{"_id":"@agentlair/vercel-ai","_rev":"2-dc6ceb37b84570f87f0b04040b5af201","name":"@agentlair/vercel-ai","dist-tags":{"latest":"0.1.1"},"versions":{"0.1.0":{"name":"@agentlair/vercel-ai","version":"0.1.0","keywords":["agentlair","vercel-ai","ai-sdk","telemetry","behavioral-trust","agent-identity","observability","typescript"],"author":{"name":"AgentLair"},"license":"MIT","_id":"@agentlair/vercel-ai@0.1.0","maintainers":[{"name":"piiiico","email":"pico@amdal.dev"}],"homepage":"https://agentlair.dev","bugs":{"url":"https://github.com/piiiico/agentlair-vercel-ai/issues"},"dist":{"shasum":"30ed43196ba4cd3eda66d7019322c280d13a015f","tarball":"https://registry.npmjs.org/@agentlair/vercel-ai/-/vercel-ai-0.1.0.tgz","fileCount":14,"integrity":"sha512-lb35MFUAjFOMR1mXNV5dMapkpxP4OzqCVRVoH/dZu01JTvczJ1+8B0D160qQl5BdEFLeO9N15QbHUGaa1pn5zg==","signatures":[{"sig":"MEUCIGHohbwjh80v+03kvka3PrmSfMv/PZ+jRG2lWi7RIRwLAiEA90chHWmqO0Kp9qmZO5j4G5Jjpe9/cfLTCY+O/N4sFWo=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":31929},"main":"./dist/index.js","type":"module","types":"./dist/index.d.ts","module":"./dist/index.js","engines":{"node":">=18.0.0"},"exports":{".":{"types":"./dist/index.d.ts","import":"./dist/index.js"}},"scripts":{"test":"bun test","build":"tsc","typecheck":"tsc --noEmit","prepublishOnly":"bun run build"},"_npmUser":{"name":"piiiico","email":"pico@amdal.dev"},"repository":{"url":"git+https://github.com/piiiico/agentlair-vercel-ai.git","type":"git"},"_npmVersion":"10.9.7","description":"AgentLair telemetry integration for the Vercel AI SDK. Captures tool calls, completions, errors, and token usage — feeds your agent's behavioral trust profile.","directories":{},"_nodeVersion":"22.22.2","_hasShrinkwrap":false,"devDependencies":{"typescript":"^5.9.3"},"peerDependencies":{"ai":">=4.0.0"},"peerDependenciesMeta":{"ai":{"optional":true}},"_npmOperationalInternal":{"tmp":"tmp/vercel-ai_0.1.0_1777634182994_0.434616698712593","host":"s3://npm-registry-packages-npm-production"}},"0.1.1":{"name":"@agentlair/vercel-ai","version":"0.1.1","description":"AgentLair telemetry integration for the Vercel AI SDK. Captures tool calls, completions, errors, and token usage — feeds your agent's behavioral trust profile.","type":"module","main":"./dist/index.js","module":"./dist/index.js","types":"./dist/index.d.ts","exports":{".":{"import":"./dist/index.js","types":"./dist/index.d.ts"}},"scripts":{"build":"tsc","test":"bun test","typecheck":"tsc --noEmit","prepublishOnly":"bun run build"},"keywords":["agentlair","vercel-ai","ai-sdk","telemetry","behavioral-trust","agent-identity","observability","typescript"],"author":{"name":"AgentLair"},"license":"MIT","repository":{"type":"git","url":"git+https://github.com/piiiico/agentlair-vercel-ai.git"},"homepage":"https://agentlair.dev","engines":{"node":">=18.0.0"},"peerDependencies":{"ai":">=4.0.0"},"peerDependenciesMeta":{"ai":{"optional":true}},"devDependencies":{"typescript":"^5.9.3"},"_id":"@agentlair/vercel-ai@0.1.1","bugs":{"url":"https://github.com/piiiico/agentlair-vercel-ai/issues"},"_nodeVersion":"22.22.2","_npmVersion":"10.9.7","dist":{"integrity":"sha512-O4uHtbAJaTykmtFliJ5kM1mM4gC8U1CB0xG+AWZZVMpqreSFJoDppkVjkCplpq9ZN21wXfGgwWw/5tg6FEOA2A==","shasum":"350f00efa19dbbf0af9dbd6689c48aa0a9553445","tarball":"https://registry.npmjs.org/@agentlair/vercel-ai/-/vercel-ai-0.1.1.tgz","fileCount":14,"unpackedSize":32034,"signatures":[{"keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U","sig":"MEYCIQDSieXiBR26jDQGeNTZG2stpttWcQEYL3ASC+GDIFgvmwIhAIo9TEV9q8rlfMSzaJxn4fx7Jtc1FnXrLV5OxZj2fQKg"}]},"_npmUser":{"name":"piiiico","email":"pico@amdal.dev"},"directories":{},"maintainers":[{"name":"piiiico","email":"pico@amdal.dev"}],"_npmOperationalInternal":{"host":"s3://npm-registry-packages-npm-production","tmp":"tmp/vercel-ai_0.1.1_1777730529178_0.7625941127689908"},"_hasShrinkwrap":false}},"time":{"created":"2026-05-01T11:16:22.911Z","modified":"2026-05-02T14:02:09.473Z","0.1.0":"2026-05-01T11:16:23.121Z","0.1.1":"2026-05-02T14:02:09.325Z"},"bugs":{"url":"https://github.com/piiiico/agentlair-vercel-ai/issues"},"author":{"name":"AgentLair"},"license":"MIT","homepage":"https://agentlair.dev","keywords":["agentlair","vercel-ai","ai-sdk","telemetry","behavioral-trust","agent-identity","observability","typescript"],"repository":{"type":"git","url":"git+https://github.com/piiiico/agentlair-vercel-ai.git"},"description":"AgentLair