diff --git a/packages/cli/src/ui/components/ModelStatsDisplay.test.tsx b/packages/cli/src/ui/components/ModelStatsDisplay.test.tsx
index d233d3b3850..619bdd774c9 100644
--- a/packages/cli/src/ui/components/ModelStatsDisplay.test.tsx
+++ b/packages/cli/src/ui/components/ModelStatsDisplay.test.tsx
@@ -9,7 +9,7 @@ import { describe, it, expect, vi, beforeAll, afterAll } from 'vitest';
 import { ModelStatsDisplay } from './ModelStatsDisplay.js';
 import * as SessionContext from '../contexts/SessionContext.js';
 import type { SessionMetrics } from '../contexts/SessionContext.js';
-import { ToolCallDecision } from '@google/gemini-cli-core';
+import { ToolCallDecision, LlmRole } from '@google/gemini-cli-core';
 
 // Mock the context to provide controlled data for testing
 vi.mock('../contexts/SessionContext.js', async (importOriginal) => {
@@ -95,6 +95,7 @@ describe('<ModelStatsDisplay />', () => {
             thoughts: 0,
             tool: 0,
           },
+          roles: {},
         },
       },
       tools: {
@@ -137,6 +138,7 @@ describe('<ModelStatsDisplay />', () => {
             thoughts: 2,
             tool: 0,
           },
+          roles: {},
         },
         'gemini-2.5-flash': {
           api: { totalRequests: 1, totalErrors: 0, totalLatencyMs: 50 },
@@ -149,6 +151,7 @@ describe('<ModelStatsDisplay />', () => {
             thoughts: 0,
             tool: 3,
           },
+          roles: {},
         },
       },
       tools: {
@@ -191,6 +194,7 @@ describe('<ModelStatsDisplay />', () => {
             thoughts: 10,
             tool: 5,
           },
+          roles: {},
         },
         'gemini-2.5-flash': {
           api: { totalRequests: 20, totalErrors: 2, totalLatencyMs: 500 },
@@ -203,6 +207,7 @@ describe('<ModelStatsDisplay />', () => {
             thoughts: 20,
             tool: 10,
           },
+          roles: {},
         },
       },
       tools: {
@@ -248,6 +253,7 @@ describe('<ModelStatsDisplay />', () => {
             thoughts: 111111111,
             tool: 222222222,
           },
+          roles: {},
         },
       },
       tools: {
@@ -286,6 +292,7 @@ describe('<ModelStatsDisplay />', () => {
             thoughts: 2,
             tool: 1,
           },
+          roles: {},
         },
       },
       tools: {
@@ -328,6 +335,7 @@ describe('<ModelStatsDisplay />', () => {
               thoughts: 100,
               tool: 50,
             },
+            roles: {},
           },
           'gemini-3-flash-preview': {
             api: { totalRequests: 20, totalErrors: 0, totalLatencyMs: 1000 },
@@ -340,6 +348,7 @@ describe('<ModelStatsDisplay />', () => {
               thoughts: 200,
               tool: 100,
             },
+            roles: {},
           },
         },
         tools: {
@@ -366,6 +375,120 @@ describe('<ModelStatsDisplay />', () => {
     const output = lastFrame();
     expect(output).toContain('gemini-3-pro-');
     expect(output).toContain('gemini-3-flash-');
+  });
+
+  it('should display role breakdown correctly', () => {
+    const { lastFrame } = renderWithMockedStats({
+      models: {
+        'gemini-2.5-pro': {
+          api: { totalRequests: 2, totalErrors: 0, totalLatencyMs: 200 },
+          tokens: {
+            input: 20,
+            prompt: 30,
+            candidates: 40,
+            total: 70,
+            cached: 10,
+            thoughts: 0,
+            tool: 0,
+          },
+          roles: {
+            [LlmRole.MAIN]: {
+              totalRequests: 1,
+              totalErrors: 0,
+              totalLatencyMs: 100,
+              tokens: {
+                input: 10,
+                prompt: 15,
+                candidates: 20,
+                total: 35,
+                cached: 5,
+                thoughts: 0,
+                tool: 0,
+              },
+            },
+          },
+        },
+      },
+      tools: {
+        totalCalls: 0,
+        totalSuccess: 0,
+        totalFail: 0,
+        totalDurationMs: 0,
+        totalDecisions: {
+          accept: 0,
+          reject: 0,
+          modify: 0,
+          [ToolCallDecision.AUTO_ACCEPT]: 0,
+        },
+        byName: {},
+      },
+      files: {
+        totalLinesAdded: 0,
+        totalLinesRemoved: 0,
+      },
+    });
+
+    const output = lastFrame();
+    expect(output).toContain('main');
+    expect(output).toContain('Input');
+    expect(output).toContain('Output');
+    expect(output).toContain('Cache Reads');
     expect(output).toMatchSnapshot();
   });
+
+  it('should handle long metric names with truncation', () => {
+    const longRoleName =
+      'this_is_a_very_long_role_name_that_should_be_truncated' as LlmRole;
+    const { lastFrame } = renderWithMockedStats({
+      models: {
+        'gemini-2.5-pro': {
+          api: { totalRequests: 1, totalErrors: 0, totalLatencyMs: 100 },
+          tokens: {
+            input: 10,
+            prompt: 10,
+            candidates: 20,
+            total: 30,
+            cached: 0,
+            thoughts: 0,
+            tool: 0,
+          },
+          roles: {
+            [longRoleName]: {
+              totalRequests: 1,
+              totalErrors: 0,
+              totalLatencyMs: 100,
+              tokens: {
+                input: 10,
+                prompt: 10,
+                candidates: 20,
+                total: 30,
+                cached: 0,
+                thoughts: 0,
+                tool: 0,
+              },
+            },
+          },
+        },
+      },
+      tools: {
+        totalCalls: 0,
+        totalSuccess: 0,
+        totalFail: 0,
+        totalDurationMs: 0,
+        totalDecisions: {
+          accept: 0,
+          reject: 0,
+          modify: 0,
+          [ToolCallDecision.AUTO_ACCEPT]: 0,
+        },
+        byName: {},
+      },
+      files: {
+        totalLinesAdded: 0,
+        totalLinesRemoved: 0,
+      },
+    });
+
+    expect(lastFrame()).toMatchSnapshot();
+  });
 });
diff --git a/packages/cli/src/ui/components/ModelStatsDisplay.tsx b/packages/cli/src/ui/components/ModelStatsDisplay.tsx
index f765bcede3c..ae7e7e8f2f7 100644
--- a/packages/cli/src/ui/components/ModelStatsDisplay.tsx
+++ b/packages/cli/src/ui/components/ModelStatsDisplay.tsx
@@ -13,17 +13,24 @@ import {
   calculateCacheHitRate,
   calculateErrorRate,
 } from '../utils/computeStats.js';
-import { useSessionStats } from '../contexts/SessionContext.js';
+import {
+  useSessionStats,
+  type ModelMetrics,
+} from '../contexts/SessionContext.js';
 import { Table, type Column } from './Table.js';
+import { LlmRole } from '@google/gemini-cli-core';
 
 interface StatRowData {
   metric: string;
   isSection?: boolean;
-  isSubtle?: boolean;
+  indentLevel?: number;
   // Dynamic keys for model values
-  [key: string]: string | React.ReactNode | boolean | undefined;
+  [key: string]: string | React.ReactNode | boolean | undefined | number;
+  color?: string;
 }
 
+type RoleMetrics = NonNullable<NonNullable<ModelMetrics['roles']>[LlmRole]>;
+
 export const ModelStatsDisplay: React.FC = () => {
   const { stats } = useSessionStats();
   const { models } = stats.metrics;
@@ -56,132 +63,187 @@ export const ModelStatsDisplay: React.FC = () => {
     ([, metrics]) => metrics.tokens.cached > 0,
   );
 
-  // Helper to create a row with values for each model
-  const createRow = (
+  const allRoles = Array.from(
+    new Set(
+      activeModels.flatMap(([, metrics]) => Object.keys(metrics.roles || {})),
+    ),
+  ).sort((a, b) => {
+    if (a === LlmRole.MAIN) return -1;
+    if (b === LlmRole.MAIN) return 1;
+    return a.localeCompare(b);
+  }) as LlmRole[];
+
+  const rows: StatRowData[] = [];
+
+  // Helper to add a row for global model metrics
+  const addRow = (
     metric: string,
-    getValue: (
-      metrics: (typeof activeModels)[0][1],
-    ) => string | React.ReactNode,
-    options: { isSection?: boolean; isSubtle?: boolean } = {},
-  ): StatRowData => {
+    getValue: (metrics: ModelMetrics) => string | React.ReactNode,
+    options: {
+      isSection?: boolean;
+      indentLevel?: number;
+    } = {},
+  ) => {
+    const { indentLevel = 0 } = options;
     const row: StatRowData = {
       metric,
       isSection: options.isSection,
-      isSubtle: options.isSubtle,
+      indentLevel,
     };
     activeModels.forEach(([name, metrics]) => {
       row[name] = getValue(metrics);
     });
-    return row;
+    rows.push(row);
   };
 
-  const rows: StatRowData[] = [
-    // API Section
-    { metric: 'API', isSection: true },
-    createRow('Requests', (m) => m.api.totalRequests.toLocaleString()),
-    createRow('Errors', (m) => {
-      const errorRate = calculateErrorRate(m);
-      return (
-        <Text
-          color={
-            m.api.totalErrors > 0 ? theme.status.error : theme.text.primary
-          }
-        >
-          {m.api.totalErrors.toLocaleString()} ({errorRate.toFixed(1)}%)
-        </Text>
-      );
-    }),
-    createRow('Avg Latency', (m) => formatDuration(calculateAverageLatency(m))),
+  // API Section
+  addRow('API', () => '', { isSection: true });
+  addRow('Requests', (m) => m.api.totalRequests.toLocaleString());
+  addRow('Errors', (m) => {
+    const errorRate = calculateErrorRate(m);
+    return (
+      <Text
+        color={m.api.totalErrors > 0 ? theme.status.error : theme.text.primary}
+      >
+        {m.api.totalErrors.toLocaleString()} ({errorRate.toFixed(1)}%)
+      </Text>
+    );
+  });
+  addRow('Avg Latency', (m) => formatDuration(calculateAverageLatency(m)));
 
-    // Spacer
-    { metric: '' },
+  // Spacer
+  rows.push({ metric: ' ' });
 
-    // Tokens Section
-    { metric: 'Tokens', isSection: true },
-    createRow('Total', (m) => (
-      <Text color={theme.text.secondary}>
-        {m.tokens.total.toLocaleString()}
-      </Text>
-    )),
-    createRow(
-      'Input',
-      (m) => (
-        <Text color={theme.text.primary}>
-          {m.tokens.input.toLocaleString()}
-        </Text>
-      ),
-      { isSubtle: true },
+  // Tokens Section
+  addRow('Tokens', () => '', { isSection: true });
+  addRow('Total', (m) => (
+    <Text color={theme.text.secondary}>{m.tokens.total.toLocaleString()}</Text>
+  ));
+  addRow(
+    'Input',
+    (m) => (
+      <Text color={theme.text.primary}>{m.tokens.input.toLocaleString()}</Text>
     ),
-  ];
+    { indentLevel: 1 },
+  );
 
   if (hasCached) {
-    rows.push(
-      createRow(
-        'Cache Reads',
-        (m) => {
-          const cacheHitRate = calculateCacheHitRate(m);
-          return (
-            <Text color={theme.text.secondary}>
-              {m.tokens.cached.toLocaleString()} ({cacheHitRate.toFixed(1)}%)
-            </Text>
-          );
-        },
-        { isSubtle: true },
-      ),
+    addRow(
+      'Cache Reads',
+      (m) => {
+        const cacheHitRate = calculateCacheHitRate(m);
+        return (
+          <Text color={theme.text.secondary}>
+            {m.tokens.cached.toLocaleString()} ({cacheHitRate.toFixed(1)}%)
+          </Text>
+        );
+      },
+      { indentLevel: 1 },
     );
   }
 
   if (hasThoughts) {
-    rows.push(
-      createRow(
-        'Thoughts',
-        (m) => (
-          <Text color={theme.text.primary}>
-            {m.tokens.thoughts.toLocaleString()}
-          </Text>
-        ),
-        { isSubtle: true },
+    addRow(
+      'Thoughts',
+      (m) => (
+        <Text color={theme.text.primary}>
+          {m.tokens.thoughts.toLocaleString()}
+        </Text>
       ),
+      { indentLevel: 1 },
     );
   }
 
   if (hasTool) {
-    rows.push(
-      createRow(
-        'Tool',
-        (m) => (
-          <Text color={theme.text.primary}>
-            {m.tokens.tool.toLocaleString()}
-          </Text>
-        ),
-        { isSubtle: true },
+    addRow(
+      'Tool',
+      (m) => (
+        <Text color={theme.text.primary}>{m.tokens.tool.toLocaleString()}</Text>
       ),
+      { indentLevel: 1 },
     );
   }
 
-  rows.push(
-    createRow(
-      'Output',
-      (m) => (
-        <Text color={theme.text.primary}>
-          {m.tokens.candidates.toLocaleString()}
-        </Text>
-      ),
-      { isSubtle: true },
+  addRow(
+    'Output',
+    (m) => (
+      <Text color={theme.text.primary}>
+        {m.tokens.candidates.toLocaleString()}
+      </Text>
     ),
+    { indentLevel: 1 },
   );
 
+  // Roles Section
+  if (allRoles.length > 0) {
+    // Spacer
+    rows.push({ metric: ' ' });
+    rows.push({ metric: 'Roles', isSection: true });
+
+    allRoles.forEach((role) => {
+      // Role Header Row
+      const roleHeaderRow: StatRowData = {
+        metric: role,
+        indentLevel: 1,
+        color: theme.text.accent,
+      };
+      // We don't populate model values for the role header row
+      rows.push(roleHeaderRow);
+
+      const addRoleMetric = (
+        metric: string,
+        getValue: (r: RoleMetrics) => string | React.ReactNode,
+      ) => {
+        const row: StatRowData = {
+          metric,
+          indentLevel: 2,
+        };
+        activeModels.forEach(([name, metrics]) => {
+          const roleMetrics = metrics.roles?.[role];
+          if (roleMetrics) {
+            row[name] = getValue(roleMetrics);
+          } else {
+            row[name] = <Text color={theme.text.secondary}>-</Text>;
+          }
+        });
+        rows.push(row);
+      };
+
+      addRoleMetric('Requests', (r) => r.totalRequests.toLocaleString());
+      addRoleMetric('Input', (r) => (
+        <Text color={theme.text.primary}>
+          {r.tokens.input.toLocaleString()}
+        </Text>
+      ));
+      addRoleMetric('Output', (r) => (
+        <Text color={theme.text.primary}>
+          {r.tokens.candidates.toLocaleString()}
+        </Text>
+      ));
+      addRoleMetric('Cache Reads', (r) => (
+        <Text color={theme.text.secondary}>
+          {r.tokens.cached.toLocaleString()}
+        </Text>
+      ));
+    });
+  }
+
   const columns: Array<Column<StatRowData>> = [
     {
       key: 'metric',
       header: 'Metric',
-      width: 28,
+      width: 36,
       renderCell: (row) => (
         <Text
           bold={row.isSection}
-          color={row.isSection ? theme.text.primary : theme.text.link}
+          color={
+            row.color ?? (row.isSection ? theme.text.primary : theme.text.link)
+          }
+          wrap="truncate-end"
         >
-          {row.isSubtle ? `  ↳ ${row.metric}` : row.metric}
+          {row.indentLevel
+            ? `${'  '.repeat(row.indentLevel)}↳ ${row.metric}`
+            : row.metric}
         </Text>
       ),
     },
@@ -191,7 +253,7 @@ export const ModelStatsDisplay: React.FC = () => {
       flexGrow: 1,
       renderCell: (row: StatRowData) => {
         // Don't render anything for section headers in model columns
-        if (row.isSection) return null;
+        if (row.isSection && !row[name]) return null;
         const val = row[name];
         if (val === undefined || val === null) return null;
         if (typeof val === 'string' || typeof val === 'number') {
diff --git a/packages/cli/src/ui/components/SessionSummaryDisplay.test.tsx b/packages/cli/src/ui/components/SessionSummaryDisplay.test.tsx
index 7476fa08d4e..c5ab844135a 100644
--- a/packages/cli/src/ui/components/SessionSummaryDisplay.test.tsx
+++ b/packages/cli/src/ui/components/SessionSummaryDisplay.test.tsx
@@ -53,6 +53,7 @@ describe('<SessionSummaryDisplay />', () => {
             thoughts: 300,
             tool: 200,
           },
+          roles: {},
         },
       },
       tools: {
diff --git a/packages/cli/src/ui/components/StatsDisplay.test.tsx b/packages/cli/src/ui/components/StatsDisplay.test.tsx
index eb34fa6bd27..a002cd0b590 100644
--- a/packages/cli/src/ui/components/StatsDisplay.test.tsx
+++ b/packages/cli/src/ui/components/StatsDisplay.test.tsx
@@ -11,6 +11,7 @@ import * as SessionContext from '../contexts/SessionContext.js';
 import type { SessionMetrics } from '../contexts/SessionContext.js';
 import {
   ToolCallDecision,
+  LlmRole,
   type RetrieveUserQuotaResponse,
 } from '@google/gemini-cli-core';
 
