neatlogs-ts-vercel-ai

Use when adding neatlogs observability to a TypeScript/Node.js project that uses the Vercel AI SDK (depends on the `ai` package, calls `generateText`/`streamText`).

SKILL.md

GitHub

Neatlogs TypeScript Setup — Vercel AI SDK (ai)

This project uses the Vercel AI SDK (ai package: generateText, streamText, generateObject, streamObject, embed, embedMany, rerank). Neatlogs instruments it with wrapAISDK(ai) from neatlogs/ai — NOT via an instrumentations list. The wrapper opts the AI SDK's native OpenTelemetry support in per call.

init({ instrumentations: ['ai_sdk'] }) throws — as does every other provider/framework key. The public option and registry were removed because global auto-instrumentors cannot be isolated from a co-tenant tracer. The JavaScript compatibility guard rejects the obsolete property; use wrapAISDK().

Core mechanism (DIFFERENT from other skills)

  1. await init({ ... }) first (sets up Neatlogs' private tracer — never registered globally). Never pass instrumentations: ['ai_sdk'] — init() throws for it; the wrapper does the work.
  2. const { generateText, streamText, ... } = wrapAISDK(ai) — wrap the ai module.
  3. Use the WRAPPED functions exactly like the originals. Each wrapped call auto-creates a WORKFLOW/CHAIN parent span + native ai.doGenerate/doStream LLM children + tool-call TOOL children.

Steps

  1. Install → references/1-install.md
  2. Add init() + wrapAISDK → references/2-init-and-wrap.md
  3. Set environment variables → references/3-set-env.md
  4. Verify: use wrapped fns, don't double-wrap → references/4-verify.md
  5. Lifecycle (flush/shutdown) → references/5-lifecycle.md

Running inside Next.js? (most apps are)

If the project is a Next.js app (it has next.config.* / app/ route handlers / server actions), follow references/nextjs.md. The key Next-specific requirement:

  • init() goes in instrumentation.ts via the register() hook, importing neatlogs with a dynamic await import("neatlogs") — NOT a top-level import. A static import 500s the build with Can't resolve 'crypto'.

Rules (apply to ALL steps)

  • await init(...) runs first (registers the TracerProvider). Then wrapAISDK(ai).
  • NEVER pass instrumentations: ['ai_sdk'] (or any provider key) — init() throws. The wrapper is the instrumentation. A provider SDK called DIRECTLY outside the AI SDK needs its own helper (wrapOpenAI, wrapAnthropic, …).
  • Replace direct ai calls with the WRAPPED equivalents: destructure generateText/streamText/etc. from wrapAISDK(ai) and call those. Don't leave bare import { generateText } from 'ai' call sites — they won't be traced.
  • Do NOT also wrap wrapped calls in span()/trace() — the wrapper already opens the parent span. Add a WORKFLOW only when the application entry point owns a real multi-step request/job; keep each wrapped AI-SDK call as its canonical child.
  • Neatlogs supports AI SDK v6 and v7 (ai >=6 <8). Keep using wrapAISDK(ai) in both versions; it selects v6's experimental_telemetry or v7's telemetry automatically.
  • AI SDK v7 requires Node.js 22+. Its @ai-sdk/otel adapter is an optional dependency of neatlogs and installs automatically unless optional dependencies are disabled.
  • Never hardcode API keys — use process.env.
  • For EU projects, set endpoint: 'https://eu.ingest.neatlogs.com' in init(); for other managed projects, omit endpoint, baseUrl, and NEATLOGS_ENDPOINT.

Safety gate

Before any edit, confirm this service is TypeScript/Node.js. Identify its package manager from the manifest and lockfile, then read the declared and installed SDK version. Do not install or change dependencies during this inspection. Run exactly one project-local command for the detected package manager:

npm:  npm exec --offline --no -- neatlogs doctor --local --json
pnpm: pnpm exec neatlogs doctor --local --json
Yarn: yarn run neatlogs doctor --local --json
Bun:  bun --no-install run neatlogs doctor --local --json

These commands let the package manager select the platform-specific local executable, including the Windows shim. Do not substitute npx, pnpm dlx, yarn dlx, bunx, a Wizard command, or another downloaded Doctor. Local mode must be read-only and network-free. It requires no credential and must not change source or configuration. Require format_version: "neatlogs.doctor/v2", runtime.language: "typescript", and runtime.schema_version: "2". Compare runtime.sdk_version with the installed project package to prove that the runner did not select another copy. Do not compare it with one hardcoded patch version.

