Files

uroma 3b128ba3bd feat: Add unified agent integration with Prometheus, Every Code, and Dexto

This commit adds comprehensive integration of three major AI agent platforms:

## MCP Servers (3)
- Prometheus MCP: Knowledge graph code reasoning with AST analysis
- Every Code MCP: Fast terminal-based coding agent with Auto Drive
- Dexto MCP: Agent harness with orchestration and session management

## Claude Code Skills (6)
- /agent-plan: Generate implementation plans
- /agent-fix-bug: Fix bugs end-to-end
- /agent-solve: Solve complex problems
- /agent-review: Review code quality
- /agent-context: Get code context
- /agent-orchestrate: Orchestrate workflows

## Ralph Auto-Integration
- Pattern-based auto-trigger for all three platforms
- Intelligent backend selection
- Multi-platform coordination
- Configuration in ralph/ralph.yml

## Documentation
- Complete integration guides
- Ralph auto-integration documentation
- Setup scripts
- Usage examples

Co-Authored-By: Claude <noreply@anthropic.com>

2026-01-27 20:23:14 +00:00

2.6 KiB

Raw Blame History

Agent: Solve

Multi-agent problem solving with orchestration across multiple tools and approaches.

Usage

/agent-solve "Optimize database queries for slow dashboard loading"

Description

The /agent-solve skill tackles complex problems by coordinating multiple agents:

Every Code's /solve command for orchestration
Prometheus for deep code analysis
Multiple solution attempts with validation
Best solution selection based on metrics

Examples

Solve performance issue

/agent-solve "Dashboard takes 10 seconds to load with 1000 items"

Solve architecture problem

/agent-solve "Refactor monolithic payment service into microservices
Constraints: Must maintain backward compatibility"

Solve integration challenge

/agent-solve "Integrate Stripe webhooks with existing payment system
Context: Using Express.js, PostgreSQL, Redis"

Backends

Primary: Every Code (/solve multi-agent orchestration)
Analysis: Prometheus (knowledge graph, AST analysis)
Validation: Both platforms (testing, review)

Workflow

1. Problem Decomposition

Break down complex problem into sub-tasks
Identify dependencies and constraints
Determine success criteria

2. Parallel Solution Attempts

Agent 1: Analyze current implementation
Agent 2: Research best practices
Agent 3: Generate solution candidates
Agent 4: Validate solutions

3. Solution Synthesis

Compare solution approaches
Merge best aspects from each
Create unified solution

4. Implementation & Testing

Apply selected solution
Run comprehensive tests
Measure improvement metrics

Output

# Problem: Dashboard loading optimization

## Analysis
- Current load time: 10.2s
- Bottleneck identified: N+1 queries in item fetching
- Database queries: 1,247 per page load

## Solution Candidates
1. Query batching with DataLoader: 2.1s (79% improvement)
2. Caching layer with Redis: 1.8s (82% improvement)
3. Combined approach: 0.9s (91% improvement)

## Selected Solution
- Implemented DataLoader for batch queries
- Added Redis caching for hot data
- Optimized database indexes

## Results
✓ Load time: 10.2s → 0.9s (91% improvement)
✓ Queries: 1,247 → 47 per page load
✓ All tests passing: 127/127
✓ No regressions detected

Files modified:
- src/services/dashboard.ts
- src/api/items.ts
- src/cache/redis.ts
- prisma/schema.prisma

Follow-up

After solving:

/agent-review - Review implementation quality
/agent-test - Validate with tests
/agent-context - Understand solution architecture

2.6 KiB Raw Blame History