[SAMurai-16]

Description

In opentelemetry.instrumentation.genai.smolagents:

• to_input_messages had an early return if not isinstance(messages, list): return [], causing messages passed as tuples to be silently dropped.
• _parts_from_content only checked if isinstance(content, list):, dropping content parts passed as a tuple.
• task_to_input_messages checked if isinstance(images, list):, dropping images passed as a tuple.
• _stop_sequences in patch.py checked if isinstance(stop, list):, dropping stop sequences passed as a tuple.
  This PR relaxes these collection checks to (list, tuple) and updates the typing to Sequence[...], consistent with PR fix(bedrock): accept tuple inputs #870 (bedrock) and PR fix(google-genai): handle tuple contents during capture #861 (google-genai).

Fixes #905

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?

• All 130 unit/integration tests in opentelemetry-instrumentation-genai-smolagents pass.
• Formatted and linted cleanly via pre-commit / tox -e ruff.

Checklist

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

[Copilot]

Copilot was unable to review this pull request because the user who requested the review has reached their quota limit.

[opentelemetry-pr-dashboard]

Pull request dashboard status

Waiting on the author · refreshed 2026-11-01 09:15 UTC

Respond to 1 review item (e.g. link a commit, explain why not, ask a follow-up):

• Top-level threads: 1

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.
• Should this be with reviewers? Comment /dashboard route:reviewers to route it to them.
• Anything wrong — including the routing? Report it with what you expected; it helps us improve the dashboard.

[AgentGymLeader]

Ran the smolagents latest and oldest envs on 4db5747: all pass. _stop_sequences has no tuple test: mlx_model(stop=("STOP",)) should record ("STOP",) as the stop sequences, and that assertion fails on main.

[eternalcuriouslearner]

Could we also add a streamed-generation test with tuple inputs? Both paths share request capture, so this would be additional regression coverage rather than a blocker.

[opentelemetry-pr-dashboard]

Hi @SAMurai-16 — just a friendly reminder that this pull request is waiting on you. The dashboard status comment has the open items and is kept current.

• Replying is enough to hand it off — answer, explain why no change is needed, or ask a follow-up. The dashboard routes it onward once nothing on the list is waiting on you.
• To hand it back for any other reason, including the dashboard getting this wrong, comment /dashboard route:reviewers.

[SAMurai-16]

Added test_generate_stream_with_tuple_messages in tests/test_models.py to cover streamed generation with tuple messages and content parts. Ran the test suite across both oldest and latest environments.