2.6

Adjusted Signal

2.6

Raw Pattern Score

100%

Time Factor

2026-10-31

Last Push

27.6K

Stars

TypeScript

Language

1.4M

Lines of Code

8.8K

Files

1.6K

Pattern Hits

2026-10-31

Scan Date

0.04

HC Hit Rate

Risk Review · Payload v1

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

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

Cognitive Ownership Risk 4.6/100 · LOW

Can maintainers explain intent, assumptions, and trade-offs? 1175 finding(s).

Hallucinated Dependency & Supply Chain Risk 7.4/100 · LOW

Are imports declared and package/API names verified? 357 finding(s).

Agent Over-Engineering Ratio 4.2/100 · LOW

Are wrappers, guards, and repeated structures necessary? 1097 finding(s).

PR Review Velocity Impact 11.7/100 · LOW

Which changes need focused human review? 1582 finding(s).

What These Metrics Mean

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

Pattern-Signal History

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

Severity Breakdown

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

CRITICAL 6HIGH 338MEDIUM 90LOW 1148

Directory Score Breakdown

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

Pattern Findings

The scanner identified 1582 distinct pattern matches across 17 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a detector match to inspect in context. Expand any category row to inspect the individual file paths, line numbers, code snippets, and the lexical context (CODE, COMMENT, or STRING) in which each match was detected.

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

Cross-Language Confusion (JS/TS)324 hits · 1995 pts

Severity	File	Line	Snippet	Context
HIGH	…ns/src/middleware/embedding/google-default-settings.ts	35	print('Embedding length:', result.embedding.length);	CODE
HIGH	…/ai-functions/src/start-batch/google/provider-tools.ts	30	print('Started batch:', batch);	CODE
HIGH	…/ai-functions/src/start-batch/google/provider-tools.ts	36	print('Result:', item);	CODE
HIGH	examples/ai-functions/src/start-batch/google/image.ts	27	print('Started batch:', batch);	CODE
HIGH	examples/ai-functions/src/start-batch/google/image.ts	31	print('Batch status:', status);	CODE
HIGH	examples/ai-functions/src/start-batch/google/image.ts	44	print('Error:', { id: item.id, error: item.error });	CODE
HIGH⚡	…ai-functions/src/start-batch/google/cancel-and-list.ts	25	print('Started batch:', batch);	CODE
HIGH⚡	…ai-functions/src/start-batch/google/cancel-and-list.ts	28	print(	CODE
HIGH⚡	…ai-functions/src/start-batch/google/cancel-and-list.ts	32	print('Next cursor:', page.nextCursor);	CODE
HIGH⚡	…ai-functions/src/start-batch/google/cancel-and-list.ts	35	print('Cancellation requested for:', batch.id);	CODE
HIGH⚡	…ai-functions/src/start-batch/google/cancel-and-list.ts	38	print('Batch status:', status);	CODE
HIGH	examples/ai-functions/src/start-batch/google/basic.ts	33	print('Started batch:', batch);	CODE
HIGH	examples/ai-functions/src/start-batch/google/basic.ts	37	print('Batch status:', status);	CODE
HIGH	examples/ai-functions/src/start-batch/google/basic.ts	48	print('Result:', {	CODE
HIGH	examples/ai-functions/src/start-batch/google/basic.ts	53	print('Error:', { id: item.id, error: item.error });	CODE
HIGH⚡	…es/ai-functions/src/start-batch/google/client-tools.ts	41	print('Started batch:', batch);	CODE
HIGH⚡	…es/ai-functions/src/start-batch/google/client-tools.ts	48	print('Result:', item);	CODE
HIGH⚡	…es/ai-functions/src/start-batch/google/client-tools.ts	53	print('Client tool execute calls:', executeCallCount);	CODE
HIGH	…les/ai-functions/src/start-batch/xai/provider-tools.ts	30	print('Started batch:', batch);	CODE
HIGH	…les/ai-functions/src/start-batch/xai/provider-tools.ts	36	print('Result:', item);	CODE
HIGH	examples/ai-functions/src/start-batch/xai/image.ts	27	print('Started batch:', batch);	CODE
HIGH	examples/ai-functions/src/start-batch/xai/image.ts	31	print('Batch status:', status);	CODE
