add proper tests

enterprise/app/jobs/captain/documents/pdf_extraction_job.rb

@@ -1,6 +1,6 @@
 class Captain::Documents::PdfExtractionJob < ApplicationJob
-  retry_on ActiveStorage::FileNotFoundError, attempts: 3, wait: 2.seconds, on: :perform
-  retry_on Faraday::BadRequestError, attempts: 3, wait: 2.seconds, on: :perform
+  retry_on ActiveStorage::FileNotFoundError, attempts: 3, wait: 2.seconds
+  retry_on Faraday::BadRequestError, attempts: 3, wait: 2.seconds
 
   queue_as :low
 

enterprise/app/services/captain/tools/pdf_extraction_service.rb

@@ -41,10 +41,27 @@ class Captain::Tools::PdfExtractionService
     log_extraction_success(chunked_content)
 
     success_response(chunked_content)
+  rescue StandardError => e
+    Rails.logger.error "PDF extraction failed: #{e.message}"
+    failure_response([e.message])
   end
 
   def log_extraction_success(chunked_content)
     total_chars = chunked_content.sum { |chunk| chunk[:content].length }
     Rails.logger.info "PDF extraction completed: #{chunked_content.length} chunks, #{total_chars} characters"
   end
+
+  def success_response(content)
+    {
+      success: true,
+      content: content
+    }
+  end
+
+  def failure_response(errors)
+    {
+      success: false,
+      errors: errors
+    }
+  end
 end

enterprise/app/services/captain/tools/pdf_extraction_service/source_handler.rb

@@ -27,9 +27,9 @@ module Captain::Tools::PdfExtractionService::SourceHandler
 
     temp_file = Down.download(
       pdf_source,
-      max_size: MAX_PDF_SIZE,
-      open_timeout: DOWNLOAD_TIMEOUT,
-      read_timeout: DOWNLOAD_TIMEOUT
+      max_size: self.class::MAX_PDF_SIZE,
+      open_timeout: self.class::DOWNLOAD_TIMEOUT,
+      read_timeout: self.class::DOWNLOAD_TIMEOUT
     )
 
     begin

enterprise/app/services/captain/tools/pdf_extraction_service/text_processor.rb

@@ -12,6 +12,12 @@ module Captain::Tools::PdfExtractionService::TextProcessor
     end
 
     text_content
+  rescue PDF::Reader::MalformedPDFError => e
+    Rails.logger.error "Malformed PDF error: #{e.message}"
+    raise StandardError, 'Invalid or corrupted PDF file'
+  rescue StandardError => e
+    Rails.logger.error "PDF extraction error: #{e.message}"
+    raise StandardError, "Failed to extract text from PDF: #{e.message}"
   end
 
   def extract_page_content(page, index)

spec/enterprise/services/captain/tools/pdf_extraction_service_spec.rb

@@ -2,7 +2,7 @@ require 'rails_helper'
 
 RSpec.describe Captain::Tools::PdfExtractionService do
   let(:service) { described_class.new(pdf_source) }
-  let(:sample_pdf_path) { Rails.root.join('spec/fixtures/files/sample.pdf') }
+  let(:sample_pdf_path) { Rails.root.join('spec/fixtures/files/valid_test.pdf') }
 
   describe '#initialize' do
     context 'with valid PDF path' do
@@ -69,12 +69,16 @@ RSpec.describe Captain::Tools::PdfExtractionService do
     end
 
     context 'with malformed PDF' do
-      let(:pdf_source) { Rails.root.join('spec/fixtures/files/sample.txt').to_s }
+      let(:pdf_source) { sample_pdf_path.to_s }
 
       it 'handles malformed PDF gracefully' do
+        # Mock PDF::Reader to raise a MalformedPDFError
+        allow(PDF::Reader).to receive(:open).and_raise(PDF::Reader::MalformedPDFError, 'PDF does not contain EOF marker')
+
         result = service.perform
         expect(result[:success]).to be false
         expect(result[:errors]).to be_an(Array)
+        expect(result[:errors]).to include('Invalid or corrupted PDF file')
       end
     end