3.5

Adjusted Signal

3.5

Raw Pattern Score

100%

Time Factor

2026-10-31

Last Push

7.2K

Stars

TypeScript

Language

227.3K

Lines of Code

1.3K

Files

649

Pattern Hits

2026-10-31

Scan Date

0.00

HC Hit Rate

Risk Review · Payload v1

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

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

Cognitive Ownership Risk 15.6/100 · LOW

Can maintainers explain intent, assumptions, and trade-offs? 632 finding(s).

Hallucinated Dependency & Supply Chain Risk 0.4/100 · LOW

Are imports declared and package/API names verified? 12 finding(s).

Agent Over-Engineering Ratio 7.2/100 · LOW

Are wrappers, guards, and repeated structures necessary? 314 finding(s).

PR Review Velocity Impact 15.0/100 · LOW

Which changes need focused human review? 649 finding(s).

What These Metrics Mean

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

Pattern-Signal History

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

Severity Breakdown

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

CRITICAL 0HIGH 4MEDIUM 36LOW 609

Directory Score Breakdown

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

Pattern Findings

The scanner identified 649 distinct pattern matches across 14 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a detector match to inspect in context. Expand any category row to inspect the individual file paths, line numbers, code snippets, and the lexical context (CODE, COMMENT, or STRING) in which each match was detected.

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

Hyper-Verbose Identifiers309 hits · 322 pts

Severity	File	Line	Snippet	Context
LOW	tools/develop/llm-parameter-sweep/sweep.ts	583	function modelOverridesFromInterfaces(interfaces: string[]): Partial<AixAPI_Model> {	CODE
LOW	tools/develop/llm-parameter-sweep/sweep.ts	1259	function loadExistingDialectResults(filePath: string): DialectReultsByModel \| null {	CODE
LOW	tools/develop/llm-parameter-sweep/sweep.ts	1339	function vendorResultToDialectResults(vendorResult: VendorSweepResult): DialectReultsByModel {	CODE
LOW	tools/develop/aix-gemini-antigravity-probe/probe.ts	34	function createRecordingTransmitter(): { pt: IParticleTransmitter; log: LogEntry[] } {	CODE
LOW	kb/modules/LLM-vendor-integration.md	32	export function vendorModelsToModelDescriptions(wireModels: unknown): ModelDescriptionSchema[] {	CODE
LOW	kb/modules/AIX-callers-analysis.md	100	function messageWasInterruptedAtStart(message: Pick<DMessage, 'generator' \| 'fragments'>): boolean {	CODE
LOW	src/server/wire.ts	25	export async function nonTrpcServerFetchOrThrow(url: string, method: 'GET' \| 'POST', headers: HeadersInit, body: object	CODE
LOW	src/server/wire.ts	143	export function serverCapitalizeFirstLetter(string: string) {	CODE
LOW	src/server/posthog/posthog.server.ts	81	export async function posthogServerSendException(error: Error \| unknown, distinctId: string \| undefined, context: {	CODE
LOW	src/server/posthog/posthog.client-mock.ts	19	export async function posthogServerSendException(): Promise<void> {	CODE
LOW	src/common/app.queryclient.ts	8	export function reactQueryClientSingleton(): QueryClient {	CODE
LOW	src/common/logger/interceptors/logger.unhandled.ts	8	export function setupClientUncaughtErrorsLogging(): () => void {	CODE
LOW	src/common/logger/interceptors/logger.network.ts	9	export function setupClientFetchErrorsLogging(): () => void {	CODE
LOW	src/common/logger/hooks/useClientLoggerInterception.ts	10	export function useClientLoggerInterception(captureUnhandledErrors: boolean, captureFetchErrors: boolean) {	CODE
LOW	src/common/util/timeUtils.ts	46	export function prettyTimestampForFilenames(useSeconds: boolean = true) {	CODE
LOW	src/common/util/timeUtils.ts	66	export function createTimeBucketClassifierEn() {	CODE
LOW	src/common/util/fileSystemUtils.ts	13	export async function getAllFilesFromDirectoryRecursively(directoryHandle: FileSystemDirectoryHandle): Promise<FileWithH	CODE
LOW	src/common/util/fileSystemUtils.ts	62	export function getDataTransferFilesOrPromises(items: DataTransferItemList, fallbackAsFiles: boolean): FileOrFileHandleP	CODE
LOW	src/common/util/fileSystemUtils.ts	104	export async function getFirstFileSystemFileHandle(dataTransfer: DataTransfer): Promise<FileSystemFileHandle \| null> {	CODE
LOW	src/common/util/objectUtils.ts	121	export function objectDeepCloneWithStringLimit(value: unknown, debugCaller: string, maxBytes: number = 2048): unknown {	CODE
LOW	src/common/util/objectUtils.ts	171	export function objectStringifyWithIndentDepth(	CODE
LOW	src/common/util/objectUtils.ts	258	export function objectFindLargestStringPaths(obj: unknown, debugCaller: string, topN: number = 5, maxDepth: number = 20)	CODE
LOW	src/common/util/storageUtils.ts	12	export async function requestPersistentStorageSafe(): Promise<boolean> {	CODE
LOW	src/common/util/storageUtils.ts	46	export async function estimatePersistentStorageOrThrow(): Promise<{ usageMB: number, quotaMB: number } \| null> {	CODE
LOW	src/common/util/canvasUtils.ts	8	export function canvasToDataURLAndMimeType(	CODE
LOW	src/common/util/canvasUtils.ts	43	export async function asyncCanvasToBlobWithValidation(	CODE
LOW	src/common/util/canvasUtils.ts	64	export function renderVideoFrameToNewCanvas(videoElement: HTMLVideoElement): HTMLCanvasElement {	CODE
LOW	src/common/util/textUtils.ts	132	export function textEqualsDotDashInsensitive(a: string, b: string): boolean {	CODE
LOW	src/common/util/forceTouchToDoubleClick.ts	30	// function initForceTouchToDoubleClick(): void {	COMMENT
LOW	src/common/util/clipboardUtils.ts	36	export async function copyBlobPromiseToClipboard(mimeType: string, blobPromise: Promise<Blob>, typeLabel: string): Promi	CODE
LOW	src/common/util/clipboardUtils.ts	79	export function clipboardCopyDOMSelectionOrFallback(containerElement: HTMLElement \| null, fallbackText: string, typeLabe	CODE
LOW	src/common/util/clipboardUtils.ts	113	export function clipboardInterceptCtrlCForCleanup(event: ReactClipboardEvent): boolean {	CODE
LOW	src/common/util/netstate.ts	96	export function netStateSubscribeOnlineHint(callback: (online: boolean) => void): () => void {	CODE
LOW	src/common/util/webGeolocationUtils.ts	45	export async function webGeolocationPermissionState(): Promise<	CODE
LOW	src/common/layout/optima/ChromelessFloatingButtons.tsx	24	export function ChromelessFloatingButtons() {	CODE
LOW	…n/layout/optima/scratchclip/useGlobalClipboardSaver.ts	7	function isTargetTypicallyEditable(target: EventTarget \| null): target is HTMLElement {	CODE
LOW	src/common/layout/optima/portals/OptimaPortalsIn.tsx	67	function useOptimaPortalTargetElement(targetPortalId: OptimaPortalId) {	CODE
LOW	src/common/providers/ProviderBackendCapabilities.tsx	74	export function ProviderBackendCapabilities(props: { children: React.ReactNode }) {	CODE
LOW	src/common/providers/single-tab/instanceLock.ts	474	export function instanceLockRequestTransfer(): void {	CODE
LOW	src/common/logic/llmsRefreshStaleServicesOnBoot.ts	23	export async function llmsRefreshStaleServicesOnBoot(remoteServices: boolean, existingServices: boolean): Promise<number	CODE
LOW	src/common/stores/store-client.ts	74	export function deviceCreateRegistrationPayload(): DeviceRegistrationClientPayload {	CODE
LOW	src/common/stores/store-ai.ts	96	// export function resetAIPreferencesToDefaults(): void {	COMMENT
LOW	src/common/stores/metrics/metrics.chatgenerate.ts	86	export function metricsPendChatGenerateLg(metrics: DMetricsChatGenerate_Lg \| undefined): void {	CODE
LOW	src/common/stores/metrics/metrics.chatgenerate.ts	91	export function metricsFinishChatGenerateLg(metrics: DMetricsChatGenerate_Lg \| undefined, isAborted: boolean): void {	CODE
LOW	src/common/stores/metrics/metrics.chatgenerate.ts	144	export function metricsChatGenerateLgToMd(metrics: DMetricsChatGenerate_Lg): DMetricsChatGenerate_Md {	CODE
LOW	src/common/stores/metrics/metrics.chatgenerate.ts	172	export function metricsComputeChatGenerateCostsMd(metrics?: Readonly<DMetricsChatGenerate_Md>, pricing?: DPricingChatGen	CODE
LOW	src/common/stores/metrics/metrics.modelservice.ts	28	function createServiceMetricsAggregate(): ServiceMetricsAggregate {	CODE
LOW	src/common/stores/metrics/store-metrics.ts	20	export function metricsStoreAddChatGenerate(costs: MetricsChatGenerateCost_Md, inputTokens: number, outputTokens: number	CODE
LOW	src/common/stores/metrics/store-metrics.ts	24	export function useCostMetricsForLLMService(serviceId?: DModelsServiceId) {	CODE
LOW	src/common/stores/chat/chat.fragment-order.ts	16	export function normalizeUserFragmentGroupsOrder(order?: readonly unknown[] \| null): UserMessageFragmentGroup[] {	CODE
LOW	src/common/stores/chat/chat.fragment-order.ts	90	export function findFirstUserPromptFragment(fragments: Immutable<DMessageFragment[]>) {	CODE
LOW	src/common/stores/chat/chat.fragment-order.ts	94	export function findLastUserPromptFragment(fragments: Immutable<DMessageFragment[]>) {	CODE
LOW	src/common/stores/chat/store-chats.ts	519	function updateMessagesTokenCounts(messages: DMessage[], forceUpdate: boolean, debugFrom: string): number {	CODE
LOW	src/common/stores/chat/store-chats.ts	572	export function getConversationSystemPurposeId(conversationId: DConversationId \| null): SystemPurposeId \| null {	CODE
LOW	src/common/stores/chat/chat.tokens.ts	12	export function estimateTokensForFragments(llm: DLLM, role: DMessageRole, fragments: DMessageFragment[], addTopGlue: boo	CODE
LOW⚡	src/common/stores/chat/chat.message.ts	165	export function createDMessageTextContent(role: DMessageRole, text: string): DMessage {	CODE
LOW⚡	src/common/stores/chat/chat.message.ts	169	export function createDMessagePlaceholderIncomplete(role: DMessageRole, placeholderText: string): DMessage {	CODE
LOW⚡	src/common/stores/chat/chat.message.ts	176	export function createDMessageFromFragments(role: DMessageRole, fragments: DMessageFragment[]): DMessage {	CODE
LOW	src/common/stores/chat/chat.message.ts	228	export function duplicateDMessageMetadata(metadata: Immutable<DMessageMetadata>): DMessageMetadata {	CODE
LOW	src/common/stores/chat/chat.message.ts	243	export function duplicateDMessageGenerator(generator: Immutable<DMessageGenerator>): DMessageGenerator {	CODE
249 more matches not shown…

