Sync in and display repo metadata

app/assets/stylesheets/project_duration.css

@@ -11,6 +11,9 @@
     padding: 1rem;
     box-shadow: 0 2px 4px rgba(0, 0, 0, 0.05);
     transition: transform 0.2s ease;
+    display: flex;
+    flex-direction: column;
+    gap: 0.5rem;
 }
 
 .project-duration-card:hover {
@@ -21,8 +24,21 @@
 .project-header {
     display: flex;
     justify-content: space-between;
+    align-items: flex-start;
+    gap: 0.5rem;
+}
+
+.project-name-section {
+    display: flex;
+    flex-direction: column;
+    gap: 0.25rem;
+    flex: 1;
+}
+
+.project-actions {
+    display: flex;
+    gap: 0.5rem;
     align-items: center;
-    margin-bottom: 0.5rem;
 }
 
 .project-header strong {
@@ -33,6 +49,34 @@
 .project-time {
     font-size: 0.875rem;
     color: var(--muted-color);
+    font-weight: 600;
+}
+
+.project-stars {
+    font-size: 0.75rem;
+    color: var(--muted-color);
+}
+
+.project-description {
+    font-size: 0.875rem;
+    color: var(--muted-color);
+    line-height: 1.4;
+}
+
+.project-languages {
+    font-size: 0.8rem;
+    color: var(--muted-color);
+}
+
+.languages-label {
+    font-weight: 600;
+    margin-right: 0.25rem;
+}
+
+.project-meta {
+    font-size: 0.75rem;
+    color: var(--muted-color);
+    margin-top: 0.25rem;
 }
 
 .project-progress-bar {

app/controllers/static_pages_controller.rb

@@ -95,7 +95,7 @@ class StaticPagesController < ApplicationController
   def project_durations
     return unless current_user
 
-    @project_repo_mappings = current_user.project_repo_mappings
+    @project_repo_mappings = current_user.project_repo_mappings.includes(:repository)
     cache_key = "user_#{current_user.id}_project_durations_#{params[:interval]}"
     cache_key += "_#{params[:from]}_#{params[:to]}" if params[:interval] == "custom"
 
@@ -104,9 +104,11 @@ class StaticPagesController < ApplicationController
       project_times = heartbeats.group(:project).duration_seconds
       project_labels = current_user.project_labels
       project_times.map do |project, duration|
+        mapping = @project_repo_mappings.find { |p| p.project_name == project }
         {
           project: project_labels.find { |p| p.project_key == project }&.label || project || "Unknown",
-          repo_url: @project_repo_mappings.find { |p| p.project_name == project }&.repo_url,
+          repo_url: mapping&.repo_url,
+          repository: mapping&.repository,
           duration: duration
         }
       end.filter { |p| p[:duration].positive? }.sort_by { |p| p[:duration] }.reverse

app/jobs/process_commit_job.rb

@@ -10,9 +10,10 @@ class ProcessCommitJob < ApplicationJob
 
   discard_on ActiveJob::DeserializationError # If User record is gone
 
-  def perform(user_id, commit_sha, commit_api_url, provider_string)
+  def perform(user_id, commit_sha, commit_api_url, provider_string, repository_id = nil)
     provider_sym = provider_string.to_sym # Convert string back to symbol
     user = User.find_by(id: user_id)
+    repository = repository_id ? Repository.find_by(id: repository_id) : nil
 
     unless user
       Rails.logger.warn "[ProcessCommitJob] User ##{user_id} not found. Skipping commit #{commit_sha}."
@@ -31,10 +32,10 @@ class ProcessCommitJob < ApplicationJob
 
