fix(openai): keep n>1 stream choices separate in recorded output - #1864

What does this PR do?

Fixes langfuse/langfuse#16998

_extract_streamed_openai_response used a single accumulator for every choice in a chat completion stream. An n>1 stream interleaves choices within a single chunk, so content and tool-call arguments from separate choices were merged into one corrupted output (the issue's repro records "AB10" instead of "A0" and "B1").

The extractor now accumulates per choice index and returns one response per choice when the stream carries multiple choices. Single-choice streams keep the existing output shape, so the common n=1 case is unchanged. A stream that only ever yields output for one nonzero choice index (partial consumption) now records that choice instead of None.

Type of change

• Bug fix
• New feature
• Breaking change
• Refactor
• Documentation update
• Tooling, CI, or repo maintenance

Verification

uv run --frozen pytest tests/unit/test_openai.py # 37 passed
uv run --frozen pytest -n auto --dist worksteal tests/unit # 672 passed, 2 skipped (18 pre-existing test_prompt.py fixture errors reproduce on clean main without provider credentials)
uv run --frozen ruff check . # All checks passed!
uv run --frozen ruff format --check . # clean; only pre-existing tests/unit/test_media.py drift on main
uv run --frozen mypy langfuse --no-error-summary # exit 0

Checklist

• I self-reviewed the diff using code_review.md.
• I added or updated tests for behavior changes.
• I updated docs, examples, or .env.template if needed. (no docs impact: internal extractor fix, public output shape for n=1 unchanged)
• I did not hand-edit generated files; if generated files changed, I used the upstream regeneration path.
• I did not commit secrets or credentials.