs points de terminaison pour le même nom de modèle—PicoCl
 {
   "model_list": [
     {
-      "model_name": "gpt-4o",
+      "model_name": "gpt-5.2",
-      "model": "openai/gpt-4o",
+      "model": "openai/gpt-5.2",
       "api_base": "https://api1.example.com/v1",
       "api_key": "sk-key1"
     },
     {
-      "model_name": "gpt-4o",
+      "model_name": "gpt-5.2",
-      "model": "openai/gpt-4o",
+      "model": "openai/gpt-5.2",
       "api_base": "https://api2.example.com/v1",
       "api_key": "sk-key2"
     }

README.ja.md

@@ -769,8 +769,8 @@ HEARTBEAT_OK 応答         ユーザーが直接結果を受け取る
 {
   "model_list": [
     {
-      "model_name": "gpt-4o",
+      "model_name": "gpt-5.2",
-      "model": "openai/gpt-4o",
+      "model": "openai/gpt-5.2",
       "api_key": "sk-your-openai-key"
     },
     {
@@ -786,7 +786,7 @@ HEARTBEAT_OK 応答         ユーザーが直接結果を受け取る
   ],
   "agents": {
     "defaults": {
-      "model": "gpt-4o"
+      "model": "gpt-5.2"
     }
   }
 }
@@ -797,8 +797,8 @@ HEARTBEAT_OK 応答         ユーザーが直接結果を受け取る
 **OpenAI**
 ```json
 {
-  "model_name": "gpt-4o",
+  "model_name": "gpt-5.2",
-  "model": "openai/gpt-4o",
+  "model": "openai/gpt-5.2",
   "api_key": "sk-..."
 }
 ```
@@ -830,14 +830,14 @@ HEARTBEAT_OK 応答         ユーザーが直接結果を受け取る
 {
   "model_list": [
     {
-      "model_name": "gpt-4o",
+      "model_name": "gpt-5.2",
-      "model": "openai/gpt-4o",
+      "model": "openai/gpt-5.2",
       "api_base": "https://api1.example.com/v1",
       "api_key": "sk-key1"
     },
     {
-      "model_name": "gpt-4o",
+      "model_name": "gpt-5.2",
-      "model": "openai/gpt-4o",
+      "model": "openai/gpt-5.2",
       "api_base": "https://api2.example.com/v1",
       "api_key": "sk-key2"
     }

README.md

@@ -218,7 +218,7 @@ picoclaw onboard
   "model_list": [
     {
       "model_name": "gpt4",
-      "model": "openai/gpt-4o",
+      "model": "openai/gpt-5.2",
       "api_key": "your-api-key"
     },
     {
@@ -728,8 +728,8 @@ This design also enables **multi-agent support** with flexible provider selectio
 {
   "model_list": [
     {
-      "model_name": "gpt-4o",
+      "model_name": "gpt-5.2",
-      "model": "openai/gpt-4o",
+      "model": "openai/gpt-5.2",
       "api_key": "sk-your-openai-key"
     },
     {
@@ -745,7 +745,7 @@ This design also enables **multi-agent support** with flexible provider selectio
   ],
   "agents": {
     "defaults": {
-      "model": "gpt-4o"
+      "model": "gpt-5.2"
     }
   }
 }
@@ -756,8 +756,8 @@ This design also enables **multi-agent support** with flexible provider selectio
 **OpenAI**
 ```json
 {
-  "model_name": "gpt-4o",
+  "model_name": "gpt-5.2",
-  "model": "openai/gpt-4o",
+  "model": "openai/gpt-5.2",
   "api_key": "sk-..."
 }
 ```
@@ -816,14 +816,14 @@ Configure multiple endpoints for the same model name—PicoClaw will automatical
 {
   "model_list": [
     {
-      "model_name": "gpt-4o",
+      "model_name": "gpt-5.2",
-      "model": "openai/gpt-4o",
+      "model": "openai/gpt-5.2",
       "api_base": "https://api1.example.com/v1",
       "api_key": "sk-key1"
     },
     {
-      "model_name": "gpt-4o",
+      "model_name": "gpt-5.2",
-      "model": "openai/gpt-4o",
+      "model": "openai/gpt-5.2",
       "api_base": "https://api2.example.com/v1",
       "api_key": "sk-key2"
     }

