Reporting prompt processing progress within the Reasoning content

[samteezy]

Inspired by what you've done with sendLoadingState, curious about using that same capability to report prompt processing progress.

As someone who's VRAM poor, running larger prompts even with efficient models takes a long time. Would be convenient when running inference in an app like Open WebUI to be able to see how far along the model's gotten with processing the prompt.

I see console data like this from llama-server:

slot launch_slot_: id  3 | task 0 | processing task
slot update_slots: id  3 | task 0 | new prompt, n_ctx_slot = 131072, n_keep = 0, task.n_tokens = 82826
slot update_slots: id  3 | task 0 | n_tokens = 0, memory_seq_rm [0, end)
slot update_slots: id  3 | task 0 | prompt processing progress, n_tokens = 2048, batch.n_tokens = 2048, progress = 0.024727
slot update_slots: id  3 | task 0 | n_tokens = 2048, memory_seq_rm [2048, end)
slot update_slots: id  3 | task 0 | prompt processing progress, n_tokens = 4096, batch.n_tokens = 2048, progress = 0.049453
slot update_slots: id  3 | task 0 | n_tokens = 4096, memory_seq_rm [4096, end)
slot update_slots: id  3 | task 0 | prompt processing progress, n_tokens = 6144, batch.n_tokens = 2048, progress = 0.074180
slot update_slots: id  3 | task 0 | n_tokens = 6144, memory_seq_rm [6144, end)
slot update_slots: id  3 | task 0 | prompt processing progress, n_tokens = 8192, batch.n_tokens = 2048, progress = 0.098906
slot update_slots: id  3 | task 0 | n_tokens = 8192, memory_seq_rm [8192, end)
slot update_slots: id  3 | task 0 | prompt processing progress, n_tokens = 10240, batch.n_tokens = 2048, progress = 0.123633
slot update_slots: id  3 | task 0 | n_tokens = 10240, memory_seq_rm [10240, end)

Would it be possible to pipe the progress amounts back into the reasoning block at all?