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 × task type fitness score
Stability	0.10	Low variance in latency/errors

Pack	Focus	Key Weight
🚀 Ship Fast	Speed	latencyInv: 0.35
💰 Cost Saver	Economy	costInv: 0.40
🎯 Quality First	Best model	taskFit: 0.40
📡 Offline Friendly	Availability	quota: 0.40

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

# 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

, , , , , ). Supports wildcard patterns (e.g., → high coding score).

File	Purpose
	Scoring function & pool normalization
	Model × task fitness lookup
	Selection logic, bandit, budget cap
	Exclusion, probes, incident mode
	4 weight profiles
	REST API