Repository Analysis

vercel/ai

The AI Toolkit for TypeScript. From the creators of Next.js, the AI SDK is a free open-source library for building AI-powered applications and agents

2.4 Likely human-written View on GitHub

Analysis Overview

This report presents the forensic synthetic code analysis of vercel/ai, a TypeScript project with 25,547 GitHub stars. SynthScan v2.0 examined 926,537 lines of code across 6328 source files, recording 908 pattern matches distributed across 16 syntactic categories. The overall adjusted score of 2.4 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).

2.4
Adjusted Score
2.4
Raw Score
100%
Time Factor
2026-07-14
Last Push
25.5K
Stars
TypeScript
Language
926.5K
Lines of Code
6.3K
Files
908
Pattern Hits
2026-07-14
Scan Date
0.03
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 2HIGH 206MEDIUM 84LOW 616

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 908 distinct pattern matches across 16 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.

Cross-Language Confusion (JS/TS)188 hits · 1178 pts
SeverityFileLineSnippetContext
HIGH…ns/src/middleware/embedding/google-default-settings.ts35 print('Embedding length:', result.embedding.length);CODE
HIGH…les/ai-functions/src/tools/mcp-tool-drift-detection.ts29 print('Baseline fingerprints:', baseline);CODE
HIGH…les/ai-functions/src/tools/mcp-tool-drift-detection.ts34 print('Drift:', drift);CODE
HIGH…les/ai-functions/src/tools/mcp-tool-drift-detection.ts37 print(CODE
HIGH…les/ai-functions/src/tools/mcp-tool-drift-detection.ts45 print('OK:', 'no drift; safe to proceed.');CODE
HIGH…ctions/src/stream-text/google/vertex-combined-tools.ts39 print('Request body:', (await result.request).body);CODE
HIGH…ctions/src/stream-text/google/vertex-combined-tools.ts40 print('Raw response chunks:', rawChunks);CODE
HIGH…ctions/src/stream-text/google/vertex-combined-tools.ts41 print('Response metadata:', await result.response);CODE
HIGH…es/ai-functions/src/stream-text/anthropic/fast-mode.ts23 print('Usage:', await result.usage);CODE
HIGH…es/ai-functions/src/stream-text/anthropic/fast-mode.ts24 print('Finish reason:', await result.finishReason);CODE
HIGH…-functions/src/stream-text/anthropic/tool-call-8516.ts104 print('Request body:', (await result.request).body);CODE
HIGH…s/src/stream-text/anthropic/subagent-with-telemetry.ts53 print('Usage:', await result.usage);CODE
HIGH…s/src/stream-text/anthropic/subagent-with-telemetry.ts54 print('Finish reason:', await result.finishReason);CODE
HIGHexamples/ai-functions/src/stream-text/anthropic/mcp.ts30 print('Request body:', (await result.request).body);CODE
HIGHexamples/ai-functions/src/stream-text/anthropic/mcp.ts31 print('Warnings:', await result.warnings);CODE
HIGH…amples/ai-functions/src/stream-text/anthropic/basic.ts19 print('Usage:', await result.usage);CODE
HIGH…amples/ai-functions/src/stream-text/anthropic/basic.ts20 print('Finish reason:', await result.finishReason);CODE
HIGH…amples/ai-functions/src/stream-text/anthropic/basic.ts21 print('Raw finish reason:', await result.rawFinishReason);CODE
HIGH…mples/ai-functions/src/stream-text/anthropic/skills.ts36 print('container', anthropicContainer);CODE
HIGH…s/src/stream-text/anthropic/mid-conversation-system.ts40 print('Usage:', await result.usage);CODE
HIGH…s/ai-functions/src/stream-text/openai/timeout-total.ts16 print('Usage:', await result.usage);CODE
HIGH…s/ai-functions/src/stream-text/openai/timeout-total.ts17 print('Finish reason:', await result.finishReason);CODE
HIGH…s/ai-functions/src/stream-text/openai/output-object.ts42 print('Output:', await result.output);CODE
HIGH…es/ai-functions/src/stream-text/openai/timeout-step.ts31 print('Usage:', await result.usage);CODE
HIGH…es/ai-functions/src/stream-text/openai/timeout-step.ts32 print('Finish reason:', await result.finishReason);CODE
HIGH…es/ai-functions/src/stream-text/openai/timeout-step.ts33 print('Steps:', (await result.steps).length);CODE
HIGH…i-functions/src/stream-text/openai/step-performance.ts48 print('Tool result:', chunk.output);CODE
HIGH…i-functions/src/stream-text/openai/step-performance.ts54 print('Usage:', chunk.usage);CODE
HIGH…i-functions/src/stream-text/openai/step-performance.ts65 print(CODE
HIGH…i-functions/src/stream-text/openai/step-performance.ts69 print('Final step performance:', (await result.finalStep).performance);CODE
HIGH…i-functions/src/stream-text/openai/step-performance.ts70 print('Total usage:', await result.usage);CODE
HIGHexamples/ai-functions/src/stream-text/openai/basic.ts16 print('Usage:', await result.usage);CODE
HIGHexamples/ai-functions/src/stream-text/openai/basic.ts17 print('Finish reason:', await result.finishReason);CODE
HIGHexamples/ai-functions/src/stream-text/openai/basic.ts18 print('Raw finish reason:', await result.rawFinishReason);CODE
HIGH…/ai-functions/src/stream-text/openai/output-default.ts20 print('Output:', await result.output);CODE
HIGHexamples/ai-functions/src/stream-text/openai/timeout.ts16 print('Usage:', await result.usage);CODE
HIGHexamples/ai-functions/src/stream-text/openai/timeout.ts17 print('Finish reason:', await result.finishReason);CODE
HIGH…ons/src/stream-text/openai/include-request-messages.ts20 print('Request metadata:', await result.request);CODE
HIGH…s/ai-functions/src/stream-text/openai/timeout-chunk.ts16 print('Usage:', await result.usage);CODE
HIGH…s/ai-functions/src/stream-text/openai/timeout-chunk.ts17 print('Finish reason:', await result.finishReason);CODE
