Repository Analysis

enricoros/big-AGI

AI suite powered by state-of-the-art models and providing advanced AI/AGI functions. Includes AI personas, AGI functions, world-class Beam multi-model chats, text-to-image, voice, response streaming, code highlighting and execution, PDF import, presets for developers, much more. Deploy on-prem or in the cloud.

3.5 Likely human-written View on GitHub

Analysis Overview

This report presents the forensic synthetic code analysis of enricoros/big-AGI, a TypeScript project with 7,050 GitHub stars. SynthScan v2.0 examined 198,689 lines of code across 1100 source files, recording 564 pattern matches distributed across 15 syntactic categories. The overall adjusted score of 3.5 places this repository in the Likely human-written band.

The scanner applied 160+ deterministic lexical heuristics, multi-line block detectors, abstract syntax tree depth profilers, and a cross-file Jaccard similarity matrix to construct a statistically normalised synthetic code estimate. All matches are individually weighted by severity coefficient and contextual multiplier before summation, and the resulting headline score is temporally discounted to account for the repository's development history relative to the commercial emergence of large language model coding tooling (November 2022 onward).

3.5
Adjusted Score
3.5
Raw Score
100%
Time Factor
2026-07-14
Last Push
7.0K
Stars
TypeScript
Language
198.7K
Lines of Code
1.1K
Files
564
Pattern Hits
2026-07-14
Scan Date
0.01
HC Hit Rate