     case provider_sym
     when :github
-      process_github_commit(user, commit_sha, commit_api_url)
+      process_github_commit(user, commit_sha, commit_api_url, repository)
     # Add other providers like :gitlab later
     # when :gitlab
-    #   process_gitlab_commit(user, commit_sha, commit_api_url)
+    #   process_gitlab_commit(user, commit_sha, commit_api_url, repository)
     else
       Rails.logger.error "[ProcessCommitJob] Unknown provider '#{provider_sym}' for commit #{commit_sha}."
     end
@@ -42,7 +43,7 @@ class ProcessCommitJob < ApplicationJob
 
   private
 
-  def process_github_commit(user, commit_sha, commit_api_url)
+  def process_github_commit(user, commit_sha, commit_api_url, repository)
     unless user.github_access_token.present?
       Rails.logger.warn "[ProcessCommitJob] User ##{user.id} missing GitHub token for commit #{commit_sha}. Skipping."
       return
@@ -82,6 +83,7 @@ class ProcessCommitJob < ApplicationJob
         Commit.create!(
           sha: api_commit_sha,
           user_id: user.id,
+          repository_id: repository&.id,
           github_raw: commit_data_json,
           created_at: commit_actual_created_at, # Manually set created_at
           updated_at: Time.current # Let Rails handle updated_at, or set explicitly
@@ -95,7 +97,7 @@ class ProcessCommitJob < ApplicationJob
           reset_time = Time.at(response.headers["X-RateLimit-Reset"].to_i)
           delay_seconds = [ (reset_time - Time.current).ceil, 5 ].max # at least 5s delay
           Rails.logger.warn "[ProcessCommitJob] GitHub API rate limit exceeded for User ##{user.id}. Retrying in #{delay_seconds}s. URL: #{commit_api_url}"
-          self.class.set(wait: delay_seconds.seconds).perform_later(user.id, commit_sha, commit_api_url, "github")
+          self.class.set(wait: delay_seconds.seconds).perform_later(user.id, commit_sha, commit_api_url, "github", repository&.id)
         else
           Rails.logger.error "[ProcessCommitJob] GitHub API forbidden (403) for User ##{user.id}. URL: #{commit_api_url}. Response: #{response.body.to_s.truncate(500)}"
         end

app/jobs/pull_repo_commits_job.rb

@@ -22,7 +22,11 @@ class PullRepoCommitsJob < ApplicationJob
       return
     end
 
-    Rails.logger.info "[PullRepoCommitsJob] Pulling commits for #{owner}/#{repo} for User ##{user.id}"
+    # Find the repository record
+    repo_url = "https://github.com/#{owner}/#{repo}"
+    repository = Repository.find_by(url: repo_url)
+
+    Rails.logger.info "[PullRepoCommitsJob] Pulling commits for #{owner}/#{repo} for User ##{user.id} (Repository: #{repository&.id})"
 
     # Get commits from the last 3 days
     since_date = 3.days.ago.iso8601
@@ -37,7 +41,7 @@ class PullRepoCommitsJob < ApplicationJob
 
       if response.status.success?
         commits_data = response.parse
-        process_commits(user, commits_data)
+        process_commits(user, commits_data, repository)
       elsif response.status.code == 404
         Rails.logger.warn "[PullRepoCommitsJob] Repository #{owner}/#{repo} not found (404) for User ##{user.id}."
       elsif response.status.code == 403 # Forbidden, could be rate limit or permissions
@@ -65,7 +69,7 @@ class PullRepoCommitsJob < ApplicationJob
 
   private
 
-  def process_commits(user, commits_data)
+  def process_commits(user, commits_data, repository)
     return if commits_data.empty?
 
