Support editing the last prompt with full input options (Text, Media & Audio) in ChatSession

[ishilmioz]

Problem Statement

When editing the last sent prompt in a chat flow, the interface should support all input modes present in the main prompt bar, specifically media attachments (photos/files) and microphone/voice dictation.

Currently, users can only edit text strings, requiring them to delete or rewrite messages from scratch if they forget to attach a photo or want to correct a prompt using voice input.

Proposed Solution

In python-genai, ChatSession should provide a native method to update the last prompt with text, media, or audio/voice inputs and regenerate the response.

Example API Usage

chat = client.chats.create(model="gemini-2.5-flash")
chat.send_message("Initial text prompt")

# Easily update the last prompt with full input options
chat.update_last_prompt(
    text="Updated prompt text",
    image=pil_image,     # Support for photos/files
    audio=audio_bytes    # Support for voice/dictation
)
response = chat.regenerate_last_turn()