Over-Commented Block234 hits · 234 pts

Severity	File	Line	Snippet	Context
LOW	next-env.d.ts	1	/// <reference types="next" />	COMMENT
LOW	next.config.ts	161		COMMENT
LOW	tools/develop/worktrees/wt.sh	221	fi	COMMENT
LOW	tools/develop/worktrees/wt.sh	241	#if [ "$ds_copied" = true ]; then	COMMENT
LOW	…develop/gen-icon-sprites/VendorIconSprite.template.tsx	1	// /**	COMMENT
LOW	…develop/gen-icon-sprites/VendorIconSprite.template.tsx	21	// * Mount once in the app root (ProviderTheming) - all `<use href="#vi-...">` references resolve from here.	COMMENT
LOW	…develop/gen-icon-sprites/VendorIconSprite.template.tsx	41	// * Near-zero per-instance cost - no Emotion/styled-components.	COMMENT
LOW	…develop/gen-icon-sprites/VendorIconSprite.template.tsx	61	// // if (sx.ml !== undefined) s.marginLeft = typeof sx.ml === 'number' ? sx.ml * 8 : sx.ml;	COMMENT
LOW	…develop/gen-icon-sprites/VendorIconSprite.template.tsx	81	// // fill: 'currentColor',	COMMENT
LOW	.claude/commands/code/tape-opens/census.sh	1	#!/usr/bin/env bash	COMMENT
LOW	.github/dependabot.yml	21	# - package-ecosystem: npm	COMMENT
LOW	.github/dependabot.yml	41	# versions: [">=5.0.7", "<6"]	COMMENT
LOW	.github/dependabot.yml	61	# patterns:	COMMENT
LOW	pages/_document.tsx	81	MyDocument.getInitialProps = async (ctx: DocumentContext) => {	COMMENT
LOW	src/common/app.nav.ts	101	hideDrawer: true,	COMMENT
LOW	src/common/app.nav.ts	121	// route: '/cortex',	COMMENT
LOW	src/common/util/urlUtils.ts	161		COMMENT
LOW	src/common/util/urlUtils.ts	181	// _update(searchParams);	COMMENT
LOW	src/common/util/urlUtils.ts	201	// }	COMMENT
LOW	src/common/util/viewTransitionUtils.ts	1	// import { flushSync } from 'react-dom';	COMMENT
LOW	src/common/util/viewTransitionUtils.ts	21	// }	COMMENT
LOW	src/common/util/animUtils.ts	321	50% {	COMMENT
LOW	src/common/util/animUtils.ts	341	// `;	COMMENT
LOW	src/common/util/animUtils.ts	361	// }	COMMENT
LOW	src/common/util/animUtils.ts	381	// box-shadow: -12px 32px 24px 0 rgba(11, 107, 203, 0.2);	COMMENT
LOW	src/common/util/stateUtils.tsx	1	// import * as React from 'react';	COMMENT
LOW	src/common/util/stateUtils.tsx	21	// {props.children}	COMMENT
LOW	src/common/util/forceTouchToDoubleClick.ts	1	// /**	COMMENT
LOW	src/common/util/forceTouchToDoubleClick.ts	21	// (_forceTouchSupported ??= typeof MouseEvent !== 'undefined' && 'webkitForce' in MouseEvent.prototype);	COMMENT
LOW	src/common/util/forceTouchToDoubleClick.ts	41	// // Force touch → synthetic double-click	COMMENT
LOW	src/common/util/eventUtils.ts	1	// /**	COMMENT
LOW	src/common/util/eventUtils.ts	21	// return () => target.removeEventListener(eventType, listener);	COMMENT
LOW	src/common/util/downloadUtils.ts	21	const url = URL.createObjectURL(blob);	COMMENT
LOW	src/common/util/downloadUtils.ts	41	// */	COMMENT
LOW	…c/common/util/mediasession/useMediaSessionCallbacks.ts	1	// import * as React from 'react';	COMMENT
LOW	…c/common/util/mediasession/useMediaSessionCallbacks.ts	21	// }, [stableHandlers]);	COMMENT
LOW	src/common/util/mediasession/MediaSessionManager.ts	1	// type MediaSessionAction = 'play' \| 'pause' \| 'stop' \| 'seekbackward' \| 'seekforward' \| 'previoustrack' \| 'nexttrack';	COMMENT
LOW	src/common/util/mediasession/MediaSessionManager.ts	21	// console.warn('Media Session API is not supported in this browser.');	COMMENT
LOW	src/common/util/mediasession/MediaSessionManager.ts	41	// public unregisterComponent(handlers: MediaSessionCallbacks): void {	COMMENT
LOW	src/common/util/mediasession/MediaSessionManager.ts	61	// if (!navigator.mediaSession.metadata)	COMMENT
LOW	src/common/util/mediasession/MediaSessionManager.ts	81	//	COMMENT
LOW	src/common/util/audio/AudioGenerator.ts	161		COMMENT
LOW	src/common/util/audio/AudioGenerator.ts	461	}	COMMENT
LOW	src/common/util/audio/AudioGenerator.ts	481	//	COMMENT
LOW	src/common/util/audio/AudioGenerator.ts	501	// oToneFilter.type = 'lowpass';	COMMENT
LOW	src/common/util/audio/AudioGenerator.ts	521	// const { pitch = 150, decay = 0.2, tone = 1, noiseType = 'white' } = options;	COMMENT
LOW	src/common/util/audio/AudioGenerator.ts	541	// const ng = ctx.createGain();	COMMENT
LOW	src/common/util/audio/AudioGenerator.ts	561	// }	COMMENT
LOW	src/common/util/audio/AudioGenerator.ts	581	//	COMMENT
LOW	src/common/util/audio/AudioGenerator.ts	601	// createEnvelope(ctx, n1gain.gain, 0.001, 0.03, 0, 0.02);	COMMENT
LOW	src/common/layout/withLayout.tsx	61	// return <OptimaLayout {...rest}>{children}</OptimaLayout>;	COMMENT
LOW	src/common/layout/overlays/store-layout-overlays.ts	121	overlays: [	COMMENT
LOW	src/common/logic/ProcessingQueue.ts	181		COMMENT
LOW	src/common/stores/llms/model.domains.registry.ts	81	// - Domains: general, specialized, task-specific, ...	COMMENT
LOW	src/common/stores/llms/llms.types.ts	321	// Future changes?	COMMENT
LOW	src/common/stores/llms/llms.types.ts	341	// mimeTypes?: string[];	COMMENT
LOW	src/common/attachment-drafts/attachment.mimetypes.ts	181	export function mimeTypeIsPlainText(mimeType: string): boolean {	COMMENT
LOW	src/common/attachment-drafts/attachment.mimetypes.ts	201	// - Maximum of 16 individual images for the gemini-pro-vision and 3600 images for gemini-1.5-pro	COMMENT
LOW	…nt-drafts/attachment-sources/useWebAttachmentModal.tsx	101	if (!cleanUrls.length) {	COMMENT
LOW	src/common/components/useDebouncer.ts	1	// import * as React from 'react';	COMMENT
174 more matches not shown…

