langchain-ai/open-swe

24.3

Adjusted Score

24.3

Raw Score

100%

Time Factor

2026-07-14

Last Push

10.3K

Stars

Python

Language

118.4K

Lines of Code

534

Files

2.7K

Pattern Hits

2026-07-14

Scan Date

0.04

HC Hit Rate

What These Metrics Mean

Adjusted Score: Primary synthetic code indicator. Raw score normalised per 1,000 lines of code and multiplied by the temporal discount factor. This is the definitive comparative metric — use it to rank repositories by AI authorship density.
Raw Score: The unmodified sum of all severity-weighted, context-multiplied pattern match scores before temporal discounting. Reflects the absolute signal strength independent of when the repository was last active.
Time Factor: The temporal discount multiplier (0–100%) applied to the raw score. Repositories last updated before ChatGPT's launch (Nov 2022) receive a 5% factor. Full signal is only assigned to repositories active in the post-adoption era (Jan 2024+).
Pattern Hits: Total count of individual pattern matches across all files and categories. A high hit count with a low score may indicate a very large codebase with isolated AI snippets; a low count with a high score indicates dense, concentrated AI signatures.
HC Hit Rate: High+Critical pattern hits per file, averaged across the repository. This orthogonal signal catches repositories where a few files are densely packed with high-severity AI tells — a strong indicator even when the normalised score appears moderate due to codebase size.
Lines of Code / Files: Total lines and files analysed. The scanner examines 94 file extensions. These denominators are used to normalise the score, enabling fair comparison between repositories of vastly different sizes.

Score History

This chart maps the temporal evolution of the adjusted synthetic code score across successive scan runs. An upward trajectory indicates ongoing incorporation of AI-generated code or expanding LLM-assisted scaffolding; a stable or declining trajectory may reflect active human refactoring, code removal, or the adoption of stricter authorship policies. The dashed secondary line (right axis) independently tracks total raw pattern hit count, which can diverge from the normalised score when codebase size changes significantly between scans.

Severity Breakdown

Classifies detected patterns by their diagnostic confidence and structural impact. CRITICAL patterns (coefficient 10) represent definitive synthetic signatures — hallucinated imports, explicit LLM attribution metadata — virtually never produced by human authors. HIGH (5) indicates strong structural tells such as cross-file repetition or cross-linguistic idioms. MEDIUM (2) covers recognisable conversational padding and AI-specific vocabulary. LOW (1) captures subtle indicators like tautological comments and generic boilerplate that require density to carry independent signal.

CRITICAL 0HIGH 20MEDIUM 26LOW 2660

Directory Score Breakdown

This horizontal bar chart decomposes the repository's raw synthetic code score by top-level directory, allowing you to pinpoint precisely which modules or components carry the highest AI authorship density. Directories with disproportionately high scores relative to their size warrant targeted manual review: concentrated AI signatures often trace back to mass-generated configuration layers, auto-ported test suites, LLM-scaffolded boilerplate classes, or entire subsystems authored under heavy copilot assistance. Use this view to prioritise your human code-review effort.

Pattern Findings

The scanner identified 2706 distinct pattern matches across 13 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a statistically significant AI authorship indicator. 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 diagnostic confidence level (CRITICAL / HIGH / MEDIUM / LOW). The Context column identifies whether the match occurred inside executable code, an inline comment, or a string literal — comment-context matches receive a ×1.5 weight because LLMs systematically over-annotate. The ⚡ bolt icon marks clustered matches: three or more patterns within a 10-line window, each receiving an additional ×1.5 density multiplier as dense clusters constitute far stronger evidence of synthetic authorship than isolated hits.