HIGH	examples/ai-functions/src/start-batch/xai/image.ts	44	print('Error:', { id: item.id, error: item.error });	CODE
HIGH⚡	…es/ai-functions/src/start-batch/xai/cancel-and-list.ts	25	print('Started batch:', batch);	CODE
HIGH⚡	…es/ai-functions/src/start-batch/xai/cancel-and-list.ts	28	print(	CODE
HIGH⚡	…es/ai-functions/src/start-batch/xai/cancel-and-list.ts	32	print('Next cursor:', page.nextCursor);	CODE
HIGH⚡	…es/ai-functions/src/start-batch/xai/cancel-and-list.ts	35	print('Cancellation requested for:', batch.id);	CODE
HIGH⚡	…es/ai-functions/src/start-batch/xai/cancel-and-list.ts	38	print('Batch status:', status);	CODE
HIGH	examples/ai-functions/src/start-batch/xai/basic.ts	33	print('Started batch:', batch);	CODE
HIGH	examples/ai-functions/src/start-batch/xai/basic.ts	37	print('Batch status:', status);	CODE
HIGH	examples/ai-functions/src/start-batch/xai/basic.ts	48	print('Result:', {	CODE
HIGH	examples/ai-functions/src/start-batch/xai/basic.ts	53	print('Error:', { id: item.id, error: item.error });	CODE
HIGH⚡	…mples/ai-functions/src/start-batch/xai/client-tools.ts	41	print('Started batch:', batch);	CODE
HIGH⚡	…mples/ai-functions/src/start-batch/xai/client-tools.ts	48	print('Result:', item);	CODE
HIGH⚡	…mples/ai-functions/src/start-batch/xai/client-tools.ts	53	print('Client tool execute calls:', executeCallCount);	CODE
HIGH	…-functions/src/start-batch/anthropic/provider-tools.ts	30	print('Started batch:', batch);	CODE
HIGH	…-functions/src/start-batch/anthropic/provider-tools.ts	36	print('Result:', item);	CODE
HIGH⚡	…functions/src/start-batch/anthropic/cancel-and-list.ts	25	print('Started batch:', batch);	CODE
HIGH⚡	…functions/src/start-batch/anthropic/cancel-and-list.ts	28	print(	CODE
HIGH⚡	…functions/src/start-batch/anthropic/cancel-and-list.ts	32	print('Next cursor:', page.nextCursor);	CODE
HIGH⚡	…functions/src/start-batch/anthropic/cancel-and-list.ts	35	print('Cancellation requested for:', batch.id);	CODE
HIGH⚡	…functions/src/start-batch/anthropic/cancel-and-list.ts	38	print('Batch status:', status);	CODE
HIGH	…amples/ai-functions/src/start-batch/anthropic/basic.ts	33	print('Started batch:', batch);	CODE
HIGH	…amples/ai-functions/src/start-batch/anthropic/basic.ts	37	print('Batch status:', status);	CODE
HIGH	…amples/ai-functions/src/start-batch/anthropic/basic.ts	48	print('Result:', {	CODE
HIGH	…amples/ai-functions/src/start-batch/anthropic/basic.ts	53	print('Error:', { id: item.id, error: item.error });	CODE
HIGH⚡	…ai-functions/src/start-batch/anthropic/client-tools.ts	41	print('Started batch:', batch);	CODE
HIGH⚡	…ai-functions/src/start-batch/anthropic/client-tools.ts	48	print('Result:', item);	CODE
HIGH⚡	…ai-functions/src/start-batch/anthropic/client-tools.ts	53	print('Client tool execute calls:', executeCallCount);	CODE
HIGH	examples/ai-functions/src/start-batch/gateway/basic.ts	30	print('Started batch:', batch);	CODE
HIGH	examples/ai-functions/src/start-batch/gateway/basic.ts	34	print('Batch status:', status);	CODE
HIGH	examples/ai-functions/src/start-batch/gateway/basic.ts	45	print('Result:', {	CODE
HIGH	examples/ai-functions/src/start-batch/gateway/basic.ts	50	print('Error:', { id: item.id, error: item.error });	CODE
HIGH	examples/ai-functions/src/start-batch/gateway/cancel.ts	21	print(	CODE
HIGH	examples/ai-functions/src/start-batch/gateway/cancel.ts	29	print('Batch status:', status);	CODE
HIGH	examples/ai-functions/src/start-batch/gateway/cancel.ts	41	print('Result:', item);	CODE
HIGH⚡	…/ai-functions/src/start-batch/openai/provider-tools.ts	35	print('Started batch:', batch);	CODE
HIGH⚡	…/ai-functions/src/start-batch/openai/provider-tools.ts	39	print('Batch status:', status);	CODE
HIGH⚡	…/ai-functions/src/start-batch/openai/provider-tools.ts	46	print('Result:', item);	CODE
HIGH⚡	…ai-functions/src/start-batch/openai/cancel-and-list.ts	25	print('Started batch:', batch);	CODE
264 more matches not shown…

Hyper-Verbose Identifiers1047 hits · 1062 pts

Severity	File	Line	Snippet	Context
LOW	tools/analyze-downloads/src/analyze-ui-frameworks.ts	30	function aggregateDownloadsForLastNMajorReleases(	CODE
LOW	contributing/testing.md	111	function prepareChunksFixtureResponse(filename: string) {	CODE
LOW	contributing/testing.md	129	function prepareChunksFixtureResponse(filename: string) {	CODE
LOW	architecture/sandbox-abstraction.md	98	async function createDockerNetworkSandboxSession(	CODE
LOW	architecture/sandbox-abstraction.md	114	async function resumeDockerNetworkSandboxSession(	CODE
LOW	…es/ai-functions/src/benchmark/stream-text-benchmark.ts	139	async function benchmarkConcurrentStreams() {	CODE
LOW	…es/ai-functions/src/benchmark/stream-text-benchmark.ts	185	async function benchmarkStreamWithToolCalls() {	CODE
LOW	examples/ai-functions/src/stream-text/gateway/auth.ts	107	async function testAuthenticationScenario(scenario: (typeof testScenarios)[0]) {	CODE
LOW	…-functions/src/harness-agent/github-copilot/_create.ts	22	export function getGitHubCopilotExampleModel(): string {	CODE
LOW	…nctions/src/ui-message/migrate-deprecated-raw-input.ts	5	function migrateDeprecatedRawInput(messages: UIMessage[]): UIMessage[] {	CODE
LOW	…ai-functions/src/lib/download-openai-container-file.ts	4	export async function downloadOpenaiContainerFile(	CODE
LOW	examples/ai-functions/src/lib/codex-acp-handoff.ts	83	export async function readACPResumeHandoffState({	CODE
LOW	examples/ai-functions/src/lib/codex-acp-handoff.ts	101	export async function readACPContinueHandoffState({	CODE
LOW	examples/ai-functions/src/lib/codex-acp-handoff.ts	127	export async function waitForACPCompletedRecoveryLog({	CODE
LOW	examples/ai-functions/src/lib/codex-acp-handoff.ts	153	export async function terminateACPBridgeForRecovery({	CODE
LOW	examples/ai-functions/src/lib/codex-acp-handoff.ts	186	export async function assertACPRecoveryArtifactsExcludeSecrets({	CODE
LOW	examples/ai-functions/src/lib/codex-acp-handoff.ts	218	function getACPBridgeRecoveryCoordinates({	CODE
LOW	examples/ai-functions/src/lib/delete-uploaded-skill.ts	1	export async function deleteUploadedOpenAISkill({	CODE
LOW	examples/ai-functions/src/lib/delete-uploaded-skill.ts	26	export async function deleteUploadedAnthropicSkill({	CODE
LOW	…/ai-functions/src/lib/download-azure-container-file.ts	4	export async function downloadAzureContainerFile(	CODE
LOW	…es/ai-functions/src/lib/anthropic-workload-identity.ts	7	export function createWorkloadIdentityAnthropic() {	CODE
LOW	…ples/ai-functions/src/lib/harness-tool-model-output.ts	25	export async function createHarnessToolModelOutputFixture(): Promise<HarnessToolModelOutputFixture> {	CODE
LOW	…ples/ai-functions/src/lib/harness-tool-model-output.ts	81	export function assertHarnessToolModelOutputResult({	CODE
LOW	examples/ai-functions/src/lib/harness-tool-approval.ts	7	export function createToolApprovalResponseMessages({	CODE
LOW	examples/ai-functions/src/lib/harness-tool-approval.ts	23	export function createToolApprovalResponsesMessages({	CODE
LOW	…ons/src/generate-text/mock/return-await-stack-trace.ts	41	function createWrappedModelWithoutAwait() {	CODE
LOW	…ons/src/generate-text/mock/return-await-stack-trace.ts	44	async function wrappedDoGenerateWithoutAwait(	CODE
LOW	…ons/src/generate-text/mock/return-await-stack-trace.ts	55	function createWrappedModelWithAwait() {	CODE
LOW	…ons/src/generate-text/mock/return-await-stack-trace.ts	58	async function wrappedDoGenerateWithAwait(	CODE
LOW	…ons/src/generate-text/mock/return-await-stack-trace.ts	81	async function sdkMiddlewareWithoutAwait() {	CODE
LOW	…ons/src/generate-text/mock/return-await-stack-trace.ts	93	async function sdkModelBoundaryWithoutAwait() {	CODE
LOW	…ons/src/generate-text/mock/return-await-stack-trace.ts	100	async function sdkModelBoundaryWithAwait() {	CODE
LOW	…s-e2e-next/app/harness/cline/workflow-stepped/page.tsx	10	export default function HarnessWorkflowSteppedPage() {	CODE
LOW	…s-e2e-next/app/harness/cline/weather-approval/page.tsx	10	export default function HarnessClineWeatherApprovalPage() {	CODE
LOW	…ss-e2e-next/app/harness/cline/basic-with-stop/page.tsx	10	export default function HarnessClineBasicWithStopPage() {	CODE
LOW	…ess-e2e-next/app/harness/cline/workflow-timed/page.tsx	10	export default function HarnessClineWorkflowTimedPage() {	CODE
LOW	…ness-e2e-next/app/harness/cline/ai-sdk-coding/page.tsx	10	export default function HarnessClineAiSdkCodingPage() {	CODE
LOW	…next/app/harness/claude-code/workflow-stepped/page.tsx	10	export default function HarnessWorkflowSteppedPage() {	CODE
LOW	…next/app/harness/claude-code/weather-approval/page.tsx	10	export default function HarnessClaudeCodeWeatherApprovalPage() {	CODE
LOW	…-next/app/harness/claude-code/basic-with-stop/page.tsx	10	export default function HarnessClaudeCodeBasicWithStopPage() {	CODE
LOW	…ness-e2e-next/app/harness/claude-code/weather/page.tsx	10	export default function HarnessClaudeCodeWeatherPage() {	CODE
LOW	…e-next/app/harness/claude-code/workflow-timed/page.tsx	10	export default function HarnessClaudeCodeWorkflowTimedPage() {	CODE
LOW	…e2e-next/app/harness/claude-code/weather-only/page.tsx	10	export default function HarnessClaudeCodeWeatherPage() {	CODE
LOW	…2e-next/app/harness/claude-code/ai-sdk-coding/page.tsx	10	export default function HarnessClaudeCodeAiSdkCodingPage() {	CODE
LOW	…e-next/app/harness/acp-codex/workflow-stepped/page.tsx	10	export default function CodexACPWorkflowSteppedPage() {	CODE
LOW	…e-next/app/harness/acp-codex/weather-approval/page.tsx	10	export default function CodexACPWeatherApprovalPage() {	CODE
LOW	…2e-next/app/harness/acp-codex/basic-with-stop/page.tsx	10	export default function CodexACPBasicWithStopPage() {	CODE
LOW	…e2e-next/app/harness/acp-codex/workflow-timed/page.tsx	10	export default function CodexACPWorkflowTimedPage() {	CODE
LOW	…-e2e-next/app/harness/cursor/workflow-stepped/page.tsx	10	export default function CursorWorkflowSteppedPage() {	CODE
LOW	…-e2e-next/app/harness/cursor/weather-approval/page.tsx	10	export default function CursorWeatherApprovalPage() {	CODE
LOW	…s-e2e-next/app/harness/codex/workflow-stepped/page.tsx	10	export default function HarnessWorkflowSteppedPage() {	CODE
LOW	…s-e2e-next/app/harness/codex/weather-approval/page.tsx	10	export default function HarnessCodexWeatherApprovalPage() {	CODE
LOW	…ss-e2e-next/app/harness/codex/basic-with-stop/page.tsx	10	export default function HarnessCodexBasicWithStopPage() {	CODE
LOW	…ess-e2e-next/app/harness/codex/workflow-timed/page.tsx	10	export default function HarnessCodexWorkflowTimedPage() {	CODE
LOW	…ness-e2e-next/app/harness/codex/ai-sdk-coding/page.tsx	10	export default function HarnessCodexAiSdkCodingPage() {	CODE
LOW	…t/app/harness/github-copilot/workflow-stepped/page.tsx	10	export default function GitHubCopilotWorkflowSteppedPage() {	CODE
LOW	…t/app/harness/github-copilot/weather-approval/page.tsx	10	export default function GitHubCopilotWeatherApprovalPage() {	CODE
LOW	…xt/app/harness/github-copilot/basic-with-stop/page.tsx	10	export default function GitHubCopilotBasicWithStopPage() {	CODE
LOW	…ext/app/harness/github-copilot/workflow-timed/page.tsx	10	export default function GitHubCopilotWorkflowTimedPage() {	CODE
LOW	…-next/app/harness/github-copilot/weather-only/page.tsx	10	export default function GitHubCopilotWeatherOnlyPage() {	CODE
987 more matches not shown…

