Conversation
This commit introduces a comprehensive guide for setting up and using the
Agent Development Kit (ADK) Web UI.
The changes include:
- A new `docs/web_ui_guide.md` file detailing:
- How to run the Web UI locally using the `adk web` command, including
explanations of `AGENTS_DIR` structure and common options like
`--port`, `--host`, and `--reload`.
- How to deploy an agent with the Web UI to Google Cloud Run using
the `adk deploy cloud_run` command, highlighting the `--with_ui`
flag and necessary arguments like `AGENT`, `--project`, and `--region`.
- Example commands and prerequisites for both local and Cloud Run setups.
- The main `README.md` file has been updated:
- The "Development UI" section is now more concise.
- It links to the new `docs/web_ui_guide.md` for detailed instructions.
This guide will make it easier for you to get up and running with the
ADK Web UI for testing and showcasing your agents.
This commit introduces an interactive shell script `startup.sh` to guide
you through running the ADK Web UI locally or deploying an agent with
the Web UI to Google Cloud Run.
Changes include:
- **New `startup.sh` script:**
- Provides a menu-driven interface for local execution or Cloud Run deployment.
- Prompts for necessary parameters (agent paths, GCP project/region, ports, etc.).
- Includes input validation for directories and required fields.
- Offers sensible defaults for many options.
- Displays the constructed `adk` command for review before execution.
- Uses a helper function for clear yes/no prompts.
- **Updated `docs/web_ui_guide.md`:**
- A new section, "Using the Interactive Startup Script (`startup.sh`)",
has been added.
- This section explains the script's purpose, how to make it executable,
how to run it, and what to expect from its interactive prompts and
confirmation steps.
This script aims to lower the barrier to entry for you by simplifying
the initial setup and deployment of ADK agents with the Web UI.
stuagano
pushed a commit
that referenced
this pull request
Jul 31, 2025
…loop agent due to a sub-agent's escalation. This commit also disables the summarization for `exit_loop` tool Fixes google#423 Related to google#1670 - This avoids the `GeneratorExit` error thrown, which would crash OTel metric collection and cause `Failed to detach context` error. - This also allows all function calls are processed when exit_loop is called together with other tools in the same LLmResponse. A sample agent for testing: ``` from google.adk import Agent from google.adk.agents.loop_agent import LoopAgent from google.adk.tools.exit_loop_tool import exit_loop worker_1 = Agent( name='worker_1', description='Worker 1', instruction="""\ Just say job #1 is done. If job #1 is said to be done. Call exit_loop tool.""", tools=[exit_loop], ) worker_2 = Agent( name='worker_2', description='Worker 2', instruction="""\ Just say job #2 is done. If job #2 is said to be done. Call exit_loop tool.""", tools=[exit_loop], ) work_agent = LoopAgent( name='work_agent', description='Do all work.', sub_agents=[worker_1, worker_2], max_iterations=5, ) root_agent = Agent( model='gemini-2.0-flash', name='hello_world_agent', description='hello world agent that can roll a check prime', instruction="""Hand off works to sub agents.""", sub_agents=[work_agent], ) ``` PiperOrigin-RevId: 785538101
stuagano
added a commit
that referenced
this pull request
Oct 2, 2025
Documentation Updates: - todo.md updated to version 3.4.0 - Marked MSA Analyzer as 100% complete (Priority #3) - Updated tool count to 24 (added service_onboarding and msa_analyzer) - Updated Cloud Functions count to 14 (added MSA analyzer function) - Added feature examples to README showing all 3 priorities Completed Stakeholder Priorities: 1. Service Onboarding (Priority #1) ✅ - URL-based service discovery - Reduced onboarding from 2 weeks to minutes 2. IAM Analysis (Priority #2) ✅ - 72.5% accuracy matching custom to built-in roles - Jaccard similarity scoring 3. MSA Analyzer (Priority #3) ✅ - Automated GCP release notes monitoring - Security/billing/compliance impact assessment - Active service filtering Current Stats: - 24 AI-powered security tools - 14 Cloud Functions for automation - 3 of 4 critical priorities complete - Service review time: 2 weeks → minutes (ACHIEVED) - Release notes: Manual → Automated daily (ACHIEVED) Next Priority: - Real Production Data Integration (50% complete) 🤖 Generated with Claude Code Co-Authored-By: Claude <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.