chore: update tenant-info to show live endpoints

[mishraomp]

AI Hub Infra Changes

Summary: 0 to add, 4 to change, 0 to destroy (across 1 stack(s))

Show plan details

Terraform will perform the following actions:

  # azurerm_api_management_api_policy.tenant["gcpe-media-monitoring"] will be updated in-place
  ~ resource "azurerm_api_management_api_policy" "tenant" {
        id                  = "/subscriptions/****/resourceGroups/ai-services-hub-test/providers/Microsoft.ApiManagement/service/ai-services-hub-test-apim/apis/gcpe-media-monitoring"
      ~ xml_content         = <<-EOT
          - <policies>
          - 	<inbound>
          - 		<base />
          - 		<!-- Extract tracking dimensions from headers -->
          - 		<include-fragment fragment-id="tracking-dimensions" />
          - 		<!-- Tenant identification -->
          - 		<set-header name="X-Tenant-Id" exists-action="override">
          - 			<value>gcpe-media-monitoring</value>
          - 		</set-header>
          - 		<!-- Per-model token rate limiting for OpenAI requests only -->
          - 		<!-- Each model has its own rate limit matching its Azure OpenAI deployment capacity -->
          - 		<!-- Only applies to /openai/* paths; DocInt/Speech/Search/Storage are not rate-limited by token count -->
          - 		<!-- CRITICAL: estimate-prompt-tokens reads the entire request body for tokenization. -->
          - 		<!-- On large binary payloads (e.g., 500KB base64 DocInt images) this causes APIM to hang. -->
          - 		<!-- Extracts deployment name from URL: /openai/deployments/{deployment-name}/... -->
          - 		<!-- For /v1/ format: extracts from request body "model" field (deployment name lookup key) -->
          - 		<choose>
          - 			<when condition="@(context.Request.Url.Path.ToLower().Contains(&quot;openai&quot;))">
          - 				<set-variable name="deploymentName" value="@{
          + <policies>
          +     <inbound>
          +         <base />
          +         <!-- Extract tracking dimensions from headers -->
          +         <include-fragment fragment-id="tracking-dimensions" />
          +         <!-- Tenant identification -->
          +         <set-header name="X-Tenant-Id" exists-action="override">
          +             <value>gcpe-media-monitoring</value>
          +         </set-header>
          +         <!-- Per-model token rate limiting for OpenAI requests only -->
          +         <!-- Each model has its own rate limit matching its Azure OpenAI deployment capacity -->
          +         <!-- Only applies to /openai/* paths; DocInt/Speech/Search/Storage are not rate-limited by token count -->
          +         <!-- CRITICAL: estimate-prompt-tokens reads the entire request body for tokenization. -->
          +         <!-- On large binary payloads (e.g., 500KB base64 DocInt images) this causes APIM to hang. -->
          +         <!-- Extracts deployment name from URL: /openai/deployments/{deployment-name}/... -->
          +         <!-- For /v1/ format: extracts from request body "model" field (deployment name lookup key) -->
          +         <choose>
          +             <when condition="@(context.Request.Url.Path.ToLower().Contains(&quot;openai&quot;))">
          +                 <set-variable name="deploymentName" value="@{
                                var path = context.Request.Url.Path;
                                var match = System.Text.RegularExpressions.Regex.Match(path, @&quot;/deployments/([^/]+)/&quot;);
                                if (match.Success) { return match.Groups[1].Value; }
                                // For /v1/ format: model field is the deployment name lookup key on Azure OpenAI
                                // Client sends e.g. "gpt-4.1-mini"; tenant-prefix to match deployment name
                                if (path.ToLower().Contains(&quot;/v1/&quot;)) {
                                    try {
                                        var body = context.Request.Body.As&lt;JObject&gt;(preserveContent: true);
