cd /news/ai-tools/kde-plasma-ai-quota-hud-my-arch-linu… · home topics ai-tools article
[ARTICLE · art-74547] src=promptcube3.com ↗ pub= topic=ai-tools verified=true sentiment=· neutral

KDE Plasma AI Quota HUD: My Arch Linux Setup

A developer built a KDE Plasma panel HUD for Arch Linux that tracks AI quota usage across Claude, Codex, Gemini, and DeepSeek using four circular indicators, after fixing a bug caused by relying on positional data in API responses. The system now uses duration-based identification and state validation to handle schema changes from providers like Codex.

read2 min views1 publishedJul 26, 2026
KDE Plasma AI Quota HUD: My Arch Linux Setup
Image: Promptcube3 (auto-discovered)

ClaudeCode, Codex, Gemini, and DeepSeek on Arch Linux is a logistical nightmare. When you're deep into a complex task with massive context and an hour of iteration, the last thing you want is to hit a rate limit mid-

git rebase

. To solve this, I built a HUD for the KDE panel that tracks remaining room and reset times for each agent via four circular indicators.## The "Token-Week" Problem

The industry has created a bizarre new unit of measurement: the token-hour or token-week. Every provider does it differently:

Claude: Uses rolling hour/day windows.Codex: Reports specific plan windows.Requires local request estimation.Gemini:Operates on a monetary balance.DeepSeek:

I've essentially turned my panel into a dashboard of "donuts." A full ring means the agent is ready; an empty one means it's time to switch models. Hovering provides the exact reset time, so I don't have to leave my terminal to check if I've exhausted my limits.

Technical Pivot: Data over Position #

My initial deployment failed because I relied on the position of data in the API response. For Codex, I assumed the first window returned was the 5-hour limit and the second was the weekly limit.

When Codex changed their schema and stopped reporting the short window, my logic broke. The widget started labeling a 7-day window as "5h" because it was the first item in the list. To fix this for a more robust AI workflow, I implemented two changes:

  1. Duration-based Identification: The system now identifies windows by their actual length. Short durations are flagged as sessions; long durations are flagged as weekly limits.

  2. State Validation: I decoupled "failed queries" from "missing data." If a query fails, the HUD preserves the last cached value. If a query succeeds but a window is missing, the HUD removes that window from the state entirely.

This prevents the "ghost value" bug where a depleted quota appears active just because the API call timed out. For anyone building a custom LLM agent monitor, avoid positional indexing at all costs—API schemas shift too often.

Next SEO Automation vs. Domain Authority: A Reality Check →

── more in #ai-tools 4 stories · sorted by recency
── more on @kde plasma 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/kde-plasma-ai-quota-…] indexed:0 read:2min 2026-07-26 ·