HIGH…s/ai-functions/src/stream-text/openai/gpt-5-3-codex.ts18 print('Usage:', await result.usage);CODE
HIGH…s/ai-functions/src/stream-text/openai/gpt-5-3-codex.ts19 print('Finish reason:', await result.finishReason);CODE
HIGH…/ai-functions/src/agent/anthropic/cache-instruction.ts36 print('Result:', result.content);CODE
HIGH…/ai-functions/src/agent/anthropic/cache-instruction.ts37 print('Metadata:', result.providerMetadata?.anthropic);CODE
HIGH…/ai-functions/src/agent/anthropic/cache-instruction.ts38 print('Request:', result.request.body);CODE
HIGH…functions/src/agent/anthropic/generate-output-array.ts25 print('Output:', output);CODE
HIGH…s/ai-functions/src/agent/openai/stream-call-options.ts45 print('REQUEST:', request.body);CODE
HIGH…ions/src/agent/openai/stream-output-array-websearch.ts39 print('REQUEST:', request.body);CODE
HIGH…ai-functions/src/agent/openai/generate-call-options.ts44 print('REQUEST:', request.body);CODE
HIGH…ai-functions/src/agent/openai/generate-call-options.ts59 print('CONTENT:', result.content);CODE
HIGHexamples/ai-functions/src/agent/openai/generate.ts16 print('CONTENT:', result.content);CODE
HIGH…-functions/src/agent/openai/stream-step-performance.ts30 print(CODE
HIGH…-functions/src/agent/openai/stream-step-performance.ts34 print('Final step performance:', (await result.finalStep).performance);CODE
HIGH…-functions/src/agent/openai/stream-step-performance.ts35 print('Total usage:', await result.usage);CODE
HIGH…ai-functions/src/agent/openai/generate-output-array.ts34 print('Output:', output);CODE
HIGHexamples/ai-functions/src/lib/run.ts18 print('Request body:', error.requestBodyValues);CODE
HIGHexamples/ai-functions/src/lib/run.ts19 print('Response body:', error.responseBody);CODE
HIGH…unctions/src/generate-text/azure/deepseek-reasoning.ts21 print('Reasoning:', result.reasoningText);CODE
HIGH…unctions/src/generate-text/azure/deepseek-reasoning.ts22 print('Text:', result.text);CODE
HIGH…ate-text/google/vertex-anthropic-output-array-tools.ts23 print('Output:', result.output);CODE
128 more matches not shown…
Hyper-Verbose Identifiers493 hits · 499 pts
SeverityFileLineSnippetContext
LOWtools/analyze-downloads/src/analyze-ui-frameworks.ts30function aggregateDownloadsForLastNMajorReleases(CODE
LOWcontributing/testing.md91function prepareChunksFixtureResponse(filename: string) {CODE
LOWcontributing/testing.md109function prepareChunksFixtureResponse(filename: string) {CODE
LOW…es/ai-functions/src/benchmark/stream-text-benchmark.ts139async function benchmarkConcurrentStreams() {CODE
LOW…es/ai-functions/src/benchmark/stream-text-benchmark.ts185async function benchmarkStreamWithToolCalls() {CODE
LOWexamples/ai-functions/src/stream-text/gateway/auth.ts107async function testAuthenticationScenario(scenario: (typeof testScenarios)[0]) {CODE
LOW…ai-functions/src/lib/download-openai-container-file.ts4export async function downloadOpenaiContainerFile(CODE
LOWexamples/ai-functions/src/lib/delete-uploaded-skill.ts1export async function deleteUploadedOpenAISkill({CODE
LOWexamples/ai-functions/src/lib/delete-uploaded-skill.ts26export async function deleteUploadedAnthropicSkill({CODE
LOW…/ai-functions/src/lib/download-azure-container-file.ts4export async function downloadAzureContainerFile(CODE
LOWexamples/ai-functions/src/lib/harness-tool-approval.ts14export async function printFullStreamAndCaptureToolApproval({CODE
LOWexamples/ai-functions/src/lib/harness-tool-approval.ts92export function createToolApprovalResponseMessages({CODE
LOW…ons/src/generate-text/mock/return-await-stack-trace.ts41function createWrappedModelWithoutAwait() {CODE
LOW…ons/src/generate-text/mock/return-await-stack-trace.ts44 async function wrappedDoGenerateWithoutAwait(CODE
LOW…ons/src/generate-text/mock/return-await-stack-trace.ts55function createWrappedModelWithAwait() {CODE
LOW…ons/src/generate-text/mock/return-await-stack-trace.ts58 async function wrappedDoGenerateWithAwait(CODE
LOW…ons/src/generate-text/mock/return-await-stack-trace.ts81async function sdkMiddlewareWithoutAwait() {CODE
LOW…ons/src/generate-text/mock/return-await-stack-trace.ts93async function sdkModelBoundaryWithoutAwait() {CODE
LOW…ons/src/generate-text/mock/return-await-stack-trace.ts100async function sdkModelBoundaryWithAwait() {CODE
LOW…next/app/harness/claude-code/weather-approval/page.tsx10export default function HarnessClaudeCodeWeatherApprovalPage() {CODE
LOW…-next/app/harness/claude-code/basic-with-stop/page.tsx10export default function HarnessClaudeCodeBasicWithStopPage() {CODE
LOW…ess-e2e-next/app/harness/claude-code/workflow/page.tsx10export default function HarnessClaudeCodeWorkflowPage() {CODE
LOW…ness-e2e-next/app/harness/claude-code/weather/page.tsx10export default function HarnessClaudeCodeWeatherPage() {CODE
LOW…e2e-next/app/harness/claude-code/weather-only/page.tsx10export default function HarnessClaudeCodeWeatherPage() {CODE
LOW…2e-next/app/harness/claude-code/ai-sdk-coding/page.tsx10export default function HarnessClaudeCodeAiSdkCodingPage() {CODE
LOW…s-e2e-next/app/harness/codex/weather-approval/page.tsx10export default function HarnessCodexWeatherApprovalPage() {CODE
LOW…ss-e2e-next/app/harness/codex/basic-with-stop/page.tsx10export default function HarnessCodexBasicWithStopPage() {CODE
LOW…ness-e2e-next/app/harness/codex/ai-sdk-coding/page.tsx10export default function HarnessCodexAiSdkCodingPage() {CODE
