agent-starter-pack 0.2.2__tar.gz → 0.2.3__tar.gz

{agent_starter_pack-0.2.2 → agent_starter_pack-0.2.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: agent-starter-pack
-Version: 0.2.2
+Version: 0.2.3
 Summary: CLI tool to create GCP-based AI agent projects from templates
 Author-email: Google LLC <agent-starter-pack@google.com>
 License: Apache-2.0
@@ -9,7 +9,7 @@ Requires-Python: >=3.10
 Requires-Dist: backoff>=2.2.1
 Requires-Dist: click~=8.1.7
 Requires-Dist: cookiecutter~=2.5.0
-Requires-Dist: google-cloud-aiplatform~=1.81.0
+Requires-Dist: google-cloud-aiplatform~=1.87.0
 Requires-Dist: pyyaml~=6.0.1
 Requires-Dist: rich~=13.7.0
 Provides-Extra: jupyter
@@ -33,7 +33,7 @@ It accelerates development by providing a holistic, production-ready solution, a
 
 | ⚡️ Launch | 🧪 Experiment  | ✅ Deploy | 🛠️ Customize |
 |---|---|---|---|
-| [Pre-built agent templates](./agents/) (ReAct, RAG, multi-agent, Live Multimodal API). | [Vertex AI evaluation](https://cloud.google.com/vertex-ai/generative-ai/docs/models/evaluation-overview) and an interactive playground. | Production-ready infra with [monitoring](./docs/monitoring.md), [observability](./docs/observability.md), and [CI/CD](./docs/deployment.md) on [Cloud Run](https://cloud.google.com/run) or [Agent Engine](https://cloud.google.com/vertex-ai/generative-ai/docs/agent-engine/overview). | Extend and customize templates according to your needs. |
+| [Pre-built agent templates](./agents/) (ReAct, RAG, multi-agent, Live Multimodal API). | [Vertex AI evaluation](https://cloud.google.com/vertex-ai/generative-ai/docs/models/evaluation-overview) and an interactive playground. | Production-ready infra with [monitoring, observability](./docs/observability.md), and [CI/CD](./docs/deployment.md) on [Cloud Run](https://cloud.google.com/run) or [Agent Engine](https://cloud.google.com/vertex-ai/generative-ai/docs/agent-engine/overview). | Extend and customize templates according to your needs. |
 
 ---
  
@@ -94,16 +94,6 @@ This starter pack covers all aspects of Agent development, from prototyping and
 
 ---
 
-#### From `e2e-gen-ai-app-starter-pack` to `agent-starter-pack`
-
-This project represents the next evolution of the [e2e-gen-ai-app-starter-pack](goo.gle/e2e-gen-ai-app-starter-pack).  Building on the foundation of the original, we've made significant improvements:
-
-*   **Streamlined CLI:**  A new command-line interface (`agent-starter-pack`) simplifies project creation, template selection, and deployment.
-*   **Expanded Agent Options:** Support for a wider variety of agent frameworks (LangGraph, CrewAI, and the Google GenAI SDK) and deployment targets (including Vertex AI Agent Engine).
-*   **Simplified setup**: Integrated gcloud authentication and projects and region configurations
-
----
-
 ## 🔧 Requirements
 
 - Python 3.10+
@@ -127,6 +117,10 @@ See the [documentation](docs/) for more details:
 - **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`.
 
+## 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!
+
 ## Contributing
 
 Contributions are welcome! See the [Contributing Guide](CONTRIBUTING.md).

{agent_starter_pack-0.2.2 → agent_starter_pack-0.2.3}/README.md

@@ -8,7 +8,7 @@ It accelerates development by providing a holistic, production-ready solution, a
 
 | ⚡️ Launch | 🧪 Experiment  | ✅ Deploy | 🛠️ Customize |
 |---|---|---|---|
-| [Pre-built agent templates](./agents/) (ReAct, RAG, multi-agent, Live Multimodal API). | [Vertex AI evaluation](https://cloud.google.com/vertex-ai/generative-ai/docs/models/evaluation-overview) and an interactive playground. | Production-ready infra with [monitoring](./docs/monitoring.md), [observability](./docs/observability.md), and [CI/CD](./docs/deployment.md) on [Cloud Run](https://cloud.google.com/run) or [Agent Engine](https://cloud.google.com/vertex-ai/generative-ai/docs/agent-engine/overview). | Extend and customize templates according to your needs. |
+| [Pre-built agent templates](./agents/) (ReAct, RAG, multi-agent, Live Multimodal API). | [Vertex AI evaluation](https://cloud.google.com/vertex-ai/generative-ai/docs/models/evaluation-overview) and an interactive playground. | Production-ready infra with [monitoring, observability](./docs/observability.md), and [CI/CD](./docs/deployment.md) on [Cloud Run](https://cloud.google.com/run) or [Agent Engine](https://cloud.google.com/vertex-ai/generative-ai/docs/agent-engine/overview). | Extend and customize templates according to your needs. |
 
 ---
  
@@ -69,16 +69,6 @@ This starter pack covers all aspects of Agent development, from prototyping and
 
 ---
 
-#### From `e2e-gen-ai-app-starter-pack` to `agent-starter-pack`
-
-This project represents the next evolution of the [e2e-gen-ai-app-starter-pack](goo.gle/e2e-gen-ai-app-starter-pack).  Building on the foundation of the original, we've made significant improvements:
-
-*   **Streamlined CLI:**  A new command-line interface (`agent-starter-pack`) simplifies project creation, template selection, and deployment.
-*   **Expanded Agent Options:** Support for a wider variety of agent frameworks (LangGraph, CrewAI, and the Google GenAI SDK) and deployment targets (including Vertex AI Agent Engine).
-*   **Simplified setup**: Integrated gcloud authentication and projects and region configurations
-
----
-
 ## 🔧 Requirements
 
 - Python 3.10+
@@ -102,6 +92,10 @@ See the [documentation](docs/) for more details:
 - **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`.
 
+## 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!
+
 ## Contributing
 
 Contributions are welcome! See the [Contributing Guide](CONTRIBUTING.md).

{agent_starter_pack-0.2.2 → agent_starter_pack-0.2.3}/docs/cli/README.md

@@ -5,6 +5,6 @@ This document provides an overview of the available CLI commands for managing yo
 ## Available Commands
 
 - [`create`](create.md) - Create a new generative AI application project
-- [`setup-cicd`](setup-cicd.md) - Set up CI/CD pipeline for your project
+- [`setup-cicd`](setup_cicd.md) - Set up CI/CD pipeline for your project
 
 For detailed usage instructions, click on the command links above.

{agent_starter_pack-0.2.2 → agent_starter_pack-0.2.3}/docs/cli/create.md

@@ -1,4 +1,4 @@
-# CLI Commands
+# `create`
 
 The Agent Starter Pack provides CLI commands to help you create and manage AI agent projects.
 

