Merge d007bd0a6f into 0ea8924727

* Test for image token usage in llama.cpp so we can more appropriately decide how many frames to include

* Limit based on frames per second

* handle zone case sensitivity

* Improve formatting

* Add observations field so model can build CoT before outputting used fields

.gitignore

@@ -22,3 +22,8 @@ core
 !/web/**/*.ts
 .idea/*
 .ipynb_checkpoints
+
+# Auto-generated Docker Compose Generator config files
+docs/src/components/DockerComposeGenerator/config/devices.ts
+docs/src/components/DockerComposeGenerator/config/hardware.ts
+docs/src/components/DockerComposeGenerator/config/ports.ts

docs/docs/frigate/installation.md

@@ -4,6 +4,8 @@ title: Installation
 ---
 
 import ShmCalculator from '@site/src/components/ShmCalculator'
+import DockerComposeGenerator from '@site/src/components/DockerComposeGenerator'
+
 
 Frigate is a Docker container that can be run on any Docker host including as a [Home Assistant App](https://www.home-assistant.io/apps/). Note that the Home Assistant App is **not** the same thing as the integration. The [integration](/integrations/home-assistant) is required to integrate Frigate into Home Assistant, whether you are running Frigate as a standalone Docker container or as a Home Assistant App.
 
@@ -71,6 +73,13 @@ Users of the Snapcraft build of Docker cannot use storage locations outside your
 
 :::
 
+### Docker Compose Generator
+
+Generate a Frigate Docker Compose configuration based on your hardware and requirements.
+
+<DockerComposeGenerator/>
+
+
 ### Calculating required shm-size
 
 Frigate utilizes shared memory to store frames during processing. The default `shm-size` provided by Docker is **64MB**.

docs/package-lock.json

@@ -14,9 +14,11 @@
         "@docusaurus/theme-mermaid": "^3.7.0",
         "@inkeep/docusaurus": "^2.0.16",
         "@mdx-js/react": "^3.1.0",
+        "@types/js-yaml": "^4.0.9",
         "clsx": "^2.1.1",
         "docusaurus-plugin-openapi-docs": "^4.5.1",
         "docusaurus-theme-openapi-docs": "^4.5.1",
+        "js-yaml": "^4.1.1",
         "prism-react-renderer": "^2.4.1",
         "raw-loader": "^4.0.2",
         "react": "^18.3.1",
@@ -5747,6 +5749,11 @@
         "@types/istanbul-lib-report": "*"
       }
     },
+    "node_modules/@types/js-yaml": {
+      "version": "4.0.9",
+      "resolved": "https://mirrors.tencent.com/npm/@types/js-yaml/-/js-yaml-4.0.9.tgz",
+      "integrity": "sha512-k4MGaQl5TGo/iipqb2UDG2UwjXziSWkh0uysQelTlJpX1qGlpUZYm8PnO4DxG1qBomtJUdYJ6qR6xdIah10JLg=="
+    },
     "node_modules/@types/json-schema": {
       "version": "7.0.15",
       "resolved": "https://registry.npmjs.org/@types/json-schema/-/json-schema-7.0.15.tgz",
@@ -12883,7 +12890,7 @@
     },
     "node_modules/js-yaml": {
       "version": "4.1.1",
-      "resolved": "https://registry.npmjs.org/js-yaml/-/js-yaml-4.1.1.tgz",
+      "resolved": "https://mirrors.tencent.com/npm/js-yaml/-/js-yaml-4.1.1.tgz",
       "integrity": "sha512-qQKT4zQxXl8lLwBtHMWwaTcGfFOZviOJet3Oy/xmGk2gZH677CJM9EvtfdSkgWcATZhj/55JZ0rmy3myCT5lsA==",
       "license": "MIT",
       "dependencies": {

docs/package.json

@@ -3,9 +3,10 @@
   "version": "0.0.0",
   "private": true,
   "scripts": {
+    "build:config": "node scripts/build-config.mjs",
     "docusaurus": "docusaurus",
-    "start": "npm run regen-docs && docusaurus start --host 0.0.0.0",
-    "build": "npm run regen-docs && docusaurus build",
+    "start": "npm run build:config && npm run regen-docs && docusaurus start --host 0.0.0.0",
+    "build": "npm run build:config && npm run regen-docs && docusaurus build",
     "swizzle": "docusaurus swizzle",
     "deploy": "docusaurus deploy",
     "clear": "docusaurus clear",
@@ -23,9 +24,11 @@
     "@docusaurus/theme-mermaid": "^3.7.0",
     "@inkeep/docusaurus": "^2.0.16",
     "@mdx-js/react": "^3.1.0",
+    "@types/js-yaml": "^4.0.9",
     "clsx": "^2.1.1",
     "docusaurus-plugin-openapi-docs": "^4.5.1",
     "docusaurus-theme-openapi-docs": "^4.5.1",
+    "js-yaml": "^4.1.1",
     "prism-react-renderer": "^2.4.1",
     "raw-loader": "^4.0.2",
     "react": "^18.3.1",

docs/scripts/build-config.mjs

@@ -0,0 +1,64 @@
+#!/usr/bin/env node
+
+/**
+ * Build script: reads config.yaml and generates TypeScript files
+ * for the Docker Compose Generator.
+ *
+ * Usage: node scripts/build-config.mjs
+ */
+
+import fs from "node:fs";
+import path from "node:path";
+import { fileURLToPath } from "node:url";
+import yaml from "js-yaml";
+
+const __dirname = path.dirname(fileURLToPath(import.meta.url));
+const CONFIG_DIR = path.resolve(__dirname, "../src/components/DockerComposeGenerator/config");
+const YAML_PATH = path.join(CONFIG_DIR, "config.yaml");
+
+// Read & parse YAML
+const raw = fs.readFileSync(YAML_PATH, "utf8");
+const config = yaml.load(raw);
+
+if (!config.devices || !config.hardware || !config.ports) {
+  console.error("config.yaml must contain 'devices', 'hardware', and 'ports' sections.");
+  process.exit(1);
+}
+
+/**
+ * Generate a .ts file from a section of the YAML config.
+ */
+function generateTsFile(sectionName, items, typeName, varName, mapVarName, yamlFilename) {
+  const jsonItems = JSON.stringify(items, null, 2);
+  // Indent JSON to fit inside the array literal
+  const indented = jsonItems
+    .split("\n")
+    .map((line, i) => (i === 0 ? line : "  " + line))
+    .join("\n");
+
+  const content = `/**
+ * AUTO-GENERATED FILE — do not edit directly.
+ * Source: ${yamlFilename}
+ * To update, edit the YAML file and run: npm run build:config
+ */
+
+import type { ${typeName} } from "./types";
+
+export const ${varName}: ${typeName}[] = ${indented};
+
+/** Lookup map for quick access by ID */
+export const ${mapVarName}: Map<string, ${typeName}> = new Map(${varName}.map((item) => [item.id, item]));
+`;
+
+  const outPath = path.join(CONFIG_DIR, `${sectionName}.ts`);
+  fs.writeFileSync(outPath, content, "utf8");
+  console.log(`  ✓ Generated ${sectionName}.ts (${items.length} items)`);
+}
+
+console.log("Building config from config.yaml...");
+
+generateTsFile("devices", config.devices, "DeviceConfig", "devices", "deviceMap", "config.yaml");
+generateTsFile("hardware", config.hardware, "HardwareOption", "hardwareOptions", "hardwareMap", "config.yaml");
+generateTsFile("ports", config.ports, "PortConfig", "ports", "portMap", "config.yaml");
+
+console.log("Done!");

docs/src/components/DockerComposeGenerator/DockerComposeGenerator.tsx

@@ -0,0 +1,110 @@
+import React from "react";
+import Admonition from "@theme/Admonition";
+import DeviceSelector from "./components/DeviceSelector";
+import HardwareOptions from "./components/HardwareOptions";
+import PortConfigSection from "./components/PortConfig";
+import StoragePaths from "./components/StoragePaths";
+import NvidiaGpuConfig from "./components/NvidiaGpuConfig";
+import OtherOptions from "./components/OtherOptions";
+import GeneratedOutput from "./components/GeneratedOutput";
+import { useConfigGenerator } from "./hooks/useConfigGenerator";
+import styles from "./styles.module.css";
+
+/**
+ * Simple markdown-link-to-React renderer for help text.
+ * Only supports [text](url) syntax — no nested brackets.
+ */
+function renderHelpText(text: string): React.ReactNode {
+  const parts = text.split(/(\[[^\]]+\]\([^)]+\))/g);
+  return parts.map((part, i) => {
+    const match = part.match(/^\[([^\]]+)\]\(([^)]+)\)$/);
+    if (match) {
+      return (
+        <a key={i} href={match[2]}>
+          {match[1]}
+        </a>
+      );
+    }
+    return <React.Fragment key={i}>{part}</React.Fragment>;
+  });
+}
+
+export default function DockerComposeGenerator() {
+  const {
+    deviceId, device, hardwareEnabled,
+    portEnabled, port5000Confirmed,
+    nvidiaGpuCount, nvidiaGpuDeviceId,
+    configPath, mediaPath, rtspPassword, timezone, shmSize,
+    shmSizeError, gpuDeviceIdError, configPathError, mediaPathError,
+    hasAnyHardware, generatedYaml,
+    selectDevice, toggleHardware, togglePort, setPort5000Confirmed,
+    handleShmSizeChange, handleConfigPathChange, handleMediaPathChange,
+    handleNvidiaGpuCountChange, handleNvidiaGpuDeviceIdChange,
+    setRtspPassword, setTimezone, isHardwareDisabled,
+  } = useConfigGenerator();
+
+  return (
+    <div className={styles.generator}>
+      <div className={styles.card}>
+        <DeviceSelector selectedId={deviceId} onSelect={selectDevice} />
+
+        {device.helpText && (
+          <Admonition type={device.helpType || "info"}>
+            {renderHelpText(device.helpText)}
+          </Admonition>
+        )}
+
+        {device.needsNvidiaConfig && (
+          <NvidiaGpuConfig
+            gpuCount={nvidiaGpuCount}
+            gpuDeviceId={nvidiaGpuDeviceId}
+            gpuDeviceIdError={gpuDeviceIdError}
+            onGpuCountChange={handleNvidiaGpuCountChange}
+            onGpuDeviceIdChange={handleNvidiaGpuDeviceIdChange}
+          />
+        )}
+
+        <HardwareOptions
+          deviceId={deviceId}
+          hardwareEnabled={hardwareEnabled}
+          onToggle={toggleHardware}
+          isDisabled={isHardwareDisabled}
+        />
+
+        <StoragePaths
+          configPath={configPath}
+          mediaPath={mediaPath}
+          configPathError={configPathError}
+          mediaPathError={mediaPathError}
+          onConfigPathChange={handleConfigPathChange}
+          onMediaPathChange={handleMediaPathChange}
+        />
+
+        <PortConfigSection
+          portEnabled={portEnabled}
+          port5000Confirmed={port5000Confirmed}
+          onTogglePort={togglePort}
+          onConfirm5000={setPort5000Confirmed}
+        />
+
+        <OtherOptions
+          rtspPassword={rtspPassword}
+          timezone={timezone}
+          shmSize={shmSize}
+          shmSizeError={shmSizeError}
+          onRtspPasswordChange={setRtspPassword}
+          onTimezoneChange={setTimezone}
+          onShmSizeChange={handleShmSizeChange}
+        />
+
+        <GeneratedOutput
+          yaml={generatedYaml}
+          configPath={configPath}
+          mediaPath={mediaPath}
+          hasAnyHardware={hasAnyHardware}
+          deviceId={deviceId}
+        />
+      </div>
+    </div>
+  );
+}

