feat: Implement validation alignment for Column Management, Run Promp…

src/components/Sidebar.astro

@@ -94,18 +94,18 @@ const isApiTab = activeTab?.tab === 'API';
 
 function inferApiMethod(title: string): { method: string; css: string } | null {
   const t = title.toLowerCase();
+  if (/\b(delete|remove)\b/.test(t)) {
+    return { method: 'DELETE', css: 'api-method-delete' };
+  }
+  if (/\b(update|edit|apply|restore)\b/.test(t)) {
+    return { method: 'PATCH', css: 'api-method-patch' };
+  }
   if (/\b(list|get|retrieve|health|find|export|progress|analytics|agreement|compare|stats|summary|voices|tts)\b/.test(t)) {
     return { method: 'GET', css: 'api-method-get' };
   }
   if (/\b(create|add|generate|execute|submit|assign|bulk|complete|skip|release|pause|unpause|check|upload|start|duplicate|fetch|run|rerun|cancel|clone|merge)\b/.test(t)) {
     return { method: 'POST', css: 'api-method-post' };
   }
-  if (/\b(delete|remove)\b/.test(t)) {
-    return { method: 'DEL', css: 'api-method-delete' };
-  }
-  if (/\b(update|edit|apply|restore)\b/.test(t)) {
-    return { method: 'PATCH', css: 'api-method-patch' };
-  }
   return null;
 }
 ---

src/lib/api-navigation.ts

@@ -61,11 +61,6 @@ export const apiNavigation: ApiNavGroup[] = [
         "title": "Add columns to a scenario",
         "href": "/docs/api/scenarios/addcolumns",
         "method": "POST"
-      },
-      {
-        "title": "Add empty rows to a scenario",
-        "href": "/docs/api/scenarios/addemptyrowstodataset",
-        "method": "POST"
       }
     ]
   },
@@ -187,11 +182,6 @@ export const apiNavigation: ApiNavGroup[] = [
         "href": "/docs/api/run-tests/executeruntest",
         "method": "POST"
       },
-      {
-        "title": "Update test run components",
-        "href": "/docs/api/run-tests/updatetestcomponents",
-        "method": "PATCH"
-      },
       {
         "title": "Get test executions",
         "href": "/docs/api/run-tests/gettestexecutions",
@@ -202,11 +192,6 @@ export const apiNavigation: ApiNavGroup[] = [
         "href": "/docs/api/run-tests/gettestscenarios",
         "method": "GET"
       },
-      {
-        "title": "Get call executions for a test run",
-        "href": "/docs/api/run-tests/getcallexecutions",
-        "method": "GET"
-      },
       {
         "title": "Get evaluation summary",
         "href": "/docs/api/run-tests/getevalsummary",

src/lib/navigation.ts

@@ -1051,7 +1051,6 @@ export const tabNavigation: NavTab[] = [
               { title: 'Delete Scenario', href: '/docs/api/scenarios/deletescenario' },
               { title: 'Add Rows with AI', href: '/docs/api/scenarios/addscenariorowswithai' },
               { title: 'Add Columns', href: '/docs/api/scenarios/addcolumns' },
-              { title: 'Add Empty Rows', href: '/docs/api/scenarios/addemptyrowstodataset' },
             ]
           },
           {
@@ -1092,10 +1091,8 @@ export const tabNavigation: NavTab[] = [
               { title: 'Get Test Run Details', href: '/docs/api/run-tests/getruntestdetails' },
               { title: 'Delete Test Run', href: '/docs/api/run-tests/deleteruntest' },
               { title: 'Execute Run Test', href: '/docs/api/run-tests/executeruntest' },
-              { title: 'Update Components', href: '/docs/api/run-tests/updatetestcomponents' },
               { title: 'Get Test Executions', href: '/docs/api/run-tests/gettestexecutions' },
               { title: 'Get Test Scenarios', href: '/docs/api/run-tests/gettestscenarios' },
-              { title: 'Get Call Executions', href: '/docs/api/run-tests/getcallexecutions' },
               { title: 'Get Eval Summary', href: '/docs/api/run-tests/getevalsummary' },
               { title: 'Compare Eval Summaries', href: '/docs/api/run-tests/compareevalsummaries' },
               { title: 'Add Eval Configs', href: '/docs/api/run-tests/addevalconfigs' },

src/lib/redirects.ts

@@ -48,7 +48,6 @@ export const redirectMap: Record<string, string> = {
   '/api-reference/prompt-workbench/get-prompt-version-by-name': '/docs/api',
   '/api-reference/run-tests/create-a-new-test-run': '/docs/api/run-tests/createruntest',
   '/api-reference/run-tests/execute-a-test-run': '/docs/api/run-tests/executeruntest',
-  '/api-reference/scenarios/add-empty-rows-to-a-scenario': '/docs/api/scenarios/addemptyrowstodataset',
   '/api-reference/scenarios/add-rows-to-a-scenario-using-ai': '/docs/api/scenarios/addscenariorowswithai',
   '/api-reference/scenarios/edit-a-scenario': '/docs/api/scenarios/editscenario',
   '/api-reference/scenarios/generate-or-create-a-scenario': '/docs/api/scenarios/createscenario',

src/pages/docs/api/run-tests/addevalconfigs.mdx

@@ -1,6 +1,6 @@
 ---
-title: "Add Eval Configs to Run Test — API"
-description: "Add one or more evaluation configurations to an existing test run. Specify template, name, config mapping, model, and error localizer per config. Returns created eval config objects."
+title: "Add evaluation configurations"
+description: "Adds evaluation configurations to a test run."
 ---
 