agent_starter_pack-0.2.3/docs/cli/setup_cicd.md

@@ -0,0 +1,93 @@
+# `setup-cicd`
+
+The `setup-cicd` command is a powerful utility provided by `agent-starter-pack` that automates the deployment of your complete Terraform infrastructure and configures your Google Cloud projects in a single operation.
+
+**⚡️ Quick Start Example:**
+
+The command is now even simpler to get started with. You can run it without any arguments, and it will prompt you for the required project IDs:
+
+```bash
+agent-starter-pack setup-cicd
+```
+*(You will be prompted for Staging and Production project IDs)*
+
+Alternatively, you can provide the project IDs directly as flags:
+
+```bash
+agent-starter-pack setup-cicd \
+  --staging-project=your-staging-project-id \
+  --prod-project=your-prod-project-id
+```
+
+**⚠️ Important Considerations:**
+
+*   **Experimental:** This command is under active development. Use it with caution and report any issues.
+*   **Production Use:** For production environments, we **strongly recommend** following the detailed instructions in `deployment/README.md`. Manual setup offers greater control over security and configuration. This automated command is best suited for development and testing.
+*   **GitHub Only:** Currently, only GitHub is supported as a Git provider.
+
+### Prerequisites
+
+1.  **Run from Project Root:** Execute the command from the root directory of your `agent-starter-pack` project (where `pyproject.toml` is located).
+2.  **Install Tools:**
+    *   Terraform
+    *   `gh` CLI (GitHub CLI): Install and authenticate using `gh auth login`.
+    *   `gcloud` CLI (Google Cloud SDK): Authenticate using `gcloud auth application-default login`.
+3.  **Google Cloud Projects:** You need at least two Google Cloud projects: one for staging and one for production. The command will prompt you for their IDs if you don't provide the `--staging-project` and `--prod-project` flags. You also need a project to host the CI/CD resources (Cloud Build, Artifact Registry, Terraform state). You can specify this using `--cicd-project`. If omitted, the production project will be used for CI/CD resources.
+4.  **Permissions:** The user or service account running this command must have the `Owner` role on the specified Google Cloud projects (staging, production, CI/CD if specified, development if specified). This is necessary for creating resources and assigning IAM roles.
+
+### How it Works
+
+The `setup-cicd` command automates the following:
+
+1.  **GitHub Integration:** Creates a new private GitHub repository or connects to an existing one (prompting for details if needed).
+2.  **Project ID Confirmation:** Prompts for Staging and Production project IDs if they are not provided via flags.
+3.  **Cloud Build Connection:** Sets up a Cloud Build connection to your GitHub repository.
+4.  **Terraform Setup:**
+    *   Configures Terraform to manage your CI/CD infrastructure (Cloud Build triggers, IAM permissions, etc.) and optionally, a development environment (if `--dev-project` is provided).
+    *   By default, sets up remote Terraform state management using a Google Cloud Storage (GCS) bucket in your CI/CD project (`<CICD_PROJECT_ID>-terraform-state`). Use `--local-state` to opt-out.
+5.  **Resource Deployment:** Runs `terraform apply` to create the necessary resources in Google Cloud and configure the GitHub repository connection.
+6.  **Local Git Setup:** Initializes a Git repository locally (if needed) and adds the GitHub repository as the `origin` remote.
+
+### Running the Command
+
+```bash
+agent-starter-pack setup-cicd \
+    [--staging-project <YOUR_STAGING_PROJECT_ID>] \
+    [--prod-project <YOUR_PROD_PROJECT_ID>] \
+    [--cicd-project <YOUR_CICD_PROJECT_ID>] \
+    [--dev-project <YOUR_DEV_PROJECT_ID>] \
+    [--region <GCP_REGION>] \
+    [--repository-name <GITHUB_REPO_NAME>] \
+    [--repository-owner <GITHUB_USERNAME_OR_ORG>] \
+    [--local-state] \
+    [--auto-approve] \
+    [--debug]
+```
+
+**Key Options:**
+
+*   `--staging-project`, `--prod-project`: **Required Information.** Your Google Cloud project IDs for staging and production environments. The command will prompt for these if the flags are omitted.
+*   `--cicd-project`: (Optional) Project ID for hosting CI/CD resources (Cloud Build, Artifact Registry, Terraform state bucket). If omitted, defaults to the production project ID (provided via flag or prompt).
+*   `--dev-project`: (Optional) Project ID for a dedicated development environment managed by Terraform. If provided, Terraform will also be applied to set up resources in this development project.
+*   `--region`: (Optional) GCP region for resources (default: `us-central1`).
+*   `--repository-name`: (Optional) Name for the GitHub repository. If omitted, you'll be prompted or a name will be generated.
+*   `--repository-owner`: (Optional) Your GitHub username or organization. Defaults to the authenticated `gh` user if omitted.
+*   `--local-state`: (Optional) Use local files for Terraform state instead of the default GCS backend. Not recommended for collaboration.
+*   `--auto-approve`: (Optional) Skip interactive prompts (including project ID prompts if flags are omitted). Use carefully.
+*   `--debug`: (Optional) Enable verbose logging.
+
+*(For advanced/programmatic use with pre-existing connections, see options like `--github-pat`, `--github-app-installation-id`, `--host-connection-name` by running `agent-starter-pack setup-cicd --help`)*
+
+### After Running the Command
+
+1.  **Commit and Push:** This is crucial to trigger the pipeline.
+    ```bash
+    git add .
+    git commit -m "Initial commit of agent starter pack"
+    git push -u origin main
+    ```
+2.  **Verify:** Check your GitHub repository and Google Cloud projects (Cloud Build > Triggers, Secret Manager, IAM) to see the created resources.
+
+### Manual CI/CD Setup (Recommended for Production)
+
+For robust, production-ready deployments with fine-grained control over security, customization, and advanced CI/CD practices, please follow the [manual setup guide](../deployment.md).

