From dfc1f663c7bb12c4b88b58d55e54f1e77acf1498 Mon Sep 17 00:00:00 2001
From: Alvaro Parker <aparker@azurian.com>
Date: Mon, 5 Oct 2026 10:13:25 -0300
Subject: [PATCH] refactor: standardize developer text and identifiers in
 English

---
 s2s-client/CHANGELOG.md                       |    5 +
 s2s-client/index.html                         |   39 +-
 s2s-client/main.js                            |  307 ++---
 s2s-client/server.py                          | 1178 +++++++----------
 s2s-client/style.css                          |   78 +-
 s2s-client/ui/chat.js                         |   14 +-
 s2s-client/ws/s2s-ws-client.js                |  221 ++--
 s2s-reasoning-engine/.env.example             |   14 +-
 s2s-reasoning-engine/Dockerfile               |   21 +-
 s2s-reasoning-engine/flows.json               |   20 +-
 s2s-reasoning-engine/package.json             |    2 +-
 s2s-reasoning-engine/settings.js              |   49 +-
 s2s-reasoning-engine/start.sh                 |   30 +-
 .../LLM/chat_completions_language_model.py    |    2 +-
 speech_to_speech/LLM/lm_output_processor.py   |   31 +-
 speech_to_speech/TTS/qwen3_tts_handler.py     |   35 +-
 .../api/openai_realtime/handlers/session.py   |    2 +-
 .../api/openai_realtime/service.py            |   11 +-
 .../arguments_classes/chat_tts_arguments.py   |    2 +-
 start_ui.sh                                   |   14 +-
 20 files changed, 933 insertions(+), 1142 deletions(-)

diff --git a/s2s-client/CHANGELOG.md b/s2s-client/CHANGELOG.md
index a36d1a0..2af9e20 100644
--- a/s2s-client/CHANGELOG.md
+++ b/s2s-client/CHANGELOG.md
@@ -16,6 +16,11 @@ the implementation at the recorded date; current operating instructions live in
   the existing document URLs as redirects.
 - Removed the obsolete `index_video.html` page, which no longer matched the
   elements required by the shared client script.
+- Translated developer comments, diagnostics, internal model instructions, and
+  local identifiers into English. Sanitization accepts both the former Spanish
+  and new English internal tool-result wrappers.
+- Renamed the reasoning engine's log-only acknowledgment field to `received`
+  and its debug phase to `log_only_phase1`.
 
 ## 2026-09-25
 
diff --git a/s2s-client/index.html b/s2s-client/index.html
index 73777eb..90f9e6f 100644
--- a/s2s-client/index.html
+++ b/s2s-client/index.html
@@ -18,8 +18,7 @@
          BEFORE the <link rel="stylesheet" href="style.css"> tag below.
 
          Problem reported by user 2026-09-10:
-           "quando faccio refresh per un momento si vede il theme precedente
-            quello purple"
+           "When I refresh, the previous purple theme briefly appears."
 
          The earlier guard `html:not([data-theme]) [data-theme-only]` only
          hid the two parallel widget branches, but the UNTHEMED DEFAULTS in
@@ -179,7 +178,7 @@
       <a class="feedback-link" href="https://tally.so/r/pb8LWq" target="_blank" rel="noopener noreferrer">Enviar feedback</a>
 
       <!-- Theme=white only: Status card between topbar and stage
-           "Listo para conversar / Informes, análisis, datos y mucho más."
+           Ready to converse / Reports, analysis, data and more.
            with light-blue chart icon and chevron-right arrow. -->
       <div class="status-card" hidden data-theme-only="white" aria-label="Estado de la sesión">
         <div class="status-card-icon" aria-hidden="true">
@@ -265,8 +264,8 @@
         <!-- WHITE THEME mic stage (replaces the purple orb)
              - Blue mic circular button (116 px, deep blue, white mic)
              - Two waveform banks left + right (audio-reactive CSS bars)
-             - "Escuchando..." status text
-             - "Detener" pill button below.
+             - Listening status text
+             - Stop pill button below.
              Mirrors the screenshot center UI exactly. -->
         <div class="white-mic-stage" hidden data-theme-only="white" aria-label="Control de voz">
           <!-- Waveform left side: 7 bars mirror right side, heights driven by JS vars -->
@@ -311,10 +310,10 @@
             <span class="w-bar wb-7" style="--bar-h: 0.4"></span>
           </div>
 
-          <!-- Status caption below mic circle: "Escuchando...", "Pensando..." etc. -->
+          <!-- Status caption below mic circle: listening, thinking, etc. -->
           <p id="white-mic-caption" class="white-mic-caption" role="status">Escuchando…</p>
 
-          <!-- Secondary pill "Detener" (Stop) below caption, with dark stop-square icon. -->
+          <!-- Secondary stop pill below caption, with a dark stop-square icon. -->
           <button id="white-stop-btn"
                   class="white-stop-btn"
                   type="button"
@@ -338,10 +337,10 @@
         </div>
       </main>
 
-      <!-- Theme=white only: Quick action pills below mic area
-           "Resumen" · "Consultar datos" · "Crear respuesta" each with icon -->
+      <!-- Theme=white only: summary, data lookup and draft-response quick
+           actions below the mic area, each with an icon. -->
       <div class="quick-actions" hidden data-theme-only="white" aria-label="Acciones rápidas">
-        <button class="quick-action-btn" type="button" data-action="resumen">
+        <button class="quick-action-btn" type="button" data-action="summary">
           <svg width="22" height="22" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="1.8" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true">
             <path d="M14 2H6a2 2 0 0 0-2 2v16a2 2 0 0 0 2 2h12a2 2 0 0 0 2-2V8z"/>
             <polyline points="14 2 14 8 20 8"/>
@@ -350,7 +349,7 @@
           </svg>
           <span>Resumen</span>
         </button>
-        <button class="quick-action-btn" type="button" data-action="consultar-datos">
+        <button class="quick-action-btn" type="button" data-action="query-data">
           <svg width="22" height="22" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="1.8" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true">
             <line x1="6"  y1="20" x2="6"  y2="12"/>
             <line x1="11" y1="20" x2="11" y2="6"/>
@@ -359,7 +358,7 @@
           </svg>
           <span>Consultar datos</span>
         </button>
-        <button class="quick-action-btn" type="button" data-action="crear-respuesta">
+        <button class="quick-action-btn" type="button" data-action="draft-response">
           <svg width="22" height="22" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="1.8" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true">
             <line x1="18" y1="2" x2="22" y2="6"/>
             <path d="M7.5 20.5 19 9l-4-4L3.5 16.5 2 22z"/>
@@ -368,15 +367,15 @@
         </button>
       </div>
 
-      <!-- Chat di testo SEMPRE VISIBILE (fissa in basso, tra stage e footer).
-           Nota: ora è un blocco diretto del flex-col #app, non più un overlay
-           destro → non c'è più bisogno del bottone toggle in topbar. -->
+      <!-- Text chat ALWAYS VISIBLE, fixed between the stage and footer.
+           The panel is now a direct child of the flex-column #app, so it
+           no longer needs a topbar toggle for a right-side overlay. -->
       <div id="chat-panel" class="chat-panel chat-panel-inline" aria-label="Chat de texto">
         <div class="chat-panel-inner">
           <header class="chat-panel-header">
             <h3>Conversación</h3>
             <div class="chat-header-actions" aria-label="Acciones de la conversación">
-              <!-- "En línea" status pill (green dot + text) — theme=white only.
+              <!-- Online status pill (green dot + text) — theme=white only.
                    Mirrors the screenshot chat header top-right corner. -->
               <span class="chat-status-pill" hidden data-theme-only="white" role="status" aria-live="polite">
                 <span class="chat-status-dot" aria-hidden="true"></span>
@@ -428,14 +427,14 @@
     <div id="bubble-stack" class="bubble-stack" aria-live="polite" aria-atomic="false"></div>
 
     <!-- Webcam self-view, shown bottom-left while the camera tool is enabled.
-         HIDDEN BY DEFAULT TODAY: riattivare togliendo hidden + scommentando listener in main.js -->
+         HIDDEN BY DEFAULT TODAY: remove hidden and restore the main.js listener to reactivate. -->
     <div id="cam-pip" class="cam-pip" aria-hidden="true" hidden>
       <video id="cam-video" class="cam-video" autoplay playsinline muted></video>
       <span class="cam-flash" aria-hidden="true"></span>
       <span class="cam-label">camera</span>
     </div>
 
-    <!-- Left sidebar: reports programados.
+    <!-- Left sidebar: scheduled reports.
          Desktop: fixed left, 320px, always visible (below topbar + above sticky footer).
          Mobile : off-canvas left overlay, toggled by #reports-sidebar-toggle button in topbar. -->
     <aside id="reports-sidebar" class="reports-sidebar" aria-label="Reportes programados" hidden data-theme-only="dark">
@@ -615,8 +614,8 @@
           </label>
 
           <!-- Camera tool row — HIDDEN BY DEFAULT TODAY.
-               Per riattivarlo in futuro: togli hidden da div + small,
-               scommenta listener toolCamSwitch + funzioni enableCamera in main.js. -->
+               To reactivate later, remove hidden from the div and small,
+               then restore the toolCamSwitch listener and enableCamera functions in main.js. -->
           <div class="tool-row tool-row-sep" id="tool-cam-row" hidden>
             <div class="tool-info">
               <span class="tool-name">Camera</span>
diff --git a/s2s-client/main.js b/s2s-client/main.js
index 240d82d..551f1f9 100644
--- a/s2s-client/main.js
+++ b/s2s-client/main.js
@@ -22,36 +22,35 @@ import { ChatView } from "./ui/chat.js?v=202609041120";
 import { Account } from "./ui/account.js?v=202609041120";
 
 // ---------------------------------------------------------------------------
-// 🔎 DEBUG BANNER (always-on): emissione incondizionata in console per capire
-// ESATTAMENTE quale versione di main.js è caricata nel browser.
-// Se NON vedi questa riga in Console = stai ancora usando il file CACHATO VECCHIO.
+// 🔎 DEBUG BANNER (always-on): identify the exact main.js version loaded.
+// If this line is missing from the console, the browser is using an older cached file.
 console.info(
-  "%c🟢 VOCERO main.js loaded. version=2026-09-24 23:12 (DEBUG FETCH WRAPPER+WS SEMPRE-ATTIVO; APIPILOT: demo flag=true + PREFETCH AUTOMATICO OGNI SESSIONE WS + PREFETCH DOPO LOGIN-BY-PHONE OK (refresh=true per invalidare cache server anonima); cache client per-utente; cambio phone = invalidate automatico; export chat; fix scroll).",
+  "%c🟢 VOCERO main.js loaded. version=2026-09-24 23:12 (ALWAYS-ON FETCH WRAPPER+WS DEBUG; APIPILOT: demo flag=true + AUTOMATIC PREFETCH FOR EVERY WS SESSION + PREFETCH AFTER PHONE LOGIN (refresh=true invalidates the anonymous server cache); per-user client cache; phone changes invalidate automatically; chat export; scroll fix).",
   "background:#1e293b;color:#86efac;font-weight:700;padding:4px 8px;border-radius:4px;"
 );
 console.info(
-  "   URL attuale location.href=", location.href,
+  "   Current URL location.href=", location.href,
   "\n   location.search=", location.search || "(empty)",
   "\n   DEBUG (imported from dom.js) =", DEBUG,
   "\n   typeof window.DEBUG =", typeof window.DEBUG
 );
 // eslint-disable-next-line no-debugger
-// debugger;  // ← scommenta per fermarti QUI all'avvio se DevTools è aperto
+// debugger;  // Uncomment to pause here at startup when DevTools is open.
 
 // ---------------------------------------------------------------------------
-// 🔎 FETCH WRAPPER (SEMANTIC DEBUG LOG) — attivo SEMPRE (non solo in DEBUG)
-// Ogni chiamata `fetch` lato browser viene intercettata e loggata con:
-//   • URL risolto, metodo, dimensioni body + preview JSON
-//   • status HTTP (colorato verde/giallo/rosso a seconda della classe)
-//   • durata (performance.now), dimensione + preview risposta JSON
-// Tag semantici per filtrare veloce la Console:
+// 🔎 FETCH WRAPPER (SEMANTIC DEBUG LOG) — always active, including outside DEBUG.
+// Every browser fetch is traced with:
+//   • resolved URL, method, body size and JSON preview
+//   • HTTP status (green/yellow/red according to status class)
+//   • duration (performance.now), response size and JSON preview
+// Semantic tags for filtering the console:
 //   [FETCH:CONFIG]     [FETCH:REASONING]  [FETCH:SEARCH]
 //   [FETCH:PROFILE]    [FETCH:REPORTS]    [FETCH:APIPILOT]
 //   [FETCH:SESSION]    [FETCH:QUEUE]      [FETCH:ME]
 // ---------------------------------------------------------------------------
 (function _installFetchDebugTracer() {
   const ORIGINAL_FETCH = window.fetch.bind(window);
-  // Classifica endpoint in tag leggibile (stesso ordine di @app route in server.py).
+  // Classify endpoints with readable tags, following the route order in server.py.
   /** @param {string} url */
   function _tagFor(url) {
     try {
@@ -108,13 +107,13 @@ console.info(
     /** @type {BodyInit | null | undefined} */
     let body = init ? init.body : undefined;
     if (body === undefined || body === null) {
-      // tenta Request
+      // Try the Request body.
       try {
         const r = /** @type {{body?:BodyInit|null}} */ (/** @type {unknown} */ (input));
         if (r && r.body != null) body = r.body;
       } catch { body = null; }
     }
-    if (body == null) return { length: 0, preview: "(nessun body)" };
+    if (body == null) return { length: 0, preview: "(no body)" };
     try {
       if (typeof body === "string") {
         const s = body;
@@ -138,7 +137,7 @@ console.info(
       if (body instanceof Blob) return { length: body.size, preview: `BLOB (${body.type || "unknown"}) size=${body.size}` };
       if (ArrayBuffer.isView(body)) return { length: body.byteLength, preview: `ArrayBufferView len=${body.byteLength}` };
       if (body instanceof ArrayBuffer) return { length: body.byteLength, preview: `ArrayBuffer len=${body.byteLength}` };
-      return { length: 0, preview: "(body non serializzabile nel log)" };
+      return { length: 0, preview: "(body cannot be serialized for logging)" };
     } catch (err) {
       return { length: -1, preview: `(err preview body: ${err})` };
     }
@@ -178,9 +177,8 @@ console.info(
     const method = _extractMethod(input, init);
     const rawUrl = _stringifyUrl(input);
     const tag = _tagFor(rawUrl);
-    // Per richieste "heartbeat / end poll" (molto frequenti) logghiamo un
-    // singleton collapse per evitare spam: se `?quiet=true` o URL match → log
-    // a riga singola e non mostriamo preview.
+    // Log frequent heartbeat/end polling requests on one line without a body
+    // preview to keep the console readable.
     const isPollish = /heartbeat|queue\/end|session\/end/i.test(tag) || (init && typeof init.keepalive === "boolean" && init.keepalive);
     const reqPreview = isPollish ? null : await _extractBodyPreview(input, init);
     if (!isPollish) {
@@ -245,18 +243,18 @@ console.info(
     return response;
   };
   console.info(
-    "%c🔎 [FETCH-DEBUG] tracer installato. Ogni fetch è loggata con tag, method, url, status, durata e preview body.",
+    "%c🔎 [FETCH-DEBUG] tracer installed. Every fetch logs its tag, method, URL, status, duration and body preview.",
     "background:#ecfeff;color:#0369a1;font-weight:700;padding:2px 6px;border-radius:4px;"
   );
 })();
 
 // ---------------------------------------------------------------------------
 // 🛡️ GATE .topbar-right (about / tools / rag / chat / settings buttons,
-// vedi index.html L36-L56) — 3-layer safety:
-//   1) HTML statico → hidden + data-debug-only="true"
+// see index.html) — 3-layer safety:
+//   1) static HTML → hidden + data-debug-only="true"
 //   2) CSS         → [data-debug-only="true"]:not([data-debug-enabled="true"]) display:none !important
-//   3) JS qui      → hidden, removeAttribute data-debug-enabled, anche style.display = "none"
-// Solo se URL query-string ha ?debug=true (strict string) abilitiamo TUTTO.
+//   3) JS here    → hidden, remove data-debug-enabled, set style.display = "none"
+// Enable all debug controls only when the URL contains ?debug=true (strict string).
 function applyDebugOnlyVisibilityGate(source = "bootstrap") {
   const qs = new URLSearchParams(window.location.search);
   const debugEnabled = qs.get("debug") === "true";
@@ -265,64 +263,61 @@ function applyDebugOnlyVisibilityGate(source = "bootstrap") {
     "%c🧭 [gate-topbar-right] applyDebugOnlyVisibilityGate()",
     "color:#f59e0b;font-weight:700;"
   );
-  console.log("chiamato da:", source);
+  console.log("called from:", source);
   console.log("location.search =", JSON.stringify(window.location.search));
   console.log("query params =", Object.fromEntries(qs.entries()));
   console.log("debugEnabled (strict === 'true') =", debugEnabled);
-  console.log("topbarRight element trovato?", !!topbarRight, topbarRight ? "vedi →" : "(null!)");
+  console.log("topbarRight element found?", !!topbarRight, topbarRight ? "see →" : "(null!)");
   const chatInline = document.getElementById("chat-panel");
-  console.log("#chat-panel (chat inline SEMPRE VISIBILE in basso) presente in DOM =", !!chatInline, chatInline ? "hidden?" : "", chatInline ? chatInline.hasAttribute("hidden") : "-");
+  console.log("#chat-panel (inline chat ALWAYS VISIBLE at the bottom) present in DOM =", !!chatInline, chatInline ? "hidden?" : "", chatInline ? chatInline.hasAttribute("hidden") : "-");
   if (topbarRight) {
-    console.log("   hidden attr prima:", topbarRight.hasAttribute("hidden"),
-                "| data-debug-enabled prima:", topbarRight.getAttribute("data-debug-enabled"),
-                "| style.display prima:", topbarRight.style.display);
+    console.log("   hidden attr before:", topbarRight.hasAttribute("hidden"),
+                "| data-debug-enabled before:", topbarRight.getAttribute("data-debug-enabled"),
+                "| style.display before:", topbarRight.style.display);
     if (debugEnabled) {
       topbarRight.setAttribute("data-debug-enabled", "true");
       topbarRight.removeAttribute("hidden");
       topbarRight.style.display = "";
-      console.log("%c   ✅ ABILITATO .topbar-right (debug=true)", "color:#22c55e;font-weight:700;");
+      console.log("%c   ✅ ENABLED .topbar-right (debug=true)", "color:#22c55e;font-weight:700;");
     } else {
       topbarRight.removeAttribute("data-debug-enabled");
       topbarRight.setAttribute("hidden", "");
       topbarRight.style.setProperty("display", "none", "important");
-      console.log("%c   🚫 DISABILITATO .topbar-right (no debug=true)",
+      console.log("%c   🚫 DISABLED .topbar-right (no debug=true)",
                   "background:#fee2e2;color:#b91c1c;font-weight:700;padding:3px 6px;border-radius:4px;");
     }
-    console.log("   hidden attr dopo:", topbarRight.hasAttribute("hidden"),
-                "| data-debug-enabled dopo:", topbarRight.getAttribute("data-debug-enabled"),
-                "| style.display dopo:", topbarRight.style.display);
+    console.log("   hidden attr after:", topbarRight.hasAttribute("hidden"),
+                "| data-debug-enabled after:", topbarRight.getAttribute("data-debug-enabled"),
+                "| style.display after:", topbarRight.style.display);
   }
-  // 3-layer gate UNIVERSALE su TUTTI gli elementi marcati con data-debug-only="true"
-  // (non solo .topbar-right, ma anche #reports-sidebar-toggle e qualsiasi
-  // altro elemento futuro marcato con lo stesso attributo).
+  // Apply the 3-layer gate to every element marked data-debug-only="true",
+  // including .topbar-right, #reports-sidebar-toggle and future controls.
   const debugOnlyEls = document.querySelectorAll("[data-debug-only='true']");
   console.log(
-    `Trovati ${debugOnlyEls.length} elementi [data-debug-only="true"] da gate-are in base a debugEnabled=${debugEnabled}`,
+    `Found ${debugOnlyEls.length} elements [data-debug-only="true"] to gate using debugEnabled=${debugEnabled}`,
   );
   debugOnlyEls.forEach((el, idx) => {
     const tag = `${el.tagName.toLowerCase()}${el.id ? `#${el.id}` : ""}${el.className && typeof el.className === "string" ? `.${el.className.split(/\s+/).filter(Boolean).slice(0, 2).join(".")}` : ""}`;
-    console.log(`   [${idx + 1}/${debugOnlyEls.length}] ${tag} — hidden prima? ${el.hasAttribute("hidden")} | display prima: ${(el instanceof HTMLElement ? el.style.display : "-")}`);
+    console.log(`   [${idx + 1}/${debugOnlyEls.length}] ${tag} — hidden before? ${el.hasAttribute("hidden")} | display before: ${(el instanceof HTMLElement ? el.style.display : "-")}`);
     if (!(el instanceof HTMLElement)) return;
     if (debugEnabled) {
       el.setAttribute("data-debug-enabled", "true");
-      // Non forziamo hidden=false su elementi che sono logicamente hidden per
-      // altri motivi (es. #reports-sidebar-toggle è hidden se non ci sono
-      // reports). Rimuoviamo lo "spegnimento debug-only" e basta.
+      // Preserve elements hidden for other reasons, such as an empty reports
+      // sidebar. Remove only the debug-only display override.
       el.style.removeProperty("display");
     } else {
       el.removeAttribute("data-debug-enabled");
       el.setAttribute("hidden", "");
       el.style.setProperty("display", "none", "important");
     }
-    console.log(`       → debugEnabled=${debugEnabled} → hidden dopo? ${el.hasAttribute("hidden")} | display dopo: ${el.style.display || "(inherit)"}`);
+    console.log(`       → debugEnabled=${debugEnabled} → hidden after? ${el.hasAttribute("hidden")} | display after: ${el.style.display || "(inherit)"}`);
   });
   console.groupEnd();
   return debugEnabled;
 }
-// Esegui SUBITO al bootstrap del modulo (prima di qualsiasi listener)
+// Run immediately during module bootstrap, before registering listeners.
 const GLOBAL_DEBUG_ENABLED__TOPBAR = applyDebugOnlyVisibilityGate("main.js module bootstrap (top)");
-// Riesegui dopo DOMContentLoaded per sicurezza (nel caso query script sia posizionato
-// in testa e l'HTML header non sia ancora parse-ato quando girano queste righe)
+// Run again after DOMContentLoaded in case the script runs before the header is parsed.
 if (document.readyState === "loading") {
   document.addEventListener("DOMContentLoaded", () => {
     applyDebugOnlyVisibilityGate("DOMContentLoaded listener");
@@ -330,7 +325,7 @@ if (document.readyState === "loading") {
 } else {
   applyDebugOnlyVisibilityGate("module bootstrap (DOM already parsed)");
 }
-// Riesegui anche a fine frame dopo un breve timeout → ultima chance.
+// Run again after a short timeout as a final fallback.
 setTimeout(() => applyDebugOnlyVisibilityGate("10ms timeout fallback"), 10);
 window.addEventListener("hashchange", () => applyDebugOnlyVisibilityGate("hashchange"), { passive: true });
 window.addEventListener("popstate", () => applyDebugOnlyVisibilityGate("popstate"), { passive: true });
@@ -339,12 +334,12 @@ const DEFAULT_VOICE = "Aiden";
 const DEFAULT_INSTRUCTIONS =
   "You are Vocero, a friendly voice assistant. " +
   "Keep replies short, warm, and spoken. Avoid long monologues. " +
-  "Respond ALWAYS and ONLY in Spanish (Castellano / español), regardless of the language used by the user or any other instruction. " +
+  "Respond ALWAYS and ONLY in Spanish, regardless of the language used by the user or any other instruction. " +
   "No responses in Italian, English, Portuguese, or any other language are allowed. " +
   "Every spoken sentence, greeting, confirmation, clarification, and error message must be in Spanish."+ 
   "the comma sign ',' in numbers it's used to separate thousands."+ 
   "the point sign '.' in numbers it's used to separate decimals."+ 
-  "If you don't know the answer, say 'I don't know' instead of guessing.";
+  "If you don't know the answer, say so in Spanish instead of guessing.";
 
 const OPENAI_RENDER_MARKER = "[VOCERO_RENDER_REPLY]";
 const OPENAI_RENDER_HINT =
@@ -1314,13 +1309,13 @@ function syncVoceroHeaderUser() {
   ul.className = "reports-list";
   const labelTintFor = (rawLabel) => {
     const l = String(rawLabel || "").toLowerCase();
-    if (l.includes("mortalidad") || l.includes("riesgo") || l.includes("kpi")) return "mortalidad";
-    if (l.includes("métrica") || l.includes("metricas") || l.includes("medici")) return "metricas";
-    if (l.includes("diario") || l.includes("diaria") || l.includes("informe")) return "diario";
-    if (l.includes("producto") || l.includes("servicio")) return "productos";
+    if (l.includes("mortalidad") || l.includes("riesgo") || l.includes("kpi")) return "mortality";
+    if (l.includes("métrica") || l.includes("metricas") || l.includes("medici")) return "metrics";
+    if (l.includes("diario") || l.includes("diaria") || l.includes("informe")) return "daily";
+    if (l.includes("producto") || l.includes("servicio")) return "products";
     if (l.includes("synapse") || l.includes("ejecucion") || l.includes("calendario") || l.includes(" ti ") || l.endsWith("ti")) return "synapse";
     if (l.includes("supply") || l.includes("cadena") || l.includes("log") || l.includes("envío") || l.includes("envio") || l.includes("chile")) return "supply";
-    if (l.includes("financiero") || l.includes("finanzas") || l.includes("costo") || l.includes("presupuesto") || l.includes("venta")) return "finanzas";
+    if (l.includes("financiero") || l.includes("finanzas") || l.includes("costo") || l.includes("presupuesto") || l.includes("venta")) return "finance";
     return "";
   };
   for (const e of entries) {
@@ -1330,7 +1325,7 @@ function syncVoceroHeaderUser() {
     li.textContent = String(e.sourceScheduleLabel);
     ul.appendChild(li);
   }
-  // Build dynamic suggestion prompts (en español) based on the actual labels so
+  // Build dynamic suggestion prompts in Spanish based on the actual labels so
   // the user knows what they can ask the assistant about. Max 4 suggestions;
   // pick first N entries by priority.
   const suggestions = /** @type {string[]} */ ([]);
@@ -1374,20 +1369,20 @@ function syncVoceroHeaderUser() {
   const qs = new URLSearchParams(window.location.search);
   const debugParamRaw = qs.get("debug");
   // eslint-disable-next-line no-debugger
-  // debugger;    // ← scommenta per fermarti dentro syncVoceroHeaderUser ogni volta
+  // debugger;    // Uncomment to pause inside every syncVoceroHeaderUser call.
   console.groupCollapsed("%c🔍 [reports-ui] syncVoceroHeaderUser() render details", "color:#60a5fa;font-weight:700;");
   console.log("location.href =", location.href);
   console.log("location.search =", JSON.stringify(window.location.search));
-  console.log("tutti i query params =", Object.fromEntries(qs.entries()));
+  console.log("all query params =", Object.fromEntries(qs.entries()));
   console.log("pageParams (legacy module-load) .get('debug') =", JSON.stringify(pageParams.get("debug")));
   console.log("fresh qs .get('debug') =", JSON.stringify(debugParamRaw), "| typeof =", typeof debugParamRaw);
   console.log("strict === 'true' ? =", debugParamRaw === "true");
-  console.log("count (labels uniche) =", count, "| wrappedLen =", totalLen);
-  console.log("suggerimenti array length (prima del gate debug) =", suggestions.length);
+  console.log("count (unique labels) =", count, "| wrappedLen =", totalLen);
+  console.log("suggestions array length (before debug gate) =", suggestions.length);
   suggestions.forEach((s, i) => console.log(`   sug[${i}] = ${s}`));
   const currentDebug = debugParamRaw === "true";
   const debugMode = currentDebug;
-  console.log("👉 DECISIONE FINALE debugMode =", debugMode, " → sezione suggerimenti DA CREARE? ", debugMode ? "✅ SÌ" : "❌ NO");
+  console.log("👉 FINAL DECISION debugMode =", debugMode, " → CREATE suggestions section? ", debugMode ? "✅ YES" : "❌ NO");
   console.groupEnd();
 
   let sugSection = null;
@@ -1406,10 +1401,10 @@ function syncVoceroHeaderUser() {
     }
     sugSection.appendChild(sugTitle);
     sugSection.appendChild(sugUl);
-    console.log("%c[reports-ui] sezione suggerimenti CREATA (debugMode=true)", "color:#22c55e;font-weight:700;",
+    console.log("%c[reports-ui] suggestions section CREATED (debugMode=true)", "color:#22c55e;font-weight:700;",
                 "nItems=", sugUl.children.length, "innerHTML=", sugSection.outerHTML.slice(0, 300));
   } else {
-    console.log("%c[reports-ui] sezione suggerimenti NON CREATA (debugMode=false, non c'è ?debug=true)",
+    console.log("%c[reports-ui] suggestions section NOT CREATED (debugMode=false, no ?debug=true)",
                 "color:#ef4444;font-weight:700;");
   }
 
