feat: add firecrawl onboarding search plugin

extensions/firecrawl/src/config.ts

@@ -0,0 +1,159 @@
+import type { OpenClawConfig } from "../../../src/config/config.js";
+import { normalizeResolvedSecretInputString } from "../../../src/config/types.secrets.js";
+import { normalizeSecretInput } from "../../../src/utils/normalize-secret-input.js";
+
+export const DEFAULT_FIRECRAWL_BASE_URL = "https://api.firecrawl.dev";
+export const DEFAULT_FIRECRAWL_SEARCH_TIMEOUT_SECONDS = 30;
+export const DEFAULT_FIRECRAWL_SCRAPE_TIMEOUT_SECONDS = 60;
+export const DEFAULT_FIRECRAWL_MAX_AGE_MS = 172_800_000;
+
+type WebSearchConfig = NonNullable<OpenClawConfig["tools"]>["web"] extends infer Web
+  ? Web extends { search?: infer Search }
+    ? Search
+    : undefined
+  : undefined;
+
+type WebFetchConfig = NonNullable<OpenClawConfig["tools"]>["web"] extends infer Web
+  ? Web extends { fetch?: infer Fetch }
+    ? Fetch
+    : undefined
+  : undefined;
+
+type FirecrawlSearchConfig =
+  | {
+      apiKey?: unknown;
+      baseUrl?: string;
+    }
+  | undefined;
+
+type FirecrawlFetchConfig =
+  | {
+      apiKey?: unknown;
+      baseUrl?: string;
+      onlyMainContent?: boolean;
+      maxAgeMs?: number;
+      timeoutSeconds?: number;
+    }
+  | undefined;
+
+function resolveSearchConfig(cfg?: OpenClawConfig): WebSearchConfig {
+  const search = cfg?.tools?.web?.search;
+  if (!search || typeof search !== "object") {
+    return undefined;
+  }
+  return search as WebSearchConfig;
+}
+
+function resolveFetchConfig(cfg?: OpenClawConfig): WebFetchConfig {
+  const fetch = cfg?.tools?.web?.fetch;
+  if (!fetch || typeof fetch !== "object") {
+    return undefined;
+  }
+  return fetch as WebFetchConfig;
+}
+
+export function resolveFirecrawlSearchConfig(cfg?: OpenClawConfig): FirecrawlSearchConfig {
+  const search = resolveSearchConfig(cfg);
+  if (!search || typeof search !== "object") {
+    return undefined;
+  }
+  const firecrawl = "firecrawl" in search ? search.firecrawl : undefined;
+  if (!firecrawl || typeof firecrawl !== "object") {
+    return undefined;
+  }
+  return firecrawl as FirecrawlSearchConfig;
+}
+
+export function resolveFirecrawlFetchConfig(cfg?: OpenClawConfig): FirecrawlFetchConfig {
+  const fetch = resolveFetchConfig(cfg);
+  if (!fetch || typeof fetch !== "object") {
+    return undefined;
+  }
+  const firecrawl = "firecrawl" in fetch ? fetch.firecrawl : undefined;
+  if (!firecrawl || typeof firecrawl !== "object") {
+    return undefined;
+  }
+  return firecrawl as FirecrawlFetchConfig;
+}
+
+function normalizeConfiguredSecret(value: unknown, path: string): string | undefined {
+  return normalizeSecretInput(
+    normalizeResolvedSecretInputString({
+      value,
+      path,
+    }),
+  );
+}
+
+export function resolveFirecrawlApiKey(cfg?: OpenClawConfig): string | undefined {
+  const search = resolveFirecrawlSearchConfig(cfg);
+  const fetch = resolveFirecrawlFetchConfig(cfg);
+  return (
+    normalizeConfiguredSecret(search?.apiKey, "tools.web.search.firecrawl.apiKey") ||
+    normalizeConfiguredSecret(fetch?.apiKey, "tools.web.fetch.firecrawl.apiKey") ||
+    normalizeSecretInput(process.env.FIRECRAWL_API_KEY) ||
+    undefined
+  );
+}
+
+export function resolveFirecrawlBaseUrl(cfg?: OpenClawConfig): string {
+  const search = resolveFirecrawlSearchConfig(cfg);
+  const fetch = resolveFirecrawlFetchConfig(cfg);
+  const configured =
