Voice entries

Dockerfile

@@ -1,4 +1,4 @@
-FROM ruby:3.4.4-slim-bookworm
+FROM ruby:3.4.7-slim-bookworm
 
 ENV APP_HOME="/app_home"
 ENV BUNDLE_PATH="${APP_HOME}/vendor/bundle"

Dockerfile.prod

@@ -1,7 +1,7 @@
 # syntax = docker/dockerfile:1
 
 # Make sure it matches the Ruby version in .ruby-version and Gemfile
-ARG RUBY_VERSION=3.4.4
+ARG RUBY_VERSION=3.4.7
 FROM ruby:$RUBY_VERSION-slim AS base
 
 # Rails app lives here

Gemfile

@@ -1,7 +1,7 @@
 source 'https://rubygems.org'
 git_source(:github) { |repo| "https://github.com/#{repo}.git" }
 
-ruby '3.4.4'
+ruby '3.4.7'
 
 gem 'puma'
 
@@ -24,6 +24,9 @@ gem 'csv'
 
 gem 'haml-rails'
 
+# AI integration for voice entry processing
+gem 'ruby_llm', '~> 1.9'
+
 # TODO: Dependency to remove
 # Use ransack for search and sorting of tables
 gem 'ransack'

Gemfile.lock

@@ -104,6 +104,17 @@ GEM
     erubi (1.13.1)
     et-orbi (1.4.0)
       tzinfo
+    event_stream_parser (1.0.0)
+    faraday (2.14.0)
+      faraday-net_http (>= 2.0, < 3.5)
+      json
+      logger
+    faraday-multipart (1.1.1)
+      multipart-post (~> 2.0)
+    faraday-net_http (3.4.2)
+      net-http (~> 0.5)
+    faraday-retry (2.3.2)
+      faraday (~> 2.0)
     fugit (1.12.1)
       et-orbi (~> 1.4)
       raabro (~> 1.4)
@@ -159,6 +170,9 @@ GEM
       stimulus-rails
       turbo-rails
     msgpack (1.8.0)
+    multipart-post (2.4.1)
+    net-http (0.8.0)
+      uri (>= 0.11.1)
     net-imap (0.5.12)
       date
       net-protocol
@@ -289,6 +303,17 @@ GEM
       lint_roller (~> 1.1)
       rubocop (~> 1.81)
     ruby-progressbar (1.13.0)
+    ruby_llm (1.9.1)
+      base64
+      event_stream_parser (~> 1)
+      faraday (>= 1.10.0)
+      faraday-multipart (>= 1)
+      faraday-net_http (>= 1)
+      faraday-retry (>= 1)
+      marcel (~> 1.0)
+      ruby_llm-schema (~> 0.2.1)
+      zeitwerk (~> 2)
+    ruby_llm-schema (0.2.5)
     securerandom (0.4.1)
     simplecov (0.22.0)
       docile (~> 1.1)
@@ -357,6 +382,7 @@ DEPENDENCIES
   rubocop-performance
   rubocop-rails
   rubocop-rspec
+  ruby_llm (~> 1.9)
   simplecov
   solid_queue (~> 1.1)
   sqlite3
@@ -365,7 +391,7 @@ DEPENDENCIES
   web-console
 
 RUBY VERSION
-   ruby 3.4.4p34
+   ruby 3.4.7p58
 
 BUNDLED WITH
    2.6.9

app/controllers/voice_entries_controller.rb

@@ -0,0 +1,73 @@
+class VoiceEntriesController < ApplicationController
+  # Rate limiting: 5 requests per minute per user
+  before_action :check_voice_entries_access
+  before_action :check_rate_limit
+
+  def create
+    validate_audio!
+
+    processor = VoiceEntryProcessor.new(
+      user: current_user,
+      audio_file: params[:audio_file].tempfile
+    )
+
+    result = processor.process
+
+    if result[:success]
+      render json: result
+    else
+      render json: result, status: :unprocessable_entity
+    end
+  rescue => e
+    Rails.logger.error "Voice entry creation failed: #{e.message}"
+    render json: {
+      success: false,
+      error: e.message,
+      transcription: nil
+    }, status: :unprocessable_entity
+  end
+
+  private
+
+  def check_voice_entries_access
+    unless current_user.voice_entries_enabled?
+      render json: {
+        success: false,
+        error: 'Voice entries feature is not enabled for your account.',
+        transcription: nil
+      }, status: :forbidden
+    end
+  end
+
+  def validate_audio!
+    audio = params[:audio_file]
+
+    raise 'No audio file provided' unless audio.present?
+
+    # Check content type
+    unless audio.content_type&.start_with?('audio/')
+      raise 'Invalid file type. Must be audio file.'
+    end
+
+    # Check file size (max 5MB)
+    if audio.size > 5.megabytes
+      raise 'Audio file too large. Maximum size is 5MB.'
+    end
+  end
+
+  def check_rate_limit
+    cache_key = "voice_entries:#{current_user.id}:#{Time.current.to_i / 60}"
+    count = Rails.cache.read(cache_key) || 0
+
+    if count >= 5
+      render json: {
+        success: false,
+        error: 'Too many requests. Please wait a moment.',
+        transcription: nil
+      }, status: :too_many_requests
+      return
+    end
+
+    Rails.cache.write(cache_key, count + 1, expires_in: 1.minute)
+  end
+end