docs/src/components/DockerComposeGenerator/components/DeviceSelector.tsx

@@ -0,0 +1,147 @@
+import React from "react";
+import { useColorMode } from "@docusaurus/theme-common";
+import { devices } from "../config";
+import type { DeviceConfig } from "../config";
+import styles from "../styles.module.css";
+
+interface Props {
+  selectedId: string;
+  onSelect: (id: string) => void;
+}
+
+/**
+ * Determine the icon type from the icon string:
+ * - Starts with "<svg" → inline SVG
+ * - Starts with "/" or "http" → image URL/path
+ * - Otherwise → emoji text
+ */
+function getIconType(icon: string): "svg" | "image" | "emoji" {
+  const trimmed = icon.trim();
+  if (trimmed.startsWith("<svg")) return "svg";
+  if (trimmed.startsWith("/") || trimmed.startsWith("http://") || trimmed.startsWith("https://")) return "image";
+  return "emoji";
+}
+
+/**
+ * Check if the style object contains background-* properties,
+ * indicating the image should be rendered as a CSS background-image
+ * rather than an <img> tag.
+ */
+function hasBackgroundProps(style: React.CSSProperties | undefined): boolean {
+  if (!style) return false;
+  return Object.keys(style).some((key) => {
+    const k = key.toLowerCase().replace(/-/g, "");
+    return k === "backgroundsize" || k === "backgroundposition" || k === "backgroundrepeat" || k === "backgroundimage";
+  });
+}
+
+/**
+ * Convert a style object to CSS custom properties (e.g. { width: "24px" } → { "--svg-width": "24px" })
+ * so they can be consumed by CSS rules targeting child elements like <svg>.
+ */
+function toCssVars(style: React.CSSProperties | undefined, prefix: string): React.CSSProperties {
+  if (!style) return {};
+  const vars: Record<string, string> = {};
+  for (const [key, value] of Object.entries(style)) {
+    const cssKey = key.replace(/([A-Z])/g, "-$1").toLowerCase();
+    vars[`--${prefix}-${cssKey}`] = value;
+  }
+  return vars as React.CSSProperties;
+}
+
+function DeviceIcon({ device }: { device: DeviceConfig }) {
+  const { isDarkTheme } = useColorMode();
+  const iconStr = isDarkTheme && device.iconDark ? device.iconDark : device.icon;
+  const iconStyle = (isDarkTheme && device.iconDarkStyle
+    ? device.iconDarkStyle
+    : device.iconStyle) as React.CSSProperties | undefined;
+  const svgStyle = (isDarkTheme && device.svgDarkStyle
+    ? device.svgDarkStyle
+    : device.svgStyle) as React.CSSProperties | undefined;
+
+  const iconType = getIconType(iconStr);
+
+  if (iconType === "svg") {
+    return (
+      <div
+        className={styles.deviceIconSvg}
+        style={{ ...iconStyle, ...toCssVars(svgStyle, "svg") }}
+        dangerouslySetInnerHTML={{ __html: iconStr }}
+      />
+    );
+  }
+
+  if (iconType === "image") {
+    // When iconStyle contains background-* properties, render as background-image
+    // on the container div instead of an <img> tag, enabling background-size/position control.
+    if (hasBackgroundProps(iconStyle)) {
+      return (
+        <div
+          className={styles.deviceIconImage}
+          style={{
+            backgroundImage: `url(${iconStr})`,
+            backgroundRepeat: "no-repeat",
+            backgroundPosition: "center",
+            backgroundSize: "contain",
+            ...iconStyle,
+          }}
+        />
+      );
+    }
+    return (
+      <div className={styles.deviceIconImage}>
+        <img src={iconStr} alt={device.name} style={iconStyle} />
+      </div>
+    );
+  }
+
+  return (
+    <div className={styles.deviceIcon} style={iconStyle}>
+      {iconStr}
+    </div>
+  );
+}
+
+function DeviceCard({
+  device,
+  active,
+  onClick,
+}: {
+  device: DeviceConfig;
+  active: boolean;
+  onClick: () => void;
+}) {
+  return (
+    <div
+      className={`${styles.deviceCard} ${active ? styles.deviceCardActive : ""}`}
+      onClick={onClick}
+      role="button"
+      tabIndex={0}
+      onKeyDown={(e) => {
+        if (e.key === "Enter" || e.key === " ") onClick();
+      }}
+    >
+      <DeviceIcon device={device} />
+      <div className={styles.deviceName}>{device.name}</div>
+      <div className={styles.deviceDesc}>{device.description}</div>
+    </div>
+  );
+}
+
+export default function DeviceSelector({ selectedId, onSelect }: Props) {
+  return (
+    <div className={styles.formSection}>
+      <h4>Device Type</h4>
+      <div className={styles.deviceGrid}>
+        {devices.map((d) => (
+          <DeviceCard
+            key={d.id}
+            device={d}
+            active={selectedId === d.id}
+            onClick={() => onSelect(d.id)}
+          />
+        ))}
+      </div>
+    </div>
+  );
+}

docs/src/components/DockerComposeGenerator/components/GeneratedOutput.tsx

@@ -0,0 +1,60 @@
+import React, { useState, useCallback } from "react";
+import CodeBlock from "@theme/CodeBlock";
+import Admonition from "@theme/Admonition";
+import styles from "../styles.module.css";
+
+interface Props {
+  yaml: string;
+  configPath: string;
+  mediaPath: string;
+  hasAnyHardware: boolean;
+  deviceId: string;
+}
+
+export default function GeneratedOutput({
+  yaml,
+  configPath,
+  mediaPath,
+  hasAnyHardware,
+  deviceId,
+}: Props) {
+  const [copied, setCopied] = useState(false);
+
+  const handleCopy = useCallback(() => {
+    navigator.clipboard.writeText(yaml).then(() => {
+      setCopied(true);
+      setTimeout(() => setCopied(false), 2000);
+    });
+  }, [yaml]);
+
+  return (
+    <div className={styles.resultSection}>
+      <div className={styles.resultHeader}>
+        <h4>Generated Configuration</h4>
+        <button className="button button--primary button--sm" onClick={handleCopy}>
+          {copied ? "Copied!" : "Copy"}
+        </button>
+      </div>
+
+      {!configPath && (
+        <Admonition type="tip">
+          <p>You haven&apos;t specified a config file directory. You may want to modify the default path.</p>
+        </Admonition>
+      )}
+      {!mediaPath && (
+        <Admonition type="tip">
+          <p>You haven&apos;t specified a recording storage directory. You may want to modify the default path.</p>
+        </Admonition>
+      )}
+      {deviceId === "stable" && !hasAnyHardware && (
+        <Admonition type="warning">
+          <p>You haven&apos;t selected any hardware acceleration. Please check if you have supported hardware available.</p>
+        </Admonition>
+      )}
+
+      <CodeBlock language="yaml" title="docker-compose.yml">
+        {yaml}
+      </CodeBlock>
+    </div>
+  );
+}

docs/src/components/DockerComposeGenerator/components/HardwareOptions.tsx

@@ -0,0 +1,62 @@
+import React from "react";
+import { hardwareOptions } from "../config";
+import type { HardwareOption } from "../config";
+import styles from "../styles.module.css";
+
+interface Props {
+  deviceId: string;
+  hardwareEnabled: Record<string, boolean>;
+  onToggle: (hwId: string) => void;
+  isDisabled: (hwId: string) => boolean;
+}
+
+function renderDescription(text: string): React.ReactNode {
+  const parts = text.split(/(\[[^\]]+\]\([^)]+\))/g);
+  return parts.map((part, i) => {
+    const match = part.match(/^\[([^\]]+)\]\(([^)]+)\)$/);
+    if (match) {
+      return <a key={i} href={match[2]}>{match[1]}</a>;
+    }
+    return <React.Fragment key={i}>{part}</React.Fragment>;
+  });
+}
+
+function HardwareCheckbox({
+  hw, disabled, checked, onToggle,
+}: {
+  hw: HardwareOption; disabled: boolean; checked: boolean; onToggle: () => void;
+}) {
+  return (
+    <div className={styles.hardwareItem}>
+      <label className={`${styles.checkboxLabel} ${disabled ? styles.checkboxDisabled : ""}`}>
+        <input type="checkbox" checked={checked} onChange={onToggle} disabled={disabled} />
+        <span>{hw.label}</span>
+      </label>
+      {checked && hw.description && (
+        <div className={styles.hardwareDescription}>{renderDescription(hw.description)}</div>
+      )}
+    </div>
+  );
+}
+
+export default function HardwareOptions({ deviceId, hardwareEnabled, onToggle, isDisabled }: Props) {
+  return (
+    <div className={styles.formSection}>
+      <h4>Generic Hardware Acceleration</h4>
+      {deviceId !== "stable" && (
+        <p className={styles.helpText}>
+          Some options have been auto-configured based on your device type.
+        </p>
+      )}
+      <div className={styles.checkboxGrid}>
+        {hardwareOptions.map((hw) => {
+          const disabled = isDisabled(hw.id);
+          const checked = disabled ? false : !!hardwareEnabled[hw.id];
+          return (
+            <HardwareCheckbox key={hw.id} hw={hw} disabled={disabled} checked={checked} onToggle={() => onToggle(hw.id)} />
+          );
+        })}
+      </div>
+    </div>
+  );
+}

