@openlines/opl-pi-sht 0.1.14

package/extensions/opl-webaccess/extract.ts

@@ -0,0 +1,83 @@
+import { Readability } from "@mozilla/readability";
+import { parseHTML } from "linkedom";
+import TurndownService from "turndown";
+import { extractPdfBuffer } from "./pdf.js";
+import { errorMessage, isAbortError, isPdfUrl, isPdfContentType } from "./utils.js";
+import type { ExtractedContent } from "./types.js";
+
+const CONCURRENT_LIMIT = 3;
+
+const td = new TurndownService({
+  headingStyle: "atx",
+  codeBlockStyle: "fenced",
+});
+
+export async function fetchAllContent(
+  urls: string[],
+  signal?: AbortSignal
+): Promise<ExtractedContent[]> {
+  const results: ExtractedContent[] = [];
+  for (let i = 0; i < urls.length; i += CONCURRENT_LIMIT) {
+    if (signal?.aborted) break;
+    const batch = urls.slice(i, i + CONCURRENT_LIMIT);
+    const batchResults = await Promise.all(batch.map((url) => fetchOne(url, signal)));
+    results.push(...batchResults);
+  }
+  return results;
+}
+
+async function fetchOne(url: string, signal?: AbortSignal): Promise<ExtractedContent> {
+  try {
+    const response = await fetch(url, {
+      signal,
+      headers: {
+        "User-Agent": "Mozilla/5.0 (compatible; pi-web-access/1.0)",
+        Accept: "text/html,application/xhtml+xml,application/pdf,*/*",
+      },
+    });
+
+    if (!response.ok) {
+      return { url, title: "", content: "", error: `HTTP ${response.status}: ${url}` };
+    }
+
+    const contentType = response.headers.get("content-type") ?? "";
+
+    if (isPdfUrl(url) || isPdfContentType(contentType)) {
+      const buffer = await response.arrayBuffer();
+      const content = await extractPdfBuffer(buffer);
+      return { url, title: url, content, error: null };
+    }
+
+    const isHtml =
+      contentType.includes("text/html") || contentType.includes("application/xhtml");
+
+    const body = await response.text();
+
+    if (!isHtml) {
+      // Plain text, markdown, JSON, etc. — return as-is
+      return { url, title: "", content: body, error: null };
+    }
+
+    const { document } = parseHTML(body);
+    let article = null;
+    try {
+      article = new Readability(document as unknown as Document).parse();
+    } catch {
+      // Readability failed — fall back to raw turndown
+    }
+
+    if (!article?.content) {
+      return { url, title: "", content: td.turndown(body), error: null };
+    }
+
+    return {
+      url,
+      title: article.title ?? "",
+      content: td.turndown(article.content),
+      error: null,
+    };
+  } catch (err) {
+    if (isAbortError(err)) return { url, title: "", content: "", error: "Aborted" };
+    return { url, title: "", content: "", error: errorMessage(err) };
+  }
+}

package/extensions/opl-webaccess/index.ts

@@ -0,0 +1,232 @@
+import type { ExtensionAPI } from "@earendil-works/pi-coding-agent";
+import { Type } from "typebox";
+import { searchWeb } from "./search.js";
+import { fetchAllContent } from "./extract.js";
+import {
+  generateId,
+  storeResult,
+  getResult,
+  persistResult,
+  restoreFromSession,
+  MAX_CONTENT_CHARS,
+} from "./storage.js";
+import { truncate, errorMessage } from "./utils.js";
+import type { StoredData } from "./types.js";
+
+export default function (pi: ExtensionAPI) {
+  pi.on("session_start", async (_event, ctx) => {
+    restoreFromSession(ctx);
+  });
+
+  // ── web_search ────────────────────────────────────────────────────────────
+
+  pi.registerTool({
+    name: "web_search",
