Files
gemini-cli/packages/cli/src/config/config.ts
Jerop Kipruto 53753f0455 Add telemetry command and refactor telemetry settings (#1060)
#750 

### Telemetry Settings
Refactors telemetry configuration to use a nested `telemetry` object in `settings.json`, for example:

```json
{
  "telemetry": {
    "enabled": true,
    "target": "gcp"
    "log-prompts": "true"
  },
  "sandbox": false
}
```

The above includes
- Centralized telemetry settings under a `telemetry` object in `settings.json`.
- CLI flags for the `gemini` command to override all telemetry sub-settings:
    - `--telemetry` / `--no-telemetry`
    - `--telemetry-target <local|gcp>`
    - `--telemetry-otlp-endpoint <URL>`
    - `--telemetry-log-prompts` / `--no-telemetry-log-prompts`
- Updates `packages/cli/src/config/config.ts` and `packages/core/src/config/config.ts` to read from the new settings structure and respect the new CLI flags.
- Modifies `scripts/handle-telemetry.js`, `scripts/local_telemetry.js`, and `scripts/telemetry_utils.js` to align with the new settings structure.
- Updates `docs/core/telemetry.md` to reflect the new settings structure, CLI flags, and order of precedence.
- Renames `logUserPromptsEnabled` to `logPrompts` for brevity.

### `npm run telemetry`

Add a new `npm run telemetry` command that uses `scripts/telemetry.js`, automates the entire process of setting up a local and GCP telemetry pipelines, including configuring the necessary settings in the `.gemini/settings.json` workspace file and installing required binaries (e.g. `otelcol-contrib`).

---
```shell
$ npm run telemetry -- --target=gcp

> gemini-cli@0.1.0 telemetry
> node scripts/telemetry.js --target=gcp

⚙️  Using command-line target: gcp
🚀 Running telemetry script for target: gcp.
 Starting Local Telemetry Exporter for Google Cloud 
⚙️  Enabled telemetry in workspace settings.
🔧 Set telemetry OTLP endpoint to http://localhost:4317.
🎯 Set telemetry target to gcp.
 Workspace settings updated.
 Using Google Cloud Project ID: foo-bar

🔑 Please ensure you are authenticated with Google Cloud:
  - Run `gcloud auth application-default login` OR ensure `GOOGLE_APPLICATION_CREDENTIALS` environment variable points to a valid service account key.
  - The account needs "Cloud Trace Agent", "Monitoring Metric Writer", and "Logs Writer" roles.
 otelcol-contrib already exists at /Users/jerop/github/gemini-cli/.gemini/otel/bin/otelcol-contrib
🧹 Cleaning up old processes and logs...
 Deleted old GCP collector log.
📄 Wrote OTEL collector config to /Users/jerop/github/gemini-cli/.gemini/otel/collector-gcp.yaml
🚀 Starting OTEL collector for GCP... Logs: /Users/jerop/github/gemini-cli/.gemini/otel/collector-gcp.log
 Waiting for OTEL collector to start (PID: 17013)...
 OTEL collector started successfully on port 4317.

 Local OTEL collector for GCP is running.

🚀 To send telemetry, run the Gemini CLI in a separate terminal window.

📄 Collector logs are being written to: /Users/jerop/github/gemini-cli/.gemini/otel/collector-gcp.log

📊 View your telemetry data in Google Cloud Console:
   - Logs: https://console.cloud.google.com/logs/query;query=logName%3D%22projects%2Ffoo-bar%2Flogs%2Fgemini_cli%22?project=foo-bar
   - Metrics: https://console.cloud.google.com/monitoring/metrics-explorer?project=foo-bar
   - Traces: https://console.cloud.google.com/traces/list?project=foo-bar

Press Ctrl+C to exit.
^C
👋 Shutting down...
⚙️  Disabled telemetry in workspace settings.
🔧 Cleared telemetry OTLP endpoint.
🎯 Cleared telemetry target.
 Workspace settings updated.
🛑 Stopping otelcol-contrib (PID: 17013)...
 otelcol-contrib stopped.
```
2025-06-15 00:47:32 -04:00