docs/src/components/DockerComposeGenerator/components/NvidiaGpuConfig.tsx

@@ -0,0 +1,63 @@
+import React from "react";
+import styles from "../styles.module.css";
+
+interface Props {
+  gpuCount: string;
+  gpuDeviceId: string;
+  gpuDeviceIdError: boolean;
+  onGpuCountChange: (value: string) => void;
+  onGpuDeviceIdChange: (value: string) => void;
+}
+
+export default function NvidiaGpuConfig({
+  gpuCount,
+  gpuDeviceId,
+  gpuDeviceIdError,
+  onGpuCountChange,
+  onGpuDeviceIdChange,
+}: Props) {
+  return (
+    <div className={styles.nvidiaConfig}>
+      <div className={styles.formGroup}>
+        <label htmlFor="dcg-gpu-count" className={styles.label}>
+          GPU count:
+        </label>
+        <input
+          id="dcg-gpu-count"
+          type="text"
+          className={styles.input}
+          value={gpuCount}
+          placeholder="1 or all"
+          onChange={(e) => onGpuCountChange(e.target.value)}
+        />
+        <p className={styles.helpText}>
+          Enter a number (e.g. 1, 2, 3) or &quot;all&quot; to use all GPUs
+        </p>
+      </div>
+      {gpuCount !== "all" && (
+        <div className={styles.formGroup}>
+          <label htmlFor="dcg-gpu-device-id" className={styles.label}>
+            GPU device IDs (required, comma-separated):
+          </label>
+          <input
+            id="dcg-gpu-device-id"
+            type="text"
+            className={`${styles.input} ${gpuDeviceIdError ? styles.inputError : ""}`}
+            value={gpuDeviceId}
+            placeholder="0"
+            onChange={(e) => onGpuDeviceIdChange(e.target.value)}
+          />
+          {gpuDeviceIdError ? (
+            <p className={styles.helpText}>
+              ⚠️ GPU device IDs are required when GPU count is a number
+            </p>
+          ) : (
+            <p className={styles.helpText}>
+              Single GPU: 0 &nbsp;|&nbsp; Multiple GPUs: 0,1,2
+            </p>
+          )}
+        </div>
+      )}
+    </div>
+  );
+}

docs/src/components/DockerComposeGenerator/components/OtherOptions.tsx

@@ -0,0 +1,89 @@
+import React from "react";
+import CodeInline from "@theme/CodeInline";
+import styles from "../styles.module.css";
+
+interface Props {
+  rtspPassword: string;
+  timezone: string;
+  shmSize: string;
+  shmSizeError: boolean;
+  onRtspPasswordChange: (value: string) => void;
+  onTimezoneChange: (value: string) => void;
+  onShmSizeChange: (value: string) => void;
+}
+
+export default function OtherOptions({
+  rtspPassword,
+  timezone,
+  shmSize,
+  shmSizeError,
+  onRtspPasswordChange,
+  onTimezoneChange,
+  onShmSizeChange,
+}: Props) {
+  return (
+    <div className={styles.formSection}>
+      <h4>Other Options</h4>
+      <div className={styles.formGrid}>
+        <div className={styles.formGroup}>
+          <label htmlFor="dcg-rtsp-password" className={styles.label}>
+            RTSP password:
+          </label>
+          <input
+            id="dcg-rtsp-password"
+            type="text"
+            className={styles.input}
+            value={rtspPassword}
+            placeholder="password"
+            onChange={(e) => onRtspPasswordChange(e.target.value)}
+          />
+          <p className={styles.helpText}>
+            Used as{" "}
+            <CodeInline>{"{FRIGATE_RTSP_PASSWORD}"}</CodeInline>{" "}
+            in the config file to reference camera stream passwords. This is NOT
+            the Frigate login password.
+          </p>
+        </div>
+        <div className={styles.formGroup}>
+          <label htmlFor="dcg-timezone" className={styles.label}>
+            Timezone:
+          </label>
+          <input
+            id="dcg-timezone"
+            type="text"
+            className={styles.input}
+            value={timezone}
+            placeholder={Intl.DateTimeFormat().resolvedOptions().timeZone || "Etc/UTC"}
+            onChange={(e) => onTimezoneChange(e.target.value)}
+          />
+        </div>
+        <div className={styles.formGroup}>
+          <label htmlFor="dcg-shm-size" className={styles.label}>
+            Shared memory (SHM):
+          </label>
+          <input
+            id="dcg-shm-size"
+            type="text"
+            className={`${styles.input} ${shmSizeError ? styles.inputError : ""}`}
+            value={shmSize}
+            placeholder="512mb"
+            onChange={(e) => onShmSizeChange(e.target.value)}
+          />
+          {shmSizeError ? (
+            <p className={styles.helpText}>
+              ⚠️ Invalid format. Use a number followed by a unit (e.g. 512mb, 1gb)
+            </p>
+          ) : (
+            <p className={styles.helpText}>
+              See{" "}
+              <a href="/frigate/installation#calculating-required-shm-size">
+                calculating required SHM size
+              </a>{" "}
+              for the correct value.
+            </p>
+          )}
+        </div>
+      </div>
+    </div>
+  );
+}

docs/src/components/DockerComposeGenerator/components/PortConfig.tsx

@@ -0,0 +1,125 @@
+import React from "react";
+import Admonition from "@theme/Admonition";
+import { ports } from "../config";
+import { useCooldown } from "../hooks/useCooldown";
+import styles from "../styles.module.css";
+
+interface Props {
+  portEnabled: Record<string, boolean>;
+  port5000Confirmed: boolean;
+  onTogglePort: (portId: string) => void;
+  onConfirm5000: (confirmed: boolean) => void;
+}
+
+function Port5000Confirmation({
+  portEnabled,
+  confirmed,
+  onToggle,
+  onConfirm,
+}: {
+  portEnabled: boolean;
+  confirmed: boolean;
+  onToggle: () => void;
+  onConfirm: (confirmed: boolean) => void;
+}) {
+  const { remaining, start, stop } = useCooldown(10);
+
+  React.useEffect(() => {
+    if (portEnabled) {
+      start();
+    } else {
+      stop();
+      onConfirm(false);
+    }
+    return stop;
+  }, [portEnabled]);
+
+  return (
+    <div className={styles.portSection}>
+      {portEnabled && (
+        <Admonition type="danger">
+          <p>
+            Exposing port 5000 allows <strong>unauthenticated access</strong> to
+            your Frigate instance. Anyone on your network (or the internet if you
+            have a public IP) could access it without credentials.
+          </p>
+          <p>
+            This may lead to <strong>unauthorized access</strong>,{" "}
+            <strong>privacy leaks</strong>, or further attacks. Ensure you have
+            proper firewall rules or VPN in place.
+          </p>
+          <label
+            className={`${styles.checkboxLabel} ${remaining > 0 ? styles.checkboxDisabled : ""}`}
+          >
+            <input
+              type="checkbox"
+              checked={confirmed}
+              onChange={(e) => onConfirm(e.target.checked)}
+              disabled={remaining > 0}
+            />
+            <span>
+              I understand the risk and confirm enabling port 5000
+              {remaining > 0 && ` (${remaining}s)`}
+            </span>
+          </label>
+        </Admonition>
+      )}
+      <label className={styles.checkboxLabel}>
+        <input
+          type="checkbox"
+          checked={portEnabled}
+          onChange={onToggle}
+        />
+        <span>Port 5000 (unauthenticated access)</span>
+        <span className={styles.warningBadge}>⚠️ Expose carefully</span>
+      </label>
+    </div>
+  );
+}
+
+export default function PortConfigSection({
+  portEnabled,
+  port5000Confirmed,
+  onTogglePort,
+  onConfirm5000,
+}: Props) {
+  return (
+    <div className={styles.formSection}>
+      <h4>Port Configuration</h4>
+
+      {/* All ports except 5000 */}
+      <div className={styles.checkboxGrid}>
+        {ports
+          .filter((p) => p.id !== "5000")
+          .map((port) => (
+            <div key={port.id} className={styles.hardwareItem}>
+              <label className={`${styles.checkboxLabel} ${port.locked ? styles.checkboxDisabled : ""}`}>
+                <input
+                  type="checkbox"
+                  checked={!!portEnabled[port.id]}
+                  onChange={() => onTogglePort(port.id)}
+                  disabled={port.locked}
+                />
+                <span>
+                  {port.locked && "🔒 "}
+                  Port {port.host}
+                  {port.protocol !== "tcp" && `/${port.protocol}`}
+                </span>
+              </label>
+              {port.description && (
+                <div className={styles.hardwareDescription}>{port.description}</div>
+              )}
+            </div>
+          ))}
+      </div>
+
+      {/* Port 5000 with special warning — placed last */}
+      <Port5000Confirmation
+        portEnabled={!!portEnabled["5000"]}
+        confirmed={port5000Confirmed}
+        onToggle={() => onTogglePort("5000")}
+        onConfirm={onConfirm5000}
+      />
+    </div>
+  );
+}

