Skip to content

fix(anthropic): empty thinking cause content block not stop#1135

Merged
looplj merged 3 commits intorelease/v0.9.xfrom
dev-tmp
Mar 23, 2026
Merged

fix(anthropic): empty thinking cause content block not stop#1135
looplj merged 3 commits intorelease/v0.9.xfrom
dev-tmp

Conversation

@looplj
Copy link
Copy Markdown
Owner

@looplj looplj commented Mar 23, 2026 •
edited by devin-ai-integration bot
Loading

@gemini-code-assist
Copy link
Copy Markdown
Contributor

gemini-code-assist bot commented Mar 23, 2026

Summary of Changes

Hello, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request addresses a specific bug in the Anthropic stream processing where an empty 'thinking' block could lead to an incorrect state, preventing other content blocks from being properly closed. The changes ensure robust handling of content block termination by explicitly closing any active blocks before introducing a synthetic thinking block, thereby improving the reliability of stream parsing and event generation.

Highlights

  • Anthropic Stream Fix: Implemented a fix in the Anthropic inbound stream transformer to ensure that any currently open text or tool content blocks are explicitly closed before a synthetic 'thinking' content block is created. This resolves an issue where an empty thinking block could prevent subsequent content blocks from properly terminating.
  • Improved Content Block Handling: Introduced logic to check hasTextContentStarted and hasToolContentStarted flags and enqueue content_block_stop events if either is true, preventing content blocks from remaining open unexpectedly.
  • New Test Cases: Added two new test cases, TestPendingSignature_SignatureWithoutThinking_AfterText and TestPendingSignature_SignatureWithoutThinking_AfterToolUse, to validate the correct behavior of content block termination when a signature arrives without preceding thinking content, specifically after a text block or a tool use block.
Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature Command Description
Code Review /gemini review Performs a code review for the current pull request in its current state.
Pull Request Summary /gemini summary Provides a summary of the current pull request in its current state.
Comment @gemini-code-assist Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help /gemini help Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for GitHub and other Google products, sign up here.

Footnotes

  1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

devin-ai-integration[bot]
devin-ai-integration bot reviewed Mar 23, 2026
View reviewed changes
Copy link
Copy Markdown
Contributor

@devin-ai-integration devin-ai-integration bot left a comment

Choose a reason for hiding this comment

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

✅ Devin Review: No Issues Found

Devin Review analyzed this PR and found no potential bugs to report.

View in Devin Review to see 3 additional findings.

Open in Devin Review

gemini-code-assist[bot]
gemini-code-assist bot reviewed Mar 23, 2026
View reviewed changes
Copy link
Copy Markdown
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

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

Code Review

This pull request refactors the Anthropic inbound stream transformer to correctly handle the closure of text and tool content blocks when a signature arrives without explicit thinking content. It introduces logic to enqueue content_block_stop events for any active text or tool blocks before creating a synthetic thinking block, and adds a hasToolContentStarted flag to track tool content state. New test cases validate this behavior for both text and tool content. Additionally, a new test data file gemini-thought.jsonl is added, likely supporting similar 'thinking' block or signature processing for Gemini models. There is no feedback to provide.

@looplj looplj merged commit a82bdfa into release/v0.9.x Mar 23, 2026
3 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@devin-ai-integration devin-ai-integration[bot] devin-ai-integration[bot] left review comments

+1 more reviewer

@gemini-code-assist gemini-code-assist[bot] gemini-code-assist[bot] left review comments

Reviewers whose approvals may not affect merge requirements

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

1 participant

@looplj