feat: add Tavily search as configurable alternative to Serper

[tavily-integrations]

Summary

• Added Tavily as a configurable search provider running in parallel with the existing Serper/Google search integration
• Users can opt-in to Tavily via Hydra config (agent=tavily_search) without affecting existing Serper workflows
• All existing Serper files, dependencies, and env vars remain untouched

Files Changed

New files

• libs/miroflow-tools/src/miroflow_tools/mcp_servers/tavily_mcp_server.py — FastMCP server exposing tavily_search tool using tavily-python SDK, with retry logic and HuggingFace URL filtering (mirrors serper_mcp_server.py interface)
• libs/miroflow-tools/src/miroflow_tools/mcp_servers/searching_tavily_mcp_server.py — Orchestrator wrapper with stdio MCP forwarding and retry logic (mirrors searching_google_mcp_server.py structure), includes scrape_website tool
• apps/miroflow-agent/conf/agent/tavily_search.yaml — Agent config variant substituting tool-tavily-search for tool-google-search in the browsing sub-agent

Modified files

• libs/miroflow-tools/pyproject.toml — Added tavily-python to dependencies
• apps/miroflow-agent/src/config/settings.py — Added TAVILY_API_KEY env var, tool-tavily-search MCP server block, and has_tavily_api_key to env info
• apps/miroflow-agent/.env.example — Added TAVILY_API_KEY entry
• apps/gradio-demo/.env.example — Added TAVILY_API_KEY entry

Dependency changes

• Added tavily-python to libs/miroflow-tools/pyproject.toml

Environment variable changes

• Added TAVILY_API_KEY to apps/miroflow-agent/.env.example and apps/gradio-demo/.env.example

Notes for reviewers

• This is an additive change — no existing search functionality is modified
• Tavily output is normalized to a serper-compatible structure (organic array with title, link, snippet fields) for downstream compatibility
• To use Tavily, set TAVILY_API_KEY and run with agent=tavily_search Hydra override

🤖 Generated with Claude Code

Automated Review

• Passed after 1 attempt(s)
• Final review: The migration correctly adds Tavily as a parallel search provider alongside the existing Serper/Google search. All seven reported files are present and properly implemented. The new MCP servers mirror the established patterns in serper_mcp_server.py and searching_google_mcp_server.py, Tavily SDK usage is correct, the output format is serper-compatible, retry logic is consistent, and the agent config variant is well-formed. Two minor issues are noted, one of which is a pre-existing dependency gap already present in the codebase.