{agent_starter_pack-0.2.2 → agent_starter_pack-0.2.3}/docs/deployment.md

@@ -1,7 +1,5 @@
 # Deployment
 
-> **Note:** For an automated setup of a basic CI/CD pipeline, see the [`setup-cicd` CLI command documentation](../docs/cli/setup_cicd.md). The automated setup is experimental and recommended primarily for development and testing. For production, follow the manual steps below.
-
 The templated agent leverages [**Terraform**](http://terraform.io) to define and provision the underlying infrastructure, while [**Cloud Build**](https://cloud.google.com/build/) orchestrates the continuous integration and continuous deployment (CI/CD) pipeline.
 
 ## Deployment Workflow
@@ -29,6 +27,8 @@ The templated agent leverages [**Terraform**](http://terraform.io) to define and
 
 ## Setup
 
+> **Note:** For a streamlined one-command deployment of the entire CI/CD pipeline and infrastructure using Terraform, you can use the [`agent-starter-pack setup-cicd` CLI command](./cli/setup_cicd.md). Currently only supporting Github.
+
 **Prerequisites:**
 
 1. A set of Google Cloud projects:
@@ -58,6 +58,7 @@ The templated agent leverages [**Terraform**](http://terraform.io) to define and
 
    | Variable               | Description                                                     | Required |
    | ---------------------- | --------------------------------------------------------------- | :------: |
+   | project_name           | Project name used as a base for resource naming                 |   Yes    |
    | prod_project_id        | **Production** Google Cloud Project ID for resource deployment. |   Yes    |
    | staging_project_id     | **Staging** Google Cloud Project ID for resource deployment.    |   Yes    |
    | cicd_runner_project_id | Google Cloud Project ID where CI/CD pipelines will execute.     |   Yes    |
@@ -65,7 +66,7 @@ The templated agent leverages [**Terraform**](http://terraform.io) to define and
    | host_connection_name   | Name of the host connection you created in Cloud Build          |   Yes    |
    | repository_name        | Name of the repository you added to Cloud Build                 |   Yes    |
 
-   Other optional variables include: telemetry and feedback BigQuery dataset IDs, log filters, sink names, service account names, bucket name suffixes, artifact registry repository name, and various role assignments.
+   Other optional variables may include: telemetry and feedback log filters, service account roles, and for projects requiring data ingestion: pipeline cron schedule, pipeline roles, and datastore-specific configurations.
 
 4. **Deploy Infrastructure with Terraform**
 
@@ -96,28 +97,3 @@ After completing these steps, your infrastructure will be set up and ready for d
 For End-to-end testing of the application, including tracing and feedback sinking to BigQuery, without the need to trigger a CI/CD pipeline.
 
 First, enable required Google Cloud APIs:
-
-```bash
-gcloud config set project <your-dev-project-id>
-gcloud services enable serviceusage.googleapis.com cloudresourcemanager.googleapis.com
-```
-
-After you edited the relative [`env.tfvars` file](../terraform/dev/vars/env.tfvars), follow the following instructions:
-
-```bash
-cd deployment/terraform/dev
-terraform init
-terraform apply --var-file vars/env.tfvars
-```
-
-Then deploy the application using the following command (from the root of the repository):
-
-```bash
-make backend
-```
-
-### End-to-end Demo video
-
-<a href="https://storage.googleapis.com/github-repo/generative-ai/sample-apps/e2e-gen-ai-app-starter-pack/template_deployment_demo.mp4">
-  <img src="https://storage.googleapis.com/github-repo/generative-ai/sample-apps/e2e-gen-ai-app-starter-pack/preview_video.png" alt="Watch the video" width="300"/>
-</a>

{agent_starter_pack-0.2.2 → agent_starter_pack-0.2.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "agent-starter-pack"
-version = "0.2.2"
+version = "0.2.3"
 description = "CLI tool to create GCP-based AI agent projects from templates"
 authors = [
     { name = "Google LLC", email = "agent-starter-pack@google.com" },
@@ -11,7 +11,7 @@ requires-python = ">=3.10"
 dependencies = [
     "click~=8.1.7",
     "cookiecutter~=2.5.0",
-    "google-cloud-aiplatform~=1.81.0",
+    "google-cloud-aiplatform~=1.87.0",
     "rich~=13.7.0",
     "pyyaml~=6.0.1",
     "backoff>=2.2.1",

