Test the self-deployed Gemini API #639

New Issue

Closed

opened 2026-02-16 10:20:00 -05:00 by yindo · 7 comments

yindo commented 2026-02-16 10:20:00 -05:00

Owner

Copy Link

Copy Source

Originally created by @ronge1012 on GitHub (Sep 11, 2025).

Self Checks

• I have read the Contributing Guide and Language Policy.
• This is only for bug report, if you would like to ask a question, please head to Discussions.
• I have searched for existing issues search for existing issues, including closed ones.
• I confirm that I am using English to submit this report, otherwise it will be closed.
• 【中文用户 & Non English User】请使用英语提交，否则会被关闭 ：）
• Please do not modify this template :) and fill in all the required fields.

Dify version

version:1.7.1

Cloud or Self Hosted

Self Hosted (Docker)

Steps to reproduce

Testing Process
test version:1.7.1

1. Test text input and output
   Test Workflow:

Test results: It works.

2. Test Audio Input Text Output
   Using gpt4o-audio, which has audio capabilities (small icon), enables new fields related to audio.

Using the official Gemini API with audio capabilities (small icon) allows for new audio fields.

Using the self-hosted version of Gemini, it lacks audio capabilities (small icon) and has no fields related to audio.

When using the self-hosted version of Gemini to recognize images, the model possesses visual capabilities and is capable of identifying images.

This is the model we provide.

We examined the source code and found that the section calling the OpenAI-compatible interface is encrypted, making it impossible for us to modify it ourselves. So, is it possible to add audio capabilities to the OpenAI-compatible functionality?

✔️ Expected Behavior

Give me a solution

❌ Actual Behavior

No response

Originally created by @ronge1012 on GitHub (Sep 11, 2025). ### Self Checks - [x] I have read the [Contributing Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) and [Language Policy](https://github.com/langgenius/dify/issues/1542). - [x] This is only for bug report, if you would like to ask a question, please head to [Discussions](https://github.com/langgenius/dify/discussions/categories/general). - [x] I have searched for existing issues [search for existing issues](https://github.com/langgenius/dify/issues), including closed ones. - [x] I confirm that I am using English to submit this report, otherwise it will be closed. - [x] 【中文用户 & Non English User】请使用英语提交，否则会被关闭 ：） - [x] Please do not modify this template :) and fill in all the required fields. ### Dify version version:1.7.1 ### Cloud or Self Hosted Self Hosted (Docker) ### Steps to reproduce Testing Process test version:1.7.1 1. Test text input and output Test Workflow:  Test results: It works.  2. Test Audio Input Text Output Using gpt4o-audio, which has audio capabilities (small icon), enables new fields related to audio. <img width="1440" height="733" alt="Image" src="https://github.com/user-attachments/assets/76e9a541-9242-4f2d-8ba7-d6ee8acba6de" /> Using the official Gemini API with audio capabilities (small icon) allows for new audio fields. <img width="960" height="491" alt="Image" src="https://github.com/user-attachments/assets/8bcb9053-b794-4264-91c3-4c0383df0d85" /> Using the self-hosted version of Gemini, it lacks audio capabilities (small icon) and has no fields related to audio. <img width="960" height="482" alt="Image" src="https://github.com/user-attachments/assets/c72321fd-751d-478b-bdaa-90d9b837f04f" /> When using the self-hosted version of Gemini to recognize images, the model possesses visual capabilities and is capable of identifying images.  This is the model we provide.  We examined the source code and found that the section calling the OpenAI-compatible interface is encrypted, making it impossible for us to modify it ourselves. So, is it possible to add audio capabilities to the OpenAI-compatible functionality? <img width="1682" height="214" alt="Image" src="https://github.com/user-attachments/assets/570d417e-eb52-411d-a791-04b2d2c6869b" /> ### ✔️ Expected Behavior Give me a solution ### ❌ Actual Behavior _No response_

yindo added the enhancement label 2026-02-16 10:20:00 -05:00

yindo closed this issue 2026-02-16 10:20:00 -05:00

yindo commented 2026-02-16 10:20:01 -05:00

Author

Owner

Copy Link

Copy Source

@dosubot[bot] commented on GitHub (Sep 11, 2025):

Hi @ronge1012! I'm Dosu and I’m helping the dify team.