LOW…ness-e2e-next/app/harness/pi/weather-approval/page.tsx10export default function HarnessPiWeatherApprovalPage() {CODE
LOW…rness-e2e-next/app/harness/pi/basic-with-stop/page.tsx10export default function HarnessPiBasicWithStopPage() {CODE
LOW…-next/app/harness/deepagents/weather-approval/page.tsx10export default function HarnessDeepAgentsWeatherApprovalPage() {CODE
LOW…e-next/app/harness/deepagents/basic-with-stop/page.tsx10export default function HarnessDeepAgentsBasicWithStopPage() {CODE
LOW…ness-e2e-next/app/harness/deepagents/workflow/page.tsx10export default function HarnessDeepAgentsWorkflowPage() {CODE
LOW…rness-e2e-next/app/harness/deepagents/weather/page.tsx10export default function HarnessDeepAgentsWeatherPage() {CODE
LOW…-e2e-next/app/harness/deepagents/weather-only/page.tsx10export default function HarnessDeepAgentsWeatherPage() {CODE
LOW…e2e-next/app/harness/deepagents/ai-sdk-coding/page.tsx10export default function HarnessDeepAgentsAiSdkCodingPage() {CODE
LOW…2e-next/app/harness/opencode/weather-approval/page.tsx10export default function HarnessOpenCodeWeatherApprovalPage() {CODE
LOW…e2e-next/app/harness/opencode/basic-with-stop/page.tsx10export default function HarnessOpenCodeBasicWithStopPage() {CODE
LOW…arness-e2e-next/app/harness/opencode/workflow/page.tsx10export default function HarnessOpenCodeWorkflowPage() {CODE
LOW…harness-e2e-next/app/harness/opencode/weather/page.tsx10export default function HarnessOpenCodeWeatherPage() {CODE
LOW…ss-e2e-next/app/harness/opencode/weather-only/page.tsx10export default function HarnessOpenCodeWeatherPage() {CODE
LOW…s-e2e-next/app/harness/opencode/ai-sdk-coding/page.tsx10export default function HarnessOpenCodeAiSdkCodingPage() {CODE
LOW…-e2e-next/components/weather-opencode-harness-chat.tsx18export default function WeatherOpenCodeHarnessChat({CODE
LOW…e-next/components/weather-claude-code-harness-chat.tsx18export default function WeatherClaudeCodeHarnessChat({CODE
LOW…2e-next/components/weather-deepagents-harness-chat.tsx17export default function WeatherDeepAgentsHarnessChat({CODE
LOWexamples/next-fastapi/api/utils/prompt.py14def convert_to_openai_messages(messages: List[ClientMessage]):CODE
LOWexamples/next-workflow/workflow/telemetry-agent.ts66function createTelemetryIntegration(telemetryRunId: string) {CODE
LOWexamples/next-workflow/lib/telemetry-store.ts54export function getTelemetryRunIdForWorkflowRun(workflowRunId: string) {CODE
LOW…e2e-next/app/chat/test-azure-image-generation/page.tsx9export default function TestOpenAIImageGeneration() {CODE
LOW…ai-e2e-next/app/chat/anthropic-code-execution/page.tsx10export default function TestAnthropicCodeExecution() {CODE
LOWexamples/ai-e2e-next/app/chat/anthropic-mcp/page.tsx10export default function TestAnthropicCodeExecution() {CODE
LOW…e-next/app/chat/openai-shell-container-skills/page.tsx8export default function ChatOpenAIShellContainerSkills() {CODE
LOW…st-azure-code-interpreter-annotation-download/page.tsx10export default function TestAzureOpenAICodeInterpreter() {CODE
LOW…t/app/chat/test-openai-responses-mcp-approval/page.tsx13export default function TestOpenAIResponsesMCPApproval() {CODE
LOW…app/chat/anthropic-code-execution-file-upload/page.tsx46export default function AnthropicCodeExecutionFileUploadPage() {CODE
LOWexamples/ai-e2e-next/app/chat/anthropic-tools/page.tsx10export default function TestAnthropicCodeExecution() {CODE
LOW…i-e2e-next/app/chat/openai-tool-search-client/page.tsx10export default function TestOpenAIToolSearchClient() {CODE
LOW…e2e-next/app/chat/openai-previous-response-id/page.tsx15export default function OpenPreviousResponseIdPage() {CODE
LOW…2e-next/app/chat/openai-pdf-fetch-custom-tool/page.tsx9export default function TestOpenAIFileGenerationPDF() {CODE
LOW…/app/chat/anthropic-programmatic-tool-calling/page.tsx10export default function ChatAnthropicProgrammaticToolCalling() {CODE
433 more matches not shown…
Decorative Section Separators57 hits · 176 pts
SeverityFileLineSnippetContext
MEDIUM…c/stream-text/anthropic/fine-grained-tool-streaming.ts47 // ── stream events ─────────────────────────────────────────────────────────COMMENT
MEDIUM…c/stream-text/anthropic/fine-grained-tool-streaming.ts142 // ── diagnosis ─────────────────────────────────────────────────────────────COMMENT
MEDIUM…mazon-bedrock/anthropic-fine-grained-tool-streaming.ts128 // ── diagnosis ─────────────────────────────────────────────────────────────COMMENT
MEDIUM…rc/realtime-model/v4/realtime-model-v4-server-event.ts9 // ── Session lifecycle ──────────────────────────────────────────────COMMENT
MEDIUM…rc/realtime-model/v4/realtime-model-v4-server-event.ts21 // ── Input audio buffer ─────────────────────────────────────────────COMMENT
MEDIUM…rc/realtime-model/v4/realtime-model-v4-server-event.ts39 // ── Conversation items ─────────────────────────────────────────────COMMENT
MEDIUM…rc/realtime-model/v4/realtime-model-v4-server-event.ts53 // ── Response lifecycle ─────────────────────────────────────────────COMMENT
MEDIUM…rc/realtime-model/v4/realtime-model-v4-server-event.ts66 // ── Output item lifecycle ──────────────────────────────────────────COMMENT
MEDIUM…rc/realtime-model/v4/realtime-model-v4-server-event.ts92 // ── Audio output ───────────────────────────────────────────────────COMMENT
MEDIUM…rc/realtime-model/v4/realtime-model-v4-server-event.ts111 // ── Audio transcript output ────────────────────────────────────────COMMENT
