Add native Kimi Code OAuth support, allowing users to authenticate with
their Kimi subscription instead of requiring a static API key.
Changes:
- New kimi-code-oauth.ts: token refresh via auth.kimi.com/api/oauth/token
- Auth dispatch: route kimi-code provider to custom refresh (same pattern
as qwen-portal and chutes)
- New 'kimi-code-oauth' onboarding auth choice: imports OAuth credentials
from Kimi CLI (~/.kimi/credentials/kimi-code.json)
- Handles expires_at conversion (Kimi uses seconds, Moltbot uses ms)
Usage:
moltbot onboard --auth-choice kimi-code-oauth
Requires Kimi CLI to be logged in first (kimi login).
🤖 AI-assisted (Claude Opus 4.5 + Kimi K2.5 sub-agent)
Testing: endpoint + refresh verified via curl; compiles clean; lint clean; not yet tested e2e through Moltbot
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)