Decorative Section Separators50 hits · 150 pts

Severity	File	Line	Snippet	Context
MEDIUM	…c/stream-text/anthropic/fine-grained-tool-streaming.ts	47	// ── stream events ─────────────────────────────────────────────────────────	COMMENT
MEDIUM	…c/stream-text/anthropic/fine-grained-tool-streaming.ts	142	// ── diagnosis ─────────────────────────────────────────────────────────────	COMMENT
MEDIUM	…mazon-bedrock/anthropic-fine-grained-tool-streaming.ts	128	// ── diagnosis ─────────────────────────────────────────────────────────────	COMMENT
MEDIUM	…rc/realtime-model/v4/realtime-model-v4-server-event.ts	57	// ── Session lifecycle ──────────────────────────────────────────────	COMMENT
MEDIUM	…rc/realtime-model/v4/realtime-model-v4-server-event.ts	68	// ── Input audio buffer ─────────────────────────────────────────────	COMMENT
MEDIUM	…rc/realtime-model/v4/realtime-model-v4-server-event.ts	86	// ── Conversation items ─────────────────────────────────────────────	COMMENT
MEDIUM	…rc/realtime-model/v4/realtime-model-v4-server-event.ts	100	// ── Response lifecycle ─────────────────────────────────────────────	COMMENT
MEDIUM	…rc/realtime-model/v4/realtime-model-v4-server-event.ts	113	// ── Output item lifecycle ──────────────────────────────────────────	COMMENT
MEDIUM	…rc/realtime-model/v4/realtime-model-v4-server-event.ts	139	// ── Audio output ───────────────────────────────────────────────────	COMMENT
MEDIUM	…rc/realtime-model/v4/realtime-model-v4-server-event.ts	158	// ── Audio transcript output ────────────────────────────────────────	COMMENT
MEDIUM	…rc/realtime-model/v4/realtime-model-v4-server-event.ts	178	// ── Text output ────────────────────────────────────────────────────	COMMENT
MEDIUM	…rc/realtime-model/v4/realtime-model-v4-server-event.ts	198	// ── Function calling ───────────────────────────────────────────────	COMMENT
MEDIUM	…rc/realtime-model/v4/realtime-model-v4-server-event.ts	229	// ── Error ──────────────────────────────────────────────────────────	COMMENT
MEDIUM	…rc/realtime-model/v4/realtime-model-v4-server-event.ts	238	// ── Custom / provider-specific ────────────────────────────────────	COMMENT
MEDIUM	…rc/realtime-model/v4/realtime-model-v4-client-event.ts	11	// ── Session ────────────────────────────────────────────────────────	COMMENT
MEDIUM	…rc/realtime-model/v4/realtime-model-v4-client-event.ts	43	// ── Input audio buffer ─────────────────────────────────────────────	COMMENT
MEDIUM	…rc/realtime-model/v4/realtime-model-v4-client-event.ts	60	// ── Conversation items ─────────────────────────────────────────────	COMMENT
MEDIUM	…rc/realtime-model/v4/realtime-model-v4-client-event.ts	84	// ── Response control ───────────────────────────────────────────────	COMMENT
MEDIUM	packages/xai/src/xai-video-model-options.ts	140	// ── Runtime schemas ───────────────────────────────────────────────────	COMMENT
MEDIUM	packages/xai/src/xai-video-options.test-d.ts	5	// ── Explicit modes accepted ────────────────────────────────────────	COMMENT
MEDIUM	packages/xai/src/xai-video-options.test-d.ts	70	// ── Plain generation + legacy no-mode compatibility ────────────────	COMMENT
MEDIUM	packages/xai/src/xai-video-options.test-d.ts	188	// ── Discriminated union: illegal combos rejected ───────────────────	COMMENT
MEDIUM	packages/xai/src/xai-video-options.test-d.ts	256	// ── Required companion fields ──────────────────────────────────────	COMMENT
MEDIUM	packages/harness/src/bridge/index.ts	412	// ─── mutable runtime state ──────────────────────────────────────────	COMMENT
MEDIUM	packages/harness/src/bridge/index.ts	554	// ─── persistence (best-effort meta + start config) ──────────────────	COMMENT
MEDIUM	packages/harness/src/bridge/index.ts	585	// ─── wire send + replay ─────────────────────────────────────────────	COMMENT
MEDIUM	packages/harness/src/bridge/index.ts	610	// ─── diagnostics ──────────────────────────────────────────────	COMMENT
MEDIUM	packages/harness/src/bridge/index.ts	718	// ─── inbound routing ────────────────────────────────────────────────	COMMENT
MEDIUM	packages/harness/src/bridge/index.ts	945	// ─── server ─────────────────────────────────────────────────────────	COMMENT
MEDIUM	…ges/harness/src/bridge/disk-replay.integration.test.ts	66	// ── Bridge #1: run a full turn, then "die". ────────────────────────	COMMENT
MEDIUM	…ges/harness/src/bridge/disk-replay.integration.test.ts	66	// ── Bridge #1: run a full turn, then "die". ────────────────────────	COMMENT
MEDIUM	packages/harness/src/utils/sandbox-channel.ts	466	// ─── internals ──────────────────────────────────────────────────────	COMMENT
MEDIUM	packages/harness/src/agent/harness-agent.ts	784	// ─── Internals ──────────────────────────────────────────────────────	COMMENT
MEDIUM	…rness/src/agent/internal/harness-stream-text-result.ts	248	// ─── Writer-side methods used by the driver ────────────────────────	COMMENT
MEDIUM	…rness/src/agent/internal/harness-stream-text-result.ts	629	// ─── Reader-side public surface (StreamTextResult contract) ────────	COMMENT
MEDIUM	…rness/src/agent/internal/harness-stream-text-result.ts	891	// ─── Helpers ────────────────────────────────────────────────────────	COMMENT
MEDIUM	…c/__fixtures__/anthropic-advisor-20250301.1.chunks.txt	7	{"type":"content_block_start","index":1,"content_block":{"type":"advisor_tool_result","tool_use_id":"srvtoolu_01R6zRtm9V	CODE
MEDIUM	…c/__fixtures__/anthropic-advisor-20250301.1.chunks.txt	83	{"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.json	23	"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.ts	40	// ── Session lifecycle ──────────────────────────────────────────	COMMENT
MEDIUM	…es/openai/src/realtime/openai-realtime-event-mapper.ts	51	// ── Input audio buffer ─────────────────────────────────────────	COMMENT
MEDIUM	…es/openai/src/realtime/openai-realtime-event-mapper.ts	74	// ── Conversation items ─────────────────────────────────────────	COMMENT
MEDIUM	…es/openai/src/realtime/openai-realtime-event-mapper.ts	91	// ── Response lifecycle ──────────────────────────────────────────	COMMENT
MEDIUM	…es/openai/src/realtime/openai-realtime-event-mapper.ts	107	// ── Output item lifecycle ───────────────────────────────────────	COMMENT
MEDIUM	…es/openai/src/realtime/openai-realtime-event-mapper.ts	140	// ── Audio output ────────────────────────────────────────────────	COMMENT
MEDIUM	…es/openai/src/realtime/openai-realtime-event-mapper.ts	158	// ── Audio transcript output ─────────────────────────────────────	COMMENT
MEDIUM	…es/openai/src/realtime/openai-realtime-event-mapper.ts	177	// ── Text output ─────────────────────────────────────────────────	COMMENT
MEDIUM	…es/openai/src/realtime/openai-realtime-event-mapper.ts	196	// ── Function calling ────────────────────────────────────────────	COMMENT
MEDIUM⚡	…es/openai/src/realtime/openai-realtime-event-mapper.ts	218	// ── Error ───────────────────────────────────────────────────────	COMMENT
MEDIUM⚡	…es/openai/src/realtime/openai-realtime-event-mapper.ts	228	// ── Pass-through ────────────────────────────────────────────────	COMMENT