MEDIUM…rc/realtime-model/v4/realtime-model-v4-server-event.ts131 // ── Text output ────────────────────────────────────────────────────COMMENT
MEDIUM…rc/realtime-model/v4/realtime-model-v4-server-event.ts151 // ── Function calling ───────────────────────────────────────────────COMMENT
MEDIUM…rc/realtime-model/v4/realtime-model-v4-server-event.ts182 // ── Error ──────────────────────────────────────────────────────────COMMENT
MEDIUM…rc/realtime-model/v4/realtime-model-v4-server-event.ts190 // ── Custom / provider-specific ────────────────────────────────────COMMENT
MEDIUM…rc/realtime-model/v4/realtime-model-v4-client-event.ts10 // ── Session ────────────────────────────────────────────────────────COMMENT
MEDIUM…rc/realtime-model/v4/realtime-model-v4-client-event.ts17 // ── Input audio buffer ─────────────────────────────────────────────COMMENT
MEDIUM…rc/realtime-model/v4/realtime-model-v4-client-event.ts33 // ── Conversation items ─────────────────────────────────────────────COMMENT
MEDIUM…rc/realtime-model/v4/realtime-model-v4-client-event.ts57 // ── Response control ───────────────────────────────────────────────COMMENT
MEDIUMpackages/xai/src/xai-video-model-options.ts90// ── Runtime schemas ───────────────────────────────────────────────────COMMENT
MEDIUMpackages/xai/src/xai-video-options.test-d.ts5 // ── Explicit modes accepted ────────────────────────────────────────COMMENT
MEDIUMpackages/xai/src/xai-video-options.test-d.ts51 // ── Plain generation + legacy no-mode compatibility ────────────────COMMENT
MEDIUMpackages/xai/src/xai-video-options.test-d.ts111 // ── Discriminated union: illegal combos rejected ───────────────────COMMENT
MEDIUMpackages/xai/src/xai-video-options.test-d.ts146 // ── Required companion fields ──────────────────────────────────────COMMENT
MEDIUMpackages/harness/src/bridge/index.ts233 // ─── mutable runtime state ──────────────────────────────────────────COMMENT
MEDIUMpackages/harness/src/bridge/index.ts344 // ─── persistence (best-effort meta + start config) ──────────────────COMMENT
MEDIUMpackages/harness/src/bridge/index.ts375 // ─── wire send + replay ─────────────────────────────────────────────COMMENT
MEDIUMpackages/harness/src/bridge/index.ts410 // ─── diagnostics ──────────────────────────────────────────────COMMENT
MEDIUMpackages/harness/src/bridge/index.ts518 // ─── inbound routing ────────────────────────────────────────────────COMMENT
MEDIUMpackages/harness/src/bridge/index.ts664 // ─── server ─────────────────────────────────────────────────────────COMMENT
MEDIUM…ges/harness/src/bridge/disk-replay.integration.test.ts66 // ── Bridge #1: run a full turn, then "die". ────────────────────────COMMENT
MEDIUM…ges/harness/src/bridge/disk-replay.integration.test.ts66 // ── Bridge #1: run a full turn, then "die". ────────────────────────COMMENT
MEDIUMpackages/harness/src/utils/sandbox-channel.ts346 // ─── internals ──────────────────────────────────────────────────────COMMENT
MEDIUMpackages/harness/src/agent/harness-agent.ts485 // ─── Internals ──────────────────────────────────────────────────────COMMENT
MEDIUM…rness/src/agent/internal/harness-stream-text-result.ts194 // ─── Writer-side methods used by the driver ────────────────────────COMMENT
MEDIUM…rness/src/agent/internal/harness-stream-text-result.ts482 // ─── Reader-side public surface (StreamTextResult contract) ────────COMMENT
MEDIUM…rness/src/agent/internal/harness-stream-text-result.ts654 // ─── Helpers ────────────────────────────────────────────────────────COMMENT
MEDIUMpackages/ai/src/realtime/realtime-session.ts104 // ── Connection ─────────────────────────────────────────────────────COMMENT
MEDIUMpackages/ai/src/realtime/realtime-session.ts153 // ── Sending events ─────────────────────────────────────────────────COMMENT
MEDIUMpackages/ai/src/realtime/realtime-session.ts191 // ── Tool output ───────────────────────────────────────────────────COMMENT
MEDIUMpackages/ai/src/realtime/realtime-session.ts235 // ── Audio capture ──────────────────────────────────────────────────COMMENT
MEDIUMpackages/ai/src/realtime/realtime-session.ts245 // ── Playback ───────────────────────────────────────────────────────COMMENT
MEDIUMpackages/ai/src/realtime/realtime-session.ts251 // ── Cleanup ────────────────────────────────────────────────────────COMMENT
MEDIUMpackages/ai/src/realtime/realtime-session.ts267 // ── Private helpers ────────────────────────────────────────────────COMMENT
MEDIUM…c/__fixtures__/anthropic-advisor-20250301.1.chunks.txt7{"type":"content_block_start","index":1,"content_block":{"type":"advisor_tool_result","tool_use_id":"srvtoolu_01R6zRtm9VCODE
MEDIUM…c/__fixtures__/anthropic-advisor-20250301.1.chunks.txt83{"type":"content_block_delta","index":2,"delta":{"type":"text_delta","text":" below.\n}\n\n// ─── Results ──────────────CODE
MEDIUM…pic/src/__fixtures__/anthropic-advisor-20260301.1.json23 "text": "Great guidance. Here is the full design outline followed by a clean, well-commented Go implementation.\n\CODE
MEDIUM…es/openai/src/realtime/openai-realtime-event-mapper.ts36 // ── Session lifecycle ──────────────────────────────────────────COMMENT
MEDIUM…es/openai/src/realtime/openai-realtime-event-mapper.ts47 // ── Input audio buffer ─────────────────────────────────────────COMMENT
MEDIUM…es/openai/src/realtime/openai-realtime-event-mapper.ts70 // ── Conversation items ─────────────────────────────────────────COMMENT