What These Metrics Mean

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

Score History

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

Severity Breakdown

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

CRITICAL 0HIGH 7MEDIUM 19LOW 538

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 564 distinct pattern matches across 15 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 Identifiers271 hits · 284 pts
SeverityFileLineSnippetContext
LOWtools/develop/llm-parameter-sweep/sweep.ts550function modelOverridesFromInterfaces(interfaces: string[]): Partial<AixAPI_Model> {CODE
LOWtools/develop/llm-parameter-sweep/sweep.ts1213function loadExistingDialectResults(filePath: string): DialectReultsByModel | null {CODE
LOWtools/develop/llm-parameter-sweep/sweep.ts1293function vendorResultToDialectResults(vendorResult: VendorSweepResult): DialectReultsByModel {CODE
LOWtools/develop/aix-gemini-antigravity-probe/probe.ts34function createRecordingTransmitter(): { pt: IParticleTransmitter; log: LogEntry[] } {CODE
LOWkb/modules/LLM-vendor-integration.md32export function vendorModelsToModelDescriptions(wireModels: unknown): ModelDescriptionSchema[] {CODE
LOWkb/modules/AIX-callers-analysis.md100function messageWasInterruptedAtStart(message: Pick<DMessage, 'generator' | 'fragments'>): boolean {CODE
LOWsrc/server/wire.ts25export async function nonTrpcServerFetchOrThrow(url: string, method: 'GET' | 'POST', headers: HeadersInit, body: object CODE
LOWsrc/server/wire.ts102export function serverCapitalizeFirstLetter(string: string) {CODE
LOWsrc/server/posthog/posthog.server.ts81export async function posthogServerSendException(error: Error | unknown, distinctId: string | undefined, context: {CODE
LOWsrc/server/posthog/posthog.client-mock.ts19export async function posthogServerSendException(): Promise<void> {CODE
LOWsrc/common/app.queryclient.ts6export function reactQueryClientSingleton(): QueryClient {CODE
LOWsrc/common/logger/interceptors/logger.unhandled.ts8export function setupClientUncaughtErrorsLogging(): () => void {CODE
LOWsrc/common/logger/interceptors/logger.network.ts8export function setupClientFetchErrorsLogging(): () => void {CODE
LOWsrc/common/logger/hooks/useClientLoggerInterception.ts10export function useClientLoggerInterception(captureUnhandledErrors: boolean, captureFetchErrors: boolean) {CODE
LOWsrc/common/util/timeUtils.ts20export function prettyTimestampForFilenames(useSeconds: boolean = true) {CODE
LOWsrc/common/util/timeUtils.ts36export function createTimeBucketClassifierEn() {CODE
LOWsrc/common/util/fileSystemUtils.ts13export async function getAllFilesFromDirectoryRecursively(directoryHandle: FileSystemDirectoryHandle): Promise<FileWithHCODE
LOWsrc/common/util/fileSystemUtils.ts62export function getDataTransferFilesOrPromises(items: DataTransferItemList, fallbackAsFiles: boolean): FileOrFileHandlePCODE
LOWsrc/common/util/fileSystemUtils.ts103export async function getFirstFileSystemFileHandle(dataTransfer: DataTransfer): Promise<FileSystemFileHandle | null> {CODE
LOWsrc/common/util/objectUtils.ts121export function objectDeepCloneWithStringLimit(value: unknown, debugCaller: string, maxBytes: number = 2048): unknown {CODE
LOWsrc/common/util/objectUtils.ts171export function objectStringifyWithIndentDepth(CODE
LOWsrc/common/util/objectUtils.ts258export function objectFindLargestStringPaths(obj: unknown, debugCaller: string, topN: number = 5, maxDepth: number = 20)CODE
LOWsrc/common/util/storageUtils.ts12export async function requestPersistentStorageSafe(): Promise<boolean> {CODE
LOWsrc/common/util/storageUtils.ts46export async function estimatePersistentStorageOrThrow(): Promise<{ usageMB: number, quotaMB: number } | null> {CODE
LOWsrc/common/util/canvasUtils.ts8export function canvasToDataURLAndMimeType(CODE
LOWsrc/common/util/canvasUtils.ts43export async function asyncCanvasToBlobWithValidation(CODE
