# LocalAI v3.8.0 — Release & Upgrade Intelligence
- **Product:** LocalAI (https://localai.io)
- **Version:** v3.8.0
- **Released:** Nov 26, 2025
- **Impact Score:** 5/10
- **Breaking Changes:** Not verified
- **Canonical Analysis:** https://changelogs.us/localai/updates/v3.8.0/

## Executive Summary (TL;DR)
LocalAI v3.8.0. Source highlight: Welcome to **LocalAI 3.8.0** !

## New Features
- **File Safety:** We added a safeguard to prevent the deletion of model files (blobs) if they are shared by multiple model configurations.
- **Live Action Streaming:** We have added a new endpoint to stream agent results as they happen. Instead of waiting for the final output, you can now watch the agent "think": seeing tool calls, reasoning steps, and intermediate actions streamed live in the UI.
- feat(llama.cpp): allow to set cache-ram and ctx_shift
- chore: show success toast when system prompt is updated
- feat(llama.cpp): consolidate options and respect tokenizer template when enabled
- feat: respect context and add request cancellation

## Improvements
- chore(docs): improve documentation and split into sections bigger topics

## Bug Fixes
- **SSE Streaming:** Fixed a critical issue where streaming responses were slightly non-compliant (e.g., sending empty content chunks or missing `finish_reason`). This resolves integration issues with `openai-node`, `LangChain`, and `LlamaIndex`.
- **Top_N Behavior:** In the reranker, `top_n` can now be omitted or set to `0` to return *all* results, rather than defaulting to an arbitrary limit.
- **Model Preview:** When downloading, you can now see the actual filename and size before committing to the download.
- **Tool Handling:** Fixed crashes when tool content is missing or malformed.
- **TTS:** Fixed dropdown selection states for TTS models.
- **Browser Storage:** Chat history is now persisted in your browser's local storage. You can switch between parallel chats, rename them, and export them to JSON.