3.6

Adjusted Signal

3.6

Raw Pattern Score

100%

Time Factor

2026-10-28

Last Push

4.5K

Stars

Ruby

Language

221.9K

Lines of Code

1.2K

Files

734

Pattern Hits

2026-10-31

Scan Date

0.00

HC Hit Rate

Risk Review · Payload v1

Use each vector to guide manual verification of the underlying findings.

Payload schema: 1.0.0 · Engine: 2.0.0 · Scoring: heuristic-density-v1 · Scan date: 2026-10-31.

Cognitive Ownership Risk 15.6/100 · LOW

Can maintainers explain intent, assumptions, and trade-offs? 719 finding(s).

Hallucinated Dependency & Supply Chain Risk 0.4/100 · LOW

Are imports declared and package/API names verified? 10 finding(s).

Agent Over-Engineering Ratio 8.1/100 · LOW

Are wrappers, guards, and repeated structures necessary? 355 finding(s).

PR Review Velocity Impact 16.9/100 · LOW

Which changes need focused human review? 734 finding(s).

What These Metrics Mean

Adjusted Signal: Legacy pattern score normalized per 1,000 scanned lines and multiplied by the repository-level time factor. It is not an estimate of AI authorship.
Raw Pattern Score: Sum of severity- and context-weighted pattern findings before applying the time factor.
Time Factor: A coarse multiplier based on repository last-push metadata. It does not identify when individual code was written.
Pattern Hits: Count of configured pattern findings. Review each location and surrounding code before acting.
HC Hit Rate: High- and critical-severity findings per scanned file. Severity is a configured detector weight, not proof of a vulnerability or authorship.
Lines / Files: Scan coverage denominators used by the legacy normalized score.

Pattern-Signal History

This chart tracks the legacy adjusted pattern score across scan runs. Changes can reflect source changes, scan coverage, or detector/scoring versions; they do not measure AI adoption or prove that a team refactored code. Compare runs only when their scoring versions are compatible. The dashed line tracks the raw pattern-hit count.

Severity Breakdown

Groups findings by configured severity weight. Severity is not a confidence estimate, security rating, or proof that a package is missing. Verify imports against the project's manifests and inspect each finding in its local design context.

CRITICAL 1HIGH 1MEDIUM 38LOW 694

Directory Score Breakdown

This horizontal bar chart shows where configured pattern scores accumulate across directories. Treat the bars as locations to inspect, not as evidence of authorship or code quality. Use the file-level findings to decide whether a directory needs a focused ownership, dependency, complexity, or review check.

Pattern Findings

The scanner identified 734 distinct pattern matches across 11 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a detector match to inspect in context. Expand any category row to inspect the individual file paths, line numbers, code snippets, and the lexical context (CODE, COMMENT, or STRING) in which each match was detected.

Reading the findings table: The Severity column indicates the configured finding weight (CRITICAL / HIGH / MEDIUM / LOW). The Context column identifies whether the match occurred inside executable code, an inline comment, or a string literal — legacy comment-context matches receive a ×1.5 score weight. The ⚡ bolt icon marks clustered matches: three or more patterns within a 10-line window, each receiving an additional ×1.5 density multiplier under the legacy scoring model.