Magic Placeholder Names14 hits · 92 pts

Severity	File	Line	Snippet	Context
HIGH	contributing/add-new-tool-to-registry.md	35	apiKeyEnvName: 'YOUR_API_KEY', // Optional: environment variable name for API key	CODE
HIGH	contributing/add-new-tool-to-registry.md	56	apiKeyUrl: 'https://your-api-key-url.com',	CODE
HIGH	…unctions/src/stream-text/azure/responses-web-search.ts	9	* AZURE_API_KEY="<your_api_key>"	COMMENT
HIGH	…i-functions/src/stream-text/azure/responses-file-id.ts	9	* AZURE_API_KEY="<your_api_key>"	COMMENT
HIGH	…ns/src/stream-text/azure/responses-code-interpreter.ts	14	* AZURE_API_KEY="<your_api_key>"	COMMENT
HIGH	…nctions/src/stream-text/azure/responses-file-search.ts	9	* AZURE_API_KEY="<your_api_key>"	COMMENT
HIGH	…ions/src/stream-text/openai/compatible-abort-reason.ts	9	apiKey: process.env.DEEPSEEK_API_KEY ?? 'YOUR_API_KEY',	CODE
HIGH	…ctions/src/generate-text/azure/responses-web-search.ts	9	* AZURE_API_KEY="<your_api_key>"	COMMENT
HIGH	…functions/src/generate-text/azure/responses-file-id.ts	9	* AZURE_API_KEY="<your_api_key>"	COMMENT
HIGH	…/src/generate-text/azure/responses-code-interpreter.ts	14	* AZURE_API_KEY="<your_api_key>"	COMMENT
HIGH	…tions/src/generate-text/azure/responses-file-search.ts	9	* AZURE_API_KEY="<your_api_key>"	COMMENT
HIGH	…-functions/src/generate-text/amazon-bedrock/api-key.ts	38	process.env.AWS_BEARER_TOKEN_BEDROCK \|\| 'your-api-key-here';	CODE
HIGH	packages/amazon-bedrock/src/amazon-bedrock-provider.ts	56	* apiKey: 'your-api-key-here',	COMMENT
HIGH	…ps/docs/app/[lang]/unauthenticated-ai-gateway/page.tsx	32	<a href="https://vercel.com/docs/ai-gateway/getting-started#set-up-your-api-key">	CODE

Structural Annotation Overuse37 hits · 62 pts

Severity	File	Line	Snippet	Context
LOW	examples/ai-functions/src/generate-video/xai/extend.ts	12	// Step 1: Generate a short source video.	COMMENT
LOW	examples/ai-functions/src/generate-video/xai/extend.ts	35	// Step 2: Extend the video with a new scene.	COMMENT
LOW	…ai-functions/src/generate-video/xai/edit-concurrent.ts	8	// Step 1: Apply first edit	COMMENT
LOW	…ai-functions/src/generate-video/xai/edit-concurrent.ts	35	// Step 2: Apply two more edits concurrently, building on step 1	COMMENT
LOW⚡	packages/ai/src/generate-text/generate-text.test.ts	3553	// Step 0: no previous steps	COMMENT
LOW⚡	packages/ai/src/generate-text/generate-text.test.ts	3556	// Step 1: has step 0's result	COMMENT
LOW⚡	packages/ai/src/generate-text/generate-text.test.ts	3566	// Step 2: has step 0 and step 1's results	COMMENT
LOW⚡	packages/ai/src/generate-text/generate-text.test.ts	10986	// Step 0: just the initial user message	COMMENT
LOW⚡	packages/ai/src/generate-text/generate-text.test.ts	10989	// Step 1: user message + assistant message + tool message	COMMENT
LOW⚡	packages/ai/src/generate-text/generate-text.test.ts	10992	// Step 2: user message + assistant + tool + assistant + tool	COMMENT
LOW⚡	packages/ai/src/generate-text/generate-text.test.ts	10995	// Step 3: continued accumulation	COMMENT
LOW⚡	packages/ai/src/generate-text/generate-text.test.ts	10998	// Step 4: continued accumulation	COMMENT
LOW	packages/ai/src/generate-text/generate-text.test.ts	9901	// Step 1: text + server_tool_use (code_execution) + 2 rollDie calls	COMMENT
LOW	packages/ai/src/generate-text/generate-text.test.ts	9956	// Step 2: 2 rollDie calls (round 2)	COMMENT
LOW	packages/ai/src/generate-text/generate-text.test.ts	10000	// Step 3: 2 rollDie calls (round 3)	COMMENT
LOW	packages/ai/src/generate-text/generate-text.test.ts	10044	// Step 4: 2 rollDie calls (round 4 - final round)	COMMENT
LOW	packages/ai/src/generate-text/generate-text.test.ts	10088	// Step 5: code_execution_tool_result + final text	COMMENT
LOW	packages/workflow/src/workflow-agent.test.ts	1859	// Step 1: tool call (executed), Step 2: text completion (no tools)	COMMENT
LOW	…xtures__/anthropic-claude-opus-5-reasoning-high.1.json	14	"text": "## Step 1: Set up the problem\n\nWe want all values of $x$ satisfying\n\n$$f(x) = x^3 - 6x^2 + 11x - 6 =	CODE
LOW	…__fixtures__/anthropic-combined-context-editing.1.json	14	"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.txt	102	{"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.ts	15	// Step 1: Find destructuring from `generateText()`	COMMENT
LOW	…d/src/codemods/v5/rename-reasoning-to-reasoningText.ts	120	// Step 3: Rename `reasoning` to `reasoningText` in the identified paths	COMMENT
LOW	skills/update-provider-models/SKILL.md	31	### Step 1: Identify Scope	COMMENT
LOW	skills/update-provider-models/SKILL.md	42	### Step 2: Find Where Similar Models Are Referenced	COMMENT
LOW	skills/update-provider-models/SKILL.md	52	### Step 3: Update Type Definitions	COMMENT
LOW	skills/update-provider-models/SKILL.md	87	### Step 4: Update Documentation	COMMENT
LOW	skills/update-provider-models/SKILL.md	97	### Step 5: Create or Update Examples	COMMENT
LOW	skills/update-provider-models/SKILL.md	114	### Step 6: Update Tests	COMMENT
LOW	skills/update-provider-models/SKILL.md	120	### Step 7: Run Tests	COMMENT
LOW	skills/update-provider-models/SKILL.md	141	### Step 1: Identify Successor	COMMENT
LOW	skills/update-provider-models/SKILL.md	147	### Step 2: Find All Exact Occurrences	COMMENT
LOW⚡	skills/update-provider-models/SKILL.md	161	### Step 3: Remove from Type Definitions	COMMENT
LOW⚡	skills/update-provider-models/SKILL.md	165	### Step 4: Update Documentation	COMMENT
LOW⚡	skills/update-provider-models/SKILL.md	171	### Step 5: Update Examples	COMMENT
LOW⚡	skills/update-provider-models/SKILL.md	177	### Step 6: Update Tests and Snapshots	COMMENT
LOW⚡	skills/update-provider-models/SKILL.md	185	### Step 7: Run Tests	COMMENT

