Native Bedrock Codex GPT-5.6 Sol lacks explicit cache controls, producing high cache-write spend

Summary 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. Environment Codex CLI: 0.147.0 Provider: native amazon-bedrock Endpoint: Bedrock Mantle Responses API, us-east-1 Model: openai.gpt-5.6-sol Observed production usage 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: Requests Cache-write tokens Estimated cache-write cost Estimated total cost 3,656 171.94M $1,182.09 $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. There were no client errors in the corresponding CloudWatch metrics. These are usage-derived estimates, not finalized AWS invoice amounts. Investigation Codex already emits a session-scoped prompt_cache_key, but the request types for both HTTP and WebSocket Responses requests do not include either: prompt_cache_options 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. That matches the workload above. Requested behavior Add support for serializing prompt_cache_options for GPT-5.6-capable Responses providers. Add a typed prompt_cache_breakpoint field to supported input content blocks. Provide a provider/model capability gate and a safe placement strategy at the end of Codex's measured stable instruction/tool prefix. Surface cache reads and cache writes in per-turn usage telemetry so users can diagnose costly full-prefix rewrites. Scope This report does not claim that every cache write is a defect. Cold starts, genuinely distinct prompts, forks, and compaction can all require writes. The issue is that native Bedrock Codex currently has no way to use the documented explicit-cache mechanism for the stable-prefix case.