Repository Analysis

withastro/flue

The sandbox agent framework.

4.6 Likely human-written View on GitHub

Analysis Overview

This report presents the forensic synthetic code analysis of withastro/flue, a TypeScript project with 7,275 GitHub stars. SynthScan v2.0 examined 179,745 lines of code across 1004 source files, recording 397 pattern matches distributed across 10 syntactic categories. The overall adjusted score of 4.6 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).

4.6
Adjusted Score
4.6
Raw Score
100%
Time Factor
2026-07-13
Last Push
7.3K
Stars
TypeScript
Language
179.7K
Lines of Code
1.0K
Files
397
Pattern Hits
2026-07-14
Scan Date
0.00
HC Hit Rate

What These Metrics Mean

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

Score History

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

Severity Breakdown

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

CRITICAL 1HIGH 2MEDIUM 204LOW 190

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 397 distinct pattern matches across 10 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.

Decorative Section Separators201 hits · 603 pts
SeverityFileLineSnippetContext
MEDIUM.flue/workflows/pr-redirect.ts58// ─── Types ──────────────────────────────────────────────────────────────────COMMENT
MEDIUM.flue/workflows/pr-redirect.ts96// ─── Step 0: fetch PR via `gh` ──────────────────────────────────────────────COMMENT
MEDIUM.flue/workflows/pr-redirect.ts140// ─── Step 1: classify ───────────────────────────────────────────────────────COMMENT
MEDIUM.flue/workflows/pr-redirect.ts187// ─── Step 2 & 3: duplicate search ───────────────────────────────────────────COMMENT
MEDIUM.flue/workflows/pr-redirect.ts378// ─── Body composition ───────────────────────────────────────────────────────COMMENT
MEDIUM.flue/workflows/pr-redirect.ts516// ─── Misc ───────────────────────────────────────────────────────────────────COMMENT
MEDIUM.flue/workflows/pr-redirect.ts572// ─── Entry point ────────────────────────────────────────────────────────────COMMENT
MEDIUM.flue/workflows/pr-redirect.ts597 // ─── LLM phase ──────────────────────────────────────────────────────COMMENT
MEDIUM.flue/workflows/pr-redirect.ts632 // ─── Build the Decision ─────────────────────────────────────────────COMMENT
MEDIUM.flue/workflows/pr-redirect.ts657 // ─── Deterministic phase ────────────────────────────────────────────COMMENT
MEDIUM.flue/lib/github.ts77// ─── REST writes ────────────────────────────────────────────────────────────COMMENT
MEDIUM.flue/lib/github.ts122// ─── GraphQL: discussions ───────────────────────────────────────────────────COMMENT
MEDIUMexamples/cloudflare/src/app.ts17// ─── Cloudflare AI Gateway (optional) ───────────────────────────────────────COMMENT
MEDIUMexamples/hello-world/src/sandboxes/daytona.ts26// ─── DaytonaSandboxApi ──────────────────────────────────────────────────────COMMENT
MEDIUMexamples/hello-world/src/sandboxes/daytona.ts118// ─── Sandbox Adapter ────────────────────────────────────────────────────────COMMENT
MEDIUMexamples/sentry/src/app.ts75// ─── 1. Sentry init ─────────────────────────────────────────────────────────COMMENT
MEDIUMexamples/sentry/src/app.ts94// ─── 2. The Flue → Sentry event bridge ──────────────────────────────────────COMMENT
MEDIUMexamples/sentry/src/app.ts152// ─── Helpers ────────────────────────────────────────────────────────────────COMMENT
MEDIUMexamples/sentry/src/app.ts207// ─── 3. Mount the Flue agent route ──────────────────────────────────────────COMMENT
MEDIUMpackages/runtime/test/submission-state.test.ts8// ─── Helpers ────────────────────────────────────────────────────────────────COMMENT
MEDIUMpackages/runtime/test/submission-state.test.ts43// ─── Tests ──────────────────────────────────────────────────────────────────COMMENT
