> ## Documentation Index
> Fetch the complete documentation index at: https://docs.matterai.so/llms.txt
> Use this file to discover all available pages before exploring further.

# AI Code Reviews Changelog

> Product updates and announcements for MatterAI Code Reviews

<Update label="December 22, 2025">
  ## v4.205.0

  ### Added

  * **New AI Code Review Features:**
    * `/matter review-max` - Advanced AI Code Review with tool-use enabled analysis
    * `/matter fix` - Automated Code Fix Generation for review comments
  * Enhanced documentation for new AI-powered code review capabilities
  * Confidence scoring system for review comments
  * Automated fix PR generation with separate branch creation

  ### Changed

  * Updated command list documentation with detailed feature descriptions
  * Enhanced code review workflow with deeper analysis capabilities
  * Improved developer experience with automated fix application

  ### Benefits

  * **Time saved**: 15-30 minutes per PR on fix application
  * **Review depth**: 3x more comprehensive with tool-use
  * **Accuracy**: Confidence scoring reduces false positives
  * **Developer satisfaction**: Zero manual copy-pasting
</Update>

<Update label="December 16, 2025">
  ## Formatting & Config

  * **Enhanced Readability**: Improved AI-generated PR review formatting for a better developer experience.
  * **Optimized Configuration**: Fine-tuned AI model settings specifically for code review workflows.
</Update>

<Update label="November 20, 2025">
  ## Reliability & Reasoning

  * **Robust Fallbacks**: Intelligent model fallback mechanisms for uninterrupted reviews.
  * **"Thinking" Models**: Added support for reasoning tool calls before review generation.
</Update>

<Update label="October 22, 2025">
  ## Fix in Cursor Button

  MatterAI review comments now have a `Fix in Cursor` button to open Cursor with a ready to use AI Prompt to fix the issue!

  <img src="https://res.cloudinary.com/dxvbskvxm/image/upload/v1761841994/Frame_3472590_hybstm.png" alt="Fix in Cursor Button" />
</Update>

<Update label="October 22, 2025">
  ## Faster Review Cycles

  With priority setting, MatterAI now adds `Low Priority` comments in the PR review body with diff patch instead of review comments. Allowing you to merge PRs faster while still getting all the code reviews.

  <img src="https://res.cloudinary.com/dxvbskvxm/image/upload/v1761732990/Screenshot_2025-10-29_at_15.46.05_1_jx6dfa.png" alt="Clear PR review body with diff patch" />
</Update>

<Update label="October 18, 2025">
  ## Hallicination Evals

  MatterAI now detects and removes 99% of hallucinations in code reviews with new eval engine, powered by Axon Code model.
</Update>

<Update label="October 13, 2025">
  ## Login via Microsoft

  You can now login via Microsoft to access your MatterAI account.
</Update>

<Update label="October 13, 2025">
  ## Enable PR Review Skip Alerts

  Enable or Disable PR review skip alerts to reduce noise in your code reviews.
</Update>

<Update label="October 13, 2025">
  ## PR Review Priority Settings

  Set the priority level for what PR review comments are added in your PRs/MRs. Options are: All, Medium and above, Only HIGH.
</Update>

<Update label="October 7, 2025">
  ## Gitlab V16 Support

  MatterAI now supports Self-Hosted Gitlab V16 to along with v17 and v18.
</Update>

<Update label="September 30, 2025">
  ## Major AI Code Review Engine Upgrade

  Smarter, faster and more accurate AI code reviews with our latest engine upgrade.
</Update>

<Update label="September 27, 2025">
  ## Dependabot PR Reviews Skip

  Configurable to skip Dependabot PR reviews to reduce noise in your code reviews.
</Update>

<Update label="September 11, 2025">
  ## Migration to Axon-Code Model

  All MatterAI Customers are now using the default `axon-code` model for all code reviews.
</Update>

<Update label="September 10, 2025">
  ## Codebase Learnings File Patterns Update

  Minor updates to skip heavy and non-essential files from the learning map.
</Update>

<Update label="September 4, 2025">
  ## Codebase Learnings in GA

  MatterAI Codebase learnings creates a learning map of all your code for maximum content in code reviews. Learn more: [Codebase Learnings](/features/codebase-learnings)
</Update>

<Update label="September 1, 2025">
  ## Mermaid Diagram Bugfix

  Fixed an issue where mermaid diagrams were not rendering correctly in the AI code review summary.
</Update>

<Update label="August 28, 2025">
  ## Auto-Resolve Conversations

  When MatterAI detects an existing review suggestion is resolved, it will automatically mark the conversation as resolved alon with a ✅ Resolved comment.

  <Frame>
    <img src="https://mintcdn.com/gravitycloud-9ebb5c50/Kf5TO2D59vS7zbLr/images/features/auto-resolve.png?fit=max&auto=format&n=Kf5TO2D59vS7zbLr&q=85&s=234e3793be307f3eea7ebb93a959ae95" alt="Auto-Resolve Conversations" width="1666" height="1392" data-path="images/features/auto-resolve.png" />
  </Frame>
</Update>

<Update label="August 25, 2025">
  ## MATTER.md Rules

  Now you can generate `MATTER.md` file in your repositories to define rules for AI code reviews.

  <Card title="MATTER.md Rules" icon="bitbucket" href="/features/rulesets#matter-md">
    Get Started with MatterAI Rulesets
  </Card>

  ### Example

  ```markdown MATTER.md lines icon="markdown" theme={null}
  # CODE_REVIEW_RULES

  ## 1. Code Format & Style
     - Use camelCase for variables and functions
     - Use PascalCase for constructors and classes
     - Use const for immutable values, let for variables
     - Prefer arrow functions for callbacks and short functions

  ## 2. Modern JavaScript Patterns
     - Use destructuring for object/array extraction
     - Prefer template literals over string concatenation
     - Use optional chaining (?.) for safe property access
     - Use nullish coalescing (??) for default values

  ## 3. Async Operations
     - Prefer async/await over .then() chains
     - Always handle promise rejections with try/catch
     - Use Promise.all() for parallel async operations
     - Avoid mixing async/await with .then()

  ## 4. Error Handling
     - Validate function parameters at entry
     - Use meaningful error messages
     - Handle edge cases (null, undefined, empty arrays)
     - Log errors with sufficient context

  ## 5. Performance & Memory
     - Avoid creating functions inside render loops
     - Use array methods (map, filter, reduce) appropriately
     - Clean up event listeners and timers
     - Minimize DOM manipulation in loops
  ```
</Update>

<Update label="August 18, 2025">
  ## Low Verbosity Summary

  Verbosity in summaries are reduced to provide a more concise and focused summary.
</Update>

<Update label="August 15, 2025">
  ## Bugfix - AI Summary generation

  Minor bugfix on AI Summary generation JSON formatting that in somecases caused undefined to show
</Update>

<Update label="August 10, 2025">
  ## Review Engine v6

  The latest version of our AI code review engine is now available, featuring:

  * **Improved Accuracy**: Enhanced understanding of code context and structure.
  * **Faster Processing**: Optimized algorithms for quicker review generation.
  * **Better Language Support**: Expanded support for more programming languages and frameworks.
  * **Enhanced Security Checks**: More robust detection of security vulnerabilities and code smells.
</Update>

<Update label="July 29, 2025">
  ## Improvements

  * Stronger code reviews with our updated review engine
  * Updates to on-prem enterprise with better scaling and lite-reviews for cost savings
  * Bug fixes in summary generations and mermaid diagrams
  * Tanka poem in Summary: Similar to Haiku but expressing deeper emotions or nature themes.

  These upgrades mean faster, sharper, and more efficient reviews, try it out and let us know what you think!
</Update>

<Update label="July 22, 2025">
  ### Slack Alerts 🔔

  Get alerts on Slack channel when any PR is merged below your configured Code Quality threshold or with an unresolved security vulnerability!

  <Card icon="slack" title="Slack Alerts" href="/connectors/slack">
    Configure Slack Alerts
  </Card>
</Update>

<Update label="July 15, 2025">
  ### Auto Resolve Comments ✅

  MatterAI automatically marks resolved issues in new commits with a ✅ Resolved comment, including a resolution reason.
  Benefits:
  Saves engineers time by eliminating manual comments and issue resolution.
  Validates fixes in new commits, exclusive to MatterAI-generated AI code reviews.

  <Card icon="message-check" title="Auto Resolve Comments" href="/features/auto-resolve">
    Learn More about Auto Resolve Comments
  </Card>
</Update>

<Update label="July 8, 2025">
  ### Similarity Search 🔍

  Similarity Search automatically reviews new or modified function calls in pull requests, comparing them to existing repository definitions. It verifies alignment with the function's contract (parameters, return value, side-effects). If a mismatch is found, it provides an inline suggestion detailing:
  The issue: What's misused and why.
  The fix: Minimal code changes needed.
  The impact: Risks if the mismatch is deployed.

  <Card icon="magnifying-glass" title="Similarity Search" href="/features/similarity-search">
    Learn More about Similarity Search
  </Card>
</Update>

<Update label="July 1, 2025">
  ## Integrations

  ### Gitlab Setup is GA

  MatterAI seamlessly integrates with GitLab to enhance your development workflow!

  <Frame>
    <img src="https://mintcdn.com/gravitycloud-9ebb5c50/-boUb8mu3Ny1_cmb/images/connectors/gitlab/gitlab-merge-request-summary.png?fit=max&auto=format&n=-boUb8mu3Ny1_cmb&q=85&s=875953b7afc2b65c678571b4c0fa0e90" alt="Setting up MatterAI service account" width="2940" height="1608" data-path="images/connectors/gitlab/gitlab-merge-request-summary.png" />
  </Frame>

  <Card title="Gitlab Integration" icon="gitlab" href="/quickstart-ai-code-review-gitlab">
    Get Started with Gitlab AI Code Reviews
  </Card>

  ### Atlassian Bitbucket Setup is GA

  MatterAI seamlessly integrates with Atlassian Bitbucket to enhance your development workflow!

