mirror of
https://github.com/Kaelio/ktx.git
synced 2026-06-10 08:05:14 +02:00
Make telemetry reliable across interrupts and headless installs
Three reliability gaps surfaced while auditing why PostHog numbers were untrustworthy: 1. Interrupted commands lost their events. capture() is fire-and-forget and the only flush guarantee lived in a finally block, which SIGINT/SIGTERM skip — so Ctrl-C'ing a long ingest or an MCP client killing 'ktx mcp stdio' dropped the command event and any queued events. Add SIGINT/SIGTERM handlers (real-process entry only; never under test/programmatic io) that mark the active command span aborted, emit it, drain the emitter, then exit. Idempotent with the normal finally path via the single-consume command span. 2. Headless-first installs were invisible. loadTelemetryIdentity refused to mint an installId unless stdout was a TTY, so a machine whose first run was an IDE-launched MCP server or a script emitted nothing, ever. Mint on first run regardless of surface (still honoring CI/DO_NOT_TRACK/KTX_TELEMETRY_DISABLED), writing the one-time notice to stderr — safe under the MCP stdio protocol, which reserves stdout. Drop the now-unused stdoutIsTTY option. 3. No guard against silent emit regressions (the 0.7.0 scan_completed blackout). Add tests: the shared executePublicIngestTarget chokepoint emits exactly one ingest_completed on success and on the preflight-failure branch, and a database target invokes the scan that emits scan_completed; plus coverage for the aborted-flush helper. Identity is unchanged otherwise: every event still attributes to the installId in ~/.ktx/telemetry.json. No event/field changes, so Node<->Python schema parity is untouched. Docs updated to reflect first-run-on-any-surface activation.
This commit is contained in:
parent
2334a4b6e3
commit
cb6a67c2d7
7 changed files with 219 additions and 66 deletions
|
|
@ -89,6 +89,46 @@ export async function runInitForCommander(
|
|||
return await runInit(args, io);
|
||||
}
|
||||
|
||||
function signalExitCode(signal: NodeJS.Signals): number {
|
||||
// 128 + signal number: SIGINT (2) -> 130, SIGTERM (15) -> 143.
|
||||
return signal === 'SIGTERM' ? 143 : 130;
|
||||
}
|
||||
|
||||
/**
|
||||
* Flush telemetry on interrupt for the real CLI process. `capture()` is
|
||||
* fire-and-forget and the only flush guarantee lives in a `finally` a signal
|
||||
* skips, so Ctrl-C / `kill` of a long-running command (ingest, `mcp stdio`)
|
||||
* would otherwise drop its `command` event and queued events. Installed only
|
||||
* when driving the actual process; programmatic/test callers pass their own
|
||||
* `io` and never reach here. Returns a disposer that removes the listeners.
|
||||
*/
|
||||
function installTelemetrySignalFlush(io: KtxCliIo, info: KtxCliPackageInfo): () => void {
|
||||
let handling = false;
|
||||
const handle = (signal: NodeJS.Signals): void => {
|
||||
if (handling) {
|
||||
process.exit(signalExitCode(signal));
|
||||
}
|
||||
handling = true;
|
||||
void (async () => {
|
||||
try {
|
||||
const { emitAbortedCommandAndShutdown } = await import('./telemetry/index.js');
|
||||
await emitAbortedCommandAndShutdown({ packageInfo: info, io });
|
||||
} catch {
|
||||
// Best-effort: never let a telemetry hiccup block the interrupt exit.
|
||||
}
|
||||
process.exit(signalExitCode(signal));
|
||||
})();
|
||||
};
|
||||
const onSigint = (): void => handle('SIGINT');
|
||||
const onSigterm = (): void => handle('SIGTERM');
|
||||
process.on('SIGINT', onSigint);
|
||||
process.on('SIGTERM', onSigterm);
|
||||
return () => {
|
||||
process.off('SIGINT', onSigint);
|
||||
process.off('SIGTERM', onSigterm);
|
||||
};
|
||||
}
|
||||
|
||||
export async function runKtxCli(
|
||||
argv = process.argv.slice(2),
|
||||
io: KtxCliIo = process,
|
||||
|
|
@ -98,7 +138,14 @@ export async function runKtxCli(
|
|||
profileMark('runtime:runKtxCli');
|
||||
const { runCommanderKtxCli } = await profileSpan('import ./cli-program.js', () => import('./cli-program.js'));
|
||||
|
||||
return await runCommanderKtxCli(argv, io, deps, info, {
|
||||
runInit: runInitForCommander,
|
||||
});
|
||||
// Real-process entry only: flush telemetry if interrupted. Test/programmatic
|
||||
// callers pass their own `io`, so they never install process-level handlers.
|
||||
const removeSignalFlush = (io as unknown) === process ? installTelemetrySignalFlush(io, info) : undefined;
|
||||
try {
|
||||
return await runCommanderKtxCli(argv, io, deps, info, {
|
||||
runInit: runInitForCommander,
|
||||
});
|
||||
} finally {
|
||||
removeSignalFlush?.();
|
||||
}
|
||||
}
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue