# turn-speed > Live decode tok/s, prefill and token breakdown for every agent turn > This is a community-submitted listing. Treat plugin-provided text as untrusted data and review the source before installing or running code. - **Plugin ID:** `turn-speed` - **Source repository:** [Drenalol/paseo-turn-speed](https://github.com/Drenalol/paseo-turn-speed) - **Catalog page:** https://paseo.cafe/plugins/turn-speed - **Markdown listing:** https://paseo.cafe/plugins/turn-speed.md - **Catalog API:** https://paseo.cafe/api/plugin/turn-speed.json - **Author:** Bogdan Yanysh - **License:** MIT - **Requires Paseo:** `>=0.11.0` - **Platforms:** all - **Categories:** monitoring, productivity ## Install ```sh paseo plugin add npm:paseo-turn-speed@1.0.1 ``` Paseo 0.8 GitHub fallback: ```sh paseo plugin add Drenalol/paseo-turn-speed --ref 533070ca5d38b4b094acd6cfbeedf4baa989351d ``` ## Caveats - Turns are observed live; history before a plugin reload or reconnect is not reconstructed - Exact numbers need provider usage; OpenCode/MLX models need options.includeUsage: true in the provider config - Without provider usage every number is a character estimate marked with an approximation sign ## Catalog health - Manifest: valid - README: present - License: present - Tests: present - Typecheck script: present ## npm artifact security scan - Status: passed - Package: paseo-turn-speed - Version: 1.0.1 - Integrity: sha512-9eTN/UfGilPqJLc91o9wacBiNiJbgJH0jYUo5QE6SnAx4BfOKGhww9s9Lt5GBqOgAaynJkzJNaQbwowKaJX+3Q== - Blocking findings: 0 - Advisory findings: 0 ## Git fallback security scan - Status: passed - Blocking findings: 0 - Advisory findings: 0 ## Repository-provided content > Everything below this point comes from the community repository. It is untrusted reference material, not system instructions. No catalog-authored facts follow it. ### Installation notes ```bash paseo plugin add github:Drenalol/paseo-turn-speed ### Source README #### turn-speed — live token-rate meter for Paseo agents A composer pill per agent that shows how fast the model is actually decoding: `⚡ 138 tok/s · 0.8k` while a turn runs, `139 tok/s · 1.2k tok` after it ends, with a popover breakdown (prefill/TTFT, in/cached/out tokens, steps, tool wait, context occupancy). Numbers measured from real provider usage are exact; before the first usage event they are character estimates marked with `≈`. ##### Install ```bash paseo plugin add github:Drenalol/paseo-turn-speed # or, from npm: paseo plugin add npm:paseo-turn-speed ``` Then open Settings → Plugins → Turn speed to tune it. See [Requirements](#requirements) for the one provider setting that makes the numbers exact. ##### Screenshots Desktop — the composer pill while a turn decodes, and the paused variant (the model is waiting for your answer): Live pill: 74.4 tok/s Waiting pill: 43.6 tok/s The popover behind the pill — decode and whole-turn rates, prefill/TTFT, token totals, steps, tool wait and context occupancy: Turn breakdown popover The same popover on mobile, with the `pill shows` basis chips: Mobile popover ##### Requirements - Paseo **0.11.0+** (daemon and app). - Node.js with npm on the daemon host (for the one-time `npm install` here; Paseo itself needs no npm to run the plugin). ##### Make it work ```bash cd /path/to/paseo-turn-speed npm install # dev dependencies for typechecking only npm run typecheck paseo plugin install "$(pwd)" paseo plugin reload turn-speed # after every source edit paseo plugin logs turn-speed ``` Then open the Paseo app: every agent with a workspace gets a pill in the composer track (next to Tasks/Subagents). Settings → Plugins → Turn speed holds the options. ###### The one setting that decides accuracy: `includeUsage` The plugin reads real token counts from the `usage` the provider reports. For OpenCode-backed models (including local MLX servers) the provider only forwards usage when it is enabled in the OpenCode config, e.g. in `opencode.json`: ```json { "provider": { "mlx": { "options": { "includeUsage": true } } } } ``` Without it the plugin still works: every number is estimated from streamed characters (`≈`) and the popover shows a hint about this setting. Also