Azure OpenAI Service - 429 Rate Limit When Token or Request Quota Is Exceeded

# Sprawdź aktualne zużycie quota dla deploymentu
az cognitiveservices usage list \
  --name my-openai-resource \
  --resource-group rg-ai \
  --query "[?name.value=='OpenAI.Standard.gpt-4o'].{model:name.value, current:currentValue, limit:limit}" -o table

# Sprawdź metryki rate limitingu z ostatnich 30 minut
az monitor metrics list \
  --resource /subscriptions/<sub-id>/resourceGroups/rg-ai/providers/Microsoft.CognitiveServices/accounts/my-openai-resource \
  --metric "AzureOpenAIRequests" \
  --dimension StatusCode \
  --interval PT1M \
  --start-time $(date -u -d '-30 minutes' +%Y-%m-%dT%H:%M:%SZ) \
  --query "value[0].timeseries[?metricValues[?statusCode=='429']]" -o json

# Lista deploymentów z ich limitami
az cognitiveservices account deployment list \
  --name my-openai-resource \
  --resource-group rg-ai \
  --query "[].{model:properties.model.name, version:properties.model.version, capacity:sku.capacity, name:name}" -o table

# Pojedyncze zapytanie testowe z wyświetleniem nagłówków
curl -s -D - https://my-openai-resource.openai.azure.com/openai/deployments/gpt-4o/chat/completions?api-version=2024-10-21 \
  -H "Content-Type: application/json" \
  -H "api-key: $AZURE_OPENAI_KEY" \
  -d '{"messages":[{"role":"user","content":"test"}],"max_tokens":5}' \
  2>&1 | grep -i "x-ratelimit\|retry-after"

# Spodziewane nagłówki:
# x-ratelimit-remaining-tokens: 0        <-- brak dostępnych tokenów
# x-ratelimit-remaining-requests: 0      <-- brak dostępnych zapytań
# retry-after: 12                         <-- czas oczekiwania w sekundach

# Sprawdź aktualne limity quota w regionie
az cognitiveservices model list \
  --location swedencentral \
  --query "[?model.name=='gpt-4o'].{model:model.name, version:model.version, maxCapacity:model.skus[0].capacity.maximum}" -o table

# Sprawdź aktualną capacity deploymentu
az cognitiveservices account deployment show \
  --name my-openai-resource \
  --resource-group rg-ai \
  --deployment-name gpt-4o \
  --query "{capacity:sku.capacity, model:properties.model.name}" -o json

# Zwiększ capacity deploymentu (np. z 80K do 150K TPM)
az cognitiveservices account deployment create \
  --name my-openai-resource \
  --resource-group rg-ai \
  --deployment-name gpt-4o \
  --model-name gpt-4o \
  --model-version "2024-08-06" \
  --model-format OpenAI \
  --sku-capacity 150 \
  --sku-name "GlobalStandard"

# Jeśli region nie ma wystarczającej capacity - sprawdź dostępność w innych regionach
az cognitiveservices model list \
  --location eastus2 \
  --query "[?model.name=='gpt-4o'].{version:model.version, available:model.skus[0].capacity.maximum}" -o table

# Uruchom LiteLLM proxy
litellm --config litellm_config.yaml --port 4000

# Test - zapytania automatycznie routowane do dostępnego deploymentu
curl http://localhost:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-4o","messages":[{"role":"user","content":"test"}]}'

# Sprawdź dostępność PTU w regionie
az cognitiveservices model list \
  --location swedencentral \
  --query "[?model.name=='gpt-4o'].model.skus[?name=='ProvisionedManaged'].{name:name, minCapacity:capacity.minimum, maxCapacity:capacity.maximum}" -o json

# Utwórz deployment typu Provisioned (minimalnie 50 PTU)
az cognitiveservices account deployment create \
  --name my-openai-resource \
  --resource-group rg-ai \
  --deployment-name gpt-4o-ptu \
  --model-name gpt-4o \
  --model-version "2024-08-06" \
  --model-format OpenAI \
  --sku-capacity 50 \
  --sku-name "ProvisionedManaged"

# Monitoruj utilization PTU (powinno być <80% dla rezerwy)
az monitor metrics list \
  --resource /subscriptions/<sub-id>/resourceGroups/rg-ai/providers/Microsoft.CognitiveServices/accounts/my-openai-resource \
  --metric "ProvisionedManagedUtilizationV2" \
  --dimension ModelDeploymentName \
  --interval PT1M \
  --start-time $(date -u -d '-60 minutes' +%Y-%m-%dT%H:%M:%SZ) \
  --query "value[0].timeseries[].data[-5:]" -o table

# 1. Wyślij serię zapytań testowych i sprawdź brak 429
for i in $(seq 1 20); do
  STATUS=$(curl -s -o /dev/null -w "%{http_code}" \
    https://my-openai-resource.openai.azure.com/openai/deployments/gpt-4o/chat/completions?api-version=2024-10-21 \
    -H "Content-Type: application/json" \
    -H "api-key: $AZURE_OPENAI_KEY" \
    -d '{"messages":[{"role":"user","content":"Say OK"}],"max_tokens":5}')
  echo "Request $i: HTTP $STATUS"
  sleep 0.5
done
# Expected: wszystkie odpowiedzi HTTP 200

# 2. Sprawdź metryki - brak nowych 429 w ostatnich 5 minutach
az monitor metrics list \
  --resource /subscriptions/<sub-id>/resourceGroups/rg-ai/providers/Microsoft.CognitiveServices/accounts/my-openai-resource \
  --metric "AzureOpenAIRequests" \
  --dimension StatusCode \
  --interval PT1M \
  --start-time $(date -u -d '-5 minutes' +%Y-%m-%dT%H:%M:%SZ) \
  --query "value[0].timeseries[].data[].{time:timeStamp, total:total}" -o table
# Expected: brak wierszy z StatusCode=429

# 3. Skonfiguruj alert na przyszłość
az monitor metrics alert create \
  --name "alert-openai-429-rate-limit" \
  --resource-group rg-ai \
  --scopes /subscriptions/<sub-id>/resourceGroups/rg-ai/providers/Microsoft.CognitiveServices/accounts/my-openai-resource \
  --condition "total AzureOpenAIRequests where StatusCode includes 429 > 10" \
  --window-size 5m \
  --evaluation-frequency 1m \
  --severity 2 \
  --action-group /subscriptions/<sub-id>/resourceGroups/rg-monitoring/providers/Microsoft.Insights/actionGroups/ag-platform-team \
  --description "Azure OpenAI rate limiting - >10 requests z 429 w 5 minut"