Add TesseractAgent for PDF/Image OCR text extraction with command-restricted bash executor #193
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
- Extend BashExecutor to accept custom BashPermissions - Add helper methods for common permission patterns (only_allow, read_only, minimal) - Implement builder pattern for ToolExecutor with custom bash configuration - Export new public APIs for creating restricted executors - Add comprehensive documentation and examples - Maintain backward compatibility with existing API - Enable per-agent bash permission policies This allows creating specialized agents (e.g., TesseractAgent) that can only execute specific whitelisted commands while maintaining full security.
Implement specialized AI agent for extracting text from images using Tesseract OCR. The agent features restricted bash access (tesseract command only), LLM-powered text cleaning and formatting, and comprehensive pre-condition verification. Key features: - Restricted bash executor allows only tesseract command - Supports multiple image formats (PNG, JPG, PDF, TIFF) - LLM-based post-processing for OCR error correction - Pre-condition checks for tesseract installation - Configurable working directory for file operations - Factory methods for easy instantiation Also includes minor formatting improvements in manager-tools SQLite module. Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Configure TesseractAgent to work with individual image files instead of a base directory path. Add API endpoint, TypeScript type generation, and GUI form support. Changes: - Update TesseractAgent to accept image_path instead of base_path - Add image validation and automatic directory extraction - Update system prompt to reference specific image file - Add TesseractAgent to API helpers and execution handlers - Register /agents/tesseract/execute endpoint in main.rs - Generate TypeScript types including TesseractAgentConfig - Add Image Path input field to Home page form - Mark task as complete Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
📊 Code Complexity Analysis
💡 Suggestion: This is a large PR with 3037 added lines. Consider:
Automated analysis by GitHub Actions |
🤖 Automated Code Review SummaryThis automated review was generated to help ensure code quality and security standards. Rust Code Analysis
TypeScript/JavaScript Code AnalysisSecurity Analysis
Recommendations
This review was automatically generated. Please address any issues before merging. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary
Key Features
Command-Restricted Bash Executor
only_allow(),read_only(),minimal()TesseractAgent
API & GUI Integration
/agents/tesseract/executeendpoint in nocodo-apiTest plan
/agents/tesseract/executewith valid image paths🤖 Generated with Claude Code