@@ -93,6 +94,7 @@ describe('<StatsDisplay />', () => {
             thoughts: 100,
             tool: 50,
           },
+          roles: {},
         },
         'gemini-2.5-flash': {
           api: { totalRequests: 5, totalErrors: 1, totalLatencyMs: 4500 },
@@ -105,6 +107,7 @@ describe('<StatsDisplay />', () => {
             thoughts: 2000,
             tool: 1000,
           },
+          roles: {},
         },
       },
     });
@@ -133,6 +136,7 @@ describe('<StatsDisplay />', () => {
             thoughts: 0,
             tool: 0,
           },
+          roles: {},
         },
       },
       tools: {
@@ -227,6 +231,7 @@ describe('<StatsDisplay />', () => {
               thoughts: 0,
               tool: 0,
             },
+            roles: {},
           },
         },
       });
@@ -410,6 +415,7 @@ describe('<StatsDisplay />', () => {
               thoughts: 0,
               tool: 0,
             },
+            roles: {},
           },
         },
       });
@@ -498,4 +504,60 @@ describe('<StatsDisplay />', () => {
       vi.useRealTimers();
     });
   });
+
+  it('renders roles correctly', () => {
+    const metrics = createTestMetrics({
+      models: {
+        'gemini-2.5-pro': {
+          api: { totalRequests: 3, totalErrors: 0, totalLatencyMs: 15000 },
+          tokens: {
+            input: 500,
+            prompt: 1000,
+            candidates: 2000,
+            total: 43234,
+            cached: 500,
+            thoughts: 100,
+            tool: 50,
+          },
+          roles: {
+            [LlmRole.MAIN]: {
+              totalRequests: 1,
+              totalErrors: 0,
+              totalLatencyMs: 1000,
+              tokens: {
+                input: 100,
+                prompt: 0,
+                candidates: 0,
+                total: 100,
+                cached: 0,
+                thoughts: 0,
+                tool: 0,
+              },
+            },
+            [LlmRole.UTILITY_TOOL]: {
+              totalRequests: 2,
+              totalErrors: 0,
+              totalLatencyMs: 14000,
+              tokens: {
+                input: 400,
+                prompt: 1000,
+                candidates: 2000,
+                total: 3400,
+                cached: 500,
+                thoughts: 100,
+                tool: 50,
+              },
+            },
+          },
+        },
+      },
+    });
+
+    const { lastFrame } = renderWithMockedStats(metrics);
+    const output = lastFrame();
+
+    expect(output).toContain('↳ ' + LlmRole.MAIN);
+    expect(output).toContain('↳ ' + LlmRole.UTILITY_TOOL);
+    expect(output).toMatchSnapshot();
+  });
 });
diff --git a/packages/cli/src/ui/components/StatsDisplay.tsx b/packages/cli/src/ui/components/StatsDisplay.tsx
index 8e89f54a6dd..175063347fd 100644
--- a/packages/cli/src/ui/components/StatsDisplay.tsx
+++ b/packages/cli/src/ui/components/StatsDisplay.tsx
@@ -95,6 +95,7 @@ const buildModelRows = (
       outputTokens: metrics.tokens.candidates.toLocaleString(),
       bucket: quotas?.buckets?.find((b) => b.modelId === modelName),
       isActive: true,
+      roles: metrics.roles,
     };
   });
 
@@ -116,6 +117,7 @@ const buildModelRows = (
         outputTokens: '-',
         bucket,
         isActive: false,
+        roles: undefined,
       })) || [];
 
   return [...activeRows, ...quotaRows];
@@ -159,7 +161,7 @@ const ModelUsageTable: React.FC<{
 
   const showQuotaColumn = !!quotas && rows.some((row) => !!row.bucket);
 
-  const nameWidth = 25;
+  const nameWidth = 38;
   const requestsWidth = 7;
   const uncachedWidth = 15;
   const cachedWidth = 14;
@@ -182,7 +184,7 @@ const ModelUsageTable: React.FC<{
     <Box flexDirection="column" marginTop={1}>
       {/* Header */}
       <Box alignItems="flex-end">
-        <Box width={nameWidth}>
+        <Box width={nameWidth} flexShrink={1}>
           <Text bold color={theme.text.primary} wrap="truncate-end">
             Model Usage
           </Text>
@@ -253,81 +255,135 @@ const ModelUsageTable: React.FC<{
         borderRight={false}
         borderColor={theme.border.default}
         width={totalWidth}
+        flexShrink={1}
       ></Box>
 
       {rows.map((row) => (
-        <Box key={row.key}>
-          <Box width={nameWidth}>
-            <Text color={theme.text.primary} wrap="truncate-end">
-              {row.modelName}
-            </Text>
-          </Box>
-          <Box
-            width={requestsWidth}
-            flexDirection="column"
-            alignItems="flex-end"
-            flexShrink={0}
-          >
-            <Text
-              color={row.isActive ? theme.text.primary : theme.text.secondary}
+        <Box key={row.key} flexDirection="column">
+          <Box flexDirection="row">
+            <Box width={nameWidth} flexShrink={1}>
+              <Text color={theme.text.primary} wrap="truncate-end">
+                {row.modelName}
+              </Text>
+            </Box>
+            <Box
+              width={requestsWidth}
+              flexDirection="column"
+              alignItems="flex-end"
+              flexShrink={0}
             >
-              {row.requests}
-            </Text>
-          </Box>
-          {!showQuotaColumn && (
-            <>
-              <Box
-                width={uncachedWidth}
-                flexDirection="column"
-                alignItems="flex-end"
-                flexShrink={0}
+              <Text
+                color={row.isActive ? theme.text.primary : theme.text.secondary}
               >
-                <Text
-                  color={
-                    row.isActive ? theme.text.primary : theme.text.secondary
-                  }
+                {row.requests}
+              </Text>
+            </Box>
+            {!showQuotaColumn && (
+              <>
+                <Box
+                  width={uncachedWidth}
+                  flexDirection="column"
+                  alignItems="flex-end"
+                  flexShrink={0}
                 >
-                  {row.inputTokens}
-                </Text>
-              </Box>
-              <Box
-                width={cachedWidth}
-                flexDirection="column"
-                alignItems="flex-end"
-                flexShrink={0}
-              >
-                <Text color={theme.text.secondary}>{row.cachedTokens}</Text>
-              </Box>
-              <Box
-                width={outputTokensWidth}
-                flexDirection="column"
-                alignItems="flex-end"
-                flexShrink={0}
-              >
-                <Text
-                  color={
-                    row.isActive ? theme.text.primary : theme.text.secondary
-                  }
+                  <Text
+                    color={
+                      row.isActive ? theme.text.primary : theme.text.secondary
+                    }
+                  >
+                    {row.inputTokens}
+                  </Text>
+                </Box>
+                <Box
+                  width={cachedWidth}
+                  flexDirection="column"
+                  alignItems="flex-end"
+                  flexShrink={0}
                 >
-                  {row.outputTokens}
-                </Text>
-              </Box>
-            </>
-          )}
-          <Box
-            width={usageLimitWidth}
-            flexDirection="column"
-            alignItems="flex-end"
-          >
-            {row.bucket &&
-              row.bucket.remainingFraction != null &&
-              row.bucket.resetTime && (
-                <Text color={theme.text.secondary} wrap="truncate-end">
-                  {(row.bucket.remainingFraction * 100).toFixed(1)}%{' '}
-                  {formatResetTime(row.bucket.resetTime)}
-                </Text>
-              )}
+                  <Text color={theme.text.secondary}>{row.cachedTokens}</Text>
+                </Box>
+                <Box
+                  width={outputTokensWidth}
+                  flexDirection="column"
+                  alignItems="flex-end"
+                  flexShrink={0}
+                >
+                  <Text
+                    color={
+                      row.isActive ? theme.text.primary : theme.text.secondary
+                    }
+                  >
+                    {row.outputTokens}
+                  </Text>
+                </Box>
+              </>
+            )}
+            <Box
+              width={usageLimitWidth}
+              flexDirection="column"
+              alignItems="flex-end"
+            >
+              {row.bucket &&
+                row.bucket.remainingFraction != null &&
+                row.bucket.resetTime && (
+                  <Text color={theme.text.secondary} wrap="truncate-end">
+                    {(row.bucket.remainingFraction * 100).toFixed(1)}%{' '}
+                    {formatResetTime(row.bucket.resetTime)}
+                  </Text>
+                )}
+            </Box>
           </Box>
+          {!showQuotaColumn &&
+            row.roles &&
+            Object.entries(row.roles).map(([role, metrics]) => (
+              <Box key={`${row.key}-${role}`} flexDirection="row">
+                <Box width={nameWidth} paddingLeft={2} flexShrink={1}>
+                  <Text color={theme.text.accent} wrap="truncate-end">
+                    {'↳ ' + role}
+                  </Text>
+                </Box>
+                <Box
+                  width={requestsWidth}
+                  flexDirection="column"
+                  alignItems="flex-end"
+                  flexShrink={0}
+                >
+                  <Text color={theme.text.secondary}>
+                    {metrics?.totalRequests}
+                  </Text>
+                </Box>
+                <Box
+                  width={uncachedWidth}
+                  flexDirection="column"
+                  alignItems="flex-end"
+                  flexShrink={0}
+                >
+                  <Text color={theme.text.secondary}>
+                    {metrics?.tokens.input.toLocaleString()}
+                  </Text>
+                </Box>
+                <Box
+                  width={cachedWidth}
+                  flexDirection="column"
+                  alignItems="flex-end"
+                  flexShrink={0}
+                >
+                  <Text color={theme.text.secondary}>
+                    {metrics?.tokens.cached.toLocaleString()}
+                  </Text>
+                </Box>
+                <Box
+                  width={outputTokensWidth}
+                  flexDirection="column"
+                  alignItems="flex-end"
+                  flexShrink={0}
+                >
+                  <Text color={theme.text.secondary}>
+                    {metrics?.tokens.candidates.toLocaleString()}
+                  </Text>
+                </Box>
+              </Box>
+            ))}
         </Box>
       ))}
 
diff --git a/packages/cli/src/ui/components/__snapshots__/ModelStatsDisplay.test.tsx.snap b/packages/cli/src/ui/components/__snapshots__/ModelStatsDisplay.test.tsx.snap
index f06cc3fe5af..841de3ae981 100644
--- a/packages/cli/src/ui/components/__snapshots__/ModelStatsDisplay.test.tsx.snap
+++ b/packages/cli/src/ui/components/__snapshots__/ModelStatsDisplay.test.tsx.snap
@@ -5,19 +5,20 @@ exports[`<ModelStatsDisplay /> > should display a single model correctly 1`] = `
 │                                                                                                  │
 │  Model Stats For Nerds                                                                           │
 │                                                                                                  │
-│  Metric                      gemini-2.5-pro                                                      │
+│  Metric                              gemini-2.5-pro                                              │
 │  ──────────────────────────────────────────────────────────────────────────────────────────────  │
 │  API                                                                                             │
-│  Requests                    1                                                                   │
-│  Errors                      0 (0.0%)                                                            │
-│  Avg Latency                 100ms                                                               │
+│  Requests                            1                                                           │
+│  Errors                              0 (0.0%)                                                    │
+│  Avg Latency                         100ms                                                       │
+│                                                                                                  │
 │  Tokens                                                                                          │
-│  Total                       30                                                                  │
-│    ↳ Input                   5                                                                   │
-│    ↳ Cache Reads             5 (50.0%)                                                           │
-│    ↳ Thoughts                2                                                                   │
-│    ↳ Tool                    1                                                                   │
-│    ↳ Output                  20                                                                  │
+│  Total                               30                                                          │
+│    ↳ Input                           5                                                           │
+│    ↳ Cache Reads                     5 (50.0%)                                                   │
+│    ↳ Thoughts                        2                                                           │
+│    ↳ Tool                            1                                                           │
+│    ↳ Output                          20                                                          │
 │                                                                                                  │
 ╰──────────────────────────────────────────────────────────────────────────────────────────────────╯"
 `;
@@ -27,19 +28,48 @@ exports[`<ModelStatsDisplay /> > should display conditional rows if at least one
 │                                                                                                  │
 │  Model Stats For Nerds                                                                           │
 │                                                                                                  │
-│  Metric                      gemini-2.5-pro                   gemini-2.5-flash                   │
+│  Metric                              gemini-2.5-pro               gemini-2.5-flash               │
+│  ──────────────────────────────────────────────────────────────────────────────────────────────  │
+│  API                                                                                             │
+│  Requests                            1                            1                              │
+│  Errors                              0 (0.0%)                     0 (0.0%)                       │
+│  Avg Latency                         100ms                        50ms                           │
+│                                                                                                  │
+│  Tokens                                                                                          │
+│  Total                               30                           15                             │
+│    ↳ Input                           5                            5                              │
+│    ↳ Cache Reads                     5 (50.0%)                    0 (0.0%)                       │
+│    ↳ Thoughts                        2                            0                              │
+│    ↳ Tool                            0                            3                              │
+│    ↳ Output                          20                           10                             │
+│                                                                                                  │
+╰──────────────────────────────────────────────────────────────────────────────────────────────────╯"
+`;
+
+exports[`<ModelStatsDisplay /> > should display role breakdown correctly 1`] = `
+"╭──────────────────────────────────────────────────────────────────────────────────────────────────╮
+│                                                                                                  │
+│  Model Stats For Nerds                                                                           │
+│                                                                                                  │
+│  Metric                              gemini-2.5-pro                                              │
 │  ──────────────────────────────────────────────────────────────────────────────────────────────  │
 │  API                                                                                             │
-│  Requests                    1                                1                                  │
-│  Errors                      0 (0.0%)                         0 (0.0%)                           │
-│  Avg Latency                 100ms                            50ms                               │
+│  Requests                            2                                                           │
+│  Errors                              0 (0.0%)                                                    │
+│  Avg Latency                         100ms                                                       │
+│                                                                                                  │
 │  Tokens                                                                                          │
-│  Total                       30                               15                                 │
-│    ↳ Input                   5                                5                                  │
-│    ↳ Cache Reads             5 (50.0%)                        0 (0.0%)                           │
-│    ↳ Thoughts                2                                0                                  │
-│    ↳ Tool                    0                                3                                  │
-│    ↳ Output                  20                               10                                 │
+│  Total                               70                                                          │
+│    ↳ Input                           20                                                          │
+│    ↳ Cache Reads                     10 (33.3%)                                                  │
+│    ↳ Output                          40                                                          │
+│                                                                                                  │
+│  Roles                                                                                           │
+│    ↳ main                                                                                        │
+│      ↳ Requests                      1                                                           │
+│      ↳ Input                         10                                                          │
+│      ↳ Output                        20                                                          │
+│      ↳ Cache Reads                   5                                                           │
 │                                                                                                  │
 ╰──────────────────────────────────────────────────────────────────────────────────────────────────╯"
 `;
@@ -49,19 +79,20 @@ exports[`<ModelStatsDisplay /> > should display stats for multiple models correc
 │                                                                                                  │
 │  Model Stats For Nerds                                                                           │
 │                                                                                                  │
-│  Metric                      gemini-2.5-pro                   gemini-2.5-flash                   │
+│  Metric                              gemini-2.5-pro               gemini-2.5-flash               │
 │  ──────────────────────────────────────────────────────────────────────────────────────────────  │
 │  API                                                                                             │
-│  Requests                    10                               20                                 │
-│  Errors                      1 (10.0%)                        2 (10.0%)                          │
-│  Avg Latency                 100ms                            25ms                               │
+│  Requests                            10                           20                             │
+│  Errors                              1 (10.0%)                    2 (10.0%)                      │
+│  Avg Latency                         100ms                        25ms                           │
+│                                                                                                  │
 │  Tokens                                                                                          │
-│  Total                       300                              600                                │
-│    ↳ Input                   50                               100                                │
-│    ↳ Cache Reads             50 (50.0%)                       100 (50.0%)                        │
-│    ↳ Thoughts                10                               20                                 │
-│    ↳ Tool                    5                                10                                 │
-│    ↳ Output                  200                              400                                │
+│  Total                               300                          600                            │
+│    ↳ Input                           50                           100                            │
+│    ↳ Cache Reads                     50 (50.0%)                   100 (50.0%)                    │
+│    ↳ Thoughts                        10                           20                             │
+│    ↳ Tool                            5                            10                             │
+│    ↳ Output                          200                          400                            │
 │                                                                                                  │
 ╰──────────────────────────────────────────────────────────────────────────────────────────────────╯"
 `;
@@ -71,43 +102,49 @@ exports[`<ModelStatsDisplay /> > should handle large values without wrapping or
 │                                                                                                  │
 │  Model Stats For Nerds                                                                           │
 │                                                                                                  │
-│  Metric                      gemini-2.5-pro                                                      │
+│  Metric                              gemini-2.5-pro                                              │
 │  ──────────────────────────────────────────────────────────────────────────────────────────────  │
 │  API                                                                                             │
-│  Requests                    999,999,999                                                         │
-│  Errors                      123,456,789 (12.3%)                                                 │
-│  Avg Latency                 0ms                                                                 │
+│  Requests                            999,999,999                                                 │
+│  Errors                              123,456,789 (12.3%)                                         │
+│  Avg Latency                         0ms                                                         │
+│                                                                                                  │
 │  Tokens                                                                                          │
-│  Total                       999,999,999                                                         │
-│    ↳ Input                   864,197,532                                                         │
-│    ↳ Cache Reads             123,456,789 (12.5%)                                                 │
-│    ↳ Thoughts                111,111,111                                                         │
-│    ↳ Tool                    222,222,222                                                         │
-│    ↳ Output                  123,456,789                                                         │
+│  Total                               999,999,999                                                 │
+│    ↳ Input                           864,197,532                                                 │
+│    ↳ Cache Reads                     123,456,789 (12.5%)                                         │
+│    ↳ Thoughts                        111,111,111                                                 │
+│    ↳ Tool                            222,222,222                                                 │
+│    ↳ Output                          123,456,789                                                 │
 │                                                                                                  │
 ╰──────────────────────────────────────────────────────────────────────────────────────────────────╯"
 `;
 