docs/src/components/DockerComposeGenerator/components/StoragePaths.tsx

@@ -0,0 +1,66 @@
+import React from "react";
+import styles from "../styles.module.css";
+
+interface Props {
+  configPath: string;
+  mediaPath: string;
+  configPathError: boolean;
+  mediaPathError: boolean;
+  onConfigPathChange: (value: string) => void;
+  onMediaPathChange: (value: string) => void;
+}
+
+export default function StoragePaths({
+  configPath,
+  mediaPath,
+  configPathError,
+  mediaPathError,
+  onConfigPathChange,
+  onMediaPathChange,
+}: Props) {
+  return (
+    <div className={styles.formSection}>
+      <h4>Storage Paths</h4>
+      <div className={styles.formGrid}>
+        <div className={styles.formGroup}>
+          <label htmlFor="dcg-config-path" className={styles.label}>
+            Config / DB / model cache directory:
+          </label>
+          <input
+            id="dcg-config-path"
+            type="text"
+            className={`${styles.input} ${configPathError ? styles.inputError : ""}`}
+            value={configPath}
+            placeholder="/path/to/your/config"
+            onChange={(e) => onConfigPathChange(e.target.value)}
+          />
+          {configPathError && (
+            <p className={styles.helpText}>
+              ⚠️ Path contains invalid characters. Only letters, numbers,
+              underscores, hyphens, slashes, and dots are allowed.
+            </p>
+          )}
+        </div>
+        <div className={styles.formGroup}>
+          <label htmlFor="dcg-media-path" className={styles.label}>
+            Recording storage directory:
+          </label>
+          <input
+            id="dcg-media-path"
+            type="text"
+            className={`${styles.input} ${mediaPathError ? styles.inputError : ""}`}
+            value={mediaPath}
+            placeholder="/path/to/your/storage"
+            onChange={(e) => onMediaPathChange(e.target.value)}
+          />
+          {mediaPathError && (
+            <p className={styles.helpText}>
+              ⚠️ Path contains invalid characters. Only letters, numbers,
+              underscores, hyphens, slashes, and dots are allowed.
+            </p>
+          )}
+        </div>
+      </div>
+    </div>
+  );
+}

docs/src/components/DockerComposeGenerator/config/index.ts

@@ -0,0 +1,12 @@
+export { devices, deviceMap } from "./devices";
+export { hardwareOptions, hardwareMap } from "./hardware";
+export { ports, portMap } from "./ports";
+
+export type {
+  DeviceConfig,
+  DeviceMapping,
+  VolumeMapping,
+  HardwareOption,
+  PortConfig,
+  NvidiaDeployConfig,
+} from "./types";

docs/src/components/DockerComposeGenerator/config/types.ts

@@ -0,0 +1,158 @@
+/**
+ * Type definitions for the Docker Compose Generator configuration.
+ * All device, hardware, and port options are declaratively defined
+ * so that adding a new device only requires editing config files.
+ */
+
+/** A single device mapping entry (e.g. /dev/dri:/dev/dri) */
+export interface DeviceMapping {
+  /** Host device path */
+  host: string;
+  /** Container device path (defaults to host if omitted) */
+  container?: string;
+  /** Inline comment for this device line */
+  comment?: string;
+}
+
+/** A single volume mapping entry */
+export interface VolumeMapping {
+  /** Host path */
+  host: string;
+  /** Container path */
+  container: string;
+  /** Whether the mount is read-only */
+  readOnly?: boolean;
+  /** Inline comment */
+  comment?: string;
+}
+
+/** NVIDIA deploy configuration for docker-compose */
+export interface NvidiaDeployConfig {
+  /** "all" or a specific number */
+  count: string;
+  /** Specific GPU device IDs (when count is a number) */
+  deviceIds?: string[];
+}
+
+/** Full device type definition */
+export interface DeviceConfig {
+  /** Unique identifier, e.g. "intel" */
+  id: string;
+  /** Display name, e.g. "Intel GPU" */
+  name: string;
+  /** Short description */
+  description: string;
+  /**
+   * Icon for the device card. Supports:
+   * - Emoji string (e.g. "🖥️")
+   * - Image URL or static path (e.g. "/img/intel.svg", "https://example.com/icon.png")
+   * - Inline SVG markup (e.g. "<svg>...</svg>")
+   */
+  icon: string;
+  /**
+   * Additional CSS properties applied to the icon element.
+   * - For image-type icons: if any `background-*` property (e.g. `background-size`,
+   *   `background-position`) is present, the image is rendered as a CSS `background-image`
+   *   on the container div, enabling full background positioning control.
+   *   Otherwise the image is rendered as an `<img>` tag and styles apply to it.
+   * - For emoji/SVG icons: styles apply to the container div.
+   */
+  iconStyle?: Record<string, string>;
+  /**
+   * Additional CSS properties applied directly to the inner `<svg>` element
+   * when the icon is an inline SVG. Use this to override the default
+   * `width: 100%; height: 100%` or set `fill`, `transform`, etc.
+   * Ignored for emoji and image-type icons.
+   */
+  svgStyle?: Record<string, string>;
+  /**
+   * Icon for dark mode. Same format as `icon`. When provided, this icon
+   * replaces `icon` when the user is in dark mode.
+   */
+  iconDark?: string;
+  /** Additional CSS properties for the dark mode icon container */
+  iconDarkStyle?: Record<string, string>;
+  /**
+   * SVG-specific styles for dark mode. Same as `svgStyle` but applied
+   * when dark mode is active. Merged over `svgStyle` in dark mode.
+   */
+  svgDarkStyle?: Record<string, string>;
+  /** Docker image tag, e.g. "stable" */
+  imageTag: string;
+  /**
+   * Image tag suffix appended to the base tag.
+   * e.g. "-standard-arm64" produces "stable-standard-arm64"
+   */
+  imageTagSuffix?: string;
+  /** Hardware option IDs to auto-enable when this device is selected */
+  autoHardware: string[];
+  /** Help text shown as an admonition when this device is selected */
+  helpText?: string;
+  /** Admonition type for help text */
+  helpType?: "info" | "warning" | "danger";
+  /** Device mappings always added for this device type */
+  devices?: DeviceMapping[];
+  /** Volume mappings always added for this device type */
+  volumes?: VolumeMapping[];
+  /** Extra environment variables for this device type */
+  env?: Record<string, string>;
+  /** NVIDIA deploy config (only for tensorrt) */
+  nvidiaDeploy?: NvidiaDeployConfig;
+  /** Runtime setting, e.g. "nvidia" for Jetson */
+  runtime?: string;
+  /** Extra hosts entries, e.g. "host.docker.internal:host-gateway" */
+  extraHosts?: string[];
+  /** Security options, e.g. ["apparmor=unconfined"] */
+  securityOpt?: string[];
+  /** Whether this device type needs the NVIDIA GPU config UI */
+  needsNvidiaConfig?: boolean;
+}
+
+/** Generic hardware acceleration option definition */
+export interface HardwareOption {
+  /** Unique identifier, e.g. "usbCoral" */
+  id: string;
+  /** Display label */
+  label: string;
+  /**
+   * Description shown below the checkbox when this option is enabled.
+   * Supports markdown link syntax: [text](url)
+   */
+  description?: string;
+  /** Device IDs that disable this option */
+  disabledWhen?: string[];
+  /** Device mappings added when this option is enabled */
+  devices?: DeviceMapping[];
+  /** Volume mappings added when this option is enabled */
+  volumes?: VolumeMapping[];
+  /** Extra environment variables */
+  env?: Record<string, string>;
+}
+
+/** Port definition */
+export interface PortConfig {
+  /** Unique identifier (also the default host port as string) */
+  id: string;
+  /** Host port number */
+  host: number;
+  /** Container port number */
+  container: number;
+  /** Protocol */
+  protocol?: "tcp" | "udp";
+  /** Description of the port's purpose */
+  description: string;
+  /** Whether enabled by default */
+  defaultEnabled: boolean;
+  /** Whether this port is locked (always enabled, cannot be toggled off) */
+  locked?: boolean;
+  /** Whether this port requires a confirmation step before enabling */
+  requiresConfirmation?: boolean;
+  /** Admonition type for the warning */
+  warningType?: "warning" | "danger";
+  /** Warning content (markdown) */
+  warningContent?: string;
+  /** Confirmation checkbox label */
+  confirmationLabel?: string;
+  /** Cooldown in seconds before the confirmation checkbox becomes available */
+  cooldownSeconds?: number;
+}

docs/src/components/DockerComposeGenerator/generator/index.ts

@@ -0,0 +1,246 @@
+import type {
+  DeviceConfig,
+  DeviceMapping,
+  VolumeMapping,
+} from "../config/types";
+import { hardwareMap } from "../config";
+
+// ---------------------------------------------------------------------------
+// Input type
+// ---------------------------------------------------------------------------
+
+export interface GeneratorInput {
+  device: DeviceConfig;
+  selectedHardware: string[];
+  enabledPorts: string[];
+  configPath: string;
+  mediaPath: string;
+  rtspPassword: string;
+  timezone: string;
+  shmSize: string;
+  nvidiaGpuCount?: string;
+  nvidiaGpuDeviceId?: string;
+}
+
+// ---------------------------------------------------------------------------
+// Helpers
+// ---------------------------------------------------------------------------
+
+function deviceLine(dm: DeviceMapping): string {
+  const host = dm.host;
+  const container = dm.container ?? dm.host;
+  const mapping = host === container ? host : `${host}:${container}`;
+  const comment = dm.comment ? ` # ${dm.comment}` : "";
+  return `      - ${mapping}${comment}`;
+}
+
+function volumeLine(vm: VolumeMapping): string {
+  const ro = vm.readOnly ? ":ro" : "";
+  const comment = vm.comment ? ` # ${vm.comment}` : "";
+  return `      - ${vm.host}:${vm.container}${ro}${comment}`;
+}
+
+// ---------------------------------------------------------------------------
+// YAML builder — each section returns an array of lines
+// ---------------------------------------------------------------------------
+
+function buildImage(device: DeviceConfig): string[] {
+  const tag = device.imageTagSuffix
+    ? `${device.imageTag}${device.imageTagSuffix}`
+    : device.imageTag;
+  return [`    image: ghcr.io/blakeblackshear/frigate:${tag}`];
+}
+
+function buildDevices(
+  device: DeviceConfig,
+  hwDevices: DeviceMapping[]
+): string[] {
+  const all: DeviceMapping[] = [
+    ...(device.devices ?? []),
+    ...hwDevices,
+  ];
+  if (all.length === 0) return [];
+  return [
+    "    devices:",
+    ...all.map(deviceLine),
+  ];
+}
+
+function buildVolumes(
+  device: DeviceConfig,
+  hwVolumes: VolumeMapping[],
+  configPath: string,
+  mediaPath: string
+): string[] {
+  const all: VolumeMapping[] = [
+    ...(device.volumes ?? []),
+    ...hwVolumes,
+  ];
+  return [
+    "    volumes:",
+    "      - /etc/localtime:/etc/localtime:ro # Sync host time",
+    `      - ${configPath}:/config # Config file directory`,
+    `      - ${mediaPath}:/media/frigate # Recording storage directory`,
+    "      - type: tmpfs # 1GB in-memory filesystem for recording segment storage",
+    "        target: /tmp/cache",
+    "        tmpfs:",
+    "          size: 1000000000",
+    ...all.map(volumeLine),
+  ];
+}
+
+function buildPorts(enabledPorts: string[]): string[] {
+  return [
+    "    ports:",
+    ...enabledPorts,
+  ];
+}
+
+function buildEnvironment(
+  device: DeviceConfig,
+  hwEnv: Record<string, string>,
+  rtspPassword: string,
+  timezone: string
+): string[] {
+  const allEnv: Record<string, string> = {
+    ...hwEnv,
+    ...(device.env ?? {}),
+  };
+
+  const lines: string[] = [
+    "    environment:",
+    `      FRIGATE_RTSP_PASSWORD: "${rtspPassword}" # RTSP password — change to your own`,
+    `      TZ: "${timezone}" # Timezone`,
+  ];
+
+  for (const [key, value] of Object.entries(allEnv)) {
+    lines.push(`      ${key}: "${value}"`);
+  }
+
+  return lines;
+}
+
+function buildDeploy(device: DeviceConfig, input: GeneratorInput): string[] {
+  if (device.id === "stable-tensorrt") {
+    const count = input.nvidiaGpuCount || "all";
+    const isAll = count.toLowerCase() === "all";
+    const deviceId = input.nvidiaGpuDeviceId?.trim();
+
+    if (isAll) {
+      return [
+        "    deploy:",
+        "      resources:",
+        "        reservations:",
+        "          devices:",
+        "            - driver: nvidia",
+        "              count: all # Use all GPUs",
+        "              capabilities: [gpu]",
+      ];
+    }
+
+    if (deviceId) {
+      const ids = deviceId
+        .split(",")
+        .map((s) => s.trim())
+        .filter(Boolean)
+        .map((s) => `'${s}'`)
+        .join(", ");
+      return [
+        "    deploy:",
+        "      resources:",
+        "        reservations:",
+        "          devices:",
+        "            - driver: nvidia",
+        `              device_ids: [${ids}] # GPU device IDs`,
+        `              count: ${count} # GPU count`,
+        "              capabilities: [gpu]",
+      ];
+    }
+
+    return [
+      "    deploy:",
+      "      resources:",
+      "        reservations:",
+      "          devices:",
+      "            - driver: nvidia",
+      `              count: ${count} # GPU count`,
+      "              capabilities: [gpu]",
+    ];
+  }
+
+  return [];
+}
+
+function buildRuntime(device: DeviceConfig): string[] {
+  if (device.runtime) {
+    return [`    runtime: ${device.runtime}`];
+  }
+  return [];
+}
+
+function buildExtraHosts(device: DeviceConfig): string[] {
+  if (!device.extraHosts?.length) return [];
+  return [
+    "    extra_hosts:",
+    ...device.extraHosts.map(
+      (h, i) =>
+        `      - "${h}"${i === 0 ? " # Required to talk to the NPU detector" : ""}`
+    ),
+  ];
+}
+
+function buildSecurityOpt(device: DeviceConfig): string[] {
+  if (!device.securityOpt?.length) return [];
+  return [
+    "    security_opt:",
+    ...device.securityOpt.map((s) => `      - ${s}`),
+  ];
+}
+
+// ---------------------------------------------------------------------------
+// Public API
+// ---------------------------------------------------------------------------
+
+/**
+ * Generate a docker-compose YAML string from the given input.
+ * The output is pure YAML with inline comments (no Shiki annotations).
+ */
+export function generateDockerCompose(input: GeneratorInput): string {
+  const { device } = input;
+
+  // Collect hardware-level devices, volumes, and env
+  const hwDevices: DeviceMapping[] = [];
+  const hwVolumes: VolumeMapping[] = [];
+  const hwEnv: Record<string, string> = {};
+
+  for (const hwId of input.selectedHardware) {
+    const hw = hardwareMap.get(hwId);
+    if (!hw) continue;
+    // Skip GPU device mapping for tensorrt images (it uses deploy instead)
+    if (hw.id === "gpu" && device.imageTag === "stable-tensorrt") continue;
+    hwDevices.push(...(hw.devices ?? []));
+    hwVolumes.push(...(hw.volumes ?? []));
+    Object.assign(hwEnv, hw.env ?? {});
+  }
+
+  const lines: string[] = [
+    "services:",
+    "  frigate:",
+    "    container_name: frigate",
+    "    privileged: true # This may not be necessary for all setups",
+    "    restart: unless-stopped",
+    "    stop_grace_period: 30s # Allow enough time to shut down the various services",
+    ...buildImage(device),
+    `    shm_size: "${input.shmSize || "512mb"}" # Update for your cameras based on SHM calculation`,
+    ...buildRuntime(device),
+    ...buildDeploy(device, input),
+    ...buildExtraHosts(device),
+    ...buildSecurityOpt(device),
+    ...buildDevices(device, hwDevices),
+    ...buildVolumes(device, hwVolumes, input.configPath, input.mediaPath),
+    ...buildPorts(input.enabledPorts),
+    ...buildEnvironment(device, hwEnv, input.rtspPassword, input.timezone),
+  ];
+
+  return lines.join("\n");
+}

docs/src/components/DockerComposeGenerator/hooks/useConfigGenerator.ts

@@ -0,0 +1,207 @@
+import { useState, useCallback, useMemo } from "react";
+import { deviceMap, hardwareMap, portMap } from "../config";
+import { generateDockerCompose } from "../generator";
+import type { GeneratorInput } from "../generator";
+
+/**
+ * Main hook that holds all form state and generates the Docker Compose output.
+ * Configuration is loaded synchronously from build-time generated .ts files.
+ */
+export function useConfigGenerator() {
+  const [deviceId, setDeviceId] = useState("stable");
+
+  const [hardwareEnabled, setHardwareEnabled] = useState<Record<string, boolean>>(() => {
+    const defaultDevice = deviceMap.get("stable");
+    const initial: Record<string, boolean> = {};
+    if (defaultDevice) {
+      for (const hwId of defaultDevice.autoHardware) {
+        initial[hwId] = true;
+      }
+    }
+    return initial;
+  });
+
+  const [portEnabled, setPortEnabled] = useState<Record<string, boolean>>(() => {
+    const initial: Record<string, boolean> = {};
+    for (const p of portMap.values()) {
+      initial[p.id] = p.defaultEnabled;
+    }
+    return initial;
+  });
+
+  const [port5000Confirmed, setPort5000Confirmed] = useState(false);
+  const [nvidiaGpuCount, setNvidiaGpuCount] = useState("all");
+  const [nvidiaGpuDeviceId, setNvidiaGpuDeviceId] = useState("");
+  const [configPath, setConfigPath] = useState("");
+  const [mediaPath, setMediaPath] = useState("");
+  const [rtspPassword, setRtspPassword] = useState("password");
+  const [timezone, setTimezone] = useState(
+    () => Intl.DateTimeFormat().resolvedOptions().timeZone || "Etc/UTC"
+  );
+  const [shmSize, setShmSize] = useState("512mb");
+  const [shmSizeError, setShmSizeError] = useState(false);
+  const [gpuDeviceIdError, setGpuDeviceIdError] = useState(false);
+  const [configPathError, setConfigPathError] = useState(false);
+  const [mediaPathError, setMediaPathError] = useState(false);
+
+  const device = useMemo(() => deviceMap.get(deviceId)!, [deviceId]);
+
+  const selectDevice = useCallback((id: string) => {
+    const newDevice = deviceMap.get(id);
+    if (!newDevice) return;
+    setDeviceId(id);
+    setHardwareEnabled(() => {
+      const next: Record<string, boolean> = {};
+      for (const hwId of newDevice.autoHardware) {
+        next[hwId] = true;
+      }
+      return next;
+    });
+    setNvidiaGpuCount("all");
+    setNvidiaGpuDeviceId("");
+    setGpuDeviceIdError(false);
+  }, []);
+
+  const toggleHardware = useCallback((hwId: string) => {
+    setHardwareEnabled((prev) => ({ ...prev, [hwId]: !prev[hwId] }));
+  }, []);
+
+  const togglePort = useCallback((portId: string) => {
+    const port = portMap.get(portId);
+    if (port?.locked) return;
+    setPortEnabled((prev) => {
+      const next = { ...prev, [portId]: !prev[portId] };
+      if (portId === "5000" && !next[portId]) {
+        setPort5000Confirmed(false);
+      }
+      return next;
+    });
+  }, []);
+
+  const isHardwareDisabled = useCallback(
+    (hwId: string): boolean => {
+      const hw = hardwareMap.get(hwId);
+      if (!hw) return false;
+      return hw.disabledWhen?.includes(deviceId) ?? false;
+    },
+    [deviceId]
+  );
+
+  const validateShmSize = useCallback((value: string): boolean => {
+    if (!value) return true;
+    return /^\d+(\.\d+)?[bkmgBKMG]{1,2}$/.test(value);
+  }, []);
+
+  const validatePath = useCallback((value: string): boolean => {
+    if (!value) return true;
+    return /^[a-zA-Z0-9_\-/./]+$/.test(value);
+  }, []);
+
+  const handleShmSizeChange = useCallback(
+    (value: string) => {
+      const filtered = value.replace(/[^0-9.bkmgBKMG]/g, "");
+      const valid = validateShmSize(filtered);
+      setShmSize(filtered);
+      setShmSizeError(!valid && filtered !== "");
+    },
+    [validateShmSize]
+  );
+
+  const handleConfigPathChange = useCallback(
+    (value: string) => {
+      const filtered = value.replace(/[^a-zA-Z0-9_\-/./]/g, "");
+      const valid = validatePath(filtered);
+      setConfigPath(filtered);
+      setConfigPathError(!valid && filtered !== "");
+    },
+    [validatePath]
+  );
+
+  const handleMediaPathChange = useCallback(
+    (value: string) => {
+      const filtered = value.replace(/[^a-zA-Z0-9_\-/./]/g, "");
+      const valid = validatePath(filtered);
+      setMediaPath(filtered);
+      setMediaPathError(!valid && filtered !== "");
+    },
+    [validatePath]
+  );
+
+  const handleNvidiaGpuCountChange = useCallback((value: string) => {
+    const lower = value.trim().toLowerCase();
+    if (lower === "all" || lower === "" || /^[0-9]+$/.test(lower)) {
+      setNvidiaGpuCount(lower || "all");
+      if (lower === "all") {
+        setNvidiaGpuDeviceId("");
+        setGpuDeviceIdError(false);
+      } else if (/^[0-9]+$/.test(lower)) {
+        setGpuDeviceIdError(false);
+      }
+    }
+  }, []);
+
+  const handleNvidiaGpuDeviceIdChange = useCallback((value: string) => {
+    setNvidiaGpuDeviceId(value.trim());
+    setGpuDeviceIdError(false);
+  }, []);
+
+  const enabledPortLines = useMemo(() => {
+    const lines: string[] = [];
+    for (const [id, enabled] of Object.entries(portEnabled)) {
+      if (!enabled) continue;
+      if (id === "5000" && !port5000Confirmed) continue;
+      const p = portMap.get(id);
+      if (!p) continue;
+      const proto = p.protocol && p.protocol !== "tcp" ? `/${p.protocol}` : "";
+      const comment = p.description ? ` # ${p.description}` : "";
+      lines.push(`      - "${p.host}:${p.container}${proto}"${comment}`);
+    }
+    return lines;
+  }, [portEnabled, port5000Confirmed]);
+
+  const selectedHardwareIds = useMemo(() => {
+    return Object.entries(hardwareEnabled)
+      .filter(([id, enabled]) => {
+        if (!enabled) return false;
+        const hw = hardwareMap.get(id);
+        if (!hw) return false;
+        if (hw.disabledWhen?.includes(deviceId)) return false;
+        return true;
+      })
+      .map(([id]) => id);
+  }, [hardwareEnabled, deviceId]);
+
+  const generatedYaml = useMemo(() => {
+    const input: GeneratorInput = {
+      device,
+      selectedHardware: selectedHardwareIds,
+      enabledPorts: enabledPortLines,
+      configPath: configPath || "/path/to/your/config",
+      mediaPath: mediaPath || "/path/to/your/storage",
+      rtspPassword: rtspPassword || "password",
+      timezone: timezone || Intl.DateTimeFormat().resolvedOptions().timeZone || "Etc/UTC",
+      shmSize: shmSize || "512mb",
+      nvidiaGpuCount,
+      nvidiaGpuDeviceId,
+    };
+    return generateDockerCompose(input);
+  }, [
+    device, selectedHardwareIds, enabledPortLines,
+    configPath, mediaPath, rtspPassword, timezone, shmSize,
+    nvidiaGpuCount, nvidiaGpuDeviceId,
+  ]);
+
+  const hasAnyHardware = selectedHardwareIds.length > 0 || !!device?.devices?.length;
+
+  return {
+    deviceId, device, hardwareEnabled, portEnabled,
+    port5000Confirmed, nvidiaGpuCount, nvidiaGpuDeviceId,
+    configPath, mediaPath, rtspPassword, timezone, shmSize,
+    shmSizeError, gpuDeviceIdError, configPathError, mediaPathError,
+    hasAnyHardware, generatedYaml,
+    selectDevice, toggleHardware, togglePort, setPort5000Confirmed,
+    handleShmSizeChange, handleConfigPathChange, handleMediaPathChange,
+    handleNvidiaGpuCountChange, handleNvidiaGpuDeviceIdChange,
+    setRtspPassword, setTimezone, isHardwareDisabled,
+  };
+}