Hyper-Verbose Identifiers1863 hits · 1935 pts

Severity	File	Line	Snippet	Context
LOW	ui/src/features/agents/experiments/ChatView.tsx	51	function findLatestPendingApproval(messages: Message[]): ToolExecutionChunk \| null {	CODE
LOW	ui/src/features/agents/experiments/PromptBar.tsx	56	function buildApprovalPromptContent(request: PromptApprovalRequest): ApprovalPromptContent {	CODE
LOW	ui/src/features/agents/components/AgentGitPanel.tsx	131	export function writeStoredPanelCollapsed(collapsed: boolean): void {	CODE
LOW	…es/agents/components/messages/TurnChangedFilesCard.tsx	8	function stripProjectPathForDisplay(path: string, projectPath?: string): string {	CODE
LOW	ui/src/features/agents/lib/queries.ts	26	export function invalidateAgentThreadLists(queryClient: QueryClient): void {	CODE
LOW	ui/src/features/agents/lib/queries.ts	63	export function useSeedAgentThreadDetails(	CODE
LOW	ui/src/features/agents/lib/queries.ts	149	export function useWorkflowApprovalDecision(threadId: string) {	CODE
LOW	ui/src/features/agents/lib/queries.ts	287	export function useAdminCancelAgentThread() {	CODE
LOW	ui/src/features/agents/lib/api.ts	140	function filenameFromContentDisposition(value: string \| null): string \| null {	CODE
LOW	…/src/features/agents/lib/AgentThreadStreamProvider.tsx	53	export function AgentThreadStreamProvider({	CODE
LOW	…tures/agents/lib/provider/useIsInAgentThreadStream.tsx	22	export function AgentThreadStreamBoundary({ children }: { children: ReactNode }) {	CODE
LOW	ui/src/features/reviews/components/ReviewMainBody.tsx	150	function buildSelectionAttachments(	CODE
LOW	ui/src/features/reviews/components/ReviewMainBody.tsx	389	function scrollFindingLineToCenter({	CODE
LOW	ui/src/features/reviews/components/ReviewMainBody.tsx	2335	function readStoredReviewPanelWidth(): number {	CODE
LOW	ui/src/features/reviews/components/ReviewChat.tsx	59	export function ReviewChatComposerProvider({	CODE
LOW	ui/src/lib/notifications.ts	9	export function getNotificationPermission(): NotificationPermission \| null {	CODE
LOW	ui/src/lib/notifications.ts	24	export async function requestNotificationPermission(): Promise<NotificationPermission \| null> {	CODE
LOW	ui/src/lib/auth-redirect-core.ts	57	export function authRedirectPathFromLocation(location: LocationParts): string {	CODE
LOW	ui/src/lib/auth-redirect-core.ts	84	export function getRememberedAuthRedirect(): string \| null {	CODE
LOW	ui/src/lib/auth-redirect-core.ts	100	export function clearRememberedAuthRedirect(): void {	CODE
LOW	ui/src/routes/admin_.evals.tsx	50	function ReviewerEvalStatusSection() {	CODE
LOW	ui/src/routes/my-settings.tsx	193	function CurrentsCredentialsSection() {	CODE
LOW	ui/src/routes/$owner.$repo.pull.$number.tsx	25	function PullRequestReviewLinkPage() {	CODE
LOW	ui/src/routes/admin.tsx	428	function ObservabilityCredentialsSection() {	CODE
LOW	evals/reviewer/target.py	78	def get_reviewer_assistant_id() -> str:	CODE
LOW	evals/reviewer/target.py	94	def get_reviewer_reasoning_effort() -> str \| None:	CODE
LOW	evals/reviewer/target.py	231	async def _extract_surfaced_comments(	CODE
LOW	evals/reviewer/target.py	280	def _score_severity_threshold() -> Severity:	CODE
LOW	tests/conftest.py	11	def _default_enable_auto_review(monkeypatch: pytest.MonkeyPatch) -> None:	CODE
LOW	tests/test_openai_responses_replay.py	7	def test_stateless_responses_replay_preserves_tool_history_without_mutation() -> None:	CODE
LOW⚡	tests/middleware/test_sanitize_tool_inputs.py	14	def test_already_int_passes_through(self) -> None:	CODE
LOW⚡	tests/middleware/test_sanitize_tool_inputs.py	20	def test_extracts_leading_integer_from_comma_string(self) -> None:	CODE
LOW⚡	tests/middleware/test_sanitize_tool_inputs.py	24	def test_extracts_leading_integer_from_embedded_json(self) -> None:	CODE
LOW⚡	tests/middleware/test_sanitize_tool_inputs.py	28	def test_extracts_leading_integer_from_trailing_comma(self) -> None:	CODE
LOW⚡	tests/middleware/test_sanitize_tool_inputs.py	32	def test_returns_none_when_no_digits(self) -> None:	CODE
LOW⚡	tests/middleware/test_sanitize_tool_inputs.py	35	def test_handles_leading_whitespace(self) -> None:	CODE
LOW⚡	tests/middleware/test_sanitize_tool_inputs.py	40	def test_coerces_offset_string_to_int(self) -> None:	CODE
LOW⚡	tests/middleware/test_sanitize_tool_inputs.py	47	def test_coerces_offset_with_embedded_json(self) -> None:	CODE
LOW⚡	tests/middleware/test_sanitize_tool_inputs.py	52	def test_coerces_offset_with_trailing_comma(self) -> None:	CODE
LOW⚡	tests/middleware/test_sanitize_tool_inputs.py	57	def test_int_offset_unchanged(self) -> None:	CODE
LOW⚡	tests/middleware/test_sanitize_tool_inputs.py	62	def test_missing_offset_unchanged(self) -> None:	CODE
LOW⚡	tests/middleware/test_sanitize_tool_inputs.py	67	def test_uncoercible_offset_passed_through_unchanged(self) -> None:	CODE
LOW⚡	tests/middleware/test_sanitize_tool_inputs.py	73	def test_does_not_mutate_original_dict(self) -> None:	CODE
LOW	tests/middleware/test_model_fallback_middleware.py	36	def _anthropic_model_not_available_error() -> anthropic.BadRequestError:	CODE
LOW	tests/middleware/test_model_fallback_middleware.py	64	def test_anthropic_rate_limit_falls_back(self) -> None:	CODE
LOW	tests/middleware/test_model_fallback_middleware.py	70	def test_httpx_remote_protocol_error_falls_back(self) -> None:	CODE
LOW	tests/middleware/test_model_fallback_middleware.py	82	def test_value_error_does_not_fall_back(self) -> None:	CODE
LOW	tests/middleware/test_model_fallback_middleware.py	88	async def test_async_falls_over_on_overloaded(self) -> None:	CODE
LOW	tests/middleware/test_model_fallback_middleware.py	110	async def test_async_falls_over_on_stream_transport_error(self) -> None:	CODE
LOW	tests/middleware/test_model_fallback_middleware.py	135	async def test_async_propagates_non_transient_error(self) -> None:	CODE
LOW	tests/middleware/test_model_fallback_middleware.py	149	async def test_async_surfaces_model_unavailable_error(self) -> None:	CODE
LOW	tests/middleware/test_model_fallback_middleware.py	162	async def test_async_retries_primary_after_fallback_failure(self) -> None:	CODE
LOW	tests/middleware/test_model_fallback_middleware.py	186	async def test_async_exhaustion_returns_outage_message(self) -> None:	CODE
LOW	tests/middleware/test_model_fallback_middleware.py	202	async def test_async_exhaustion_raises_when_message_disabled(self) -> None:	CODE
LOW	tests/middleware/test_ensure_no_empty_msg.py	15	def test_returns_messages_after_last_human(self) -> None:	CODE
LOW	tests/middleware/test_ensure_no_empty_msg.py	30	def test_returns_all_messages_when_no_human(self) -> None:	CODE
LOW	tests/middleware/test_ensure_no_empty_msg.py	44	def test_returns_empty_when_human_is_last(self) -> None:	CODE
LOW	tests/middleware/test_ensure_no_empty_msg.py	56	def test_returns_multiple_messages_after_human(self) -> None:	CODE
LOW⚡	tests/middleware/test_ensure_no_empty_msg.py	75	def test_returns_true_for_slack_thread_reply(self) -> None:	CODE
LOW⚡	tests/middleware/test_ensure_no_empty_msg.py	82	def test_returns_true_for_linear_comment(self) -> None:	CODE
1803 more matches not shown…

