[WIP] Refactor agentscope instrument using genai util to replace

[sipercai]

Description

This PR refactors the AgentScope instrumentation to use ExtendedTelemetryHandler from opentelemetry-util-genai instead of the previous custom implementation. This change provides better consistency with other GenAI instrumentations, improved span lifecycle management.

opentelemetry-util-genai: support for metrics

Fixes # (issue)

Type of change

Please delete options that are not relevant.

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• This change requires a documentation update

How Has This Been Tested?

• Unit Tests:

  • test_instrumentor.py: Tests for covering instrumentor initialization, instrumentation, and uninstrumentation
  • test_model.py: Tests for chat model and embedding model instrumentation
  • test_agent.py: Tests for agent instrumentation with tools
  • test_span_content.py: Tests for span content capture

• Integration Tests: Verified with real AgentScope examples:

  • structured_output/main.py: Tests structured output with tool calls
  • stream_printing_messages/multi_agent.py: Tests multi-agent conversations
  • rag/agent_usage.py: Tests RAG functionality with embeddings

Test Configuration

# Install the updated package
pip install -e loongsuite-python-agent/instrumentation-loongsuite/loongsuite-instrumentation-agentscope

# Run unit tests
pytest tests/ -v

# Run integration test
opentelemetry-instrument --traces_exporter console --metrics_exporter console \
  python agentscope/examples/functionality/structured_output/main.py

Does This PR Require a Core Repo Change?

• Yes. - Link to PR:
• No.

Checklist:

See contributing.md for styleguide, changelog guidelines, and more.

• Followed the style guidelines of this project
• Changelogs have been updated
• Unit tests have been added
• Documentation has been updated