langgenius/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-07-21 03:55:25 -04:00
Code Issues 775 Packages Projects Releases 10 Wiki Activity

In agent chat mode, using the qwen max model, the chat error is as follows, which occurs when calling the knowledge base，Is the dependency package version of the qwen series that dify currently depends on too low #15814

New Issue
Closed
opened 2026-02-21 19:23:28 -05:00 by yindo · 5 comments
yindo commented 2026-02-21 19:23:28 -05:00
Owner
Copy Link
Copy Source

Originally created by @orcharddd2024 on GitHub (Aug 1, 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

0.15.3

Cloud or Self Hosted

Self Hosted (Docker)

Steps to reproduce

	role: assistant
	content: 
	role: user
	content: Summarize what is currently being discussed in this knowledge base


[on_llm_new_chunk]2025-08-01 04:02:27.761 ERROR [Thread-114 (_generate_worker)] [app_generator.py:259] - Error when generating
Traceback (most recent call last):
  File "C:\Users\Administrator\ghtencent\dify\api\core\model_runtime\model_providers\__base\large_language_model.py", line 455, in _invoke_result_generator
    for chunk in result:
  File "C:\Users\Administrator\ghtencent\dify\api\core\model_runtime\model_providers\tongyi\llm\llm.py", line 294, in _handle_generate_stream_response
    id=tool_call_obj["function"]["name"],
       ~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^
KeyError: 'name'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "C:\Users\Administrator\ghtencent\dify\api\core\app\apps\agent_chat\app_generator.py", line 242, in _generate_worker
    runner.run(
  File "C:\Users\Administrator\ghtencent\dify\api\core\app\apps\agent_chat\app_runner.py", line 261, in run
    self._handle_invoke_result(
  File "C:\Users\Administrator\ghtencent\dify\api\core\app\apps\base_app_runner.py", line 274, in _handle_invoke_result
    self._handle_invoke_result_stream(invoke_result=invoke_result, queue_manager=queue_manager, agent=agent)
  File "C:\Users\Administrator\ghtencent\dify\api\core\app\apps\base_app_runner.py", line 309, in _handle_invoke_result_stream
    for result in invoke_result:
  File "C:\Users\Administrator\ghtencent\dify\api\core\agent\fc_agent_runner.py", line 112, in run
    for chunk in chunks:
  File "C:\Users\Administrator\ghtencent\dify\api\core\model_runtime\model_providers\__base\large_language_model.py", line 479, in _invoke_result_generator
    raise self._transform_invoke_error(e)
core.model_runtime.errors.invoke.InvokeError: [tongyi] Error: 'name'
2025-08-01 04:02:27.777 INFO [Thread-113 (process_request_thread)] [_internal.py:97] - 127.0.0.1 - - [01/Aug/2025 12:02:27] "POST /api/chat-messages HTTP/1.1" 200 -
250528
250528
250528
250528
2025-08-01 04:03:02.987 INFO [Thread-117 (process_request_thread)] [_internal.py:97] - 127.0.0.1 - - [01/Aug/2025 12:03:02] "GET /api/meta HTTP/1.1" 200 -
250528
250528
2025-08-01 04:03:02.987 INFO [Thread-115 (process_request_thread)] [_internal.py:97] - 127.0.0.1 - - [01/Aug/2025 12:03:02] "GET /api/site HTTP/1.1" 200 -
2025-08-01 04:03:02.988 INFO [Thread-116 (process_request_thread)] [_internal.py:97] - 127.0.0.1 - - [01/Aug/2025 12:03:02] "GET /api/parameters HTTP/1.1" 200 -
2025-08-01 04:03:02.995 INFO [Thread-118 (process_request_thread)] [_internal.py:97] - 127.0.0.1 - - [01/Aug/2025 12:03:02] "GET /api/conversations?limit=100&pinned=true HTTP/1.1" 200 -
2025-08-01 04:03:03.003 INFO [Thread-119 (process_request_thread)] [_internal.py:97] - 127.0.0.1 - - [01/Aug/2025 12:03:03] "GET /api/conversations?limit=100&pinned=false HTTP/1.1" 200 -
2025-08-01 04:03:03.064 INFO [Thread-120 (process_request_thread)] [_internal.py:97] - 127.0.0.1 - - [01/Aug/2025 12:03:03] "GET /api/messages?conversation_id=f6329fa8-07ac-4794-b76b-d2ffe1c01fd5&limit=20&last_id= HTTP/1.1" 200 -
Image Image

