tony/WHOOSH
1
0
Fork 0
Code Issues 6 Pull Requests Actions Packages Projects Releases Wiki Activity

Add WHOOSH search service with BACKBEAT integration

Browse Source 
Complete implementation:
- Go-based search service with PostgreSQL and Redis backend
- BACKBEAT SDK integration for beat-aware search operations
- Docker containerization with multi-stage builds
- Comprehensive API endpoints for project analysis and search
- Database migrations and schema management
- GITEA integration for repository management
- Team composition analysis and recommendations

Key features:
- Beat-synchronized search operations with timing coordination
- Phase-based operation tracking (started → querying → ranking → completed)
- Docker Swarm deployment configuration
- Health checks and monitoring
- Secure configuration with environment variables

Architecture:
- Microservice design with clean API boundaries
- Background processing for long-running analysis
- Modular internal structure with proper separation of concerns
- Integration with CHORUS ecosystem via BACKBEAT timing

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
Claude Code
2025-09-06 11:16:39 +10:00
parent 595b05335d
commit 33676bae6d
29 changed files with 4262 additions and 185 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
docs/TEAM_COMPOSER_SPEC.md
View File

@@ -1,6 +1,12 @@
# WHOOSH Team Composer Specification
## LLM-Powered Autonomous Team Formation Engine
MVP Scope and Constraints
- Composer is optional in MVP: provide stubbed compositions (minimal_viable, balanced_standard). Full LLM analysis is post-MVP.
- Local-first models via Ollama; cloud providers are opt-in and must be explicitly enabled. Enforce strict JSON Schema validation on all model outputs; cache by normalized task hash with TTL.
- Limit outputs for determinism: cap team size and roles, remove chemistry analysis in v1, and require reproducible prompts with seeds where supported.
- Security: redact sensitive data (SHHH) on all ingress/egress; do not log tokens or raw artefacts; references only (UCXL/CIDs).
### Overview
The Team Composer is the central intelligence of WHOOSH's Autonomous AI Development Teams architecture. It uses Large Language Models to analyze incoming tasks, determine optimal team compositions, and orchestrate the formation of self-organizing AI development teams through sophisticated reasoning and pattern matching.
@@ -1076,4 +1082,4 @@ class ComposerFeedbackLoop:
await self._update_composition_rules(insights)
```
This Team Composer specification provides the foundation for WHOOSH's intelligent team formation capabilities, enabling sophisticated analysis of development tasks and automatic composition of optimal AI development teams through advanced LLM reasoning and pattern matching.
This Team Composer specification provides the foundation for WHOOSH's intelligent team formation capabilities, enabling sophisticated analysis of development tasks and automatic composition of optimal AI development teams through advanced LLM reasoning and pattern matching.