+    (typeof search?.baseUrl === "string" ? search.baseUrl.trim() : "") ||
+    (typeof fetch?.baseUrl === "string" ? fetch.baseUrl.trim() : "") ||
+    normalizeSecretInput(process.env.FIRECRAWL_BASE_URL) ||
+    "";
+  return configured || DEFAULT_FIRECRAWL_BASE_URL;
+}
+
+export function resolveFirecrawlOnlyMainContent(cfg?: OpenClawConfig, override?: boolean): boolean {
+  if (typeof override === "boolean") {
+    return override;
+  }
+  const fetch = resolveFirecrawlFetchConfig(cfg);
+  if (typeof fetch?.onlyMainContent === "boolean") {
+    return fetch.onlyMainContent;
+  }
+  return true;
+}
+
+export function resolveFirecrawlMaxAgeMs(cfg?: OpenClawConfig, override?: number): number {
+  if (typeof override === "number" && Number.isFinite(override) && override >= 0) {
+    return Math.floor(override);
+  }
+  const fetch = resolveFirecrawlFetchConfig(cfg);
+  if (
+    typeof fetch?.maxAgeMs === "number" &&
+    Number.isFinite(fetch.maxAgeMs) &&
+    fetch.maxAgeMs >= 0
+  ) {
+    return Math.floor(fetch.maxAgeMs);
+  }
+  return DEFAULT_FIRECRAWL_MAX_AGE_MS;
+}
+
+export function resolveFirecrawlScrapeTimeoutSeconds(
+  cfg?: OpenClawConfig,
+  override?: number,
+): number {
+  if (typeof override === "number" && Number.isFinite(override) && override > 0) {
+    return Math.floor(override);
+  }
+  const fetch = resolveFirecrawlFetchConfig(cfg);
+  if (
+    typeof fetch?.timeoutSeconds === "number" &&
+    Number.isFinite(fetch.timeoutSeconds) &&
+    fetch.timeoutSeconds > 0
+  ) {
+    return Math.floor(fetch.timeoutSeconds);
+  }
+  return DEFAULT_FIRECRAWL_SCRAPE_TIMEOUT_SECONDS;
+}
+
+export function resolveFirecrawlSearchTimeoutSeconds(override?: number): number {
+  if (typeof override === "number" && Number.isFinite(override) && override > 0) {
+    return Math.floor(override);
+  }
+  return DEFAULT_FIRECRAWL_SEARCH_TIMEOUT_SECONDS;
+}

extensions/firecrawl/src/firecrawl-client.ts

@@ -0,0 +1,446 @@
+import { markdownToText, truncateText } from "../../../src/agents/tools/web-fetch-utils.js";
+import { withTrustedWebToolsEndpoint } from "../../../src/agents/tools/web-guarded-fetch.js";
+import {
+  DEFAULT_CACHE_TTL_MINUTES,
+  normalizeCacheKey,
+  readCache,
+  readResponseText,
+  resolveCacheTtlMs,
+  writeCache,
+} from "../../../src/agents/tools/web-shared.js";
+import type { OpenClawConfig } from "../../../src/config/config.js";
+import { wrapExternalContent, wrapWebContent } from "../../../src/security/external-content.js";
+import {
+  resolveFirecrawlApiKey,
+  resolveFirecrawlBaseUrl,
+  resolveFirecrawlMaxAgeMs,
+  resolveFirecrawlOnlyMainContent,
+  resolveFirecrawlScrapeTimeoutSeconds,
+  resolveFirecrawlSearchTimeoutSeconds,
+} from "./config.js";
+
+const SEARCH_CACHE = new Map<
+  string,
+  { value: Record<string, unknown>; expiresAt: number; insertedAt: number }
+>();
+const SCRAPE_CACHE = new Map<
+  string,
+  { value: Record<string, unknown>; expiresAt: number; insertedAt: number }
+>();
+const DEFAULT_SEARCH_COUNT = 5;
+const DEFAULT_SCRAPE_MAX_CHARS = 50_000;
+const DEFAULT_ERROR_MAX_BYTES = 64_000;
+
+type FirecrawlSearchItem = {
+  title: string;
+  url: string;
+  description?: string;
+  content?: string;
+  published?: string;
+  siteName?: string;
+};
+
+export type FirecrawlSearchParams = {
+  cfg?: OpenClawConfig;
+  query: string;
+  count?: number;
+  timeoutSeconds?: number;
+  sources?: string[];
+  categories?: string[];
+  scrapeResults?: boolean;
+};
+