Modern AI Meta-Vocabulary27 hits · 82 pts

Severity	File	Line	Snippet	Context
MEDIUM	src/common/stores/chat/chat.message.ts	30	// Session metadata for multi-turn agentic sessions was considered here (see commit 3cd38f47)	COMMENT
MEDIUM	src/common/stores/llms/model.domains.editorial.ts	108	{ vendor: 'xai', modelId: 'grok-4.6' }, // 2026-08-12 GA - frontier for coding/agentic/knowledge work, extend	CODE
MEDIUM⚡	src/common/stores/llms/model.domains.editorial.ts	125	{ vendor: 'googleai', modelId: 'models/gemini-3.6-flash' }, // 2026-07-21 GA - "improved code/agentic planning" +	CODE
MEDIUM⚡	src/common/stores/llms/model.domains.editorial.ts	127	{ vendor: 'openai', modelId: 'gpt-6.1-sol' }, // 2026-09-29 - "exceptionally strong on agentic coding", same pri	CODE
MEDIUM⚡	src/common/stores/llms/model.domains.editorial.ts	128	{ vendor: 'openai', modelId: 'gpt-6-sol' }, // 2026-09-22 - "built for complex coding and agentic workflows"	CODE
MEDIUM⚡	src/common/stores/llms/model.domains.editorial.ts	129	{ vendor: 'openai', modelId: 'gpt-5.6-sol' }, // 2026-07-09 GA - "strongest yet for agentic coding"	CODE
MEDIUM	src/common/stores/llms/model.domains.editorial.ts	141	{ vendor: 'xai', modelId: 'grok-4.6' }, // xAI frontier for coding/agentic; new Grok Build default (2026-08-1	CODE
MEDIUM	src/common/stores/llms/model.domains.editorial.ts	150	{ vendor: 'nvidianim', modelId: 'nvidia/nemotron-3.5-super-vl-120b-a12b' }, // agentic/tool-use tuned, 12B active (	CODE
MEDIUM	src/modules/llms/server/gemini/gemini.models.ts	357	// Improved token efficiency and code/agentic planning capabilities, at a lower price point than 3.5 Flash	COMMENT
MEDIUM	src/modules/llms/server/gemini/gemini.models.ts	420	// First "point one" update - introduces 'medium' thinking level, improved agentic coding	COMMENT
MEDIUM	src/modules/llms/server/openai/models/zai.models.ts	45	// GLM-5.3 - 1M context flagship (post-train of the GLM-5.2 base; coding, cyber, agentic)	COMMENT
MEDIUM	src/modules/llms/server/openai/models/cohere.models.ts	38	// chatPrice is set only where Cohere publishes per-token prices; newer/agentic models are	COMMENT
MEDIUM	src/modules/llms/server/openai/models/cohere.models.ts	103	// North Mini Code - agentic coding (North platform)	COMMENT
MEDIUM	src/modules/llms/server/openai/models/alibaba.models.ts	435	// GA release of V4 Pro (2026-08-13), superseding the April preview: same 1.6T/49B MoE, re-post-trained for agentic	COMMENT
MEDIUM	src/modules/llms/server/openai/models/alibaba.models.ts	436	// with a DSpark speculative-decoding module attached. Large agentic deltas vs the preview (DeepSWE 62.7 vs 12.8,	COMMENT
MEDIUM	…c/modules/llms/server/openai/models/deepseek.models.ts	32	// Open weights MIT on HF (deepseek-ai/DeepSeek-V4.1-Flash). DeepSeek's table puts it ahead of V4-Pro-0813 on the agen	COMMENT
MEDIUM	…c/modules/llms/server/openai/models/deepseek.models.ts	38	// - The hidden agentic preamble that made 'low' cheaper on V4 is gone (identical prompt_tokens at every effort, with an	COMMENT
MEDIUM⚡	…c/modules/llms/server/openai/models/deepseek.models.ts	63	// - Preview architecture unchanged (1.6T/49B) plus a DSpark speculative-decoding module, re-post-trained for agentic	COMMENT
MEDIUM⚡	…c/modules/llms/server/openai/models/deepseek.models.ts	64	// work; open weights MIT on HF (deepseek-ai/DeepSeek-V4-Pro-0813). Gains are agentic (DeepSWE 12.8 -> 62.7, Terminal	COMMENT
MEDIUM⚡	…c/modules/llms/server/openai/models/deepseek.models.ts	66	// - Pro's effort mapping now matches flash: 'low' is a real cheaper tier, skipping the ~79-token hidden agentic preambl	COMMENT
MEDIUM⚡	…c/modules/llms/server/openai/models/deepseek.models.ts	72	// - Same 'deepseek-v4-flash' id, same arch/size/pricing, public beta. Reported agentic gains are vs V4-Pro-Preview on	COMMENT
MEDIUM	…c/modules/llms/server/openai/models/deepseek.models.ts	120	// 'low' keeps reasoning on yet skips the hidden agentic preamble (8 vs 87 prompt tokens), so it is cheaper per re	COMMENT
MEDIUM	src/modules/llms/server/openai/models/openai.models.ts	18	// GPT-6 Astra: Pro reasoning mode, probed live 2026-09-04: the answer streams as one whole delta, ~1.5K input-token s	COMMENT
MEDIUM	src/modules/llms/server/openai/models/openai.models.ts	43	// on a trivial prompt); each request adds ~1.7K billed input tokens of orchestration scaffold; background mode su	COMMENT
MEDIUM	…atch/wiretypes/_upstream/gemini.deep-research.guide.md	1109	Pricing follows a [pay-as-you-go model](https://ai.google.dev/gemini-api/docs/pricing#pricing-for-agents) based on the u	CODE
MEDIUM	…atch/wiretypes/_upstream/gemini.deep-research.guide.md	1109	Pricing follows a [pay-as-you-go model](https://ai.google.dev/gemini-api/docs/pricing#pricing-for-agents) based on the u	CODE
MEDIUM	…spatch/chatGenerate/adapters/openai.chatCompletions.ts	204	// (on V4 'low' also skipped a hidden agentic preamble; gone on V4.1-Flash, probed 2026-09-12)	COMMENT

