Skip to content

Use vercelRunOutcome in Vercel AI SDK Core framework guide #3443

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

Open
rainbowFi wants to merge 1 commit into
base: main
Choose a base branch
from
+15 −8
Open

Use vercelRunOutcome in Vercel AI SDK Core framework guide #3443

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
23 changes: 15 additions & 8 deletions src/pages/docs/ai-transport/frameworks/vercel-ai-sdk-core.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,8 +46,10 @@ On the server, AI Transport replaces `createUIMessageStreamResponse()` with `Run
return createUIMessageStreamResponse({ stream: result.toUIMessageStream() });

// After: Ably transport
const { reason } = await run.pipe(result.toUIMessageStream());
await run.end({ reason });
const pipeResult = await run.pipe(result.toUIMessageStream());
const outcome = await vercelRunOutcome(pipeResult, result.finishReason);
await run.end(outcome);

return Response.json({ invocationId: run.invocationId });
```
</Code>
Expand All @@ -59,9 +61,9 @@ A full agent route:
import { after } from 'next/server';
import { streamText, convertToModelMessages } from 'ai';
import { anthropic } from '@ai-sdk/anthropic';
import Ably from 'ably';
import * as Ably from 'ably';
import { Invocation } from '@ably/ai-transport';
import { createAgentSession } from '@ably/ai-transport/vercel';
import { createAgentSession, vercelRunOutcome } from '@ably/ai-transport/vercel';

const ably = new Ably.Realtime({ key: process.env.ABLY_API_KEY });

Expand All @@ -81,12 +83,17 @@ export async function POST(req) {
abortSignal: run.abortSignal,
});

const { reason } = await run.pipe(result.toUIMessageStream());
await run.end({ reason });
const pipeResult = await run.pipe(result.toUIMessageStream());
const outcome = await vercelRunOutcome(pipeResult, result.finishReason);
if (outcome.reason === 'suspend') {
await run.suspend();
} else {
await run.end(outcome);
}
session.close();
});

return Response.json({ invocationId: run.invocationId });
return Response.json({ runId: run.runId, invocationId: run.invocationId });
}
```
</Code>
Expand All @@ -95,7 +102,7 @@ The integration has three pieces:

1. The `UIMessageCodec` encodes Vercel's `UIMessageChunk` events as Ably messages. Every chunk type maps to an Ably operation with headers that track the metadata. The codec encodes on the agent and decodes on the client.
2. `createAgentSession({ client, channelName })` from `@ably/ai-transport/vercel` constructs the agent session bound to the channel from the invocation. The default codec is `UIMessageCodec`.
3. `run.pipe()` reads the model's `UIMessageChunk` stream, encodes each chunk, and publishes the resulting Ably messages. `run.abortSignal` wires cancellation through from the client.
3. `run.pipe()` reads the model's `UIMessageChunk` stream, encodes each chunk, and publishes the resulting Ably messages. `run.abortSignal` wires cancellation through from the client. [`vercelRunOutcome()`](/docs/ai-transport/api/javascript/vercel/run-outcome) then maps the pipe result and Vercel's `finishReason` to the right lifecycle action: suspend the Run when the model requested tools the SDK did not auto-execute, otherwise end it with the matching reason.

## Scope and trade-offs <a id="scope"/>

Expand Down