v0.1.4

RightNow-AI/openfangv0.1.4Feb 27, 2026by jaberjaber23

AI Summary

Major release introducing editable provider base URLs with hot-reload support and adding 17 new AI models across multiple providers.

Key Highlights

Editable provider base URLs with hot-reload (no restart needed)
17 new models from Anthropic, OpenAI, Google, Meta, xAI, and AWS Bedrock
Model alias updates (sonnet/opus → Claude 4.6, gpt5 → GPT-5, etc.)
Dashboard UI for base URL input on local provider cards
PUT /api/providers/{name}/url endpoint with health probing

New Features

Editable provider base URLs via API or dashboard
[provider_urls] config section persisted to config.toml
17 new AI models across 6 providers

Full Release Notes

## What's New

### Editable Provider Base URLs
- Local providers (Ollama, vLLM, LM Studio) can now have their base URLs customized via API or dashboard
- `PUT /api/providers/{name}/url` endpoint with URL validation and automatic health probe
- `[provider_urls]` config section persisted to `config.toml`, applied on boot
- Hot-reload support — provider URL changes applied without restart
- Dashboard UI base URL input on local provider cards in Settings > Providers
- `base_url` field added to `GET /api/providers` response

### 17 New Models
- **Anthropic**: Claude Opus 4.6, Claude Sonnet 4.6
- **OpenAI**: GPT-5, GPT-5 Mini, GPT-5 Nano, GPT-5.1, GPT-5.2, GPT-5.2 Pro
- **Google**: Gemini 3.1 Pro, Gemini 3 Flash, Gemini 3 Deep Think, Gemini 2.5 Flash Lite
- **Meta**: Llama 4 Scout 17B
- **xAI**: Grok 4, Grok 4.1 Fast
- **AWS Bedrock**: Claude Opus 4.6, Claude Sonnet 4.6

### Alias Updates
- `sonnet` / `opus` → Claude 4.6 variants
- `gpt5` / `gpt5-mini` → GPT-5 / GPT-5 Mini
- `flash` / `gemini-flash` → Gemini 3 Flash
- `gemini-pro` → Gemini 3.1 Pro
- `grok` → Grok 4
- `grok-fast` → Grok 4.1 Fast