fix(messages): reduce audio transcription 400 retry noise (#13487)

## Summary
This PR reduces duplicate failure noise for audio transcription jobs
that fail with permanent HTTP 400 responses, and fixes a file-format
edge case causing intermittent 400s.

Sentry issue: [CHATWOOT-99E /
6660541334](https://chatwoot-p3.sentry.io/issues/6660541334/)

## Confirmed root cause
For some attachments, the stored filename had no extension (example:
`speech`, content type `audio/mpeg`).
When the temporary transcription upload file was created without an
extension, OpenAI returned:
`Unrecognized file format` (HTTP 400).

## Scope of changes
1. `Messages::AudioTranscriptionJob`
- Keeps `discard_on Faraday::BadRequestError` to avoid retry storms on
permanent request errors.
- Adds explicit Rails warning logs for discarded jobs with
attachment/job/status context.

2. `Messages::AudioTranscriptionService`
- Keeps guaranteed temp file cleanup via `ensure`.
- Ensures temp upload files include an extension when the original
filename has none, derived from blob `content_type`.
- This addresses intermittent failures like extensionless `audio/mpeg`
files.

## Reproduction
Enable audio transcription for an account and process an audio
attachment whose stored filename has no extension (for example `speech`)
but valid audio content type (`audio/mpeg`).
Before this fix, OpenAI transcription could return HTTP 400
`Unrecognized file format` for that attachment while similar attachments
with extensions succeeded.

## Testing
Ran:
`bundle exec rubocop
enterprise/app/jobs/messages/audio_transcription_job.rb
enterprise/app/services/messages/audio_transcription_service.rb`

Result: both modified files pass lint with no offenses.

enterprise/app/jobs/messages/audio_transcription_job.rb

@@ -1,6 +1,15 @@
 class Messages::AudioTranscriptionJob < ApplicationJob
   queue_as :low
 
+  discard_on Faraday::BadRequestError do |job, error|
+    log_context = {
+      attachment_id: job.arguments.first,
+      job_id: job.job_id,
+      status_code: error.response&.dig(:status)
+    }
+
+    Rails.logger.warn("Discarding audio transcription job due to bad request: #{log_context}")
+  end
   retry_on ActiveStorage::FileNotFoundError, wait: 2.seconds, attempts: 3
 
   def perform(attachment_id)

enterprise/app/services/messages/audio_transcription_service.rb

@@ -31,12 +31,20 @@ class Messages::AudioTranscriptionService< Llm::LegacyBaseOpenAiService
   end
 
   def fetch_audio_file
+    blob = attachment.file.blob
     temp_dir = Rails.root.join('tmp/uploads/audio-transcriptions')
     FileUtils.mkdir_p(temp_dir)
-    temp_file_path = File.join(temp_dir, "#{attachment.file.blob.key}-#{attachment.file.filename}")
+    temp_file_name = "#{blob.key}-#{blob.filename}"
+
+    if blob.filename.extension_without_delimiter.blank?
+      extension = extension_from_content_type(blob.content_type)
+      temp_file_name = "#{temp_file_name}.#{extension}" if extension.present?
+    end
+
+    temp_file_path = File.join(temp_dir, temp_file_name)
 
     File.open(temp_file_path, 'wb') do |file|
-      attachment.file.blob.open do |blob_file|
+      blob.open do |blob_file|
         IO.copy_stream(blob_file, file)
       end
     end
@@ -49,13 +57,12 @@ class Messages::AudioTranscriptionService< Llm::LegacyBaseOpenAiService
     return transcribed_text if transcribed_text.present?
 
     temp_file_path = fetch_audio_file
-
     transcribed_text = nil
 
     File.open(temp_file_path, 'rb') do |file|
       response = @client.audio.transcribe(
         parameters: {
-          model: 'whisper-1',
+          model: WHISPER_MODEL,
           file: file,
           temperature: 0.4
         }
@@ -63,10 +70,10 @@ class Messages::AudioTranscriptionService< Llm::LegacyBaseOpenAiService
       transcribed_text = response['text']
     end
 
-    FileUtils.rm_f(temp_file_path)
-
     update_transcription(transcribed_text)
     transcribed_text
+  ensure
+    FileUtils.rm_f(temp_file_path) if temp_file_path.present?
   end
 
   def instrumentation_params(file_path)
@@ -90,4 +97,15 @@ class Messages::AudioTranscriptionService< Llm::LegacyBaseOpenAiService
 
     message.reindex
   end
+
+  def extension_from_content_type(content_type)
+    subtype = content_type.to_s.downcase.split(';').first.to_s.split('/').last.to_s
+    return if subtype.blank?
+
+    {
+      'x-m4a' => 'm4a',
+      'x-wav' => 'wav',
+      'x-mp3' => 'mp3'
+    }.fetch(subtype, subtype)
+  end
 end

spec/enterprise/services/messages/audio_transcription_service_spec.rb

@@ -8,8 +8,8 @@ RSpec.describe Messages::AudioTranscriptionService, type: :service do
 
   before do
     # Create required installation configs
-    create(:installation_config, name: 'CAPTAIN_OPEN_AI_API_KEY', value: 'test-api-key')
-    create(:installation_config, name: 'CAPTAIN_OPEN_AI_MODEL', value: 'gpt-4o-mini')
+    InstallationConfig.find_or_create_by!(name: 'CAPTAIN_OPEN_AI_API_KEY') { |config| config.value = 'test-api-key' }
+    InstallationConfig.find_or_create_by!(name: 'CAPTAIN_OPEN_AI_MODEL') { |config| config.value = 'gpt-4o-mini' }
 
     # Mock usage limits for transcription to be available
     allow(account).to receive(:usage_limits).and_return({ captain: { responses: { current_available: 100 } } })
@@ -64,4 +64,24 @@ RSpec.describe Messages::AudioTranscriptionService, type: :service do
       end
     end
   end
+
+  describe '#fetch_audio_file' do
+    let(:service) { described_class.new(attachment) }
+
+    before do
+      attachment.file.attach(
+        io: File.open(Rails.public_path.join('audio/widget/ding.mp3')),
+        filename: 'speech',
+        content_type: 'audio/mpeg'
+      )
+    end
+
+    it 'adds extension from content type when filename has no extension' do
+      temp_file_path = service.send(:fetch_audio_file)
+
+      expect(File.extname(temp_file_path)).to eq('.mpeg')
+    ensure
+      FileUtils.rm_f(temp_file_path) if temp_file_path.present?
+    end
+  end
 end