Feature request: per-tool `eager_input_streaming` so `assistant.tool_call_delta` fires early for Anthropic models

### What
The recently added `assistant.tool_call_delta` provides access to incremental tool call deltas. For recent OpenAI models (e.g. GPT 5.5), it works as expected to send deltas smoothly *as they are generated*. However, for Anthropic models (e.g. Claude Opus 4.8), the deltas arrive as a burst because Claude buffers them. Anthropic provided the `eager_input_streaming` flag for the expected behavior: https://platform.claude.com/docs/en/agents-and-tools/tool-use/fine-grained-tool-streaming#how-to-use-fine-grained-tool-streaming. But the SDK hasn't exposed this option yet.

#### Proposed Usage Example
```js
defineTool("my_tool", {
description,
parameters,
handler,
eagerInputStreaming: true, // or a different name
});
```

### Why

Responsiveness: for tools capable of handling partial arguments, this improves responsiveness when the whole response might take many seconds - sometimes minutes - to generate.

Start by tracing the assistant.tool_call_delta flow and the per-tool definition API used by the proposed defineTool example, then inspect where Anthropic model options are sent. Done means a per-tool eager input streaming option is exposed and causes tool-call deltas to arrive incrementally for Anthropic models without changing existing behavior.

Written by the indexing model from the issue text.