MEDIUM…es/runtime/test/agent-execution-store-contract.test.ts27// ─── Backend factories ──────────────────────────────────────────────────────COMMENT
MEDIUM…es/runtime/test/agent-execution-store-contract.test.ts73// ─── Contract tests (shared) ────────────────────────────────────────────────COMMENT
MEDIUM…es/runtime/test/agent-execution-store-contract.test.ts83// ─── sqlite() PersistenceAdapter tests ──────────────────────────────────────COMMENT
MEDIUMpackages/runtime/test/node-agent-coordinator.test.ts1576 // ─── Direct prompt admission ────────────────────────────────────────────COMMENT
MEDIUMpackages/runtime/test/node-agent-coordinator.test.ts1774 // ─── Real Anthropic API smoke (integration) ─────────────────────────────COMMENT
MEDIUMpackages/runtime/src/errors.ts103// ─── Helpers ────────────────────────────────────────────────────────────────COMMENT
MEDIUMpackages/runtime/src/errors.ts118// ─── Base classes ───────────────────────────────────────────────────────────COMMENT
MEDIUMpackages/runtime/src/errors.ts222// ─── HTTP-layer error vocabulary ────────────────────────────────────────────COMMENT
MEDIUMpackages/runtime/src/errors.ts433// ─── Persistence error vocabulary ───────────────────────────────────────────COMMENT
MEDIUMpackages/runtime/src/errors.ts548// ─── Sandbox error vocabulary ───────────────────────────────────────────────COMMENT
MEDIUMpackages/runtime/src/errors.ts582// ─── Session error vocabulary ───────────────────────────────────────────────COMMENT
MEDIUMpackages/runtime/src/errors.ts1138// ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━COMMENT
MEDIUMpackages/runtime/src/errors.ts1140// ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━COMMENT
MEDIUMpackages/runtime/src/compaction.ts24// ─── Settings ───────────────────────────────────────────────────────────────COMMENT
MEDIUMpackages/runtime/src/compaction.ts74// ─── Token Estimation ───────────────────────────────────────────────────────COMMENT
MEDIUMpackages/runtime/src/compaction.ts181// ─── File Operation Tracking ────────────────────────────────────────────────COMMENT
MEDIUMpackages/runtime/src/compaction.ts236// ─── Message Serialization ──────────────────────────────────────────────────COMMENT
MEDIUMpackages/runtime/src/compaction.ts300// ─── Summarization Prompts ──────────────────────────────────────────────────COMMENT
MEDIUMpackages/runtime/src/compaction.ts392// ─── Cut Point Detection ────────────────────────────────────────────────────COMMENT
MEDIUMpackages/runtime/src/compaction.ts459// ─── Compaction Preparation ─────────────────────────────────────────────────COMMENT
MEDIUMpackages/runtime/src/compaction.ts558// ─── Summary Generation ─────────────────────────────────────────────────────COMMENT
MEDIUMpackages/runtime/src/compaction.ts659// ─── Main Compaction Function ───────────────────────────────────────────────COMMENT
MEDIUMpackages/runtime/src/agent.ts506// ─── Helpers ────────────────────────────────────────────────────────────────COMMENT
MEDIUMpackages/runtime/src/context.ts25// ─── Context Discovery ──────────────────────────────────────────────────────COMMENT
MEDIUMpackages/runtime/src/adapter-helpers.ts46// ─── Payload validation ─────────────────────────────────────────────────────COMMENT
MEDIUMpackages/runtime/src/adapter-helpers.ts91// ─── Submission admission ───────────────────────────────────────────────────COMMENT
MEDIUMpackages/runtime/src/adapter-helpers.ts233// ─── Timestamp parsing ──────────────────────────────────────────────────────COMMENT
MEDIUMpackages/runtime/src/adapter-helpers.ts247// ─── Limit clamping ──────────────────────────────────────────────────────────COMMENT
MEDIUMpackages/runtime/src/result.ts130// ─── Result tools ───────────────────────────────────────────────────────────COMMENT
MEDIUMpackages/runtime/src/result.ts331// ─── Helpers ────────────────────────────────────────────────────────────────COMMENT
MEDIUMpackages/runtime/src/result.ts373// ─── Errors ─────────────────────────────────────────────────────────────────COMMENT
MEDIUMpackages/runtime/src/agent-execution-store.ts18// ─── Durability defaults ────────────────────────────────────────────────────COMMENT
MEDIUMpackages/runtime/src/agent-execution-store.ts27// ─── Submission ─────────────────────────────────────────────────────────────COMMENT
MEDIUMpackages/runtime/src/agent-execution-store.ts101// ─── Dispatch admission ─────────────────────────────────────────────────────COMMENT
MEDIUMpackages/runtime/src/agent-execution-store.ts113// ─── Submission store ───────────────────────────────────────────────────────COMMENT
MEDIUMpackages/runtime/src/agent-execution-store.ts278// ─── Execution store ────────────────────────────────────────────────────────COMMENT
MEDIUMpackages/runtime/src/agent-execution-store.ts284// ─── Persistence adapter ────────────────────────────────────────────────────COMMENT
MEDIUMpackages/runtime/src/types.ts117// ─── Skill ──────────────────────────────────────────────────────────────────COMMENT
MEDIUMpackages/runtime/src/types.ts148// ─── File Stat ──────────────────────────────────────────────────────────────COMMENT
141 more matches not shown…
Hyper-Verbose Identifiers167 hits · 170 pts
SeverityFileLineSnippetContext
LOWdemo/src/components/chat/message-list.tsx85function abortAdvisorySubmissionId(message: FlueConversationMessage): string | undefined {CODE
LOWblueprints/sandbox--cloudflare-shell.md110function createWorkspaceSessionEnv(CODE
LOWblueprints/channel--salesforce-marketing-cloud.md56export function createSalesforceMarketingCloudClient({CODE
LOWblueprints/channel--salesforce-marketing-cloud.md106export function salesforceMarketingCloudRestOrigin(value: string): string {CODE
LOWblueprints/channel--discord.md105function destinationFromInteraction(interaction: APIInteraction): DiscordDestinationRef | undefined {CODE
LOW.flue/workflows/pr-redirect.ts386function originalImplementationLine(pr: PrDetails): string {CODE
LOWexamples/shopify-channel/src/channels/shopify.ts90export function parseShopifyOrderInstanceId(id: string): ShopifyOrderRef {CODE
LOWexamples/cloudflare/src/sandboxes/cloudflare-shell.ts115function createWorkspaceSessionEnv(CODE
LOWexamples/stripe-channel/src/channels/stripe.ts88export function parseStripeCustomerInstanceId(id: string): StripeCustomerRef {CODE
LOW…-cloud-channel/src/salesforce-marketing-cloud-email.ts57export function parseEmailEventInstanceId(id: string): SalesforceMarketingCloudEmailRef {CODE
LOW…cloud-channel/src/salesforce-marketing-cloud-client.ts20export function createSalesforceMarketingCloudClient({CODE
LOW…cloud-channel/src/salesforce-marketing-cloud-client.ts67export function salesforceMarketingCloudRestOrigin(restBaseUrl: string): string {CODE
LOWexamples/discord-channel/src/channels/discord.ts69function destinationFromInteraction(CODE
LOWpackages/opentelemetry/src/index.ts66export function createOpenTelemetryInstrumentation(CODE
LOWpackages/google-chat/src/index.ts291function validateInteractionAuthentication(CODE
LOWpackages/google-chat/src/index.ts316function validatePubSubAuthentication(authentication: GoogleChatPubSubAuthentication): void {CODE
LOWpackages/google-chat/src/auth.ts84export function createInteractionTokenVerifier(CODE
LOWpackages/google-chat/src/auth.ts119export function createPubSubTokenVerifier(CODE
LOW…es/runtime/test/agent-execution-store-contract.test.ts36function createCloudflareSqlBackend(): AgentExecutionStore {CODE
LOW…ckages/runtime/test/helpers/test-event-stream-store.ts9export function createTestEventStreamStore(CODE
LOWpackages/runtime/src/conversation-public.ts114export function projectAgentConversationSnapshot(CODE
LOWpackages/runtime/src/conversation-public.ts129export function projectAgentConversationBatch(options: {CODE
LOWpackages/runtime/src/persisted-images.ts46export function extractSubmissionAttachments(CODE
LOWpackages/runtime/src/persisted-images.ts63export function hydrateSubmissionAttachments(CODE
LOWpackages/runtime/src/conversation-projections.ts153export function classifyConversationSubmission(CODE
LOWpackages/runtime/src/conversation-projections.ts211export function getActiveConversationPathSince(CODE
LOWpackages/runtime/src/conversation-projections.ts221export function aggregateConversationUsageSince(CODE
LOWpackages/runtime/src/conversation-projections.ts239export function getLatestConversationCompaction(CODE
LOWpackages/runtime/src/conversation-projections.ts247export function projectConversationModelContext(CODE
LOWpackages/runtime/src/conversation-projections.ts254export function projectConversationModelContextEntries(CODE
LOWpackages/runtime/src/conversation-projections.ts334function materializeInterruptedAssistant(message: InProgressAssistantMessage): AssistantMessage {CODE
LOWpackages/runtime/src/tool.ts102export async function validateAndRunTool<TTool extends ToolDefinition>(CODE
LOWpackages/runtime/src/execution-interceptor.ts55export function registerExecutionInterceptor(interceptor: FlueExecutionInterceptor): () => void {CODE
LOWpackages/runtime/src/tool-adapter.ts14export function registerPreparedToolAdapter(CODE
LOWpackages/runtime/src/compaction.ts94function getLastAssistantUsageInfo(CODE
LOWpackages/runtime/src/compaction.ts193function extractFileOpsFromMessage(message: AgentMessage, fileOps: FileOps): void {CODE
LOWpackages/runtime/src/compaction.ts612async function generateTurnPrefixSummary(CODE
LOWpackages/runtime/src/agent.ts59export function createPackagedSkillReadTool(CODE
LOWpackages/runtime/src/agent.ts560export function formatPackagedSkillFilePath(skillId: string, filePath: string): string {CODE
LOWpackages/runtime/src/mcp.ts93export async function connectMcpServerWithClient(CODE
LOWpackages/runtime/src/sql-persisted-chunk-store.ts9export function ensureSqlPersistedChunkTable(sql: SqlStorage): void {CODE
LOWpackages/runtime/src/sql-persisted-chunk-store.ts24export function createSqlPersistedChunkStore(sql: SqlStorage): PersistedChunkStore {CODE
LOWpackages/runtime/src/event-redaction.ts77export function redactObservationDetailImages(CODE
LOWpackages/runtime/src/submission-state.ts244export function findTrailingPartialToolBatch(CODE
LOWpackages/runtime/src/submission-state.ts302function isCompletedAssistantResponse(message: AssistantMessage): boolean {CODE
LOWpackages/runtime/src/submission-state.ts306export function countConsecutiveRetryableModelErrors(CODE
LOWpackages/runtime/src/result.ts29export function buildResultFollowUpPrompt(): string {CODE
LOWpackages/runtime/src/result.ts79export function buildWorkspaceSkillPrompt(CODE
LOWpackages/runtime/src/result.ts102export function buildSkillByPathlessNamePrompt(CODE
LOWpackages/runtime/src/agent-definition.ts102export function assertResolvedAgentProfile(profile: AgentProfile, label: string): AgentProfile {CODE
LOWpackages/runtime/src/action.ts149export async function validateAndRunAction<TAction extends ActionDefinition>(CODE
LOWpackages/runtime/src/skill-package.ts51export function getSkillReferenceDirectory(CODE
LOWpackages/runtime/src/conversation-records.ts277export function generateConversationRecordId(): string {CODE
LOWpackages/runtime/src/conversation-records.ts281export function generateConversationEntryId(): string {CODE