Currently, Dify exposes model capabilities like audio through the features field in the model schema, which is set during provider/model registration. For your self-hosted Gemini model, audio features are missing because the schema does not include ModelFeature.AUDIO, and there is no configuration or plugin mechanism to enable this without code changes. Even if you could patch the schema, the backend must support audio endpoints for it to work—otherwise, the UI fields will not function as expected.

There are ongoing efforts to standardize media content types (including audio) for Gemini and OpenAI-compatible models, but these changes are not yet merged and are unavailable in Dify 1.7.1 [source]. The OpenAI-compatible plugin also lacks audio processing logic, so adding audio capability would require updating the code to handle audio prompt messages [source].

If you need speech-to-text or TTS features, you can enable them in the system provider's settings and the app's Function settings, then publish the app for changes to take effect [source]. However, this does not enable audio input/output for the Gemini model itself.

In summary: enabling audio for self-hosted Gemini via the OpenAI-compatible interface is not possible without code changes or waiting for upstream updates that add this support. If you need audio now, use a model and provider that already advertises audio capability in Dify.

To reply, just mention @dosu.

---

^{How did I do? Good | Irrelevant | Incorrect | Verbose | Hallucination | Report 🐛 | Other}    

@dosubot[bot] commented on GitHub (Sep 11, 2025): <!-- Greeting --> Hi @ronge1012! I'm [Dosu](https://go.dosu.dev/dosubot) and I’m helping the dify team. <!-- Answer --> Currently, Dify exposes model capabilities like audio through the `features` field in the model schema, which is set during provider/model registration. For your self-hosted Gemini model, audio features are missing because the schema does not include `ModelFeature.AUDIO`, and there is no configuration or plugin mechanism to enable this without code changes. Even if you could patch the schema, the backend must support audio endpoints for it to work—otherwise, the UI fields will not function as expected. There are ongoing efforts to standardize media content types (including audio) for Gemini and OpenAI-compatible models, but these changes are not yet merged and are unavailable in Dify 1.7.1 [[source](https://github.com/langgenius/dify/issues/11590)]. The OpenAI-compatible plugin also lacks audio processing logic, so adding audio capability would require updating the code to handle audio prompt messages [[source](https://github.com/langgenius/dify-official-plugins/issues/1010)]. If you need speech-to-text or TTS features, you can enable them in the system provider's settings and the app's Function settings, then publish the app for changes to take effect [[source](https://github.com/langgenius/dify/issues/16758)]. However, this does not enable audio input/output for the Gemini model itself. In summary: enabling audio for self-hosted Gemini via the OpenAI-compatible interface is not possible without code changes or waiting for upstream updates that add this support. If you need audio now, use a model and provider that already advertises audio capability in Dify. <!-- Dosu Comment Footer --> *To reply, just mention [@dosu](https://go.dosu.dev/dosubot).* --- ^{How did I do? [Good](https://app.dosu.dev/response-feedback/ec24a627-bf53-469f-8547-5cc8e6699a28?feedback_type=great_response) | [Irrelevant](https://app.dosu.dev/response-feedback/ec24a627-bf53-469f-8547-5cc8e6699a28?feedback_type=irrelevant_answer) | [Incorrect](https://app.dosu.dev/response-feedback/ec24a627-bf53-469f-8547-5cc8e6699a28?feedback_type=incorrect_sources) | [Verbose](https://app.dosu.dev/response-feedback/ec24a627-bf53-469f-8547-5cc8e6699a28?feedback_type=too_verbose) | [Hallucination](https://app.dosu.dev/response-feedback/ec24a627-bf53-469f-8547-5cc8e6699a28?feedback_type=hallucination) | [Report 🐛](https://app.dosu.dev/response-feedback/ec24a627-bf53-469f-8547-5cc8e6699a28?feedback_type=bug_report) | [Other](https://app.dosu.dev/response-feedback/ec24a627-bf53-469f-8547-5cc8e6699a28?feedback_type=other)}&nbsp;&nbsp;[](https://app.dosu.dev/6088a4f4-073a-43f3-b3d4-4f06fb0c05a0/ask?utm_source=github)&nbsp;[](https://go.dosu.dev/discord-bot)&nbsp;[](https://twitter.com/intent/tweet?text=%40dosu_ai%20helped%20me%20solve%20this%20issue!&url=https%3A//github.com/langgenius/dify/issues/25579)

