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
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).
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.
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.
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.
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.
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH | …ns/src/middleware/embedding/google-default-settings.ts | 35 | print('Embedding length:', result.embedding.length); | CODE |
| HIGH⚡ | …les/ai-functions/src/tools/mcp-tool-drift-detection.ts | 29 | print('Baseline fingerprints:', baseline); | CODE |
| HIGH⚡ | …les/ai-functions/src/tools/mcp-tool-drift-detection.ts | 34 | print('Drift:', drift); | CODE |
| HIGH⚡ | …les/ai-functions/src/tools/mcp-tool-drift-detection.ts | 37 | print( | CODE |
| HIGH⚡ | …les/ai-functions/src/tools/mcp-tool-drift-detection.ts | 45 | print('OK:', 'no drift; safe to proceed.'); | CODE |
| HIGH⚡ | …ctions/src/stream-text/google/vertex-combined-tools.ts | 39 | print('Request body:', (await result.request).body); | CODE |
| HIGH⚡ | …ctions/src/stream-text/google/vertex-combined-tools.ts | 40 | print('Raw response chunks:', rawChunks); | CODE |
| HIGH⚡ | …ctions/src/stream-text/google/vertex-combined-tools.ts | 41 | print('Response metadata:', await result.response); | CODE |
| HIGH | …es/ai-functions/src/stream-text/anthropic/fast-mode.ts | 23 | print('Usage:', await result.usage); | CODE |
| HIGH | …es/ai-functions/src/stream-text/anthropic/fast-mode.ts | 24 | print('Finish reason:', await result.finishReason); | CODE |
| HIGH | …-functions/src/stream-text/anthropic/tool-call-8516.ts | 104 | print('Request body:', (await result.request).body); | CODE |
| HIGH | …s/src/stream-text/anthropic/subagent-with-telemetry.ts | 53 | print('Usage:', await result.usage); | CODE |
| HIGH | …s/src/stream-text/anthropic/subagent-with-telemetry.ts | 54 | print('Finish reason:', await result.finishReason); | CODE |
| HIGH | examples/ai-functions/src/stream-text/anthropic/mcp.ts | 30 | print('Request body:', (await result.request).body); | CODE |
| HIGH | examples/ai-functions/src/stream-text/anthropic/mcp.ts | 31 | print('Warnings:', await result.warnings); | CODE |
| HIGH⚡ | …amples/ai-functions/src/stream-text/anthropic/basic.ts | 19 | print('Usage:', await result.usage); | CODE |
| HIGH⚡ | …amples/ai-functions/src/stream-text/anthropic/basic.ts | 20 | print('Finish reason:', await result.finishReason); | CODE |
| HIGH⚡ | …amples/ai-functions/src/stream-text/anthropic/basic.ts | 21 | print('Raw finish reason:', await result.rawFinishReason); | CODE |
| HIGH | …mples/ai-functions/src/stream-text/anthropic/skills.ts | 36 | print('container', anthropicContainer); | CODE |
| HIGH | …s/src/stream-text/anthropic/mid-conversation-system.ts | 40 | print('Usage:', await result.usage); | CODE |
| HIGH | …s/ai-functions/src/stream-text/openai/timeout-total.ts | 16 | print('Usage:', await result.usage); | CODE |
| HIGH | …s/ai-functions/src/stream-text/openai/timeout-total.ts | 17 | print('Finish reason:', await result.finishReason); | CODE |
| HIGH | …s/ai-functions/src/stream-text/openai/output-object.ts | 42 | print('Output:', await result.output); | CODE |
| HIGH⚡ | …es/ai-functions/src/stream-text/openai/timeout-step.ts | 31 | print('Usage:', await result.usage); | CODE |
| HIGH⚡ | …es/ai-functions/src/stream-text/openai/timeout-step.ts | 32 | print('Finish reason:', await result.finishReason); | CODE |
| HIGH⚡ | …es/ai-functions/src/stream-text/openai/timeout-step.ts | 33 | print('Steps:', (await result.steps).length); | CODE |
| HIGH | …i-functions/src/stream-text/openai/step-performance.ts | 48 | print('Tool result:', chunk.output); | CODE |
| HIGH | …i-functions/src/stream-text/openai/step-performance.ts | 54 | print('Usage:', chunk.usage); | CODE |
| HIGH⚡ | …i-functions/src/stream-text/openai/step-performance.ts | 65 | print( | CODE |
| HIGH⚡ | …i-functions/src/stream-text/openai/step-performance.ts | 69 | print('Final step performance:', (await result.finalStep).performance); | CODE |
