Deliverables

sequenceDiagram
  autonumber
  participant C as Client
  participant G as API Gateway
  participant O as Order Service
  participant P as Payment Gateway
  participant Q as Event Log

  C->>G: POST /orders (Idempotency-Key)
  G->>O: create order
  O->>O: persist as PENDING
  O->>P: authorise (deadline 3s)
  alt authorised
    P-->>O: approved + auth id
    O->>O: mark CONFIRMED
    O->>Q: OrderConfirmed
    O-->>G: 201 Created
  else declined
    P-->>O: declined
    O->>O: mark REJECTED
    O-->>G: 402 Payment Required
  else timeout
    P--xO: no response by deadline
    O->>O: keep PENDING
    O-->>G: 202 Accepted (poll for status)
    Note over O,P: reconciliation job settles<br/>PENDING against the provider
  end
  G-->>C: response

flowchart TB
  users(["Users"]) --> dns["Global DNS<br/><i>latency routing + health checks</i>"]

  subgraph r1["Region: primary"]
    direction TB
    lb1["Load Balancer<br/><i>public</i>"]
    subgraph az1["Zone A"]
      n1["Node Pool<br/><i>api ×3, worker ×2</i>"]
    end
    subgraph az2["Zone B"]
      n2["Node Pool<br/><i>api ×3, worker ×2</i>"]
    end
    subgraph az3["Zone C"]
      n3["Node Pool<br/><i>api ×2, worker ×1</i>"]
    end
    db1[("Primary DB<br/><i>synchronous replica in Zone B</i>")]
    lb1 --> n1
    lb1 --> n2
    lb1 --> n3
    n1 --> db1
    n2 --> db1
    n3 --> db1
  end

  subgraph r2["Region: secondary"]
    direction TB
    lb2["Load Balancer<br/><i>warm</i>"]
    n4["Node Pool<br/><i>api ×2, scaled down</i>"]
    db2[("Read Replica<br/><i>asynchronous — RPO 30s</i>")]
    lb2 --> n4 --> db2
  end

  dns --> lb1
  dns -.->|"failover only"| lb2
  db1 -.->|"async replication"| db2

flowchart TB
  s(["Alert: order submit p99 > 900 ms<br/>for 5 min"])
  s --> c1["1. Confirm scope<br/><i>one region or global?</i>"]
  c1 --> q1{"Global?"}
  q1 -->|"no"| a1["2a. Check that region's<br/>dependency health"]
  q1 -->|"yes"| a2["2b. Check shared dependencies:<br/>DB, cache, identity"]
  a1 --> q2{"Region-local cause?"}
  q2 -->|"yes"| m1["3. Shift traffic away<br/><i>runbook OPS-04</i>"]
  q2 -->|"no"| a2
  a2 --> q3{"DB CPU > 80%<br/>or replication lag > 10s?"}
  q3 -->|"yes"| m2["4. Enable read-path cache bypass=off<br/>+ raise connection limit<br/><i>flag: cache.aggressive</i>"]
  q3 -->|"no"| q4{"Recent deploy<br/>in last 60 min?"}
  q4 -->|"yes"| m3["5. Roll back<br/><i>runbook OPS-01</i>"]
  q4 -->|"no"| esc(["6. Escalate to<br/>Order team on-call<br/><i>stop investigating</i>"])
  m1 --> v["7. Verify p99 recovers<br/>within 10 min"]
  m2 --> v
  m3 --> v
  v --> q5{"Recovered?"}
  q5 -->|"yes"| done(["Close · record in incident log"])
  q5 -->|"no"| esc