feat: update the read tool to remove the pages param, and no longer output PDF content in base64

Author: qorzj

packages/core/src/prompt.ts

@@ -589,7 +589,7 @@ export function getTools(_options: PromptToolOptions = {}, externalTools: ToolDe
       type: "function",
       function: {
         name: "read",
-        description: "Read files from the filesystem (text, images, PDFs, notebooks).",
+        description: "Read files from the filesystem (text, images, notebooks).",
         parameters: {
           type: "object",
           properties: {
@@ -605,10 +605,6 @@ export function getTools(_options: PromptToolOptions = {}, externalTools: ToolDe
               type: "number",
               description: "Number of lines to read",
             },
-            pages: {
-              type: "string",
-              description: 'Page range for PDF files (e.g., "1-5", "3", "10-20"). Only applicable to PDF files.',
-            },
           },
           required: ["file_path"],
           additionalProperties: false,

packages/core/src/tests/prompt.test.ts

@@ -55,6 +55,12 @@ test("getTools requires bash sideEffects permission scopes", () => {
   assert.equal(runInBackground.type, "boolean");
 });
 
+test("getTools does not expose the unused PDF pages parameter", () => {
+  const tool = getTools().find((candidate) => candidate.function.name === "read");
+  assert.ok(tool);
+  assert.equal("pages" in tool.function.parameters.properties, false);
+});
+
 test("getSystemPrompt always includes WebSearch docs", () => {
   const prompt = getSystemPrompt("/tmp/project");
   assert.equal(prompt.includes("## WebSearch"), true);

packages/core/src/tests/tool-handlers.test.ts

@@ -998,6 +998,24 @@ test("Read returns an acknowledgement for images and attaches the image as a fol
   );
 });
 
+test("Read reports PDFs as binary without attaching their contents", async () => {
+  const workspace = createTempWorkspace();
+  const filePath = path.join(workspace, "document.pdf");
+  fs.writeFileSync(filePath, "%PDF-1.7\n" + "x".repeat(1024 * 1024));
+
+  const readResult = await handleReadTool({ file_path: filePath }, createContext("pdf-read", workspace));
+
+  assert.equal(readResult.ok, true);
+  assert.equal(readResult.output, "WARNING: File is binary.");
+  assert.deepEqual(readResult.metadata, {
+    mime: "application/pdf",
+    encoding: "base64",
+    bytes: 1024 * 1024 + "%PDF-1.7\n".length,
+    pageCount: 0,
+  });
+  assert.equal(readResult.followUpMessages, undefined);
+});
+
 function createContext(
   sessionId: string,
   projectRoot: string,

packages/core/src/tools/read-handler.ts

@@ -13,8 +13,6 @@ import {
 
 const DEFAULT_LINE_LIMIT = 2000;
 const MAX_LINE_LENGTH = 2000;
-const PDF_LARGE_PAGE_THRESHOLD = 10;
-const PDF_MAX_PAGE_RANGE = 20;
 const LINE_NUMBER_WIDTH = 6;
 const DEFAULT_GITIGNORE = [
   "node_modules/",
@@ -41,12 +39,6 @@ const DEFAULT_GITIGNORE = [
   "target/",
 ];
 
-type PageRange = {
-  start: number;
-  end: number;
-  count: number;
-};
-
 type TextReadResult = {
   content: string;
   output: string;
@@ -159,36 +151,8 @@ export async function handleReadTool(
     }
 