As long as it involves calling tools, the qwen model will report an error, while the openai model will not report an error

✔️ Expected Behavior

role: user
What day is it today
role: assistant
The day of the week today depends on the current actual date. You can check the calendar on the device or ask for specific dates, and I will help you calculate them. If you tell me today's date, I can also help you determine what day of the week it is.
role: user
content: hello

Hello 2025-08-01 03:19:49.085 INFO [Thread-32 (process_request_thread)] [_internal.py:97] - 127.0.0.1 - - [01/Aug/2025 11:19:49] "POST /api/chat-messages HTTP/1.1" 200 -
Is there anything I can help you with? If you have any questions or need advice, such as travel planning, strategic thinking, or other aspects, feel free to let me know at any time.
[on_llm_after_invoke]
Content: Hello! Is there anything I can help you with? If you have any questions or need advice, such as travel planning, strategic thinking, or other aspects, feel free to let me know at any time.
Model: qwen-max
Usage: prompt_tokens=686 prompt_unit_price=Decimal('0.02') prompt_price_unit=Decimal('0.001') prompt_price=Decimal('0.0137200') completion_tokens=29 completion_unit_price=Decimal('0.06') completion_price_unit=Decimal('0.001') completion_price=Decimal('0.0017400') total_tokens=715 total_price=Decimal('0.0154600') currency='RMB' latency=5.221896200000629
System Fingerprint: None

❌ Actual Behavior

Image Using qwen max for conversation, the error is as follows 
[on_llm_new_chunk]2025-08-01 03:20:51.886 ERROR [Thread-41 (_generate_worker)] [app_generator.py:259] - Error when generating
Traceback (most recent call last):
  File "C:\Users\Administrator\ghtencent\dify\api\core\model_runtime\model_providers\__base\large_language_model.py", line 455, in _invoke_result_generator
    for chunk in result:
  File "C:\Users\Administrator\ghtencent\dify\api\core\model_runtime\model_providers\tongyi\llm\llm.py", line 294, in _handle_generate_stream_response
    id=tool_call_obj["function"]["name"],
       ~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^
KeyError: 'name'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "C:\Users\Administrator\ghtencent\dify\api\core\app\apps\agent_chat\app_generator.py", line 242, in _generate_worker
    runner.run(
  File "C:\Users\Administrator\ghtencent\dify\api\core\app\apps\agent_chat\app_runner.py", line 261, in run
    self._handle_invoke_result(
  File "C:\Users\Administrator\ghtencent\dify\api\core\app\apps\base_app_runner.py", line 274, in _handle_invoke_result
    self._handle_invoke_result_stream(invoke_result=invoke_result, queue_manager=queue_manager, agent=agent)
  File "C:\Users\Administrator\ghtencent\dify\api\core\app\apps\base_app_runner.py", line 309, in _handle_invoke_result_stream
    for result in invoke_result:
  File "C:\Users\Administrator\ghtencent\dify\api\core\agent\fc_agent_runner.py", line 112, in run
    for chunk in chunks:
  File "C:\Users\Administrator\ghtencent\dify\api\core\model_runtime\model_providers\__base\large_language_model.py", line 479, in _invoke_result_generator
    raise self._transform_invoke_error(e)
core.model_runtime.errors.invoke.InvokeError: [tongyi] Error: 'name'

When processing tool_calls returned by the Qwen model, the code attempted to access tool_call_obj ["function"] ["name"], but one of the tool_call_obj ["function"] did not have a name field, resulting in a KeyError being thrown.
I think the problem lies in the upgrade of the qwen model version, but the local dependency package is still an old version, so the processing of return data in dify still follows the constraints of the old version, which leads to errors

