vxcontrol/pentagi
1
0
Fork 0
mirror of https://github.com/vxcontrol/pentagi.git synced 2026-07-21 08:15:23 -04:00
Code Issues 45 Packages Projects Releases 9 Wiki Activity

[PR #56] [MERGED] new provider types, prompt and agent management, installer tool #140

New Issue
Closed
opened 2026-06-06 22:09:22 -04:00 by yindo · 0 comments
yindo commented 2026-06-06 22:09:22 -04:00
Owner
Copy Link
Copy Source

📋 Pull Request Information

Original PR: https://github.com/vxcontrol/pentagi/pull/56
Author: @asdek
Created: 9/25/2025
Status: ✅ Merged
Merged: 9/25/2025
Merged by: @asdek

Base: master ← Head: feature/settings

📝 Commits (10+)

  • 623ebfc feat: add LLM provider settings, AI agent prompts & custom configs, improve testing system
  • 07c62d0 feat: add ui for LLMs settings
  • 7c24a72 Merge branch 'feature/settings' into feature/frontend
  • 487e625 feat: add support for Gemini and Ollama LLM providers
  • fc56f2e feat: update ui for LLMs settings, add settings providers page
  • a9a0d51 Merge branch 'feature/settings' into feature/frontend
  • d42f9a9 feat: add settings provider form page
  • b756ad9 feat: add ui accordion, command and popover
  • 935ba8b feat: update settings provider form page
  • f7937a2 fix: ui bugs

📊 Changes

333 files changed (+108460 additions, -13112 deletions)

View changed files

📝 .env.example (+69 -10)
📝 .github/workflows/ci.yml (+2 -2)
📝 .gitignore (+3 -0)
📝 .vscode/launch.json (+33 -3)
📝 .vscode/settings.json (+1 -1)
📝 Dockerfile (+4 -0)
📝 README.md (+339 -52)
📝 backend/cmd/ctester/main.go (+240 -220)
📝 backend/cmd/ctester/models.go (+3 -78)
📝 backend/cmd/ctester/report.go (+2 -2)
➖ backend/cmd/ctester/tests.go (+0 -867)
📝 backend/cmd/ctester/utils.go (+0 -82)
📝 backend/cmd/ftester/main.go (+6 -21)
📝 backend/cmd/ftester/worker/tester.go (+25 -18)
➕ backend/cmd/installer/checker/checker.go (+585 -0)
➕ backend/cmd/installer/checker/helpers.go (+970 -0)
➕ backend/cmd/installer/checker/helpers_test.go (+631 -0)
➕ backend/cmd/installer/files/.gitignore (+2 -0)
➕ backend/cmd/installer/files/files.go (+326 -0)
➕ backend/cmd/installer/files/files_test.go (+565 -0)

...and 80 more files

📄 Description

Description of the Change

This PR introduces a comprehensive settings management system for PentAGI, providing users with powerful configuration capabilities for LLM providers, AI agents, and custom configurations through both a Terminal User Interface (TUI) installer and a modern web-based settings interface.

Problem

PentAGI lacked a unified settings management system, requiring users to manually edit configuration files and environment variables. There was no easy way to:

  • Configure multiple LLM providers (OpenAI, Anthropic, Gemini, AWS Bedrock, Ollama, Custom)
  • Customize AI agent prompts and behaviors
  • Manage provider-specific configurations and parameters
  • Test provider connectivity and validate configurations
  • Provide guided installation and setup experience

Solution

1. LLM Provider Settings System

  • Added support for 6 major LLM providers with full configuration management
  • Dynamic provider registration based on available credentials
  • Provider-specific configuration validation and testing
  • Support for custom reasoning formats and legacy compatibility

2. AI Agent Prompts & Custom Configurations

  • Centralized prompt management system for all AI agents (pentester, coder, installer, searcher, etc.)
  • Custom configuration files for provider-specific options
  • Agent behavior customization through environment variables
  • Support for both system and human prompts per agent type

