Skip to content

fix(deps): update dependency @ai-sdk/openai-compatible to v3 - #12

Open
renovate[bot] wants to merge 1 commit into
mainfrom
renovate/ai-sdk-openai-compatible-3.x
Open

fix(deps): update dependency @ai-sdk/openai-compatible to v3#12
renovate[bot] wants to merge 1 commit into
mainfrom
renovate/ai-sdk-openai-compatible-3.x

Conversation

@renovate

@renovate renovate Bot commented Jul 1, 2026 •
edited
Loading

Copy link
Copy Markdown

ℹ️ Note

This PR body was truncated due to platform limits.

This PR contains the following updates:

Package Change Age Confidence
@ai-sdk/openai-compatible (source) 1.0.27 → 3.0.67 age confidence

Release Notes

vercel/ai (@​ai-sdk/openai-compatible)

v3.0.67

Compare Source

Patch Changes

v3.0.66

Compare Source

Patch Changes

v3.0.65

Compare Source

Patch Changes

v3.0.64

Compare Source

Patch Changes

  • 268225c: feat(provider): add a portable max reasoning level with native provider mappings, compatibility coercions, and budget-based fallback support.

    Compatibility notes:

    • TypeScript source compatibility: Adding max widens LanguageModelV4CallOptions['reasoning'] and the derived ReasoningLevel type. Third-party providers and consumers with exhaustive switches or Record<ReasoningLevel, ...> mappings must handle max before upgrading. Ordinary calls using existing reasoning levels remain accepted.
    • Amazon Bedrock: Existing Nova 2 calls using portable reasoning: 'xhigh' now send maxReasoningEffort: 'high' instead of the unsupported 'max', and return a compatibility warning. Anthropic and OpenAI Bedrock effort mappings retain their existing xhigh behavior. Partial Bedrock reasoning configurations continue to preserve explicit values and derive missing fields; explicit effort/budget overrides and disabled thinking no longer emit warnings for portable mappings that are not sent.
    • Fireworks: Existing portable minimal and xhigh calls keep their request mappings to low and high, respectively, and now return compatibility warnings in generation and streaming results. Portable max maps to high with the same warning behavior.

    Release classification: This remains a patch changeset under the repository's explicit release policy, which uses patch releases for both fixes and features. The TypeScript source-compatibility caveat for exhaustive consumers is disclosed above. Maintainers can override this classification with a major label if they decide to align the provider-spec addition with a future AI SDK major release.

  • Updated dependencies [fc1e19e]

  • Updated dependencies [5094ebd]

  • Updated dependencies [268225c]

  • Updated dependencies [0af2f7c]

v3.0.63

Compare Source

Patch Changes

v3.0.62

Compare Source

Patch Changes
  • 04be48f: fix(openai-compatible): support multipart tool results for compatible providers

v3.0.61

Compare Source

Patch Changes

v3.0.60

Compare Source

Patch Changes

v3.0.59

Compare Source

Patch Changes

v3.0.58

Compare Source

Patch Changes

  • e3605f6: Fix streamed tool calls with missing, blank, or repeated IDs.

  • 525efc5: feat(provider): advertise image model file and mask input support

    Use confirmed model IDs for capability declarations so unrecognized model names
    remain unknown. Include Together AI FLUX.2 Pro and Flex single-image editing, and
    allow asynchronous capability lookups and middleware overrides to resolve to
    unknown.

    Advertise QuiverAI Arrow 2 and Arrow 2 Telos file-input support, and mark Together
    AI Gemini image inputs unsupported by the current single-image request mapping.

  • Updated dependencies [e3605f6]

  • Updated dependencies [525efc5]

v3.0.57

Compare Source

Patch Changes

v3.0.55

Compare Source

Patch Changes

v3.0.54

Compare Source

Patch Changes

v3.0.53

Compare Source

Patch Changes

v3.0.52

Compare Source

Patch Changes

v3.0.51

Compare Source

Patch Changes

v3.0.50

Compare Source

Patch Changes

v3.0.49

Compare Source

Patch Changes

v3.0.48

Compare Source

Patch Changes

v3.0.47

Compare Source

Patch Changes

v3.0.46

Compare Source

Patch Changes

v3.0.45

Compare Source

Patch Changes

v3.0.44

Compare Source

Patch Changes
  • e5a22f0: fix(openai-compatible): keep reasoning streams contiguous when deltas include empty tool call arrays

v3.0.43

Compare Source

Patch Changes

v3.0.42

Compare Source

Patch Changes

v3.0.41

Compare Source

Patch Changes

v3.0.40

Compare Source

Patch Changes

v3.0.39

Compare Source

Patch Changes

v3.0.37

Compare Source

Patch Changes

v3.0.36

Compare Source

Patch Changes
  • ece5bdb: fix: send reasoning_effort: "none" when top-level reasoning is disabled

v3.0.35

Compare Source

Patch Changes

v3.0.34

Compare Source

Patch Changes
  • 99989ba: feat(provider/openai-compatible): report image generation token usage

v3.0.33

Compare Source

Patch Changes
  • d68139c: fix(openai-compatible): report truncated chat streams as errors

v3.0.32

Compare Source

Patch Changes

v3.0.31

Patch Changes

  • 86892f3: fix(openai-compatible): preserve unmapped usage fields in usage.raw

    usage.raw is specified as usage "in the shape that the provider returns",
    and the chat model already parsed the usage object loosely so that extra
    top-level fields survived. The nested prompt_tokens_details and
    completion_tokens_details objects were still strict, so anything a provider
    reported inside them was dropped — which is where providers put their most
    distinguishing detail. The existing "should preserve extra usage fields"
    fixture was itself losing audio_tokens, image_tokens and text_tokens
    this way.

    Both nested objects are now parsed loosely, as is the completion model's usage
    schema, which was strict throughout despite feeding the same raw field.

    Only usage.raw changes. The mapped token counts are unaffected.

v3.0.30

Patch Changes

v3.0.29

Compare Source

Patch Changes

v3.0.28

Compare Source

Patch Changes
  • 83e6510: fix(provider/openai-compatible): clamp outputTokens.text at 0 when a provider reports completion_tokens_details.reasoning_tokens greater than completion_tokens (observed with Baseten serving reasoning models that hit the length stop mid-reasoning). The text share of completion tokens can never be negative; total and reasoning remain as reported by the provider.

v3.0.27

Compare Source

Patch Changes

v3.0.26

Compare Source

Patch Changes

v3.0.25

Compare Source

Patch Changes

v3.0.24

Compare Source

Patch Changes

v3.0.23

Compare Source

Patch Changes

v3.0.22

Compare Source

Patch Changes

v3.0.21

Compare Source

Patch Changes

v3.0.20

Compare Source

Patch Changes

v3.0.19

Compare Source

Patch Changes

v3.0.18

Compare Source

Patch Changes

v3.0.17

Compare Source

Patch Changes

v3.0.16

Compare Source

Patch Changes

v3.0.15

Compare Source

Patch Changes

v3.0.14

Compare Source

Patch Changes

v3.0.13

Compare Source

Patch Changes
  • 8b52503: feat(openai-compatible): add an extensible providerOptions type for image model requests and stop forcing response_format

v3.0.12

Compare Source

Patch Changes

v3.0.11

Compare Source

Patch Changes
  • 0b61267: Preserve structured error data from chat completion SSE streams.

v3.0.10

Compare Source

Patch Changes

v3.0.9

Compare Source

Patch Changes

v3.0.7

Compare Source

Patch Changes

v3.0.6

Compare Source

Patch Changes

v3.0.5

Compare Source

Patch Changes

v3.0.4

Compare Source

Patch Changes

v3.0.3

Compare Source

Patch Changes

v3.0.2

Compare Source

Patch Changes

v3.0.1

Compare Source

Patch Changes

v3.0.0

Compare Source

Major Changes

  • ef992f8: Remove CommonJS exports from all packages. All packages are now ESM-only ("type": "module"). Consumers using require() must switch to ESM import syntax.