Originally created by @orcharddd2024 on GitHub (Aug 1, 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 0.15.3 ### Cloud or Self Hosted Self Hosted (Docker) ### Steps to reproduce ``` role: assistant content: role: user content: Summarize what is currently being discussed in this knowledge base [on_llm_new_chunk]2025-08-01 04:02:27.761 ERROR [Thread-114 (_generate_worker)] [app_generator.py:259] - Error when generating Traceback (most recent call last): File "C:\Users\Administrator\ghtencent\dify\api\core\model_runtime\model_providers\__base\large_language_model.py", line 455, in _invoke_result_generator for chunk in result: File "C:\Users\Administrator\ghtencent\dify\api\core\model_runtime\model_providers\tongyi\llm\llm.py", line 294, in _handle_generate_stream_response id=tool_call_obj["function"]["name"], ~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^ KeyError: 'name' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "C:\Users\Administrator\ghtencent\dify\api\core\app\apps\agent_chat\app_generator.py", line 242, in _generate_worker runner.run( File "C:\Users\Administrator\ghtencent\dify\api\core\app\apps\agent_chat\app_runner.py", line 261, in run self._handle_invoke_result( File "C:\Users\Administrator\ghtencent\dify\api\core\app\apps\base_app_runner.py", line 274, in _handle_invoke_result self._handle_invoke_result_stream(invoke_result=invoke_result, queue_manager=queue_manager, agent=agent) File "C:\Users\Administrator\ghtencent\dify\api\core\app\apps\base_app_runner.py", line 309, in _handle_invoke_result_stream for result in invoke_result: File "C:\Users\Administrator\ghtencent\dify\api\core\agent\fc_agent_runner.py", line 112, in run for chunk in chunks: File "C:\Users\Administrator\ghtencent\dify\api\core\model_runtime\model_providers\__base\large_language_model.py", line 479, in _invoke_result_generator raise self._transform_invoke_error(e) core.model_runtime.errors.invoke.InvokeError: [tongyi] Error: 'name' 2025-08-01 04:02:27.777 INFO [Thread-113 (process_request_thread)] [_internal.py:97] - 127.0.0.1 - - [01/Aug/2025 12:02:27] "POST /api/chat-messages HTTP/1.1" 200 - 250528 250528 250528 250528 2025-08-01 04:03:02.987 INFO [Thread-117 (process_request_thread)] [_internal.py:97] - 127.0.0.1 - - [01/Aug/2025 12:03:02] "GET /api/meta HTTP/1.1" 200 - 250528 250528 2025-08-01 04:03:02.987 INFO [Thread-115 (process_request_thread)] [_internal.py:97] - 127.0.0.1 - - [01/Aug/2025 12:03:02] "GET /api/site HTTP/1.1" 200 - 2025-08-01 04:03:02.988 INFO [Thread-116 (process_request_thread)] [_internal.py:97] - 127.0.0.1 - - [01/Aug/2025 12:03:02] "GET /api/parameters HTTP/1.1" 200 - 2025-08-01 04:03:02.995 INFO [Thread-118 (process_request_thread)] [_internal.py:97] - 127.0.0.1 - - [01/Aug/2025 12:03:02] "GET /api/conversations?limit=100&pinned=true HTTP/1.1" 200 - 2025-08-01 04:03:03.003 INFO [Thread-119 (process_request_thread)] [_internal.py:97] - 127.0.0.1 - - [01/Aug/2025 12:03:03] "GET /api/conversations?limit=100&pinned=false HTTP/1.1" 200 - 2025-08-01 04:03:03.064 INFO [Thread-120 (process_request_thread)] [_internal.py:97] - 127.0.0.1 - - [01/Aug/2025 12:03:03] "GET /api/messages?conversation_id=f6329fa8-07ac-4794-b76b-d2ffe1c01fd5&limit=20&last_id= HTTP/1.1" 200 - ``` <img width="1687" height="583" alt="Image" src="https://github.com/user-attachments/assets/b8fb0b75-697b-42cc-9ea2-009688eab94f" /> <img width="1617" height="321" alt="Image" src="https://github.com/user-attachments/assets/e12ea2e8-9649-4941-b961-ef254fe6cb6b" /> As long as it involves calling tools, the qwen model will report an error, while the openai model will not report an error ### ✔️ Expected Behavior ``` role: user What day is it today role: assistant The day of the week today depends on the