     # Get existing commit SHAs to avoid duplicates
@@ -106,7 +110,8 @@ class PullRepoCommitsJob < ApplicationJob
               user.id,
               commit_sha,
               commit_api_url,
-              "github"
+              "github",
+              repository&.id
             )
             enqueued_count += 1
           else

app/jobs/scan_repo_events_for_commits_job.rb

@@ -53,11 +53,23 @@ class ScanRepoEventsForCommitsJob < ApplicationJob
           next
         end
 
+        # Extract repository info from commit API URL
+        # Format: https://api.github.com/repos/owner/repo/commits/sha
+        repository_id = nil
+        if commit_api_url =~ %r{https://api\.github\.com/repos/([^/]+)/([^/]+)/commits/}
+          owner = $1
+          repo = $2
+          repo_url = "https://github.com/#{owner}/#{repo}"
+          repository = Repository.find_by(url: repo_url)
+          repository_id = repository&.id
+        end
+
         potential_commits_buffer << {
           sha: commit_sha,
           api_url: commit_api_url,
           user_id: user.id,
-          provider: event.provider.to_s
+          provider: event.provider.to_s,
+          repository_id: repository_id
         }
       end
 
@@ -101,7 +113,8 @@ class ScanRepoEventsForCommitsJob < ApplicationJob
           commit_details[:user_id],
           commit_details[:sha],
           commit_details[:api_url],
-          commit_details[:provider]
+          commit_details[:provider],
+          commit_details[:repository_id]
         )
         enqueued_count += 1
       end

app/jobs/sync_repo_metadata_job.rb

@@ -0,0 +1,36 @@
+class SyncRepoMetadataJob < ApplicationJob
+  queue_as :default
+
+  retry_on HTTP::TimeoutError, HTTP::ConnectionError, wait: :exponentially_longer, attempts: 3
+  retry_on JSON::ParserError, wait: 10.seconds, attempts: 2
+  discard_on ArgumentError # Invalid repository URLs
+
+  def perform(repository_id)
+    repository = Repository.find_by(id: repository_id)
+    return unless repository
+
+    Rails.logger.info "[SyncRepoMetadataJob] Syncing metadata for #{repository.url}"
+
+    begin
+      # Use any user who has mapped to this repository for API access
+      user = repository.users.joins(:project_repo_mappings).first
+      return unless user
+
+      service = RepoHost::ServiceFactory.for_url(user, repository.url)
+      metadata = service.fetch_repo_metadata
+
+      if metadata
+        repository.update!(metadata)
+        Rails.logger.info "[SyncRepoMetadataJob] Updated metadata for #{repository.url}"
+      else
+        Rails.logger.warn "[SyncRepoMetadataJob] No metadata returned for #{repository.url}"
+      end
+    rescue ArgumentError => e
+      Rails.logger.error "[SyncRepoMetadataJob] #{e.message} for repository #{repository.id}"
+      raise # Discard job for unsupported hosts
+    rescue => e
+      Rails.logger.error "[SyncRepoMetadataJob] Unexpected error: #{e.message}"
+      raise # Retry for other errors
+    end
+  end
+end

app/jobs/sync_stale_repo_metadata_job.rb

@@ -0,0 +1,53 @@
+class SyncStaleRepoMetadataJob < ApplicationJob
+  queue_as :default
+
+  def perform
+    Rails.logger.info "[SyncStaleRepoMetadataJob] Starting sync of stale repository metadata"
+
+    # Find all mappings where the repository has stale metadata or is missing metadata entirely
+    mappings_with_stale_repos = ProjectRepoMapping.includes(:repository, :user)
+                                                  .joins(:repository)
+                                                  .where("repositories.last_synced_at IS NULL OR repositories.last_synced_at < ?", 1.day.ago)
+
+    # Also find mappings where repository is nil (shouldn't happen, but just in case)
+    mappings_without_repos = ProjectRepoMapping.includes(:user)
+                                               .where(repository: nil)
+
+    all_stale_mappings = mappings_with_stale_repos.to_a + mappings_without_repos.to_a
+
+    Rails.logger.info "[SyncStaleRepoMetadataJob] Found #{all_stale_mappings.count} project mappings with stale or missing repository metadata"
+
+    # Group by repository to avoid duplicate API calls
+    repos_to_sync = {}
+
+    all_stale_mappings.each do |mapping|
+      if mapping.repository
+        repos_to_sync[mapping.repository.id] = mapping.repository
+      else
+        # Handle mappings without repository - recreate the repository
+        Rails.logger.warn "[SyncStaleRepoMetadataJob] Found mapping without repository: #{mapping.inspect}"
+        if mapping.repo_url.present?
+          begin
+            repo = Repository.find_or_create_by_url(mapping.repo_url)
+            mapping.update!(repository: repo)
+            repos_to_sync[repo.id] = repo
+          rescue => e
+            Rails.logger.error "[SyncStaleRepoMetadataJob] Failed to create repository for mapping #{mapping.id}: #{e.message}"
+          end
+        end
+      end
+    end
+
+    Rails.logger.info "[SyncStaleRepoMetadataJob] Enqueuing sync for #{repos_to_sync.count} unique repositories"
+
+    repos_to_sync.each_value do |repository|
+      # Only sync if the repository has at least one user (needed for API access)
+      next unless repository.users.exists?
+
+      Rails.logger.info "[SyncStaleRepoMetadataJob] Enqueuing sync for #{repository.url}"
+      SyncRepoMetadataJob.perform_later(repository.id)
+    end
+
+    Rails.logger.info "[SyncStaleRepoMetadataJob] Completed enqueuing sync jobs"
+  end
+end