LOWpackages/runtime/src/conversation-reader.ts8export async function loadReducedConversationState(options: {CODE
LOWpackages/runtime/src/conversation-reader.ts24export async function loadReducedConversationPrefix(options: {CODE
LOWpackages/runtime/src/session.ts376function getRegisteredPackagedSkills(CODE
LOWpackages/runtime/src/client.ts223async function createLocalConversationRuntime(config: FlueContextConfig): Promise<{CODE
LOWpackages/runtime/src/conversation-reducer.ts170export function createReducedInstanceState(): ReducedInstanceState {CODE
LOWpackages/runtime/src/conversation-reducer.ts179export function reduceConversationRecords(CODE
107 more matches not shown…
Over-Commented Block14 hits · 14 pts
SeverityFileLineSnippetContext
LOWexamples/cloudflare/seed-r2.sh1#!/usr/bin/env bashCOMMENT
LOWexamples/cloudflare/src/app.ts21// gateway, override caching, attach metadata) — or to opt out entirely —COMMENT
LOWexamples/cloudflare/src/app.ts41// api: 'cloudflare-ai-binding',COMMENT
LOWexamples/cloudflare/src/app.ts61// behind your own auth middleware:COMMENT
LOWexamples/hello-world/src/app.ts41COMMENT
LOWexamples/slack-channel/src/channels/slack.ts41 // Path: /channels/slack/interactionsCOMMENT
LOWpackages/runtime/tsdown.config.ts21 // `cloudflare:workers` is a virtual module that only resolvesCOMMENT
LOWpackages/runtime/src/errors.ts581COMMENT
LOWpackages/runtime/src/agent.ts201 parameters: BashParams,COMMENT
LOWpackages/runtime/src/index.ts161// FlueContextConfig/FlueContextInternal types are intentionally NOT re-exportedCOMMENT
LOWpackages/runtime/src/runtime/agent-submissions.ts341 // append, so a reconciler that loses the CAS never mutates session history.COMMENT
LOWpackages/sdk/src/public/stream.ts121 warnOnHttp: false,COMMENT
LOWpackages/react/src/types.ts1// Flue's conversation message types are owned by @flue/sdk and consumedCOMMENT
LOW.github/workflows/pr-redirect.yml1name: PR RedirectCOMMENT
Hallucination Indicators1 hit · 10 pts
SeverityFileLineSnippetContext
CRITICAL.github/workflows/pr-redirect.yml47 const author = context.payload.pull_request.user.login.toLowerCase();CODE
Magic Placeholder Names2 hits · 10 pts
SeverityFileLineSnippetContext
HIGHapps/docs/src/content/docs/ecosystem/deploy/node.md74OPENAI_API_KEY="your-api-key"CODE
HIGH…s/docs/src/content/docs/ecosystem/deploy/cloudflare.md126ANTHROPIC_API_KEY="your-api-key"CODE
Verbosity Indicators4 hits · 8 pts
SeverityFileLineSnippetContext
LOWapps/www/src/pages/start.md.ts20## Step 1: Gather ContextCOMMENT
LOWapps/www/src/pages/start.md.ts27## Step 2: Discover RequirementsCOMMENT
LOWapps/www/src/pages/start.md.ts71## Step 3: Build the Smallest Useful Starter ProjectCOMMENT
LOWapps/www/src/pages/start.md.ts105## Step 4: Verify ImplementationCOMMENT
Structural Annotation Overuse4 hits · 8 pts
SeverityFileLineSnippetContext
LOWapps/www/src/pages/start.md.ts20## Step 1: Gather ContextCOMMENT
LOWapps/www/src/pages/start.md.ts27## Step 2: Discover RequirementsCOMMENT
LOWapps/www/src/pages/start.md.ts71## Step 3: Build the Smallest Useful Starter ProjectCOMMENT
LOWapps/www/src/pages/start.md.ts105## Step 4: Verify ImplementationCOMMENT
Modern AI Meta-Vocabulary2 hits · 6 pts
SeverityFileLineSnippetContext
MEDIUM…ps/docs/src/content/docs/ecosystem/deploy/gitlab-ci.md286## Typed results and orchestrationCOMMENT
MEDIUM…cs/src/content/docs/ecosystem/deploy/github-actions.md272## Typed results and orchestrationCOMMENT
AI Slop Vocabulary1 hit · 3 pts
SeverityFileLineSnippetContext
MEDIUMpackages/runtime/src/runtime/agent-submissions.ts572 // Abort: keyed on the coordinator signal's reason (robust even when theCOMMENT
Example Usage Blocks1 hit · 2 pts
SeverityFileLineSnippetContext
LOWexamples/cloudflare/seed-r2.sh8# Usage:COMMENT