-exports[`<ModelStatsDisplay /> > should handle models with long names (gemini-3-*-preview) without layout breaking 1`] = `
-"╭──────────────────────────────────────────────────────────────────────────────╮
-│                                                                              │
-│  Model Stats For Nerds                                                       │
-│                                                                              │
-│  Metric                      gemini-3-pro-preview   gemini-3-flash-preview   │
-│  ──────────────────────────────────────────────────────────────────────────  │
-│  API                                                                         │
-│  Requests                    10                     20                       │
-│  Errors                      0 (0.0%)               0 (0.0%)                 │
-│  Avg Latency                 200ms                  50ms                     │
-│  Tokens                                                                      │
-│  Total                       6,000                  12,000                   │
-│    ↳ Input                   1,000                  2,000                    │
-│    ↳ Cache Reads             500 (25.0%)            1,000 (25.0%)            │
-│    ↳ Thoughts                100                    200                      │
-│    ↳ Tool                    50                     100                      │
-│    ↳ Output                  4,000                  8,000                    │
-│                                                                              │
-╰──────────────────────────────────────────────────────────────────────────────╯"
+exports[`<ModelStatsDisplay /> > should handle long metric names with truncation 1`] = `
+"╭──────────────────────────────────────────────────────────────────────────────────────────────────╮
+│                                                                                                  │
+│  Model Stats For Nerds                                                                           │
+│                                                                                                  │
+│  Metric                              gemini-2.5-pro                                              │
+│  ──────────────────────────────────────────────────────────────────────────────────────────────  │
+│  API                                                                                             │
+│  Requests                            1                                                           │
+│  Errors                              0 (0.0%)                                                    │
+│  Avg Latency                         100ms                                                       │
+│                                                                                                  │
+│  Tokens                                                                                          │
+│  Total                               30                                                          │
+│    ↳ Input                           10                                                          │
+│    ↳ Output                          20                                                          │
+│                                                                                                  │
+│  Roles                                                                                           │
+│    ↳ this_is_a_very_long_role_name_…                                                             │
+│      ↳ Requests                      1                                                           │
+│      ↳ Input                         10                                                          │
+│      ↳ Output                        20                                                          │
+│      ↳ Cache Reads                   0                                                           │
+│                                                                                                  │
+╰──────────────────────────────────────────────────────────────────────────────────────────────────╯"
 `;
 
 exports[`<ModelStatsDisplay /> > should not display conditional rows if no model has data for them 1`] = `
@@ -115,16 +152,17 @@ exports[`<ModelStatsDisplay /> > should not display conditional rows if no model
 │                                                                                                  │
 │  Model Stats For Nerds                                                                           │
 │                                                                                                  │
-│  Metric                      gemini-2.5-pro                                                      │
+│  Metric                              gemini-2.5-pro                                              │
 │  ──────────────────────────────────────────────────────────────────────────────────────────────  │
 │  API                                                                                             │
-│  Requests                    1                                                                   │
-│  Errors                      0 (0.0%)                                                            │
-│  Avg Latency                 100ms                                                               │
+│  Requests                            1                                                           │
+│  Errors                              0 (0.0%)                                                    │
+│  Avg Latency                         100ms                                                       │
+│                                                                                                  │
 │  Tokens                                                                                          │
-│  Total                       30                                                                  │
-│    ↳ Input                   10                                                                  │
-│    ↳ Output                  20                                                                  │
+│  Total                               30                                                          │
+│    ↳ Input                           10                                                          │
+│    ↳ Output                          20                                                          │
 │                                                                                                  │
 ╰──────────────────────────────────────────────────────────────────────────────────────────────────╯"
 `;
diff --git a/packages/cli/src/ui/components/__snapshots__/SessionSummaryDisplay.test.tsx.snap b/packages/cli/src/ui/components/__snapshots__/SessionSummaryDisplay.test.tsx.snap
index 224758bca9d..6cb99a932d5 100644
--- a/packages/cli/src/ui/components/__snapshots__/SessionSummaryDisplay.test.tsx.snap
+++ b/packages/cli/src/ui/components/__snapshots__/SessionSummaryDisplay.test.tsx.snap
@@ -18,9 +18,9 @@ exports[`<SessionSummaryDisplay /> > renders the summary display with a title 1`
 │    » Tool Time:              0s (0.0%)                                                           │
 │                                                                                                  │
 │                                                                                                  │
-│  Model Usage                 Reqs   Input Tokens   Cache Reads  Output Tokens                    │
-│  ────────────────────────────────────────────────────────────────────────────                    │
-│  gemini-2.5-pro                10            500           500          2,000                    │
+│  Model Usage                              Reqs   Input Tokens   Cache Reads  Output Tokens       │
+│  ─────────────────────────────────────────────────────────────────────────────────────────       │
+│  gemini-2.5-pro                             10            500           500          2,000       │
 │                                                                                                  │
 │  Savings Highlight: 500 (50.0%) of input tokens were served from the cache, reducing costs.      │
 │                                                                                                  │
diff --git a/packages/cli/src/ui/components/__snapshots__/StatsDisplay.test.tsx.snap b/packages/cli/src/ui/components/__snapshots__/StatsDisplay.test.tsx.snap
index 7bac29f45da..a25c343ecfb 100644
--- a/packages/cli/src/ui/components/__snapshots__/StatsDisplay.test.tsx.snap
+++ b/packages/cli/src/ui/components/__snapshots__/StatsDisplay.test.tsx.snap
@@ -118,9 +118,9 @@ exports[`<StatsDisplay /> > Conditional Rendering Tests > hides Efficiency secti
 │    » Tool Time:              0s (0.0%)                                                           │
 │                                                                                                  │
 │                                                                                                  │
-│  Model Usage                 Reqs   Input Tokens   Cache Reads  Output Tokens                    │
-│  ────────────────────────────────────────────────────────────────────────────                    │
-│  gemini-2.5-pro                 1            100             0            100                    │
+│  Model Usage                              Reqs   Input Tokens   Cache Reads  Output Tokens       │
+│  ─────────────────────────────────────────────────────────────────────────────────────────       │
+│  gemini-2.5-pro                              1            100             0            100       │
 │                                                                                                  │
 ╰──────────────────────────────────────────────────────────────────────────────────────────────────╯"
 `;
@@ -162,9 +162,9 @@ exports[`<StatsDisplay /> > Quota Display > renders quota information for unused
 │    » Tool Time:              0s (0.0%)                                                           │
 │                                                                                                  │
 │                                                                                                  │
-│  Model Usage                 Reqs                  Usage left                                    │
-│  ────────────────────────────────────────────────────────────                                    │
-│  gemini-2.5-flash               -        50.0% (Resets in 2h)                                    │
+│  Model Usage                              Reqs                  Usage left                       │
+│  ─────────────────────────────────────────────────────────────────────────                       │
+│  gemini-2.5-flash                            -        50.0% (Resets in 2h)                       │
 │                                                                                                  │
 │  Usage limits span all sessions and reset daily.                                                 │
 │  /auth to upgrade or switch to API key.                                                          │
@@ -192,9 +192,9 @@ exports[`<StatsDisplay /> > Quota Display > renders quota information when quota
 │    » Tool Time:              0s (0.0%)                                                           │
 │                                                                                                  │
 │                                                                                                  │
-│  Model Usage                 Reqs                  Usage left                                    │
-│  ────────────────────────────────────────────────────────────                                    │
-│  gemini-2.5-pro                 1    75.0% (Resets in 1h 30m)                                    │
+│  Model Usage                              Reqs                  Usage left                       │
+│  ─────────────────────────────────────────────────────────────────────────                       │
+│  gemini-2.5-pro                              1    75.0% (Resets in 1h 30m)                       │
 │                                                                                                  │
 │  Usage limits span all sessions and reset daily.                                                 │
 │  /auth to upgrade or switch to API key.                                                          │
@@ -262,10 +262,10 @@ exports[`<StatsDisplay /> > renders a table with two models correctly 1`] = `
 │    » Tool Time:              0s (0.0%)                                                           │
 │                                                                                                  │
 │                                                                                                  │
-│  Model Usage                 Reqs   Input Tokens   Cache Reads  Output Tokens                    │
-│  ────────────────────────────────────────────────────────────────────────────                    │
-│  gemini-2.5-pro                 3            500           500          2,000                    │
-│  gemini-2.5-flash               5         15,000        10,000         15,000                    │
+│  Model Usage                              Reqs   Input Tokens   Cache Reads  Output Tokens       │
+│  ─────────────────────────────────────────────────────────────────────────────────────────       │
+│  gemini-2.5-pro                              3            500           500          2,000       │
+│  gemini-2.5-flash                            5         15,000        10,000         15,000       │
 │                                                                                                  │
 │  Savings Highlight: 10,500 (40.4%) of input tokens were served from the cache, reducing costs.   │
 │                                                                                                  │
@@ -290,9 +290,9 @@ exports[`<StatsDisplay /> > renders all sections when all data is present 1`] =
 │    » Tool Time:              123ms (55.2%)                                                       │
 │                                                                                                  │
 │                                                                                                  │
-│  Model Usage                 Reqs   Input Tokens   Cache Reads  Output Tokens                    │
-│  ────────────────────────────────────────────────────────────────────────────                    │
-│  gemini-2.5-pro                 1             50            50            100                    │
+│  Model Usage                              Reqs   Input Tokens   Cache Reads  Output Tokens       │
+│  ─────────────────────────────────────────────────────────────────────────────────────────       │
+│  gemini-2.5-pro                              1             50            50            100       │
 │                                                                                                  │
 │  Savings Highlight: 50 (50.0%) of input tokens were served from the cache, reducing costs.       │
 │                                                                                                  │
@@ -318,3 +318,31 @@ exports[`<StatsDisplay /> > renders only the Performance section in its zero sta
 │                                                                                                  │
 ╰──────────────────────────────────────────────────────────────────────────────────────────────────╯"
 `;
+
+exports[`<StatsDisplay /> > renders roles correctly 1`] = `
+"╭──────────────────────────────────────────────────────────────────────────────────────────────────╮
+│                                                                                                  │
+│  Session Stats                                                                                   │
+│                                                                                                  │
+│  Interaction Summary                                                                             │
+│  Session ID:                 test-session-id                                                     │
+│  Tool Calls:                 0 ( ✓ 0 x 0 )                                                       │
+│  Success Rate:               0.0%                                                                │
+│                                                                                                  │
+│  Performance                                                                                     │
+│  Wall Time:                  1s                                                                  │
+│  Agent Active:               15.0s                                                               │
+│    » API Time:               15.0s (100.0%)                                                      │
+│    » Tool Time:              0s (0.0%)                                                           │
+│                                                                                                  │
+│                                                                                                  │
+│  Model Usage                              Reqs   Input Tokens   Cache Reads  Output Tokens       │
+│  ─────────────────────────────────────────────────────────────────────────────────────────       │
+│  gemini-2.5-pro                              3            500           500          2,000       │
+│    ↳ main                                    1            100             0              0       │
+│    ↳ utility_tool                            2            400           500          2,000       │
+│                                                                                                  │
+│  Savings Highlight: 500 (50.0%) of input tokens were served from the cache, reducing costs.      │
+│                                                                                                  │
+╰──────────────────────────────────────────────────────────────────────────────────────────────────╯"
+`;
diff --git a/packages/cli/src/ui/contexts/SessionContext.test.tsx b/packages/cli/src/ui/contexts/SessionContext.test.tsx
index 5ab02042557..5ab76e45191 100644
--- a/packages/cli/src/ui/contexts/SessionContext.test.tsx
+++ b/packages/cli/src/ui/contexts/SessionContext.test.tsx
@@ -100,6 +100,7 @@ describe('SessionStatsContext', () => {
             thoughts: 20,
             tool: 10,
           },
+          roles: {},
         },
       },
       tools: {
@@ -180,6 +181,7 @@ describe('SessionStatsContext', () => {
             thoughts: 0,
             tool: 0,
           },
+          roles: {},
         },
       },
       tools: {
diff --git a/packages/cli/src/ui/hooks/usePromptCompletion.ts b/packages/cli/src/ui/hooks/usePromptCompletion.ts
index c666b82900f..b17c802a553 100644
--- a/packages/cli/src/ui/hooks/usePromptCompletion.ts
+++ b/packages/cli/src/ui/hooks/usePromptCompletion.ts
@@ -6,7 +6,7 @@
 