MEDIUM…es/openai/src/realtime/openai-realtime-event-mapper.ts87 // ── Response lifecycle ──────────────────────────────────────────COMMENT
MEDIUM…es/openai/src/realtime/openai-realtime-event-mapper.ts103 // ── Output item lifecycle ───────────────────────────────────────COMMENT
MEDIUM…es/openai/src/realtime/openai-realtime-event-mapper.ts136 // ── Audio output ────────────────────────────────────────────────COMMENT
MEDIUM…es/openai/src/realtime/openai-realtime-event-mapper.ts154 // ── Audio transcript output ─────────────────────────────────────COMMENT
MEDIUM…es/openai/src/realtime/openai-realtime-event-mapper.ts173 // ── Text output ─────────────────────────────────────────────────COMMENT
MEDIUM…es/openai/src/realtime/openai-realtime-event-mapper.ts192 // ── Function calling ────────────────────────────────────────────COMMENT
MEDIUM…es/openai/src/realtime/openai-realtime-event-mapper.ts214 // ── Error ───────────────────────────────────────────────────────COMMENT
MEDIUM…es/openai/src/realtime/openai-realtime-event-mapper.ts223 // ── Pass-through ────────────────────────────────────────────────COMMENT
Magic Placeholder Names18 hits · 118 pts
SeverityFileLineSnippetContext
HIGHcontributing/add-new-tool-to-registry.md35 apiKeyEnvName: 'YOUR_API_KEY', // Optional: environment variable name for API keyCODE
HIGHcontributing/add-new-tool-to-registry.md56 apiKeyUrl: 'https://your-api-key-url.com',CODE
HIGH…/src/stream-text/azure/responses-web-search-preview.ts9 * AZURE_API_KEY="<your_api_key>"COMMENT
HIGH…unctions/src/stream-text/azure/responses-web-search.ts9 * AZURE_API_KEY="<your_api_key>"COMMENT
HIGH…i-functions/src/stream-text/azure/responses-file-id.ts9 * AZURE_API_KEY="<your_api_key>"COMMENT
HIGH…ns/src/stream-text/azure/responses-code-interpreter.ts14 * AZURE_API_KEY="<your_api_key>"COMMENT
HIGH…nctions/src/stream-text/azure/responses-file-search.ts9 * AZURE_API_KEY="<your_api_key>"COMMENT
HIGH…ions/src/stream-text/openai/compatible-abort-reason.ts9 apiKey: process.env.DEEPSEEK_API_KEY ?? 'YOUR_API_KEY',CODE
HIGH…rc/generate-text/azure/responses-web-search-preview.ts9 * AZURE_API_KEY="<your_api_key>"COMMENT
HIGH…ctions/src/generate-text/azure/responses-web-search.ts9 * AZURE_API_KEY="<your_api_key>"COMMENT
HIGH…functions/src/generate-text/azure/responses-file-id.ts9 * AZURE_API_KEY="<your_api_key>"COMMENT
HIGH…/src/generate-text/azure/responses-code-interpreter.ts14 * AZURE_API_KEY="<your_api_key>"COMMENT
HIGH…tions/src/generate-text/azure/responses-file-search.ts9 * AZURE_API_KEY="<your_api_key>"COMMENT
HIGH…-functions/src/generate-text/amazon-bedrock/api-key.ts38 process.env.AWS_BEARER_TOKEN_BEDROCK || 'your-api-key-here';CODE
HIGHpackages/amazon-bedrock/README.md45export AWS_BEARER_TOKEN_BEDROCK=your-api-key-hereCODE
HIGHpackages/amazon-bedrock/src/amazon-bedrock-provider.ts48 * apiKey: 'your-api-key-here',COMMENT
HIGHpackages/bytedance/README.md190ARK_API_KEY=your-api-keyCODE
HIGHpackages/bytedance/README.md199 apiKey: 'your-api-key',CODE
Structural Annotation Overuse54 hits · 90 pts
SeverityFileLineSnippetContext
LOWexamples/ai-functions/src/generate-video/xai/extend.ts12 // Step 1: Generate a short source video.COMMENT
LOWexamples/ai-functions/src/generate-video/xai/extend.ts35 // Step 2: Extend the video with a new scene.COMMENT
LOW…ai-functions/src/generate-video/xai/edit-concurrent.ts8 // Step 1: Apply first editCOMMENT
LOW…ai-functions/src/generate-video/xai/edit-concurrent.ts35 // Step 2: Apply two more edits concurrently, building on step 1COMMENT
LOWpackages/alibaba/src/alibaba-video-model.ts462 // Step 1: Create taskCOMMENT
LOWpackages/alibaba/src/alibaba-video-model.ts493 // Step 2: Poll for task completionCOMMENT
LOWpackages/xai/src/xai-video-model.ts391 // Step 1: Create video generation/edit/extension requestCOMMENT
LOWpackages/xai/src/xai-video-model.ts412 // Step 2: Poll for completionCOMMENT
LOWpackages/ai/src/generate-text/generate-text.test.ts2103 // Step 0: no previous stepsCOMMENT
LOWpackages/ai/src/generate-text/generate-text.test.ts2106 // Step 1: has step 0's resultCOMMENT
LOWpackages/ai/src/generate-text/generate-text.test.ts2116 // Step 2: has step 0 and step 1's resultsCOMMENT
LOWpackages/ai/src/generate-text/generate-text.test.ts8701 // Step 0: just the initial user messageCOMMENT
LOWpackages/ai/src/generate-text/generate-text.test.ts8704 // Step 1: user message + assistant message + tool messageCOMMENT
LOWpackages/ai/src/generate-text/generate-text.test.ts8707 // Step 2: user message + assistant + tool + assistant + toolCOMMENT
LOWpackages/ai/src/generate-text/generate-text.test.ts8710 // Step 3: continued accumulationCOMMENT
LOWpackages/ai/src/generate-text/generate-text.test.ts8713 // Step 4: continued accumulationCOMMENT
LOWpackages/ai/src/generate-text/generate-text.test.ts7615 // Step 1: text + server_tool_use (code_execution) + 2 rollDie callsCOMMENT
LOWpackages/ai/src/generate-text/generate-text.test.ts7670 // Step 2: 2 rollDie calls (round 2)COMMENT
LOWpackages/ai/src/generate-text/generate-text.test.ts7714 // Step 3: 2 rollDie calls (round 3)COMMENT
LOWpackages/ai/src/generate-text/generate-text.test.ts7758 // Step 4: 2 rollDie calls (round 4 - final round)COMMENT
LOWpackages/ai/src/generate-text/generate-text.test.ts7802 // Step 5: code_execution_tool_result + final textCOMMENT