Structural Annotation Overuse38 hits · 71 pts

Severity	File	Line	Snippet	Context
LOW	.claude/commands/code/grep-history.md	25	### Step 1: Resolve the ancestor commit	COMMENT
LOW⚡	.claude/commands/code/grep-history.md	39	### Step 2: Run pickaxe search	COMMENT
LOW⚡	.claude/commands/code/grep-history.md	47	### Step 3: Check endpoints	COMMENT
LOW⚡	.claude/commands/code/grep-history.md	56	### Step 4: Report	COMMENT
LOW	.claude/commands/code/tape-opens/SKILL.md	17	## Step 1 - census (deterministic, run exactly this)	COMMENT
LOW	.claude/commands/code/tape-opens/SKILL.md	27	## Step 2 - read the spine	COMMENT
LOW	.claude/commands/code/tape-opens/SKILL.md	38	## Step 3 - build the tree	COMMENT
LOW	.claude/commands/code/tape-opens/SKILL.md	52	## Step 4 - output	COMMENT
LOW⚡	.claude/commands/rel/release-open.md	8	## Step 1: Determine Version	COMMENT
LOW⚡	.claude/commands/rel/release-open.md	12	## Step 2: Gather Context	COMMENT
LOW⚡	.claude/commands/rel/release-open.md	20	## Step 3: Update Files	COMMENT
LOW⚡	.claude/commands/rel/release-open.md	40	## Step 4: README	COMMENT
LOW⚡	.claude/commands/rel/release-open.md	48	## Step 5: Git Operations	COMMENT
LOW⚡	.claude/commands/rel/release-open.md	56	## Step 6: GitHub Release	COMMENT
LOW	.claude/commands/rel/release-open.md	88	## Step 7: Changelog (big-agi.com/changes)	COMMENT
LOW	.claude/commands/rel/release-open.md	95	## Step 8: Announcements	COMMENT
LOW	.claude/commands/rel/release-open.md	119	## Step 9: Cover Image Prompts	COMMENT
LOW	docs/config-azure-openai.md	58	### Step 1: Azure Account & Subscription	COMMENT
LOW	docs/config-azure-openai.md	67	### Step 2: Create Azure OpenAI Resource	COMMENT
LOW	docs/config-azure-openai.md	92	### Step 3: Deploy Models	COMMENT
LOW⚡	docs/deploy-cloudflare.md	23	## Step 1: Repository Forking	COMMENT
LOW⚡	docs/deploy-cloudflare.md	27	## Step 2: Linking Cloudflare Pages to Your GitHub Account	COMMENT
LOW⚡	docs/deploy-cloudflare.md	33	## Step 3: Configuring Build and Deployments	COMMENT
LOW	docs/deploy-cloudflare.md	44	## Step 4: Monitoring the Deployment Process	COMMENT
LOW	docs/deploy-cloudflare.md	49	## Step 5: Required: Set the `nodejs_compat` compatibility flag	COMMENT
LOW⚡	docs/deploy-k8s.md	8	### Step 1: Clone the big-AGI repository	COMMENT
LOW⚡	docs/deploy-k8s.md	15	### Step 2: Create the namespace	COMMENT
LOW⚡	docs/deploy-k8s.md	21	### Step 3: Fill in the key information into env-secret.yaml	COMMENT
LOW	docs/deploy-k8s.md	34	### Step 4: Deploying Kubernetes Resources	COMMENT
LOW	docs/deploy-k8s.md	40	### Step 5: Verifying the Resource Statuses	COMMENT
LOW	docs/deploy-k8s.md	54	### Step 6: Testing the Service	COMMENT
LOW⚡	…ocks/enhanced-code/livefile-patch/useLiveFilePatch.tsx	40	// // Step 1: Load the latest version of the file	COMMENT
LOW⚡	…ocks/enhanced-code/livefile-patch/useLiveFilePatch.tsx	45	// // Step 2: Generate patch	COMMENT
LOW⚡	…ocks/enhanced-code/livefile-patch/useLiveFilePatch.tsx	50	// // Step 3: Apply patch and check if it succeeds	COMMENT
LOW⚡	…ocks/enhanced-code/livefile-patch/useLiveFilePatch.tsx	53	// // Step 4: Success - user can decide to proceed	COMMENT
LOW	…atch/wiretypes/_upstream/gemini.deep-research.guide.md	115	### Step 1: Request a plan	COMMENT
LOW	…atch/wiretypes/_upstream/gemini.deep-research.guide.md	178	### Step 2: Refine the plan (optional)	COMMENT
LOW	…atch/wiretypes/_upstream/gemini.deep-research.guide.md	240	### Step 3: Approve and execute	COMMENT