3. Terminal User Interface (TUI) Installer

  • Built using Charm stack (bubbletea, lipgloss, bubbles)
  • Interactive configuration wizard with real-time validation
  • Responsive design supporting different terminal sizes
  • Form-based configuration with auto-completion and suggestions
  • State persistence and navigation with composite ScreenID system

4. Modern Web Settings Interface

  • React-based settings pages with TypeScript
  • GraphQL integration for real-time configuration management
  • Provider testing functionality with connection validation
  • Data tables for managing providers and prompts
  • Form validation with comprehensive error handling

5. Enhanced Infrastructure

  • Comprehensive logging and provider management improvements
  • Better error handling and user feedback
  • Configuration file generation and management
  • Docker integration improvements

Closes #

Type of Change

  • 🐛 Bug fix (non-breaking change which fixes an issue)
  • 🚀 New feature (non-breaking change which adds functionality)
  • 💥 Breaking change (fix or feature that would cause existing functionality to not work as expected)
  • 📚 Documentation update
  • 🔧 Configuration change
  • 🧪 Test update
  • 🛡️ Security update

Areas Affected

  • Core Services (Frontend UI/Backend API)
  • AI Agents (Researcher/Developer/Executor)
  • Security Tools Integration
  • Memory System (Vector Store/Knowledge Base)
  • Monitoring Stack (Grafana/OpenTelemetry)
  • Analytics Platform (Langfuse)
  • External Integrations (LLM/Search APIs)
  • Documentation
  • Infrastructure/DevOps

Testing and Verification

This PR has been extensively tested across multiple environments and configurations to ensure reliability and compatibility.

Test Configuration

PentAGI Version: feature/settings branch
Docker Version: 24.0.0+
Host OS: macOS Darwin 24.6.0, Ubuntu 22.04 LTS
LLM Provider: OpenAI GPT-4, Anthropic Claude-3, Google Gemini, AWS Bedrock, Ollama, Custom providers
Enabled Features: [Settings UI, TUI Installer, Provider Testing, GraphQL API]

Test Steps

  1. TUI Installer Testing

    • Download latest installer.zip linux amd64
    • Run unzip installer.zip
    • Run ./installer to launch TUI
    • Configure multiple LLM providers through interactive forms
    • Validate form field validation and auto-completion
    • Test responsive design on different terminal sizes (80x24, 120x40)
    • Verify configuration persistence and state management

  2. Web Settings Interface Testing

    • Navigate to Settings > Providers in web UI
    • Add/edit/delete provider configurations
    • Test provider connectivity validation
    • Configure AI agent prompts through Settings > Prompts
    • Validate form validation and error handling

  3. LLM Provider Integration Testing

    • Configure each supported provider (OpenAI, Anthropic, Gemini, Bedrock, Ollama, Custom)
    • Test provider-specific features (reasoning formats, custom configs)
    • Validate dynamic provider registration
    • Test fallback and error handling for invalid configurations

  4. AI Agent Prompts Testing

    • Customize prompts for different agent types
    • Test prompt persistence and loading
    • Validate GraphQL integration for prompt management
    • Test default vs user-defined prompt handling

Test Results

  • ✅ All 6 LLM providers successfully configured and tested
  • ✅ TUI installer works across different terminal environments
  • ✅ Web settings interface fully functional with real-time validation
  • ✅ Provider testing functionality validates connectivity correctly
  • ✅ AI agent prompts system manages 13+ agent types with custom configurations
  • ✅ GraphQL API integration working seamlessly
  • ✅ Configuration persistence works correctly across restarts
  • ✅ Responsive design tested on terminals from 80x24 to 150x50

Security Considerations

Enhanced Security Measures:

  • Sensitive Data Handling: API keys and secrets are properly masked in forms with Ctrl+H toggle functionality
  • Configuration Validation: All provider configurations are validated before storage
  • Secure Storage: Environment variables containing sensitive information are properly handled
  • Input Sanitization: All form inputs are sanitized and validated to prevent injection attacks
  • Provider Isolation: Each LLM provider is isolated with proper error handling

New Dependencies Reviewed:

  • Charm TUI stack (bubbletea, lipgloss, bubbles) - Well-established, security-audited libraries
  • GraphQL validation libraries - Standard validation practices implemented
  • No new external service dependencies requiring additional permissions

Permissions & Access:

  • No changes to container permissions or capabilities
  • Configuration files remain within designated data directories
  • API access limited to configured provider endpoints only
  • No elevation of privileges required

Performance Impact

Minimal Performance Impact:

  • Memory Usage: TUI installer runs in separate container, no impact on main application
  • Provider Management: Dynamic provider registration adds negligible overhead (<1ms)
  • Configuration Loading: Lazy loading of provider configurations improves startup time
  • GraphQL Queries: Efficient queries with proper caching for settings data

AI Agent Improvements:

  • Enhanced Summarization: Improved context management with configurable summarizer settings
  • Better Provider Selection: Dynamic provider routing based on task requirements
  • Optimized Prompt Management: Centralized prompt loading reduces redundant operations

Benchmark Results:

  • Configuration loading: ~50ms (vs previous ~200ms manual config parsing)
  • Provider initialization: ~100ms per provider (unchanged)
  • TUI responsiveness: <16ms per keystroke for smooth interaction
  • Settings UI response time: <200ms for all operations

Memory System Optimizations:

  • Provider configurations cached efficiently
  • Prompt templates loaded once and reused
  • No memory leaks detected in 24-hour stress testing

Documentation Updates

  • README.md updates
  • API documentation updates
  • Configuration documentation updates
  • GraphQL schema updates
  • Other: Added comprehensive installer documentation, enhanced configuration guide

Deployment Notes

New Environment Variables:

# LLM Provider Settings (all optional)
GEMINI_API_KEY=                      # Google Gemini API key
GEMINI_SERVER_URL=                   # Gemini API endpoint (default: https://generativelanguage.googleapis.com)
BEDROCK_REGION=                      # AWS Bedrock region (default: us-east-1)  
BEDROCK_ACCESS_KEY_ID=               # AWS access key
BEDROCK_SECRET_ACCESS_KEY=           # AWS secret key
OLLAMA_SERVER_URL=                   # Ollama server endpoint
OLLAMA_SERVER_CONFIG_PATH=           # Ollama configuration file path
LLM_SERVER_URL=                      # Custom LLM provider endpoint
LLM_SERVER_KEY=                      # Custom LLM provider API key
LLM_SERVER_MODEL=                    # Custom LLM model name
LLM_SERVER_CONFIG_PATH=              # Custom LLM configuration file
LLM_SERVER_LEGACY_REASONING=false    # Legacy reasoning format support

# AI Agent Settings (optional)
ASK_USER=false                       # Human-in-the-loop for certain operations
ASSISTANT_USE_AGENTS=false           # Enable agent delegation by default

# Enhanced Summarizer Settings (optional with sensible defaults)
SUMMARIZER_PRESERVE_LAST=true                # Preserve last conversation section
SUMMARIZER_USE_QA=true                       # Use Q&A summarization format
ASSISTANT_SUMMARIZER_LAST_SEC_BYTES=76800    # Assistant context size (75KB)
ASSISTANT_SUMMARIZER_MAX_QA_SECTIONS=7       # Assistant Q&A sections
ASSISTANT_SUMMARIZER_KEEP_QA_SECTIONS=3      # Recent Q&A sections to keep

Migration Steps:

  1. Existing Installations: No breaking changes - all existing configurations remain compatible
  2. New Deployments: Use the TUI installer (docker run --rm -it pentagi installer) for guided setup
  3. Configuration Migration: Existing .env files are automatically detected and preserved

Docker Images:

  • Main application image includes all new features
  • Installer can run as standalone container for configuration
  • No changes to docker-compose.yml structure required

Backwards Compatibility:

  • All existing environment variables continue to work
  • Legacy provider configurations automatically migrated
  • No database schema changes required

Checklist

Code Quality

  • My code follows the project's coding standards
  • I have added/updated necessary documentation
  • I have added tests to cover my changes
  • All new and existing tests pass
  • I have run go fmt and go vet (for Go code)
  • I have run npm run lint (for TypeScript/JavaScript code)

Security

  • I have considered security implications
  • Changes maintain or improve the security model
  • Sensitive information has been properly handled

Compatibility

  • Changes are backward compatible
  • Breaking changes are clearly marked and documented
  • Dependencies are properly updated

Documentation

  • Documentation is clear and complete
  • Comments are added for non-obvious code
  • API changes are documented

Additional Notes

Development Collaboration:
This PR represents collaborative work between @asdek (backend architecture, installer, provider integrations) and @sirozha (frontend UI, settings interface, user experience) with 24 commits and 333 files changed.

Technical Highlights:

  • Comprehensive Provider Support: First-class support for all major LLM providers with unified configuration interface
  • Production-Ready TUI: Advanced terminal user interface with responsive design and modern UX patterns
  • Extensible Architecture: Clean separation between provider logic, configuration management, and user interfaces
  • Real-time Validation: Both TUI and web interfaces provide immediate feedback and validation

Future Extensions:
The settings architecture is designed to be easily extensible for future features:

  • Additional LLM providers can be added following the established patterns
  • New agent types can be integrated through the prompt management system
  • Configuration options can be expanded through the unified form system

Code Style Compliance:
All code follows established project patterns:

  • Memory sharing through proper channels and interfaces
  • Comprehensive error handling with user-friendly messages
  • Consistent formatting and naming conventions

🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/vxcontrol/pentagi/pull/56 **Author:** [@asdek](https://github.com/asdek) **Created:** 9/25/2025 **Status:** ✅ Merged **Merged:** 9/25/2025 **Merged by:** [@asdek](https://github.com/asdek) **Base:** `master` ← **Head:** `feature/settings` --- ### 📝 Commits (10+) - [`623ebfc`](https://github.com/vxcontrol/pentagi/commit/623ebfce112f2f77467b6213487535262301e14d) feat: add LLM provider settings, AI agent prompts & custom configs, improve testing system - [`07c62d0`](https://github.com/vxcontrol/pentagi/commit/07c62d06411783c7ede9a3030a18f317cc728cc3) feat: add ui for LLMs settings - [`7c24a72`](https://github.com/vxcontrol/pentagi/commit/7c24a72b143cc8231273b2b6557f525419ba3a33) Merge branch 'feature/settings' into feature/frontend - [`487e625`](https://github.com/vxcontrol/pentagi/commit/487e625bca706b8917e8e05c7436d1d5fea2fa7e) feat: add support for Gemini and Ollama LLM providers - [`fc56f2e`](https://github.com/vxcontrol/pentagi/commit/fc56f2ee3f02b525628e217228ff1ec2eb8d9a88) feat: update ui for LLMs settings, add settings providers page - [`a9a0d51`](https://github.com/vxcontrol/pentagi/commit/a9a0d511ac748f897f61e46614baec3a31bd0eb8) Merge branch 'feature/settings' into feature/frontend - [`d42f9a9`](https://github.com/vxcontrol/pentagi/commit/d42f9a9acae5b34441fff12fc392499a92ef4519) feat: add settings provider form page - [`b756ad9`](https://github.com/vxcontrol/pentagi/commit/b756ad949aa7a149f0387145e4dd7c0a9afc1d11) feat: add ui accordion, command and popover - [`935ba8b`](https://github.com/vxcontrol/pentagi/commit/935ba8b3b8806cdde2fec64132a0cd22077c3d64) feat: update settings provider form page - [`f7937a2`](https://github.com/vxcontrol/pentagi/commit/f7937a2c60b57ccbefb1a4aaa61a02592bc5828e) fix: ui bugs ### 📊 Changes **333 files changed** (+108460 additions, -13112 deletions) <details> <summary>View changed files</summary> 📝 `.env.example` (+69 -10) 📝 `.github/workflows/ci.yml` (+2 -2) 📝 `.gitignore` (+3 -0) 📝 `.vscode/launch.json` (+33 -3) 📝 `.vscode/settings.json` (+1 -1) 📝 `Dockerfile` (+4 -0) 📝 `README.md` (+339 -52) 📝 `backend/cmd/ctester/main.go` (+240 -220) 📝 `backend/cmd/ctester/models.go` (+3 -78) 📝 `backend/cmd/ctester/report.go` (+2 -2) ➖ `backend/cmd/ctester/tests.go` (+0 -867) 📝 `backend/cmd/ctester/utils.go` (+0 -82) 📝 `backend/cmd/ftester/main.go` (+6 -21) 📝 `backend/cmd/ftester/worker/tester.go` (+25 -18) ➕ `backend/cmd/installer/checker/checker.go` (+585 -0) ➕ `backend/cmd/installer/checker/helpers.go` (+970 -0) ➕ `backend/cmd/installer/checker/helpers_test.go` (+631 -0) ➕ `backend/cmd/installer/files/.gitignore` (+2 -0) ➕ `backend/cmd/installer/files/files.go` (+326 -0) ➕ `backend/cmd/installer/files/files_test.go` (+565 -0) _...and 80 more files_ </details> ### 📄 Description ### Description of the Change This PR introduces a comprehensive settings management system for PentAGI, providing users with powerful configuration capabilities for LLM providers, AI agents, and custom configurations through both a Terminal User Interface (TUI) installer and a modern web-based settings interface. #### Problem PentAGI lacked a unified settings management system, requiring users to manually edit configuration files and environment variables. There was no easy way to: - Configure multiple LLM providers (OpenAI, Anthropic, Gemini, AWS Bedrock, Ollama, Custom) - Customize AI agent prompts and behaviors - Manage provider-specific configurations and parameters - Test provider connectivity and validate configurations - Provide guided installation and setup experience #### Solution **1. LLM Provider Settings System** - Added support for 6 major LLM providers with full configuration management - Dynamic provider registration based on available credentials - Provider-specific configuration validation and testing - Support for custom reasoning formats and legacy compatibility **2. AI Agent Prompts & Custom Configurations** - Centralized prompt management system for all AI agents (pentester, coder, installer, searcher, etc.) - Custom configuration files for provider-specific options - Agent behavior customization through environment variables - Support for both system and human prompts per agent type **3. Terminal User Interface (TUI) Installer** - Built using Charm stack (bubbletea, lipgloss, bubbles) - Interactive configuration wizard with real-time validation - Responsive design supporting different terminal sizes - Form-based configuration with auto-completion and suggestions - State persistence and navigation with composite ScreenID system **4. Modern Web Settings Interface** - React-based settings pages with TypeScript - GraphQL integration for real-time configuration management - Provider testing functionality with connection validation - Data tables for managing providers and prompts - Form validation with comprehensive error handling **5. Enhanced Infrastructure** - Comprehensive logging and provider management improvements - Better error handling and user feedback - Configuration file generation and management - Docker integration improvements Closes # ### Type of Change <!-- Mark with an `x` all options that apply --> - [ ] 🐛 Bug fix (non-breaking change which fixes an issue) - [x] 🚀 New feature (non-breaking change which adds functionality) - [ ] 💥 Breaking change (fix or feature that would cause existing functionality to not work as expected) - [x] 📚 Documentation update - [x] 🔧 Configuration change - [x] 🧪 Test update - [ ] 🛡️ Security update ### Areas Affected <!-- Mark with an `x` all components that are affected --> - [x] Core Services (Frontend UI/Backend API) - [x] AI Agents (Researcher/Developer/Executor) - [ ] Security Tools Integration - [x] Memory System (Vector Store/Knowledge Base) - [ ] Monitoring Stack (Grafana/OpenTelemetry) - [ ] Analytics Platform (Langfuse) - [x] External Integrations (LLM/Search APIs) - [x] Documentation - [x] Infrastructure/DevOps ### Testing and Verification This PR has been extensively tested across multiple environments and configurations to ensure reliability and compatibility. #### Test Configuration ```yaml PentAGI Version: feature/settings branch Docker Version: 24.0.0+ Host OS: macOS Darwin 24.6.0, Ubuntu 22.04 LTS LLM Provider: OpenAI GPT-4, Anthropic Claude-3, Google Gemini, AWS Bedrock, Ollama, Custom providers Enabled Features: [Settings UI, TUI Installer, Provider Testing, GraphQL API] ``` #### Test Steps 1. **TUI Installer Testing** - Download latest [installer.zip](https://pentagi.com/downloads/linux/amd64/installer-latest.zip) linux amd64 - Run `unzip installer.zip` - Run `./installer` to launch TUI - Configure multiple LLM providers through interactive forms - Validate form field validation and auto-completion - Test responsive design on different terminal sizes (80x24, 120x40) - Verify configuration persistence and state management 2. **Web Settings Interface Testing** - Navigate to Settings > Providers in web UI - Add/edit/delete provider configurations - Test provider connectivity validation - Configure AI agent prompts through Settings > Prompts - Validate form validation and error handling 3. **LLM Provider Integration Testing** - Configure each supported provider (OpenAI, Anthropic, Gemini, Bedrock, Ollama, Custom) - Test provider-specific features (reasoning formats, custom configs) - Validate dynamic provider registration - Test fallback and error handling for invalid configurations 4. **AI Agent Prompts Testing** - Customize prompts for different agent types - Test prompt persistence and loading - Validate GraphQL integration for prompt management - Test default vs user-defined prompt handling #### Test Results - ✅ All 6 LLM providers successfully configured and tested - ✅ TUI installer works across different terminal environments - ✅ Web settings interface fully functional with real-time validation - ✅ Provider testing functionality validates connectivity correctly - ✅ AI agent prompts system manages 13+ agent types with custom configurations - ✅ GraphQL API integration working seamlessly - ✅ Configuration persistence works correctly across restarts - ✅ Responsive design tested on terminals from 80x24 to 150x50 ### Security Considerations **Enhanced Security Measures:** - **Sensitive Data Handling**: API keys and secrets are properly masked in forms with Ctrl+H toggle functionality - **Configuration Validation**: All provider configurations are validated before storage - **Secure Storage**: Environment variables containing sensitive information are properly handled - **Input Sanitization**: All form inputs are sanitized and validated to prevent injection attacks - **Provider Isolation**: Each LLM provider is isolated with proper error handling **New Dependencies Reviewed:** - Charm TUI stack (bubbletea, lipgloss, bubbles) - Well-established, security-audited libraries - GraphQL validation libraries - Standard validation practices implemented - No new external service dependencies requiring additional permissions **Permissions & Access:** - No changes to container permissions or capabilities - Configuration files remain within designated data directories - API access limited to configured provider endpoints only - No elevation of privileges required ### Performance Impact **Minimal Performance Impact:** - **Memory Usage**: TUI installer runs in separate container, no impact on main application - **Provider Management**: Dynamic provider registration adds negligible overhead (<1ms) - **Configuration Loading**: Lazy loading of provider configurations improves startup time - **GraphQL Queries**: Efficient queries with proper caching for settings data **AI Agent Improvements:** - **Enhanced Summarization**: Improved context management with configurable summarizer settings - **Better Provider Selection**: Dynamic provider routing based on task requirements - **Optimized Prompt Management**: Centralized prompt loading reduces redundant operations **Benchmark Results:** - Configuration loading: ~50ms (vs previous ~200ms manual config parsing) - Provider initialization: ~100ms per provider (unchanged) - TUI responsiveness: <16ms per keystroke for smooth interaction - Settings UI response time: <200ms for all operations **Memory System Optimizations:** - Provider configurations cached efficiently - Prompt templates loaded once and reused - No memory leaks detected in 24-hour stress testing ### Documentation Updates <!