mirror of
https://github.com/CopilotKit/CopilotKit.git
synced 2026-09-14 16:26:20 +08:00
Maxim
0dd43f2d36
buildRowRenderKeys previously fell back to message.id without consulting
the claimed set. A message whose literal id happened to begin with "tc:"
and matched an earlier-claimed tool-call key would produce duplicate
React keys — React then reconciles a row against the wrong DOM node and
inherits stale state. The docblock's "unique by construction" claim was
also wrong: it relied on a precondition (no raw id begins with "tc:")
that the function did not enforce.
Make uniqueness structural: every assigned key is checked against the
claimed set, and a deterministic numeric suffix (":2", ":3", ...) is
appended when a collision is detected. Normal-path behavior is byte-
identical (no claimed.has(candidate) miss, no claimed.has(message.id)
hit → still assigns candidate-or-id).
Also:
- Correct the docblock; add explicit precondition (caller must
deduplicate) and an order-sensitivity caveat for shared-anchor cases.
- Add a regression test for the pathological tc:-prefixed-id collision.
- Strengthen the existing shared-anchor test to pin first-claimant-wins
precedence via input-order textContent assertions.
- Fix an inaccurate comment that claimed duplicate keys "silently drop"
a row — the real failure mode is wrong-node reconciliation.
- Note the limitations in the changeset prose.
Call-site enumeration: buildRowRenderKeys has a single call site in
CopilotChatMessageView.tsx (inside the rowRenderKeys useMemo). The
input is always deduplicatedMessages, so the precondition holds.
Red-green evidence: with the claimed.has(assigned) else-if removed,
the new pathological-collision test fails with 3 "two children with
the same key" warnings; restoring the guard returns to green.
CopilotKit - React Core
✨ Why CopilotKit?
- Minutes to integrate - Get started quickly with our CLI
- Framework agnostic - Works with React, Next.js, AGUI and more
- Production-ready UI - Use customizable components or build with headless UI
- Built-in security - Prompt injection protection
- Open source - Full transparency and community-driven
🧑💻 Real life use cases
Deploy deeply-integrated AI assistants & agents that work alongside your users inside your applications.
🖥️ Code Samples
Drop in these building blocks and tailor them to your needs.
Build with Headless APIs and Pre-Built Components
// Headless UI with full control
const { visibleMessages, appendMessage, setMessages, ... } = useCopilotChat();
// Pre-built components with deep customization options (CSS + pass custom sub-components)
<CopilotPopup
instructions={"You are assisting the user as best as you can. Answer in the best way possible given the data you have."}
labels={{ title: "Popup Assistant", initial: "Need any help?" }}
/>
// Frontend actions + generative UI, with full streaming support
useCopilotAction({
name: "appendToSpreadsheet",
description: "Append rows to the current spreadsheet",
parameters: [
{ name: "rows", type: "object[]", attributes: [{ name: "cells", type: "object[]", attributes: [{ name: "value", type: "string" }] }] }
],
render: ({ status, args }) => <Spreadsheet data={canonicalSpreadsheetData(args.rows)} />,
handler: ({ rows }) => setSpreadsheet({ ...spreadsheet, rows: [...spreadsheet.rows, ...canonicalSpreadsheetData(rows)] }),
});
Integrate In-App CoAgents with LangGraph
// Share state between app and agent
const { agentState } = useCoAgent({
name: "basic_agent",
initialState: { input: "NYC" }
});
// agentic generative UI
useCoAgentStateRender({
name: "basic_agent",
render: ({ state }) => <WeatherDisplay {...state.final_response} />,
});
// Human in the Loop (Approval)
useCopilotAction({
name: "email_tool",
parameters: [
{
name: "email_draft",
type: "string",
description: "The email content",
required: true,
},
],
renderAndWaitForResponse: ({ args, status, respond }) => {
return (
<EmailConfirmation
emailContent={args.email_draft || ""}
isExecuting={status === "executing"}
onCancel={() => respond?.({ approved: false })}
onSend={() =>
respond?.({
approved: true,
metadata: { sentAt: new Date().toISOString() },
})
}
/>
);
},
});
// intermediate agent state streaming (supports both LangGraph.js + LangGraph python)
const modifiedConfig = copilotKitCustomizeConfig(config, {
emitIntermediateState: [
{
stateKey: "outline",
tool: "set_outline",
toolArgument: "outline",
},
],
});
const response = await ChatOpenAI({ model: "gpt-4o" }).invoke(
messages,
modifiedConfig,
);
🏆 Featured Examples
Documentation
To get started with CopilotKit, please check out the documentation.