| HIGH⚡ | …i-functions/src/stream-text/openai/step-performance.ts | 70 | print('Total usage:', await result.usage); | CODE |
| HIGH⚡ | examples/ai-functions/src/stream-text/openai/basic.ts | 16 | print('Usage:', await result.usage); | CODE |
| HIGH⚡ | examples/ai-functions/src/stream-text/openai/basic.ts | 17 | print('Finish reason:', await result.finishReason); | CODE |
| HIGH⚡ | examples/ai-functions/src/stream-text/openai/basic.ts | 18 | print('Raw finish reason:', await result.rawFinishReason); | CODE |
| HIGH | …/ai-functions/src/stream-text/openai/output-default.ts | 20 | print('Output:', await result.output); | CODE |
| HIGH | examples/ai-functions/src/stream-text/openai/timeout.ts | 16 | print('Usage:', await result.usage); | CODE |
| HIGH | examples/ai-functions/src/stream-text/openai/timeout.ts | 17 | print('Finish reason:', await result.finishReason); | CODE |
| HIGH | …ons/src/stream-text/openai/include-request-messages.ts | 20 | print('Request metadata:', await result.request); | CODE |
| HIGH | …s/ai-functions/src/stream-text/openai/timeout-chunk.ts | 16 | print('Usage:', await result.usage); | CODE |
| HIGH | …s/ai-functions/src/stream-text/openai/timeout-chunk.ts | 17 | print('Finish reason:', await result.finishReason); | CODE |
| HIGH | …s/ai-functions/src/stream-text/openai/gpt-5-3-codex.ts | 18 | print('Usage:', await result.usage); | CODE |
| HIGH | …s/ai-functions/src/stream-text/openai/gpt-5-3-codex.ts | 19 | print('Finish reason:', await result.finishReason); | CODE |
| HIGH⚡ | …/ai-functions/src/agent/anthropic/cache-instruction.ts | 36 | print('Result:', result.content); | CODE |
| HIGH⚡ | …/ai-functions/src/agent/anthropic/cache-instruction.ts | 37 | print('Metadata:', result.providerMetadata?.anthropic); | CODE |
| HIGH⚡ | …/ai-functions/src/agent/anthropic/cache-instruction.ts | 38 | print('Request:', result.request.body); | CODE |
| HIGH | …functions/src/agent/anthropic/generate-output-array.ts | 25 | print('Output:', output); | CODE |
| HIGH | …s/ai-functions/src/agent/openai/stream-call-options.ts | 45 | print('REQUEST:', request.body); | CODE |
| HIGH | …ions/src/agent/openai/stream-output-array-websearch.ts | 39 | print('REQUEST:', request.body); | CODE |
| HIGH | …ai-functions/src/agent/openai/generate-call-options.ts | 44 | print('REQUEST:', request.body); | CODE |
| HIGH | …ai-functions/src/agent/openai/generate-call-options.ts | 59 | print('CONTENT:', result.content); | CODE |
| HIGH | examples/ai-functions/src/agent/openai/generate.ts | 16 | print('CONTENT:', result.content); | CODE |
| HIGH⚡ | …-functions/src/agent/openai/stream-step-performance.ts | 30 | print( | CODE |
| HIGH⚡ | …-functions/src/agent/openai/stream-step-performance.ts | 34 | print('Final step performance:', (await result.finalStep).performance); | CODE |
| HIGH⚡ | …-functions/src/agent/openai/stream-step-performance.ts | 35 | print('Total usage:', await result.usage); | CODE |
| HIGH | …ai-functions/src/agent/openai/generate-output-array.ts | 34 | print('Output:', output); | CODE |
| HIGH | examples/ai-functions/src/lib/run.ts | 18 | print('Request body:', error.requestBodyValues); | CODE |
| HIGH | examples/ai-functions/src/lib/run.ts | 19 | print('Response body:', error.responseBody); | CODE |
| HIGH | …unctions/src/generate-text/azure/deepseek-reasoning.ts | 21 | print('Reasoning:', result.reasoningText); | CODE |
| HIGH | …unctions/src/generate-text/azure/deepseek-reasoning.ts | 22 | print('Text:', result.text); | CODE |
| HIGH | …ate-text/google/vertex-anthropic-output-array-tools.ts | 23 | print('Output:', result.output); | CODE |
| 128 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | tools/analyze-downloads/src/analyze-ui-frameworks.ts | 30 | function aggregateDownloadsForLastNMajorReleases( | CODE |
| LOW | contributing/testing.md | 91 | function prepareChunksFixtureResponse(filename: string) { | CODE |