Unused Imports379 hits · 336 pts

Severity	File	Line	Context
LOW	evals/reviewer/run_eval.py	7	CODE
LOW	evals/reviewer/store_reporter.py	10	CODE
LOW	evals/reviewer/judge.py	13	CODE
LOW	evals/reviewer/target.py	10	CODE
LOW	evals/reviewer/build_dataset.py	12	CODE
LOW	tests/conftest.py	3	CODE
LOW	tests/middleware/test_sanitize_tool_inputs.py	8	CODE
LOW	tests/middleware/test_model_fallback_middleware.py	3	CODE
LOW	tests/middleware/test_prepare_run_middleware.py	1	CODE
LOW	tests/middleware/test_subdir_agents_middleware.py	3	CODE
LOW	tests/middleware/test_sanitize_thinking_blocks.py	1	CODE
LOW	tests/middleware/test_tool_artifact_middleware.py	3	CODE
LOW	tests/middleware/test_check_message_queue.py	1	CODE
LOW	tests/middleware/test_repair_orphaned_tool_calls.py	1	CODE
LOW	tests/middleware/test_sanitize_fireworks_messages.py	1	CODE
LOW	tests/reviewer/test_pr_ready_auto_review.py	3	CODE
LOW	tests/reviewer/test_review_styles_store.py	1	CODE
LOW	tests/reviewer/test_fetch_review_diff_tool.py	1	CODE
LOW	tests/reviewer/test_reviewer_eval_target.py	1	CODE
LOW	tests/reviewer/test_reviewer_outcomes.py	1	CODE
LOW	tests/reviewer/test_review_chat.py	1	CODE
LOW	tests/reviewer/test_review_style_collector.py	1	CODE
LOW	tests/reviewer/test_reviewer_eval_judge.py	1	CODE
LOW	tests/reviewer/test_reviewer_tools.py	3	CODE
LOW	tests/reviewer/test_review_style_sync.py	1	CODE
LOW	tests/reviewer/test_reviewer_reconcile.py	1	CODE
LOW	tests/reviewer/test_reviewer_groups.py	1	CODE
LOW	tests/reviewer/test_reviewer_publish.py	3	CODE
LOW	tests/reviewer/test_reconcile_sweep.py	1	CODE
LOW	tests/reviewer/test_reviewer_watch.py	3	CODE
LOW	tests/reviewer/test_reviewer_diff.py	3	CODE
LOW	tests/reviewer/test_reviewer_findings.py	3	CODE
LOW	tests/reviewer/test_reviewer.py	1	CODE
LOW	tests/reviewer/test_reviewer_trace_context.py	1	CODE
LOW	tests/reviewer/test_reviewer_eval_run.py	1	CODE
LOW	tests/tools/test_http_security.py	1	CODE
LOW	tests/tools/test_corridor_mcp.py	1	CODE
LOW	tests/tools/test_observability_tools.py	1	CODE
LOW	tests/tools/test_report_platform_issue_tool.py	1	CODE
LOW	tests/tools/test_currents_tools.py	1	CODE
LOW	tests/tools/test_schedule_thread_wakeup.py	1	CODE
LOW	tests/auth/test_slack_oauth.py	1	CODE
LOW	tests/auth/test_auth_sources.py	1	CODE
LOW	tests/auth/test_user_credentials.py	1	CODE
LOW	tests/auth/test_github_token_ttl.py	11	CODE
LOW	tests/auth/test_github_oauth_refresh.py	1	CODE
LOW	tests/auth/test_authorship.py	1	CODE
LOW	tests/auth/test_notion_oauth.py	1	CODE
LOW	tests/auth/test_encryption.py	1	CODE
LOW	tests/agent/test_dispatch.py	1	CODE
LOW	tests/agent/test_agent_usage.py	1	CODE
LOW	tests/agent/test_agents_md.py	1	CODE
LOW	tests/agent/test_prompt_default_repo.py	1	CODE
LOW	tests/agent/test_agent_thread_pr_state.py	3	CODE
LOW	tests/agent/test_plan_review.py	1	CODE
LOW	tests/agent/test_task_retry.py	1	CODE
LOW	tests/agent/test_multimodal.py	1	CODE
LOW	tests/agent/test_agent_assembly_context.py	10	CODE
LOW	tests/agent/test_agent_instructions.py	1	CODE
LOW	tests/agent/test_agent_schedules.py	1	CODE
319 more matches not shown…

