generated from google/new-project
-
Notifications
You must be signed in to change notification settings - Fork 357
Open
Description
What happened?
When running the example, content_creation under samples/python/hosts/content_creation, the host agent failed after the user submit the request.
To re-produce the bug, simply follows the instructions in the content_creation, you should meet the bug when running the final section, Start the Host Agent.
Btw, I already patch the python-based content planner with my PR here. It is not helpful in this case.
Relevant log output
cheny0y@acclnode03:~/git/a2a-samples/samples/python/hosts/content_creation$ uv run .
ERROR: Failed to initialize connection for http://localhost:10003: HTTP Error 404: Failed to fetch agent card from http://localhost:10003/.well-known/agent-card.json: Client error '404 Not Found' for url 'http://localhost:10003/.well-known/agent-card.json'
For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404
ERROR: Failed to initialize connection for http://localhost:10002: HTTP Error 404: Failed to fetch agent card from http://localhost:10002/.well-known/agent-card.json: Client error '404 Not Found' for url 'http://localhost:10002/.well-known/agent-card.json'
For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404
agent_card: additional_interfaces=None capabilities=AgentCapabilities(extensions=None, push_notifications=None, state_transition_history=None, streaming=True) default_input_modes=['text', 'text/plain'] default_output_modes=['text', 'text/plain'] description='Planning agent that creates a detailed and logical outline for a piece of content,given a high-level description.' documentation_url=None icon_url=None name='Content Planner Agent' preferred_transport='JSONRPC' protocol_version='0.3.0' provider=None security=None security_schemes=None signatures=None skills=[AgentSkill(description='Creates outlines for content given a high-level description of the content', examples=['Create an outline for a short, upbeat, and encouraging X post about learning Java'], id='content_planner', input_modes=None, name='Creates outlines for content', output_modes=None, security=None, tags=['plan', 'outline'])] supports_authenticated_extended_card=None url='http://localhost:10001' version='1.0.0'
agent_url: http://localhost:10001
Found agent card: {'capabilities': {'streaming': True}, 'defaultInputModes': ['text', 'text/plain'], 'defaultOutputModes': ['text', 'text/plain'], 'description': 'Planning agent that creates a detailed and logical outline for a piece of content,given a high-level description.', 'name': 'Content Planner Agent', 'preferredTransport': 'JSONRPC', 'protocolVersion': '0.3.0', 'skills': [{'description': 'Creates outlines for content given a high-level description of the content', 'examples': ['Create an outline for a short, upbeat, and encouraging X post about learning Java'], 'id': 'content_planner', 'name': 'Creates outlines for content', 'tags': ['plan', 'outline']}], 'url': 'http://localhost:10001', 'version': '1.0.0'}
====================================================================================================
Using hardcoded model: gemini-2.5-flash
Creating ADK session...
ADK session created successfully.
/home/cheny0y/git/a2a-samples/samples/python/hosts/content_creation/.venv/lib/python3.13/site-packages/gradio/chat_interface.py:345: UserWarning: The 'tuples' format for chatbot messages is deprecated and will be removed in a future version of Gradio. Please set type='messages' instead, which uses openai-style 'role' and 'content' keys.
self.chatbot = Chatbot(
Launching Gradio interface...
* Running on local URL: http://0.0.0.0:8083
* To create a public link, set `share=True` in `launch()`.
Warning: there are non-text parts in the response: ['thought_signature', 'function_call'], returning concatenated text result from text parts. Check the full candidates.content.parts accessor to get the full model response.
sending message to Content Planner Agent
send_response {
"error": {
"code": -32001,
"message": "Task ceb1fe7a-f31e-4993-a283-03830614f4c6 was specified but does not exist"
},
"jsonrpc": "2.0"
}
received non-success response. Aborting get task
Warning: there are non-text parts in the response: ['thought_signature'], returning concatenated text result from text parts. Check the full candidates.content.parts accessor to get the full model response.
Code of Conduct
- I agree to follow this project's Code of Conduct
Metadata
Metadata
Assignees
Labels
No labels