Add soft-deletion / update field_hash generation

app/jobs/one_time/recalc_heartbeat_field_hash_job.rb

@@ -0,0 +1,15 @@
+class OneTime::RecalcHeartbeatFieldHashJob < ApplicationJob
+  queue_as :default
+
+  def perform
+    Heartbeat.find_each(batch_size: 100) do |heartbeat|
+      begin
+        heartbeat.send(:set_fields_hash!)
+        heartbeat.save!
+      rescue ActiveRecord::RecordNotUnique
+        # If we have a duplicate fields_hash, soft delete this record
+        heartbeat.soft_delete
+      end
+    end
+  end
+end

app/models/heartbeat.rb

@@ -6,8 +6,13 @@ class Heartbeat < ApplicationRecord
 
   time_range_filterable_field :time
 
+  # Default scope to exclude deleted records
+  default_scope { where(deleted_at: nil) }
+
   scope :today, -> { where(time: Time.current.beginning_of_day..Time.current.end_of_day) }
   scope :recent, -> { where("created_at > ?", 24.hours.ago) }
+  scope :with_deleted, -> { unscope(where: :deleted_at) }
+  scope :only_deleted, -> { with_deleted.where.not(deleted_at: nil) }
 
   enum :source_type, {
     direct_entry: 0,
@@ -97,11 +102,25 @@ class Heartbeat < ApplicationRecord
   end
 
   def self.generate_fields_hash(attributes)
-    Digest::MD5.hexdigest(attributes.except(*self.unindexed_attributes).to_json)
+    string_attributes = attributes.transform_keys(&:to_s)
+    indexed_attributes = string_attributes.slice(*self.indexed_attributes)
+    Digest::MD5.hexdigest(indexed_attributes.to_json)
   end
 
-  def self.unindexed_attributes
-    %w[id created_at updated_at source_type fields_hash ysws_program]
+  def self.indexed_attributes
+    %w[user_id branch category dependencies editor entity language machine operating_system project type user_agent line_additions line_deletions lineno lines cursorpos project_root_count time is_write]
+  end
+
+  def set_raw_data
+    self.raw_data = self.attributes.slice(*self.class.indexed_attributes)
+  end
+
+  def soft_delete
+    update_column(:deleted_at, Time.current)
+  end
+
+  def restore
+    update_column(:deleted_at, nil)
   end
 
   private

db/migrate/20250507182617_add_deleted_at_to_heartbeats.rb

@@ -0,0 +1,5 @@
+class AddDeletedAtToHeartbeats < ActiveRecord::Migration[8.0]
+  def change
+    add_column :heartbeats, :deleted_at, :datetime
+  end
+end

db/schema.rb

@@ -10,7 +10,7 @@
 #
 # It's strongly recommended that you check this file into your version control system.
 
-ActiveRecord::Schema[8.0].define(version: 2025_05_07_174855) do
+ActiveRecord::Schema[8.0].define(version: 2025_05_07_182617) do
   # These are extensions that must be enabled in order to support this database
   enable_extension "pg_catalog.plpgsql"
 
@@ -207,6 +207,7 @@ ActiveRecord::Schema[8.0].define(version: 2025_05_07_174855) do
     t.integer "source_type", null: false
     t.inet "ip_address"
     t.integer "ysws_program", default: 0, null: false
+    t.datetime "deleted_at"
     t.index ["category", "time"], name: "index_heartbeats_on_category_and_time"
     t.index ["fields_hash"], name: "index_heartbeats_on_fields_hash", unique: true
     t.index ["user_id"], name: "index_heartbeats_on_user_id"