Impact Score: 5/10
Dify: v0.9.2
Source available — automated, not human-reviewed
Component: dify · Channel: stable. Automated analysis, not a compatibility certification. How this works.
Analysis updated: 2026-11-01.
⚡ Executive Summary (TL;DR)
Dify 0.9.2. Source highlight: ✨ What’s New in v0.9.2? ✨
Who Does This Impact? (Role-Based Analysis)
💻 Software Engineers & Devs
Check the source notes against the package and APIs you use before upgrading.
📊 Product & Engineering Leads
Use the documented changes to assess relevance to your product; release frequency alone is not a quality measure.
⚙️ DevOps & Security
Verify the target version, runtime requirements and rollback procedure in the official documentation.
✨ New Features & Capabilities (6)
- **Model Additions and Enhancements:** Added models `qwen2.5-72b` and `llama3.2` for OpenRouter by @hwzhuhao in #8956. Also, `O1-mini`, `O1-preview`, and `LlamaGuard` models have joined the lineup thanks to contributions from @charli117 and @crazywoola.
- **Workflow System Parameters:** Now, you can access `sys.app_id`, `sys.workflow_id`, and `sys.workflow_run_id` in your workflow system variables for more dynamic workflows, courtesy of @ZhouhaoJiang in #9108.
- **Image Generation Enhancements:** The StepFun image generation tool got a boost, enabling richer and broader capabilities, spearheaded by @hwzhuhao in #8954.
- **Tools Update:** Discord Incoming Webhook now lets you send messages directly, created by @yaoice. Props to @hwzhuhao for adding tags for Vanna tools too.
- **Vector Provider:** Meet the new kid on the block, Volcengine VikingDB, integrated into the system and ready to expand your vector capabilities, brought to you by @yaoice in #9287.
- **CSP Support:** Content Security Policy (CSP) is now supported, adding an extra layer of security to your operations, thanks to @douxc.
⚡ Performance & Enhancements (5)
- **Richer Time Tool Functions:** Now you can convert and retrieve timestamps with the Time Tool, unlocking more precise temporal operations courtesy of @hwzhuhao.
- **Non-Root User for Web Container:** Security gets a bump with the use of a non-root user in the web container, hats off to @s2oBCN for that.
- **Prompt Editor Optimization:** Clearer and more efficient prompt editing with reset capabilities, devised by @HiChen404.
- **Customizeable Chatbot Embed:** Change the size to fit your needs with default values set for your convenience—well done, @alterxyz for this addition.
- improve: Refresh updated_at field of DataSourceOauthBinding model
🔧 Bug Fixes & Patches (6)
- **Responsive Front-end Updates:** With rerank model verification and error logs only in debug mode, your interface just became more practical and informative. Thanks, @YIXIAO0 and @hwzhuhao.
- **API and Logs:** Chat API now reliably retrieves conversation history (thanks @xuzuodong), and fixes have been applied to API proxy updates and missing model information in LLM spans.
- **Tool Descriptions:** Essential descriptions are back where they belong—visible and complete, thanks to @crazywoola.
- **External Knowledge and Retrievals:** Addressing issues in agent retrieval and entry allows external knowledge operation to run smoother, thanks to @JohnJyong.
- **Miscellaneous Fixes:** Including max-token adjustments in OpenRouter by @infinitnet, correct session history fetching, stopping notification errors, and many more have tightened up the system, courtesy of multiple contributors.
- fix: chat API is not bringing the conversation/session history
📄 View Raw Release Notes (Original Developer Log)
## ✨ What’s New in v0.9.2? ✨
The most recent release brings some solid new features, enhancements, and bug fixes that should enhance your experience across the platform. Check out what's changed:
### 🚀 New Features
- **Model Additions and Enhancements:** Added models `qwen2.5-72b` and `llama3.2` for OpenRouter by @hwzhuhao in #8956. Also, `O1-mini`, `O1-preview`, and `LlamaGuard` models have joined the lineup thanks to contributions from @charli117 and @crazywoola.
- **Workflow System Parameters:** Now, you can access `sys.app_id`, `sys.workflow_id`, and `sys.workflow_run_id` in your workflow system variables for more dynamic workflows, courtesy of @ZhouhaoJiang in #9108.
- **Image Generation Enhancements:** The StepFun image generation tool got a boost, enabling richer and broader capabilities, spearheaded by @hwzhuhao in #8954.
