[FEATURE]:Support GPT-5.6 prompt caching defaults

[AbdoKnbGit]

Feature hasn't been suggested before.

• I have verified this feature I'm about to request hasn't been suggested before.

Describe the enhancement you want to request

OpenAI introduced new prompt caching behavior for GPT-5.6 and later models.

We should make opencode automatically use the right GPT-5.6 cache defaults while keeping GPT-5.5 and older models on the existing behavior.

Docs: https://developers.openai.com/api/docs/guides/prompt-caching

Why

GPT-5.6 uses prompt_cache_key for more reliable cache matching and supports request-wide cache options through prompt_cache_options.

The GPT-5.6 family includes multiple model ids, such as:

• gpt-5.6
• gpt-5.6-sol
• gpt-5.6-terra
• gpt-5.6-luna

There may also be provider or suffix variants like gpt-5.6-fast, so detection should match the whole gpt-5.6* family rather than only the exact gpt-5.6 id.

Desired behavior

For GPT-5.6 family OpenAI models, opencode should send:

promptCacheOptions: {
  mode: "implicit",
  ttl: "30m"
}

[github-actions]

This issue might be a duplicate of existing issues. Please check:

• Support GPT-5.6 family prompt caching without changing older models #36315: Near-identical feature request (GPT-5.6 prompt caching defaults) by the same author, closed for needs:compliance — the new issue appears to be a resubmission of that one.
• OpenAI prompt cache key is not stable across forked sessions #36098: OpenAI prompt cache key instability across forked sessions — overlaps with prompt cache key handling for OpenAI models.
• xAI requests missing prompt cache routing identifier (x-grok-conv-id / prompt_cache_key) #35033: xAI requests missing prompt cache routing identifier (prompt_cache_key) — related prompt_cache_key support across providers.

[rekram1-node]

yeah we will support this in v2