Hallucination Indicators6 hits · 60 pts

Severity	File	Line	Snippet	Context
CRITICAL	packages/harness-opencode/src/bridge/index.test.ts	1217	client.session.promptAsync.mock.calls.map(	CODE
CRITICAL	packages/harness-opencode/src/bridge/index.test.ts	1254	client.session.promptAsync.mock.calls.every(	CODE
CRITICAL	packages/harness-opencode/src/bridge/index.test.ts	1293	client.session.promptAsync.mock.calls.every(	CODE
CRITICAL	packages/ai/src/ui/chat.ts	634	this.activeResponse.state.message.parts.map(updatePart);	CODE
CRITICAL	packages/ai/src/ui/chat.ts	733	this.activeResponse.state.message.parts.map(updatePart);	CODE
CRITICAL	…ckages/ai/src/realtime/browser-realtime-webrtc.test.ts	111	expect(pc.sender.replaceTrack.mock.calls.map(([track]) => track)).toEqual([	CODE

AI Slop Vocabulary16 hits · 56 pts

Severity	File	Line	Snippet	Context
MEDIUM⚡	tools/run-harness-agent-examples.sh	3	# Run harness-agent examples from examples/ai-functions/src/harness-agent.	COMMENT
MEDIUM⚡	tools/run-harness-agent-examples.sh	6	# tools/run-harness-agent-examples.sh [--harness <name>...] [--example <name>...] [--auth <mode>]	COMMENT
MEDIUM⚡	tools/run-harness-agent-examples.sh	9	# --harness <name> Only run examples for the given harness folder(s)	COMMENT
MEDIUM⚡	tools/run-harness-agent-examples.sh	10	# (e.g. --harness grok-build). Defaults to all harnesses.	COMMENT
MEDIUM⚡	tools/run-harness-agent-examples.sh	19	# helper in its own harness folder. An example missing the required import is	COMMENT
MEDIUM⚡	tools/run-harness-agent-examples.sh	22	# By default every *.ts example in every harness folder is run (slow!).	COMMENT
MEDIUM⚡	tools/run-harness-agent-examples.sh	23	# Only direct children of a harness folder are treated as examples; nested	COMMENT
MEDIUM	tools/run-harness-agent-examples.sh	133	# harness folders. Sorted for stable output.	COMMENT
MEDIUM	tools/run-harness-agent-examples.sh	185	# A temp file accumulates "harness\|example\|STATUS" rows; sorted at the end.	COMMENT
MEDIUM	tools/run-harness-agent-examples.sh	198	# the harness folder is run.	COMMENT
MEDIUM	tools/run-harness-agent-examples.sh	225	# An example must initialize its harness through the folder's custom	COMMENT
MEDIUM	tools/run-harness-agent-examples.sh	267	# No explicit examples: run every runnable *.ts file in the harness	COMMENT
MEDIUM	…ages/deepseek/src/chat/__fixtures__/deepseek-text.json	11	"content": "## Holiday Name: Gratitude of Small Things Day (GST Day)\n\nDate: The first Saturday after t	CODE
MEDIUM⚡	…ai/src/responses/__fixtures__/xai-x-search-tool.1.json	20	"text": "### What People Are Saying About AI on X (as of Late October 2025)\n\nBased on recent posts on X (for	CODE
MEDIUM⚡	…ai/src/responses/__fixtures__/xai-x-search-tool.1.json	20	"text": "### What People Are Saying About AI on X (as of Late October 2025)\n\nBased on recent posts on X (for	CODE
MEDIUM	…anthropic/src/__fixtures__/anthropic-compaction.1.json	9	"content": "## Summary of Conversation\n\n### Task Context\nThe user shared a very large reference document about	CODE

