# SPEC-020 — Operational Readiness and SRE Model

## Agent Platform OCI

Version: 1.0.0


---

## Reading guide

each SPEC is organizada for servir tanto como Contract arquitetural quanto como guia practical of adoção.

The document structure is:

1. Concept.
2. Problem addressed.
3. When to use.
4. When not to use.
5. Architecture.
6. Implementation.
7. Examples.
8. Common errors.
9. Acceptance criteria.

---


# 1. Concept

Operational readiness defines the minimum requirements to run the Agent Platform OCI in production with reliability, observability, incident response capabilities, and recovery.

# 2. Managed components

- Agent Gateway;
- Channel Gateway;
- Agent Runtime;
- AI Gateway;
- MCP Gateway;
- MCP Servers;
- Evaluator;
- bancos/repositórios;
- Langfuse/OTEL;
- Redis/Mongo/ADB when usados.

# 3. Health and readiness

Minimum endpoints:

```text
GET /health
GET /ready
GET /version
```

# 4. SLOs

| Componente | Latency | Availability |
| --- | --- | --- |
| Agent Gateway | p95 < 1s | 99.5% |
| Agent Runtime | p95 < 5s | 99.0% |
| AI Gateway | p95 < 10s | 99.0% |
| MCP Gateway | p95 < 2s | 99.0% |
| Evaluator | janela batch | Execution diária |


# 5. Metrics

- requests_total;
- request_latency_ms;
- errors_total;
- active_sessions;
- llm_tokens_total;
- llm_cost_estimated;
- mcp_tool_calls_total;
- guardrail_blocks_total;
- judge_scores;
- evaluator_scores.

# 6. Dashboards

Minimum dashboards:

- Platform Overview;
- Runtime;
- Gateway;
- AI Gateway;
- MCP Gateway;
- Guardrails;
- Evaluator;
- Cost/Usage;
- Incidents.

# 7. Alerts

| Alert | Condition |
| --- | --- |
| HighErrorRate | 5xx above of the Limit. |
| LatencySLOBreach | p95 above of the SLO. |
| LLMProviderDown | Failures consecutive no provider. |
| MCPTimeoutSpike | increase of timeout MCP. |
| GuardrailSpike | increase abnormal of Blocks. |
| EvaluatorFailed | Run failed. |


# 8. Runbooks

A runbook must contain:

- symptom;
- Impact;
- queries;
- dashboards;
- logs;
- actions;
- rollback;
- escalation.

# 9. Incident management

Flow:

```mermaid
flowchart LR
    Detect[Detect] --> Triage[Triage]
    Triage --> Mitigate[Mitigate]
    Mitigate --> Recover[Recover]
    Recover --> Postmortem[Postmortem]
```

# 10. Capacity

Assess:

- QPS;
- Sessions concurrent;
- tokens/minuto;
- Calls MCP/minuto;
- Latency of provider;
- uso of Memory;
- storage of checkpoints.

# 11. Common errors

| Error | Impact | Correction |
| --- | --- | --- |
| without readiness | traffic before of app estar ready. | implement /ready. |
| without Alerts MCP | Failure silenciosa. | create Alerts por tool. |
| without runbook | MTTR high. | create runbooks por incidente. |
| without Cost LLM | without control financial. | Registrar tokens/Costs. |


# 12. Production readiness checklist

- [ ] Health checks ativos.
- [ ] Readiness checks ativos.
- [ ] Structured logs.
- [ ] Metrics exportadas.
- [ ] Exported traces.
- [ ] Dashboards created.
- [ ] Configured alerts.
- [ ] Runbooks disponíveis.
- [ ] Rollback validado.
- [ ] Defined SLOs.
- [ ] Estimated capacity.
- [ ] Incident process definido.