+export type FirecrawlScrapeParams = {
+  cfg?: OpenClawConfig;
+  url: string;
+  extractMode: "markdown" | "text";
+  maxChars?: number;
+  onlyMainContent?: boolean;
+  maxAgeMs?: number;
+  proxy?: "auto" | "basic" | "stealth";
+  storeInCache?: boolean;
+  timeoutSeconds?: number;
+};
+
+function resolveEndpoint(baseUrl: string, pathname: "/v2/search" | "/v2/scrape"): string {
+  const trimmed = baseUrl.trim();
+  if (!trimmed) {
+    return new URL(pathname, "https://api.firecrawl.dev").toString();
+  }
+  try {
+    const url = new URL(trimmed);
+    if (url.pathname && url.pathname !== "/") {
+      return url.toString();
+    }
+    url.pathname = pathname;
+    return url.toString();
+  } catch {
+    return new URL(pathname, "https://api.firecrawl.dev").toString();
+  }
+}
+
+function resolveSiteName(urlRaw: string): string | undefined {
+  try {
+    const host = new URL(urlRaw).hostname.replace(/^www\./, "");
+    return host || undefined;
+  } catch {
+    return undefined;
+  }
+}
+
+async function postFirecrawlJson(params: {
+  baseUrl: string;
+  pathname: "/v2/search" | "/v2/scrape";
+  apiKey: string;
+  body: Record<string, unknown>;
+  timeoutSeconds: number;
+  errorLabel: string;
+}): Promise<Record<string, unknown>> {
+  const endpoint = resolveEndpoint(params.baseUrl, params.pathname);
+  return await withTrustedWebToolsEndpoint(
+    {
+      url: endpoint,
+      timeoutSeconds: params.timeoutSeconds,
+      init: {
+        method: "POST",
+        headers: {
+          Accept: "application/json",
+          Authorization: `Bearer ${params.apiKey}`,
+          "Content-Type": "application/json",
+        },
+        body: JSON.stringify(params.body),
+      },
+    },
+    async ({ response }) => {
+      if (!response.ok) {
+        const detail = await readResponseText(response, { maxBytes: DEFAULT_ERROR_MAX_BYTES });
+        throw new Error(
+          `${params.errorLabel} API error (${response.status}): ${detail.text || response.statusText}`,
+        );
+      }
+      const payload = (await response.json()) as Record<string, unknown>;
+      if (payload.success === false) {
+        const error =
+          typeof payload.error === "string"
+            ? payload.error
+            : typeof payload.message === "string"
+              ? payload.message
+              : "unknown error";
+        throw new Error(`${params.errorLabel} API error: ${error}`);
+      }
+      return payload;
+    },
+  );
+}
+
+function resolveSearchItems(payload: Record<string, unknown>): FirecrawlSearchItem[] {
+  const candidates = [
+    payload.data,
+    payload.results,
+    (payload.data as { results?: unknown } | undefined)?.results,
+    (payload.data as { data?: unknown } | undefined)?.data,
+    (payload.data as { web?: unknown } | undefined)?.web,
+    (payload.web as { results?: unknown } | undefined)?.results,
+  ];
+  const rawItems = candidates.find((candidate) => Array.isArray(candidate));
+  if (!Array.isArray(rawItems)) {
+    return [];
+  }
+  const items: FirecrawlSearchItem[] = [];
+  for (const entry of rawItems) {
+    if (!entry || typeof entry !== "object") {
+      continue;
+    }
+    const record = entry as Record<string, unknown>;
+    const metadata =
+      record.metadata && typeof record.metadata === "object"
+        ? (record.metadata as Record<string, unknown>)
+        : undefined;
+    const url =
+      (typeof record.url === "string" && record.url) ||
+      (typeof record.sourceURL === "string" && record.sourceURL) ||
+      (typeof record.sourceUrl === "string" && record.sourceUrl) ||
+      (typeof metadata?.sourceURL === "string" && metadata.sourceURL) ||
+      "";
+    if (!url) {
+      continue;
+    }
+    const title =
+      (typeof record.title === "string" && record.title) ||
+      (typeof metadata?.title === "string" && metadata.title) ||
+      "";
+    const description =
+      (typeof record.description === "string" && record.description) ||
+      (typeof record.snippet === "string" && record.snippet) ||
+      (typeof record.summary === "string" && record.summary) ||
+      undefined;
+    const content =
+      (typeof record.markdown === "string" && record.markdown) ||
+      (typeof record.content === "string" && record.content) ||
+      (typeof record.text === "string" && record.text) ||
+      undefined;
+    const published =
+      (typeof record.publishedDate === "string" && record.publishedDate) ||
+      (typeof record.published === "string" && record.published) ||
+      (typeof metadata?.publishedTime === "string" && metadata.publishedTime) ||
+      (typeof metadata?.publishedDate === "string" && metadata.publishedDate) ||
+      undefined;
+    items.push({
+      title,
+      url,
+      description,
+      content,
+      published,
+      siteName: resolveSiteName(url),
+    });
+  }
+  return items;
+}
+
+function buildSearchPayload(params: {
+  query: string;
+  provider: "firecrawl";
+  items: FirecrawlSearchItem[];
+  tookMs: number;
+  scrapeResults: boolean;
+}): Record<string, unknown> {
+  return {
+    query: params.query,
+    provider: params.provider,
+    count: params.items.length,
+    tookMs: params.tookMs,
+    externalContent: {
+      untrusted: true,
+      source: "web_search",
+      provider: params.provider,
+      wrapped: true,
+    },
+    results: params.items.map((entry) => ({
+      title: entry.title ? wrapWebContent(entry.title, "web_search") : "",
+      url: entry.url,
+      description: entry.description ? wrapWebContent(entry.description, "web_search") : "",
+      ...(entry.published ? { published: entry.published } : {}),
+      ...(entry.siteName ? { siteName: entry.siteName } : {}),
+      ...(params.scrapeResults && entry.content
+        ? { content: wrapWebContent(entry.content, "web_search") }
+        : {}),
+    })),
+  };
+}
+
+export async function runFirecrawlSearch(
+  params: FirecrawlSearchParams,
+): Promise<Record<string, unknown>> {
+  const apiKey = resolveFirecrawlApiKey(params.cfg);
+  if (!apiKey) {
+    throw new Error(
+      "web_search (firecrawl) needs a Firecrawl API key. Set FIRECRAWL_API_KEY in the Gateway environment, or configure tools.web.search.firecrawl.apiKey.",
+    );
+  }
+  const count =
+    typeof params.count === "number" && Number.isFinite(params.count)
+      ? Math.max(1, Math.min(10, Math.floor(params.count)))
+      : DEFAULT_SEARCH_COUNT;
+  const timeoutSeconds = resolveFirecrawlSearchTimeoutSeconds(params.timeoutSeconds);
+  const scrapeResults = params.scrapeResults === true;
+  const sources = Array.isArray(params.sources) ? params.sources.filter(Boolean) : [];
+  const categories = Array.isArray(params.categories) ? params.categories.filter(Boolean) : [];
+  const baseUrl = resolveFirecrawlBaseUrl(params.cfg);
+  const cacheKey = normalizeCacheKey(
+    JSON.stringify({
+      type: "firecrawl-search",
