Shangjie Chen comments

Results 11 comments of


                                            Shangjie Chen

Fast API server: Update session behaviour incorrect as per documentation

Hi @polong-lin , the documented behavior is not correct, this endpoint won't update existing session, could you help update?

Cannot Use Gemini 3 with Agent Engine

Hi @lambda72453 , could you do something like this: `root_agent = LlmAgent( name='orchestrator_agent', model='projects/cloud-llm-preview1/locations/global/publishers/google/models/gemini-2.5-flash', description="""Cool dude""", tools=[], )`

Cannot Use Gemini 3 with Agent Engine

+ @yeesian

Bug: AttributeError: 'dict' object has no attribute 'inline_data' when uploading a file to a custom ADK Agent via AgentSpace

Hi eng team from Gemini Enterprise is taking a look at this issue

Error adk_web_server.py:1431 - Error in event_generator: Failed to parse the parameter file_patterns: List[str] | None = None of function cleanup_unused_files

Hi @ymodak , could your team help reproduce before assign this back to @wyf7107 ? Thanks!

Run the code with adk web, and return an image im after each call to the tool.

Hi, could you add more details to reproduce? Thanks!

run_config.save_input_blobs_as_artifacts not respected.

Thanks @simond for your help. @Datise could you check if that works for you?

run_config.save_input_blobs_as_artifacts not respected.

Hi @wyf7107 , I don't have the permission to migrate this issue to adk-web, I think this ticket is more about adding Web UI support for showing all the artifacts.

Enable Attachment Processing - INVALID_ARGUMENT Error (mimeType message/rfc822)

Hi @nikogamulin , are you uploading file with `adk web` UI or using the artifact service directly?

Enable Attachment Processing - INVALID_ARGUMENT Error (mimeType message/rfc822)

You might using the load_artifacts tool, see sample in https://github.com/google/adk-python/tree/main/contributing/samples/generate_image.