Add link understanding tool support (#1637)

* Add

* Fix

---------

Co-authored-by: Richard <dasilva333@DESKTOP-74E3GJO.localdomain>

src/link-understanding/apply.ts

@@ -0,0 +1,37 @@
+import type { ClawdbotConfig } from "../config/config.js";
+import type { MsgContext } from "../auto-reply/templating.js";
+import { finalizeInboundContext } from "../auto-reply/reply/inbound-context.js";
+import { formatLinkUnderstandingBody } from "./format.js";
+import { runLinkUnderstanding } from "./runner.js";
+
+export type ApplyLinkUnderstandingResult = {
+  outputs: string[];
+  urls: string[];
+};
+
+export async function applyLinkUnderstanding(params: {
+  ctx: MsgContext;
+  cfg: ClawdbotConfig;
+}): Promise<ApplyLinkUnderstandingResult> {
+  const result = await runLinkUnderstanding({
+    cfg: params.cfg,
+    ctx: params.ctx,
+  });
+
+  if (result.outputs.length === 0) {
+    return result;
+  }
+
+  params.ctx.LinkUnderstanding = [...(params.ctx.LinkUnderstanding ?? []), ...result.outputs];
+  params.ctx.Body = formatLinkUnderstandingBody({
+    body: params.ctx.Body,
+    outputs: result.outputs,
+  });
+
+  finalizeInboundContext(params.ctx, {
+    forceBodyForAgent: true,
+    forceBodyForCommands: true,
+  });
+
+  return result;
+}

src/link-understanding/defaults.ts

@@ -0,0 +1,2 @@
+export const DEFAULT_LINK_TIMEOUT_SECONDS = 30;
+export const DEFAULT_MAX_LINKS = 3;

src/link-understanding/detect.test.ts

@@ -0,0 +1,27 @@
+import { describe, expect, it } from "vitest";
+
+import { extractLinksFromMessage } from "./detect.js";
+
+describe("extractLinksFromMessage", () => {
+  it("extracts bare http/https URLs in order", () => {
+    const links = extractLinksFromMessage("see https://a.example and http://b.test");
+    expect(links).toEqual(["https://a.example", "http://b.test"]);
+  });
+
+  it("dedupes links and enforces maxLinks", () => {
+    const links = extractLinksFromMessage("https://a.example https://a.example https://b.test", {
+      maxLinks: 1,
+    });
+    expect(links).toEqual(["https://a.example"]);
+  });
+
+  it("ignores markdown links", () => {
+    const links = extractLinksFromMessage("[doc](https://docs.example) https://bare.example");
+    expect(links).toEqual(["https://bare.example"]);
+  });
+
+  it("blocks 127.0.0.1", () => {
+    const links = extractLinksFromMessage("http://127.0.0.1/test https://ok.test");
+    expect(links).toEqual(["https://ok.test"]);
+  });
+});

src/link-understanding/detect.ts

@@ -0,0 +1,49 @@
+import { DEFAULT_MAX_LINKS } from "./defaults.js";
+
+// Remove markdown link syntax so only bare URLs are considered.
+const MARKDOWN_LINK_RE = /\[[^\]]*]\((https?:\/\/\S+?)\)/gi;
+const BARE_LINK_RE = /https?:\/\/\S+/gi;
+
+function stripMarkdownLinks(message: string): string {
+  return message.replace(MARKDOWN_LINK_RE, " ");
+}
+
+function resolveMaxLinks(value?: number): number {
+  if (typeof value === "number" && Number.isFinite(value) && value > 0) {
+    return Math.floor(value);
+  }
+  return DEFAULT_MAX_LINKS;
+}
+
+function isAllowedUrl(raw: string): boolean {
+  try {
+    const parsed = new URL(raw);
+    if (parsed.protocol !== "http:" && parsed.protocol !== "https:") return false;
+    if (parsed.hostname === "127.0.0.1") return false;
+    return true;
+  } catch {
+    return false;
+  }
+}
+
+export function extractLinksFromMessage(message: string, opts?: { maxLinks?: number }): string[] {
+  const source = message?.trim();
+  if (!source) return [];
+
+  const maxLinks = resolveMaxLinks(opts?.maxLinks);
+  const sanitized = stripMarkdownLinks(source);
+  const seen = new Set<string>();
+  const results: string[] = [];
+
+  for (const match of sanitized.matchAll(BARE_LINK_RE)) {
+    const raw = match[0]?.trim();
+    if (!raw) continue;
+    if (!isAllowedUrl(raw)) continue;
+    if (seen.has(raw)) continue;
+    seen.add(raw);
+    results.push(raw);
+    if (results.length >= maxLinks) break;
+  }
+
+  return results;
+}

src/link-understanding/format.ts

@@ -0,0 +1,10 @@
+export function formatLinkUnderstandingBody(params: { body?: string; outputs: string[] }): string {
+  const outputs = params.outputs.map((output) => output.trim()).filter(Boolean);
+  if (outputs.length === 0) {
+    return params.body ?? "";
+  }
+
+  const base = (params.body ?? "").trim();
+  if (!base) return outputs.join("\n");
+  return `${base}\n\n${outputs.join("\n")}`;
+}

