Repository navigation
[FEATURE]: tokens-per-second in the desktop app (context usage indicator) #49380
Description
Summary
The desktop app has no tokens-per-second readout. The TUI has a built-in per-response t/s in the assistant footer (plus a plugin ecosystem for live indicators), but desktop users cannot see throughput while agents run. The existing context usage indicator already surfaces cost, context usage %, and token counts on hover; adding tok/s there closes the gap with minimal UI.
Environment
- opencode version: 0.0.0-beta-19425 (desktop beta)
- OS: macOS 26.6.2 (Darwin 25.6.0, arm64)
- Install/channel: desktop beta app
- Plugins: none relevant — the desktop app has no plugin UI extension points
Proposal
Show live and settled tokens per second in the desktop app's context usage indicator (the progress circle in the session header and message timeline):
- While streaming: an estimated live rate (e.g.
~51 t/s), counting output + reasoning deltas. - When the model step ends: settle to an exact rate from reported usage over the stream span, matching the TUI's built-in math.
- On hover (where cost, context %, and total tokens already appear): include the last measured rate.
- No new chrome; an optional display setting if needed.
Why this can't be a plugin
Desktop UI extension is not supported today: the UI plugin slots (@opencode/plugin/tui, OpenTUI renderables) are terminal-only, so only the app itself can add this.
Prior art
- TUI has built-in assistant-footer t/s; accuracy follow-ups tracked in tui: tok/s excludes reported reasoning tokens in V2 #48705 and PR fix(tui): include reasoning tokens in throughput #48689. TUI feature requests: Feature request: show token throughput (tok/s) in the TUI #43857, [FEATURE]: Real-time token generation speed (tok/s) in TUI status bar, like Hermes #47914.
- Desktop PR feat(app): show tokens-per-second in context usage indicator #42372 ("feat(app): show tokens-per-second in context usage indicator", 2026-08-13) implemented exactly this and was closed on 2026-09-13 by the automated stale-PR cleanup (age > 1 month, fewer than 2 positive reactions) rather than on technical merit. Filing this issue so the work is tracked and can be revived or re-landed.
Additional context
Desktop sessions on this machine stream at rates where a live readout is genuinely useful (~50–180 t/s depending on model and step), and the only current workaround is a separate TUI instance or a home-grown sidecar.
Activity
github-actions commentedon Sep 16, 2026
This issue might be a duplicate of existing issues. Please check:
If the intent is specifically to track the desktop app implementation separately from the TUI work, it may be worth linking these issues to avoid duplicated effort.
VladSmr commentedon Oct 2, 2026
The context-usage half of this works on Desktop today: /context gives an instant
per-session summary and /context-breakdown a full per-category table
(tokens-per-second isn't covered).
I've built it as a plugin — opencode-context-indicator. Still in a testing
stage; with your help and feedback we can make it better together.
reasoning, tool args, residual
ctx and %
https://github.com/VladSmr/opencode-context-indicator
npm: opencode-context-indicator
opencodejr commentedon Oct 28, 2026
Thanks for the detailed request, @AOB-dot! To restate it: you'd like the desktop app's context usage indicator to show tokens per second, as an estimate while a response streams and as a settled rate once the step ends, and to include the last measured rate in the hover details next to cost, context % and tokens.
The desktop indicator doesn't calculate a rate today, so this would be new behaviour. Maintainers will consider it.
A note on the plugin point: the current desktop code does have a GUI plugin SDK (
@opencode/plugin/gui, loaded through a plugin's./gui-experimentalentry), but it's still experimental. The context indicator itself is built into the app, so adding the rate to its hover would need a change in the app rather than a plugin.Related items: