source_monitor 0.13.0 → 0.14.0

data/lib/source_monitor/items/normalized_entry.rb

@@ -0,0 +1,61 @@
+# frozen_string_literal: true
+
+require "active_support/core_ext/object/blank"
+require "source_monitor/items/item_creator/entry_parser"
+require "source_monitor/items/item_creator/content_extractor"
+
+module SourceMonitor
+  module Items
+    class NormalizedEntry
+      def self.call(source:, entry:, content_extractor: nil)
+        new(source: source, entry: entry, content_extractor: content_extractor).item_attributes
+      end
+
+      def initialize(source:, entry:, content_extractor: nil)
+        @source = source
+        @entry = entry
+        @content_extractor = content_extractor || ItemCreator::ContentExtractor.new(source: source)
+      end
+
+      def attributes
+        @attributes ||= parser.parse
+      end
+
+      def item_attributes
+        attributes.merge(guid: item_guid)
+      end
+
+      def raw_guid
+        attributes[:guid]
+      end
+
+      def normalized_guid
+        raw_guid.present? ? raw_guid.downcase : nil
+      end
+
+      def raw_guid_present?
+        normalized_guid.present?
+      end
+
+      def item_guid
+        normalized_guid.presence || content_fingerprint
+      end
+
+      def content_fingerprint
+        attributes[:content_fingerprint]
+      end
+
+      private
+
+      attr_reader :source, :entry, :content_extractor
+
+      def parser
+        @parser ||= ItemCreator::EntryParser.new(
+          source: source,
+          entry: entry,
+          content_extractor: content_extractor
+        )
+      end
+    end
+  end
+end

data/lib/source_monitor/security/authentication.rb

@@ -31,6 +31,16 @@ module SourceMonitor
         config.authenticate_handler.present? || config.authorize_handler.present?
       end
 
+      # Fail-closed predicate. The engine denies access when the host app has
+      # configured no authentication/authorization handler AND has not
+      # explicitly opted into open access. Configured handlers always win: when
+      # a handler is present the handler decides and this returns false.
+      def self.access_denied_by_default?(_controller = nil)
+        return false if authentication_configured?
+
+        !SourceMonitor.config.authentication.open_access
+      end
+
       def self.authorize_configured?
         SourceMonitor.config.authentication.authorize_handler.present?
       end

data/lib/source_monitor/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module SourceMonitor
-  VERSION = "0.13.0"
+  VERSION = "0.14.0"
 end

data/lib/source_monitor.rb

@@ -89,6 +89,7 @@ module SourceMonitor
 
   module ImportSessions
     autoload :EntryNormalizer, "source_monitor/import_sessions/entry_normalizer"
+    autoload :Wizard, "source_monitor/import_sessions/wizard"
     autoload :HealthCheckBroadcaster, "source_monitor/import_sessions/health_check_broadcaster"
     autoload :HealthCheckUpdater, "source_monitor/import_sessions/health_check_updater"
     autoload :OPMLImporter, "source_monitor/import_sessions/opml_importer"
@@ -108,6 +109,7 @@ module SourceMonitor
 
   module Items
     autoload :ItemCreator, "source_monitor/items/item_creator"
+    autoload :NormalizedEntry, "source_monitor/items/normalized_entry"
     autoload :RetentionPruner, "source_monitor/items/retention_pruner"
     autoload :RetentionStrategies, "source_monitor/items/retention_strategies"
   end

data/source_monitor.gemspec

@@ -23,11 +23,16 @@ Gem::Specification.new do |spec|
   spec.files = Dir.chdir(File.expand_path(__dir__)) do
     tracked_files = `git ls-files -z`.split("\x0")
     tracked_files.reject do |file|
-      file.start_with?(".ai/", ".github/", ".vbw-planning/", "coverage/", "node_modules/", "pkg/", "spec/", "test/", "tmp/", "vendor/", "examples/", "bin/")
+      file.start_with?(".ai/", ".github/", ".vbw-planning/", "coverage/", "node_modules/", "pkg/", "spec/", "test/", "tmp/", "vendor/", "examples/", "bin/") ||
+        # Exclude all .claude internals (agents, hooks, agent-memory, settings,
+        # commands) but keep the intended SourceMonitor sm-* skills. Driven from
+        # git ls-files (inside Dir.chdir) so packaging is CWD-independent --- a
+        # bare Dir[] glob here returned nothing on CI when another test had
+        # changed the process working directory.
+        (file.start_with?(".claude/") && !file.start_with?(".claude/skills/sm-"))
     end
   end
   spec.files += [ "CHANGELOG.md" ].select { |path| File.exist?(File.join(__dir__, path)) }
-  spec.files += Dir[".claude/skills/sm-*/**/*"]
   spec.files.uniq!
 
   spec.require_paths = [ "lib" ]