  <Frame>
    <img src="https://mintcdn.com/gravitycloud-9ebb5c50/-boUb8mu3Ny1_cmb/images/connectors/bitbucket/matterai-bitbucket-summary.png?fit=max&auto=format&n=-boUb8mu3Ny1_cmb&q=85&s=c370c097ecfd75f840a33777506dccdd" alt="Setting up MatterAI service account" width="2940" height="1632" data-path="images/connectors/bitbucket/matterai-bitbucket-summary.png" />
  </Frame>

  <Card title="Bitbucket Integration" icon="bitbucket" href="/quickstart-ai-code-review-atlassian-bitbucket">
    Get Started with Bitbucket AI Code Reviews
  </Card>
</Update>

<Update label="June 24, 2025">
  ### Developer Workflow Integration

  * **Keyboard Shortcut Customization**: Personalize your MatterAI interaction experience.

  ### Code Analysis Upgrades

  * **Cross-Repository Analysis**: Identify patterns and issues across multiple repositories.
  * **Legacy Code Support**: Improved analysis for older codebases and deprecated languages.
</Update>

<Update label="June 17, 2025">
  ### Review Engine Improvements

  * **End Line Character Fixes**: Intelligent handling of line ending inconsistencies in GitHub.
  * **Committable Code Generation**: Enhanced code suggestions that are ready to commit without manual fixes.
  * **Reduced Verbosity**: More concise code and text outputs without sacrificing clarity.

  ### LLM Cost Metrics

  * **Token Usage**: Tools to monitor and optimize token consumption.
  * **Model Performance**: Side-by-side comparison of different LLM providers.
</Update>

<Update label="June 10, 2025">
  ### Enterprise AI Integration

  * **Vertex AI Support**: Native integration with Google's Vertex AI platform for enhanced model capabilities.
  * **Multi-Model Orchestration**: Intelligent routing between different AI providers based on task requirements.

  ### Enterprise Security Enhancements

  * **Role-Based Access Control**: Granular permission management for teams of all sizes.
</Update>

<Update label="June 3, 2025">
  ### New Features & Improvements

  * ✅ **Similarity Search (GA)**: Now generally available with AST grep functionality (no AI required).
  * 🔍 **Enhanced Code Reviews**: Deeper analysis, better accuracy, and improved string literals handling.
  * 📝 **Code Suggestion Formatting**: Fixed edge-case issues.
  * 🤖 **Vertex API Support**: Added Service Account authentication.
  * ✨ **Gemini Models**: Updated to latest stable versions.

  ### Fixes & Tweaks

  * 🔧 **GitHub New-Line Character Parsing**: Fixed edge cases.
  * 📊 **Updated PR Review & Summary Formats**: Improved presentation and clarity.
  * 📈 **Added LLM Cost/Usage Tracking Metrics**: Better visibility into AI consumption.
  * 🐛 **Command Pattern Recognition**: Bug fixes for improved command detection.
</Update>

<Update label="May 2025">
  ### AI Summaries v2

  * **Advanced Detail Summary**: Comprehensive PR summaries with deeper context understanding
  * **Structured Information**: Automatically splits summaries into logical sections for better readability
  * **Security Visualization**: Tables for package vulnerabilities, CVEs, and detailed explanations

  ### AI Code Review Engine V2

  * **Precise Code Suggestions**: Deterministic commit positioning ensures feedback exactly where you need it
  * **Duplicate Prevention**: Smarter review intelligence avoids re-analyzing unchanged code sections
  * **Cost Optimization**: Auto-model swapping selects the best AI for each use-case, balancing performance and efficiency

  ### Command Improvements

  * **/matter review**: Reviews only new commits for faster and more efficient reviews
  * **/matter review-full**: Triggers a comprehensive re-review of the entire codebase when needed

  ### Agentic Chat

  * **Code-Aware Conversations**: Parses PR diffs, file context, and repo structure for relevant answers
  * **Technical Explanations**: Explains implementation decisions with precise technical details
  * **Impact Analysis**: Identifies potential side effects and integration points of code changes

  ***

  <Note>
    For detailed release notes and API changes, please refer to our [GitHub repository](https://github.com/MatterAIOrg/matter-ai).
  </Note>
</Update>

<Update label="April 22, 2025">
  ### Knowledge Retention

  * **Codebase Familiarity**: Develops understanding of project-specific patterns and conventions

  ***
</Update>

<Update label="April 15, 2025">
  ### Continuous Improvement

  * **Adaptive Reviews**: Refines review approach based on team interactions and preferences
  * **Team Alignment**: Becomes increasingly aligned with team-specific needs and standards
</Update>

<Update label="April 8, 2025">
  ### AI Memories

  * **Learning & Adaptation**: Observes developer interactions to capture team preferences and coding styles
  * **Pattern Recognition**: Identifies recurring patterns in code reviews and discussions for better context
  * **Contextual Understanding**: Builds deeper understanding of your codebase and project architecture
</Update>