fix: mark tool outputs after interrupted replies

[chenghao-mou]

Why

Tool outputs remain in chat history after execution. If the user interrupts their spoken reply, the next LLM turn can treat that explanation as delivered and return no reply.

Behavior

Mark interrupted tool results in model-facing payloads while preserving existing payloads for completed replies. Keep immediate commits so tools with side effects are not replayed.

Addresses AGT-3295

Initial prompt and agent context

Model: GPT-5.6

so today, we commit the tool output after execution, but if the user interrupts the tool reply, llm might treat the tool output as spoken and skips the reply altogether in the new reply. We should try wrapping the tool output with some kind of interrupted:bool flag so it is clear to them that it is delivered or not.