Skip to content

feat: add role-specific statistics to telemetry and UI (cont. #15234) #18824

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
yunaseoul merged 5 commits into from
Feb 17, 2026
Merged

feat: add role-specific statistics to telemetry and UI (cont. #15234) #18824

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
74eece1
feat: add role-specific statistics to telemetry and UI (cont. #15234)
Feb 11, 2026
6e48392
test: add LLM role logging tests and simplify telemetry loggers
Feb 11, 2026
dfc6da6
consolidate subagent roles into one llm role to address original PR c…
Feb 12, 2026
0cbb2c3
remove role-specific stats from the main /stats, following the UX fee…
Feb 12, 2026
a1470a3
Filter out invalid LLM roles to fix the type lint error.
Feb 17, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
187 changes: 186 additions & 1 deletion packages/cli/src/ui/components/ModelStatsDisplay.test.tsx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@ import * as SessionContext from '../contexts/SessionContext.js';
import * as SettingsContext from '../contexts/SettingsContext.js';
import type { LoadedSettings } from '../../config/settings.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) => {
Expand Down Expand Up @@ -118,6 +118,7 @@ describe('<ModelStatsDisplay />', () => {
thoughts: 0,
tool: 0,
},
roles: {},
},
},
tools: {
Expand Down Expand Up @@ -160,6 +161,7 @@ describe('<ModelStatsDisplay />', () => {
thoughts: 2,
tool: 0,
},
roles: {},
},
'gemini-2.5-flash': {
api: { totalRequests: 1, totalErrors: 0, totalLatencyMs: 50 },
Expand All @@ -172,6 +174,7 @@ describe('<ModelStatsDisplay />', () => {
thoughts: 0,
tool: 3,
},
roles: {},
},
},
tools: {
Expand Down Expand Up @@ -214,6 +217,7 @@ describe('<ModelStatsDisplay />', () => {
thoughts: 10,
tool: 5,
},
roles: {},
},
'gemini-2.5-flash': {
api: { totalRequests: 20, totalErrors: 2, totalLatencyMs: 500 },
Expand All @@ -226,6 +230,7 @@ describe('<ModelStatsDisplay />', () => {
thoughts: 20,
tool: 10,
},
roles: {},
},
},
tools: {
Expand Down Expand Up @@ -271,6 +276,7 @@ describe('<ModelStatsDisplay />', () => {
thoughts: 111111111,
tool: 222222222,
},
roles: {},
},
},
tools: {
Expand Down Expand Up @@ -309,6 +315,7 @@ describe('<ModelStatsDisplay />', () => {
thoughts: 2,
tool: 1,
},
roles: {},
},
},
tools: {
Expand Down Expand Up @@ -351,6 +358,7 @@ describe('<ModelStatsDisplay />', () => {
thoughts: 100,
tool: 50,
},
roles: {},
},
'gemini-3-flash-preview': {
api: { totalRequests: 20, totalErrors: 0, totalLatencyMs: 1000 },
Expand All @@ -363,6 +371,7 @@ describe('<ModelStatsDisplay />', () => {
thoughts: 200,
tool: 100,
},
roles: {},
},
},
tools: {
Expand Down Expand Up @@ -390,6 +399,64 @@ 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();
});

Expand Down Expand Up @@ -427,6 +494,7 @@ describe('<ModelStatsDisplay />', () => {
thoughts: 0,
tool: 0,
},
roles: {},
},
},
tools: {
Expand Down Expand Up @@ -462,4 +530,121 @@ describe('<ModelStatsDisplay />', () => {
expect(output).toContain('Tier:');
expect(output).toContain('Pro');
});

it('should handle long role name layout', () => {
// Use the longest valid role name to test layout
const longRoleName = LlmRole.UTILITY_LOOP_DETECTOR;

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,
},
});

const output = lastFrame();
expect(output).toContain(longRoleName);
expect(output).toMatchSnapshot();
});

it('should filter out invalid role names', () => {
const invalidRoleName =
'this_is_a_very_long_role_name_that_should_be_wrapped' 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: {
[invalidRoleName]: {
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,
},
});

const output = lastFrame();
expect(output).not.toContain(invalidRoleName);
expect(output).toMatchSnapshot();
});
});
85 changes: 82 additions & 3 deletions packages/cli/src/ui/components/ModelStatsDisplay.tsx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,10 +13,17 @@ 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 { useSettings } from '../contexts/SettingsContext.js';
import { getDisplayString, isAutoModel } from '@google/gemini-cli-core';
import {
getDisplayString,
isAutoModel,
LlmRole,
} from '@google/gemini-cli-core';
import type { QuotaStats } from '../types.js';
import { QuotaStatsInfo } from './QuotaStatsInfo.js';

Expand All @@ -25,9 +32,11 @@ interface StatRowData {
isSection?: boolean;
isSubtle?: boolean;
// Dynamic keys for model values
[key: string]: string | React.ReactNode | boolean | undefined;
[key: string]: string | React.ReactNode | boolean | undefined | number;
}

type RoleMetrics = NonNullable<NonNullable<ModelMetrics['roles']>[LlmRole]>;

interface ModelStatsDisplayProps {
selectedAuthType?: string;
userEmail?: string;
Expand Down Expand Up @@ -81,6 +90,22 @@ export const ModelStatsDisplay: React.FC<ModelStatsDisplayProps> = ({
([, metrics]) => metrics.tokens.cached > 0,
);

const allRoles = [
...new Set(
activeModels.flatMap(([, metrics]) => Object.keys(metrics.roles ?? {})),
),
]
.filter((role): role is LlmRole => {
const validRoles: string[] = Object.values(LlmRole);
return validRoles.includes(role);
})
.sort((a, b) => {
if (a === b) return 0;
if (a === LlmRole.MAIN) return -1;
if (b === LlmRole.MAIN) return 1;
return a.localeCompare(b);
});

// Helper to create a row with values for each model
const createRow = (
metric: string,
Expand Down Expand Up @@ -204,6 +229,60 @@ export const ModelStatsDisplay: React.FC<ModelStatsDisplayProps> = ({
),
);

// 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,
isSection: true,
color: theme.text.primary,
};
// 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,
isSubtle: true,
};
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',
Expand Down
Loading
Loading