chore(deps): Bump @openrouter/ai-sdk-provider from 2.8.1 to 3.0.0

[dependabot]

Bumps @openrouter/ai-sdk-provider from 2.8.1 to 3.0.0.

Release notes

Sourced from @​openrouter/ai-sdk-provider's releases.

3.0.0

What's Changed

• feat: switch image generation to dedicated images api by @​Robinnnnn in OpenRouterTeam/ai-sdk-provider#513
• Version Packages by @​github-actions[bot] in OpenRouterTeam/ai-sdk-provider#514
• feat: support Vercel AI SDK v7 by @​Shreyaan in OpenRouterTeam/ai-sdk-provider#511
• Version Packages by @​github-actions[bot] in OpenRouterTeam/ai-sdk-provider#516

New Contributors

• @​Robinnnnn made their first contribution in OpenRouterTeam/ai-sdk-provider#513
• @​Shreyaan made their first contribution in OpenRouterTeam/ai-sdk-provider#511

Full Changelog: OpenRouterTeam/ai-sdk-provider@2.9.1...3.0.0

2.9.1

What's Changed

• fix: send null content for tool-only assistant messages by @​robert-j-y in OpenRouterTeam/ai-sdk-provider#506
• Version Packages by @​github-actions[bot] in OpenRouterTeam/ai-sdk-provider#507

Full Changelog: OpenRouterTeam/ai-sdk-provider@2.9.0...2.9.1

2.9.0

What's Changed

• fix: allow query strings and fragments in image URL regex (#484) by @​robert-j-y in OpenRouterTeam/ai-sdk-provider#485
• fix: allow opting out of response_format strict mode (#483) by @​robert-j-y in OpenRouterTeam/ai-sdk-provider#486
• fix: stop emitting duplicate tool-call events on trailing-whitespace deltas by @​0age in OpenRouterTeam/ai-sdk-provider#489
• Version Packages by @​github-actions[bot] in OpenRouterTeam/ai-sdk-provider#490

New Contributors

• @​0age made their first contribution in OpenRouterTeam/ai-sdk-provider#489

Full Changelog: OpenRouterTeam/ai-sdk-provider@2.8.1...2.9.0

Changelog

Sourced from @​openrouter/ai-sdk-provider's changelog.

3.0.0

Major Changes

• #511 0c90b8b Thanks @​Shreyaan! - Support Vercel AI SDK v7 as a v7-only major release.

  This is a breaking change because the provider now peers on ai@^7.0.0, requires Node.js 22 or newer, and publishes ESM-only output. The provider, language, embedding, image, and video model implementations now target the @ai-sdk/provider@4 V4 interfaces, with V4 file payloads and provider-defined tool factories.

  Consumers should upgrade to ai@7, run on Node.js 22+, and import this package from ESM. Usage accounting follows the AI SDK v7 shape: cached input tokens are exposed via usage.inputTokenDetails.cacheReadTokens, and reasoning tokens are exposed via usage.outputTokenDetails.reasoningTokens. OpenRouter-specific cost, BYOK, reasoning details, annotations, and cache-control metadata remain available under providerMetadata.openrouter.

Unreleased

Major Changes

• feat: support Vercel AI SDK v7.

  This release line is v7-only: it peers on ai@^7.0.0, requires Node.js 22 or newer, and publishes ESM-only output. The provider now implements the @ai-sdk/provider@4 V4 provider/model interfaces across chat, completion, embedding, image, and video models.

  Usage accounting is mapped to the AI SDK v7 token detail shape: cached input tokens are available through usage.inputTokenDetails.cacheReadTokens, and reasoning tokens are available through usage.outputTokenDetails.reasoningTokens. OpenRouter-specific cost, BYOK, reasoning details, annotations, and cache-control metadata continue to be exposed through providerMetadata.openrouter.

2.10.0

Minor Changes

• #513 384f3c8 Thanks @​Robinnnnn! - Switch image generation to dedicated /api/v1/images endpoint

  Migrates OpenRouterImageModel from the legacy chat completions path (/chat/completions with modalities: ["image", "text"]) to OpenRouter's dedicated image generation endpoint (/images).

  Request changes:

  • Sends { model, prompt, n, size, aspect_ratio, seed, input_references } directly instead of wrapping in a chat messages array
  • files are mapped to input_references (array of { type: "image_url", image_url: { url } }) instead of inline message content parts
  • aspectRatio maps to aspect_ratio (was image_config.aspect_ratio)
  • size and n are now passed through (previously emitted warnings)

  Response changes:

  • Parses { created, data: [{ b64_json }], usage } instead of { choices: [{ message: { images } }] }
  • maxImagesPerCall updated from 1 to 10 (the new endpoint supports batch generation)

2.9.1

Patch Changes

• #506 e9cff3a Thanks @​robert-j-y! - Send content: null instead of content: "" for assistant messages that contain only tool calls. Fixes AWS Bedrock Nova rejecting requests with "The text field in the ContentBlock object is blank."

2.9.0

Minor Changes

... (truncated)

Commits

• c1ce69a Version Packages (#516)
• 0c90b8b feat: support Vercel AI SDK v7 (#511)
• 4247ab2 Version Packages (#514)
• 384f3c8 feat: switch image generation to dedicated images api (#513)
• 07a98d6 Version Packages (#507)
• e9cff3a fix: send null content for tool-only assistant messages (#506)
• 5cef3c5 Version Packages (#490)
• bb2d4cb fix: stop emitting duplicate tool-call events on trailing-whitespace deltas (...
• 82e8014 fix: allow opting out of response_format strict mode (#483) (#486)
• bf664b1 fix: allow query strings and fragments in image URL regex (#484) (#485)
• See full diff in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

---

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

• @dependabot rebase will rebase this PR
• @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
• @dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
• @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)

[dependabot]

OK, I won't notify you again about this release, but will get in touch when a new version is available. If you'd rather skip all updates until the next major or minor version, let me know by commenting @dependabot ignore this major version or @dependabot ignore this minor version. You can also ignore all major, minor, or patch releases for a dependency by adding an ignore condition with the desired update_types to your config file.

If you change your mind, just re-open this PR and I'll resolve any conflicts on it.