- **Tools Update:** Discord Incoming Webhook now lets you send messages directly, created by @yaoice. Props to @hwzhuhao for adding tags for Vanna tools too.
- **Vector Provider:** Meet the new kid on the block, Volcengine VikingDB, integrated into the system and ready to expand your vector capabilities, brought to you by @yaoice in #9287.
- **CSP Support:** Content Security Policy (CSP) is now supported, adding an extra layer of security to your operations, thanks to @douxc.
- **Supabase Object Storage:** A new storage option at your disposal, big cheers to @hwzhuhao for the integration in #9229.
### ⚙️ Enhancements
- **Richer Time Tool Functions:** Now you can convert and retrieve timestamps with the Time Tool, unlocking more precise temporal operations courtesy of @hwzhuhao.
- **Non-Root User for Web Container:** Security gets a bump with the use of a non-root user in the web container, hats off to @s2oBCN for that.
- **Prompt Editor Optimization:** Clearer and more efficient prompt editing with reset capabilities, devised by @HiChen404.
- **Customizeable Chatbot Embed:** Change the size to fit your needs with default values set for your convenience—well done, @alterxyz for this addition.
- **Responsive Front-end Updates:** With rerank model verification and error logs only in debug mode, your interface just became more practical and informative. Thanks, @YIXIAO0 and @hwzhuhao.
### 🛠️ Bug Fixes
- **API and Logs:** Chat API now reliably retrieves conversation history (thanks @xuzuodong), and fixes have been applied to API proxy updates and missing model information in LLM spans.
- **Tool Descriptions:** Essential descriptions are back where they belong—visible and complete, thanks to @crazywoola.
- **External Knowledge and Retrievals:** Addressing issues in agent retrieval and entry allows external knowledge operation to run smoother, thanks to @JohnJyong.
- **Miscellaneous Fixes:** Including max-token adjustments in OpenRouter by @infinitnet, correct session history fetching, stopping notification errors, and many more have tightened up the system, courtesy of multiple contributors.
### Miscellaneous
- **Typos and Documentation:** Corrected typos and added documentation on key integrations like Google Cloud Terraform, thanks to the hawk-eyed @y-omr and @sotazum.
This version packs plenty to explore, ensuring your workflows and integrations are smoother, faster, and richer with features. Happy upgrading!
---
## Upgrade Guide
> [!WARNING]
> This version includes a migration that might update a large volume of messages. If you have a significant amount of message data, please review our changes in [#9132](https://github.com/langgenius/dify/pull/9132) before upgrading.