Excessive Try-Catch Wrapping237 hits · 237 pts

Severity	File	Line	Snippet	Context
LOW	evals/reviewer/run_eval.py	246	except Exception:	CODE
LOW	evals/reviewer/run_eval.py	273	except Exception:	CODE
LOW	evals/reviewer/run_eval.py	288	except Exception as exc:	CODE
LOW	evals/reviewer/store_reporter.py	106	except Exception:	CODE
LOW	evals/reviewer/target.py	181	except Exception:	CODE
LOW	evals/reviewer/build_dataset.py	134	except Exception as exc:	CODE
LOW⚡	agent/server.py	185	except Exception:	CODE
LOW⚡	agent/server.py	200	except Exception:	CODE
LOW⚡	agent/server.py	275	except Exception: # noqa: BLE001	CODE
LOW	agent/server.py	355	except Exception: # noqa: BLE001	CODE
LOW	agent/server.py	484	except Exception:	CODE
LOW	agent/server.py	632	except Exception:	CODE
LOW	agent/server.py	703	except Exception as e: # noqa: BLE001	CODE
LOW	agent/server.py	787	except Exception:	CODE
LOW	agent/completion.py	161	except Exception: # noqa: BLE001	CODE
LOW	agent/completion.py	184	except Exception: # noqa: BLE001	CODE
LOW	agent/analyzer.py	111	except Exception as e: # noqa: BLE001	STRING
LOW	agent/chat.py	125	except Exception as e: # noqa: BLE001	STRING
LOW	agent/reviewer.py	829	except Exception as e: # noqa: BLE001	CODE
LOW	agent/reviewer.py	1102	except Exception:	CODE
LOW	agent/reviewer.py	1139	except Exception:	CODE
MEDIUM	agent/reviewer.py	1132	def _prepare_pr_trace_context() -> PRTraceContext \| None:	CODE
LOW	agent/prompt.py	55	except Exception:	CODE
LOW	agent/reconcile.py	64	except Exception:	CODE
LOW	agent/reconcile.py	107	except Exception:	CODE
LOW⚡	agent/middleware/refresh_github_proxy.py	33	except Exception: # noqa: BLE001	CODE
LOW⚡	agent/middleware/refresh_github_proxy.py	41	except Exception: # noqa: BLE001	CODE
LOW	agent/middleware/sandbox_circuit_breaker.py	258	except Exception:	CODE
LOW	agent/middleware/tool_artifact.py	71	except Exception:	CODE
LOW	agent/middleware/tool_artifact.py	203	except Exception:	CODE
LOW	agent/middleware/model_fallback.py	177	except Exception as exc:	CODE
LOW	agent/middleware/notify_step_limit.py	85	except Exception:	CODE
LOW	agent/middleware/subdir_agents.py	52	except Exception:	CODE
LOW	agent/middleware/subdir_agents.py	178	except Exception:	CODE
LOW	agent/middleware/refresh_slack_status.py	122	except Exception:	CODE
LOW	agent/middleware/refresh_slack_status.py	183	except Exception:	CODE
LOW	agent/middleware/refresh_slack_status.py	189	except Exception:	CODE
LOW	agent/middleware/workflow_push_guard.py	101	except Exception:	CODE
LOW	agent/middleware/workflow_push_guard.py	231	except Exception:	CODE
LOW	agent/middleware/workflow_push_guard.py	508	except Exception:	CODE
LOW	agent/middleware/settle_review_check.py	84	except Exception:	CODE
LOW	agent/middleware/tool_error_handler.py	101	except Exception:	CODE
LOW	agent/middleware/tool_error_handler.py	172	except Exception:	CODE
LOW	agent/middleware/tool_error_handler.py	175	except Exception as e:	CODE
LOW	agent/middleware/check_message_queue.py	47	except Exception:	CODE
LOW⚡	agent/middleware/check_message_queue.py	108	except Exception: # noqa: BLE001	CODE
LOW⚡	agent/middleware/check_message_queue.py	117	except Exception: # noqa: BLE001	CODE
LOW	agent/middleware/check_message_queue.py	159	except Exception as e: # noqa: BLE001	CODE
LOW	agent/middleware/check_message_queue.py	175	except Exception as e: # noqa: BLE001	CODE
LOW	agent/middleware/check_message_queue.py	226	except Exception:	CODE
LOW	agent/tools/schedule_thread_wakeup.py	113	except Exception:	CODE
LOW	agent/tools/schedule_thread_wakeup.py	210	except Exception as exc:	CODE
LOW	agent/tools/open_pull_request.py	70	except Exception:	CODE
LOW	agent/tools/open_pull_request.py	82	except Exception:	CODE
LOW	agent/tools/open_pull_request.py	519	except Exception:	CODE
LOW	agent/tools/open_pull_request.py	531	except Exception:	CODE
LOW	agent/tools/open_pull_request.py	603	except Exception:	CODE
LOW	agent/tools/open_pull_request.py	608	except Exception:	CODE
MEDIUM	agent/tools/open_pull_request.py	79	def _configurable() -> dict[str, Any]:	CODE
LOW	agent/tools/list_review_findings.py	64	except Exception as exc: # noqa: BLE001	CODE
177 more matches not shown…

