admin/ClaudeCode-Custom-Skills
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Compare commits

base: admin:cf0d6489d18cc6e5f91ec3bfd1cf807794bb4d6f
Branches Tags
admin:main
...
compare: admin:fb1f68015a7b72d389baaa8d10107a4a4f8015ca
Branches Tags
admin:main

2 Commits
cf0d6489d1 ... fb1f68015a

  • feat: use correct DashScope API endpoint for Qwen OAuth 
    Based on ZeroClaw implementation study:
- Change API endpoint from api.qwen.ai to dashscope.aliyuncs.com/compatible-mode/v1
- Update credentials file reference to oauth_creds.json
- Add ZeroClaw native qwen-oauth provider documentation
- Add API endpoints and models reference table
- Update import script with correct endpoint and platform support
- Add PicoClaw and NanoClaw platform configurations

Key findings from ZeroClaw binary:
- Native qwen-oauth provider with auto token refresh
- Uses DashScope OpenAI-compatible endpoint
- Reads ~/.qwen/oauth_creds.json directly

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
    Claude Code · 2026-02-22 05:07:51 -05:00
    fb1f68015a
  • docs: clarify ZeroClaw native qwen-oauth vs OpenAI-compatible import 
    - Document ZeroClaw's native qwen-oauth provider with auto token refresh
- Explain two import methods: Native vs OpenAI-compatible
- Add OAuth credentials structure documentation
- Add comparison table showing feature differences
- Update platform table to show ZeroClaw has Native (not Import) OAuth support

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
    Claude Code · 2026-02-22 04:48:44 -05:00
    c8ef0ee3b5
3 changed files with 421 additions and 249 deletions
Expand all files Collapse all files

169
skills/claw-setup/README.md
View File

@@ -78,7 +78,7 @@
| **OpenClaw** | TypeScript | >1GB | ~500s | ✅ Import | ✅ | Full-featured, 1700+ plugins | | **OpenClaw** | TypeScript | >1GB | ~500s | ✅ Import | ✅ | Full-featured, 1700+ plugins |
| **NanoBot** | Python | ~100MB | ~30s | ✅ Import | ✅ | Research, Python devs | | **NanoBot** | Python | ~100MB | ~30s | ✅ Import | ✅ | Research, Python devs |
| **PicoClaw** | Go | <10MB | ~1s | ✅ Import | ✅ | Embedded, $10 hardware | | **PicoClaw** | Go | <10MB | ~1s | ✅ Import | ✅ | Embedded, $10 hardware |
| **ZeroClaw** | Rust | <5MB | <10ms | ✅ Import | ✅ | Maximum performance | | **ZeroClaw** | Rust | <5MB | <10ms | ✅ Native | ✅ | Maximum performance |
| **NanoClaw** | TypeScript | ~50MB | ~5s | ✅ Import | ✅ | WhatsApp integration | | **NanoClaw** | TypeScript | ~50MB | ~5s | ✅ Import | ✅ | WhatsApp integration |
### Platform Selection Guide ### Platform Selection Guide
@@ -126,66 +126,163 @@
### Quick Start ### Quick Start
```bash ```bash
# Step 1: Install Qwen Code # Step 1: Install Qwen Code CLI
npm install -g @qwen-code/qwen-code@latest npm install -g @qwen-code/qwen-code@latest
# Step 2: Get FREE OAuth # Step 2: Get FREE OAuth (opens browser for login)
qwen qwen --auth-type qwen-oauth -p "test"
/auth # Select "Qwen OAuth" → Browser login with qwen.ai # Credentials saved to: ~/.qwen/oauth_creds.json
# Step 3: Import to ANY platform # Step 3: Import to ANY platform
source ~/.qwen/.env && openclaw
source ~/.qwen/.env && nanobot gateway # ZeroClaw (native provider - auto token refresh)
source ~/.qwen/.env && picoclaw gateway cat > ~/.zeroclaw/config.toml << EOF
source ~/.qwen/.env && zeroclaw gateway default_provider = "qwen-oauth"
default_model = "qwen3-coder-plus"
EOF
# Other platforms (OpenAI-compatible)
export OPENAI_API_KEY=$(cat ~/.qwen/oauth_creds.json | jq -r '.access_token')
export OPENAI_BASE_URL="https://dashscope.aliyuncs.com/compatible-mode/v1"
``` ```
### Platform-Specific Import ### Platform-Specific Import
#### OpenClaw + FREE Qwen #### OpenClaw + FREE Qwen (OpenAI-Compatible)
```bash ```bash
git clone https://github.com/openclaw/openclaw.git git clone https://github.com/openclaw/openclaw.git