@@ -1453,7 +1448,7 @@ function syncVoceroHeaderUser() {
     const qs = new URLSearchParams(window.location.search);
     const debugParam = qs.get("debug") === "true";
     console.info(
-      "%c[reports-ui] toggle reports-sidebar-toggle: hidden? PRIMA=%s | debug=%s",
+      "%c[reports-ui] toggle reports-sidebar-toggle: hidden? BEFORE=%s | debug=%s",
       "color:#f59e0b;font-weight:700;",
       reportsSidebarToggle.hasAttribute("hidden"),
       debugParam,
@@ -1464,7 +1459,7 @@ function syncVoceroHeaderUser() {
       reportsSidebarToggle.setAttribute("hidden", "");
       reportsSidebarToggle.style.setProperty("display", "none", "important");
       reportsSidebarToggle.removeAttribute("data-debug-enabled");
-      console.info("%c[reports-ui] 🚫 reports sidebar toggle FORZATO HIDDEN (no debug=true)",
+      console.info("%c[reports-ui] 🚫 reports sidebar toggle FORCED HIDDEN (no debug=true)",
                     "background:#fee2e2;color:#b91c1c;font-weight:700;padding:3px 6px;border-radius:4px;");
     }
   }
@@ -1476,10 +1471,10 @@ function syncVoceroHeaderUser() {
 
   // eslint-disable-next-line no-console
   console.info(
-    "%c[reports-ui] FINE RENDER. reportsHint.querySelectorAll('.reports-suggestions').length =",
+    "%c[reports-ui] RENDER COMPLETE. reportsHint.querySelectorAll('.reports-suggestions').length =",
     "color:#a855f7;font-weight:700;",
     reportsHint.querySelectorAll(".reports-suggestions").length,
-    "| children nel blocco:", reportsHint.children.length,
+    "| children in block:", reportsHint.children.length,
     "| reportsHint.hidden=", reportsHint.hidden,
     "| #reports-sidebar hidden=", reportsSidebar ? reportsSidebar.hidden : "no-sidebar-el",
     "| badge count:", reportsSidebarBadge ? reportsSidebarBadge.getAttribute("data-count") : "no-badge"
@@ -1513,21 +1508,19 @@ function effectiveReasoningInstructions() {
     ragAppended = true;
   }
   // ───────────────────────────────────────────────────────────────────────────
-  // 2026-09-25 INJECT API-PILOT HERAMIENTAS DINÁMICAS (PASADA 1).
-  // Formato IDENTICO a server.py Python: marker <<<APIPILOT_TOOLS_LIST_BEGIN>>>
-  // / ...lista name+description+requires_auth+required_parameters... / <<<END>>>.
-  // Il client ottiene la lista dal proxy GET api/apipilot/tools (cache 240 s
-  // per-utente in s2s-ws-client.js _apipilotClientCache) e la appende qui alle
-  // instructions STESSE (luogo #1 di massima priorità per l'LLM).
-  // Dedup: se le instructions già contengono il marker (già appese in una
-  // esecuzione precedente, oppure server Python ha già patchato il payload)
-  // → NON appendere nuovamente (no doppioni, no blob gigante).
+  // 2026-09-25 INJECT API-PILOT DYNAMIC TOOLS (PASS 1).
+  // Match the server.py format: <<<APIPILOT_TOOLS_LIST_BEGIN>>>, followed by
+  // name+description+requires_auth+required_parameters and the closing marker.
+  // Fetch tools through GET api/apipilot/tools (240 s per-user client cache in
+  // s2s-ws-client.js) and append them directly to the LLM instructions.
+  // Deduplicate by marker when a previous call or the Python server already
+  // injected the list, avoiding duplicate or oversized prompt blocks.
   let apipilotBlock = "";
   let apipilotCount = 0;
   let apipilotAppended = false;
   try {
-    // @ts-ignore: esposto globalmente da s2s-ws-client.js (caricato prima di
-    // main.js in index.html). Valuta sicuro: typeof + early-skip.
+    // @ts-ignore: exported globally by s2s-ws-client.js, loaded before main.js.
+    // Check typeof before calling the optional helper.
     const getter = typeof window !== "undefined" && window.__s2sGetApipilotPass1ContextInfo;
     if (typeof getter === "function") {
       const info = getter();
@@ -1544,7 +1537,7 @@ function effectiveReasoningInstructions() {
       }
     }
   } catch (_) {
-    /* never-fail: non bloccare il resto dell'istruzione prompt. */
+    /* Never block the rest of the instructions prompt. */
   }
   const key = `effInst:${injectProfile ? "T" : "F"}:${ctx ? "hasCtx" : "noCtx"}:${ragCtx ? "hasRag" : "noRag"}:${apipilotAppended ? "apipilotY" : "apipilotN"}:${(base || "").length}`;
   _logOnce(key, () => {
@@ -1701,7 +1694,7 @@ async function fetchOpenAiReasoningAnswer(transcript) {
   const json = await res.json();
   const answer = typeof json?.answer === "string" ? json.answer.trim() : "";
   const log_only = Boolean(json && json.log_only === true);
-  // Log-only mode: può tornare answer="" — non è un errore.
+  // Log-only mode may return answer=""; that is not an error.
   if (!answer && !log_only) throw new Error("reasoning returned no answer");
   return { answer, log_only, raw: json };
 }
@@ -1732,10 +1725,10 @@ async function maybeRunOpenAiReasoning(transcript, itemId) {
     });
     return;
   }
-  // ── LOG-ONLY MODE (FASE 1) ─────────────────────────────────────────────
-  // Node-RED si limita a loggare e torna log_only=true.
-  // NON cancelliamo la risposta backend, NON iniettiamo testo, NON parliamo.
-  // Il flusso resta COMPLETAMENTE a carico del backend S2S nativo.
+  // ── LOG-ONLY MODE (PHASE 1) ────────────────────────────────────────────
+  // Node-RED only logs the request and returns log_only=true.
+  // Preserve the backend response without injecting text or speaking.
+  // The native S2S backend remains responsible for the entire turn.
   if (result && result.log_only) {
     reportDebug("R", "main.js:maybeRunOpenAiReasoning", "external reasoning in LOG_ONLY mode — pass through to native S2S backend", {
       itemId,
@@ -1749,9 +1742,9 @@ async function maybeRunOpenAiReasoning(transcript, itemId) {
     );
     return;
   }
-  // ── MODE STANDARD (fasi successive) ────────────────────────────────────
-  // Il reasoning esterno vince: annulla la risposta nativa, inserisci il
-  // testo dell'assistente e parla via SpeechSynthesis.
+  // ── STANDARD MODE (LATER PHASES) ──────────────────────────────────────
+  // External reasoning takes priority: cancel the native response, insert
+  // the assistant text and speak through SpeechSynthesis.
   const answer = (result && result.answer) || "";
   if (!answer) {
     console.warn(`[Vocero REASONING] empty non-log-only answer itemId=${JSON.stringify(itemId)}`);
@@ -2461,16 +2454,16 @@ async function fetchVoceroUserProfile() {
         Object.keys(voceroUserProfile).join(","),
         extractVoceroUserName(voceroUserProfile) || "(none)",
       );
-      // ── 🚀 PREFETCH ApiPilot IMMEDIATAMENTE DOPO LOGIN-BY-PHONE RIUSCITO
-      // Forza refresh=true per bypassare la cache SERVER lato proxy S2S (TTL 300s)
-      // perché adesso abbiamo un profilo utente autenticato (non più anonimo).
-      // In questo modo vediamo la riga [apipilot] list_tools.start user=(non-anon)
-      // nel backend AquaPortal OGNI VOLTA che c'è un login phone riuscito.
+      // ── 🚀 PREFETCH ApiPilot IMMEDIATELY AFTER SUCCESSFUL PHONE LOGIN
+      // Force refresh=true to bypass the S2S proxy server cache (TTL 300 s)
+      // now that the caller is authenticated rather than anonymous.
+      // AquaPortal logs [apipilot] list_tools.start user=(non-anon) after
+      // every successful phone login.
       try {
         if (window.__s2sApipilot) {
           const t0 = performance.now();
           console.info(
-            "%c🔧 [APIPILOT-CLIENT] post-login phone → FORZO refresh api/apipilot/tools (bypass cache S2S 300s perché utente appena autenticato)",
+            "%c🔧 [APIPILOT-CLIENT] post-login phone → FORCE refresh api/apipilot/tools (bypass the 300 s S2S cache for the newly authenticated user)",
             "background:#ede9fe;color:#5b21b6;font-weight:700;padding:2px 6px;border-radius:4px;"
           );
           const demoToken = typeof window.__s2sDemoSessionToken === "string" ? window.__s2sDemoSessionToken : "";
@@ -2485,24 +2478,23 @@ async function fetchVoceroUserProfile() {
             if (!r.ok) throw new Error(`HTTP ${r.status}`);
             const j = await r.json().catch(() => ({}));
             const ok = j && j.success && j.data;
-            if (!ok) throw new Error(`envelope non corretto success=${Boolean(j && j.success)}`);
+            if (!ok) throw new Error(`invalid envelope success=${Boolean(j && j.success)}`);
             const tools = Array.isArray(j.data.tools) ? j.data.tools : [];
             const count = typeof j.data.count === "number" ? j.data.count : tools.length;
             const names = tools.slice(0, 6).map((t) => (typeof t.name === "string" ? t.name : "?")).join(", ");
-            // Invalida cache client WS per ogni sessione futura (in modo che
-            // al prossimo connect() venga fatto un refresh per ri-confermare).
+            // Invalidate the WS client cache so the next session refreshes it.
             try {
               // @ts-ignore
               if (typeof window.__s2sInvalidateApipilotCache === "function") window.__s2sInvalidateApipilotCache();
             } catch (_) { /* noop */ }
             console.info(
-              `%c🔧 [APIPILOT-CLIENT] post-login OK (dt=${dt}ms): N=${count} strumenti [primi 6: ${names || "(nessuno)"}]`,
+              `%c🔧 [APIPILOT-CLIENT] post-login OK (dt=${dt}ms): N=${count} tools [first 6: ${names || "(none)"}]`,
               "background:#ecfdf5;color:#047857;font-weight:700;padding:2px 6px;border-radius:4px;"
             );
           }).catch((err) => {
             const dt = Math.round(performance.now() - t0);
             console.warn(
-              `%c🔧 [APIPILOT-CLIENT] post-login FAIL (dt=${dt}ms): ${String(err instanceof Error ? err.message : err)} → controlla [APIPILOT-DISCOVERY] nel log server S2S`,
+              `%c🔧 [APIPILOT-CLIENT] post-login FAIL (dt=${dt}ms): ${String(err instanceof Error ? err.message : err)} → check [APIPILOT-DISCOVERY] in the S2S server logs`,
               "background:#fffbeb;color:#92400e;font-weight:700;padding:2px 6px;border-radius:4px;"
             );
           });
@@ -2618,10 +2610,9 @@ async function fetchConfig() {
       pinnedPrompt = (json.primaryPrompt || "").trim();
       injectProfile = !!json.injectProfile;
       debugPrompt = !!json.debugPrompt;
-      // Feature flag: ApiPilot AquaPortal bridge attivo sul server.
-      // Se true = S2S_APIPILOT_TOOLS_URL è valorizzato lato backend e
-      // gli endpoint proxy /api/apipilot/tools e /api/apipilot/execute
-      // sono disponibili per il frontend.
+      // Feature flag for the server-side ApiPilot AquaPortal bridge.
+      // True means S2S_APIPILOT_TOOLS_URL is configured and the frontend can
+      // use /api/apipilot/tools and /api/apipilot/execute.
       const apipilotEnabled = !!json.apipilot;
       if (typeof window.__s2sApipilot === "undefined") {
         try { Object.defineProperty(window, "__s2sApipilot", { value: false, writable: true, configurable: true }); }
@@ -2672,16 +2663,15 @@ async function fetchConfig() {
         apipilotEnabled,
       });
       // #endregion
-      // ── Demo call ApiPilot (fire-and-forget, solo se flag=true sul server)
-      // Serve ESCLUSIVAMENTE per attivare il tracer fetch lato browser e
-      // mostrare in console la riga [FETCH:APIPILOT:TOOLS] con preview
-      // status, durata e lista strumenti. Proxy server-side verso
+      // ── ApiPilot demo call (fire-and-forget, only when the server flag is true)
+      // Trigger the browser fetch tracer to show [FETCH:APIPILOT:TOOLS] with
+      // status, duration and a tool-list preview. The server proxies to
       // S2S_APIPILOT_TOOLS_URL/tools.
       if (apipilotEnabled) {
         try {
           const demoUrl = "api/apipilot/tools?include_unauthorized=true";
           console.info(
-            "%c🔧 [APIPILOT-CLIENT] flag=true → DEMO CALL %s (tracer sempre-attivo logga [FETCH:APIPILOT:TOOLS] sotto)",
+            "%c🔧 [APIPILOT-CLIENT] flag=true → DEMO CALL %s (always-on tracer logs [FETCH:APIPILOT:TOOLS] below)",
             "background:#e0e7ff;color:#3730a3;font-weight:700;padding:2px 6px;border-radius:4px;",
             demoUrl
           );
@@ -2693,15 +2683,15 @@ async function fetchConfig() {
               const count = (j && j.data && typeof j.data.count === "number") ? j.data.count : tools.length;
               const names = tools.slice(0, 5).map((t) => (typeof t.name === "string" ? t.name : "?")).join(", ");
               console.info(
-                "%c🔧 [APIPILOT-CLIENT] demo OK: %s strumenti  [primi 5: %s]   usa POST api/apipilot/execute {name,arguments} per eseguire",
+                "%c🔧 [APIPILOT-CLIENT] demo OK: %s tools  [first 5: %s]   use POST api/apipilot/execute {name,arguments} to execute",
                 "background:#ecfdf5;color:#047857;font-weight:700;padding:2px 6px;border-radius:4px;",
                 count,
-                names || "(nessuno)"
+                names || "(none)"
               );
             })
             .catch((err) => {
               console.warn(
-                "%c🔧 [APIPILOT-CLIENT] demo FAIL: %s. Lato server logga [APIPILOT-DISCOVERY] per diagnosticare",
+                "%c🔧 [APIPILOT-CLIENT] demo FAIL: %s. Check [APIPILOT-DISCOVERY] server logs to diagnose",
                 "background:#fffbeb;color:#92400e;font-weight:700;padding:2px 6px;border-radius:4px;",
                 String(err)
               );
@@ -2903,16 +2893,16 @@ function _applyThemeRuntime() {
     }
   }
 