LOWsrc/common/util/canvasUtils.ts64export function renderVideoFrameToNewCanvas(videoElement: HTMLVideoElement): HTMLCanvasElement {CODE
LOWsrc/common/util/forceTouchToDoubleClick.ts30// function initForceTouchToDoubleClick(): void {COMMENT
LOWsrc/common/util/clipboardUtils.ts31export function copyBlobPromiseToClipboard(mimeType: string, blobPromise: Promise<Blob>, typeLabel: string) {CODE
LOWsrc/common/util/clipboardUtils.ts82export function clipboardCopyDOMSelectionOrFallback(containerElement: HTMLElement | null, fallbackText: string, typeLabeCODE
LOWsrc/common/util/clipboardUtils.ts116export function clipboardInterceptCtrlCForCleanup(event: ReactClipboardEvent): boolean {CODE
LOWsrc/common/util/webGeolocationUtils.ts45export async function webGeolocationPermissionState(): Promise<CODE
LOWsrc/common/layout/optima/ChromelessFloatingButtons.tsx24export function ChromelessFloatingButtons() {CODE
LOW…mmon/layout/optima/panel/MobilePreferencesListItem.tsx11export function MobilePreferencesListItem(props: { autoClosePanel?: boolean }) {CODE
LOW…n/layout/optima/scratchclip/useGlobalClipboardSaver.ts7function isTargetTypicallyEditable(target: EventTarget | null): target is HTMLElement {CODE
LOWsrc/common/layout/optima/portals/OptimaPortalsIn.tsx67function useOptimaPortalTargetElement(targetPortalId: OptimaPortalId) {CODE
LOWsrc/common/providers/ProviderBackendCapabilities.tsx74export function ProviderBackendCapabilities(props: { children: React.ReactNode }) {CODE
LOWsrc/common/logic/store-logic-sherpa.ts78export async function sherpaReconfigureBackendModels() {CODE
LOWsrc/common/stores/store-client.ts74export function deviceCreateRegistrationPayload(): DeviceRegistrationClientPayload {CODE
LOWsrc/common/stores/store-ai.ts71// export function resetAIPreferencesToDefaults(): void {COMMENT
LOWsrc/common/stores/metrics/metrics.chatgenerate.ts72export function metricsPendChatGenerateLg(metrics: DMetricsChatGenerate_Lg | undefined): void {CODE
LOWsrc/common/stores/metrics/metrics.chatgenerate.ts77export function metricsFinishChatGenerateLg(metrics: DMetricsChatGenerate_Lg | undefined, isAborted: boolean): void {CODE
LOWsrc/common/stores/metrics/metrics.chatgenerate.ts123export function metricsChatGenerateLgToMd(metrics: DMetricsChatGenerate_Lg): DMetricsChatGenerate_Md {CODE
LOWsrc/common/stores/metrics/metrics.chatgenerate.ts155export function metricsComputeChatGenerateCostsMd(metrics?: Readonly<DMetricsChatGenerate_Md>, pricing?: DPricingChatGenCODE
LOWsrc/common/stores/metrics/metrics.modelservice.ts28function createServiceMetricsAggregate(): ServiceMetricsAggregate {CODE
LOWsrc/common/stores/metrics/store-metrics.ts20export function metricsStoreAddChatGenerate(costs: MetricsChatGenerateCost_Md, inputTokens: number, outputTokens: numberCODE
LOWsrc/common/stores/metrics/store-metrics.ts24export function useCostMetricsForLLMService(serviceId?: DModelsServiceId) {CODE
LOWsrc/common/stores/chat/store-chats.ts544function updateMessagesTokenCounts(messages: DMessage[], forceUpdate: boolean, debugFrom: string): number {CODE
LOWsrc/common/stores/chat/store-chats.ts597export function getConversationSystemPurposeId(conversationId: DConversationId | null): SystemPurposeId | null {CODE
LOWsrc/common/stores/chat/chat.tokens.ts12export function estimateTokensForFragments(llm: DLLM, role: DMessageRole, fragments: DMessageFragment[], addTopGlue: booCODE
LOWsrc/common/stores/chat/chat.message.ts164export function createDMessageTextContent(role: DMessageRole, text: string): DMessage {CODE
LOWsrc/common/stores/chat/chat.message.ts168export function createDMessagePlaceholderIncomplete(role: DMessageRole, placeholderText: string): DMessage {CODE
LOWsrc/common/stores/chat/chat.message.ts175export function createDMessageFromFragments(role: DMessageRole, fragments: DMessageFragment[]): DMessage {CODE
LOWsrc/common/stores/chat/chat.message.ts227export function duplicateDMessageMetadata(metadata: Readonly<DMessageMetadata>): DMessageMetadata {CODE
