[Sampsonyu]

What does this PR do?

Add regression coverage for the row-counting fix in #2101. A caller may clear a page's data after processing it to release memory. The iterator must still count those rows toward max_items.

Exercise both Langfuse.iter_observation_pages and Langfuse.aiter_observation_pages with a three-item cap. The tests consume and clear each page, then verify that only three observation IDs are delivered and that the final request is limited to one remaining item. A further scripted page is available to expose an extra fetch.

This is a test-only contribution. The current implementation already counts rows before yielding; runtime code is unchanged.

Type of change

• Other: regression test coverage

Verification

uv sync --locked
uv run --frozen pytest tests/unit/test_pagination.py -q
uv run --frozen ruff check tests/unit/test_pagination.py
uv run --frozen ruff format --check tests/unit/test_pagination.py
git diff --check

The original pagination suite passes 10 cases; the expanded suite passes 12, including both new sync/async cases. Tests use the existing scripted API fixture and require no Langfuse server or model calls. The repository-wide suite, e2e tests and live-provider tests were not run for this single test-file change.

Checklist

• The diff was reviewed using code_review.md.
• Regression coverage was added and passes.
• Documentation changes are unnecessary for this test-only addition.
• No generated files or credentials are changed.

Confidence Score: 5/5

This test-only PR appears safe to merge.

Summary

Adds sync and async regression tests for callers that clear page.data after reading it.

• Pagination tests cover callers clearing yielded pages.

_{Reviews (1) · Last reviewed commit: "test(pagination): preserve item limits w..." · Reviewed by Greptile}

[claude]

Claude Code Review

This pull request is from a fork — automated review is disabled. A repository maintainer can comment @claude review to run a one-time review.

[CLAassistant]

All committers have signed the CLA.