Synthetic Comment Markers3 hits · 20 pts

Severity	File	Line	Snippet	Context
HIGH	tools/develop/worktrees/wt.sh	325	# Handle --materialize flag: bring an EXISTING worktree (e.g. created by an AI	COMMENT
HIGH	…ules/aix/server/dispatch/wiretypes/openai.wiretypes.ts	979	// Control the content-moderation level for images generated by GPT Image models.	COMMENT
HIGH	…/message/fragments-content/BlockPartHostedResource.tsx	228	From now on, files generated by Claude tools (code execution, etc.) will be automatically downloaded and embed	CODE

Decorative Section Separators5 hits · 15 pts

Severity	File	Line	Snippet	Context
MEDIUM	tools/develop/gen-icon-sprites/generate-llm-sprites.ts	35	// ── Step 1: Parse vendor registry (vendorId → component name → file) ──────────	COMMENT
MEDIUM	tools/develop/gen-icon-sprites/generate-llm-sprites.ts	65	// ── Step 2: Parse a vendor icon .tsx file ─────────────────────────────────────	COMMENT
MEDIUM	tools/develop/gen-icon-sprites/generate-llm-sprites.ts	110	// ── Step 3: Build <symbol> JSX for one vendor ─────────────────────────────────	COMMENT
MEDIUM	tools/develop/gen-icon-sprites/generate-llm-sprites.ts	156	// ── Step 4: Generate output by replacing template placeholders ────────────────	COMMENT
MEDIUM	tools/develop/gen-icon-sprites/generate-llm-sprites.ts	176	// ── Main ──────────────────────────────────────────────────────────────────────	COMMENT

Fake / Example Data11 hits · 12 pts

Severity	File	Line	Snippet	Context
LOW	src/apps/chat/components/composer/Composer.tsx	979	<span className={speechInterimResult.interimTranscript === PLACEHOLDER_INTERIM_TRANSCRIPT ? 'place	CODE
LOW	…t/components/message/render-tree/cmRenderTree.build.ts	121	nodes.push({ kind: 'placeholder', key: `placeholder:${fragment.fId}`, fragment: _withPart(fragment, part) })	CODE
LOW	…t/components/message/render-tree/cmRenderTree.types.ts	101	export interface CMNodePlaceholder extends _CMNodeBase<'placeholder'> {	CODE
LOW⚡	…at/components/message/render-tree/cmRenderTree.test.ts	89	assert.deepEqual(kinds(tree), ['tool-calls', 'placeholder', 'tool-response']);	CODE
LOW⚡	…at/components/message/render-tree/cmRenderTree.test.ts	97	assert.deepEqual(kinds(spanned), ['reasoning', 'placeholder']);	CODE
LOW⚡	…at/components/message/render-tree/cmRenderTree.test.ts	99	assert.deepEqual(kinds(build([t1, notice, t2])), ['text', 'placeholder', 'text']);	CODE
LOW	…at/components/message/render-tree/cmRenderTree.test.ts	140	assert.deepEqual(kinds(build([vehicle, redacted, t, ph], 'edit')), ['reasoning', 'edit-text', 'placeholder']);	CODE
LOW	…at/components/message/render-tree/cmRenderTree.test.ts	141	assert.deepEqual(kinds(build([vehicle, redacted, t, ph])), ['reasoning', 'text', 'placeholder']);	CODE
LOW	…at/components/message/render-tree/cmRenderTree.test.ts	313	assert.deepEqual(kinds(edit), ['reasoning', 'edit-text', 'placeholder']);	CODE
LOW	…t/components/message/render-tree/CMRenderTreeNodes.tsx	378	&& body[0].kind === 'placeholder';	CODE
LOW	…t/components/message/render-tree/CMRenderTreeNodes.tsx	571	case 'placeholder': {	CODE

Redundant / Tautological Comments7 hits · 10 pts

Severity	File	Line	Snippet	Context
LOW	tools/develop/worktrees/wt.sh	456	# Check if trying to remove the main branch	COMMENT
LOW	tools/develop/worktrees/wt.sh	505	# Check if branch exists	COMMENT
LOW	tools/develop/worktrees/wt.sh	703	# Check if branch already exists	COMMENT
LOW	tools/develop/worktrees/wt.sh	711	# Check if worktree already exists	COMMENT
LOW	tools/ai/repo-structure.sh	31	# Check if we're in a git repository	COMMENT
LOW	tools/ai/repo-structure.sh	76	# Check if TMP_FILE is empty after filtering	COMMENT
LOW	tools/ai/repo-structure.sh	117	# Check if we've already processed this directory	COMMENT

Verbosity Indicators4 hits · 9 pts

Severity	File	Line	Snippet	Context
LOW⚡	…ocks/enhanced-code/livefile-patch/useLiveFilePatch.tsx	40	// // Step 1: Load the latest version of the file	COMMENT
LOW⚡	…ocks/enhanced-code/livefile-patch/useLiveFilePatch.tsx	45	// // Step 2: Generate patch	COMMENT
LOW⚡	…ocks/enhanced-code/livefile-patch/useLiveFilePatch.tsx	50	// // Step 3: Apply patch and check if it succeeds	COMMENT
LOW⚡	…ocks/enhanced-code/livefile-patch/useLiveFilePatch.tsx	53	// // Step 4: Success - user can decide to proceed	COMMENT

Self-Referential Comments2 hits · 6 pts

Severity	File	Line	Snippet	Context
MEDIUM	tools/develop/worktrees/wt.sh	734	# Create the worktree with a new branch at the selected source ref.	COMMENT
MEDIUM	docs/docker/docker-compose-browserless.yaml	1	# This file is used to run `big-AGI` and `browserless` with Docker Compose.	COMMENT

TODO Padding4 hits · 6 pts

Severity	File	Line	Snippet	Context
LOW	src/common/stores/chat/chat.tokens.ts	64	// TODO: implement this properly - as we don't have resolutions in the part(!) - and this could be really expens	COMMENT
LOW	src/common/stores/chat/chat.tokens.ts	85	// TODO: implement this properly - as we don't have resolutions in the part(!) - and this could be really expens	COMMENT
LOW	…erver/dispatch/chatGenerate/ChatGenerateTransmitter.ts	86	// TODO: implement throttling on a particle basis	COMMENT
LOW	…c/modules/aix/client/aix.client.chatGenerateRequest.ts	587	// TODO: implement mid-chat system messages if needed	COMMENT

Magic Placeholder Names1 hit · 5 pts

Severity	File	Line	Snippet	Context
HIGH	docs/config-azure-openai.md	32	AZURE_OPENAI_API_KEY=your-api-key	CODE

AI Slop Vocabulary2 hits · 5 pts

Severity	File	Line	Snippet	Context
MEDIUM	src/common/util/webGeolocationUtils.ts	130	// TODO: use a robust geocoding service	COMMENT
MEDIUM	…patch/chatGenerate/adapters/anthropic.messageCreate.ts	16	const hotFixAntSeparateContiguousThinkingBlocks = true; // Interleave continuous thinking blocks (without aText) with th	CODE

Example Usage Blocks2 hits · 3 pts

Severity	File	Line	Snippet	Context
LOW	tools/develop/aix-gemini-antigravity-probe/examples.sh	5	# Usage:	COMMENT
LOW	src/common/util/idbUtils.ts	314	// Example usage:	COMMENT

enricoros/big-AGI

Open-Source Code Quality, Security and Technical Debt Review