{agent_starter_pack-0.2.2 → agent_starter_pack-0.2.3}/src/base_template/Makefile

@@ -1,5 +1,5 @@
 install:
-	@command -v uv >/dev/null 2>&1 || { echo "uv is not installed. Installing uv..."; curl -LsSf https://astral.sh/uv/install.sh | sh; source ~/.bashrc; }
+	@command -v uv >/dev/null 2>&1 || { echo "uv is not installed. Installing uv..."; curl -LsSf https://astral.sh/uv/0.6.12/install.sh | sh; source ~/.bashrc; }
 	uv sync --dev {% if cookiecutter.agent_name != 'live_api' %}--extra streamlit{%- endif %} --extra jupyter --frozen{% if cookiecutter.agent_name == 'live_api' %} && npm --prefix frontend install{%- endif %}
 
 test:
@@ -19,7 +19,9 @@ backend:
 {%- if cookiecutter.deployment_target == 'cloud_run' %}
 	uv run uvicorn app.server:app --host 0.0.0.0 --port 8000 --reload
 {%- elif cookiecutter.deployment_target == 'agent_engine' %}
-	uv export --no-hashes --no-sources --no-header --no-emit-project --frozen > .requirements.txt && uv run app/agent_engine_app.py
+	# Export dependencies to requirements file using uv export (preferred method), otherwise fall back to uv pip freeze
+	uv export --no-hashes --no-sources --no-header --no-dev --no-emit-project --no-annotate --frozen > .requirements.txt 2>/dev/null || \
+	uv pip freeze --exclude-editable > .requirements.txt && uv run app/agent_engine_app.py
 {%- endif %}
 
 {% if cookiecutter.deployment_target == 'cloud_run' -%}
@@ -34,8 +36,7 @@ ui:
 setup-dev-env:
 	@if [ -z "$$PROJECT_ID" ]; then echo "Error: PROJECT_ID environment variable is not set"; exit 1; fi
 	(cd deployment/terraform/dev && terraform init && terraform apply --var-file vars/env.tfvars --var dev_project_id=$$PROJECT_ID --auto-approve)
-	
-{%- if cookiecutter.data_ingestion%}
+{% if cookiecutter.data_ingestion %}
 data-ingestion:
 	@if [ -z "$$PROJECT_ID" ]; then echo "Error: PROJECT_ID environment variable is not set"; exit 1; fi
 	$(MAKE) install
@@ -48,6 +49,7 @@ data-ingestion:
 {%- elif cookiecutter.datastore_type == "vertex_ai_vector_search" %}
 		--vector-search-index="{{cookiecutter.project_name}}-vector-search" \
 		--vector-search-index-endpoint="{{cookiecutter.project_name}}-vector-search-endpoint" \
+		--vector-search-data-bucket-name="$$PROJECT_ID-{{cookiecutter.project_name}}-vs" \
 {%- endif %}
 		--service-account="{{cookiecutter.project_name}}-rag@$$PROJECT_ID.iam.gserviceaccount.com" \
 		--pipeline-root="gs://$$PROJECT_ID-{{cookiecutter.project_name}}-rag" \

{agent_starter_pack-0.2.2 → agent_starter_pack-0.2.3}/src/base_template/README.md

@@ -56,6 +56,10 @@ make install && make playground
 {%- endif %}
 | `make test`          | Run unit and integration tests                                                              |
 | `make lint`          | Run code quality checks (codespell, ruff, mypy)                                             |
+| `make setup-dev-env` | Set up development environment resources using Terraform                                    |
+{%- if cookiecutter.data_ingestion %}
+| `make data-ingestion`| Run data ingestion pipeline in the Dev environment                                           |
+{%- endif %}
 | `uv run jupyter lab` | Launch Jupyter notebook                                                                     |
 