+    label: "Web Search",
+    description:
+      "Search the web using the configured search provider (gemini, tavily, ddgs, searxng, or exa). Returns a synthesized answer with source citations. Provider is set in ~/.pi/agent/configs/opl-webaccess.json. Use queries (plural) to run multiple searches in parallel.",
+    parameters: Type.Object({
+      query: Type.Optional(Type.String({ description: "Single search query" })),
+      queries: Type.Optional(
+        Type.Array(Type.String(), { description: "Multiple search queries run in parallel" })
+      ),
+    }),
+    async execute(_toolCallId, params, signal) {
+      const queryList = params.queries ?? (params.query ? [params.query] : null);
+      if (!queryList?.length) {
+        return {
+          content: [{ type: "text", text: "Error: provide either query or queries." }],
+          isError: true,
+          details: {} as Record<string, unknown>,
+        };
+      }
+
+      let results;
+      try {
+        results = await Promise.all(queryList.map((q) => searchWeb(q, signal)));
+      } catch (err) {
+        return {
+          content: [{ type: "text", text: `Error: ${errorMessage(err)}` }],
+          isError: true,
+          details: {} as Record<string, unknown>,
+        };
+      }
+
+      const id = generateId();
+      const data: StoredData = { id, type: "search", timestamp: Date.now(), queries: results };
+      storeResult(id, data);
+      persistResult(pi, data);
+
+      const sections = results.map((r) => {
+        if (r.error) return `## Query: "${r.query}"\n\nError: ${r.error}`;
+        const sources =
+          r.results.length > 0
+            ? "\n\n**Sources:**\n" +
+              r.results.map((s, i) => `${i + 1}. [${s.title}](${s.url})`).join("\n")
+            : "";
+        return `## Query: "${r.query}"\n\n${r.answer}${sources}`;
+      });
+
+      const body = truncate(sections.join("\n\n---\n\n"), MAX_CONTENT_CHARS);
+      return {
+        content: [{ type: "text", text: `${body}\n\n*responseId: ${id}*` }],
+        details: { responseId: id, queryCount: results.length },
+      };
+    },
+  });
+
+  // ── fetch_content ─────────────────────────────────────────────────────────
+
+  pi.registerTool({
+    name: "fetch_content",
+    label: "Fetch Content",
+    description:
+      "Fetch one or more URLs and extract readable content as markdown. Supports regular web pages and PDFs. No API key required. Use urls (plural) for multiple URLs.",
+    parameters: Type.Object({
+      url: Type.Optional(Type.String({ description: "Single URL to fetch" })),
+      urls: Type.Optional(
+        Type.Array(Type.String(), { description: "Multiple URLs to fetch in parallel (max 3 at a time)" })
+      ),
+    }),
+    async execute(_toolCallId, params, signal) {
+      const urlList = params.urls ?? (params.url ? [params.url] : null);
+      if (!urlList?.length) {
+        return {
+          content: [{ type: "text", text: "Error: provide either url or urls." }],
+          isError: true,
+          details: {} as Record<string, unknown>,
+        };
+      }
+
+      let results;
+      try {
+        results = await fetchAllContent(urlList, signal);
+      } catch (err) {
+        return {
+          content: [{ type: "text", text: `Error: ${errorMessage(err)}` }],
+          isError: true,
+          details: {} as Record<string, unknown>,
+        };
+      }
+
+      const id = generateId();
+      const data: StoredData = { id, type: "fetch", timestamp: Date.now(), urls: results };