Modern Structural Boilerplate131 hits · 130 pts

Severity	File	Line	Snippet	Context
LOW	evals/reviewer/run_eval.py	37	logger = logging.getLogger(__name__)	CODE
LOW	evals/reviewer/store_reporter.py	27	logger = logging.getLogger(__name__)	CODE
LOW	evals/reviewer/target.py	26	logger = logging.getLogger(__name__)	CODE
LOW	tests/reviewer/test_reviewer_outcomes.py	75	def update_example(self, **kwargs: Any) -> None:	CODE
LOW	tests/auth/test_encryption.py	15	def _set_key(monkeypatch: pytest.MonkeyPatch, value: str) -> None:	CODE
LOW	tests/agent/test_langsmith_trace_url.py	12	def _set_env(monkeypatch: pytest.MonkeyPatch) -> None:	CODE
LOW	tests/github/test_open_pull_request.py	87	def _set_config(monkeypatch: pytest.MonkeyPatch, configurable: dict[str, Any]) -> None:	CODE
LOW	tests/e2e/agent_entrypoint.py	21	__all__ = ["traced_agent"]	CODE
LOW	tests/e2e/patches.py	20	logger = logging.getLogger(__name__)	CODE
LOW	agent/server.py	17	logger = logging.getLogger(__name__)	CODE
LOW	agent/encryption.py	8	logger = logging.getLogger(__name__)	CODE
LOW	agent/completion.py	29	logger = logging.getLogger(__name__)	CODE
LOW	agent/dispatch.py	27	logger = logging.getLogger(__name__)	CODE
LOW	agent/webapp.py	5	__all__ = ["app"]	CODE
LOW	agent/analyzer.py	61	logger = logging.getLogger(__name__)	CODE
LOW	agent/chat.py	69	logger = logging.getLogger(__name__)	CODE
LOW	agent/reviewer.py	25	logger = logging.getLogger(__name__)	CODE
LOW	agent/scheduler.py	14	logger = logging.getLogger(__name__)	CODE
LOW	agent/prompt.py	17	logger = logging.getLogger(__name__)	CODE
LOW	agent/reconcile.py	18	logger = logging.getLogger(__name__)	CODE
LOW⚡	agent/middleware/refresh_github_proxy.py	21	logger = logging.getLogger(__name__)	CODE
LOW	agent/middleware/sandbox_circuit_breaker.py	22	logger = logging.getLogger(__name__)	CODE
LOW	agent/middleware/repair_orphaned_tool_calls.py	27	logger = logging.getLogger(__name__)	CODE
LOW	agent/middleware/tool_artifact.py	33	logger = logging.getLogger(__name__)	CODE
LOW	agent/middleware/model_fallback.py	43	logger = logging.getLogger(__name__)	CODE
LOW	agent/middleware/notify_step_limit.py	15	logger = logging.getLogger(__name__)	CODE
LOW	agent/middleware/__init__.py	32	__all__ = [	CODE
LOW	agent/middleware/subdir_agents.py	19	logger = logging.getLogger(__name__)	CODE
LOW	agent/middleware/refresh_slack_status.py	35	logger = logging.getLogger(__name__)	CODE
LOW	agent/middleware/refresh_slack_status.py	114	async def _set_status(channel_id: str, thread_ts: str, status: str) -> None:	CODE
LOW	agent/middleware/workflow_push_guard.py	30	logger = logging.getLogger(__name__)	CODE
LOW	agent/middleware/sanitize_tool_inputs.py	20	logger = logging.getLogger(__name__)	CODE
LOW	agent/middleware/settle_review_check.py	23	logger = logging.getLogger(__name__)	CODE
LOW	agent/middleware/tool_error_handler.py	24	logger = logging.getLogger(__name__)	CODE
LOW	agent/middleware/check_message_queue.py	28	logger = logging.getLogger(__name__)	CODE
LOW	agent/tools/schedule_thread_wakeup.py	14	logger = logging.getLogger(__name__)	CODE
LOW	agent/tools/open_pull_request.py	20	logger = logging.getLogger(__name__)	CODE
LOW	agent/tools/__init__.py	38	__all__ = [	CODE
LOW	agent/tools/save_review_style.py	13	logger = logging.getLogger(__name__)	CODE
LOW	agent/tools/enter_plan_mode.py	15	logger = logging.getLogger(__name__)	CODE
LOW	agent/tools/web_search.py	6	logger = logging.getLogger(__name__)	CODE
