fix(anthropic): replace retired model IDs in tests and docstrings

[Mason Daugherty (mdrxy)]

Summary

• Replace claude-3-5-haiku-20241022 and claude-3-7-sonnet-20250219 with claude-haiku-4-5-20251001 and claude-sonnet-4-5-20250929 respectively
• Both models were retired by Anthropic on February 19, 2026, causing all anthropic integration tests to fail
• Updates integration tests, a unit test, and docstring examples in langchain-core

See: https://platform.claude.com/docs/en/docs/resources/model-deprecations

[codspeed-hq]

Merging this PR will degrade performance by 18.18%

⚠️ Unknown Walltime execution environment detected

Using the Walltime instrument on standard Hosted Runners will lead to inconsistent data.

For the most accurate results, we recommend using CodSpeed Macro Runners: bare-metal machines fine-tuned for performance measurement consistency.

⚡ 9 improved benchmarks
❌ 1 regressed benchmark
✅ 3 untouched benchmarks
⏩ 23 skipped benchmarks¹

⚠️ Please fix the performance issues or acknowledge them on CodSpeed.

Performance Changes

	Mode	Benchmark	BASE	HEAD	Efficiency
⚡	WallTime	test_import_time[InMemoryVectorStore]	715.7 ms	619.3 ms	+15.55%
⚡	WallTime	test_import_time[CallbackManager]	533.2 ms	480.8 ms	+10.91%
⚡	WallTime	test_import_time[InMemoryRateLimiter]	196.8 ms	173.7 ms	+13.28%
⚡	WallTime	test_import_time[Runnable]	583.7 ms	514.1 ms	+13.54%
⚡	WallTime	test_import_time[RunnableLambda]	587.7 ms	516 ms	+13.9%
⚡	WallTime	test_import_time[PydanticOutputParser]	623.9 ms	553.9 ms	+12.64%
⚡	WallTime	test_import_time[ChatPromptTemplate]	749 ms	661 ms	+13.31%
⚡	WallTime	test_import_time[BaseChatModel]	669.7 ms	553.1 ms	+21.09%
⚡	WallTime	test_import_time[Document]	213.4 ms	188.8 ms	+13.05%
❌	WallTime	test_async_callbacks_in_sync	19.5 ms	23.9 ms	-18.18%

---

_{Comparing mdrxy/remove-depr-anthropic (08b258d) with master (63f3669)}

Footnotes

1. 23 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. ↩