 For full command options and usage, refer to the [Makefile](Makefile).
@@ -144,12 +148,14 @@ This template follows a "bring your own agent" approach - you focus on your busi
 1. **Prototype:** Build your Generative AI Agent using the intro notebooks in `notebooks/` for guidance. Use Vertex AI Evaluation to assess performance.
 2. **Integrate:** Import your agent into the app by editing `app/agent.py`.
 3. **Test:** Explore your agent functionality using the Streamlit playground with `make playground`. The playground offers features like chat history, user feedback, and various input types, and automatically reloads your agent on code changes.
-4. **Deploy:** Configure and trigger the CI/CD pipelines, editing tests if needed. See the [deployment section](#deployment) for details.
+4. **Deploy:** Set up and initiate the CI/CD pipelines, customizing tests as necessary. Refer to the [deployment section](#deployment) for comprehensive instructions. For streamlined infrastructure deployment, simply run `agent-starter-pack setup-cicd`. Check out the [`agent-starter-pack setup-cicd` CLI command](https://github.com/GoogleCloudPlatform/agent-starter-pack/blob/main/docs/cli/setup_cicd.md). Currently only supporting Github.
 5. **Monitor:** Track performance and gather insights using Cloud Logging, Tracing, and the Looker Studio dashboard to iterate on your application.
 {% endif %}
 
 ## Deployment
 
+> **Note:** For a streamlined one-command deployment of the entire CI/CD pipeline and infrastructure using Terraform, you can use the [`agent-starter-pack setup-cicd` CLI command](https://github.com/GoogleCloudPlatform/agent-starter-pack/blob/main/docs/cli/setup_cicd.md). Currently only supporting Github.
+
 ### Dev Environment
 
 {%- if cookiecutter.deployment_target == 'agent_engine' %}

{agent_starter_pack-0.2.2 → agent_starter_pack-0.2.3}/src/base_template/deployment/README.md

@@ -29,6 +29,8 @@ The application leverages [**Terraform**](http://terraform.io) to define and pro
 
 ## Setup
 
+> **Note:** For a streamlined one-command deployment of the entire CI/CD pipeline and infrastructure using Terraform, you can use the [`agent-starter-pack setup-cicd` CLI command](https://github.com/GoogleCloudPlatform/agent-starter-pack/blob/main/docs/cli/setup_cicd.md). Currently only supporting Github.
+
 **Prerequisites:**
 
 1. A set of Google Cloud projects:
@@ -58,6 +60,7 @@ The application leverages [**Terraform**](http://terraform.io) to define and pro
 
    | Variable               | Description                                                     | Required |
    | ---------------------- | --------------------------------------------------------------- | :------: |
+   | project_name           | Project name used as a base for resource naming                 |   Yes    |
    | prod_project_id        | **Production** Google Cloud Project ID for resource deployment. |   Yes    |
    | staging_project_id     | **Staging** Google Cloud Project ID for resource deployment.    |   Yes    |
    | cicd_runner_project_id | Google Cloud Project ID where CI/CD pipelines will execute.     |   Yes    |
@@ -65,7 +68,7 @@ The application leverages [**Terraform**](http://terraform.io) to define and pro
    | host_connection_name   | Name of the host connection you created in Cloud Build          |   Yes    |
    | repository_name        | Name of the repository you added to Cloud Build                 |   Yes    |
 
-   Other optional variables include: telemetry and feedback BigQuery dataset IDs, log filters, sink names, service account names, bucket name suffixes, artifact registry repository name, and various role assignments.
+   Other optional variables may include: telemetry and feedback log filters, service account roles, and for projects requiring data ingestion: pipeline cron schedule, pipeline roles, and datastore-specific configurations.
 
 4. **Deploy Infrastructure with Terraform**
 

{agent_starter_pack-0.2.2 → agent_starter_pack-0.2.3}/src/base_template/deployment/cd/deploy-to-prod.yaml

@@ -20,7 +20,7 @@ steps:
     args:
       - -c
       - |
-        cd data_ingestion && pip install uv --user && uv sync --frozen && \
+        cd data_ingestion && pip install uv==0.6.12 --user && uv sync --frozen && \
         uv run python data_ingestion_pipeline/submit_pipeline.py
     env:
       - "PIPELINE_ROOT=${_PIPELINE_GCS_ROOT}"
@@ -75,7 +75,7 @@ steps:
     args:
       - "-c"
       - |
-        pip install uv --user && uv sync --frozen
+        pip install uv==0.6.12 --user && uv sync --frozen
     env:
       - 'PATH=/usr/local/bin:/usr/bin:~/.local/bin'
 
@@ -85,7 +85,7 @@ steps:
     args:
       - "-c"
       - |
-        uv export --no-hashes --no-sources --no-header --no-emit-project --frozen > .requirements.txt
+        uv export --no-hashes --no-sources --no-header --no-dev --no-emit-project --no-annotate --frozen > .requirements.txt
         uv run app/agent_engine_app.py \
           --project ${_PROD_PROJECT_ID} \
           --location ${_REGION} \