LOWsrc/common/stores/chat/chat.message.ts242export function duplicateDMessageGenerator(generator: Readonly<DMessageGenerator>): DMessageGenerator {CODE
LOWsrc/common/stores/chat/chat.message.ts272export function messageWasInterruptedAtStart(message: Pick<DMessage, 'generator' | 'fragments'>): boolean {CODE
LOWsrc/common/stores/chat/chat.message.ts277// export function messageOnlyContainsPlaceholder(message: Pick<DMessage, 'fragments'>): boolean {COMMENT
LOWsrc/common/stores/chat/chat.message.ts331export function messageFragmentsReduceText(fragments: Immutable<DMessageFragment[]>, fragmentSeparator: string = '\n\n',CODE
LOWsrc/common/stores/chat/chat.fragments.ts357export function isContentOrAttachmentFragment(fragment: DMessageFragment) {CODE
LOWsrc/common/stores/chat/chat.fragments.ts366export function isVoidAnnotationsFragment(fragment: DMessageFragment): fragment is DVoidFragmentModelAnnotations {CODE
211 more matches not shown…
Over-Commented Block215 hits · 215 pts
SeverityFileLineSnippetContext
LOWnext.config.ts101 { source: '/a/ph/array/:path*', destination: 'https://us-assets.i.posthog.com/array/:path*' },COMMENT
LOWtools/develop/worktrees/create-dev-worktree.sh181 #if [ -f ".idea/dataSources.xml" ]; thenCOMMENT
LOWtools/develop/worktrees/create-dev-worktree.sh201 #local xml_count=0COMMENT
LOW…develop/gen-icon-sprites/VendorIconSprite.template.tsx1// /**COMMENT
LOW…develop/gen-icon-sprites/VendorIconSprite.template.tsx21// * Mount once in the app root (ProviderTheming) - all `<use href="#vi-...">` references resolve from here.COMMENT
LOW…develop/gen-icon-sprites/VendorIconSprite.template.tsx41// * Near-zero per-instance cost - no Emotion/styled-components.COMMENT
LOW…develop/gen-icon-sprites/VendorIconSprite.template.tsx61// // if (sx.ml !== undefined) s.marginLeft = typeof sx.ml === 'number' ? sx.ml * 8 : sx.ml;COMMENT
LOW…develop/gen-icon-sprites/VendorIconSprite.template.tsx81// // fill: 'currentColor',COMMENT
LOW.github/dependabot.yml21# - package-ecosystem: npmCOMMENT
LOW.github/dependabot.yml41# versions: [">=5.0.7", "<6"]COMMENT
LOW.github/dependabot.yml61# patterns:COMMENT
LOWpages/_document.tsx81MyDocument.getInitialProps = async (ctx: DocumentContext) => {COMMENT
LOWsrc/common/app.nav.ts101 hideDrawer: true,COMMENT
LOWsrc/common/app.nav.ts121 // route: '/cortex',COMMENT
LOWsrc/common/util/urlUtils.ts141 return text.match(urlRegex) || [];COMMENT
LOWsrc/common/util/urlUtils.ts161// export function updateParam(key: string, value: string): void {COMMENT
LOWsrc/common/util/urlUtils.ts181// console.error('[DEV] SearchParams: error parsing URL:', error);COMMENT
LOWsrc/common/util/viewTransitionUtils.ts1// import { flushSync } from 'react-dom';COMMENT
LOWsrc/common/util/viewTransitionUtils.ts21// }COMMENT
LOWsrc/common/util/animUtils.ts321 50% {COMMENT
LOWsrc/common/util/animUtils.ts341// `;COMMENT
LOWsrc/common/util/animUtils.ts361// }COMMENT
LOWsrc/common/util/animUtils.ts381// box-shadow: -12px 32px 24px 0 rgba(11, 107, 203, 0.2);COMMENT
LOWsrc/common/util/stateUtils.tsx1// import * as React from 'react';COMMENT
LOWsrc/common/util/stateUtils.tsx21// {props.children}COMMENT
LOWsrc/common/util/forceTouchToDoubleClick.ts1// /**COMMENT
LOWsrc/common/util/forceTouchToDoubleClick.ts21// (_forceTouchSupported ??= typeof MouseEvent !== 'undefined' && 'webkitForce' in MouseEvent.prototype);COMMENT
LOWsrc/common/util/forceTouchToDoubleClick.ts41// // Force touch → synthetic double-clickCOMMENT
LOWsrc/common/util/eventUtils.ts1// /**COMMENT
LOWsrc/common/util/eventUtils.ts21// return () => target.removeEventListener(eventType, listener);COMMENT
LOWsrc/common/util/downloadUtils.ts21 const url = URL.createObjectURL(blob);COMMENT
LOWsrc/common/util/downloadUtils.ts41// */COMMENT
LOW…c/common/util/mediasession/useMediaSessionCallbacks.ts1// import * as React from 'react';COMMENT
LOW…c/common/util/mediasession/useMediaSessionCallbacks.ts21// }, [stableHandlers]);COMMENT