 import { useState, useCallback, useRef, useEffect, useMemo } from 'react';
 import type { Config } from '@google/gemini-cli-core';
-import { debugLogger, getResponseText } from '@google/gemini-cli-core';
+import { debugLogger, getResponseText, LlmRole } from '@google/gemini-cli-core';
 import type { Content } from '@google/genai';
 import type { TextBuffer } from '../components/shared/text-buffer.js';
 import { isSlashCommand } from '../utils/commandUtils.js';
@@ -110,6 +110,7 @@ export function usePromptCompletion({
         { model: 'prompt-completion' },
         contents,
         signal,
+        LlmRole.UTILITY_AUTOCOMPLETE,
       );
 
       if (signal.aborted) {
diff --git a/packages/cli/src/ui/utils/computeStats.test.ts b/packages/cli/src/ui/utils/computeStats.test.ts
index b3677164a78..09baec304f0 100644
--- a/packages/cli/src/ui/utils/computeStats.test.ts
+++ b/packages/cli/src/ui/utils/computeStats.test.ts
@@ -29,6 +29,7 @@ describe('calculateErrorRate', () => {
         thoughts: 0,
         tool: 0,
       },
+      roles: {},
     };
     expect(calculateErrorRate(metrics)).toBe(0);
   });
@@ -45,6 +46,7 @@ describe('calculateErrorRate', () => {
         thoughts: 0,
         tool: 0,
       },
+      roles: {},
     };
     expect(calculateErrorRate(metrics)).toBe(20);
   });
@@ -63,6 +65,7 @@ describe('calculateAverageLatency', () => {
         thoughts: 0,
         tool: 0,
       },
+      roles: {},
     };
     expect(calculateAverageLatency(metrics)).toBe(0);
   });
@@ -79,6 +82,7 @@ describe('calculateAverageLatency', () => {
         thoughts: 0,
         tool: 0,
       },
+      roles: {},
     };
     expect(calculateAverageLatency(metrics)).toBe(150);
   });
@@ -97,6 +101,7 @@ describe('calculateCacheHitRate', () => {
         thoughts: 0,
         tool: 0,
       },
+      roles: {},
     };
     expect(calculateCacheHitRate(metrics)).toBe(0);
   });
@@ -113,6 +118,7 @@ describe('calculateCacheHitRate', () => {
         thoughts: 0,
         tool: 0,
       },
+      roles: {},
     };
     expect(calculateCacheHitRate(metrics)).toBe(25);
   });
@@ -170,6 +176,7 @@ describe('computeSessionStats', () => {
             thoughts: 0,
             tool: 0,
           },
+          roles: {},
         },
       },
       tools: {
@@ -209,6 +216,7 @@ describe('computeSessionStats', () => {
             thoughts: 0,
             tool: 0,
           },
+          roles: {},
         },
       },
       tools: {
diff --git a/packages/cli/src/zed-integration/zedIntegration.test.ts b/packages/cli/src/zed-integration/zedIntegration.test.ts
index 0a6341a158b..187a5bae943 100644
--- a/packages/cli/src/zed-integration/zedIntegration.test.ts
+++ b/packages/cli/src/zed-integration/zedIntegration.test.ts
@@ -24,6 +24,7 @@ import {
   ReadManyFilesTool,
   type GeminiChat,
   type Config,
+  LlmRole,
 } from '@google/gemini-cli-core';
 import { SettingScope, type LoadedSettings } from '../config/settings.js';
 import { loadCliConfig, type CliArgs } from '../config/config.js';
@@ -527,7 +528,8 @@ describe('Session', () => {
         }),
       ]),
       expect.anything(),
-      expect.anything(),
+      expect.any(AbortSignal),
+      LlmRole.MAIN,
     );
   });
 
diff --git a/packages/cli/src/zed-integration/zedIntegration.ts b/packages/cli/src/zed-integration/zedIntegration.ts
index b87bb7e77c1..d1fd3863530 100644
--- a/packages/cli/src/zed-integration/zedIntegration.ts
+++ b/packages/cli/src/zed-integration/zedIntegration.ts
@@ -30,6 +30,7 @@ import {
   getEffectiveModel,
   createWorkingStdio,
   startupProfiler,
+  LlmRole,
 } from '@google/gemini-cli-core';
 import * as acp from '@agentclientprotocol/sdk';
 import { AcpFileSystemService } from './fileSystemService.js';
@@ -291,6 +292,7 @@ export class Session {
           nextMessage?.parts ?? [],
           promptId,
           pendingSend.signal,
+          LlmRole.MAIN,
         );
         nextMessage = null;
 
diff --git a/packages/core/src/agents/local-executor.ts b/packages/core/src/agents/local-executor.ts
index 6cb78c5f113..fc3f2215de7 100644
--- a/packages/core/src/agents/local-executor.ts
+++ b/packages/core/src/agents/local-executor.ts
@@ -45,6 +45,7 @@ import { zodToJsonSchema } from 'zod-to-json-schema';
 import { debugLogger } from '../utils/debugLogger.js';
 import { getModelConfigAlias } from './registry.js';
 import { ApprovalMode } from '../policy/types.js';
+import { LlmRole } from '../telemetry/types.js';
 
 /** A callback function to report on agent activity. */
 export type ActivityCallback = (activity: SubagentActivityEvent) => void;
@@ -577,6 +578,11 @@ export class LocalAgentExecutor<TOutput extends z.ZodTypeAny> {
     signal: AbortSignal,
     promptId: string,
   ): Promise<{ functionCalls: FunctionCall[]; textResponse: string }> {
+    const role =
+      this.definition.name === 'codebase_investigator'
+        ? LlmRole.SUBAGENT_CODEBASE_INVESTIGATOR
+        : LlmRole.SUBAGENT;
+
     const responseStream = await chat.sendMessageStream(
       {
         model: getModelConfigAlias(this.definition),
@@ -585,6 +591,7 @@ export class LocalAgentExecutor<TOutput extends z.ZodTypeAny> {
       message.parts || [],
       promptId,
       signal,
+      role,
     );
 
     const functionCalls: FunctionCall[] = [];
diff --git a/packages/core/src/code_assist/server.test.ts b/packages/core/src/code_assist/server.test.ts
index 91873a796eb..5080457efb3 100644
--- a/packages/core/src/code_assist/server.test.ts
+++ b/packages/core/src/code_assist/server.test.ts
@@ -9,6 +9,7 @@ import { CodeAssistServer } from './server.js';
 import { OAuth2Client } from 'google-auth-library';
 import { UserTierId, ActionStatus } from './types.js';
 import { FinishReason } from '@google/genai';
+import { LlmRole } from '../telemetry/types.js';
 
 vi.mock('google-auth-library');
 
@@ -69,6 +70,7 @@ describe('CodeAssistServer', () => {
         contents: [{ role: 'user', parts: [{ text: 'request' }] }],
       },
       'user-prompt-id',
+      LlmRole.MAIN,
     );
 
     expect(mockRequest).toHaveBeenCalledWith({
@@ -126,6 +128,7 @@ describe('CodeAssistServer', () => {
         contents: [{ role: 'user', parts: [{ text: 'request' }] }],
       },
       'user-prompt-id',
+      LlmRole.MAIN,
     );
 
     expect(recordConversationOfferedSpy).toHaveBeenCalledWith(
@@ -170,6 +173,7 @@ describe('CodeAssistServer', () => {
         contents: [{ role: 'user', parts: [{ text: 'request' }] }],
       },
       'user-prompt-id',
+      LlmRole.MAIN,
     );
 
     expect(server.recordCodeAssistMetrics).toHaveBeenCalledWith(
@@ -205,6 +209,7 @@ describe('CodeAssistServer', () => {
         contents: [{ role: 'user', parts: [{ text: 'request' }] }],
       },
       'user-prompt-id',
+      LlmRole.MAIN,
     );
 
     const mockResponseData = {
@@ -344,6 +349,7 @@ describe('CodeAssistServer', () => {
         contents: [{ role: 'user', parts: [{ text: 'request' }] }],
       },
       'user-prompt-id',
+      LlmRole.MAIN,
     );
 
     // Push SSE data to the stream
diff --git a/packages/core/src/code_assist/server.ts b/packages/core/src/code_assist/server.ts
index ccebc80977f..a3ff14663a9 100644
--- a/packages/core/src/code_assist/server.ts
+++ b/packages/core/src/code_assist/server.ts
@@ -51,6 +51,7 @@ import {
   recordConversationOffered,
 } from './telemetry.js';
 import { getClientMetadata } from './experiments/client_metadata.js';
+import type { LlmRole } from '../telemetry/types.js';
 
 /** HTTP options to be used in each of the requests. */
 export interface HttpOptions {
@@ -73,6 +74,8 @@ export class CodeAssistServer implements ContentGenerator {
   async generateContentStream(
     req: GenerateContentParameters,
     userPromptId: string,
+    // eslint-disable-next-line @typescript-eslint/no-unused-vars
+    role: LlmRole,
   ): Promise<AsyncGenerator<GenerateContentResponse>> {
     const responses =
       await this.requestStreamingPost<CaGenerateContentResponse>(
@@ -123,6 +126,8 @@ export class CodeAssistServer implements ContentGenerator {
   async generateContent(
     req: GenerateContentParameters,
     userPromptId: string,
+    // eslint-disable-next-line @typescript-eslint/no-unused-vars
+    role: LlmRole,
   ): Promise<GenerateContentResponse> {
     const start = Date.now();
     const response = await this.requestPost<CaGenerateContentResponse>(
diff --git a/packages/core/src/core/baseLlmClient.test.ts b/packages/core/src/core/baseLlmClient.test.ts
index bcb701e739d..8e9dafa21b7 100644
--- a/packages/core/src/core/baseLlmClient.test.ts
+++ b/packages/core/src/core/baseLlmClient.test.ts
@@ -30,6 +30,7 @@ import { MalformedJsonResponseEvent } from '../telemetry/types.js';
 import { getErrorMessage } from '../utils/errors.js';
 import type { ModelConfigService } from '../services/modelConfigService.js';
 import { makeResolvedModelConfig } from '../services/modelConfigServiceTestUtils.js';
+import { LlmRole } from '../telemetry/types.js';
 
 vi.mock('../utils/errorReporting.js');
 vi.mock('../telemetry/loggers.js');
@@ -129,6 +130,7 @@ describe('BaseLlmClient', () => {
       schema: { type: 'object', properties: { color: { type: 'string' } } },
       abortSignal: abortController.signal,
       promptId: 'test-prompt-id',
+      role: LlmRole.UTILITY_TOOL,
     };
   });
 
@@ -170,6 +172,7 @@ describe('BaseLlmClient', () => {
           },
         },
         'test-prompt-id',
+        LlmRole.UTILITY_TOOL,
       );
     });
 
@@ -192,6 +195,7 @@ describe('BaseLlmClient', () => {
           }),
         }),
         expect.any(String),
+        LlmRole.UTILITY_TOOL,
       );
     });
 
@@ -210,6 +214,7 @@ describe('BaseLlmClient', () => {
       expect(mockGenerateContent).toHaveBeenCalledWith(
         expect.any(Object),
         customPromptId,
+        LlmRole.UTILITY_TOOL,
       );
     });
 
@@ -529,6 +534,7 @@ describe('BaseLlmClient', () => {
         contents: [{ role: 'user', parts: [{ text: 'Give me content.' }] }],
         abortSignal: abortController.signal,
         promptId: 'content-prompt-id',
+        role: LlmRole.UTILITY_TOOL,
       };
 
       const result = await client.generateContent(options);
@@ -557,6 +563,7 @@ describe('BaseLlmClient', () => {
           },
         },
         'content-prompt-id',
+        LlmRole.UTILITY_TOOL,
       );
     });
 
@@ -569,6 +576,7 @@ describe('BaseLlmClient', () => {
         contents: [{ role: 'user', parts: [{ text: 'Give me content.' }] }],
         abortSignal: abortController.signal,
         promptId: 'content-prompt-id',
+        role: LlmRole.UTILITY_TOOL,
       };
 
       await client.generateContent(options);
@@ -591,6 +599,7 @@ describe('BaseLlmClient', () => {
         contents: [{ role: 'user', parts: [{ text: 'Give me content.' }] }],
         abortSignal: abortController.signal,
         promptId: 'content-prompt-id',
+        role: LlmRole.UTILITY_TOOL,
       };
 
       await expect(client.generateContent(options)).rejects.toThrow(
@@ -635,6 +644,7 @@ describe('BaseLlmClient', () => {
         contents: [{ role: 'user', parts: [{ text: 'Give me a color.' }] }],
         abortSignal: abortController.signal,
         promptId: 'content-prompt-id',
+        role: LlmRole.UTILITY_TOOL,
       };
 
       jsonOptions = {
@@ -656,6 +666,7 @@ describe('BaseLlmClient', () => {
       await client.generateContent({
         ...contentOptions,
         modelConfigKey: { model: successfulModel },
+        role: LlmRole.UTILITY_TOOL,
       });
 
       expect(mockAvailabilityService.markHealthy).toHaveBeenCalledWith(
@@ -681,6 +692,7 @@ describe('BaseLlmClient', () => {
         ...contentOptions,
         modelConfigKey: { model: firstModel },
         maxAttempts: 2,
+        role: LlmRole.UTILITY_TOOL,
       });
 
       await vi.runAllTimersAsync();
@@ -690,6 +702,7 @@ describe('BaseLlmClient', () => {
         ...contentOptions,
         modelConfigKey: { model: firstModel },
         maxAttempts: 2,
+        role: LlmRole.UTILITY_TOOL,
       });
 
       expect(mockConfig.setActiveModel).toHaveBeenCalledWith(firstModel);
@@ -700,6 +713,7 @@ describe('BaseLlmClient', () => {
       expect(mockGenerateContent).toHaveBeenLastCalledWith(
         expect.objectContaining({ model: fallbackModel }),
         expect.any(String),
+        LlmRole.UTILITY_TOOL,
       );
     });
 
@@ -725,6 +739,7 @@ describe('BaseLlmClient', () => {
       await client.generateContent({
         ...contentOptions,
         modelConfigKey: { model: stickyModel },
+        role: LlmRole.UTILITY_TOOL,
       });
 
       expect(mockAvailabilityService.consumeStickyAttempt).toHaveBeenCalledWith(
@@ -764,6 +779,7 @@ describe('BaseLlmClient', () => {
       expect(mockGenerateContent).toHaveBeenLastCalledWith(
         expect.objectContaining({ model: availableModel }),
         jsonOptions.promptId,
+        LlmRole.UTILITY_TOOL,
       );
     });
 
@@ -815,6 +831,7 @@ describe('BaseLlmClient', () => {
         ...contentOptions,
         modelConfigKey: { model: firstModel },
         maxAttempts: 2,
+        role: LlmRole.UTILITY_TOOL,
       });
 
       expect(mockGenerateContent).toHaveBeenCalledTimes(2);
diff --git a/packages/core/src/core/baseLlmClient.ts b/packages/core/src/core/baseLlmClient.ts
index a508cdd038f..453d95a7c4d 100644
--- a/packages/core/src/core/baseLlmClient.ts
+++ b/packages/core/src/core/baseLlmClient.ts
@@ -27,6 +27,7 @@ import {
   applyModelSelection,
   createAvailabilityContextProvider,
 } from '../availability/policyHelpers.js';
+import type { LlmRole } from '../telemetry/types.js';
 
 const DEFAULT_MAX_ATTEMPTS = 5;
 
@@ -55,6 +56,10 @@ export interface GenerateJsonOptions {
    * The maximum number of attempts for the request.
    */
   maxAttempts?: number;
+  /**
+   * The role of the LLM call.
+   */
+  role: LlmRole;
 }
 
 /**
@@ -80,6 +85,10 @@ export interface GenerateContentOptions {
    * The maximum number of attempts for the request.
    */
   maxAttempts?: number;
+  /**
+   * The role of the LLM call.
+   */
+  role: LlmRole;
 }
 
 interface _CommonGenerateOptions {
@@ -116,6 +125,7 @@ export class BaseLlmClient {
       abortSignal,
       promptId,
       maxAttempts,
+      role,
     } = options;
 
     const { model } =
@@ -150,6 +160,7 @@ export class BaseLlmClient {
       },
       shouldRetryOnContent,
       'generateJson',
+      role,
     );
 
