TanStackOSS
    ai
    feat(ai-mistral): support document (PDF) input via document_url The Mistral text adapter already snake-cased a `document_url` part in messageToWire, but convertContentPartToMistral never produced one and threw for any `document` content part, and model-meta declared no `document` input modality. Add the document branch (mirroring the image path: hosted URLs pass through, inline bytes become a data: URL) and declare `document` input for the vision-capable models, matching how the other provider adapters expose PDF input. Verified against Mistral's API: /v1/models reports vision=true for these models, and document_url round-trips a PDF on mistral-small-latest and mistral-medium-latest (both hosted-URL and inline base64).
    nx run-many --targets=build --exclude=examples/**,testing/**
Succeeded
CI Pipeline Execution

nx run-many --targets=build --exclude=examples/**,testing/**

Click to copy
Linux
4 CPU cores
read access token used
887fb9b1912
98%

Cache hits

46 of 47 tasks used cache.

Get faster results

Learn how to enable distribution.

Atomizer enabled

47 groups of tasks optimized.

© 2026 - Nx Cloud

Terms of ServicePrivacy PolicyChangelogStatusDocsContact Nx CloudPricingCompany@NxDevTools