README.pt-br.md

@@ -834,8 +834,8 @@ Este design também possibilita o **suporte multi-agent** com seleção flexíve
 {
   "model_list": [
     {
-      "model_name": "gpt-4o",
+      "model_name": "gpt-5.2",
-      "model": "openai/gpt-4o",
+      "model": "openai/gpt-5.2",
       "api_key": "sk-your-openai-key"
     },
     {
@@ -851,7 +851,7 @@ Este design também possibilita o **suporte multi-agent** com seleção flexíve
   ],
   "agents": {
     "defaults": {
-      "model": "gpt-4o"
+      "model": "gpt-5.2"
     }
   }
 }
@@ -862,8 +862,8 @@ Este design também possibilita o **suporte multi-agent** com seleção flexíve
 **OpenAI**
 ```json
 {
-  "model_name": "gpt-4o",
+  "model_name": "gpt-5.2",
-  "model": "openai/gpt-4o",
+  "model": "openai/gpt-5.2",
   "api_key": "sk-..."
 }
 ```
@@ -895,14 +895,14 @@ Configure vários endpoints para o mesmo nome de modelo—PicoClaw fará round-r
 {
   "model_list": [
     {
-      "model_name": "gpt-4o",
+      "model_name": "gpt-5.2",
-      "model": "openai/gpt-4o",
+      "model": "openai/gpt-5.2",
       "api_base": "https://api1.example.com/v1",
       "api_key": "sk-key1"
     },
     {
-      "model_name": "gpt-4o",
+      "model_name": "gpt-5.2",
-      "model": "openai/gpt-4o",
+      "model": "openai/gpt-5.2",
       "api_base": "https://api2.example.com/v1",
       "api_key": "sk-key2"
     }

README.vi.md

@@ -811,8 +811,8 @@ Thiết kế này cũng cho phép **hỗ trợ đa tác nhân** với lựa ch
 {
   "model_list": [
     {
-      "model_name": "gpt-4o",
+      "model_name": "gpt-5.2",
-      "model": "openai/gpt-4o",
+      "model": "openai/gpt-5.2",
       "api_key": "sk-your-openai-key"
     },
     {
@@ -828,7 +828,7 @@ Thiết kế này cũng cho phép **hỗ trợ đa tác nhân** với lựa ch
   ],
   "agents": {
     "defaults": {
-      "model": "gpt-4o"
+      "model": "gpt-5.2"
     }
   }
 }
@@ -839,8 +839,8 @@ Thiết kế này cũng cho phép **hỗ trợ đa tác nhân** với lựa ch
 **OpenAI**
 ```json
 {
-  "model_name": "gpt-4o",
+  "model_name": "gpt-5.2",
-  "model": "openai/gpt-4o",
+  "model": "openai/gpt-5.2",
   "api_key": "sk-..."
 }
 ```
@@ -872,14 +872,14 @@ Thiết kế này cũng cho phép **hỗ trợ đa tác nhân** với lựa ch
 {
   "model_list": [
     {
-      "model_name": "gpt-4o",
+      "model_name": "gpt-5.2",
-      "model": "openai/gpt-4o",
+      "model": "openai/gpt-5.2",
       "api_base": "https://api1.example.com/v1",
       "api_key": "sk-key1"
     },
     {
-      "model_name": "gpt-4o",
+      "model_name": "gpt-5.2",
-      "model": "openai/gpt-4o",
+      "model": "openai/gpt-5.2",
       "api_base": "https://api2.example.com/v1",
       "api_key": "sk-key2"
     }

README.zh.md

@@ -227,7 +227,7 @@ picoclaw onboard
   "model_list": [
     {
       "model_name": "gpt4",
-      "model": "openai/gpt-4o",
+      "model": "openai/gpt-5.2",
       "api_key": "your-api-key"
     },
     {
@@ -605,8 +605,8 @@ Agent 读取 HEARTBEAT.md
 {
   "model_list": [
     {
-      "model_name": "gpt-4o",
+      "model_name": "gpt-5.2",
-      "model": "openai/gpt-4o",
+      "model": "openai/gpt-5.2",
       "api_key": "sk-your-openai-key"
     },
     {
@@ -622,7 +622,7 @@ Agent 读取 HEARTBEAT.md
   ],
   "agents": {
     "defaults": {
-      "model": "gpt-4o"
+      "model": "gpt-5.2"
     }
   }
 }
@@ -633,8 +633,8 @@ Agent 读取 HEARTBEAT.md
 **OpenAI**
 ```json
 {
-  "model_name": "gpt-4o",
+  "model_name": "gpt-5.2",
-  "model": "openai/gpt-4o",
+  "model": "openai/gpt-5.2",
   "api_key": "sk-..."
 }
 ```
@@ -693,14 +693,14 @@ Agent 读取 HEARTBEAT.md
 {
   "model_list": [
     {
-      "model_name": "gpt-4o",
+      "model_name": "gpt-5.2",
-      "model": "openai/gpt-4o",
+      "model": "openai/gpt-5.2",
       "api_base": "https://api1.example.com/v1",
       "api_key": "sk-key1"
     },
     {
-      "model_name": "gpt-4o",
+      "model_name": "gpt-5.2",
-      "model": "openai/gpt-4o",
+      "model": "openai/gpt-5.2",
       "api_base": "https://api2.example.com/v1",
       "api_key": "sk-key2"
     }

cmd/picoclaw/cmd_auth.go

@@ -9,6 +9,7 @@ import (
 	"io"
 	"net/http"
 	"os"
+	"strings"
 	"time"
 
 	"github.com/sipeed/picoclaw/pkg/auth"
@@ -118,7 +119,31 @@ func authLoginOpenAI(useDeviceCode bool) {
 
 	appCfg, err := loadConfig()
 	if err == nil {
+		// Update Providers (legacy format)
 		appCfg.Providers.OpenAI.AuthMethod = "oauth"
+
+		// Update or add openai in ModelList
+		foundOpenAI := false
+		for i := range appCfg.ModelList {
+			if isOpenAIModel(appCfg.ModelList[i].Model) {
+				appCfg.ModelList[i].AuthMethod = "oauth"
+				foundOpenAI = true
+				break
+			}
+		}
+
+		// If no openai in ModelList, add it
+		if !foundOpenAI {
+			appCfg.ModelList = append(appCfg.ModelList, config.ModelConfig{
+				ModelName:  "gpt-5.2",
+				Model:      "openai/gpt-5.2",
+				AuthMethod: "oauth",
+			})
+		}
+
+		// Update default model to use OpenAI
+		appCfg.Agents.Defaults.Model = "gpt-5.2"
+
 		if err := config.SaveConfig(getConfigPath(), appCfg); err != nil {
 			fmt.Printf("Warning: could not update config: %v\n", err)
 		}
@@ -128,6 +153,7 @@ func authLoginOpenAI(useDeviceCode bool) {
 	if cred.AccountID != "" {
 		fmt.Printf("Account: %s\n", cred.AccountID)
 	}
+	fmt.Println("Default model set to: gpt-5.2")
 }
 
 func authLoginGoogleAntigravity() {
@@ -167,20 +193,38 @@ func authLoginGoogleAntigravity() {
 
 	appCfg, err := loadConfig()
 	if err == nil {
+		// Update Providers (legacy format, for backward compatibility)
 		appCfg.Providers.Antigravity.AuthMethod = "oauth"
-		if appCfg.Agents.Defaults.Provider == "" {
+
-			appCfg.Agents.Defaults.Provider = "antigravity"
+		// Update or add antigravity in ModelList
+		foundAntigravity := false
+		for i := range appCfg.ModelList {
+			if isAntigravityModel(appCfg.ModelList[i].Model) {
+				appCfg.ModelList[i].AuthMethod = "oauth"
+				foundAntigravity = true
+				break
+			}
 		}
-		if appCfg.Agents.Defaults.Provider == "antigravity" || appCfg.Agents.Defaults.Provider == "google-antigravity" {
+
-			appCfg.Agents.Defaults.Model = "gemini-3-flash"
+		// If no antigravity in ModelList, add it
+		if !foundAntigravity {
+			appCfg.ModelList = append(appCfg.ModelList, config.ModelConfig{
+				ModelName:  "gemini-flash",
+				Model:      "antigravity/gemini-3-flash",
+				AuthMethod: "oauth",
+			})
 		}
+
+		// Update default model
+		appCfg.Agents.Defaults.Model = "gemini-flash"
+
 		if err := config.SaveConfig(getConfigPath(), appCfg); err != nil {
 			fmt.Printf("Warning: could not update config: %v\n", err)
 		}
 	}
 
 	fmt.Println("\n✓ Google Antigravity login successful!")
-	fmt.Println("Config updated: provider=antigravity, model=gemini-3-flash")
+	fmt.Println("Default model set to: gemini-flash")
 	fmt.Println("Try it: picoclaw agent -m \"Hello world\"")
 }
 
@@ -229,8 +273,44 @@ func authLoginPasteToken(provider string) {
 		switch provider {
 		case "anthropic":
 			appCfg.Providers.Anthropic.AuthMethod = "token"
+			// Update ModelList
+			found := false
+			for i := range appCfg.ModelList {
+				if isAnthropicModel(appCfg.ModelList[i].Model) {
+					appCfg.ModelList[i].AuthMethod = "token"
+					found = true
+					break
+				}
+			}
+			if !found {
+				appCfg.ModelList = append(appCfg.ModelList, config.ModelConfig{
+					ModelName:  "claude-sonnet-4",
+					Model:      "anthropic/claude-sonnet-4-20250514",
+					AuthMethod: "token",
+				})
+			}
+			// Update default model
+			appCfg.Agents.Defaults.Model = "claude-sonnet-4"
 		case "openai":
 			appCfg.Providers.OpenAI.AuthMethod = "token"
+			// Update ModelList
+			found := false
+			for i := range appCfg.ModelList {
+				if isOpenAIModel(appCfg.ModelList[i].Model) {
+					appCfg.ModelList[i].AuthMethod = "token"
+					found = true
+					break
+				}
+			}
+			if !found {
+				appCfg.ModelList = append(appCfg.ModelList, config.ModelConfig{
+					ModelName:  "gpt-5.2",
+					Model:      "openai/gpt-5.2",
+					AuthMethod: "token",
+				})
+			}
+			// Update default model
+			appCfg.Agents.Defaults.Model = "gpt-5.2"
 		}
 		if err := config.SaveConfig(getConfigPath(), appCfg); err != nil {
 			fmt.Printf("Warning: could not update config: %v\n", err)
@@ -238,6 +318,7 @@ func authLoginPasteToken(provider string) {
 	}
 
 	fmt.Printf("Token saved for %s!\n", provider)
+	fmt.Printf("Default model set to: %s\n", appCfg.Agents.Defaults.Model)
 }
 
 func authLogoutCmd() {
@@ -262,6 +343,24 @@ func authLogoutCmd() {
 
 		appCfg, err := loadConfig()
 		if err == nil {
+			// Clear AuthMethod in ModelList
+			for i := range appCfg.ModelList {
+				switch provider {
+				case "openai":
+					if isOpenAIModel(appCfg.ModelList[i].Model) {
+						appCfg.ModelList[i].AuthMethod = ""
+					}
+				case "anthropic":
+					if isAnthropicModel(appCfg.ModelList[i].Model) {
+						appCfg.ModelList[i].AuthMethod = ""
+					}
+				case "google-antigravity", "antigravity":
+					if isAntigravityModel(appCfg.ModelList[i].Model) {
+						appCfg.ModelList[i].AuthMethod = ""
+					}
+				}
+			}
+			// Clear AuthMethod in Providers (legacy)
 			switch provider {
 			case "openai":
 				appCfg.Providers.OpenAI.AuthMethod = ""
@@ -282,6 +381,11 @@ func authLogoutCmd() {
 