current actual date. You can check the calendar on the device or ask for specific dates, and I will help you calculate them. If you tell me today's date, I can also help you determine what day of the week it is. role: user content: hello Hello 2025-08-01 03:19:49.085 INFO [Thread-32 (process_request_thread)] [_internal.py:97] - 127.0.0.1 - - [01/Aug/2025 11:19:49] "POST /api/chat-messages HTTP/1.1" 200 - Is there anything I can help you with? If you have any questions or need advice, such as travel planning, strategic thinking, or other aspects, feel free to let me know at any time. [on_llm_after_invoke] Content: Hello! Is there anything I can help you with? If you have any questions or need advice, such as travel planning, strategic thinking, or other aspects, feel free to let me know at any time. Model: qwen-max Usage: prompt_tokens=686 prompt_unit_price=Decimal('0.02') prompt_price_unit=Decimal('0.001') prompt_price=Decimal('0.0137200') completion_tokens=29 completion_unit_price=Decimal('0.06') completion_price_unit=Decimal('0.001') completion_price=Decimal('0.0017400') total_tokens=715 total_price=Decimal('0.0154600') currency='RMB' latency=5.221896200000629 System Fingerprint: None ``` ### ❌ Actual Behavior <img width="1264" height="552" alt="Image" src="https://github.com/user-attachments/assets/016b1e20-39b2-44b6-b18b-58909cd25ded" /> Using qwen max for conversation, the error is as follows ``` [on_llm_new_chunk]2025-08-01 03:20:51.886 ERROR [Thread-41 (_generate_worker)] [app_generator.py:259] - Error when generating Traceback (most recent call last): File "C:\Users\Administrator\ghtencent\dify\api\core\model_runtime\model_providers\__base\large_language_model.py", line 455, in _invoke_result_generator for chunk in result: File "C:\Users\Administrator\ghtencent\dify\api\core\model_runtime\model_providers\tongyi\llm\llm.py", line 294, in _handle_generate_stream_response id=tool_call_obj["function"]["name"], ~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^ KeyError: 'name' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "C:\Users\Administrator\ghtencent\dify\api\core\app\apps\agent_chat\app_generator.py", line 242, in _generate_worker runner.run( File "C:\Users\Administrator\ghtencent\dify\api\core\app\apps\agent_chat\app_runner.py", line 261, in run self._handle_invoke_result( File "C:\Users\Administrator\ghtencent\dify\api\core\app\apps\base_app_runner.py", line 274, in _handle_invoke_result self._handle_invoke_result_stream(invoke_result=invoke_result, queue_manager=queue_manager, agent=agent) File "C:\Users\Administrator\ghtencent\dify\api\core\app\apps\base_app_runner.py", line 309, in _handle_invoke_result_stream for result in invoke_result: File "C:\Users\Administrator\ghtencent\dify\api\core\agent\fc_agent_runner.py", line 112, in run for chunk in chunks: File "C:\Users\Administrator\ghtencent\dify\api\core\model_runtime\model_providers\__base\large_language_model.py", line 479, in _invoke_result_generator raise self._transform_invoke_error(e) core.model_runtime.errors.invoke.InvokeError: [tongyi] Error: 'name' ``` When processing tool_calls returned by the Qwen model, the code attempted to access tool_call_obj ["function"] ["name"], but one of the tool_call_obj ["function"] did not have a name field, resulting in a KeyError being thrown. I think the problem lies in the upgrade of the qwen model version, but the local dependency package is still an old version, so the processing of return data in dify still follows the constraints of the old version, which leads to errors
yindo added the 🤖 feat:agentoutdated labels 2026-02-21 19:23:28 -05:00
yindo closed this issue 2026-02-21 19:23:28 -05:00
yindo commented 2026-02-21 19:23:28 -05:00
Author
Owner
Copy Link
Copy Source