LOWsrc/common/util/mediasession/MediaSessionManager.ts1// type MediaSessionAction = 'play' | 'pause' | 'stop' | 'seekbackward' | 'seekforward' | 'previoustrack' | 'nexttrack';COMMENT
LOWsrc/common/util/mediasession/MediaSessionManager.ts21// console.warn('Media Session API is not supported in this browser.');COMMENT
LOWsrc/common/util/mediasession/MediaSessionManager.ts41// public unregisterComponent(handlers: MediaSessionCallbacks): void {COMMENT
LOWsrc/common/util/mediasession/MediaSessionManager.ts61// if (!navigator.mediaSession.metadata)COMMENT
LOWsrc/common/util/mediasession/MediaSessionManager.ts81//COMMENT
LOWsrc/common/util/audio/AudioGenerator.ts161COMMENT
LOWsrc/common/util/audio/AudioGenerator.ts441// interface TR909Options {COMMENT
LOWsrc/common/util/audio/AudioGenerator.ts461//COMMENT
LOWsrc/common/util/audio/AudioGenerator.ts481// oToneFilter.connect(compressor);COMMENT
LOWsrc/common/util/audio/AudioGenerator.ts501//COMMENT
LOWsrc/common/util/audio/AudioGenerator.ts521// nHighpassFilter.frequency.setValueAtTime(2000, now);COMMENT
LOWsrc/common/util/audio/AudioGenerator.ts541// const now = ctx.currentTime;COMMENT
LOWsrc/common/util/audio/AudioGenerator.ts561// noise.start(now);COMMENT
LOWsrc/common/util/audio/AudioGenerator.ts581// createEnvelope(ctx, n2gain.gain, 0.02, decay - 0.02, 0.1, 0.05);COMMENT
LOWsrc/common/layout/withLayout.tsx61// return <OptimaLayout {...rest}>{children}</OptimaLayout>;COMMENT
LOWsrc/common/layout/overlays/store-layout-overlays.ts121 ],COMMENT
LOWsrc/common/logic/ProcessingQueue.ts181COMMENT
LOWsrc/common/stores/llms/llms.parameters.ts361 // when undefined, the model chooses automaticallyCOMMENT
LOWsrc/common/stores/llms/model.domains.registry.ts61};COMMENT
LOWsrc/common/stores/llms/model.domains.registry.ts81//COMMENT
LOWsrc/common/stores/llms/llms.types.ts321// Future changes?COMMENT
LOWsrc/common/stores/llms/llms.types.ts341// mimeTypes?: string[];COMMENT
LOWsrc/common/attachment-drafts/attachment.mimetypes.ts181// - Images are first scaled to fit within a 2048 x 2048 square (if larger), maintaining their aspect ratio.COMMENT
LOWsrc/common/attachment-drafts/attachment.mimetypes.ts201// - Supported Video formats:COMMENT
LOW…nt-drafts/attachment-sources/useWebAttachmentModal.tsx101 if (!cleanUrls.length) {COMMENT
LOWsrc/common/components/useDebouncer.ts1// import * as React from 'react';COMMENT
155 more matches not shown…
Structural Annotation Overuse34 hits · 65 pts
SeverityFileLineSnippetContext
LOW.claude/commands/code/grep-history.md25### Step 1: Resolve the ancestor commitCOMMENT
LOW.claude/commands/code/grep-history.md39### Step 2: Run pickaxe searchCOMMENT
LOW.claude/commands/code/grep-history.md48### Step 3: Check endpointsCOMMENT
LOW.claude/commands/code/grep-history.md57### Step 4: ReportCOMMENT
LOW.claude/commands/rel/release-open.md8## Step 1: Determine VersionCOMMENT
LOW.claude/commands/rel/release-open.md12## Step 2: Gather ContextCOMMENT
LOW.claude/commands/rel/release-open.md20## Step 3: Update FilesCOMMENT
LOW.claude/commands/rel/release-open.md40## Step 4: READMECOMMENT
LOW.claude/commands/rel/release-open.md48## Step 5: Git OperationsCOMMENT
LOW.claude/commands/rel/release-open.md56## Step 6: GitHub ReleaseCOMMENT
LOW.claude/commands/rel/release-open.md88## Step 7: Changelog (big-agi.com/changes)COMMENT
LOW.claude/commands/rel/release-open.md95## Step 8: AnnouncementsCOMMENT
LOW.claude/commands/rel/release-open.md119## Step 9: Cover Image PromptsCOMMENT
LOWdocs/config-azure-openai.md58### Step 1: Azure Account & SubscriptionCOMMENT
LOWdocs/config-azure-openai.md67### Step 2: Create Azure OpenAI ResourceCOMMENT
LOWdocs/config-azure-openai.md92### Step 3: Deploy ModelsCOMMENT
LOWdocs/deploy-cloudflare.md23## Step 1: Repository ForkingCOMMENT
LOWdocs/deploy-cloudflare.md27## Step 2: Linking Cloudflare Pages to Your GitHub AccountCOMMENT
LOWdocs/deploy-cloudflare.md33## Step 3: Configuring Build and DeploymentsCOMMENT