app/models/commit.rb

@@ -4,6 +4,7 @@ class Commit < ApplicationRecord
   self.primary_key = :sha
 
   belongs_to :user
+  belongs_to :repository, optional: true
 
   validates :sha, presence: true, uniqueness: true
   validates :user_id, presence: true

app/models/project_repo_mapping.rb

@@ -1,5 +1,6 @@
 class ProjectRepoMapping < ApplicationRecord
   belongs_to :user
+  belongs_to :repository, optional: true
 
   has_paper_trail
 
@@ -20,7 +21,8 @@ class ProjectRepoMapping < ApplicationRecord
     "<<LAST PROJECT>>"
   ]
 
-  after_create :schedule_commit_pull
+  after_create :create_repository_and_sync
+  after_update :sync_repository_if_url_changed
 
   private
 
@@ -30,6 +32,24 @@ class ProjectRepoMapping < ApplicationRecord
     end
   end
 
+  def create_repository_and_sync
+    # Create or find repository record
+    repo = Repository.find_or_create_by_url(repo_url)
+    update_column(:repository_id, repo.id)
+
+    # Schedule commit pull and metadata sync
+    schedule_commit_pull
+    SyncRepoMetadataJob.perform_later(repo.id)
+  end
+
+  def sync_repository_if_url_changed
+    if saved_change_to_repo_url?
+      repo = Repository.find_or_create_by_url(repo_url)
+      update_column(:repository_id, repo.id)
+      SyncRepoMetadataJob.perform_later(repo.id)
+    end
+  end
+
   def schedule_commit_pull
     # Extract owner and repo name from the URL
     # Example URL: https://github.com/owner/repo

app/models/repository.rb

@@ -0,0 +1,44 @@
+class Repository < ApplicationRecord
+  has_many :project_repo_mappings, dependent: :destroy
+  has_many :users, through: :project_repo_mappings
+  has_many :commits, dependent: :destroy
+
+  validates :url, presence: true, uniqueness: true
+  validates :host, presence: true
+  validates :owner, presence: true
+  validates :name, presence: true
+
+  # Check if metadata needs refreshing (older than 1 day)
+  def metadata_stale?
+    last_synced_at.nil? || last_synced_at < 1.day.ago
+  end
+
+  # Get formatted languages list
+  def formatted_languages
+    return nil if languages.blank?
+    languages.split(", ").first(3).join(", ") + (languages.split(", ").length > 3 ? "..." : "")
+  end
+
+  # Parse owner and repo from URL
+  def self.parse_url(url)
+    if url =~ %r{https?://([^/]+)/([^/]+)/([^/]+)/?$}
+      {
+        host: $1,
+        owner: $2,
+        name: $3
+      }
+    else
+      raise ArgumentError, "Invalid repository URL format: #{url}"
+    end
+  end
+
+  # Find or create repository from URL
+  def self.find_or_create_by_url(url)
+    parsed = parse_url(url)
+    find_or_create_by(url: url) do |repo|
+      repo.host = parsed[:host]
+      repo.owner = parsed[:owner]
+      repo.name = parsed[:name]
+    end
+  end
+end

