OSVauco/docs/Cost_Management_Rules.md

83 lines
2.2 KiB
Markdown

# Cost Management Rules
**OSVauco-NMTMD-GCOS | GCP Agent Master Repo**
## 1. Budget Alerts
```bash
gcloud billing budgets create \
--billing-account="${BILLING_ACCOUNT_ID}" \
--display-name="Agent Platform Budget" \
--budget-amount=500USD \
--threshold-rule=percent=0.5,basis=CURRENT_SPEND \
--threshold-rule=percent=0.8,basis=CURRENT_SPEND \
--threshold-rule=percent=1.0,basis=CURRENT_SPEND
```
## 2. Resource Labeling
All GCP resources MUST carry:
| Label Key | Example | Purpose |
|-----------|---------|--------|
| env | prod/dev/staging | Environment |
| team | osvaucoe | Cost attribution |
| cost-center | ai-platform | Finance |
| agent | orchestrator/rag | Per-agent tracking |
## 3. Cloud Run Cost Controls
```bash
gcloud run deploy ${SERVICE} \
--max-instances=10 \
--concurrency=80 \
--timeout=300
```
- CPU throttling on for non-latency-critical agents
- min-instances=1 only for latency-sensitive services
## 4. Vertex AI Cost Controls
- Use gemini-2.0-flash for high-volume sub-agent calls
- Context caching for repeated prompts (up to 75% savings)
- max_output_tokens=2048 for most tasks
- Monitor: aiplatform.googleapis.com/prediction/online/token_count
## 5. RAG Engine Cost Controls
- Delete stale documents from corpus
- Batch embedding for initial ingestion
- top_k=5 (not higher)
- Archive cold corpora to Cloud Storage lower tier
## 6. Memory Bank Cost Controls
- TTL: 7 days for short-lived session memories
- Firestore-backed for most use cases
- Index only user_id and session_id
## 7. Networking Cost Controls
- Private Google Access to avoid Vertex AI egress charges
- VPC routing for all agent traffic
- Cloud NAT only where unavoidable
## 8. Storage Lifecycle
```json
{
"rule": [{
"action": { "type": "Delete" },
"condition": { "age": 7 }
}]
}
```
Apply with: `gcloud storage buckets update gs://BUCKET --lifecycle-file=lifecycle.json`
## 9. End-of-Day Teardown Checklist
- [ ] Run 03-teardown.sh
- [ ] Verify no active Agent Runtimes: `gcloud ai agent-engines list --region=us-central1`
- [ ] Verify no active Vertex AI endpoints: `gcloud ai endpoints list --region=us-central1`
- [ ] Check billing dashboard for anomalies