fix(langchain): use get_buffer_string for message summarization

[mdrxy]

Fixes #34517

Supersedes #34557, #34570

Fixes token inflation in SummarizationMiddleware that caused context window overflow during summarization.

Root cause: When formatting messages for the summary prompt, str(messages) was implicitly called, which includes all Pydantic metadata fields (usage_metadata, response_metadata, additional_kwargs, etc.). This caused the stringified representation to use ~2.5x more tokens than count_tokens_approximately estimates.

Problem:

• Summarization triggers at 85% of context window based on count_tokens_approximately
• But str(messages) in the prompt uses 2.5x more tokens
• Results in ContextLengthExceeded

Fix: Use get_buffer_string() to format messages, which produces compact output:

Human: What's the weather?
AI: Let me check...[tool_calls]
Tool: 72°F and sunny

Instead of verbose Pydantic repr:

[HumanMessage(content='What's the weather?', additional_kwargs={}, response_metadata={}), ...]

[codspeed-hq]

Merging this PR will improve performance by 25.09%

⚠️ 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.

Summary

⚡ 2 improved benchmarks
✅ 11 untouched benchmarks
⏩ 21 skipped benchmarks¹

Performance Changes

	Mode	Benchmark	BASE	HEAD	Efficiency
⚡	WallTime	test_async_callbacks_in_sync	23.1 ms	18.4 ms	+25.09%
⚡	WallTime	test_import_time[ChatPromptTemplate]	626.8 ms	567.6 ms	+10.43%

---

_{Comparing mdrxy/fix-summarization (ab08dbf) with master (c1f1641)²}

Footnotes

1. 21 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. ↩

2. No successful run was found on master (0438f8c) during the generation of this report, so c1f1641 was used instead as the comparison base. There might be some changes unrelated to this pull request in this report. ↩