     // If we are here, the content is valid (not empty and parsable).
@@ -216,6 +227,7 @@ export class BaseLlmClient {
       abortSignal,
       promptId,
       maxAttempts,
+      role,
     } = options;
 
     const shouldRetryOnContent = (response: GenerateContentResponse) => {
@@ -234,6 +246,7 @@ export class BaseLlmClient {
       },
       shouldRetryOnContent,
       'generateContent',
+      role,
     );
   }
 
@@ -241,6 +254,7 @@ export class BaseLlmClient {
     options: _CommonGenerateOptions,
     shouldRetryOnContent: (response: GenerateContentResponse) => boolean,
     errorContext: 'generateJson' | 'generateContent',
+    role: LlmRole = 'utility_tool' as LlmRole,
   ): Promise<GenerateContentResponse> {
     const {
       modelConfigKey,
@@ -293,7 +307,11 @@ export class BaseLlmClient {
           config: finalConfig,
           contents,
         };
-        return this.contentGenerator.generateContent(requestParams, promptId);
+        return this.contentGenerator.generateContent(
+          requestParams,
+          promptId,
+          role,
+        );
       };
 
       return await retryWithBackoff(apiCall, {
diff --git a/packages/core/src/core/client.test.ts b/packages/core/src/core/client.test.ts
index 3f496564ab7..063f4e95db0 100644
--- a/packages/core/src/core/client.test.ts
+++ b/packages/core/src/core/client.test.ts
@@ -47,6 +47,7 @@ import type {
 import { ClearcutLogger } from '../telemetry/clearcut-logger/clearcut-logger.js';
 import { HookSystem } from '../hooks/hookSystem.js';
 import * as policyCatalog from '../availability/policyCatalog.js';
+import { LlmRole } from '../telemetry/types.js';
 
 vi.mock('../services/chatCompressionService.js');
 
@@ -2545,6 +2546,7 @@ ${JSON.stringify(
         { model: 'test-model' },
         contents,
         abortSignal,
+        LlmRole.MAIN,
       );
 
       expect(mockContentGenerator.generateContent).toHaveBeenCalledWith(
@@ -2559,6 +2561,7 @@ ${JSON.stringify(
           contents,
         },
         'test-session-id',
+        LlmRole.MAIN,
       );
     });
 
@@ -2570,6 +2573,7 @@ ${JSON.stringify(
         { model: initialModel },
         contents,
         new AbortController().signal,
+        LlmRole.MAIN,
       );
 
       expect(mockContentGenerator.generateContent).toHaveBeenCalledWith(
@@ -2577,6 +2581,7 @@ ${JSON.stringify(
           model: initialModel,
         }),
         'test-session-id',
+        LlmRole.MAIN,
       );
     });
   });
diff --git a/packages/core/src/core/client.ts b/packages/core/src/core/client.ts
index fba1a5bd1a0..16d3094cf22 100644
--- a/packages/core/src/core/client.ts
+++ b/packages/core/src/core/client.ts
@@ -58,6 +58,7 @@ import {
   createAvailabilityContextProvider,
 } from '../availability/policyHelpers.js';
 import type { RetryAvailabilityContext } from '../utils/retry.js';
+import type { LlmRole } from '../telemetry/types.js';
 
 const MAX_TURNS = 100;
 
@@ -660,6 +661,7 @@ export class GeminiClient {
     modelConfigKey: ModelConfigKey,
     contents: Content[],
     abortSignal: AbortSignal,
+    role: LlmRole,
   ): Promise<GenerateContentResponse> {
     const desiredModelConfig =
       this.config.modelConfigService.getResolvedConfig(modelConfigKey);
@@ -714,6 +716,7 @@ export class GeminiClient {
             contents,
           },
           this.lastPromptId,
+          role,
         );
       };
       const onPersistent429Callback = async (
diff --git a/packages/core/src/core/contentGenerator.ts b/packages/core/src/core/contentGenerator.ts
index 7c733bce0f9..a654aedce1d 100644
--- a/packages/core/src/core/contentGenerator.ts
+++ b/packages/core/src/core/contentGenerator.ts
@@ -24,6 +24,7 @@ import { FakeContentGenerator } from './fakeContentGenerator.js';
 import { parseCustomHeaders } from '../utils/customHeaderUtils.js';
 import { RecordingContentGenerator } from './recordingContentGenerator.js';
 import { getVersion, getEffectiveModel } from '../../index.js';
+import type { LlmRole } from '../telemetry/llmRole.js';
 
 /**
  * Interface abstracting the core functionalities for generating content and counting tokens.
@@ -32,11 +33,13 @@ export interface ContentGenerator {
   generateContent(
     request: GenerateContentParameters,
     userPromptId: string,
+    role: LlmRole,
   ): Promise<GenerateContentResponse>;
 
   generateContentStream(
     request: GenerateContentParameters,
     userPromptId: string,
+    role: LlmRole,
   ): Promise<AsyncGenerator<GenerateContentResponse>>;
 
   countTokens(request: CountTokensParameters): Promise<CountTokensResponse>;
diff --git a/packages/core/src/core/fakeContentGenerator.test.ts b/packages/core/src/core/fakeContentGenerator.test.ts
index de8306e5167..673fa6b2e72 100644
--- a/packages/core/src/core/fakeContentGenerator.test.ts
+++ b/packages/core/src/core/fakeContentGenerator.test.ts
@@ -18,6 +18,7 @@ import {
   type CountTokensParameters,
   type EmbedContentParameters,
 } from '@google/genai';
+import { LlmRole } from '../telemetry/types.js';
 
 vi.mock('node:fs', async (importOriginal) => {
   const actual = await importOriginal<typeof import('node:fs')>();
@@ -79,6 +80,7 @@ describe('FakeContentGenerator', () => {
     const response = await generator.generateContent(
       {} as GenerateContentParameters,
       'id',
+      LlmRole.MAIN,
     );
     expect(response).instanceOf(GenerateContentResponse);
     expect(response).toEqual(fakeGenerateContentResponse.response);
@@ -91,6 +93,7 @@ describe('FakeContentGenerator', () => {
     const stream = await generator.generateContentStream(
       {} as GenerateContentParameters,
       'id',
+      LlmRole.MAIN,
     );
     const responses = [];
     for await (const response of stream) {
@@ -121,7 +124,11 @@ describe('FakeContentGenerator', () => {
     ];
     const generator = new FakeContentGenerator(fakeResponses);
     for (const fakeResponse of fakeResponses) {
-      const response = await generator[fakeResponse.method]({} as never, '');
+      const response = await generator[fakeResponse.method](
+        {} as never,
+        '',
+        LlmRole.MAIN,
+      );
       if (fakeResponse.method === 'generateContentStream') {
         const responses = [];
         for await (const item of response as AsyncGenerator<GenerateContentResponse>) {
@@ -137,7 +144,11 @@ describe('FakeContentGenerator', () => {
 
   it('should throw error when no more responses', async () => {
     const generator = new FakeContentGenerator([fakeGenerateContentResponse]);
-    await generator.generateContent({} as GenerateContentParameters, 'id');
+    await generator.generateContent(
+      {} as GenerateContentParameters,
+      'id',
+      LlmRole.MAIN,
+    );
     await expect(
       generator.embedContent({} as EmbedContentParameters),
     ).rejects.toThrowError('No more mock responses for embedContent');
@@ -145,10 +156,18 @@ describe('FakeContentGenerator', () => {
       generator.countTokens({} as CountTokensParameters),
     ).rejects.toThrowError('No more mock responses for countTokens');
     await expect(
-      generator.generateContentStream({} as GenerateContentParameters, 'id'),
+      generator.generateContentStream(
+        {} as GenerateContentParameters,
+        'id',
+        LlmRole.MAIN,
+      ),
     ).rejects.toThrow('No more mock responses for generateContentStream');
     await expect(
-      generator.generateContent({} as GenerateContentParameters, 'id'),
+      generator.generateContent(
+        {} as GenerateContentParameters,
+        'id',
+        LlmRole.MAIN,
+      ),
     ).rejects.toThrowError('No more mock responses for generateContent');
   });
 
@@ -161,6 +180,7 @@ describe('FakeContentGenerator', () => {
       const response = await generator.generateContent(
         {} as GenerateContentParameters,
         'id',
+        LlmRole.MAIN,
       );
       expect(response).toEqual(fakeGenerateContentResponse.response);
     });
diff --git a/packages/core/src/core/fakeContentGenerator.ts b/packages/core/src/core/fakeContentGenerator.ts
index a464c4f8faa..3ead5dcc022 100644
--- a/packages/core/src/core/fakeContentGenerator.ts
+++ b/packages/core/src/core/fakeContentGenerator.ts
@@ -16,6 +16,7 @@ import { promises } from 'node:fs';
 import type { ContentGenerator } from './contentGenerator.js';
 import type { UserTierId } from '../code_assist/types.js';
 import { safeJsonStringify } from '../utils/safeJsonStringify.js';
+import type { LlmRole } from '../telemetry/types.js';
 
 export type FakeResponse =
   | {
@@ -76,6 +77,8 @@ export class FakeContentGenerator implements ContentGenerator {
   async generateContent(
     request: GenerateContentParameters,
     _userPromptId: string,
+    // eslint-disable-next-line @typescript-eslint/no-unused-vars
+    role: LlmRole,
   ): Promise<GenerateContentResponse> {
     return Object.setPrototypeOf(
       this.getNextResponse('generateContent', request),
@@ -86,6 +89,8 @@ export class FakeContentGenerator implements ContentGenerator {
   async generateContentStream(
     request: GenerateContentParameters,
     _userPromptId: string,
+    // eslint-disable-next-line @typescript-eslint/no-unused-vars
+    role: LlmRole,
   ): Promise<AsyncGenerator<GenerateContentResponse>> {
     const responses = this.getNextResponse('generateContentStream', request);
     async function* stream() {
diff --git a/packages/core/src/core/geminiChat.test.ts b/packages/core/src/core/geminiChat.test.ts
index baf8973904d..5ee20e6019f 100644
--- a/packages/core/src/core/geminiChat.test.ts
+++ b/packages/core/src/core/geminiChat.test.ts
@@ -28,6 +28,7 @@ import { createAvailabilityServiceMock } from '../availability/testUtils.js';
 import type { ModelAvailabilityService } from '../availability/modelAvailabilityService.js';
 import * as policyHelpers from '../availability/policyHelpers.js';
 import { makeResolvedModelConfig } from '../services/modelConfigServiceTestUtils.js';
+import { LlmRole } from '../telemetry/types.js';
 
 // Mock fs module to prevent actual file system operations during tests
 const mockFileSystem = new Map<string, string>();
@@ -259,6 +260,7 @@ describe('GeminiChat', () => {
         'test message',
         'prompt-id-tool-call-empty-end',
         new AbortController().signal,
+        LlmRole.MAIN,
       );
       await expect(
         (async () => {
@@ -312,6 +314,7 @@ describe('GeminiChat', () => {
         'test message',
         'prompt-id-no-finish-empty-end',
         new AbortController().signal,
+        LlmRole.MAIN,
       );
       await expect(
         (async () => {
@@ -359,6 +362,7 @@ describe('GeminiChat', () => {
         'test message',
         'prompt-id-valid-then-invalid-end',
         new AbortController().signal,
+        LlmRole.MAIN,
       );
       await expect(
         (async () => {
@@ -407,6 +411,7 @@ describe('GeminiChat', () => {
         'test message',
         'prompt-id-empty-chunk-consolidation',
         new AbortController().signal,
+        LlmRole.MAIN,
       );
       for await (const _ of stream) {
         // Consume the stream
@@ -466,6 +471,7 @@ describe('GeminiChat', () => {
         'test message',
         'prompt-id-multi-chunk',
         new AbortController().signal,
+        LlmRole.MAIN,
       );
       for await (const _ of stream) {
         // Consume the stream to trigger history recording.
@@ -515,6 +521,7 @@ describe('GeminiChat', () => {
         'test message',
         'prompt-id-mixed-chunk',
         new AbortController().signal,
+        LlmRole.MAIN,
       );
       for await (const _ of stream) {
         // This loop consumes the stream.
@@ -584,6 +591,7 @@ describe('GeminiChat', () => {
         },
         'prompt-id-stream-1',
         new AbortController().signal,
+        LlmRole.MAIN,
       );
 
       // 4. Assert: The stream processing should throw an InvalidStreamError.
@@ -628,6 +636,7 @@ describe('GeminiChat', () => {
         'test message',
         'prompt-id-1',
         new AbortController().signal,
+        LlmRole.MAIN,
       );
 
       // Should not throw an error
@@ -665,6 +674,7 @@ describe('GeminiChat', () => {
         'test message',
         'prompt-id-1',
         new AbortController().signal,
+        LlmRole.MAIN,
       );
 
       await expect(
@@ -701,6 +711,7 @@ describe('GeminiChat', () => {
         'test message',
         'prompt-id-1',
         new AbortController().signal,
+        LlmRole.MAIN,
       );
 
       await expect(
@@ -737,6 +748,7 @@ describe('GeminiChat', () => {
         'test message',
         'prompt-id-1',
         new AbortController().signal,
+        LlmRole.MAIN,
       );
 
       // Should not throw an error
@@ -774,6 +786,7 @@ describe('GeminiChat', () => {
         'test',
         'prompt-id-malformed',
         new AbortController().signal,
+        LlmRole.MAIN,
       );
 
       // Should throw an error
@@ -821,6 +834,7 @@ describe('GeminiChat', () => {
         'test retry',
         'prompt-id-retry-malformed',
         new AbortController().signal,
+        LlmRole.MAIN,
       );
       const events: StreamEvent[] = [];
       for await (const event of stream) {
@@ -878,6 +892,7 @@ describe('GeminiChat', () => {
         'hello',
         'prompt-id-1',
         new AbortController().signal,
+        LlmRole.MAIN,
       );
       for await (const _ of stream) {
         // consume stream
@@ -903,6 +918,7 @@ describe('GeminiChat', () => {
           },
         },
         'prompt-id-1',
+        LlmRole.MAIN,
       );
     });
 
@@ -926,6 +942,7 @@ describe('GeminiChat', () => {
         'hello',
         'prompt-id-thinking-level',
         new AbortController().signal,
+        LlmRole.MAIN,
       );
       for await (const _ of stream) {
         // consume stream
@@ -942,6 +959,7 @@ describe('GeminiChat', () => {
           }),
         }),
         'prompt-id-thinking-level',
+        LlmRole.MAIN,
       );
     });
 
@@ -965,6 +983,7 @@ describe('GeminiChat', () => {
         'hello',
         'prompt-id-thinking-budget',
         new AbortController().signal,
+        LlmRole.MAIN,
       );
       for await (const _ of stream) {
         // consume stream
@@ -975,12 +994,13 @@ describe('GeminiChat', () => {
           model: 'gemini-2.0-flash',
           config: expect.objectContaining({
             thinkingConfig: {
-              thinkingBudget: DEFAULT_THINKING_MODE,
+              thinkingBudget: 8192,
               thinkingLevel: undefined,
             },
           }),
         }),
         'prompt-id-thinking-budget',
+        LlmRole.MAIN,
       );
     });
   });
@@ -1032,6 +1052,7 @@ describe('GeminiChat', () => {
         'test',
         'prompt-id-no-retry',
         new AbortController().signal,
+        LlmRole.MAIN,
       );
 
       await expect(
@@ -1080,6 +1101,7 @@ describe('GeminiChat', () => {
         'test message',
         'prompt-id-yield-retry',
         new AbortController().signal,
+        LlmRole.MAIN,
       );
       const events: StreamEvent[] = [];
       for await (const event of stream) {
@@ -1122,6 +1144,7 @@ describe('GeminiChat', () => {
         'test',
         'prompt-id-retry-success',
         new AbortController().signal,
+        LlmRole.MAIN,
       );
       const chunks: StreamEvent[] = [];
       for await (const chunk of stream) {
@@ -1194,6 +1217,7 @@ describe('GeminiChat', () => {
         'test message',
         'prompt-id-retry-temperature',
         new AbortController().signal,
+        LlmRole.MAIN,
       );
 
       for await (const _ of stream) {
@@ -1215,6 +1239,7 @@ describe('GeminiChat', () => {
           }),
         }),
         'prompt-id-retry-temperature',
+        LlmRole.MAIN,
       );
 
