-
Couldn't load subscription status.
- Fork 134
Feature/super planner #62
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
base: main
Are you sure you want to change the base?
Conversation
- Complete documentation website with enhanced content expansion - Interactive examples with copy-paste ready commands - Progressive difficulty levels (Beginner → Intermediate → Advanced) - Real-world workflows covering all major scenarios: * Feature development with agent orchestration * Systematic debugging and incident response * Knowledge-driven development patterns * Performance optimization strategies * Parallel development approaches - Platform-specific setup guides with troubleshooting - Detailed agent catalog with practical use cases - Fully responsive design with smooth animations - Working interactive features (tabs, collapsible sections, copy buttons) 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
…h content Build comprehensive website generation tool that creates high-quality, paradigm-aware websites from repository analysis. Addresses user requirement: "Ideally it should just work without you having to look at it. So, let's fix the tool to generate the site, not fix the generated site. Ideally the tool should generate a similar site to our rich one." Major achievements: • Enhanced agents.html from 1.8KB to 423KB (235x content increase) • Generated instructor-level rich content with detailed agent descriptions, capabilities, use cases, and examples for all 23 Amplifier agents • Fixed CSS filename linking (amplifier-styles.css vs styles.css) • Complete template coverage for all page sections Components implemented: • Repository analyzer with YAML frontmatter parsing and paradigm detection • Content generator creating revolution sections, progressive setup tiers, rich agent showcases • Jinja2 template engine with custom filters and comprehensive section templates • CSS generator producing 18KB responsive stylesheets from design system config • Configuration system with YAML templates for different project types Generated website features: • index.html (120KB) - Complete homepage with revolution section • agents.html (423KB) - Rich agent showcase with detailed descriptions • setup.html (14KB) - Progressive setup guide • amplifier-styles.css (18KB) - Complete responsive stylesheet • script.js (3KB) - Interactive JavaScript functionality The tool successfully generates professional websites matching and exceeding the quality of manually created instructor site, with automatic paradigm shift detection and content adaptation. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
…ect coordination Implement the core foundation for Super-Planner, a multi-agent project coordination system within amplifier. This Phase 1 implementation provides hierarchical task management, dependency tracking, and JSON persistence following amplifier's ruthless simplicity philosophy. Key Features: - Task and Project data models with hierarchical structure - State management (PENDING → IN_PROGRESS → COMPLETED → BLOCKED) - Dependency validation and prerequisite checking - JSON persistence using amplifier's defensive file I/O utilities - Complete test coverage with 16 comprehensive tests Architecture (139 total lines): - models.py (60 lines): Task/Project dataclasses with navigation methods - storage.py (70 lines): Git-friendly JSON persistence - __init__.py (9 lines): Clean public API exports - Comprehensive README with usage examples and design overview - Phase 2 roadmap for CLI tools and LLM integration Foundation ready for Phase 2 intelligence features including: - AI-driven task decomposition via CCSDK toolkit - Strategic agent assignment and spawning via Task tool - Hybrid code+AI workflow orchestration Follows amplifier's "bricks and studs" modular design with stable contracts and regenerable internals. All tests pass, code quality validated by zen-architect (9/10 philosophy alignment). 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
Add two comprehensive test files to validate Super-Planner Phase 1 functionality: - test_planner_phase1.py: Basic functionality validation including task creation, hierarchical structure, dependencies, state management, and persistence with Django blog project example - test_planner_hostile.py: Hostile testing suite using "Vi Editor Rewrite in Python" as complex test project with 72+ tasks, 5-level hierarchy, stress testing for edge cases, circular dependencies, bulk operations, Unicode handling, and performance validation Both tests validate the core Phase 1 foundation is robust and ready for Phase 2 AI-driven orchestration features. All 48 hostile tests pass, confirming Phase 1 can handle complex real-world project structures. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
…i-agent project orchestration Add complete three-layer integration following amplifier-cli-architect guidance: **Core Integration (amplifier/core/):** - ProjectContext class for automatic project detection via .amplifier/project.json - Cross-session state persistence with directory tree traversal - Seamless integration with existing Phase 1 planner models **User Interface (scenarios/project_planner/):** - Full CLI with init, plan, status, execute commands - Natural language goal specification with AI decomposition foundation - Complete README following amplifier patterns **Makefile Integration:** - make project-init PROJECT_NAME="..." - Initialize projects with persistent planning - make project-plan GOALS="..." - AI-driven task decomposition - make project-status - Cross-session progress tracking - make project-execute - Multi-agent coordination foundation **Key Capabilities Delivered:** - Persistent planning state across multiple amplifier invocations - Automatic project context detection (zero configuration) - Foundation for AI task decomposition and agent coordination - Integration with bulletproof Phase 1 foundation (48/48 hostile tests passing) This enables amplifier to maintain long-term project context and coordinate specialized agents across complex multi-session workflows. Users can now tell amplifier a project needs planning, and it persists that context automatically. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
|
@ramparte please read the following Contributor License Agreement(CLA). If you agree with the CLA, please reply with the following information.
Contributor License AgreementContribution License AgreementThis Contribution License Agreement (“Agreement”) is agreed to by the party signing below (“You”),
|
…on and multi-agent coordination Complete implementation of Phase 2 capabilities: • Core Architecture: - decomposer.py: Intelligent goal breakdown using PydanticAI - agent_mapper.py: Smart agent assignment with capability mapping - orchestrator.py: Multi-agent execution coordination • User Interface: - scenarios/smart_decomposer/: Complete CLI tool for task decomposition - Makefile integration: make smart-decomposer command • System Enhancement: - Multi-task tracking capability - Session management integration ready - Philosophy-aligned implementation (8.5/10 validation score) • Testing & Validation: - Comprehensive test suite with golden test specifications - Performance benchmarks and integration tests - Used "super recursion" - Phase 1 coordinated Phase 2 development Follows amplifier patterns: bricks & studs modular design, ruthless simplicity, hybrid code+AI approach. Ready for multi-agent project orchestration. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
- Update PydanticAI API usage (output_type, result.output) - Add null checks for datetime comparisons in tests - Fix parameter types in test utilities Core Phase 2 modules now pass type checking with 0 errors. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
- Fix PydanticAI API usage in decomposer tests (.data → .output) - Add hashable StateTransition dataclass for protocols - Fix retry decorator type annotations in defensive coordination - Update Protocol type annotations in contract validation - Fix None type annotations in website_generator - Fix test hostile warning about accessing .tasks on False All core Super-Planner Phase 2 components now pass: ✅ 37/37 tests passing ✅ 0 type checking errors ✅ CLI tools functional ✅ End-to-end integration working 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
First version of this, integrated into amplifier.