continue[bot] a89187b409 fix(openai-adapters): Don't emit usage from fullStream finish event
The Vercel AI SDK's fullStream may emit a finish event with incomplete or
zero usage data. The correct usage is available via the stream.usage Promise
which resolves after the stream completes.

Changed strategy:
- convertVercelStream now skips the finish event entirely (returns null)
- After consuming fullStream, we await stream.usage Promise
- Emit usage chunk with complete data from the Promise

This fixes the "expected 0 to be greater than 0" test failures.

Co-authored-by: nate <nate@continue.dev>
Generated with [Continue](https://continue.dev)
2025-12-10 19:36:54 +00:00
2025-12-04 10:10:40 -08:00
2025-12-05 16:36:25 -08:00
2025-09-24 14:52:36 -07:00

Continue logo

Continue

Ship faster with Continuous AI

The future of coding isn't writing more code. It's delegating the boring parts, so you can build the interesting stuff

Get started in Mission Control, CLI (Headless Mode), or CLI (TUI mode)

Quick Install

npm i -g @continuedev/cli
cn

Cloud Agents

Set workflows to run automatically on PR opens, schedules, or any event trigger

Cloud Agents

CLI Agents

Watch workflows execute in real-time and approve decisions step-by-step from your terminal

CLI Agents

IDE Agents

Trigger workflows from VS Code or JetBrains—let agents handle the refactoring while you keep coding

IDE Agents

Contributing

Read the contributing guide, and join #contribute on Discord.

License

Apache 2.0 © 2023-2024 Continue Dev, Inc.

Description
Ship faster with Continuous AI. Build and run custom agents across your IDE, terminal, and CI
Readme Apache-2.0 1.1 GiB
Languages
TypeScript 78.9%
JavaScript 13.2%
Kotlin 3.7%
Python 2.2%
Rust 0.7%
Other 1.2%