app/services/repo_host/base_service.rb

@@ -0,0 +1,64 @@
+module RepoHost
+  class BaseService
+    def initialize(user, repo_url)
+      @user = user
+      @repo_url = repo_url
+      @owner, @repo = parse_repo_url(repo_url)
+    end
+
+    def fetch_repo_metadata
+      raise NotImplementedError, "Subclasses must implement fetch_repo_metadata"
+    end
+
+    private
+
+    attr_reader :user, :repo_url, :owner, :repo
+
+    def parse_repo_url(url)
+      # Extract owner and repo from URL
+      # Example: https://github.com/owner/repo -> ["owner", "repo"]
+      # Example: https://gitlab.com/owner/repo -> ["owner", "repo"]
+      if url =~ %r{https?://[^/]+/([^/]+)/([^/]+)/?$}
+        [ $1, $2 ]
+      else
+        raise ArgumentError, "Invalid repository URL format: #{url}"
+      end
+    end
+
+    def api_headers
+      raise NotImplementedError, "Subclasses must implement api_headers"
+    end
+
+    def make_api_request(url)
+      response = HTTP.headers(api_headers)
+                     .timeout(connect: 5, read: 10)
+                     .get(url)
+
+      handle_response(response)
+    end
+
+    def handle_response(response)
+      case response.status.code
+      when 200
+        response.parse
+      when 403
+        handle_rate_limit(response)
+      when 404
+        Rails.logger.warn "[#{self.class.name}] Repository #{owner}/#{repo} not found (404)"
+        nil
+      else
+        Rails.logger.error "[#{self.class.name}] API error. Status: #{response.status}"
+        nil
+      end
+    end
+
+    def handle_rate_limit(response)
+      if response.headers["X-RateLimit-Remaining"]&.to_i == 0
+        reset_time = Time.at(response.headers["X-RateLimit-Reset"].to_i)
+        delay_seconds = [ (reset_time - Time.current).ceil, 5 ].max
+        Rails.logger.warn "[#{self.class.name}] Rate limit exceeded. Reset in #{delay_seconds}s"
+      end
+      nil
+    end
+  end
+end

