Native Codex CLI requests to Amazon Bedrock Mantle cannot opt into GPT-5.6 Sol explicit prompt caching. On an agentic coding workload, this has produced a large volume of cache-write tokens and materially higher cost. This is related to #35300, but adds independent production usage evidence from the native `amazon-bedrock` provider.

For the completed days 2026-08-05 through 2026-08-08, Cost Explorer usage quantities and the Bedrock rate card produced the following cache-aware estimate for Sol: 3,656 requests, 171.94M cache-write tokens, estimated cache-write cost $1,182.09, estimated total cost $1,386.46. Cache writes were about 85% of the model's estimated spend. A local Codex session also reported 76 Sol requests with 6.709M `cache_write_input_tokens`, zero `cached_input_tokens`, and an average of about 88K cache-write tokens per request.

Investigation shows Codex already emits a session-scoped `prompt_cache_key`, but the request types for both HTTP and Web Socket Responses requests do not include either `prompt_cache_options` or `prompt_cache_breakpoint`. The built-in Amazon Bedrock provider config exposes transport/auth settings, not structured request-body transformation, so this cannot be configured through `config.toml`. AWS documents explicit cache mode for GPT-5.6 on Bedrock specifically for agentic workflows with long stable instructions/tool definitions followed by changing tool and user content.

Requested behavior: 1) Add support for serializing `prompt_cache_options` for GPT-5.6-capable Responses providers. 2) Add a typed `prompt_cache_breakpoint` field to supported input content blocks. 3) Provide a provider/model capability gate and a safe placement strategy at the end of Codex's measured stable instruction/tool prefix. 4) Surface cache reads and cache writes in per-turn usage telemetry so users can diagnose costly full-prefix rewrites.