docs/src/components/DockerComposeGenerator/hooks/useCooldown.ts

@@ -0,0 +1,42 @@
+import { useState, useEffect, useCallback, useRef } from "react";
+
+/**
+ * Hook for a countdown timer (e.g. cooldown before confirming port 5000).
+ */
+export function useCooldown(initialSeconds: number) {
+  const [remaining, setRemaining] = useState(0);
+  const timerRef = useRef<ReturnType<typeof setInterval> | null>(null);
+
+  const start = useCallback(() => {
+    // Clear any existing timer
+    if (timerRef.current) clearInterval(timerRef.current);
+    setRemaining(initialSeconds);
+    timerRef.current = setInterval(() => {
+      setRemaining((prev) => {
+        if (prev <= 1) {
+          if (timerRef.current) clearInterval(timerRef.current);
+          timerRef.current = null;
+          return 0;
+        }
+        return prev - 1;
+      });
+    }, 1000);
+  }, [initialSeconds]);
+
+  const stop = useCallback(() => {
+    if (timerRef.current) {
+      clearInterval(timerRef.current);
+      timerRef.current = null;
+    }
+    setRemaining(0);
+  }, []);
+
+  // Cleanup on unmount
+  useEffect(() => {
+    return () => {
+      if (timerRef.current) clearInterval(timerRef.current);
+    };
+  }, []);
+
+  return { remaining, start, stop };
+}

docs/src/components/DockerComposeGenerator/index.ts

@@ -0,0 +1 @@
+export { default } from "./DockerComposeGenerator";

docs/src/components/DockerComposeGenerator/styles.module.css

@@ -0,0 +1,362 @@
+/* ===================================================================
+   Docker Compose Generator — styles
+   Uses Docusaurus / Infima CSS variables for theme compatibility.
+   =================================================================== */
+
+.generator {
+  margin: 2rem 0;
+}
+
+.card {
+  background: var(--ifm-background-surface-color);
+  border: 1px solid var(--ifm-color-emphasis-400);
+  border-radius: 12px;
+  padding: 2rem;
+  box-shadow: var(--ifm-global-shadow-lw);
+}
+
+[data-theme="light"] .card {
+  background: var(--ifm-color-emphasis-100);
+  border: 1px solid var(--ifm-color-emphasis-300);
+}
+
+/* --- Form sections --- */
+
+.formSection {
+  margin-bottom: 1.5rem;
+  padding-bottom: 1.5rem;
+  border-bottom: 1px solid var(--ifm-color-emphasis-400);
+}
+
+.formSection:last-child {
+  border-bottom: none;
+  margin-bottom: 0;
+  padding-bottom: 0;
+}
+
+.formSection h4 {
+  margin: 0 0 1rem 0;
+  color: var(--ifm-font-color-base);
+  font-size: 1.1rem;
+  font-weight: var(--ifm-font-weight-semibold);
+}
+
+/* --- Form controls --- */
+
+.formGroup {
+  margin-bottom: 1rem;
+}
+
+.formGroup:last-child {
+  margin-bottom: 0;
+}
+
+.label {
+  display: block;
+  margin-bottom: 0.25rem;
+  color: var(--ifm-font-color-base);
+  font-weight: var(--ifm-font-weight-semibold);
+  font-size: 0.9rem;
+}
+
+.input {
+  width: 100%;
+  padding: 0.5rem 0.75rem;
+  border: 1px solid var(--ifm-color-emphasis-400);
+  border-radius: 6px;
+  background: var(--ifm-background-color);
+  color: var(--ifm-font-color-base);
+  font-size: 0.95rem;
+  transition: border-color 0.2s, box-shadow 0.2s;
+}
+
+[data-theme="light"] .input {
+  background: #fff;
+  border: 1px solid #d0d7de;
+}
+
+.input:focus {
+  outline: none;
+  border-color: var(--ifm-color-primary);
+  box-shadow: 0 0 0 3px var(--ifm-color-primary-lightest);
+}
+
+[data-theme="dark"] .input {
+  border-color: var(--ifm-color-emphasis-300);
+}
+
+.inputError {
+  border-color: #e74c3c;
+  animation: shake 0.3s ease-in-out;
+}
+
+@keyframes shake {
+  0%,
+  100% {
+    transform: translateX(0);
+  }
+  25% {
+    transform: translateX(-5px);
+  }
+  75% {
+    transform: translateX(5px);
+  }
+}
+
+.helpText {
+  margin: 0.5rem 0 0 0;
+  font-size: 0.85rem;
+  color: var(--ifm-font-color-secondary);
+  line-height: 1.5;
+}
+
+.helpText a {
+  color: var(--ifm-color-primary);
+}
+
+/* --- Device grid --- */
+
+.deviceGrid {
+  display: grid;
+  grid-template-columns: repeat(auto-fill, minmax(130px, 1fr));
+  gap: 0.75rem;
+  margin-top: 0.5rem;
+}
+
+.deviceCard {
+  padding: 0.75rem;
+  border: 2px solid var(--ifm-color-emphasis-400);
+  border-radius: 12px;
+  cursor: pointer;
+  transition: all 0.2s;
+  text-align: center;
+  background: var(--ifm-background-color);
+  display: flex;
+  flex-direction: column;
+  align-items: center;
+}
+
+[data-theme="light"] .deviceCard {
+  border: 2px solid #d0d7de;
+  background: #fff;
+}
+
+.deviceCard:hover {
+  border-color: var(--ifm-color-primary);
+  background: var(--ifm-color-emphasis-100);
+  transform: translateY(-2px);
+}
+
+.deviceCardActive {
+  border-color: var(--ifm-color-primary);
+  background: var(--ifm-color-primary-lightest);
+  box-shadow: 0 0 0 1px var(--ifm-color-primary);
+}
+
+[data-theme="light"] .deviceCardActive {
+  background: color-mix(in srgb, var(--ifm-color-primary) 12%, #fff);
+}
+
+[data-theme="dark"] .deviceCardActive {
+  background: color-mix(in srgb, var(--ifm-color-primary) 25%, #1b1b1b);
+}
+
+[data-theme="dark"] .deviceCardActive .deviceName {
+  color: var(--ifm-color-primary-light);
+}
+
+[data-theme="dark"] .deviceCardActive .deviceDesc {
+  color: var(--ifm-color-primary-light);
+  opacity: 0.85;
+}
+
+.deviceIcon {
+  font-size: 2rem;
+  margin-bottom: 0.25rem;
+  height: 40px;
+  width: 50px;
+  display: flex;
+  align-items: center;
+  justify-content: center;
+}
+
+.deviceIconSvg {
+  margin-bottom: 0.25rem;
+  height: 40px;
+  width: 50px;
+  display: flex;
+  align-items: center;
+  justify-content: center;
+  overflow: visible;
+  /* Allow iconStyle width/height to override */
+  flex-shrink: 0;
+}
+
+.deviceIconSvg svg {
+  width: var(--svg-width, 100%);
+  height: var(--svg-height, 100%);
+  fill: var(--svg-fill, currentColor);
+  transform: var(--svg-transform, none);
+}
+
+.deviceIconImage {
+  margin-bottom: 0.25rem;
+  height: 40px;
+  width: 50px;
+  display: flex;
+  align-items: center;
+  justify-content: center;
+}
+
+.deviceIconImage img {
+  max-width: 100%;
+  max-height: 100%;
+  object-fit: contain;
+}
+
+.deviceName {
+  font-weight: var(--ifm-font-weight-semibold);
+  color: var(--ifm-font-color-base);
+  margin-bottom: 0.15rem;
+  font-size: 0.9rem;
+}
+
+.deviceDesc {
+  font-size: 0.75rem;
+  color: var(--ifm-font-color-secondary);
+  line-height: 1.3;
+}
+
+/* --- Checkbox grid --- */
+
+.checkboxGrid {
+  display: grid;
+  grid-template-columns: repeat(2, 1fr);
+  gap: 0.5rem;
+}
+
+@media (max-width: 576px) {
+  .checkboxGrid {
+    grid-template-columns: 1fr;
+  }
+}
+
+.hardwareItem {
+  margin-bottom: 0;
+}
+
+.hardwareDescription {
+  margin: 0.15rem 0 0.4rem 1.6rem;
+  font-size: 0.8rem;
+  color: var(--ifm-font-color-secondary);
+  line-height: 1.5;
+}
+
+.hardwareDescription a {
+  color: var(--ifm-color-primary);
+  text-decoration: underline;
+  text-underline-offset: 2px;
+}
+
+.checkboxLabel {
+  display: flex;
+  align-items: center;
+  gap: 0.5rem;
+  cursor: pointer;
+  padding: 0.4rem 0.5rem;
+  border-radius: 6px;
+  transition: background-color 0.2s;
+  font-size: 0.9rem;
+}
+
+.checkboxLabel:hover {
+  background: var(--ifm-color-emphasis-100);
+}
+
+.checkboxLabel input[type="checkbox"] {
+  width: 1.1rem;
+  height: 1.1rem;
+  cursor: pointer;
+  flex-shrink: 0;
+}
+
+.checkboxLabel span {
+  color: var(--ifm-font-color-base);
+}
+
+.checkboxDisabled {
+  cursor: not-allowed;
+}
+
+.checkboxDisabled:hover {
+  background: transparent;
+}
+
+.checkboxDisabled input[type="checkbox"] {
+  cursor: not-allowed;
+  opacity: 0.5;
+}
+
+/* --- Form grid (side-by-side) --- */
+
+.formGrid {
+  display: grid;
+  grid-template-columns: repeat(2, 1fr);
+  gap: 1rem;
+}
+
+@media (max-width: 576px) {
+  .formGrid {
+    grid-template-columns: 1fr;
+  }
+}
+
+.formGrid .formGroup {
+  margin-bottom: 0;
+}
+
+/* --- Port section --- */
+
+.portSection {
+  margin-bottom: 0.75rem;
+}
+
+.warningBadge {
+  margin-left: auto;
+  color: #e67e22;
+  font-size: 0.85rem;
+}
+
+/* --- NVIDIA config --- */
+
+.nvidiaConfig {
+  margin-top: 1rem;
+  margin-bottom: 1.5rem;
+  padding: 1rem;
+  background: var(--ifm-background-color);
+  border-radius: 8px;
+  border-left: 3px solid var(--ifm-color-primary);
+}
+
+[data-theme="light"] .nvidiaConfig {
+  background: #f6f8fa;
+  border-left: 3px solid var(--ifm-color-primary);
+}
+
+/* --- Result section --- */
+
+.resultSection {
+  margin-top: 2rem;
+}
+
+.resultHeader {
+  display: flex;
+  justify-content: space-between;
+  align-items: center;
+  margin-bottom: 1rem;
+}
+
+.resultHeader h4 {
+  margin: 0;
+  color: var(--ifm-font-color-base);
+}

frigate/api/chat.py

@@ -36,6 +36,7 @@ from frigate.api.defs.response.chat_response import (
 )
 from frigate.api.defs.tags import Tags
 from frigate.api.event import events
+from frigate.config import FrigateConfig
 from frigate.genai.utils import build_assistant_message_for_conversation
 from frigate.jobs.vlm_watch import (
     get_vlm_watch_job,
@@ -401,9 +402,38 @@ def get_tools() -> JSONResponse:
     return JSONResponse(content={"tools": tools})
 
 
+def _resolve_zones(
+    zones: List[str],
+    config: FrigateConfig,
+    target_cameras: List[str],
+) -> List[str]:
+    """Map zone names to their canonical config keys, case-insensitively.
+
+    LLMs frequently echo a user's casing ("Front Yard") instead of the
+    configured key ("front_yard"). The downstream zone filter is a SQLite GLOB
+    over the JSON-encoded zones column, which is case-sensitive — so an
+    unnormalized name silently returns zero matches. Build a lookup over the
+    relevant cameras' configured zones and substitute when we find a match;
+    unknown names pass through so behavior matches what the model asked for.
+    """
+    if not zones:
+        return zones
+
+    lookup: Dict[str, str] = {}
+    for camera_id in target_cameras:
+        camera_config = config.cameras.get(camera_id)
+        if camera_config is None:
+            continue
+        for zone_name in camera_config.zones.keys():
+            lookup.setdefault(zone_name.lower(), zone_name)
+
+    return [lookup.get(z.lower(), z) for z in zones]
+
+
 async def _execute_search_objects(
     arguments: Dict[str, Any],
     allowed_cameras: List[str],
+    config: FrigateConfig,
 ) -> JSONResponse:
     """
     Execute the search_objects tool.
@@ -437,6 +467,11 @@ async def _execute_search_objects(
     # Convert zones array to comma-separated string if provided
     zones = arguments.get("zones")
     if isinstance(zones, list):
+        camera_arg = arguments.get("camera")
+        target_cameras = (
+            [camera_arg] if camera_arg and camera_arg != "all" else allowed_cameras
+        )
+        zones = _resolve_zones(zones, config, target_cameras)
         zones = ",".join(zones)
     elif zones is None:
         zones = "all"
@@ -528,6 +563,11 @@ async def _execute_find_similar_objects(
     sub_labels = arguments.get("sub_labels")
     zones = arguments.get("zones")
 
+    if zones:
+        zones = _resolve_zones(
+            zones, request.app.frigate_config, cameras or list(allowed_cameras)
+        )
+
     similarity_mode = arguments.get("similarity_mode", "fused")
     if similarity_mode not in ("visual", "semantic", "fused"):
         similarity_mode = "fused"
@@ -655,7 +695,9 @@ async def execute_tool(
     logger.debug(f"Executing tool: {tool_name} with arguments: {arguments}")
 
     if tool_name == "search_objects":
-        return await _execute_search_objects(arguments, allowed_cameras)
+        return await _execute_search_objects(
+            arguments, allowed_cameras, request.app.frigate_config
+        )
 
     if tool_name == "find_similar_objects":
         result = await _execute_find_similar_objects(
@@ -835,7 +877,9 @@ async def _execute_tool_internal(
     This is used by the chat completion endpoint to execute tools.
     """
     if tool_name == "search_objects":
-        response = await _execute_search_objects(arguments, allowed_cameras)
+        response = await _execute_search_objects(
+            arguments, allowed_cameras, request.app.frigate_config
+        )
         try:
             if hasattr(response, "body"):
                 body_str = response.body.decode("utf-8")
@@ -899,6 +943,9 @@ async def _execute_start_camera_watch(
 
     await require_camera_access(camera, request=request)
 
+    if zones:
+        zones = _resolve_zones(zones, config, [camera])
+
     genai_manager = request.app.genai_manager
     chat_client = genai_manager.chat_client
     if chat_client is None or not chat_client.supports_vision:

frigate/data_processing/post/review_descriptions.py

@@ -39,6 +39,8 @@ logger = logging.getLogger(__name__)
 
 RECORDING_BUFFER_EXTENSION_PERCENT = 0.10
 MIN_RECORDING_DURATION = 10
+MAX_IMAGE_TOKENS = 24000
+MAX_FRAMES_PER_SECOND = 2
 
 
 class ReviewDescriptionProcessor(PostProcessorApi):
@@ -60,14 +62,22 @@ class ReviewDescriptionProcessor(PostProcessorApi):
     def calculate_frame_count(
         self,
         camera: str,
+        duration: float,
         image_source: ImageSourceEnum = ImageSourceEnum.preview,
         height: int = 480,
     ) -> int:
-        """Calculate optimal number of frames based on context size, image source, and resolution.
+        """Calculate optimal number of frames based on event duration, context size,
+        image source, and resolution.
 
