handle reasoning_summary_part events

[wasaga]

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

currently reasoning_summary_part is not handled.

[streamText] Skipping unknown chunk type: response.reasoning_summary_part.added {
  type: 'response.reasoning_summary_part.added',
  sequence_number: 9615,
  item_id: 'rs_687eeda5f0c8819b887870419a41cea001f1b6410f0ef7d3',
  output_index: 210,
  summary_index: 0,
  part: { type: 'summary_text', text: '' }
}
[streamText] Skipping unknown chunk type: response.reasoning_summary_part.done {
  type: 'response.reasoning_summary_part.done',
  sequence_number: 9718,
  item_id: 'rs_687eeda5f0c8819b887870419a41cea001f1b6410f0ef7d3',
  output_index: 210,
  summary_index: 0,
  part: {
    type: 'summary_text',
    text: '**Considering AI and multi-agent concepts**\n' +
      '\n' +
      "I can explore the idea of multi-agent systems in science and maybe footnote some examples. For instance, there's the notion of an AI agent discovering new mathematical formulas. In 2023, there was the example of AlphaDev from DeepMind, which developed a faster sorting algorithm, although it leans more toward algorithmic advancements. Additionally, IBM's RXN for chemistry serves as another example, where AI aids in planning syntheses. However, RXN isn't a recent development."
  }
}

Describe the solution you'd like

Preferably display that as a "Reasoning Summary" block that may provide an insight into what the reasoning model is doing under the hood.

Describe alternatives you've considered

Explain any additional use-cases

If there are any use-cases that would help us understand the use/need/value please share them as they can help us decide on acceptance and prioritization.

Additional context

Add any other context or screenshots about the feature request here.