-  // 6. Quick action buttons: clicking "Resumen" / "Consultar datos" /
-  //    "Crear respuesta" populates the text input or — if a realtime
+  // 6. Quick action buttons for summaries, data lookup and response drafts
+  //    populate the text input or — if a realtime
   //    session is live — sends it as user text straight away.
   document.querySelectorAll(".quick-action-btn").forEach(btn => {
     btn.addEventListener("click", () => {
       const action = btn.getAttribute("data-action") || "";
       const prompts = {
-        "resumen":          "haz un resumen ejecutivo del último informe programado",
-        "consultar-datos":  "consulto los datos más recientes del dashboard, dame las cifras clave",
-        "crear-respuesta":  "redacta un borrador de respuesta profesional con tono ejecutivo",
+        "summary":         "haz un resumen ejecutivo del último informe programado",
+        "query-data":      "consulto los datos más recientes del dashboard, dame las cifras clave",
+        "draft-response":  "redacta un borrador de respuesta profesional con tono ejecutivo",
       };
       const text = prompts[action] || "";
       if (!text) return;
@@ -3480,8 +3470,8 @@ function onClientStatus(status) {
     case "creating-session":
     case "connecting":
       // Qualsiasi inizio connessione (manuale da Orb / restart o unlocker):
-      // se il talk-unlocker è ancora visibile (utente ha cliccato l'Orb prima
-      // del 2s warmup, ad esempio) lo nascondiamo subito.
+      // Hide the talk unlocker immediately if it is still visible, for
+      // example when the user taps the orb before the 2 s warmup ends.
       hideTalkUnlocker();
       setState("connecting");
       break;
@@ -3575,19 +3565,16 @@ function onFatalError(err) {
 setState("idle");
 chat.renderEmptyState();
 initGateArc();
-// Schedulo auto-start TALK / TALKFIRST (S2S_START_SESSION_MODE nel .env):
-//   • "TALK"      → dopo 2s mostra overlay unlocker (policy browser:
-//                   getUserMedia() richiede gesture). Click/touch/tasto =
-//                   doStart() dentro la gesture, poi ws startWithResponse
-//                   inject hola vocero via sendUserText+requestResponse nel
-//                   ws client (stesso flow identico a wake-word).
-//   • "TALKFIRST" → dopo 2s TENTA direttamete doStart() dal timer, con
-//                   pendingWakeWordConfirmationText preimpostato. Se i
-//                   permessi del mic sono GRANTED (già consentiti in passato
-//                   o Chrome policy permissive), la wake-word simulata scatta
-//                   subito senza nessun click. Se invece fallisce per
-//                   permesso / gesture (Safari/iOS), fallback sullo stesso
-//                   unlocker di TALK.
+// Schedule TALK / TALKFIRST auto-start (S2S_START_SESSION_MODE in .env):
+//   • "TALK"      → show the unlocker after 2 s. Browser policy requires a
+//                   gesture for getUserMedia(). A click/touch/key starts
+//                   doStart(), then WS startWithResponse injects hola vocero
+//                   through sendUserText+requestResponse, like a wake word.
+//   • "TALKFIRST" → try doStart() directly from the timer after 2 s with
+//                   pendingWakeWordConfirmationText already set. If mic
+//                   permission is granted, the simulated wake word triggers
+//                   without a click. Permission/gesture failures on Safari
+//                   or iOS fall back to the TALK unlocker.
 let autoStartTalkTimerId = 0;
 let _talkUnlockerShown = false;
 function hideTalkUnlocker() {
@@ -3599,11 +3586,9 @@ function showTalkUnlocker(fallbackHint = false) {
   if (!(startSessionMode === "TALK" || startSessionMode === "TALKFIRST")) return;
   const el = document.getElementById("talk-unlocker");
   if (!el) return;
-  // L'unlocker è utile solo a stato idle/error: se l'utente ha già cliccato l'Orb
-  // o è connecting/connected non mostriamo niente.
+  // Show the unlocker only while idle/error, before a session starts.
   if (!(currentState === "idle" || currentState === "error")) return;
-  // Se è fallback da TALKFIRST cambiamo il testo in modo che spieghi perché
-  // è comparso ("tocca per consentire il microfono", invece di "preparando")
+  // Explain the microphone permission requirement when TALKFIRST falls back.
   const subEl = el.querySelector(".talk-unlocker-sub");
   const titleEl = el.querySelector(".talk-unlocker-title");
   if (fallbackHint) {
@@ -3613,20 +3598,20 @@ function showTalkUnlocker(fallbackHint = false) {
   el.removeAttribute("hidden");
   _talkUnlockerShown = true;
   console.info(
-    "%c[start-session] ▶️ talk-unlocker mostrato (%s): attende gesture utente",
+    "%c[start-session] ▶️ talk-unlocker shown (%s): waiting for a user gesture",
     "color:#2563eb;font-weight:700;background:#dbeafe;padding:3px 6px;border-radius:4px;",
     fallbackHint ? "fallback TALKFIRST" : "TALK mode"
   );
 }
 function maybeScheduleAutoStart() {
-  // Pulisco un eventuale timer precedente (caso di doppia chiamata non attesa).
+  // Clear any previous timer if this function was unexpectedly called twice.
   if (autoStartTalkTimerId) {
     clearTimeout(autoStartTalkTimerId);
     autoStartTalkTimerId = 0;
   }
   if (startSessionMode !== "TALK" && startSessionMode !== "TALKFIRST") return;
   console.info(
-    `%c[start-session] S2S_START_SESSION_MODE=${startSessionMode}: azione tra 2000 ms (warmup profilo/reports/episode)`,
+    `%c[start-session] S2S_START_SESSION_MODE=${startSessionMode}: action in 2000 ms (profile/reports/episode warmup)`,
     "color:#2563eb;font-weight:700;background:#dbeafe;padding:3px 6px;border-radius:4px;"
   );
   autoStartTalkTimerId = window.setTimeout(() => {
@@ -3638,49 +3623,45 @@ function maybeScheduleAutoStart() {
     }
   }, 2000);
 }
-/** Tenta l'auto-start diretto (TALKFIRST) SENZA gesture. Simula la wake word
- *  impostando pendingWakeWordConfirmationText="hola vocero" (stessa variabile
- *  del riconoscitore vocale reale), poi chiama doStart() — se i permessi sono
- *  già grantiti (Chrome/Android dopo "allow always"), tutto funziona senza
- *  click. Altrimenti fallback sull'unlocker. */
+/** Attempt direct TALKFIRST auto-start without a gesture. Simulate a wake word
+ *  by setting pendingWakeWordConfirmationText="hola vocero", as the real speech
+ *  recognizer does, then call doStart(). Existing permissions may allow this
+ *  without a click; otherwise fall back to the unlocker. */
 async function tryTalkFirstDirect() {
   if (!(currentState === "idle" || currentState === "error")) return;
   if (missingServerUrl()) {
-    console.warn("[start-session] skip TALKFIRST: manca server URL");
+    console.warn("[start-session] skip TALKFIRST: missing server URL");
     promptServerUrl();
     return;
   }
-  // Step 1: pre-carico la wake-word simulata. Quando onClientStatus riceve
-  // "connected", la frase viene injectata e il modello risponde esattamente
-  // come quando la hot-word è stata pronunciata dal microfono.
+  // Prepare the simulated wake word. When onClientStatus receives "connected",
+  // inject it so the model responds as if the user had spoken it.
   pendingWakeWordConfirmationText = pendingWakeWordConfirmationText?.trim()
     ? pendingWakeWordConfirmationText
     : "hola vocero";
   console.info(
-    `%c[start-session] 🎤 TALKFIRST: imposto wake-word simulata=${JSON.stringify(pendingWakeWordConfirmationText)} e provo doStart() diretto (SENZA gesture)`,
+    `%c[start-session] 🎤 TALKFIRST: set simulated wake word=${JSON.stringify(pendingWakeWordConfirmationText)} and try doStart() directly (WITHOUT a gesture)`,
     "color:#2563eb;font-weight:700;background:#dbeafe;padding:3px 6px;border-radius:4px;"
   );
   try {
     setCaption("Preparing your session…", "muted");
-    // Non forzo AudioContext da fuori (non c'è gesture): lo crea internamente
-    // _ensureAudioContext; se rimane suspended il client lo resume() quando
-    // arriva il primo audio (o sul prossimo click utente che lo unlocka).
+    // Let _ensureAudioContext create the context. If it stays suspended, the
+    // client resumes it on the first audio or the next user click.
     await doStart();
   } catch (err) {
-    console.warn("[start-session] ⚠️ TALKFIRST doStart() diretto FALLITO → fallback unlocker", err && err instanceof Error ? err.message : err);
-    // Fallback: mostro unlocker con la frase esplicativa "permesso mic".
+    console.warn("[start-session] ⚠️ direct TALKFIRST doStart() FAILED → fallback unlocker", err && err instanceof Error ? err.message : err);
+    // Show the unlocker with the microphone permission explanation.
     try { await teardown(); } catch (_) { /* no-op */ }
     setState("idle");
     chat.renderEmptyState();
-    // Ripristino pendingWakeWordConfirmationText: nel caso l'utente usi
-    // l'unlocker per avviare, NON vogliamo perdere la frase simulata (la
-    // useremo di nuovo al connected, scattando quindi sempre la greet).
+    // Preserve the simulated phrase so starting through the unlocker still
+    // injects it on connection and triggers the greeting.
     pendingWakeWordConfirmationText = pendingWakeWordConfirmationText || "hola vocero";
     showTalkUnlocker(true);
     void handleStartError(err instanceof Error ? err : new Error(String(err || "mic permission required")));
   }
 }
-// Attacca una sola volta i listener sull'unlocker: click + touchstart = unlock
+// Register unlocker listeners once: click + touchstart unlock audio.
 (() => {
   const el = document.getElementById("talk-unlocker");
   if (!el) return;
@@ -3692,28 +3673,28 @@ async function tryTalkFirstDirect() {
   window.addEventListener("keydown", (ev) => {
     if (startSessionMode !== "TALK") return;
     if (!_talkUnlockerShown) return;
-    // Qualsiasi tasto = unlock (Enter/Space/anche Altri)
+    // Any key unlocks audio, including Enter and Space.
     startTalkFromGesture();
   }, { passive: true });
 })();
-/** Avvia doStart() dentro una gesture valida (click/touch/key).
-Chiamato dal talk-unlocker o da qualsiasi altro unlocker valido. */
+/** Start doStart() within a valid click/touch/key gesture.
+ * Called by the talk unlocker or another valid audio unlocker. */
 async function startTalkFromGesture() {
   hideTalkUnlocker();
   if (!(currentState === "idle" || currentState === "error")) return;
   if (missingServerUrl()) {
-    console.warn("[start-session] skip unlocker: manca server URL (missingServerUrl=true)");
+    console.warn("[start-session] skip unlocker: missing server URL (missingServerUrl=true)");
     promptServerUrl();
     return;
   }
   try {
-    // Qui SIAMO dentro la user gesture: AudioContext + getUserMedia funzionano.
-    console.info("[start-session] 🎤 avvio doStart() da gesture unlocker (TALK mode)");
+    // This user gesture permits AudioContext and getUserMedia to start.
+    console.info("[start-session] 🎤 start doStart() from unlocker gesture (TALK mode)");
     const audioContext = createResumedAudioContext();
     setCaption("Preparing your session…", "muted");
     await doStart(audioContext);
   } catch (err) {
-    console.error("[start-session] ⛔ doStart() da unlocker fallito", err);
+    console.error("[start-session] ⛔ doStart() from unlocker failed", err);
     void handleStartError(err);
   }
 }
diff --git a/s2s-client/server.py b/s2s-client/server.py
index adadb95..7a6517a 100644
--- a/s2s-client/server.py
+++ b/s2s-client/server.py
@@ -72,13 +72,13 @@ if not _logging_configured:
     logging.basicConfig(level=logging.DEBUG, handlers=[_handler], force=True)
     _lvl_env = (os.environ.get("LOG_LEVEL") or os.environ.get("S2S_LOG_LEVEL") or "INFO").strip().upper()
     _is_debug = _lvl_env in {"DEBUG", "TRACE", "10"}
-    # Logger rumorosi: a meno che LOG_LEVEL=debug esplicito, tienili quiet.
+    # Keep noisy loggers quiet unless LOG_LEVEL explicitly enables debug.
     logging.getLogger("httpx").setLevel(logging.DEBUG if _is_debug else logging.WARNING)
     logging.getLogger("websockets").setLevel(logging.DEBUG if _is_debug else logging.INFO)
     logging.getLogger("uvicorn").setLevel(logging.DEBUG if _is_debug else logging.INFO)
     logging.getLogger("uvicorn.access").setLevel(logging.DEBUG if _is_debug else logging.INFO)
     logging.getLogger("httpcore").setLevel(logging.DEBUG if _is_debug else logging.WARNING)
-    logger.setLevel(logging.DEBUG if _is_debug else logging.DEBUG)  # s2s sempre almeno DEBUG in dev
+    logger.setLevel(logging.DEBUG if _is_debug else logging.DEBUG)  # s2s always uses at least DEBUG in development
     _logging_configured = True
     logger.debug(
         "LOG_LEVEL env=%s — noisy-logger levels: httpx=%s uvicorn=%s websockets=%s",
@@ -154,7 +154,7 @@ S2S_REPORT_LIST = (os.environ.get("S2S_REPORT_LIST", "") or "").strip().rstrip("
 # contents (podcastScript) into the LLM instructions / context.  When "false" (DEFAULT)
 # the proxy NEVER injects scheduled reports into the prompt — not even the TOC — and
 # skips the upstream S2S_REPORT_LIST network call entirely, fixing the user issue:
-#   "Attualmente stai iniettando TUTTI i reports con tutto il loro podcastScript integrale."
+#   "All reports are currently injected with their complete podcastScript."
 #
 # Historical note (2026-09-11): before this flag existed, if S2S_INJECT_PROFILE=true AND
 # S2S_REPORT_LIST was set the server eagerly fetched every scheduled report for the
@@ -172,7 +172,7 @@ S2S_INJECT_REPORTS = (
 # content for more than N reports, even when the upstream API returns 20+. Configurable
 # from .env; value is integer-parsed and clamped to [1, 50] (invalid values fall back to
 # the default = 5, which is the user's requested "max 3-5" default range). User request
-# 2026-09-11: "riduci il quick hint report max 3-5 configurabile da .env".
+# 2026-09-11: "Limit report quick hints to 3-5 entries, configurable through .env."
 try:
     _S2S_REPORTS_QUICK_HINT_MAX_RAW = int((os.environ.get("S2S_REPORTS_QUICK_HINT_MAX", "") or "5").strip())
 except Exception:
@@ -181,15 +181,15 @@ S2S_REPORTS_QUICK_HINT_MAX = max(1, min(50, _S2S_REPORTS_QUICK_HINT_MAX_RAW))
 del _S2S_REPORTS_QUICK_HINT_MAX_RAW
 # Feature flag: when "true" → prepend a TODAY date + anti-hallucination guard to
 # every LLM prompt and session instructions. Fixes user bug 3 2026-09-11:
-#   "Qwen2.5 training cutoff ~2024 metà, vede report 2026 e impazzisce meta-commenti in cinese:
-#    'L'ora mondiale oggi è 2023, perché report nel 2026?'"
+#   "Qwen2.5 has a training cutoff around mid-2024 and produces Chinese meta-comments
+#    about 2026 reports: 'Today is 2023; why are these reports dated 2026?'"
 # Default = ON (safe even when empty/unset). Explicit S2S_INJECT_TODAY="false" to disable.
 # Injected text contains:
-#   • real "La data di OGGI è: YYYY-MM-DD (ISO, server local date)
-#   • "Report con date precedenti = archivio storico → non commentare date future
-#   • Rule anti-meta-commenti: NIENTE commenti interni / prompt introspection
-#   • Rule anti-thinking-leak (GPTQ Int4 quantized): "sólo lo que dice Vocero en voz alta"
-#   • Rule RAG report: "para contenido de reportes usa RAG, no inventes con el resumen"
+#   • The actual date: "TODAY is YYYY-MM-DD" (ISO, server local date).
+#   • Earlier reports are historical records; do not question their dates.
+#   • No internal meta-comments or prompt introspection.
+#   • No thinking leaks with GPTQ Int4: only words Vocero says aloud.
+#   • Retrieve report content through RAG rather than inventing it from summaries.
 S2S_INJECT_TODAY = not (
     (os.environ.get("S2S_INJECT_TODAY", "") or "").strip().lower()
     in {"0", "false", "no", "off"}
@@ -198,7 +198,7 @@ S2S_INJECT_TODAY = not (
 # prompt for scheduled reports. Values (case-insensitive, default="minimal"):
 #   • "minimal"  → ONLY last N = S2S_REPORTS_QUICK_HINT_MAX items as a pure
 #                   TOC (label + date ONLY). NO podcastScript is ever exposed. This
-#                   the user's "Mantieni i report? Allora solo sommario MINIMO"
+#                   the user's "Keep reports only as a MINIMAL summary"
 #                   fix. Token budget: ~50 tokens instead of ~3200.
 #   • "full"     → legacy behaviour: full JSON array with podcastScript
 #                   (still capped to S2S_REPORTS_QUICK_HINT_MAX items). Used to be
@@ -234,47 +234,43 @@ OPENAI_REASONING_MODEL = os.environ.get("OPENAI_REASONING_MODEL", "gpt-4.1-mini"
 OPENAI_ORGANIZATION = os.environ.get("OPENAI_ORGANIZATION", "").strip()
 OPENAI_PROJECT = os.environ.get("OPENAI_PROJECT", "").strip()
 # ──────────────────────────────────────────────────────────────────────────────
-# APIPILOT — Backend AquaPortal dynamic-tool bridge (GUIDA_APIPILOT_CLIENTE.md)
+# APIPILOT — Backend AquaPortal dynamic-tool bridge (docs/client/tool-calling.md)
 # ──────────────────────────────────────────────────────────────────────────────
-# URL base per il discovery e l'esecuzione dei tool dinamici ApiPilot. Quando
-# valorizzata, il proxy effettua GET <url>/tools con include_unauthorized=true
-# (§2.1 della guida) per ottenere la lista tool e POST <url>/execute per
-# invocarne uno (§2.2). Può finire o meno con "/": il proxy normalizza
-# sempre con rstrip("/") sotto.
+# Base URL for ApiPilot dynamic tool discovery and execution. When configured,
+# the proxy sends GET <url>/tools with include_unauthorized=true (guide §2.1)
+# to discover tools, and POST <url>/execute (§2.2) to invoke one. The trailing
+# slash is optional; the proxy normalizes it with rstrip("/") below.
 #
-# ES.: S2S_APIPILOT_TOOLS_URL=https://aquachile.azurianlab.com/api/v1/apipilot
+# Example: S2S_APIPILOT_TOOLS_URL=https://aquachile.azurianlab.com/api/v1/apipilot
 S2S_APIPILOT_TOOLS_URL = os.environ.get("S2S_APIPILOT_TOOLS_URL", "").strip().rstrip("/")
-# Override ESPLICITO per l'URL di execute (§2.2 GUIDA_APIPILOT_CLIENTE.md).
-# Se valorizzato, ha la precedenza su S2S_APIPILOT_TOOLS_URL per le chiamate POST execute.
-# Normalizza togliendo "/" alla fine; il proxy appenderebbe "/execute" SOLO se la URL
-# non termina già con "/execute".
-# ES.1 (base): S2S_APIPILOT_TOOLS_EXECUTE_URL=https://aquachile.azurianlab.com/api/v1/apipilot
+# Explicit execution URL override (guide §2.2). When set, it takes precedence
+# over S2S_APIPILOT_TOOLS_URL for POST execution calls. Remove trailing slashes
+# and append "/execute" only if the URL does not already end with that suffix.
+# Example 1 (base): S2S_APIPILOT_TOOLS_EXECUTE_URL=https://aquachile.azurianlab.com/api/v1/apipilot
 #         → POST https://aquachile.azurianlab.com/api/v1/apipilot/execute
-# ES.2 (utente .env:45): S2S_APIPILOT_TOOLS_EXECUTE_URL=https://aquachile.azurianlab.com/api/v1/apipilot/tools
+# Example 2: S2S_APIPILOT_TOOLS_EXECUTE_URL=https://aquachile.azurianlab.com/api/v1/apipilot/tools
 #         → POST https://aquachile.azurianlab.com/api/v1/apipilot/tools/execute
 S2S_APIPILOT_TOOLS_EXECUTE_URL = os.environ.get("S2S_APIPILOT_TOOLS_EXECUTE_URL", "").strip().rstrip("/")
-# Bearer token fisso (opzionale) usato SOLO se il chiamante NON fornisce un
-# token di sessione (Authorization / x-demo-session). Utile in ambienti di
-# pre-produzione con token di servizio hardcoded.
+# Optional fixed bearer token, used only when the caller supplies no session
+# token (Authorization / x-demo-session). Useful for staging service tokens.
 S2S_APIPILOT_SERVICE_TOKEN = os.environ.get("S2S_APIPILOT_SERVICE_TOKEN", "").strip()
-# 2026-09-25 SUPER API KEY (BYPASS AUTENTICAZIONE AQUAPORTAL TEMPORANEO).
-#    Se valorizzata: 3 forme contemporaneamente in headers per max compatibilità:
+# 2026-09-25 SUPER API KEY (TEMPORARY AQUAPORTAL AUTHENTICATION BYPASS).
+#    When set, send all three header forms for maximum compatibility:
 #      1) X-API-Key: <key>
 #      2) Authorization: Bearer <key>
 #      3) x-demo-session: <key>
-#    Ha MAXIMA priorità e disabilita completamente login_by_phone (non serve).
-#    Basta vuotare la stringa per tornare al login standard.
+#    Highest priority; completely disables the unnecessary login_by_phone call.
+#    Clear the value to restore standard login.
 S2S_APIPILOT_API_KEY = os.environ.get("S2S_APIPILOT_API_KEY", "").strip().strip("\"'")
-# TTL della cache di discovery tools (in secondi). La guida dice "max ogni 5
-# minuti se tieni cache lato client"; lato server usiamo lo stesso valore per
-# default: 300 secondi = 5 minuti.
+# Tool discovery cache TTL in seconds. The guide recommends a five-minute
+# client cache; the server uses the same default: 300 seconds.
 try:
     _APIPILOT_TTL_RAW = int((os.environ.get("S2S_APIPILOT_TTL_SEC", "") or "300").strip())
 except Exception:
     _APIPILOT_TTL_RAW = 300
 APIPILOT_CACHE_TTL_SEC = max(15, min(3600, _APIPILOT_TTL_RAW))
 del _APIPILOT_TTL_RAW
-# Timeout HTTP per chiamate ApiPilot (discovery + execute), in secondi.
+# HTTP timeout for ApiPilot discovery and execution calls, in seconds.
 try:
     _APIPILOT_TO_RAW = float((os.environ.get("S2S_APIPILOT_TIMEOUT_SEC", "") or "15.0").strip())
 except Exception:
@@ -282,12 +278,12 @@ except Exception:
 APIPILOT_HTTP_TIMEOUT = max(1.0, min(120.0, _APIPILOT_TO_RAW))
 del _APIPILOT_TO_RAW
 
-# Cache in-process + lock asyncrona (uno solo refresha, gli altri leggono la
-# entry stantia). Struttura `_APIPILOT_CACHE[auth_fingerprint] = (fetched_at_monotonic, tools_list)`.
+# In-process cache and asynchronous lock: one caller refreshes while others
+# read the stale entry. `_APIPILOT_CACHE[auth_fingerprint] = (fetched_at_monotonic, tools_list)`.
 _APIPILOT_CACHE: dict[str, tuple[float, list[dict]]] = {}
 _APIPILOT_CACHE_LOCK = asyncio.Lock()
 
-# Helper tempo monotonic per misure duration senza drift NTP.
+# Monotonic time helper for duration measurements unaffected by NTP drift.
 import time as _time_mod_gbl
 _monotonic_now: callable = _time_mod_gbl.monotonic
 del _time_mod_gbl
@@ -313,7 +309,7 @@ def _apipilot_parse_authorization(request: Request | None) -> tuple[str | None,
     """Extract (Authorization header value, x-demo-session header value) from a FastAPI request.
 
     Returns a tuple of two optional strings. Both are forwarded to the upstream
-    ApiPilot backend verbatim when non-empty (see GUIDA_APIPILOT_CLIENTE.md §2.1 note).
+    ApiPilot backend verbatim when non-empty (see docs/client/tool-calling.md).
     """
     if request is None:
         return None, None
@@ -334,13 +330,11 @@ def _apipilot_parse_authorization(request: Request | None) -> tuple[str | None,
 def _apipilot_resolve_execute_url() -> str:
     """Resolve the final POST URL for ApiPilot tool execution.
 
-    Priorità (§2.2 + override esplicito utente .env riga 45):
-      1. S2S_APIPILOT_TOOLS_EXECUTE_URL se valorizzato: se NON termina con
-         "/execute", appendiamo "/execute".
+    Priority (guide §2.2 and explicit environment override):
+      1. When S2S_APIPILOT_TOOLS_EXECUTE_URL is set, append "/execute" if needed.
       2. Fallback S2S_APIPILOT_TOOLS_URL + "/execute".
-    La funzione non può mai restituire stringa vuota: se nessuna è configurata
-    è responsabilità del caller (tipicamente _apipilot_execute_tool) tornare
-    envelope errore APIPILOT_NOT_CONFIGURED prima di arrivare qui.
+    If neither URL is configured, the caller (usually _apipilot_execute_tool)
+    must return an APIPILOT_NOT_CONFIGURED error envelope before calling this.
     """
     base = S2S_APIPILOT_TOOLS_EXECUTE_URL or S2S_APIPILOT_TOOLS_URL
     base = base.strip().rstrip("/")
@@ -354,12 +348,9 @@ def _apipilot_resolve_execute_url() -> str:
 def _apipilot_strip_tool_for_llm(tool_def: dict) -> dict:
     """Return a tool definition that is safe for LLM function-calling providers.
 
-    §4 della guida:
-      "NON mandare direttamente l'output grezzo di /tools al modello, perché
-       contiene il campo requires_auth che non fa parte dello standard
-       function-calling e alcuni provider lo rifiutano."
-    Questa funzione è l'esatto complemento di quella regola: prende un
-    `ToolDefinition` nativo e restituisce la proiezione OpenAI-compatibile
+    Guide §4 forbids passing raw /tools output directly to the model because
+    requires_auth is outside the function-calling standard and some providers
+    reject it. Project the native `ToolDefinition` into the OpenAI-compatible
     `{type: "function", function: {name, description, parameters}}`.
     """
     if not isinstance(tool_def, dict):
@@ -400,17 +391,17 @@ async def _apipilot_fetch_tools(
     replied with a non-2xx / non-JSON response. When env is empty → returns
     `[]` silently (passthrough).
     """
-    # 2026-09-25 ALIAS BACKWARD: parametro `refresh` usato in WS connect L4632
-    #    (nome sbagliato) — se presente, usa force_refresh corrispondente.
+    # 2026-09-25 compatibility alias: WS connect uses `refresh`; when present,
+    # apply it to force_refresh.
     if refresh is not None:
         force_refresh = bool(refresh) or bool(force_refresh)
     if not S2S_APIPILOT_TOOLS_URL:
         return []
     import time as _time_mod
-    # 2026-09-25 FIX FINGERPRINT CONSISTENCY: PRIMA determiniamo auth/demo EFFETTIVI
-    #    (SUPER API KEY PRIORITÀ MASSIMA), POI calcoliamo fp cache.
-    #    Altrimenti fp = anon-ws... ma headers reali = APIKEY → chiave cache sbagliata
-    #    e sessione demo session non matcha (Aquachile user_type=null → 403).
+    # 2026-09-25 fingerprint consistency: determine effective auth/demo values
+    # first (SUPER API KEY takes precedence), then calculate the cache fingerprint.
+    # An anonymous fingerprint with APIKEY headers would mismatch the cache and
+    # demo session, causing Aquachile user_type=null and a 403 response.
     if S2S_APIPILOT_API_KEY:
         final_auth = "BYPASS-API-KEY"
         _demo_used = S2S_APIPILOT_API_KEY
@@ -441,8 +432,8 @@ async def _apipilot_fetch_tools(
         url = f"{S2S_APIPILOT_TOOLS_URL}/tools"
         params = {"include_unauthorized": "true" if include_unauthorized else "false"}
         headers = {"accept": "application/json"}
-        # 2026-09-25 SUPER API KEY: MAX PRIORITY. Se valorizzata → disabilita tutti gli altri auth
-        #    e mette TUTTE e 3 le forme contemporaneamente per max compatibilità.
+        # 2026-09-25 SUPER API KEY overrides other authentication and sends all
+        # three header forms simultaneously for maximum compatibility.
         if S2S_APIPILOT_API_KEY:
             headers["X-API-Key"] = S2S_APIPILOT_API_KEY
             headers["Authorization"] = f"Bearer {S2S_APIPILOT_API_KEY}"
@@ -486,12 +477,12 @@ async def _apipilot_fetch_tools(
         try:
             payload = resp.json()
         except Exception:
-            logger.error("[APIPILOT-DISCOVERY] ✗ risposta non JSON: %s", resp.text[:500])
+            logger.error("[APIPILOT-DISCOVERY] ✗ non-JSON response: %s", resp.text[:500])
             if stale_tools is not None:
                 return stale_tools
             raise HTTPException(
                 status_code=502,
-                detail={"code": "APIPILOT_BAD_JSON", "message": "La risposta di ApiPilot tools non è JSON valido."},
+                detail={"code": "APIPILOT_BAD_JSON", "message": "La respuesta de ApiPilot tools no es JSON válido."},
             )
         # Backend might return: list OR {"result": [...]} OR {"tools": [...]} OR
         # {"data": {"tools": [...]}}. Unwrap generic wrapper-style payloads.
@@ -521,7 +512,7 @@ async def _apipilot_fetch_tools(
                 parameters = {"type": "object", "properties": {}, "required": []}
             requires_auth = raw.get("requires_auth", False)
             if not isinstance(requires_auth, bool):
-                # Some backends return 0/1; normalize to bool. Guard per regola.
+                # Some backends return 0/1; normalize to bool as required.
                 try:
                     requires_auth = bool(int(requires_auth))
                 except Exception:
@@ -552,18 +543,14 @@ def _apipilot_validate_arguments(arguments: dict | None, tool_def: dict) -> tupl
     """Validate / execute arguments strictly against the tool's JSON-Schema parameters.
 
     Implements §2.2 PRE-CHECK #3:
-      • rimuove TUTTE le chiavi extra non in parameters.properties — MA SOLO SE
-        parameters.properties è un dict NON VUOTO.
-      • Caso speciale 2026-09-25 (OSSERVATO AquaPortal):
-        tool.get_user_briefing ha parameters.properties={} e required=[].
-        Significa "nessuno schema esplicito dichiarato / args flessibili"
-        (phone viene preso internamente al backend dal token). In questo caso
-        NON facciamo stripping di chiavi (altrimenti rimuoveremmo phone
-        indispensabile per la business logic).
-      • valorizza required (restituisce errori se mancanti)
-      • NON inventare parametri → non vengono aggiunte chiavi.
+      • Remove unknown keys only when parameters.properties is nonempty.
+      • AquaPortal tool.get_user_briefing has parameters.properties={} and
+        required=[]: no explicit schema, so arguments remain flexible. The
+        backend resolves phone from the token; preserve supplied arguments.
+      • Validate required parameters and return errors for missing values.
+      • Never invent parameters or add keys.
 
-    Returns `(filtered_args, list_of_validation_errors_in_spagnolo)`.
+    Returns `(filtered_args, list_of_validation_errors_in_spanish)`.
     If the returned errors list is non-empty, MUST block the execution (see
     the `_apipilot_execute_tool` caller).
     """
@@ -574,16 +561,14 @@ def _apipilot_validate_arguments(arguments: dict | None, tool_def: dict) -> tupl
     required = [x for x in required if isinstance(x, str)]
     args = arguments if isinstance(arguments, dict) else {}
 
-    # ── 2026-09-25 FLESSIBILITÀ SCHEMA VUOTO: se parameters non ha properties
-    #    dichiarate esplicitamente (dict vuoto) → pass-through TUTTI gli args,
-    #    nessuno stripping. Utile per AquaPortal tool tipo get_user_briefing.
+    # 2026-09-25 empty-schema flexibility: preserve all arguments when no
+    # properties are explicitly declared, as with AquaPortal get_user_briefing.
     schema_is_open: bool = (not isinstance(properties, dict)) or len(properties) == 0
     requires_auth_flag = bool(tool_def.get("requires_auth"))
-    # 2026-09-25 TOOL AUTH-ONLY: requires_auth=true + parameters.properties vuoto
-    #    + required=[] + description contiene "Requires a valid session token"
-    #    → AquaPortal ricava TUTTI i dati utente dal bearer JWT del token.
-    #    In questo caso passiamo arguments={} (nessun parametro) per evitare
-    #    conflitti (es. phone argomento vs phone utente token) → 403.
+    # 2026-09-25 auth-only tools: requires_auth=true, empty properties and
+    # required=[], with a valid-session description, resolve user data from
+    # the bearer JWT. Send arguments={} to avoid conflicts between a phone
+    # argument and the token's user, which would produce a 403 response.
     auth_only_tool = False
     if schema_is_open and requires_auth_flag and len(required) == 0:
         _d = tool_def.get("description") if isinstance(tool_def.get("description"), str) else ""
@@ -592,13 +577,13 @@ def _apipilot_validate_arguments(arguments: dict | None, tool_def: dict) -> tupl
     if auth_only_tool:
         cleaned = {}
         logger.info(
-            "[APIPILOT-VALIDATE] tool=%s richiede SOLO sessione auth (nessun parametro) → arguments forzati {} (evitiamo conflitto phone-args vs user-token)",
+            "[APIPILOT-VALIDATE] tool=%s requires only an authenticated session → arguments forced to {} (avoid phone-argument/user-token conflicts)",
             tool_def.get("name") or "?",
         )
     elif schema_is_open:
         cleaned = dict(args)
         logger.info(
-            "[APIPILOT-VALIDATE] tool=%s schema aperto (parameters.properties vuoto) → pass-through tutti gli args N=%d keys=%s",
+            "[APIPILOT-VALIDATE] tool=%s open schema (empty parameters.properties) → preserve all arguments N=%d keys=%s",
             tool_def.get("name") or "?",
             len(cleaned),
             sorted(list(cleaned.keys())),
@@ -613,8 +598,7 @@ def _apipilot_validate_arguments(arguments: dict | None, tool_def: dict) -> tupl
                     "[APIPILOT-VALIDATE] tool=%s removing unknown arg=%s",
                     tool_def.get("name") or "?", key,
                 )
-    # Required check: abilitato SOLO se lo schema NON è open (altrimenti
-    # required=[] è vacuo e non ha senso).
+    # Check required fields only for a closed schema; open required=[] is vacuous.
     if (not schema_is_open):
         for req in required:
             if req not in cleaned:
@@ -623,29 +607,25 @@ def _apipilot_validate_arguments(arguments: dict | None, tool_def: dict) -> tupl
 
 
 # ---------------------------------------------------------------------------
-# APIPILOT — Integrazione nel motore di reasoning (2 passate)
+# APIPILOT — Reasoning engine integration (two passes)
 # ---------------------------------------------------------------------------
-# Marker dedup/inizio/fine usati da _classify_context_block per evitare
-# doppie injection dello stesso blocco (se client già lo invia o se dedup layer 2
-# lo trova già nel base_instructions originale).
+# Deduplication/start/end markers used by _classify_context_block to avoid
+# injecting a block already supplied by the client or found in base_instructions.
 APIPILOT_PASS1_LIST_MARKER = "<<<APIPILOT_TOOLS_LIST_BEGIN>>>"
 APIPILOT_PASS2_RESULT_MARKER = "<<<APIPILOT_RESULT:"
 
-# Regola:
-#   PASSATA 1: iniettiamo lista {name,description,required,parameters} + regole
-#             marker nel prompt. AI deve decidere se matcha description e
-#             emettere <<<APIPILOT_CALL:NAME=nome_tool,ARGUMENTS={...}>>>.
-#   PASSATA 2: marker catturato → esegui S2S_APIPILOT_TOOLS_EXECUTE_URL via
-#              helper → prendi body text risultato → inietta nel prompt e
-#              chiedi all'AI di rielaborarlo in linguaggio naturale per
-#              raccontarlo all'utente via voce.
+# Flow:
+#   PASS 1: inject {name,description,required,parameters} and marker rules.
+#           The model matches descriptions and emits the CALL marker.
+#   PASS 2: capture the marker, execute through S2S_APIPILOT_TOOLS_EXECUTE_URL,
+#           inject the result text, and request a natural spoken response.
 # ---------------------------------------------------------------------------
 
 _APIPILOT_CALL_MARKER_RE = re.compile(
     r"[<]{1,3}\s*APIPILOT_CALL:NAME=([A-Za-z0-9_.-]+),ARGUMENTS=(.*?)[>]{1,3}",
     re.IGNORECASE | re.DOTALL,
 )
-# 2026-09-25: marker INVERTITO caso osservato (LLM sbaglia sintassi):
+# 2026-09-25: observed inverted marker (incorrect LLM syntax):
 #   >>>APIPILOT_CALL:NAME=tool,ARGUMENTS=json<<<
 _APIPILOT_CALL_MARKER_INVERTED_RE = re.compile(
     r"[>]{1,3}\s*APIPILOT_CALL:NAME=([A-Za-z0-9_.-]+),ARGUMENTS=(.*?)[<]{1,3}",
@@ -654,17 +634,17 @@ _APIPILOT_CALL_MARKER_INVERTED_RE = re.compile(
 
 
 def _apipilot_parse_call_marker(answer_text: str, *, defaults: dict | None = None) -> tuple[str | None, dict | None]:
-    """Parse the mandatory CALL marker emitted by the LLM in passata 1.
+    """Parse the mandatory CALL marker emitted by the LLM in pass 1.
 