 		appCfg, err := loadConfig()
 		if err == nil {
+			// Clear all AuthMethods in ModelList
+			for i := range appCfg.ModelList {
+				appCfg.ModelList[i].AuthMethod = ""
+			}
+			// Clear all AuthMethods in Providers (legacy)
 			appCfg.Providers.OpenAI.AuthMethod = ""
 			appCfg.Providers.Anthropic.AuthMethod = ""
 			appCfg.Providers.Antigravity.AuthMethod = ""
@@ -384,3 +488,23 @@ func authModelsCmd() {
 		fmt.Printf("  %s %s\n", status, name)
 	}
 }
+
+// isAntigravityModel checks if a model string belongs to antigravity provider
+func isAntigravityModel(model string) bool {
+	return model == "antigravity" ||
+		model == "google-antigravity" ||
+		strings.HasPrefix(model, "antigravity/") ||
+		strings.HasPrefix(model, "google-antigravity/")
+}
+
+// isOpenAIModel checks if a model string belongs to openai provider
+func isOpenAIModel(model string) bool {
+	return model == "openai" ||
+		strings.HasPrefix(model, "openai/")
+}
+
+// isAnthropicModel checks if a model string belongs to anthropic provider
+func isAnthropicModel(model string) bool {
+	return model == "anthropic" ||
+		strings.HasPrefix(model, "anthropic/")
+}

config/config.example.json

@@ -12,7 +12,7 @@
   "model_list": [
     {
       "model_name": "gpt4",
-      "model": "openai/gpt-4o",
+      "model": "openai/gpt-5.2",
       "api_key": "sk-your-openai-key",
       "api_base": "https://api.openai.com/v1"
     },
@@ -34,13 +34,13 @@
     },
     {
       "model_name": "loadbalanced-gpt4",
-      "model": "openai/gpt-4o",
+      "model": "openai/gpt-5.2",
       "api_key": "sk-key1",
       "api_base": "https://api1.example.com/v1"
     },
     {
       "model_name": "loadbalanced-gpt4",
-      "model": "openai/gpt-4o",
+      "model": "openai/gpt-5.2",
       "api_key": "sk-key2",
       "api_base": "https://api2.example.com/v1"
     }

docs/design/provider-refactoring.md

@@ -66,7 +66,7 @@ Problem: Agent needs to know both `provider` and `model`, adding complexity.
 Inspired by [LiteLLM](https://docs.litellm.ai/docs/proxy/configs) design:
 
 1. **Model-centric**: Users care about models, not providers
-2. **Protocol prefix**: Use `protocol/model_name` format, e.g., `openai/gpt-4o`, `anthropic/claude-3-sonnet`
+2. **Protocol prefix**: Use `protocol/model_name` format, e.g., `openai/gpt-5.2`, `anthropic/claude-3-sonnet`
 3. **Configuration-driven**: Adding new Providers only requires config changes, no code changes
 
 ### 2.2 New Configuration Structure
@@ -81,8 +81,8 @@ Inspired by [LiteLLM](https://docs.litellm.ai/docs/proxy/configs) design:
       "api_key": "sk-xxx"
     },
     {
-      "model_name": "gpt-4o",
+      "model_name": "gpt-5.2",
-      "model": "openai/gpt-4o",
+      "model": "openai/gpt-5.2",
       "api_key": "sk-xxx"
     },
     {
@@ -128,7 +128,7 @@ type Config struct {
 type ModelConfig struct {
     // Required
     ModelName string `json:"model_name"`  // user-facing name (alias)
-    Model     string `json:"model"`       // protocol/model, e.g., openai/gpt-4o
+    Model     string `json:"model"`       // protocol/model, e.g., openai/gpt-5.2
 
