agent-starter-pack 0.4.1__tar.gz → 0.4.3__tar.gz

{agent_starter_pack-0.4.1 → agent_starter_pack-0.4.3}/PKG-INFO

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: agent-starter-pack
-Version: 0.4.1
-Summary: CLI tool to create GCP-based AI agent projects from templates
+Version: 0.4.3
+Summary: CLI to bootstrap production-ready Google Cloud GenAI agent projects from templates.
 Author-email: Google LLC <agent-starter-pack@google.com>
 License: Apache-2.0
 License-File: LICENSE
@@ -38,7 +38,7 @@ Description-Content-Type: text/markdown
       alt="Try in Firebase Studio"
       src="https://cdn.firebasestudio.dev/btn/try_blue_20.svg">
   </picture>
-</a> ![Stars](https://img.shields.io/github/stars/GoogleCloudPlatform/agent-starter-pack?color=yellow)
+</a> [![Launch in Cloud Shell](https://img.shields.io/badge/Launch-in_Cloud_Shell-white)](https://shell.cloud.google.com/cloudshell/editor?cloudshell_git_repo=https%3A%2F%2Fgithub.com%2Feliasecchig%2Fasp-open-in-cloud-shell&cloudshell_print=open-in-cs) ![Stars](https://img.shields.io/github/stars/GoogleCloudPlatform/agent-starter-pack?color=yellow)
 
 
 The `agent-starter-pack` is a collection of production-ready Generative AI Agent templates built for Google Cloud. <br>
@@ -66,7 +66,7 @@ agent-starter-pack create my-awesome-agent
 ```
 
 **That's it!** You now have a fully functional agent project—complete with backend, frontend, and deployment infrastructure—ready for you to explore and customize.
-For more installation options, see the [Installation Guide](https://googlecloudplatform.github.io/agent-starter-pack/guide/installation). You can also [try it in Firebase Studio](https://studio.firebase.google.com/new?template=https%3A%2F%2Fgithub.com%2FGoogleCloudPlatform%2Fagent-starter-pack%2Ftree%2Fmain%2Fsrc%2Fresources%2Fidx) with zero setup.
+See [Installation Guide](https://googlecloudplatform.github.io/agent-starter-pack/guide/installation) for more options, or try with zero setup in [Firebase Studio](https://studio.firebase.google.com/new?template=https%3A%2F%2Fgithub.com%2FGoogleCloudPlatform%2Fagent-starter-pack%2Ftree%2Fmain%2Fsrc%2Fresources%2Fidx) or [Cloud Shell](https://shell.cloud.google.com/cloudshell/editor?cloudshell_git_repo=https%3A%2F%2Fgithub.com%2Feliasecchig%2Fasp-open-in-cloud-shell&cloudshell_print=open-in-cs).
 
 ---
 
@@ -129,13 +129,12 @@ Visit our [documentation site](https://googlecloudplatform.github.io/agent-start
 
 ### Video Walkthrough:
 
-## Video Tutorials
+- **[Exploring the Agent Starter Pack](https://www.youtube.com/watch?v=9zqwym-N3lg)**: A comprehensive tutorial demonstrating how to rapidly deploy AI Agents using the Agent Starter Pack, covering architecture, templates, and step-by-step deployment.
 
-- **April 2024**: A [6-minute introduction video](https://www.youtube.com/live/eZ-8UQ_t4YM?feature=shared&t=2791) Explaining the Agent Starter Pack and demonstrating its key features. Part of the Kaggle GenAI intensive course.
-- **March 6, 2025**: A [120 Minute livestream video demo](https://www.youtube.com/watch?v=yIRIT_EtALs&t=235s) of the new `agent-starter-pack` were we build 3 Agents under 30 minutes!
-- **Oct 29, 2024**: A [20-Minute Video Walkthrough](https://youtu.be/kwRG7cnqSu0) is available, showcasing the previous `agent-starter-pack`.
+- **[6-minute introduction](https://www.youtube.com/live/eZ-8UQ_t4YM?feature=shared&t=2791)** (April 2024): Explaining the Agent Starter Pack and demonstrating its key features. Part of the Kaggle GenAI intensive course.
+
+- **[120-minute livestream demo](https://www.youtube.com/watch?v=yIRIT_EtALs&t=235s)** (March 6, 2025): Watch us build 3 Agents in under 30 minutes using the `agent-starter-pack`!
 
-## Explore More Generative AI Resources
 
 Looking for more examples and resources for Generative AI on Google Cloud? Check out the [GoogleCloudPlatform/generative-ai](https://github.com/GoogleCloudPlatform/generative-ai) repository for notebooks, code samples, and more!
 

{agent_starter_pack-0.4.1 → agent_starter_pack-0.4.3}/README.md

@@ -13,7 +13,7 @@
       alt="Try in Firebase Studio"
       src="https://cdn.firebasestudio.dev/btn/try_blue_20.svg">
   </picture>
-</a> ![Stars](https://img.shields.io/github/stars/GoogleCloudPlatform/agent-starter-pack?color=yellow)
+</a> [![Launch in Cloud Shell](https://img.shields.io/badge/Launch-in_Cloud_Shell-white)](https://shell.cloud.google.com/cloudshell/editor?cloudshell_git_repo=https%3A%2F%2Fgithub.com%2Feliasecchig%2Fasp-open-in-cloud-shell&cloudshell_print=open-in-cs) ![Stars](https://img.shields.io/github/stars/GoogleCloudPlatform/agent-starter-pack?color=yellow)
 
 
 The `agent-starter-pack` is a collection of production-ready Generative AI Agent templates built for Google Cloud. <br>
@@ -41,7 +41,7 @@ agent-starter-pack create my-awesome-agent
 ```
 
