- Add xAI to AuthChoiceGroupId and AuthChoice type unions
- Add xAI group to AUTH_CHOICE_GROUP_DEFS with "Grok models (API key)" hint
- Create setXaiApiKey() helper and XAI_DEFAULT_MODEL_REF constant (xai/grok-4.1)
- Implement applyXaiConfig() and applyXaiProviderConfig() for model configuration
- Add xAI handler to applyAuthChoiceApiProviders() with env var detection
- Export all xAI functions via onboard-auth.ts
xAI infrastructure (env var mapping, model filters) already existed but was
hidden from onboarding UI. This change exposes xAI as a selectable provider
during clawdbot onboard/configure flows.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Venice AI is a privacy-focused AI inference provider with support for
uncensored models and access to major proprietary models via their
anonymized proxy.
This integration adds:
- Complete model catalog with 25 models:
- 15 private models (Llama, Qwen, DeepSeek, Venice Uncensored, etc.)
- 10 anonymized models (Claude, GPT-5.2, Gemini, Grok, Kimi, MiniMax)
- Auto-discovery from Venice API with fallback to static catalog
- VENICE_API_KEY environment variable support
- Interactive onboarding via 'venice-api-key' auth choice
- Model selection prompt showing all available Venice models
- Provider auto-registration when API key is detected
- Comprehensive documentation covering:
- Privacy modes (private vs anonymized)
- All 25 models with context windows and features
- Streaming, function calling, and vision support
- Model selection recommendations
Privacy modes:
- Private: Fully private, no logging (open-source models)
- Anonymized: Proxied through Venice (proprietary models)
Default model: venice/llama-3.3-70b (good balance of capability + privacy)
Venice API: https://api.venice.ai/api/v1 (OpenAI-compatible)