-    Returns (tool_name, arguments_dict) oppure (None, None) se nessun marker.
+    Returns (tool_name, arguments_dict), or (None, None) when no marker exists.
 
-    Gestisce:
-      (1) ARGUMENTS={"key":"val"} JSON valido (formato corretto)
-      (2) ARGUMENTS={} vuoto corretto
-      (3) ARGUMENTS=  vuoto SENZA graffe (OSSERVATO oggi su WS realtime)
-      (4) args_raw tipo key=val,key2=val2 string semplice (fallback manual parse)
-      (5) FASE 2: dopo il parse, applica un dict di defaults (es. phone, episode_id)
-          riempiendo parametri required MANCANTI in args (se non sono presenti).
+    Supports:
+      (1) ARGUMENTS={"key":"val"}, valid JSON.
+      (2) ARGUMENTS={}, a valid empty object.
+      (3) ARGUMENTS= without braces, observed on realtime WebSocket sessions.
+      (4) key=val,key2=val2 strings through a manual parsing fallback.
+      (5) After parsing, fill missing required arguments from defaults such as
+          phone and episode_id.
     """
     if not isinstance(answer_text, str) or not answer_text.strip():
         logger.info("[APIPILOT-CALL-NAME] USE=PARSE_EMPTY_INPUT name=None markerFound=N")
@@ -684,29 +664,29 @@ def _apipilot_parse_call_marker(answer_text: str, *, defaults: dict | None = Non
         return None, None
     logger.info("[APIPILOT-CALL-NAME] USE=PARSE_MARKER_OK name=%r argsRawLen=%d markerFound=Y inverted=%s", name_raw, len(args_raw), ("Y" if inverted else "N"))
     args: dict = {}
-    # ── Parse args_raw a dict (varianti tollerate) ────────────────────────────
+    # Parse args_raw into a dict, tolerating common formatting variations.
     if args_raw == "" or args_raw in {"{}", "null", "None"}:
         args = {}
     else:
-        # Tenta 1: JSON standard (graffe incluse o NO)
+        # Attempt 1: standard JSON, with or without braces.
         _candidate = args_raw
         try:
             args = json.loads(_candidate)
         except Exception:
             try:
-                # Tenta 2: mancano graffe esterne, aggiungiamo { } attorno
+                # Attempt 2: supply missing outer braces.
                 args = json.loads("{" + _candidate + "}")
             except Exception:
                 try:
-                    # Tenta 3: virgolette singole invece che doppie
+                    # Attempt 3: replace single quotes with double quotes.
                     args = json.loads(_candidate.replace("'", '"'))
                 except Exception:
                     try:
-                        # Tenta 4: { } + virgolette singole
+                        # Attempt 4: supply braces and replace single quotes.
                         args = json.loads("{" + _candidate.replace("'", '"') + "}")
                     except Exception:
-                        # Fallback 5 manuale: separatore = e virgole.
-                        # Es. args_raw="phone=+56,name=Mario" → dict
+                        # Manual fallback 5: equals signs and commas.
+                        # Example: args_raw="phone=+56,name=Mario" → dict.
                         args = {}
                         for piece in args_raw.split(","):
                             kv = piece.strip()
@@ -719,7 +699,7 @@ def _apipilot_parse_call_marker(answer_text: str, *, defaults: dict | None = Non
                                 args[k] = v
     if not isinstance(args, dict):
         args = {}
-    # ── FASE 2: auto-fill defaults (phone, etc.) per parametri mancanti ──────
+    # Stage 2: fill missing arguments from defaults (phone, etc.).
     if isinstance(defaults, dict) and defaults:
         for dk, dv in defaults.items():
             if dk not in args or args[dk] in (None, "", []):
@@ -737,20 +717,17 @@ def _resolve_apipilot_reasoning_context_block(
 ) -> str:
     """Build the ApiPilot context block for the reasoning prompt.
 
-    Quando call_result=None → PASSATA 1: emetti la lista strumenti + la regola
-    sintattica del marker che l'AI deve emettere quando description matcha.
+    With call_result=None, pass 1 supplies the tool list and marker syntax
+    the model must emit when a description matches.
 
-    Quando call_result={'name':str, 'text':str, 'error':bool} → PASSATA 2:
-    inietta il risultato testuale ottenuto da execute e chiedi all'AI di
-    rielaborarlo per l'utente finale (voce / testo).
+    With call_result={'name':str, 'text':str, 'error':bool}, pass 2 injects the
+    execution result and requests a final spoken/text response for the user.
 
-    Parametro NUOVO 2026-09-25 context_defaults (dict opzionale):
-      per PASSATA 1 se non-None aggiunge una sezione "VALORES POR DEFECTO
-      CONOCIDOS" per dire all'AI "quando lo strumento richiede 'phone' usa
-      esattamente questo valore già disponibile (non inventarlo)."
-      Tipicamente contiene {"phone": "+56..."} da inject_phone del caller.
+    The optional context_defaults dict adds known default values to pass 1.
+    The model must use these exact values for required arguments rather than
+    inventing them. Usually contains {"phone": "+56..."} from inject_phone.
     """
-    # ── PASSATA 2: Risultato strumento già iniettato ─────────────────────────
+    # Pass 2: the tool result is already available.
     if isinstance(call_result, dict) and call_result.get("name"):
         name = call_result.get("name") or "?"
         text = (call_result.get("text") if isinstance(call_result.get("text"), str) else "") or ""
@@ -758,23 +735,23 @@ def _resolve_apipilot_reasoning_context_block(
         status_label = "ERROR" if is_err else "OK"
         title = f"<<<APIPILOT_RESULT:STATUS={status_label},NAME={name}>>>"
         trailer = (
-            "Ahora debes reinterpretar EL TEXTO RESULTADO (arriba) en lenguaje natural claro "
-            "y conciso, exclusivamente en el idioma del usuario (language field). "
-            "No menciones la herramienta internamente ni detalles técnicos. "
-            "Responde SOLAMENTE con el contenido final que le quieres transmitir al usuario."
+            "Now reinterpret THE RESULT TEXT (above) in clear, concise natural language, "
+            "exclusively in the user's language (language field; Spanish by default). "
+            "Do not mention the internal tool or technical details. "
+            "Respond ONLY with the final content intended for the user."
         )
         return (
             f"{APIPILOT_PASS2_RESULT_MARKER}PASS2>>>\n"
-            "### Resultado de la herramienta ApiPilot invocada\n"
+            "### Invoked ApiPilot tool result\n"
             f"{title}\n"
             f"\n```tool-output\n"
-            f"{text.rstrip() if text.strip() else '(salida vacía)'}\n"
+            f"{text.rstrip() if text.strip() else '(empty output)'}\n"
             f"```\n\n"
             f"{trailer}\n"
         )
-    # ── PASSATA 1: Lista strumenti disponibili + regola marker ───────────────
+    # Pass 1: available tools and marker rules.
     tools = tools_list if isinstance(tools_list, list) else []
-    # Cap: max 100 strumenti (anche se la guida ne dichiara max 50 in demo)
+    # Limit to 100 tools, although the guide specifies at most 50 for the demo.
     tools_cap = tools[:100]
     if not tools_cap:
         return ""
@@ -791,7 +768,7 @@ def _resolve_apipilot_reasoning_context_block(
         required_fields: list[str] = []
         if isinstance(params, dict) and isinstance(params.get("required"), list):
             required_fields = [str(x) for x in params.get("required") if isinstance(x, str)]
-        # Truncate description a ~500 chars per evitare injection enorme di token
+        # Limit descriptions to about 500 characters to control prompt size.
         desc_cut = desc[:500].rstrip()
         if len(desc) > 500:
             desc_cut += "…"
@@ -805,50 +782,47 @@ def _resolve_apipilot_reasoning_context_block(
         return ""
     rule = (
         f"{APIPILOT_PASS1_LIST_MARKER}\n"
-        "### Herramientas dinámicas disponibles (ApiPilot AquaPortal)\n"
+        "### Available dynamic tools (ApiPilot AquaPortal)\n"
         "\n"
-        "Cada herramienta tiene un campo `name` (identificador único, NO lo modifiques, "
-        "NO camelCase, NO traducir) y un campo `description` que describe el caso de uso.\n"
+        "Each tool has a `name` field (a unique identifier: do NOT modify it, "
+        "use camelCase, or translate it) and a `description` describing its use case.\n"
         "\n"
-        "REGLAS EJECUCIÓN OBLIGATORIAS:\n"
-        "1. Si la petición DEL USUARIO (transcript) coincide claramente con la `description` "
-        "de EXACTAMENTE una (1) herramienta de la lista inferior → DEBES emitir EXCLUSIVAMENTE "
-        "una sola riga como PRIMERA línea de TU RESPUESTA, con este formato sintattico:\n"
-        "   <<<APIPILOT_CALL:NAME=nome_herramienta,ARGUMENTS={\"parametro1\":\"valor1\",\"parametro2\":\"valor2\"}>>>\n"
-        "2. La parte ARGUMENTS={…} DEBE ser JSON válido (virgolette doppie, virgole, senza "
-        "commenti). Includi SOLAMENTE i campi elencati in `required_parameters:` (se ci sono).\n"
-        "3. Subito DOPO la riga marker NON aggiungere altro testo (niente spiegazioni, "
-        "niente anticipazioni). Il motore eseguirà lo strumento e ti risomministrerà il "
-        "risultato in una seconda chiamata.\n"
-        "4. Se NESSUNA `description` corrisponde, NON emettere marker e rispondi normalmente.\n"
-        "5. Se più di una descrizione corrisponde, scegli la più specifica e usa il marker.\n"
-        "6. 🔴 MODO RISPOSTA ESCLUSIVO (priorità MASSIMA, non negoziabile): quando decidi di usare il "
-        "marker CALL, la TUA RISPOSTA INTERA DEVE ESSERE ESCLUSIVAMENTE LA RIGA DEL MARKER. "
-        "NON scrivere NIENTE PRIMA (niente 'Claro que sí', niente 'Voy a revisar', niente "
-        "'Voy a generar tu briefing', nessun saluto, nessuna frase transitoria). "
-        "NON scrivere NIENTE DOPO (nessun commento, nessuna anticipazione, nessuna spiegazione). "
-        "Una sola riga, esattamente il marker. Se scrivi altro testo oltre al marker il motore "
-        "non lo riconosce e non esegue alcuna herramienta.\n"
-        "8. Ejemplos SBAGLIATI (NON fare MAI):\n"
+        "MANDATORY EXECUTION RULES:\n"
+        "1. If the USER REQUEST (transcript) clearly matches the `description` of "
+        "EXACTLY one tool below, emit ONLY one line as the FIRST line of YOUR RESPONSE, "
+        "with this exact syntax:\n"
+        "   <<<APIPILOT_CALL:NAME=tool_name,ARGUMENTS={\"parameter1\":\"value1\",\"parameter2\":\"value2\"}>>>\n"
+        "2. ARGUMENTS={…} MUST be valid JSON (double quotes, commas, no comments). "
+        "Include ONLY fields listed in `required_parameters:`, if present.\n"
+        "3. Add NO text after the marker line: no explanations or previews. The engine "
+        "will execute the tool and supply its result in a second call.\n"
+        "4. If NO description matches, emit NO marker and respond normally in Spanish.\n"
+        "5. If multiple descriptions match, choose the most specific one and use the marker.\n"
+        "6. 🔴 EXCLUSIVE RESPONSE MODE (HIGHEST priority, mandatory): when using a CALL "
+        "marker, YOUR ENTIRE RESPONSE MUST CONTAIN ONLY THE MARKER LINE. "
+        "Write NOTHING BEFORE it: no 'Claro que sí', 'Voy a revisar', "
+        "'Voy a generar tu briefing', greeting, or transition. "
+        "Write NOTHING AFTER it: no comments, previews, or explanations. "
+        "Exactly one line containing the marker. Additional text prevents the engine "
+        "from recognizing the marker and executing the tool.\n"
+        "8. INCORRECT examples (NEVER do this):\n"
         "   'Claro que sí, ahora ejecuto'\n"
         "   'Voy a generar tu briefing ejecutivo personal.'\n"
         "   'Claro que sí.\\n<<<APIPILOT_CALL:...>>>'\n"
         "   '<<<APIPILOT_CALL:...>>>\\nAhora proceso el resultado.'\n"
-        "9. 🔴 REGLAS TTS ANTI-LEAK (NON negoziabili, priorità MASSIMA sul audio):\n"
-        "   Il marcador <<<APIPILOT_CALL:...>>> È UN SEGNALE INTERNO DI SISTEMA e NON DEVE MAI\n"
-        "   essere pronunciato / letto / sintetizzato dall' audio TTS. Quando emetti il marcador:\n"
-        "   - Il canale RAGIONAMENTO INTERNO (text/transcript) DEVE contenere la riga esatta del marcador.\n"
-        "   - Il canale AUDIO TTS FINALE che ascolta l'utente DEVE contenere SOLAMENTE il placeholder:\n"
+        "9. 🔴 TTS ANTI-LEAK RULES (mandatory, HIGHEST audio priority):\n"
+        "   <<<APIPILOT_CALL:...>>> IS AN INTERNAL SYSTEM SIGNAL and MUST NEVER be spoken,\n"
+        "   read aloud, or synthesized by TTS. When emitting the marker:\n"
+        "   - INTERNAL REASONING (text/transcript) MUST contain the exact marker line.\n"
+        "   - FINAL TTS AUDIO heard by the user MUST contain ONLY this placeholder:\n"
         "     \"Voy a consultar tus datos, un momento por favor.\"\n"
-        "   - NESSUNA delle parole seguenti deve MAI comparire nel TTS audio finale pronunciato:\n"
-        "     APIPILOT, CALL, ARGUMENTS, tool, herramienta, ejecutar, funzione, funzione chiamata,\n"
-        "     marcador, marker. (Nemmeno come spiegazione o descrizione della chiamata.)\n"
+        "   - NEVER speak any of these technical terms in final TTS audio:\n"
+        "     APIPILOT, CALL, ARGUMENTS, tool, herramienta, ejecutar, function, function call,\n"
+        "     marcador, marker, even to explain or describe the call.\n"
         "\n"
     )
-    # ── 2026-09-25 SECCIÓN NUEVA: VALORES POR DEFECTO CONOCIDOS ─────────────────
-    # I valori che GIA' ABBIAMO da URL o profilo (es. phoneNumber della sessione
-    # corrente) sono iniettati QUI così che quando l'AI decide di chiamare lo
-    # strumento inserisce esattamente i parametri senza lasciarli vuoti.
+    # 2026-09-25 known defaults: inject values already resolved from the URL or
+    # profile, such as phoneNumber, so tool arguments use those exact values.
     if isinstance(context_defaults, dict) and context_defaults:
         defaults_lines = []
         for dk, dv in context_defaults.items():
@@ -864,15 +838,14 @@ def _resolve_apipilot_reasoning_context_block(
             defaults_lines.append(f"- {dk} = \"{dv_repr}\"")
         if defaults_lines:
             rule += (
-                "VALORES POR DEFECTO CONOCIDOS (usa estos valores textualmente "
-                "en el ARGUMENTS={…} cuando la herramienta correspondiente tenga "
-                "estos nombres en required_parameters; no los inventes, no los "
-                "traduzcas, no los normalices):\n"
+                "KNOWN DEFAULT VALUES (use these exact values in ARGUMENTS={…} when "
+                "the corresponding tool lists these names in required_parameters; "
+                "do not invent, translate, or normalize them):\n"
                 f"{chr(10).join(defaults_lines)}\n"
                 "\n"
             )
     rule += (
-        "Lista herramientas (name / description):\n"
+        "Tool list (name / description):\n"
         f"{chr(10).join(entries)}\n"
         "<<<APIPILOT_TOOLS_LIST_END>>>"
     )
@@ -880,27 +853,21 @@ def _resolve_apipilot_reasoning_context_block(
 
 
 def _sanitize_pass2_internal_context(text: str) -> str:
-    """Sanitize LEGGERA per blocco PASS-2 iniettato ALL'AI upstream (NON all'utente).
+    """Lightly sanitize the pass-2 block injected into the upstream model.
 
-    NON USIAMO _sanitize_text_strip_apipilot_markers perché quella cancella
-    l'intero wrapper <<<APIPILOT_RESULT:PASS2>>> tramite BLOCCO 1 FULL STRIP —
-    quello wrapper serve ALL'AI per riconoscere che sono dati della chiamata.
-
-    Qui facciamo SOLO:
-      - BLOCCO 3 PATH leak filesystem (.trae-server / workspaceStorage / paths)
-      - BLOCCO 4 FRAGMENT marker parole singole leak
-      - TIER 6 phone contextual leak (solo se riga contiene marker)
+    Unlike _sanitize_text_strip_apipilot_markers, preserve the pass-2 wrapper:
+    the model needs it to recognize tool data. Limit sanitation to filesystem
+    path leaks, fragmented marker tokens, and contextual phone leaks.
     """
     if not isinstance(text, str) or not text.strip():
         return text
-    # ── BLOCCO 3 (path leaks Unix/Windows/TRAE token) ────────────────────
-    # (pattern identico a _sanitize_text_strip_apipilot_markers Blocco3)
+    # Block 3: Unix/Windows/TRAE path leaks, matching the user-output sanitizer.
     import re as _re_pass2
     text = _re_pass2.sub(r"(?i)(?:/[A-Za-z0-9_.\-@~]+){2,}/(?:\.trae[^\s\"']*|workspaceStorage[^\s\"']*|User[^\s\"']*|home[^\s\"']*)", " ", text)
     text = _re_pass2.sub(r"(?i)(?:[A-Z]:)?[\\/](?:Users|home|root|tmp|var|mnt|opt|srv)[\\/][^\s\"']{5,}", " ", text)
     text = _re_pass2.sub(r"(?i)(?:\.trae-server|\.trae[^\s\"']{0,40}|workspaceStorage[0-9a-f]+)", " ", text)
     text = _re_pass2.sub(r"\s{2,}", " ", text)
-    # ── BLOCCO 4 FRAGMENT marker leak tier-4 ─────────────────────────────
+    # Block 4: fragmented marker leaks, tier 4.
     tier4_out_parts: list[str] = []
     for _line in text.splitlines(keepends=True):
         _orig = _line
@@ -938,26 +905,15 @@ def _sanitize_text_strip_apipilot_markers(
     *,
     placeholder: str | None = None,
 ) -> str:
-    """Rimuovi TUTTI i marker interni di ApiPilot (PASS-1 CALL e PASS-2 RESULT)
-    dal testo che arriva all'utente finale (UI chat + audio TTS + conversation
-    item visualizzazione).
+    """Remove all internal ApiPilot markers from user-visible chat and TTS text.
 
-    Regole stripping:
-      - MARKER CALL <<<APIPILOT_CALL:...>>> → placeholder spagnolo
-        (se l'AI emette il marker e viene mandato alla TTS per sbaglio, lo
-        mascheriamo con messaggio UI coerente).
-      - MARKER PASS-2 <<<APIPILOT_RESULT:...>>> + <<<APIPILOT_RESULT:PASS2>>>
-        + wrapper "### Resultado de la herramienta ApiPilot..."
-        + blocco ```tool-output ... ``` + re-instruction trailer finale
-        → RIMOSSI SILENZIOSAMENTE (nessun placeholder: sono segnali server
-          interni per la PASS-2 di reasoning; NON devono mai arrivare a
-          TTS/UI. Se l'AI per sbaglio li ripete nella risposta finale,
-          li cancelliamo senza lasciare traccia).
+    Replace pass-1 CALL markers with a Spanish placeholder. Silently remove
+    pass-2 RESULT markers, their heading, tool-output block and instruction
+    trailer. These server-only signals must never reach the user.
 
-    Parametri:
-      - text: la stringa da sanificare
-      - placeholder: None = default spagnolo "Voy a consultar tus datos, un momento por favor."
-        (lingua coerente con la lingua UI e vocale target)
+    Args:
+      text: Text to sanitize.
+      placeholder: Optional replacement; defaults to the Spanish UI/voice message.
     """
     if not isinstance(text, str) or not text:
         return text
@@ -965,23 +921,20 @@ def _sanitize_text_strip_apipilot_markers(
         placeholder = "Voy a consultar tus datos, un momento por favor."
 
     # ================================================================
-    # BLOCCO 1: PASS-2 RESULT markers + wrapper (RIMOZIONE SILENZIOSA)
-    # Questi NON devono MAI finire in TTS/UI.
+    # Block 1: silently remove pass-2 RESULT markers and wrappers from TTS/UI.
     # ================================================================
-    # (1a) Blocco intero PASS-2 wrapper (order matters: blocco largo PRIMA)
-    #      Pattern: riga PASS2>>> marker + titolo MD + RESULT STATUS marker +
-    #               block ```tool-output ... ``` (multilinea DOTALL) + trailer.
+    # (1a) Full pass-2 wrapper first: marker, heading, status, output, trailer.
     pass2_full_block_pattern = re.compile(
         r"[ \t]*(?:\r?\n|\r)?[ \t]*"
         r"<<<APIPILOT_RESULT:PASS2>>>[ \t]*(?:\r?\n|\r)+"
-        r"###[ \t]+Resultado de la herramienta ApiPilot invocada[ \t]*(?:\r?\n|\r)+"
+        r"###[ \t]+(?:Resultado de la herramienta ApiPilot invocada|Invoked ApiPilot tool result)[ \t]*(?:\r?\n|\r)+"
         r"<<<APIPILOT_RESULT:STATUS=[A-Za-z_]+,NAME=[A-Za-z0-9_.-]+>>>[ \t]*(?:\r?\n|\r)*"
         r"(?:\r?\n|\r)?"
         r"```tool-output[ \t]*(?:\r?\n|\r)?"
         r"(?P<tool_body>.*?)"
         r"(?:\r?\n|\r)?```[ \t]*(?:\r?\n|\r){0,3}"
         r"(?:"
-        r"Ahora debes reinterpretar EL TEXTO RESULTADO[\s\S]{0,1200}?"
+        r"(?:Ahora debes reinterpretar EL TEXTO RESULTADO|Now reinterpret THE RESULT TEXT)[\s\S]{0,1200}?"
         r"(?:\r?\n|\r){0,2}"
         r")?"
         r"[ \t]*",
@@ -989,54 +942,48 @@ def _sanitize_text_strip_apipilot_markers(
     )
     text = pass2_full_block_pattern.sub("", text)
 
-    # (1b) Marker PASS2 standalone (se il wrapper non è completo o frammentato)
+    # (1b) Standalone PASS2 markers when the wrapper is incomplete or fragmented.
     pass2_marker_pattern = re.compile(
         r"[ \t]*(?:\r?\n|\r)?[ \t]*<<<APIPILOT_RESULT(?::PASS2|:STATUS=[A-Za-z_]+,NAME=[A-Za-z0-9_.-]+)?>>>[ \t]*(?:\r?\n|\r)?[ \t]*",
         re.IGNORECASE,
     )
     text = pass2_marker_pattern.sub("", text)
 
-    # (1c) Titolo MD "### Resultado de la herramienta ApiPilot invocada"
-    #      residuo (se marker già stato rimosso prima)
+    # (1c) Residual Markdown heading after the marker has been removed.
     pass2_title_pattern = re.compile(
-        r"[ \t]*(?:\r?\n|\r)?[ \t]*###[ \t]+Resultado de la herramienta ApiPilot invocada[ \t]*(?:\r?\n|\r)?[ \t]*",
+        r"[ \t]*(?:\r?\n|\r)?[ \t]*###[ \t]+(?:Resultado de la herramienta ApiPilot invocada|Invoked ApiPilot tool result)[ \t]*(?:\r?\n|\r)?[ \t]*",
         re.IGNORECASE,
     )
     text = pass2_title_pattern.sub("", text)
 
-    # (1d) Blocco ```tool-output``` residuo standalone (senza wrapper PASS2)
+    # (1d) Standalone tool-output blocks without a PASS2 wrapper.
     pass2_codeblock_pattern = re.compile(
         r"```tool-output[ \t]*(?:\r?\n|\r)?.*?(?:\r?\n|\r)?```",
         re.IGNORECASE | re.DOTALL,
     )
     text = pass2_codeblock_pattern.sub("", text)
 