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: source_monitor
 version: !ruby/object:Gem::Version
-  version: 0.13.0
+  version: 0.14.0
 platform: ruby
 authors:
 - dchuk
@@ -258,67 +258,6 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
-- ".claude/agent-memory/vbw-vbw-debugger/MEMORY.md"
-- ".claude/agent-memory/vbw-vbw-dev/MEMORY.md"
-- ".claude/agent-memory/vbw-vbw-lead/MEMORY.md"
-- ".claude/agents/rails-concern.md"
-- ".claude/agents/rails-controller.md"
-- ".claude/agents/rails-hotwire.md"
-- ".claude/agents/rails-implement.md"
-- ".claude/agents/rails-job.md"
-- ".claude/agents/rails-lint.md"
-- ".claude/agents/rails-mailer.md"
-- ".claude/agents/rails-migration.md"
-- ".claude/agents/rails-model.md"
-- ".claude/agents/rails-policy.md"
-- ".claude/agents/rails-presenter.md"
-- ".claude/agents/rails-query.md"
-- ".claude/agents/rails-review.md"
-- ".claude/agents/rails-service.md"
-- ".claude/agents/rails-state-records.md"
-- ".claude/agents/rails-tdd.md"
-- ".claude/agents/rails-test.md"
-- ".claude/agents/rails-view-component.md"
-- ".claude/commands/rails-audit.md"
-- ".claude/commands/release.md"
-- ".claude/hooks/block-secrets.sh"
-- ".claude/settings.json"
-- ".claude/skills/action-cable-patterns/SKILL.md"
-- ".claude/skills/action-mailer-patterns/SKILL.md"
-- ".claude/skills/active-storage-setup/SKILL.md"
-- ".claude/skills/api-versioning/SKILL.md"
-- ".claude/skills/authentication-flow/SKILL.md"
-- ".claude/skills/authentication-flow/reference/current.md"
-- ".claude/skills/authentication-flow/reference/passwordless.md"
-- ".claude/skills/authentication-flow/reference/sessions.md"
-- ".claude/skills/authorization-pundit/SKILL.md"
-- ".claude/skills/caching-strategies/SKILL.md"
-- ".claude/skills/database-migrations/SKILL.md"
-- ".claude/skills/form-object-patterns/SKILL.md"
-- ".claude/skills/hotwire-patterns/SKILL.md"
-- ".claude/skills/hotwire-patterns/reference/stimulus.md"
-- ".claude/skills/hotwire-patterns/reference/tailwind-integration.md"
-- ".claude/skills/hotwire-patterns/reference/turbo-frames.md"
-- ".claude/skills/hotwire-patterns/reference/turbo-streams.md"
-- ".claude/skills/i18n-patterns/SKILL.md"
-- ".claude/skills/install/SKILL.md"
-- ".claude/skills/performance-optimization/SKILL.md"
-- ".claude/skills/rails-architecture/SKILL.md"
-- ".claude/skills/rails-architecture/reference/error-handling.md"
-- ".claude/skills/rails-architecture/reference/event-tracking.md"
-- ".claude/skills/rails-architecture/reference/layer-interactions.md"
-- ".claude/skills/rails-architecture/reference/multi-tenancy.md"
-- ".claude/skills/rails-architecture/reference/query-patterns.md"
-- ".claude/skills/rails-architecture/reference/service-patterns.md"
-- ".claude/skills/rails-architecture/reference/state-records.md"
-- ".claude/skills/rails-architecture/reference/testing-strategy.md"
-- ".claude/skills/rails-concern/SKILL.md"
-- ".claude/skills/rails-controller/SKILL.md"
-- ".claude/skills/rails-model-generator/SKILL.md"
-- ".claude/skills/rails-model-generator/reference/validations.md"
-- ".claude/skills/rails-presenter/SKILL.md"
-- ".claude/skills/rails-query-object/SKILL.md"
-- ".claude/skills/rails-service-object/SKILL.md"
 - ".claude/skills/sm-architecture/SKILL.md"
 - ".claude/skills/sm-architecture/reference/extraction-patterns.md"
 - ".claude/skills/sm-architecture/reference/module-map.md"
@@ -358,9 +297,6 @@ files:
 - ".claude/skills/sm-upgrade/SKILL.md"
 - ".claude/skills/sm-upgrade/reference/upgrade-workflow.md"
 - ".claude/skills/sm-upgrade/reference/version-history.md"
-- ".claude/skills/solid-queue-setup/SKILL.md"
-- ".claude/skills/tdd-cycle/SKILL.md"
-- ".claude/skills/viewcomponent-patterns/SKILL.md"
 - ".gitignore"
 - ".rubocop.yml"
 - ".ruby-version"
@@ -408,9 +344,6 @@ files:
 - app/controllers/source_monitor/health_controller.rb
 - app/controllers/source_monitor/import_history_dismissals_controller.rb
 - app/controllers/source_monitor/import_sessions/bulk_configuration.rb
-- app/controllers/source_monitor/import_sessions/entry_annotation.rb
-- app/controllers/source_monitor/import_sessions/health_check_management.rb
-- app/controllers/source_monitor/import_sessions/opml_parser.rb
 - app/controllers/source_monitor/import_sessions_controller.rb
 - app/controllers/source_monitor/item_scrapes_controller.rb
 - app/controllers/source_monitor/items_controller.rb
@@ -545,6 +478,13 @@ files:
 - docs/configuration.md
 - docs/deployment.md
 - docs/gh-cli-workflow.md
+- docs/goals/engine-hardening/.goalbuddy-board/app.js
+- docs/goals/engine-hardening/.goalbuddy-board/goalbuddy-mark.png
+- docs/goals/engine-hardening/.goalbuddy-board/index.html
+- docs/goals/engine-hardening/.goalbuddy-board/styles.css
+- docs/goals/engine-hardening/goal.md
+- docs/goals/engine-hardening/notes/T001-spec-validation.md
+- docs/goals/engine-hardening/state.yaml
 - docs/setup-validation-log.md
 - docs/setup.md
 - docs/troubleshooting.md
@@ -598,7 +538,9 @@ files:
 - lib/source_monitor/fetching/feed_fetcher.rb
 - lib/source_monitor/fetching/feed_fetcher/adaptive_interval.rb
 - lib/source_monitor/fetching/feed_fetcher/entry_processor.rb
+- lib/source_monitor/fetching/feed_fetcher/failure_outcome.rb
 - lib/source_monitor/fetching/feed_fetcher/source_updater.rb
+- lib/source_monitor/fetching/feed_fetcher/success_outcome.rb
 - lib/source_monitor/fetching/fetch_error.rb
 - lib/source_monitor/fetching/fetch_runner.rb
 - lib/source_monitor/fetching/retry_orchestrator.rb
@@ -619,12 +561,14 @@ files:
 - lib/source_monitor/import_sessions/health_check_broadcaster.rb
 - lib/source_monitor/import_sessions/health_check_updater.rb
 - lib/source_monitor/import_sessions/opml_importer.rb
+- lib/source_monitor/import_sessions/wizard.rb
 - lib/source_monitor/instrumentation.rb
 - lib/source_monitor/items/batch_item_creator.rb
 - lib/source_monitor/items/item_creator.rb
 - lib/source_monitor/items/item_creator/content_extractor.rb
 - lib/source_monitor/items/item_creator/entry_parser.rb
 - lib/source_monitor/items/item_creator/entry_parser/media_extraction.rb
+- lib/source_monitor/items/normalized_entry.rb
 - lib/source_monitor/items/retention_pruner.rb
 - lib/source_monitor/items/retention_strategies.rb
 - lib/source_monitor/items/retention_strategies/destroy.rb

