# Dify 0.15.2 — Release & Upgrade Intelligence
- **Product:** Dify (https://dify.ai)
- **Version:** 0.15.2
- **Released:** Jan 22, 2025
- **Impact Score:** 5/10
- **Breaking Changes:** Not verified
- **Canonical Analysis:** https://changelogs.us/dify/updates/0.15.2/

## Executive Summary (TL;DR)
Dify 0.15.2. Source highlight: ✨ What’s New in v0.15.2? ✨

## New Features
- **Deepseek-reasoner/deepseek-r1**
- **Minimax-Text-01 Support**: Added support for the new Minimax-Text-01 model by @AAlexDing in #12763.
- **Gemini-2.0-Flash-Thinking-Exp-01-21**: New experimental model added by @jiandanfeng in #12924.
- **Doubao 1.5 Model Series**: Support for Doubao 1.5 models in our tooling setup by @sinomoe in #12935.
- **Profile Avatar Customization**: You can now change your profile avatar and keep it fresh, thanks to @miya in #12642.
- **Environment Configuration for Chunk Length**: Configure document chunk length through environment variables by @iamjoel in #12925.

## Improvements
- **Credential Extraction Logic**: Enhanced credential extraction logic for better configurability by @fujita-h in #12853.
- **Document Chunk Setting Updates**: Now possible to update chunk settings for existing documents by @kurokobo in #12833.
- **Full-Text Search in Milvus**: You can now configure full-text search capabilities within Milvus by @JohnJyong in #12930.

## Bug Fixes
- **Rerank Model Bug**: Fixed the rerank model and switch issues across various tools by @WTW0313 in #12721 and @luckylhb90 in #12774.
- **Clipboard WriteText on HTTP**: Resolved issues with clipboard text writing under the HTTP protocol by @le0zh in #12936.
- **OpenAI Bad Request Error**: Cleaned up issues causing bad request errors on OpenAI o1 endpoint by @k-zaku in #12839.
- **ReAct Inference Error**: Fixed error logging issue when ReAct inference mode is enabled by @jiandanfeng in #12920.
- **Agent Log Formatting**: Tweaked DeepSeek's API response handling to fix format issues by @jiandanfeng in #12747.
- fix: Fix rerank model switching issue