     // Common config
     APIBase   string `json:"api_base,omitempty"`
@@ -180,7 +180,7 @@ Identify protocol via prefix in `model` field:
       "model": "deepseek-chat"
     },
     "coder": {
-      "model": "gpt-4o",
+      "model": "gpt-5.2",
       "system_prompt": "You are a coding assistant..."
     },
     "translator": {
@@ -200,7 +200,7 @@ Each Agent only needs to specify `model` (corresponds to `model_name` in `model_
 model_list:
   - model_name: gpt-4o
     litellm_params:
-      model: openai/gpt-4o
+      model: openai/gpt-5.2
       api_key: xxx
   - model_name: my-custom
     litellm_params:

docs/migration/model-list-migration.md

@@ -40,7 +40,7 @@ The new `model_list` configuration offers several advantages:
   "agents": {
     "defaults": {
       "provider": "openai",
-      "model": "gpt-4o"
+      "model": "gpt-5.2"
     }
   }
 }
@@ -53,7 +53,7 @@ The new `model_list` configuration offers several advantages:
   "model_list": [
     {
       "model_name": "gpt4",
-      "model": "openai/gpt-4o",
+      "model": "openai/gpt-5.2",
       "api_key": "sk-your-openai-key",
       "api_base": "https://api.openai.com/v1"
     },
@@ -82,7 +82,7 @@ The `model` field uses a protocol prefix format: `[protocol/]model-identifier`
 
 | Prefix | Description | Example |
 |--------|-------------|---------|
-| `openai/` | OpenAI API (default) | `openai/gpt-4o` |
+| `openai/` | OpenAI API (default) | `openai/gpt-5.2` |
 | `anthropic/` | Anthropic API | `anthropic/claude-3-opus` |
 | `antigravity/` | Google via Antigravity OAuth | `antigravity/gemini-2.0-flash` |
 | `claude-cli/` | Claude CLI (local) | `claude-cli/claude-3-sonnet` |
@@ -101,7 +101,7 @@ The `model` field uses a protocol prefix format: `[protocol/]model-identifier`
 | Field | Required | Description |
 |-------|----------|-------------|
 | `model_name` | Yes | User-facing alias for the model |
-| `model` | Yes | Protocol and model identifier (e.g., `openai/gpt-4o`) |
+| `model` | Yes | Protocol and model identifier (e.g., `openai/gpt-5.2`) |
 | `api_base` | No | API endpoint URL |
 | `api_key` | No* | API authentication key |
 | `proxy` | No | HTTP proxy URL |
@@ -121,19 +121,19 @@ Configure multiple endpoints for the same model to distribute load:
   "model_list": [
     {
       "model_name": "gpt4",
-      "model": "openai/gpt-4o",
+      "model": "openai/gpt-5.2",
       "api_key": "sk-key1",
       "api_base": "https://api1.example.com/v1"
     },
     {
       "model_name": "gpt4",
-      "model": "openai/gpt-4o",
+      "model": "openai/gpt-5.2",
       "api_key": "sk-key2",
       "api_base": "https://api2.example.com/v1"
     },
     {
       "model_name": "gpt4",
-      "model": "openai/gpt-4o",
+      "model": "openai/gpt-5.2",
       "api_key": "sk-key3",
       "api_base": "https://api3.example.com/v1"
     }

pkg/config/defaults.go

@@ -105,8 +105,8 @@ func DefaultConfig() *Config {
 
 			// OpenAI - https://platform.openai.com/api-keys
 			{
-				ModelName: "gpt-4o",
+				ModelName: "gpt-5.2",
-				Model:     "openai/gpt-4o",
+				Model:     "openai/gpt-5.2",
 				APIBase:   "https://api.openai.com/v1",
 				APIKey:    "",
 			},
@@ -161,8 +161,8 @@ func DefaultConfig() *Config {
 
 			// OpenRouter (100+ models) - https://openrouter.ai/keys
 			{
-				ModelName: "openrouter-gpt-4o",
+				ModelName: "openrouter-gpt-5.2",
-				Model:     "openrouter/openai/gpt-4o",
+				Model:     "openrouter/openai/gpt-5.2",
 				APIBase:   "https://openrouter.ai/api/v1",
 				APIKey:    "",
 			},
@@ -208,8 +208,8 @@ func DefaultConfig() *Config {
 
