Context windowPro

• Type: Component (special)
• Access: Xzero Pro
• Page: https://ui.xzero.co.uk/components/context-window
• Markdown: https://ui.xzero.co.uk/components/context-window/markdown
• Source file: registry/components/context-window/context-window.tsx
• Dependencies: motion, lucide-react, @radix-ui/react-dropdown-menu
• Keywords: special, ai, tokens, chart, motion, new, context window, token usage, llm context, compaction, summarize conversation, prompt tokens, mcp tools tokens, output reserve, ai session, token budget

When to use

• Showing developers or power users what fills a model's context and when it will compact.
• Agent and coding tools that compact long sessions and want the effect to be understandable.
• Docs and onboarding that explain context windows, compaction and output reserves.

When not to use

• A simple quota or plan usage bar; use usage-meter.
• Choosing a model; use model-picker.
• Billing or spend over time; use usage-billing.

Installation

Register both Xzero UI namespaces in your project's components.json:

{
  "registries": {
    "@xzero-ui": "https://mcp.xzero.co.uk/r/{name}.json",
    "@xzero-ui-pro": "https://mcp.xzero.co.uk/r/pro/{name}.json"
  }
}

npx shadcn@4.23.0 add @xzero-ui-pro/context-window

Install xzero-foundation once, and import @/components/xzero/foundation.css in your app root. No Xzero token is used by this snapshot. For sample portraits, photos, fonts, or logos, download https://mcp.xzero.co.uk/install-assets.mjs and run node xzero-install-assets.mjs <receiving-project>.

Usage

import { ContextWindow } from "@/components/xzero/context-window/context-window";

export function SessionContext({ items }) {
  return (
    <ContextWindow
      items={items}
      threshold={0.8}
      onCompact={({ folded, summary }) => console.log(`Folded ${folded} tokens into ${summary}`)}
    />
  );
}

API reference

ContextWindow

A model's context window shown as a fixed budget of 200 cells that fills in reading order: system prompt, tools, files and memory, a summary, then the conversation, followed by free space, with the output reserve held as outlined cells at the end. A dashed line marks the compaction threshold. Send message and Attach file add tokens; crossing the threshold, switching to a smaller model or pressing Compact now folds the older messages into a short summary and the space comes back. A legend lists every part with tokens and percent, adding up to 100%.

Prop	Type	Default	Description
models	ContextModel[]	sampleModels	Models to switch between, each { id, name, window, reserve, mark, color? } with window and reserve in tokens. The sample uses Claude Opus 5.5's real 1M window; reserves and the other two models are sample settings.
defaultModelId	string	–	The model shown first. Defaults to the first model.
onModelChange	(model: ContextModel) => void	–	Called when someone switches models.
items	ContextItem[]	sampleItems	What is in the window: { id, category, label, tokens } with category "system", "tools", "files", "summary" or "messages". Items are grouped by category for the grid, so their order only matters within a category.
threshold	number	0.8	Fraction of the window at which compaction runs on its own.
turns	ContextTurn[]	sampleTurns	Turns that Send message adds, in order, each { label, tokens }: a message plus the tool results and reply it produced.
files	ContextTurn[]	sampleFiles	Files that Attach file adds, in order.
summarize	(folded: ContextItem[]) => number	–	Returns the summary size in tokens for the folded messages. Defaults to about 6% of them, between 4K and 24K.
onCompact	(compaction: ContextCompaction) => void	–	Called after each compaction with { folded, summary, before, after, automatic }.
onItemsChange	(items: ContextItem[]) => void	–	Called with the new items after a send, an attachment or a compaction.
className	string	–	Class on the root section.

Keyboard interactions

Keys	Action
Tab	Moves through the model menu, Send message, Attach file and Compact now.
Enter, Space	Opens the model menu or runs an action.
Arrow up / Arrow down, Enter	In the model menu, moves between models and chooses one.
Escape	Closes the model menu and returns focus to its trigger.

Accessibility

• The grid is one image with a full text description: model, tokens used, every category with its tokens, and the threshold.
• The legend is a list with tokens and percent for each part, so nothing depends on color.
• Every send, attachment, model switch and compaction is announced through a polite status line with an icon and text.
• The model menu is a Radix dropdown with radio items; the trigger names the model and its window.
• Pointer focus draws no ring; keyboard focus shows Xzero's shared ring.

Motion

• New tokens fill cells in a short wave from where the change happened, about 4 to 9ms per cell and never more than 360ms in total.
• Compaction dims the messages in one sweep from oldest to newest, then the summary lands right after the files and the freed cells turn back to free space in the same wave.
• Switching models re-scales every cell in one quick pass from the first cell.
• Token counts and percentages roll to their new values; status lines crossfade in place.
• Pointing at a legend row lights its cells and quiets the rest.
• Reduced motion changes cells and numbers at once and keeps every status line.

Responsive behavior

• On wide containers the legend sits beside the grid; below 640px it moves under the grid and the cells tighten.
• Below 420px the header stacks, with the model menu under the token readout.
• Cells are square and fluid, so the grid always fills its column without horizontal scroll.

Performance

• 200 cells are plain spans whose color changes through CSS transitions with a per-cell delay; nothing re-renders per frame except the rolling numbers.
• The layout is recomputed only when the items or the model change.

Notes for AI

• Feed it the real token usage of a session: system prompt, tool definitions (for example MCP servers), attached files and memory, any summary and the messages.
• Keep reserve equal to the max output you request, so the grid shows the space the reply needs.
• Use onCompact to run your own summarization when the threshold is crossed; pass summarize to report the real summary size.
• The 200 cell grid is fixed, so each cell is window / 200 tokens; the note under the grid says how many.

Related

• Model picker: A model picker in one quiet pill: open it to choose from featured models with a one line note each, set the reasoning effort, or browse every other model by provider, and the pill swaps to your choice in place.
• AI composer: The prompt box at the bottom of an AI app: files upload in place, / opens commands, @ inserts mentions, a model and effort menu sits in the toolbar, and the send button turns into a stop control ringed by the reply's progress.
• Agent run: A single card that follows one AI coding agent through a task: steps stream in with the live one shimmering, tool calls open in place, and the agent stops on a two-file diff for you to approve or send back before it writes. When the run ends, the steps fold into one line and a result shows the files changed, the checks that passed and a pull request button.
• Usage meter: Show what fills an allowance and how close it is to the limit.
• AI chat: A full-screen AI chat where answers stream in as markdown with folding reasoning, tool chips and cited sources. People can switch chats and models, edit or retry a message into versions, rate replies and stop a reply mid-stream.

Also in ai

• Agent status: A compact live status pill for a running AI agent: the agent's mark in a live ring, the current activity and an elapsed timer, opening into the steps so far.
• Tool call: A tool call row for agent transcripts: the tool's mark and the call in plain words, a live state while it runs, and the input and output a click away, with approval and retry when needed.
• Agent plan: The plan an agent writes before it acts: edit, reorder or add steps while it is a draft, then watch it work through them as a live checklist.
• Agent timeline: A compact timeline of one orchestrated agent run: the orchestrator and its subagents share a time axis, handoffs draw in between rows, and a playhead replays thinking, tool calls and waiting while the header counts time, tokens and cost. Hover a span for what it did, or click it to trace its handoff path.
• Reasoning block: The collapsible thinking block of an AI reply. While the model thinks, a shimmering label counts the seconds and the latest reasoning streams underneath. When it finishes, it folds to "Thought for 7s" and opens to show the full reasoning as calm steps with headings.
• Source cards: A row of cited sources under an AI answer where cards stream in with real site marks while the model searches, the overflow collapses into a stack of favicons, hovering lifts a preview with the passage, and an inline [n] citation highlights its card.
• Model card: A model details card where switching models rolls every price, limit and score in place, a token slider estimates monthly cost live, and benchmark bars show each model's rank on hover. Compare crossfades to a side-by-side table against any rival with the better values marked, and the card never changes size.
• AI workflow: A Linear-style AI workflow card where a Gmail trigger, a Claude step, a branch and Slack and Linear actions sit on one hairline rail, and a test run glides down it, opening each step's output inline. Steps are added from a compact command menu with real app marks.
• Code suggestion: An AI code edit suggestion where the model's proposed changes stream into a small editor panel as inline diff hunks, and you accept or reject each one, or all at once with Cmd+Enter. Accepted hunks fold into the file with a smooth height change.
• Ghost text: An inline AI autocomplete where muted ghost text continues your sentence exactly at the caret and Tab turns it solid in place. Cmd+Right takes it one word at a time, Escape fades it away, and a calm chip shows the model behind it.
• Image generation: An image generation card where four images resolve as a pixel mosaic, from coarse colour blocks to full detail under a soft shimmer, each with its own progress ring. Pick one to upscale with a sweeping pixel band, vary or download it, with real provider marks and a built-in simulation.
• Dictation button: A chat composer with voice input, where the mic springs into a recording pill with a smooth live waveform, a timer, and cancel and insert buttons. Words stream into the field as you speak, muted until the recognizer settles them.
• Speech player: A read-aloud player for AI replies. The Read aloud button in the message's action row turns into a compact player with play, a scrubbable progress bar, speed and a voice picker, and a highlight follows the spoken word through the reply, karaoke style.
• Meeting summary: An AI meeting notes card: the header shows the Google Meet or Zoom mark, the attendees and the duration. Summary, Decisions and Action items stream in after a short summarizing pass. Hover any line to see the transcript quote it came from, then check off action items or send them to Linear or Notion.
• Reply draft: An AI email reply drafter where Claude streams a reply under a received Gmail message. Quick replies steer a fresh draft, tone and length rewrite it with a single crossfade, and you can edit the finished draft before you insert it.
• Agent handoff: A support conversation where an AI assistant hands off to a person. When it transfers, a card shows the summary it passes to the team and the typical wait. The person then joins and takes over, and a thin timeline on the left marks each step.
• PII redaction: A guardrail card where personal data is redacted before the prompt reaches the model. Scan marks each name, email, phone number and card with its type and swaps it for a placeholder like [EMAIL_1]. The safe prompt travels to Claude, and the reply comes back with the original values put back for the person.
• Response feedback: A feedback control for AI replies where thumbs down opens an inline panel with reason chips and an optional note, thumbs up fills and asks what was good, and a submit shows a short thank-you before folding back into the row.
• LLM cost calculator: A pricing calculator for LLM workloads. Set tokens per request, requests per day and prompt caching, and eight current models re-rank by monthly cost. Bars glide and prices roll as you drag.
• Provider keys: A settings card for bring-your-own-key AI products. Each provider row shows its real mark, the masked key, a status and when the key was last used. You can reveal a key for five seconds, copy, rotate or remove it with undo. Adding or rotating a key opens an inline form that checks the format as you type, then tests the connection before saving.
• Generation stats: A live stats strip for a streaming LLM response where time to first token, speed with a sparkline, output tokens and cost count up in tabular numerals beside the model's real mark, then settle and open into a latency and token cost breakdown.
• AI translate: A message card where picking a language streams the AI translation in place, sentence by sentence over the dimmed original, with a detected-language chip, a Show original toggle and a status line credited to the model's mark.
• TL;DR toggle: An article card with a Full, Summary and Key points switch and a length slider. Switching streams an AI summary in place of the article as the card's height springs to fit, and each key point links back to the paragraph it came from, which gets scrolled to and highlighted.
• Connector setup: A "Connect your tools" card for an AI assistant. Each app connects inline: it redirects, authorizes and runs a first sync with a progress hairline, then lists the scopes it was granted and offers Disconnect with an inline confirm.
• Smart form fill: A paste-to-fill form card where AI reads an email signature or messy notes and fills a contact field by field. Each value flashes in with a confidence dot, its source lights up in the pasted text, low-confidence guesses ask for review, and Undo puts the old values back.
• Enrich column: An AI enrichment column for a data table, where one prompt runs down every row and each cell shimmers while it works, then settles into a value with its source or a failure you can retry.
• Ticket router: A support ticket router where messages from Gmail, Intercom, Slack and Zendesk come in one at a time. An AI classifier labels each one with intent, sentiment and confidence, and the ticket moves into a team lane with an assignee. Low confidence tickets wait in a review lane, and one click there routes them to the suggested team.
• Ask your data: A natural language to chart card: you ask a question, PostgreSQL streams into a collapsible, syntax highlighted panel, the query runs with a rolling row count, and the answer builds as stacked bars, lines or a table, with a one line insight streamed in underneath.
• Agent cursor: A live document where Claude edits like a collaborator. Its labeled cursor comes out of its avatar, selects a paragraph and streams in a rewrite, adds a heading and fixes a typo, while a teammate's cursor reads along. Changes stay tinted until someone accepts or undoes them from a floating review bar.
• Provider status: A status card for the AI providers your product depends on. Each row shows the provider's real mark, its health as an icon and label, p50 latency and a 30-day uptime bar with a tooltip for each day. An incident row expands into its timeline of updates, and the card checks again on a visible countdown.
• Training run: A fine-tuning job card where a live train and validation loss curve draws across a fixed step axis that doubles as the epoch progress bar. It shows the learning rate, elapsed time, ETA and the latest evals and checkpoints, has Pause and Cancel while it runs, and ends in results with a Deploy button.
• AI command: A Cmd+K command palette with an AI mode. Search pages and actions, or press Tab to ask a question: the answer streams inside the palette with numbered sources, and the next steps it suggests, like filing a Linear issue or opening a Notion doc, run straight from the list.
• Starter prompts: A greeting and a grid of starter cards for the empty state of an AI app. The cards are grouped into Write, Code, Analyze and Plan tabs, and a shuffle swaps them with a short staggered crossfade. Picking a card fills the composer, and cards that use a connected app show its mark (Gmail, GitHub, Notion, Linear, Google Calendar).
• AI mascot: A small assistant character, a soft pebble with pill eyes and a companion dot, that shows what the AI is doing. It breathes and glances when idle, leans in to listen, looks up while the dot orbits its head, reads along the line it writes, squints with a sparkle when done and shakes once with worried brows on an error.
• Image reveal: An image generation canvas where a soft, blurred preview made from the image's own colors sharpens top to bottom behind a soft-edged band. It works the way ChatGPT, Midjourney and Gemini show images forming, with fine film grain, a translucent progress pill and calm queued and error states.
• AI spark: A brand-quality animated spark mark. Four tapered rays and four lighter diagonals breathe at rest, ripple while thinking, pulse like a heartbeat while writing, then gather and settle when done. Every status change blends from the pose the mark is already in.
• Pixel mascot: A pixel-art robot that shows what an AI assistant is doing. It idles, thinks, types, celebrates and errors in frame-stepped sprite animations, and stays crisp at every integer size from 24px to 192px.
• Ghost mascot: A floating ghost mascot whose soft sheet ripples at the hem while it hovers. It blinks when idle, turns toward you to listen, fades a little translucent while thinking, draws a tiny pen line while writing, smiles with a sparkle when done and wobbles once on an error.
• Cube mascot: An isometric cube mascot where three shaded faces and a painted-on face show what the assistant is doing. It turns a quarter turn in eased steps while thinking, prints lines onto the floor while writing, settles with a sparkle when done, and shakes once on error.
• Tone tuner: A brand voice card where two sliders (formality and detail) and Friendly, Confident and Empathetic chips rewrite a customer reply. Each changed sentence crossfades in place, new words can be highlighted against the original, and Copy takes the current version.
• Upgrade prompt: An upgrade nudge for the moment someone hits a limit. It shows a usage meter at 50 of 50 AI credits, a rolling price with a monthly and yearly toggle, three concrete unlocks with real model marks, and Upgrade or Maybe later. Upgrading leads into a success state with the new limits, and the card never changes size between states.
• Referral card: A give-and-get referral card where people copy or share their invite link, invite friends by email as chips, and watch invites move from invited to signed up to earned, with the credit total counting up and a milestone reward unlocking.
• Trial banner: A trial status banner where a ring counts down the days left, the copy names what the workspace loses, and the upgrade path is one click away. It comes as a slim banner, a sidebar card or a header pill. It shifts to a warning tone in the last days, has expired and upgraded states, and folds into the pill when dismissed or snoozed.
• Team switcher: A workspace switcher like Linear, Vercel or Slack. The trigger shows the current workspace's logo and plan. The menu has search, your role in each workspace and a Cmd+1 to 9 shortcut for each, and lets you create or join a workspace inline. A highlight glides between rows, and switching crossfades the trigger through a short loading state.
• Live visitors: A realtime visitors card where the live count rolls digit by digit, new arrivals ping in on a dotted world map, the top pages reorder with bars, and signups and upgrades tick in with country flags.
• Social proof toast: A stack of social proof notifications for landing and pricing pages, where recent trials, upgrades and verified purchases from people and companies arrive every few seconds. The stack pauses and fans out on hover, and visitors can dismiss any toast.
• Install snippet: A "get started in 30 seconds" card where framework tabs, three numbered steps and highlighted snippets take a developer from install to first event. Generate key wipes a fresh API key into the placeholder in place.

Guidance for AI tools

Context window: An AI context window as a grid of 200 cells: the system prompt, tools, files, summary and messages fill it in order, a threshold row marks where compaction starts, and sending a message, attaching a file or compacting shows exactly how much still fits. Follow the declared prop types and do not invent props. Keep keyboard access, reduced motion support, and both light and dark themes intact when adapting it.

Full library index: https://ui.xzero.co.uk/llms.txt