{agent_starter_pack-0.2.2 → agent_starter_pack-0.2.3}/src/base_template/deployment/cd/staging.yaml

@@ -20,7 +20,7 @@ steps:
     args:
       - -c
       - |
-        cd data_ingestion && pip install uv --user && uv sync --frozen && \
+        cd data_ingestion && pip install uv==0.6.12 --user && uv sync --frozen && \
         uv run python data_ingestion_pipeline/submit_pipeline.py
     env:
       - "PIPELINE_ROOT=${_PIPELINE_GCS_ROOT}"
@@ -108,7 +108,7 @@ steps:
     args:
       - "-c"
       - |
-        pip install uv --user && uv sync --frozen
+        pip install uv==0.6.12 --user && uv sync --frozen
     env:
       - 'PATH=/usr/local/bin:/usr/bin:~/.local/bin'
 
@@ -118,7 +118,7 @@ steps:
     args:
       - "-c"
       - |
-        uv export --no-hashes --no-sources --no-header --no-emit-project --frozen > .requirements.txt
+        uv export --no-hashes --no-sources --no-header --no-dev --no-emit-project --no-annotate --frozen > .requirements.txt
         uv run app/agent_engine_app.py \
           --project ${_STAGING_PROJECT_ID} \
           --location ${_REGION} \
@@ -146,7 +146,7 @@ steps:
 {%- if cookiecutter.deployment_target == 'cloud_run' %}
         export _ID_TOKEN=$(cat id_token.txt)
         export _STAGING_URL=$(cat staging_url.txt)
-        pip install uv --user && uv sync --frozen
+        pip install uv==0.6.12 --user && uv sync --frozen
 {%- elif cookiecutter.deployment_target == 'agent_engine' %}
         export _AUTH_TOKEN=$(cat auth_token.txt)
 {%- endif %}

{agent_starter_pack-0.2.2 → agent_starter_pack-0.2.3}/src/base_template/deployment/ci/pr_checks.yaml

@@ -20,7 +20,7 @@ steps:
     args:
       - "-c"
       - |
-        pip install uv --user && uv sync --frozen
+        pip install uv==0.6.12 --user && uv sync --frozen
     env:
       - 'PATH=/usr/local/bin:/usr/bin:~/.local/bin'
 

{agent_starter_pack-0.2.2 → agent_starter_pack-0.2.3}/src/base_template/deployment/terraform/build_triggers.tf

@@ -38,6 +38,7 @@ resource "google_cloudbuild_trigger" "pr_checks" {
     "data_ingestion/**",
   {% endif %}
   ]
+  include_build_logs = "INCLUDE_BUILD_LOGS_WITH_STATUS"
   depends_on = [resource.google_project_service.cicd_services, resource.google_project_service.shared_services]
 }
 
@@ -64,6 +65,7 @@ resource "google_cloudbuild_trigger" "cd_pipeline" {
     "deployment/**",
     "uv.lock"
   ]
+  include_build_logs = "INCLUDE_BUILD_LOGS_WITH_STATUS"
   substitutions = {
     _STAGING_PROJECT_ID            = var.staging_project_id
     _BUCKET_NAME_LOAD_TEST_RESULTS = resource.google_storage_bucket.bucket_load_test_results.name
@@ -104,6 +106,7 @@ resource "google_cloudbuild_trigger" "deploy_to_prod_pipeline" {
     repository = "projects/${var.cicd_runner_project_id}/locations/${var.region}/connections/${var.host_connection_name}/repositories/${var.repository_name}"
   }
   filename = "deployment/cd/deploy-to-prod.yaml"
+  include_build_logs = "INCLUDE_BUILD_LOGS_WITH_STATUS"
   approval_config {
     approval_required = true
   }

{agent_starter_pack-0.2.2 → agent_starter_pack-0.2.3}/src/base_template/pyproject.toml

