Glove

Glove Framework — Development Guide

You are an expert on the Glove framework. Use this knowledge when writing, debugging, or reviewing Glove code.

What Glove Is

Glove is an open-source TypeScript framework for building AI-powered applications. Users describe what they want in conversation, and an AI decides which capabilities (tools) to invoke. Developers define tools and renderers; Glove handles the agent loop.

Repository: https://github.com/porkytheblack/glove Docs site: https://glove.dterminal.net License: MIT (dterminal)

Package Overview

Most projects need just glove-react + glove-next. glove-core is included as a dependency of glove-react.

Architecture at a Glance

User message → Agent Loop → Model decides tool calls → Execute tools → Feed results back → Loop until done
                                                          ↓
                                                   Display Stack (pushAndWait / pushAndForget)
                                                          ↓
                                                   React renders UI slots

Core Concepts

• Agent — AI coordinator that replaces router/navigation logic. Reads tools, decides which to call.
• Tool — A capability: name, description, inputSchema (Zod), do function, optional render + renderResult.
• Display Stack — Stack of UI slots tools push onto. pushAndWait blocks tool; pushAndForget doesn't.
• Display Strategy — Controls slot visibility lifecycle: "stay", "hide-on-complete", "hide-on-new".
• renderData — Client-only data returned from do() that is NOT sent to the AI model. Used by renderResult for history rendering.
• Adapter — Pluggable interfaces for Model, Store, DisplayManager, and Subscriber. Swap providers without changing app code.
• Context Compaction — Auto-summarizes long conversations to stay within context window limits. The store preserves full message history (so frontends can display the entire chat), while Context.getMessages() splits at the last compaction summary so the model only sees post-compaction context. Summary messages are marked with is_compaction: true.

Quick Start (Next.js)

1. Install

pnpm add glove-core glove-react glove-next zod

2. Server route

// app/api/chat/route.ts
import { createChatHandler } from "glove-next";

export const POST = createChatHandler({
  provider: "anthropic",     // or "openai", "openrouter", "gemini", etc.
  model: "claude-sonnet-4-20250514",
});

Set ANTHROPIC_API_KEY (or OPENAI_API_KEY, etc.) in .env.local.

3. Define tools with defineTool

// lib/glove.tsx
import { GloveClient, defineTool } from "glove-react";
import type { ToolConfig } from "glove-react";
import { z } from "zod";

const inputSchema = z.object({
  question: z.string().describe("The question to display"),
  options: z.array(z.object({
    label: z.string().describe("Display text"),
    value: z.string().describe("Value returned when selected"),
  })),
});

const askPreferenceTool = defineTool({
  name: "ask_preference",
  description: "Present options for the user to choose from.",
  inputSchema,
  displayPropsSchema: inputSchema,       // Zod schema for display props
  resolveSchema: z.string(),             // Zod schema for resolve value
  displayStrategy: "hide-on-complete",   // Hide slot after user responds
  async do(input, display) {
    const selected = await display.pushAndWait(input);  // typed!
    return {
      status: "success" as const,
      data: `User selected: ${selected}`,         // sent to AI
      renderData: { question: input.question, selected },  // client-only
    };
  },
  render({ props, resolve }) {           // typed props, typed resolve
    return (
      <div>
        <p>{props.question}</p>
        {props.options.map(opt => (
          <button key={opt.value} => resolve(opt.value)}>
            {opt.label}
          </button>
        ))}
      </div>
    );
  },
  renderResult({ data }) {               // renders from history
    const { question, selected } = data as { question: string; selected: string };
    return <div><p>{question}</p><span>Selected: {selected}</span></div>;
  },
});

// Tools without display stay as raw ToolConfig
const getDateTool: ToolConfig = {
  name: "get_date",
  description: "Get today's date",
  inputSchema: z.object({}),
  async do() { return { status: "success", data: new Date().toLocaleDateString() }; },
};

export const gloveClient = new GloveClient({
  endpoint: "/api/chat",
  systemPrompt: "You are a helpful assistant.",
  tools: [askPreferenceTool, getDateTool],
});

4. Provider + Render

// app/providers.tsx
"use client";
import { GloveProvider } from "glove-react";
import { gloveClient } from "@/lib/glove";

export function Providers({ children }: { children: React.ReactNode }) {
  return <GloveProvider client={gloveClient}>{children}</GloveProvider>;
}