Hyper-Verbose Identifiers350 hits · 360 pts

Severity	File	Line	Snippet	Context
LOW	spec/ruby_llm/chat_tools_spec.rb	6	def skip_unless_supports_functions(provider, model)	CODE
LOW	spec/ruby_llm/chat_tools_spec.rb	194	def assistant_tool_call_messages(chat)	CODE
LOW	spec/ruby_llm/uploaded_file_spec.rb	151	def stub_default_model_provider(provider, config: RubyLLM.config)	CODE
LOW	spec/ruby_llm/chat_tool_attachments_spec.rb	66	def messages_with_tool_attachment(path)	CODE
LOW	spec/ruby_llm/chat_tool_attachments_spec.rb	74	def chat_with_tool_attachment(model, provider, protocol: nil, attachment: image_path)	CODE
LOW	spec/ruby_llm/chat_streaming_spec.rb	13	def visible_output_token_count(message)	CODE
LOW	spec/ruby_llm/open_telemetry_spec.rb	356	def complete_standalone_operation(operation, reported: true)	CODE
LOW	spec/ruby_llm/active_record/acts_as_action_text_spec.rb	72	def attachable_plain_text_representation(caption)	CODE
LOW	spec/ruby_llm/generators/chat_ui_generator_spec.rb	23	def expect_messages_helper_content(path)	CODE
LOW	spec/ruby_llm/generators/chat_ui_generator_spec.rb	36	def expect_generated_view_set( # rubocop:disable Metrics/AbcSize	CODE
LOW	spec/ruby_llm/generators/chat_ui_generator_spec.rb	148	def expect_queued_message_views(base_path, path_helper)	CODE
LOW	spec/ruby_llm/generators/chat_ui_generator_spec.rb	169	def expect_broadcasting_model(path:, acts_as_message_lines:)	CODE
LOW	spec/ruby_llm/generators/chat_ui_generator_spec.rb	198	def run_rails_runner_outside_executor(script)	CODE
LOW	spec/ruby_llm/generators/chat_ui_generator_spec.rb	208	def give_chat_agent_an_approval_tool(agent_path)	CODE
LOW	spec/ruby_llm/generators/chat_ui_generator_spec.rb	394	def expect_chat_script_to_succeed(script)	CODE
LOW	…y_llm/protocols/invoke_model/embedding_batches_spec.rb	72	def cleanup_live_embedding_batch(batch)	CODE
LOW	…y_llm/protocols/invoke_model/embedding_batches_spec.rb	89	def wait_for_live_embedding_batch(batch)	CODE
LOW	spec/support/websocket_cassette.rb	82	def ensure_websocket_recording_allowed(path, key)	CODE
LOW	spec/support/models_to_test.rb	16	def filter_unrecorded_providers(models)	CODE
LOW	spec/support/models_to_test.rb	36	def skip_without_cassette_or_key(env_key)	CODE
LOW⚡	benchmarks/support/payloads.rb	115	def chat_completions_text_stream(count)	CODE
LOW⚡	benchmarks/support/payloads.rb	121	def chat_completions_large_event(bytes, piece:)	CODE
LOW⚡	benchmarks/support/payloads.rb	127	def openrouter_reasoning_stream(count)	CODE
LOW	benchmarks/support/payloads.rb	173	def converse_reasoning_stream(count)	CODE
LOW	lib/ruby_llm/tool.rb	561	def validate_keyword_arguments(arguments) # :nodoc:	CODE
LOW	lib/ruby_llm/cost.rb	91	def missing_recorded_components(amounts, tokens, total)	CODE
LOW	lib/ruby_llm/agent.rb	732	def validate_thinking_options(enabled, options)	CODE
LOW	lib/ruby_llm/agent.rb	844	def apply_passthrough_options(chat)	CODE
LOW	lib/ruby_llm/agent.rb	938	def apply_assume_model_exists(chat_object)	CODE
LOW	lib/ruby_llm/agent.rb	958	def resolved_instruction_value(declaration, chat_object, runtime, inputs:)	CODE
LOW	lib/ruby_llm/model.rb	210	def pricing_data_with_long_context(pricing)	CODE
LOW	lib/ruby_llm/model.rb	234	def normalize_reasoning_options(options)	CODE
LOW⚡	lib/ruby_llm/chat.rb	2157	def handle_concurrent_tool_calls(tool_calls)	CODE
LOW⚡	lib/ruby_llm/chat.rb	2167	def execute_tools_concurrently(tool_calls, &on_result)	CODE
LOW⚡	lib/ruby_llm/chat.rb	2173	def execute_tool_with_callbacks(tool_call)	CODE
LOW	lib/ruby_llm/chat.rb	1300	def convert_unsupported_attachments(&)	CODE
LOW	lib/ruby_llm/chat.rb	1557	def extract_schema_definition(schema)	CODE
LOW	lib/ruby_llm/chat.rb	1944	def replacing_missing_uploads(request_messages, streamed = -> { false })	CODE
LOW	lib/ruby_llm/chat.rb	2008	def execute_pending_tool_calls(response)	CODE
LOW	lib/ruby_llm/chat.rb	2019	def answer_claimed_tool_calls(claimed, server_calls, decisions, executable, denied)	CODE
LOW	lib/ruby_llm/chat.rb	2059	def respond_to_tool_approvals(tool_calls, decisions)	CODE
LOW	lib/ruby_llm/chat.rb	2070	def partition_pending_tool_calls(pending)	CODE
LOW	lib/ruby_llm/chat.rb	2089	def record_tool_call_decision(tool_call, decision)	CODE
LOW	lib/ruby_llm/chat.rb	2144	def handle_sequential_tool_calls(tool_calls)	CODE
LOW	lib/ruby_llm/chat.rb	2332	def normalize_tool_concurrency(concurrency)	CODE
LOW	lib/ruby_llm/chat.rb	2362	def tool_name_for_choice_class(tool_class)	CODE
LOW	lib/ruby_llm/protocol.rb	380	def render_video_extension_payload(*)	CODE
LOW	lib/ruby_llm/protocol.rb	384	def video_extension_attachment(source)	CODE
LOW	lib/ruby_llm/protocol.rb	428	def render_transcription_options(timestamps:, **)	CODE
LOW	lib/ruby_llm/protocol.rb	609	def resolve_provider_tools_for_request(entries)	CODE
LOW	lib/ruby_llm/protocol.rb	633	def merge_server_tool_entries(payload, entries)	CODE
LOW	lib/ruby_llm/protocol.rb	641	def ensure_embedding_per_text(embedding, text, attachments, response)	CODE
LOW	lib/ruby_llm/protocol.rb	668	def apply_before_request_hooks(payload, hooks)	CODE
LOW	lib/ruby_llm/protocol.rb	695	def replace_unsupported_attachment(attachment, handler, message)	CODE
LOW	lib/ruby_llm/protocol.rb	761	def provider_file_upload_options(_attachment)	CODE
LOW	lib/ruby_llm/protocol.rb	805	def parse_completion_response(response)	CODE
LOW	lib/ruby_llm/provider.rb	531	def cache_write_input_multiplier(_model_id, _ttl) # :nodoc:	CODE
LOW	lib/ruby_llm/provider.rb	686	def configured_remote_providers(config) # :nodoc:	CODE
LOW	lib/ruby_llm/provider.rb	788	def validation_detail_message(detail)	CODE
LOW	lib/ruby_llm/models.rb	255	def models_dev_provider_models(provider_key, provider_data) # :nodoc:	CODE
290 more matches not shown…

Over-Commented Block333 hits · 294 pts

Severity	File	Line	Snippet	Context
LOW	Archspec.rb	241	# job (they word an option list, resolve a speech format, or guess from a	COMMENT
LOW	.mutineer.yml	1	# Mutineer settings shared by bin/mutineer and direct mutineer runs; see	COMMENT
LOW	spec/dummy/config/puma.rb	1	# frozen_string_literal: true	COMMENT
LOW	spec/dummy/config/puma.rb	21	# response time (latency) of the application.	COMMENT
LOW	spec/dummy/config/database.yml	21	database: storage/test<%= ENV['TEST_ENV_NUMBER'] %>.sqlite3	COMMENT
LOW	spec/dummy/config/locales/en.yml	1	# Files in the config/locales directory are used for internationalization and	COMMENT
LOW	spec/dummy/config/locales/en.yml	21	#	COMMENT
LOW	spec/dummy/config/environments/production.rb	61	# /.*\.example\.com/ # Allow requests from subdomains like `www.example.com`	COMMENT
LOW	spec/dummy/config/environments/test.rb	1	# frozen_string_literal: true	COMMENT
LOW	spec/dummy/config/initializers/inflections.rb	1	# frozen_string_literal: true	COMMENT
LOW	spec/dummy/config/initializers/cors.rb	1	# frozen_string_literal: true	COMMENT
LOW	spec/dummy/db/seeds.rb	1	# frozen_string_literal: true	COMMENT
LOW	.github/scripts/indexnow.rb	1	#!/usr/bin/env ruby	COMMENT
LOW	lib/ruby_llm.rb	61	# end	COMMENT
LOW	lib/ruby_llm.rb	81	# - Chat#with_fallbacks tries other models when a request fails.	COMMENT
LOW	lib/ruby_llm.rb	101	# format: each request lists them, the model loads the instructions and	COMMENT
LOW	lib/ruby_llm.rb	121	# VideoJob that you can poll. Speech.speak also streams SpeechChunk objects	COMMENT
LOW	lib/ruby_llm.rb	141	#	COMMENT
LOW	lib/ruby_llm.rb	161	# result. Implement Evaluation#perform to return a value, Message, Chat, or	COMMENT
LOW	lib/ruby_llm.rb	181	# method evaluates supplied text, structured data, or images passed as +with:+	COMMENT
LOW	lib/ruby_llm.rb	201	# and attempts that produced no message. Provider-reported costs take	COMMENT
LOW	lib/ruby_llm.rb	241	# Duplicates the global configuration and yields the copy if a block is	COMMENT
LOW	lib/ruby_llm.rb	261	# RubyLLM.workflow("Write article", id: "article-42") do \|workflow\|	COMMENT
LOW	lib/ruby_llm.rb	281	# restore the outer owner when they end. Each fiber and thread keeps its	COMMENT
LOW	lib/ruby_llm.rb	301	#	COMMENT
LOW	lib/ruby_llm.rb	321	def mcp(...)	COMMENT
LOW	lib/ruby_llm.rb	341		COMMENT
LOW	lib/ruby_llm.rb	361	# embedding requests, not both. Look up an existing batch with	COMMENT
LOW	lib/ruby_llm.rb	381	Embedding.embed(...)	COMMENT
LOW	lib/ruby_llm.rb	401	# result = RubyLLM.moderate("Some user input text")	COMMENT
LOW	lib/ruby_llm.rb	441		COMMENT
LOW	lib/ruby_llm.rb	461	def animate_later(...)	COMMENT
LOW	lib/ruby_llm.rb	481	# transcription.text	COMMENT
LOW	lib/ruby_llm.rb	501	# Ranks documents by relevance to a query on providers with a rerank	COMMENT
LOW	lib/ruby_llm.rb	521		COMMENT
LOW	lib/ruby_llm.rb	541	end	COMMENT
LOW	lib/ruby_llm.rb	561	#	COMMENT
LOW	lib/ruby_llm.rb	581	# RubyLLM.configure do \|config\|	COMMENT
LOW	lib/ruby_llm/image.rb	21	attr_reader :data	COMMENT
LOW	lib/ruby_llm/image.rb	41	# images for editing, and +mask:+ constrains which parts of the image	COMMENT
LOW	lib/ruby_llm/image.rb	141	end	COMMENT
LOW	lib/ruby_llm/video_job.rb	1	# frozen_string_literal: true	COMMENT
LOW	lib/ruby_llm/tool.rb	21	#	COMMENT
LOW	lib/ruby_llm/tool.rb	101	# class Weather < RubyLLM::Tool	COMMENT
LOW	lib/ruby_llm/tool.rb	121	# the tools in its own namespace:	COMMENT
LOW	lib/ruby_llm/tool.rb	141	# parameter :destination, description: "Destination city name"	COMMENT
LOW	lib/ruby_llm/tool.rb	161	# object :window, description: "Time window to reserve" do	COMMENT
LOW	lib/ruby_llm/tool.rb	181	# Chat#approve or Chat#deny, so Chat#complete returns cleanly and	COMMENT
LOW	lib/ruby_llm/tool.rb	201	# request, make that a find-or-create.	COMMENT
LOW	lib/ruby_llm/tool.rb	221	# Without an argument, returns the declared value, or +nil+.	COMMENT
LOW	lib/ruby_llm/tool.rb	241	#	COMMENT
LOW	lib/ruby_llm/tool.rb	261	def defer	COMMENT
LOW	lib/ruby_llm/tool.rb	481	else	COMMENT
LOW	lib/ruby_llm/tool.rb	501	# end	COMMENT
LOW	lib/ruby_llm/tool.rb	541	# can show it before the result arrives. Chat#after_tool_progress	COMMENT
LOW	lib/ruby_llm/fallback.rb	1	# frozen_string_literal: true	COMMENT
LOW	lib/ruby_llm/video.rb	1	# frozen_string_literal: true	COMMENT
LOW	lib/ruby_llm/video.rb	21	attr_reader :mime_type	COMMENT
LOW	lib/ruby_llm/video.rb	41	# +default_video_model+. +provider:+ forces a specific provider, and	COMMENT
LOW	lib/ruby_llm/cost.rb	1	# frozen_string_literal: true	COMMENT
273 more matches not shown…

