Repository navigation
feat: validate providers without model allowlists (stack 2/4) - #2941
Open
antonvishal wants to merge 19 commits into
Open
antonvishal wants to merge 19 commits into
antonvishal wants to merge 19 commits into
Conversation
🦋 Changeset detectedLatest commit: e2007c0 The changes in this PR will be included in the next version bump. This PR includes changesets to release 25 packages
Not sure what this means? Click here to learn what changesets are. Click here if you're a maintainer who wants to add another changeset to this PR |
Contributor
|
This PR is from an external contributor and must be approved by a stagehand team member with write access before CI can run. |
github-actions
Bot
added
external-contributor
antonvishal
marked this pull request as ready for review
September 15, 2026 17:54
4 tasks done
miguelg719
reviewed
Sep 27, 2026
# Conflicts: # packages/sdk-go/internal/extensionassets/stagehand-extension.zip
# Conflicts: # packages/sdk-go/internal/extensionassets/stagehand-extension.zip # pnpm-lock.yaml
…2-pr-2921 # Conflicts: # packages/sdk-go/internal/extensionassets/stagehand-extension.zip
antonvishal
force-pushed
the
newer-models-extension-protocol-sdks
branch
from
October 3, 2026 17:42
c1aeddd to
e06a3ff
Compare
|
Review the following changes in direct dependencies. Learn more about Socket for GitHub.
|
antonvishal
changed the title
Use current OpenAI, Anthropic, and Google catalog IDs in SDK examples, generated schema samples, eval defaults, and harness pricing. GPT-6 models default to hybrid agent mode. CUA defaults stay on the existing computer-use IDs.
Keep oxfmt happy after the current provider ID strings.
Leave eval harness IDs unchanged. Use gpt-6-luna for former mini defaults, keep Sol for larger OpenAI fixtures.
…ion-protocol-sdks Co-authored-by: Cursor <cursoragent@cursor.com> # Conflicts: # pnpm-lock.yaml # pnpm-workspace.yaml
…-models-extension-protocol-sdks
# Conflicts: # packages/sdk-go/internal/extensionassets/stagehand-extension.zip
# Conflicts: # packages/sdk-go/internal/extensionassets/stagehand-extension.zip
2 tasks
This branch has not been deployed
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Why
Stack 2/4. New model IDs should work without a Stagehand release. Addresses the request to remove the allowlist in #2941.
Merge order: #2921, #2941, #3098, #3068. Fork PRs target upstream
main; merge in this order. Each branch contains its predecessor. Depends on #2921.What
Validate only the OpenAI, Anthropic, or Google provider prefix and a nonempty, whitespace-free model ID. Pass opaque IDs to the provider and preserve its inference errors. Widen generated model ID types and share direct provider construction.
Examples, unit tests, and generated schema samples use current catalog IDs:
openai/gpt-6-luna(mini-class),openai/gpt-6.1-sol(default),openai/gpt-6-astra(largest), andanthropic/claude-sonnet-5-5. Eval harness defaults and eval tests are unchanged. xAI arrives in stack 4.Focused diff: antonvishal/stagehand@remove-groq-cerebras...newer-models-extension-protocol-sdks
How
Extension, Go SDK, and Python SDK unit tests passed.
Reviewer: accept an unknown ID under each registered provider; reject unsupported prefixes, empty IDs, and whitespace. Check direct inference and Gateway forwarding. This replaces this PR's earlier model-list refresh.