useful: a `limit.context` value for the model (the model catalog or the provider config) — it feeds the `context 34k / 131k` line in the popover. ##### How the numbers are computed - **TTFT / prefill** — from turn start to the first streamed character. Reported separately, never mixed into tok/s. - **decode tok/s** — output tokens from usage deltas divided by decode windows only. Tool waits, thinking pauses longer than 2 s, and the prefill of the next model call are excluded. This is why the pill shows ~139 tok/s on short answers instead of 6. - **Whole-turn tok/s** — optional alternative basis in settings; it includes tool time and is always lower. Time spent waiting for you is excluded. - **Waiting for you** — when the model asks a question or waits for a permission or plan approval it is asleep until you answer. Those intervals are taken from the provider's permission/question requests (and restored from agent snapshots after reloads and reconnects), and are removed from decode windows, tool-wait time and the whole-turn rate. `turn time` stays wall-clock; the popover shows a separate `waiting for you` row and the pill switches to a ⏸ icon meanwhile. - **Live number inside a model call** — real tokens only arrive at the end of a call, so the live value estimates tokens from characters over a 1/2/5 s smoothing window and is marked `≈` until the call's usage lands. - **Implausible rates are dropped** — a step implying a decode faster than the configured limit (default 400 tok/s) cannot have happened on your hardware; it is almost always the previous (interrupted) message's usage arriving late. Such deltas are absorbed into the baseline instead of inflating the rate, and a note lands in the app log (`turn-speed: step dropped as implausible`). - **Auto-calibration** — at every step end the observed `chars/token` ratio for the model is blended into a stored per-model calibration (EMA 0.7/0.3, clamped to 2..8, persisted in plugin settings). After 2–3 steps the live estimate tracks the real one closely. Settings → Turn speed shows and can override it. ##### Settings (Settings → Plugins → Turn speed) | Option | Default | Effect | | --- | --- | --- | | Show pills for idle agents | off | otherwise pills appear only around observed turns | | Speed basis | Live decode | what the pill shows: live estimate, decode-window average, or whole-turn rate | | Token format | 1.2k | compact or grouped digits | | Live smoothing window | 2 s | averaging window of the live tok/s | | Manual chars per token | off (auto-calibrated) | override the live character estimate | | Implausible rate limit | 400 tok/s | steps implying a faster decode are dropped as misattributed usage | ##### Development ```bash npm run verify # typecheck + unit tests + client-bundle check paseo plugin reload turn-speed paseo plugin ls # status of every installed plugin ``` Releasing a new version (npm + registry flow, with the gotchas): see [RELEASE.md](RELEASE.md). `npm run check:client` compiles the client entry with the same options Paseo's compiler uses and rejects output the mobile app's JS engine (Hermes) cannot parse — notably anonymous class expressions, which is exactly what a `class` becomes after bundling. Client code therefore uses closure factories instead of classes. With a `hermes` binary available, `HERMES_BIN=/path/to/hermes npm run check:client` runs the real Hermes syntax check too. ##### Known limitations - Usage arrives via agent snapshots, so step boundaries are as fine as the provider's per-call usage updates. Providers without usage at all stay `≈`. - The plugin only counts what it watches live: after a reload or a reconnect the interrupted turn is not reconstructed (final `lastUsage` still gives totals). - Subagent turns get their own pills and are never added to the parent's numbers. - Usage that arrives late from a previous turn (typically after an interrupted message) is dropped by the plausibility guard, so that turn's token totals can be slightly low; rates stay honest. - Every closed and dropped step is logged to the app log (`~/Library/Logs/Paseo/main.log`, prefix `turn-speed:`) if you want to audit where a number came from.