  • c29a26f: feat(provider): add support for provider references and uploading files as supported per provider

  • 8359612: Start v7 pre-release

  • 04e9009: chore: make provider implementations code patterns more consistent, including renaming certain exported symbols

    For all externally exported symbols that were renamed, the old names continue to work via deprecated aliases.

Patch Changes

  • ab81968: fix(openai-compatible): buffer tool call deltas until function.name arrives

  • 38fc777: Add AI Gateway hint to provider READMEs

  • 74d520f: feat: migrate providers to support new top-level reasoning parameter

  • e59c955: feat(vertex): add grok models to vertex provider

  • 816ff67: fix(openai-compatible): honor camelCase providerOptions key in chat and completion models

  • 9f1e1ba: fix: accept empty string role in streaming delta chunks from OpenAI-compatible providers

  • 45b3d76: fix(security): prevent streaming tool calls from finalizing on parsable partial JSON

    Streaming tool call arguments were finalized using isParsableJson() as a heuristic for completion. If partial accumulated JSON happened to be valid JSON before all chunks arrived, the tool call would be executed with incomplete arguments. Tool call finalization now only occurs in flush() after the stream is fully consumed.

  • 9f0e36c: trigger release for all packages after provenance setup

  • 58a2ad7: fix: more precise default message for tool execution denial

  • 8f3e1da: chore(openai-compat): update v3 specs to v4

  • f7295cb: revert incorrect fix #​13172

  • 008271d: feat(openai-compatible): emit warning when using kebab-case instead of camelCase

  • 7fc6bd6: Raise minimum supported Node.js version to 22. Supported versions: 22, 24, and 26.

  • f807e45: Extract shared StreamingToolCallTracker class into @ai-sdk/provider-utils to deduplicate streaming tool call handling across OpenAI-compatible providers. Also adds missing generateId() fallback for toolCallId in Alibaba's doGenerate path and ensures all providers finalize unfinished tool calls during stream flush.

  • 0c4c275: trigger initial canary release

  • 6fd51c0: fix(provider): preserve error type prefix in getErrorMessage

  • cd9c311: fix(openai, openai-compatible): only send null content for assistant messages with tool calls

  • 9bd6512: feat(provider): change file part data property to be tagged with a type and remove the image part type

  • 258c093: chore: ensure consistent import handling and avoid import duplicates or cycles

  • b8396f0: trigger initial beta release

  • bfb756d: patch - send content: null instead of empty string for tool-only assistant messages

  • 90e2d8a: chore: fix unused vars not being flagged by our lint tooling

  • b3976a2: Add workflow serialization support to all provider models.

    @ai-sdk/provider-utils: New serializeModel() helper that extracts only serializable properties from a model instance, filtering out functions and objects containing functions. Third-party provider authors can use this to add workflow support to their own models.

    All providers: headers is now optional in provider config types. This is non-breaking — existing code that passes headers continues to work. Custom provider implementations that construct model configs manually can now omit headers, which is useful when models are deserialized from a workflow step boundary where auth is provided separately.

    All provider model classes now include WORKFLOW_SERIALIZE and WORKFLOW_DESERIALIZE static methods, enabling them to cross workflow step boundaries without serialization errors.

v2.0.81

Compare Source

Patch Changes

v2.0.80

Compare Source

Patch Changes

v2.0.79

Compare Source

Patch Changes

v2.0.78

Compare Source

Patch Changes

v2.0.77

Compare Source

Patch Changes

v2.0.76

Compare Source

Patch Changes

v2.0.75

Compare Source

Patch Changes

v2.0.74

Patch Changes

v2.0.73

Patch Changes

v2.0.72

Compare Source

Patch Changes

v2.0.71

Compare Source

Patch Changes

v2.0.70

Compare Source

Patch Changes
  • c79dd10: fix(openai-compatible): report truncated chat streams as errors

v2.0.69

Compare Source

Patch Changes

  • 7440d89: fix(openai-compatible): preserve unmapped usage fields in usage.raw

    usage.raw is specified as usage "in the shape that the provider returns",
    and the chat model already parsed the usage object loosely so that extra
    top-level fields survived. The nested prompt_tokens_details and
    completion_tokens_details objects were still strict, so anything a provider
    reported inside them was dropped — which is where providers put their most
    distinguishing detail. The existing "should preserve extra usage fields"
    fixture was itself losing audio_tokens, image_tokens and text_tokens
    this way.

