Repository Analysis

tashfeenahmed/freellmapi

7.4 billion tokens per month. 34 free LLM providers. 635 free model endpoints. All behind one /v1 endpoint, plus any custom OpenAI-compatible endpoint. Smart routing, automatic failover, encrypted keys. Personal experimentation only.

3.8 Likely human-written View on GitHub

Analysis Overview

This report presents the forensic synthetic code analysis of tashfeenahmed/freellmapi, a TypeScript project with 21,587 GitHub stars. SynthScan v2.0 examined 214,591 lines of code across 683 source files, recording 519 pattern matches distributed across 10 syntactic categories. The overall adjusted score of 3.8 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).

3.8
Adjusted Score
3.8
Raw Score
100%
Time Factor
2026-08-28
Last Push
21.6K
Stars
TypeScript
Language
214.6K
Lines of Code
683
Files
519
Pattern Hits
2026-08-29
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 0HIGH 3MEDIUM 144LOW 372

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 519 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 Separators129 hits · 388 pts
SeverityFileLineSnippetContext
MEDIUMdesktop/src/main.ts94 // ── popover IPC ──────────────────────────────────────────────────────────COMMENT
MEDIUMserver/src/providers/index.ts438// ── Chinese domestic providers (#922/#923/#924) ─────────────────────────────COMMENT
MEDIUMserver/src/providers/index.ts438// ── Chinese domestic providers (#922/#923/#924) ─────────────────────────────COMMENT
MEDIUMserver/src/__tests__/providers/google.test.ts627 // ── Streaming ──────────────────────────────────────────────────────────────COMMENT
MEDIUMserver/src/__tests__/providers/google.test.ts726 // ── timeoutMs plumbing ────────────────────────────────────────────────────COMMENT
MEDIUMserver/src/__tests__/lib/exhaustion-statuses.test.ts71// ── isContextTooLargeError: real provider error shapes ───────────────────────COMMENT
MEDIUMserver/src/__tests__/lib/exhaustion-statuses.test.ts143// ── exhaustedRetryError: failure-kind → terminal-status taxonomy ─────────────COMMENT
MEDIUMserver/src/__tests__/lib/exhaustion-statuses.test.ts261// ── routingExhaustionBody: zero attempts ran ─────────────────────────────────COMMENT
MEDIUMserver/src/__tests__/lib/exhaustion-statuses.test.ts341// ── Wire helpers: OpenAI error payload + Retry-After header ──────────────────COMMENT
MEDIUMserver/src/__tests__/lib/exhaustion-statuses.test.ts377// ── End-to-end through the shared loop ───────────────────────────────────────COMMENT
MEDIUMserver/src/__tests__/routes/routing-semantics.test.ts232// ── #919: remaining-quota key selection ─────────────────────────────────────COMMENT
MEDIUMserver/src/__tests__/routes/routing-semantics.test.ts232// ── #919: remaining-quota key selection ─────────────────────────────────────COMMENT
MEDIUMserver/src/__tests__/routes/logs.test.ts86 // ── Capture ────────────────────────────────────────────────────────────────COMMENT
MEDIUMserver/src/__tests__/routes/logs.test.ts156 // ── Structured events ──────────────────────────────────────────────────────COMMENT
MEDIUMserver/src/__tests__/routes/logs.test.ts198 // ── Storage ────────────────────────────────────────────────────────────────COMMENT
MEDIUMserver/src/__tests__/routes/logs.test.ts248 // ── API ────────────────────────────────────────────────────────────────────COMMENT
MEDIUMserver/src/__tests__/routes/logs.test.ts365 // ── Auth ───────────────────────────────────────────────────────────────────COMMENT
MEDIUMserver/src/__tests__/routes/logs.test.ts376 // ── Retention ──────────────────────────────────────────────────────────────COMMENT
MEDIUMserver/src/__tests__/routes/anthropic.test.ts516 // ── Same-model cross-provider failover (#932) ────────────────────────────COMMENT
MEDIUMserver/src/__tests__/routes/anthropic.test.ts516 // ── Same-model cross-provider failover (#932) ────────────────────────────COMMENT