### Docker compose deployments
1. Back up your customized docker-compose YAML file (optional)
```bash
cd docker
cp docker-compose.yaml docker-compose.yaml.$(date +%s).bak
```
2. Get the latest code from the main branch
```bash
git checkout main
git pull origin main
```
3. Stop the service,Command, please execute in the docker directory
```bash
docker compose down
```
4. Back up data
```bash
tar -cvf volumes-$(date +%s).tgz volumes
```
5. Upgrade services
```bash
docker compose up -d
```
### Source Code deployments
1. Stop API server, Worker and Web frontend Server.
2. Get the latest code from the release branch:
```bash
git checkout 0.9.2
```
3. Update Python dependencies:
```bash
cd api
poetry install
```
7. Then, let's run the migration script:
```bash
poetry run flask db upgrade
```
8. Finally, run API server, Worker and Web frontend Server again.
---
## What's Changed
* chore: add missing models from Voyage by @CXwudi in https://github.com/langgenius/dify/pull/8950
* chore: sort Gemini models by @CXwudi in https://github.com/langgenius/dify/pull/8951
* refactor: remove unnecessary comment by @y-omr in https://github.com/langgenius/dify/pull/8949
* chore: remove unexecuted scripts to avoid ambiguity by @yaoice in https://github.com/langgenius/dify/pull/8946
* feat: add qwen2.5-72b and llama3.2 for openrouter by @hwzhuhao in https://github.com/langgenius/dify/pull/8956
* feat: enhance stepfun image generation tool by @hwzhuhao in https://github.com/langgenius/dify/pull/8954
* fix: chat API is not bringing the conversation/session history by @xuzuodong in https://github.com/langgenius/dify/pull/8965
* fix: corrected typo by @y-omr in https://github.com/langgenius/dify/pull/8979
* feat(Tools): add discord incoming webhook for sending messages by @yaoice in https://github.com/langgenius/dify/pull/7852
* Update json_in_md_parser.py by @zhao85 in https://github.com/langgenius/dify/pull/8983
* feat: Update AWS Bedrock supported regions by @Retr0-01 in https://github.com/langgenius/dify/pull/8992
* fix: tools description is missing by @crazywoola in https://github.com/langgenius/dify/pull/8999
* fix: failed to open links to images generated by QR code tool when using Huawei OBS by @hwzhuhao in https://github.com/langgenius/dify/pull/9034
* fix bug when adding openai or openai-compatible stt model instance by @zhao85 in https://github.com/langgenius/dify/pull/9006
* chore: fix the yanked dependency vesion aiohappyeyeballs 2.4.2 by @bowenliang123 in https://github.com/langgenius/dify/pull/9020
* refactor: remove the duplicate definitions across different modules by @hwzhuhao in https://github.com/langgenius/dify/pull/9022
* feat: add baidu obs storage by @hwzhuhao in https://github.com/langgenius/dify/pull/9024
* fix: Missing model information in llm span of Langfuse #9029 by @aiscrm in https://github.com/langgenius/dify/pull/9030
* fix:ddg ratelimit 202 by @leslie2046 in https://github.com/langgenius/dify/pull/9047
* chore: move testing env variables from pyproject.toml to pytest.ini by @bowenliang123 in https://github.com/langgenius/dify/pull/9019
* feat: Improvement- use non root user for Web container by @s2oBCN in https://github.com/langgenius/dify/pull/8928
* chore: removing unused imports in tests by @bowenliang123 in https://github.com/langgenius/dify/pull/9049
* fix: Ignore the error toast notification if the status is 401 and isPublicAPI is true by @douxc in https://github.com/langgenius/dify/pull/9062
* chore: refine python dependency list and check dependencies in order by @bowenliang123 in https://github.com/langgenius/dify/pull/9061
* fix: zhipu ai web_search not work by @hjlarry in https://github.com/langgenius/dify/pull/9058
* docs: Add Google Cloud Terraform to README by @sotazum in https://github.com/langgenius/dify/pull/9065
* Correct max_tokens for OpenRouter Sonnet 3.5 by @infinitnet in https://github.com/langgenius/dify/pull/9068
* fix: Count exception occurs when searching conversations by @Gaocarri in https://github.com/langgenius/dify/pull/8754
* feat: update the xinf tool's API key to optional by @hwzhuhao in https://github.com/langgenius/dify/pull/9073
* fix: #8969 by @Blackman99 in https://github.com/langgenius/dify/pull/9076
* feat: add timestamp conversion and timestamp retrieval for time tool by @hwzhuhao in https://github.com/langgenius/dify/pull/9085
* Feat/9081 add support for llamaguard through groq provider by @crazywoola in https://github.com/langgenius/dify/pull/9083
* fix: prompt-editor regex.lastIndex needed to reset by @HiChen404 in https://github.com/langgenius/dify/pull/9097
* fix s3 presign url check problem, support two versions(v2,v4) by @ybalbert001 in https://github.com/langgenius/dify/pull/9093
* refactor: Update countries & languages list for SearchApi engines by @SebastjanPrachovskij in https://github.com/langgenius/dify/pull/9090