-        Token usage varies by resolution: larger images (ultra-wide aspect ratios) use more tokens.
-        Estimates ~1 token per 1250 pixels. Targets 98% context utilization with safety margin.
-        Capped at 20 frames.
+        Per-image token cost is asked of the GenAI provider so providers that know
+        their model's true cost (e.g. llama.cpp can probe the loaded mmproj) can
+        diverge from the default ~1-token-per-1250-pixels heuristic. The frame
+        budget is bounded by:
+          - remaining context window after prompt + response reservations
+          - a fixed MAX_IMAGE_TOKENS ceiling
+          - MAX_FRAMES_PER_SECOND x duration, to avoid drowning short events in
+            near-duplicate frames where the model latches onto the redundant middle
+            and skips the start/end action
         """
         client = self.genai_manager.description_client
 
@@ -105,14 +115,15 @@ class ReviewDescriptionProcessor(PostProcessorApi):
                 width = target_width
                 height = int(target_width / aspect_ratio)
 
-        pixels_per_image = width * height
-        tokens_per_image = pixels_per_image / 1250
+        tokens_per_image = client.estimate_image_tokens(width, height)
         prompt_tokens = 3800
         response_tokens = 300
-        available_tokens = context_size - prompt_tokens - response_tokens
-        max_frames = int(available_tokens / tokens_per_image)
-
-        return min(max(max_frames, 3), 20)
+        context_budget = context_size - prompt_tokens - response_tokens
+        image_token_budget = min(context_budget, MAX_IMAGE_TOKENS)
+        max_frames_by_tokens = int(image_token_budget / tokens_per_image)
+        max_frames_by_duration = int(duration * MAX_FRAMES_PER_SECOND)
+        max_frames = min(max_frames_by_tokens, max_frames_by_duration)
+        return max(max_frames, 3)
 
     def process_data(
         self, data: dict[str, Any], data_type: PostProcessDataEnum
@@ -376,7 +387,9 @@ class ReviewDescriptionProcessor(PostProcessorApi):
             all_frames.append(os.path.join(preview_dir, file))
 
         frame_count = len(all_frames)
-        desired_frame_count = self.calculate_frame_count(camera)
+        desired_frame_count = self.calculate_frame_count(
+            camera, duration=end_time - start_time
+        )
 
         if frame_count <= desired_frame_count:
             return all_frames
@@ -400,7 +413,7 @@ class ReviewDescriptionProcessor(PostProcessorApi):
         """Get frames from recordings at specified timestamps."""
         duration = end_time - start_time
         desired_frame_count = self.calculate_frame_count(
-            camera, ImageSourceEnum.recordings, height
+            camera, duration, ImageSourceEnum.recordings, height
         )
 
         # Calculate evenly spaced timestamps throughout the duration

frigate/data_processing/post/types.py

@@ -4,6 +4,10 @@ from pydantic import BaseModel, ConfigDict, Field
 class ReviewMetadata(BaseModel):
     model_config = ConfigDict(extra="ignore", protected_namespaces=())
 
+    observations: list[str] = Field(
+        default_factory=list,
+        description="Chronological list of significant observations from the frames, written before the scene narrative is composed.",
+    )
     title: str = Field(
         description="A short title characterizing what took place and where, under 10 words."
     )

frigate/genai/__init__.py

@@ -163,6 +163,38 @@ Each line represents a detection state, not necessarily unique individuals. The
             if prop is not None:
                 prop.update(hints)
 
+        # observations is a chain-of-thought-by-schema field: forcing the model
+        # to enumerate concrete facts before writing scene/title surfaces details
+        # the narrative would otherwise gloss past (e.g. brief vehicle arrivals
+        # overshadowed by a longer activity). The minItems floor scales with
+        # event duration so longer clips get more observations.
+        observations_prop = schema.get("properties", {}).get("observations")
+        if observations_prop is not None:
+            duration_seconds = float(review_data.get("duration") or 0)
+            min_observations = max(3, round(duration_seconds / 5))
+            max_observations = min_observations + 8
+            observations_prop["description"] = (
+                "Enumerate the significant observations across all frames, in "
+                "chronological order, BEFORE composing the scene narrative. "
+                "Include the very start of the activity — for example, a "
+                "vehicle entering the frame or pulling into the driveway — "
+                "even if it lasts only a few frames and the rest of the clip "
+                "is dominated by a longer activity. Include each arrival, "
+                "departure, motion event, object handled, and notable change "
+                "in position or state. Each item is a single concrete fact "
+                "written as a complete sentence (e.g., 'A blue sedan turns "
+                "from the street into the driveway', 'Nick exits the driver "
+                "side carrying a plant pot'). Do not summarize, interpret, or "
+                "assign meaning here — that belongs in the scene field."
+            )
+            observations_prop["minItems"] = min_observations
+            observations_prop["maxItems"] = max_observations
+            observations_prop["items"] = {"type": "string", "minLength": 20}
+
+            required = schema.setdefault("required", [])
+            if "observations" not in required:
+                required.append("observations")
+
         # OpenAI strict mode requires additionalProperties: false on all objects
         schema["additionalProperties"] = False
 
@@ -356,6 +388,14 @@ Guidelines:
         """Get the context window size for this provider in tokens."""
         return 4096
 
+    def estimate_image_tokens(self, width: int, height: int) -> float:
+        """Estimate prompt tokens consumed by a single image of the given dimensions.
+
+        Default heuristic: ~1 token per 1250 pixels. Providers that can measure or
+        know their model's exact image-token cost should override.
+        """
+        return (width * height) / 1250
+
     def embed(
         self,
         texts: list[str] | None = None,

frigate/genai/llama_cpp.py

@@ -42,6 +42,8 @@ class LlamaCppClient(GenAIClient):
     _supports_vision: bool
     _supports_audio: bool
     _supports_tools: bool
+    _image_token_cache: dict[tuple[int, int], int]
+    _text_baseline_tokens: int | None
 
     def _init_provider(self) -> str | None:
         """Initialize the client and query model metadata from the server."""
@@ -52,6 +54,8 @@ class LlamaCppClient(GenAIClient):
         self._supports_vision = False
         self._supports_audio = False
         self._supports_tools = False
+        self._image_token_cache = {}
+        self._text_baseline_tokens = None
 
         base_url = (
             self.genai_config.base_url.rstrip("/")
@@ -272,6 +276,91 @@ class LlamaCppClient(GenAIClient):
             return self._context_size
         return 4096
 
+    def estimate_image_tokens(self, width: int, height: int) -> float:
+        """Probe the llama.cpp server to learn the model's image-token cost at the
+        requested dimensions.
+
+        llama.cpp's image tokenization is a deterministic function of dimensions and
+        the loaded mmproj, so the result is cached per (width, height) for the
+        lifetime of the process. Falls back to the base pixel heuristic if the
+        server is unreachable or the response is malformed.
+        """
+        if self.provider is None:
+            return super().estimate_image_tokens(width, height)
+
+        cached = self._image_token_cache.get((width, height))
+
+        if cached is not None:
+            return cached
+
+        try:
+            baseline = self._probe_baseline_tokens()
+            with_image = self._probe_image_prompt_tokens(width, height)
+            tokens = max(1, with_image - baseline)
+        except Exception as e:
+            logger.debug(
+                "llama.cpp image-token probe failed for %dx%d (%s); using heuristic",
+                width,
+                height,
+                e,
+            )
+            return super().estimate_image_tokens(width, height)
+
+        self._image_token_cache[(width, height)] = tokens
+        logger.debug(
+            "llama.cpp model '%s' uses ~%d tokens for %dx%d images",
+            self.genai_config.model,
+            tokens,
+            width,
+            height,
+        )
+        return tokens
+
+    def _probe_baseline_tokens(self) -> int:
+        """Return prompt_tokens for a minimal text-only request. Cached after first call."""
+        if self._text_baseline_tokens is not None:
+            return self._text_baseline_tokens
+
+        self._text_baseline_tokens = self._probe_prompt_tokens(
+            [{"type": "text", "text": "."}]
+        )
+        return self._text_baseline_tokens
+
+    def _probe_image_prompt_tokens(self, width: int, height: int) -> int:
+        """Return prompt_tokens for a single synthetic image plus minimal text."""
+        img = Image.new("RGB", (width, height), (128, 128, 128))
+        buf = io.BytesIO()
+        img.save(buf, format="JPEG", quality=60)
+        encoded = base64.b64encode(buf.getvalue()).decode("utf-8")
+        return self._probe_prompt_tokens(
+            [
+                {"type": "text", "text": "."},
+                {
+                    "type": "image_url",
+                    "image_url": {"url": f"data:image/jpeg;base64,{encoded}"},
+                },
+            ]
+        )
+
+    def _probe_prompt_tokens(self, content: list[dict[str, Any]]) -> int:
+        """POST a 1-token chat completion and return reported prompt_tokens.
+
+        Uses a generous timeout to absorb a cold model load on the first probe
+        when the server lazily loads models on demand (e.g. llama-swap).
+        """
+        payload = {
+            "model": self.genai_config.model,
+            "messages": [{"role": "user", "content": content}],
+            "max_tokens": 1,
+        }
+        response = requests.post(
+            f"{self.provider}/v1/chat/completions",
+            json=payload,
+            timeout=60,
+        )
+        response.raise_for_status()
+        return int(response.json()["usage"]["prompt_tokens"])
+
     def _build_payload(
         self,
         messages: list[dict[str, Any]],

web/src/components/chat/ChatMessage.tsx

@@ -155,14 +155,40 @@ export function MessageBubble({
         ) : (
           <div
             className={cn(
-              "[&>*:last-child]:inline",
               !isComplete &&
-                "after:ml-0.5 after:inline-block after:h-4 after:w-2 after:animate-cursor-blink after:rounded-sm after:bg-foreground after:align-middle after:content-['']",
+                "[&>p:last-child]:inline after:ml-0.5 after:inline-block after:h-4 after:w-2 after:animate-cursor-blink after:rounded-sm after:bg-foreground after:align-middle after:content-['']",
             )}
           >
             <ReactMarkdown
               remarkPlugins={[remarkGfm]}
               components={{
+                p: ({ node: _n, ...props }) => (
+                  <p className="my-2 first:mt-0 last:mb-0" {...props} />
+                ),
+                ul: ({ node: _n, ...props }) => (
+                  <ul
+                    className="my-2 list-disc space-y-1 pl-6 first:mt-0 last:mb-0"
+                    {...props}
+                  />
+                ),
+                ol: ({ node: _n, ...props }) => (
+                  <ol
+                    className="my-2 list-decimal space-y-1 pl-6 first:mt-0 last:mb-0"
+                    {...props}
+                  />
+                ),
+                li: ({ node: _n, ...props }) => (
+                  <li className="pl-1" {...props} />
+                ),
+                code: ({ node: _n, className, ...props }) => (
+                  <code
+                    className={cn(
+                      "rounded bg-foreground/10 px-1 py-0.5 font-mono text-sm",
+                      className,
+                    )}
+                    {...props}
+                  />
+                ),
                 table: ({ node: _n, ...props }) => (
                   <table
                     className="my-2 w-full border-collapse border border-border"