 **That's it!** You now have a fully functional agent project—complete with backend, frontend, and deployment infrastructure—ready for you to explore and customize.
-For more installation options, see the [Installation Guide](https://googlecloudplatform.github.io/agent-starter-pack/guide/installation). You can also [try it in Firebase Studio](https://studio.firebase.google.com/new?template=https%3A%2F%2Fgithub.com%2FGoogleCloudPlatform%2Fagent-starter-pack%2Ftree%2Fmain%2Fsrc%2Fresources%2Fidx) with zero setup.
+See [Installation Guide](https://googlecloudplatform.github.io/agent-starter-pack/guide/installation) for more options, or try with zero setup in [Firebase Studio](https://studio.firebase.google.com/new?template=https%3A%2F%2Fgithub.com%2FGoogleCloudPlatform%2Fagent-starter-pack%2Ftree%2Fmain%2Fsrc%2Fresources%2Fidx) or [Cloud Shell](https://shell.cloud.google.com/cloudshell/editor?cloudshell_git_repo=https%3A%2F%2Fgithub.com%2Feliasecchig%2Fasp-open-in-cloud-shell&cloudshell_print=open-in-cs).
 
 ---
 
@@ -104,13 +104,12 @@ Visit our [documentation site](https://googlecloudplatform.github.io/agent-start
 
 ### Video Walkthrough:
 
-## Video Tutorials
+- **[Exploring the Agent Starter Pack](https://www.youtube.com/watch?v=9zqwym-N3lg)**: A comprehensive tutorial demonstrating how to rapidly deploy AI Agents using the Agent Starter Pack, covering architecture, templates, and step-by-step deployment.
 
-- **April 2024**: A [6-minute introduction video](https://www.youtube.com/live/eZ-8UQ_t4YM?feature=shared&t=2791) Explaining the Agent Starter Pack and demonstrating its key features. Part of the Kaggle GenAI intensive course.
-- **March 6, 2025**: A [120 Minute livestream video demo](https://www.youtube.com/watch?v=yIRIT_EtALs&t=235s) of the new `agent-starter-pack` were we build 3 Agents under 30 minutes!
-- **Oct 29, 2024**: A [20-Minute Video Walkthrough](https://youtu.be/kwRG7cnqSu0) is available, showcasing the previous `agent-starter-pack`.
+- **[6-minute introduction](https://www.youtube.com/live/eZ-8UQ_t4YM?feature=shared&t=2791)** (April 2024): Explaining the Agent Starter Pack and demonstrating its key features. Part of the Kaggle GenAI intensive course.
+
+- **[120-minute livestream demo](https://www.youtube.com/watch?v=yIRIT_EtALs&t=235s)** (March 6, 2025): Watch us build 3 Agents in under 30 minutes using the `agent-starter-pack`!
 
-## Explore More Generative AI Resources
 
 Looking for more examples and resources for Generative AI on Google Cloud? Check out the [GoogleCloudPlatform/generative-ai](https://github.com/GoogleCloudPlatform/generative-ai) repository for notebooks, code samples, and more!
 

