Skip to content

docs(cloudflare): Add Clef to the Workers AI evaluation tracing section #19877

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
JPeer264 merged 1 commit into from
Oct 9, 2026
Merged

docs(cloudflare): Add Clef to the Workers AI evaluation tracing section #19877

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion docs/platforms/javascript/common/configuration/integrations/typesafe.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,7 @@ This integration is enabled by default when <PlatformLink to="/tracing/">tracing

The `typesafeIntegration` adds instrumentation for [`@typesafe-ai/sdk`](https://www.npmjs.com/package/@typesafe-ai/sdk) to capture <PlatformLink to="/agent-tracing/">agent tracing</PlatformLink> `gen_ai.evaluate` spans, recording model, token usage, latency, and (when enabled) evaluation inputs and answers.

If you call Jev through Vercel AI SDK's `experimental_evaluate()`, see the [Vercel AI integration](/platforms/javascript/guides/node/configuration/integrations/vercelai/#trace-jev-evaluations) instead. If you call Jev through Cloudflare Workers AI, see [Workers AI](/platforms/javascript/guides/cloudflare/agent-tracing/workers-ai/#trace-jev-evaluations). If you call Jev through a Mastra `Classifier`, see [Mastra Classifier Evaluations](/platforms/javascript/guides/mastra/agent-tracing/classifier-evaluations/).
If you call Jev through Vercel AI SDK's `experimental_evaluate()`, see the [Vercel AI integration](/platforms/javascript/guides/node/configuration/integrations/vercelai/#trace-jev-evaluations) instead. If you call Jev through Cloudflare Workers AI, see [Workers AI](/platforms/javascript/guides/cloudflare/agent-tracing/workers-ai/#trace-jev-and-clef-evaluations). If you call Jev through a Mastra `Classifier`, see [Mastra Classifier Evaluations](/platforms/javascript/guides/mastra/agent-tracing/classifier-evaluations/).

```javascript
Sentry.init({
Expand Down
16 changes: 14 additions & 2 deletions docs/platforms/javascript/guides/cloudflare/agent-tracing/workers-ai.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,7 +30,7 @@ Only `env.AI.run` is instrumented. Streaming spans end when the stream is fully

You can browse the full list of available models in the [Cloudflare Workers AI models directory](https://developers.cloudflare.com/ai/models/).

## Trace Jev Evaluations
## Trace Jev and Clef Evaluations

<AvailableSince version="11.3.0" />

Expand Down Expand Up @@ -59,7 +59,19 @@ export default {
} satisfies ExportedHandler<Env>;
```

Each call creates a `gen_ai.evaluate` span named `evaluate <model>`, with the response model (for example, `jev-1.13.0`), latency, and token usage. When recording is enabled, Sentry captures `state` and `questions` as input messages and `answers` as output messages, including probabilities and confidence values returned by Jev. These spans have the same attributes as spans from the [TypeSafe integration](/platforms/javascript/guides/node/configuration/integrations/typesafe/) on other runtimes.
The SDK traces calls to Cloudflare's [Clef model](https://developers.cloudflare.com/workers-ai/models/clef/) (`@cf/cloudflare/clef`) the same way. Clef takes the same `state` and `questions` input as Jev:

```typescript
const result = await env.AI.run("@cf/cloudflare/clef", {
model: "clef",
state: "Checkout has been failing for every customer for the last hour.",
questions: {
urgent: { type: "noul", instructions: "Is this support request urgent?" },
},
});
```
Comment thread
sentry[bot] marked this conversation as resolved.
Resolved

Each call creates a `gen_ai.evaluate` span named `evaluate <model>`, with the response model (for example, `jev-1.13.0` or `clef`), latency, and token usage. When recording is enabled, Sentry captures `state` and `questions` as input messages and `answers` as output messages, including probabilities and confidence values returned by the model. These spans have the same attributes as spans from the [TypeSafe integration](/platforms/javascript/guides/node/configuration/integrations/typesafe/) on other runtimes.

Evaluation state and answers can contain sensitive data. To stop recording them, set `genAI: { inputs: false, outputs: false }` in the <PlatformLink to="/configuration/options/#dataCollection">`dataCollection` option</PlatformLink>.

Expand Down
Loading