MEDIUMserver/src/lib/provider-identity.ts1// ── Provider identity for analytics ─────────────────────────────────────────COMMENT
MEDIUMserver/src/lib/fallback-loop.ts61// ── Model-level failure benching ─────────────────────────────────────────────COMMENT
MEDIUMserver/src/lib/fallback-loop.ts115// ── Wall-clock retry budget ──────────────────────────────────────────────────COMMENT
MEDIUMserver/src/lib/fallback-loop.ts222// ── Empty-completion streak (issue #751) ─────────────────────────────────────COMMENT
MEDIUMserver/src/lib/fallback-loop.ts222// ── Empty-completion streak (issue #751) ─────────────────────────────────────COMMENT
MEDIUMserver/src/lib/fallback-loop.ts342// ── Upstream 401 handling (key-fatal, not request-fatal) ─────────────────────COMMENT
MEDIUMserver/src/lib/fallback-loop.ts402// ── Attempt trail ─────────────────────────────────────────────────────────────COMMENT
MEDIUMserver/src/lib/fallback-loop.ts461// ── Detailed failover trace header (opt-in) ──────────────────────────────────COMMENT
MEDIUMserver/src/lib/fallback-loop.ts801// ── Routing exhaustion (zero attempts ran) ───────────────────────────────────COMMENT
MEDIUMserver/src/lib/guardrails.ts58// ── Token budget (pre-flight) ────────────────────────────────────────────────COMMENT
MEDIUMserver/src/lib/server-logs.ts87// ── State ────────────────────────────────────────────────────────────────────COMMENT
MEDIUMserver/src/lib/server-logs.ts112// ── Formatting ───────────────────────────────────────────────────────────────COMMENT
MEDIUMserver/src/lib/server-logs.ts149// ── Ingest ───────────────────────────────────────────────────────────────────COMMENT
MEDIUMserver/src/lib/server-logs.ts256// ── Persistence ──────────────────────────────────────────────────────────────COMMENT
MEDIUMserver/src/lib/server-logs.ts395// ── Read side ────────────────────────────────────────────────────────────────COMMENT
MEDIUMserver/src/lib/sampling-params.ts190// ── Per-platform support policy ──────────────────────────────────────────────COMMENT
MEDIUMserver/src/lib/sampling-params.ts365// ── Unified output-token cap ─────────────────────────────────────────────────COMMENT
MEDIUMserver/src/lib/endpoint-scope.ts1// ── Endpoint identity for custom relay models (#651) ────────────────────────COMMENT
MEDIUMserver/src/lib/endpoint-scope.ts1// ── Endpoint identity for custom relay models (#651) ────────────────────────COMMENT
MEDIUMserver/src/lib/error-classify.ts113// ── Transport failures hidden in the cause chain (undici) ────────────────────COMMENT
MEDIUMserver/src/lib/error-classify.ts229// ── Timeout wording ─────────────────────────────────────────────────────────COMMENT
MEDIUMserver/src/lib/error-classify.ts253// ── Client-caused aborts ─────────────────────────────────────────────────────COMMENT
MEDIUMserver/src/lib/error-classify.ts279// ── Fallback time-budget hedging (fallback-v2) ──────────────────────────────COMMENT
MEDIUMserver/src/lib/error-classify.ts554// ── Permanent upstream retirement (issue #634) ───────────────────────────────COMMENT
MEDIUMserver/src/lib/error-classify.ts554// ── Permanent upstream retirement (issue #634) ───────────────────────────────COMMENT
MEDIUMserver/src/routes/fallback.ts22// ── Bandit routing strategy ─────────────────────────────────────────────────COMMENT
MEDIUMserver/src/routes/anthropic.ts53// ── Request schema ──────────────────────────────────────────────────────────COMMENT
MEDIUMserver/src/routes/anthropic.ts132// ── Response shape ──────────────────────────────────────────────────────────COMMENT
MEDIUMserver/src/routes/anthropic.ts194// ── Auth (shared with the OpenAI route) ─────────────────────────────────────COMMENT
MEDIUMserver/src/routes/anthropic.ts205// ── Request translation: Anthropic → internal (OpenAI-shaped) ───────────────COMMENT
