feat: show live token usage during streaming

[arsham]

Token counts only showed up after messages finished, so you had no idea how many tokens were being used until it was done.

Now token usage shows live while streaming:

• IN↓/OUT↑ format shows what you're sending vs receiving

• ~X tok estimates appear immediately and update in real-time

• ~X think shows reasoning token usage separately

• Tool results are now properly counted when sent back to the API

• Added sentEstimate and contextEstimate fields to track what's actually being sent

Makes it way easier to keep an eye on token budget instead of being surprised at the end.

Showcase

[Sewer56]

I like this :+1:

[iamhenry]

looking forward to it!

[modelnova-ai]

@rekram1-node any plans to include this feature in upcoming releases?

[shuv1337]

@arsham - found a bug in this one while using it in my fork:

the upstream code has:

assistantMessage.finish = "tool-calls" assistantMessage.time.completed = Date.now() await Session.updateMessage(assistantMessage) if (result && part.state.status === "running") { await Session.updatePart({ ...part, state: { status: "completed", // ... rest of completed state }, } satisfies MessageV2.ToolPart) }

But your commit 7faa5e2cbc ("feat: real-time token tracking in TUI") accidentally removed completion handling code when refactoring the subtask execution.

[shuv1337]

The implication of the bug is that custom /commands that have subtask: true set will complete it's task and then spawn another task trying to do the same thing, over and over until manual intervention