R77-A1: 修复腾讯OCR的PDF识别链路

server/src/jobs/ocrJob.js

@@ -6,7 +6,13 @@ const { readFileBuffer } = require("../services/storage");
 const OCR_DUPLICATE_ERROR = "duplicate_invoice_code_number";
 
 function trimErrorMessage(error) {
-  const message = error?.message ?? "ocr_failed";
+  const code = typeof error?.code === "string" ? error.code : null;
+  const transportMode = typeof error?.transportMode === "string" ? error.transportMode : null;
+  const baseMessage = error?.message ?? "ocr_failed";
+  const message =
+    transportMode || code
+      ? `[${transportMode ?? "unknown"}][${code ?? "ocr_failed"}] ${baseMessage}`
+      : baseMessage;
   if (message.length > 500) {
     return message.slice(0, 500);
   }
@@ -53,7 +59,7 @@ async function claimPendingInvoices(prisma, config, workerId) {
         ocr_lock_owner = ${workerId}
     FROM candidates
     WHERE i.id = candidates.id
-    RETURNING i.id, i.file_sha256, i.ocr_type, i.storage_path, i.ocr_attempts
+    RETURNING i.id, i.file_sha256, i.ocr_type, i.storage_path, i.mime_type, i.ocr_attempts
   `;
 }
 
@@ -110,6 +116,7 @@ async function getOrCreateOcrResult(prisma, config, claimedInvoice, imageBase64)
     config,
     ocrType: claimedInvoice.ocr_type,
     imageBase64,
+    sourceMimeType: claimedInvoice.mime_type,
   });
 
   try {
@@ -271,6 +278,8 @@ async function processClaimedInvoice(prisma, config, claimedInvoice, workerId, l
         {
           invoiceId: claimedInvoice.id,
           ocrType: claimedInvoice.ocr_type,
+          mimeType: claimedInvoice.mime_type,
+          transportMode: normalized?.transportMode ?? normalized?.raw?.transportMode ?? null,
           qualityError,
         },
         "OCR invoice marked as failed for missing required fields",
@@ -291,6 +300,8 @@ async function processClaimedInvoice(prisma, config, claimedInvoice, workerId, l
         {
           invoiceId: claimedInvoice.id,
           duplicateInvoiceId: duplicate.id,
+          mimeType: claimedInvoice.mime_type,
+          transportMode: normalized?.transportMode ?? normalized?.raw?.transportMode ?? null,
         },
         "OCR invoice marked as duplicate",
       );
@@ -302,7 +313,16 @@ async function processClaimedInvoice(prisma, config, claimedInvoice, workerId, l
   } catch (error) {
     const message = trimErrorMessage(error);
     await markInvoiceAsFailed(prisma, claimedInvoice, message, config);
-    logger.error({ err: error, invoiceId: claimedInvoice.id, workerId }, "OCR processing failed");
+    logger.error(
+      {
+        err: error,
+        invoiceId: claimedInvoice.id,
+        mimeType: claimedInvoice.mime_type,
+        workerId,
+        transportMode: error?.transportMode ?? null,
+      },
+      "OCR processing failed",
+    );
     return { outcome: "failed" };
   }
 }