fix: prevent duplicate cleanup intervals on background script reload

[Copilot]

Each time the background script reloads without a full context reset, a new setInterval loop was spawned without clearing the previous one — silently multiplying cleanup executions and leaking memory/CPU over time.

Change

• Guard the setInterval registration in background.js by storing its ID on globalThis under a namespaced key and clearing any prior interval before creating a new one:

const CLEANUP_INTERVAL_KEY = "__acceptLangExt_cleanupIntervalId";
const existingCleanupIntervalId = globalThis[CLEANUP_INTERVAL_KEY];
if (typeof existingCleanupIntervalId === "number" || typeof existingCleanupIntervalId === "object") {
  clearInterval(existingCleanupIntervalId);
}
globalThis[CLEANUP_INTERVAL_KEY] = setInterval(cleanupStaleTrackedRequests, REQUEST_TRACK_TTL_MS);

• The key is namespaced (__acceptLangExt_cleanupIntervalId) to avoid collisions with other scripts or future dependencies.
• A typeof type guard (number or object) ensures only our own interval is ever cleared, protecting against accidental interference with unrelated globals.

globalThis persists across script re-executions within the same global context, ensuring exactly one cleanup loop is active regardless of how many times the script reloads.

Original prompt

---

This section details on the original issue you should resolve

<issue_title>Nettoyer l'intervalle de purge des requêtes orphelines</issue_title>
<issue_description>## Contexte
L'extension maintient un suivi des requêtes initiales via une Map en mémoire, et exécute une fonction cleanupStaleTrackedRequests régulièrement.

Problème

La fonction setInterval est appelée au niveau global de background.js sans conserver son identifiant. Bien que cela fonctionne dans un environnement persistant, les cycles de vie modernes d'extensions (suspend/resume) peuvent amener le script à se recharger partiellement, multipliant silencieusement les boucles d'intervalle et provoquant une fuite de mémoire.

Scénario de Reproduction

1. Recharger le script d'arrière-plan plusieurs fois d'affilée sans réinitialiser le contexte global.
2. Monitorer les performances du worker.
3. Constater l'exécution multiple et superflue de la fonction de nettoyage chaque minute.

Comportement Attendu

Il ne doit y avoir qu'une seule instance de la boucle de nettoyage en cours d'exécution.

Pistes Techniques

Fichier background.js :
Conserver la référence de l'intervalle et la nettoyer avant de la recréer, ou lier le nettoyage aux événements de cycle de vie de l'extension.

if (globalThis.cleanupIntervalId) {
  clearInterval(globalThis.cleanupIntervalId);
}
globalThis.cleanupIntervalId = setInterval(cleanupStaleTrackedRequests, REQUEST_TRACK_TTL_MS);

Environnement

Service Worker / Background Script.</issue_description>

Comments on the Issue (you are @copilot in this section)

• Fixes Nettoyer l'intervalle de purge des requêtes orphelines #84

---

💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.

[Copilot]

Pull request overview

This PR aims to prevent multiple concurrent cleanup loops from accumulating by ensuring the periodic cleanupStaleTrackedRequests interval is de-duplicated across background script re-executions.

Changes:

• Clear any previously registered cleanup interval before creating a new one.
• Store the interval ID on globalThis to allow reuse across script re-execution within the same global context.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

globalThis.cleanupIntervalId is a very generic global property name; if more background scripts (or future dependencies) add their own interval tracking, this risks collisions and accidentally clearing the wrong interval. Consider namespacing the key (e.g., a project-specific prefix) and/or guarding the clearInterval call with a type check (number/object) to ensure you only clear your own interval.

Suggested change

	if (globalThis.cleanupIntervalId) {
	clearInterval(globalThis.cleanupIntervalId);
	}
	globalThis.cleanupIntervalId = setInterval(cleanupStaleTrackedRequests, REQUEST_TRACK_TTL_MS);
	const CLEANUP_INTERVAL_KEY = "__acceptLangExt_cleanupIntervalId";
	const existingCleanupIntervalId = globalThis[CLEANUP_INTERVAL_KEY];
	if (typeof existingCleanupIntervalId === "number" || typeof existingCleanupIntervalId === "object") {
	clearInterval(existingCleanupIntervalId);
	}
	globalThis[CLEANUP_INTERVAL_KEY] = setInterval(cleanupStaleTrackedRequests, REQUEST_TRACK_TTL_MS);

[Copilot]

PR description references a MV3 Service Worker lifecycle, but this repo’s manifest.json is manifest_version: 2 with a classic background page (background.scripts). In MV2, background reloads typically destroy the old JS context (and its interval), so this change may not address the reported reproduction scenario; please confirm the issue occurs in the current MV2 runtime or update the PR description/linked issue context accordingly.

[ormidales]

@copilot apply changes based on the comments in this thread

[Copilot]

@copilot apply changes based on the comments in this thread

Done in 874cebb. The globalThis key is now namespaced to __acceptLangExt_cleanupIntervalId, and a typeof type check (number or object) guards the clearInterval call to ensure only our own interval is ever cleared.