LOWpackages/ai/src/generate-text/stream-text.test.ts24893 // Step 0: just the initial user messageCOMMENT
LOWpackages/ai/src/generate-text/stream-text.test.ts24896 // Step 1: user message + assistant message + tool messageCOMMENT
LOWpackages/ai/src/generate-text/stream-text.test.ts24899 // Step 2: user message + assistant + tool + assistant + toolCOMMENT
LOWpackages/ai/src/generate-text/stream-text.test.ts24902 // Step 3: continued accumulationCOMMENT
LOWpackages/ai/src/generate-text/stream-text.test.ts24905 // Step 4: continued accumulationCOMMENT
LOWpackages/ai/src/generate-text/stream-text.test.ts23907 // Step 1: text + server_tool_use (code_execution) + rollDie callCOMMENT
LOWpackages/ai/src/generate-text/stream-text.test.ts23964 // Step 2: rollDie call (player2)COMMENT
LOWpackages/ai/src/generate-text/stream-text.test.ts24006 // Step 3: rollDie calls (round 2)COMMENT
LOWpackages/ai/src/generate-text/stream-text.test.ts24048 // Step 4: more rollDie callsCOMMENT
LOWpackages/ai/src/generate-text/stream-text.test.ts24090 // Step 5: code_execution_tool_result + final textCOMMENT
LOWpackages/ai/src/generate-text/stream-text.test.ts25615 // Step 1: tool call without resultCOMMENT
LOWpackages/ai/src/generate-text/stream-text.test.ts25640 // Step 2: tool-error arrivesCOMMENT
LOWpackages/workflow/src/workflow-agent.test.ts1326 // Step 1: tool call (executed), Step 2: text completion (no tools)COMMENT
LOWpackages/klingai/src/klingai-video-model.ts299 // Step 1: Create the taskCOMMENT
LOWpackages/klingai/src/klingai-video-model.ts324 // Step 2: Poll for task completionCOMMENT
LOW…__fixtures__/anthropic-combined-context-editing.1.json14 "text": "# 25 × 37\n\nLet me break this down into easier parts:\n\n## Method: Split 37 into 30 + 7\n\n**25 × 37 = CODE
LOW…ures__/anthropic-combined-context-editing.1.chunks.txt102{"type":"content_block_delta","index":1,"delta":{"type":"text_delta","text":"\n\n### Step 3: Add the results"}}CODE
LOW…d/src/codemods/v5/rename-reasoning-to-reasoningText.ts15 // Step 1: Find destructuring from `generateText()`COMMENT
LOW…d/src/codemods/v5/rename-reasoning-to-reasoningText.ts120 // Step 3: Rename `reasoning` to `reasoningText` in the identified pathsCOMMENT
LOWskills/update-provider-models/SKILL.md31### Step 1: Identify ScopeCOMMENT
LOWskills/update-provider-models/SKILL.md42### Step 2: Find Where Similar Models Are ReferencedCOMMENT
LOWskills/update-provider-models/SKILL.md52### Step 3: Update Type DefinitionsCOMMENT
LOWskills/update-provider-models/SKILL.md87### Step 4: Update DocumentationCOMMENT
LOWskills/update-provider-models/SKILL.md97### Step 5: Create or Update ExamplesCOMMENT
LOWskills/update-provider-models/SKILL.md114### Step 6: Update TestsCOMMENT
LOWskills/update-provider-models/SKILL.md120### Step 7: Run TestsCOMMENT
LOWskills/update-provider-models/SKILL.md141### Step 1: Identify SuccessorCOMMENT
LOWskills/update-provider-models/SKILL.md147### Step 2: Find All Exact OccurrencesCOMMENT
LOWskills/update-provider-models/SKILL.md161### Step 3: Remove from Type DefinitionsCOMMENT
LOWskills/update-provider-models/SKILL.md165### Step 4: Update DocumentationCOMMENT
LOWskills/update-provider-models/SKILL.md171### Step 5: Update ExamplesCOMMENT
LOWskills/update-provider-models/SKILL.md177### Step 6: Update Tests and SnapshotsCOMMENT
LOWskills/update-provider-models/SKILL.md185### Step 7: Run TestsCOMMENT
Verbosity Indicators39 hits · 64 pts
SeverityFileLineSnippetContext
LOWexamples/ai-functions/src/generate-video/xai/extend.ts12 // Step 1: Generate a short source video.COMMENT
LOWexamples/ai-functions/src/generate-video/xai/extend.ts35 // Step 2: Extend the video with a new scene.COMMENT
LOW…ai-functions/src/generate-video/xai/edit-concurrent.ts8 // Step 1: Apply first editCOMMENT
LOW…ai-functions/src/generate-video/xai/edit-concurrent.ts35 // Step 2: Apply two more edits concurrently, building on step 1COMMENT
LOWpackages/alibaba/src/alibaba-video-model.ts462 // Step 1: Create taskCOMMENT
LOWpackages/alibaba/src/alibaba-video-model.ts493 // Step 2: Poll for task completionCOMMENT
LOWpackages/xai/src/xai-video-model.ts391 // Step 1: Create video generation/edit/extension requestCOMMENT
LOWpackages/xai/src/xai-video-model.ts412 // Step 2: Poll for completionCOMMENT
LOWpackages/ai/src/generate-text/generate-text.test.ts2103 // Step 0: no previous stepsCOMMENT
LOWpackages/ai/src/generate-text/generate-text.test.ts2106 // Step 1: has step 0's resultCOMMENT
LOWpackages/ai/src/generate-text/generate-text.test.ts2116 // Step 2: has step 0 and step 1's resultsCOMMENT
LOWpackages/ai/src/generate-text/generate-text.test.ts8701 // Step 0: just the initial user messageCOMMENT
LOWpackages/ai/src/generate-text/generate-text.test.ts8704 // Step 1: user message + assistant message + tool messageCOMMENT
LOWpackages/ai/src/generate-text/generate-text.test.ts8707 // Step 2: user message + assistant + tool + assistant + toolCOMMENT
LOWpackages/ai/src/generate-text/generate-text.test.ts8710 // Step 3: continued accumulationCOMMENT
LOWpackages/ai/src/generate-text/generate-text.test.ts8713 // Step 4: continued accumulationCOMMENT
LOWpackages/ai/src/generate-text/generate-text.test.ts7615 // Step 1: text + server_tool_use (code_execution) + 2 rollDie callsCOMMENT
LOWpackages/ai/src/generate-text/generate-text.test.ts7670 // Step 2: 2 rollDie calls (round 2)COMMENT
LOWpackages/ai/src/generate-text/generate-text.test.ts7714 // Step 3: 2 rollDie calls (round 3)COMMENT
