# Agent does not reply and is blank

**URL:** <https://discuss.google.dev/t/agent-does-not-reply-and-is-blank/343491>\
**Category:** Agents\
**Tags:** adk, development, agent-builder\
**Created:** [March 26, 2026, 2:31am UTC](https://discuss.google.dev/t/agent-does-not-reply-and-is-blank/343491 "2026-03-26T02:31:09Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![P\_K\_1](https://d3byx8b92xw3lq.cloudfront.net/user_avatar/discuss.google.dev/p_k_1/32/187725_2.png) [@P\_K\_1](https://discuss.google.dev/u/P_K_1)\
**Post date:** [March 26, 2026, 2:31am UTC](https://discuss.google.dev/t/agent-does-not-reply-and-is-blank/343491/1 "2026-03-26T02:31:09Z")

</div>

Hello all,

I am from non-it (non-programming) background.

I have attended the recent “ **Asia Pacific: Cloud Technical Series, AI in Action** “. It was interesting and I loved it.

While doing the lab, I performed all the action as provided. However, after the below steps, the Agent does not respond.

* * *

_ **Task 4. Run the agent using the ADK Dev UI** _

_ADK includes a development UI designed to run locally to help you develop and test your agents. It can help you visualize what each agent is doing and how multiple agents interact with one another. In this task, you explore this interface._

_ **Note:** When you run an agent, ADK needs to know who is requesting the model API calls. You can provide this information in one of two ways:_

1. _Provide a [Gemini API key](https://aistudio.google.com/apikey)._

2. _Authenticate your environment with Google Cloud credentials and associate your model API calls with a Vertex AI project and location._

_In this lab, you take the Vertex AI approach._

1. _In the Cloud Shell Terminal, run the following to write an `.env` file to set environment variables instructing the agent to use your project and the global endpoint:_

_These variables play the following roles:_

- _`GOOGLE_GENAI_USE_VERTEXAI=TRUE` indicates that you use Vertex AI for authentication as opposed to Gemini API key authentication._

- _`GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` provide the project and location with which to associate your model calls._

- _`MODEL` is not required, but is stored here so that it can be loaded as another environment variable. This can be a convenient way to try different models in different deployment environments._

_The ADK Dev UI and CLI chat interface automatically load configurations from an `.env` file. If no file is present, they use system environment variables with matching names._

1. _In the Cloud Shell Terminal, ensure you are in the **adk\_project** directory where your agent subdirectories are located by running:_

2. _Launch the ADK Dev UI, allowing Cloud Shell as an origin, with the following command:_

3. _To view the web interface in a new tab, click the **[http://127.0.0.1:8000](http://127.0.0.1:8000)** link in the Terminal output, which links you via proxy to this app running locally on your Cloud Shell instance._

4. _From the **Select an agent** menu options on the left, select **my\_google\_search\_agent**._

5. _To encourage the agent to use its Google Search tool, enter the question:_

* * *

* * *

So, I tried Gemini if it could help and followed the below steps:

_It looks like we’ve hit two different snags at once. Let’s break them down so we can get your agent back on track. 🛠_

### _1. The Directory Error_

_The error `shell-init: error retrieving current directory` usually happens when the folder you are currently “standing” in has been deleted or moved while you were inside it. Since your terminal can’t find its own feet, it’s having trouble running commands._

### _2. The Invalid Argument_

_The `INVALID_ARGUMENT` error likely occurred because the `$GOOGLE_CLOUD_PROJECT` variable we tried to use didn’t stay “stuck” in the terminal’s memory, or it was empty._

* * *

### _Let’s Reset Your Connection ⚡_

_We can fix both of these by refreshing your location and manually defining the project. Please follow these steps in order:_

1. _ **Move to a safe directory** : Run `cd ~` to move to your home folder. This fixes the “cannot access parent directories” error._

2. _ **Go back to your project** : Run `cd ~/adk_project`._

3. _ **Run the quota command manually** : Instead of using the variable, let’s type the Project ID directly._

_ **Run this command** (Replace `[YOUR_PROJECT_ID]` with your actual lab ID, e.g., `qwiklabs-gcp-00-1234`):_

_`gcloud auth application-default set-quota-project [YOUR_PROJECT_ID]`_

_Once you run that, does it return a success message like “Credentials updated with quota project,” or does it give you a new error? 📋_

* * *

* * *

 ![ADK Agent Error](https://d2yds90mtvelsl.cloudfront.net/original/3X/1/1/1112e9a533a39c206ff1881920a6ab77fa4a0d64.jpeg)

I have tried 4 times. .. but I get the same error

I need to complete the lab by April 03, 2026.

Can someone please guide me how to resolve this and proceed further.

Thank you in advance for your help.

Kumar.