       // Second call (retry) should have temperature 1
@@ -1228,6 +1253,7 @@ describe('GeminiChat', () => {
           }),
         }),
         'prompt-id-retry-temperature',
+        LlmRole.MAIN,
       );
     });
 
@@ -1253,6 +1279,7 @@ describe('GeminiChat', () => {
         'test',
         'prompt-id-retry-fail',
         new AbortController().signal,
+        LlmRole.MAIN,
       );
       await expect(async () => {
         for await (const _ of stream) {
@@ -1319,6 +1346,7 @@ describe('GeminiChat', () => {
           'test message',
           'prompt-id-400',
           new AbortController().signal,
+          LlmRole.MAIN,
         );
 
         await expect(
@@ -1358,9 +1386,11 @@ describe('GeminiChat', () => {
           'test message',
           'prompt-id-429-retry',
           new AbortController().signal,
+          LlmRole.MAIN,
         );
 
         const events: StreamEvent[] = [];
+
         for await (const event of stream) {
           events.push(event);
         }
@@ -1407,9 +1437,11 @@ describe('GeminiChat', () => {
           'test message',
           'prompt-id-500-retry',
           new AbortController().signal,
+          LlmRole.MAIN,
         );
 
         const events: StreamEvent[] = [];
+
         for await (const event of stream) {
           events.push(event);
         }
@@ -1464,9 +1496,11 @@ describe('GeminiChat', () => {
           'test message',
           'prompt-id-fetch-error-retry',
           new AbortController().signal,
+          LlmRole.MAIN,
         );
 
         const events: StreamEvent[] = [];
+
         for await (const event of stream) {
           events.push(event);
         }
@@ -1528,6 +1562,7 @@ describe('GeminiChat', () => {
       'Second question',
       'prompt-id-retry-existing',
       new AbortController().signal,
+      LlmRole.MAIN,
     );
     for await (const _ of stream) {
       // consume stream
@@ -1600,6 +1635,7 @@ describe('GeminiChat', () => {
       'test empty stream',
       'prompt-id-empty-stream',
       new AbortController().signal,
+      LlmRole.MAIN,
     );
     const chunks: StreamEvent[] = [];
     for await (const chunk of stream) {
@@ -1681,6 +1717,7 @@ describe('GeminiChat', () => {
       'first',
       'prompt-1',
       new AbortController().signal,
+      LlmRole.MAIN,
     );
     const firstStreamIterator = firstStream[Symbol.asyncIterator]();
     await firstStreamIterator.next();
@@ -1691,6 +1728,7 @@ describe('GeminiChat', () => {
       'second',
       'prompt-2',
       new AbortController().signal,
+      LlmRole.MAIN,
     );
 
     // 5. Assert that only one API call has been made so far.
@@ -1796,6 +1834,7 @@ describe('GeminiChat', () => {
         'trigger 429',
         'prompt-id-fb1',
         new AbortController().signal,
+        LlmRole.MAIN,
       );
 
       // Consume stream to trigger logic
@@ -1862,6 +1901,7 @@ describe('GeminiChat', () => {
       'test message',
       'prompt-id-discard-test',
       new AbortController().signal,
+      LlmRole.MAIN,
     );
     const events: StreamEvent[] = [];
     for await (const event of stream) {
@@ -2078,6 +2118,7 @@ describe('GeminiChat', () => {
         'test',
         'prompt-healthy',
         new AbortController().signal,
+        LlmRole.MAIN,
       );
       for await (const _ of stream) {
         // consume
@@ -2113,6 +2154,7 @@ describe('GeminiChat', () => {
         'test',
         'prompt-sticky-once',
         new AbortController().signal,
+        LlmRole.MAIN,
       );
       for await (const _ of stream) {
         // consume
@@ -2163,6 +2205,7 @@ describe('GeminiChat', () => {
           'test',
           'prompt-fallback-arg',
           new AbortController().signal,
+          LlmRole.MAIN,
         );
         for await (const _ of stream) {
           // consume
@@ -2241,6 +2284,7 @@ describe('GeminiChat', () => {
         'test',
         'prompt-config-refresh',
         new AbortController().signal,
+        LlmRole.MAIN,
       );
       // Consume to drive both attempts
       for await (const _ of stream) {
@@ -2253,9 +2297,12 @@ describe('GeminiChat', () => {
         1,
         expect.objectContaining({
           model: 'model-a',
-          config: expect.objectContaining({ temperature: 0.1 }),
+          config: expect.objectContaining({
+            temperature: 0.1,
+          }),
         }),
         expect.any(String),
+        LlmRole.MAIN,
       );
       expect(
         mockContentGenerator.generateContentStream,
@@ -2263,9 +2310,12 @@ describe('GeminiChat', () => {
         2,
         expect.objectContaining({
           model: 'model-b',
-          config: expect.objectContaining({ temperature: 0.9 }),
+          config: expect.objectContaining({
+            temperature: 0.9,
+          }),
         }),
         expect.any(String),
+        LlmRole.MAIN,
       );
     });
   });
diff --git a/packages/core/src/core/geminiChat.ts b/packages/core/src/core/geminiChat.ts
index 3dc91e1b6c6..57be3771448 100644
--- a/packages/core/src/core/geminiChat.ts
+++ b/packages/core/src/core/geminiChat.ts
@@ -54,6 +54,7 @@ import {
   fireBeforeModelHook,
   fireBeforeToolSelectionHook,
 } from './geminiChatHookTriggers.js';
+import type { LlmRole } from '../telemetry/types.js';
 
 export enum StreamEventType {
   /** A regular content chunk from the API. */
@@ -260,6 +261,7 @@ export class GeminiChat {
     message: PartListUnion,
     prompt_id: string,
     signal: AbortSignal,
+    role: LlmRole,
   ): Promise<AsyncGenerator<StreamEvent>> {
     await this.sendPromise;
 
@@ -316,6 +318,7 @@ export class GeminiChat {
               requestContents,
               prompt_id,
               signal,
+              role,
             );
             isConnectionPhase = false;
             for await (const chunk of stream) {
@@ -383,6 +386,7 @@ export class GeminiChat {
     requestContents: Content[],
     prompt_id: string,
     abortSignal: AbortSignal,
+    role: LlmRole,
   ): Promise<AsyncGenerator<GenerateContentResponse>> {
     const contentsForPreviewModel =
       this.ensureActiveLoopHasThoughtSignatures(requestContents);
@@ -517,6 +521,7 @@ export class GeminiChat {
           config,
         },
         prompt_id,
+        role,
       );
     };
 
diff --git a/packages/core/src/core/geminiChat_network_retry.test.ts b/packages/core/src/core/geminiChat_network_retry.test.ts
index d8bd4b726db..778585e0a90 100644
--- a/packages/core/src/core/geminiChat_network_retry.test.ts
+++ b/packages/core/src/core/geminiChat_network_retry.test.ts
@@ -14,6 +14,7 @@ import { setSimulate429 } from '../utils/testUtils.js';
 import { HookSystem } from '../hooks/hookSystem.js';
 import { createMockMessageBus } from '../test-utils/mock-message-bus.js';
 import { createAvailabilityServiceMock } from '../availability/testUtils.js';
+import { LlmRole } from '../telemetry/types.js';
 
 // Mock fs module
 vi.mock('node:fs', () => ({
@@ -150,6 +151,7 @@ describe('GeminiChat Network Retries', () => {
       'test message',
       'prompt-id-retry-network',
       new AbortController().signal,
+      LlmRole.MAIN,
     );
 
     const events: StreamEvent[] = [];
@@ -219,6 +221,7 @@ describe('GeminiChat Network Retries', () => {
       'test message',
       'prompt-id-retry-fetch',
       new AbortController().signal,
+      LlmRole.MAIN,
     );
 
     const events: StreamEvent[] = [];
@@ -259,6 +262,7 @@ describe('GeminiChat Network Retries', () => {
       'test message',
       'prompt-id-no-retry',
       new AbortController().signal,
+      LlmRole.MAIN,
     );
 
     await expect(async () => {
diff --git a/packages/core/src/core/loggingContentGenerator.test.ts b/packages/core/src/core/loggingContentGenerator.test.ts
index e591f86be98..d884c3e5337 100644
--- a/packages/core/src/core/loggingContentGenerator.test.ts
+++ b/packages/core/src/core/loggingContentGenerator.test.ts
@@ -30,7 +30,7 @@ import type {
 import type { ContentGenerator } from './contentGenerator.js';
 import { LoggingContentGenerator } from './loggingContentGenerator.js';
 import type { Config } from '../config/config.js';
-import { ApiRequestEvent } from '../telemetry/types.js';
+import { ApiRequestEvent, LlmRole } from '../telemetry/types.js';
 
 describe('LoggingContentGenerator', () => {
   let wrapped: ContentGenerator;
@@ -87,13 +87,18 @@ describe('LoggingContentGenerator', () => {
       const promise = loggingContentGenerator.generateContent(
         req,
         userPromptId,
+        LlmRole.MAIN,
       );
 
       vi.advanceTimersByTime(1000);
 
       await promise;
 
-      expect(wrapped.generateContent).toHaveBeenCalledWith(req, userPromptId);
+      expect(wrapped.generateContent).toHaveBeenCalledWith(
+        req,
+        userPromptId,
+        LlmRole.MAIN,
+      );
       expect(logApiRequest).toHaveBeenCalledWith(
         config,
         expect.any(ApiRequestEvent),
@@ -116,6 +121,7 @@ describe('LoggingContentGenerator', () => {
       const promise = loggingContentGenerator.generateContent(
         req,
         userPromptId,
+        LlmRole.MAIN,
       );
 
       vi.advanceTimersByTime(1000);
@@ -154,12 +160,17 @@ describe('LoggingContentGenerator', () => {
       vi.mocked(wrapped.generateContentStream).mockResolvedValue(
         createAsyncGenerator(),
       );
+
       const startTime = new Date('2025-01-01T00:00:00.000Z');
+
       vi.setSystemTime(startTime);
 
       const stream = await loggingContentGenerator.generateContentStream(
         req,
+
         userPromptId,
+
+        LlmRole.MAIN,
       );
 
       vi.advanceTimersByTime(1000);
@@ -171,6 +182,7 @@ describe('LoggingContentGenerator', () => {
       expect(wrapped.generateContentStream).toHaveBeenCalledWith(
         req,
         userPromptId,
+        LlmRole.MAIN,
       );
       expect(logApiRequest).toHaveBeenCalledWith(
         config,
@@ -201,6 +213,7 @@ describe('LoggingContentGenerator', () => {
       const stream = await loggingContentGenerator.generateContentStream(
         req,
         userPromptId,
+        LlmRole.MAIN,
       );
 
       vi.advanceTimersByTime(1000);
diff --git a/packages/core/src/core/loggingContentGenerator.ts b/packages/core/src/core/loggingContentGenerator.ts
index de16b8de69e..0a7064238ed 100644
--- a/packages/core/src/core/loggingContentGenerator.ts
+++ b/packages/core/src/core/loggingContentGenerator.ts
@@ -22,6 +22,7 @@ import {
   ApiResponseEvent,
   ApiErrorEvent,
 } from '../telemetry/types.js';
+import type { LlmRole } from '../telemetry/llmRole.js';
 import type { Config } from '../config/config.js';
 import {
   logApiError,
@@ -55,6 +56,7 @@ export class LoggingContentGenerator implements ContentGenerator {
     contents: Content[],
     model: string,
     promptId: string,
+    role: LlmRole,
     generationConfig?: GenerateContentConfig,
     serverDetails?: ServerDetails,
   ): void {
@@ -70,6 +72,7 @@ export class LoggingContentGenerator implements ContentGenerator {
           server: serverDetails,
         },
         requestText,
+        role,
       ),
     );
   }
@@ -112,6 +115,7 @@ export class LoggingContentGenerator implements ContentGenerator {
     durationMs: number,
     model: string,
     prompt_id: string,
+    role: LlmRole,
     responseId: string | undefined,
     responseCandidates?: Candidate[],
     usageMetadata?: GenerateContentResponseUsageMetadata,
@@ -137,6 +141,7 @@ export class LoggingContentGenerator implements ContentGenerator {
         this.config.getContentGeneratorConfig()?.authType,
         usageMetadata,
         responseText,
+        role,
       ),
     );
   }
@@ -147,6 +152,7 @@ export class LoggingContentGenerator implements ContentGenerator {
     model: string,
     prompt_id: string,
     requestContents: Content[],
+    role: LlmRole,
     generationConfig?: GenerateContentConfig,
     serverDetails?: ServerDetails,
   ): void {
@@ -170,6 +176,7 @@ export class LoggingContentGenerator implements ContentGenerator {
         isStructuredError(error)
           ? (error as StructuredError).status
           : undefined,
+        role,
       ),
     );
   }
@@ -177,6 +184,7 @@ export class LoggingContentGenerator implements ContentGenerator {
   async generateContent(
     req: GenerateContentParameters,
     userPromptId: string,
+    role: LlmRole,
   ): Promise<GenerateContentResponse> {
     return runInDevTraceSpan(
       {
@@ -192,6 +200,7 @@ export class LoggingContentGenerator implements ContentGenerator {
           contents,
           req.model,
           userPromptId,
+          role,
           req.config,
           serverDetails,
         );
@@ -199,6 +208,7 @@ export class LoggingContentGenerator implements ContentGenerator {
           const response = await this.wrapped.generateContent(
             req,
             userPromptId,
+            role,
           );
           spanMetadata.output = {
             response,
@@ -210,6 +220,7 @@ export class LoggingContentGenerator implements ContentGenerator {
             durationMs,
             response.modelVersion || req.model,
             userPromptId,
+            role,
             response.responseId,
             response.candidates,
             response.usageMetadata,
@@ -226,6 +237,7 @@ export class LoggingContentGenerator implements ContentGenerator {
             req.model,
             userPromptId,
             contents,
+            role,
             req.config,
             serverDetails,
           );
@@ -238,6 +250,7 @@ export class LoggingContentGenerator implements ContentGenerator {
   async generateContentStream(
     req: GenerateContentParameters,
     userPromptId: string,
+    role: LlmRole,
   ): Promise<AsyncGenerator<GenerateContentResponse>> {
     return runInDevTraceSpan(
       {
@@ -255,13 +268,18 @@ export class LoggingContentGenerator implements ContentGenerator {
           toContents(req.contents),
           req.model,
           userPromptId,
+          role,
           req.config,
           serverDetails,
         );
 
         let stream: AsyncGenerator<GenerateContentResponse>;
         try {
-          stream = await this.wrapped.generateContentStream(req, userPromptId);
+          stream = await this.wrapped.generateContentStream(
+            req,
+            userPromptId,
+            role,
+          );
         } catch (error) {
           const durationMs = Date.now() - startTime;
           this._logApiError(
@@ -270,6 +288,7 @@ export class LoggingContentGenerator implements ContentGenerator {
             req.model,
             userPromptId,
             toContents(req.contents),
+            role,
             req.config,
             serverDetails,
           );
@@ -281,6 +300,7 @@ export class LoggingContentGenerator implements ContentGenerator {
           stream,
           startTime,
           userPromptId,
+          role,
           spanMetadata,
           endSpan,
         );
@@ -293,6 +313,7 @@ export class LoggingContentGenerator implements ContentGenerator {
     stream: AsyncGenerator<GenerateContentResponse>,
     startTime: number,
     userPromptId: string,
+    role: LlmRole,
     spanMetadata: SpanMetadata,
     endSpan: () => void,
   ): AsyncGenerator<GenerateContentResponse> {
@@ -316,6 +337,7 @@ export class LoggingContentGenerator implements ContentGenerator {
         durationMs,
         responses[0]?.modelVersion || req.model,
         userPromptId,
+        role,
         responses[0]?.responseId,
         responses.flatMap((response) => response.candidates || []),
         lastUsageMetadata,
@@ -339,6 +361,7 @@ export class LoggingContentGenerator implements ContentGenerator {
         responses[0]?.modelVersion || req.model,
         userPromptId,
         requestContents,
+        role,
         req.config,
         serverDetails,
       );
diff --git a/packages/core/src/core/recordingContentGenerator.test.ts b/packages/core/src/core/recordingContentGenerator.test.ts
index c69c62ebfa0..cbdb239ecfe 100644
--- a/packages/core/src/core/recordingContentGenerator.test.ts
+++ b/packages/core/src/core/recordingContentGenerator.test.ts
@@ -18,6 +18,7 @@ import { describe, it, expect, vi, beforeEach, type Mock } from 'vitest';
 import { safeJsonStringify } from '../utils/safeJsonStringify.js';
 import type { ContentGenerator } from './contentGenerator.js';
 import { RecordingContentGenerator } from './recordingContentGenerator.js';
+import { LlmRole } from '../telemetry/types.js';
 