@@ -14,11 +14,11 @@ dependencies = [
     "traceloop-sdk~=0.38.7",
     "google-cloud-logging~=3.11.4",
 {%- if cookiecutter.deployment_target == 'cloud_run' %}
-    "google-cloud-aiplatform[evaluation]~=1.81.0",
+    "google-cloud-aiplatform[evaluation]~=1.87.0",
     "fastapi~=0.115.8",
     "uvicorn~=0.34.0"
 {%- elif cookiecutter.deployment_target == 'agent_engine' %}
-    "google-cloud-aiplatform[evaluation,reasoningengine]~=1.81.0"
+    "google-cloud-aiplatform[evaluation,reasoningengine]~=1.87.0"
 {%- endif %}
 ]
 {% if cookiecutter.deployment_target == 'cloud_run' %}

{agent_starter_pack-0.2.2 → agent_starter_pack-0.2.3}/src/cli/commands/create.py

@@ -37,6 +37,40 @@ from ..utils.template import (
 console = Console()
 
 
+def normalize_project_name(project_name: str) -> str:
+    """Normalize project name for better compatibility with cloud resources and tools."""
+
+    needs_normalization = (
+        any(char.isupper() for char in project_name) or "_" in project_name
+    )
+
+    if needs_normalization:
+        normalized_name = project_name
+        console.print(
+            "Note: Project names are normalized (lowercase, hyphens only) for better compatibility with cloud resources and tools.",
+            style="dim",
+        )
+        if any(char.isupper() for char in normalized_name):
+            normalized_name = normalized_name.lower()
+            console.print(
+                f"Info: Converting to lowercase for compatibility: '{project_name}' -> '{normalized_name}'",
+                style="bold yellow",
+            )
+
+        if "_" in normalized_name:
+            # Capture the name state before this specific change
+            name_before_hyphenation = normalized_name
+            normalized_name = normalized_name.replace("_", "-")
+            console.print(
+                f"Info: Replacing underscores with hyphens for compatibility: '{name_before_hyphenation}' -> '{normalized_name}'",
+                style="yellow",
+            )
+
+        return normalized_name
+
+    return project_name
+
+
 @click.command()
 @click.pass_context
 @click.argument("project_name")
@@ -110,15 +144,7 @@ def create(
             )
             return
 
-        # Convert project name to lowercase
-        if any(char.isupper() for char in project_name):
-            original_name = project_name
-            project_name = project_name.lower()
-            console.print(
-                f"Warning: Project name '{original_name}' contains uppercase characters. "
-                f"Converting to lowercase: '{project_name}'",
-                style="bold yellow",
-            )
+        project_name = normalize_project_name(project_name)
 
         # Setup debug logging if enabled
         if debug:

{agent_starter_pack-0.2.2 → agent_starter_pack-0.2.3}/src/cli/commands/setup_cicd.py

@@ -356,9 +356,11 @@ console = Console()
 
 @click.command()
 @click.option("--dev-project", help="Development project ID")
-@click.option("--staging-project", required=True, help="Staging project ID")
-@click.option("--prod-project", required=True, help="Production project ID")
-@click.option("--cicd-project", required=True, help="CICD project ID")
+@click.option("--staging-project", help="Staging project ID")
+@click.option("--prod-project", help="Production project ID")
+@click.option(
+    "--cicd-project", help="CICD project ID (defaults to prod project if not specified)"
+)
 @click.option("--region", default="us-central1", help="GCP region")
 @click.option("--repository-name", help="Repository name (optional)")
 @click.option(
@@ -402,9 +404,9 @@ console = Console()
 )
 def setup_cicd(
     dev_project: str | None,
-    staging_project: str,
-    prod_project: str,
-    cicd_project: str,
+    staging_project: str | None,
+    prod_project: str | None,
+    cicd_project: str | None,
     region: str,
     repository_name: str | None,
     repository_owner: str | None,
@@ -426,6 +428,20 @@ def setup_cicd(
             "Make sure you are in the folder created by agent-starter-pack."
         )
 
+    # Prompt for staging and prod projects if not provided
+    if staging_project is None:
+        staging_project = click.prompt(
+            "Enter your staging project ID (where tests will be run)", type=str
+        )
+
+    if prod_project is None:
+        prod_project = click.prompt("Enter your production project ID", type=str)
+
+    # If cicd_project is not provided, default to prod_project
+    if cicd_project is None:
+        cicd_project = prod_project
+        console.print(f"Using production project '{prod_project}' for CI/CD resources")
+
     console.print(
         "\n⚠️  WARNING: The setup-cicd command is experimental and may have unexpected behavior.",
         style="bold yellow",