data/.claude/agent-memory/vbw-vbw-debugger/MEMORY.md

@@ -1,15 +0,0 @@
-# Debugger Memory
-
-## Rails Association Cache Pollution Pattern
-- `source.items.new` AND `Item.new(source: source)` both add to the loaded association cache via inverse_of
-- Only `Item.new(source_id: source.id)` truly bypasses inverse_of and avoids cache pollution
-- When unsaved/invalid records are in a loaded has_many cache, `parent.update!` triggers auto-save and fails with `RecordInvalid: Items is invalid`
-- `update_columns` bypasses all callbacks and auto-save, safe to use with polluted caches
-- After `update_columns`, call `reload` so the in-memory object reflects DB state
-
-## Test Patterns
-- Use `clean_source_monitor_tables!` in setup for blank-slate DB
-- `create_source!` is the factory helper (in test_helper.rb)
-- WebMock stubs + VCR cassettes for HTTP; `stub_request(:get, url)`
-- Stub class methods with `singleton_class.define_method` pattern
-- Always restore stubs in `ensure` block

data/.claude/agent-memory/vbw-vbw-dev/MEMORY.md

@@ -1,34 +0,0 @@
-# VBW Dev Agent Memory
-
-## Project: source_monitor
-- Rails engine gem for RSS/feed monitoring
-- Ruby 3.4.4, Rails 8.x
-- Test suite: 473 tests via `bin/rails test` (takes ~76 seconds)
-- RuboCop uses `rubocop-rails-omakase` base config
-
-## Key Learnings
-
-### Shell/Bash in zsh
-- `!` in zsh inline scripts causes `command not found` errors. Use `case` statements instead of `if ! ...` patterns.
-- Use `IFS= read -r` when reading filenames from pipes to handle edge cases.
-
-### RuboCop scope vs git scope
-- RuboCop inspects ALL Ruby-like files (Gemfile, Rakefile, .gemspec, .rake, bin/*, config.ru), not just `.rb` files.
-- `git ls-files -- '*.rb'` only matches `.rb` extensions. Plans scoped to `.rb` files may miss RuboCop violations in non-`.rb` Ruby files.
-- `test/tmp/` contains untracked generated Rails app templates. These are NOT git-tracked but RuboCop scans them unless excluded.
-
-### File structure
-- `test/lib/tmp/install_generator/` contains test fixtures (1 tracked file: `config/initializers/source_monitor.rb`)
-- `test/tmp/host_app_template_*` directories are generated test artifacts, not git-tracked
-- `.rubocop.yml` is at project root, inherits from `rubocop-rails-omakase`
-
-### Frozen string literal pragma
-- Completed in commit `5f02db8` -- 113 files modified
-- Added `test/tmp/**/*` to RuboCop exclude list
-
-### RuboCop omakase ruleset details
-- Only 45 cops enabled (out of 775 available)
-- ALL Metrics cops disabled (ClassLength, MethodLength, BlockLength, etc.)
-- After frozen_string_literal fix, codebase had zero remaining violations
-- No `.rubocop.yml` exclusions needed for large files since Metrics cops are off
-- Plan 02 completed with no code changes required