 vi.mock('node:fs', () => ({
   appendFileSync: vi.fn(),
@@ -51,9 +52,14 @@ describe('RecordingContentGenerator', () => {
     const response = await recorder.generateContent(
       {} as GenerateContentParameters,
       'id1',
+      LlmRole.MAIN,
     );
     expect(response).toEqual(mockResponse);
-    expect(mockRealGenerator.generateContent).toHaveBeenCalledWith({}, 'id1');
+    expect(mockRealGenerator.generateContent).toHaveBeenCalledWith(
+      {},
+      'id1',
+      LlmRole.MAIN,
+    );
 
     expect(appendFileSync).toHaveBeenCalledWith(
       filePath,
@@ -90,6 +96,7 @@ describe('RecordingContentGenerator', () => {
     const stream = await recorder.generateContentStream(
       {} as GenerateContentParameters,
       'id1',
+      LlmRole.MAIN,
     );
     const responses = [];
     for await (const response of stream) {
@@ -100,6 +107,7 @@ describe('RecordingContentGenerator', () => {
     expect(mockRealGenerator.generateContentStream).toHaveBeenCalledWith(
       {},
       'id1',
+      LlmRole.MAIN,
     );
 
     expect(appendFileSync).toHaveBeenCalledWith(
diff --git a/packages/core/src/core/recordingContentGenerator.ts b/packages/core/src/core/recordingContentGenerator.ts
index 27abcb418ff..121cd838f4a 100644
--- a/packages/core/src/core/recordingContentGenerator.ts
+++ b/packages/core/src/core/recordingContentGenerator.ts
@@ -17,6 +17,7 @@ import type { ContentGenerator } from './contentGenerator.js';
 import type { FakeResponse } from './fakeContentGenerator.js';
 import type { UserTierId } from '../code_assist/types.js';
 import { safeJsonStringify } from '../utils/safeJsonStringify.js';
+import type { LlmRole } from '../telemetry/types.js';
 
 // A ContentGenerator that wraps another content generator and records all the
 // responses, with the ability to write them out to a file. These files are
@@ -35,10 +36,12 @@ export class RecordingContentGenerator implements ContentGenerator {
   async generateContent(
     request: GenerateContentParameters,
     userPromptId: string,
+    role: LlmRole,
   ): Promise<GenerateContentResponse> {
     const response = await this.realGenerator.generateContent(
       request,
       userPromptId,
+      role,
     );
     const recordedResponse: FakeResponse = {
       method: 'generateContent',
@@ -54,6 +57,7 @@ export class RecordingContentGenerator implements ContentGenerator {
   async generateContentStream(
     request: GenerateContentParameters,
     userPromptId: string,
+    role: LlmRole,
   ): Promise<AsyncGenerator<GenerateContentResponse>> {
     const recordedResponse: FakeResponse = {
       method: 'generateContentStream',
@@ -63,6 +67,7 @@ export class RecordingContentGenerator implements ContentGenerator {
     const realResponses = await this.realGenerator.generateContentStream(
       request,
       userPromptId,
+      role,
     );
 
     async function* stream(filePath: string) {
diff --git a/packages/core/src/core/turn.test.ts b/packages/core/src/core/turn.test.ts
index e951d809330..20803b86651 100644
--- a/packages/core/src/core/turn.test.ts
+++ b/packages/core/src/core/turn.test.ts
@@ -14,6 +14,7 @@ import type { GenerateContentResponse, Part, Content } from '@google/genai';
 import { reportError } from '../utils/errorReporting.js';
 import type { GeminiChat } from './geminiChat.js';
 import { InvalidStreamError, StreamEventType } from './geminiChat.js';
+import { LlmRole } from '../telemetry/types.js';
 
 const mockSendMessageStream = vi.fn();
 const mockGetHistory = vi.fn();
@@ -102,6 +103,7 @@ describe('Turn', () => {
         reqParts,
         'prompt-id-1',
         expect.any(AbortSignal),
+        LlmRole.MAIN,
       );
 
       expect(events).toEqual([
diff --git a/packages/core/src/core/turn.ts b/packages/core/src/core/turn.ts
index 86c7fdf49c6..af0b7ee5752 100644
--- a/packages/core/src/core/turn.ts
+++ b/packages/core/src/core/turn.ts
@@ -32,6 +32,7 @@ import { parseThought, type ThoughtSummary } from '../utils/thoughtUtils.js';
 import { createUserContent } from '@google/genai';
 import type { ModelConfigKey } from '../services/modelConfigService.js';
 import { getCitations } from '../utils/generateContentResponseUtilities.js';
+import { LlmRole } from '../telemetry/types.js';
 
 // Define a structure for tools passed to the server
 export interface ServerTool {
@@ -242,6 +243,7 @@ export class Turn {
     modelConfigKey: ModelConfigKey,
     req: PartListUnion,
     signal: AbortSignal,
+    role: LlmRole = LlmRole.MAIN,
   ): AsyncGenerator<ServerGeminiStreamEvent> {
     try {
       // Note: This assumes `sendMessageStream` yields events like
@@ -251,6 +253,7 @@ export class Turn {
         req,
         this.prompt_id,
         signal,
+        role,
       );
 
       for await (const streamEvent of responseStream) {
diff --git a/packages/core/src/output/json-formatter.test.ts b/packages/core/src/output/json-formatter.test.ts
index 14d2cb47c4a..13321fae77a 100644
--- a/packages/core/src/output/json-formatter.test.ts
+++ b/packages/core/src/output/json-formatter.test.ts
@@ -79,6 +79,7 @@ describe('JsonFormatter', () => {
             thoughts: 103,
             tool: 0,
           },
+          roles: {},
         },
         'gemini-2.5-flash': {
           api: {
@@ -95,6 +96,7 @@ describe('JsonFormatter', () => {
             thoughts: 138,
             tool: 0,
           },
+          roles: {},
         },
       },
       tools: {
diff --git a/packages/core/src/output/stream-json-formatter.test.ts b/packages/core/src/output/stream-json-formatter.test.ts
index 557b72a0a9d..69dbaac23bb 100644
--- a/packages/core/src/output/stream-json-formatter.test.ts
+++ b/packages/core/src/output/stream-json-formatter.test.ts
@@ -289,6 +289,7 @@ describe('StreamJsonFormatter', () => {
           thoughts: 0,
           tool: 0,
         },
+        roles: {},
       };
       metrics.tools.totalCalls = 2;
       metrics.tools.totalDecisions[ToolCallDecision.AUTO_ACCEPT] = 2;
@@ -319,6 +320,7 @@ describe('StreamJsonFormatter', () => {
           thoughts: 0,
           tool: 0,
         },
+        roles: {},
       };
       metrics.models['gemini-ultra'] = {
         api: { totalRequests: 1, totalErrors: 0, totalLatencyMs: 2000 },
@@ -331,6 +333,7 @@ describe('StreamJsonFormatter', () => {
           thoughts: 0,
           tool: 0,
         },
+        roles: {},
       };
       metrics.tools.totalCalls = 5;
 
@@ -360,6 +363,7 @@ describe('StreamJsonFormatter', () => {
           thoughts: 0,
           tool: 0,
         },
+        roles: {},
       };
 
       const result = formatter.convertToStreamStats(metrics, 1200);
diff --git a/packages/core/src/routing/strategies/classifierStrategy.ts b/packages/core/src/routing/strategies/classifierStrategy.ts
index 4747bc5352a..944efc6041c 100644
--- a/packages/core/src/routing/strategies/classifierStrategy.ts
+++ b/packages/core/src/routing/strategies/classifierStrategy.ts
@@ -20,6 +20,7 @@ import {
   isFunctionResponse,
 } from '../../utils/messageInspectors.js';
 import { debugLogger } from '../../utils/debugLogger.js';
+import { LlmRole } from '../../telemetry/types.js';
 
 // The number of recent history turns to provide to the router for context.
 const HISTORY_TURNS_FOR_CONTEXT = 4;
@@ -161,6 +162,7 @@ export class ClassifierStrategy implements RoutingStrategy {
         systemInstruction: CLASSIFIER_SYSTEM_PROMPT,
         abortSignal: context.signal,
         promptId,
+        role: LlmRole.UTILITY_ROUTER,
       });
 
       const routerResponse = ClassifierResponseSchema.parse(jsonResponse);
diff --git a/packages/core/src/services/chatCompressionService.ts b/packages/core/src/services/chatCompressionService.ts
index 2336b75f551..d71fb81cedc 100644
--- a/packages/core/src/services/chatCompressionService.ts
+++ b/packages/core/src/services/chatCompressionService.ts
@@ -24,6 +24,7 @@ import {
 } from '../config/models.js';
 import { firePreCompressHook } from '../core/sessionHookTriggers.js';
 import { PreCompressTrigger } from '../hooks/types.js';
+import { LlmRole } from '../telemetry/types.js';
 
 /**
  * Default threshold for compression token count as a fraction of the model's
@@ -194,6 +195,7 @@ export class ChatCompressionService {
       promptId,
       // TODO(joshualitt): wire up a sensible abort signal,
       abortSignal: new AbortController().signal,
+      role: LlmRole.UTILITY_COMPRESSOR,
     });
     const summary = getResponseText(summaryResponse) ?? '';
 
diff --git a/packages/core/src/services/loopDetectionService.ts b/packages/core/src/services/loopDetectionService.ts
index d8049dbdb68..41c5566a425 100644
--- a/packages/core/src/services/loopDetectionService.ts
+++ b/packages/core/src/services/loopDetectionService.ts
@@ -25,6 +25,7 @@ import {
   isFunctionResponse,
 } from '../utils/messageInspectors.js';
 import { debugLogger } from '../utils/debugLogger.js';
+import { LlmRole } from '../telemetry/types.js';
 
 const TOOL_CALL_LOOP_THRESHOLD = 5;
 const CONTENT_LOOP_THRESHOLD = 10;
@@ -529,6 +530,7 @@ export class LoopDetectionService {
         abortSignal: signal,
         promptId: this.promptId,
         maxAttempts: 2,
+        role: LlmRole.UTILITY_LOOP_DETECTOR,
       });
 
       if (
diff --git a/packages/core/src/services/sessionSummaryService.ts b/packages/core/src/services/sessionSummaryService.ts
index 98ffd66fcac..09c60a2e310 100644
--- a/packages/core/src/services/sessionSummaryService.ts
+++ b/packages/core/src/services/sessionSummaryService.ts
@@ -10,6 +10,7 @@ import { partListUnionToString } from '../core/geminiRequest.js';
 import { debugLogger } from '../utils/debugLogger.js';
 import type { Content } from '@google/genai';
 import { getResponseText } from '../utils/partUtils.js';
+import { LlmRole } from '../telemetry/types.js';
 
 const DEFAULT_MAX_MESSAGES = 20;
 const DEFAULT_TIMEOUT_MS = 5000;
@@ -124,6 +125,7 @@ export class SessionSummaryService {
           contents,
           abortSignal: abortController.signal,
           promptId: 'session-summary-generation',
+          role: LlmRole.UTILITY_SUMMARIZER,
         });
 
         const summary = getResponseText(response);
diff --git a/packages/core/src/telemetry/index.ts b/packages/core/src/telemetry/index.ts
index 11bc00773f9..661dce3c0bd 100644
--- a/packages/core/src/telemetry/index.ts
+++ b/packages/core/src/telemetry/index.ts
@@ -63,6 +63,7 @@ export {
   WebFetchFallbackAttemptEvent,
   ToolCallDecision,
 } from './types.js';
+export { LlmRole } from './llmRole.js';
 export { makeSlashCommandEvent, makeChatCompressionEvent } from './types.js';
 export type { TelemetryEvent } from './types.js';
 export { SpanStatusCode, ValueType } from '@opentelemetry/api';
diff --git a/packages/core/src/telemetry/llmRole.ts b/packages/core/src/telemetry/llmRole.ts
new file mode 100644
index 00000000000..6f8474dbb73
--- /dev/null
+++ b/packages/core/src/telemetry/llmRole.ts
@@ -0,0 +1,19 @@
+/**
+ * @license
+ * Copyright 2025 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+export enum LlmRole {
+  MAIN = 'main',
+  SUBAGENT = 'subagent',
+  SUBAGENT_CODEBASE_INVESTIGATOR = 'subagent_codebase_investigator',
+  UTILITY_TOOL = 'utility_tool',
+  UTILITY_COMPRESSOR = 'utility_compressor',
+  UTILITY_SUMMARIZER = 'utility_summarizer',
+  UTILITY_ROUTER = 'utility_router',
+  UTILITY_LOOP_DETECTOR = 'utility_loop_detector',
+  UTILITY_NEXT_SPEAKER = 'utility_next_speaker',
+  UTILITY_EDIT_CORRECTOR = 'utility_edit_corrector',
+  UTILITY_AUTOCOMPLETE = 'utility_autocomplete',
+}
diff --git a/packages/core/src/telemetry/loggers.ts b/packages/core/src/telemetry/loggers.ts
index 8a2c08f2a5e..411def04e09 100644
--- a/packages/core/src/telemetry/loggers.ts
+++ b/packages/core/src/telemetry/loggers.ts
@@ -184,7 +184,12 @@ export function logApiRequest(config: Config, event: ApiRequestEvent): void {
   ClearcutLogger.getInstance(config)?.logApiRequestEvent(event);
   bufferTelemetryEvent(() => {
     const logger = logs.getLogger(SERVICE_NAME);
-    logger.emit(event.toLogRecord(config));
+    const logRecord: LogRecord = event.toLogRecord(config);
+    if (event.role) {
+      if (!logRecord.attributes) logRecord.attributes = {};
+      logRecord.attributes['role'] = event.role;
+    }
+    logger.emit(logRecord);
     logger.emit(event.toSemanticLogRecord(config));
   });
 }
diff --git a/packages/core/src/telemetry/types.ts b/packages/core/src/telemetry/types.ts
index 95893f34d02..79df62e4c44 100644
--- a/packages/core/src/telemetry/types.ts
+++ b/packages/core/src/telemetry/types.ts
@@ -39,6 +39,8 @@ import {
   toSystemInstruction,
 } from './semantic.js';
 import { sanitizeHookName } from './sanitize.js';
+import { LlmRole } from './llmRole.js';
+export { LlmRole };
 
 export interface BaseTelemetryEvent {
   'event.name': string;
@@ -363,17 +365,20 @@ export class ApiRequestEvent implements BaseTelemetryEvent {
   model: string;
   prompt: GenAIPromptDetails;
   request_text?: string;
+  role?: LlmRole;
 
   constructor(
     model: string,
     prompt_details: GenAIPromptDetails,
     request_text?: string,
+    role?: LlmRole,
   ) {
     this['event.name'] = 'api_request';
     this['event.timestamp'] = new Date().toISOString();
     this.model = model;
     this.prompt = prompt_details;
     this.request_text = request_text;
+    this.role = role;
   }
 
   toLogRecord(config: Config): LogRecord {
@@ -385,6 +390,9 @@ export class ApiRequestEvent implements BaseTelemetryEvent {
       prompt_id: this.prompt.prompt_id,
       request_text: this.request_text,
     };
+    if (this.role) {
+      attributes['role'] = this.role;
+    }
     return { body: `API request to ${this.model}.`, attributes };
   }
 
