# LocalAI v4.6.0 — Release & Upgrade Intelligence
- **Product:** LocalAI (https://localai.io)
- **Version:** v4.6.0
- **Released:** Jul 04, 2026
- **Impact Score:** 5/10
- **Breaking Changes:** Not verified
- **Canonical Analysis:** https://changelogs.us/localai/updates/v4.6.0/

## Executive Summary (TL;DR)
LocalAI v4.6.0. Source highlight: 🎉 LocalAI 4.6.0 Release! 🚀

## Bug Fixes
- 🔒 **Gallery SSRF fix** - `POST /models/apply` config-URL fetches are validated against private/loopback/metadata addresses.
- `fix(vllm)`: restore non-streaming tool-call extraction that regressed after #10351 (a capability flag was mistaken for run state) - #10638
- `fix(python-backends)`: decode tool-call `arguments` for chat templates (unbreaks MLX/Qwen3.5 agent loops) and split reasoning when a model emits only a closing `
- `fix(cloud-proxy)`: drop `temperature`/`top_p` and send `max_completion_tokens` so routing to the newest reasoning models (Claude Opus 4.x, GPT-5.x) stops 400ing - #10640
- `fix(config)`: revert defaulting `swa_full:true` for sliding-window-attention models (restores the memory-light reduced KV cache; still available as an explicit per-model opt-in) - #10674
- `fix(kokoros)`: implement the `AudioTranscriptionLive` trait stub so the backend compiles against the updated proto - #10612