MEDIUMserver/src/routes/anthropic.ts381// ── Response translation: internal → Anthropic ──────────────────────────────COMMENT
MEDIUMserver/src/routes/anthropic.ts417// ── SSE helpers ─────────────────────────────────────────────────────────────COMMENT
MEDIUMserver/src/routes/mcp.ts12// ─────────────────────────────────────────────────────────────────────────COMMENT
MEDIUMserver/src/routes/mcp.ts30// ─────────────────────────────────────────────────────────────────────────COMMENT
MEDIUMserver/src/routes/mcp.ts66// ── Tool implementations ─────────────────────────────────────────────────COMMENT
MEDIUMserver/src/routes/mcp.ts187// ── Tool registry ────────────────────────────────────────────────────────COMMENT
MEDIUMserver/src/routes/mcp.ts249// ── JSON-RPC dispatch ────────────────────────────────────────────────────COMMENT
MEDIUMserver/src/routes/keys.ts611// ── Custom OpenAI-compatible providers (#117, #212) ───────────────────────COMMENT
MEDIUMserver/src/routes/keys.ts611// ── Custom OpenAI-compatible providers (#117, #212) ───────────────────────COMMENT
MEDIUMserver/src/routes/proxy.ts1618 // ── Fusion: multi-model synthesis ──────────────────────────────────────────COMMENT
69 more matches not shown…
Over-Commented Block201 hits · 192 pts
SeverityFileLineSnippetContext
LOWdesktop/src/server-host.ts41// This function mirrors the boot sequence of server/src/index.ts — everyCOMMENT
LOWdesktop/src/server-host.ts81 // password is random and never shown), so password re-verification forCOMMENT
LOWdesktop/src/logger.ts1// A file log for the desktop app (#824).COMMENT
LOWdesktop/src/preload.ts21COMMENT
LOWdesktop/src/__tests__/version.test.ts1import { readFileSync } from 'node:fs';COMMENT
LOWserver/src/app.ts101 ...cfg.dashboardOrigins,COMMENT
LOWserver/src/app.ts181 // 10MB and used to 413 HERE, before auth/routing: no fallback attempt, noCOMMENT
LOWserver/src/app.ts201 // auth scheme. Its legacy /api/embeddings handler explicitly falls throughCOMMENT
LOWserver/src/app.ts221 const adminRateLimiter = createAdminRateLimiter();COMMENT
LOWserver/src/app.ts281 // OpenAI-compatible proxy. Per-IP rate limiting (#35 item #6) runs first soCOMMENT
LOWserver/src/app.ts301 // like /v1 — NOT behind the dashboard session gate. Same per-IP limiter asCOMMENT
LOWserver/src/app.ts321 if (cfg.serveStaticAssets) {COMMENT
LOWserver/src/middleware/rateLimit.ts1import type { Request, Response, NextFunction } from 'express';COMMENT
LOWserver/src/providers/openai-compat.ts261 // the whitespace between two valid JSON documents.COMMENT
LOWserver/src/providers/google.ts21COMMENT
LOWserver/src/providers/index.ts41 platform: 'bai',COMMENT
LOWserver/src/providers/index.ts61 platform: 'anyapi',COMMENT
LOWserver/src/providers/index.ts121// openai-compat chat routing plus console autodetect: the domesticCOMMENT
LOWserver/src/providers/index.ts141 baseUrl: 'https://router.huggingface.co/v1',COMMENT
LOWserver/src/providers/index.ts181// text.pollinations.ai host returned 502 in the July 2026 audit; publishableCOMMENT
LOWserver/src/providers/index.ts201// adapter as Groq/OpenRouter. A handful of promotional models are free for aCOMMENT
LOWserver/src/providers/index.ts221 platform: 'ovh',COMMENT
LOWserver/src/providers/index.ts241 platform: 'agnes',COMMENT
LOWserver/src/providers/index.ts381// NOT the API); the real API is api.unorouter.com/v1. Free key fromCOMMENT
LOWserver/src/providers/index.ts401// reports free_tokens limit_per_day=5,000,000; paid models answer an instantCOMMENT
LOWserver/src/providers/index.ts421// account-wide. Token from modelscope.cn/my/myaccesstoken, BUT calls only workCOMMENT
LOWserver/src/docs/docs-page.ts1// Self-contained API reference page served at `GET /v1/docs`.COMMENT
LOWserver/src/docs/openapi.ts1// Hand-written OpenAPI 3.0 description of the public `/v1` surface.COMMENT
LOWserver/src/__tests__/lib/module-purity.test.ts1import fs from 'node:fs';COMMENT