    Both nested objects are now parsed loosely, as is the completion model's usage
    schema, which was strict throughout despite feeding the same raw field.

    Only usage.raw changes. The mapped token counts are unaffected.

v2.0.68

Compare Source

Patch Changes

v2.0.67

Compare Source

Patch Changes

v2.0.66

Compare Source

Patch Changes
  • de18066: fix(provider/openai-compatible): clamp outputTokens.text at 0 when a provider reports completion_tokens_details.reasoning_tokens greater than completion_tokens (observed with Baseten serving reasoning models that hit the length stop mid-reasoning). The text share of completion tokens can never be negative; total and reasoning remain as reported by the provider.
  • Updated dependencies [2171d15]

v2.0.65

Compare Source

Patch Changes

v2.0.64

Compare Source

Patch Changes

v2.0.63

Compare Source

Patch Changes

v2.0.62

Compare Source

Patch Changes

v2.0.61

Compare Source

Patch Changes
  • 94fda5c: Preserve structured error data from chat completion SSE streams.

[v2.0.60](https://redirect.gith

❗ Important

✂ PR body was truncated to here.

Configuration

📅 Schedule: (UTC)

  • Branch creation
    • At any time (no schedule defined)
  • Automerge
    • At any time (no schedule defined)

🚦 Automerge: Disabled by config. Please merge this manually once you are satisfied.

♻ Rebasing: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox.

🔕 Ignore: Close this PR and you won't be reminded about this update again.

  • If you want to rebase/retry this PR, check this box

This PR was generated by Mend Renovate. View the repository job log.

@renovate
renovate Bot force-pushed the renovate/ai-sdk-openai-compatible-3.x branch from 74083d7 to 93fb554 Compare July 4, 2026 07:52
@renovate
renovate Bot force-pushed the renovate/ai-sdk-openai-compatible-3.x branch 2 times, most recently from 0e4bf9a to 4d47c17 Compare July 18, 2026 15:18
@renovate
renovate Bot force-pushed the renovate/ai-sdk-openai-compatible-3.x branch 2 times, most recently from 7c46919 to 8f9ccb5 Compare July 29, 2026 03:47
@renovate
renovate Bot force-pushed the renovate/ai-sdk-openai-compatible-3.x branch 3 times, most recently from 6d8acd9 to 195a803 Compare August 8, 2026 11:54
@renovate
renovate Bot force-pushed the renovate/ai-sdk-openai-compatible-3.x branch 2 times, most recently from 93a8934 to cf9664d Compare August 17, 2026 23:48
@renovate
renovate Bot force-pushed the renovate/ai-sdk-openai-compatible-3.x branch 2 times, most recently from 641adfd to fa95c66 Compare August 29, 2026 07:53
@renovate
renovate Bot force-pushed the renovate/ai-sdk-openai-compatible-3.x branch 2 times, most recently from 07b5329 to 137661e Compare September 6, 2026 00:18
@renovate
renovate Bot force-pushed the renovate/ai-sdk-openai-compatible-3.x branch 2 times, most recently from 97f2b53 to ad2b1b0 Compare September 19, 2026 15:31
@renovate
renovate Bot force-pushed the renovate/ai-sdk-openai-compatible-3.x branch 2 times, most recently from 321fcc9 to 0d6fd2d Compare October 3, 2026 11:00
@renovate
renovate Bot force-pushed the renovate/ai-sdk-openai-compatible-3.x branch from 0d6fd2d to e23b687 Compare October 6, 2026 21:07
@renovate
renovate Bot force-pushed the renovate/ai-sdk-openai-compatible-3.x branch from e23b687 to 5ef63f6 Compare October 9, 2026 07:57
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

0 participants