fix(langchain): alias Bedrock providers in summarization token check

[ccurme (ccurme)]

SummarizationMiddleware triggers based on approximate token counting, but includes a fallback checking if the reported token counts in the AIMessage usage_metadata already exceeds the threshold. It gates this fallback on the last AIMessage originating from the same provider as the summarization model, comparing response_metadata["model_provider"] against the model's ls_provider. These values aren't consistent for ChatBedrock and ChatBedrockConverse.

Here we special-case the comparison for those chat models.

[codspeed-hq]

Merging this PR will not alter performance

✅ 2 untouched benchmarks
⏩ 13 skipped benchmarks¹

---

_{Comparing cc/aws_fix_summarization (2c2acac) with master (f42d80c)²}

Footnotes

1. 13 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 (0831e44) during the generation of this report, so f42d80c was used instead as the comparison base. There might be some changes unrelated to this pull request in this report. ↩