mosaic/stack
1
0
Fork 0
Code Issues 10 Pull Requests Actions Packages Projects Releases 2 Wiki Activity

[EPIC] Implement Non-AI Coordinator Pattern (PoC) #142

New Issue
Closed
opened 2026-01-31 20:58:22 +00:00 by jason.woltje · 0 comments
jason.woltje commented 2026-01-31 20:58:22 +00:00
Owner
Copy Link

Overview

This epic implements a two-layer non-AI coordinator architecture that solves:

  1. Quality enforcement problem - Agents claiming done prematurely
  2. Orchestration problem - Context exhaustion preventing autonomous multi-issue completion

Architecture Document

See:

Proof of Concept Goals

The PoC validates the architecture through 4 phases over 4 weeks:

  • Phase 1 (Week 1): Context monitoring and estimation
  • Phase 2 (Week 2): Agent assignment logic
  • Phase 3 (Week 3): Quality gates enforcement
  • Phase 4 (Week 4): Integration and end-to-end testing

Sub-Issues

Phase 1: Context Monitoring

  • COORD-001: Implement context estimator
  • COORD-002: Build basic context monitor
  • COORD-003: Validate 50% rule

Phase 2: Agent Assignment

  • COORD-004: Implement agent profiles
  • COORD-005: Build assignment algorithm
  • COORD-006: Test assignment scenarios

Phase 3: Quality Gates

  • COORD-007: Implement core gates
  • COORD-008: Build Quality Orchestrator service
  • COORD-009: Test rejection loop

Phase 4: Integration

  • COORD-010: Build orchestration loop
  • COORD-011: Implement compaction
  • COORD-012: Implement session rotation
  • COORD-013: End-to-end test

Success Metrics

Metric Target How to Measure
Autonomy 100% completion without human intervention Count of human interventions / total issues
Quality 100% of commits pass quality gates Commits passing gates / total commits
Cost optimization >70% issues use free models Issues on GLM/MiniMax / total issues
Context management 0 agents exceed 95% without rotation Context exhaustion events
Estimation accuracy ±20% of actual usage

Rollout Plan

  • PoC (Weeks 1-4): Standalone Python orchestrator, test with Mosaic Stack M4 remaining issues
  • Production Alpha (Weeks 5-8): Integrate Quality Orchestrator, multi-agent support
  • Production Beta (Weeks 9-12): Self-hosted models, advanced features, monitoring dashboard
## Overview This epic implements a **two-layer non-AI coordinator architecture** that solves: 1. **Quality enforcement problem** - Agents claiming done prematurely 2. **Orchestration problem** - Context exhaustion preventing autonomous multi-issue completion ## Architecture Document See: ## Proof of Concept Goals The PoC validates the architecture through 4 phases over 4 weeks: - **Phase 1 (Week 1):** Context monitoring and estimation - **Phase 2 (Week 2):** Agent assignment logic - **Phase 3 (Week 3):** Quality gates enforcement - **Phase 4 (Week 4):** Integration and end-to-end testing ## Sub-Issues ### Phase 1: Context Monitoring - [ ] COORD-001: Implement context estimator - [ ] COORD-002: Build basic context monitor - [ ] COORD-003: Validate 50% rule ### Phase 2: Agent Assignment - [ ] COORD-004: Implement agent profiles - [ ] COORD-005: Build assignment algorithm - [ ] COORD-006: Test assignment scenarios ### Phase 3: Quality Gates - [ ] COORD-007: Implement core gates - [ ] COORD-008: Build Quality Orchestrator service - [ ] COORD-009: Test rejection loop ### Phase 4: Integration - [ ] COORD-010: Build orchestration loop - [ ] COORD-011: Implement compaction - [ ] COORD-012: Implement session rotation - [ ] COORD-013: End-to-end test ## Success Metrics | Metric | Target | How to Measure | |--------|--------|----------------| | **Autonomy** | 100% completion without human intervention | Count of human interventions / total issues | | **Quality** | 100% of commits pass quality gates | Commits passing gates / total commits | | **Cost optimization** | >70% issues use free models | Issues on GLM/MiniMax / total issues | | **Context management** | 0 agents exceed 95% without rotation | Context exhaustion events | | **Estimation accuracy** | ±20% of actual usage | |estimated - actual| / actual | ## Rollout Plan - **PoC (Weeks 1-4):** Standalone Python orchestrator, test with Mosaic Stack M4 remaining issues - **Production Alpha (Weeks 5-8):** Integrate Quality Orchestrator, multi-agent support - **Production Beta (Weeks 9-12):** Self-hosted models, advanced features, monitoring dashboard
jason.woltje added the p0 label 2026-01-31 20:58:22 +00:00
jason.woltje added this to the M4.1-Coordinator (0.0.4) milestone 2026-01-31 21:10:03 +00:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
ai
AI/LLM integration
 api
Backend/API work
 api
auth
Authentication
 database
database
Database/schema work
 devops
Docker/deployment
 docs
Documentation
 frontend
graph
knowledge-module
migration
Data migration
 orchestrator
Orchestrator service (apps/orchestrator/)
 p0
Critical priority
 p1
High priority
 p2
Medium priority
 p3
Low priority
 performance
Performance work
 phase-1
phase-2
phase-3
phase-4
phase-5
plugin
MoltBot plugin work
 search
security
Security-related
 setup
Initial setup
 testing
Testing/QA
 web
Frontend work
No Label p0
Milestone
No items
No Milestone M4.1-Coordinator (0.0.4)
Projects
Clear projects
No project
Assignees
Clear assignees
jason.woltje
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: mosaic/stack#142
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?