LOWserver/src/__tests__/lib/module-purity.test.ts121 it('every listed module actually exists', () => {COMMENT
LOW…_tests__/routes/responses-fallback-convergence.test.ts1import { describe, it, expect, beforeAll, beforeEach, vi } from 'vitest';COMMENT
LOWserver/src/__tests__/routes/rescue-wants-tools.test.ts1import { describe, it, expect, beforeAll, beforeEach, afterEach, vi } from 'vitest';COMMENT
LOWserver/src/__tests__/routes/analytics.test.ts481 // #889 — custom endpoints all share the platform id 'custom', so theCOMMENT
LOWserver/src/__tests__/routes/auth-reset-password.test.ts1import { describe, it, expect, beforeEach, afterAll, vi } from 'vitest';COMMENT
LOWserver/src/__tests__/services/ratelimit.test.ts141 // 1st 429 → transient (no signal yet). Subsequent 429s stay transientCOMMENT
LOWserver/src/__tests__/services/router-bandit.test.ts461 it('a saved intelligence_rank override visibly moves the axis (#673)', () => {COMMENT
LOWserver/src/lib/image-normalize.ts1import type { ChatMessage } from '@freellmapi/shared/types.js';COMMENT
LOWserver/src/lib/image-normalize.ts21// hiccup.COMMENT
LOWserver/src/lib/tool-args.ts1// Schema-aware repair of double-encoded tool-call arguments.COMMENT
LOWserver/src/lib/provider-identity.ts1// ── Provider identity for analytics ─────────────────────────────────────────COMMENT
LOWserver/src/lib/setup-code.ts1import { createOneTimeCode } from './one-time-code.js';COMMENT
LOWserver/src/lib/think-tags.ts1import type { ChatCompletionChunk } from '@freellmapi/shared/types.js';COMMENT
LOWserver/src/lib/header-value.ts1// Header-value sanitizer for the diagnostics headers built out of provider andCOMMENT
LOWserver/src/lib/fallback-loop.ts1// One shared provider retry/fallback loop for every OpenAI-, Responses- andCOMMENT
LOWserver/src/lib/fallback-loop.ts61// ── Model-level failure benching ─────────────────────────────────────────────COMMENT
LOWserver/src/lib/fallback-loop.ts301 if (isModelNotFoundError(err) || isModelAccessForbiddenError(err) || isContextTooLargeError(err) || err?.skipModelForRCOMMENT
LOWserver/src/lib/fallback-loop.ts461// ── Detailed failover trace header (opt-in) ──────────────────────────────────COMMENT
LOWserver/src/lib/fallback-loop.ts801// ── Routing exhaustion (zero attempts ran) ───────────────────────────────────COMMENT
LOWserver/src/lib/fallback-loop.ts901 timedOut: boolean;COMMENT
LOWserver/src/lib/fallback-loop.ts921 // attempt's fetch/body/stream is canceled the moment the client goes; theCOMMENT
LOWserver/src/lib/fallback-loop.ts1101 outcome,COMMENT
LOWserver/src/lib/fallback-loop.ts1141 let outcome: DispatchOutcome;COMMENT
LOWserver/src/lib/fallback-loop.ts1201 // A still-exempt skipBench failure (format ignored, hidden-reasoningCOMMENT
LOWserver/src/lib/guardrails.ts1// Request-level guardrails: two hard limits, both OFF by default so anCOMMENT
LOWserver/src/lib/provider-timeout.ts1// Per-provider HTTP timeout overrides (issue #547, reworked from PR #509).COMMENT
LOWserver/src/lib/content.ts141}COMMENT
LOWserver/src/lib/attempt-trace.ts1// Per-request attempt trace: the durable record of the failover ladder oneCOMMENT
LOWserver/src/lib/attempt-trace.ts21// finish (mid-stream error the surface rendered honestly, orCOMMENT
LOWserver/src/lib/served-model.ts1// Served-model drift guard (#534 follow-up).COMMENT
LOWserver/src/lib/served-model.ts21// differs is treated as drift.COMMENT
141 more matches not shown…
Hyper-Verbose Identifiers99 hits · 100 pts
SeverityFileLineSnippetContext
LOWserver/src/providers/google.ts66function noteDummyThoughtSignature(name: string | undefined): void {CODE
LOWserver/src/providers/modelscope.ts16function modelscopeValidateCacheMs(): number {CODE
LOWserver/src/__tests__/db/migrate/roundtrip.test.ts169function getLatestAppliedMigrationName(db: Database.Database): string {CODE