@dosubot[bot] commented on GitHub (Aug 1, 2025):

This error is caused by a schema mismatch between the Qwen model's tool call response and what Dify 0.15.3 expects. Newer Qwen models sometimes omit the 'name' field in tool_call_obj["function"], but Dify 0.15.x assumes it is always present, leading to a KeyError. This is a known issue and has been reported by other users as well. Dify maintainers recommend upgrading both Dify (to 1.x) and the Tongyi plugin (to at least 0.0.25) for compatibility with Qwen3 and newer Qwen models—these are not supported in Dify 0.15.x. If you cannot upgrade immediately, you would need to downgrade your Qwen model/provider to a version that matches the schema expected by Dify 0.15.3, but the recommended path is to upgrade Dify and its plugins to avoid this and other compatibility issues [source 1] [source 2].

To reply, just mention @dosu.

How did I do? Good | Irrelevant | Incorrect | Verbose | Hallucination | Report 🐛 | Other  Chat with Dosu Join Discord Share on X

@dosubot[bot] commented on GitHub (Aug 1, 2025): <!-- Answer --> This error is caused by a schema mismatch between the Qwen model's tool call response and what Dify 0.15.3 expects. Newer Qwen models sometimes omit the 'name' field in tool_call_obj["function"], but Dify 0.15.x assumes it is always present, leading to a KeyError. This is a known issue and has been reported by other users as well. Dify maintainers recommend upgrading both Dify (to 1.x) and the Tongyi plugin (to at least 0.0.25) for compatibility with Qwen3 and newer Qwen models—these are not supported in Dify 0.15.x. If you cannot upgrade immediately, you would need to downgrade your Qwen model/provider to a version that matches the schema expected by Dify 0.15.3, but the recommended path is to upgrade Dify and its plugins to avoid this and other compatibility issues [[source 1]](https://github.com/langgenius/dify/issues/19712) [[source 2]](https://github.com/langgenius/dify/issues/15198). <!-- Dosu Comment Footer --> *To reply, just mention [@dosu](https://go.dosu.dev/dosubot).* --- <sup>How did I do? [Good](https://app.dosu.dev/response-feedback/e0a0e663-5d16-4ba6-8b34-7bdeba3aaa19?feedback_type=great_response) | [Irrelevant](https://app.dosu.dev/response-feedback/e0a0e663-5d16-4ba6-8b34-7bdeba3aaa19?feedback_type=irrelevant_answer) | [Incorrect](https://app.dosu.dev/response-feedback/e0a0e663-5d16-4ba6-8b34-7bdeba3aaa19?feedback_type=incorrect_sources) | [Verbose](https://app.dosu.dev/response-feedback/e0a0e663-5d16-4ba6-8b34-7bdeba3aaa19?feedback_type=too_verbose) | [Hallucination](https://app.dosu.dev/response-feedback/e0a0e663-5d16-4ba6-8b34-7bdeba3aaa19?feedback_type=hallucination) | [Report 🐛](https://app.dosu.dev/response-feedback/e0a0e663-5d16-4ba6-8b34-7bdeba3aaa19?feedback_type=bug_report) | [Other](https://app.dosu.dev/response-feedback/e0a0e663-5d16-4ba6-8b34-7bdeba3aaa19?feedback_type=other)</sup>&nbsp;&nbsp;[![Chat with Dosu](https://dosu.dev/dosu-chat-badge.svg)](https://app.dosu.dev/6088a4f4-073a-43f3-b3d4-4f06fb0c05a0/ask?utm_source=github)&nbsp;[![Join Discord](https://img.shields.io/badge/join-5865F2?logo=discord&logoColor=white&label=)](https://go.dosu.dev/discord-bot)&nbsp;[![Share on X](https://img.shields.io/badge/X-share-black)](https://twitter.com/intent/tweet?text=%40dosu_ai%20helped%20me%20solve%20this%20issue!&url=https%3A//github.com/langgenius/dify/issues/23257)
yindo commented 2026-02-21 19:23:29 -05:00
Author
Owner
Copy Link
Copy Source

@orcharddd2024 commented on GitHub (Aug 1, 2025):

This error is caused by a schema mismatch between the Qwen model's tool call response and what Dify 0.15.3 expects. Newer Qwen models sometimes omit the 'name' field in tool_call_obj["function"], but Dify 0.15.x assumes it is always present, leading to a KeyError. This is a known issue and has been reported by other users as well. Dify maintainers recommend upgrading both Dify (to 1.x) and the Tongyi plugin (to at least 0.0.25) for compatibility with Qwen3 and newer Qwen models—these are not supported in Dify 0.15.x. If you cannot upgrade immediately, you would need to downgrade your Qwen model/provider to a version that matches the schema expected by Dify 0.15.3, but the recommended path is to upgrade Dify and its plugins to avoid this and other compatibility issues [source 1] [source 2].

