feat(openai): support automatic server-side compaction

[ccurme (ccurme)]

Relevant OpenAI docs: https://developers.openai.com/api/docs/guides/compaction

Usage:

from langchain_openai import ChatOpenAI

model = ChatOpenAI(
    model="gpt-5.2",
    context_management=[{"type": "compaction", "compact_threshold": 10_000}],
)

[codspeed-hq]

Merging this PR will not alter performance

✅ 6 untouched benchmarks
⏩ 29 skipped benchmarks¹

---

_{Comparing cc/oai_compact (172aa8c) with master (8e35924)}

Footnotes

1. 29 benchmarks were skipped, so the baseline results were used instead. If they were deleted from the codebase, click here and archive them to remove them from the performance reports. ↩

[Mason Daugherty (mdrxy)]

Supersedes #34926 ?