data/.claude/agent-memory/vbw-vbw-lead/MEMORY.md

@@ -1,49 +0,0 @@
-# Lead Agent Memory -- SourceMonitor
-
-## Project Quick Facts
-- Rails 8 engine, Ruby 3.4+, PostgreSQL-only
-- 325 git-tracked Ruby files, 130 test files
-- Coverage baseline: 2328 uncovered lines in config/coverage_baseline.json
-- RuboCop: rubocop-rails-omakase, config at .rubocop.yml
-- CI: .github/workflows/ci.yml (lint, security, test, release-verify, nightly profiling)
-- Large files: FeedFetcher (627), Configuration (655), ImportSessionsController (792)
-
-## Phase 1 Findings
-- 98 git-tracked .rb files missing frozen_string_literal (out of 325)
-- Breakdown: app/(5), lib/(24), test/(43 non-dummy), test/dummy/(22), config/(1), db/migrate/(4)
-- test/tmp/ is NOT git-tracked (generated by install_generator tests) -- exclude from changes
-- test/lib/tmp/install_generator/config/initializers/source_monitor.rb IS tracked and already has pragma
-- bin/rubocop wrapper forces --config .rubocop.yml
-- Phase 1 criterion #3 (10% coverage shrink) not addressed by plans 01/02 -- noted for future
-
-## Phase 2 Planning Insights
-- Coverage baseline.json has 2117 uncovered lines across 105 files (not 2328 -- that was line count)
-- Top 7 files account for ~743 uncovered lines (35% of total)
-- FeedFetcher: 245 uncovered, 12 existing tests, uses VCR+WebMock
-- ItemCreator: 228 uncovered, 8 existing tests, needs mock entries for Atom/JSON branches
-- Configuration: 94 uncovered, 5 existing tests, ~12 nested settings classes
-- Dashboard::Queries: 66 uncovered, 7 existing tests, uses raw SQL + Cache
-- BulkSourceScraper: 66 uncovered, 6 existing tests, ActiveJob test adapter
-- Broadcaster: 48 uncovered, NO existing test file -- needs creation
-- SourcesIndexMetrics: 34 uncovered, 3 existing tests
-- All 5 Phase 2 plans are Wave 1 (no inter-plan dependencies, no file conflicts)
-- Testing main files will indirectly cover supporting files (retry_policy, fetch_error, state, enqueuer, etc.)
-- Broadcaster tests need Turbo::StreamsChannel stubs -- no full Action Cable required
-- 50% coverage target requires ~1059 lines covered; direct plans target ~630, rest from indirect
-
-## Phase 4 Planning Insights
-- 3 plans: conventions-audit (wave 1), item-creator-extraction (wave 1), final-verification (wave 2)
-- SourcesController has dead `fetch`/`retry` methods (leftover from Phase 3 CRUD extraction)
-- ImportSessionsController `new` and `create` are byte-for-byte identical
-- 4 RuboCop violations in db/migrate/20260210204022_add_composite_index_to_log_entries.rb
-- Duplicate test: test/controllers/concerns/ vs test/controllers/source_monitor/concerns/
-- ItemCreator at 601 lines is the last file over 300 lines -- extract to entry_parser + content_extractor
-- Coverage baseline still at 2117 uncovered (not regenerated since Phase 1) -- must regenerate
-- 60% reduction target: at most 847 uncovered lines
-- dashboard/queries.rb (356) and application_helper.rb (346) are near 300 but acceptable as view/query code
-- `bin/update-coverage-baseline` requires `COVERAGE=1 bin/rails test` first
-
-## Bash/Shell Notes
-- zsh on macOS -- `!` in shell conditionals causes `command not found` errors
-- Use `case` statements instead of `if ! grep` patterns in zsh
-- git ls-files piped to while loops works reliably for file enumeration