{agent_starter_pack-0.4.1 → agent_starter_pack-0.4.3}/agents/live_api/README.md

@@ -6,7 +6,7 @@ This pattern showcases a real-time conversational agent powered by Google Gemini
 
 **Key components:**
 
-- **Python Backend** (in `app/` folder): A production-ready server built with [FastAPI](https://fastapi.tiangolo.com/) and [google-genai](https://googleapis.github.io/python-python-genai/) that features:
+- **Python Backend** (in `app/` folder): A production-ready server built with [FastAPI](https://fastapi.tiangolo.com/) and [google-genai](https://googleapis.github.io/python-genai/) that features:
 
   - **Real-time bidirectional communication** via WebSockets between the frontend and Gemini model
   - **Integrated tool calling** with a weather information tool for demonstrating external data retrieval

{agent_starter_pack-0.4.1 → agent_starter_pack-0.4.3}/agents/live_api/app/agent.py

@@ -22,8 +22,7 @@ from google.genai import types
 # Constants
 VERTEXAI = os.getenv("VERTEXAI", "true").lower() == "true"
 LOCATION = "us-central1"
-EMBEDDING_MODEL = "text-embedding-004"
-MODEL_ID = "gemini-2.0-flash-exp"
+MODEL_ID = "gemini-2.0-flash-live-preview-04-09"
 
 # Initialize Google Cloud clients
 credentials, project_id = google.auth.default()

{agent_starter_pack-0.4.1 → agent_starter_pack-0.4.3}/agents/live_api/app/server.py

@@ -70,6 +70,7 @@ class GeminiSession:
         while True:
             try:
                 data = await self.websocket.receive_json()
+
                 if isinstance(data, dict) and (
                     "realtimeInput" in data or "clientContent" in data
                 ):
@@ -98,13 +99,7 @@ class GeminiSession:
     async def _handle_tool_call(
         self, session: Any, tool_call: LiveServerToolCall
     ) -> None:
-        """Process tool calls from Gemini and send back responses.
-
-        Args:
-            session: The Gemini session
-            tool_call: Tool call request from Gemini
-        """
-        # Handle case where function_calls might be None
+        """Process tool calls from Gemini and send back responses."""
         if tool_call.function_calls is None:
             logging.debug("No function calls in tool_call")
             return
@@ -116,7 +111,14 @@ class GeminiSession:
                 logging.error(f"Function {fc.name} not found")
                 continue
             args = fc.args if fc.args is not None else {}
-            response = func(**args)
+
+            # Handle both async and sync functions appropriately
+            if asyncio.iscoroutinefunction(func):
+                # Function is already async
+                response = await func(**args)
+            else:
+                # Run sync function in a thread pool to avoid blocking
+                response = await asyncio.to_thread(func, **args)
 
             tool_response = types.LiveClientToolResponse(
                 function_responses=[
@@ -127,18 +129,15 @@ class GeminiSession:
             await session.send(input=tool_response)
 
     async def receive_from_gemini(self) -> None:
-        """Listen for and process messages from Gemini.
-
-        Continuously receives messages from Gemini, forwards them to the client,
-        and handles any tool calls. Handles connection errors gracefully.
-        """
+        """Listen for and process messages from Gemini without blocking."""
         while result := await self.session._ws.recv(decode=False):
             await self.websocket.send_bytes(result)
             raw_message = json.loads(result)
             if "toolCall" in raw_message:
                 message = types.LiveServerMessage.model_validate(raw_message)
                 tool_call = LiveServerToolCall.model_validate(message.tool_call)
-                await self._handle_tool_call(self.session, tool_call)
+                # Create a separate task to handle the tool call without blocking
+                asyncio.create_task(self._handle_tool_call(self.session, tool_call))
 
 
 def get_connect_and_run_callable(websocket: WebSocket) -> Callable:

{agent_starter_pack-0.4.1 → agent_starter_pack-0.4.3}/docs/.vitepress/config.js

@@ -2,9 +2,11 @@ import { defineConfig } from 'vitepress'
 
 export default defineConfig({
   title: 'Agent Starter Pack',
-  description: 'Build Production Agents faster',
+  description: 'Build Production AI Agents faster using Agent Starter Pack',
   base: '/agent-starter-pack/',
   head: [
+    ['meta', {property: 'og:image', content: '/images/agent_starter_pack_screenshot.png'}],
+    ['meta', {property: 'og:twitter:image', content: '/images/agent_starter_pack_screenshot.png'}],
     ['link', { rel: 'preconnect', href: 'https://fonts.googleapis.com' }],
     ['link', { rel: 'preconnect', href: 'https://fonts.gstatic.com', crossorigin: '' }],
     ['link', { href: 'https://fonts.googleapis.com/css2?family=Roboto:wght@300;400;500;700&display=swap', rel: 'stylesheet' }],

{agent_starter_pack-0.4.1 → agent_starter_pack-0.4.3}/docs/guide/getting-started.md

@@ -3,7 +3,7 @@
 
 This guide quickly walks you through setting up your first agent project.
 