yindo commented 2026-02-16 10:20:01 -05:00

Author

Owner

Copy Link

Copy Source

@dosubot[bot] commented on GitHub (Sep 11, 2025):

The self-hosted Gemini API in Dify currently lacks audio capabilities because the underlying Gemini model and its API do not expose audio endpoints or features. Dify's OpenAI-compatible interface can only surface audio support if both the model and its provider configuration explicitly support it. While Dify's infrastructure does recognize audio and vision features at the metadata/configuration level, the self-hosted Gemini implementation does not include the necessary audio processing routines or annotate audio support, so the UI and API do not show audio fields or icons. There is no hardcoded technical barrier in Dify's code; the limitation is with the self-hosted Gemini model/API itself, not the Dify integration. To enable audio, the Gemini model/API you deploy must support audio features, and the provider configuration must expose them—currently, this is not the case for self-hosted Gemini setups^{1 2 3} .

To reply, just mention @dosu.

---

^{How did I do? Good | Irrelevant | Incorrect | Verbose | Hallucination | Report 🐛 | Other}   

---

1. OpenAI plugin missing audio support ↩︎

2. Model capability system in Dify ↩︎

3. Gemini plugin config and limitations ↩︎

@dosubot[bot] commented on GitHub (Sep 11, 2025): <!-- Answer --> The self-hosted Gemini API in Dify currently lacks audio capabilities because the underlying Gemini model and its API do not expose audio endpoints or features. Dify's OpenAI-compatible interface can only surface audio support if both the model and its provider configuration explicitly support it. While Dify's infrastructure does recognize audio and vision features at the metadata/configuration level, the self-hosted Gemini implementation does not include the necessary audio processing routines or annotate audio support, so the UI and API do not show audio fields or icons. There is no hardcoded technical barrier in Dify's code; the limitation is with the self-hosted Gemini model/API itself, not the Dify integration. To enable audio, the Gemini model/API you deploy must support audio features, and the provider configuration must expose them—currently, this is not the case for self-hosted Gemini setups[^1][^2][^3]. [^1]: [OpenAI plugin missing audio support](https://github.com/langgenius/dify-official-plugins/issues/1010) [^2]: [Model capability system in Dify](https://github.com/langgenius/dify/blob/c0e1015c6e150900cd9ce729f0ac3b276a924a69/api/core/model_runtime/entities/model_entities.py) [^3]: [Gemini plugin config and limitations](https://github.com/langgenius/dify-official-plugins/pull/1539) <!-- Dosu Comment Footer --> *To reply, just mention [@dosu](https://go.dosu.dev/dosubot).* --- ^{How did I do? [Good](https://app.dosu.dev/response-feedback/cf0fe22f-b07f-4735-a9e4-ec5e6b0b853b?feedback_type=great_response) | [Irrelevant](https://app.dosu.dev/response-feedback/cf0fe22f-b07f-4735-a9e4-ec5e6b0b853b?feedback_type=irrelevant_answer) | [Incorrect](https://app.dosu.dev/response-feedback/cf0fe22f-b07f-4735-a9e4-ec5e6b0b853b?feedback_type=incorrect_sources) | [Verbose](https://app.dosu.dev/response-feedback/cf0fe22f-b07f-4735-a9e4-ec5e6b0b853b?feedback_type=too_verbose) | [Hallucination](https://app.dosu.dev/response-feedback/cf0fe22f-b07f-4735-a9e4-ec5e6b0b853b?feedback_type=hallucination) | [Report 🐛](https://app.dosu.dev/response-feedback/cf0fe22f-b07f-4735-a9e4-ec5e6b0b853b?feedback_type=bug_report) | [Other](https://app.dosu.dev/response-feedback/cf0fe22f-b07f-4735-a9e4-ec5e6b0b853b?feedback_type=other)}&nbsp;&nbsp;[](https://go.dosu.dev/discord-bot)&nbsp;[](https://twitter.com/intent/tweet?text=%40dosu_ai%20helped%20me%20solve%20this%20issue!&url=https%3A//github.com/langgenius/dify-official-plugins/issues/1699)