343 lines
11 KiB
TypeScript

/**
* @license
* Copyright 2025 Google LLC
* SPDX-License-Identifier: Apache-2.0
*/
import yargs from 'yargs/yargs';
import { hideBin } from 'yargs/helpers';
import process from 'node:process';
import {
Config,
loadServerHierarchicalMemory,
setGeminiMdFilename as setServerGeminiMdFilename,
getCurrentGeminiMdFilename,
ApprovalMode,
ContentGeneratorConfig,
GEMINI_CONFIG_DIR as GEMINI_DIR,
DEFAULT_GEMINI_MODEL,
DEFAULT_GEMINI_EMBEDDING_MODEL,
FileDiscoveryService,
TelemetryTarget,
} from '@gemini-cli/core';
import { Settings } from './settings.js';
import { getEffectiveModel } from '../utils/modelCheck.js';
import { Extension } from './extension.js';
import * as dotenv from 'dotenv';
import * as fs from 'node:fs';
import * as path from 'node:path';
import * as os from 'node:os';
// Simple console logger for now - replace with actual logger if available
const logger = {
// eslint-disable-next-line @typescript-eslint/no-explicit-any
debug: (...args: any[]) => console.debug('[DEBUG]', ...args),
// eslint-disable-next-line @typescript-eslint/no-explicit-any
warn: (...args: any[]) => console.warn('[WARN]', ...args),
// eslint-disable-next-line @typescript-eslint/no-explicit-any
error: (...args: any[]) => console.error('[ERROR]', ...args),
};
interface CliArgs {
model: string | undefined;
sandbox: boolean | string | undefined;
debug: boolean | undefined;
prompt: string | undefined;
all_files: boolean | undefined;
show_memory_usage: boolean | undefined;
yolo: boolean | undefined;
telemetry: boolean | undefined;
checkpoint: boolean | undefined;
telemetryTarget: string | undefined;
telemetryOtlpEndpoint: string | undefined;
telemetryLogPrompts: boolean | undefined;
}
async function parseArguments(): Promise<CliArgs> {
const argv = await yargs(hideBin(process.argv))
.option('model', {
alias: 'm',
type: 'string',
description: `Model`,
default: process.env.GEMINI_MODEL || DEFAULT_GEMINI_MODEL,
})
.option('prompt', {
alias: 'p',
type: 'string',
description: 'Prompt. Appended to input on stdin (if any).',
})
.option('sandbox', {
alias: 's',
type: 'boolean',
description: 'Run in sandbox?',
})
.option('debug', {
alias: 'd',
type: 'boolean',
description: 'Run in debug mode?',
default: false,
})
.option('all_files', {
alias: 'a',
type: 'boolean',
description: 'Include ALL files in context?',
default: false,
})
.option('show_memory_usage', {
type: 'boolean',
description: 'Show memory usage in status bar',
default: false,
})
.option('yolo', {
alias: 'y',
type: 'boolean',
description:
'Automatically accept all actions (aka YOLO mode, see https://www.youtube.com/watch?v=xvFZjo5PgG0 for more details)?',
default: false,
})
.option('telemetry', {
type: 'boolean',
description:
'Enable telemetry? This flag specifically controls if telemetry is sent. Other --telemetry-* flags set specific values but do not enable telemetry on their own.',
})
.option('telemetry-target', {
type: 'string',
choices: ['local', 'gcp'],
description:
'Set the telemetry target (local or gcp). Overrides settings files.',
})
.option('telemetry-otlp-endpoint', {
type: 'string',
description:
'Set the OTLP endpoint for telemetry. Overrides environment variables and settings files.',
})
.option('telemetry-log-prompts', {
type: 'boolean',
description:
'Enable or disable logging of user prompts for telemetry. Overrides settings files.',
})
.option('checkpoint', {
alias: 'c',
type: 'boolean',
description: 'Enables checkpointing of file edits',
default: false,
})