LOWdocs/deploy-cloudflare.md44## Step 4: Monitoring the Deployment ProcessCOMMENT
LOWdocs/deploy-cloudflare.md49## Step 5: Required: Set the `nodejs_compat` compatibility flagCOMMENT
LOWdocs/deploy-k8s.md8### Step 1: Clone the big-AGI repositoryCOMMENT
LOWdocs/deploy-k8s.md15### Step 2: Create the namespaceCOMMENT
LOWdocs/deploy-k8s.md21### Step 3: Fill in the key information into env-secret.yamlCOMMENT
LOWdocs/deploy-k8s.md34### Step 4: Deploying Kubernetes ResourcesCOMMENT
LOWdocs/deploy-k8s.md40### Step 5: Verifying the Resource StatusesCOMMENT
LOWdocs/deploy-k8s.md54### Step 6: Testing the ServiceCOMMENT
LOW…ocks/enhanced-code/livefile-patch/useLiveFilePatch.tsx40 // // Step 1: Load the latest version of the fileCOMMENT
LOW…ocks/enhanced-code/livefile-patch/useLiveFilePatch.tsx45 // // Step 2: Generate patchCOMMENT
LOW…ocks/enhanced-code/livefile-patch/useLiveFilePatch.tsx50 // // Step 3: Apply patch and check if it succeedsCOMMENT
LOW…ocks/enhanced-code/livefile-patch/useLiveFilePatch.tsx53 // // Step 4: Success - user can decide to proceedCOMMENT
LOW…atch/wiretypes/_upstream/gemini.deep-research.guide.md115### Step 1: Request a planCOMMENT
LOW…atch/wiretypes/_upstream/gemini.deep-research.guide.md178### Step 2: Refine the plan (optional)COMMENT
LOW…atch/wiretypes/_upstream/gemini.deep-research.guide.md240### Step 3: Approve and executeCOMMENT
Modern AI Meta-Vocabulary10 hits · 26 pts
SeverityFileLineSnippetContext
MEDIUMsrc/common/stores/chat/chat.message.ts30 // Session metadata for multi-turn agentic sessions was considered here (see commit 3cd38f47)COMMENT
MEDIUMsrc/common/stores/llms/model.domains.editorial.ts91 { vendor: 'openai', modelId: 'gpt-5.6-sol' }, // 2026-07-09 GA - "strongest yet for agentic coding"; codex stillCODE
MEDIUMsrc/modules/llms/server/gemini/gemini.models.ts247 // First "point one" update - introduces 'medium' thinking level, improved agentic codingCOMMENT
MEDIUMsrc/modules/llms/server/openai/models/cohere.models.ts37// chatPrice is set only where Cohere publishes per-token prices; newer/agentic models areCOMMENT
MEDIUMsrc/modules/llms/server/openai/models/cohere.models.ts97 // North Mini Code - agentic coding (North platform)COMMENT
MEDIUM…c/modules/llms/server/openai/models/cerebras.models.ts74 // Z.ai GLM 4.7 - agentic coding, strong tool use (~1,000 tok/s). Preview.COMMENT
MEDIUMsrc/modules/llms/server/openai/models/alibaba.models.ts75 interfaces: [LLM_IF_OAI_Chat, LLM_IF_OAI_Fn], // coding/agentic; non-thinkingCODE
MEDIUMsrc/modules/llms/server/openai/models/openai.models.ts25 // on a trivial prompt); each request adds ~1.7K billed input tokens of orchestration scaffold; background mode suCOMMENT
MEDIUM…atch/wiretypes/_upstream/gemini.deep-research.guide.md1109Pricing follows a [pay-as-you-go model](https://ai.google.dev/gemini-api/docs/pricing#pricing-for-agents) based on the uCODE
MEDIUM…atch/wiretypes/_upstream/gemini.deep-research.guide.md1109Pricing follows a [pay-as-you-go model](https://ai.google.dev/gemini-api/docs/pricing#pricing-for-agents) based on the uCODE
Synthetic Comment Markers3 hits · 20 pts
SeverityFileLineSnippetContext
HIGHtools/develop/worktrees/create-dev-worktree.sh275# Handle --materialize flag: bring an EXISTING worktree (e.g. created by an AICOMMENT
HIGH…ules/aix/server/dispatch/wiretypes/openai.wiretypes.ts917 // Control the content-moderation level for images generated by GPT Image models.COMMENT
HIGH…/message/fragments-content/BlockPartHostedResource.tsx219 From now on, files generated by Claude tools (code execution, etc.) will be automatically downloaded and embedCODE
Decorative Section Separators5 hits · 15 pts
SeverityFileLineSnippetContext
MEDIUMtools/develop/gen-icon-sprites/generate-llm-sprites.ts34// ── Step 1: Parse vendor registry (vendorId → component name → file) ──────────COMMENT