LOWpackages/ai/src/generate-text/generate-text.test.ts7758 // Step 4: 2 rollDie calls (round 4 - final round)COMMENT
LOWpackages/ai/src/generate-text/generate-text.test.ts7802 // Step 5: code_execution_tool_result + final textCOMMENT
LOWpackages/ai/src/generate-text/stream-text.test.ts24893 // Step 0: just the initial user messageCOMMENT
LOWpackages/ai/src/generate-text/stream-text.test.ts24896 // Step 1: user message + assistant message + tool messageCOMMENT
LOWpackages/ai/src/generate-text/stream-text.test.ts24899 // Step 2: user message + assistant + tool + assistant + toolCOMMENT
LOWpackages/ai/src/generate-text/stream-text.test.ts24902 // Step 3: continued accumulationCOMMENT
LOWpackages/ai/src/generate-text/stream-text.test.ts24905 // Step 4: continued accumulationCOMMENT
LOWpackages/ai/src/generate-text/stream-text.test.ts23907 // Step 1: text + server_tool_use (code_execution) + rollDie callCOMMENT
LOWpackages/ai/src/generate-text/stream-text.test.ts23964 // Step 2: rollDie call (player2)COMMENT
LOWpackages/ai/src/generate-text/stream-text.test.ts24006 // Step 3: rollDie calls (round 2)COMMENT
LOWpackages/ai/src/generate-text/stream-text.test.ts24048 // Step 4: more rollDie callsCOMMENT
LOWpackages/ai/src/generate-text/stream-text.test.ts24090 // Step 5: code_execution_tool_result + final textCOMMENT
LOWpackages/ai/src/generate-text/stream-text.test.ts25615 // Step 1: tool call without resultCOMMENT
LOWpackages/ai/src/generate-text/stream-text.test.ts25640 // Step 2: tool-error arrivesCOMMENT
LOWpackages/workflow/src/workflow-agent.test.ts1326 // Step 1: tool call (executed), Step 2: text completion (no tools)COMMENT
LOWpackages/klingai/src/klingai-video-model.ts299 // Step 1: Create the taskCOMMENT
LOWpackages/klingai/src/klingai-video-model.ts324 // Step 2: Poll for task completionCOMMENT
LOW…__fixtures__/anthropic-combined-context-editing.1.json14 "text": "# 25 × 37\n\nLet me break this down into easier parts:\n\n## Method: Split 37 into 30 + 7\n\n**25 × 37 = CODE
LOW…d/src/codemods/v5/rename-reasoning-to-reasoningText.ts15 // Step 1: Find destructuring from `generateText()`COMMENT
LOW…d/src/codemods/v5/rename-reasoning-to-reasoningText.ts120 // Step 3: Rename `reasoning` to `reasoningText` in the identified pathsCOMMENT
Modern AI Meta-Vocabulary16 hits · 46 pts
SeverityFileLineSnippetContext
MEDIUM…-functions/src/middleware/your-guardrail-middleware.ts28 // Note: streaming guardrails are difficult to implement, becauseCOMMENT
MEDIUM…ai/src/responses/__fixtures__/xai-x-search-tool.1.json20 "text": "### What People Are Saying About AI on X (as of Late October 2025)\n\nBased on recent posts on X (forCODE
MEDIUM…rc/responses/__fixtures__/xai-x-search-tool.chunks.txt1754{"sequence_number":1753,"type":"response.output_text.done","content_index":0,"item_id":"msg_b7b464ea-cc85-d44a-0f2f-1f73CODE
MEDIUM…rc/responses/__fixtures__/xai-x-search-tool.chunks.txt1754{"sequence_number":1753,"type":"response.output_text.done","content_index":0,"item_id":"msg_b7b464ea-cc85-d44a-0f2f-1f73CODE
MEDIUM…rc/responses/__fixtures__/xai-x-search-tool.chunks.txt1754{"sequence_number":1753,"type":"response.output_text.done","content_index":0,"item_id":"msg_b7b464ea-cc85-d44a-0f2f-1f73CODE
MEDIUM…rc/responses/__fixtures__/xai-x-search-tool.chunks.txt1755{"sequence_number":1754,"type":"response.content_part.done","content_index":0,"item_id":"msg_b7b464ea-cc85-d44a-0f2f-1f7CODE
MEDIUM…rc/responses/__fixtures__/xai-x-search-tool.chunks.txt1755{"sequence_number":1754,"type":"response.content_part.done","content_index":0,"item_id":"msg_b7b464ea-cc85-d44a-0f2f-1f7CODE
MEDIUM…rc/responses/__fixtures__/xai-x-search-tool.chunks.txt1755{"sequence_number":1754,"type":"response.content_part.done","content_index":0,"item_id":"msg_b7b464ea-cc85-d44a-0f2f-1f7CODE
MEDIUM…rc/responses/__fixtures__/xai-x-search-tool.chunks.txt1756{"sequence_number":1755,"type":"response.output_item.done","item":{"content":[{"type":"output_text","text":"### Latest VCODE
MEDIUM…rc/responses/__fixtures__/xai-x-search-tool.chunks.txt1756{"sequence_number":1755,"type":"response.output_item.done","item":{"content":[{"type":"output_text","text":"### Latest VCODE
MEDIUM…rc/responses/__fixtures__/xai-x-search-tool.chunks.txt1756{"sequence_number":1755,"type":"response.output_item.done","item":{"content":[{"type":"output_text","text":"### Latest VCODE
MEDIUM…rc/responses/__fixtures__/xai-x-search-tool.chunks.txt1757{"sequence_number":1756,"type":"response.completed","response":{"created_at":1764611504,"id":"b7b464ea-cc85-d44a-0f2f-1fCODE
MEDIUM…rc/responses/__fixtures__/xai-x-search-tool.chunks.txt1757{"sequence_number":1756,"type":"response.completed","response":{"created_at":1764611504,"id":"b7b464ea-cc85-d44a-0f2f-1fCODE
MEDIUM…rc/responses/__fixtures__/xai-x-search-tool.chunks.txt1757{"sequence_number":1756,"type":"response.completed","response":{"created_at":1764611504,"id":"b7b464ea-cc85-d44a-0f2f-1fCODE
MEDIUM…anthropic/src/__fixtures__/anthropic-compaction.1.json9 "content": "## Summary of Conversation\n\n### Task Context\nThe user shared a very large reference document about CODE
MEDIUM…pic/src/__fixtures__/anthropic-compaction.1.chunks.txt4{"type":"content_block_delta","index":0,"delta":{"type":"compaction_delta","content":"## Summary of Conversation\n\n### CODE
Hallucination Indicators2 hits · 20 pts
SeverityFileLineSnippetContext