                                        var model = body?[&quot;model&quot;]?.ToString();
                                        if (!string.IsNullOrEmpty(model)) { return &quot;gcpe-media-monitoring-&quot; + model; }
                                    } catch { }
                                }
                                return &quot;unknown&quot;;
          -                 }" />
          - 				<choose>
          - 					<when condition="@(context.Variables.GetValueOrDefault&lt;string&gt;(&quot;deploymentName&quot;, &quot;&quot;) == &quot;gpt-4.1&quot;)">
          - 						<!-- Rate limit for gpt-4.1: 300k TPM (deployment capacity is in thousands of TPM) -->
          - 						<llm-token-limit counter-key="@(context.Subscription.Id + &quot;-gpt-4.1&quot;)" tokens-per-minute="300000" estimate-prompt-tokens="true" remaining-tokens-variable-name="remainingTokens" remaining-tokens-header-name="x-ratelimit-remaining-tokens" tokens-consumed-variable-name="tokensConsumed" />
          - 					</when>
          - 					<when condition="@(context.Variables.GetValueOrDefault&lt;string&gt;(&quot;deploymentName&quot;, &quot;&quot;) == &quot;gpt-4.1-mini&quot;)">
          - 						<!-- Rate limit for gpt-4.1-mini: 1500k TPM (deployment capacity is in thousands of TPM) -->
          - 						<llm-token-limit counter-key="@(context.Subscription.Id + &quot;-gpt-4.1-mini&quot;)" tokens-per-minute="1500000" estimate-prompt-tokens="true" remaining-tokens-variable-name="remainingTokens" remaining-tokens-header-name="x-ratelimit-remaining-tokens" tokens-consumed-variable-name="tokensConsumed" />
          - 					</when>
          - 					<when condition="@(context.Variables.GetValueOrDefault&lt;string&gt;(&quot;deploymentName&quot;, &quot;&quot;) == &quot;gpt-4.1-nano&quot;)">
          - 						<!-- Rate limit for gpt-4.1-nano: 1500k TPM (deployment capacity is in thousands of TPM) -->
          - 						<llm-token-limit counter-key="@(context.Subscription.Id + &quot;-gpt-4.1-nano&quot;)" tokens-per-minute="1500000" estimate-prompt-tokens="true" remaining-tokens-variable-name="remainingTokens" remaining-tokens-header-name="x-ratelimit-remaining-tokens" tokens-consumed-variable-name="tokensConsumed" />
          - 					</when>
          - 					<when condition="@(context.Variables.GetValueOrDefault&lt;string&gt;(&quot;deploymentName&quot;, &quot;&quot;) == &quot;gpt-4o&quot;)">
          - 						<!-- Rate limit for gpt-4o: 300k TPM (deployment capacity is in thousands of TPM) -->
          - 						<llm-token-limit counter-key="@(context.Subscription.Id + &quot;-gpt-4o&quot;)" tokens-per-minute="300000" estimate-prompt-tokens="true" remaining-tokens-variable-name="remainingTokens" remaining-tokens-header-name="x-ratelimit-remaining-tokens" tokens-consumed-variable-name="tokensConsumed" />
          - 					</when>
          - 					<when condition="@(context.Variables.GetValueOrDefault&lt;string&gt;(&quot;deploymentName&quot;, &quot;&quot;) == &quot;gpt-4o-mini&quot;)">
          - 						<!-- Rate limit for gpt-4o-mini: 1500k TPM (deployment capacity is in thousands of TPM) -->
          - 						<llm-token-limit counter-key="@(context.Subscription.Id + &quot;-gpt-4o-mini&quot;)" tokens-per-minute="1500000" estimate-prompt-tokens="true" remaining-tokens-variable-name="remainingTokens" remaining-tokens-header-name="x-ratelimit-remaining-tokens" tokens-consumed-variable-name="tokensConsumed" />
          - 					</when>
          - 					<when condition="@(context.Variables.GetValueOrDefault&lt;string&gt;(&quot;deploymentName&quot;, &quot;&quot;) == &quot;gpt-5-mini&quot;)">
          - 						<!-- Rate limit for gpt-5-mini: 100k TPM (deployment capacity is in thousands of TPM) -->
          - 						<llm-token-limit counter-key="@(context.Subscription.Id + &quot;-gpt-5-mini&quot;)" tokens-per-minute="100000" estimate-prompt-tokens="true" remaining-tokens-variable-name="remainingTokens" remaining-tokens-header-name="x-ratelimit-remaining-tokens" tokens-consumed-variable-name="tokensConsumed" />
          - 					</when>