-    # (1e) Trailer instruction residuo standalone "Ahora debes reinterpretar..."
-    #      (intero o frammenti parziali che non hanno preso il pattern largo)
+    # (1e) Residual instruction trailers missed by the full-wrapper pattern.
     pass2_trailer_pattern = re.compile(
-        r"Ahora debes reinterpretar EL TEXTO RESULTADO[\s\S]{0,1200}?contenido final que le quieres transmitir al usuario\.",
+        r"(?:Ahora debes reinterpretar EL TEXTO RESULTADO[\s\S]{0,1200}?contenido final que le quieres transmitir al usuario|Now reinterpret THE RESULT TEXT[\s\S]{0,1200}?final content intended for the user)\.",
         re.IGNORECASE | re.DOTALL,
     )
     text = pass2_trailer_pattern.sub("", text)
-    # (1e-bis) Safety più largo: "Ahora debes reinterpretar" → qualsiasi cosa
-    # fino a fine frase "al usuario." (anche troncata nel mezzo) — questo
-    # gestisce i casi edge dove il pattern DOTALL non ha chiuso.
+    # Broader fallback also handles trailers truncated before their closing text.
     pass2_trailer_fallback = re.compile(
-        r"Ahora debes reinterpretar[\s\S]{0,1500}?(?:al usuario\.|$)",
+        r"(?:Ahora debes reinterpretar[\s\S]{0,1500}?(?:al usuario\.|$)|Now reinterpret THE RESULT TEXT[\s\S]{0,1500}?(?:for the user\.|$))",
         re.IGNORECASE | re.DOTALL,
     )
     text = pass2_trailer_fallback.sub("", text)
-    # (1e-tris) Safety ancora più largo: frammento trailer tipo
-    # "en lenguaje natural claro y conciso ... contenido final al usuario"
-    # (casi in cui Ahora debes... è stato consumato fuori e rimane residuo).
+    # Handle residual middle fragments after the trailer's opening was removed.
     pass2_trailer_broad = re.compile(
-        r"en lenguaje natural[\s\S]{0,800}?contenido final que le quieres transmitir al usuario\.?",
+        r"(?:en lenguaje natural[\s\S]{0,800}?contenido final que le quieres transmitir al usuario|in clear, concise natural language[\s\S]{0,800}?final content intended for the user)\.?",
         re.IGNORECASE | re.DOTALL,
     )
     text = pass2_trailer_broad.sub("", text)
 
     # ================================================================
-    # BLOCCO 2: PASS-1 CALL marker (placeholder spagnolo, come oggi)
+    # Block 2: pass-1 CALL marker replacement with a Spanish placeholder.
     # ================================================================
     marker_full_pattern = re.compile(
         r"<<<APIPILOT_CALL:NAME=[A-Za-z0-9_.-]+,ARGUMENTS=.*?>>>",
@@ -1048,67 +995,54 @@ def _sanitize_text_strip_apipilot_markers(
     )
 
     def _replacement_full(_m: re.Match) -> str:
-        """Se l'intera riga è solo il marker → placeholder. Se inline → placeholder circondato da spazi."""
+        """Replace standalone or inline markers with the spoken placeholder."""
         return placeholder
 
     text = line_wrapped_pattern.sub(_replacement_full, text)
     text = marker_full_pattern.sub(_replacement_full, text)
 
-    # Safety extra: marker troncato CALL tipo <<<APIPILOT_CALL:NAME=tool,ARGS… (incompleto)
+    # Remove truncated CALL markers such as <<<APIPILOT_CALL:NAME=tool,ARGS….
     trunc_call_pattern = re.compile(
         r"<<<APIPILOT_CALL(?::NAME=[A-Za-z0-9_.-]+,?[^>\n]{0,500}?)?>>*",
         re.IGNORECASE,
     )
     text = trunc_call_pattern.sub(_replacement_full, text)
 
-    # Safety extra: marker troncato RESULT tipo <<<APIPILOT_RESULT:... incompleto
-    #   OSS: rendiamo i caratteri `>` FINALI opzionali (+ opzionali `>` dopo)
-    #   così gestisce anche casi TTS audio troncato a metà stringa
-    #   (es. "<<<APIPILOT_RESULT:STATUS=OK,NAM" che non ha chiusura >>>)
+    # Make closing brackets optional to remove RESULT markers truncated by TTS,
+    # such as <<<APIPILOT_RESULT:STATUS=OK,NAM without closing >>>.
     trunc_result_pattern = re.compile(
         r"<<<APIPILOT_RESULT(?::[A-Za-z0-9_=,:.\- ]{0,800}?)?>?>?>?",
         re.IGNORECASE,
     )
     text = trunc_result_pattern.sub("", text)
-    # (Safety più largo: se rimane frammento APIPILOT_RESULT senza <<<
-    #  per casi TTS/sanitize frammentati, cancelliamo anche quello
-    #  MA SOLO se non è contenuto in testo normale - regex su "APIPILOT_RESULT"
-    #  sarebbe troppo aggressivo → solo con prefisso "<" o "<<<" residuo)
+    # Remove remaining APIPILOT_RESULT fragments after partial sanitation.
     trunc_result_residual = re.compile(
         r"<{0,3}APIPILOT_RESULT(?::[^\s<]{0,800})?<{0,3}",
         re.IGNORECASE,
     )
     text = trunc_result_residual.sub("", text)
 
-    # Collapse final whitespace (non vogliamo spazi multipli / newline vuoti
-    # lasciati dalla rimozione di blocchi PASS-2)
+    # Collapse whitespace left by pass-2 block removal.
     text = re.sub(r"[ \t]{2,}", " ", text)
     text = re.sub(r"\n{3,}", "\n\n", text)
-    # Safety cleanup: frammenti residuali super-comuni del trailer PASS-2
-    # tipo "(arriba)" o parentesi vuote (non hanno senso pronunciati da TTS)
-    text = re.sub(r"\s*\(arriba\)\s*", " ", text, flags=re.IGNORECASE)
+    # Remove residual trailer fragments and empty parentheses before TTS.
+    text = re.sub(r"\s*\((?:arriba|above)\)\s*", " ", text, flags=re.IGNORECASE)
     text = re.sub(r"\(\s*\)", "", text)
     # ================================================================
-    # BLOCCO 3: SANITIZZAZIONE PATH FILE SYSTEM (hallucination / leak TTS)
-    #   Qualsiasi path assoluto misto o Windows/Unix contenente /home,
-    #   \Users, .trae-server, workspaceStorage, .txt locale, unità C:\
-    #   NON deve MAI arrivare alla TTS (sono leak host).
-    #   Strategia: matcha path lungo 20+ chars con almeno 3 separatori.
+    # Block 3: remove filesystem paths and host information leaked into TTS.
+    # Match long absolute Unix/Windows/mixed paths and known workspace tokens.
     # ================================================================
-    # (3a) Path Unix-like assoluti: /home/... /tmp/... /var/... /root/... /opt/...
-    #      + qualsiasi path con >2 slash consecutivi tipo .../xyz/abc/def.ext
+    # (3a) Absolute Unix paths and nested paths with multiple separators.
     unix_path_pattern = re.compile(
         r"\b(?:/(?:home|tmp|var|root|opt|mnt|media|srv|proc|sys|etc|usr|Users|trae)[/\w@.+\-:#$%^&()[\]{}!~=,]*){2,}[A-Za-z0-9_./\-+@#$%^&()[\]{}!~=,:]*\.(?:txt|md|log|json|csv|pdf|doc|docx|py|js|ts|html|css|sh|yaml|yml|env|conf|cfg|ini|mp3|wav|ogg|png|jpg|jpeg|gif)\b"
         r"|"
-        # Fallback larghissimo: qualsiasi path ASSOLUTO Unix (inizia con / + cartella nota)
-        # con len>=20 chars, anche senza estensione — evitiamo falsi positivi tipo "/api/v1"
-        # ma catturiamo /home/duxiter/..., /tmp/prova, /var/log/... etc.
+        # Broad fallback for long absolute Unix paths under known directories,
+        # including paths without extensions; avoid short URLs such as /api/v1.
         r"(?:^|\s+|\(|[,.;:!?])(/(?:home|tmp|var|root|opt|mnt|media|srv|proc|sys|etc|usr|Users|trae)[/A-Za-z0-9_\-+@#$%^&()[\]{}!~=,.]{10,})(?=$|\s|\)|[,.;:!?])",
         re.IGNORECASE,
     )
     text = unix_path_pattern.sub("", text)
-    # (3b) Path Windows-like con backslash singoli o doppi: \Users\...  C:\...
-    #      e misti come /home\duxiter\.trae-server\... (hallucination mix)
+    # (3b) Windows paths with single/double backslashes and mixed separators.
     win_path_pattern = re.compile(
         r"(?:^|\s|\(|[,.;:])"
         r"([A-Za-z]:[\\/]"
@@ -1121,15 +1055,13 @@ def _sanitize_text_strip_apipilot_markers(
         re.IGNORECASE,
     )
     text = win_path_pattern.sub("", text)
-    # (3c) Hallucination folder markers specifici di TRAE (se arrivano frammenti
-    #      senza path completo, rimuoviamo anche i token chiave)
+    # (3c) TRAE workspace tokens, including fragments without complete paths.
     trae_leak_tokens = re.compile(
         r"\b(?:workspaceStorage|long-text|\.trae-server|\.trae|ckg_server|ai-agent)\b[^\s()'\"`,.]{0,80}",
         re.IGNORECASE,
     )
     text = trae_leak_tokens.sub("", text)
-    # (3d) Safety: qualsiasi token lungo > 80 chars che contenga BOTH (/) e (\)
-    #      o più di 5 slash/backslash ravvicinati → 100% path leak → rimuovi
+    # (3d) Remove long tokens containing mixed separators or many path segments.
     mixed_path_pattern = re.compile(
         r"(?=\S{0,200})"
         r"(?=\S*(?:[/\\].*){5,})"
@@ -1145,15 +1077,12 @@ def _sanitize_text_strip_apipilot_markers(
         return s
     text = mixed_path_pattern.sub(_mixed_safe, text)
     # ================================================================
-    # BLOCCO 4: SANITIZZAZIONE FRAGMENT-BASED APIPILOT CALL (anti-TTS leak)
-    #   Quando il pipeline upstream (start_pipeline_rag / Qwen3-TTS)
-    #   normalizza il marker RIMUOVENDO <<< >>>, il TTS pronuncia letteralmente:
+    # Block 4: remove fragmented APIPILOT CALL text from TTS. The upstream
+    # pipeline (start_pipeline_rag / Qwen3-TTS) can remove <<< >>> and read:
     #   "APIPILOT CALL name get_user_briefing arguments phone +56912345678"
-    #   Questi pattern NON sono più catturati dai marker <<<...>>> del Blocco 2.
-    #   Quindi catturiamo FRAMMENTI con regole di contesto, 5 tier fallback.
+    # The bracketed patterns cannot catch this, so use contextual fallback tiers.
     # ================================================================
-    # Tier 1 - Forma normalizzata completa (senza graffe):
-    #   APIPILOT CALL name <toolname> arguments <qualsiasi cosa fino a end-frases>
+    # Tier 1: full normalized form without braces, through the sentence ending.
     call_normalized_full = re.compile(
         r"(?:^|\s+|\(|[,.;:!?\"\'])\s*"
         r"(?:"
@@ -1169,7 +1098,7 @@ def _sanitize_text_strip_apipilot_markers(
         re.IGNORECASE,
     )
     text = call_normalized_full.sub(placeholder, text)
-    # Tier 2 - Forme abbreviate (qualsiasi contesto con token APIPILOT_CALL o APIPILOT + CALL vicini)
+    # Tier 2: shortened forms with APIPILOT_CALL or adjacent APIPILOT and CALL.
     apipilot_call_token = re.compile(
         r"(?:^|\s|\(|[,.;:!?\"\'])\s*"
         r"APIPILOT(?:[\s_\-]+CALL|_CALL|\s+llamada|\s+marker)"
@@ -1178,9 +1107,7 @@ def _sanitize_text_strip_apipilot_markers(
         re.IGNORECASE,
     )
     text = apipilot_call_token.sub(placeholder, text)
-    # Tier 3 - Singoli token di servizio che non devono MAI comparire soli in
-    #   output assistant (se lo fanno → 99% leak marker normalizzato):
-    #   ARGUMENTS=... o APIPILOT solitario in contesto "call / name / argument"
+    # Tier 3: standalone service tokens in call/name/argument contexts.
     service_token_context = re.compile(
         r"(?:"
         r"ARGUMENTS\s*[:=]\s*(?:\{[^{}]{0,800}\}|[^\s,.;!?]{3,100})"
@@ -1189,67 +1116,54 @@ def _sanitize_text_strip_apipilot_markers(
         re.IGNORECASE,
     )
     text = service_token_context.sub("", text)
-    # Tier 4 - Safety catch-all: se dopo i blocchi 1/2/3/4 rimane la
-    #   sequenza "APIPILOT" (non APIClient o simili) in un contesto che ha
-    #   "name", "arguments", "tool", "herramienta", "phone", "+56" o "+44"
-    #   nella stessa frase → rimuoviamo l'intera frase.
-    def _apipilot_frase(m):
-        frase = m.group(0)
-        lowered = frase.lower()
-        # Se già contiene il placeholder spagnolo di sanitize CALL → Tier1/2/5
-        # hanno già sostituito il marker. Non cancellare la frase intera
-        # (altrimenti perdiamo testo naturale "prima/dopo" attorno).
+    # Tier 4: remove sentences containing APIPILOT with technical call context.
+    def _apipilot_sentence(m):
+        sentence = m.group(0)
+        lowered = sentence.lower()
+        # Preserve a sentence already containing the Spanish CALL placeholder,
+        # including any natural text surrounding it.
         if "voy a consultar tus datos" in lowered:
-            return frase
+            return sentence
         ctx_kw = ("name", "argument", "arg", "herramienta", "tool",
                   "funci", "phone", "tel", "+56", "+44", "marker",
                   "call", "llamada", "señal", "marcador")
         if any(k in lowered for k in ctx_kw) and "apipilot" in lowered:
             return ""
-        return frase
-    catchall_frase = re.compile(
+        return sentence
+    catchall_sentence = re.compile(
         r"[^.?!;\n]{0,600}APIPILOT[^.?!;\n]{0,600}[.?!;\n]{0,1}",
         re.IGNORECASE,
     )
-    text = catchall_frase.sub(_apipilot_frase, text)
-    # Tier 5 - Safety ultimo: se rimane "APIPILOT CALL" o "APIPILOT_CALL"
-    #   anche senza contesto → placeholder (non si pronuncia mai)
+    text = catchall_sentence.sub(_apipilot_sentence, text)
+    # Tier 5: replace any remaining APIPILOT CALL tokens, even without context.
     final_apipilot_leak = re.compile(
         r"\bAPIPILOT[\s_\-]+CALL\b|\bAPIPILOT_CALL\b",
         re.IGNORECASE,
     )
     text = final_apipilot_leak.sub(placeholder, text)
-    # Tier 6 - Phone blacklist safety (placeholder fake e/o phone reale leaks):
-    #   Quando APIPILOT CALL viene catturato ma la parte "phone" e'
-    #   residua, rimuoviamo i numeri di telefono finti/placeholder che
-    #   NON devono mai comparire in TTS (sono interni al motore).
-    #   N.B. Le regex matchano SIA forma compatta (+56912345678) SIA spaziata
-    #   (+56 9 1 2 3 4 5 6 7 8) per tolleranza alla normalizzazione TTS.
+    # Tier 6: remove residual fake/real phone numbers from internal call text.
+    # Match compact and spaced forms to tolerate TTS normalization.
     fake_phone_pattern = re.compile(
         r"("
-        # Forme COMPATTE (nessuno spazio):
+        # Compact forms without spaces:
         r"\+56912345678"
         r"|\+1234567890"
         r"|\+447432477433"
         r"|56912345678"
         r"|1234567890"
         r"|447432477433"
-        # Forme SPAZIATE / CON SEGNI:
+        # Spaced forms with punctuation:
         r"|\+?\s*56\s*[\s\-()]?9\s*[\s\-()]?1\s*[\s\-()]?2\s*[\s\-()]?3\s*[\s\-()]?4\s*[\s\-()]?5\s*[\s\-()]?6\s*[\s\-()]?7\s*[\s\-()]?8"
         r"|\+?\s*1\s*[\s\-()]?2\s*[\s\-()]?3\s*[\s\-()]?4\s*[\s\-()]?5\s*[\s\-()]?6\s*[\s\-()]?7\s*[\s\-()]?8\s*[\s\-()]?9\s*[\s\-()]?0"
         r"|\+?\s*44\s*[\s\-()]?7\s*[\s\-()]?4\s*[\s\-()]?3\s*[\s\-()]?2\s*[\s\-()]?4\s*[\s\-()]?7\s*[\s\-()]?7\s*[\s\-()]?4\s*[\s\-()]?3\s*[\s\-()]?3"
-        # Forme GENERICHE con etichetta (phone/teléfono):
+        # Generic labeled forms (English or Spanish phone labels):
         r"|phone\s*[:=]\s*[+()\-\s]*[0-9][+()\-\s0-9]{6,}"
         r"|tel(?:éfono|efono)?\s*[:=]\s*[+()\-\s]*[0-9][+()\-\s0-9]{6,}"
         r")",
         re.IGNORECASE,
     )
-    # Applichiamo lo strip SOLO se nella frase (stessa riga / stessa frase)
-    # e' presente "APIPILOT", "CALL", "ARGUMENTS", "marker", "herramienta",
-    # "función", "ejecutar", "llamada", "marcador", "señal"
-    # OPPURE se c'e' il placeholder spagnolo (Voy a consultar tus datos...)
-    # perche' vuol dire che abbiamo appena sostituito un marker CALL in
-    # questa stessa frase, quindi il phone residuo appartiene a quel contesto.
+    # Strip numbers only from lines with technical call context or the Spanish
+    # placeholder, indicating that the number belongs to a replaced CALL marker.
     lines = text.splitlines(keepends=True)
     _phone_ctx = ("apipilot", "call", "arguments", "marker", "herramienta",
                   "funcion", "función", "ejecutar", "llamada", "marcador",
@@ -1262,7 +1176,7 @@ def _sanitize_text_strip_apipilot_markers(
             return fake_phone_pattern.sub(" ", line)
         return line
     text = "".join(_phone_line_safe(l) for l in lines)
-    # Collapse whitespace finale (dopo strip di marker/path si creano buchi)
+    # Collapse whitespace left by marker and path removal.
     text = re.sub(r"[ \t]{2,}", " ", text)
     text = re.sub(r"\n{3,}", "\n\n", text)
     return text.strip()
@@ -1279,14 +1193,12 @@ async def _apipilot_execute_tool(
 
     Implements the full PRE-CHECK flow (§2.2) BEFORE sending the HTTP
     request:
-      1. Fresh tool discovery (<= TTL cache, force_refresh=True se tool non trovato)
-      2. requires_auth check: blocco con HTTP 401 se true ma nessun token
-      3. Strict JSON-Schema validation: filtra params extra, controlla required
+      1. Fresh discovery (TTL cache; force_refresh=True if a tool is missing).
+      2. requires_auth: return HTTP 401 when authentication is required but absent.
+      3. Strict JSON-Schema validation: filter unknown parameters and check required.
 
-    Il payload di ritorno è SEMPRE la busta standard `{success, data, error}`
-    della guida §2.2. In caso di errori PRE-CHECK (network discovery,
-    requires_auth, validazione arg) la busta ha `success=false` e
-    `error.{code,message,status_code}` popolati.
+    Always return the standard `{success, data, error}` envelope (guide §2.2).
+    Pre-check failures populate error.{code,message,status_code}, with success=false.
     """
     name_clean = (name or "").strip() if isinstance(name, str) else ""
     logger.info("[APIPILOT-CALL-NAME] USE=EXECUTE_ENTRYPOINT name=%r argsKeys=%s authHead=%.20s demo=%.20s", name_clean, sorted(list((arguments or {}).keys())) if isinstance(arguments, dict) else [], str(auth_header or "")[:20], str(demo_session or "")[:20])
@@ -1310,8 +1222,8 @@ async def _apipilot_execute_tool(
     tools = await _apipilot_fetch_tools(auth_header=auth_header, demo_session=demo_session, force_refresh=False)
     tool_def = next((t for t in tools if t.get("name") == name_clean), None)
     if tool_def is None:
-        # Tool sconosciuto: forza refresh discovery e riprova (max 1).
-        logger.info("[APIPILOT-EXEC] tool=%s non found → forced re-discovery", name_clean)
+        # Unknown tool: refresh discovery and retry once.
+        logger.info("[APIPILOT-EXEC] tool=%s not found → forced re-discovery", name_clean)
         tools = await _apipilot_fetch_tools(auth_header=auth_header, demo_session=demo_session, force_refresh=True)
         tool_def = next((t for t in tools if t.get("name") == name_clean), None)
     if tool_def is None:
@@ -1332,7 +1244,7 @@ async def _apipilot_execute_tool(
     requires_auth = bool(tool_def.get("requires_auth"))
     has_token = bool(auth_header) or bool(demo_session) or bool(S2S_APIPILOT_SERVICE_TOKEN)
     if requires_auth and not has_token:
-        logger.warning("[APIPILOT-EXEC] tool=%s requires_auth=true bloccato (nessun token)", name_clean)
+        logger.warning("[APIPILOT-EXEC] tool=%s requires_auth=true blocked (no token)", name_clean)
         return {
             "success": False,
             "data": None,
@@ -1346,7 +1258,7 @@ async def _apipilot_execute_tool(
                 "raw": None,
             },
         }
-    # ── PRE-CHECK 3: validazione argomenti strict JSON-Schema ─────────────────
+    # Pre-check 3: strict JSON-Schema argument validation.
     cleaned_args, errors = _apipilot_validate_arguments(arguments, tool_def)
     if errors:
         return {
@@ -1367,28 +1279,26 @@ async def _apipilot_execute_tool(
             "data": None,
             "error": {
                 "code": "APIPILOT_NOT_CONFIGURED",
-                "message": "ApiPilot no está configurado en este despliegue (S2S_APIPILOT_TOOLS_URL e S2S_APIPILOT_TOOLS_EXECUTE_URL entrambe vuote).",
+                "message": "ApiPilot no está configurado en este despliegue (S2S_APIPILOT_TOOLS_URL y S2S_APIPILOT_TOOLS_EXECUTE_URL están vacíos).",
                 "status_code": 501,
                 "raw": None,
             },
         }
     headers = {"Content-Type": "application/json", "accept": "application/json,text/plain,*/*"}
-    # 2026-09-25 SUPER API KEY (PRIORITÀ ASSOLUTA 🔴): bypass autenticazione AquaPortal.
-    #    Tutti e 3 le forme contemporaneamente per max compatibilità:
+    # 2026-09-25 SUPER API KEY (highest priority): bypass AquaPortal authentication.
+    #    Send all three header forms simultaneously for maximum compatibility:
     #      - X-API-Key: <key>
     #      - Authorization: Bearer <key>
     #      - x-demo-session: <key>
-    #    Qualsiasi altro auth (service token, login_by_phone) viene completamente
-    #    ignorato quando la API KEY è valorizzata.
+    #    Ignore service tokens and login_by_phone when the API KEY is set.
     if S2S_APIPILOT_API_KEY:
         headers["X-API-Key"] = S2S_APIPILOT_API_KEY
         headers["Authorization"] = f"Bearer {S2S_APIPILOT_API_KEY}"
         headers["x-demo-session"] = S2S_APIPILOT_API_KEY
         final_auth = f"Bearer {S2S_APIPILOT_API_KEY}"
     else:
-        # 2026-09-25 Priorità auth: 1) S2S_APIPILOT_SERVICE_TOKEN (override max .env),
-        #    2) auth_header (Bearer AquaPortal da _login_by_phone, da WS connect DISCOVERY
-        #    o fallback PASS-2 login), 3) nessun auth.
+        # Authentication priority: service-token override, then caller auth_header
+        # from phone login/discovery/pass-2 fallback, then no authentication.
         if S2S_APIPILOT_SERVICE_TOKEN:
             _svc = S2S_APIPILOT_SERVICE_TOKEN.strip()
             final_auth = (f"Bearer {_svc}" if (not _svc.lower().startswith("bearer ")) else _svc) if _svc else None
@@ -1416,12 +1326,10 @@ async def _apipilot_execute_tool(
             "data": None,
             "error": {"code": "EXECUTION_ERROR", "message": f"Error de red al ejecutar «{name_clean}»: {exc}", "status_code": 502, "raw": None},
         }
-    # Tentativo di deserializzare come busta standard. Se il backend risponde
-    # 5xx o body non-JSON, costruisce una envelope errore coerente.
+    # Parse a standard envelope; construct a matching error for non-JSON/5xx responses.
     raw_text = resp.text
-    # 2026-09-25 Diagnostica Dettagliata ALWAYS-ON se http >= 400 (401/403/404/5xx)
-    #    Log: payload request (name + arguments RAW completo demo session NON mascherato
-    #    response http status code, raw response body full (max 2000 chars).
+    # Detailed diagnostics are always enabled for HTTP >= 400: request payload,
+    # unmasked demo session, response status and bounded raw response body.
     if resp.status_code >= 400:
         try:
             payload_dump = __import__("json").dumps(payload, ensure_ascii=False)
@@ -1451,7 +1359,7 @@ async def _apipilot_execute_tool(
                 "raw": raw_text[:2000] if raw_text else None,
             },
         }
-    # Caso: envelope standard `{success,data,error}` — ritorno as-is.
+    # Return standard {success,data,error} envelopes unchanged.
     if isinstance(parsed, dict) and "success" in parsed and isinstance(parsed.get("success"), bool):
         envelope_ok = parsed["success"] and parsed.get("error") in (None, {})
         logger.info(
@@ -1467,10 +1375,9 @@ async def _apipilot_execute_tool(
                 (str(err.get("message"))[:200] if err.get("message") is not None else "-"),
             )
         return parsed
-    # Caso: backend ha restituito data pura (senza envelope). Wrappa come
-    # success=true (§2.2 della guida: envelope obbligatorio — se non lo
-    # rispetta noi normalizziamo lato proxy per stabilità downstream).
-    logger.warning("[APIPILOT-EXEC] backend non ha restituito envelope standard → wrap manuale http=%s", resp.status_code)
+    # Wrap raw backend data in the required envelope (guide §2.2) for stable
+    # downstream behavior when an upstream response omits the wrapper.
+    logger.warning("[APIPILOT-EXEC] backend omitted standard envelope → wrapping response http=%s", resp.status_code)
     return {
         "success": 200 <= resp.status_code < 300,
         "data": parsed if (200 <= resp.status_code < 300) else None,
@@ -1485,8 +1392,8 @@ async def _apipilot_execute_tool(
     }
 