.version(process.env.CLI_VERSION || '0.0.0') // This will enable the --version flag based on package.json
.help()
.alias('h', 'help')
.strict().argv;
return argv;
}
// This function is now a thin wrapper around the server's implementation.
// It's kept in the CLI for now as App.tsx directly calls it for memory refresh.
// TODO: Consider if App.tsx should get memory via a server call or if Config should refresh itself.
export async function loadHierarchicalGeminiMemory(
currentWorkingDirectory: string,
debugMode: boolean,
fileService: FileDiscoveryService,
extensionContextFilePaths: string[] = [],
): Promise<{ memoryContent: string; fileCount: number }> {
if (debugMode) {
logger.debug(
`CLI: Delegating hierarchical memory load to server for CWD: ${currentWorkingDirectory}`,
);
}
// Directly call the server function.
// The server function will use its own homedir() for the global path.
return loadServerHierarchicalMemory(
currentWorkingDirectory,
debugMode,
fileService,
extensionContextFilePaths,
);
}
export async function loadCliConfig(
settings: Settings,
extensions: Extension[],
sessionId: string,
): Promise<Config> {
loadEnvironment();
const argv = await parseArguments();
const debugMode = argv.debug || false;
// Set the context filename in the server's memoryTool module BEFORE loading memory
// TODO(b/343434939): This is a bit of a hack. The contextFileName should ideally be passed
// directly to the Config constructor in core, and have core handle setGeminiMdFilename.
// However, loadHierarchicalGeminiMemory is called *before* createServerConfig.
if (settings.contextFileName) {
setServerGeminiMdFilename(settings.contextFileName);
} else {
// Reset to default if not provided in settings.
setServerGeminiMdFilename(getCurrentGeminiMdFilename());
}
const extensionContextFilePaths = extensions.flatMap((e) => e.contextFiles);
const fileService = new FileDiscoveryService(process.cwd());
// Call the (now wrapper) loadHierarchicalGeminiMemory which calls the server's version
const { memoryContent, fileCount } = await loadHierarchicalGeminiMemory(
process.cwd(),
debugMode,
fileService,
extensionContextFilePaths,
);
const contentGeneratorConfig = await createContentGeneratorConfig(argv);
const mcpServers = mergeMcpServers(settings, extensions);
return new Config({
sessionId,
contentGeneratorConfig,
embeddingModel: DEFAULT_GEMINI_EMBEDDING_MODEL,
sandbox: argv.sandbox ?? settings.sandbox,
targetDir: process.cwd(),
debugMode,
question: argv.prompt || '',
fullContext: argv.all_files || false,
coreTools: settings.coreTools || undefined,
excludeTools: settings.excludeTools || undefined,
toolDiscoveryCommand: settings.toolDiscoveryCommand,
toolCallCommand: settings.toolCallCommand,
mcpServerCommand: settings.mcpServerCommand,
mcpServers,
userMemory: memoryContent,
geminiMdFileCount: fileCount,
approvalMode: argv.yolo || false ? ApprovalMode.YOLO : ApprovalMode.DEFAULT,
showMemoryUsage:
argv.show_memory_usage || settings.showMemoryUsage || false,
accessibility: settings.accessibility,
telemetry: {
enabled: argv.telemetry ?? settings.telemetry?.enabled,
target: (argv.telemetryTarget ??
settings.telemetry?.target) as TelemetryTarget,
otlpEndpoint:
argv.telemetryOtlpEndpoint ??
process.env.OTEL_EXPORTER_OTLP_ENDPOINT ??
settings.telemetry?.otlpEndpoint,
logPrompts: argv.telemetryLogPrompts ?? settings.telemetry?.logPrompts,
},
// Git-aware file filtering settings
fileFilteringRespectGitIgnore: settings.fileFiltering?.respectGitIgnore,
checkpoint: argv.checkpoint,
proxy:
process.env.HTTPS_PROXY ||
process.env.https_proxy ||
process.env.HTTP_PROXY ||
process.env.http_proxy,
cwd: process.cwd(),
fileDiscoveryService: fileService,
bugCommand: settings.bugCommand,
});
}
function mergeMcpServers(settings: Settings, extensions: Extension[]) {
const mcpServers = { ...(settings.mcpServers || {}) };
for (const extension of extensions) {
Object.entries(extension.config.mcpServers || {}).forEach(
([key, server]) => {
if (mcpServers[key]) {
logger.warn(
`Skipping extension MCP config for server with key "${key}" as it already exists.`,
);
return;
}
mcpServers[key] = server;
},
);
}
return mcpServers;
}
async function createContentGeneratorConfig(
argv: CliArgs,
): Promise<ContentGeneratorConfig> {
const geminiApiKey = process.env.GEMINI_API_KEY;
const googleApiKey = process.env.GOOGLE_API_KEY;
const googleCloudProject = process.env.GOOGLE_CLOUD_PROJECT;
const googleCloudLocation = process.env.GOOGLE_CLOUD_LOCATION;
const hasCodeAssist = process.env.GEMINI_CODE_ASSIST === 'true';
const hasGeminiApiKey = !!geminiApiKey;
const hasGoogleApiKey = !!googleApiKey;
const hasVertexProjectLocationConfig =
!!googleCloudProject && !!googleCloudLocation;
if (hasGeminiApiKey && hasGoogleApiKey) {
logger.warn(
'Both GEMINI_API_KEY and GOOGLE_API_KEY are set. Using GOOGLE_API_KEY.',
);
}
if (
!hasCodeAssist &&
!hasGeminiApiKey &&
!hasGoogleApiKey &&
!hasVertexProjectLocationConfig
) {
logger.error(
'No valid API authentication configuration found. Please set ONE of the following combinations in your environment variables or .env file:\n' +
'1. GEMINI_CODE_ASSIST=true (for Code Assist access).\n' +
'2. GEMINI_API_KEY (for Gemini API access).\n' +
'3. GOOGLE_API_KEY (for Gemini API or Vertex AI Express Mode access).\n' +
'4. GOOGLE_CLOUD_PROJECT and GOOGLE_CLOUD_LOCATION (for Vertex AI access).\n\n' +
'For Gemini API keys, visit: https://ai.google.dev/gemini-api/docs/api-key\n' +
'For Vertex AI authentication, visit: https://cloud.google.com/vertex-ai/docs/authentication\n' +
'The GOOGLE_GENAI_USE_VERTEXAI environment variable can also be set to true/false to influence service selection when ambiguity exists.',
);
process.exit(1);
}
const config: ContentGeneratorConfig = {
model: argv.model || DEFAULT_GEMINI_MODEL,
apiKey: googleApiKey || geminiApiKey || '',
vertexai: hasGeminiApiKey ? false : undefined,
codeAssist: hasCodeAssist,
};
if (config.apiKey) {
config.model = await getEffectiveModel(config.apiKey, config.model);
}
return config;
}
function findEnvFile(startDir: string): string | null {
let currentDir = path.resolve(startDir);
while (true) {
// prefer gemini-specific .env under GEMINI_DIR
const geminiEnvPath = path.join(currentDir, GEMINI_DIR, '.env');
if (fs.existsSync(geminiEnvPath)) {
return geminiEnvPath;
}
const envPath = path.join(currentDir, '.env');
if (fs.existsSync(envPath)) {
return envPath;
}
const parentDir = path.dirname(currentDir);
if (parentDir === currentDir || !parentDir) {
// check .env under home as fallback, again preferring gemini-specific .env
const homeGeminiEnvPath = path.join(os.homedir(), GEMINI_DIR, '.env');
if (fs.existsSync(homeGeminiEnvPath)) {
return homeGeminiEnvPath;
}
const homeEnvPath = path.join(os.homedir(), '.env');
if (fs.existsSync(homeEnvPath)) {
return homeEnvPath;
}
return null;
}
currentDir = parentDir;
}
}
export function loadEnvironment(): void {
const envFilePath = findEnvFile(process.cwd());
if (envFilePath) {
dotenv.config({ path: envFilePath });
}
}