Add basic CI

.github/workflows/ci.yaml

@@ -0,0 +1,23 @@
+name: CI
+
+on:
+  push:
+    branches: [main, add_ci]
+
+  pull_request:
+    branches: [main, add_ci]
+
+  workflow_dispatch:
+
+jobs:
+  pre-commit:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v6
+
+      - name: "Set up Python"
+        uses: actions/setup-python@v6
+        with:
+          python-version-file: ".python-version"
+
+      - uses: pre-commit/action@v3.0.1

.pre-commit-config.yaml

@@ -0,0 +1,14 @@
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v6.0.0
+    hooks:
+      - id: end-of-file-fixer
+      - id: trailing-whitespace
+      - id: check-added-large-files # Default is 500kB
+
+  # Ensure uv.lock file is up to date with pyproject.toml
+  - repo: https://github.com/astral-sh/uv-pre-commit
+    # uv version.
+    rev: 0.9.27
+    hooks:
+      - id: uv-lock

.python-version

@@ -0,0 +1 @@
+3.10

README.md

@@ -128,13 +128,13 @@ If you find MAESTRO or its dataset useful in your research, please consider citi
 
 ```
 @misc{maestro,
-      title={MAESTRO: Multi-Agent Evaluation Suite for Testing, Reliability, and Observability}, 
+      title={MAESTRO: Multi-Agent Evaluation Suite for Testing, Reliability, and Observability},
       author={Tie Ma and Yixi Chen and Vaastav Anand and Alessandro Cornacchia and Amândio R. Faustino and Guanheng Liu and Shan Zhang and Hongbin Luo and Suhaib A. Fahmy and Zafar A. Qazi and Marco Canini},
       year={2026},
       eprint={2601.00481},
       archivePrefix={arXiv},
       primaryClass={cs.NI},
-      url={https://arxiv.org/abs/2601.00481}, 
+      url={https://arxiv.org/abs/2601.00481},
 }
 ```
 
@@ -158,3 +158,13 @@ If you find MAESTRO or its dataset useful in your research, please consider citi
 10. [Testing and Enhancing Multi-Agent Systems for Robust Code Generation](https://arxiv.org/html/2510.10460)
 11. [Evaluating Variance in Visual Question Answering Benchmarks](https://arxiv.org/html/2508.02645)
 -->
+
+
+## Developing MAESTRO
+```bash
+git clone git@github.com:sands-lab/maestro.git
+cd maestro
+uv sync
+# Install pre-commit hooks
+uv run -- pre-commit install
+```

examples/.gitignore

@@ -1,4 +1,4 @@
 deprecated/
 agntcy/
 
-langgraph_flat/
+langgraph_flat/

examples/adk/brand-search-optimization/README.md

@@ -219,4 +219,4 @@ This agent sample is provided for illustrative purposes only and is not intended
 
 This sample has not been rigorously tested, may contain bugs or limitations, and does not include features or optimizations typically required for a production environment (e.g., robust error handling, security measures, scalability, performance considerations, comprehensive logging, or advanced configuration options).
 
-Users are solely responsible for any further development, testing, security hardening, and deployment of agents based on this sample. We recommend thorough review, testing, and the implementation of appropriate safeguards before using any derived agent in a live or critical system.
+Users are solely responsible for any further development, testing, security hardening, and deployment of agents based on this sample. We recommend thorough review, testing, and the implementation of appropriate safeguards before using any derived agent in a live or critical system.

examples/adk/brand-search-optimization/brand_search_optimization/sub_agents/keyword_finding/prompt.py

@@ -22,7 +22,7 @@
 6. Transfer to root_agent
 
 You are helpful keyword finding agent for a brand name.
-Your primary function is to find keywords shoppers would type in when trying to find for the products from the brand user provided. 
+Your primary function is to find keywords shoppers would type in when trying to find for the products from the brand user provided.
 
 <Tool Calling>
     - call `get_product_details_for_brand` tool to find product from a brand

examples/adk/brand-search-optimization/brand_search_optimization/sub_agents/search_results/prompt.py

@@ -31,7 +31,7 @@
         - if the user says google shopping, visit this website link is https://www.google.com/search?hl=en&q=<keyword> and click on "shopping" tab
     </Navigation & Searching>
 
-    <Gather Information> 
+    <Gather Information>
         - getting titles of the top 3 products by analyzing the webpage
         - Do not make up 3 products
         - Show title of the products in a markdown format
@@ -40,7 +40,7 @@
     <Key Constraints>
         - Continue until you believe the title, description and attribute information is gathered
         - Do not make up title, description and attribute information
-        - If you can not find the information, convery this information to the user 
+        - If you can not find the information, convery this information to the user
     </Key Constraints>
 
     Please follow these steps to accomplish the task at hand: