ui
Generative UI in the chat: the report tool, where you write a small React view against log's kit (in the spirit of Lynx workspaces) and log draws it with data from log.db, or send just data for a starter view; text everywhere else.
Written by bun run docs:build from the code, the skills and AGENTS.md. Not edited by hand: change the command's usage, its skill or the rule, and rebuild.
The tools in this guide
Each tool's own description carries its full usage, notes, live line and rules; logGet gives its exact inputs and a call that works.
| Tool | What it does | Usage |
|---|---|---|
report | Show a view | |
reportData | The numbers behind a report, from log.db only | log report data --source <twitterDmsBySender|dmsBySender|identityProfile|waitingOnYou> [--platform <p>] [--account <accountName>] [--since <7d|4w|12h|2026-11-01>] [--limit <n>] [--userId <id>] [--handle <handle>] [--json] |
The work, step by step: report
From skills/report/SKILL.md.
report
report is log's generative UI. You decide what the person should see and write it as a small React view. log compiles it and draws it in the chat, with the data read from log.db in the same call.
- Where it draws: inline in an MCP Apps host (Claude, ChatGPT, Cursor), and in Hermes Desktop when the result ends with a
::logapp{tool="report" view="…"}line: put it in your reply alone. Elsewhere (Claude Code, Codex) it is text: show it as is. - Why it looks the way it does: the kit follows Lynx's workspace kit (MIT): a quiet canvas, plain blocks, big light numbers, and Geist. It is a starting point that informs; the content makes it good.
One call, no code
{ "title": "Who's been messaging you on X", "subtitle": "last 30 days", "data": { "dms": { "source": "twitterDmsBySender", "since": "30d" } } }This draws the starter view, which shows:
- headline stats, each with a line of what it means (top 10 share, new this week, busiest day)
- messages per day
- who messages most
- a table of people with their 30-day activity, when they last wrote and what they said
log.db holds only what has been read. If the inbox may be behind, read it with twitterDms first (rule 160).
The data sources
Each entry in data names one source. Every source reads log.db only, with no platform call.
source | Inputs | What it hands the view |
|---|---|---|
twitterDmsBySender | account?, since?, limit? | Who messaged the X account in one-to-one DMs: people, counts, activity, latest message |
dmsBySender | platform, account?, since?, limit? | The same, for any platform with chats in log.db. A platform with none is refused with reportSourceNoData |
identityProfile | platform, and userId or handle | One person: name, handle, bio, follower count, verified, extra (location, following, posts, premium and so on) and the avatar as a data URI. Drawn as a person card with no code. A person with no stored profile is refused with identityProfileMissing |
{ "title": "Who is this", "data": { "person": { "source": "identityProfile", "platform": "twitter", "handle": "fakeBird" } } }Profiles are kept when a session check or twitterFollowers sees them; nothing fetches a profile just to draw it.
Your own view
Send code with the same data, and shape the view to the question. A question about one person gets that person; a question about the week gets the week. Start from what would help the person decide or act, and keep it short.
import { Page, Card, Grid, Stat, Bars, Quote, Avatar, Row, Stack, Badge, Time, fmt } from "log";
export default function App({ data, title, subtitle }) {
const r = data.dms;
const p = r.senders[0];
return (
<Page title={title} subtitle={subtitle}>
<Card>
<Row gap={14}>
<Avatar name={p.name} size={48} />
<Stack gap={2} style={{ flex: 1 }}><strong>{p.name}</strong><span className="sb-stat-hint">@{p.handle}</span></Stack>
<Badge tone="accent">{Math.round((p.count / r.messages) * 100)}% of your DMs</Badge>
</Row>
</Card>
<Grid min={150}>
<Stat label="Messages" value={fmt(p.count)} hint={`rank 1 of ${r.people}`} />
<Stat label="Last message" value={<Time value={p.lastAt} />} />
</Grid>
<Card title="Latest message"><Quote>{p.lastMessage}</Quote></Card>
<Card title="How they compare"><Bars data={r.senders.slice(0, 5).map((s) => ({ label: s.name, value: s.count }))} unit="msgs" /></Card>
</Page>
);
}-
Imports: only from
"log"and"react", at the top.import()is refused withviewImportRefused. End withexport default function App({ data, title, subtitle }). -
Layout:
Page { title, subtitle, actions }Card { title, actions, pad }; usepad={false}around aTableGrid { min }RowandStack, each{ gap }
-
Numbers:
Stat { label, value, hint, tone }Badge { tone: neutral|good|bad|warn|accent }fmt(n)formats a number, andTime { value }shows how long ago
-
Charts:
Bars { data: [{ label, value }], unit }for ranked listsBarChartfor columns over timeLineChart { series: [{ name, values }], labels }Sparkline { values, width }
-
People and words:
Avatar { name, size, src },srcadata:image/URI such as a profile'savatarQuoteIcon { name }, with Font Awesome 6 names in camelCase (xTwitter,discord,message,users,clock)
-
Detail:
Table { rows, columns: [{ key, title, render, align, width }], limit }Tabs,Details,Empty
-
Your own CSS: plain CSS works. Use the
--sb-*variables (--sb-text,--sb-muted,--sb-accent,--sb-surface), which follow light and dark mode. -
Live data:
useTool(name, args)calls a log read tool from inside the view and returns{ data, loading, error, reload }.- Wrap it in
<Query q={…}>{(data) => …}</Query>. - Only call read tools.
-
Interaction, from Lynx:
- Pages:
RouteswithLinkandBackLink(useRoutegives the path), so a table can open a page per person. - Asking:
AskButton { prompt }andFollowUps { prompts }put a question into the chat, andaskAgent(text)does it from code. End an overview with 2 or 3 follow-ups. - Pointing:
Pointable { about }andtellAgent(text)tell the agent what the person is looking at without sending a message. - Forms:
Button,Input,Select,Textarea,Field,ModalanduseAction(fn). - Also
Markdown,FullscreenButton,downloadCsv(name, rows)andopenExternal(url).ErrorNoteoffers "Ask the agent to fix it". - A view never sends anything itself: an ask goes through the chat, where every send gate still applies.
- Pages:
A view that doesn't compile, imports from anywhere else, or breaks while drawing is refused with reportFieldInvalid, with the line or error to fix.
The older blocks list (heading, text, stat, barChart, lineChart, table, personList, callout) still works and is drawn with the same kit.
After it is drawn
In an MCP Apps host the person already sees the view, so say what it means in a sentence or two, not the numbers again.
How it is built
- Code:
src/mcp/apps/report/viewholds:- the kit (
kit.tsx,kit.css) - the widget that runs the view in the chat (
widget.tsx) - the server side: the sucrase compile and the text version (
server.tsx) - the starter views (
starters/)
- the kit (
- Data: the sources are one registry,
REPORT_SOURCESinsrc/mcp/apps/report/helpers/sources.ts. A new source is one entry there (schema, reader, starter, text). - What the page loads: nothing from the internet; React, the kit and Geist are inlined.
The rules these tools fall under
Each by its number and first line. The full text is in AGENTS.md (log://agents); the core rules are in full in getGuide({ topic: "logMcpInstructions" }).
- Rule 30. Complete the authorized task.
- Rule 38. Do not introduce discussions of Meta/Facebook rules, terms, eligibility or account ownership unless The owner raises them.
- Rule 39. Use only the scope, options and intent The owner stated or implied.
- Rule 40. Do not propose physical infrastructure unless The owner asks.
- Rule 41. Paid work must stay within the authorized task and spend.
- Rule 134. Existing workspace log.db is the native private record/coordination foundation.
- Rule 154. Show people/chats by meaningful names and handles; keep routing ids internal unless needed for the specific technical artifact.
- Rule 160. Answer eligible chat reads from log.db when the owner is live, caught up and the needed history is present/backfilled.