src/link-understanding/index.ts

@@ -0,0 +1,4 @@
+export { applyLinkUnderstanding } from "./apply.js";
+export { extractLinksFromMessage } from "./detect.js";
+export { formatLinkUnderstandingBody } from "./format.js";
+export { runLinkUnderstanding } from "./runner.js";

src/link-understanding/runner.ts

@@ -0,0 +1,136 @@
+import type { ClawdbotConfig } from "../config/config.js";
+import type { MsgContext } from "../auto-reply/templating.js";
+import { applyTemplate } from "../auto-reply/templating.js";
+import type { LinkModelConfig, LinkToolsConfig } from "../config/types.tools.js";
+import { logVerbose, shouldLogVerbose } from "../globals.js";
+import { runExec } from "../process/exec.js";
+import { CLI_OUTPUT_MAX_BUFFER } from "../media-understanding/defaults.js";
+import { resolveTimeoutMs } from "../media-understanding/resolve.js";
+import {
+  normalizeMediaUnderstandingChatType,
+  resolveMediaUnderstandingScope,
+} from "../media-understanding/scope.js";
+import { DEFAULT_LINK_TIMEOUT_SECONDS } from "./defaults.js";
+import { extractLinksFromMessage } from "./detect.js";
+
+export type LinkUnderstandingResult = {
+  urls: string[];
+  outputs: string[];
+};
+
+function resolveScopeDecision(params: {
+  config?: LinkToolsConfig;
+  ctx: MsgContext;
+}): "allow" | "deny" {
+  return resolveMediaUnderstandingScope({
+    scope: params.config?.scope,
+    sessionKey: params.ctx.SessionKey,
+    channel: params.ctx.Surface ?? params.ctx.Provider,
+    chatType: normalizeMediaUnderstandingChatType(params.ctx.ChatType),
+  });
+}
+
+function resolveTimeoutMsFromConfig(params: {
+  config?: LinkToolsConfig;
+  entry: LinkModelConfig;
+}): number {
+  const configured = params.entry.timeoutSeconds ?? params.config?.timeoutSeconds;
+  return resolveTimeoutMs(configured, DEFAULT_LINK_TIMEOUT_SECONDS);
+}
+
+async function runCliEntry(params: {
+  entry: LinkModelConfig;
+  ctx: MsgContext;
+  url: string;
+  config?: LinkToolsConfig;
+}): Promise<string | null> {
+  if ((params.entry.type ?? "cli") !== "cli") return null;
+  const command = params.entry.command.trim();
+  if (!command) return null;
+  const args = params.entry.args ?? [];
+  const timeoutMs = resolveTimeoutMsFromConfig({ config: params.config, entry: params.entry });
+  const templCtx = {
+    ...params.ctx,
+    LinkUrl: params.url,
+  };
+  const argv = [command, ...args].map((part, index) =>
+    index === 0 ? part : applyTemplate(part, templCtx),
+  );
+
+  if (shouldLogVerbose()) {
+    logVerbose(`Link understanding via CLI: ${argv.join(" ")}`);
+  }
+
+  const { stdout } = await runExec(argv[0], argv.slice(1), {
+    timeoutMs,
+    maxBuffer: CLI_OUTPUT_MAX_BUFFER,
+  });
+  const trimmed = stdout.trim();
+  return trimmed || null;
+}
+
+async function runLinkEntries(params: {
+  entries: LinkModelConfig[];
+  ctx: MsgContext;
+  url: string;
+  config?: LinkToolsConfig;
+}): Promise<string | null> {
+  let lastError: unknown;
+  for (const entry of params.entries) {
+    try {
+      const output = await runCliEntry({
+        entry,
+        ctx: params.ctx,
+        url: params.url,
+        config: params.config,
+      });
+      if (output) return output;
+    } catch (err) {
+      lastError = err;
+      if (shouldLogVerbose()) {
+        logVerbose(`Link understanding failed for ${params.url}: ${String(err)}`);
+      }
+    }
+  }
+  if (lastError && shouldLogVerbose()) {
+    logVerbose(`Link understanding exhausted for ${params.url}`);
+  }
+  return null;
+}
+
+export async function runLinkUnderstanding(params: {
+  cfg: ClawdbotConfig;
+  ctx: MsgContext;
+  message?: string;
+}): Promise<LinkUnderstandingResult> {
+  const config = params.cfg.tools?.links;
+  if (!config || config.enabled === false) return { urls: [], outputs: [] };
+
+  const scopeDecision = resolveScopeDecision({ config, ctx: params.ctx });
+  if (scopeDecision === "deny") {
+    if (shouldLogVerbose()) {
+      logVerbose("Link understanding disabled by scope policy.");
+    }
+    return { urls: [], outputs: [] };
+  }
+
+  const message = params.message ?? params.ctx.CommandBody ?? params.ctx.RawBody ?? params.ctx.Body;
+  const links = extractLinksFromMessage(message ?? "", { maxLinks: config?.maxLinks });
+  if (links.length === 0) return { urls: [], outputs: [] };
+
+  const entries = config?.models ?? [];
+  if (entries.length === 0) return { urls: links, outputs: [] };
+
+  const outputs: string[] = [];
+  for (const url of links) {
+    const output = await runLinkEntries({
+      entries,
+      ctx: params.ctx,
+      url,
+      config,
+    });
+    if (output) outputs.push(output);
+  }
+
+  return { urls: links, outputs };
+}