- Changed NetworkName from 'chorus_default' to 'chorus_net'
- This matches the actual network 'CHORUS_chorus_net' (service prefix added automatically)
- Fixes discovered_count:0 issue - now successfully discovering all 25 agents
- Updated IMPLEMENTATION-SUMMARY with deployment status
Result: All 25 CHORUS agents now discovered successfully via Docker Swarm API
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Resolves WHOOSH-LLM-002: Replace stubbed LLM functions with full Ollama API integration
## New Features
- Full Ollama API integration with automatic endpoint discovery
- LLM-powered task classification using configurable models
- LLM-powered skill requirement analysis
- Graceful fallback to heuristics on LLM failures
- Feature flag support for LLM vs heuristic execution
- Performance optimization with smaller, faster models (llama3.2:latest)
## Implementation Details
- Created OllamaClient with connection pooling and timeout handling
- Structured prompt engineering for consistent JSON responses
- Robust error handling with automatic failover to heuristics
- Comprehensive integration tests validating functionality
- Support for multiple Ollama endpoints with health checking
## Performance & Reliability
- Timeout configuration prevents hanging requests
- Fallback mechanism ensures system reliability
- Uses 3.2B parameter model for balance of speed vs accuracy
- Graceful degradation when LLM services unavailable
## Files Added
- internal/composer/ollama.go: Core Ollama API integration
- internal/composer/llm_test.go: Comprehensive integration tests
## Files Modified
- internal/composer/service.go: Implemented LLM functions
- internal/composer/models.go: Updated config for performance
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
Add sophisticated team formation engine with:
- Task analysis and classification algorithms
- Skill requirement detection and mapping
- Agent capability matching with confidence scoring
- Database persistence with PostgreSQL/pgx integration
- Production-ready REST API endpoints
API endpoints added:
- POST /api/v1/teams (create teams with analysis)
- GET /api/v1/teams (list teams with pagination)
- GET /api/v1/teams/{id} (get team details)
- POST /api/v1/teams/analyze (analyze without creating)
- POST /api/v1/agents/register (register new agents)
Core Team Composer capabilities:
- Heuristic task classification (9 task types)
- Multi-dimensional complexity assessment
- Technology domain identification
- Role-based team composition strategies
- Agent matching with skill/availability scoring
- Full database CRUD with transaction support
This moves WHOOSH from basic N8N workflow stubs to a fully
functional team composition system with real business logic.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