Modern AI Meta-Vocabulary17 hits · 48 pts

Severity	File	Line	Snippet	Context
MEDIUM	…-functions/src/middleware/your-guardrail-middleware.ts	28	// Note: streaming guardrails are difficult to implement, because	COMMENT
MEDIUM⚡	…ai/src/responses/__fixtures__/xai-x-search-tool.1.json	20	"text": "### What People Are Saying About AI on X (as of Late October 2025)\n\nBased on recent posts on X (for	CODE
MEDIUM⚡	…rc/responses/__fixtures__/xai-x-search-tool.chunks.txt	1754	{"sequence_number":1753,"type":"response.output_text.done","content_index":0,"item_id":"msg_b7b464ea-cc85-d44a-0f2f-1f73	CODE
MEDIUM⚡	…rc/responses/__fixtures__/xai-x-search-tool.chunks.txt	1754	{"sequence_number":1753,"type":"response.output_text.done","content_index":0,"item_id":"msg_b7b464ea-cc85-d44a-0f2f-1f73	CODE
MEDIUM⚡	…rc/responses/__fixtures__/xai-x-search-tool.chunks.txt	1754	{"sequence_number":1753,"type":"response.output_text.done","content_index":0,"item_id":"msg_b7b464ea-cc85-d44a-0f2f-1f73	CODE
MEDIUM⚡	…rc/responses/__fixtures__/xai-x-search-tool.chunks.txt	1755	{"sequence_number":1754,"type":"response.content_part.done","content_index":0,"item_id":"msg_b7b464ea-cc85-d44a-0f2f-1f7	CODE
MEDIUM⚡	…rc/responses/__fixtures__/xai-x-search-tool.chunks.txt	1755	{"sequence_number":1754,"type":"response.content_part.done","content_index":0,"item_id":"msg_b7b464ea-cc85-d44a-0f2f-1f7	CODE
MEDIUM⚡	…rc/responses/__fixtures__/xai-x-search-tool.chunks.txt	1755	{"sequence_number":1754,"type":"response.content_part.done","content_index":0,"item_id":"msg_b7b464ea-cc85-d44a-0f2f-1f7	CODE
MEDIUM⚡	…rc/responses/__fixtures__/xai-x-search-tool.chunks.txt	1756	{"sequence_number":1755,"type":"response.output_item.done","item":{"content":[{"type":"output_text","text":"### Latest V	CODE
MEDIUM⚡	…rc/responses/__fixtures__/xai-x-search-tool.chunks.txt	1756	{"sequence_number":1755,"type":"response.output_item.done","item":{"content":[{"type":"output_text","text":"### Latest V	CODE
MEDIUM⚡	…rc/responses/__fixtures__/xai-x-search-tool.chunks.txt	1756	{"sequence_number":1755,"type":"response.output_item.done","item":{"content":[{"type":"output_text","text":"### Latest V	CODE
MEDIUM⚡	…rc/responses/__fixtures__/xai-x-search-tool.chunks.txt	1757	{"sequence_number":1756,"type":"response.completed","response":{"created_at":1764611504,"id":"b7b464ea-cc85-d44a-0f2f-1f	CODE
MEDIUM⚡	…rc/responses/__fixtures__/xai-x-search-tool.chunks.txt	1757	{"sequence_number":1756,"type":"response.completed","response":{"created_at":1764611504,"id":"b7b464ea-cc85-d44a-0f2f-1f	CODE
MEDIUM⚡	…rc/responses/__fixtures__/xai-x-search-tool.chunks.txt	1757	{"sequence_number":1756,"type":"response.completed","response":{"created_at":1764611504,"id":"b7b464ea-cc85-d44a-0f2f-1f	CODE
MEDIUM	…anthropic/src/__fixtures__/anthropic-compaction.1.json	9	"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.txt	4	{"type":"content_block_delta","index":0,"delta":{"type":"compaction_delta","content":"## Summary of Conversation\n\n###	CODE
MEDIUM	packages/amazon-bedrock/CHANGELOG.md	801	ref: https://docs.aws.amazon.com/bedrock/latest/userguide/guardrails-use-converse-api.html	CODE

Verbosity Indicators22 hits · 36 pts

Severity	File	Line	Snippet	Context
LOW	examples/ai-functions/src/generate-video/xai/extend.ts	12	// Step 1: Generate a short source video.	COMMENT
LOW	examples/ai-functions/src/generate-video/xai/extend.ts	35	// Step 2: Extend the video with a new scene.	COMMENT
LOW	…ai-functions/src/generate-video/xai/edit-concurrent.ts	8	// Step 1: Apply first edit	COMMENT
LOW	…ai-functions/src/generate-video/xai/edit-concurrent.ts	35	// Step 2: Apply two more edits concurrently, building on step 1	COMMENT
LOW⚡	packages/ai/src/generate-text/generate-text.test.ts	3553	// Step 0: no previous steps	COMMENT
LOW⚡	packages/ai/src/generate-text/generate-text.test.ts	3556	// Step 1: has step 0's result	COMMENT
LOW⚡	packages/ai/src/generate-text/generate-text.test.ts	3566	// Step 2: has step 0 and step 1's results	COMMENT
LOW⚡	packages/ai/src/generate-text/generate-text.test.ts	10986	// Step 0: just the initial user message	COMMENT
LOW⚡	packages/ai/src/generate-text/generate-text.test.ts	10989	// Step 1: user message + assistant message + tool message	COMMENT
LOW⚡	packages/ai/src/generate-text/generate-text.test.ts	10992	// Step 2: user message + assistant + tool + assistant + tool	COMMENT
LOW⚡	packages/ai/src/generate-text/generate-text.test.ts	10995	// Step 3: continued accumulation	COMMENT
LOW⚡	packages/ai/src/generate-text/generate-text.test.ts	10998	// Step 4: continued accumulation	COMMENT
LOW	packages/ai/src/generate-text/generate-text.test.ts	9901	// Step 1: text + server_tool_use (code_execution) + 2 rollDie calls	COMMENT
LOW	packages/ai/src/generate-text/generate-text.test.ts	9956	// Step 2: 2 rollDie calls (round 2)	COMMENT
LOW	packages/ai/src/generate-text/generate-text.test.ts	10000	// Step 3: 2 rollDie calls (round 3)	COMMENT
LOW	packages/ai/src/generate-text/generate-text.test.ts	10044	// Step 4: 2 rollDie calls (round 4 - final round)	COMMENT
LOW	packages/ai/src/generate-text/generate-text.test.ts	10088	// Step 5: code_execution_tool_result + final text	COMMENT
LOW	packages/workflow/src/workflow-agent.test.ts	1859	// Step 1: tool call (executed), Step 2: text completion (no tools)	COMMENT
LOW	…xtures__/anthropic-claude-opus-5-reasoning-high.1.json	14	"text": "## Step 1: Set up the problem\n\nWe want all values of $x$ satisfying\n\n$$f(x) = x^3 - 6x^2 + 11x - 6 =	CODE
LOW	…__fixtures__/anthropic-combined-context-editing.1.json	14	"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.ts	15	// Step 1: Find destructuring from `generateText()`	COMMENT
LOW	…d/src/codemods/v5/rename-reasoning-to-reasoningText.ts	120	// Step 3: Rename `reasoning` to `reasoningText` in the identified paths	COMMENT

