Qwen-agent

- Add the [Tool-Integrated Reasoning (TIR) agent](https://github.com/QwenLM/Qwen-Agent/blob/main/examples/tir_math.py) for Qwen2.5-Math.
- Add support for [caching the LLM's responses](https://github.com/QwenLM/Qwen-Agent/blob/main/qwen_agent/llm/base.py#L65). LLM caching can be enabled by providing `cache_dir` in the LLM's config, i.e.,`llm = get_chat_model(cfg={..., "cache_dir": "/tmp/directory_to_save_llm_cache"})`.
- Add [self-play agents](https://github.com/QwenLM/Qwen-Agent/blob/main/qwen_agent/agents/dialogue_simulator.py) to simulate a dialogue between a user and an AI agent, mainly for data synthesis and testing purposes.

- Bug fix: Incomplete PyPI packaging caused by the absence of `__init__.py`.

- Multimodal function calling for [Qwen2-VL](https://github.com/QwenLM/Qwen2-VL). Please see [the function calling example](https://github.com/QwenLM/Qwen-Agent/blob/main/examples/qwen2vl_function_calling.py) and [the agent example](https://github.com/QwenLM/Qwen-Agent/blob/main/examples/qwen2vl_assistant_tooluse.py) for example usage.

- Make dependencies for the code interpreter and RAG optional.
- `pip install qwen-agent` now only installs minimal dependencies for function calling.
- `pip install qwen-agent[rag,code_interpreter,gui]` installs optional dependencies for RAG, Code Interpreter, and GUI.

- Added experimental support for [parallel tool calling](https://github.com/QwenLM/Qwen-Agent/blob/main/examples/function_calling_in_parallel.py#L68) and [tool choice](https://github.com/QwenLM/Qwen-Agent/blob/main/examples/function_calling.py#L77).

- Added long-context agents to understand *1-million-token* documents. Read the [blog](https://qwenlm.github.io/blog/qwen-agent-2405/) for technical details.