app/services/repo_host/github_service.rb

@@ -0,0 +1,94 @@
+require "http"
+
+module RepoHost
+  class GithubService < BaseService
+    def fetch_repo_metadata
+      return nil unless user.github_access_token.present?
+
+      # Fetch basic repository info
+      repo_data = fetch_repository_info
+      return nil unless repo_data
+
+      # Fetch additional metadata
+      languages_data = fetch_languages
+      commits_data = fetch_recent_commits
+      commit_count = fetch_commit_count(repo_data["default_branch"])
+
+      {
+        stars: repo_data["stargazers_count"],
+        description: repo_data["description"],
+        language: repo_data["language"],
+        languages: languages_data&.keys&.join(", "),
+        homepage: repo_data["homepage"].presence,
+        commit_count: commit_count,
+        last_commit_at: commits_data&.first&.dig("commit", "committer", "date")&.then { |date| Time.parse(date) },
+        last_synced_at: Time.current
+      }
+    end
+
+    private
+
+    def api_headers
+      {
+        "Accept" => "application/vnd.github.v3+json",
+        "Authorization" => "Bearer #{user.github_access_token}",
+        "X-GitHub-Api-Version" => "2022-11-28"
+      }
+    end
+
+    def fetch_repository_info
+      url = "https://api.github.com/repos/#{owner}/#{repo}"
+      make_api_request(url)
+    end
+
+    def fetch_languages
+      url = "https://api.github.com/repos/#{owner}/#{repo}/languages"
+      make_api_request(url)
+    end
+
+    def fetch_recent_commits
+      # Get just the last few commits for metadata
+      url = "https://api.github.com/repos/#{owner}/#{repo}/commits?per_page=5"
+      make_api_request(url)
+    end
+
+    def fetch_commit_count(default_branch = nil)
+      # GitHub API doesn't provide commit count directly, so we need to use a workaround
+      # We'll get the commit count from the commits endpoint with minimal data
+      branch_param = default_branch ? "&sha=#{default_branch}" : ""
+      url = "https://api.github.com/repos/#{owner}/#{repo}/commits?per_page=1#{branch_param}"
+
+      response = HTTP.headers(api_headers)
+                     .timeout(connect: 5, read: 10)
+                     .get(url)
+
+      case response.status.code
+      when 200
+        # Extract commit count from Link header pagination
+        link_header = response.headers["Link"]
+        if link_header
+          # Look for the "last" page number in the Link header
+          # Format: <https://api.github.com/repos/owner/repo/commits?page=962&per_page=1>; rel="last"
+          if match = link_header.match(/.*page=(\d+)[^>]*>;\s*rel="last"/)
+            match[1].to_i
+          else
+            # If no "last" link, there's only one page of commits
+            1
+          end
+        else
+          # No Link header means there's only one page
+          1
+        end
+      when 404
+        Rails.logger.warn "[#{self.class.name}] Repository #{owner}/#{repo} not found for commit count"
+        0
+      else
+        Rails.logger.warn "[#{self.class.name}] Failed to fetch commit count for #{owner}/#{repo}: #{response.status}"
+        0
+      end
+    rescue => e
+      Rails.logger.error "[#{self.class.name}] Error fetching commit count for #{owner}/#{repo}: #{e.message}"
+      0
+    end
+  end
+end

app/services/repo_host/service_factory.rb

@@ -0,0 +1,23 @@
+module RepoHost
+  class ServiceFactory
+    def self.for_url(user, repo_url)
+      case repo_url
+      when %r{github\.com}
+        GithubService.new(user, repo_url)
+      else
+        raise ArgumentError, "Unsupported repository host: #{repo_url}. Currently only GitHub is supported."
+      end
+    end
+
+    def self.supported_hosts
+      %w[github.com]
+    end
+
+    def self.host_for_url(repo_url)
+      uri = URI.parse(repo_url)
+      uri.host
+    rescue URI::InvalidURIError
+      nil
+    end
+  end
+end