+      q: params.query,
+      count,
+      baseUrl,
+      sources,
+      categories,
+      scrapeResults,
+    }),
+  );
+  const cached = readCache(SEARCH_CACHE, cacheKey);
+  if (cached) {
+    return { ...cached.value, cached: true };
+  }
+
+  const body: Record<string, unknown> = {
+    query: params.query,
+    limit: count,
+  };
+  if (sources.length > 0) {
+    body.sources = sources;
+  }
+  if (categories.length > 0) {
+    body.categories = categories;
+  }
+  if (scrapeResults) {
+    body.scrapeOptions = {
+      formats: ["markdown"],
+    };
+  }
+
+  const start = Date.now();
+  const payload = await postFirecrawlJson({
+    baseUrl,
+    pathname: "/v2/search",
+    apiKey,
+    body,
+    timeoutSeconds,
+    errorLabel: "Firecrawl Search",
+  });
+  const result = buildSearchPayload({
+    query: params.query,
+    provider: "firecrawl",
+    items: resolveSearchItems(payload),
+    tookMs: Date.now() - start,
+    scrapeResults,
+  });
+  writeCache(
+    SEARCH_CACHE,
+    cacheKey,
+    result,
+    resolveCacheTtlMs(undefined, DEFAULT_CACHE_TTL_MINUTES),
+  );
+  return result;
+}
+
+function resolveScrapeData(payload: Record<string, unknown>): Record<string, unknown> {
+  const data = payload.data;
+  if (data && typeof data === "object") {
+    return data as Record<string, unknown>;
+  }
+  return {};
+}
+
+export function parseFirecrawlScrapePayload(params: {
+  payload: Record<string, unknown>;
+  url: string;
+  extractMode: "markdown" | "text";
+  maxChars: number;
+}): Record<string, unknown> {
+  const data = resolveScrapeData(params.payload);
+  const metadata =
+    data.metadata && typeof data.metadata === "object"
+      ? (data.metadata as Record<string, unknown>)
+      : undefined;
+  const markdown =
+    (typeof data.markdown === "string" && data.markdown) ||
+    (typeof data.content === "string" && data.content) ||
+    "";
+  if (!markdown) {
+    throw new Error("Firecrawl scrape returned no content.");
+  }
+  const rawText = params.extractMode === "text" ? markdownToText(markdown) : markdown;
+  const truncated = truncateText(rawText, params.maxChars);
+  return {
+    url: params.url,
+    finalUrl:
+      (typeof metadata?.sourceURL === "string" && metadata.sourceURL) ||
+      (typeof data.url === "string" && data.url) ||
+      params.url,
+    status:
+      (typeof metadata?.statusCode === "number" && metadata.statusCode) ||
+      (typeof data.statusCode === "number" && data.statusCode) ||
+      undefined,
+    title:
+      typeof metadata?.title === "string" && metadata.title
+        ? wrapExternalContent(metadata.title, { source: "web_fetch", includeWarning: false })
+        : undefined,
+    extractor: "firecrawl",
+    extractMode: params.extractMode,
+    externalContent: {
+      untrusted: true,
+      source: "web_fetch",
+      wrapped: true,
+    },
+    truncated: truncated.truncated,
+    rawLength: rawText.length,
+    wrappedLength: wrapExternalContent(truncated.text, {
+      source: "web_fetch",
+      includeWarning: false,
+    }).length,
+    text: wrapExternalContent(truncated.text, {
+      source: "web_fetch",
+      includeWarning: false,
+    }),
+    warning:
+      typeof params.payload.warning === "string" && params.payload.warning
+        ? wrapExternalContent(params.payload.warning, {
+            source: "web_fetch",
+            includeWarning: false,
+          })
+        : undefined,
+  };
+}
+