cd openclaw && npm install cd openclaw && npm install
export OPENAI_API_KEY=$(cat ~/.qwen/oauth-token.json | jq -r '.access_token') # Extract token from Qwen OAuth credentials
export OPENAI_BASE_URL="https://api.qwen.ai/v1" export OPENAI_API_KEY=$(cat ~/.qwen/oauth_creds.json | jq -r '.access_token')
export OPENAI_BASE_URL="https://dashscope.aliyuncs.com/compatible-mode/v1"
export OPENAI_MODEL="qwen3-coder-plus" export OPENAI_MODEL="qwen3-coder-plus"
npm run start npm run start
``` ```
#### NanoBot + FREE Qwen #### NanoBot + FREE Qwen (OpenAI-Compatible)
```bash ```bash
pip install nanobot-ai pip install nanobot-ai
cat > ~/.nanobot/config.json << CONFIG # Extract token and configure
{ export OPENAI_API_KEY=$(cat ~/.qwen/oauth_creds.json | jq -r '.access_token')
"providers": { export OPENAI_BASE_URL="https://dashscope.aliyuncs.com/compatible-mode/v1"
"qwen": { export OPENAI_MODEL="qwen3-coder-plus"
"apiKey": "$(cat ~/.qwen/oauth-token.json | jq -r '.access_token')",
"baseURL": "https://api.qwen.ai/v1"
}
},
"agents": { "defaults": { "model": "qwen/qwen3-coder-plus" } }
}
CONFIG
nanobot gateway nanobot gateway
``` ```
#### ZeroClaw + FREE Qwen #### PicoClaw + FREE Qwen (OpenAI-Compatible)
```bash
# Extract token and set environment
export OPENAI_API_KEY=$(cat ~/.qwen/oauth_creds.json | jq -r '.access_token')
export OPENAI_BASE_URL="https://dashscope.aliyuncs.com/compatible-mode/v1"
picoclaw gateway
```
#### NanoClaw + FREE Qwen (OpenAI-Compatible)
```bash
# Extract token and set environment
export OPENAI_API_KEY=$(cat ~/.qwen/oauth_creds.json | jq -r '.access_token')
export OPENAI_BASE_URL="https://dashscope.aliyuncs.com/compatible-mode/v1"
nanoclaw
```
#### ZeroClaw + FREE Qwen (NATIVE Provider)
```bash ```bash
# Install ZeroClaw # Install ZeroClaw
wget https://github.com/zeroclaw-labs/zeroclaw/releases/latest/zeroclaw-linux-amd64 wget https://github.com/zeroclaw-labs/zeroclaw/releases/latest/zeroclaw-linux-amd64
chmod +x zeroclaw-linux-amd64 && sudo mv zeroclaw-linux-amd64 /usr/local/bin/zeroclaw chmod +x zeroclaw-linux-amd64 && sudo mv zeroclaw-linux-amd64 /usr/local/bin/zeroclaw
# Import Qwen OAuth # ZeroClaw has NATIVE qwen-oauth provider support!
export OPENAI_API_KEY=$(cat ~/.qwen/oauth-token.json | jq -r '.access_token') # First, get OAuth credentials via Qwen Code:
export OPENAI_MODEL="qwen3-coder-plus" qwen && /auth # Select Qwen OAuth → creates ~/.qwen/oauth_creds.json
# Configure ZeroClaw to use native qwen-oauth provider
cat > ~/.zeroclaw/config.toml << CONFIG
default_provider = "qwen-oauth"
default_model = "qwen3-coder-plus"
default_temperature = 0.7
CONFIG
# ZeroClaw reads ~/.qwen/oauth_creds.json directly with auto token refresh!
zeroclaw gateway zeroclaw gateway
``` ```
### Understanding Qwen OAuth Import Methods
```
┌─────────────────────────────────────────────────────────────────────────────┐
│ QWEN OAUTH IMPORT METHODS │
├─────────────────────────────────────────────────────────────────────────────┤
│ │
│ METHOD 1: Native Provider (ZeroClaw ONLY) │
│ ───────────────────────────────────────────────────── │
│ • ZeroClaw has built-in "qwen-oauth" provider │
│ • Reads ~/.qwen/oauth_creds.json directly │
│ • Automatic token refresh using refresh_token │
│ • Tracks expiry_date and refreshes when needed │
│ • Configuration: default_provider = "qwen-oauth" │
│ │
│ METHOD 2: OpenAI-Compatible (All Other Platforms) │
│ ───────────────────────────────────────────────────── │
│ • Treats Qwen API as OpenAI-compatible endpoint │
│ • Extract access_token and use as OPENAI_API_KEY │
│ • Set OPENAI_BASE_URL=https://dashscope.aliyuncs.com/compatible-mode/v1 │
│ • Manual re-export needed when token expires │
│ │
│ COMPARISON: │
│ ┌─────────────────┬────────────────┬─────────────────────┐ │
│ │ Feature │ Native │ OpenAI-Compatible │ │
│ ├─────────────────┼────────────────┼─────────────────────┤ │
