Connect to Remote Agents with ADK and the Agent2Agent (A2A) SDK avis

Hi Support, I would like to request a credit refund for this lab. I encountered a persistent technical issue with the ADK Web UI on Cloud Shell. Even after following the instructions, the interface failed to generate a Session ID and User ID, returning a '403 Forbidden' error on every POST /sessions request. This prevented me from completing the lab tasks despite multiple attempts (including Incognito mode and port changes). It seems to be a backend/proxy issue with the Cloud Shell Web Preview. Please check and restore my credits. Thank you.

Mutiara N. · Examiné il y a environ un mois

Daksh B. · Examiné il y a environ un mois

SOMSUBHRA N. · Examiné il y a environ un mois

Problem 1 — Tasks 2 & 4: ADK Web UI Broken in Cloud Shell (403 Forbidden)The lab instructs students to launch adk web and interact with agents through the Cloud Shell web preview. Every POST request (/run_sse, /apps/.../sessions) returns 403 Forbidden, while GET requests succeed. This makes the UI completely non-functional for testing agents locally.The lab itself acknowledges this failure with a buried footnote: "If you get a Forbidden Error 403, you may have multiple accounts signed into your Incognito session." This is a misleading and incorrect diagnosis. The real cause is that the Cloud Shell web preview proxy drops POST authentication for Qwiklabs-provisioned student accounts. No combination of browser switching, cookie settings, authuser parameter adjustments, ADC resets, or session clearing resolves it.Workaround attempted and confirmed working: adk run CLI mode, which bypasses the web proxy entirely. Problem 2 — Task 4: Model IDs Injected by Lab Startup Script Are Invalid The lab's startup script injects model ID environment variables (MODEL, IMAGE_MODEL) via template variables into the .env file. In this session, the injected values (gemini-1.5-flash-001, gemini-2.5-flash-image) are not available in the Qwiklabs project's Vertex AI quota, returning: 404 NOT_FOUND: Publisher Model ... was not found or your project does not have access to it. This error surfaces both locally (in the slide_content_agent) and remotely (in the deployed Cloud Run illustration_agent service). The student has no visibility into which model IDs are actually provisioned for their temporary project. Every model variant attempted — gemini-2.0-flash-001, gemini-2.0-flash, gemini-1.5-flash-001 — returned 404 in at least one environment configuration, making it impossible to complete Task 4 regardless of workarounds applied. The Cloud Run service compounds the problem because it bakes the broken model ID into the deployment, requiring gcloud run services update commands not described anywhere in the lab instructions.

MD. Mamdud H. · Examiné il y a environ un mois

Kept going to 403 Forbidden. Tried all the things

Palak K. · Examiné il y a environ un mois

Muthappa M. · Examiné il y a environ un mois

Yuvraj Singh S. · Examiné il y a environ un mois

Rupali A. · Examiné il y a environ un mois

Kusum A. · Examiné il y a environ un mois

there is issue face in task 2 and 4 no one output get from agent

Parth N. · Examiné il y a environ un mois

good

Varsha Priya J. · Examiné il y a environ un mois

**Lab Review: Connect to Remote Agents with ADK and A2A SDK** This lab covers an interesting and important concept—enabling communication between AI agents using A2A and ADK. The overall structure and learning objectives are clear, and the hands-on approach is valuable for understanding how multi-agent systems work in practice. However, the lab has significant technical issues that impact the learning experience. The primary problem is that the agent often fails to respond during testing, even when all steps are followed correctly. This appears to be due to backend configuration or Vertex AI access issues, rather than user error. Unfortunately, these failures happen silently, with no meaningful error messages, making it difficult to debug. Additionally, the lab does not clearly explain critical setup steps such as configuring the `.env` file with valid model IDs. The provided placeholders can easily mislead users and cause the agent to fail without explanation. Suggestions for improvement: * Ensure Vertex AI and model access are fully functional in all lab instances * Add proper error handling and clearer logs when model calls fail * Provide correct default model IDs instead of placeholders * Include a troubleshooting section for common issues Overall, the concept is strong, but the execution needs improvement. Currently, the lab can lead to wasted time and credits due to issues outside the learner’s control.

Khush P. · Examiné il y a environ un mois

Amrita Deviayu T. · Examiné il y a environ un mois

Jayandhan S. · Examiné il y a environ un mois

things are not working properly even when followed all instructions properly

Siddh S. · Examiné il y a environ un mois

Kavish N. · Examiné il y a environ un mois

i am getting only 404 error

Siddhant G. · Examiné il y a environ un mois

Cloud shell editor failed to launch adk web with 403 forbidden error. I tried Incrementing the authuser=1 & 2 but didn't work! My credits got wasted.

Mohith L. · Examiné il y a environ un mois

steps are not clear

Vedhakshari Kumari G. · Examiné il y a environ un mois

Arnab C. · Examiné il y a environ un mois

Htut K. · Examiné il y a environ un mois

Swayam J. · Examiné il y a environ un mois

Muhammed R. · Examiné il y a environ un mois

the project did not run in the editor

Jai D. · Examiné il y a environ un mois

Eshwar R. · Examiné il y a environ un mois