+export async function runFirecrawlScrape(
+  params: FirecrawlScrapeParams,
+): Promise<Record<string, unknown>> {
+  const apiKey = resolveFirecrawlApiKey(params.cfg);
+  if (!apiKey) {
+    throw new Error(
+      "firecrawl_scrape needs a Firecrawl API key. Set FIRECRAWL_API_KEY in the Gateway environment, or configure tools.web.fetch.firecrawl.apiKey.",
+    );
+  }
+  const baseUrl = resolveFirecrawlBaseUrl(params.cfg);
+  const timeoutSeconds = resolveFirecrawlScrapeTimeoutSeconds(params.cfg, params.timeoutSeconds);
+  const onlyMainContent = resolveFirecrawlOnlyMainContent(params.cfg, params.onlyMainContent);
+  const maxAgeMs = resolveFirecrawlMaxAgeMs(params.cfg, params.maxAgeMs);
+  const proxy = params.proxy ?? "auto";
+  const storeInCache = params.storeInCache ?? true;
+  const maxChars =
+    typeof params.maxChars === "number" && Number.isFinite(params.maxChars) && params.maxChars > 0
+      ? Math.floor(params.maxChars)
+      : DEFAULT_SCRAPE_MAX_CHARS;
+  const cacheKey = normalizeCacheKey(
+    JSON.stringify({
+      type: "firecrawl-scrape",
+      url: params.url,
+      extractMode: params.extractMode,
+      baseUrl,
+      onlyMainContent,
+      maxAgeMs,
+      proxy,
+      storeInCache,
+      maxChars,
+    }),
+  );
+  const cached = readCache(SCRAPE_CACHE, cacheKey);
+  if (cached) {
+    return { ...cached.value, cached: true };
+  }
+
+  const payload = await postFirecrawlJson({
+    baseUrl,
+    pathname: "/v2/scrape",
+    apiKey,
+    timeoutSeconds,
+    errorLabel: "Firecrawl",
+    body: {
+      url: params.url,
+      formats: ["markdown"],
+      onlyMainContent,
+      timeout: timeoutSeconds * 1000,
+      maxAge: maxAgeMs,
+      proxy,
+      storeInCache,
+    },
+  });
+  const result = parseFirecrawlScrapePayload({
+    payload,
+    url: params.url,
+    extractMode: params.extractMode,
+    maxChars,
+  });
+  writeCache(
+    SCRAPE_CACHE,
+    cacheKey,
+    result,
+    resolveCacheTtlMs(undefined, DEFAULT_CACHE_TTL_MINUTES),
+  );
+  return result;
+}
+
+export const __testing = {
+  parseFirecrawlScrapePayload,
+  resolveSearchItems,
+};

extensions/firecrawl/src/firecrawl-scrape-tool.ts

@@ -0,0 +1,89 @@
+import { Type } from "@sinclair/typebox";
+import { optionalStringEnum } from "../../../src/agents/schema/typebox.js";
+import { jsonResult, readNumberParam, readStringParam } from "../../../src/agents/tools/common.js";
+import type { OpenClawPluginApi } from "../../../src/plugins/types.js";
+import { runFirecrawlScrape } from "./firecrawl-client.js";
+
+const FirecrawlScrapeToolSchema = Type.Object(
+  {
+    url: Type.String({ description: "HTTP or HTTPS URL to scrape via Firecrawl." }),
+    extractMode: optionalStringEnum(["markdown", "text"] as const, {
+      description: 'Extraction mode ("markdown" or "text"). Default: markdown.',
+    }),
+    maxChars: Type.Optional(
+      Type.Number({
+        description: "Maximum characters to return.",
+        minimum: 100,
+      }),
+    ),
+    onlyMainContent: Type.Optional(
+      Type.Boolean({
+        description: "Keep only main content when Firecrawl supports it.",
+      }),
+    ),
+    maxAgeMs: Type.Optional(
+      Type.Number({
+        description: "Maximum Firecrawl cache age in milliseconds.",
+        minimum: 0,
+      }),
+    ),
+    proxy: optionalStringEnum(["auto", "basic", "stealth"] as const, {
+      description: 'Firecrawl proxy mode ("auto", "basic", or "stealth").',
