Raymond Chen comments

Results 6 comments of


                                            Raymond Chen

Incorrect validation workflow for tool_use parameters in generateText

Facing this exact issue, can't find a graceful way to intercept validation errors right now. Even though tool repairs exist, I still want to be able to handle errors gracefully...

Support Google Vertex AI Express Mode

Also running into this issue. Any idea how to workaround or get something working for now @akarimcheese?

`message.id` changes when new `part` is added

Also encountering this with `ai@^4.3.2`. Here's a screenshot of the messages being rendered (as the next part streams in). @lgrammel any idea what's going on here? Some context on my...

Memory leak with high `tracesSampleRate`

Thanks for the response @Lms24! Here's how we init the SDK: ```typescript import * as Sentry from '@sentry/node' import 'dotenv/config' const DISABLED_DEFAULT_INTEGRATIONS = [ 'Amqplib', 'Kafka', 'OpenAI', 'Tedious', 'Prisma', 'Mysql2',...

Memory leak with high `tracesSampleRate`

@JPeer264 just tried disabling `ContextLines` and `Context` and it didn't seem to stop the leak unfortunately

Memory leak with high `tracesSampleRate`

@JPeer264 The only setting we have that may affect whether all spans are sent to Sentry (I assume) is `tracesSampleRate`. I'm not aware of any other flag. However, we have...