feat(mappers): langfuse provider changes to support newer version of langfuse

[poshinchen]

Description

LangfuseProvider multi-framework support

• Makes LangfuseProvider work with traces from any framework (LangChain, Strands, LlamaIndex, CrewAI, etc.) — not just Strands.

This PR makes the provider framework-agnostic by routing on obs.type (universal across all frameworks in Langfuse) with a Strands-specific fallback for backward compatibility.

Changes

• langfuse_provider.py — Multi-framework observation routing:
• _convert_observation(): Route by universal obs.type (GENERATION → InferenceSpan, TOOL → ToolExecutionSpan, CHAIN/AGENT root → AgentInvocationSpan) with Strands SPAN name-based fallback preserved
• _convert_tool_execution(): Handle both Strands format (obs.input.name) and LangChain/universal format (obs.name + obs.input as arguments)
• _parse_tool_result(): Support LangChain ToolMessage format ({"content": "...", "type": "tool"})
• _convert_message(): Parse LangChain tool_calls field on assistant messages
• _extract_user_prompt(): Handle LangChain CHAIN formats ({"input": "..."}, {"messages": [...]}) and Strands message-list format via OTEL ([{"role": "user", "content": '[{"text": "..."}]'}])
• _extract_agent_response(): Handle LangChain CHAIN output formats ({"output": "..."}, {"messages": [...]}) and Strands message-list output format
• _extract_text_from_content(): New helper to unwrap Strands content (plain string, JSON-encoded [{"text": "..."}], or parsed list)
• pyproject.toml: Cap langfuse dependency at <4

Related Issues

#91
#159

Documentation PR

N/A

Type of Change

New feature

Testing

How have you tested the change? Verify that the changes do not break functionality or introduce warnings in consuming repositories: agents-docs, agents-tools, agents-cli

• I ran hatch run prepare

Checklist

• I have read the CONTRIBUTING document
• I have added any necessary tests that prove my fix is effective or my feature works
• I have updated the documentation accordingly
• I have added an appropriate example to the documentation to outline the feature, or no new docs are needed
• My changes generate no new warnings
• Any dependent changes have been merged and published

---

By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.

[afarntrog]

this seems like a wide range. Also, my understanding is that the versions have drastic differences which would be incompatible with evals sdk (one of the reasons we introduced this PR). I would recommend a range of: langfuse>=4.0.0,<5

[poshinchen]

I think I would be fine with langfuse>=3,< 5, since it basically means that older version of langfuse will be deprecated. v2/3 has similar concept/component, but v3/v4 has some major diffs and I prefer to keep both versions.