 <ApiPlayground
@@ -10,8 +10,25 @@ description: "Add one or more evaluation configurations to an existing test run.
   parameters={[
     {"name": "run_test_id", "in": "path", "required": true, "description": "UUID of the test run to add evaluation configurations to.", "type": "string"}
   ]}
-  requestBody={{"evaluations_config": [{"template_id": "your-template-id", "name": "My Eval Config", "config": {}, "mapping": {}, "error_localizer": false, "model": "turing_large"}]}}
-  responseExample={{"message": "Evaluation configs added successfully", "created_eval_configs": [{"id": "uuid", "name": "My Eval Config", "config": {}, "mapping": {}, "filters": {}, "error_localizer": false, "model": "turing_large", "status": "pending", "template_id": "your-template-id"}], "run_test_id": "uuid"}}
+  requestBody={{"evaluations_config": [{"template_id": "your-template-id", "name": "My Eval Config", "config": {}, "mapping": {}, "filters": {}, "error_localizer": false, "model": "turing_large"}]}}
+  responseExample={{
+    message: "Successfully added 1 evaluation config(s) to run test",
+    created_eval_configs: [
+      {
+        id: "ec1b2c3d-e5f6-7890-abcd-ef1234567890",
+        name: "My Eval Config",
+        config: {},
+        mapping: {},
+        filters: {},
+        error_localizer: false,
+        model: "turing_large",
+        status: null,
+        eval_group: null,
+        template_id: "your-template-uuid"
+      }
+    ],
+    run_test_id: "f7a8b9c0-d1e2-3456-789a-bcdef0123456"
+  }}
   responseStatus={201}
   responseStatusText="Created"
 />
@@ -33,65 +50,59 @@ description: "Add one or more evaluation configurations to an existing test run.
 
 <ApiSection title="Request body">
   <ParamField body="evaluations_config" type="array of objects" required>
-    Array of evaluation configuration objects.
+    Array of evaluation configuration objects. Each object supports the following fields:
 
-    <ApiCollapsible title="Show 7 properties">
-      <ResponseField name="template_id" type="string" required>
-        UUID of the evaluation template to use.
-      </ResponseField>
+    - **`template_id`** (string, UUID, required) -- UUID of the evaluation template to use.
 
-      <ResponseField name="name" type="string" required>
-        Name for this evaluation configuration. Must be unique within the test run.
-      </ResponseField>
+    - **`name`** (string, optional) -- Name for this evaluation configuration. Defaults to `Eval-<template_id>` if omitted. Must be unique within the test run.
 
-      <ResponseField name="config" type="object">
-        Template-specific configuration parameters.
-      </ResponseField>
+    - **`config`** (object, optional) -- Template-specific configuration parameters.
 
-      <ResponseField name="mapping" type="object">
-        Maps test execution data fields to the evaluation template's expected inputs.
-      </ResponseField>
+    - **`mapping`** (object, optional) -- Maps test execution data fields to the evaluation template's expected inputs.
 
-      <ResponseField name="filters" type="object">
-        Filter criteria to restrict which test results are evaluated.
-      </ResponseField>
+    - **`filters`** (object, optional) -- Filter criteria to restrict which test results are evaluated.
 
-      <ResponseField name="error_localizer" type="boolean">
-        Enables granular error localization on evaluation failures. Defaults to `false`.
-      </ResponseField>
+    - **`error_localizer`** (boolean, optional) -- Enables granular error localization on evaluation failures. Defaults to `false`.
 
-      <ResponseField name="model" type="string">
-        Model to use for running this evaluation.
-      </ResponseField>
-    </ApiCollapsible>
+    - **`model`** (string, optional) -- Model to use for running this evaluation.
   </ParamField>
 </ApiSection>
 
 <ApiSection title="Response" status={201} statusText="Created">
-  <ResponseField name="message" type="string">Confirmation of successful addition.</ResponseField>
-
+  <ResponseField name="message" type="string">Confirmation message indicating how many evaluation configs were added.</ResponseField>
   <ResponseField name="created_eval_configs" type="array of objects">
-    Array of the newly created evaluation config objects. Each object contains: `id`, `name`, `config`, `mapping`, `filters`, `error_localizer`, `model`, `status`, `template_id`.
-  </ResponseField>
-
-  <ResponseField name="run_test_id" type="string">UUID of the test run the configs were added to.</ResponseField>
-
-  <ResponseField name="warnings" type="array of strings" optional>
-    Present only when some configs in the request failed to create while others succeeded. Lists per-item error messages.
+    Array of created evaluation configuration objects. Each object contains: `id`, `name`, `config`, `mapping`, `filters`, `error_localizer`, `model`, `status`, `eval_group`, and `template_id`.
   </ResponseField>
+  <ResponseField name="run_test_id" type="string">UUID of the parent test run.</ResponseField>
+  <ResponseField name="warnings" type="array of strings">Non-fatal issues encountered while processing individual configs. Only present if partial failures occurred.</ResponseField>
 </ApiSection>
 
 <ApiSection title="Errors">
   <ParamField name="400" type="Bad Request">
-    Invalid or missing fields such as a non-existent `template_id`, duplicate `name`, or malformed `config`/`mapping`.
+    Validation error. Common causes: empty `evaluations_config`, duplicate `name` within request, name already exists in test run, non-existent `template_id`.
+    ```json
+    {
+      "evaluations_config": ["Duplicate eval name 'My Eval Config' found in the request. Each evaluation config must have a unique name."]
+    }
+    ```
+    Or for existing name conflict:
+    ```json
+    {"error": "An evaluation config with the name 'My Eval Config' already exists in this run test. Please use a different name."}
+    ```
   </ParamField>
   <ParamField name="401" type="Unauthorized">
     Missing or invalid `X-Api-Key` or `X-Secret-Key` headers.
   </ParamField>
   <ParamField name="404" type="Not Found">
     No test run found with the specified `run_test_id`.
+    ```json
+    {"detail": "No RunTest matches the given query."}
+    ```
   </ParamField>
   <ParamField name="500" type="Internal Server Error">
     Unexpected server error.
+    ```json
+    {"error": "Failed to add evaluation configs: <message>"}
+    ```
   </ParamField>
 </ApiSection>

src/pages/docs/api/run-tests/compareevalsummaries.mdx

@@ -11,7 +11,10 @@ description: "Compare evaluation summaries side-by-side across multiple test exe
     {"name": "run_test_id", "in": "path", "required": true, "description": "UUID of the test run containing the executions to compare.", "type": "string"},
     {"name": "execution_ids", "in": "query", "required": false, "description": "JSON-encoded array of test execution UUIDs to compare.", "type": "string"}
   ]}
-  responseExample={{"execution-uuid-1": {"evaluations": [{"name": "Tone Check", "average_score": 0.85}]}, "execution-uuid-2": {"evaluations": [{"name": "Tone Check", "average_score": 0.92}]}}}
+  responseExample={{
+    "execution-uuid-1": [{"name": "Tone Check", "average_score": 0.85, "total_runs": 10, "passed": 8, "failed": 2}],
+    "execution-uuid-2": [{"name": "Tone Check", "average_score": 0.92, "total_runs": 10, "passed": 9, "failed": 1}]
+  }}
   responseStatus={200}
   responseStatusText="OK"
 />
@@ -33,25 +36,47 @@ description: "Compare evaluation summaries side-by-side across multiple test exe
 
 <ApiSection title="Query parameters">
   <ParamField query="execution_ids" type="string" required>
-    JSON-encoded array of test execution UUIDs to compare. Must be URL-encoded.
+    JSON-encoded array of test execution UUIDs to compare. Must be URL-encoded. Example: `["uuid1","uuid2"]`.
   </ParamField>
 </ApiSection>
 
 <ApiSection title="Response" status={200} statusText="OK">
-  <ResponseField name="comparison" type="object">Dictionary keyed by execution ID, each mapping to its evaluation summary metrics.</ResponseField>
+  <ResponseField name="(execution_id)" type="object">
+    Dictionary keyed by execution UUID. Each value is an array of evaluation summary objects for that execution.
+  </ResponseField>
+  <ApiCollapsible title="Show evaluation summary object properties">
+    <ResponseField name="name" type="string">Name of the evaluation configuration.</ResponseField>
+    <ResponseField name="average_score" type="number">Average score across all evaluated calls.</ResponseField>
+    <ResponseField name="total_runs" type="integer">Total evaluation runs for this config.</ResponseField>
+    <ResponseField name="passed" type="integer">Number of passing evaluations.</ResponseField>
+    <ResponseField name="failed" type="integer">Number of failing evaluations.</ResponseField>
+  </ApiCollapsible>
 </ApiSection>
 
 <ApiSection title="Errors">
   <ParamField name="400" type="Bad Request">
-    Missing, malformed, or invalid `execution_ids` parameter.
+    Missing, malformed, or empty `execution_ids` parameter.
+    ```json
+    {"execution_ids": ["execution_ids must be valid JSON"]}
+    ```
+    Or when empty:
+    ```json
+    {"execution_ids": ["execution_ids list is required"]}
+    ```
   </ParamField>
   <ParamField name="401" type="Unauthorized">
     Missing or invalid `X-Api-Key` or `X-Secret-Key` headers.
   </ParamField>
   <ParamField name="404" type="Not Found">
     No test run found with the specified `run_test_id`.
+    ```json
+    {"error": "RunTest not found."}
+    ```
   </ParamField>
   <ParamField name="500" type="Internal Server Error">
-    Unexpected server error. Retry later or contact support.
+    Unexpected server error.
+    ```json
+    {"error": "Unable to fetch eval summary"}
+    ```
   </ParamField>
 </ApiSection>