* chore: add the missing tool names to the _position file by @hwzhuhao in https://github.com/langgenius/dify/pull/9099
* feat: add tags for vanna tools by @hwzhuhao in https://github.com/langgenius/dify/pull/9102
* feat: output the execution results of tool should only in debug mode by @hwzhuhao in https://github.com/langgenius/dify/pull/9104
* refactor: introduce storage factory and speed up api startup by importing storage client on demand by @bowenliang123 in https://github.com/langgenius/dify/pull/9086
* chore: avoid implicit optional in type annotations of method by @bowenliang123 in https://github.com/langgenius/dify/pull/8727
* feat: respect x-* headers for redirections by @kurokobo in https://github.com/langgenius/dify/pull/9054
* azure add o1-mini、o1-preview models by @charli117 in https://github.com/langgenius/dify/pull/9088
* Add customizable size for chatbot embed with default values by @alterxyz in https://github.com/langgenius/dify/pull/9115
* Fix the margin for the rerank switch in retrieval setting by @YIXIAO0 in https://github.com/langgenius/dify/pull/9124
* add generate conversation name error log by @pinsily in https://github.com/langgenius/dify/pull/9117
* fix: follow-up (suggested questions) does not refer to the most recen… by @xuzuodong in https://github.com/langgenius/dify/pull/9122
* fix: docker env typo by @hjlarry in https://github.com/langgenius/dify/pull/9119
* chore: avoid star imports usage by @bowenliang123 in https://github.com/langgenius/dify/pull/9123
* fix: response_format of model_parameters will not be removed by @hjlarry in https://github.com/langgenius/dify/pull/9148
* chore:add azure openai api version 2024-09-01-preview by @leslie2046 in https://github.com/langgenius/dify/pull/9141
* fix(migrations): correct parent_message_id for service-api records by @laipz8200 in https://github.com/langgenius/dify/pull/9132
* fix: vertex ai remote url error(Error: not enough values to unpack) by @luckylhb90 in https://github.com/langgenius/dify/pull/9134
* fix: #9076 by @crazywoola in https://github.com/langgenius/dify/pull/9150
* Corrected type annotation to "Any" from "any" all files in "model_providers" folder by @ronaksingh27 in https://github.com/langgenius/dify/pull/9135
* Feat/add workflow sys params by @ZhouhaoJiang in https://github.com/langgenius/dify/pull/9108
* fix: Twitter to X(Twitter) by @daisuke0926dev in https://github.com/langgenius/dify/pull/9157
* Fixes #9159: Modify to make it works to llama.cpp rerank API by @ziyu4huang in https://github.com/langgenius/dify/pull/9160
* Fix code indentation errors by @charli117 in https://github.com/langgenius/dify/pull/9164
* fix: delete offline "how to write a good knowledge description" helper by @YIXIAO0 in https://github.com/langgenius/dify/pull/9165
* fix: missing usage of metadata in the chatflow app by @takatost in https://github.com/langgenius/dify/pull/9167
* downgrade elastic to 8.14 by @JohnJyong in https://github.com/langgenius/dify/pull/9171
* fix: Typo Correction in jina.yaml by @Nick17t in https://github.com/langgenius/dify/pull/9161
* improve: Refresh updated_at field of DataSourceOauthBinding model by @sunxiaoguang in https://github.com/langgenius/dify/pull/9173
* feat: add allow_llm_to_see_data flag for vanna by @hwzhuhao in https://github.com/langgenius/dify/pull/9156
* fix(log list): prevent duplicate data fetch by @laipz8200 in https://github.com/langgenius/dify/pull/9190
* fix retrieval resource positon missed by @JohnJyong in https://github.com/langgenius/dify/pull/9155
* feat: add gte rerank for tongyi by @droxer in https://github.com/langgenius/dify/pull/9153
* fix: add loading to 'delete' button & 'save' button by @WTW0313 in https://github.com/langgenius/dify/pull/9214
* feat: add NotFound error for dataset service by @crazywoola in https://github.com/langgenius/dify/pull/9215
* fix: update inner api proxies by @ZhouhaoJiang in https://github.com/langgenius/dify/pull/9174
* Update docker-compose.yaml by @massif-01 in https://github.com/langgenius/dify/pull/9183
* feat: add siliconflow custom add model interface by @AAEE86 in https://github.com/langgenius/dify/pull/8745
* fix: reduce webapp icon displayed on browser tab flickering when page is loading by @xuzuodong in https://github.com/langgenius/dify/pull/9212
* Chore/model icon url by @zxhlyh in https://github.com/langgenius/dify/pull/9218
* Fix/add es num_candidates by @JohnJyong in https://github.com/langgenius/dify/pull/9225
* chore: check all dependencies groups in pyproject.toml by @bowenliang123 in https://github.com/langgenius/dify/pull/9224
* feat: support csp by @douxc in https://github.com/langgenius/dify/pull/9111
* chore(deps): bump micromatch from 4.0.5 to 4.0.8 in /web by @dependabot in https://github.com/langgenius/dify/pull/9234
