Resolve conflicts in docs and TypeScript files after project rename
from Moltbot to OpenClaw. All GLM provider implementations updated to
use OpenClawConfig type and openclaw CLI command in documentation.
Generated with [Claude Code](https://claude.ai/code)
via [Happy](https://happy.engineering)
Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>
Resolve conflicts with Xiaomi MiMo provider addition (#3454).
Both PRs added new providers to the same infrastructure files.
Conflicts resolved by including both sets of changes:
- docs/providers/index.md: Add Xiaomi link alongside GLM docs
- src/cli/program/register.onboard.ts: Add all CLI flags
- src/commands/auth-choice-options.ts: Add all auth choices and groups
- src/commands/auth-choice.apply.api-providers.ts: Add all handlers
- src/commands/onboard-auth.config-core.ts: Add all config imports
- src/commands/onboard-auth.credentials.ts: Add all credentials functions
- src/commands/onboard-auth.ts: Add all exports
- src/commands/onboard-non-interactive/local/auth-choice.ts: Add all handlers
- src/commands/onboard-types.ts: Add all types
- src/infra/provider-usage.shared.ts: Add all provider labels
- src/infra/provider-usage.types.ts: Add all provider IDs
Generated with [Claude Code](https://claude.ai/code)
via [Happy](https://happy.engineering)
Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>
Add four distinct provider variants for GLM models:
- zai: International pay-as-you-go (api.z.ai)
- zai-coding: International Coding Plan (api.z.ai/coding)
- zhipu: China pay-as-you-go (bigmodel.cn)
- zhipu-coding: China Coding Plan (bigmodel.cn/coding)
Includes:
- Provider config functions with proper base URLs
- GLM model definition (glm-4.7, 205K context)
- Env var resolution with fallback chains
- Provider ID normalization for aliases
- Usage provider IDs and labels
Generated with [Claude Code](https://claude.ai/code)
via [Happy](https://happy.engineering)
Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>
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)