LOW	agent/tools/save_plan.py	25	logger = logging.getLogger(__name__)	CODE
LOW	agent/providers/__init__.py	9	__all__ = [	CODE
LOW	agent/runtime/__init__.py	15	__all__ = [	CODE
LOW	agent/utils/auth.py	26	logger = logging.getLogger(__name__)	CODE
LOW	agent/utils/gateway.py	17	logger = logging.getLogger(__name__)	CODE
LOW	agent/utils/slack_feedback.py	18	logger = logging.getLogger(__name__)	CODE
LOW	agent/utils/sandbox_state.py	26	logger = logging.getLogger(__name__)	CODE
LOW	agent/utils/authorship.py	11	logger = logging.getLogger(__name__)	CODE
LOW	agent/utils/repo_prep.py	23	logger = logging.getLogger(__name__)	CODE
LOW	agent/utils/linear.py	15	logger = logging.getLogger(__name__)	CODE
LOW	agent/utils/github_feedback.py	17	logger = logging.getLogger(__name__)	CODE
LOW	agent/utils/langsmith.py	15	logger = logging.getLogger(__name__)	CODE
LOW	agent/utils/github_app.py	17	logger = logging.getLogger(__name__)	CODE
LOW	agent/utils/multimodal.py	18	logger = logging.getLogger(__name__)	CODE
LOW	agent/utils/github_http.py	28	logger = logging.getLogger(__name__)	CODE
LOW	agent/utils/github_org_membership.py	11	logger = logging.getLogger(__name__)	CODE
LOW	agent/utils/ttl_cache.py	8	logger = logging.getLogger(__name__)	CODE
LOW	agent/utils/ttl_cache.py	104	def set_cached(key: str, value: object, ttl_seconds: float) -> None:	CODE
LOW	agent/utils/github_proxy.py	26	logger = logging.getLogger(__name__)	CODE
71 more matches not shown…

Cross-Language Confusion16 hits · 108 pts

Severity	File	Line	Snippet	Context
HIGH	tests/reviewer/test_reviewer_publish.py	616	explicit null, so the fetch must guard against it and return collected threads."""	STRING
HIGH⚡	tests/agent/test_repo_prep.py	57	assert "git checkout --force abc123 --quiet 2>/dev/null \|\| true" not in cmd	CODE
HIGH⚡	tests/agent/test_repo_prep.py	59	assert "git fetch --all --quiet \|\| true" in cmd	CODE
HIGH⚡	tests/agent/test_workflow_push_guard.py	91	"cd /repo && git push -u origin HEAD:feature"	CODE
HIGH⚡	tests/agent/test_workflow_push_guard.py	99	assert guard._parse_git_push("git status && git push") is None	CODE
HIGH⚡	tests/sandbox/test_sandbox_paths.py	75	assert backend.commands == ["test -d /workspace && test -w /workspace"]	CODE
HIGH⚡	tests/sandbox/test_sandbox_paths.py	92	"test -d /workspace && test -w /workspace",	CODE
HIGH⚡	tests/sandbox/test_sandbox_paths.py	94	"test -d /home/daytona && test -w /home/daytona",	CODE
HIGH⚡	tests/sandbox/test_sandbox_paths.py	109	assert backend.commands == ["test -d /workspace && test -w /workspace"]	CODE
HIGH⚡	tests/sandbox/test_sandbox_paths.py	121	assert backend.commands == ["test -d /home/daytona && test -w /home/daytona"]	CODE
HIGH	tests/e2e/fake_llm.py	205	{"name": "execute", "args": {"command": "echo planning && ls"}, "id": "call-plan-read"}	STRING
HIGH	agent/reviewer.py	366	GH_TOKEN=dummy git fetch origin {head_sha_or_placeholder} --quiet \|\| GH_TOKEN=dummy git fetch origin refs/pull/{pr_numbe	CODE
HIGH⚡	agent/utils/repo_prep.py	52	f" cd {q_repo_dir} && {{ GH_TOKEN=dummy git fetch --all --quiet \|\| true; }}",	CODE
HIGH⚡	agent/utils/repo_prep.py	59	lines.append(f"GH_TOKEN=dummy git fetch origin {q_base} --quiet 2>/dev/null \|\| true")	CODE
HIGH⚡	agent/utils/repo_prep.py	63	lines.append(f"GH_TOKEN=dummy git fetch origin {q_head} --quiet 2>/dev/null \|\| true")	CODE
HIGH⚡	agent/utils/repo_prep.py	66	lines.append(f"GH_TOKEN=dummy git fetch origin {pull_ref} --quiet 2>/dev/null \|\| true")	CODE