Modern AI Meta-Vocabulary27 hits · 75 pts

Severity	File	Line	Snippet	Context
MEDIUM	Archspec.rb	18	# User-facing objects and orchestration. These are nouns like Chat, Batch,	COMMENT
MEDIUM	spec/ruby_llm/chat_error_spec.rb	80	# Create enough copies to overflow the model's context window	COMMENT
MEDIUM	docs/_advanced/batches.md	135	Rails saves approval decisions so another process can resume. See [Tool Approvals]({% link _core_features/tool-execution	CODE
MEDIUM	docs/_advanced/error-handling.md	97	# Reduce prompt size or use a model with a larger context window	COMMENT
MEDIUM	docs/_core_features/citations.md	67	## Citing Tool Results (RAG)	COMMENT
MEDIUM	docs/_core_features/moderation.md	91	Apply a [configured Bedrock guardrail]({% link _getting_started/configuration-providers.md %}#guardrails) without select	CODE
MEDIUM	docs/_data/provider_coverage.json	197	"s81": {"title": "Bedrock ApplyGuardrail API", "url": "https://docs.aws.amazon.com/bedrock/latest/userguide/guardrai	CODE
MEDIUM	docs/_data/provider_coverage.json	371	"s255": {"url": "https://elevenlabs.io/docs/eleven-agents/best-practices/guardrails", "title": "Guardrails"},	CODE
MEDIUM	lib/ruby_llm/workflow.rb	5	# records while leaving orchestration in ordinary Ruby code.	COMMENT
MEDIUM	lib/ruby_llm/attachment.rb	40	# How the model reads a video: +:static+, +:agentic+, or +nil+ for the	COMMENT
MEDIUM	lib/ruby_llm/attachment.rb	101	# frames across the whole video up front. +:agentic+ lets the model	COMMENT
MEDIUM	lib/ruby_llm/attachment.rb	105	# RubyLLM::Attachment.new("lecture.mp4", processing: :agentic)	COMMENT
MEDIUM	lib/ruby_llm/chat.rb	937	# going instead of overflowing the context window. The provider condenses	COMMENT
MEDIUM	lib/ruby_llm/error.rb	226	# Raised when the request exceeds the model's context window or token	COMMENT
MEDIUM	lib/ruby_llm/embedding.rb	83	# +model:+ selects the embedding model and defaults to the	COMMENT
MEDIUM	lib/ruby_llm/embedding_request.rb	21	# The Model of the embedding model the request targets.	COMMENT
MEDIUM	lib/ruby_llm/providers/openrouter/chat.rb	21	# would overflow the model's context window. It summarizes nothing	COMMENT
MEDIUM	lib/ruby_llm/providers/xai/responses.rb	7	# Grok models. Usage counts agentic tool activity.	COMMENT
MEDIUM	lib/ruby_llm/protocols/gemini/chat.rb	238	# the frames of an agentic video, apart from the prompt, and bills it	COMMENT
MEDIUM	lib/generators/ruby_llm/generator_helpers.rb	276	# scaffold conventions without complicating scaffold templates.	COMMENT
MEDIUM	lib/generators/ruby_llm/chat_ui/chat_ui_generator.rb	8	# Generates a simple chat UI scaffold for RubyLLM	COMMENT
MEDIUM	lib/generators/ruby_llm/chat_ui/chat_ui_generator.rb	46	# - `scaffold` should stay close to Rails scaffold ERB output.	COMMENT
MEDIUM	lib/generators/ruby_llm/chat_ui/chat_ui_generator.rb	47	# - `tailwind` should stay close to tailwindcss-rails scaffold output.	COMMENT
MEDIUM	media/tour/video/hyperframes/index.html	2662	<svg id="b7cur" width="26" height="26" viewBox="0 0 24 24" style="position:absolute;left:300px;top:150px"><path d="M	CODE
MEDIUM	media/tour/video/hyperframes/tools/snippets.rb	269	# 9. Agent with approval. Sources: docs/_core_features/tool-execution.md, docs/_advanced/agentic-workflows.md	COMMENT
MEDIUM	media/tour/video/hyperframes/tools/snippets.rb	460	# agentic-workflows.md:43, chat-request-control.md:80, tokenization.md:57, _reference/models.md:177/220	COMMENT
MEDIUM	media/tour/video/hyperframes/src/index.html	2662	<svg id="b7cur" width="26" height="26" viewBox="0 0 24 24" style="position:absolute;left:300px;top:150px"><path d="M	CODE

