feat: add Tavily search as optional provider in ChuanhuAgent

[tavily-integrations]

Summary

• Added tavily-python dependency to requirements.txt
• Added TAVILY_API_KEY config field to config_example.json under the ChuanhuAgent section
• Extended modules/config.py to load TAVILY_API_KEY from config.json into environment
• Added conditional Tavily search tool registration in ChuanhuAgent.__init__ — when TAVILY_API_KEY is set, a TavilySearchResults tool is appended alongside existing search tools

Files changed

• requirements.txt — added tavily-python
• config_example.json — added TAVILY_API_KEY entry
• modules/config.py — added TAVILY_API_KEY to env loading loop
• modules/models/ChuanhuAgent.py — conditional Tavily tool registration

Dependency changes

• Added tavily-python to requirements.txt

Environment variable changes

• Added TAVILY_API_KEY (read from config.json or environment)

Notes for reviewers

• This is an additive change — all existing search providers (DuckDuckGo, Google CSE, SerpAPI) are untouched
• Tavily tool uses langchain_community.tools.tavily_search.TavilySearchResults which reads TAVILY_API_KEY from the environment
• Import is wrapped in try/except to gracefully handle missing dependencies

🤖 Generated with Claude Code

Automated Review

• Passed after 1 attempt(s)
• Final review: The Tavily migration for chuanhu-agent-search is well-implemented and additive. All four reported files are correctly modified: tavily-python is added to requirements.txt, TAVILY_API_KEY is documented in config_example.json, the key is propagated to the environment in config.py (consistent with other API keys), and ChuanhuAgent.py adds the tool with a lazy import inside try/except. Existing search providers are untouched. No regressions, no dead code, no unrelated changes.