[opentelemetry-instrumentation-genai-smolagents] instrument agent runs

[alexander-akhmetov]

Description

Adds invoke_agent instrumentation, duration and token-usage metrics for smolagents MultiStepAgent.run. The span records agent and model metadata, tool and managed-agent definitions, token usage from the current run, finish reason, task and answer content when capture is enabled.

Known gaps:

• Tool calls do not emit execute_tool spans.
• Agent steps do not get separate spans. See Adding ReAct Iterations Spans in Reasoning-Acting Agents semantic-conventions-genai#81.

Part of #141

Type of change

• New feature (non-breaking change which adds functionality)

How has this been tested?

uv run tox -e py310-test-instrumentation-genai-smolagents-oldest
uv run tox -e py314-test-instrumentation-genai-smolagents-latest
uv run tox -e py314-test-instrumentation-genai-smolagents-conformance
uv run tox -e precommit
uv run tox -e typecheck
uv run tox -e readme

Checklist

See CONTRIBUTING.md
for the style guide, changelog guidance, and more.

• Followed the style guidelines of this project
• Changelog updated if the change requires an entry
• Unit tests added
• Documentation updated

[opentelemetry-pr-dashboard]

Pull request dashboard status

Waiting on the author · refreshed 2026-08-20 15:38 UTC

Move out of draft to request review.

Status above doesn't look right?

• Just replied or pushed? Anything around or after the refresh time above may not be picked up yet — give it a few minutes.
• Anything look wrong? Report it with what you expected; it helps us improve the dashboard.