| LOW | contributing/testing.md | 109 | function prepareChunksFixtureResponse(filename: string) { | 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 | …ai-functions/src/lib/download-openai-container-file.ts | 4 | export async function downloadOpenaiContainerFile( | 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 | examples/ai-functions/src/lib/harness-tool-approval.ts | 14 | export async function printFullStreamAndCaptureToolApproval({ | CODE |
| LOW | examples/ai-functions/src/lib/harness-tool-approval.ts | 92 | export function createToolApprovalResponseMessages({ | 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 | …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 | …ess-e2e-next/app/harness/claude-code/workflow/page.tsx | 10 | export default function HarnessClaudeCodeWorkflowPage() { | CODE |
| LOW | …ness-e2e-next/app/harness/claude-code/weather/page.tsx | 10 | export default function HarnessClaudeCodeWeatherPage() { | 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 | …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 | …ness-e2e-next/app/harness/codex/ai-sdk-coding/page.tsx | 10 | export default function HarnessCodexAiSdkCodingPage() { | CODE |
| LOW | …ness-e2e-next/app/harness/pi/weather-approval/page.tsx | 10 | export default function HarnessPiWeatherApprovalPage() { | CODE |
| LOW | …rness-e2e-next/app/harness/pi/basic-with-stop/page.tsx | 10 | export default function HarnessPiBasicWithStopPage() { | CODE |
| LOW | …-next/app/harness/deepagents/weather-approval/page.tsx | 10 | export default function HarnessDeepAgentsWeatherApprovalPage() { | CODE |
| LOW | …e-next/app/harness/deepagents/basic-with-stop/page.tsx | 10 | export default function HarnessDeepAgentsBasicWithStopPage() { | CODE |
| LOW | …ness-e2e-next/app/harness/deepagents/workflow/page.tsx | 10 | export default function HarnessDeepAgentsWorkflowPage() { | CODE |
| LOW | …rness-e2e-next/app/harness/deepagents/weather/page.tsx | 10 | export default function HarnessDeepAgentsWeatherPage() { | CODE |
| LOW | …-e2e-next/app/harness/deepagents/weather-only/page.tsx | 10 | export default function HarnessDeepAgentsWeatherPage() { | CODE |
| LOW | …e2e-next/app/harness/deepagents/ai-sdk-coding/page.tsx | 10 | export default function HarnessDeepAgentsAiSdkCodingPage() { | CODE |
| LOW | …2e-next/app/harness/opencode/weather-approval/page.tsx | 10 | export default function HarnessOpenCodeWeatherApprovalPage() { | CODE |
| LOW | …e2e-next/app/harness/opencode/basic-with-stop/page.tsx | 10 | export default function HarnessOpenCodeBasicWithStopPage() { | CODE |
| LOW | …arness-e2e-next/app/harness/opencode/workflow/page.tsx | 10 | export default function HarnessOpenCodeWorkflowPage() { | CODE |
| LOW | …harness-e2e-next/app/harness/opencode/weather/page.tsx | 10 | export default function HarnessOpenCodeWeatherPage() { | CODE |
| LOW | …ss-e2e-next/app/harness/opencode/weather-only/page.tsx | 10 | export default function HarnessOpenCodeWeatherPage() { | CODE |
| LOW | …s-e2e-next/app/harness/opencode/ai-sdk-coding/page.tsx | 10 | export default function HarnessOpenCodeAiSdkCodingPage() { | CODE |
| LOW | …-e2e-next/components/weather-opencode-harness-chat.tsx | 18 | export default function WeatherOpenCodeHarnessChat({ | CODE |
| LOW | …e-next/components/weather-claude-code-harness-chat.tsx | 18 | export default function WeatherClaudeCodeHarnessChat({ | CODE |
| LOW | …2e-next/components/weather-deepagents-harness-chat.tsx | 17 | export default function WeatherDeepAgentsHarnessChat({ | CODE |
| LOW | examples/next-fastapi/api/utils/prompt.py | 14 | def convert_to_openai_messages(messages: List[ClientMessage]): | CODE |
| LOW | examples/next-workflow/workflow/telemetry-agent.ts | 66 | function createTelemetryIntegration(telemetryRunId: string) { | CODE |
| LOW | examples/next-workflow/lib/telemetry-store.ts | 54 | export function getTelemetryRunIdForWorkflowRun(workflowRunId: string) { | CODE |
| LOW | …e2e-next/app/chat/test-azure-image-generation/page.tsx | 9 | export default function TestOpenAIImageGeneration() { | CODE |
