feat(schema): track LLM cache-creation (write) tokens in PromptTokenDetails

**Is your feature request related to a problem? Please describe.**

`schema.PromptTokenDetails` models only CachedTokens (cache read). There's no field for cache write (creation) tokens. Multiple providers bill cache writes at a premium and report a distinct count - Anthropic cache_creation_input_tokens (1.25x/2x), OpenAI cache_write_tokens (newer manual-cache models, 1.25x), AWS Bedrock cacheWriteInputTokens - but eino has nowhere to put it, so bindings fold it into `PromptTokens`. The total is preserved, but the distinct write count isn't surfaced:

```go
promptTokens := int(usage.InputTokens + usage.CacheReadInputTokens + usage.CacheCreationInputTokens)
PromptTokenDetails{ CachedTokens: int(usage.CacheReadInputTokens) } // write count not surfaced
```

Result: write tokens are counted, but unattributable - they land in the input bucket and get priced at 1x instead of the provider's write rate, so cost tracking under-reports the write premium and can't break out write volume.

**Describe the solution you'd like**

```go
type PromptTokenDetails struct {
CachedTokens int `json:"cached_tokens"` // cache read
CacheCreationTokens int `json:"cache_creation_tokens"` // cache write
}
```

**Describe alternatives you've considered**

- Compute downstream - impossible; the write count is already summed into `PromptTokens` at the binding and can't be separated back out.
- Carry via ResponseMeta.Extra - works but unshaped and per-consumer; a typed field is the right home.

**Additional context**

Every other provider-agnostic framework already models write separately and provider-neutrally: LangChain / LangChain.js (input_token_details.cache_creation), Vercel AI SDK (inputTokens.cacheWrite), LlamaIndex (cache_creation_input_tokens). Gemini is the one provider with no per-request write count (write billed in a separate caches.create call) — a neutral field simply stays zero there.

Start at the Go definition of schema.PromptTokenDetails and trace the provider bindings that construct it from cache usage. Add the distinct cache-creation token field described in the issue, preserving existing cached-token behavior, and verify that provider-reported write counts are surfaced without changing total prompt-token accounting.

Written by the indexing model from the issue text.