LOWserver/src/__tests__/db/migrate/roundtrip.test.ts193function getEnabledZenDeadPromoCount(db: Database.Database): number {CODE
LOWserver/src/__tests__/routes/proxy-stream-usage.test.ts89function sseResponseUsageMidStream() {CODE
LOWserver/src/__tests__/routes/proxy-stream-usage.test.ts111function sseResponseUsageOnContentFrame() {CODE
LOWserver/src/__tests__/services/custom-model-sync.test.ts32function addDisabledCustomEndpoint(baseUrl: string, label = 'disabled-endpoint'): void {CODE
LOWserver/src/__tests__/services/catalog-sync.test.ts77function existingAsCatalogEmbeddings(): CatalogEmbedding[] {CODE
LOWserver/src/lib/custom-provider-cleanup.ts31export function deleteUnusedCustomEndpointKey(db: Db, keyId: number | null | undefined) {CODE
LOWserver/src/lib/fallback-loop.ts234export function resetEmptyCompletionStreaks(): void {CODE
LOWserver/src/lib/fallback-loop.ts250function consumeSkipBenchExemption(route: RouteResult, err: any): boolean {CODE
LOWserver/src/lib/fallback-loop.ts483export function isFallbackDetailHeaderEnabled(): boolean {CODE
LOWserver/src/lib/guardrails.ts49export function getRequestMaxTokensBudget(): number {CODE
LOWserver/src/lib/guardrails.ts54export function getMaxConsecutiveUpstreamFails(): number {CODE
LOWserver/src/lib/provider-timeout.ts57export function streamStallTimeoutEnvName(platform: string): string {CODE
LOWserver/src/lib/content.ts113export function truncateMessagesForGithub(CODE
LOWserver/src/lib/crypto.ts178export function isEncryptionKeyInitialized(): boolean {CODE
LOWserver/src/lib/served-model.ts50export function resetServedModelObservations(): void {CODE
LOWserver/src/lib/error-redaction.ts18export function sanitizeProviderErrorMessage(message: unknown): string {CODE
LOWserver/src/lib/tool-validate.ts37export function isToolArgumentValidationEnabled(): boolean {CODE
LOWserver/src/lib/tool-validate.ts151export function invalidToolArgumentsError(displayName: string, reasons: string[]): Error {CODE
LOWserver/src/lib/url-guard.ts144export function isLoopbackOrPrivateHostname(hostname: string): boolean {CODE
LOWserver/src/lib/config.ts30function parseRequestBodyLimitBytes(): number {CODE
LOWserver/src/lib/config.ts84function parseCspUpgradeInsecureRequests(): boolean | undefined {CODE
LOWserver/src/lib/sampling-params.ts402export function platformDropsResponseFormat(platform: string): boolean {CODE
LOWserver/src/lib/sampling-params.ts423export function supportedParametersForPlatforms(platforms: string[], caps: { tools?: boolean } = {}): string[] {CODE
LOWserver/src/lib/error-classify.ts355export function isDailyQuotaExhaustedError(err: any): boolean {CODE
LOWserver/src/lib/error-classify.ts421export function isUpstreamClassificationOutput(text: unknown, platform?: string): boolean {CODE
LOWserver/src/lib/error-classify.ts430export function isProviderBadRequestError(err: any): boolean {CODE
LOWserver/src/lib/error-classify.ts517export function isModelAccessForbiddenError(err: any): boolean {CODE
LOWserver/src/db/index.ts140function parseDirHardeningOverride(): boolean | undefined {CODE
LOWserver/src/db/index.ts187function restrictDbFilePermissions(resolvedPath: string): void {CODE
LOWserver/src/db/migrate/cli.ts104function updateDefaultMigrationRegistry(filename: string): void {CODE
LOWserver/src/db/migrate/runner.ts98function initializeMigrationTracking(db: Db): void {CODE
LOWserver/src/db/migrate/runner.ts173function runLatestDownMigrationSync(CODE
LOWserver/src/db/migrate/runner.ts213function getDefaultMigrationRecords(): MigrationRecord[] {CODE
LOWserver/src/db/migrate/runner.ts262function getMigrationFileExtension(options: MigrationRunnerOptions): '.ts' | '.js' {CODE
LOWserver/src/routes/anthropic.ts115export function effortFromAnthropicThinking(CODE
LOWserver/src/routes/proxy.ts921function completionPromptToMessages(prompt: string, suffix?: string): ChatMessage[] {CODE
LOWserver/src/routes/responses.ts286export function responsesInputHasFileIdImage(req: ResponsesRequest): boolean {CODE
LOWserver/src/routes/responses.ts304export function responsesInputRequestsComputerUse(req: ResponsesRequest): boolean {CODE
LOWserver/src/services/model-state.ts131export function recordCatalogModelTombstone(CODE
LOWserver/src/services/model-state.ts164export function retireCatalogModelUpstream(CODE
LOWserver/src/services/model-state.ts184export function reinstateUpstreamRetiredCatalogModel(CODE
LOWserver/src/services/model-state.ts201export function clearCatalogModelTombstone(CODE
LOWserver/src/services/model-state.ts253export function modelsWithOverriddenField(CODE
LOWserver/src/services/model-state.ts299export function deleteTombstonedCatalogModels(db: Db): number {CODE
LOWserver/src/services/provider-quota.ts80export function getQuotaObservationContext(): QuotaObservationContext | undefined {CODE
LOWserver/src/services/provider-quota.ts239export function parseQuotaObservationsFromResponse(CODE
LOWserver/src/services/provider-quota.ts422export function recordQuotaObservationsFromResponse(CODE
LOWserver/src/services/provider-quota.ts438function normalizeExpiredQuotaState(db: ReturnType<typeof getDb>): void {CODE
LOWserver/src/services/provider-quota.ts522export function invalidateKeyQuotaHeadroom(platform?: Platform): void {CODE
LOWserver/src/services/custom-endpoint.ts63function defaultCustomEndpointLabel(baseUrl: string): string {CODE
LOWserver/src/services/custom-model-tombstone.ts18export function recordCustomModelTombstone(CODE
LOWserver/src/services/custom-model-tombstone.ts41export function clearCustomModelTombstone(CODE
LOWserver/src/services/profile-models.ts35export function ensureAllModelsInProfiles(db: Db): void {CODE
LOWserver/src/services/router.ts592function invalidateCommunityPriorCache(): void {CODE
LOWserver/src/services/router.ts936function usableKeyCountsByPlatform(db: Db): Map<string, number> {CODE
LOWserver/src/services/router.ts1334function orderKeysByRemainingQuota(entry: ChainRow, ordered: KeyRow[]): KeyRow[] {CODE
LOWserver/src/services/router.ts1676export function resolveModelGroupCandidates(CODE
39 more matches not shown…
Fake / Example Data68 hits · 70 pts
SeverityFileLineSnippetContext
LOWserver/src/__tests__/routes/auth-setup-code.test.ts38const CREDS = { email: 'admin@example.com', password: 'supersecret' };CODE
LOWserver/src/__tests__/routes/auth.test.ts60 const { status, body } = await call(app, 'POST', '/api/auth/setup', { email: 'admin@example.com', password: 'superseCODE
LOWserver/src/__tests__/routes/auth.test.ts73 const ok = await call(app, 'POST', '/api/auth/login', { email: 'admin@example.com', password: 'supersecret' });CODE
LOWserver/src/__tests__/routes/auth.test.ts77 const bad = await call(app, 'POST', '/api/auth/login', { email: 'admin@example.com', password: 'wrongpassword' });CODE
LOWserver/src/__tests__/routes/auth.test.ts84 expect(body).toMatchObject({ needsSetup: false, authenticated: true, email: 'admin@example.com' });CODE
LOWserver/src/__tests__/routes/auth.test.ts88 const login = await call(app, 'POST', '/api/auth/login', { email: 'admin@example.com', password: 'supersecret' });CODE
LOW…/src/__tests__/routes/custom-provider-multikey.test.ts330 await post(app, '/api/keys/custom', { baseUrl: ENDPOINT, model: 'placeholder', apiKey: 'second-secret' });CODE
LOW…/src/__tests__/routes/custom-provider-multikey.test.ts333 expect((await del(app, `/api/models/custom/${chatModel('placeholder')!.id}`)).status).toBe(200);CODE
LOWclient/src/i18n/locales/tr.json986 "placeholder": "Sayfaları, modelleri, eylemleri arayın…",CODE
LOWclient/src/i18n/locales/or.json986 "placeholder": "ପୃଷ୍ଠା, ମଡେଲ୍, କ୍ରିୟାଗୁଡିକ ସନ୍ଧାନ କରନ୍ତୁ...",CODE
LOWclient/src/i18n/locales/hu.json986 "placeholder": "Keresőoldalak, modellek, akciók...",CODE
LOWclient/src/i18n/locales/mr.json986 "placeholder": "पृष्ठे, मॉडेल, क्रिया शोधा…",CODE
LOWclient/src/i18n/locales/lt.json986 "placeholder": "Paieškos puslapiai, modeliai, veiksmai...",CODE
LOWclient/src/i18n/locales/bn.json986 "placeholder": "অনুসন্ধান পৃষ্ঠা, মডেল, কর্ম…",CODE
LOWclient/src/i18n/locales/ha.json986 "placeholder": "Bincika shafuka, samfura, ayyuka…",CODE
LOWclient/src/i18n/locales/ig.json986 "placeholder": "Chọọ ibe, ụdị, omume…",CODE
LOWclient/src/i18n/locales/yo.json986 "placeholder": "Ṣewadii awọn oju-iwe, awọn awoṣe, awọn iṣe…",CODE
LOWclient/src/i18n/locales/nl.json986 "placeholder": "Zoek pagina's, modellen, acties...",CODE
LOWclient/src/i18n/locales/ms.json986 "placeholder": "Halaman carian, model, tindakan...",CODE
LOWclient/src/i18n/locales/ja.json986 "placeholder": "ページ、モデル、アクションを検索します...",CODE
LOWclient/src/i18n/locales/de.json986 "placeholder": "Suchseiten, Modelle, Aktionen…",CODE
LOWclient/src/i18n/locales/ru.json986 "placeholder": "Поиск по страницам, моделям, действиям…",CODE
LOWclient/src/i18n/locales/pl.json986 "placeholder": "Przeszukaj strony, modele, działania…",CODE
LOWclient/src/i18n/locales/uk.json986 "placeholder": "Пошук сторінок, моделей, дій…",CODE
LOWclient/src/i18n/locales/fi.json986 "placeholder": "Hakusivuja, malleja, toimintoja...",CODE
LOWclient/src/i18n/locales/ta.json986 "placeholder": "தேடல் பக்கங்கள், மாதிரிகள், செயல்கள்...",CODE
LOWclient/src/i18n/locales/ur.json986 "placeholder": "تلاش کے صفحات، ماڈل، اعمال…",CODE
LOWclient/src/i18n/locales/zh-CN.json986 "placeholder": "搜索页面、模型、操作…",CODE
LOWclient/src/i18n/locales/sk.json986 "placeholder": "Vyhľadávajte stránky, modely, akcie...",CODE
LOWclient/src/i18n/locales/ml.json986 "placeholder": "പേജുകൾ, മോഡലുകൾ, പ്രവർത്തനങ്ങൾ എന്നിവ തിരയുക...",CODE
LOWclient/src/i18n/locales/az.json986 "placeholder": "Axtarış səhifələri, modellər, fəaliyyətlər...",CODE
LOWclient/src/i18n/locales/en.json1019 "placeholder": "Search pages, models, actions…",CODE
LOWclient/src/i18n/locales/ka.json986 "placeholder": "მოძებნეთ გვერდები, მოდელები, მოქმედებები…",CODE
LOWclient/src/i18n/locales/pa.json986 "placeholder": "ਖੋਜ ਪੰਨੇ, ਮਾਡਲ, ਕਾਰਵਾਈਆਂ…",CODE
LOWclient/src/i18n/locales/my.json986 "placeholder": "စာမျက်နှာများ၊ မော်ဒယ်များ၊ လုပ်ဆောင်ချက်များကို ရှာဖွေပါ...",CODE
LOWclient/src/i18n/locales/pt-PT.json986 "placeholder": "Páginas de pesquisa, modelos, ações...",CODE
LOWclient/src/i18n/locales/km.json986 "placeholder": "ទំព័រស្វែងរក ម៉ូដែល សកម្មភាព...",CODE
LOWclient/src/i18n/locales/it.json986 "placeholder": "Cerca pagine, modelli, azioni…",CODE
LOWclient/src/i18n/locales/sr.json986 "placeholder": "Претражи странице, моделе, акције…",CODE
LOWclient/src/i18n/locales/hr.json986 "placeholder": "Pretraži stranice, modele, akcije...",CODE
LOWclient/src/i18n/locales/tl.json986 "placeholder": "Mga pahina ng paghahanap, mga modelo, mga aksyon...",CODE
LOWclient/src/i18n/locales/kn.json986 "placeholder": "ಪುಟಗಳು, ಮಾದರಿಗಳು, ಕ್ರಿಯೆಗಳನ್ನು ಹುಡುಕಿ...",CODE
LOWclient/src/i18n/locales/ne.json986 "placeholder": "पृष्ठ, नमूना, कार्य खोजी गर्नुहोस्...",CODE
LOWclient/src/i18n/locales/fr.json986 "placeholder": "Rechercher des pages, modèles, actions…",CODE
LOWclient/src/i18n/locales/am.json986 "placeholder": "የፍለጋ ገጾች፣ ሞዴሎች፣ ድርጊቶች...",CODE
LOWclient/src/i18n/locales/gu.json986 "placeholder": "શોધ પૃષ્ઠો, મોડેલો, ક્રિયાઓ...",CODE
LOWclient/src/i18n/locales/el.json986 "placeholder": "Αναζήτηση σελίδων, μοντέλων, ενεργειών...",CODE
LOWclient/src/i18n/locales/bg.json986 "placeholder": "Страници за търсене, модели, действия...",CODE
LOWclient/src/i18n/locales/ro.json986 "placeholder": "Pagini de căutare, modele, acțiuni...",CODE
LOWclient/src/i18n/locales/hi.json986 "placeholder": "खोज पृष्ठ, मॉडल, क्रियाएँ...",CODE
LOWclient/src/i18n/locales/si.json986 "placeholder": "පිටු, ආකෘති, ක්‍රියා සොයන්න...",CODE
LOWclient/src/i18n/locales/pt-BR.json986 "placeholder": "Buscar páginas, modelos, ações…",CODE
