-
Notifications
You must be signed in to change notification settings - Fork 748
fix(core): planning cache #1505
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
✅ Deploy Preview for midscene ready!
To edit notification comments on pull requests, go to your Netlify project configuration. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
💡 Codex Review
Here are some automated review suggestions for this pull request.
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| let thinkingLevelToUse = opt?._thinkingLevel; | ||
| if (!thinkingLevelToUse && this.opts.aiActionContext) { |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Restore thinkingLevel option handling
The aiAct options now only read opt._thinkingLevel, so any caller still passing the documented thinkingLevel flag has its request ignored and the method falls back to the medium/high defaults. For example, packages/web-integration/tests/ai/web/puppeteer/e2e.test.ts:42-44 still passes { thinkingLevel: 'high' }, which will now be treated as if no level was provided. This silently changes planning behaviour for consumers relying on that knob; please continue accepting the existing option or update the call sites.
Useful? React with 👍 / 👎.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
👎
| // Check if the modelFamily is valid | ||
| if (!MODEL_FAMILY_VALUES.includes(modelFamily as any)) { | ||
| throw new Error(`Invalid modelFamily: ${modelFamily}`); | ||
| throw new Error(`Invalid MIDSCENE_MODEL_FAMILY value: ${modelFamily}`); |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Align invalid modelFamily error with tests
The error message for invalid MIDSCENE_MODEL_FAMILY was changed to Invalid MIDSCENE_MODEL_FAMILY value: …, but packages/shared/tests/unit-test/env/parse.test.ts:52-54 still asserts the previous Invalid modelFamily: invalid. This change causes that unit test to fail and will break the test suite until the message or expectation is brought back into sync.
Useful? React with 👍 / 👎.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
👍
No description provided.