| LOW | …ai-e2e-next/app/chat/anthropic-code-execution/page.tsx | 10 | export default function TestAnthropicCodeExecution() { | CODE |
| LOW | examples/ai-e2e-next/app/chat/anthropic-mcp/page.tsx | 10 | export default function TestAnthropicCodeExecution() { | CODE |
| LOW | …e-next/app/chat/openai-shell-container-skills/page.tsx | 8 | export default function ChatOpenAIShellContainerSkills() { | CODE |
| LOW | …st-azure-code-interpreter-annotation-download/page.tsx | 10 | export default function TestAzureOpenAICodeInterpreter() { | CODE |
| LOW | …t/app/chat/test-openai-responses-mcp-approval/page.tsx | 13 | export default function TestOpenAIResponsesMCPApproval() { | CODE |
| LOW | …app/chat/anthropic-code-execution-file-upload/page.tsx | 46 | export default function AnthropicCodeExecutionFileUploadPage() { | CODE |
| LOW | examples/ai-e2e-next/app/chat/anthropic-tools/page.tsx | 10 | export default function TestAnthropicCodeExecution() { | CODE |
| LOW | …i-e2e-next/app/chat/openai-tool-search-client/page.tsx | 10 | export default function TestOpenAIToolSearchClient() { | CODE |
| LOW | …e2e-next/app/chat/openai-previous-response-id/page.tsx | 15 | export default function OpenPreviousResponseIdPage() { | CODE |
| LOW | …2e-next/app/chat/openai-pdf-fetch-custom-tool/page.tsx | 9 | export default function TestOpenAIFileGenerationPDF() { | CODE |
| LOW | …/app/chat/anthropic-programmatic-tool-calling/page.tsx | 10 | export default function ChatAnthropicProgrammaticToolCalling() { | CODE |
| 433 more matches not shown… | ||||
| 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 | 9 | // ── Session lifecycle ────────────────────────────────────────────── | COMMENT |
| MEDIUM | …rc/realtime-model/v4/realtime-model-v4-server-event.ts | 21 | // ── Input audio buffer ───────────────────────────────────────────── | COMMENT |
| MEDIUM | …rc/realtime-model/v4/realtime-model-v4-server-event.ts | 39 | // ── Conversation items ───────────────────────────────────────────── | COMMENT |
| MEDIUM | …rc/realtime-model/v4/realtime-model-v4-server-event.ts | 53 | // ── Response lifecycle ───────────────────────────────────────────── | COMMENT |
| MEDIUM | …rc/realtime-model/v4/realtime-model-v4-server-event.ts | 66 | // ── Output item lifecycle ────────────────────────────────────────── | COMMENT |
| MEDIUM | …rc/realtime-model/v4/realtime-model-v4-server-event.ts | 92 | // ── Audio output ─────────────────────────────────────────────────── | COMMENT |
| MEDIUM | …rc/realtime-model/v4/realtime-model-v4-server-event.ts | 111 | // ── Audio transcript output ──────────────────────────────────────── | COMMENT |
| MEDIUM | …rc/realtime-model/v4/realtime-model-v4-server-event.ts | 131 | // ── Text output ──────────────────────────────────────────────────── | COMMENT |
| MEDIUM | …rc/realtime-model/v4/realtime-model-v4-server-event.ts | 151 | // ── Function calling ─────────────────────────────────────────────── | COMMENT |
| MEDIUM | …rc/realtime-model/v4/realtime-model-v4-server-event.ts | 182 | // ── Error ────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | …rc/realtime-model/v4/realtime-model-v4-server-event.ts | 190 | // ── Custom / provider-specific ──────────────────────────────────── | COMMENT |
| MEDIUM | …rc/realtime-model/v4/realtime-model-v4-client-event.ts | 10 | // ── Session ──────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | …rc/realtime-model/v4/realtime-model-v4-client-event.ts | 17 | // ── Input audio buffer ───────────────────────────────────────────── | COMMENT |
| MEDIUM | …rc/realtime-model/v4/realtime-model-v4-client-event.ts | 33 | // ── Conversation items ───────────────────────────────────────────── | COMMENT |
| MEDIUM | …rc/realtime-model/v4/realtime-model-v4-client-event.ts | 57 | // ── Response control ─────────────────────────────────────────────── | COMMENT |
| MEDIUM | packages/xai/src/xai-video-model-options.ts | 90 | // ── 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 | 51 | // ── Plain generation + legacy no-mode compatibility ──────────────── | COMMENT |