 
-# Node-RED reasoning engine endpoint (modalità NODE_RED).
-# Es.: http://localhost:1881  oppure  http://s2s-reasoning:1880  (rete docker)
+# Node-RED reasoning engine endpoint (NODE_RED mode).
+# Examples: http://localhost:1881 or http://s2s-reasoning:1880 (Docker network).
 NODE_RED_REASONING_URL = os.environ.get("S2S_REASONING_NODE_RED_URL", "").strip().rstrip("/")
 # Speech-to-speech load balancer URL. When set, the browser POSTs /api/session
 # (which proxies <lb>/session here, server-side) and connects to the URL the LB
@@ -1524,10 +1431,8 @@ app = FastAPI(title="s2s-demo")
 # Sign-in only matters when we're metering (prod Space), so gate it on that.
 AUTH_ENABLED = LIMITER_ENABLED and auth.attach(app)
 
-# Calcolo dell'URL execute risolto (serve per STARTUP banner e _apipilot_resolve_execute_url).
-# Nota: la funzione formale _apipilot_resolve_execute_url è definita più avanti (dopo
-# _apipilot_parse_authorization) e usa la stessa identica logica; la ripetiamo qui
-# perché il banner STARTUP viene stampato PRIMA della funzione.
+# Resolve the execution URL for the startup banner using the same normalization
+# as _apipilot_resolve_execute_url.
 def _resolve_exec_url_for_startup_banner():
     base = (S2S_APIPILOT_TOOLS_EXECUTE_URL or S2S_APIPILOT_TOOLS_URL).strip().rstrip("/")
     if not base:
@@ -1561,12 +1466,12 @@ logger.info(
     S2S_THEME or "-",
     AUTH_ENABLED,
     S2S_APIPILOT_TOOLS_URL or "-",
-    (S2S_APIPILOT_TOOLS_EXECUTE_URL + f"(risolto:{_STARTUP_APIPILOT_EXEC_URL})") if S2S_APIPILOT_TOOLS_EXECUTE_URL else "-",
+    (S2S_APIPILOT_TOOLS_EXECUTE_URL + f"(resolved:{_STARTUP_APIPILOT_EXEC_URL})") if S2S_APIPILOT_TOOLS_EXECUTE_URL else "-",
     "Y" if bool(S2S_APIPILOT_SERVICE_TOKEN) else "-",
     APIPILOT_CACHE_TTL_SEC,
     APIPILOT_HTTP_TIMEOUT,
     "Y" if (bool(S2S_APIPILOT_TOOLS_URL) or bool(S2S_APIPILOT_TOOLS_EXECUTE_URL)) else "-",
-    ("YES head=" + (S2S_APIPILOT_API_KEY[:6] + "..." if len(S2S_APIPILOT_API_KEY) > 6 else S2S_APIPILOT_API_KEY) + " (3 FORME!)") if S2S_APIPILOT_API_KEY else "-",
+    ("YES head=" + (S2S_APIPILOT_API_KEY[:6] + "..." if len(S2S_APIPILOT_API_KEY) > 6 else S2S_APIPILOT_API_KEY) + " (3 FORMS!)") if S2S_APIPILOT_API_KEY else "-",
 )
 del _STARTUP_APIPILOT_EXEC_URL
 logger.debug(
@@ -1650,12 +1555,12 @@ def _realtime_event_summary(raw: str) -> dict | None:
             elif part.get("type") == "audio":
                 if isinstance(part.get("transcript"), str) and part["transcript"]:
                     summary["text"] = part["transcript"]
-    # Variante standard OpenAI:
+    # Standard OpenAI variant:
     elif event_type == "response.audio_transcript.done":
         summary["response_id"] = payload.get("response_id")
         summary["item_id"] = payload.get("item_id")
         summary["text"] = payload.get("transcript", "")
-    # Variante upstream custom (osservato nel log dell'utente):
+    # Custom upstream variant observed in user logs:
     elif event_type == "response.output_audio_transcript.done":
         summary["response_id"] = payload.get("response_id")
         summary["item_id"] = payload.get("item_id")
@@ -1669,7 +1574,7 @@ def _realtime_event_summary(raw: str) -> dict | None:
             if isinstance(v, str) and v.strip():
                 text = v.strip()
                 break
-        # Se text ancora vuoto, cerca all'interno di eventuali sotto-oggetti noti
+        # If text is still empty, search known nested objects.
         if not text:
             for container in ("item", "part", "content", "output", "delta", "audio"):
                 sub = payload.get(container)
@@ -1682,7 +1587,7 @@ def _realtime_event_summary(raw: str) -> dict | None:
                     if text:
                         break
             if not text:
-                # Ultima risorsa: content[] array
+                # Last resort: the content[] array.
                 arr = payload.get("content")
                 if isinstance(arr, list):
                     parts = []
@@ -1695,8 +1600,7 @@ def _realtime_event_summary(raw: str) -> dict | None:
                     if parts:
                         text = " ".join(parts)
         summary["text"] = text
-        # Se non abbiamo ancora trovato testo, salva un'anteprima del raw
-        # per capire dove lo sta emettendo l'upstream custom.
+        # If no text was found, retain a raw preview to inspect the custom format.
         if not text:
             preview = raw[:800]
             try:
@@ -1706,13 +1610,12 @@ def _realtime_event_summary(raw: str) -> dict | None:
             summary["_raw_preview"] = pretty
     elif event_type == "response.function_call_arguments.done":
         summary["arguments"] = payload.get("arguments")
-        # Questo evento è il KEY CHECK della Strategia B: se lo vediamo =
-        # ai-server ha accettato tools[] nativi (native toolcall detected).
+        # This event confirms strategy B: ai-server accepted native tools[].
         _tool_name = payload.get("name") if isinstance(payload.get("name"), str) else ""
         _call_id = payload.get("call_id") if isinstance(payload.get("call_id"), str) else ""
         _args_json = payload.get("arguments") if isinstance(payload.get("arguments"), str) else "{}"
         logger.info(
-            "[TOOLCALL] ✓ UPSTREAM ha emesso response.function_call_arguments.done! "
+            "[TOOLCALL] ✓ UPSTREAM emitted response.function_call_arguments.done! "
             "tool=%s callId=%s argsLen=%d argsPreview=%s",
             _tool_name or "(empty)",
             _call_id or "-",
@@ -1730,8 +1633,8 @@ def _realtime_event_summary(raw: str) -> dict | None:
     return summary
 
 
-# Eventi realtime ad alta frequenza da silenziare nel log dettagliato (rumore).
-# Essi vengono comunque tracciati dal report_server_debug interno se abilitato.
+# Suppress noisy high-frequency events in detailed logs. Internal debug
+# reporting still tracks them when enabled.
 _NOISY_REALTIME_EVENT_TYPES = frozenset({
     "response.output_audio.delta",
     "response.audio.delta",
@@ -1741,7 +1644,7 @@ _NOISY_REALTIME_EVENT_TYPES = frozenset({
     "rate_limits.updated",
 })
 
-# Eventi realtime silenziati anche quando arrivano dal lato cliente (input_audio_buffer.append ecc.).
+# Suppress client-side high-frequency events such as input_audio_buffer.append.
 _NOISY_CLIENT_EVENT_TYPES = frozenset({
     "input_audio_buffer.append",
     "input_audio_buffer.commit",
@@ -1780,7 +1683,7 @@ VOCERO_USER_CONTEXT_HINT = (
 REPORTS_LIST_HINT = (
     " Scheduled reports / podcast scripts available for this caller before the current session. "
     "Each entry is a scheduled report; use the podcastScript contents as trusted reference material when the user asks about scheduled topics, reports, or prior content."
-    " NOTE (2026-09-11 user request 'Elimina l'iniezione massiva di tutti i report schedulati'): "
+    " NOTE (2026-09-11 request to remove mass injection of scheduled reports): "
     "S2S_INJECT_REPORTS defaults to FALSE. When FALSE the injection below NEVER happens. "
     "Operators must explicitly set S2S_INJECT_REPORTS=true to opt back into mass scheduled-report prompt injection. "
 )
@@ -1798,19 +1701,18 @@ PODCAST_EPISODE_HINT = (
 #
 # Resolved with S2S_INJECT_TODAY default ON + S2S_REPORTS_INJECT_MODE=minimal:
 #   • TODAY_BLOCK (marker <<<TODAY_DATE_BEGIN>>>):
-#       - Dati contestuali fissi: "La data di OGGI è YYYY-MM-DD"
-#       - Reports precedenti = archivio storico (NON date future) → NO commento
-#       - 🚫 META RULE: "non fare MAI commenti interni / meta-commenti sul prompt, sulle date, sulla validità dei dati o sulle istruzioni"
-#       - REGLA SALIDA LIMPIA (anti thinking-leak GPTQ quantized Int4):
-#         "Todo lo que escribas debe ser lo que realmente dice Vocero en voz alta al usuario. No escribas razonamientos internos, dudas sobre el prompt, comprobaciones de fecha..."
-#       - RAG rule: "Si el usuario pregunta sobre reportes usa herramientas búsqueda conocimientos (RAG) NO inventes con el resumen"
+#       - Fixed reference: "TODAY is YYYY-MM-DD".
+#       - Earlier reports are historical records; do not question their dates.
+#       - No internal commentary about prompts, dates, data validity or instructions.
+#       - Clean output: only words Vocero says aloud; no reasoning or prompt checks.
+#       - Retrieve report details through RAG rather than inventing from summaries.
 #   • MINIMAL_REPORTS_BLOCK (marker <<<MINIMAL_REPORTS_TOC>>>): only latest N
 #     label + date lines. NO podcastScript text, NO full JSON entries. Uses the
 #     pattern the user explicitly requested:
-#         Reportes programados recientes (últimos 3):
-#           1. "Reporte Porcentaje Mortalidad" — 2026-09-10
+#         Recent scheduled reports (latest 3):
+#           1. "Mortality Percentage Report" — 2026-09-10
 #           2. ...
-#         (Para contenido completo usa la búsqueda de conocimientos.)
+#         (Retrieve full content through knowledge search.)
 #   • We register both blocks with the dedupe layer via the new TYPE IDs
 #     "today_fixed" and "reports_minimal" so they also can never get duplicated.
 #
@@ -1877,9 +1779,9 @@ def _extract_user_name_parts(profile) -> list[str]:
     ["Alessandro", "Valenti"]). Returns [] when profile has no name.
 
     Used by:
-      • _build_voice_rules_head_lock_block — prompt rule #5 "Nombre exacto"
-      • _resolve_user_context_text       — profile NOTA dynamic anti-anglicization
-      • _sanitize_agent_output           — strato 7 terminal regex whole-word replace
+      • _build_voice_rules_head_lock_block — prompt rule #5, exact name.
+      • _resolve_user_context_text — dynamic profile note against name translation.
+      • _sanitize_agent_output — layer 7 final whole-word regex replacement.
     """
     if not profile or not isinstance(profile, dict):
         return []
@@ -1914,39 +1816,39 @@ def _build_voice_rules_head_lock_block(profile=None) -> str:
 
     Fixes 6 hallucination categories seen in user log 2026-09-11 07:57:
       (1) [-]: checking_podcast_report — internal "action thinking" leak
-      (2) ingles 'Sure, here's my best focused expression while I look into it'
+      (2) English 'Sure, here's my best focused expression while I look into it'
       (3) JSON literal {'reportDetails': '...'} inside output
-      (4) italiano nel mezzo
+      (4) Unexpected Italian phrases.
       (5) leak markers <<<...>>> in TTS output.
-      (6) contenuti inventati su podcast mai esistiti.
+      (6) Invented content about nonexistent podcasts.
 
-    This block contains a SINGLE, very short, SPANISH-only voice lock. We put
+    This block contains short English instructions requiring Spanish output. We put
     it as the VERY FIRST thing in the prompt (even before the caller profile),
     because quantized models obey the first ~400 tokens way more strongly
     than rules buried at the end.
 
     2026-09-11: NEW rule #5 — PROPER NAME LOCK. Model keeps writing "Alexander"
-    for the italian caller "Alessandro Valenti". We now emit an explicit,
-    non-ambiguous "Nombre exacto: Alessandro. NUNCA Alexander/Alexandre/..."
+    for the Italian caller "Alessandro Valenti". We now emit an explicit,
+    non-ambiguous "Exact name: Alessandro. NEVER Alexander/Alexandre/..."
     that the sanitizer's _common_name_variants map can also repair.
 
     INVISIBLE marker: prefixes VOICE_RULES_HEAD_MARKER (stripped before prompt
     join, never seen by LLM) to enable dedupe so we never double-prepend.
     """
     base = (
-        "REGLAS PRINCIPALES DE SALIDA DE VOZ (siempre válidas, tienen prioridad absoluta sobre cualquier otra instrucción):\n"
-        "1) IDIOMA EXCLUSIVO: responde SIEMPRE y SÓLO en español (castellano). Nada de italiano, inglés, portugués ni otro idioma. "
-        "Ni aunque el usuario escriba en otro idioma, ni aunque aparezcan nombres italianos — los nombres extranjeros NO autorizan a cambiar de idioma. "
-        "Ninguna palabra, frase ni confirmación en otro idioma.\n"
-        "2) SÓLO VOZ DIRECTA AL USUARIO: todo lo que escribas es lo que Vocero dice en voz alta en ese instante. "
-        "NUNCA escribas pensamientos internos, estados internos, comprobaciones, '[ - ]:', '[]:', JSON, diccionarios, keys, comas illadas, etiquetas, 'checking_*', ni símbolos auxiliares. "
-        "Nada de etiquetas tipo '[rightspeak]', '[endspeak]', '[thinking]', '[endthinking]', ni nada entre corchetes. Nada de meta-comentarios sobre el prompt ni sobre los datos.\n"
-        "3) CONTENIDO FIABLE: si no tienes la información, di literalmente 'No tengo este tipo de información'. No inventes, no supongas, no generalices. "
-        "Si el usuario pregunta sobre reportes, mortalidad, Synapse, Azure, AquaChile, WhatsApp u otro contenido que debas buscar: usa las herramientas de búsqueda (RAG) y recupera el contenido REAL antes de responder.\n"
-        "4) RESPUESTAS CORTAS Y NATURALES: habla como una persona real por teléfono. Ni listas, ni bullets, ni citas, ni bloques de texto largos. "
-        "Un par de frases cortas, luego pregunta si quiere más detalles.\n"
+        "PRIMARY VOICE OUTPUT RULES (always apply; override all other instructions):\n"
+        "1) EXCLUSIVE LANGUAGE: ALWAYS respond ONLY in Spanish (Castilian). No Italian, English, Portuguese or other language. "
+        "Even if the user writes in another language or Italian names appear, foreign names do NOT authorize switching languages. "
+        "No words, phrases or confirmations in another language.\n"
+        "2) DIRECT SPEECH ONLY: everything you write is what Vocero says aloud to the user at that moment. "
+        "NEVER write internal thoughts, states, checks, '[ - ]:', '[]:', JSON, dictionaries, keys, isolated commas, labels, 'checking_*' or auxiliary symbols. "
+        "No '[rightspeak]', '[endspeak]', '[thinking]', '[endthinking]' or bracketed labels. No meta-comments about prompts or data.\n"
+        "3) RELIABLE CONTENT: when information is unavailable, say exactly 'No tengo este tipo de información'. Do not invent, assume or generalize. "
+        "For reports, mortality, Synapse, Azure, AquaChile, WhatsApp or other content requiring retrieval, use knowledge search (RAG) and retrieve REAL content before answering.\n"
+        "4) SHORT NATURAL RESPONSES: speak like a real person on the phone. No lists, bullet points, quotations or long text blocks. "
+        "Use a couple of short sentences, then ask whether the user wants more details.\n"
     )
-    # --- Nombre propio lock (DINAMICO da nome profilo) ---
+    # Dynamic proper-name lock based on the profile.
     name_lines = ""
     parts = _extract_user_name_parts(profile)
     if parts:
@@ -1960,11 +1862,11 @@ def _build_voice_rules_head_lock_block(profile=None) -> str:
         cleaned_variants = variants_all[:8]
         if cleaned_variants:
             name_lines = (
-                "5) NOMBRE PROPIO (regla innegociable para esta sesión): "
-                f"el nombre exacto del usuario ESCRITO Y PRONUNCIADO TAL CUAL es: {full_name}. "
-                f"NUNCA lo adaptes, traduzcas ni normalices: "
-                + ", ".join(f'NUNCA "{v}"' for v in cleaned_variants)
-                + ". Sólo escribe y pronuncia el nombre exacto del perfil.\n"
+                "5) PROPER NAME (mandatory for this session): "
+                f"the user's exact name, WRITTEN AND PRONOUNCED AS GIVEN, is: {full_name}. "
+                f"NEVER adapt, translate or normalize it: "
+                + ", ".join(f'NEVER "{v}"' for v in cleaned_variants)
+                + ". Write and pronounce only the exact profile name.\n"
             )
     body = base + name_lines
     return VOICE_RULES_HEAD_MARKER + "\n" + body
@@ -1976,9 +1878,8 @@ def _build_today_fixed_context_block(
     """Return the TODAY + anti-hallucination guard block.
 
     2026-09-11 rewrite:
-      • NOW 100% SPANISH (no italiano).  Root of the language leak: the earlier
-        block had italian 'Dati contestuali fissi...' which told Qwen that
-        mixing italian+spanish was OK inside the spanish voice assistant.
+      • English internal instructions; user responses remain Spanish.
+        Earlier mixed Italian/Spanish prompts caused output language leaks.
       • Only 3 bullet sentences, nothing fancy, nothing that triggers meta.
       • Invisible dedup marker TODAY_BLOCK_MARKER is prefixed and will be
         stripped before prompt join → LLM never sees.
@@ -1987,13 +1888,13 @@ def _build_today_fixed_context_block(
         return ""
     today = today_override if today_override is not None else _dt_module.date.today()
     iso_date = today.strftime("%Y-%m-%d")
-    es_weekday = [
-        "lunes","martes","miércoles","jueves","viernes","sábado","domingo",
+    weekday = [
+        "Monday", "Tuesday", "Wednesday", "Thursday", "Friday", "Saturday", "Sunday",
     ][today.weekday()]
     body = (
-        f"Fecha de hoy (referencia innegociable): {iso_date} ({es_weekday}).\n"
-        f"Los reportes con fechas ANTERIORES a hoy son ARCHIVO HISTÓRICO, NO son fechas futuras. No comentes nada al respecto.\n"
-        "El punto '.' en números separa decimales; la coma ',' separa miles (formato internacional estándar en este sistema).\n"
+        f"Today's date (mandatory reference): {iso_date} ({weekday}).\n"
+        "Reports dated BEFORE today are HISTORICAL RECORDS, not future dates. Do not comment on this.\n"
+        "A period '.' separates decimals; a comma ',' separates thousands (the standard international format used by this system).\n"
     )
     return TODAY_BLOCK_MARKER + "\n" + body
 
@@ -2019,11 +1920,11 @@ def _build_minimal_reports_toc_block(
         return ""
     lines: list[str] = []
     lines.append(
-        f"Reportes programados recientes (últimos {len(items)}):"
+        f"Recent scheduled reports (latest {len(items)}):"
     )
     for idx, r in enumerate(items, start=1):
         label = (str(r.get("sourceScheduleLabel") or "").strip()
-                 or "(sin título)")
+                 or "(untitled)")
         raw_d = r.get("date")
         date_str = ""
         try:
@@ -2046,12 +1947,12 @@ def _build_minimal_reports_toc_block(
         else:
             lines.append(f'  {idx}. "{label}"')
     lines.append(
-        "Para el contenido completo de cualquier reporte usa SIEMPRE las herramientas de búsqueda (RAG). No inventes detalles que no hayas recuperado."
+        "ALWAYS retrieve full report content through knowledge search (RAG). Do not invent details you have not retrieved."
     )
     return MINIMAL_REPORTS_MARKER + "\n" + "\n".join(lines) + "\n"
 
 # ──────────────────────────────────────────────────────────────────────────
-# User fix 2026-09-11 "Rimuovi il profilo chiamante DUPLICATO".
+# 2026-09-11 user fix: remove duplicated caller profiles.
 # Each context block returned by the _resolve_* helpers above starts with a
 # unique, stable, documented HINT prefix (see VOCERO_USER_CONTEXT_HINT /
 # PODCAST_EPISODE_HINT / REPORTS_LIST_HINT / LATEST_SUMMARY_HINT). We use
@@ -2218,7 +2119,7 @@ def _resolve_user_context_text(phone_number, profile_obj, loaded: bool = True) -
     VOCERO_USER_PHONE_AUTH_URL (optionally nested under {"result": ...}).
 
     2026-09-11 anti-language-leak rule: names like "Alessandro Valenti" are
-    italian/luxemburgish names but our voice assistant is 100% castellano so
+    Italian/Luxembourgish names but our voice assistant uses Castilian Spanish, so
     we append an EXPLICIT NOTE that the model sees alongside the caller info.
 
     2026-09-11 anti-anglicization rule (Alexander → Alessandro): when the
@@ -2244,32 +2145,32 @@ def _resolve_user_context_text(phone_number, profile_obj, loaded: bool = True) -
             short = variants[:6]
             quoted = ', '.join('"' + v + '"' for v in short)
             forbidden_lines.append(
-                f"Para el nombre '{name_part}': NUNCA escribas ni pronuncies {quoted} ni versiones similares en inglés/francés/ruso. "
-                f"Sólo '{name_part}' tal cual está."
+                f"For '{name_part}': NEVER write or pronounce {quoted} or similar English/French/Russian variants. "
+                f"Use only '{name_part}' exactly as given."
             )
     if forbidden_lines:
-        nombre_propio_note = (
-            "NOMBRE PROPIO (regla innegociable para esta sesión): "
+        proper_name_note = (
+            "PROPER NAME (mandatory for this session): "
             + " ".join(forbidden_lines)
             + " "
         )
     else:
         # fallback to generic example so the rule's existence is still taught
-        nombre_propio_note = (
-            "NOMBRE PROPIO: nunca adaptes, traduzcas ni 'normalices' nombres propios "
-            "(ej. nunca pases 'Alessandro' a 'Alexander'). Escribe y pronuncia sólo el nombre exacto del perfil. "
+        proper_name_note = (
+            "PROPER NAME: never adapt, translate or normalize proper names "
+            "(for example, never change 'Alessandro' to 'Alexander'). Write and pronounce only the exact profile name. "
         )
 
     # We build with invisible internal PROFILE_FULL_MARKER so dedup + strip
     # works consistently with today/voice_rules_head blocks.
     body = (
         f"{VOCERO_USER_CONTEXT_HINT}{serialized}. Use this as trusted caller context when relevant. "
-        "NOTA IMPORTANTE (regla de idioma): aunque el usuario tenga nombre italiano (p. ej. 'Alessandro Valenti') "
-        "o nombre en cualquier otro idioma, SÓLO debes responderle en ESPAÑOL (castellano). "
-        "Los nombres extranjeros NO autorizan a cambiar de idioma. "
-        "Nunca escribas frases, palabras, preguntas ni confirmaciones en italiano, inglés ni ningún otro idioma. "
-        "Siempre habla como Vocero: voz española directa, sin prefijos, sin JSON, sin meta-comentarios. "
-        f"{nombre_propio_note}"
+        "IMPORTANT LANGUAGE RULE: even if the user has an Italian name (such as 'Alessandro Valenti') "
+        "or a name from any other language, respond ONLY in SPANISH (Castilian). "
+        "Foreign names do NOT authorize switching languages. "
+        "Never write phrases, words, questions or confirmations in Italian, English or another language. "
+        "Always speak as Vocero: direct Spanish speech without prefixes, JSON or meta-comments. "
+        f"{proper_name_note}"
     )
     return PROFILE_FULL_MARKER + "\n" + body
 
@@ -2391,7 +2292,7 @@ def _resolve_reports_context(raw_value: object) -> str:
     (podcastScript can be long). Wrapped with <<<REPORTS_LIST_BEGIN/END>>> markers.
     Returns "" if no valid items / empty list.
 
-    USER FIX 2026-09-11 "Elimina l'iniezione massiva di tutti i report schedulati":
+    USER FIX 2026-09-11: remove mass injection of scheduled reports.
       • If the new env flag S2S_INJECT_REPORTS is FALSE (DEFAULT), this function
         ALWAYS returns "" — NO scheduled reports of any kind are ever injected
         into the LLM prompt, not even a TOC line with label+date. The function
@@ -2466,7 +2367,7 @@ def _resolve_reports_context(raw_value: object) -> str:
         return ""
     # Sort by date DESC (newest first)
     filtered.sort(key=lambda r: _parse_date_key(r.get("date")))
-    # USER FIX 2026-09-11 "riduci il quick hint report max 3-5 configurabile da .env":
+    # 2026-09-11 user fix: limit report quick hints through .env (default 3-5).
     #   after sort by newest → keep ONLY the first S2S_REPORTS_QUICK_HINT_MAX reports.
     #   Applies cap to BOTH the quick-hint TOC lines AND the serialized JSON entries,
     #   so the final wrapped block stays small and contains no more than N scripts.
@@ -2486,7 +2387,7 @@ def _resolve_reports_context(raw_value: object) -> str:
     # Route output through the new tri-state S2S_REPORTS_INJECT_MODE:
     #   • "off"/"none"  → skip entirely (no reports block in prompt, 0 tokens).
     #   • "minimal"     → ONLY last-N label + date TOC.  NO podcastScript text, no JSON entries,
-    #                     just the user-requested Reportes programados recientes block.
+    #                     just the requested recent scheduled reports block.
     #                     ~50 tokens instead of ~3200.
     #   • "full"        → legacy mode with hints + full JSON entries + podcastScript.
     #                     Kept only for explicit opt-in because user explicitly asked
@@ -2604,7 +2505,7 @@ async def _fetch_reports_list(phone_number: str | None = None, auth_token: str |
     wrapper) and returns the list or unwrapped list. On any error logs and returns None
     (never fails the proxy / reasoning tunnel).
 