│ │ Token Refresh │ ✅ Automatic │ ❌ Manual │ │
│ │ Token Expiry │ ✅ Handled │ ⚠️ Re-export needed│ │
│ │ Platforms │ ZeroClaw only │ All others │ │
│ │ Config File │ ~/.qwen/oauth_creds.json │ env vars │ │
│ └─────────────────┴────────────────┴─────────────────────┘ │
│ │
└─────────────────────────────────────────────────────────────────────────────┘
```
### OAuth Credentials Structure
Qwen Code stores OAuth credentials in `~/.qwen/oauth_creds.json`:
```json
{
"access_token": "pIFwnvSC3fQPG0i5waDbozvUNEWE4w9x...",
"refresh_token": "9Fm_Ob-c8_WAT_3QvgGwVGfgoNfAdP...",
"token_type": "Bearer",
"resource_url": "portal.qwen.ai",
"expiry_date": 1771774796531
}
```
| Field | Purpose |
|-------|---------|
| `access_token` | Used for API authentication |
| `refresh_token` | Used to get new access_token when expired |
| `expiry_date` | Unix timestamp when access_token expires |
### API Endpoints
| Endpoint | URL |
|----------|-----|
| **API Base** | `https://dashscope.aliyuncs.com/compatible-mode/v1` |
| **Chat Completions** | `https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions` |
| **Token Refresh** | `https://chat.qwen.ai/api/v1/oauth2/token` |
### Available Models (FREE Tier)
| Model | Best For |
|-------|----------|
| `qwen3-coder-plus` | Coding (recommended) |
| `qwen3-coder-flash` | Fast coding |
| `qwen-max` | Complex tasks |
--- ---
## 🤖 FEATURE 2: 25+ AI Providers ## 🤖 FEATURE 2: 25+ AI Providers
@@ -412,10 +509,11 @@ zeroclaw gateway
```bash ```bash
# ~/.qwen/.env or ~/.config/claw/.env # ~/.qwen/.env or ~/.config/claw/.env
# Qwen OAuth (FREE - from qwen && /auth) # Qwen OAuth (FREE - from qwen --auth-type qwen-oauth)
OPENAI_API_KEY=$(cat ~/.qwen/oauth-token.json | jq -r '.access_token') # Credentials stored in: ~/.qwen/oauth_creds.json
OPENAI_BASE_URL=https://api.qwen.ai/v1 export OPENAI_API_KEY=$(cat ~/.qwen/oauth_creds.json | jq -r '.access_token')
OPENAI_MODEL=qwen3-coder-plus export OPENAI_BASE_URL="https://dashscope.aliyuncs.com/compatible-mode/v1"
export OPENAI_MODEL="qwen3-coder-plus"
# Or use paid providers # Or use paid providers
ANTHROPIC_API_KEY=sk-ant-xxx ANTHROPIC_API_KEY=sk-ant-xxx
@@ -508,8 +606,11 @@ source ~/.qwen/.env
### API Errors ### API Errors
```bash ```bash
# Verify token is valid # Verify token is valid
curl -H "Authorization: Bearer $OPENAI_API_KEY" \ QWEN_TOKEN=$(cat ~/.qwen/oauth_creds.json | jq -r '.access_token')
https://api.qwen.ai/v1/models curl -X POST "https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions" \
-H "Authorization: Bearer $QWEN_TOKEN" \
-H "Content-Type: application/json" \
-d '{"model": "qwen3-coder-plus", "messages": [{"role": "user", "content": "Hello"}]}'
# Check rate limits # Check rate limits
# FREE tier: 60 req/min, 2000/day # FREE tier: 60 req/min, 2000/day

244
skills/claw-setup/SKILL.md
View File

@@ -1,14 +1,14 @@
--- ---
name: claw-setup name: claw-setup
description: Use this skill when the user asks to "setup openclaw", "install nanobot", "deploy zeroclaw", "configure picoclaw", "setup qwen code", "import qwen oauth", "use free qwen tier", "configure AI providers", "add openai provider", "AI agent setup", or mentions setting up AI platforms. description: Use this skill when the user asks to "setup openclaw", "install nanobot", "deploy zeroclaw", "configure picoclaw", "setup qwen code", "import qwen oauth", "use free qwen tier", "configure AI providers", "add openai provider", "AI agent setup", or mentions setting up AI platforms.
version: 1.3.0 version: 2.0.0
--- ---
# Claw Setup Skill # Claw Setup Skill
End-to-end professional setup of AI Agent platforms with **25+ OpenCode-compatible providers** and **FREE Qwen OAuth cross-platform import**. End-to-end professional setup of AI Agent platforms with **25+ OpenCode-compatible providers** and **FREE Qwen OAuth cross-platform import**.