| MEDIUM | packages/xai/src/xai-video-options.test-d.ts | 111 | // ── Discriminated union: illegal combos rejected ─────────────────── | COMMENT |
| MEDIUM | packages/xai/src/xai-video-options.test-d.ts | 146 | // ── Required companion fields ────────────────────────────────────── | COMMENT |
| MEDIUM | packages/harness/src/bridge/index.ts | 233 | // ─── mutable runtime state ────────────────────────────────────────── | COMMENT |
| MEDIUM | packages/harness/src/bridge/index.ts | 344 | // ─── persistence (best-effort meta + start config) ────────────────── | COMMENT |
| MEDIUM | packages/harness/src/bridge/index.ts | 375 | // ─── wire send + replay ───────────────────────────────────────────── | COMMENT |
| MEDIUM | packages/harness/src/bridge/index.ts | 410 | // ─── diagnostics ────────────────────────────────────────────── | COMMENT |
| MEDIUM | packages/harness/src/bridge/index.ts | 518 | // ─── inbound routing ──────────────────────────────────────────────── | COMMENT |
| MEDIUM | packages/harness/src/bridge/index.ts | 664 | // ─── 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 | 346 | // ─── internals ────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | packages/harness/src/agent/harness-agent.ts | 485 | // ─── Internals ────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | …rness/src/agent/internal/harness-stream-text-result.ts | 194 | // ─── Writer-side methods used by the driver ──────────────────────── | COMMENT |
| MEDIUM | …rness/src/agent/internal/harness-stream-text-result.ts | 482 | // ─── Reader-side public surface (StreamTextResult contract) ──────── | COMMENT |
| MEDIUM | …rness/src/agent/internal/harness-stream-text-result.ts | 654 | // ─── Helpers ──────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | packages/ai/src/realtime/realtime-session.ts | 104 | // ── Connection ───────────────────────────────────────────────────── | COMMENT |
| MEDIUM | packages/ai/src/realtime/realtime-session.ts | 153 | // ── Sending events ───────────────────────────────────────────────── | COMMENT |
| MEDIUM | packages/ai/src/realtime/realtime-session.ts | 191 | // ── Tool output ─────────────────────────────────────────────────── | COMMENT |
| MEDIUM⚡ | packages/ai/src/realtime/realtime-session.ts | 235 | // ── Audio capture ────────────────────────────────────────────────── | COMMENT |
| MEDIUM⚡ | packages/ai/src/realtime/realtime-session.ts | 245 | // ── Playback ─────────────────────────────────────────────────────── | COMMENT |
| MEDIUM⚡ | packages/ai/src/realtime/realtime-session.ts | 251 | // ── Cleanup ──────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | packages/ai/src/realtime/realtime-session.ts | 267 | // ── Private 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 | 36 | // ── Session lifecycle ────────────────────────────────────────── | COMMENT |
| MEDIUM | …es/openai/src/realtime/openai-realtime-event-mapper.ts | 47 | // ── Input audio buffer ───────────────────────────────────────── | COMMENT |
| MEDIUM | …es/openai/src/realtime/openai-realtime-event-mapper.ts | 70 | // ── Conversation items ───────────────────────────────────────── | COMMENT |
| MEDIUM | …es/openai/src/realtime/openai-realtime-event-mapper.ts | 87 | // ── Response lifecycle ────────────────────────────────────────── | COMMENT |
| MEDIUM | …es/openai/src/realtime/openai-realtime-event-mapper.ts | 103 | // ── Output item lifecycle ─────────────────────────────────────── | COMMENT |
| MEDIUM | …es/openai/src/realtime/openai-realtime-event-mapper.ts | 136 | // ── Audio output ──────────────────────────────────────────────── | COMMENT |
| MEDIUM | …es/openai/src/realtime/openai-realtime-event-mapper.ts | 154 | // ── Audio transcript output ───────────────────────────────────── | COMMENT |
| MEDIUM | …es/openai/src/realtime/openai-realtime-event-mapper.ts | 173 | // ── Text output ───────────────────────────────────────────────── | COMMENT |
| MEDIUM | …es/openai/src/realtime/openai-realtime-event-mapper.ts | 192 | // ── Function calling ──────────────────────────────────────────── | COMMENT |