LOWclient/src/i18n/locales/ko.json986 "placeholder": "페이지, 모델, 작업 검색…",CODE
LOWclient/src/i18n/locales/he.json986 "placeholder": "דפי חיפוש, דגמים, פעולות...",CODE
LOWclient/src/i18n/locales/zh-TW.json986 "placeholder": "搜尋頁面、模型、操作...",CODE
LOWclient/src/i18n/locales/vi.json986 "placeholder": "Tìm kiếm trang, mô hình, hành động…",CODE
LOWclient/src/i18n/locales/fa.json986 "placeholder": "جستجوی صفحات، مدل‌ها، اقدامات…",CODE
LOWclient/src/i18n/locales/cs.json986 "placeholder": "Hledejte stránky, modely, akce...",CODE
LOWclient/src/i18n/locales/te.json986 "placeholder": "శోధన పేజీలు, నమూనాలు, చర్యలు...",CODE
LOWclient/src/i18n/locales/id.json986 "placeholder": "Cari halaman, model, tindakan…",CODE
8 more matches not shown…
Modern AI Meta-Vocabulary12 hits · 36 pts
SeverityFileLineSnippetContext
MEDIUMserver/src/__tests__/lib/unified-max-tokens.test.ts9// way guardrails.test.ts drives its knobs.COMMENT
MEDIUMserver/src/__tests__/lib/guardrails.test.ts3// Unit tests for the request guardrails (ported from @coffcoe's fork): theCOMMENT
MEDIUMserver/src/__tests__/routes/custom-provider.test.ts466 // #470: custom models used to register with supports_tools = 0, so agenticCOMMENT
MEDIUMserver/src/__tests__/routes/custom-provider.test.ts466 // #470: custom models used to register with supports_tools = 0, so agenticCOMMENT
MEDIUMserver/src/__tests__/routes/proxy-auto-model.test.ts146 // #282: clients read a model's context window from /v1/models; advertise itCOMMENT
MEDIUMserver/src/__tests__/services/scoring.test.ts165 // The two guardrails agree wherever the remaining fraction agrees.COMMENT
MEDIUMserver/src/lib/guardrails.ts1// Request-level guardrails: two hard limits, both OFF by default so anCOMMENT
MEDIUMserver/src/db/model-pricing.ts64 // Groq (compound is an agentic pipeline — estimated at its underlyingCOMMENT
MEDIUMserver/src/routes/fallback.ts24// breakdown (reliability / speed / intelligence + guardrails).COMMENT
MEDIUMserver/src/routes/settings.ts271// Get the request guardrails (per-request token budget + failover circuitCOMMENT
MEDIUMserver/src/routes/settings.ts272// breaker). Both default to 0 = disabled; see lib/guardrails.ts.COMMENT
MEDIUMserver/src/routes/settings.ts319// Update the guardrails. Partial: send just the knob you want to change.COMMENT
Magic Placeholder Names3 hits · 15 pts
SeverityFileLineSnippetContext
HIGHclient/src/pages/MediaDetailPage.tsx46 const key = keyData?.apiKey || 'YOUR_API_KEY'CODE
HIGHclient/src/pages/ModelDetailPage.tsx225 -H "Authorization: Bearer ${keyData?.apiKey || 'YOUR_API_KEY'}" \\CODE
HIGHclient/src/pages/EmbeddingDetailPage.tsx49 const key = keyData?.apiKey || 'YOUR_API_KEY'CODE
AI Slop Vocabulary2 hits · 6 pts
SeverityFileLineSnippetContext
MEDIUMserver/src/lib/error-classify.ts10 // This structured check is the robust primary signal; the message-substringCOMMENT
MEDIUMserver/src/services/fusion.ts69 // the whole request — a panel is robust to missing members by design.COMMENT
Verbosity Indicators2 hits · 3 pts
SeverityFileLineSnippetContext
LOWserver/src/providers/modelscope.ts102 // Step 1: pick a live model id for the auth probe. This call is NOT theCOMMENT
LOWserver/src/providers/modelscope.ts120 // Step 2: the actual auth check — a minimal 1-token completion.COMMENT
Structural Annotation Overuse2 hits · 3 pts
SeverityFileLineSnippetContext
LOWserver/src/providers/modelscope.ts102 // Step 1: pick a live model id for the auth probe. This call is NOT theCOMMENT
LOWserver/src/providers/modelscope.ts120 // Step 2: the actual auth check — a minimal 1-token completion.COMMENT
Slop Phrases1 hit · 2 pts
SeverityFileLineSnippetContext
MEDIUMserver/src/__tests__/lib/structured-output.test.ts26 const r = enforceJsonContent('Sure! Here is the requested JSON: {"name":"Ada","tags":["a","b"]} Let me know if you nCODE