AI Slop Vocabulary11 hits · 34 pts

Severity	File	Line	Snippet	Context
MEDIUM⚡	tests/github/test_github_comment_prompts.py	86	# "Open SWE" identity lives in the harness-profile base prompt that	COMMENT
MEDIUM	tests/slack/test_slack_context.py	878	# resolve to a mapping (login_for_email returns None in this harness).	COMMENT
MEDIUM	tests/e2e/harness.py	170	# dev:mock), not this harness, so the cookie + the hot-reloading UI line up.	COMMENT
MEDIUM	tests/e2e/dev-mock.sh	2	# Local dev against the mock harness, with a REAL LLM and a Vite HMR dev server.	COMMENT
MEDIUM	tests/e2e/dev-mock.sh	5	# Slack/GitHub + sign-in to the harness ($API). Same-origin is what lets the	COMMENT
MEDIUM	tests/e2e/dev-mock.sh	20	# Pulled line-by-line, not by sourcing .env, which would clobber the harness's	COMMENT
MEDIUM	tests/e2e/dev-mock.sh	37	# own origin and Vite proxies it (and the WS) to the harness.	COMMENT
MEDIUM	tests/e2e/patches.py	44	# Set E2E_REAL_LLM=1 to drive the harness (mock Slack/GitHub, real agent)	COMMENT
MEDIUM	agent/prompt.py	25	# Provider keys the harness profile is registered under. deepagents resolves a	COMMENT
MEDIUM	agent/prompt.py	64	# Registered as the harness profile's `base_system_prompt`, it REPLACES	COMMENT
MEDIUM	.github/workflows/reviewer_eval.yml	3	# selecting the `prod` branch so the harness + judge match the deployed reviewer it scores.	COMMENT

Deep Nesting31 hits · 28 pts

Severity	File	Line	Context
LOW	evals/reviewer/run_eval.py	292	CODE
LOW	agent/server.py	432	CODE
LOW	agent/reconcile.py	39	CODE
LOW	agent/middleware/pr_creation_guard.py	102	CODE
LOW	agent/middleware/sandbox_circuit_breaker.py	67	CODE
LOW	agent/tools/open_pull_request.py	542	CODE
LOW	agent/tools/publish_review.py	246	CODE
LOW	agent/tools/publish_review.py	818	CODE
LOW	agent/tools/publish_review.py	962	CODE
LOW	agent/utils/multimodal.py	51	CODE
LOW	agent/utils/model.py	250	CODE
LOW	agent/utils/model.py	283	CODE
LOW	agent/utils/reviewer_outcomes.py	285	CODE
LOW	agent/utils/slack.py	913	CODE
LOW	agent/utils/slack.py	1110	CODE
LOW	agent/dashboard/review_chat_api.py	128	CODE
LOW	agent/dashboard/review_chat_api.py	313	CODE
LOW	agent/dashboard/agent_usage.py	485	CODE
LOW	agent/dashboard/agent_usage.py	513	CODE
LOW	agent/dashboard/thread_api.py	668	CODE
LOW	agent/dashboard/thread_api.py	731	CODE
LOW	agent/dashboard/thread_api.py	1156	CODE
LOW	agent/integrations/langsmith.py	541	CODE
LOW	agent/review/diff.py	75	CODE
LOW	agent/review/style_collector.py	287	CODE
LOW	agent/review/publish.py	543	CODE
LOW	agent/review/publish.py	665	CODE
LOW	agent/webhooks/linear.py	15	CODE
LOW	agent/webhooks/common.py	720	CODE
LOW	agent/webhooks/github.py	199	CODE
LOW	agent/webhooks/github.py	868	CODE

Fake / Example Data17 hits · 22 pts

Severity	File	Line	Snippet	Context
LOW⚡	tests/reviewer/test_review_chat.py	420	async def fake_token(repositories=None):	CODE
LOW⚡	tests/reviewer/test_review_chat.py	429	monkeypatch.setattr(review_chat_api, "get_github_app_installation_token", fake_token)	CODE
LOW⚡	tests/reviewer/test_review_api.py	108	async def fake_token():	CODE
LOW⚡	tests/reviewer/test_review_api.py	115	monkeypatch.setattr(review_api, "_require_app_token", fake_token)	CODE
LOW⚡	tests/reviewer/test_review_api.py	122	async def fake_token():	CODE
LOW⚡	tests/reviewer/test_review_api.py	128	monkeypatch.setattr(review_api, "_require_app_token", fake_token)	CODE
LOW⚡	tests/tools/test_observability_tools.py	221	monkeypatch.setenv("CONFIGURED_ADMINS", "admin@example.com")	CODE
LOW⚡	tests/tools/test_observability_tools.py	225	admin_config = {"configurable": {"user_email": "admin@example.com"}}	CODE
LOW⚡	tests/dashboard/test_dashboard_thread_api.py	1617	routes._require_admin({"sub": "not-admin", "email": "user@example.com"})	CODE
LOW⚡	tests/dashboard/test_public_repo_org_gate.py	342	async def fake_token() -> None:	CODE
LOW⚡	tests/dashboard/test_public_repo_org_gate.py	345	monkeypatch.setattr(github_org_membership, "get_github_app_installation_token", fake_token)	CODE
LOW	tests/dashboard/test_public_repo_org_gate.py	376	async def fake_token() -> str:	CODE
LOW	tests/dashboard/test_public_repo_org_gate.py	379	monkeypatch.setattr(github_org_membership, "get_github_app_installation_token", fake_token)	CODE
LOW	tests/github/test_repo_extraction.py	102	"user": {"id": "user-1", "name": "Test User", "email": "test@test.com"},	CODE
LOW	tests/github/test_repo_extraction.py	156	"user": {"id": "user-1", "name": "Test User", "email": "test@test.com"},	CODE
LOW	tests/e2e/patches.py	80	return "dummy-user-oauth-token"	CODE
LOW	docs/CUSTOMIZATION.md	415	"user_email": "user@example.com",	CODE

Decorative Section Separators7 hits · 21 pts

Severity	File	Line	Snippet	Context
MEDIUM	…/src/features/agents/experiments/SourceControlTile.tsx	904	// ─── DiffCard ────────────────────────────────────────────────────────────────	COMMENT
MEDIUM	agent/dashboard/user_mappings.py	62	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	agent/dashboard/user_mappings.py	64	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	agent/dashboard/user_mappings.py	124	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	agent/dashboard/user_mappings.py	126	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	agent/dashboard/user_mappings.py	167	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	agent/dashboard/user_mappings.py	169	# ---------------------------------------------------------------------------	COMMENT

Cross-File Repetition3 hits · 15 pts

Severity	File	Snippet	Context
HIGH	agent/webhooks/linear.py	slack webhook handler — moved out of common.py (behavior-identical). helpers and constants stay in common.py; they are a	STRING
HIGH	agent/webhooks/github.py	slack webhook handler — moved out of common.py (behavior-identical). helpers and constants stay in common.py; they are a	STRING
HIGH	agent/webhooks/slack.py	slack webhook handler — moved out of common.py (behavior-identical). helpers and constants stay in common.py; they are a	STRING

AI Structural Patterns6 hits · 5 pts

Severity	File	Line	Context
LOW	agent/dispatch.py	106	CODE
LOW	agent/prompt.py	337	CODE
LOW	agent/middleware/workflow_push_guard.py	251	CODE
LOW	agent/dashboard/thread_api.py	812	CODE
LOW	agent/dashboard/routes.py	1523	CODE
LOW	agent/integrations/langsmith.py	541	CODE

Docstring Block Structure1 hit · 5 pts

Severity	File	Line	Snippet	Context
HIGH	agent/integrations/stagehand_browser.py	185	Perform a single natural-language action on the current page. Examples: "click the Sign in button", "type 'hello' i	STRING

Over-Commented Block4 hits · 4 pts

Severity	File	Line	Snippet	Context
LOW	tests/e2e/dev-mock.sh	1	#!/usr/bin/env bash	COMMENT
LOW	agent/utils/github_app.py	21	GITHUB_APP_INSTALLATION_ID = os.environ.get("GITHUB_APP_INSTALLATION_ID", "")	COMMENT
LOW	docs/INSTALLATION.md	441	# Without these, all agent operations use the GitHub App's bot token.	COMMENT
LOW	docs/INSTALLATION.md	461	# Used across all triggers when no repo is specified.	COMMENT

Analysis Overview

What These Metrics Mean

Score History

Severity Breakdown

Directory Score Breakdown

Pattern Findings