#ai-sdk

Ryu Hi Nekomiya, Since the same request works with only: ['anthropic'] but fails with only: ['bedrock'], I’d treat this as a Gateway → Bedrock request translation/schema issue first, not an auth issue. providerOptions.gateway.only is the right kind of option for restricting routing, but Bedrock seems to be rejecting an extra field inside the tool definition: tools.0.custom.eager_input_streaming: Extra inputs are not permitted A useful isolation test would be to run three tiny requests against the same model/provider route: no tools at all one minimal tool with only name, description, and input_sch

Ryu Hi Wyatt, I would split this into two stored representations instead of trying to make one MongoDB document serve both jobs. For example: UI/history record what you show in the chat UI can include reasoning parts, metadata, timestamps, model name, token usage, etc. Model context record only the clean ModelMessage[] you plan to send back into generateText/streamText no UI-only fields no provider response metadata no fields copied blindly from the provider response outputs.response.messages is useful for continuing a conversation, but I would avoid persisting the full object and replaying it for

Ryu Hi MountainMan, Yes, I’d expect the same Bedrock providerOptions shape to work with streamText. The docs show generateText, but the guardrail config is a provider option on the Bedrock model call, not something specific to generateText. Example: import { bedrock, type AmazonBedrockLanguageModelOptions } from "@ai-sdk/amazon-bedrock" import { streamText } from "ai" const result = streamText({ model: bedrock("anthropic.claude-3-sonnet-20240229-v1:0"), prompt: "Write a story about space exploration.", providerOptions: { bedrock: { guardrailConfig: { guardrailIdentifier: "1abcd2ef34gh", guardrailV

ADALIGO Honestly same here 😅 I’ve been waiting for MCP Apps support too. It feels like a big missing piece, especially now that MCP is getting more powerful. From what I’ve seen 👀 Vercel usually ships fast once things are stable, so maybe this is still being worked on internally for the AI SDK 🤔 Also, this isn’t just a one-off request — I’ve seen multiple discussions about it across GitHub and the community (like the issues opened in January and even on Jan). So there’s clearly real demand building up. What would really help: native support in the Chat UI smoother app-to-tool chaining clearer docs and

BestCodes Since this has been inactive for over a month, I'm sending this message to hopefully bump it back up to the top!

Pauline P. Narvas Sharing with the team again ❤️

Pauline P. Narvas This has gone to our AI SDK team, thank you for sharing!

mo0hie Before sending the response to the frontend, just modify the tool parts and hide their output. For example: onFinish: async ({ messages, responseMessage }) => { responseMessage.parts = responseMessage.parts.map((part) => { if ( part.type.startsWith("tool-") && part.state === "output-available" ) { return { ...part, output: "[REDACTED]", }; } return part; }); },

Pauline P. Narvas Hey, I'm guessing you mean on the AI SDK and not v0? You can use google/gemini-2.5-flash-image. This is the latest stable model with image generation.

Gertie01 Yes. On the AI SDK.

Anush Hey @yusuf-eren. I’m from the Qdrant team (anush.shetty@qdrant.com). We’d be happy to help build/maintain this integration for the community. Looking forward to hearing from the Vercel AI SDK team.

Gregor @anush a community plugin would be great, we will be happy to add it to the list of AI SDK community providers: ai-sdk.dev/providers/community-providers. The AI SDK does support reranking and embedding, but we do not have a store abstraction built into the AI SDK, that’s currently out of scope. Maybe you can add a guide on how to use Qdrant with AI SDK using your community provider and vector store?

Anush Hey @gr2m I’m a fan of your work on Octokit.js and Semantic Release. Thank you. but we do not have a store abstraction built into the AI SDK, that’s currently out of scope. I see. Building a plugin without a common abstraction means users won’t have the ability to swap the vector store providers. Like with other components. How about we have examples/guides on how to use the AI SDK with the Qdrant client instead?

Pauline P. Narvas Thanks for reporting this feature gap! You're correct - while the AI SDK supports imageConfig for Google Gemini models (via PR #12059), this isn't currently available through the AI Gateway REST API. You could try the following workarounds though: Use the AI SDK with TypeScript (already supports this) If using BYOK, make direct calls to Google's API with imageConfig parameters Thanks again! Keep an eye out for updates :)

René Schubert Thanks for pointing to the PR, it helped me understand a bit more. However I’m not sure about the difference between generateText({ model: google("gemini-3-pro-image-preview"), // from the test in the PR /* … / }); and generateText({ model: "google/gemini-3-pro-image", // what we're using / … */ }); Is it basically the same and for both the structure of the providerOptions should be providerOptions: { google: { responseModalities: ['TEXT', 'IMAGE'], imageConfig: { aspectRatio: '16:9', imageSize: '4K', }, }, }, or does it differ, depending on whether I use @ai-sdk/google or not?