To reply, just mention @dosu.

How did I do? Good | Irrelevant | Incorrect | Verbose | Hallucination | Report 🐛 | Other  Chat with Dosu Join Discord Share on X

ok

@orcharddd2024 commented on GitHub (Aug 1, 2025): > This error is caused by a schema mismatch between the Qwen model's tool call response and what Dify 0.15.3 expects. Newer Qwen models sometimes omit the 'name' field in tool_call_obj["function"], but Dify 0.15.x assumes it is always present, leading to a KeyError. This is a known issue and has been reported by other users as well. Dify maintainers recommend upgrading both Dify (to 1.x) and the Tongyi plugin (to at least 0.0.25) for compatibility with Qwen3 and newer Qwen models—these are not supported in Dify 0.15.x. If you cannot upgrade immediately, you would need to downgrade your Qwen model/provider to a version that matches the schema expected by Dify 0.15.3, but the recommended path is to upgrade Dify and its plugins to avoid this and other compatibility issues [[source 1]](https://github.com/langgenius/dify/issues/19712) [[source 2]](https://github.com/langgenius/dify/issues/15198). > > _To reply, just mention [@dosu](https://go.dosu.dev/dosubot)._ > > How did I do? [Good](https://app.dosu.dev/response-feedback/e0a0e663-5d16-4ba6-8b34-7bdeba3aaa19?feedback_type=great_response) | [Irrelevant](https://app.dosu.dev/response-feedback/e0a0e663-5d16-4ba6-8b34-7bdeba3aaa19?feedback_type=irrelevant_answer) | [Incorrect](https://app.dosu.dev/response-feedback/e0a0e663-5d16-4ba6-8b34-7bdeba3aaa19?feedback_type=incorrect_sources) | [Verbose](https://app.dosu.dev/response-feedback/e0a0e663-5d16-4ba6-8b34-7bdeba3aaa19?feedback_type=too_verbose) | [Hallucination](https://app.dosu.dev/response-feedback/e0a0e663-5d16-4ba6-8b34-7bdeba3aaa19?feedback_type=hallucination) | [Report 🐛](https://app.dosu.dev/response-feedback/e0a0e663-5d16-4ba6-8b34-7bdeba3aaa19?feedback_type=bug_report) | [Other](https://app.dosu.dev/response-feedback/e0a0e663-5d16-4ba6-8b34-7bdeba3aaa19?feedback_type=other)  [![Chat with Dosu](https://camo.githubusercontent.com/d9ffebb979729c9ef0fc4e3090dbae5b17cabbfec8afe378ada6b81913d6ad8a/68747470733a2f2f646f73752e6465762f646f73752d636861742d62616467652e737667)](https://app.dosu.dev/6088a4f4-073a-43f3-b3d4-4f06fb0c05a0/ask?utm_source=github) [![Join Discord](https://camo.githubusercontent.com/d562c2df5e4567ea41d37f1d91a4da0839d8341037045b103b2da268998de17f/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f6a6f696e2d3538363546323f6c6f676f3d646973636f7264266c6f676f436f6c6f723d7768697465266c6162656c3d)](https://go.dosu.dev/discord-bot) [![Share on X](https://camo.githubusercontent.com/4649f705e2396d6f328dbc8e800a0509c9c17b3b20253b36706c393df124b93d/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f582d73686172652d626c61636b)](https://twitter.com/intent/tweet?text=%40dosu_ai%20helped%20me%20solve%20this%20issue!&url=https%3A//github.com/langgenius/dify/issues/23257) ok
yindo commented 2026-02-21 19:23:29 -05:00
Author
Owner
Copy Link
Copy Source

@orcharddd2024 commented on GitHub (Aug 1, 2025):

This error is caused by a schema mismatch between the Qwen model's tool call response and what Dify 0.15.3 expects. Newer Qwen models sometimes omit the 'name' field in tool_call_obj["function"], but Dify 0.15.x assumes it is always present, leading to a KeyError. This is a known issue and has been reported by other users as well. Dify maintainers recommend upgrading both Dify (to 1.x) and the Tongyi plugin (to at least 0.0.25) for compatibility with Qwen3 and newer Qwen models—these are not supported in Dify 0.15.x. If you cannot upgrade immediately, you would need to downgrade your Qwen model/provider to a version that matches the schema expected by Dify 0.15.3, but the recommended path is to upgrade Dify and its plugins to avoid this and other compatibility issues [source 1] [source 2].