telemetry integration for the Vercel AI SDK. Captures tool calls, completions, errors, and token usage — feeds your agent's behavioral trust profile.","maintainers":[{"name":"piiiico","email":"pico@amdal.dev"}],"readme":"# @agentlair/vercel-ai\n\nAgentLair telemetry integration for the [Vercel AI SDK](https://ai-sdk.dev). Captures tool calls, completions, errors, and token usage from your AI SDK generations and forwards them to [AgentLair](https://agentlair.dev) to build your agent's behavioral trust profile.\n\nZero runtime dependencies. Works with any AI SDK model provider.\n\n## Install\n\n```bash\nnpm install @agentlair/vercel-ai\n# or\nbun add @agentlair/vercel-ai\n```\n\n## Quick start\n\n```bash\nbun add @agentlair/vercel-ai ai @ai-sdk/openai\n```\n\n```typescript\nimport { generateText } from \"ai\";\nimport { openai } from \"@ai-sdk/openai\";\nimport { createAgentLairExporter } from \"@agentlair/vercel-ai\";\n\nconst agentlair = createAgentLairExporter({\n  apiKey: process.env.AGENTLAIR_API_KEY!, // al_live_...\n  agentId: \"my-agent\",\n});\n\nconst { text } = await generateText({\n  model: openai(\"gpt-4o-mini\"),\n  prompt: \"Summarise last week's sales\",\n  tools: { ... },\n  experimental_telemetry: { isEnabled: true, tracer: agentlair },\n});\n\nawait agentlair.shutdown(); // flush before process exit\n```\n\nCaptures tool call timing, token usage, and session lifecycle — no prompt content leaves your process.\nGet your API key at [agentlair.dev](https://agentlair.dev).\n\n## What gets captured\n\n| AI SDK event | AgentLair event | Category | Data |\n|---|---|---|---|\n| `onStart` | `generation_start` | session | model, provider, temperature, tool count |\n| `onToolCallStart` | `{toolName}` | tool | tool name, call ID |\n| `onToolCallFinish` | `{toolName}_complete` | tool | duration, success/failure, error |\n| `onStepFinish` | `step_complete` | session | token usage, finish reason, tool call count |\n| `onFinish` | `generation_complete` | session | total token usage, finish reason |\n\nEvents are batched and flushed every 5 seconds (configurable). Buffer auto-flushes when it reaches 50 events.\n\n## Configuration\n\n```typescript\nconst agentlair = createAgentLairExporter({\n  // Required\n  apiKey: 'al_live_...',     // Your AgentLair API key\n  agentId: 'my-agent',       // Agent identifier for event attribution\n\n  // Optional\n  baseUrl: 'https://agentlair.dev',  // API base URL\n  flushInterval: 5000,               // Batch flush interval (ms)\n  maxBufferSize: 50,                 // Force-flush threshold\n  sessionId: 'custom-session-id',    // Group events by session\n  timeout: 3000,                     // Request timeout (ms)\n  captureInputs: false,              // Log input metadata (prompt length, message count)\n  captureOutputs: false,             // Log output metadata (response length)\n  onError: (err) => console.error(err),  // Error handler (swallowed by default)\n});\n```\n\n## Behavioral attestation\n\nEvents submitted through this adapter feed AgentLair's trust engine. Your agent's trust score reflects:\n\n- **Consistency** of tool usage patterns over time\n- **Transparency** through complete audit trails\n- **Behavioral adherence** to declared capabilities\n\nView your agent's trust profile at `https://agentlair.dev/badge/{agentId}/score.json` or embed a badge in your README.\n\n## License\n\nMIT\n","readmeFilename":"README.md"}