yindo commented 2026-02-16 10:20:01 -05:00

Author

Owner

Copy Link

Copy Source

@SenWeiV commented on GitHub (Sep 16, 2025):

The self-hosted Gemini API in Dify currently lacks audio capabilities because the underlying Gemini model and its API do not expose audio endpoints or features. Dify's OpenAI-compatible interface can only surface audio support if both the model and its provider configuration explicitly support it. While Dify's infrastructure does recognize audio and vision features at the metadata/configuration level, the self-hosted Gemini implementation does not include the necessary audio processing routines or annotate audio support, so the UI and API do not show audio fields or icons. There is no hardcoded technical barrier in Dify's code; the limitation is with the self-hosted Gemini model/API itself, not the Dify integration. To enable audio, the Gemini model/API you deploy must support audio features, and the provider configuration must expose them—currently, this is not the case for self-hosted Gemini setups123.

To reply, just mention @dosu.

How did I do? Good | Irrelevant | Incorrect | Verbose | Hallucination | Report 🐛 | Other   

Footnotes

1. OpenAI plugin missing audio support ↩
2. Model capability system in Dify ↩
3. Gemini plugin config and limitations ↩

hi! so you mean that this issue is not the platform issue? they need to make the self-hosted Gemini api to support the audio features?

@SenWeiV commented on GitHub (Sep 16, 2025): > The self-hosted Gemini API in Dify currently lacks audio capabilities because the underlying Gemini model and its API do not expose audio endpoints or features. Dify's OpenAI-compatible interface can only surface audio support if both the model and its provider configuration explicitly support it. While Dify's infrastructure does recognize audio and vision features at the metadata/configuration level, the self-hosted Gemini implementation does not include the necessary audio processing routines or annotate audio support, so the UI and API do not show audio fields or icons. There is no hardcoded technical barrier in Dify's code; the limitation is with the self-hosted Gemini model/API itself, not the Dify integration. To enable audio, the Gemini model/API you deploy must support audio features, and the provider configuration must expose them—currently, this is not the case for self-hosted Gemini setups[1](#user-content-fn-1-98054ed3e7f319e0158d15554272ff8c)[2](#user-content-fn-2-98054ed3e7f319e0158d15554272ff8c)[3](#user-content-fn-3-98054ed3e7f319e0158d15554272ff8c). > > _To reply, just mention [@dosu](https://go.dosu.dev/dosubot)._ > > How did I do? [Good](https://app.dosu.dev/response-feedback/cf0fe22f-b07f-4735-a9e4-ec5e6b0b853b?feedback_type=great_response) | [Irrelevant](https://app.dosu.dev/response-feedback/cf0fe22f-b07f-4735-a9e4-ec5e6b0b853b?feedback_type=irrelevant_answer) | [Incorrect](https://app.dosu.dev/response-feedback/cf0fe22f-b07f-4735-a9e4-ec5e6b0b853b?feedback_type=incorrect_sources) | [Verbose](https://app.dosu.dev/response-feedback/cf0fe22f-b07f-4735-a9e4-ec5e6b0b853b?feedback_type=too_verbose) | [Hallucination](https://app.dosu.dev/response-feedback/cf0fe22f-b07f-4735-a9e4-ec5e6b0b853b?feedback_type=hallucination) | [Report 🐛](https://app.dosu.dev/response-feedback/cf0fe22f-b07f-4735-a9e4-ec5e6b0b853b?feedback_type=bug_report) | [Other](https://app.dosu.dev/response-feedback/cf0fe22f-b07f-4735-a9e4-ec5e6b0b853b?feedback_type=other)  [](https://go.dosu.dev/discord-bot) [](https://twitter.com/intent/tweet?text=%40dosu_ai%20helped%20me%20solve%20this%20issue!&url=https%3A//github.com/langgenius/dify-official-plugins/issues/1699) > > ## Footnotes > 1. [OpenAI plugin missing audio support](https://github.com/langgenius/dify-official-plugins/issues/1010) [↩](#user-content-fnref-1-98054ed3e7f319e0158d15554272ff8c) > 2. [Model capability system in Dify](https://github.com/langgenius/dify/blob/c0e1015c6e150900cd9ce729f0ac3b276a924a69/api/core/model_runtime/entities/model_entities.py) [↩](#user-content-fnref-2-98054ed3e7f319e0158d15554272ff8c) > 3. [Gemini plugin config and limitations](https://github.com/langgenius/dify-official-plugins/pull/1539) [↩](#user-content-fnref-3-98054ed3e7f319e0158d15554272ff8c) hi! so you mean that this issue is not the platform issue? they need to make the self-hosted Gemini api to support the audio features?