@@ -433,6 +441,7 @@ export class ApiErrorEvent implements BaseTelemetryEvent {
   status_code?: number | string;
   duration_ms: number;
   auth_type?: string;
+  role?: LlmRole;
 
   constructor(
     model: string,
@@ -442,6 +451,7 @@ export class ApiErrorEvent implements BaseTelemetryEvent {
     auth_type?: string,
     error_type?: string,
     status_code?: number | string,
+    role?: LlmRole,
   ) {
     this['event.name'] = 'api_error';
     this['event.timestamp'] = new Date().toISOString();
@@ -452,6 +462,7 @@ export class ApiErrorEvent implements BaseTelemetryEvent {
     this.duration_ms = duration_ms;
     this.prompt = prompt_details;
     this.auth_type = auth_type;
+    this.role = role;
   }
 
   toLogRecord(config: Config): LogRecord {
@@ -470,6 +481,10 @@ export class ApiErrorEvent implements BaseTelemetryEvent {
       auth_type: this.auth_type,
     };
 
+    if (this.role) {
+      attributes['role'] = this.role;
+    }
+
     if (this.error_type) {
       attributes['error.type'] = this.error_type;
     }
@@ -578,6 +593,7 @@ export class ApiResponseEvent implements BaseTelemetryEvent {
   response: GenAIResponseDetails;
   usage: GenAIUsageDetails;
   finish_reasons: OTelFinishReason[];
+  role?: LlmRole;
 
   constructor(
     model: string,
@@ -587,6 +603,7 @@ export class ApiResponseEvent implements BaseTelemetryEvent {
     auth_type?: string,
     usage_data?: GenerateContentResponseUsageMetadata,
     response_text?: string,
+    role?: LlmRole,
   ) {
     this['event.name'] = 'api_response';
     this['event.timestamp'] = new Date().toISOString();
@@ -607,6 +624,7 @@ export class ApiResponseEvent implements BaseTelemetryEvent {
       total_token_count: usage_data?.totalTokenCount ?? 0,
     };
     this.finish_reasons = toFinishReasons(this.response.candidates);
+    this.role = role;
   }
 
   toLogRecord(config: Config): LogRecord {
@@ -627,6 +645,9 @@ export class ApiResponseEvent implements BaseTelemetryEvent {
       status_code: this.status_code,
       finish_reasons: this.finish_reasons,
     };
+    if (this.role) {
+      attributes['role'] = this.role;
+    }
     if (this.response_text) {
       attributes['response_text'] = this.response_text;
     }
diff --git a/packages/core/src/telemetry/uiTelemetry.test.ts b/packages/core/src/telemetry/uiTelemetry.test.ts
index 825852f5070..52f0911730c 100644
--- a/packages/core/src/telemetry/uiTelemetry.test.ts
+++ b/packages/core/src/telemetry/uiTelemetry.test.ts
@@ -181,6 +181,7 @@ describe('UiTelemetryService', () => {
           thoughts: 2,
           tool: 3,
         },
+        roles: {},
       });
       expect(service.getLastPromptTokenCount()).toBe(0);
     });
@@ -236,6 +237,7 @@ describe('UiTelemetryService', () => {
           thoughts: 6,
           tool: 9,
         },
+        roles: {},
       });
       expect(service.getLastPromptTokenCount()).toBe(0);
     });
@@ -311,6 +313,7 @@ describe('UiTelemetryService', () => {
           thoughts: 0,
           tool: 0,
         },
+        roles: {},
       });
     });
 
@@ -356,6 +359,35 @@ describe('UiTelemetryService', () => {
           thoughts: 2,
           tool: 3,
         },
+        roles: {},
+      });
+    });
+
+    it('should update role metrics when processing an ApiErrorEvent with a role', () => {
+      const event = {
+        'event.name': EVENT_API_ERROR,
+        model: 'gemini-2.5-pro',
+        duration_ms: 300,
+        error: 'Something went wrong',
+        role: 'utility_tool',
+      } as unknown as ApiErrorEvent & { 'event.name': typeof EVENT_API_ERROR };
+
+      service.addEvent(event);
+
+      const metrics = service.getMetrics();
+      expect(metrics.models['gemini-2.5-pro'].roles['utility_tool']).toEqual({
+        totalRequests: 1,
+        totalErrors: 1,
+        totalLatencyMs: 300,
+        tokens: {
+          input: 0,
+          prompt: 0,
+          candidates: 0,
+          total: 0,
+          cached: 0,
+          thoughts: 0,
+          tool: 0,
+        },
       });
     });
   });
diff --git a/packages/core/src/telemetry/uiTelemetry.ts b/packages/core/src/telemetry/uiTelemetry.ts
index 6caf2a86063..8c9f2adb83d 100644
--- a/packages/core/src/telemetry/uiTelemetry.ts
+++ b/packages/core/src/telemetry/uiTelemetry.ts
@@ -18,6 +18,8 @@ import type {
   ToolCallEvent,
 } from './types.js';
 
+import type { LlmRole } from './types.js';
+
 export type UiEvent =
   | (ApiResponseEvent & { 'event.name': typeof EVENT_API_RESPONSE })
   | (ApiErrorEvent & { 'event.name': typeof EVENT_API_ERROR })
@@ -36,6 +38,21 @@ export interface ToolCallStats {
   };
 }
 
+export interface RoleMetrics {
+  totalRequests: number;
+  totalErrors: number;
+  totalLatencyMs: number;
+  tokens: {
+    input: number;
+    prompt: number;
+    candidates: number;
+    total: number;
+    cached: number;
+    thoughts: number;
+    tool: number;
+  };
+}
+
 export interface ModelMetrics {
   api: {
     totalRequests: number;
@@ -51,6 +68,7 @@ export interface ModelMetrics {
     thoughts: number;
     tool: number;
   };
+  roles: Partial<Record<LlmRole, RoleMetrics>>;
 }
 
 export interface SessionMetrics {
@@ -74,6 +92,21 @@ export interface SessionMetrics {
   };
 }
 
+const createInitialRoleMetrics = (): RoleMetrics => ({
+  totalRequests: 0,
+  totalErrors: 0,
+  totalLatencyMs: 0,
+  tokens: {
+    input: 0,
+    prompt: 0,
+    candidates: 0,
+    total: 0,
+    cached: 0,
+    thoughts: 0,
+    tool: 0,
+  },
+});
+
 const createInitialModelMetrics = (): ModelMetrics => ({
   api: {
     totalRequests: 0,
@@ -89,6 +122,7 @@ const createInitialModelMetrics = (): ModelMetrics => ({
     thoughts: 0,
     tool: 0,
   },
+  roles: {},
 });
 
 const createInitialMetrics = (): SessionMetrics => ({
@@ -177,6 +211,25 @@ export class UiTelemetryService extends EventEmitter {
       0,
       modelMetrics.tokens.prompt - modelMetrics.tokens.cached,
     );
+
+    if (event.role) {
+      if (!modelMetrics.roles[event.role]) {
+        modelMetrics.roles[event.role] = createInitialRoleMetrics();
+      }
+      const roleMetrics = modelMetrics.roles[event.role]!;
+      roleMetrics.totalRequests++;
+      roleMetrics.totalLatencyMs += event.duration_ms;
+      roleMetrics.tokens.prompt += event.usage.input_token_count;
+      roleMetrics.tokens.candidates += event.usage.output_token_count;
+      roleMetrics.tokens.total += event.usage.total_token_count;
+      roleMetrics.tokens.cached += event.usage.cached_content_token_count;
+      roleMetrics.tokens.thoughts += event.usage.thoughts_token_count;
+      roleMetrics.tokens.tool += event.usage.tool_token_count;
+      roleMetrics.tokens.input = Math.max(
+        0,
+        roleMetrics.tokens.prompt - roleMetrics.tokens.cached,
+      );
+    }
   }
 
   private processApiError(event: ApiErrorEvent) {
@@ -184,6 +237,16 @@ export class UiTelemetryService extends EventEmitter {
     modelMetrics.api.totalRequests++;
     modelMetrics.api.totalErrors++;
     modelMetrics.api.totalLatencyMs += event.duration_ms;
+
+    if (event.role) {
+      if (!modelMetrics.roles[event.role]) {
+        modelMetrics.roles[event.role] = createInitialRoleMetrics();
+      }
+      const roleMetrics = modelMetrics.roles[event.role]!;
+      roleMetrics.totalRequests++;
+      roleMetrics.totalErrors++;
+      roleMetrics.totalLatencyMs += event.duration_ms;
+    }
   }
 
   private processToolCall(event: ToolCallEvent) {
diff --git a/packages/core/src/tools/web-fetch.ts b/packages/core/src/tools/web-fetch.ts
index 57591343f3f..d7ce113dde8 100644
--- a/packages/core/src/tools/web-fetch.ts
+++ b/packages/core/src/tools/web-fetch.ts
@@ -27,6 +27,7 @@ import {
   logWebFetchFallbackAttempt,
   WebFetchFallbackAttemptEvent,
 } from '../telemetry/index.js';
+import { LlmRole } from '../telemetry/llmRole.js';
 import { WEB_FETCH_TOOL_NAME } from './tool-names.js';
 import { debugLogger } from '../utils/debugLogger.js';
 import { retryWithBackoff } from '../utils/retry.js';
@@ -187,6 +188,7 @@ ${textContent}
         { model: 'web-fetch-fallback' },
         [{ role: 'user', parts: [{ text: fallbackPrompt }] }],
         signal,
+        LlmRole.UTILITY_TOOL,
       );
       const resultText = getResponseText(result) || '';
       return {
@@ -271,6 +273,7 @@ ${textContent}
         { model: 'web-fetch' },
         [{ role: 'user', parts: [{ text: userPrompt }] }],
         signal, // Pass signal
+        LlmRole.UTILITY_TOOL,
       );
 
       debugLogger.debug(
diff --git a/packages/core/src/tools/web-search.ts b/packages/core/src/tools/web-search.ts
index c85ca02a6cd..42891ea1261 100644
--- a/packages/core/src/tools/web-search.ts
+++ b/packages/core/src/tools/web-search.ts
@@ -14,6 +14,7 @@ import { ToolErrorType } from './tool-error.js';
 import { getErrorMessage } from '../utils/errors.js';
 import { type Config } from '../config/config.js';
 import { getResponseText } from '../utils/partUtils.js';
+import { LlmRole } from '../telemetry/llmRole.js';
 
 interface GroundingChunkWeb {
   uri?: string;
@@ -83,6 +84,7 @@ class WebSearchToolInvocation extends BaseToolInvocation<
         { model: 'web-search' },
         [{ role: 'user', parts: [{ text: this.params.query }] }],
         signal,
+        LlmRole.UTILITY_TOOL,
       );
 
       const responseText = getResponseText(response);
diff --git a/packages/core/src/utils/editCorrector.ts b/packages/core/src/utils/editCorrector.ts
index 9c74d81f5a9..50f91c93c5a 100644
--- a/packages/core/src/utils/editCorrector.ts
+++ b/packages/core/src/utils/editCorrector.ts
@@ -22,6 +22,7 @@ import {
 } from '../utils/messageInspectors.js';
 import * as fs from 'node:fs';
 import { promptIdContext } from './promptIdContext.js';
+import { LlmRole } from '../telemetry/types.js';
 
 const CODE_CORRECTION_SYSTEM_PROMPT = `
 You are an expert code-editing assistant. Your task is to analyze a failed edit attempt and provide a corrected version of the text snippets.
@@ -418,6 +419,7 @@ Return ONLY the corrected target snippet in the specified JSON format with the k
       abortSignal,
       systemInstruction: CODE_CORRECTION_SYSTEM_PROMPT,
       promptId: getPromptId(),
+      role: LlmRole.UTILITY_EDIT_CORRECTOR,
     });
 
     if (
@@ -507,6 +509,7 @@ Return ONLY the corrected string in the specified JSON format with the key 'corr
       abortSignal,
       systemInstruction: CODE_CORRECTION_SYSTEM_PROMPT,
       promptId: getPromptId(),
+      role: LlmRole.UTILITY_EDIT_CORRECTOR,
     });
 
     if (
@@ -577,6 +580,7 @@ Return ONLY the corrected string in the specified JSON format with the key 'corr
       abortSignal,
       systemInstruction: CODE_CORRECTION_SYSTEM_PROMPT,
       promptId: getPromptId(),
+      role: LlmRole.UTILITY_EDIT_CORRECTOR,
     });
 
     if (
@@ -644,6 +648,7 @@ Return ONLY the corrected string in the specified JSON format with the key 'corr
       abortSignal,
       systemInstruction: CODE_CORRECTION_SYSTEM_PROMPT,
       promptId: getPromptId(),
+      role: LlmRole.UTILITY_EDIT_CORRECTOR,
     });
 
     if (
diff --git a/packages/core/src/utils/llm-edit-fixer.ts b/packages/core/src/utils/llm-edit-fixer.ts
index 363c973cd7e..d83bcb2c5fd 100644
--- a/packages/core/src/utils/llm-edit-fixer.ts
+++ b/packages/core/src/utils/llm-edit-fixer.ts
@@ -10,6 +10,7 @@ import { type BaseLlmClient } from '../core/baseLlmClient.js';
 import { LruCache } from './LruCache.js';
 import { promptIdContext } from './promptIdContext.js';
 import { debugLogger } from './debugLogger.js';
+import { LlmRole } from '../telemetry/types.js';
 
 const MAX_CACHE_SIZE = 50;
 const GENERATE_JSON_TIMEOUT_MS = 40000; // 40 seconds
@@ -182,6 +183,7 @@ export async function FixLLMEditWithInstruction(
       systemInstruction: EDIT_SYS_PROMPT,
       promptId,
       maxAttempts: 1,
+      role: LlmRole.UTILITY_EDIT_CORRECTOR,
     },
     GENERATE_JSON_TIMEOUT_MS,
   );
diff --git a/packages/core/src/utils/nextSpeakerChecker.ts b/packages/core/src/utils/nextSpeakerChecker.ts
index 76b1c6a440a..e5b54340f6d 100644
--- a/packages/core/src/utils/nextSpeakerChecker.ts
+++ b/packages/core/src/utils/nextSpeakerChecker.ts
@@ -9,6 +9,7 @@ import type { BaseLlmClient } from '../core/baseLlmClient.js';
 import type { GeminiChat } from '../core/geminiChat.js';
 import { isFunctionResponse } from './messageInspectors.js';
 import { debugLogger } from './debugLogger.js';
+import { LlmRole } from '../telemetry/types.js';
 
 const CHECK_PROMPT = `Analyze *only* the content and structure of your immediately preceding response (your last turn in the conversation history). Based *strictly* on that response, determine who should logically speak next: the 'user' or the 'model' (you).
 **Decision Rules (apply in order):**
@@ -115,6 +116,7 @@ export async function checkNextSpeaker(
       schema: RESPONSE_SCHEMA,
       abortSignal,
       promptId,
+      role: LlmRole.UTILITY_NEXT_SPEAKER,
     })) as unknown as NextSpeakerResponse;
 
     if (
diff --git a/packages/core/src/utils/summarizer.ts b/packages/core/src/utils/summarizer.ts
index b25961e1492..99653d4c598 100644
--- a/packages/core/src/utils/summarizer.ts
+++ b/packages/core/src/utils/summarizer.ts
@@ -11,6 +11,7 @@ import { getResponseText, partToString } from './partUtils.js';
 import { debugLogger } from './debugLogger.js';
 import type { ModelConfigKey } from '../services/modelConfigService.js';
 import type { Config } from '../config/config.js';
+import { LlmRole } from '../telemetry/llmRole.js';
 
 /**
  * A function that summarizes the result of a tool execution.
@@ -94,6 +95,7 @@ export async function summarizeToolOutput(
       modelConfigKey,
       contents,
       abortSignal,
+      LlmRole.UTILITY_SUMMARIZER,
     );
     return getResponseText(parsedResponse) || textToSummarize;
   } catch (error) {