-    USER FIX 2026-09-11 "Elimina l'iniezione massiva di tutti i report schedulati":
+    USER FIX 2026-09-11: remove mass injection of scheduled reports.
       • If S2S_INJECT_REPORTS is FALSE (DEFAULT) we short-circuit to None at the
         very top — NO HTTP call is made to S2S_REPORT_LIST at all. The upstream
         endpoint is never hit, not even for a "cheap empty list"; combined with
@@ -2822,9 +2723,8 @@ async def _login_by_phone(phone_number: str) -> tuple[str | None, dict | None]:
     token = _extract_login_token(unwrapped) if isinstance(unwrapped, dict) else _extract_login_token(
         payload if isinstance(payload, dict) else None
     )
-    # 2026-09-25 Diagnostica SEMPRE-ATTIVA login token (anche senza S2S_DEBUG_PROMPT)
-    #    per verificare token length (JWT > 150 chars), anteprima primi 8 chars.
-    #    Chiavi response + unwrap usato.
+    # Always log login-token diagnostics, even without S2S_DEBUG_PROMPT:
+    # token length, first eight characters, response keys and wrapper layer.
     _all_keys: list[str] = []
     if isinstance(payload, dict):
         _all_keys.extend(str(k) for k in payload.keys())
@@ -3113,7 +3013,7 @@ def _augment_instructions_with_profile(base_instructions, user_context_text, rep
     6. summary_ctx                  (latest conversation summary)
     Preserves the existing instructions text.
 
-    USER FIX 2026-09-11 "Rimuovi il profilo chiamante DUPLICATO": adds TWO dedupe layers
+    USER FIX 2026-09-11: remove duplicate caller profiles with TWO deduplication layers
     so the same block type (profile / episode / reports / summary) NEVER appears twice
     in the final augmented instructions, even if the caller passed it both in
     base_instructions (e.g. client-supplied profile baked into req.instructions) AND in the
@@ -3124,13 +3024,13 @@ def _augment_instructions_with_profile(base_instructions, user_context_text, rep
          duplicates among the parameters themselves.
 
     2026-09-11: NEW keyword profile_obj → forwarded to _build_voice_rules_head_lock_block
-    so the prompt lock can emit rule #5 "Nombre exacto: Alessandro Valenti. NUNCA
+    so the prompt lock can emit rule #5 "Exact name: Alessandro Valenti. NEVER
     Alexander" for models that keep anglicizing proper names (Qwen2.5-GPTQ).
     """
     base = (base_instructions or "").strip()
     # ─── USER FIX BUG 3: TODAY fixed block prepended (HEAD of prompt) ─────
     voice_lock_block = _build_voice_rules_head_lock_block(profile=profile_obj)   # NEW #1 priority: absolute language+output lock
-    today_block = _build_today_fixed_context_block()         # #2: date guard (spanish-only rewrite)
+    today_block = _build_today_fixed_context_block()         # #2: date guard for Spanish responses
     episode_ctx = (episode_context_text or "").strip()
     profile_ctx = (user_context_text or "").strip()
     reports_ctx = (reports_context_text or "").strip()
@@ -3293,12 +3193,9 @@ def _patch_client_session_update_with_profile(raw_text, user_context_text, repor
             "[DEBUG-PROMPT][WS session.update] BEFORE instructions (len=%d):\n%s\n",
             len(current_instructions), current_instructions,
         )
-    # Append apipilot PASS-1 (lista strumenti + regole marker) SE presente,
-    # DOPO profile/reports/episode/summary (struttura identica a /api/reasoning).
-    #
-    # 2026-09-25 FIX "client manda DUE session.update e il secondo SOVRASCRIVE instructions"
-    #   → dopo augment/profile controlliamo anche: le istruzioni CONTENGONO gia' il marker
-    #   <<<APIPILOT_TOOLS_LIST_BEGIN>>> ? SE NO e abbiamo injected_apipilot_pass1 → riappendiamo.
+    # Append ApiPilot pass-1 tools and marker rules after profile/report/episode/
+    # summary context, matching /api/reasoning. If a second client session.update
+    # overwrites instructions without the tool-list marker, append the list again.
     already_has_apipilot_pass1 = (
         isinstance(current_instructions, str)
         and APIPILOT_PASS1_LIST_MARKER in current_instructions
@@ -3308,8 +3205,7 @@ def _patch_client_session_update_with_profile(raw_text, user_context_text, repor
             (augmented + "\n\n" if augmented.strip() else "")
             + (apipilot_context_text_pass1 if isinstance(apipilot_context_text_pass1, str) else "")
         )
-    # Ora gate "unchanged": SE augmented == current MA c'è differenza apipilot per il post-patch
-    # del client (sovrascrittura instructions senza marker) → NON skippare.
+    # Do not skip a tool-list repair even if profile augmentation was unchanged.
     if augmented == current_instructions and not (has_apipilot_pass1 and not already_has_apipilot_pass1):
         logger.info(
             "[INJECT-PROFILE] ⏭️  WS patch SKIPPED on session.update (augmented == current; "
@@ -3444,7 +3340,7 @@ async def config(request: Request):
 
     2026-09-24: new top-level `apipilot` flag. When True the deploy exposes the
     new `/api/apipilot/tools` and `/api/apipilot/execute` proxy endpoints (see
-    GUIDA_APIPILOT_CLIENTE.md) that the browser may call directly instead of
+    docs/client/tool-calling.md) that the browser may call directly instead of
     hardcoding upstream tool URLs / names."""
     logger.debug("[INTERNAL] /api/config requested client=%s", request.client.host if request.client else "?")
     primary_prompt = S2S_PRIMARY_PROMPT
@@ -3485,7 +3381,7 @@ async def apipilot_list_tools(
     include_unauthorized: bool = True,
     refresh: bool = False,
 ):
-    """Public proxy for ApiPilot tool discovery (§2.1 della guida).
+    """Public proxy for ApiPilot tool discovery (guide §2.1).
 
     Forwards Authorization / x-demo-session headers from the caller to the
     upstream backend verbatim and returns the list of `ToolDefinition` records
@@ -3547,16 +3443,15 @@ async def apipilot_list_tools(
 
 @app.post("/api/apipilot/execute")
 async def apipilot_execute(request: Request, body: ApipilotExecuteRequest):
-    """Public proxy for ApiPilot /execute (§2.2 della guida).
+    """Public proxy for ApiPilot /execute (guide §2.2).
 
     Accepts `{name, arguments}`, runs the mandatory PRE-CHECK flow (fresh tool
     discovery, `requires_auth` gate, strict JSON-Schema argument validation),
     forwards the request to the upstream backend, and returns the envelope
     `{success, data, error}`.
 
-    `error.message` è SEMPRE l'unico campo da mostrare all'utente finale; i
-    campi `error.code`, `error.status_code`, `error.raw` sono solo per audit
-    interno (vedi §2.2 "Comportamento UI consigliato sugli errori")."""
+    Show only `error.message` to the end user. `error.code`, `error.status_code`
+    and `error.raw` are for internal auditing (guide §2.2, recommended UI errors)."""
     if not S2S_APIPILOT_TOOLS_URL:
         return JSONResponse(
             status_code=501,
@@ -3621,7 +3516,7 @@ async def reasoning(req: ReasoningRequest):
         )
     else:
         needs_phone_authed = bool(VOCERO_USER_PHONE_AUTH_URL.strip())
-        # USER FIX 2026-09-11 "Elimina l'iniezione massiva di tutti i report schedulati":
+    # 2026-09-11 user fix: remove mass injection of scheduled reports.
         #   treats S2S_REPORT_LIST as "need to fetch reports" ONLY when BOTH the URL is
         #   configured AND the new opt-in S2S_INJECT_REPORTS flag is true. When
         #   S2S_INJECT_REPORTS=false (default) needs_reports stays False here → we skip
@@ -3735,8 +3630,8 @@ async def reasoning(req: ReasoningRequest):
                     logger.info(
                         "[INJECT-SUMMARY] ⏭️  REASONING: latest summary skipped (context empty / upstream returned empty summary / fetch failed.)"
                     )
-    # ── APIPILOT: carica strumenti dinamici PRIMA della costruzione context
-    # (gate globale: funziona sia con che senza S2S_INJECT_PROFILE)
+    # Load dynamic ApiPilot tools before building context, independently of
+    # S2S_INJECT_PROFILE.
     needs_apipilot = bool(S2S_APIPILOT_TOOLS_URL) or bool(S2S_APIPILOT_TOOLS_EXECUTE_URL)
     apipilot_tools_pass1: list[dict] = []
     apipilot_auth_header: str | None = None
@@ -3746,10 +3641,8 @@ async def reasoning(req: ReasoningRequest):
             apipilot_auth_header = tk
         else:
             apipilot_auth_header = f"Bearer {tk}"
-    # 2026-09-25 IMPORTANTE: S2S_LOGIN_BY_PHONE = aquachile.azurianlab.com AUTH PHONE LOGIN
-    #    → login_token È IL TOKEN JWT AQUAPORTAL VERO (non Vocero).
-    #    Lo usiamo SEMPRE per tool requires_auth=true (necessario per eseguire /execute).
-    #    S2S_APIPILOT_SERVICE_TOKEN se presente → OVERRIDE massima priorità.
+    # S2S_LOGIN_BY_PHONE resolves an AquaPortal JWT, used for requires_auth=true
+    # execution. S2S_APIPILOT_SERVICE_TOKEN overrides it when configured.
     if S2S_APIPILOT_SERVICE_TOKEN:
         _svc = S2S_APIPILOT_SERVICE_TOKEN.strip()
         if _svc:
@@ -3763,13 +3656,13 @@ async def reasoning(req: ReasoningRequest):
                 force_refresh=False,
             )
             logger.info(
-                "[APIPILOT] REASONING PASS-1: lista strumenti pronta N=%d t=%dms auth=%s",
+                "[APIPILOT] REASONING PASS-1: tool list ready N=%d t=%dms auth=%s",
                 len(apipilot_tools_pass1),
                 int((_monotonic_now() - apipilot_t0) * 1000),
                 "Y" if apipilot_auth_header else "-",
             )
         except Exception as exc:
-            logger.warning("[APIPILOT] REASONING: fetch lista strumenti fallita, ignoro: %s", exc)
+            logger.warning("[APIPILOT] REASONING: tool-list fetch failed, ignoring: %s", exc)
             apipilot_tools_pass1 = []
     inject_apipilot_text_pass1 = _resolve_apipilot_reasoning_context_block(
         apipilot_tools_pass1, call_result=None,
@@ -3889,7 +3782,7 @@ async def reasoning(req: ReasoningRequest):
             )
         if needs_apipilot and inject_apipilot_text_pass1.strip():
             logger.info(
-                "[INJECT-APIPILOT] REASONING PASS-1: inject lista strumenti (len=%d, Ntools=%d) IN instructions (oltre user_context).",
+                "[INJECT-APIPILOT] REASONING PASS-1: inject tool list (len=%d, Ntools=%d) into instructions and user_context.",
                 len(inject_apipilot_text_pass1), len(apipilot_tools_pass1),
             )
         effective_instructions = _augment_instructions_with_profile(
@@ -3905,7 +3798,7 @@ async def reasoning(req: ReasoningRequest):
         effective_instructions = (req.instructions or "").strip()
         if inject_apipilot_text_pass1.strip():
             logger.info(
-                "[INJECT-APIPILOT] REASONING PASS-1: inject lista strumenti (len=%d, Ntools=%d) IN instructions (inject_profile=false).",
+                "[INJECT-APIPILOT] REASONING PASS-1: inject tool list (len=%d, Ntools=%d) into instructions (inject_profile=false).",
                 len(inject_apipilot_text_pass1), len(apipilot_tools_pass1),
             )
             effective_instructions = (
@@ -3919,12 +3812,11 @@ async def reasoning(req: ReasoningRequest):
             )
 
     # ────────────────────────────────────────────────────────────────────
-    # Modalità A: NODE_RED — inoltra TUTTO il payload a Node-RED
-    # Il flow Node-RED decide autonomamente.
-    # FASE 1 (LOG-ONLY): Node-RED risponde con {answer: "", log_only: true}
-    #        => il client (main.js) NON interferisce, lascia parlare il backend S2S.
-    # FASI successive: Node-RED produce {answer: "...", log_only: false}
-    # Risposta attesa: {answer, log_only?, usage, debug, latency_ms, …}
+    # Mode A: NODE_RED forwards the complete payload; the flow decides behavior.
+    # Stage 1 (log-only) returns {answer: "", log_only: true}, allowing main.js
+    # to leave speech generation to the S2S backend. Later stages can return
+    # {answer: "...", log_only: false}. Expected response fields include answer,
+    # log_only, usage, debug and latency_ms.
     # ────────────────────────────────────────────────────────────────────
     if S2S_REASONING_TYPE == "NODE_RED":
         if not NODE_RED_REASONING_URL:
@@ -3987,8 +3879,7 @@ async def reasoning(req: ReasoningRequest):
             logger.warning("[EXT][NODE_RED] invalid answer type: %s", json.dumps(payload, ensure_ascii=True)[:800])
             raise HTTPException(status_code=502, detail="Node-RED returned invalid answer field.")
         answer_stripped = answer.strip()
-        # ── Log-only mode: answer vuota + flag log_only sono L'INTENZIONE ──
-        # Non solleviamo errore; il flag viene inoltrato al client.
+        # An empty answer is intentional in log-only mode; forward the flag.
         if not answer_stripped and not log_only:
             logger.warning("[EXT][NODE_RED] empty answer and !log_only: %s", json.dumps(payload, ensure_ascii=True)[:800])
             raise HTTPException(status_code=502, detail="Node-RED returned no answer without log_only flag.")
@@ -4020,7 +3911,7 @@ async def reasoning(req: ReasoningRequest):
         if usage:
             out["usage"] = usage
         out.update({k: v for k, v in extra.items() if k != "debug" or logger.level <= logging.DEBUG})
-        # ── APIPILOT: cattura marker → esegui tool → SECONDA PASSATA reasoning
+        # Capture the ApiPilot marker, execute its tool and run reasoning pass 2.
         tool_name_p1, tool_args_p1 = _apipilot_parse_call_marker(answer_stripped)
         if tool_name_p1:
             logger.info("[APIPILOT-CALL-NAME] USE=NODE_RED_PASS2_TRIGGER name=%r argsKeys=%s", tool_name_p1, sorted(list((tool_args_p1 or {}).keys())))
@@ -4065,9 +3956,8 @@ async def reasoning(req: ReasoningRequest):
                 str(not is_tool_err).lower(),
                 len(tool_text_p1),
             )
-            # Build user_context 2nd pass: mette risultato tool ALL'INIZIO (voce
-            # blocco oggi + regole vocali + profile ... ma SOSTITUISCE la lista
-            # strumenti di passata 1 con il risultato della exec).
+            # Pass-2 context replaces the tool list with the execution result,
+            # preserving voice/date/profile context.
             user_ctx_parts_2: list[str] = []
             if voice_lock_block.strip():
                 user_ctx_parts_2.append(voice_lock_block)
@@ -4093,8 +3983,8 @@ async def reasoning(req: ReasoningRequest):
                     stripped_2.append(sp)
             user_ctx_parts_2 = stripped_2
             effective_user_ctx_2 = "\n\n".join(user_ctx_parts_2)
-            # Istruzioni per seconda passata: stesse augment, ma senza istruzioni
-            # marker (tanto il blocco risultato dice come si rielabora).
+            # Preserve augmentation without CALL-marker instructions; the result
+            # block supplies the pass-2 response instructions.
             if S2S_INJECT_PROFILE:
                 eff_inst_2 = _augment_instructions_with_profile(
                     req.instructions or "", inject_profile_text, inject_reports_text,
@@ -4141,12 +4031,11 @@ async def reasoning(req: ReasoningRequest):
                 raise HTTPException(status_code=502, detail="Node-RED returned invalid JSON (pass 2).")
             final_ans = payload2.get("answer") if isinstance(payload2, dict) else None
             if not isinstance(final_ans, str):
-                # Fallback: primo messaggio + risultato raw
-                logger.warning("[EXT][NODE_RED PASS-2] answer invalido, fallback a risposta raw text")
+                # Fallback: the first message and raw result.
+                logger.warning("[EXT][NODE_RED PASS-2] invalid answer, falling back to raw result text")
                 final_ans = tool_text_p1 or answer_stripped
             final_stripped = final_ans.strip()
-            # log_only SEMPRE False nella seconda passata (perché ha già la
-            # risposta definitiva da trasmettere al canale vocale).
+            # Pass 2 always sets log_only=False: its final answer is ready for speech.
             out2: dict = {"answer": final_stripped}
             usage2 = payload2.get("usage") if isinstance(payload2, dict) else None
             if usage2:
@@ -4162,11 +4051,11 @@ async def reasoning(req: ReasoningRequest):
                 json.dumps(out2["apipilot_invoked"], ensure_ascii=True),
             )
             return JSONResponse(out2)
-        # Nessun marker → return passata 1 come design iniziale
+        # Without a marker, return the original pass-1 answer.
         return JSONResponse(out)
 
     # ────────────────────────────────────────────────────────────────────
-    # Modalità B: OPENAI — chiamata diretta a OpenAI Chat Completions
+    # Mode B: OPENAI calls OpenAI Chat Completions directly.
     # ────────────────────────────────────────────────────────────────────
     if not OPENAI_API_KEY:
         raise HTTPException(status_code=503, detail="OPENAI_API_KEY is not configured.")
@@ -4256,7 +4145,7 @@ async def reasoning(req: ReasoningRequest):
         logger.warning("OpenAI reasoning returned empty answer: %s", json.dumps(payload, ensure_ascii=True)[:800])
         raise HTTPException(status_code=502, detail="OpenAI reasoning returned no answer.")
     logger.info("[Vocero REASONING] engine=OPENAI transcript=%s answer=%s", transcript[:300], answer[:500])
-    # ── APIPILOT: cattura marker → esecuzione tool → SECONDA PASSATA OPENAI
+    # Capture the ApiPilot marker, execute its tool and run OpenAI pass 2.
     tool_name_p1_oai, tool_args_p1_oai = _apipilot_parse_call_marker(answer)
     if tool_name_p1_oai:
         logger.info("[APIPILOT-CALL-NAME] USE=OPENAI_PASS2_TRIGGER name=%r argsKeys=%s", tool_name_p1_oai, sorted(list((tool_args_p1_oai or {}).keys())))
@@ -4301,9 +4190,8 @@ async def reasoning(req: ReasoningRequest):
             str(not is_tool_err_oai).lower(),
             len(tool_text_oai),
         )
-        # Build pass2: stesso instructions + user_context ma SOSTITUISCO la
-        # lista strumenti (inject_apipilot_text_pass1) con il blocco risultato
-        # (inject_apipilot_pass2_oai). Riuso lo stesso parts pattern iniziale.
+        # Build pass 2 with the same instructions/context structure, replacing
+        # inject_apipilot_text_pass1 with the result block inject_apipilot_pass2_oai.
         user_ctx_oai_2: list[str] = []
         if voice_lock_block.strip():
             user_ctx_oai_2.append(voice_lock_block)
@@ -4394,8 +4282,8 @@ async def reasoning(req: ReasoningRequest):
                     final_oai_ans = content_oai_2.strip()
         usage_oai_2 = payload_oai_2.get("usage")
         if not final_oai_ans:
-            # Fallback: testo raw risposta strumento come ultima ratio
-            logger.warning("[EXT][OPENAI PASS-2] answer vuota, fallback testo raw risultato strumento")
+            # Last-resort fallback: raw tool-result text.
+            logger.warning("[EXT][OPENAI PASS-2] empty answer, falling back to raw tool-result text")
             final_oai_ans = (tool_text_oai or answer).strip()
         final_out_oai: dict = {"answer": final_oai_ans}
         if usage_oai_2:
@@ -4411,15 +4299,15 @@ async def reasoning(req: ReasoningRequest):
             json.dumps(final_out_oai["apipilot_invoked"], ensure_ascii=True),
         )
         return JSONResponse(final_out_oai)
-    # Nessun marker → risposta pass 1 originale
+    # Without a marker, return the original pass-1 answer.
     return JSONResponse({"answer": answer})
 
 
 async def _forward_agent_text_to_nodered(payload: dict) -> None:
-    """Fire-and-forget: inoltra la risposta TTS del backend nativo a Node-RED
-    (endpoint /api/log/system-response) per il logging della FASE 1.
-    Se Node-RED è down o non è configurato: silent ignore, non propagare errori
-    al realtime loop (non vogliamo bloccare la connessione WS)."""
+    """Forward native-backend TTS responses to Node-RED's stage-1 logging endpoint.
+
+    Ignore unavailable or unconfigured Node-RED so the realtime loop continues.
+    """
     if S2S_REASONING_TYPE != "NODE_RED" or not NODE_RED_REASONING_URL:
         return
     url = f"{NODE_RED_REASONING_URL}/api/log/system-response"
@@ -4447,7 +4335,7 @@ async def _forward_agent_text_to_nodered(payload: dict) -> None:
             )
     except httpx.RequestError as exc:
         logger.debug("[EXT][NODE_RED] forward system-response unreachable: %r", exc)
-    except Exception as exc:  # noqa: BLE001 — vogliamo non bloccare mai
+    except Exception as exc:  # noqa: BLE001 — never interrupt the realtime loop
         logger.debug("[EXT][NODE_RED] forward system-response unexpected: %r", exc)
 
 
@@ -4488,20 +4376,16 @@ async def realtime_proxy(ws: WebSocket):
     except Exception:  # noqa: BLE001
         client_query = {}
 