-**Want zero setup?** 👉 [Try in Firebase Studio](https://studio.firebase.google.com/new?template=https%3A%2F%2Fgithub.com%2FGoogleCloudPlatform%2Fagent-starter-pack%2Ftree%2Fmain%2Fsrc%2Fresources%2Fidx)
+**Want zero setup?** 👉 [Try in Firebase Studio](https://studio.firebase.google.com/new?template=https%3A%2F%2Fgithub.com%2FGoogleCloudPlatform%2Fagent-starter-pack%2Ftree%2Fmain%2Fsrc%2Fresources%2Fidx) or in [Cloud Shell](https://shell.cloud.google.com/cloudshell/editor?cloudshell_git_repo=https%3A%2F%2Fgithub.com%2Feliasecchig%2Fasp-open-in-cloud-shell&cloudshell_print=open-in-cs)
 
 ### Prerequisites
 

{agent_starter_pack-0.4.1 → agent_starter_pack-0.4.3}/docs/guide/video-tutorials.md

@@ -1,5 +1,11 @@
 # Video Tutorials
 
+## Exploring Agent Starter Pack
+
+This comprehensive tutorial demonstrates how to rapidly deploy AI Agents using the Agent Starter Pack. We cover the architecture, detail the templates and their usage, showcase a live demo, and guide you through template-based deployment from start to finish.
+
+<iframe width="560" height="315" src="https://www.youtube.com/embed/9zqwym-N3lg?si=K4kHS0G463VBGons" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>
+
 ## Kaggle GenAI Intensive Course Introduction (April 2024)
 A 6-minute introduction explaining the Agent Starter Pack and demonstrating its key features. Part of the Kaggle GenAI intensive course.
 

{agent_starter_pack-0.4.1 → agent_starter_pack-0.4.3}/docs/index.md

@@ -15,7 +15,7 @@ hero:
       link: /guide/getting-started
     - theme: alt
       text: Watch Demo Video
-      link: https://www.youtube.com/embed/eZ-8UQ_t4YM?start=2791
+      link: https://www.youtube.com/watch?v=9zqwym-N3lg
 
 features:
   - icon: ⚡️
@@ -38,6 +38,7 @@ Help us spread the word by giving us a star on GitHub!
 <a href="https://github.com/GoogleCloudPlatform/agent-starter-pack/stargazers" target="_blank" rel="noopener noreferrer" style="display: inline-block; margin-top: 8px;"> <!-- Link the badge too! -->
   ![GitHub Stars](https://img.shields.io/github/stars/GoogleCloudPlatform/agent-starter-pack?style=social&color=yellow) <!-- Added style=social for better look -->
 </a>
+
 :::
 
 ## Quick Links

{agent_starter_pack-0.4.1 → agent_starter_pack-0.4.3}/docs/package-lock.json

@@ -8,7 +8,7 @@
       "name": "project-docs",
       "version": "1.0.0",
       "devDependencies": {
-        "vitepress": "^1.0.0-rc.40"
+        "vitepress": "^1.6.3"
       }
     },
     "node_modules/@algolia/autocomplete-core": {

{agent_starter_pack-0.4.1 → agent_starter_pack-0.4.3}/docs/package.json

@@ -10,6 +10,6 @@
     "docs:preview": "vitepress preview"
   },
   "devDependencies": {
-    "vitepress": "^1.0.0-rc.40"
+    "vitepress": "^1.6.3"
   }
 }

{agent_starter_pack-0.4.1 → agent_starter_pack-0.4.3}/pyproject.toml

@@ -1,7 +1,7 @@
 [project]
 name = "agent-starter-pack"
-version = "0.4.1"
-description = "CLI tool to create GCP-based AI agent projects from templates"
+version = "0.4.3"
+description = "CLI to bootstrap production-ready Google Cloud GenAI agent projects from templates."
 authors = [
     { name = "Google LLC", email = "agent-starter-pack@google.com" },
 ]

{agent_starter_pack-0.4.1 → agent_starter_pack-0.4.3}/src/cli/commands/setup_cicd.py