Over-Commented Block22 hits · 22 pts

Severity	File	Line	Snippet	Context
LOW	tools/run-harness-agent-examples.sh	1	#!/usr/bin/env bash	COMMENT
LOW	examples/ai-functions/src/stream-text/google/caching.ts	41	// e.g.	COMMENT
LOW	…functions/src/generate-video/bytedance/task-failure.ts	1	import { byteDance } from '@ai-sdk/bytedance';	COMMENT
LOW	…mples/ai-functions/src/generate-text/google/caching.ts	21	// thoughtsTokenCount: 634,	COMMENT
LOW	…mples/ai-functions/src/generate-text/google/caching.ts	41	// cachedContentTokenCount: 2027,	COMMENT
LOW	…s/src/generate-text/anthropic/cache-control-beta-1h.ts	101	// cache_creation: { ephemeral_5m_input_tokens: 0, ephemeral_1h_input_tokens: 0 },	COMMENT
LOW	…rate-text/anthropic/cache-control-beta-1h-streaming.ts	101	console.log(	COMMENT
LOW	…functions/src/generate-text/huggingface/temperature.ts	21	// temperature: 1.5,	COMMENT
LOW	packages/tui/src/tui/terminal-renderer.ts	161	#inputText = '';	COMMENT
LOW	…harness-claude-code/src/claude-code-bridge-protocol.ts	61	}),	COMMENT
LOW	packages/harness-claude-code/src/bridge/index.ts	761	],	COMMENT
LOW	packages/deepgram/src/deepgram-speech-options.ts	1	// Deepgram TTS voices are addressed by voice family; the upstream model ID	COMMENT
LOW	packages/provider-utils/src/secure-json-parse.test.ts	1	// Licensed under BSD-3-Clause (this file only)	COMMENT
LOW	packages/provider-utils/src/secure-json-parse.ts	1	// Licensed under BSD-3-Clause (this file only)	COMMENT
LOW	packages/harness/src/v1/harness-v1-stream-part.ts	81	// Step boundary inside a multi-step turn.	COMMENT
LOW	packages/devtools/src/viewer/server.ts	41	// We rely exclusively on an explicit env flag to avoid false positives in	COMMENT
LOW	packages/ai/src/util/deep-partial.ts	1	// License for this File only:	COMMENT
LOW	packages/ai/src/util/value-of.ts	1	// License for this File only:	COMMENT
LOW	.github/dependabot.yml	1	# Dependabot configuration — migrated from .github/renovate.json5	COMMENT
LOW	.github/workflows/update-model-settings.yml	1	# Update Gateway Model Settings	COMMENT
LOW	.github/workflows/backport.yml	521	BASE_BRANCH: ${{ needs.find-branch.outputs.release-branch }}	COMMENT
LOW	apps/docs/lib/tools-registry.ts	1	// The tools registry is unversioned: production always serves the current	COMMENT

Fake / Example Data13 hits · 15 pts

Severity	File	Line	Snippet	Context
LOW	…les/ai-functions/src/stream-text/baseten/custom-url.ts	15	// "placeholder", which servers that check the field reject with	COMMENT
LOW	…les/ai-functions/src/stream-text/baseten/custom-url.ts	16	// `The model 'placeholder' does not exist`. Ask the deployment if unsure:	COMMENT
LOW	…s/ai-functions/src/generate-text/baseten/custom-url.ts	15	// "placeholder", which servers that check the field reject with	COMMENT
LOW	…s/ai-functions/src/generate-text/baseten/custom-url.ts	16	// `The model 'placeholder' does not exist`. Ask the deployment if unsure:	COMMENT
LOW	…enerate-text/openai/responses-tool-search-namespace.ts	33	name: 'Jane Doe',	CODE
LOW	packages/baseten/src/baseten-provider.ts	206	return new OpenAICompatibleChatLanguageModel(modelId ?? 'placeholder', {	CODE
LOW	packages/baseten/src/baseten-provider.unit.test.ts	300	'placeholder',	CODE
LOW	packages/langchain/src/utils.test.ts	2509	arguments: { to: 'user@example.com' },	CODE
LOW	packages/langchain/src/utils.test.ts	2559	input: { to: 'user@example.com' },	CODE
LOW	…nteractions/google-interactions-language-model.test.ts	474	"text": "{"name":"John Doe","age":30}",	CODE
LOW	packages/ai/src/prompt/create-tool-model-output.test.ts	418	name: 'John Doe',	CODE
LOW	packages/ai/src/prompt/create-tool-model-output.test.ts	457	"name": "John Doe",	CODE
LOW	…responses/huggingface-responses-language-model.test.ts	1209	text: '{"name": "John Doe", "age": 30}',	CODE

Self-Referential Comments4 hits · 12 pts

Severity	File	Line	Snippet	Context
MEDIUM⚡	…/__fixtures__/anthropic-code-execution-20250825.2.json	18	"file_text": "import pandas as pd\nimport os\n\ndef fibonacci(n):\n \"\"\"\n Calculate the nth Fibonacci n	CODE
MEDIUM	.github/workflows/update-model-settings.yml	151	# Create the remote branch at the base tip (or reset an orphaned	COMMENT
MEDIUM	.github/workflows/backport.yml	458	# Create a new branch from the latest release branch for the backport	COMMENT
MEDIUM	.github/workflows/backport.yml	675	# Create the backport PR	COMMENT

Slop Phrases3 hits · 7 pts

Severity	File	Line	Snippet	Context
MEDIUM	…-functions/src/generate-text/amazon-bedrock/api-key.ts	36	// For demonstration purposes - in real applications, load from secure environment	COMMENT
MEDIUM	…les/ai-functions/src/stream-speech/elevenlabs/basic.ts	10	'in small pieces, as a language model would produce it. ',	CODE
MEDIUM	…c/src/__fixtures__/anthropic-web-fetch-tool.error.json	29	"text": "I'm unable to access the PDF document at that URL as the web_fetch tool is currently unavailable. To help	CODE

Redundant / Tautological Comments2 hits · 3 pts

Severity	File	Line	Snippet	Context
LOW⚡	…/__fixtures__/anthropic-code-execution-20250825.2.json	18	"file_text": "import pandas as pd\nimport os\n\ndef fibonacci(n):\n \"\"\"\n Calculate the nth Fibonacci n	CODE
LOW	.github/workflows/slack-team-review-notification.yml	23	# Check if ai-sdk team is in the requested teams	COMMENT

Overly Generic Function Names2 hits · 2 pts

Severity	File	Line	Snippet	Context
LOW	packages/harness-acp/src/v1/bridge/host-tool-relay.ts	238	async function handleRequest({	CODE
LOW	packages/ai/src/util/value-of.ts	40	* export function getData(name: string): ValueOf<typeof data> {	COMMENT

Example Usage Blocks1 hit · 2 pts

Severity	File	Line	Snippet	Context
LOW⚡	tools/run-harness-agent-examples.sh	5	# Usage:	COMMENT

Deep Nesting2 hits · 2 pts

Severity	File	Line	Snippet	Context
LOW	examples/next-fastapi/api/index.py	31		CODE
LOW	examples/next-fastapi/api/utils/prompt.py	14		CODE

vercel/ai

Open-Source Code Quality, Security and Technical Debt Review