Skip to content

fix(deps): update dependency @openai/agents-extensions to ^0.14.0 - #143

Open
renovate[bot] wants to merge 1 commit into
mainfrom
renovate/openai-agents-extensions-0.x
Open

fix(deps): update dependency @openai/agents-extensions to ^0.14.0#143
renovate[bot] wants to merge 1 commit into
mainfrom
renovate/openai-agents-extensions-0.x

Conversation

@renovate

@renovate renovate Bot commented Aug 10, 2026

Copy link
Copy Markdown
Contributor

This PR contains the following updates:

Package Change Age Confidence
@openai/agents-extensions (source) ^0.13.0^0.14.0 age confidence

Release Notes

openai/openai-agents-js (@​openai/agents-extensions)

v0.14.3

Compare Source

What's Changed

Documentation & Other Changes

Full Changelog: openai/openai-agents-js@v0.14.2...v0.14.3

v0.14.2

Compare Source

What's Changed
Documentation & Other Changes

Full Changelog: openai/openai-agents-js@v0.14.1...v0.14.2

v0.14.1

Compare Source

What's Changed

Documentation & Other Changes

Full Changelog: openai/openai-agents-js@v0.14.0...v0.14.1

v0.14.0

Compare Source

Key Changes
Programmatic Tool Calling support

The SDK now supports Programmatic Tool Calling, allowing supported models to generate hosted JavaScript that coordinates eligible tools and reduces their intermediate results. Program calls are preserved across streaming, sessions, replay, and serialized RunState. Refer to a simple example to see how it works.

Sensitive model and tool data logging is now disabled by default

Model and tool data is no longer logged unless explicitly enabled. Use setSensitiveDataLoggingEnabled(true) to opt in programmatically, or set the corresponding OPENAI_AGENTS_DONT_LOG_* environment variables to 0 or false.

Task and turn tracing is enabled by default

Runs now emit task and turn spans by default, providing a clearer trace hierarchy and usage metadata. Set includeTaskAndTurnSpans to false in the per-run tracing configuration to opt out.

Run cancellation now propagates to function and MCP tools

Cancellation signals now reach streaming and non-streaming function tools as well as MCP tool requests. Stream completion also waits for background work and cleanup to settle before resolving.

AI SDK 7 support

The AI SDK adapter now supports LanguageModelV4 models and AI SDK 7 while preserving existing v2 and v3 compatibility.

Vercel S3 bucket mounts

A new VercelCloudBucketMountStrategy enables S3 buckets to be mounted in Vercel sandboxes using Mountpoint for Amazon S3.

What's Changed
Documentation & Other Changes
New Contributors

Full Changelog: openai/openai-agents-js@v0.13.5...v0.14.0

v0.13.5

Compare Source

What's Changed
Documentation & Other Changes
New Contributors

Full Changelog: openai/openai-agents-js@v0.13.4...v0.13.5


Configuration

📅 Schedule: (in timezone America/New_York)

  • Branch creation
    • "before 9am on Monday"
  • 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.

@dawsontoth dawsontoth left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Approved — and this one unblocks #146

Verified locally on 1e440602, Node 24.17.0:

  • npm ci clean; dprint check clean; oxlint clean; npm run build succeeds (ESM + DTS).
  • Tests: 52/53 files, 341/345 pass. The only failures are ink/main.test.tsx, which fails locally on macOS regardless of branch (terminal-width-dependent rendering) — CI is green on this PR, so that's local noise, not this bump.

@openai/agents-extensions@0.14.3 is the version that adds AI SDK spec-v4 support:

if (typeof spec === 'string' && spec.toLowerCase().startsWith('v4')) return 'v4';
// ...
throw new UserError(`Unsupported AI SDK specificationVersion: ... Only v2, v3, and v4 are supported.`)
peerDependencies: { '@ai-sdk/provider': '^2.0.0 || ^3.0.0 || ^4.0.0', ai: '^6.0.0 || ^7.0.0' }

That makes it the prerequisite for #146 (@ai-sdk/anthropic@4), which is broken on its own — I've requested changes there with the details.

One note on merge order: land this together with #140

On its own, this branch splits @openai/agents-core across majors, because extensions 0.14.3 pins core 0.14.3 while @openai/agents stays at 0.13.5:

+-- @openai/agents-extensions@0.14.3 -> @openai/agents-core@0.14.3
+-- @openai/agents@0.13.5            -> @openai/agents-core@0.13.5

I probed that seam and it does work — getModel('claude-…') handed to Agent/run() reaches APICallError: invalid x-api-key, i.e. a real Anthropic call — because the model interface is structural with no version gate. So this is safe to merge alone.

But merging #140 alongside it is strictly better: the tree dedupes to a single @openai/agents-core@0.14.3 and all three providers resolve:

claude-sonnet-4-5: APICallError: invalid x-api-key
gemini-2.5-pro:    APICallError: API key not valid. Please pass a valid API key.
gpt-5:             APICallError: Incorrect API key provided: bad

Worth a Renovate group rule so @openai/agents and @openai/agents-extensions always move together — they've now split in both directions across two cycles.

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