CRITICALpackages/ai/src/ui/chat.ts509 this.activeResponse.state.message.parts.map(updatePart);CODE
CRITICALpackages/ai/src/ui/chat.ts558 this.activeResponse.state.message.parts.map(updatePart);CODE
Over-Commented Block16 hits · 16 pts
SeverityFileLineSnippetContext
LOWexamples/ai-functions/src/stream-text/google/caching.ts41 // e.g.COMMENT
LOW…mples/ai-functions/src/generate-text/google/caching.ts21 // thoughtsTokenCount: 634,COMMENT
LOW…mples/ai-functions/src/generate-text/google/caching.ts41 // cachedContentTokenCount: 2027,COMMENT
LOW…s/src/generate-text/anthropic/cache-control-beta-1h.ts101 // cache_creation: { ephemeral_5m_input_tokens: 0, ephemeral_1h_input_tokens: 0 },COMMENT
LOW…rate-text/anthropic/cache-control-beta-1h-streaming.ts101 console.log(COMMENT
LOW…functions/src/generate-text/huggingface/temperature.ts21 // temperature: 1.5,COMMENT
LOWpackages/tui/src/tui/terminal-renderer.ts161 #status = streamingStatus;COMMENT
LOWpackages/harness-codex/src/bridge/index.ts1// Long-running process that runs alongside the `codex` CLI in the sandbox.COMMENT
LOWpackages/provider-utils/src/secure-json-parse.test.ts1// Licensed under BSD-3-Clause (this file only)COMMENT
LOWpackages/provider-utils/src/secure-json-parse.ts1// Licensed under BSD-3-Clause (this file only)COMMENT
LOWpackages/harness/src/v1/harness-v1-stream-part.ts61 // Tool calls, approvals, results — reuse V4 primitives.COMMENT
LOWpackages/devtools/src/viewer/server.ts41// We rely exclusively on an explicit env flag to avoid false positives inCOMMENT
LOWpackages/ai/src/util/deep-partial.ts1// License for this File only:COMMENT
LOWpackages/ai/src/util/value-of.ts1// License for this File only:COMMENT
LOW.github/dependabot.yml1# Dependabot configuration — migrated from .github/renovate.json5COMMENT
LOW.github/workflows/update-model-settings.yml1# Update Gateway Model SettingsCOMMENT
AI Slop Vocabulary5 hits · 12 pts
SeverityFileLineSnippetContext
MEDIUMpackages/harness-codex/src/codex-harness.test.ts195 "node /tmp/harness/codex/bridge.mjs --workdir '/vercel/sandbox/codex-s1; env > /tmp/workdir-leak #' --bridge-stateCODE
MEDIUM…ages/deepseek/src/chat/__fixtures__/deepseek-text.json11 "content": "## **Holiday Name: Gratitude of Small Things Day (GST Day)**\n\n**Date:** The first Saturday after tCODE
MEDIUM…ai/src/responses/__fixtures__/xai-x-search-tool.1.json20 "text": "### What People Are Saying About AI on X (as of Late October 2025)\n\nBased on recent posts on X (forCODE
MEDIUM…ai/src/responses/__fixtures__/xai-x-search-tool.1.json20 "text": "### What People Are Saying About AI on X (as of Late October 2025)\n\nBased on recent posts on X (forCODE
MEDIUM…anthropic/src/__fixtures__/anthropic-compaction.1.json9 "content": "## Summary of Conversation\n\n### Task Context\nThe user shared a very large reference document about CODE
Self-Referential Comments4 hits · 12 pts
SeverityFileLineSnippetContext
MEDIUM…/__fixtures__/anthropic-code-execution-20250825.2.json18 "file_text": "import pandas as pd\nimport os\n\ndef fibonacci(n):\n \"\"\"\n Calculate the nth Fibonacci nCODE
MEDIUM.github/workflows/update-model-settings.yml151 # Create the remote branch at the base tip (or reset an orphanedCOMMENT
MEDIUM.github/workflows/backport.yml449 # Create a new branch from the latest release branch for the backportCOMMENT
MEDIUM.github/workflows/backport.yml626 # Create the backport PRCOMMENT
Fake / Example Data9 hits · 9 pts
SeverityFileLineSnippetContext
LOW…enerate-text/openai/responses-tool-search-namespace.ts33 name: 'Jane Doe',CODE
LOWpackages/baseten/src/baseten-provider.ts148 return new OpenAICompatibleChatLanguageModel(modelId ?? 'placeholder', {CODE
LOWpackages/baseten/src/baseten-provider.unit.test.ts166 'placeholder',CODE
LOWpackages/langchain/src/utils.test.ts2188 arguments: { to: 'user@example.com' },CODE
LOWpackages/langchain/src/utils.test.ts2238 input: { to: 'user@example.com' },CODE
LOW…nteractions/google-interactions-language-model.test.ts407 "text": "{"name":"John Doe","age":30}",CODE
LOWpackages/ai/src/prompt/create-tool-model-output.test.ts362 name: 'John Doe',CODE
LOWpackages/ai/src/prompt/create-tool-model-output.test.ts401 "name": "John Doe",CODE
LOW…responses/huggingface-responses-language-model.test.ts1087 text: '{"name": "John Doe", "age": 30}',CODE
Slop Phrases2 hits · 5 pts
SeverityFileLineSnippetContext
MEDIUM…-functions/src/generate-text/amazon-bedrock/api-key.ts36 // For demonstration purposes - in real applications, load from secure environmentCOMMENT
MEDIUM…c/src/__fixtures__/anthropic-web-fetch-tool.error.json29 "text": "I'm unable to access the PDF document at that URL as the web_fetch tool is currently unavailable. To helpCODE
Redundant / Tautological Comments2 hits · 3 pts
SeverityFileLineSnippetContext
LOW…/__fixtures__/anthropic-code-execution-20250825.2.json18 "file_text": "import pandas as pd\nimport os\n\ndef fibonacci(n):\n \"\"\"\n Calculate the nth Fibonacci nCODE
LOW.github/workflows/slack-team-review-notification.yml23 # Check if ai-sdk team is in the requested teamsCOMMENT
Deep Nesting2 hits · 2 pts
SeverityFileLineSnippetContext
LOWexamples/next-fastapi/api/index.py31CODE
LOWexamples/next-fastapi/api/utils/prompt.py14CODE
Overly Generic Function Names1 hit · 2 pts
SeverityFileLineSnippetContext
LOWpackages/ai/src/util/value-of.ts40 * export function getData(name: string): ValueOf<typeof data> {COMMENT