## ⭐ Two Key Features ## Two Key Features
``` ```
┌─────────────────────────────────────────────────────────────────┐ ┌─────────────────────────────────────────────────────────────────┐
@@ -21,6 +21,7 @@ End-to-end professional setup of AI Agent platforms with **25+ OpenCode-compatib
│ • Works with: OpenClaw, NanoBot, PicoClaw, ZeroClaw │ │ • Works with: OpenClaw, NanoBot, PicoClaw, ZeroClaw │
│ • Model: Qwen3-Coder (optimized for coding) │ │ • Model: Qwen3-Coder (optimized for coding) │
│ • Auth: Browser OAuth via qwen.ai │ │ • Auth: Browser OAuth via qwen.ai │
│ • Token refresh: Automatic (ZeroClaw) / Manual (others) │
│ │ │ │
│ FEATURE 2: 25+ OpenCode-Compatible AI Providers │ │ FEATURE 2: 25+ OpenCode-Compatible AI Providers │
│ ───────────────────────────────────────────────── │ │ ───────────────────────────────────────────────── │
@@ -38,10 +39,10 @@ End-to-end professional setup of AI Agent platforms with **25+ OpenCode-compatib
| Platform | Language | Memory | Qwen OAuth | All Providers | Best For | | Platform | Language | Memory | Qwen OAuth | All Providers | Best For |
|----------|----------|--------|------------|---------------|----------| |----------|----------|--------|------------|---------------|----------|
| **Qwen Code** | TypeScript | ~200MB | ✅ Native | ✅ | FREE coding | | **Qwen Code** | TypeScript | ~200MB | ✅ Native | ✅ | FREE coding |
| **ZeroClaw** | Rust | <5MB | ✅ Native | ✅ | Max performance |
| **PicoClaw** | Go | <10MB | ✅ Import | ✅ | Embedded |
| **OpenClaw** | TypeScript | >1GB | ✅ Import | ✅ | Full-featured | | **OpenClaw** | TypeScript | >1GB | ✅ Import | ✅ | Full-featured |
| **NanoBot** | Python | ~100MB | ✅ Import | ✅ | Research | | **NanoBot** | Python | ~100MB | ✅ Import | ✅ | Research |
| **PicoClaw** | Go | <10MB | ✅ Import | ✅ | Embedded |
| **ZeroClaw** | Rust | <5MB | ✅ Import | ✅ | Performance |
| **NanoClaw** | TypeScript | ~50MB | ✅ Import | ✅ | WhatsApp | | **NanoClaw** | TypeScript | ~50MB | ✅ Import | ✅ | WhatsApp |
--- ---
@@ -51,32 +52,80 @@ End-to-end professional setup of AI Agent platforms with **25+ OpenCode-compatib
## Get FREE Qwen OAuth ## Get FREE Qwen OAuth
```bash ```bash
# Install Qwen Code # Install Qwen Code CLI
npm install -g @qwen-code/qwen-code@latest npm install -g @qwen-code/qwen-code@latest
# Authenticate (FREE) # Authenticate (FREE - opens browser)
qwen qwen --auth-type qwen-oauth -p "test"
/auth # Select "Qwen OAuth" → Browser login with qwen.ai
# FREE: 2,000 requests/day, 60 req/min # FREE: 2,000 requests/day, 60 req/min
# Credentials saved to: ~/.qwen/oauth_creds.json
``` ```
## Import to Any Platform ## Credentials File Structure
```json
{
"access_token": "your-access-token",
"refresh_token": "your-refresh-token",
"token_type": "Bearer",
"resource_url": "portal.qwen.ai",
"expiry_date": 1771774796531
}
```
## API Endpoints
| Endpoint | URL |
|----------|-----|
| **API Base** | `https://dashscope.aliyuncs.com/compatible-mode/v1` |
| **Chat Completions** | `/chat/completions` |
| **Token Refresh** | `https://chat.qwen.ai/api/v1/oauth2/token` |
## Available Models (FREE Tier)
| Model | Best For |
|-------|----------|
| `qwen3-coder-plus` | Coding (recommended) |
| `qwen3-coder-flash` | Fast coding |
| `qwen-max` | Complex tasks |
## Import Methods
### ZeroClaw (Native Provider - Auto Token Refresh)
ZeroClaw has **built-in qwen-oauth provider** that handles token refresh automatically:
```bash
# Configure ZeroClaw to use native qwen-oauth provider
cat > ~/.zeroclaw/config.toml << EOF
default_provider = "qwen-oauth"
default_model = "qwen3-coder-plus"
default_temperature = 0.7
EOF
# ZeroClaw automatically:
# • Reads ~/.qwen/oauth_creds.json
# • Refreshes expired tokens using refresh_token
# • Uses correct DashScope API endpoint
zeroclaw agent -m "Hello!"
