Skip to content

ci: Version Packages#873

Merged
AlemTuzlak merged 1 commit into
mainfrom
changeset-release/main
Jul 1, 2026
Merged

ci: Version Packages#873
AlemTuzlak merged 1 commit into
mainfrom
changeset-release/main

Conversation

@github-actions

@github-actions github-actions Bot commented Jul 1, 2026

Copy link
Copy Markdown
Contributor

This PR was opened by the Changesets release GitHub action. When you're ready to do a release, you can merge this and the packages will be published to npm automatically. If you're not ready to do a release yet, that's fine, whenever you add more changesets to main, this PR will be updated.

Releases

@tanstack/ai-gemini@0.19.0

Minor Changes

  • #875 f0c12ba - Drop retired Gemini media models and add Veo 3.1 Lite.

    The following models return 404 NOT_FOUND from the Gemini Developer API and have been removed from the adapter's model lists and type maps:

    • imagen-3.0-generate-002 (superseded by the Imagen 4 family)
    • veo-2.0-generate-001
    • veo-3.0-generate-001
    • veo-3.0-fast-generate-001

    Added veo-3.1-lite-generate-preview (Veo 3.1 Lite) — the lowest-cost Veo 3.1 tier ($0.05/sec, 720p, video + audio), with the same 4 | 6 | 8 second durations as the rest of the Veo 3.1 family.

    If you were referencing one of the removed model ids, switch to a current model (e.g. imagen-4.0-generate-001, veo-3.1-generate-preview, or veo-3.1-lite-generate-preview).

  • #874 84d1225 - Add proper support for Nano Banana 2 Lite (gemini-3.1-flash-lite-image) as a Gemini-native image model. The automated model sync had landed this model mis-classified as a text-only chat model (output: ['text'], in GEMINI_MODELS); it's now corrected and wired into the image surface — routed through the generateContent API with output: ['text', 'image'], template-literal sizes (aspectRatio_resolution, e.g. "1:1_2K"), and image-conditioned prompts, matching the other native image models. Built for ultra-low-latency, low-cost image generation and editing.

    Also fixes the OpenRouter model sync (scripts/sync-provider-models.ts) so native image models that output both text and image are skipped for manual curation instead of being inserted as chat models.

Patch Changes

  • #772 00505fe - Update model metadata from OpenRouter API

@tanstack/ai-anthropic@0.15.13

Patch Changes

  • #772 00505fe - Update model metadata from OpenRouter API

@tanstack/ai-react@0.16.2

Patch Changes

  • #772 00505fe - Restructure the @tanstack/ai-react/mcp-apps entry so its source is resolvable by the docs snippet type-checker: the JSX implementation moves to mcp-app-resource.tsx and mcp-apps.ts re-exports it. Public exports (MCPAppResource, MCPAppResourceProps) and the subpath are unchanged.

@github-actions github-actions Bot force-pushed the changeset-release/main branch from 6db2618 to fe11d38 Compare July 1, 2026 08:26
@github-actions github-actions Bot force-pushed the changeset-release/main branch from fe11d38 to 50517e4 Compare July 1, 2026 09:12
@AlemTuzlak AlemTuzlak merged commit c5abf7a into main Jul 1, 2026
2 checks passed
@AlemTuzlak AlemTuzlak deleted the changeset-release/main branch July 1, 2026 09:15
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant