Song Search with CLAP by gcolangiuli

Description

Contrastive Language-Audio Pretraining (CLAP) is an open-source library that enables the training of a neural network on both Audio and Text descriptions, making it possible to search for Audio using a Text input. Several pre-trained models for song search are already available on huggingface

Goals

Evaluate how CLAP can be used for song searching and determine which types of queries yield the best results by developing a Minimum Viable Product (MVP) in Python. Based on the results of this MVP, future steps could include:

• Music Tagging;
• Free text search;
• Integration with an LLM (for example, with MCP or the OpenAI API) for music suggestions based on your own library.

The code for this project will be entirely written using AI to better explore and demonstrate AI capabilities.

Result

In this MVP we implemented:

• Async Song Analysis with Clap model
• Free Text Search of the songs
• Similar song search based on vector representation
• Containerised version with web interface

We also documented what went well and what can be improved in the use of AI.

You can have a look at the result here:

• Result Presentation
• hw25-song-search Github repo

Future implementation can be related to performance improvement and stability of the analysis.

References

• CLAP: The main model being researched;
• huggingface: Pre-trained models for CLAP;
• Free Music Archive: Creative Commons songs that can be used for testing;

---

AI-Powered Unit Test Automation for Agama by joseivanlopez

The Agama project is a multi-language Linux installer that leverages the distinct strengths of several key technologies:

• Rust: Used for the back-end services and the core HTTP API, providing performance and safety.
• TypeScript (React/PatternFly): Powers the modern web user interface (UI), ensuring a consistent and responsive user experience.
• Ruby: Integrates existing, robust YaST libraries (e.g., yast-storage-ng) to reuse established functionality.

The Problem: Testing Overhead

Developing and maintaining code across these three languages requires a significant, tedious effort in writing, reviewing, and updating unit tests for each component. This high cost of testing is a drain on developer resources and can slow down the project's evolution.

The Solution: AI-Driven Automation

This project aims to eliminate the manual overhead of unit testing by exploring and integrating AI-driven code generation tools. We will investigate how AI can:

1. Automatically generate new unit tests as code is developed.
2. Intelligently correct and update existing unit tests when the application code changes.

By automating this crucial but monotonous task, we can free developers to focus on feature implementation and significantly improve the speed and maintainability of the Agama codebase.

Goals

• Proof of Concept: Successfully integrate and demonstrate an authorized AI tool (e.g., gemini-cli) to automatically generate unit tests.
• Workflow Integration: Define and document a new unit test automation workflow that seamlessly integrates the selected AI tool into the existing Agama development pipeline.
• Knowledge Sharing: Establish a set of best practices for using AI in code generation, sharing the learned expertise with the broader team.

Contribution & Resources

We are seeking contributors interested in AI-powered development and improving developer efficiency. Whether you have previous experience with code generation tools or are eager to learn, your participation is highly valuable.

If you want to dive deep into AI for software quality, please reach out and join the effort!

• Authorized AI Tools: Tools supported by SUSE (e.g., gemini-cli)
• Focus Areas: Rust, TypeScript, and Ruby components within the Agama project.

Interesting Links

• goose

---

GenAI-Powered Systemic Bug Evaluation and Management Assistant by rtsvetkov

Motivation

What is the decision critical question which one can ask on a bug? How this question affects the decision on a bug and why?

Let's make GenAI look on the bug from the systemic point and evaluate what we don't know. Which piece of information is missing to take a decision?

Description

To build a tool that takes a raw bug report (including error messages and context) and uses a large language model (LLM) to generate a series of structured, Socratic-style or Systemic questions designed to guide a the integration and development toward the root cause, rather than just providing a direct, potentially incorrect fix.

Goals

Set up a Python environment

Set the environment and get a Gemini API key. 2. Collect 5-10 realistic bug reports (from open-source projects, personal projects, or public forums like Stack Overflow—include the error message and the initial context).

Build the Dialogue Loop

1. Write a basic Python script using the Gemini API.
2. Implement a simple conversational loop: User Input (Bug) -> AI Output (Question) -> User Input (Answer to AI's question) -> AI Output (Next Question). Code Implementation

Socratic/Systemic Strategy Implementation

1. Refine the logic to ensure the questions follow a Socratic and Systemic path (e.g., from symptom-> context -> assumptions -> -> critical parts -> ).
2. Implement Function Calling (an advanced feature of the Gemini API) to suggest specific actions to the user, like "Run a ping test" or "Check the database logs."
3. Implement Bugzillla call to collect the
4. Implement Questioning Framework as LLVM pre-conditioning
5. Define set of instructions
6. Assemble the Tool

Resources

What are Systemic Questions?

Systemic questions explore the relationships, patterns, and interactions within a system rather than focusing on isolated elements.
In IT, they help uncover hidden dependencies, feedback loops, assumptions, and side-effects during debugging or architecture analysis.

Gitlab Project

gitlab.suse.de/sle-prjmgr/BugDecisionCritical_Question

---

Multi-agent AI assistant for Linux troubleshooting by doreilly

Description

Explore multi-agent architecture as a way to avoid MCP context rot.