app/javascript/controllers/voice_recorder_controller.js

@@ -0,0 +1,170 @@
+import { Controller } from "@hotwired/stimulus"
+
+export default class extends Controller {
+  static targets = ["button", "status", "indicator", "amountField", "dateField", "notesField", "categorySelect"]
+  static values = { url: String }
+
+  connect() {
+    this.mediaRecorder = null
+    this.audioChunks = []
+    this.isRecording = false
+  }
+
+  async toggleRecording() {
+    if (this.isRecording) {
+      this.stopRecording()
+    } else {
+      await this.startRecording()
+    }
+  }
+
+  async startRecording() {
+    try {
+      // Check if browser supports MediaRecorder
+      if (!navigator.mediaDevices || !navigator.mediaDevices.getUserMedia) {
+        this.showError('Voice recording is not supported in your browser')
+        return
+      }
+
+      // Request microphone permission
+      const stream = await navigator.mediaDevices.getUserMedia({ audio: true })
+
+      // Initialize MediaRecorder
+      this.mediaRecorder = new MediaRecorder(stream, { mimeType: 'audio/webm' })
+      this.audioChunks = []
+
+      this.mediaRecorder.addEventListener('dataavailable', (event) => {
+        this.audioChunks.push(event.data)
+      })
+
+      this.mediaRecorder.addEventListener('stop', () => {
+        const audioBlob = new Blob(this.audioChunks, { type: 'audio/webm' })
+        this.submitAudio(audioBlob)
+
+        // Stop all audio tracks to release microphone
+        stream.getTracks().forEach(track => track.stop())
+      })
+
+      this.mediaRecorder.start()
+      this.isRecording = true
+      this.showRecording()
+    } catch (error) {
+      this.showError('Failed to start recording. Please check your microphone permissions.')
+    }
+  }
+
+  stopRecording() {
+    if (this.mediaRecorder && this.isRecording) {
+      this.mediaRecorder.stop()
+      this.isRecording = false
+      this.showProcessing()
+    }
+  }
+
+  async submitAudio(blob) {
+    try {
+      const formData = new FormData()
+      formData.append('audio_file', blob, 'recording.webm')
+
+      // Get CSRF token
+      const csrfToken = document.querySelector('meta[name="csrf-token"]')?.content
+
+      const response = await fetch(this.urlValue, {
+        method: 'POST',
+        headers: {
+          'X-CSRF-Token': csrfToken
+        },
+        body: formData
+      })
+
+      const result = await response.json()
+
+      if (result.success) {
+        this.populateForm(result.data)
+        this.clearFeedback()
+      } else {
+        this.showError(result.error || 'Failed to process audio')
+      }
+    } catch (error) {
+      this.showError('Failed to upload audio. Please try again.')
+    } finally {
+      this.showIdle()
+    }
+  }
+
+  populateForm(data) {
+    // Populate amount field
+    if (data.amount && this.hasAmountFieldTarget) {
+      this.amountFieldTarget.value = data.amount
+    }
+
+    // Populate date field only if a date was extracted
+    // If null, leave the form's default date (today)
+    if (data.date && data.date !== null && this.hasDateFieldTarget) {
+      this.dateFieldTarget.value = data.date
+    }
+
+    // Populate notes field
+    if (data.notes && this.hasNotesFieldTarget) {
+      this.notesFieldTarget.value = data.notes
+    }
+
+    // Populate category select (case-insensitive match)
+    if (data.category_name && this.hasCategorySelectTarget) {
+      const categorySelect = this.categorySelectTarget
+      const options = Array.from(categorySelect.options)
+
+      // Try to find matching category by text (case-insensitive)
+      const matchingOption = options.find(option =>
+        option.text.toLowerCase() === data.category_name.toLowerCase()
+      )
+
+      if (matchingOption) {
+        categorySelect.value = matchingOption.value
+      }
+    }
+  }
+
+  showRecording() {
+    if (this.hasButtonTarget) {
+      this.buttonTarget.innerHTML = '<span data-voice-recorder-target="indicator">🔴</span> <span>Stop Recording</span>'
+      this.buttonTarget.disabled = false
+    }
+    if (this.hasIndicatorTarget) {
+      this.indicatorTarget.style.display = 'inline'
+    }
+  }
+
+  showProcessing() {
+    if (this.hasButtonTarget) {
+      this.buttonTarget.innerHTML = '<span>Processing...</span>'
+      this.buttonTarget.disabled = true
+    }
+  }
+
+  showIdle() {
+    if (this.hasButtonTarget) {
+      this.buttonTarget.innerHTML = '<span>Record Voice Entry</span>'
+      this.buttonTarget.disabled = false
+    }
+    if (this.hasIndicatorTarget) {
+      this.indicatorTarget.style.display = 'none'
+    }
+  }
+
+  showError(message) {
+    if (this.hasStatusTarget) {
+      this.statusTarget.innerHTML = `
+        <div style="padding: 1rem; background: #f8d7da; border: 1px solid #f5c6cb; border-radius: 4px; margin-top: 1rem;">
+          <p style="margin: 0; color: #721c24; font-size: 0.9rem;">${message}</p>
+        </div>
+      `
+    }
+  }
+
+  clearFeedback() {
+    if (this.hasStatusTarget) {
+      this.statusTarget.innerHTML = ''
+    }
+  }
+}