fix(rake): preserve host configuration

README.md

@@ -142,7 +142,8 @@ puts result.issues.to_a.map(&:message)
 - `pages`: fetched page snapshots
 - `issues`: structured issues with `code`, `severity`, `category`, `url`, and `message`
 
-`result.ok?` returns `false` if any error, warning, or notice is present.
+`result.ok?` returns `false` when an error is present. Warnings and notices
+remain available through `result.issues` without making the result fail.
 
 ## Rails Usage
 
@@ -177,7 +178,10 @@ Crawlscope.configuration.audit
 ```
 
 Rake tasks apply it automatically because `crawlscope/tasks` loads the gem
-before Rails evaluates the initializer.
+before Rails evaluates the initializer. Each Rake entry point passes the shared
+`Crawlscope.configuration` object to the CLI, so configured base URLs, sitemap
+paths, registries, and runtime settings are preserved unless a task argument or
+environment override replaces them.
 
 Then run:
 
@@ -220,7 +224,12 @@ bundle exec rake crawlscope:validate:ldjson URL=https://example.com/article
 bundle exec rake 'crawlscope:validate:ldjson[https://example.com/article]'
 ```
 
-`crawlscope:validate` runs all default sitemap rules: indexability, metadata, structured data, uniqueness, content quality, and links. `URL` is the site base. Without `SITEMAP`, Crawlscope uses `/sitemap.xml`. With `SITEMAP`, Crawlscope uses `URL` as the site base and validates URLs from that sitemap. `SITEMAP` may be a full URL or a local file path.
+`crawlscope:validate` runs all default sitemap rules: indexability, metadata,
+structured data, uniqueness, content quality, and links. `URL` is the site
+base. Without `SITEMAP`, Crawlscope uses the configured sitemap path, then
+falls back to `/sitemap.xml`. With `SITEMAP`, Crawlscope uses `URL` as the site
+base and validates URLs from that sitemap. `SITEMAP` may be a full URL or a
+local file path.
 
 Plain `rake` does not pass `--url` style flags to tasks. Use `URL=...` or the
 task-argument form above instead.

lib/crawlscope/rake_tasks.rb

@@ -16,8 +16,8 @@ def validate_rule(rule, url: nil, sitemap_path: nil)
       validate(url: url, sitemap_path: sitemap_path, rule_names: rule)
     end
 
-    def run(command, argv: [])
-      status = Cli.start([command, *argv], out: $stdout, err: $stderr)
+    def run(command, argv: [], configuration: Crawlscope.configuration)
+      status = Cli.start([command, *argv], out: $stdout, err: $stderr, configuration: configuration)
       exit(status) unless status.zero?
     end
 

test/crawlscope/rake_tasks_test.rb

@@ -3,6 +3,8 @@
 require "test_helper"
 
 class CrawlscopeRakeTasksTest < Minitest::Test
+  Rule = Data.define(:code)
+
   def setup
     @original_start = Crawlscope::Cli.method(:start)
   end
@@ -13,6 +15,7 @@ def teardown
     singleton_class.define_method(:start) do |*args, **kwargs|
       original_start.call(*args, **kwargs)
     end
+    Crawlscope.reset!
   end
 
   def test_validate_passes_rake_arguments_to_cli
@@ -56,14 +59,43 @@ def test_ldjson_passes_rake_url_argument_to_cli
     )
   end
 
+  def test_run_passes_the_shared_configuration_to_cli
+    calls = capture_cli_calls
+    configuration = Crawlscope.configuration
+
+    Crawlscope::RakeTasks.run("validate")
+
+    assert_same configuration, calls.fetch(0).fetch(:kwargs).fetch(:configuration)
+  end
+
+  def test_validate_passes_the_host_rule_registry_to_cli
+    registry = Crawlscope::RuleRegistry.new(rules: [Rule.new(:host)], default_codes: [:host])
+    Crawlscope.configure { |configuration| configuration.rule_registry = registry }
+    calls = capture_cli_calls
+
+    Crawlscope::RakeTasks.validate
+
+    call = calls.fetch(0)
+    assert_equal "validate", call.fetch(:argv).first
+    assert_same registry, call.fetch(:kwargs).fetch(:configuration).rule_registry
+  end
+
+  def test_run_exits_with_a_nonzero_cli_status
+    capture_cli_calls(status: 2)
+
+    error = assert_raises(SystemExit) { Crawlscope::RakeTasks.run("validate") }
+
+    assert_equal 2, error.status
+  end
+
   private
 
-  def capture_cli_calls
+  def capture_cli_calls(status: 0)
     calls = []
     singleton_class = class << Crawlscope::Cli; self; end
     singleton_class.define_method(:start) do |argv, **kwargs|
       calls << {argv: argv, kwargs: kwargs}
-      0
+      status
     end
     calls
   end