SPEC-001 — Architecture
Scope
The Agent Platform OCI consists of reusable components, deployable applications, integration contracts, agent templates, an evaluation layer, and operational artifacts.
Components
| Componente |
Tipo |
Responsibility |
libs/agent_framework |
Lib |
Core reutilizável of the framework. |
runtimes/langgraph_runtime |
Runtime |
Execution of Agents based on LangGraph. |
apps/agent_gateway |
App |
Input padronizada and Routing of Agents/backends. |
apps/channel_gateway |
App |
Normalização of canais external. |
apps/ai_gateway |
App |
Abstração, Governance and Routing of modelos. |
apps/mcp_gateway |
App |
Governance, Catalog and Execution of tools MCP. |
mcp/servers |
Apps |
MCP servers of Domain. |
evals/offline |
App/Lib |
Evaluation offline/batch. |
evals/certification |
Suite |
Certification técnica and funcional. |
templates/agent_template_backend |
Template |
Scaffold for new Agents. |
specs |
documentation |
contracts SDD versionados. |
deploy |
Operations |
Docker, Kubernetes and Helm. |
Repository structure
Logical architecture
Physical architecture
| service |
Porta Standard |
Deploy |
Escala |
| Agent Gateway |
9000 |
Kubernetes Deployment |
Horizontal |
| Agent Backend / Runtime |
8000 |
Kubernetes Deployment |
Horizontal with external storage |
| Channel Gateway |
7000 |
Kubernetes Deployment |
Horizontal |
| AI Gateway |
9100 |
Kubernetes Deployment |
Horizontal |
| MCP Gateway |
8300 |
Kubernetes Deployment |
Horizontal |
| MCP Servers |
8001+ |
Kubernetes Deployment |
Per domain |
| Evaluator API |
9300 |
Deployment/CronJob |
By batch workload |
| Frontend Demo |
5173 |
Optional |
Noncritical |
Main contracts
| Contract |
producer |
consumer |
| GatewayRequest |
Channel Gateway / Agent Gateway |
Agent Runtime |
| ChannelResponse |
Agent Runtime |
Channel Gateway / Cliente |
| BusinessContext |
Channel Gateway / Identity resolve |
Runtime / Agents / MCP |
| LLMRequest |
Agent Runtime |
AI Gateway |
| LLMResponse |
AI Gateway |
Agent Runtime |
| ToolInvocation |
Agent Runtime / MCP Gateway |
MCP Server |
| ToolResult |
MCP Server / MCP Gateway |
Agent Runtime |
| GuardrailResult |
Guardrail Engine |
Runtime / Observability |
| JudgeResult |
Judge Engine / Evaluator |
Runtime / Evaluator |
| EvaluationRun |
Evaluator |
Persistence / Dashboards |
GatewayRequest
ChannelResponse
Flow main
Configuration
| file |
Uso |
.env |
Provider, Authentication, flags and endpoints por ambiente. |
agents.yaml |
Registration of Agents. |
routing.yaml |
Intents, rotas, Policies and fallback. |
guardrails.yaml |
Guardrails global. |
judges.yaml |
Judges global. |
llm_profiles.yaml |
Profiles of modelos por componente. |
mcp_servers.yaml |
MCP servers disponíveis. |
tools.yaml |
Catalog of tools. |
mcp_parameter_mapping.yaml |
Mapeamento BusinessContext → argumentos MCP. |
identity.yaml |
Resolução of Identity of negócio. |
observability.yaml |
Logs, Metrics, traces and exporters. |
evals.yaml |
Datasets, Metrics and Configuration of the evaluator. |
Events
| Evento |
Origem |
Description |
gateway.request.received |
Agent Gateway |
Request recebida. |
channel.normalized |
Channel Gateway |
Payload convertido em GatewayRequest. |
runtime.started |
Runtime |
Execution iniciada. |
guardrail.input.completed |
Guardrails |
Guardrails of Input concluídos. |
route.selected |
Router/Supervisor |
Rota definida. |
mcp.tool.completed |
MCP Gateway |
Tool executada. |
llm.completed |
AI Gateway |
Call LLM concluída. |
judge.completed |
Judge Engine |
Evaluation concluída. |
runtime.completed |
Runtime |
Execution finalizada. |
Requirements No Funcionais
| Categoria |
Requirement |
| Availability |
Components deployáveis expõem /health and /ready. |
| Escalabilidade |
Apps stateless escalam horizontalmente. State conversational fica em repositórios external. |
| Security |
Segredos are fornecidos por secret store or Kubernetes Secrets. |
| Observability |
Logs, Metrics and traces usam correlation por request_id, trace_id, session_id, tenant_id and agent_id. |
| Auditabilidade |
Decisions of rota, guardrail, judge, MCP and LLM are rastreáveis. |
| Portabilidade |
Execution suportada em local, Docker Compose and Kubernetes/OKE. |
| Configuration |
Comportamento variável is controlado por .env and YAML versionado. |
Acceptance criteria
Glossário
| Termo |
Definição |
| Agent Platform |
Plataforma composta por runtime, gateways, evaluator, templates, contracts and Components operational. |
| Agent Framework |
Biblioteca/core reutilizável with contracts, guardrails, judges, Memory, telemetria, providers and utilitários. |
| Agent Runtime |
Motor of Execution of Agents based on LangGraph, State, Session, Memory, checkpoints, Routing and ciclo of vida. |
| Agent Gateway |
Aplicação deployável of Input, Routing and orquestração between backends/Agents. |
| Channel Gateway |
Aplicação or módulo of normalização of payloads of canais for GatewayRequest. |
| AI Gateway |
Aplicação of Governance, Routing and abstração of Calls LLM/embedding. |
| MCP Gateway |
Aplicação of Governance and Routing of tools MCP. |
| Evaluator |
layer of Evaluation online/offline, regressão and Certification. |
| Business Context |
Conjunto of chaves canônicas of negócio: customer_key, contract_key, interaction_key, account_key, resource_key and session_key. |