yindo commented 2026-02-16 10:20:01 -05:00

Author

Owner

Copy Link

Copy Source

@SenWeiV commented on GitHub (Sep 16, 2025):

Hi @ronge1012! I'm Dosu and I’m helping the dify team.

Currently, Dify exposes model capabilities like audio through the features field in the model schema, which is set during provider/model registration. For your self-hosted Gemini model, audio features are missing because the schema does not include ModelFeature.AUDIO, and there is no configuration or plugin mechanism to enable this without code changes. Even if you could patch the schema, the backend must support audio endpoints for it to work—otherwise, the UI fields will not function as expected.

There are ongoing efforts to standardize media content types (including audio) for Gemini and OpenAI-compatible models, but these changes are not yet merged and are unavailable in Dify 1.7.1 [source]. The OpenAI-compatible plugin also lacks audio processing logic, so adding audio capability would require updating the code to handle audio prompt messages [source].

If you need speech-to-text or TTS features, you can enable them in the system provider's settings and the app's Function settings, then publish the app for changes to take effect [source]. However, this does not enable audio input/output for the Gemini model itself.

In summary: enabling audio for self-hosted Gemini via the OpenAI-compatible interface is not possible without code changes or waiting for upstream updates that add this support. If you need audio now, use a model and provider that already advertises audio capability in Dify.

To reply, just mention @dosu.

How did I do? Good | Irrelevant | Incorrect | Verbose | Hallucination | Report 🐛 | Other    

cool! I think this might be a good solution. with the update of the dify and "open ai compatible plugin", this problem should be solved. Hope this can be done soon!

