Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Latest commit

Β 

History

History
63 lines (46 loc) Β· 2.88 KB

File metadata and controls

63 lines (46 loc) Β· 2.88 KB

OmniRoute Auto-Combo Engine

Self-managing model chains with adaptive scoring

How It Works

The Auto-Combo Engine dynamically selects the best provider/model for each request using a 6-factor scoring function:

Factor Weight Description
Quota 0.20 Remaining capacity [0..1]
Health 0.25 Circuit breaker: CLOSED=1.0, HALF=0.5, OPEN=0.0
CostInv 0.20 Inverse cost (cheaper = higher score)
LatencyInv 0.15 Inverse p95 latency (faster = higher)
TaskFit 0.10 Model Γ— task type fitness score
Stability 0.10 Low variance in latency/errors

Mode Packs

Pack Focus Key Weight
πŸš€ Ship Fast Speed latencyInv: 0.35
πŸ’° Cost Saver Economy costInv: 0.40
🎯 Quality First Best model taskFit: 0.40
πŸ“‘ Offline Friendly Availability quota: 0.40

Self-Healing

  • Temporary exclusion: Score < 0.2 β†’ excluded for 5 min (progressive backoff, max 30 min)
  • Circuit breaker awareness: OPEN β†’ auto-excluded; HALF_OPEN β†’ probe requests
  • Incident mode: >50% OPEN β†’ disable exploration, maximize stability
  • Cooldown recovery: After exclusion, first request is a "probe" with reduced timeout

Bandit Exploration

5% of requests (configurable) are routed to random providers for exploration. Disabled in incident mode.

API

# Create auto-combo
curl -X POST http://localhost:20128/api/combos/auto \
  -H "Content-Type: application/json" \
  -d '{"id":"my-auto","name":"Auto Coder","candidatePool":["anthropic","google","openai"],"modePack":"ship-fast"}'

# List auto-combos
curl http://localhost:20128/api/combos/auto

Task Fitness

30+ models scored across 6 task types (coding, review, planning, analysis, debugging, documentation). Supports wildcard patterns (e.g., *-coder β†’ high coding score).

Files

File Purpose
open-sse/services/autoCombo/scoring.ts Scoring function & pool normalization
open-sse/services/autoCombo/taskFitness.ts Model Γ— task fitness lookup
open-sse/services/autoCombo/engine.ts Selection logic, bandit, budget cap
open-sse/services/autoCombo/selfHealing.ts Exclusion, probes, incident mode
open-sse/services/autoCombo/modePacks.ts 4 weight profiles
src/app/api/combos/auto/route.ts REST API