Self-Referential Comments5 hits · 15 pts

Severity	File	Line	Snippet	Context
MEDIUM	spec/ruby_llm/chat_error_spec.rb	77	# Create a huge conversation (matching <MASSIVE_TEXT> in spec_helper)	COMMENT
MEDIUM	spec/ruby_llm/models_refresh_spec.rb	169	# Create a temporary file for testing	COMMENT
MEDIUM	spec/ruby_llm/chat_schema_spec.rb	5	# Define a test schema class for testing Schematist::Schema instances	COMMENT
MEDIUM	…ec/ruby_llm/active_record/acts_as_with_context_spec.rb	67	# Create a different API key in custom context	COMMENT
MEDIUM	spec/ruby_llm/protocols/gemini/chat_spec.rb	8	# Create a test object that includes the module to access private methods	COMMENT

Decorative Section Separators4 hits · 12 pts

Severity	File	Line	Snippet	Context
MEDIUM	media/tour/music-shared/tired_wired.py	79	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	media/tour/music-shared/tired_wired.py	83	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	media/tour/music-shared/tired_wired.py	595	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	media/tour/music-shared/tired_wired.py	597	# ---------------------------------------------------------------------------	COMMENT

Hallucination Indicators1 hit · 10 pts

Severity	File	Line	Snippet	Context
CRITICAL	spec/ruby_llm/evaluation_live_spec.rb	107	messages = report.first.evaluations.first.evidence.fetch(:messages)	CODE

AI Slop Vocabulary2 hits · 6 pts

Severity	File	Line	Snippet	Context
MEDIUM	spec/tasks/models_workflow_spec.rb	51	# exec calls, and clear inherited Ruby options so the harness stays isolated.	COMMENT
MEDIUM	conformance/client.rb	4	# suite. The harness starts a scenario server, passes its URL as the last	COMMENT

Fake / Example Data5 hits · 5 pts

Severity	File	Line	Snippet	Context
LOW	spec/ruby_llm/chat_tools_spec.rb	705	expect(response.content).to match(/simple PDF file\|Lorem ipsum/i)	CODE
LOW	spec/ruby_llm/mcp/input_request_spec.rb	11	request = form('name' => { 'type' => 'string', 'default' => 'John Doe' },	CODE
LOW	spec/ruby_llm/mcp/input_request_spec.rb	19	.to eq(action: 'accept', content: { 'name' => 'John Doe', 'age' => 31, 'verified' => false })	CODE
LOW	docs/_getting_started/configuration-providers.md	440	config.openai_api_key = ENV['CUSTOM_API_KEY'] # Or 'dummy-key' if not required	CODE
LOW	docs/_getting_started/configuration-providers.md	458	config.openai_api_key = "dummy-key" # If required by your server	CODE

Empty Error Handlers1 hit · 5 pts

Severity	File	Line	Snippet	Context
HIGH	media/tour/music-shared/preview.py	163	except ImportError:	CODE

Unused Imports4 hits · 4 pts

Severity	File	Line	Context
LOW	media/tour/video/hyperframes/tools/film.py	2	CODE
LOW	media/tour/video/hyperframes/tools/open_test.py	3	CODE
LOW	media/tour/video/hyperframes/tools/full.py	3	CODE
LOW	media/tour/video/hyperframes/tools/full.py	4	CODE

Deep Nesting2 hits · 2 pts

Severity	File	Line	Snippet	Context
LOW	media/tour/music-shared/tired_wired.py	405		CODE
LOW	media/tour/music-shared/verify_tw.py	25		CODE

crmne/ruby_llm

Open-Source Code Quality, Security and Technical Debt Review