@SenWeiV commented on GitHub (Sep 16, 2025): > Hi [@ronge1012](https://github.com/ronge1012)! I'm [Dosu](https://go.dosu.dev/dosubot) and I’m helping the dify team. > > Currently, Dify exposes model capabilities like audio through the `features` field in the model schema, which is set during provider/model registration. For your self-hosted Gemini model, audio features are missing because the schema does not include `ModelFeature.AUDIO`, and there is no configuration or plugin mechanism to enable this without code changes. Even if you could patch the schema, the backend must support audio endpoints for it to work—otherwise, the UI fields will not function as expected. > > There are ongoing efforts to standardize media content types (including audio) for Gemini and OpenAI-compatible models, but these changes are not yet merged and are unavailable in Dify 1.7.1 [[source](https://github.com/langgenius/dify/issues/11590)]. The OpenAI-compatible plugin also lacks audio processing logic, so adding audio capability would require updating the code to handle audio prompt messages [[source](https://github.com/langgenius/dify-official-plugins/issues/1010)]. > > If you need speech-to-text or TTS features, you can enable them in the system provider's settings and the app's Function settings, then publish the app for changes to take effect [[source](https://github.com/langgenius/dify/issues/16758)]. However, this does not enable audio input/output for the Gemini model itself. > > In summary: enabling audio for self-hosted Gemini via the OpenAI-compatible interface is not possible without code changes or waiting for upstream updates that add this support. If you need audio now, use a model and provider that already advertises audio capability in Dify. > > _To reply, just mention [@dosu](https://go.dosu.dev/dosubot)._ > > How did I do? [Good](https://app.dosu.dev/response-feedback/ec24a627-bf53-469f-8547-5cc8e6699a28?feedback_type=great_response) | [Irrelevant](https://app.dosu.dev/response-feedback/ec24a627-bf53-469f-8547-5cc8e6699a28?feedback_type=irrelevant_answer) | [Incorrect](https://app.dosu.dev/response-feedback/ec24a627-bf53-469f-8547-5cc8e6699a28?feedback_type=incorrect_sources) | [Verbose](https://app.dosu.dev/response-feedback/ec24a627-bf53-469f-8547-5cc8e6699a28?feedback_type=too_verbose) | [Hallucination](https://app.dosu.dev/response-feedback/ec24a627-bf53-469f-8547-5cc8e6699a28?feedback_type=hallucination) | [Report 🐛](https://app.dosu.dev/response-feedback/ec24a627-bf53-469f-8547-5cc8e6699a28?feedback_type=bug_report) | [Other](https://app.dosu.dev/response-feedback/ec24a627-bf53-469f-8547-5cc8e6699a28?feedback_type=other)  [](https://app.dosu.dev/6088a4f4-073a-43f3-b3d4-4f06fb0c05a0/ask?utm_source=github) [](https://go.dosu.dev/discord-bot) [](https://twitter.com/intent/tweet?text=%40dosu_ai%20helped%20me%20solve%20this%20issue!&url=https%3A//github.com/langgenius/dify/issues/25579) cool! I think this might be a good solution. with the update of the dify and "open ai compatible plugin", this problem should be solved. Hope this can be done soon!

yindo commented 2026-02-16 10:20:01 -05:00

Author

Owner

Copy Link

Copy Source

@newnewliu commented on GitHub (Sep 16, 2025):

DEAL WITH IT! IT BOTHER ME A LOT!

@newnewliu commented on GitHub (Sep 16, 2025): DEAL WITH IT! IT BOTHER ME A LOT!

yindo commented 2026-02-16 10:20:01 -05:00

Author

Owner

Copy Link

Copy Source

@Alwaysoffline commented on GitHub (Sep 16, 2025):

I also encountered the same problem, hope you can pay attention to it.

@Alwaysoffline commented on GitHub (Sep 16, 2025): I also encountered the same problem, hope you can pay attention to it.

yindo commented 2026-02-16 10:20:01 -05:00

Author

Owner

Copy Link

Copy Source

@dosubot[bot] commented on GitHub (Oct 2, 2025):

Hi, @ronge1012. I'm Dosu, and I'm helping the dify-official-plugins team manage their backlog and am marking this issue as stale.

Issue Summary:

• You reported that the self-hosted Gemini API v1.7.1 on Docker supports text I/O but lacks audio I/O features.
• This limitation is due to the self-hosted Gemini model and API not exposing audio endpoints or including audio in the schema.
• Dify requires both model and provider support to enable audio features.
• Efforts to standardize media types and update plugins may address this in the future.
• Other users have also expressed interest in audio support and a timely fix.

Next Steps:

• Please let me know if this issue is still relevant with the latest version of the dify-official-plugins repository by commenting here.
• If I do not hear back within 5 days, I will automatically close this issue.

Thank you for your understanding and contribution!

@dosubot[bot] commented on GitHub (Oct 2, 2025): Hi, @ronge1012. I'm [Dosu](https://dosu.dev), and I'm helping the dify-official-plugins team manage their backlog and am marking this issue as stale. **Issue Summary:** - You reported that the self-hosted Gemini API v1.7.1 on Docker supports text I/O but lacks audio I/O features. - This limitation is due to the self-hosted Gemini model and API not exposing audio endpoints or including audio in the schema. - Dify requires both model and provider support to enable audio features. - Efforts to standardize media types and update plugins may address this in the future. - Other users have also expressed interest in audio support and a timely fix. **Next Steps:** - Please let me know if this issue is still relevant with the latest version of the dify-official-plugins repository by commenting here. - If I do not hear back within 5 days, I will automatically close this issue. Thank you for your understanding and contribution!