// app/page.tsx — using <Render> component
"use client";
import { useGlove, Render } from "glove-react";

export default function Chat() {
  const glove = useGlove();

  return (
    <Render
      glove={glove}
      strategy="interleaved"
      renderMessage={({ entry }) => (
        <div><strong>{entry.kind === "user" ? "You" : "AI"}:</strong> {entry.text}</div>
      )}
      renderStreaming={({ text }) => <div style={{ opacity: 0.7 }}>{text}</div>}
    />
  );
}

Or use useGlove() directly for full manual control:

// app/page.tsx — manual rendering
"use client";
import { useState } from "react";
import { useGlove } from "glove-react";

export default function Chat() {
  const { timeline, streamingText, busy, slots, sendMessage, renderSlot, renderToolResult } = useGlove();
  const [input, setInput] = useState("");

  return (
    <div>
      {timeline.map((entry, i) => (
        <div key={i}>
          {entry.kind === "user" && <p><strong>You:</strong> {entry.text}</p>}
          {entry.kind === "agent_text" && <p><strong>AI:</strong> {entry.text}</p>}
          {entry.kind === "tool" && (
            <>
              <p>Tool: {entry.name} — {entry.status}</p>
              {entry.renderData !== undefined && renderToolResult(entry)}
            </>
          )}
        </div>
      ))}
      {streamingText && <p style={{ opacity: 0.7 }}>{streamingText}</p>}
      {slots.map(renderSlot)}
      <form => { e.preventDefault(); sendMessage(input.trim()); setInput(""); }}>
        <input value={input} => setInput(e.target.value)} disabled={busy} />
        <button type="submit" disabled={busy}>Send</button>
      </form>
    </div>
  );
}

Display Stack Patterns

pushAndForget — Show results (non-blocking)

async do(input, display) {
  const data = await fetchData(input);
  await display.pushAndForget({ input: data }); // Shows UI, tool continues
  return { status: "success", data: "Displayed results", renderData: data };
},
render({ data }) {
  return <Card>{data.title}</Card>;
},
renderResult({ data }) {
  return <Card>{(data as any).title}</Card>;  // Same card from history
},

pushAndWait — Collect user input (blocking)

async do(input, display) {
  const confirmed = await display.pushAndWait({ input }); // Pauses until user responds
  return {
    status: "success",
    data: confirmed ? "Confirmed" : "Cancelled",
    renderData: { confirmed },
  };
},
render({ data, resolve }) {
  return (
    <div>
      <p>{data.message}</p>
      <button => resolve(true)}>Yes</button>
      <button => resolve(false)}>No</button>
    </div>
  );
},
renderResult({ data }) {
  const { confirmed } = data as { confirmed: boolean };
  return <div>{confirmed ? "Confirmed" : "Cancelled"}</div>;
},

Display Strategies

SlotRenderProps

Tool Definition

defineTool (recommended for tools with UI)

import { defineTool } from "glove-react";

const tool = defineTool({
  name: string,
  description: string,
  inputSchema: z.ZodType,              // Zod schema for tool input
  displayPropsSchema?: z.ZodType,      // Zod schema for display props (recommended for tools with UI)
  resolveSchema?: z.ZodType,           // Zod schema for resolve value (omit for pushAndForget-only)
  displayStrategy?: SlotDisplayStrategy,
  requiresPermission?: boolean,
  do(input, display): Promise<ToolResultData>,  // display is TypedDisplay<D, R>
  render?({ props, resolve, reject }): ReactNode,
  renderResult?({ data, output, status }): ReactNode,
});

Key points:

• do() should return { status, data, renderData } — data goes to model, renderData stays client-only
• render() gets typed props (matching displayPropsSchema) and typed resolve (matching resolveSchema)
• renderResult() receives renderData for showing read-only views from history
• displayPropsSchema is optional but recommended — tools without display should use raw ToolConfig

ToolConfig (for tools without UI or manual control)

interface ToolConfig<I = any> {
  name: string;
  description: string;
  inputSchema: z.ZodType<I>;
  do: (input: I, display: ToolDisplay) => Promise<ToolResultData>;
  render?: (props: SlotRenderProps) => ReactNode;
  renderResult?: (props: ToolResultRenderProps) => ReactNode;
  displayStrategy?: SlotDisplayStrategy;
  requiresPermission?: boolean;
}

ToolResultData

interface ToolResultData {
  status: "success" | "error";
  data: unknown;          // Sent to the AI model
  message?: string;       // Error message (for status: "error")
  renderData?: unknown;   // Client-only — NOT sent to model, used by renderResult
}

Important: Model adapters explicitly strip renderData before sending to the AI. This makes it safe to store sensitive client-only data (e.g., email addresses, UI state) in renderData.