```
### Other Platforms (OpenAI-Compatible Import)
For OpenClaw, NanoBot, PicoClaw, NanoClaw - use OpenAI-compatible endpoint:
```bash ```bash
# Extract token # Extract token
export QWEN_TOKEN=$(cat ~/.qwen/oauth-token.json | jq -r '.access_token') export OPENAI_API_KEY=$(cat ~/.qwen/oauth_creds.json | jq -r '.access_token')
export OPENAI_BASE_URL="https://dashscope.aliyuncs.com/compatible-mode/v1"
# Configure for any platform # Use with any platform
export OPENAI_API_KEY="$QWEN_TOKEN"
export OPENAI_BASE_URL="https://api.qwen.ai/v1"
export OPENAI_MODEL="qwen3-coder-plus"
# Use with any platform!
openclaw # OpenClaw with FREE Qwen openclaw # OpenClaw with FREE Qwen
nanobot # NanoBot with FREE Qwen nanobot # NanoBot with FREE Qwen
picoclaw # PicoClaw with FREE Qwen picoclaw # PicoClaw with FREE Qwen
zeroclaw # ZeroClaw with FREE Qwen nanoclaw # NanoClaw with FREE Qwen
``` ```
--- ---
@@ -87,7 +136,7 @@ zeroclaw # ZeroClaw with FREE Qwen
| Provider | Free Tier | Model | Setup | | Provider | Free Tier | Model | Setup |
|----------|-----------|-------|-------| |----------|-----------|-------|-------|
| **Qwen OAuth** | 2,000/day | Qwen3-Coder | `qwen && /auth` | | **Qwen OAuth** | 2,000/day | Qwen3-Coder | `qwen --auth-type qwen-oauth` |
## Tier 2: Major AI Labs ## Tier 2: Major AI Labs
@@ -143,126 +192,29 @@ zeroclaw # ZeroClaw with FREE Qwen
--- ---
# Multi-Provider Configuration # Quick Import Script
## Full Configuration Example
```json
{
"providers": {
"qwen_oauth": {
"type": "oauth",
"free": true,
"daily_limit": 2000,
"model": "qwen3-coder-plus"
},
"anthropic": {
"apiKey": "${ANTHROPIC_API_KEY}",
"baseURL": "https://api.anthropic.com"
},
"openai": {
"apiKey": "${OPENAI_API_KEY}",
"baseURL": "https://api.openai.com/v1"
},
"google": {
"apiKey": "${GOOGLE_API_KEY}",
"baseURL": "https://generativelanguage.googleapis.com/v1"
},
"azure": {
"apiKey": "${AZURE_OPENAI_API_KEY}",
"baseURL": "${AZURE_OPENAI_ENDPOINT}"
},
"vertex": {
"projectId": "${GOOGLE_CLOUD_PROJECT}",
"location": "${GOOGLE_CLOUD_LOCATION}"
},
"bedrock": {
"region": "us-east-1",
"accessKeyId": "${AWS_ACCESS_KEY_ID}",
"secretAccessKey": "${AWS_SECRET_ACCESS_KEY}"
},
"openrouter": {
"apiKey": "${OPENROUTER_API_KEY}",
"baseURL": "https://openrouter.ai/api/v1"
},
"xai": {
"apiKey": "${XAI_API_KEY}",
"baseURL": "https://api.x.ai/v1"
},
"mistral": {
"apiKey": "${MISTRAL_API_KEY}",
"baseURL": "https://api.mistral.ai/v1"
},
"groq": {
"apiKey": "${GROQ_API_KEY}",
"baseURL": "https://api.groq.com/openai/v1"
},
"cerebras": {
"apiKey": "${CEREBRAS_API_KEY}",
"baseURL": "https://api.cerebras.ai/v1"
},
"deepinfra": {
"apiKey": "${DEEPINFRA_API_KEY}",
"baseURL": "https://api.deepinfra.com/v1"
},
"cohere": {
"apiKey": "${COHERE_API_KEY}",
"baseURL": "https://api.cohere.ai/v1"
},
"together": {
"apiKey": "${TOGETHER_API_KEY}",
"baseURL": "https://api.together.xyz/v1"
},
"perplexity": {
"apiKey": "${PERPLEXITY_API_KEY}",
"baseURL": "https://api.perplexity.ai"
},
"ollama": {
"baseURL": "http://localhost:11434/v1",
"apiKey": "ollama"
}
},
"agents": {
"defaults": {
"model": "anthropic/claude-sonnet-4-5",
"temperature": 0.7
},
"free": {
"model": "qwen/qwen3-coder-plus"
},
"fast": {
"model": "groq/llama-3.3-70b-versatile"
},
"local": {
"model": "ollama/llama3.2:70b"
}
}
}
```
## Fetch Available Models
```bash ```bash
# OpenRouter - All 100+ models #!/bin/bash
curl -s https://openrouter.ai/api/v1/models \ # Usage: source import-qwen-oauth.sh [platform]
-H "Authorization: Bearer $OPENROUTER_API_KEY" | jq '.data[].id'
# OpenAI - GPT models CREDS_FILE="$HOME/.qwen/oauth_creds.json"
curl -s https://api.openai.com/v1/models \ PLATFORM="${1:-zeroclaw}"