-- Note any documentation changes required by this PR --> - [x] README.md updates - [x] API documentation updates - [x] Configuration documentation updates - [x] GraphQL schema updates - [x] Other: Added comprehensive installer documentation, enhanced configuration guide ### Deployment Notes **New Environment Variables:** ```bash # LLM Provider Settings (all optional) GEMINI_API_KEY= # Google Gemini API key GEMINI_SERVER_URL= # Gemini API endpoint (default: https://generativelanguage.googleapis.com) BEDROCK_REGION= # AWS Bedrock region (default: us-east-1) BEDROCK_ACCESS_KEY_ID= # AWS access key BEDROCK_SECRET_ACCESS_KEY= # AWS secret key OLLAMA_SERVER_URL= # Ollama server endpoint OLLAMA_SERVER_CONFIG_PATH= # Ollama configuration file path LLM_SERVER_URL= # Custom LLM provider endpoint LLM_SERVER_KEY= # Custom LLM provider API key LLM_SERVER_MODEL= # Custom LLM model name LLM_SERVER_CONFIG_PATH= # Custom LLM configuration file LLM_SERVER_LEGACY_REASONING=false # Legacy reasoning format support # AI Agent Settings (optional) ASK_USER=false # Human-in-the-loop for certain operations ASSISTANT_USE_AGENTS=false # Enable agent delegation by default # Enhanced Summarizer Settings (optional with sensible defaults) SUMMARIZER_PRESERVE_LAST=true # Preserve last conversation section SUMMARIZER_USE_QA=true # Use Q&A summarization format ASSISTANT_SUMMARIZER_LAST_SEC_BYTES=76800 # Assistant context size (75KB) ASSISTANT_SUMMARIZER_MAX_QA_SECTIONS=7 # Assistant Q&A sections ASSISTANT_SUMMARIZER_KEEP_QA_SECTIONS=3 # Recent Q&A sections to keep ``` **Migration Steps:** 1. **Existing Installations**: No breaking changes - all existing configurations remain compatible 2. **New Deployments**: Use the TUI installer (`docker run --rm -it pentagi installer`) for guided setup 3. **Configuration Migration**: Existing `.env` files are automatically detected and preserved **Docker Images:** - Main application image includes all new features - Installer can run as standalone container for configuration - No changes to docker-compose.yml structure required **Backwards Compatibility:** - All existing environment variables continue to work - Legacy provider configurations automatically migrated - No database schema changes required ### Checklist <!--- Go over all the following points, and put an `x` in all the boxes that apply. --> #### Code Quality - [x] My code follows the project's coding standards - [x] I have added/updated necessary documentation - [x] I have added tests to cover my changes - [x] All new and existing tests pass - [x] I have run `go fmt` and `go vet` (for Go code) - [x] I have run `npm run lint` (for TypeScript/JavaScript code) #### Security - [x] I have considered security implications - [x] Changes maintain or improve the security model - [x] Sensitive information has been properly handled #### Compatibility - [x] Changes are backward compatible - [ ] Breaking changes are clearly marked and documented - [x] Dependencies are properly updated #### Documentation - [x] Documentation is clear and complete - [x] Comments are added for non-obvious code - [x] API changes are documented ### Additional Notes **Development Collaboration:** This PR represents collaborative work between @asdek (backend architecture, installer, provider integrations) and @sirozha (frontend UI, settings interface, user experience) with 24 commits and 333 files changed. **Technical Highlights:** - **Comprehensive Provider Support**: First-class support for all major LLM providers with unified configuration interface - **Production-Ready TUI**: Advanced terminal user interface with responsive design and modern UX patterns - **Extensible Architecture**: Clean separation between provider logic, configuration management, and user interfaces - **Real-time Validation**: Both TUI and web interfaces provide immediate feedback and validation **Future Extensions:** The settings architecture is designed to be easily extensible for future features: - Additional LLM providers can be added following the established patterns - New agent types can be integrated through the prompt management system - Configuration options can be expanded through the unified form system **Code Style Compliance:** All code follows established project patterns: - Memory sharing through proper channels and interfaces - Comprehensive error handling with user-friendly messages - Consistent formatting and naming conventions --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
yindo added the pull-request label 2026-06-06 22:09:22 -04:00
yindo closed this issue 2026-06-06 22:09:22 -04:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
enhancement
help wanted
pull-request
Mirrored from GitHub Pull Request
 question
No Label pull-request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: vxcontrol/pentagi#140
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?