@@ -12,7 +12,6 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-import json
 import logging
 import re
 import shutil
@@ -228,40 +227,18 @@ def prompt_for_repository_details(
                 repo_url = click.prompt(
                     "Enter existing repository URL (e.g., https://github.com/owner/repo)"
                 )
-                # Extract owner and name from URL
-                match = re.match(r"https://github\.com/([^/]+)/([^/]+)", repo_url)
+                # Extract owner and repo name from URL
+                match = re.search(r"github\.com/([^/]+)/([^/]+)", repo_url)
                 if match:
                     repository_owner = match.group(1)
-                    repository_name = match.group(2)
-
-                    # Verify repository exists and is empty
-                    try:
-                        result = run_command(
-                            [
-                                "gh",
-                                "repo",
-                                "view",
-                                f"{repository_owner}/{repository_name}",
-                                "--json",
-                                "isEmpty",
-                            ],
-                            capture_output=True,
-                        )
-                        if not json.loads(result.stdout).get("isEmpty", False):
-                            if not click.confirm(
-                                "Repository is not empty. Are you sure you want to use it?",
-                                default=False,
-                            ):
-                                continue
-                        break
-                    except subprocess.CalledProcessError:
-                        console.print(
-                            "❌ Repository not found or not accessible",
-                            style="bold red",
-                        )
-                        continue
+                    # Remove .git suffix if present
+                    repository_name = match.group(2).rstrip(".git")
+                    break
                 else:
-                    console.print("❌ Invalid repository URL format", style="bold red")
+                    console.print(
+                        "❌ Invalid repository URL format. Please use https://github.com/owner/repo",
+                        style="bold red",
+                    )
 
     if repository_name is None or repository_owner is None:
         raise ValueError("Repository name and owner must be provided")
@@ -570,15 +547,12 @@ def setup_cicd(
 
     if git_provider == "github" and detected_mode == "interactive":
         # First create the repository since we're in interactive mode
-        create_github_repository(repository_owner, repository_name)
+        if not repository_exists:
+            create_github_repository(repository_owner, repository_name)
 
         # Then create the connection
         oauth_token_secret_id, github_app_installation_id = create_github_connection(
-            project_id=cicd_project,
-            region=region,
-            connection_name=host_connection_name,
-            repository_name=repository_name,
-            repository_owner=repository_owner,
+            project_id=cicd_project, region=region, connection_name=host_connection_name
         )
         repository_exists = True
     elif git_provider == "github" and detected_mode == "programmatic":

{agent_starter_pack-0.4.1 → agent_starter_pack-0.4.3}/src/cli/utils/cicd.py

@@ -89,11 +89,7 @@ def setup_repository_name(
 
 
 def create_github_connection(
-    project_id: str,
-    region: str,
-    connection_name: str,
-    repository_name: str,
-    repository_owner: str,
+    project_id: str, region: str, connection_name: str
 ) -> tuple[str, str]:
     """Create and verify GitHub connection using gcloud command.
 
@@ -101,53 +97,12 @@ def create_github_connection(
         project_id: GCP project ID
         region: GCP region
         connection_name: Name for the GitHub connection
-        repository_name: Name of repository to create
-        repository_owner: Owner of repository
 
     Returns:
         tuple[str, str]: The OAuth token secret ID and the app installation ID
     """
     console.print("\n🔗 Creating GitHub connection...")
 
-    # Create repository if details provided
-    try:
-        # Check if repo exists
-        result = run_command(
-            [
-                "gh",
-                "repo",
-                "view",
-                f"{repository_owner}/{repository_name}",
-                "--json",
-                "name",
-            ],
-            capture_output=True,
-            check=False,
-        )
-
-        if result.returncode != 0:
-            # Repository doesn't exist, create it
-            console.print(
-                f"\n📦 Creating GitHub repository: {repository_owner}/{repository_name}"
-            )
-            run_command(
-                [
-                    "gh",
-                    "repo",
-                    "create",
-                    f"{repository_owner}/{repository_name}",
-                    "--private",
-                    "--description",
-                    "Repository created by Terraform",
-                ]
-            )
-            console.print("✅ GitHub repository created")
-        else:
-            console.print("✅ Using existing GitHub repository")
-    except subprocess.CalledProcessError as e:
-        console.print(f"❌ Failed to create/check repository: {e!s}", style="bold red")
-        raise
-
     def try_create_connection() -> subprocess.CompletedProcess[str]:
         cmd = [
             "gcloud",

{agent_starter_pack-0.4.1 → agent_starter_pack-0.4.3}/uv.lock

@@ -11,7 +11,7 @@ resolution-markers = [
 
 [[package]]
 name = "agent-starter-pack"
-version = "0.4.1"
+version = "0.4.3"
 source = { editable = "." }
 dependencies = [
     { name = "backoff" },