To reply, just mention @dosu.

How did I do? Good | Irrelevant | Incorrect | Verbose | Hallucination | Report 🐛 | Other  Chat with Dosu Join Discord Share on X

@dosu
When was Dify 0.15.3 released? What is the most stable version of Dify currently, or what is the latest version of Dify

@orcharddd2024 commented on GitHub (Aug 1, 2025): > This error is caused by a schema mismatch between the Qwen model's tool call response and what Dify 0.15.3 expects. Newer Qwen models sometimes omit the 'name' field in tool_call_obj["function"], but Dify 0.15.x assumes it is always present, leading to a KeyError. This is a known issue and has been reported by other users as well. Dify maintainers recommend upgrading both Dify (to 1.x) and the Tongyi plugin (to at least 0.0.25) for compatibility with Qwen3 and newer Qwen models—these are not supported in Dify 0.15.x. If you cannot upgrade immediately, you would need to downgrade your Qwen model/provider to a version that matches the schema expected by Dify 0.15.3, but the recommended path is to upgrade Dify and its plugins to avoid this and other compatibility issues [[source 1]](https://github.com/langgenius/dify/issues/19712) [[source 2]](https://github.com/langgenius/dify/issues/15198). > > _To reply, just mention [@dosu](https://go.dosu.dev/dosubot)._ > > How did I do? [Good](https://app.dosu.dev/response-feedback/e0a0e663-5d16-4ba6-8b34-7bdeba3aaa19?feedback_type=great_response) | [Irrelevant](https://app.dosu.dev/response-feedback/e0a0e663-5d16-4ba6-8b34-7bdeba3aaa19?feedback_type=irrelevant_answer) | [Incorrect](https://app.dosu.dev/response-feedback/e0a0e663-5d16-4ba6-8b34-7bdeba3aaa19?feedback_type=incorrect_sources) | [Verbose](https://app.dosu.dev/response-feedback/e0a0e663-5d16-4ba6-8b34-7bdeba3aaa19?feedback_type=too_verbose) | [Hallucination](https://app.dosu.dev/response-feedback/e0a0e663-5d16-4ba6-8b34-7bdeba3aaa19?feedback_type=hallucination) | [Report 🐛](https://app.dosu.dev/response-feedback/e0a0e663-5d16-4ba6-8b34-7bdeba3aaa19?feedback_type=bug_report) | [Other](https://app.dosu.dev/response-feedback/e0a0e663-5d16-4ba6-8b34-7bdeba3aaa19?feedback_type=other)  [![Chat with Dosu](https://camo.githubusercontent.com/d9ffebb979729c9ef0fc4e3090dbae5b17cabbfec8afe378ada6b81913d6ad8a/68747470733a2f2f646f73752e6465762f646f73752d636861742d62616467652e737667)](https://app.dosu.dev/6088a4f4-073a-43f3-b3d4-4f06fb0c05a0/ask?utm_source=github) [![Join Discord](https://camo.githubusercontent.com/d562c2df5e4567ea41d37f1d91a4da0839d8341037045b103b2da268998de17f/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f6a6f696e2d3538363546323f6c6f676f3d646973636f7264266c6f676f436f6c6f723d7768697465266c6162656c3d)](https://go.dosu.dev/discord-bot) [![Share on X](https://camo.githubusercontent.com/4649f705e2396d6f328dbc8e800a0509c9c17b3b20253b36706c393df124b93d/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f582d73686172652d626c61636b)](https://twitter.com/intent/tweet?text=%40dosu_ai%20helped%20me%20solve%20this%20issue!&url=https%3A//github.com/langgenius/dify/issues/23257) @dosu When was Dify 0.15.3 released? What is the most stable version of Dify currently, or what is the latest version of Dify
yindo commented 2026-02-21 19:23:29 -05:00
Author
Owner
Copy Link
Copy Source

