feat: interactive onboard wizard — pick provider and enter API key in one step

Previously, 'v1claw onboard' generated a config with a hardcoded Chinese
model (glm-4.7) and told users to manually edit JSON. Now it interactively
asks which provider to use (Gemini recommended as free), prompts for the
API key, and sets the correct model automatically. Config is ready to use
immediately — no manual editing needed.

Changes:
- Add interactive provider selection + API key prompt to onboard command
- Change default model from 'glm-4.7' to empty (set during onboard)
- Update config.example.json to show gemini-2.0-flash
- Simplify README setup steps across all 4 platforms (remove manual JSON
  editing step)
- Update tests to reflect new empty default model

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Author: amit-vikramaditya

README.md

@@ -197,91 +197,31 @@ This compiles V1Claw into a single file. It takes 2-5 minutes on a phone. When i
 ./build/v1claw-linux-arm64 onboard
 ```
 
-This creates your config file at `~/.v1claw/config.json`.
+The setup wizard will ask you to:
+1. **Pick your AI provider** (Gemini is free and recommended)
+2. **Paste your API key**
 
-#### Step 7: Add your API key
+That's it — your config is ready at `~/.v1claw/config.json`.
 
-Open the config file in a text editor:
+> **Don't have an API key yet?** Press Enter to pick Gemini, then get a free key at [aistudio.google.com/apikey](https://aistudio.google.com/apikey). You can re-run `onboard` anytime, or edit the config manually with `nano ~/.v1claw/config.json`.
 
-```bash
-nano ~/.v1claw/config.json
-```
-
-Find the `"agents"` section and change the model name. Find the `"providers"` section and add your API key.
-
-**If you're using Google Gemini** (free), change it to look like this:
-
-```json
-{
-  "agents": [
-    {
-      "name": "v1claw",
-      "model": "gemini-2.0-flash"
-    }
-  ],
-  "providers": {
-    "gemini": {
-      "api_key": "YOUR_GEMINI_API_KEY_HERE"
-    }
-  }
-}
-```
-
-**If you're using OpenAI:**
-
-```json
-{
-  "agents": [
-    {
-      "name": "v1claw",
-      "model": "gpt-4o"
-    }
-  ],
-  "providers": {
-    "openai": {
-      "api_key": "sk-YOUR_OPENAI_KEY_HERE"
-    }
-  }
-}
-```
-
-**If you're using Anthropic Claude:**
-
-```json
-{
-  "agents": [
-    {
-      "name": "v1claw",
-      "model": "claude-sonnet-4-20250514"
-    }
-  ],
-  "providers": {
-    "anthropic": {
-      "api_key": "sk-ant-YOUR_KEY_HERE"
-    }
-  }
-}
-```
-
-Save the file: press `Ctrl+O`, then `Enter`, then `Ctrl+X`.
-
-#### Step 8: Test it!
+#### Step 7: Test it!
 
 ```bash
 ./build/v1claw-linux-arm64 agent -m "Hello! What can you do?"
 ```
 
 You should see the AI respond. **If it does — congratulations, V1Claw is working on your phone!** 🎉
 
-#### Step 9: Start chatting
+#### Step 8: Start chatting
 
 ```bash
 ./build/v1claw-linux-arm64 agent
 ```
 
 This opens an interactive chat. Type anything and press Enter. Type `exit` or press `Ctrl+C` to quit.
 
-#### Step 10: Enable phone hardware (optional)
+#### Step 9: Enable phone hardware (optional)
 
 Want V1Claw to use your mic, camera, or read notifications? Edit the config again:
 
@@ -309,7 +249,7 @@ Add a `"permissions"` section (you can turn each feature on or off individually)
 
 > 🔒 **Every feature is OFF by default.** Only turn on what you need. You can change these anytime by editing the config and restarting.
 
-#### Step 11: Run V1Claw 24/7 in the background (optional)
+#### Step 10: Run V1Claw 24/7 in the background (optional)
 
 ```bash
 nohup ./build/v1claw-linux-arm64 gateway > v1claw.log 2>&1 &
@@ -391,31 +331,23 @@ The binary will appear at `build/v1claw-darwin-arm64` (Apple Silicon) or `build/
 ./build/v1claw-darwin-* onboard
 ```
 
-#### Step 5: Add your API key
-
-```bash
-nano ~/.v1claw/config.json
-```
-
-Change the model and add your API key (see the Android Step 7 above for examples with Gemini, OpenAI, or Claude).
-
-Save: `Ctrl+O` → Enter → `Ctrl+X`.
+The setup wizard will ask you to pick a provider and enter your API key. Your config is ready immediately.
 
-#### Step 6: Test it
+#### Step 5: Test it
 
 ```bash
 ./build/v1claw-darwin-* agent -m "Hello! Tell me a fun fact."
 ```
 
 If you see a response — **it's working!** 🎉
 
-#### Step 7: Interactive chat
+#### Step 6: Interactive chat
 
 ```bash
 ./build/v1claw-darwin-* agent
 ```
 
-#### Step 8: Run as a 24/7 service (optional)
+#### Step 7: Run as a 24/7 service (optional)
 
 ```bash
 # Quick background mode
@@ -478,23 +410,15 @@ The binary will appear at `build/v1claw-linux-amd64` or `build/v1claw-linux-arm6
 ./build/v1claw-linux-* onboard
 ```
 
-#### Step 5: Add your API key
-
-```bash
-nano ~/.v1claw/config.json
-```
-
-Change the model and add your API key (see the Android Step 7 above for examples with Gemini, OpenAI, or Claude).
-
-Save: `Ctrl+O` → Enter → `Ctrl+X`.
+The setup wizard will ask you to pick a provider and enter your API key. Your config is ready immediately.
 
-#### Step 6: Test it
+#### Step 5: Test it
 
 ```bash
 ./build/v1claw-linux-* agent -m "Hello! What can you do?"
 ```
 
-#### Step 7: Run as a 24/7 system service (optional)
+#### Step 6: Run as a 24/7 system service (optional)
 
 ```bash
 # Install the binary
@@ -572,19 +496,15 @@ go build -o build/v1claw.exe ./cmd/v1claw
 build\v1claw.exe onboard
 ```
 
-#### Step 5: Add your API key
-
-Open the config file at `%USERPROFILE%\.v1claw\config.json` in Notepad or any text editor.
-
-Change the model and add your API key (see the Android Step 7 above for examples with Gemini, OpenAI, or Claude).
+The setup wizard will ask you to pick a provider and enter your API key. Your config is ready immediately.
 
-#### Step 6: Test it
+#### Step 5: Test it
 
 ```bash
 build\v1claw.exe agent -m "Hello! What can you do?"
 ```
 
-#### Step 7: Interactive chat
+#### Step 6: Interactive chat
 
 ```bash
 build\v1claw.exe agent
@@ -608,7 +528,7 @@ cd V1Claw
 
 # Copy the example config and edit it
 cp config/config.example.json config/config.json
-nano config/config.json   # Add your API key (see Android Step 7 above)
+nano config/config.json   # Add your provider API key
 
 # Run a one-shot query
 docker compose run --rm v1claw-agent -m "Hello V1Claw!"

cmd/v1claw/main.go

@@ -247,6 +247,78 @@ func onboard() {
 	}
 
 	cfg := config.DefaultConfig()
+
+	// Interactive provider setup
+	scanner := bufio.NewScanner(os.Stdin)
+
+	fmt.Println("\n🔧 Let's set up your AI provider.")
+	fmt.Println("")
+	fmt.Println("Pick a provider:")
+	fmt.Println("  1. Google Gemini  (free — recommended)")
+	fmt.Println("  2. OpenAI         (GPT-5, GPT-4)")
+	fmt.Println("  3. Anthropic      (Claude)")
+	fmt.Println("  4. Groq           (fast, free tier)")
+	fmt.Println("  5. DeepSeek")
+	fmt.Println("  6. OpenRouter     (100+ models)")
+	fmt.Println("  7. Ollama         (local, no API key)")
+	fmt.Println("  8. Skip           (configure later)")
+	fmt.Print("\nEnter number [1]: ")
+
+	choice := "1"
+	if scanner.Scan() {
+		t := strings.TrimSpace(scanner.Text())
+		if t != "" {
+			choice = t
+		}
+	}
+
+	type providerInfo struct {
+		name    string
+		model   string
+		keyHint string
+		keyURL  string
+	}
+
+	providerMap := map[string]providerInfo{
+		"1": {name: "gemini", model: "gemini-2.0-flash", keyHint: "Gemini API key", keyURL: "https://aistudio.google.com/apikey"},
+		"2": {name: "openai", model: "gpt-4o", keyHint: "OpenAI API key (starts with sk-)", keyURL: "https://platform.openai.com/api-keys"},
+		"3": {name: "anthropic", model: "claude-sonnet-4-20250514", keyHint: "Anthropic API key (starts with sk-ant-)", keyURL: "https://console.anthropic.com/keys"},
+		"4": {name: "groq", model: "llama-3.3-70b-versatile", keyHint: "Groq API key", keyURL: "https://console.groq.com/keys"},
+		"5": {name: "deepseek", model: "deepseek-chat", keyHint: "DeepSeek API key", keyURL: "https://platform.deepseek.com/api_keys"},
+		"6": {name: "openrouter", model: "google/gemini-2.0-flash-exp:free", keyHint: "OpenRouter API key", keyURL: "https://openrouter.ai/keys"},
+		"7": {name: "ollama", model: "llama3.2"},
+	}
+
+	if info, ok := providerMap[choice]; ok {
+		cfg.Agents.Defaults.Model = info.model
+
+		if info.name == "ollama" {
+			cfg.Providers.Ollama.APIBase = "http://localhost:11434/v1"
+			fmt.Println("\n✓ Ollama selected. Make sure Ollama is running locally.")
+			fmt.Printf("  Model: %s (change with: ollama pull <model>)\n", info.model)
+		} else {
+			fmt.Printf("\nGet your key at: %s\n", info.keyURL)
+			fmt.Printf("Enter your %s: ", info.keyHint)
+
+			apiKey := ""
+			if scanner.Scan() {
+				apiKey = strings.TrimSpace(scanner.Text())
+			}
+
+			if apiKey == "" {
+				fmt.Println("\n⚠ No API key entered. You can add it later in:", configPath)
+			} else {
+				setProviderKey(cfg, info.name, apiKey)
+				fmt.Println("\n✓ API key saved.")
+			}
+			fmt.Printf("  Model: %s\n", cfg.Agents.Defaults.Model)
+		}
+	} else if choice != "8" {
+		fmt.Println("\n⚠ Invalid choice. You can configure manually in:", configPath)
+	} else {
+		fmt.Println("\n⚠ Skipped. Add your provider and API key in:", configPath)
+	}
+
 	if err := config.SaveConfig(configPath, cfg); err != nil {
 		fmt.Printf("Error saving config: %v\n", err)
 		os.Exit(1)
@@ -255,11 +327,26 @@ func onboard() {
 	workspace := cfg.WorkspacePath()
 	createWorkspaceTemplates(workspace)
 
-	fmt.Printf("%s V1 is ready!\n", logo)
-	fmt.Println("\nNext steps:")
-	fmt.Println("  1. Add your API key to", configPath)
-	fmt.Println("     Get one at: https://openrouter.ai/keys")
-	fmt.Println("  2. Chat: v1claw agent -m \"Hello!\"")
+	fmt.Printf("\n%s V1 is ready!\n", logo)
+	fmt.Println("\nTry it out:")
+	fmt.Println("  v1claw agent -m \"Hello!\"")
+}
+
+func setProviderKey(cfg *config.Config, provider, key string) {
+	switch provider {
+	case "gemini":
+		cfg.Providers.Gemini.APIKey = key
+	case "openai":
+		cfg.Providers.OpenAI.APIKey = key
+	case "anthropic":
+		cfg.Providers.Anthropic.APIKey = key
+	case "groq":
+		cfg.Providers.Groq.APIKey = key
+	case "deepseek":
+		cfg.Providers.DeepSeek.APIKey = key
+	case "openrouter":
+		cfg.Providers.OpenRouter.APIKey = key
+	}
 }
 
 func copyEmbeddedToTarget(targetDir string) error {

config/config.example.json

@@ -3,7 +3,7 @@
     "defaults": {
       "workspace": "~/.v1claw/workspace",
       "restrict_to_workspace": true,
-      "model": "glm-4.7",
+      "model": "gemini-2.0-flash",
       "max_tokens": 8192,
       "temperature": 0.7,
       "max_tool_iterations": 20

pkg/config/config.go

@@ -271,7 +271,7 @@ func DefaultConfig() *Config {
 				Workspace:           "~/.v1claw/workspace",
 				RestrictToWorkspace: true,
 				Provider:            "",
-				Model:               "glm-4.7",
+				Model:               "",
 				MaxTokens:           8192,
 				Temperature:         0.7,
 				MaxToolIterations:   20,

pkg/config/config_test.go

@@ -27,12 +27,12 @@ func TestDefaultConfig_WorkspacePath(t *testing.T) {
 	}
 }
 
-// TestDefaultConfig_Model verifies model is set
+// TestDefaultConfig_Model verifies model default is empty (set during interactive onboard)
 func TestDefaultConfig_Model(t *testing.T) {
 	cfg := DefaultConfig()
 
-	if cfg.Agents.Defaults.Model == "" {
-		t.Error("Model should not be empty")
+	if cfg.Agents.Defaults.Model != "" {
+		t.Errorf("Model should be empty by default, got %q", cfg.Agents.Defaults.Model)
 	}
 }
 
@@ -182,9 +182,7 @@ func TestConfig_Complete(t *testing.T) {
 	if cfg.Agents.Defaults.Workspace == "" {
 		t.Error("Workspace should not be empty")
 	}
-	if cfg.Agents.Defaults.Model == "" {
-		t.Error("Model should not be empty")
-	}
+	// Model is empty by default (set during interactive onboard)
 	if cfg.Agents.Defaults.Temperature == 0 {
 		t.Error("Temperature should have default value")
 	}

pkg/migrate/migrate_test.go

@@ -293,8 +293,8 @@ func TestConvertConfig(t *testing.T) {
 		if len(warnings) != 0 {
 			t.Errorf("expected no warnings, got %v", warnings)
 		}
-		if cfg.Agents.Defaults.Model != "glm-4.7" {
-			t.Errorf("default model should be glm-4.7, got %q", cfg.Agents.Defaults.Model)
+		if cfg.Agents.Defaults.Model != "" {
+			t.Errorf("default model should be empty, got %q", cfg.Agents.Defaults.Model)
 		}
 	})
 }