feat(tools): added textract, added v2 for mistral, updated tag dropdown

[waleedlatif1]

Summary

• added textract

Type of Change

• Bug fix

Testing

Tested manually

Checklist

• Code follows project style guidelines
• Self-reviewed my changes
• Tests added/updated and passing
• No new warnings introduced
• I confirm that I have read and agree to the terms outlined in the Contributor License Agreement (CLA)

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

1 Skipped Deployment

Project	Deployment	Review	Updated (UTC)
docs	Skipped		Jan 21, 2026 2:32am

[greptile-apps]

Greptile Summary

This PR adds AWS Textract integration for document OCR and analysis, along with several improvements to existing document processing blocks.

Key Changes:

• New AWS Textract tool with sync (single-page) and async (multi-page) processing modes
• Proper AWS SigV4 authentication implementation for direct Textract API calls
• SSRF protection and input validation for external URLs and S3 URIs
• New validateAwsRegion and validateS3BucketName security validators with comprehensive test coverage
• Added S3 URI output (s3://bucket/key) to S3 put/copy operations for Textract async integration
• Refactored File, Mistral Parser, Pulse, and Reducto blocks to use consistent basic/advanced mode UI pattern with canonicalParamId
• Created V2 versions of File and Mistral Parser tools/blocks while preserving legacy versions (hidden from toolbar)
• Fixed editor advanced options display logic to respect user toggle when editing
• Added getS3InfoForKey helper for direct S3 access scenarios

Architecture Notes:

• The Textract integration follows the established tool/block pattern with proper separation of concerns
• Security validators are well-tested and follow AWS naming conventions
• The basic/advanced mode refactoring improves UX consistency across document processing blocks

Confidence Score: 4/5

• This PR is safe to merge with good security practices and follows established patterns
• Score reflects well-structured code with proper input validation, SSRF protection, and comprehensive test coverage for new validators. Minor documentation inconsistencies noted but no blocking issues.
• No files require special attention - the Textract API route has proper security measures in place

Important Files Changed

Filename	Overview
apps/sim/app/api/tools/textract/parse/route.ts	New Textract API route with AWS SigV4 authentication, sync/async processing modes, SSRF protection, and proper input validation. Well-structured with good security practices.
apps/sim/tools/textract/parser.ts	Textract tool definition with proper params, request handling, and response transformation. Uses 'user-only' visibility for credentials as per project standards.
apps/sim/blocks/blocks/textract.ts	Textract block definition with sync/async mode selector, file upload support, AWS credentials, and feature type toggles. Uses 'user-only' pattern for credentials.
apps/sim/lib/core/security/input-validation.ts	Added validateAwsRegion and validateS3BucketName validators for AWS resource validation. Comprehensive pattern matching and security checks.
apps/sim/lib/core/security/input-validation.test.ts	Comprehensive test coverage for new AWS region and S3 bucket name validators. Covers valid cases, edge cases, and security scenarios.
apps/sim/blocks/blocks/file.ts	Added FileV2Block with simplified basic/advanced mode UI pattern. Legacy FileBlock marked as hidden. Uses createVersionedToolSelector for versioning.
apps/sim/blocks/blocks/mistral_parse.ts	Added MistralParseV2Block with simplified UI pattern (basic/advanced modes). Legacy block hidden. Fixed TypeScript error typing from any to unknown.
apps/sim/app/workspace/[workspaceId]/w/[workflowId]/components/panel/components/editor/editor.tsx	Fixed advanced options display logic - respects user toggle when editing, shows based on values when read-only.

Sequence Diagram

sequenceDiagram
    participant User
    participant TextractBlock
    participant TextractAPI as /api/tools/textract/parse
    participant StorageService
    participant AWSTextract as AWS Textract

    User->>TextractBlock: Configure block (credentials, mode, document)
    TextractBlock->>TextractAPI: POST request with params
    
    alt Sync Mode (single-page)
        TextractAPI->>TextractAPI: Validate inputs (region, URL)
        alt Internal File Path
            TextractAPI->>StorageService: Generate presigned URL
            StorageService-->>TextractAPI: Presigned download URL
        end
        TextractAPI->>TextractAPI: Fetch document bytes
        TextractAPI->>AWSTextract: AnalyzeDocument / DetectDocumentText
        AWSTextract-->>TextractAPI: Blocks response
    else Async Mode (multi-page)
        TextractAPI->>TextractAPI: Parse & validate S3 URI
        TextractAPI->>AWSTextract: StartDocumentAnalysis / StartDocumentTextDetection
        AWSTextract-->>TextractAPI: JobId
        loop Poll until complete
            TextractAPI->>AWSTextract: GetDocumentAnalysis / GetDocumentTextDetection
            AWSTextract-->>TextractAPI: JobStatus + Blocks
        end
    end
    
    TextractAPI-->>TextractBlock: Parsed blocks + metadata
    TextractBlock-->>User: Display results

Loading

[greptile-apps]

_{15 files reviewed, 1 comment}

_{Edit Code Review Agent Settings | Greptile}

[waleedlatif1]

@greptile

[greptile-apps]

_{15 files reviewed, 1 comment}

_{Edit Code Review Agent Settings | Greptile}

[waleedlatif1]

@greptile

[waleedlatif1]

@greptile

[icecrasher321]

@cursor review

[icecrasher321]

@cursor review

[icecrasher321]

@cursor review

[cursor]

✅ Bugbot reviewed your changes and found no new issues!

Comment @cursor review or bugbot run to trigger another review on this PR