Claude/next phase implementation y ah6 b #6
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
- Convert blockquote to Nextra callout in open-superintelligence.mdx - Add Edison link and improve content flow - Refine language for better clarity
- Restructured main content with cleaner formatting - Added comprehensive internal linking for better navigation - Improved visual hierarchy and readability - Enhanced acknowledgements section with better organization - Updated product suite section with consistent formatting
- Updated handbook/_meta.json to properly organize navigation - Fixed duplicate entries by removing files that belong in subfolders - Updated why folder title to 'Why does Jan exist?' - Cleaned up why/_meta.json with proper titles for Open Superintelligence and Open-Source sections
- Fix broken links in troubleshooting.mdx pointing to install pages - Remove privacy.mdx page and update _meta.json navigation - Update various documentation links for consistency - Ensure all internal links use proper absolute paths
✨ SEO Improvements: - Mac: 'Run AI models locally on your Mac - Jan' - Linux: 'Run AI models locally on Linux - Jan' - Windows: 'Run AI models locally on Windows - Jan' 🎯 Meta descriptions now include: - Target keywords (local AI, LLM, offline, ChatGPT-like) - Platform-specific details (Apple Silicon, Ubuntu/Debian, Windows 10/11) - Key benefits (GPU acceleration, privacy, no internet required) 📍 Sidebar navigation titles unchanged - only SEO meta data optimized
- Revert titles to clean sidebar navigation (Mac, Linux, Windows) - Improve meta descriptions to be concise but SEO-friendly - Keep key terms: local AI, offline, GPU acceleration, platform details
Update handbook content with Nextra callout and content improvements
Show supported files
…redirects docs: update missing redirect links
Co-authored-by: Copilot <[email protected]>
Co-authored-by: Copilot <[email protected]>
…edia-web enhancement: social media navbar and update menu footer
# Conflicts: # web-app/src/lib/utils.ts
Disable the option to select text on the Toaster to consist the swiping action on the toast in order to dismiss it
…tion-disable feat: Disable text selection on Toaster
…g-event chore: revert track event posthog
docs: update jan server url
* enable new prompt input while waiting for an answer * correct spelling of handleSendMessage function * remove test for disabling input while streaming content
feat: file attachment
chore: update happy dom deps version
docs: update changelog for Jan v0.7.2
This commit introduces a change to prevent **Markdown** rendering issues where a dollar sign followed by a number (like **`$1`**) is incorrectly interpreted as **LaTeX** by the rendering engine. --- The `normalizeLatex` function in `RenderMarkdown.tsx` now explicitly escapes these sequences (e.g., **`$1`** becomes **`\$1`**), ensuring they are displayed literally instead of being processed as mathematical expressions. This improves the fidelity of text that might contain currency or similar numerical notations.
* update model capabilites * refactor + remove projects
Co-authored-by: dtecho <[email protected]>
Co-authored-by: dtecho <[email protected]>
Co-authored-by: dtecho <[email protected]>
Co-authored-by: dtecho <[email protected]>
Co-authored-by: dtecho <[email protected]>
…ion-engine Implement OpenCog as Jan Autonomous Orchestration Engine
Major enhancements to the OpenCog autonomous orchestration engine: - Real task execution: Replaced simulated delays with strategy-based task processing including analysis, generation, search, validation, and execution task types with proper retry logic and metrics collection - Persistence layer: Added plan persistence with execution history tracking and learning insights extraction for improved future planning - Cognitive reasoning: Enhanced goal analysis with complexity scoring, feasibility assessment, capability identification, risk analysis, and intelligent task decomposition - Dynamic replanning: Automatic plan adjustment based on execution results, failure detection, and confidence thresholds - Multi-agent coordination: Parallel task execution with specialized agents (coordinator, researcher, analyst, creator, validator), intelligent task assignment based on capabilities, and inter-agent communication - Learning from history: Goal pattern insights, task success rates, execution time tracking, and failure pattern identification for continuous improvement New settings: enable_persistence, enable_multi_agent, enable_dynamic_replanning, and max_parallel_tasks for fine-grained control over orchestration behavior.
Implement OpenCog v2.0 with enhanced orchestration capabilities
This commit introduces a complete testing and CI/CD infrastructure: E2E Testing: - Playwright test suite with 8 comprehensive spec files - Tests for app, chat, models, settings, assistants, extensions, providers, keyboard shortcuts - Multi-browser support (Chromium, Firefox, WebKit) - Mobile viewport testing CI Workflows: - jan-e2e-tests.yml: Cross-browser E2E testing - jan-unit-tests.yml: TypeScript and Rust unit test suite - jan-release-all.yml: Unified release workflow for all platforms - jan-release-mobile.yml: Android and iOS release builds - jan-release-web.yml: Web app release and deployment - publish-npm-packages.yml: NPM package publishing - coverage-badge.yml: Automated coverage badge generation Unit Tests: - Added vitest configs and tests for extensions: - assistant-extension - conversational-extension - download-extension - rag-extension - vector-db-extension Enhanced Makefile: - New testing targets (test-e2e, test-rust, test-coverage, test-extensions) - Build targets for all platforms (build-android, build-ios, build-web-app) - Release targets (release-desktop, release-web, release-mobile) - CI/CD helper targets (ci-test, ci-build, ci-e2e) - Comprehensive help command Coverage: - Updated vitest.config.ts with coverage thresholds (50%) - JSON summary reporter for badge generation
Add comprehensive E2E CI, unit tests, and release builds
Add missing dependencies to useEffect and useCallback hooks to satisfy eslint react-hooks/exhaustive-deps rule. The threadId reset effect is intentionally kept with only threadId as dependency to prevent unnecessary re-runs when other stable functions change.
Fix React hooks dependency warnings in useThreadScrolling
This release adds three major features to the OpenCog orchestration engine: ## Atomspace Knowledge Graph (~700 lines) - Graph-based knowledge representation with nodes and links - Truth values (strength, confidence) for uncertain knowledge - Attention values (STI, LTI) for importance tracking - Pattern-matching query engine - Automatic indexing of plans, goals, and tasks - Similar goal finding based on shared concepts ## PLN (Probabilistic Logic Networks) (~600 lines) - Truth value formulas: deduction, induction, abduction, modus ponens - Forward chaining: derive new knowledge from existing atoms - Backward chaining: prove goals by finding evidence - Task success prediction based on similar past tasks - Learning from execution results ## Tool Integration (~500 lines) - 8 integrated tools: rag_retrieve, file_read, file_write, web_search, llm_inference, code_analysis, data_transform, summarize - Tool chains for multi-step operations - Automatic tool selection based on task description - Execution statistics and reliability tracking ## New MCP Tools - query_knowledge: Query the Atomspace - infer_knowledge: Perform PLN inference - execute_tool: Execute integrated tools - get_knowledge_stats: Get system statistics ## New Settings - Enable Atomspace, PLN, Tool Integration - PLN max iterations and min confidence ## Tests - 3 new test files with 60+ tests - All 1,404 tests passing
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Describe Your Changes
Fixes Issues
Self Checklist