-H "Authorization: Bearer $OPENAI_API_KEY" | jq '.data[].id'
# Groq - Fast inference models QWEN_TOKEN=$(cat "$CREDS_FILE" | jq -r '.access_token')
curl -s https://api.groq.com/openai/v1/models \
-H "Authorization: Bearer $GROQ_API_KEY" | jq '.data[].id'
# Ollama - Local models case "$PLATFORM" in
curl -s http://localhost:11434/api/tags | jq '.models[].name' zeroclaw)
# Native provider - just set config
# Anthropic (static list) sed -i 's/^default_provider = .*/default_provider = "qwen-oauth"/' ~/.zeroclaw/config.toml
# claude-opus-4-5-20250219, claude-sonnet-4-5-20250219, claude-3-5-sonnet-20241022 sed -i 's/^default_model = .*/default_model = "qwen3-coder-plus"/' ~/.zeroclaw/config.toml
;;
# Google Gemini *)
curl -s "https://generativelanguage.googleapis.com/v1/models?key=$GOOGLE_API_KEY" # OpenAI-compatible
export OPENAI_API_KEY="$QWEN_TOKEN"
export OPENAI_BASE_URL="https://dashscope.aliyuncs.com/compatible-mode/v1"
;;
esac
``` ```
--- ---
@@ -272,7 +224,7 @@ curl -s "https://generativelanguage.googleapis.com/v1/models?key=$GOOGLE_API_KEY
## Qwen Code (Native FREE OAuth) ## Qwen Code (Native FREE OAuth)
```bash ```bash
npm install -g @qwen-code/qwen-code@latest npm install -g @qwen-code/qwen-code@latest
qwen && /auth qwen --auth-type qwen-oauth -p "test"
``` ```
## OpenClaw ## OpenClaw
@@ -313,8 +265,24 @@ chmod +x zeroclaw-linux-amd64 && sudo mv zeroclaw-linux-amd64 /usr/local/bin/zer
--- ---
# Automation Scripts # Troubleshooting
See `scripts/` directory: ## Token Expired
- `import-qwen-oauth.sh` - Import FREE Qwen OAuth to any platform
- `fetch-models.sh` - Fetch available models from all providers ```bash
# ZeroClaw: Automatic refresh (no action needed)
# Other platforms: Re-authenticate and re-export
qwen --auth-type qwen-oauth -p "test"
export OPENAI_API_KEY=$(cat ~/.qwen/oauth_creds.json | jq -r '.access_token')
```
## API Test
```bash
QWEN_TOKEN=$(cat ~/.qwen/oauth_creds.json | jq -r '.access_token')
curl -X POST "https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions" \
-H "Authorization: Bearer $QWEN_TOKEN" \
-H "Content-Type: application/json" \
-d '{"model": "qwen3-coder-plus", "messages": [{"role": "user", "content": "Hello"}]}'
```

251
skills/claw-setup/scripts/import-qwen-oauth.sh
View File

@@ -1,99 +1,202 @@
#!/bin/bash #!/bin/bash
# import-qwen-oauth.sh - Import Qwen OAuth to any platform # Import FREE Qwen OAuth to any Claw platform
# Usage: source import-qwen-oauth.sh && <platform-command> # Usage: source import-qwen-oauth.sh [platform]
#
# Platforms:
# zeroclaw - Native qwen-oauth provider (recommended, auto token refresh)
# picoclaw - OpenAI-compatible import
# openclaw - OpenAI-compatible import
# nanobot - OpenAI-compatible import
# nanoclaw - OpenAI-compatible import
#
# Requirements:
# - qwen-code CLI installed: npm install -g @qwen-code/qwen-code@latest
# - jq for JSON parsing
# - Authenticated: qwen --auth-type qwen-oauth -p "test"
set -e set -e
echo "╔═══════════════════════════════════════════════════════════════╗" CREDS_FILE="$HOME/.qwen/oauth_creds.json"
echo "║ QWEN OAUTH CROSS-PLATFORM IMPORTER ║" PLATFORM="${1:-zeroclaw}"
echo "║ FREE: 2,000 requests/day, 60 req/min ║"
echo "╚═══════════════════════════════════════════════════════════════╝"
# Check if Qwen Code is installed # Colors
if ! command -v qwen &> /dev/null; then RED='\033[0;31m'
echo "📦 Qwen Code not found. Installing..." GREEN='\033[0;32m'
npm install -g @qwen-code/qwen-code@latest YELLOW='\033[1;33m'
fi NC='\033[0m' # No Color
# Check if Qwen Code is authenticated echo "🦞 Claw Setup - Qwen OAuth Import"
if [ ! -d ~/.qwen ]; then echo "=================================="
echo "" echo ""
echo "❌ Qwen Code not authenticated."
