Skip to content

feat(cli): show model token speed in chat toolbar - #303

Merged
frostming merged 1 commit into
mainfrom
feat/chat-token-speed
Sep 11, 2026
Merged

frostming merged 1 commit into
mainfrom
feat/chat-token-speed

Conversation

@lodyai

@lodyai lodyai Bot commented Sep 11, 2026

Copy link
Copy Markdown
Contributor

bub chat now shows the latest completed model call's average output speed in the bottom toolbar, for example speed:42.0 token/s. The value persists between turns and displays - when usage is unavailable.

The model runner emits usage and monotonic call duration before tool execution. The CLI computes output tokens per second, including request latency and excluding tool execution, with validation for missing or invalid usage. English and Chinese CLI documentation describe the metric.

Validation:

  • pytest: 343 passed, 1 skipped
  • mypy: no issues in 49 source files
  • Commit hooks, including Ruff and formatting: passed
  • Astro production build: passed via BUB_ASTRO_IMAGE_MODE=build node node_modules/astro/bin/astro.mjs build in website/. The make docs-test wrapper was blocked by local pnpm dependency build approval settings.

@cloudflare-workers-and-pages

Copy link
Copy Markdown

Deploying with  Cloudflare Workers  Cloudflare Workers

The latest updates on your project. Learn more about integrating Git with Workers.

Status Name Latest Commit Preview URL Updated (UTC)
✅ Deployment successful!
View logs
bub a69444f Commit Preview URL

Branch Preview URL
Sep 11 2026, 07:56 AM

@frostming
frostming merged commit afee43f into main Sep 11, 2026
6 checks passed
@frostming
frostming deleted the feat/chat-token-speed branch September 11, 2026 09:42
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant