Impact Score: 5/10
Dify: v0.6.2 EMERGENCY FIX
Source available β automated, not human-reviewed
Component: dify Β· Channel: stable. Automated analysis, not a compatibility certification. How this works.
Analysis updated: 2026-11-01.
β‘ Executive Summary (TL;DR)
Dify 0.6.2. Source highlight: PLEASE UPGRADE to `v0.6.2` AS SOON AS POSSIBLE TO PREVENT DATA LEAKAGE.
Who Does This Impact? (Role-Based Analysis)
π» Software Engineers & Devs
Check the source notes against the package and APIs you use before upgrading.
π Product & Engineering Leads
Use the documented changes to assess relevance to your product; release frequency alone is not a quality measure.
βοΈ DevOps & Security
Verify the target version, runtime requirements and rollback procedure in the official documentation.
β¨ New Features & Capabilities (6)
- feat: OpenAI `gpt-4-turbo` & `gpt-4-turbo-2024-04-09` support by @Yeuoly in #3263
- feat: Azure OpenAI `gpt-4-turbo-2024-04-09` support by @Kennytian in #3300
- feat: Add Cohere Command R / R+ model support by @takatost in #3333
- feat: Add Google `gemini-1.5-pro` support by @lroolle in #2925
- feat: Enabled vision feature support of OpenAI Compatible API by @takatost in #3272
- feat: Agent app support image input for reasoning by @Yeuoly in #3293
β‘ Performance & Enhancements (3)
- refactor: Enhanced ReAct mode of Agent app by @Yeuoly in #3355
- For additional enhancements and updates, refer to the What's Changed section below.
- improvement: speed up dependency installation in docker image rebuilds by mounting cache layer
π§ Bug Fixes & Patches (6)
- fix: agent chat multiple model debug
- fix: image was sent to an unsupported LLM when sending second message
- fix: var assigner input node can not find caused error
- fix: variable-assigner node connect
- fix dataset retrival in dataset mode
- fix: leave progress page still call indexing-status api
π View Raw Release Notes (Original Developer Log)
> [!WARNING]
> ## β οΈ EMERGENCY FIX β οΈ
> ## PLEASE UPGRADE to `v0.6.2` AS SOON AS POSSIBLE TO PREVENT DATA LEAKAGE.
>
> Fix the issue where `sys.query`/`sys.files` data gets confused with other tasks during high concurrency in `workflow`/`chatflow` in #3378.
---
# β¨ Spotlight on Dify v0.6.0 β¨
## π Introducing Dify Workflow π
### Eager to elevate the stability and reproducibility of your LLM applications? The latest release, **Dify Workflow**, is here to empower you.
### Curious for more? Swing by the [v0.6.0 Release Notes](https://github.com/langgenius/dify/releases/tag/0.6.0) for the full scoop.
---
## Whatβs New in v0.6.2?
This update primarily focuses on enhancing system stability and improving user experience. Key updates include:
* feat: OpenAI `gpt-4-turbo` & `gpt-4-turbo-2024-04-09` support by @Yeuoly in #3263
* feat: Azure OpenAI `gpt-4-turbo-2024-04-09` support by @Kennytian in #3300
* feat: Add Cohere Command R / R+ model support by @takatost in #3333
* feat: Add Google `gemini-1.5-pro` support by @lroolle in #2925
* feat: Enabled vision feature support of OpenAI Compatible API by @takatost in #3272
* feat: Agent app support image input for reasoning by @Yeuoly in #3293
* feat: Update aws bedrock new models by @crazywoola in #3326
* refactor: Enhanced ReAct mode of Agent app by @Yeuoly in #3355
* For additional enhancements and updates, refer to the What's Changed section below.
## Update Guide
### Docker compose deployments:
1. Get the latest code from the main branch:
```Shell
git checkout main
git pull origin main
```
2. Go to the next step and update to the latest image:
```Shell
cd docker
docker compose up -d
```
### Source Code deployments:
1. Stop API server, Worker and Web frontend Server.
2. Get the latest code from the main branch:
```Shell
git checkout main
git pull origin main
```
3. Update Python dependencies:
```Shell
cd api
pip install --upgrade -r requirements.txt
```
4. Then, let's run the migration script:
```Shell
flask db upgrade
```
5. Finally, run API server, Worker and Web frontend Server again.
## What's Changed
* fix: agent chat multiple model debug by @zxhlyh in https://github.com/langgenius/dify/pull/3258
* feat: gpt-4-turbo by @Yeuoly in https://github.com/langgenius/dify/pull/3263
* fix: image was sent to an unsupported LLM when sending second message by @takatost in https://github.com/langgenius/dify/pull/3268
* feat: vision parameter support of OpenAI Compatible API by @takatost in https://github.com/langgenius/dify/pull/3272
* fix: var assigner input node can not find caused error by @iamjoel in https://github.com/langgenius/dify/pull/3274
* fix: variable-assigner node connect by @zxhlyh in https://github.com/langgenius/dify/pull/3288
* Feat/Agent-Image-Processing by @Yeuoly in https://github.com/langgenius/dify/pull/3293
* chore: address security alerts on braces escape and KaTeX by @nite-knite in https://github.com/langgenius/dify/pull/3301
* chore(deps): bump katex from 0.16.8 to 0.16.10 in /web by @dependabot in https://github.com/langgenius/dify/pull/3307
* Update README.md by @guchenhe in https://github.com/langgenius/dify/pull/3281
* Remove langchain dataset retrival agent logic by @JohnJyong in https://github.com/langgenius/dify/pull/3311
* add german translations by @guchenhe in https://github.com/langgenius/dify/pull/3322
* feat: add missing workflow i18n keys by @khazic in https://github.com/langgenius/dify/pull/3309
* feat:add 'name' field return by @leslie2046 in https://github.com/langgenius/dify/pull/3152
* improvement: speed up dependency installation in docker image rebuilds by mounting cache layer by @bowenliang123 in https://github.com/langgenius/dify/pull/3218
* feat: support gpt-4-turbo-2024-04-09 model by @Kennytian in https://github.com/langgenius/dify/pull/3300
* feat: Add Cohere Command R / R+ model support by @takatost in https://github.com/langgenius/dify/pull/3333
* fix dataset retrival in dataset mode by @JohnJyong in https://github.com/langgenius/dify/pull/3334
* chore:bump pypdfium2 from 4.16.0 to 4.17.0 by @leslie2046 in https://github.com/langgenius/dify/pull/3310
* feat(llm/models): add gemini-1.5-pro by @lroolle in https://github.com/langgenius/dify/pull/2925
* feat: make input size bigger in start by @crazywoola in https://github.com/langgenius/dify/pull/3340
* Doc/update readme by @crazywoola in https://github.com/langgenius/dify/pull/3344
* fix: leave progress page still call indexing-status api by @iamjoel in https://github.com/langgenius/dify/pull/3345
* feat: update aws bedrock by @crazywoola in https://github.com/langgenius/dify/pull/3326
* fix/moonshot-function-call by @Yeuoly in https://github.com/langgenius/dify/pull/3339
* fix issue: userβs keywords do not affect when add segment by @JohnJyong in https://github.com/langgenius/dify/pull/3349
* fix: add segment with keyword issue by @JohnJyong in https://github.com/langgenius/dify/pull/3351
* Fix issue : don't delete DatasetProcessRule, DatasetQuery and AppDatasetJoin when delete dataset with no document by @JohnJyong in https://github.com/langgenius/dify/pull/3354
* fix: remove middle editor may cause render placement error by @iamjoel in https://github.com/langgenius/dify/pull/3356
* Added a note on the front-end docker build: use taobao source to accelerate the installation of front-end dependency packages to achieve the purpose of quickly building containers by @khazic in https://github.com/langgenius/dify/pull/3358
* fix: var name too long would break ui in var assigner and end nodes by @iamjoel in https://github.com/langgenius/dify/pull/3361
* Refactor/react agent by @Yeuoly in https://github.com/langgenius/dify/pull/3355
* Fix/Bing Search url endpoint cannot be customized by @Yeuoly in https://github.com/langgenius/dify/pull/3366
* fix: image token calc of OpenAI Compatible API by @takatost in https://github.com/langgenius/dify/pull/3368
* Update README.md by @guchenhe in https://github.com/langgenius/dify/pull/3371
* update workflow intro mp4 codec by @guchenhe in https://github.com/langgenius/dify/pull/3372
* fix: cohere tool call does not support single tool by @takatost in https://github.com/langgenius/dify/pull/3373
* version to 0.6.2 by @takatost in https://github.com/langgenius/dify/pull/3375
* fix: variable pool mapping variable mixed up by @takatost in https://github.com/langgenius/dify/pull/3378
* fix: yarn install extract package err when using GitHub Cache in amd6β¦ by @takatost in https://github.com/langgenius/dify/pull/3383
## New Contributors
* @khazic made their first contribution in https://github.com/langgenius/dify/pull/3309
**Full Changelog**: https://github.com/langgenius/dify/compare/0.6.1...0.6.2