# Check for credentials file
if [ ! -f "$CREDS_FILE" ]; then
echo -e "${RED}Error: Qwen OAuth credentials not found${NC}"
echo "File expected at: $CREDS_FILE"
echo "" echo ""
echo "Please run:" echo "To authenticate, run:"
echo " qwen" echo " npm install -g @qwen-code/qwen-code@latest"
echo " /auth # Select 'Qwen OAuth'" echo " qwen --auth-type qwen-oauth -p 'test'"
echo "" echo ""
echo "Then run this script again." echo "This will open a browser for FREE OAuth login."
exit 1 exit 1
fi fi
# Find OAuth token file # Check for jq
TOKEN_FILES=$(find ~/.qwen -name "*.json" -type f 2>/dev/null) if ! command -v jq &> /dev/null; then
if [ -z "$TOKEN_FILES" ]; then echo -e "${YELLOW}Warning: jq not found, using grep/sed fallback${NC}"
echo "❌ No OAuth token found in ~/.qwen/" QWEN_TOKEN=$(cat "$CREDS_FILE" | grep -o '"access_token"[[:space:]]*:[[:space:]]*"[^"]*"' | sed 's/.*"access_token"[[:space:]]*:[[:space:]]*"\([^"]*\)".*/\1/')
echo " Please authenticate first: qwen && /auth" else
exit 1 QWEN_TOKEN=$(cat "$CREDS_FILE" | jq -r '.access_token')
fi fi
# Try to extract token from various file formats
QWEN_TOKEN=""
for TOKEN_FILE in $TOKEN_FILES; do
# Try different JSON structures
QWEN_TOKEN=$(cat "$TOKEN_FILE" | jq -r '.access_token // .token // .accessToken // .credentials?.token // empty' 2>/dev/null)
if [ -n "$QWEN_TOKEN" ] && [ "$QWEN_TOKEN" != "null" ]; then
echo "✅ Found token in: $TOKEN_FILE"
break
fi
done
if [ -z "$QWEN_TOKEN" ] || [ "$QWEN_TOKEN" = "null" ]; then if [ -z "$QWEN_TOKEN" ] || [ "$QWEN_TOKEN" = "null" ]; then
echo "❌ Could not extract OAuth token" echo -e "${RED}Error: Could not extract access_token from credentials${NC}"
echo " Token files found but no valid token structure" echo "Credentials file may be corrupted. Try re-authenticating:"
echo " Try re-authenticating: qwen && /auth" echo " qwen --auth-type qwen-oauth -p 'test'"
exit 1 exit 1
fi fi
# Export environment variables echo "Platform: $PLATFORM"
echo "Token: ${QWEN_TOKEN:0:20}..."
echo ""
case "$PLATFORM" in
zeroclaw)
# ZeroClaw uses native qwen-oauth provider
CONFIG_FILE="$HOME/.zeroclaw/config.toml"
if [ ! -f "$CONFIG_FILE" ]; then
echo -e "${YELLOW}ZeroClaw config not found, creating...${NC}"
mkdir -p "$HOME/.zeroclaw"
cat > "$CONFIG_FILE" << 'EOF'
default_provider = "qwen-oauth"
default_model = "qwen3-coder-plus"
default_temperature = 0.7
[autonomy]
level = "supervised"
workspace_only = true
[memory]
backend = "sqlite"
EOF
else
# Update existing config
sed -i 's/^default_provider = .*/default_provider = "qwen-oauth"/' "$CONFIG_FILE"
sed -i 's/^default_model = .*/default_model = "qwen3-coder-plus"/' "$CONFIG_FILE"
fi
echo -e "${GREEN}✅ ZeroClaw configured with native qwen-oauth provider${NC}"
echo ""
echo "ZeroClaw automatically:"
echo " • Reads ~/.qwen/oauth_creds.json"
echo " • Refreshes expired tokens"
echo " • Uses correct DashScope API endpoint"
echo ""
echo "Test with:"
echo " zeroclaw agent -m 'Hello!'"
;;
picoclaw)
export OPENAI_API_KEY="$QWEN_TOKEN" export OPENAI_API_KEY="$QWEN_TOKEN"
export OPENAI_BASE_URL="https://api.qwen.ai/v1" export OPENAI_BASE_URL="https://dashscope.aliyuncs.com/compatible-mode/v1"
echo -e "${GREEN}✅ PicoClaw environment configured${NC}"
echo ""
echo "Environment variables set:"
echo " OPENAI_API_KEY=${QWEN_TOKEN:0:20}..."
echo " OPENAI_BASE_URL=https://dashscope.aliyuncs.com/compatible-mode/v1"
echo ""
echo "Test with:"
echo " picoclaw agent -m 'Hello!'"