app/views/static_pages/_project_durations.html.erb

@@ -6,17 +6,41 @@
     <% project_durations.each do |project| %>
       <div class="project-duration-card">
         <div class="project-header">
-          <strong title="<%= project[:project] %>">
+          <div class="project-name-section">
-            <%= (project[:project].presence || "Unknown").truncate(12) %>
+            <strong title="<%= project[:project] %>">
-          </strong>
+              <%= (project[:project].presence || "Unknown").truncate(15) %>
-          <% if project[:repo_url].present? %>
+            </strong>
-            <%= link_to "🔗", project[:repo_url], target: "_blank" %>
+            <% if project[:repository]&.stars.present? %>
-          <% end %>
+              <span class="project-stars">⭐ <%= project[:repository].stars %></span>
-          <% if current_user.github_uid.present? && project[:project].present? %>
+            <% end %>
-            <%= link_to "✏️", edit_my_project_repo_mapping_path(project_name: project[:project]), class: "edit-repo-link", data: { turbo_frame: '_top'} %>
+          </div>
-          <% end %>
+          <div class="project-actions">
+            <% if project[:repository]&.homepage.present? %>
+              <%= link_to "🌐", project[:repository].homepage, target: "_blank", title: "View project website" %>
+            <% end %>
+            <% if project[:repo_url].present? %>
+              <%= link_to "🔗", project[:repo_url], target: "_blank", title: "View repository" %>
+            <% end %>
+            <% if current_user.github_uid.present? && project[:project].present? %>
+              <%= link_to "✏️", edit_my_project_repo_mapping_path(project_name: project[:project]), class: "edit-repo-link", data: { turbo_frame: '_top'}, title: "Edit mapping" %>
+            <% end %>
+          </div>
           <span class="project-time"><%= short_time_detailed project[:duration] %></span>
         </div>
+        
+        <% if project[:repository]&.description.present? %>
+          <div class="project-description">
+            <%= project[:repository].description.truncate(80) %>
+          </div>
+        <% end %>
+        
+        <% if project[:repository]&.formatted_languages.present? %>
+          <div class="project-languages">
+            <span class="languages-label">Languages:</span>
+            <%= project[:repository].formatted_languages %>
+          </div>
+        <% end %>
+        
         <div class="project-progress-bar">
           <div 
             class="progress" 
@@ -24,6 +48,12 @@
                   background-color: var(--primary-color);"
           ></div>
         </div>
+        
+        <% if project[:repository]&.last_commit_at.present? %>
+          <div class="project-meta">
+            Last commit: <%= time_ago_in_words(project[:repository].last_commit_at) %> ago
+          </div>
+        <% end %>
       </div>
     <% end %>
   </div>

config/initializers/good_job.rb

@@ -141,6 +141,11 @@ Rails.application.configure do
     cleanup_successful_jobs: {
       cron: "0 0 * * *",
       class: "CleanupSuccessfulJobsJob"
+    },
+    sync_stale_repo_metadata: {
+      cron: "0 4 * * *", # Daily at 4 AM
+      class: "SyncStaleRepoMetadataJob",
+      description: "Refreshes repository metadata (stars, commit counts, etc.) for repositories with stale data."
     }
   }
 end

db/migrate/20250530015016_create_repositories.rb

@@ -0,0 +1,20 @@
+class CreateRepositories < ActiveRecord::Migration[8.0]
+  def change
+    create_table :repositories do |t|
+      t.string :url
+      t.string :host
+      t.string :owner
+      t.string :name
+      t.integer :stars
+      t.text :description
+      t.string :language
+      t.text :languages
+      t.integer :commit_count
+      t.datetime :last_commit_at
+      t.datetime :last_synced_at
+
+      t.timestamps
+    end
+    add_index :repositories, :url, unique: true
+  end
+end

db/migrate/20250530015024_update_project_repo_mappings_to_use_repository.rb

@@ -0,0 +1,6 @@
+class UpdateProjectRepoMappingsToUseRepository < ActiveRecord::Migration[8.0]
+  def change
+    # Add repository reference
+    add_reference :project_repo_mappings, :repository, null: true, foreign_key: true
+  end
+end

db/migrate/20250530015530_add_repository_to_commits.rb

@@ -0,0 +1,5 @@
+class AddRepositoryToCommits < ActiveRecord::Migration[8.0]
+  def change
+    add_reference :commits, :repository, null: true, foreign_key: true
+  end
+end

db/migrate/20250530135145_add_homepage_to_repositories.rb

@@ -0,0 +1,5 @@
+class AddHomepageToRepositories < ActiveRecord::Migration[8.0]
+  def change
+    add_column :repositories, :homepage, :string
+  end
+end

db/schema.rb

@@ -10,9 +10,12 @@
 #
 # It's strongly recommended that you check this file into your version control system.
 
