fix(core): support PDF files in V2 read tool

packages/core/src/tool/read-filesystem.ts

@@ -209,7 +209,31 @@ export const read = Effect.fn("ReadTool.read")(function* (
           mime,
         }
       }
-      if (startsWith(first, [0x25, 0x50, 0x44, 0x46]) || extensions.has(path.extname(resource).toLowerCase()))
+      if (startsWith(first, [0x25, 0x50, 0x44, 0x46])) {
+        if (info.size > MAX_MEDIA_INGEST_BYTES)
+          return yield* Effect.fail(new MediaIngestLimitError({ resource, maximumBytes: MAX_MEDIA_INGEST_BYTES }))
+        const chunks = [first]
+        let total = first.length
+        while (total <= MAX_MEDIA_INGEST_BYTES) {
+          const chunk = yield* file.readAlloc(Math.min(64 * 1024, MAX_MEDIA_INGEST_BYTES + 1 - total))
+          if (Option.isNone(chunk)) break
+          chunks.push(chunk.value)
+          total += chunk.value.length
+        }
+        if (total > MAX_MEDIA_INGEST_BYTES)
+          return yield* Effect.fail(new MediaIngestLimitError({ resource, maximumBytes: MAX_MEDIA_INGEST_BYTES }))
+        return {
+          uri: pathToFileURL(real).href,
+          name: path.basename(real),
+          content: Buffer.concat(
+            chunks.map((chunk) => Buffer.from(chunk)),
+            total,
+          ).toString("base64"),
+          encoding: "base64" as const,
+          mime: "application/pdf",
+        }
+      }
+      if (extensions.has(path.extname(resource).toLowerCase()))
         return yield* Effect.fail(new BinaryFileError({ resource }))
       const paged = info.size > MAX_READ_BYTES || page.offset !== undefined || page.limit !== undefined
       if (!paged) {

packages/core/src/tool/read.ts

@@ -39,16 +39,22 @@ const layer = Layer.effectDiscard(
       .register({
         [name]: Tool.make({
           description:
-            "Read a text file or supported image, page through a large UTF-8 text file by line offset, or list a directory page. Relative paths resolve from the current location; absolute paths inside it are accepted, while external absolute paths require external_directory approval.",
+            "Read a text file, supported image, or PDF; page through a large UTF-8 text file by line offset; or list a directory page. Relative paths resolve from the current location; absolute paths inside it are accepted, while external absolute paths require external_directory approval.",
           input: Input,
           output: Output,
           toModelOutput: ({ input, output }) => {
-            if (!("encoding" in output) || output.encoding !== "base64" || !SUPPORTED_IMAGE_MIMES.has(output.mime))
-              return []
-            return [
-              { type: "text", text: "Image read successfully" },
-              { type: "file", data: output.content, mime: output.mime, name: input.path },
-            ]
+            if (!("encoding" in output) || output.encoding !== "base64") return []
+            if (SUPPORTED_IMAGE_MIMES.has(output.mime))
+              return [
+                { type: "text", text: "Image read successfully" },
+                { type: "file", data: output.content, mime: output.mime, name: input.path },
+              ]
+            if (output.mime === "application/pdf")
+              return [
+                { type: "text", text: "PDF read successfully" },
+                { type: "file", data: output.content, mime: output.mime, name: input.path },
+              ]
+            return []
           },
           execute: (input, context) => {
             return Effect.gen(function* () {
@@ -88,7 +94,7 @@ const layer = Layer.effectDiscard(
                   .normalize(resource, { ...content, encoding: "base64" })
                   .pipe(Effect.catchTag("Image.ResizerUnavailableError", () => Effect.succeed(content)))
               }
-              if ("encoding" in content && content.encoding === "base64")
+              if ("encoding" in content && content.encoding === "base64" && content.mime !== "application/pdf")
                 return yield* Effect.fail(new ReadToolFileSystem.BinaryFileError({ resource }))
               return content
             }).pipe(