;;
openclaw)
export OPENAI_API_KEY="$QWEN_TOKEN"
export OPENAI_BASE_URL="https://dashscope.aliyuncs.com/compatible-mode/v1"
echo -e "${GREEN}✅ OpenClaw environment configured${NC}"
echo ""
echo "Environment variables set:"
echo " OPENAI_API_KEY=${QWEN_TOKEN:0:20}..."
echo " OPENAI_BASE_URL=https://dashscope.aliyuncs.com/compatible-mode/v1"
echo ""
echo "Test with:"
echo " openclaw"
;;
nanobot)
export OPENAI_API_KEY="$QWEN_TOKEN"
export OPENAI_BASE_URL="https://dashscope.aliyuncs.com/compatible-mode/v1"
export OPENAI_MODEL="qwen3-coder-plus" export OPENAI_MODEL="qwen3-coder-plus"
# Save to .env for persistence echo -e "${GREEN}✅ NanoBot environment configured${NC}"
mkdir -p ~/.qwen echo ""
cat > ~/.qwen/.env << ENVEOF echo "Environment variables set:"
# Qwen OAuth Configuration for Cross-Platform Use echo " OPENAI_API_KEY=${QWEN_TOKEN:0:20}..."
# Generated: $(date) echo " OPENAI_BASE_URL=https://dashscope.aliyuncs.com/compatible-mode/v1"
OPENAI_API_KEY=$QWEN_TOKEN echo " OPENAI_MODEL=qwen3-coder-plus"
OPENAI_BASE_URL=https://api.qwen.ai/v1 echo ""
OPENAI_MODEL=qwen3-coder-plus echo "Test with:"
echo " nanobot"
;;
# Usage: nanoclaw)
# source ~/.qwen/.env && openclaw export OPENAI_API_KEY="$QWEN_TOKEN"
# source ~/.qwen/.env && nanobot gateway export OPENAI_BASE_URL="https://dashscope.aliyuncs.com/compatible-mode/v1"
# source ~/.qwen/.env && picoclaw gateway
# source ~/.qwen/.env && zeroclaw gateway
ENVEOF
chmod 600 ~/.qwen/.env echo -e "${GREEN}✅ NanoClaw environment configured${NC}"
echo ""
echo "Environment variables set:"
echo " OPENAI_API_KEY=${QWEN_TOKEN:0:20}..."
echo " OPENAI_BASE_URL=https://dashscope.aliyuncs.com/compatible-mode/v1"
echo ""
echo "Test with:"
echo " nanoclaw"
;;
all)
# Configure all platforms
echo "Configuring all platforms..."
echo ""
# ZeroClaw
CONFIG_FILE="$HOME/.zeroclaw/config.toml"
if [ -f "$CONFIG_FILE" ]; then
sed -i 's/^default_provider = .*/default_provider = "qwen-oauth"/' "$CONFIG_FILE"
sed -i 's/^default_model = .*/default_model = "qwen3-coder-plus"/' "$CONFIG_FILE"
echo -e "${GREEN}✅ ZeroClaw${NC}"
fi
# Set environment for other platforms
export OPENAI_API_KEY="$QWEN_TOKEN"
export OPENAI_BASE_URL="https://dashscope.aliyuncs.com/compatible-mode/v1"
echo -e "${GREEN}✅ PicoClaw, OpenClaw, NanoBot, NanoClaw${NC}"
echo ""
echo "Environment exported for current session."
echo "Add to ~/.bashrc for persistence:"
echo ""
echo 'export OPENAI_API_KEY="$(cat ~/.qwen/oauth_creds.json | jq -r '\''.access_token'\'')"' >> ~/.bashrc
echo 'export OPENAI_BASE_URL="https://dashscope.aliyuncs.com/compatible-mode/v1"' >> ~/.bashrc
;;
*)
# Generic - set environment variables
export OPENAI_API_KEY="$QWEN_TOKEN"
export OPENAI_BASE_URL="https://dashscope.aliyuncs.com/compatible-mode/v1"
echo -e "${GREEN}✅ Generic environment configured for $PLATFORM${NC}"
echo ""
echo "Environment variables set:"
echo " OPENAI_API_KEY=${QWEN_TOKEN:0:20}..."
echo " OPENAI_BASE_URL=https://dashscope.aliyuncs.com/compatible-mode/v1"
;;
esac
echo "" echo ""
echo "✅ Qwen OAuth imported successfully!" echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
echo "" echo "FREE Qwen OAuth: 2,000 requests/day, 60 req/min"
echo " OPENAI_API_KEY=***${QWEN_TOKEN: -8}" echo "API Endpoint: https://dashscope.aliyuncs.com/compatible-mode/v1"
echo " OPENAI_BASE_URL=$OPENAI_BASE_URL" echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
echo " OPENAI_MODEL=$OPENAI_MODEL"
echo ""
echo "✅ Configuration saved to ~/.qwen/.env"
echo ""
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
echo "Usage with platforms:"
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
echo ""
echo " source ~/.qwen/.env && openclaw"
echo " source ~/.qwen/.env && nanobot gateway"
echo " source ~/.qwen/.env && picoclaw gateway"
echo " source ~/.qwen/.env && zeroclaw gateway"
echo ""
echo "Free tier limits: 2,000 requests/day, 60 requests/minute"
echo ""