-ActiveRecord::Schema[8.0].define(version: 2025_05_27_052632) do
+ActiveRecord::Schema[8.0].define(version: 2025_05_30_135145) do
+  create_schema "pganalyze"
+
   # These are extensions that must be enabled in order to support this database
   enable_extension "pg_catalog.plpgsql"
+  enable_extension "pg_stat_statements"
 
   create_table "ahoy_events", force: :cascade do |t|
     t.bigint "visit_id"
@@ -74,6 +77,8 @@ ActiveRecord::Schema[8.0].define(version: 2025_05_27_052632) do
     t.jsonb "github_raw"
     t.datetime "created_at", null: false
     t.datetime "updated_at", null: false
+    t.bigint "repository_id"
+    t.index ["repository_id"], name: "index_commits_on_repository_id"
     t.index ["user_id"], name: "index_commits_on_user_id"
   end
 
@@ -310,7 +315,9 @@ ActiveRecord::Schema[8.0].define(version: 2025_05_27_052632) do
     t.string "repo_url", null: false
     t.datetime "created_at", null: false
     t.datetime "updated_at", null: false
+    t.bigint "repository_id"
     t.index ["project_name"], name: "index_project_repo_mappings_on_project_name"
+    t.index ["repository_id"], name: "index_project_repo_mappings_on_repository_id"
     t.index ["user_id", "project_name"], name: "index_project_repo_mappings_on_user_id_and_project_name", unique: true
     t.index ["user_id"], name: "index_project_repo_mappings_on_user_id"
   end
@@ -333,6 +340,24 @@ ActiveRecord::Schema[8.0].define(version: 2025_05_27_052632) do
     t.index ["user_id"], name: "index_repo_host_events_on_user_id"
   end
 
+  create_table "repositories", force: :cascade do |t|
+    t.string "url"
+    t.string "host"
+    t.string "owner"
+    t.string "name"
+    t.integer "stars"
+    t.text "description"
+    t.string "language"
+    t.text "languages"
+    t.integer "commit_count"
+    t.datetime "last_commit_at"
+    t.datetime "last_synced_at"
+    t.datetime "created_at", null: false
+    t.datetime "updated_at", null: false
+    t.string "homepage"
+    t.index ["url"], name: "index_repositories_on_url", unique: true
+  end
+
   create_table "sailors_log_leaderboards", force: :cascade do |t|
     t.string "slack_channel_id"
     t.string "slack_uid"
@@ -428,6 +453,7 @@ ActiveRecord::Schema[8.0].define(version: 2025_05_27_052632) do
   end
 
   add_foreign_key "api_keys", "users"
+  add_foreign_key "commits", "repositories"
   add_foreign_key "commits", "users"
   add_foreign_key "email_addresses", "users"
   add_foreign_key "email_verification_requests", "users"
@@ -437,6 +463,7 @@ ActiveRecord::Schema[8.0].define(version: 2025_05_27_052632) do
   add_foreign_key "leaderboard_entries", "users"
   add_foreign_key "mailing_addresses", "users"
   add_foreign_key "physical_mails", "users"
+  add_foreign_key "project_repo_mappings", "repositories"
   add_foreign_key "project_repo_mappings", "users"
   add_foreign_key "repo_host_events", "users"
   add_foreign_key "sign_in_tokens", "users"

test/fixtures/repositories.yml

@@ -0,0 +1,27 @@
+# Read about fixtures at https://api.rubyonrails.org/classes/ActiveRecord/FixtureSet.html
+
+one:
+  url: MyString
+  host: MyString
+  owner: MyString
+  name: MyString
+  stars: 1
+  description: MyText
+  language: MyString
+  languages: MyText
+  commit_count: 1
+  last_commit_at: 2025-05-30 01:50:16
+  last_synced_at: 2025-05-30 01:50:16
+
+two:
+  url: MyString
+  host: MyString
+  owner: MyString
+  name: MyString
+  stars: 1
+  description: MyText
+  language: MyString
+  languages: MyText
+  commit_count: 1
+  last_commit_at: 2025-05-30 01:50:16
+  last_synced_at: 2025-05-30 01:50:16

test/models/repository_test.rb

@@ -0,0 +1,7 @@
+require "test_helper"
+
+class RepositoryTest < ActiveSupport::TestCase
+  # test "the truth" do
+  #   assert true
+  # end
+end