| MEDIUM⚡ | …es/openai/src/realtime/openai-realtime-event-mapper.ts | 214 | // ── Error ─────────────────────────────────────────────────────── | COMMENT |
| MEDIUM⚡ | …es/openai/src/realtime/openai-realtime-event-mapper.ts | 223 | // ── Pass-through ──────────────────────────────────────────────── | COMMENT |
| 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 | …/src/stream-text/azure/responses-web-search-preview.ts | 9 | * AZURE_API_KEY="<your_api_key>" | COMMENT |
| 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 | …rc/generate-text/azure/responses-web-search-preview.ts | 9 | * AZURE_API_KEY="<your_api_key>" | COMMENT |
| 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/README.md | 45 | export AWS_BEARER_TOKEN_BEDROCK=your-api-key-here | CODE |
| HIGH | packages/amazon-bedrock/src/amazon-bedrock-provider.ts | 48 | * apiKey: 'your-api-key-here', | COMMENT |
| HIGH | packages/bytedance/README.md | 190 | ARK_API_KEY=your-api-key | CODE |
| HIGH | packages/bytedance/README.md | 199 | apiKey: 'your-api-key', | CODE |
| 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/alibaba/src/alibaba-video-model.ts | 462 | // Step 1: Create task | COMMENT |
| LOW | packages/alibaba/src/alibaba-video-model.ts | 493 | // Step 2: Poll for task completion | COMMENT |
| LOW | packages/xai/src/xai-video-model.ts | 391 | // Step 1: Create video generation/edit/extension request | COMMENT |
| LOW | packages/xai/src/xai-video-model.ts | 412 | // Step 2: Poll for completion | COMMENT |
| LOW⚡ | packages/ai/src/generate-text/generate-text.test.ts | 2103 | // Step 0: no previous steps | COMMENT |
| LOW⚡ | packages/ai/src/generate-text/generate-text.test.ts | 2106 | // Step 1: has step 0's result | COMMENT |
| LOW⚡ | packages/ai/src/generate-text/generate-text.test.ts | 2116 | // Step 2: has step 0 and step 1's results | COMMENT |
| LOW⚡ | packages/ai/src/generate-text/generate-text.test.ts | 8701 | // Step 0: just the initial user message | COMMENT |
| LOW⚡ | packages/ai/src/generate-text/generate-text.test.ts | 8704 | // Step 1: user message + assistant message + tool message | COMMENT |
| LOW⚡ | packages/ai/src/generate-text/generate-text.test.ts | 8707 | // Step 2: user message + assistant + tool + assistant + tool | COMMENT |
| LOW⚡ | packages/ai/src/generate-text/generate-text.test.ts | 8710 | // Step 3: continued accumulation | COMMENT |
| LOW⚡ | packages/ai/src/generate-text/generate-text.test.ts | 8713 | // Step 4: continued accumulation | COMMENT |
| LOW | packages/ai/src/generate-text/generate-text.test.ts | 7615 | // Step 1: text + server_tool_use (code_execution) + 2 rollDie calls | COMMENT |
| LOW | packages/ai/src/generate-text/generate-text.test.ts | 7670 | // Step 2: 2 rollDie calls (round 2) | COMMENT |
| LOW | packages/ai/src/generate-text/generate-text.test.ts | 7714 | // Step 3: 2 rollDie calls (round 3) | COMMENT |
| LOW | packages/ai/src/generate-text/generate-text.test.ts | 7758 | // Step 4: 2 rollDie calls (round 4 - final round) | COMMENT |
| LOW | packages/ai/src/generate-text/generate-text.test.ts | 7802 | // Step 5: code_execution_tool_result + final text | COMMENT |
| LOW⚡ | packages/ai/src/generate-text/stream-text.test.ts | 24893 | // Step 0: just the initial user message | COMMENT |
| LOW⚡ | packages/ai/src/generate-text/stream-text.test.ts | 24896 | // Step 1: user message + assistant message + tool message | COMMENT |
| LOW⚡ | packages/ai/src/generate-text/stream-text.test.ts | 24899 | // Step 2: user message + assistant + tool + assistant + tool | COMMENT |
| LOW⚡ | packages/ai/src/generate-text/stream-text.test.ts | 24902 | // Step 3: continued accumulation | COMMENT |
| LOW⚡ | packages/ai/src/generate-text/stream-text.test.ts | 24905 | // Step 4: continued accumulation | COMMENT |
| LOW | packages/ai/src/generate-text/stream-text.test.ts | 23907 | // Step 1: text + server_tool_use (code_execution) + rollDie call | COMMENT |
| LOW | packages/ai/src/generate-text/stream-text.test.ts | 23964 | // Step 2: rollDie call (player2) | COMMENT |
| LOW | packages/ai/src/generate-text/stream-text.test.ts | 24006 | // Step 3: rollDie calls (round 2) | COMMENT |
| LOW | packages/ai/src/generate-text/stream-text.test.ts | 24048 | // Step 4: more rollDie calls | COMMENT |
| LOW | packages/ai/src/generate-text/stream-text.test.ts | 24090 | // Step 5: code_execution_tool_result + final text | COMMENT |
| LOW | packages/ai/src/generate-text/stream-text.test.ts | 25615 | // Step 1: tool call without result | COMMENT |
| LOW | packages/ai/src/generate-text/stream-text.test.ts | 25640 | // Step 2: tool-error arrives | COMMENT |
| LOW | packages/workflow/src/workflow-agent.test.ts | 1326 | // Step 1: tool call (executed), Step 2: text completion (no tools) | COMMENT |
| LOW | packages/klingai/src/klingai-video-model.ts | 299 | // Step 1: Create the task | COMMENT |
| LOW | packages/klingai/src/klingai-video-model.ts | 324 | // Step 2: Poll for task completion | COMMENT |
| 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 |
| 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/alibaba/src/alibaba-video-model.ts | 462 | // Step 1: Create task | COMMENT |
| LOW | packages/alibaba/src/alibaba-video-model.ts | 493 | // Step 2: Poll for task completion | COMMENT |
| LOW | packages/xai/src/xai-video-model.ts | 391 | // Step 1: Create video generation/edit/extension request | COMMENT |
| LOW | packages/xai/src/xai-video-model.ts | 412 | // Step 2: Poll for completion | COMMENT |
| LOW⚡ | packages/ai/src/generate-text/generate-text.test.ts | 2103 | // Step 0: no previous steps | COMMENT |
| LOW⚡ | packages/ai/src/generate-text/generate-text.test.ts | 2106 | // Step 1: has step 0's result | COMMENT |
| LOW⚡ | packages/ai/src/generate-text/generate-text.test.ts | 2116 | // Step 2: has step 0 and step 1's results | COMMENT |
| LOW⚡ | packages/ai/src/generate-text/generate-text.test.ts | 8701 | // Step 0: just the initial user message | COMMENT |
| LOW⚡ | packages/ai/src/generate-text/generate-text.test.ts | 8704 | // Step 1: user message + assistant message + tool message | COMMENT |
| LOW⚡ | packages/ai/src/generate-text/generate-text.test.ts | 8707 | // Step 2: user message + assistant + tool + assistant + tool | COMMENT |
| LOW⚡ | packages/ai/src/generate-text/generate-text.test.ts | 8710 | // Step 3: continued accumulation | COMMENT |
| LOW⚡ | packages/ai/src/generate-text/generate-text.test.ts | 8713 | // Step 4: continued accumulation | COMMENT |
| LOW | packages/ai/src/generate-text/generate-text.test.ts | 7615 | // Step 1: text + server_tool_use (code_execution) + 2 rollDie calls | COMMENT |
| LOW | packages/ai/src/generate-text/generate-text.test.ts | 7670 | // Step 2: 2 rollDie calls (round 2) | COMMENT |
| LOW | packages/ai/src/generate-text/generate-text.test.ts | 7714 | // Step 3: 2 rollDie calls (round 3) | COMMENT |
| LOW | packages/ai/src/generate-text/generate-text.test.ts | 7758 | // Step 4: 2 rollDie calls (round 4 - final round) | COMMENT |
| LOW | packages/ai/src/generate-text/generate-text.test.ts | 7802 | // Step 5: code_execution_tool_result + final text | COMMENT |
| LOW⚡ | packages/ai/src/generate-text/stream-text.test.ts | 24893 | // Step 0: just the initial user message | COMMENT |
| LOW⚡ | packages/ai/src/generate-text/stream-text.test.ts | 24896 | // Step 1: user message + assistant message + tool message | COMMENT |
| LOW⚡ | packages/ai/src/generate-text/stream-text.test.ts | 24899 | // Step 2: user message + assistant + tool + assistant + tool | COMMENT |
| LOW⚡ | packages/ai/src/generate-text/stream-text.test.ts | 24902 | // Step 3: continued accumulation | COMMENT |
| LOW⚡ | packages/ai/src/generate-text/stream-text.test.ts | 24905 | // Step 4: continued accumulation | COMMENT |
| LOW | packages/ai/src/generate-text/stream-text.test.ts | 23907 | // Step 1: text + server_tool_use (code_execution) + rollDie call | COMMENT |
| LOW | packages/ai/src/generate-text/stream-text.test.ts | 23964 | // Step 2: rollDie call (player2) | COMMENT |