          - 					<when condition="@(context.Variables.GetValueOrDefault&lt;string&gt;(&quot;deploymentName&quot;, &quot;&quot;) == &quot;gpt-5-nano&quot;)">
          - 						<!-- Rate limit for gpt-5-nano: 1500k TPM (deployment capacity is in thousands of TPM) -->
          - 						<llm-token-limit counter-key="@(context.Subscription.Id + &quot;-gpt-5-nano&quot;)" tokens-per-minute="1500000" estimate-prompt-tokens="true" remaining-tokens-variable-name="remainingTokens" remaining-tokens-header-name="x-ratelimit-remaining-tokens" tokens-consumed-variable-name="tokensConsumed" />
          - 					</when>
          - 					<when condition="@(context.Variables.GetValueOrDefault&lt;string&gt;(&quot;deploymentName&quot;, &quot;&quot;) == &quot;gpt-5.1-chat&quot;)">
          - 						<!-- Rate limit for gpt-5.1-chat: 50k TPM (deployment capacity is in thousands of TPM) -->
          - 						<llm-token-limit counter-key="@(context.Subscription.Id + &quot;-gpt-5.1-chat&quot;)" tokens-per-minute="50000" estimate-prompt-tokens="true" remaining-tokens-variable-name="remainingTokens" remaining-tokens-header-name="x-ratelimit-remaining-tokens" tokens-consumed-variable-name="tokensConsumed" />
          - 					</when>
          - 					<when condition="@(context.Variables.GetValueOrDefault&lt;string&gt;(&quot;deploymentName&quot;, &quot;&quot;) == &quot;gpt-5.1-codex-mini&quot;)">
          - 						<!-- Rate limit for gpt-5.1-codex-mini: 100k TPM (deployment capacity is in thousands of TPM) -->
          - 						<llm-token-limit counter-key="@(context.Subscription.Id + &quot;-gpt-5.1-codex-mini&quot;)" tokens-per-minute="100000" estimate-prompt-tokens="true" remaining-tokens-variable-name="remainingTokens" remaining-tokens-header-name="x-ratelimit-remaining-tokens" tokens-consumed-variable-name="tokensConsumed" />
          - 					</when>
          - 					<when condition="@(context.Variables.GetValueOrDefault&lt;string&gt;(&quot;deploymentName&quot;, &quot;&quot;) == &quot;o1&quot;)">
          - 						<!-- Rate limit for o1: 50k TPM (deployment capacity is in thousands of TPM) -->
          - 						<llm-token-limit counter-key="@(context.Subscription.Id + &quot;-o1&quot;)" tokens-per-minute="50000" estimate-prompt-tokens="true" remaining-tokens-variable-name="remainingTokens" remaining-tokens-header-name="x-ratelimit-remaining-tokens" tokens-consumed-variable-name="tokensConsumed" />
          - 					</when>
          - 					<when condition="@(context.Variables.GetValueOrDefault&lt;string&gt;(&quot;deploymentName&quot;, &quot;&quot;) == &quot;o3-mini&quot;)">
          - 						<!-- Rate limit for o3-mini: 50k TPM (deployment capacity is in thousands of TPM) -->
          - 						<llm-token-limit counter-key="@(context.Subscription.Id + &quot;-o3-mini&quot;)" tokens-per-minute="50000" estimate-prompt-tokens="true" remaining-tokens-variable-name="remainingTokens" remaining-tokens-header-name="x-ratelimit-remaining-tokens" tokens-consumed-variable-name="tokensConsumed" />
          - 					</when>
          - 					<when condition="@(context.Variables.GetValueOrDefault&lt;string&gt;(&quot;deploymentName&quot;, &quot;&quot;) == &quot;o4-mini&quot;)">
          - 						<!-- Rate limit for o4-mini: 100k TPM (deployment capacity is in thousands of TPM) -->
          - 						<llm-token-limit counter-key="@(context.Subscription.Id + &quot;-o4-mini&quot;)" tokens-per-minute="100000" estimate-prompt-tokens="true" remaining-tokens-variable-name="remainingTokens" remaining-tokens-header-name="x-ratelimit-remaining-tokens" tokens-consumed-variable-name="tokensConsumed" />
          - 					</when>
          - 					<when condition="@(context.Variables.GetValueOrDefault&lt;string&gt;(&quot;deploymentName&quot;, &quot;&quot;) == &quot;text-embedding-ada-002&quot;)">
          - 						<!-- Rate limit for text-embedding-ada-002: 100k TPM (deployment capacity is in thousands of TPM) -->
          - 						<llm-token-limit counte
(truncated, see workflow logs for complete plan)

---

Updated by CI — plan against test environment (run #216).