     if (ext === ".pdf") {
-      const pagesParam = typeof args.pages === "string" ? args.pages.trim() : "";
       const buffer = fs.readFileSync(filePath);
       const pageCount = countPdfPages(buffer);
-      const pageRange = pagesParam ? parsePageRange(pagesParam) : null;
-
-      if (!pageRange && pageCount !== null && pageCount > PDF_LARGE_PAGE_THRESHOLD) {
-        return {
-          ok: false,
-          name: "read",
-          error: `PDF has ${pageCount} pages; provide "pages" to read a range.`,
-        };
-      }
-
-      if (pageRange && pageRange.count > PDF_MAX_PAGE_RANGE) {
-        return {
-          ok: false,
-          name: "read",
-          error: `PDF page range exceeds ${PDF_MAX_PAGE_RANGE} pages.`,
-        };
-      }
-
-      if (pageRange && pageCount !== null && pageRange.end > pageCount) {
-        return {
-          ok: false,
-          name: "read",
-          error: `PDF page range exceeds total page count (${pageCount}).`,
-        };
-      }
-
-      const base64 = buffer.toString("base64");
       markFileRead(context.sessionId, filePath, {
         content: "",
         timestamp: Math.floor(stat.mtimeMs),
@@ -197,13 +161,12 @@ export async function handleReadTool(
       return {
         ok: true,
         name: "read",
-        output: `data:application/pdf;base64,${base64}`,
+        output: "WARNING: File is binary.",
         metadata: {
           mime: "application/pdf",
           encoding: "base64",
           bytes: buffer.length,
           pageCount,
-          pages: pageRange ? `${pageRange.start}-${pageRange.end}` : null,
         },
       };
     }
@@ -520,45 +483,6 @@ function countPdfPages(buffer: Buffer): number | null {
   }
 }
 
-function parsePageRange(input: string): PageRange {
-  const trimmed = input.trim();
-  if (!trimmed) {
-    throw new Error("pages must be a non-empty string.");
-  }
-  if (trimmed.includes(",")) {
-    throw new Error('pages must be a single range like "1-5" or "3".');
-  }
-
-  const parts = trimmed.split("-").map((part) => part.trim());
-  if (parts.length === 1) {
-    const value = parsePositiveInt(parts[0], "pages");
-    return { start: value, end: value, count: 1 };
-  }
-
-  if (parts.length === 2) {
-    const start = parsePositiveInt(parts[0], "pages");
-    const end = parsePositiveInt(parts[1], "pages");
-    if (end < start) {
-      throw new Error("pages range end must be >= start.");
-    }
-    return { start, end, count: end - start + 1 };
-  }
-
-  throw new Error('pages must be a single range like "1-5" or "3".');
-}
-
-function parsePositiveInt(value: string, label: string): number {
-  const numeric = Number(value);
-  if (!Number.isFinite(numeric)) {
-    throw new Error(`${label} must be a number.`);
-  }
-  const integer = Math.trunc(numeric);
-  if (integer < 1) {
-    throw new Error(`${label} must be >= 1.`);
-  }
-  return integer;
-}
-
 function readNotebook(filePath: string): string {
   const raw = fs.readFileSync(filePath, "utf8");
   if (!raw) {

packages/core/templates/tools/read.md.ejs

@@ -15,7 +15,6 @@ Usage:
 <%_ } else { _%>
 - This tool can inspect image files, but the current model is not multimodal, so image reads are not presented visually to the model.
 <%_ } _%>
-- This tool can read PDF files (.pdf). For large PDFs (more than 10 pages), you MUST provide the pages parameter to read specific page ranges (e.g., pages: "1-5"). Reading a large PDF without the pages parameter will fail. Maximum 20 pages per request.
 - This tool can read Jupyter notebooks (.ipynb files) and returns all cells with their outputs, combining code, text, and visualizations.
 - This tool can only read files, not directories. To read a directory, use an ls command via the Bash tool.
 - You can call multiple tools in a single response. It is always better to speculatively read multiple potentially useful files in parallel.
@@ -38,10 +37,6 @@ Usage:
     "limit": {
       "description": "The number of lines to read. Only provide if the file is too large to read at once.",
       "type": "number"
-    },
-    "pages": {
-      "description": "Page range for PDF files (e.g., \"1-5\", \"3\", \"10-20\"). Only applicable to PDF files. Maximum 20 pages per request.",
-      "type": "string"
     }
   },
   "required": [