If the command is missing or its result has the wrong format, language, schema, or installed-package identity, fail closed. Check the canonical package registry for the latest published stable release. If the project uses an older release, show the exact upgrade command for the detected package manager and obtain explicit user approval before running it. Accept newer compatible releases and never downgrade one. If the installed release is already current but lacks Doctor v2, stop and give safe manual/support remediation. Rerun local Doctor after any approved upgrade. Do not edit while this gate is unresolved.

A local pass proves only that the installed SDK produced and validated its controlled in-process envelope. It does not prove that the application is instrumented, that anything was exported, or that a hosted trace is visible. Preserve every reason_code and remediation_code exactly. Treat a warning, failure, or unknown future code as manual/support remediation unless the code is explicitly safe/fixable here. The only source fixes allowed by this gate are:

  • INSTRUMENTOR_INACTIVE: apply only this skill's documented initialization or wrapper/hook step.
  • ROOT_MISSING: add only the already-requested, documented WORKFLOW boundary at a confirmed entry point.
  • ROOT_NOT_ENDED: add only this skill's documented lifecycle hook.

Do not edit for credential, authentication, transport, backend, ambiguous ownership, or unknown codes. Never reproduce backend PII, routing, mapping, or finalization implementation. Before any build, test, or user-workflow command, show the exact command and obtain explicit user approval. Make reruns idempotent: reread the target first and never duplicate initialization, wrappers, roots, or shutdown hooks. Keep a pre-edit diff. If an approved check fails, use the rollback plan to revert only the edits from this run when they can be isolated safely. Otherwise, stop and give manual recovery instructions that preserve unrelated user work.

After instrumentation, obtain approval for the project checks and one representative real workflow. Obtain separate approval for the authenticated probe. Use only a credential already supplied through the process environment. Never print it, place it in command arguments or files, copy it into output, or put it in agent context.

Run the matching project-local command:

npm:  npm exec --offline --no -- neatlogs doctor --probe --json
pnpm: pnpm exec neatlogs doctor --probe --json
Yarn: yarn run neatlogs doctor --probe --json
Bun:  bun --no-install run neatlogs doctor --probe --json

Probe mode sends one controlled four-span trace through POST /v1/traces with x-neatlogs-doctor: v1, then reads that exact trace through GET /api/traces/v3/{trace_id} with the same project credential. Accept a probe pass only when capture and readback trace IDs match, the trace is finalized, exactly four spans contain one meaningful WORKFLOW root with AGENT→LLM and root→TOOL relationships, there are no duplicates, required semantics and I/O are present, and token values remain numeric. Never infer success from installation, local logs, exporter flush, HTTP 2xx, or any uncorrelated trace. Probe success proves the controlled path only. Verify the real user workflow separately through the completion gate below.

Completion gate

After local Doctor passes and the requested instrumentation is in place:

  1. Show the exact project build, test, and real-workflow commands and obtain explicit user approval before running them.
  2. Run only the approved checks. Restart a long-running process so it loads the new initialization and wrappers; keep reruns idempotent.
  3. Exercise one representative real user workflow. End every opened span and use the documented flush/shutdown lifecycle for that process type.
  4. Through the target project's normal product trace view or supported public read path, verify that exact run is finalized, has one meaningful root and the expected semantic hierarchy, and contains no duplicate operation spans.

Keep project credentials in the process environment or client secret storage; never put them in commands, output, files, or agent context. Do not use a legacy marker-discovery protocol. Installation, local logs, exporter flush, HTTP 2xx, a local Doctor pass, and a separate probe pass are not proof that the application's real workflow is correct. If the exact user trace cannot be inspected, report the missing access or observation as a blocker and provide rollback/manual recovery instructions without claiming completion.

Reference

  • Next.js setup (serverExternalPackages + instrumentation.ts) → references/nextjs.md
  • Sessions & end-users (per-turn identify()) → references/sessions-and-end-users.md
  • Custom span()/trace() (for real app-owned request/job orchestration) → references/decorators-and-traces.md
  • Troubleshooting → references/troubleshooting.md