+    }),
+    storeInCache: Type.Optional(
+      Type.Boolean({
+        description: "Whether Firecrawl should store the scrape in its cache.",
+      }),
+    ),
+    timeoutSeconds: Type.Optional(
+      Type.Number({
+        description: "Timeout in seconds for the Firecrawl scrape request.",
+        minimum: 1,
+      }),
+    ),
+  },
+  { additionalProperties: false },
+);
+
+export function createFirecrawlScrapeTool(api: OpenClawPluginApi) {
+  return {
+    name: "firecrawl_scrape",
+    label: "Firecrawl Scrape",
+    description:
+      "Scrape a page using Firecrawl v2/scrape. Useful for JS-heavy or bot-protected pages where plain web_fetch is weak.",
+    parameters: FirecrawlScrapeToolSchema,
+    execute: async (_toolCallId: string, rawParams: Record<string, unknown>) => {
+      const url = readStringParam(rawParams, "url", { required: true });
+      const extractMode =
+        readStringParam(rawParams, "extractMode") === "text" ? "text" : "markdown";
+      const maxChars = readNumberParam(rawParams, "maxChars", { integer: true });
+      const maxAgeMs = readNumberParam(rawParams, "maxAgeMs", { integer: true });
+      const timeoutSeconds = readNumberParam(rawParams, "timeoutSeconds", {
+        integer: true,
+      });
+      const proxyRaw = readStringParam(rawParams, "proxy");
+      const proxy =
+        proxyRaw === "basic" || proxyRaw === "stealth" || proxyRaw === "auto"
+          ? proxyRaw
+          : undefined;
+      const onlyMainContent =
+        typeof rawParams.onlyMainContent === "boolean" ? rawParams.onlyMainContent : undefined;
+      const storeInCache =
+        typeof rawParams.storeInCache === "boolean" ? rawParams.storeInCache : undefined;
+
+      return jsonResult(
+        await runFirecrawlScrape({
+          cfg: api.config,
+          url,
+          extractMode,
+          maxChars,
+          onlyMainContent,
+          maxAgeMs,
+          proxy,
+          storeInCache,
+          timeoutSeconds,
+        }),
+      );
+    },
+  };
+}

extensions/firecrawl/src/firecrawl-search-provider.ts

@@ -0,0 +1,63 @@
+import { Type } from "@sinclair/typebox";
+import type { WebSearchProviderPlugin } from "../../../src/plugins/types.js";
+import { runFirecrawlSearch } from "./firecrawl-client.js";
+
+const GenericFirecrawlSearchSchema = Type.Object(
+  {
+    query: Type.String({ description: "Search query string." }),
+    count: Type.Optional(
+      Type.Number({
+        description: "Number of results to return (1-10).",
+        minimum: 1,
+        maximum: 10,
+      }),
+    ),
+  },
+  { additionalProperties: false },
+);
+
+function getScopedCredentialValue(searchConfig?: Record<string, unknown>): unknown {
+  const scoped = searchConfig?.firecrawl;
+  if (!scoped || typeof scoped !== "object" || Array.isArray(scoped)) {
+    return undefined;
+  }
+  return (scoped as Record<string, unknown>).apiKey;
+}
+
+function setScopedCredentialValue(
+  searchConfigTarget: Record<string, unknown>,
+  value: unknown,
+): void {
+  const scoped = searchConfigTarget.firecrawl;
+  if (!scoped || typeof scoped !== "object" || Array.isArray(scoped)) {
+    searchConfigTarget.firecrawl = { apiKey: value };
+    return;
+  }
+  (scoped as Record<string, unknown>).apiKey = value;
+}
+
+export function createFirecrawlWebSearchProvider(): WebSearchProviderPlugin {
+  return {
+    id: "firecrawl",
+    label: "Firecrawl Search",