+      storeResult(id, data);
+      persistResult(pi, data);
+
+      const sections = results.map((r) => {
+        if (r.error) return `## ${r.url}\n\nError: ${r.error}`;
+        const title = r.title ? `**${r.title}**\n\n` : "";
+        return `## ${r.url}\n\n${title}${r.content}`;
+      });
+
+      const body = truncate(sections.join("\n\n---\n\n"), MAX_CONTENT_CHARS);
+      return {
+        content: [{ type: "text", text: `${body}\n\n*responseId: ${id}*` }],
+        details: { responseId: id, urlCount: results.length },
+      };
+    },
+  });
+
+  // ── get_search_content ────────────────────────────────────────────────────
+
+  pi.registerTool({
+    name: "get_search_content",
+    label: "Get Search Content",
+    description:
+      "Retrieve full stored content from a previous web_search or fetch_content call. Use when content was truncated in the original response.",
+    parameters: Type.Object({
+      responseId: Type.String({
+        description: "The responseId returned by web_search or fetch_content",
+      }),
+      queryIndex: Type.Optional(
+        Type.Number({ description: "Index of the query to retrieve (web_search, default: 0)" })
+      ),
+      urlIndex: Type.Optional(
+        Type.Number({ description: "Index of the URL to retrieve (fetch_content, default: 0)" })
+      ),
+      url: Type.Optional(
+        Type.String({ description: "Retrieve content for a specific URL (fetch_content)" })
+      ),
+    }),
+    async execute(_toolCallId, params) {
+      const data = getResult(params.responseId);
+      if (!data) {
+        return {
+          content: [
+            {
+              type: "text",
+              text: `No stored content found for responseId: ${params.responseId}. Results expire after 1 hour or when a new session starts.`,
+            },
+          ],
+          isError: true,
+          details: {} as Record<string, unknown>,
+        };
+      }
+
+      if (data.type === "search") {
+        const idx = params.queryIndex ?? 0;
+        const result = data.queries?.[idx];
+        if (!result) {
+          return {
+            content: [
+              {
+                type: "text",
+                text: `No query at index ${idx}. This response has ${data.queries?.length ?? 0} quer${data.queries?.length === 1 ? "y" : "ies"}.`,
+              },
+            ],
+            isError: true,
+            details: {} as Record<string, unknown>,
+          };
+        }
+        const sources =
+          result.results.length > 0
+            ? "\n\n**Sources:**\n" +
+              result.results.map((s, i) => `${i + 1}. [${s.title}](${s.url})`).join("\n")
+            : "";
+        return {
+          content: [{ type: "text", text: `## Query: "${result.query}"\n\n${result.answer}${sources}` }],
+          details: { responseId: params.responseId },
+        };
+      }
+
+      if (data.type === "fetch") {
+        const result =
+          params.url != null
+            ? data.urls?.find((u) => u.url === params.url)
+            : data.urls?.[params.urlIndex ?? 0];
+
+        if (!result) {
+          return {
+            content: [
+              {
+                type: "text",
+                text: `No URL found. This response has ${data.urls?.length ?? 0} URL(s).`,
+              },
+            ],
+            isError: true,
+            details: {} as Record<string, unknown>,
+          };
+        }
+        if (result.error) {
+          return {
+            content: [{ type: "text", text: `Error fetching ${result.url}: ${result.error}` }],
+            isError: true,
+            details: {} as Record<string, unknown>,
+          };
+        }
+        const title = result.title ? `**${result.title}**\n\n` : "";
+        return {
+          content: [{ type: "text", text: `## ${result.url}\n\n${title}${result.content}` }],
+          details: { responseId: params.responseId },
+        };
+      }
+
+      return {
+        content: [{ type: "text", text: "Unknown result type." }],
+        isError: true,
+        details: {},
+      };
+    },
+  });
+}

package/extensions/opl-webaccess/package-lock.json

@@ -0,0 +1,345 @@
+{
+  "name": "opl-webaccess",
+  "version": "1.0.0",
+  "lockfileVersion": 3,
+  "requires": true,
+  "packages": {
+    "": {
+      "name": "opl-webaccess",
+      "version": "1.0.0",
+      "license": "ISC",
+      "dependencies": {
+        "@mozilla/readability": "^0.6.0",
+        "linkedom": "^0.18.13",
+        "turndown": "^7.2.4",
+        "unpdf": "^1.8.0"
+      }
+    },
+    "node_modules/@mixmark-io/domino": {
+      "version": "2.2.0",
+      "resolved": "https://registry.npmjs.org/@mixmark-io/domino/-/domino-2.2.0.tgz",
+      "integrity": "sha512-Y28PR25bHXUg88kCV7nivXrP2Nj2RueZ3/l/jdx6J9f8J4nsEGcgX0Qe6lt7Pa+J79+kPiJU3LguR6O/6zrLOw==",
+      "license": "BSD-2-Clause"
+    },
+    "node_modules/@mozilla/readability": {
+      "version": "0.6.0",
+      "resolved": "https://registry.npmjs.org/@mozilla/readability/-/readability-0.6.0.tgz",
+      "integrity": "sha512-juG5VWh4qAivzTAeMzvY9xs9HY5rAcr2E4I7tiSSCokRFi7XIZCAu92ZkSTsIj1OPceCifL3cpfteP3pDT9/QQ==",
+      "license": "Apache-2.0",
+      "engines": {
+        "node": ">=14.0.0"
+      }
+    },
+    "node_modules/boolbase": {
+      "version": "2.0.0",
+      "resolved": "https://registry.npmjs.org/boolbase/-/boolbase-2.0.0.tgz",
+      "integrity": "sha512-DkVaaQHymRhpYEYo9x1oo7Q7B0Y6KJUsjm3c9eTyFDby4MHLBTwZ6ZDWBel5zrYxj1WsZgC5oLpiz+93MluXeA==",
+      "license": "ISC",
+      "engines": {
+        "node": ">=20.19.0"
+      },
+      "funding": {
+        "type": "github",
+        "url": "https://github.com/sponsors/fb55"
+      }
+    },
+    "node_modules/css-select": {
+      "version": "7.0.0",
+      "resolved": "https://registry.npmjs.org/css-select/-/css-select-7.0.0.tgz",
+      "integrity": "sha512-snmjEVXy+1LnwXdxhYvTMj1d9tOh4HxkA1YmoayVBeeyR2C14Pum7fcxJIm4SswYspVy866eYNwlH6xC3/VH5g==",
+      "license": "BSD-2-Clause",
+      "dependencies": {
+        "boolbase": "^2.0.0",
+        "css-what": "^8.0.0",
+        "domhandler": "^6.0.1",
+        "domutils": "^4.0.2",
+        "nth-check": "^3.0.1"
+      },
+      "engines": {
+        "node": ">=20.19.0"
+      },
+      "funding": {
+        "type": "github",
+        "url": "https://github.com/sponsors/fb55"
+      }
+    },
+    "node_modules/css-what": {
+      "version": "8.0.0",
+      "resolved": "https://registry.npmjs.org/css-what/-/css-what-8.0.0.tgz",
+      "integrity": "sha512-DH0Bqq3DNp5tdOReuNyAA+Ev4Y2GS5FMbZpeTLP6C4CDi0h5nL0BmUPChXw3o/qbHLDWHl49sbNqQVY7bMSDdw==",
+      "license": "BSD-2-Clause",
+      "engines": {
+        "node": ">=20.19.0"
+      },
+      "funding": {
+        "type": "github",
+        "url": "https://github.com/sponsors/fb55"
+      }
+    },
+    "node_modules/cssom": {
+      "version": "0.5.0",
+      "resolved": "https://registry.npmjs.org/cssom/-/cssom-0.5.0.tgz",
+      "integrity": "sha512-iKuQcq+NdHqlAcwUY0o/HL69XQrUaQdMjmStJ8JFmUaiiQErlhrmuigkg/CU4E2J0IyUKUrMAgl36TvN67MqTw==",
+      "license": "MIT"
+    },
+    "node_modules/dom-serializer": {
+      "version": "3.1.1",
+      "resolved": "https://registry.npmjs.org/dom-serializer/-/dom-serializer-3.1.1.tgz",
+      "integrity": "sha512-4MEa38/QexBob6gFNwu+EGdWvhJ1OKuNwdYY3Y3NyeWDQfnGeDYQUDfIRzWu5B5gsv03so2Uxd28YC6zrsx3Lw==",
+      "license": "MIT",
+      "dependencies": {
+        "domelementtype": "^3.0.0",
+        "domhandler": "^6.0.0",
+        "entities": "^8.0.0"
+      },
+      "engines": {
+        "node": ">=20.19.0"
+      },
+      "funding": {
+        "type": "github",
+        "url": "https://github.com/cheeriojs/dom-serializer?sponsor=1"
+      }
+    },
+    "node_modules/domelementtype": {
+      "version": "3.0.0",
+      "resolved": "https://registry.npmjs.org/domelementtype/-/domelementtype-3.0.0.tgz",
+      "integrity": "sha512-umCQid3jKbDmVjx8jGaW7uUykm4DEUeyV21hPxNMo2nV955DhUThwqyOIDtreepP31hl84X7G5U9ZfsWvIB3Pg==",
+      "funding": [
+        {
+          "type": "github",
+          "url": "https://github.com/sponsors/fb55"
+        }
+      ],
+      "license": "BSD-2-Clause",
+      "engines": {
+        "node": ">=20.19.0"
+      }
+    },
+    "node_modules/domhandler": {
+      "version": "6.0.1",
+      "resolved": "https://registry.npmjs.org/domhandler/-/domhandler-6.0.1.tgz",
+      "integrity": "sha512-gYzvtM72ZtxQO0T048kd6HWSbbGCNOUwcnfQ01cqIJ4X2IYKFFHZ5mKvrQETcFXxsRObZulDaKmy//R7TPtsBg==",
+      "license": "BSD-2-Clause",
+      "dependencies": {
+        "domelementtype": "^3.0.0"
+      },
+      "engines": {
+        "node": ">=20.19.0"
+      },
+      "funding": {
+        "type": "github",
+        "url": "https://github.com/fb55/domhandler?sponsor=1"
+      }
+    },
+    "node_modules/domutils": {
+      "version": "4.0.2",
+      "resolved": "https://registry.npmjs.org/domutils/-/domutils-4.0.2.tgz",
+      "integrity": "sha512-qI4JLRKnSzqFqr7hAlS5xQDusBCjKSEG4t4+7aNrIQMHBcsC2TGEhuyABJdYkgSewL57PNLYEiibY2iPKhKpaA==",
+      "license": "BSD-2-Clause",
+      "dependencies": {
+        "dom-serializer": "^3.0.0",
+        "domelementtype": "^3.0.0",
+        "domhandler": "^6.0.0"
+      },
+      "engines": {
+        "node": ">=20.19.0"
+      },
+      "funding": {
+        "type": "github",
+        "url": "https://github.com/fb55/domutils?sponsor=1"
+      }
+    },
+    "node_modules/entities": {
+      "version": "8.0.0",
+      "resolved": "https://registry.npmjs.org/entities/-/entities-8.0.0.tgz",
+      "integrity": "sha512-zwfzJecQ/Uej6tusMqwAqU/6KL2XaB2VZ2Jg54Je6ahNBGNH6Ek6g3jjNCF0fG9EWQKGZNddNjU5F1ZQn/sBnA==",
+      "license": "BSD-2-Clause",
+      "engines": {
+        "node": ">=20.19.0"
+      },
+      "funding": {
+        "url": "https://github.com/fb55/entities?sponsor=1"
+      }
+    },
+    "node_modules/html-escaper": {
+      "version": "3.0.3",
+      "resolved": "https://registry.npmjs.org/html-escaper/-/html-escaper-3.0.3.tgz",
+      "integrity": "sha512-RuMffC89BOWQoY0WKGpIhn5gX3iI54O6nRA0yC124NYVtzjmFWBIiFd8M0x+ZdX0P9R4lADg1mgP8C7PxGOWuQ==",
+      "license": "MIT"
+    },
+    "node_modules/htmlparser2": {
+      "version": "10.1.0",
+      "resolved": "https://registry.npmjs.org/htmlparser2/-/htmlparser2-10.1.0.tgz",
+      "integrity": "sha512-VTZkM9GWRAtEpveh7MSF6SjjrpNVNNVJfFup7xTY3UpFtm67foy9HDVXneLtFVt4pMz5kZtgNcvCniNFb1hlEQ==",
+      "funding": [
+        "https://github.com/fb55/htmlparser2?sponsor=1",
+        {
+          "type": "github",
+          "url": "https://github.com/sponsors/fb55"
+        }
+      ],
+      "license": "MIT",
+      "dependencies": {
+        "domelementtype": "^2.3.0",
+        "domhandler": "^5.0.3",
+        "domutils": "^3.2.2",
+        "entities": "^7.0.1"
+      }
+    },
+    "node_modules/htmlparser2/node_modules/dom-serializer": {
+      "version": "2.0.0",
+      "resolved": "https://registry.npmjs.org/dom-serializer/-/dom-serializer-2.0.0.tgz",
+      "integrity": "sha512-wIkAryiqt/nV5EQKqQpo3SToSOV9J0DnbJqwK7Wv/Trc92zIAYZ4FlMu+JPFW1DfGFt81ZTCGgDEabffXeLyJg==",
+      "license": "MIT",
+      "dependencies": {
+        "domelementtype": "^2.3.0",
+        "domhandler": "^5.0.2",
+        "entities": "^4.2.0"
+      },
+      "funding": {
+        "url": "https://github.com/cheeriojs/dom-serializer?sponsor=1"
+      }
+    },
+    "node_modules/htmlparser2/node_modules/dom-serializer/node_modules/entities": {
+      "version": "4.5.0",
+      "resolved": "https://registry.npmjs.org/entities/-/entities-4.5.0.tgz",
+      "integrity": "sha512-V0hjH4dGPh9Ao5p0MoRY6BVqtwCjhz6vI5LT8AJ55H+4g9/4vbHx1I54fS0XuclLhDHArPQCiMjDxjaL8fPxhw==",
+      "license": "BSD-2-Clause",
+      "engines": {
+        "node": ">=0.12"
+      },
+      "funding": {
+        "url": "https://github.com/fb55/entities?sponsor=1"
+      }
+    },
+    "node_modules/htmlparser2/node_modules/domelementtype": {
+      "version": "2.3.0",
+      "resolved": "https://registry.npmjs.org/domelementtype/-/domelementtype-2.3.0.tgz",
+      "integrity": "sha512-OLETBj6w0OsagBwdXnPdN0cnMfF9opN69co+7ZrbfPGrdpPVNBUj02spi6B1N7wChLQiPn4CSH/zJvXw56gmHw==",
+      "funding": [
+        {
+          "type": "github",
+          "url": "https://github.com/sponsors/fb55"
+        }
+      ],
+      "license": "BSD-2-Clause"
+    },
+    "node_modules/htmlparser2/node_modules/domhandler": {
+      "version": "5.0.3",
+      "resolved": "https://registry.npmjs.org/domhandler/-/domhandler-5.0.3.tgz",
+      "integrity": "sha512-cgwlv/1iFQiFnU96XXgROh8xTeetsnJiDsTc7TYCLFd9+/WNkIqPTxiM/8pSd8VIrhXGTf1Ny1q1hquVqDJB5w==",
+      "license": "BSD-2-Clause",
+      "dependencies": {
+        "domelementtype": "^2.3.0"
+      },
+      "engines": {
+        "node": ">= 4"
+      },
+      "funding": {
+        "url": "https://github.com/fb55/domhandler?sponsor=1"
+      }
+    },
+    "node_modules/htmlparser2/node_modules/domutils": {
+      "version": "3.2.2",
+      "resolved": "https://registry.npmjs.org/domutils/-/domutils-3.2.2.tgz",
+      "integrity": "sha512-6kZKyUajlDuqlHKVX1w7gyslj9MPIXzIFiz/rGu35uC1wMi+kMhQwGhl4lt9unC9Vb9INnY9Z3/ZA3+FhASLaw==",
+      "license": "BSD-2-Clause",
+      "dependencies": {
+        "dom-serializer": "^2.0.0",
+        "domelementtype": "^2.3.0",
+        "domhandler": "^5.0.3"
+      },
+      "funding": {
+        "url": "https://github.com/fb55/domutils?sponsor=1"
+      }
+    },
+    "node_modules/htmlparser2/node_modules/entities": {
+      "version": "7.0.1",
+      "resolved": "https://registry.npmjs.org/entities/-/entities-7.0.1.tgz",
+      "integrity": "sha512-TWrgLOFUQTH994YUyl1yT4uyavY5nNB5muff+RtWaqNVCAK408b5ZnnbNAUEWLTCpum9w6arT70i1XdQ4UeOPA==",
+      "license": "BSD-2-Clause",
+      "engines": {
+        "node": ">=0.12"
+      },
+      "funding": {
+        "url": "https://github.com/fb55/entities?sponsor=1"
+      }
+    },
+    "node_modules/linkedom": {
+      "version": "0.18.13",
+      "resolved": "https://registry.npmjs.org/linkedom/-/linkedom-0.18.13.tgz",
+      "integrity": "sha512-ES/o9qotMpzpN2MHs+Iq/JcVoOj8Fa5wiQYrTdFpvAnwXL0g66XHHUc9WUMk6nAlBtGsFQ24ne+SYnvnaQ2FSw==",
+      "license": "ISC",
+      "dependencies": {
+        "css-select": "^7.0.0",
+        "cssom": "^0.5.0",
+        "html-escaper": "^3.0.3",
+        "htmlparser2": "^10.1.0",
+        "uhyphen": "^0.2.0"
+      },
+      "engines": {
+        "node": ">=16"
+      },
+      "peerDependencies": {
+        "canvas": ">= 2"
+      },
+      "peerDependenciesMeta": {
+        "canvas": {
+          "optional": true
+        }
+      }
+    },
+    "node_modules/nth-check": {
+      "version": "3.0.1",
+      "resolved": "https://registry.npmjs.org/nth-check/-/nth-check-3.0.1.tgz",
+      "integrity": "sha512-GX0gsdbGVCgnRgbeGaubfjpBXyYRWOOCVeYh08bSQvDZqxz5ndXs1OTfAt/h36G1xvI94YIspsI0sVFqAV9+RQ==",
+      "license": "BSD-2-Clause",
+      "dependencies": {
+        "boolbase": "^2.0.0"
+      },
+      "engines": {
+        "node": ">=20.19.0"
+      },
+      "funding": {
+        "type": "github",
+        "url": "https://github.com/fb55/nth-check?sponsor=1"
+      }
+    },
+    "node_modules/turndown": {
+      "version": "7.2.4",
+      "resolved": "https://registry.npmjs.org/turndown/-/turndown-7.2.4.tgz",
+      "integrity": "sha512-I8yFsfRzmzK0WV1pNNOA4A7y4RDfFxPRxb3t+e3ui14qSGOxGtiSP6GjeX+Y6CHb7HYaFj7ECUD7VE5kQMZWGQ==",
+      "license": "MIT",
+      "dependencies": {
+        "@mixmark-io/domino": "^2.2.0"
+      },
+      "engines": {
+        "node": ">=18",
+        "npm": ">=9"
+      }
+    },
+    "node_modules/uhyphen": {
+      "version": "0.2.0",
+      "resolved": "https://registry.npmjs.org/uhyphen/-/uhyphen-0.2.0.tgz",
+      "integrity": "sha512-qz3o9CHXmJJPGBdqzab7qAYuW8kQGKNEuoHFYrBwV6hWIMcpAmxDLXojcHfFr9US1Pe6zUswEIJIbLI610fuqA==",
+      "license": "ISC"
+    },
+    "node_modules/unpdf": {
+      "version": "1.8.0",
+      "resolved": "https://registry.npmjs.org/unpdf/-/unpdf-1.8.0.tgz",
+      "integrity": "sha512-jQlkckbe5nKxRHQdbvo9IKHlU6Cjq00UlxxB8lrCIxvS2o5IbAL1wM+4a1Yc3+BIohg9p5AsoaftwO+G4Aq/qQ==",
+      "license": "MIT",
+      "engines": {
+        "node": ">=22"
+      },
+      "peerDependencies": {
+        "@napi-rs/canvas": "^0.1.69 || ^1.0.0"
+      },
+      "peerDependenciesMeta": {
+        "@napi-rs/canvas": {
+          "optional": true
+        }
+      }
+    }
+  }
+}

package/extensions/opl-webaccess/package.json

@@ -0,0 +1,18 @@
+{
+  "name": "opl-webaccess",
+  "version": "1.0.0",
+  "description": "Web search and content extraction for pi. Search the web via Gemini AI, fetch and read web pages, and extract text from PDFs — all from within the agent.",
+  "main": "index.js",
+  "scripts": {
+    "test": "echo \"Error: no test specified\" && exit 1"
+  },
+  "keywords": [],
+  "author": "",
+  "license": "ISC",
+  "dependencies": {
+    "@mozilla/readability": "^0.6.0",
+    "linkedom": "^0.18.13",
+    "turndown": "^7.2.4",
+    "unpdf": "^1.8.0"
+  }
+}

package/extensions/opl-webaccess/pdf.ts

@@ -0,0 +1,8 @@
+import { errorMessage } from "./utils.js";
+
+export async function extractPdfBuffer(buffer: ArrayBuffer): Promise<string> {
+  const { getDocumentProxy, extractText } = await import("unpdf");
+  const pdf = await getDocumentProxy(new Uint8Array(buffer));
+  const { text } = await extractText(pdf, { mergePages: true });
+  return text ?? "";
+}