Metadata-Version: 2.4
Name: career_emulator_techarena
Version: 1.0.5
Summary: TechArena Career Survival Agent challenge dataset (English dev validation set)
Author-email: Yuwei <yuwei.willow.z@gmail.com>, Hugo <hugo@hugohuang.com>
License-Expression: MIT
Project-URL: Homepage, https://github.com/RAI-Internal/techarena-career-sim
Project-URL: Documentation, https://techarena-career-sim.readthedocs.io/en/latest/
Project-URL: Source, https://github.com/RAI-Internal/techarena-career-sim
Project-URL: Issues, https://github.com/RAI-Internal/techarena-career-sim/issues
Keywords: python,career-sim,simulation,agent,llm,techarena,competition,mcp client,client,mcp,fastmcp,mcp server,model context protocol
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: Implementation :: CPython
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Intended Audience :: Developers
Requires-Python: <4,>=3.11
Description-Content-Type: text/markdown
License-File: LICENSE
Dynamic: license-file

# TechArena Career Survival Agent — challenge dataset

[![Documentation](https://img.shields.io/badge/Docs-blue?style=for-the-badge&logo=readthedocs&link=https%3A%2F%2Ftecharena-career-sim.readthedocs.io%2Fen%2Flatest%2Findex.html)](https://techarena-career-sim.readthedocs.io/en/latest/) [![GitHub](https://img.shields.io/badge/Participant%20Repo-black?style=for-the-badge&logo=GitHub)](https://github.com/RAI-Internal/techarena-career-sim)

👾Welcome to Huawei TechArena 2026. 👾

You will need two PyPI packages. This one, `career-emulator-techarena`, is the data. The other one, [`career-emulator-engine`](https://pypi.org/project/career-emulator-engine/), is the engine that actually runs the game.

Inside this package you will find the **dev validation dataset**. Use it to build your agent, try things out and see how you are doing. There is also a test dataset, but that one stays with us and is only used for scoring. We are keeping it closed so you can focus on playing well, rather than tuning to the marking data. Have fun and good luck. ☘️🐈

🙇🏻‍♀️ Two little reminders before you start.

Please play through the five official MCP tools only: `new_game`, `observe`, `take_action`, `check_latest_logs`, and `show_employee_handbook`. Unpacking the package to read the data or the rules inside counts as cheating and a team that does this can be banned.

Please also spend your energy on the agent itself. A threshold or a formula you notice in the validation set may change when we score you. We want to see how well your agent generalizes. Have fun with it. 

## Install (dataset only)

```bash
pip install career-emulator-techarena
```

## Install (engine + dataset + MCP)

```bash
pip install "career-emulator-engine[mcp]"
```

Load the packaged dataset in **distribution** mode:

```bash
career-emulator-engine update --source distribution --split dev
```

## Links
- Participant starter: <https://github.com/RAI-Internal/techarena-career-sim>
- Huawei TechArena 2026: <https://techarena-uk.hydro.ac/>
- discord: https://discord.gg/TPKam7ZDp
