Update model-latency-benchmarking: latest SDK/models and configurable prompt caching

## Summary

Proposal to update the [`model-latency-benchmarking`](https://github.com/aws-samples/amazon-bedrock-samples/tree/main/model-latency-benchmarking) tool so it uses current SDK/APIs, benchmarks the latest Bedrock models, and can benchmark prompt caching.

## Motivation

- The example dataset and model list point at older models (Llama 3.1 70B, Claude 3.5 Haiku).
- Bedrock now offers newer models (Claude 4.5 family, Amazon Nova) that users want to benchmark.
- Prompt caching is generally available and reduces latency by up to 85%, but the tool cannot benchmark it today.

## Proposed changes

1. SDK/API refresh
- Use current `boto3`/`botocore`.
- Keep the Converse/ConverseStream APIs; tidy client setup and error handling.
- Fix an existing inconsistency where `get_body` hardcodes `temperature=0` and `topP=1` and ignores the configured inference parameters.

2. Latest model support
- Update the dummy JSONL and README to current cross-region inference profile IDs (for example Claude Opus 4.5, Claude Sonnet 4.5, Claude Haiku 4.5, Claude 3.7 Sonnet, and Amazon Nova Pro/Lite/Micro).

3. Configurable prompt caching (opt-in)
- Add optional per-row JSONL fields, defaulting off: `prompt_caching` (bool), `cache_ttl` ("5m"/"1h"), and a field for the cacheable static prefix (system prompt / context).
- Insert Converse `cachePoint` checkpoints when caching is enabled.
- Capture `cacheReadInputTokens` and `cacheWriteInputTokens` from the Converse `usage` block, derive a `cache_hit_rate`, and report TTFT cached vs uncached.
- Provide a longer sample prompt that meets the per-model cache minimums (1,024-4,096 tokens).

## Backward compatibility

- Existing JSONL files run unchanged. All new fields are optional and default to off.

## Out of scope

- No change to the core benchmarking methodology beyond adding cache-related columns and plots.

## Contribution

I would like to submit a pull request for this. Happy to adjust the scope based on maintainer feedback.

Start in the model-latency-benchmarking tool, reviewing get_body, the dummy JSONL, and README before checking the existing Converse and ConverseStream paths. Confirm how current inference parameters, model IDs, and usage data flow through the benchmark. Done means backward-compatible inputs, opt-in prompt caching, updated examples and documentation, and cached versus uncached latency reporting.

Written by the indexing model from the issue text.