 			// GitHub Copilot - https://github.com/settings/tokens
 			{
-				ModelName:  "copilot-gpt-4o",
+				ModelName:  "copilot-gpt-5.2",
-				Model:      "github-copilot/gpt-4o",
+				Model:      "github-copilot/gpt-5.2",
 				APIBase:    "http://localhost:4321",
 				AuthMethod: "oauth",
 			},

pkg/config/migration.go

@@ -50,7 +50,7 @@ func ConvertProvidersToModelList(cfg *Config) []ModelConfig {
 				}
 				return ModelConfig{
 					ModelName:  "openai",
-					Model:      "openai/gpt-4o",
+					Model:      "openai/gpt-5.2",
 					APIKey:     p.OpenAI.APIKey,
 					APIBase:    p.OpenAI.APIBase,
 					Proxy:      p.OpenAI.Proxy,
@@ -276,7 +276,7 @@ func ConvertProvidersToModelList(cfg *Config) []ModelConfig {
 				}
 				return ModelConfig{
 					ModelName:   "github-copilot",
-					Model:       "github-copilot/gpt-4o",
+					Model:       "github-copilot/gpt-5.2",
 					APIBase:     p.GitHubCopilot.APIBase,
 					ConnectMode: p.GitHubCopilot.ConnectMode,
 				}, true

pkg/config/migration_test.go

@@ -31,8 +31,8 @@ func TestConvertProvidersToModelList_OpenAI(t *testing.T) {
 	if result[0].ModelName != "openai" {
 		t.Errorf("ModelName = %q, want %q", result[0].ModelName, "openai")
 	}
-	if result[0].Model != "openai/gpt-4o" {
+	if result[0].Model != "openai/gpt-5.2" {
-		t.Errorf("Model = %q, want %q", result[0].Model, "openai/gpt-4o")
+		t.Errorf("Model = %q, want %q", result[0].Model, "openai/gpt-5.2")
 	}
 	if result[0].APIKey != "sk-test-key" {
 		t.Errorf("APIKey = %q, want %q", result[0].APIKey, "sk-test-key")
@@ -331,8 +331,8 @@ func TestConvertProvidersToModelList_MultipleProviders_PreservesUserModel(t *tes
 	for _, mc := range result {
 		switch mc.ModelName {
 		case "openai":
-			if mc.Model != "openai/gpt-4o" {
+			if mc.Model != "openai/gpt-5.2" {
-				t.Errorf("OpenAI Model = %q, want %q (default)", mc.Model, "openai/gpt-4o")
+				t.Errorf("OpenAI Model = %q, want %q (default)", mc.Model, "openai/gpt-5.2")
 			}
 		case "deepseek":
 			if mc.Model != "deepseek/deepseek-reasoner" {

pkg/providers/factory_provider.go

@@ -67,10 +67,29 @@ func CreateProviderFromConfig(cfg *config.ModelConfig) (LLMProvider, string, err
 	protocol, modelID := ExtractProtocol(cfg.Model)
 
 	switch protocol {
-	case "openai", "openrouter", "groq", "zhipu", "gemini", "nvidia",
+	case "openai":
+		// OpenAI with OAuth/token auth (Codex-style)
+		if cfg.AuthMethod == "oauth" || cfg.AuthMethod == "token" {
+			provider, err := createCodexAuthProvider()
+			if err != nil {
+				return nil, "", err
+			}
+			return provider, modelID, nil
+		}
+		// OpenAI with API key
+		if cfg.APIKey == "" && cfg.APIBase == "" {
+			return nil, "", fmt.Errorf("api_key or api_base is required for HTTP-based protocol %q", protocol)
+		}
+		apiBase := cfg.APIBase
+		if apiBase == "" {
+			apiBase = getDefaultAPIBase(protocol)
+		}
+		return NewHTTPProviderWithMaxTokensField(cfg.APIKey, apiBase, cfg.Proxy, cfg.MaxTokensField), modelID, nil
+
+	case "openrouter", "groq", "zhipu", "gemini", "nvidia",
 		"ollama", "moonshot", "shengsuanyun", "deepseek", "cerebras",
 		"volcengine", "vllm", "qwen":
-		// All OpenAI-compatible HTTP providers
+		// All other OpenAI-compatible HTTP providers
 		if cfg.APIKey == "" && cfg.APIBase == "" {
 			return nil, "", fmt.Errorf("api_key or api_base is required for HTTP-based protocol %q", protocol)
 		}