feat(telemetry): anonymous posthog usage telemetry across node cli and python daemon (#205)

* feat: add telemetry phase 1

* feat: add node telemetry event catalog

* feat: add telemetry event helpers

* feat: emit setup and connection telemetry

* feat: emit connection and stack telemetry

* feat: emit ingest and scan telemetry

* feat: emit query telemetry

* feat: emit sampled mcp telemetry

* docs: expand telemetry event catalog

* feat: add telemetry schema sync artifact

* feat: pass telemetry project id to semantic daemon

* feat: add daemon telemetry foundation

* feat: emit semantic daemon telemetry

* feat: emit daemon lifecycle telemetry

* docs: document full telemetry event catalog

* feat(telemetry): dim first-run notice

* feat(telemetry): show first-run notice before command output

* feat(telemetry): wire ktx PostHog project for live ingestion

* docs(telemetry): drop posthog project name and host from storage section

* docs(telemetry): trim to general overview and disclaimer

* docs(agents): add short telemetry guidelines

* feat(telemetry): enable posthog geoip enrichment

* docs(telemetry): drop ip-geoip note from public overview

* refactor(telemetry): drop no-op groupIdentify, rely on capture groups field

* fix(telemetry): respect CI kill switch in python daemon identity

* fix(sql): route table-count analysis to existing analyze-batch endpoint

* fix(telemetry): emit install_first_run from notice path and derive flagsPresent from commander

* fix(telemetry): read package info via getKtxCliPackageInfo to satisfy boundary check

* fix(telemetry): make python identity env={} bypass os.environ and unset CI in tests

* fix(telemetry): unset CI kill switch in cli-program-telemetry tests
This commit is contained in:
Andrey Avtomonov 2026-05-22 18:18:47 +02:00 committed by GitHub
parent c87d14a554
commit b0dd13ce7c
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
73 changed files with 6576 additions and 48 deletions

View file

@ -6,6 +6,9 @@ import { type KtxOutputMode, resolveOutputMode } from './io/mode.js';
import { createKtxCliScanConnector } from './local-scan-connectors.js';
import { createManagedDaemonSqlAnalysisPort } from './managed-python-http.js';
import { profileMark } from './startup-profile.js';
import { isDemoConnection } from './telemetry/demo-detect.js';
import { emitTelemetryEvent } from './telemetry/index.js';
import { scrubErrorClass } from './telemetry/scrubber.js';
profileMark('module:sql');
@ -54,6 +57,27 @@ function sqlAnalysisDialectForDriver(driver: string | undefined): SqlAnalysisDia
return map[normalized] ?? 'postgres';
}
function queryVerb(sql: string): 'select' | 'explain' | 'show' | 'with' | 'other' {
const first = sql.trim().split(/\s+/, 1)[0]?.toLowerCase();
if (first === 'select' || first === 'explain' || first === 'show' || first === 'with') {
return first;
}
return 'other';
}
async function safeReferencedTableCount(
port: SqlAnalysisPort,
sql: string,
dialect: SqlAnalysisDialect,
): Promise<number> {
try {
const results = await port.analyzeBatch([{ id: 'cli-sql', sql }], dialect);
return results.get('cli-sql')?.tablesTouched.length ?? 0;
} catch {
return 0;
}
}
function formatValue(value: unknown): string {
if (value === null || value === undefined) return '';
if (typeof value === 'string') return value;
@ -119,14 +143,19 @@ function resultOutput(connectionId: string, result: KtxQueryResult): SqlExecutio
}
export async function runKtxSql(args: KtxSqlArgs, io: KtxCliIo = process, deps: KtxSqlDeps = {}): Promise<number> {
const startedAt = performance.now();
let driver = 'unknown';
let demoConnection = false;
try {
const project = await (deps.loadProject ?? loadKtxProject)({ projectDir: args.projectDir });
const connection = project.config.connections[args.connectionId];
if (!connection) {
throw new Error(`Connection "${args.connectionId}" is not configured in ktx.yaml`);
}
driver = String(connection.driver ?? 'unknown').toLowerCase();
demoConnection = isDemoConnection(args.connectionId, connection);
const sqlAnalysis =
const createSqlAnalysis =
deps.createSqlAnalysis ??
(() =>
createManagedDaemonSqlAnalysisPort({
@ -135,10 +164,13 @@ export async function runKtxSql(args: KtxSqlArgs, io: KtxCliIo = process, deps:
installPolicy: 'auto',
io,
}));
const validation = await sqlAnalysis().validateReadOnly(args.sql, sqlAnalysisDialectForDriver(connection.driver));
const analysisPort = createSqlAnalysis();
const dialect = sqlAnalysisDialectForDriver(connection.driver);
const validation = await analysisPort.validateReadOnly(args.sql, dialect);
if (!validation.ok) {
throw new Error(validation.error ?? 'SQL is not read-only.');
}
const referencedTableCount = await safeReferencedTableCount(analysisPort, args.sql, dialect);
const createScanConnector = deps.createScanConnector ?? createKtxCliScanConnector;
let connector: KtxScanConnector | null = null;
@ -157,11 +189,39 @@ export async function runKtxSql(args: KtxSqlArgs, io: KtxCliIo = process, deps:
);
const mode = resolveOutputMode({ explicit: args.output, json: args.json, io });
printSqlResult(resultOutput(args.connectionId, result), mode, io);
await emitTelemetryEvent({
name: 'sql_completed',
projectDir: args.projectDir,
io,
fields: {
driver,
isDemoConnection: demoConnection,
queryVerb: queryVerb(args.sql),
referencedTableCount,
durationMs: Math.max(0, performance.now() - startedAt),
outcome: 'ok',
},
});
return 0;
} finally {
await cleanupConnector(connector);
}
} catch (error) {
const errorClass = scrubErrorClass(error);
await emitTelemetryEvent({
name: 'sql_completed',
projectDir: args.projectDir,
io,
fields: {
driver,
isDemoConnection: demoConnection,
queryVerb: queryVerb(args.sql),
referencedTableCount: 0,
durationMs: Math.max(0, performance.now() - startedAt),
outcome: 'error',
...(errorClass ? { errorClass } : {}),
},
});
io.stderr.write(`${error instanceof Error ? error.message : String(error)}\n`);
return 1;
}