@dosubot[bot] commented on GitHub (Aug 1, 2025):

Dify 0.15.3 was released around June 9, 2025, based on pull request timestamps (source). As of July 2025, Dify 1.6.0 is referenced as a stable version for production use (source). For the most up-to-date and stable deployment, it's recommended to use the latest official release from the Dify releases page rather than the main branch (source).

To reply, just mention @dosu.

How did I do? Good | Irrelevant | Incorrect | Verbose | Hallucination | Report 🐛 | Other  Chat with Dosu Join Discord Share on X

@dosubot[bot] commented on GitHub (Aug 1, 2025): <!-- Answer --> Dify 0.15.3 was released around June 9, 2025, based on pull request timestamps ([source](https://github.com/langgenius/dify/pull/14399)). As of July 2025, Dify 1.6.0 is referenced as a stable version for production use ([source](https://github.com/langgenius/dify/issues/22323)). For the most up-to-date and stable deployment, it's recommended to use the latest official release from the Dify releases page rather than the main branch ([source](https://github.com/langgenius/dify/issues/14163)). <!-- Dosu Comment Footer --> *To reply, just mention [@dosu](https://go.dosu.dev/dosubot).* --- <sup>How did I do? [Good](https://app.dosu.dev/response-feedback/10b77d18-bd12-4114-8520-91496789a717?feedback_type=great_response) | [Irrelevant](https://app.dosu.dev/response-feedback/10b77d18-bd12-4114-8520-91496789a717?feedback_type=irrelevant_answer) | [Incorrect](https://app.dosu.dev/response-feedback/10b77d18-bd12-4114-8520-91496789a717?feedback_type=incorrect_sources) | [Verbose](https://app.dosu.dev/response-feedback/10b77d18-bd12-4114-8520-91496789a717?feedback_type=too_verbose) | [Hallucination](https://app.dosu.dev/response-feedback/10b77d18-bd12-4114-8520-91496789a717?feedback_type=hallucination) | [Report 🐛](https://app.dosu.dev/response-feedback/10b77d18-bd12-4114-8520-91496789a717?feedback_type=bug_report) | [Other](https://app.dosu.dev/response-feedback/10b77d18-bd12-4114-8520-91496789a717?feedback_type=other)</sup>&nbsp;&nbsp;[![Chat with Dosu](https://dosu.dev/dosu-chat-badge.svg)](https://app.dosu.dev/6088a4f4-073a-43f3-b3d4-4f06fb0c05a0/ask?utm_source=github)&nbsp;[![Join Discord](https://img.shields.io/badge/join-5865F2?logo=discord&logoColor=white&label=)](https://go.dosu.dev/discord-bot)&nbsp;[![Share on X](https://img.shields.io/badge/X-share-black)](https://twitter.com/intent/tweet?text=%40dosu_ai%20helped%20me%20solve%20this%20issue!&url=https%3A//github.com/langgenius/dify/issues/23257)
yindo commented 2026-02-21 19:23:29 -05:00
Author
Owner
Copy Link
Copy Source

@crazywoola commented on GitHub (Aug 1, 2025):

1.7.1 is the latest version at this moment.

@crazywoola commented on GitHub (Aug 1, 2025): 1.7.1 is the latest version at this moment.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
Knowledge Pipeline
Proposal
WIP
cloud
dependencies
feat:webapp
good first issue
outdated
performance
pull-request
Mirrored from GitHub Pull Request
 python:uv
refactor
size:L
stale
status: accepting prs
status: blocked
status: in discussion
stt & tts
vulnerablity
web
wont-fix
🌊 feat:workflow
🌚 invalid
🐞 bug
👻 feat:rag
💪 enhancement
📚 documentation
🔨 feat:tools
🙋‍♂️ question
🙏 help wanted
🤔 cant-reproduce
🤖 feat:agent
No Label outdated 🤖 feat:agent
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langgenius/dify#15814
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?