feat(hub): expose pdf_to_md_bundle as MCP tool to agent + skill (ADR-0027) (#9)

Co-authored-by: Hong Jiarong <me@jrhim.com>
Co-committed-by: Hong Jiarong <me@jrhim.com>

hub/src/feishu/fileDeliveryTool.ts

@@ -7,11 +7,16 @@ import { readFeishuContext } from "./read.js";
 import type { ApprovalManager } from "./approval.js";
 import { CPH_HUB_MCP_TOOL_IDS, type CphHubMcpToolId } from "../agent/roleTools.js";
 import { WorkspaceFileBoundaryError } from "../security/workspaceFiles.js";
+import type { PrismaClient } from "@prisma/client";
+import type { LocalSecretEnvelope } from "../security/secretEnvelope.js";
+import { createPdfToMdBundleAdapter } from "../capability/pdfToMdBundle.js";
+import { AliyunDocmindClient } from "../capability/docmindClient.js";
 
 export interface FileDeliveryToolOptions {
   readonly rt: FeishuRuntime;
   readonly chatId: string;
   readonly projectId: string;
+  readonly organizationId: string;
   readonly runId: string;
   readonly workspaceRoot?: string | undefined;
   readonly workspaceDir: string;
@@ -20,6 +25,8 @@ export interface FileDeliveryToolOptions {
   readonly approvalManager: ApprovalManager;
   readonly onDelivered?: (path: string) => void;
   readonly tools?: readonly CphHubMcpToolId[] | undefined;
+  readonly prisma: PrismaClient;
+  readonly secretEnvelope: LocalSecretEnvelope;
 }
 
 export function createFileDeliveryMcpServer(options: FileDeliveryToolOptions): McpSdkServerConfigWithInstance {
@@ -230,6 +237,51 @@ export function createFileDeliveryMcpServer(options: FileDeliveryToolOptions): M
     );
   }
 
+  if (enabledTools.has("convert_pdf_to_md")) {
+    const adapter = createPdfToMdBundleAdapter({
+      secrets: options.secretEnvelope,
+      client: new AliyunDocmindClient(),
+      prisma: options.prisma,
+    });
+    tools.push(
+      tool(
+        "convert_pdf_to_md",
+        "Convert a PDF file in the workspace to a Markdown bundle (markdown + extracted images) using Alibaba Cloud Document Mind. The PDF must already be in the workspace (use feishu_download_resource first if it came from Feishu). Returns the path to the generated markdown file and the list of extracted image paths. Mathematical formulas are converted to LaTeX.",
+        {
+          input_path: z.string().describe("Relative path to the input PDF within the workspace."),
+          output_dir: z.string().describe("Relative directory within the workspace to write the markdown and images into. Will be created if it does not exist."),
+        },
+        async (args) => {
+          try {
+            const result = await adapter.invoke({
+              runId: options.runId,
+              organizationId: options.organizationId,
+              projectId: options.projectId,
+              workspaceDir: options.workspaceDir,
+              inputPath: args.input_path,
+              outputDir: args.output_dir,
+              prisma: options.prisma,
+            });
+            const lines = [`Converted PDF to markdown. ${result.artifacts.length} files written:`];
+            for (const artifact of result.artifacts) {
+              lines.push(`  - ${artifact.path} (${artifact.kind})`);
+            }
+            lines.push(`Pages: ${result.consumption.quantity}, Cost: $${(result.consumption.costUsd ?? 0).toFixed(4)}`);
+            return {
+              content: [{ type: "text", text: lines.join("\n") }],
+            };
+          } catch (e) {
+            return {
+              isError: true,
+              content: [{ type: "text", text: e instanceof Error ? e.message : String(e) }],
+            };
+          }
+        },
+        { alwaysLoad: true },
+      ),
+    );
+  }
+
   const instructions = mcpInstructions(enabledTools);
   return createSdkMcpServer({
     name: "cph_hub",
@@ -260,5 +312,12 @@ function mcpInstructions(enabledTools: ReadonlySet<CphHubMcpToolId>): string {
   if (enabledTools.has("request_approval")) {
     instructions.push("Use request_approval when explicit human approval or confirmation is required before continuing.");
   }
+  if (enabledTools.has("convert_pdf_to_md")) {
+    instructions.push(
+      "Use convert_pdf_to_md when the user asks to convert a PDF to Markdown.",
+      "If the PDF came from a Feishu message, first use feishu_download_resource to save it to the workspace, then call convert_pdf_to_md.",
+      "Do NOT attempt to parse PDFs yourself with Read or Bash — always use convert_pdf_to_md for accurate text, formula, and image extraction.",
+    );
+  }
   return instructions.join(" ");
 }