fix: maxTokens not used #3013

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

Jump to bottom

Open

dingdinglz wants to merge 1 commit into onlook-dev:main

from dingdinglz:main

Open

fix: maxTokens not used #3013

dingdinglz wants to merge 1 commit into onlook-dev:main from dingdinglz:main

+1 −0

Conversation

dingdinglz

Copy link

@dingdinglz dingdinglz commented Oct 14, 2025 •

edited by coderabbitai bot

Loading

Description

maxOutputTokens set but never used

Type of Change

Bug fix
New feature
Documentation
Refactor
Other (please describe):

Important

Fix missing maxOutputTokens parameter in streamText call in createRootAgentStream in root.ts.

Bug Fix:
- Add maxOutputTokens: modelConfig.maxOutputTokens to streamText call in createRootAgentStream in root.ts to ensure token limit is applied.

^{This description was created by}Ellipsis ^{for 7e42a07. You can customize this summary. It will automatically update as commits are pushed.}

Summary by CodeRabbit

New Features
- Added support for configuring a maximum output length for AI responses. This enables finer control over response size during streaming, helping manage cost and maintain concise outputs. Responses now adhere to a cap derived from the selected model’s settings, improving predictability and preventing overly long generations.

@dingdinglz


 fix: maxTokens not used

7e42a07

@vercel Vercel

Copy link

vercel bot commented Oct 14, 2025

@dingdinglz is attempting to deploy a commit to the Onlook Team on Vercel.

A member of the Team first needs to authorize it.

@coderabbitai coderabbitai

Copy link

coderabbitai bot commented Oct 14, 2025 •

edited

Loading

Walkthrough

Adds the maxOutputTokens parameter to the streamText call within createRootAgentStream, sourcing its value from modelConfig.maxOutputTokens. No other logic or control-flow changes.

Changes

Cohort / File(s)	Summary
Root agent streaming config `packages/ai/src/agents/root.ts`	Passes `maxOutputTokens` from `modelConfig.maxOutputTokens` into `streamText` within `createRootAgentStream`.

Sequence Diagram(s)

sequenceDiagram
 autonumber
 participant Caller
 participant RootAgent
 participant TextStreamer as streamText
 Caller->>RootAgent: createRootAgentStream(modelConfig)
 Note right of RootAgent: Extract maxOutputTokens from modelConfig
 RootAgent->>TextStreamer: streamText({... , maxOutputTokens})
 TextStreamer-->>RootAgent: Streamed text chunks
 RootAgent-->>Caller: Forward streamed output

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~8 minutes

Poem

I tweak my dials, hop hop—no fuss,
A token cap guides the output bus.
Streams now heed a gentle bound,
Carrots counted, neatly sound.
With fewer words, I still delight—
A tidy burrow, snug and bright.

Pre-merge checks and finishing touches

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Description Check	⚠️ Warning	The pull request provides a clear description of the issue and correctly labels it as a bug fix, but it omits the Related Issues and Testing sections required by the template, leaving out links to any issue trackers and steps or tests used to verify the change.	Please add a Related Issues section linking any relevant issue numbers and a Testing section that describes how you verified the fix or any tests you added to ensure maxOutputTokens is applied correctly.

✅ Passed checks (2 passed)

Check name	Status	Explanation
Title Check	✅ Passed	The title succinctly describes the primary change by indicating that the token limit parameter was not being used, which directly aligns with the bug fix in createRootAgentStream. It is concise and clearly conveys the main change without unnecessary detail.
Docstring Coverage	✅ Passed	No functions found in the changes. Docstring coverage check skipped.

✨ Finishing touches

📝 Generate docstrings

🧪 Generate unit tests (beta)

Create PR with unit tests
Post copyable unit tests in a comment

📜 Recent review details

Configuration used: CodeRabbit UI

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between f273632 and 7e42a07.

📒 Files selected for processing (1)

packages/ai/src/agents/root.ts (1 hunks)

🧰 Additional context used

📓 Path-based instructions (2)

**/*.{ts,tsx}

📄 CodeRabbit inference engine (AGENTS.md)

Do not use the any type unless necessary

Files:

packages/ai/src/agents/root.ts

{apps,packages}/**/*.{ts,tsx}

📄 CodeRabbit inference engine (CLAUDE.md)

Avoid using the any type unless absolutely necessary

Files:

packages/ai/src/agents/root.ts

🔇 Additional comments (1)

packages/ai/src/agents/root.ts (1)

25-25: Approve change: maxOutputTokens is defined on ModelConfig and initialized in initModel using MODEL_MAX_TOKENS, so no further action needed.

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

Navigation Menu

Search code, repositories, users, issues, pull requests...

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

fix: maxTokens not used #3013

Are you sure you want to change the base?

fix: maxTokens not used #3013

Conversation

@dingdinglz dingdinglz commented Oct 14, 2025 •

edited by coderabbitai bot

Loading

Uh oh!

Description

Type of Change

Summary by CodeRabbit

Uh oh!

vercel bot commented Oct 14, 2025

Uh oh!

coderabbitai bot commented Oct 14, 2025 •

edited

Loading

Uh oh!

Walkthrough

Changes

Sequence Diagram(s)

Estimated code review effort

Poem

Pre-merge checks and finishing touches

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

fix: maxTokens not used #3013

Are you sure you want to change the base?

fix: maxTokens not used #3013

Conversation

@dingdinglz dingdinglz commented Oct 14, 2025 • edited by coderabbitai bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Description

Type of Change

Summary by CodeRabbit

Uh oh!

vercel bot commented Oct 14, 2025

Uh oh!

coderabbitai bot commented Oct 14, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Walkthrough

Changes

Sequence Diagram(s)

Estimated code review effort

Poem

Pre-merge checks and finishing touches

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

@dingdinglz dingdinglz commented Oct 14, 2025 •

edited by coderabbitai bot

Loading

coderabbitai bot commented Oct 14, 2025 •

edited

Loading