feat: add avg cost per page to test results, comparison, and downloads

- Add Avg Cost/Page metric to TestResults key metrics section
- Add Avg Cost/Page row to TestComparison performance metrics table
- Include avgCostPerPage in CSV and JSON downloads
- Computed from existing costBreakdown page counts and totalCost
- Update CHANGELOG.md and test-studio.md docs

Author: Taniya Mathur

CHANGELOG.md

@@ -7,6 +7,8 @@ SPDX-License-Identifier: MIT-0
 
 ### Added
 
+- **Average Cost Per Page Metric** — Test results and test comparison views now display an "Avg Cost/Page" metric, calculated from total cost and page counts in the cost breakdown. Also included in CSV and JSON exports from the comparison view.
+
 - **Prompt Preview** — New "Prompt Preview" tab in the Configuration page lets you preview the actual prompts sent to the LLM for each processing step (Classification, Extraction, Assessment, Summarization). Config-derived placeholders are filled in with real values (class names, cleaned JSON Schema), while document-specific placeholders are shown as highlighted markers. Includes token estimates, copy-to-clipboard, and a substitution details panel showing the exact schema sent to the LLM. Helps optimize document class schemas and prompt templates.
 
 - **IDP CLI `chat` Command & SDK `ChatOperation`** — Interactive Agent Companion Chat from the terminal and programmatic SDK access. Runs the same multi-agent orchestrator as the Web UI locally, with real-time streaming and multi-turn conversation support. Includes Analytics Agent, Error Analyzer Agent, and optionally Code Intelligence Agent (`--enable-code-intelligence`). Available as `idp-cli chat --stack-name <stack>` for interactive use, `--prompt` flag for single-shot scripting, and `client.chat.send_message()` in the Python SDK. See `docs/idp-cli.md#chat`.

docs/test-studio.md

@@ -484,6 +484,7 @@ For full details on configuration versioning, see [configuration-versions.md](co
 - Comprehensive metrics display including:
   - **Test run metadata**: Configuration version, duration, context, file counts
   - **Overall accuracy and confidence metrics**
+  - **Cost metrics**: Total cost and average cost per page
   - **Accuracy breakdown** (precision, recall, F1-score, false alarm rate, false discovery rate)
   - **Field-Level Metrics**: Per-field extraction performance table with columns: Field Name, Accuracy, Precision, Recall, TP, FP, TN, FN
   - **Average Document Split Classification Metrics**:

src/ui/src/components/test-studio/TestComparison.tsx

@@ -302,6 +302,19 @@ const TestComparison = ({ preSelectedTestRunIds = [] }: TestComparisonProps): Re
           run.totalCost !== null && run.totalCost !== undefined ? `$${Number(run.totalCost).toFixed(4)}` : 'N/A',
         ),
       ],
+      [
+        'Avg Cost/Page',
+        ...Object.values(completeTestRuns).map((run) => {
+          if (run.totalCost == null || !run.costBreakdown) return 'N/A';
+          let totalPages = 0;
+          Object.values(run.costBreakdown as Record<string, Record<string, Record<string, unknown>>>).forEach((services) => {
+            Object.values(services).forEach((details) => {
+              if (details.unit === 'pages') totalPages += Number(details.value) || 0;
+            });
+          });
+          return totalPages > 0 ? `$${(Number(run.totalCost) / totalPages).toFixed(4)}` : 'N/A';
+        }),
+      ],
       [
         'Average Accuracy',
         ...Object.values(completeTestRuns).map((run) =>
@@ -624,6 +637,16 @@ const TestComparison = ({ preSelectedTestRunIds = [] }: TestComparisonProps): Re
             completedFiles: testRun.completedFiles,
             failedFiles: testRun.failedFiles,
             totalCost: testRun.totalCost,
+            avgCostPerPage: (() => {
+              if (testRun.totalCost == null || !testRun.costBreakdown) return null;
+              let totalPages = 0;
+              Object.values(testRun.costBreakdown as Record<string, Record<string, Record<string, unknown>>>).forEach((services) => {
+                Object.values(services).forEach((details) => {
+                  if (details.unit === 'pages') totalPages += Number(details.value) || 0;
+                });
+              });
+              return totalPages > 0 ? Number(testRun.totalCost) / totalPages : null;
+            })(),
             averageAccuracy: testRun.overallAccuracy,
             averageConfidence: testRun.averageConfidence,
             averageWeightedOverallScore: (() => {
@@ -818,6 +841,23 @@ const TestComparison = ({ preSelectedTestRunIds = [] }: TestComparisonProps): Re
                     ]),
                   ),
                 },
+                {
+                  metric: 'Avg Cost/Page',
+                  ...Object.fromEntries(
+                    Object.entries(completeTestRuns).map(([testRunId, testRun]) => {
+                      if (testRun.totalCost == null || !testRun.costBreakdown) return [testRunId, 'N/A'];
+                      let totalPages = 0;
+                      Object.values(testRun.costBreakdown as Record<string, Record<string, Record<string, unknown>>>).forEach(
+                        (services) => {
+                          Object.values(services).forEach((details) => {
+                            if (details.unit === 'pages') totalPages += Number(details.value) || 0;
+                          });
+                        },
+                      );
+                      return [testRunId, totalPages > 0 ? `$${(Number(testRun.totalCost) / totalPages).toFixed(4)}` : 'N/A'];
+                    }),
+                  ),
+                },
                 {
                   metric: 'Average Accuracy',
                   ...Object.fromEntries(

src/ui/src/components/test-studio/TestResults.tsx

@@ -751,6 +751,18 @@ const TestResults = ({ testRunId, setSelectedTestRunId }: TestResultsProps): Rea
 
   // eslint-disable-next-line @typescript-eslint/no-explicit-any
   const costBreakdown: any = results.costBreakdown ? parseCostBreakdown(results.costBreakdown as string) : null;
+
+  // Calculate avg cost per page from costBreakdown page counts
+  const avgCostPerPage = (() => {
+    if (results.totalCost == null || !costBreakdown) return null;
+    let totalPages = 0;
+    Object.values(costBreakdown as Record<string, Record<string, Record<string, unknown>>>).forEach((services) => {
+      Object.values(services).forEach((details) => {
+        if (details.unit === 'pages') totalPages += Number(details.value) || 0;
+      });
+    });
+    return totalPages > 0 ? (results.totalCost as number) / totalPages : null;
+  })();
   // eslint-disable-next-line @typescript-eslint/no-explicit-any
   const accuracyBreakdown: any = results.accuracyBreakdown ? parseAccuracyBreakdown(results.accuracyBreakdown as string) : null;
   // eslint-disable-next-line @typescript-eslint/no-explicit-any
@@ -1012,6 +1024,10 @@ const TestResults = ({ testRunId, setSelectedTestRunId }: TestResultsProps): Rea
               {results.totalCost !== null && results.totalCost !== undefined ? `$${(results.totalCost as number).toFixed(4)}` : 'N/A'}
             </Box>
           </Box>
+          <Box>
+            <Box variant="awsui-key-label">Avg Cost/Page</Box>
+            <Box fontSize="heading-l">{avgCostPerPage !== null ? `$${avgCostPerPage.toFixed(4)}` : 'N/A'}</Box>
+          </Box>
           <Box>
             <Box variant="awsui-key-label">Avg Confidence</Box>
             <Box fontSize="heading-l">