Having one agent with many tools bloats the context with low-level details about tool descriptions, parameter schemas etc which hurts LLM performance. Instead have many specialised agents, each with just the tools it needs for its role. A top level supervisor agent takes the user prompt and delegates to appropriate sub-agents.

Goals

Create an AI assistant with some sub-agents that are specialists at troubleshooting Linux subsystems, e.g. systemd, selinux, firewalld etc. The agents can get information from the system by implementing their own tools with simple function calls, or use tools from MCP servers, e.g. a systemd-agent can use tools from systemd-mcp.

Example prompts/responses:

user$ the system seems slow
assistant$ process foo with pid 12345 is using 1000% cpu ...

user$ I can't connect to the apache webserver
assistant$ the firewall is blocking http ... you can open the port with firewall-cmd --add-port ...

Resources

Language Python. The Python ADK is more mature than Golang.

https://google.github.io/adk-docs/

https://github.com/djoreilly/linux-helper

---

issuefs: FUSE filesystem representing issues (e.g. JIRA) for the use with AI agents code-assistants by llansky3

Description

Creating a FUSE filesystem (issuefs) that mounts issues from various ticketing systems (Github, Jira, Bugzilla, Redmine) as files to your local file system.

And why this is good idea?

• User can use favorite command line tools to view and search the tickets from various sources
• User can use AI agents capabilities from your favorite IDE or cli to ask question about the issues, project or functionality while providing relevant tickets as context without extra work.
• User can use it during development of the new features when you let the AI agent to jump start the solution. The issuefs will give the AI agent the context (AI agents just read few more files) about the bug or requested features. No need for copying and pasting issues to user prompt or by using extra MCP tools to access the issues. These you can still do but this approach is on purpose different.

Goals

1. Add Github issue support
2. Proof the concept/approach by apply the approach on itself using Github issues for tracking and development of new features
3. Add support for Bugzilla and Redmine using this approach in the process of doing it. Record a video of it.
4. Clean-up and test the implementation and create some documentation
5. Create a blog post about this approach

Resources

There is a prototype implementation here. This currently sort of works with JIRA only.

---

mgr-ansible-ssh - Intelligent, Lightweight CLI for Distributed Remote Execution by deve5h

Description

By the end of Hack Week, the target will be to deliver a minimal functional version 1 (MVP) of a custom command-line tool named mgr-ansible-ssh (a unified wrapper for BOTH ad-hoc shell & playbooks) that allows operators to:

1. Execute arbitrary shell commands on thousand of remote machines simultaneously using Ansible Runner with artifacts saved locally.
2. Pass runtime options such as inventory file, remote command string/ playbook execution, parallel forks, limits, dry-run mode, or no-std-ansible-output.
3. Leverage existing SSH trust relationships without additional setup.
4. Provide a clean, intuitive CLI interface with --help for ease of use. It should provide consistent UX & CI-friendly interface.
5. Establish a foundation that can later be extended with advanced features such as logging, grouping, interactive shell mode, safe-command checks, and parallel execution tuning.

The MVP should enable day-to-day operations to efficiently target thousands of machines with a single, consistent interface.

Goals

Primary Goals (MVP):

Build a functional CLI tool (mgr-ansible-ssh) capable of executing shell commands on multiple remote hosts using Ansible Runner. Test the tool across a large distributed environment (1000+ machines) to validate its performance and reliability.

Looking forward to significantly reducing the zypper deployment time across all 351 RMT VM servers in our MLM cluster by eliminating the dependency on the taskomatic service, bringing execution down to a fraction of the current duration. The tool should also support multiple runtime flags, such as:

mgr-ansible-ssh: Remote command execution wrapper using Ansible Runner

Usage: mgr-ansible-ssh [--help] [--version] [--inventory INVENTORY]
                   [--run RUN] [--playbook PLAYBOOK] [--limit LIMIT]
                   [--forks FORKS] [--dry-run] [--no-ansible-output]

Required Arguments
--inventory, -i      Path to Ansible inventory file to use

Any One of the Arguments Is Required
--run, -r            Execute the specified shell command on target hosts
--playbook, -p       Execute the specified Ansible playbook on target hosts

Optional Arguments
--help, -h           Show the help message and exit
--version, -v        Show the version and exit
--limit, -l          Limit execution to specific hosts or groups
--forks, -f          Number of parallel Ansible forks
--dry-run            Run in Ansible check mode (requires -p or --playbook)
--no-ansible-output  Suppress Ansible stdout output

Secondary/Stretched Goals (if time permits):

1. Add pretty output formatting (success/failure summary per host).
2. Implement basic logging of executed commands and results.
3. Introduce safety checks for risky commands (shutdown, rm -rf, etc.).
4. Package the tool so it can be installed with pip or stored internally.