Sign in to join this conversation.

No Branch/Tag Specified

Branches Tags

main

dosu/doc-update-3502

linw/snp-556-tongyi-qwen-long-document-input-support

dependabot/uv/extensions/llamacloud/uv-6242a161da

feat/moonshot-kimi-k3-k27-code

feat/gemini-system-instruction-semantics

fix/gemini-text-system-parts

dosu/doc-update-3436

feat/openai-gpt-5-6-support

fix/outlook-trigger-readme-permissions

fix/microsoft-oauth-datasource-tenant

fix/byteplus-api-base-url-label

feat/ark-video-generation-custom-models

fix/openai-stream-reasoning-thinking

fix/skip-live-tests-missing-keys

codex/enhance-discord-integrations

codex/harden-trigger-oauth-permissions

update-lemonade-default-port

codex/fix-pr-review-ci

feat/ark-multimodal-polling

copilot/update-mineru-3x-plugin-file-types

feat/action-security-fix

feat/claude-fable5

codex/fix-ollama-model-category

codex/upgrade-ollama-latest

feat/minimax-m3

codex/refine-plugin-readmes

fix/fireworks-model-label-zh-hans

chore/version-bump-plugins-batch-06

chore/version-bump-plugins-batch-05

chore/version-bump-plugins-batch-04

chore/version-bump-plugins-batch-03

chore/version-bump-plugins-batch-02

fix/plugin-sdk-i18n-fields

chore/version-bump-plugins-batch-01

chore/dependencies-high-priority

chore/dependencies-medium-priority

chore/dependencies-low-priority-clean

chore/dependencies-low-priority

fix/tongyi-align-deepseek-model-metadata

codex/update-openrouter-models

codex/azure-ai-studio-cjk-version-bump

feat/ernie-image-tool

claude/cranky-thompson-b6a281

fix/remove-unavailable-volcengine-models

fix/legacy-plugin-daemon-compatibility

copilot/add-deepseek-v4-to-openrouter

codex/merge-tongyi-tts-prs

codex/depot-runners

chore/migrate-selected-plugins-to-uv-lock

fix/repair-failed-plugin-deploys

ci/fix-plugin-change-detection

chore/migrate-aws-s3-storage-to-uv-lock

chore/migrate-somark-dependencies-to-uv-lock

ci/uv-lock-dependency-validation

fix/2911-openai-api-compatible-tool-call-content

chore/remove-deprecated-plugins

copilot/add-more-models-openrouter-provider

copilot/fix-error-connecting-fireworks-ai

fix/openai-compatible-max-completion-tokens-validation

fix/gemini-lockfile

chore/add-React-fallback-desc

feat/add-gemini-embedding-2-preview

copilot/add-claude-sonnet-opus-4-6

codex/update-xai-models-2721

fix/remove-sentence-transformer-for-hubspot

feat/add-gpt-5.4

copilot/fix-ci-errors-and-bump-version

copilot/fix-security-errors-combined

copilot/update-gemini-model-version

fix/anthropic-parallel-tool-call

codex/fix-azure-ai-studio-azure-core-1-38

codex/fix-azure-blob-azure-core-1-38

codex/fix-azure-openai-azure-core-1-38

gitlab-credentials-c

fix/openrouter-validation-model

fix/gemini-null-checks

fix/deepseek-tool-message-ignore

fix/gemini-dependencies

No results found.

Labels

Clear labels

bug

bug

bug

dependencies

documentation

enhancement

good first issue

invalid

pull-request

Mirrored from GitHub Pull Request

question

stale

No Label enhancement

Milestone

No items

No Milestone

Projects

Clear projects

No project

Assignees

Clear assignees

yindo

No Assignees

1 Participants

Notifications

Subscribe

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: langgenius/dify-official-plugins#639