+    hint: "Structured results with optional result scraping",
+    envVars: ["FIRECRAWL_API_KEY"],
+    placeholder: "fc-...",
+    signupUrl: "https://www.firecrawl.dev/",
+    docsUrl: "https://docs.openclaw.ai/tools/firecrawl",
+    autoDetectOrder: 60,
+    getCredentialValue: getScopedCredentialValue,
+    setCredentialValue: setScopedCredentialValue,
+    createTool: (ctx) => ({
+      description:
+        "Search the web using Firecrawl. Returns structured results with snippets from Firecrawl Search. Use firecrawl_search for Firecrawl-specific knobs like sources or categories.",
+      parameters: GenericFirecrawlSearchSchema,
+      execute: async (args) =>
+        await runFirecrawlSearch({
+          cfg: ctx.config,
+          query: typeof args.query === "string" ? args.query : "",
+          count: typeof args.count === "number" ? args.count : undefined,
+        }),
+    }),
+  };
+}

extensions/firecrawl/src/firecrawl-search-tool.ts

@@ -0,0 +1,76 @@
+import { Type } from "@sinclair/typebox";
+import {
+  jsonResult,
+  readNumberParam,
+  readStringArrayParam,
+  readStringParam,
+} from "../../../src/agents/tools/common.js";
+import type { OpenClawPluginApi } from "../../../src/plugins/types.js";
+import { runFirecrawlSearch } from "./firecrawl-client.js";
+
+const FirecrawlSearchToolSchema = Type.Object(
+  {
+    query: Type.String({ description: "Search query string." }),
+    count: Type.Optional(
+      Type.Number({
+        description: "Number of results to return (1-10).",
+        minimum: 1,
+        maximum: 10,
+      }),
+    ),
+    sources: Type.Optional(
+      Type.Array(Type.String(), {
+        description: 'Optional sources list, for example ["web"], ["news"], or ["images"].',
+      }),
+    ),
+    categories: Type.Optional(
+      Type.Array(Type.String(), {
+        description: 'Optional Firecrawl categories, for example ["github"] or ["research"].',
+      }),
+    ),
+    scrapeResults: Type.Optional(
+      Type.Boolean({
+        description: "Include scraped result content when Firecrawl returns it.",
+      }),
+    ),
+    timeoutSeconds: Type.Optional(
+      Type.Number({
+        description: "Timeout in seconds for the Firecrawl Search request.",
+        minimum: 1,
+      }),
+    ),
+  },
+  { additionalProperties: false },
+);
+
+export function createFirecrawlSearchTool(api: OpenClawPluginApi) {
+  return {
+    name: "firecrawl_search",
+    label: "Firecrawl Search",
+    description:
+      "Search the web using Firecrawl v2/search. Can optionally include scraped content from result pages.",
+    parameters: FirecrawlSearchToolSchema,
+    execute: async (_toolCallId: string, rawParams: Record<string, unknown>) => {
+      const query = readStringParam(rawParams, "query", { required: true });
+      const count = readNumberParam(rawParams, "count", { integer: true });
+      const timeoutSeconds = readNumberParam(rawParams, "timeoutSeconds", {
+        integer: true,
+      });
+      const sources = readStringArrayParam(rawParams, "sources");
+      const categories = readStringArrayParam(rawParams, "categories");
+      const scrapeResults = rawParams.scrapeResults === true;
+
+      return jsonResult(
+        await runFirecrawlSearch({
+          cfg: api.config,
+          query,
+          count,
+          timeoutSeconds,
+          sources,
+          categories,
+          scrapeResults,
+        }),
+      );
+    },
+  };
+}