| LOW | packages/ai/src/generate-text/stream-text.test.ts | 24006 | // Step 3: rollDie calls (round 2) | COMMENT |
| LOW | packages/ai/src/generate-text/stream-text.test.ts | 24048 | // Step 4: more rollDie calls | COMMENT |
| LOW | packages/ai/src/generate-text/stream-text.test.ts | 24090 | // Step 5: code_execution_tool_result + final text | COMMENT |
| LOW | packages/ai/src/generate-text/stream-text.test.ts | 25615 | // Step 1: tool call without result | COMMENT |
| LOW | packages/ai/src/generate-text/stream-text.test.ts | 25640 | // Step 2: tool-error arrives | COMMENT |
| LOW | packages/workflow/src/workflow-agent.test.ts | 1326 | // Step 1: tool call (executed), Step 2: text completion (no tools) | COMMENT |
| LOW | packages/klingai/src/klingai-video-model.ts | 299 | // Step 1: Create the task | COMMENT |
| LOW | packages/klingai/src/klingai-video-model.ts | 324 | // Step 2: Poll for task completion | COMMENT |
| 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 |
| 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 |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| CRITICAL | packages/ai/src/ui/chat.ts | 509 | this.activeResponse.state.message.parts.map(updatePart); | CODE |
| CRITICAL | packages/ai/src/ui/chat.ts | 558 | this.activeResponse.state.message.parts.map(updatePart); | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | examples/ai-functions/src/stream-text/google/caching.ts | 41 | // e.g. | 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 | #status = streamingStatus; | COMMENT |
| LOW | packages/harness-codex/src/bridge/index.ts | 1 | // Long-running process that runs alongside the `codex` CLI in the sandbox. | 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 | 61 | // Tool calls, approvals, results — reuse V4 primitives. | 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 |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM | packages/harness-codex/src/codex-harness.test.ts | 195 | "node /tmp/harness/codex/bridge.mjs --workdir '/vercel/sandbox/codex-s1; env > /tmp/workdir-leak #' --bridge-state | CODE |
| MEDIUM | …ages/deepseek/src/chat/__fixtures__/deepseek-text.json | 11 | "content": "## **Holiday Name: Gratitude of Small Things Day (GST Day)**\n\n**Date:** 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 |
| 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 | 449 | # Create a new branch from the latest release branch for the backport | COMMENT |
| MEDIUM | .github/workflows/backport.yml | 626 | # Create the backport PR | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | …enerate-text/openai/responses-tool-search-namespace.ts | 33 | name: 'Jane Doe', | CODE |
| LOW | packages/baseten/src/baseten-provider.ts | 148 | return new OpenAICompatibleChatLanguageModel(modelId ?? 'placeholder', { | CODE |
| LOW | packages/baseten/src/baseten-provider.unit.test.ts | 166 | 'placeholder', | CODE |
| LOW | packages/langchain/src/utils.test.ts | 2188 | arguments: { to: 'user@example.com' }, | CODE |
| LOW | packages/langchain/src/utils.test.ts | 2238 | input: { to: 'user@example.com' }, | CODE |
| LOW | …nteractions/google-interactions-language-model.test.ts | 407 | "text": "{"name":"John Doe","age":30}", | CODE |
| LOW | packages/ai/src/prompt/create-tool-model-output.test.ts | 362 | name: 'John Doe', | CODE |
| LOW | packages/ai/src/prompt/create-tool-model-output.test.ts | 401 | "name": "John Doe", | CODE |
| LOW | …responses/huggingface-responses-language-model.test.ts | 1087 | text: '{"name": "John Doe", "age": 30}', | CODE |
| 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 | …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 |
| 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 |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | examples/next-fastapi/api/index.py | 31 | CODE | |
| LOW | examples/next-fastapi/api/utils/prompt.py | 14 | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | packages/ai/src/util/value-of.ts | 40 | * export function getData(name: string): ValueOf<typeof data> { | COMMENT |