Resources

Collaboration is welcome from anyone interested in CLI tooling, automation, or distributed systems. Skills that would be particularly valuable include:

1. Python especially around CLI dev (argparse, click, rich)

---

Move Uyuni Test Framework from Selenium to Playwright + AI by oscar-barrios

Description

This project aims to migrate the existing Uyuni Test Framework from Selenium to Playwright. The move will improve the stability, speed, and maintainability of our end-to-end tests by leveraging Playwright's modern features. We'll be rewriting the current Selenium code in Ruby to Playwright code in TypeScript, which includes updating the test framework runner, step definitions, and configurations. This is also necessary because we're moving from Cucumber Ruby to CucumberJS.

If you're still curious about the AI in the title, it was just a way to grab your attention. Thanks for your understanding.

Nah, let's be honest AI helped a lot to vibe code a good part of the Ruby methods of the Test framework, moving them to Typescript, along with the migration from Capybara to Playwright. I've been using "Cline" as plugin for WebStorm IDE, using Gemini API behind it.

---

Goals

• Migrate Core tests including Onboarding of clients
• Improve test reliabillity: Measure and confirm a significant reduction of flakiness.
• Implement a robust framework: Establish a well-structured and reusable Playwright test framework using the CucumberJS

---

Resources

• Existing Uyuni Test Framework (Cucumber Ruby + Capybara + Selenium)
• My Template for CucumberJS + Playwright in TypeScript
• Started Hackweek Project

---

Enhance setup wizard for Uyuni by PSuarezHernandez

Description

This project wants to enhance the intial setup on Uyuni after its installation, so it's easier for a user to start using with it.

Uyuni currently uses "uyuni-tools" (mgradm) as the installation entrypoint, to trigger the installation of Uyuni in the given host, but does not really perform an initial setup, for instance:

• user creation
• adding products / channels
• generating bootstrap repos
• create activation keys
• ...

Goals

• Provide initial setup wizard as part of mgradm uyuni installation

Resources

---

Uyuni read-only replica by cbosdonnat

Description

For now, there is no possible HA setup for Uyuni. The idea is to explore setting up a read-only shadow instance of an Uyuni and make it as useful as possible.

Possible things to look at:

• live sync of the database, probably using the WAL. Some of the tables may have to be skipped or some features disabled on the RO instance (taskomatic, PXT sessions…)
• Can we use a load balancer that routes read-only queries to either instance and the other to the RW one? For example, packages or PXE data can be served by both, the API GET requests too. The rest would be RW.

Goals

• Prepare a document explaining how to do it.
• PR with the needed code changes to support it

---

Flaky Tests AI Finder for Uyuni and MLM Test Suites by oscar-barrios

Description

Our current Grafana dashboards provide a great overview of test suite health, including a panel for "Top failed tests." However, identifying which of these failures are due to legitimate bugs versus intermittent "flaky tests" is a manual, time-consuming process. These flaky tests erode trust in our test suites and slow down development.

This project aims to build a simple but powerful Python script that automates flaky test detection. The script will directly query our Prometheus instance for the historical data of each failed test, using the jenkins_build_test_case_failure_age metric. It will then format this data and send it to the Gemini API with a carefully crafted prompt, asking it to identify which tests show a flaky pattern.

The final output will be a clean JSON list of the most probable flaky tests, which can then be used to populate a new "Top Flaky Tests" panel in our existing Grafana test suite dashboard.

Goals

By the end of Hack Week, we aim to have a single, working Python script that:

1. Connects to Prometheus and executes a query to fetch detailed test failure history.
2. Processes the raw data into a format suitable for the Gemini API.
3. Successfully calls the Gemini API with the data and a clear prompt.
4. Parses the AI's response to extract a simple list of flaky tests.
5. Saves the list to a JSON file that can be displayed in Grafana.
6. New panel in our Dashboard listing the Flaky tests

Resources

• Jenkins Prometheus Exporter: https://github.com/uyuni-project/jenkins-exporter/
• Data Source: Our internal Prometheus server.
• Key Metric: jenkins_build_test_case_failure_age{jobname, buildid, suite, case, status, failedsince}.
• Existing Query for Reference: count by (suite) (max_over_time(jenkins_build_test_case_failure_age{status=~"FAILED|REGRESSION", jobname="$jobname"}[$__range])).
• AI Model: The Google Gemini API.
• Example about how to interact with Gemini API: https://github.com/srbarrios/FailTale/
• Visualization: Our internal Grafana Dashboard.
• Internal IaC: https://gitlab.suse.de/galaxy/infrastructure/-/tree/master/srv/salt/monitoring

Outcome

• Jenkins Flaky Test Detector: https://github.com/srbarrios/jenkins-flaky-tests-detector and its container
• IaC on MLM Team: https://gitlab.suse.de/galaxy/infrastructure/-/tree/master/srv/salt/monitoring/jenkinsflakytestsdetector?reftype=heads, https://gitlab.suse.de/galaxy/infrastructure/-/blob/master/srv/salt/monitoring/grafana/dashboards/flaky-tests.json?ref_type=heads, and others.
• Grafana Dashboard: https://grafana.mgr.suse.de/d/flaky-tests/flaky-tests-detection @ @ text

---