MEDIUMtools/develop/gen-icon-sprites/generate-llm-sprites.ts64// ── Step 2: Parse a vendor icon .tsx file ─────────────────────────────────────COMMENT
MEDIUMtools/develop/gen-icon-sprites/generate-llm-sprites.ts99// ── Step 3: Build <symbol> JSX for one vendor ─────────────────────────────────COMMENT
MEDIUMtools/develop/gen-icon-sprites/generate-llm-sprites.ts145// ── Step 4: Generate output by replacing template placeholders ────────────────COMMENT
MEDIUMtools/develop/gen-icon-sprites/generate-llm-sprites.ts165// ── Main ──────────────────────────────────────────────────────────────────────COMMENT
Cross-Language Confusion (JS/TS)3 hits · 15 pts
SeverityFileLineSnippetContext
HIGHsrc/modules/3rdparty/aider/wholeFilePrompts.ts56 print(f"Hey {{name}}")CODE
HIGHsrc/modules/3rdparty/aider/editBlockPrompts.ts159 print("hello")CODE
HIGHsrc/modules/3rdparty/aider/editBlockPrompts.ts169 print("hello")CODE
Redundant / Tautological Comments7 hits · 10 pts
SeverityFileLineSnippetContext
LOWtools/develop/worktrees/create-dev-worktree.sh407 # Check if trying to remove the main branchCOMMENT
LOWtools/develop/worktrees/create-dev-worktree.sh456 # Check if branch existsCOMMENT
LOWtools/develop/worktrees/create-dev-worktree.sh654# Check if branch already existsCOMMENT
LOWtools/develop/worktrees/create-dev-worktree.sh662# Check if worktree already existsCOMMENT
LOWtools/ai/repo-structure.sh31# Check if we're in a git repositoryCOMMENT
LOWtools/ai/repo-structure.sh76 # Check if TMP_FILE is empty after filteringCOMMENT
LOWtools/ai/repo-structure.sh117 # Check if we've already processed this directoryCOMMENT
Verbosity Indicators4 hits · 9 pts
SeverityFileLineSnippetContext
LOW…ocks/enhanced-code/livefile-patch/useLiveFilePatch.tsx40 // // Step 1: Load the latest version of the fileCOMMENT
LOW…ocks/enhanced-code/livefile-patch/useLiveFilePatch.tsx45 // // Step 2: Generate patchCOMMENT
LOW…ocks/enhanced-code/livefile-patch/useLiveFilePatch.tsx50 // // Step 3: Apply patch and check if it succeedsCOMMENT
LOW…ocks/enhanced-code/livefile-patch/useLiveFilePatch.tsx53 // // Step 4: Success - user can decide to proceedCOMMENT
Self-Referential Comments2 hits · 6 pts
SeverityFileLineSnippetContext
MEDIUMtools/develop/worktrees/create-dev-worktree.sh685# Create the worktree with a new branch at the selected source refCOMMENT
MEDIUMdocs/docker/docker-compose-browserless.yaml1# This file is used to run `big-AGI` and `browserless` with Docker Compose.COMMENT
TODO Padding4 hits · 6 pts
SeverityFileLineSnippetContext
LOWsrc/common/stores/chat/chat.tokens.ts64 // TODO: implement this properly - as we don't have resolutions in the part(!) - and this could be really expensCOMMENT
LOWsrc/common/stores/chat/chat.tokens.ts85 // TODO: implement this properly - as we don't have resolutions in the part(!) - and this could be really expensCOMMENT
LOW…erver/dispatch/chatGenerate/ChatGenerateTransmitter.ts68 // TODO: implement throttling on a particle basisCOMMENT
LOW…c/modules/aix/client/aix.client.chatGenerateRequest.ts570 // TODO: implement mid-chat system messages if neededCOMMENT
Magic Placeholder Names1 hit · 5 pts
SeverityFileLineSnippetContext
HIGHdocs/config-azure-openai.md32AZURE_OPENAI_API_KEY=your-api-keyCODE
AI Slop Vocabulary2 hits · 5 pts
SeverityFileLineSnippetContext
MEDIUMsrc/common/util/webGeolocationUtils.ts130 // TODO: use a robust geocoding serviceCOMMENT
MEDIUM…patch/chatGenerate/adapters/anthropic.messageCreate.ts17const hotFixAntSeparateContiguousThinkingBlocks = true; // Interleave continuous thinking blocks (without aText) with thCODE
Example Usage Blocks2 hits · 3 pts
SeverityFileLineSnippetContext
LOWtools/develop/aix-gemini-antigravity-probe/examples.sh5# Usage:COMMENT
LOWsrc/common/util/idbUtils.ts314// Example usage:COMMENT
Fake / Example Data1 hit · 1 pts
SeverityFileLineSnippetContext
LOWsrc/apps/chat/components/composer/Composer.tsx934 <span className={speechInterimResult.interimTranscript === PLACEHOLDER_INTERIM_TRANSCRIPT ? 'placeCODE