<Render> Component

Headless render component that replaces manual timeline rendering:

import { Render } from "glove-react";

<Render
  glove={gloveHandle}           // return value of useGlove()
  strategy="interleaved"        // "interleaved" | "slots-before" | "slots-after" | "slots-only"
  renderMessage={({ entry, index, isLast }) => ...}
  renderToolStatus={({ entry, index, hasSlot }) => ...}
  renderStreaming={({ text }) => ...}
  renderInput={({ send, busy, abort }) => ...}
  renderSlotContainer={({ slots, renderSlot }) => ...}
  as="div"                      // wrapper element
  className="chat"
/>

Features:

• Automatic slot visibility based on displayStrategy
• Automatic renderResult rendering for completed tools with renderData
• Interleaving: slots appear inline next to their tool call
• Sensible defaults for all render props

GloveHandle Interface

The interface consumed by <Render>, returned by useGlove():

interface GloveHandle {
  timeline: TimelineEntry[];
  streamingText: string;
  busy: boolean;
  slots: EnhancedSlot[];
  sendMessage: (text: string, images?: { data: string; media_type: string }[]) => void;
  abort: () => void;
  renderSlot: (slot: EnhancedSlot) => ReactNode;
  renderToolResult: (entry: ToolEntry) => ReactNode;
  resolveSlot: (slotId: string, value: unknown) => void;
  rejectSlot: (slotId: string, reason?: string) => void;
}

useGlove Hook Return

TimelineEntry

type TimelineEntry =
  | { kind: "user"; text: string; images?: string[] }
  | { kind: "agent_text"; text: string }
  | { kind: "tool"; id: string; name: string; input: unknown; status: "running" | "success" | "error"; output?: string; renderData?: unknown };

type ToolEntry = Extract<TimelineEntry, { kind: "tool" }>;

Supported Providers

Pre-built Tool Registry

Available at https://glove.dterminal.net/tools — copy-paste into your project:

• confirm_action — Yes/No confirmation dialog
• collect_form — Multi-field form
• ask_preference — Single-select preference picker
• text_input — Free-text input
• show_info_card — Info/success/warning card (pushAndForget)
• suggest_options — Multiple-choice suggestions
• approve_plan — Step-by-step plan approval

Supporting Files

For detailed API reference, see api-reference.md. For example patterns from real implementations, see examples.md.

Common Gotchas

1. model_response_complete vs model_response: Streaming adapters emit model_response_complete, not model_response. Subscribers must handle both.
2. Closure capture in React hooks: When re-keying sessions, use mutable let currentKey = key to avoid stale closures.
3. React useEffect timing: State updates don't take effect in the same render cycle — guard with early returns.
4. Browser-safe imports: glove-core barrel exports include native deps (better-sqlite3). For browser code, import from subpaths: glove-core/core, glove-core/glove, glove-core/display-manager, glove-core/tools/task-tool.
5. Displaymanager casing: The concrete class is Displaymanager (lowercase 'm'), not DisplayManager. Import it as: import { Displaymanager } from "glove-core/display-manager".
6. createAdapter stream default: stream defaults to true, not false. Pass stream: false explicitly if you want synchronous responses.
7. Tool return values: The do function should return ToolResultData with { status, data, renderData? }. data goes to the AI; renderData stays client-only.
8. Zod .describe(): Always add .describe() to schema fields — the AI reads these descriptions to understand what to provide.
9. displayPropsSchema is optional but recommended: defineTool's displayPropsSchema is optional, but recommended for tools with display UI — tools without display should use raw ToolConfig instead.
10. renderData is stripped by model adapters: Model adapters explicitly exclude renderData when formatting tool results for the AI, so it's safe for client-only data.