* chore(deps): bump dompurify from 3.0.5 to 3.1.7 in /web by @dependabot in https://github.com/langgenius/dify/pull/9232
* fix:#9222 create or update custum tools error by @AkisAya in https://github.com/langgenius/dify/pull/9228
* fix: reference issue in external knowledge api by @YIXIAO0 in https://github.com/langgenius/dify/pull/9240
* Fix/agent external knowledge retrieval by @JohnJyong in https://github.com/langgenius/dify/pull/9241
* fix: dialog box cannot correctly display LaTeX formulas by @likenamehaojie in https://github.com/langgenius/dify/pull/9242
* feat: add supabase object storage by @hwzhuhao in https://github.com/langgenius/dify/pull/9229
* fix: move exception to debug mode by @crazywoola in https://github.com/langgenius/dify/pull/9258
* fix: add new domain to whitelist by @douxc in https://github.com/langgenius/dify/pull/9265
* chore: fix the misclassification of the opensearch-py package by @hwzhuhao in https://github.com/langgenius/dify/pull/9266
* chore: use cache instead of re-querying node record during workflow execution by @takatost in https://github.com/langgenius/dify/pull/9280
* chore: optimize the trace ops slow queries on node executions. by @takatost in https://github.com/langgenius/dify/pull/9282
* Fix/s3 iam add region name by @GarfieldDai in https://github.com/langgenius/dify/pull/7819
* Feat: rerank model verification in front end by @YIXIAO0 in https://github.com/langgenius/dify/pull/9271
* feat:support baidu vector db by @WayneCao in https://github.com/langgenius/dify/pull/9185
* chore: translate i18n files by @github-actions in https://github.com/langgenius/dify/pull/9284
* feat: refresh-token by @WTW0313 in https://github.com/langgenius/dify/pull/9286
* Feat/implement-refresh-tokens by @laipz8200 in https://github.com/langgenius/dify/pull/9233
* Feat/new account page by @douxc in https://github.com/langgenius/dify/pull/9236
* chore: add abstract decorator and output log when query embedding fails by @hwzhuhao in https://github.com/langgenius/dify/pull/9264
* chore: add baidu-obs and supabase for .env.example by @hwzhuhao in https://github.com/langgenius/dify/pull/9289
* chore: translate i18n files by @github-actions in https://github.com/langgenius/dify/pull/9288
* Add Volcengine VikingDB as new vector provider by @yaoice in https://github.com/langgenius/dify/pull/9287
* fix: remove the latest message from the user that does not have any answer yet by @kurokobo in https://github.com/langgenius/dify/pull/9297
* chore: remove the copied zhipu_ai sdk by @hjlarry in https://github.com/langgenius/dify/pull/9270
* refactor: Refactor the service of retrieval the recommend app by @hwzhuhao in https://github.com/langgenius/dify/pull/9302
* chore: Optimize operations in Q&A mode by @Blubiubiu in https://github.com/langgenius/dify/pull/9274
* chore: add reopen preview btn by @Blubiubiu in https://github.com/langgenius/dify/pull/9279
* fix: Add new Milvus Lite wheel for manylinux2014_aarch64 by @laipz8200 in https://github.com/langgenius/dify/pull/9316
* fix: token refreshing logic issue by @WTW0313 in https://github.com/langgenius/dify/pull/9308
* chore(release): bump version to 0.9.2 by @laipz8200 in https://github.com/langgenius/dify/pull/9314
## New Contributors
* @zhao85 made their first contribution in https://github.com/langgenius/dify/pull/8983
* @Retr0-01 made their first contribution in https://github.com/langgenius/dify/pull/8992
* @aiscrm made their first contribution in https://github.com/langgenius/dify/pull/9030
* @s2oBCN made their first contribution in https://github.com/langgenius/dify/pull/8928
* @sotazum made their first contribution in https://github.com/langgenius/dify/pull/9065
* @infinitnet made their first contribution in https://github.com/langgenius/dify/pull/9068
* @Gaocarri made their first contribution in https://github.com/langgenius/dify/pull/8754
* @Blackman99 made their first contribution in https://github.com/langgenius/dify/pull/9076
* @alterxyz made their first contribution in https://github.com/langgenius/dify/pull/9115
* @ronaksingh27 made their first contribution in https://github.com/langgenius/dify/pull/9135
* @daisuke0926dev made their first contribution in https://github.com/langgenius/dify/pull/9157
* @ziyu4huang made their first contribution in https://github.com/langgenius/dify/pull/9160
* @WTW0313 made their first contribution in https://github.com/langgenius/dify/pull/9214
* @massif-01 made their first contribution in https://github.com/langgenius/dify/pull/9183
* @AkisAya made their first contribution in https://github.com/langgenius/dify/pull/9228
* @WayneCao made their first contribution in https://github.com/langgenius/dify/pull/9185
* @Blubiubiu made their first contribution in https://github.com/langgenius/dify/pull/9274
**Full Changelog**: https://github.com/langgenius/dify/compare/0.9.1...0.9.2