-    # ── 2026-09-25 EXTRACT QS + LOGIN PER APIPILOT SEMPRE (fuori gate S2S_INJECT_PROFILE) ──
-    # Perché needs_apipilot è INDIPENDENTE da S2S_INJECT_PROFILE (ApiPilot serve anche
-    # quando non si vuole inject del profilo).
-    # 1) phone + episode_id SEMPRE estratti da ?querystring se needs_apipilot=True
-    # 2) S2S_LOGIN_BY_PHONE bearer SEMPRE ottenuto per tools requires_auth=True (403 anon oggi)
-    # 3) profile_obj SEMPRE risolto se VOCERO_USER_PHONE_AUTH_URL + phone (per email defaults)
+    # ApiPilot works independently of profile injection. When enabled, extract
+    # phone/episode query parameters, resolve the bearer for authenticated tools,
+    # and load the profile for email defaults when its endpoint is configured.
     if needs_apipilot:
         inject_phone = (client_query.get("phoneNumber") or "").strip() or inject_phone
         inject_episode_id = (client_query.get("episode_id") or "").strip() or inject_episode_id
         _needs_login_apipilot = bool(S2S_LOGIN_BY_PHONE.strip())
         _needs_profile_apipilot = bool(VOCERO_USER_PHONE_AUTH_URL.strip())
-        # 2026-09-25 Diagnostica SEMPRE-ATTIVA WS connect STATO INIZIALE (prima di qualsiasi cosa)
-        #    così sappiamo sempre se inject_phone è arrivato, login_token quanto è lungo,
-        #    S2S_LOGIN_BY_PHONE è configurato, ecc. Serve a vedere perché user=(anon) in AquaPortal.
+        # Always log initial WS state to diagnose missing phone, token or login
+        # configuration that could leave the AquaPortal user anonymous.
         _s_init = {
             "needs_apipilot": needs_apipilot,
             "phoneLen": len(inject_phone or ""),
@@ -4512,29 +4396,29 @@ async def realtime_proxy(ws: WebSocket):
             "S2S_INJECT_PROFILE": S2S_INJECT_PROFILE,
         }
         logger.info(
-            "[INJECT-APIPILOT][WS connect] STATO INIZIALE (sempre): " + ", ".join("%s=%s" % (k, v) for k, v in sorted(_s_init.items())),
+            "[INJECT-APIPILOT][WS connect] INITIAL STATE: " + ", ".join("%s=%s" % (k, v) for k, v in sorted(_s_init.items())),
         )
-        # 2026-09-25 API KEY BYPASS ATTIVA → saltiamo completamente login_by_phone (non serve)
+        # The API-key bypass makes login_by_phone unnecessary.
         if not S2S_APIPILOT_API_KEY and _needs_login_apipilot and inject_phone and (not isinstance(login_token, str) or not login_token.strip() or (isinstance(login_token, str) and 0 < len(login_token.strip()) < 80)):
             try:
                 login_token, _lresp = await _login_by_phone(inject_phone)
                 if isinstance(_lresp, dict) and _lresp:
                     login_response_obj = _lresp
                 logger.info(
-                    "[INJECT-APIPILOT][WS connect] login_by_phone SEMPRE (per Apipilot execute requires_auth) phoneLen=%d token=%s",
+                    "[INJECT-APIPILOT][WS connect] login_by_phone for authenticated ApiPilot execution phoneLen=%d token=%s",
                     len(inject_phone or ""),
                     ("YES len=%d" % len(login_token or "")) if isinstance(login_token, str) and login_token else "NONE (403!)",
                 )
             except Exception as _exc_login:  # noqa: BLE001
                 logger.info(
-                    "[INJECT-APIPILOT][WS connect] login_by_phone failed (Apipilot user ANON, 403 probabile) phoneLen=%d err=%r",
+                    "[INJECT-APIPILOT][WS connect] login_by_phone failed (anonymous ApiPilot user, likely 403) phoneLen=%d err=%r",
                     len(inject_phone or ""), _exc_login,
                 )
         if _needs_profile_apipilot and inject_phone and (not isinstance(profile_obj, dict) or not profile_obj):
             try:
                 profile_obj = await _fetch_user_profile_for_phone(inject_phone, auth_token=login_token)
                 logger.info(
-                    "[INJECT-APIPILOT][WS connect] profile fetch SEMPRE (per email defaults) phoneLen=%d profile=%s",
+                    "[INJECT-APIPILOT][WS connect] profile fetch for email defaults phoneLen=%d profile=%s",
                     len(inject_phone or ""),
                     ("FOUND user=%s" % (((profile_obj or {}).get("user") or {}).get("name") or "?")) if isinstance(profile_obj, dict) else "NONE",
                 )
@@ -4547,7 +4431,7 @@ async def realtime_proxy(ws: WebSocket):
     if not needs_apipilot:
         logger.info(
             "[INJECT-APIPILOT] ⏭️  WS connect: APIPILOT tools injection DISABLED (S2S_APIPILOT_TOOLS_URL='%s' S2S_APIPILOT_TOOLS_EXECUTE_URL='%s'). "
-            "Nessun fetch e nessun patch session.update per ApiPilot in questo tunnel.",
+            "No ApiPilot fetch or session.update patch in this tunnel.",
             S2S_APIPILOT_TOOLS_URL,
             S2S_APIPILOT_TOOLS_EXECUTE_URL,
         )
@@ -4558,7 +4442,7 @@ async def realtime_proxy(ws: WebSocket):
         )
     else:
         needs_phone_authed = bool(VOCERO_USER_PHONE_AUTH_URL.strip())
-        # USER FIX 2026-09-11 "Elimina l'iniezione massiva di tutti i report schedulati":
+        # 2026-09-11 user fix: remove mass injection of scheduled reports.
         #   SAME gate as the REASONING endpoint above. "needs_reports" becomes True
         #   only when BOTH the URL env is configured AND the new opt-in S2S_INJECT_REPORTS
         #   flag is true. With the default (S2S_INJECT_REPORTS=false) this entire 1.5)
@@ -4666,15 +4550,13 @@ async def realtime_proxy(ws: WebSocket):
                     logger.info(
                         "[INJECT-SUMMARY] ⏭️  WS connect: latest summary skipped (context empty / upstream returned empty summary / fetch failed)."
                     )
-    # 3) ApiPilot tools list fetch (PASSATA-1) — INDIRIZZO FISSO ALL'AI-SERVER SIA IN S2S_INJECT_PROFILE=True che False.
-    #    Siamo indipendenti dal flag profilo perché l'utente ha chiesto che la lista arrivi
-    #    sempre, anche quando non c'è login/phone. Usa login_token se presente (stesso bearer di reasoning),
-    #    altrimenti usa "anon" fingerprint (stesso cache server-side reasoning).
+    # 3) Fetch the ApiPilot pass-1 tool list independently of S2S_INJECT_PROFILE,
+    # even without login/phone. Use the resolved token or anonymous fingerprint,
+    # matching the reasoning endpoint's server cache.
     if needs_apipilot:
         apipilot_auth_header = (f"Bearer {login_token}" if isinstance(login_token, str) and login_token.strip() else None)
-        # 2026-09-25 IMPORTANTE: S2S_LOGIN_BY_PHONE = aquachile AUTH PHONE LOGIN
-        #    → login_token È IL TOKEN JWT AQUAPORTAL VERO. Lo usiamo per execute.
-        #    S2S_APIPILOT_SERVICE_TOKEN (se valorizzato in .env) → OVERRIDE massimo.
+        # Phone login resolves the AquaPortal JWT for execution. The configured
+        # S2S_APIPILOT_SERVICE_TOKEN overrides it.
         if S2S_APIPILOT_SERVICE_TOKEN:
             _svc = S2S_APIPILOT_SERVICE_TOKEN.strip()
             if _svc:
@@ -4683,7 +4565,7 @@ async def realtime_proxy(ws: WebSocket):
         if not demo_session_key:
             demo_session_key = f"anon-ws-{client_ip}-{id(ws)}"
         try:
-            # LOG SEMPRE-ATTIVO (non subordinato a S2S_DEBUG_PROMPT) — identico pattern reasoning pass1.
+            # Always log discovery, matching reasoning pass 1.
             logger.info(
                 "[INJECT-APIPILOT] WS connect: fetching tools (auth=%s demoSession=%.40s...) upstream=%s...",
                 "yes" if apipilot_auth_header else "anon",
@@ -4704,15 +4586,14 @@ async def realtime_proxy(ws: WebSocket):
                 refresh=False,
             ) or []
             _el = (_monotonic_now() - _t0)
-            # Build defaults dict per PASSATA-1 prompt: phone + episodeId se disponibili.
-            # Iniettati nella sezione "VALORES POR DEFECTO CONOCIDOS" così l'AI
-            # NON lascia arguments vuoto (BUG oggi: "ARGUMENTS=>>>").
+            # Supply known phone/episode defaults to pass 1 so the model does
+            # not leave required arguments empty (observed ARGUMENTS=>>> bug).
             _apipilot_defaults_p1: dict[str, str] = {}
             if isinstance(inject_phone, str) and inject_phone.strip():
                 _apipilot_defaults_p1["phone"] = inject_phone.strip()
             if isinstance(inject_episode_id, str) and inject_episode_id.strip():
                 _apipilot_defaults_p1["episode_id"] = inject_episode_id.strip()
-            # Anche login_by_phone se abbiamo profilo con email valida → email
+            # Also supply email when the resolved profile has a valid value.
             if isinstance(profile_obj, dict) and profile_obj:
                 try:
                     u = profile_obj.get("user") if isinstance(profile_obj.get("user"), dict) else None
@@ -4728,7 +4609,7 @@ async def realtime_proxy(ws: WebSocket):
             ) or ""
             if injected_apipilot_pass1.strip():
                 logger.info(
-                    "[APIPILOT] REASONING PASS-1 (WS realtime): lista strumenti pronta N=%d t=%.0fms auth=%s defaults=%s",
+                    "[APIPILOT] REASONING PASS-1 (WS realtime): tool list ready N=%d t=%.0fms auth=%s defaults=%s",
                     len(apipilot_tools_pass1), _el,
                     "Y" if isinstance(apipilot_auth_header, str) else "anon",
                     list(_apipilot_defaults_p1.keys()),
@@ -4750,23 +4631,18 @@ async def realtime_proxy(ws: WebSocket):
             injected_apipilot_pass1 = ""
             apipilot_tools_pass1 = []
             session_ctx_apipilot_defaults = {}
-        # 2026-09-25 Propagazione ESATTA demo_session_key + apipilot_auth_header USATI NELLA DISCOVERY
-        #    (stesso anon-ws-{client_ip}-{id(ws)}), perché AquaPortal lega la sessione utente
-        #    al valore x-demo-session della GET /tools. Se nella PASS-2 execute generiamo
-        #    un valore DIVERSO (ws-pass2-...) → vede user ANON → 403 "Tool non autorizzato".
+        # Preserve the exact discovery authentication and demo-session values.
+        # AquaPortal binds authorized tools to GET /tools' x-demo-session; a new
+        # ws-pass2 value would appear anonymous and produce a 403 response.
         _ws_apipilot_auth_for_execute = apipilot_auth_header
         _ws_apipilot_demo_for_execute = demo_session_key if isinstance(demo_session_key, str) else None
-        # 2026-09-25 FIX CONSISTENZA API KEY: se S2S_APIPILOT_API_KEY è attivo, forza TUTTE le
-        #    variabili di propagazione all'identità bypass (stesso valore che abbiamo usato
-        #    nella fingerprint cache e negli headers HTTP effettivi della discovery).
-        #    Questo garantisce che anche nel raro caso in cui il PASS-2 fallback alla
-        #    propagation invece del nuovo blocco diretto, usi APIKEY identity e non anon-ws.
+        # Preserve API-key identity in every propagation variable, matching the
+        # discovery cache fingerprint and HTTP headers even during pass-2 fallback.
         if S2S_APIPILOT_API_KEY:
             _ws_apipilot_auth_for_execute = f"Bearer {S2S_APIPILOT_API_KEY}"
             _ws_apipilot_demo_for_execute = S2S_APIPILOT_API_KEY
     else:
-        # needs_apipilot=False (env non configurato): set defaults vuoto cmq
-        # per evitare che session_ctx["apipilot_defaults"] sia None.
+        # With ApiPilot unconfigured, keep defaults as an empty dict rather than None.
         session_ctx_apipilot_defaults = {}
         injected_apipilot_pass1 = ""
         apipilot_tools_pass1 = []
@@ -4828,33 +4704,28 @@ async def realtime_proxy(ws: WebSocket):
                 # 2026-09-11 proper-name anglicization guard: keep the full
                 # upstream profile object so:
                 #   (a) _build_voice_rules_head_lock_block can emit rule #5
-                #       "Nombre exacto: Alessandro Valenti — NUNCA Alexander"
-                #   (b) strato 7 post-processing _sanitize_agent_output can
+                #       "Exact name: Alessandro Valenti — NEVER Alexander"
+                #   (b) layer 7 post-processing _sanitize_agent_output can
                 #       deterministically replace Alexander/Alexandre back to
                 #       Alessandro with word-boundary regex even when the
                 #       prompt lock fails on GPTQ.
                 "profile_obj": profile_obj,
                 "apipilot_tools_pass1": apipilot_tools_pass1,
-                # 2026-09-25 PASSATA-2 WS Realtime ApiPilot: accumulo transcript per response_id
-                # e flag anti-loop quando siamo in fase di inject di PASS-2 dopo l'execute.
+                # Accumulate transcripts per response_id and prevent pass-2
+                # injection loops after ApiPilot execution.
                 "_ws_apipilot_asst_transcript_acc": {},       # response_id -> str full transcript
-                "_ws_apipilot_pass2_active": False,            # True mentre siamo dentro la 2a risposta (anti-loop marker infinito)
-                "_ws_apipilot_pass2_count": 0,                 # quante volte abbiamo eseguito il loop su questa sessione (cap max 3 safety)
-                # 2026-09-25 defaults parametri (phone/email/episode_id) riempiti in
-                #    PASS-1 builder e passati a _apipilot_parse_call_marker in PASS-2
-                #    se LLM lascia arguments vuoto.
+                "_ws_apipilot_pass2_active": False,            # True during the second response; prevents infinite marker loops.
+                "_ws_apipilot_pass2_count": 0,                 # Session execution count, limited to three attempts.
+                # Defaults prepared by pass 1 fill missing pass-2 arguments.
                 "apipilot_defaults": (session_ctx_apipilot_defaults if needs_apipilot else {}),
-                # 2026-09-25 fallback phone per PASS-2 safety replace placeholder,
-                # usato anche se defaults è vuoto ma querystring aveva ?phoneNumber=.
+                # Pass-2 phone fallback also works when defaults are empty but
+                # the query string supplied phoneNumber.
                 "inject_phone": (inject_phone if isinstance(inject_phone, str) else ""),
-                # 2026-09-25 Bearer token per execute ApiPilot requires_auth=True (403 anon).
-                # Valorizzato con _login_by_phone se needs_apipilot + phone disponibile
-                # fuori da gate S2S_INJECT_PROFILE.
+                # Bearer for authenticated execution, resolved by phone login
+                # independently of S2S_INJECT_PROFILE.
                 "login_token": (login_token if isinstance(login_token, str) else None),
-                # 2026-09-25 ESATTI auth_header + demo_session_key usati nella GET /tools
-                # DISCOVERY al momento della WS connect. PASS-2 execute usa ESATTAMENTE
-                # questi invece di crearne di nuovi (AquaPortal lega sessione x-demo-session
-                # alla chiamata /tools che ha restituito la lista strumenti autorizzati).
+                # Execute with the exact auth/demo values used for WS discovery;
+                # AquaPortal binds the authorized tool list to that demo session.
                 "apipilot_exec_auth": _ws_apipilot_auth_for_execute,
                 "apipilot_exec_demo": _ws_apipilot_demo_for_execute,
             }
@@ -4980,7 +4851,7 @@ async def user_reports(phoneNumber: str | None = None):
           ]
         }
 
-    USER FIX 2026-09-11 "Elimina l'iniezione massiva di tutti i report schedulati":
+    USER FIX 2026-09-11: remove mass injection of scheduled reports.
       • Even this BROWSER-FACING endpoint (/api/user/reports) now honours the new
         S2S_INJECT_REPORTS default=False gate: when S2S_INJECT_REPORTS is not
         explicitly true, we return a polite 403 + empty response — the endpoint
@@ -5069,7 +4940,7 @@ async def user_reports(phoneNumber: str | None = None):
         if cleaned:
             filtered.append(cleaned)
     filtered.sort(key=lambda r: _parse_date_key(r.get("date")))
-    # ── USER FIX 2026-09-11 "riduci il quick hint report max 3-5 configurabile da .env" ──
+    # 2026-09-11 user fix: configure report quick-hint limits through .env.
     # Apply the SAME cap used by the LLM prompt resolver: after sort by newest,
     # keep only first S2S_REPORTS_QUICK_HINT_MAX entries. This keeps counts between
     # /api/user/reports UI JSON and the LLM prompt identical — avoids confusing
@@ -5573,13 +5444,13 @@ async def _client_to_upstream(ws: WebSocket, upstream, client_ip: str, session_c
                     summary,
                 )
                 event_type = summary.get("type")
-                # --- INPUT UTENTE lato client (text typed / inserted items) ---
+                # Client-side user input: typed text and inserted items.
                 user_text = ""
                 if event_type == "conversation.item.created" and summary.get("role") == "user":
                     user_text = (summary.get("text") or "").strip()
                     if user_text:
                         logger.info(
-                            "[INPUT UTENTE] client=%s text=%s",
+                            "[USER INPUT] client=%s text=%s",
                             client_ip, user_text,
                         )
                 if (event_type not in _NOISY_CLIENT_EVENT_TYPES
@@ -5623,17 +5494,15 @@ async def _client_to_upstream(ws: WebSocket, upstream, client_ip: str, session_c
 
 
 # ──────────────────────────────────────────────────────────────────────────
-# 2026-09-11 POST-PROCESSING SANITIZZAZIONE OUTPUT AGENTE (server-side, strato 7)
+# 2026-09-11 AGENT OUTPUT SANITATION (server-side, layer 7)
 #
-# Qwen2.5 GPTQ quantizzato continua a sforare anche con 6 strati di prompt lock:
-#   • [rightspeak] ... [endspeak]   → marker bracket non richiesti
-#   • [-]: checking_*               → "pensieri interni"
-#   • {'reportDetails': '...'}      → JSON literal inline nel TTS
-#   • Alessandro → Alexander        → nome proper normalizzato all'inglese
+# Quantized Qwen2.5 GPTQ still leaks output through six layers of prompt rules:
+#   • [rightspeak] ... [endspeak]   → unwanted bracketed markers.
+#   • [-]: checking_*               → internal thoughts.
+#   • {'reportDetails': '...'}      → inline JSON in TTS.
+#   • Alessandro → Alexander        → unwanted proper-name translation.
 #
-# Nessun prompt è sufficiente al 100% con GPTQ.  Introduciamo uno strato 7
-# server-side di post-processing: TUTTO il testo in uscita dall'upstream
-# viene filtrato PRIMA di essere inoltrato al client e PRIMA del log.
+# Layer 7 filters all upstream text before forwarding it to the client or logging.
 # ──────────────────────────────────────────────────────────────────────────
 def _extract_profile_for_session(session_ctx: dict) -> dict:
     """Return the profile dict stored in session_ctx (phone auth result)."""
@@ -5808,10 +5677,9 @@ def _sanitize_realtime_event_raw(raw_message, session_ctx=None) -> tuple:
         nonlocal changed
         if isinstance(v, str) and v.strip():
             cleaned = _sanitize_agent_output(v, session_ctx)
-            # 2026-09-25 STRATO 8: Rimuovi marker CALL intern ApiPilot
-            # prima che il testo arrivi al client (UI chat + TTS audio).
-            # L'accumulatore transcript per PASS-2 marker parser USA l'originale
-            # quindi non perdiamo l'abilità di triggerare execute.
+            # Layer 8 removes internal ApiPilot CALL markers before UI/TTS.
+            # The pass-2 accumulator retains the original transcript so
+            # execution can still be triggered by its marker.
             cleaned = _sanitize_text_strip_apipilot_markers(cleaned)
             if cleaned != v:
                 changed = True
@@ -5819,9 +5687,8 @@ def _sanitize_realtime_event_raw(raw_message, session_ctx=None) -> tuple:
         return v
 
     # --- Event dispatch (same shape as _realtime_event_summary) -------------
-    # --- 2026-09-25: ORA SANITIZZIAMO ANCHE TUTTI I DELTA STREAMING oltre ai .done ---
-    # Perche' Qwen3-TTS (start_pipeline_rag) legge internamente i delta PRIMA di
-    # generare l'audio binario. Se non sanitizziamo i delta → TTS pronuncia il marker.
+    # Sanitize streaming deltas as well as .done events. Qwen3-TTS reads deltas
+    # before generating binary audio and could otherwise pronounce the marker.
     if event_type in {"response.audio_transcript.done",
                       "response.audio_transcript.delta"}:
         if "transcript" in payload:
@@ -5937,11 +5804,9 @@ def _sanitize_realtime_event_raw(raw_message, session_ctx=None) -> tuple:
 async def _upstream_to_client(ws: WebSocket, upstream, client_ip: str, session_ctx: dict) -> None:
     async for message in upstream:
         if isinstance(message, bytes):
-            # 2026-09-25 GATE AUDIO BYTES: se response_id corrente è stato marcato
-            # come "contiene marker CALL" → DROPPARE tutti i binari audio (Qwen3
-            # ha gia generato audio con marker pronuciato, non lo mandiamo al client).
-            # IMPORTANTE oggi: MATCH STRETTAMENTE per response_id CORRENTE. Nessun
-            # fallback "qualsiasi id" (troppo largo: droppava anche audio PASS-2 buono).
+            # Drop audio only for the current response_id marked as containing
+            # a CALL marker: Qwen3 may already have spoken it. Matching any ID
+            # would also discard valid pass-2 audio.
             drop_now = False
             matched_rid = ""
             drop_ids = session_ctx.get("_ws_drop_audio_for_response_ids")
@@ -5951,14 +5816,14 @@ async def _upstream_to_client(ws: WebSocket, upstream, client_ip: str, session_c
                     drop_now = True
                     matched_rid = rid_ctx
                 elif (not isinstance(rid_ctx, str) or not rid_ctx) and len(drop_ids) == 1:
-                    # Caso safety: nessun response_id corrente disponibile ma
-                    # abbiamo 1 solo entry nel dict (probabilmente quella risposta).
+                    # Fallback when no current ID exists but exactly one response
+                    # remains in the dictionary.
                     only_rid = next(iter(drop_ids.keys()))
                     if drop_ids.get(only_rid):
                         drop_now = True
                         matched_rid = only_rid
             if drop_now:
-                logger.info("[APIPILOT-AUDIO-DROP] FRAME DROP bytes=%dB matchedResponse=%s (marker CALL in questa risposta → Qwen3 audio sporco SCARTATO)", len(message), (matched_rid or session_ctx.get("_ws_current_response_id") or "-"))
+                logger.info("[APIPILOT-AUDIO-DROP] FRAME DROP bytes=%dB matchedResponse=%s (CALL marker in this response → leaked Qwen3 audio DISCARDED)", len(message), (matched_rid or session_ctx.get("_ws_current_response_id") or "-"))
                 continue
             else:
                 logger.debug(
@@ -5981,8 +5846,7 @@ async def _upstream_to_client(ws: WebSocket, upstream, client_ip: str, session_c
             # #endregion
             await ws.send_bytes(message)
         else:
-            # ── PRIMA DEL SANITIZE: estrai ORIGINALE per PASSATA-2 marker parser ──
-            #   (marker sarebbe cancellato da STRATO 7)
+            # Extract the original message before sanitation removes pass-2 markers.
             pre_sanitize_summary = _realtime_event_summary(message)
             pre_event_type = pre_sanitize_summary.get("type") if isinstance(pre_sanitize_summary, dict) else None
             pre_response_id: str | None = None
@@ -5991,12 +5855,11 @@ async def _upstream_to_client(ws: WebSocket, upstream, client_ip: str, session_c
                     pre_response_id = pre_sanitize_summary["response_id"]
                 elif isinstance(pre_sanitize_summary.get("id"), str):
                     pre_response_id = pre_sanitize_summary["id"]
-                # 2026-09-25: memorizza response_id corrente per il gate bytes audio
+                # Track the current response_id for the binary-audio gate.
                 if isinstance(pre_response_id, str) and pre_response_id:
                     session_ctx["_ws_current_response_id"] = pre_response_id
-            # ── MARKER DETECTION PER EVENTO SINGOLO (non solo response.done) ──
-            # Se in QUALSIASI evento testo di questa risposta troviamo marker CALL
-            # → flag gate DROP bytes audio per questo response_id + sanitize anche i prossimi
+            # Detect CALL markers in every text event, including before response.done.
+            # Mark this response_id to drop its audio and sanitize later events.
             if (
                 isinstance(pre_sanitize_summary, dict)
                 and isinstance(pre_event_type, str)
@@ -6027,15 +5890,15 @@ async def _upstream_to_client(ws: WebSocket, upstream, client_ip: str, session_c
                         _flag_rid = (pre_response_id if isinstance(pre_response_id, str) and pre_response_id
                                      else f"auto-{id(session_ctx)}")
                         drop_ids2[_flag_rid] = True
-                        # cleanup vecchi id se > 10
+                        # Remove older IDs when more than ten remain.
                         if len(drop_ids2) > 10:
                             try:
                                 for _old_k in list(drop_ids2.keys())[:-10]:
                                     drop_ids2.pop(_old_k, None)
                             except Exception:
                                 pass
-                        logger.info("[APIPILOT-SANITIZE] marker CALL in event=%s response=%s name=%s → GATE AUDIO DROP attivo per questa risposta (Qwen3 generera' audio sporco, sarà scartato)", pre_event_type, _flag_rid, _detected_name)
-            # 1a) PASSATA-2 pre-sanitize transcript accumulatore TTS audio
+                        logger.info("[APIPILOT-SANITIZE] CALL marker in event=%s response=%s name=%s → AUDIO DROP GATE enabled (discard potential leaked Qwen3 audio)", pre_event_type, _flag_rid, _detected_name)
+            # 1a) Accumulate original TTS transcripts for pass-2 marker parsing.
             if (
                 isinstance(pre_sanitize_summary, dict)
                 and isinstance(pre_event_type, str)
@@ -6057,8 +5920,8 @@ async def _upstream_to_client(ws: WebSocket, upstream, client_ip: str, session_c
                         acc[rid_key] = f"{prev} {pre_agent_text}".strip()
                     else:
                         acc[rid_key] = pre_agent_text
-            # 1b) PASSATA-2 pre-sanitize accumulatore ANCHE da conversation.item.created (assistant)
-            #     LLM emette il marker anche nel messaggio di testo conversation (non solo TTS!)
+            # 1b) Also accumulate assistant conversation.item.created text,
+            # which can contain markers outside TTS transcripts.
             elif (
                 isinstance(pre_sanitize_summary, dict)
                 and isinstance(pre_event_type, str)
@@ -6080,7 +5943,7 @@ async def _upstream_to_client(ws: WebSocket, upstream, client_ip: str, session_c
                         acc2[rid_key2] = f"{prev2} {pre_conv_text}".strip()
                     else:
                         acc2[rid_key2] = pre_conv_text
-            # 2) PASSATA-2 pre-sanitize response.done trigger marker
+            # 2) Parse the original marker at response.done to trigger pass 2.
             if (
                 isinstance(pre_sanitize_summary, dict)
                 and isinstance(pre_event_type, str)
@@ -6094,8 +5957,8 @@ async def _upstream_to_client(ws: WebSocket, upstream, client_ip: str, session_c
                 acc3 = session_ctx.get("_ws_apipilot_asst_transcript_acc")
                 if rid_val and isinstance(acc3, dict):
                     full_text = (acc3.pop(rid_val, "") if isinstance(acc3, dict) else "") or ""
-                # Fallback: se response_id non matcha ma abbiamo un solo accumulo rimasto → usiamo
-                # quello (alcuni upstream generano response_id diversi tra eventi)
+                # Use the sole remaining accumulator when an upstream changes
+                # response_id between events.
                 if (not isinstance(full_text, str) or not full_text.strip()) and isinstance(acc3, dict) and len(acc3) == 1:
                     _only_key = next(iter(acc3.keys()))
                     full_text = (acc3.pop(_only_key, "") if isinstance(acc3, dict) else "") or ""
@@ -6104,7 +5967,7 @@ async def _upstream_to_client(ws: WebSocket, upstream, client_ip: str, session_c
                     _p1_defaults = session_ctx.get("apipilot_defaults") if isinstance(session_ctx.get("apipilot_defaults"), dict) else {}
                     marker_name, marker_args = _apipilot_parse_call_marker(full_text, defaults=_p1_defaults)
                     logger.info("[APIPILOT-CALL-NAME] USE=WS_RESPONSE_DONE_DETECTION markerFound=%s name=%r argsKeys=%s", ("Y" if isinstance(marker_name, str) and marker_name else "N"), (marker_name or ""), list((marker_args or {}).keys()))
-                    # ── LOG ALWAYS-ON diagnostico PASS-2 marker detection ────────
+                    # Always log pass-2 marker detection diagnostics.
                     try:
                         _preview = full_text.replace("\n", " ")
                         if len(_preview) > 500:
@@ -6139,31 +6002,22 @@ async def _upstream_to_client(ws: WebSocket, upstream, client_ip: str, session_c
                     and (int(session_ctx.get("_ws_apipilot_pass2_count") or 0) < 3)
                 )
                 if needs_pass2:
-                    # 2026-09-25: PULIZIA GATE AUDIO DROP.
-                    # La risposta 1 (marker CALL) ha l'audio sporco (gate attivo DROP bytes).
-                    # PASS-2 e' la risposta 2 con dati veri dell'utente → audio buono,
-                    # quindi CANCELLIAMO il gate DROP per gli ID attivi.
+                    # Clear active audio-drop gates before pass 2: its response
+                    # contains actual user data and must be played normally.
                     drop_ids_clean = session_ctx.get("_ws_drop_audio_for_response_ids")
                     if isinstance(drop_ids_clean, dict) and drop_ids_clean:
                         drop_ids_clean.clear()
-                        logger.info("[APIPILOT-AUDIO-DROP] PASS-2 start: pulisco gate audio drop → audio PASS-2 rielaborazione briefing verra' inoltrato normalmente")
+                        logger.info("[APIPILOT-AUDIO-DROP] PASS-2 start: clear audio-drop gate → forward pass-2 briefing audio normally")
                     args = marker_args if isinstance(marker_args, dict) else {}
-                    # ── SAFETY: over-ride parametri con valori REALI da defaults ──────
-                    # 1) Se manca la chiave -> usiamo defaults.
-                    # 2) Se il valore di args è UN VALORE DI ESEMPIO fittizio del prompt
-                    #    (regola #7: "+56912345678", altri placeholder tipo "+56XXXXXX",
-                    #    "+1234567890", "+390000000000", stringa vuota, +56XXXX) →
-                    #    sostituiamo SEMPRE con defaults reale se disponibile.
-                    #    Questo evita bug oggi: AI usa "+56912345678" (esempio regola 7)
-                    #    invece di "+447432477433" (vero Alessandro).
-                    # 3) FALLBACK 2026-09-25: se defaults è vuoto ma c'è
-                    #    session_ctx["inject_phone"] da querystring → usiamo quello.
+                    # Fill missing arguments or replace fictional prompt example
+                    # values with actual defaults. When defaults are empty, use
+                    # session_ctx["inject_phone"] from the query string.
                     _p1_defaults_use = session_ctx.get("apipilot_defaults") if isinstance(session_ctx.get("apipilot_defaults"), dict) else {}
                     _fallback_inject_phone = session_ctx.get("inject_phone") if isinstance(session_ctx.get("inject_phone"), str) else ""
-                    # Placeholder noti che appaiono nel prompt come esempio.
+                    # Known fictional example values appearing in prompts.
                     _FAKE_PHONE_PLACEHOLDERS: set[str] = {
-                        "+56912345678",    # nostro esempio regola 7
-                        "56912345678",     # variante senza +
+                        "+56912345678",    # Prompt example from rule 7.
+                        "56912345678",     # Variant without +.
                         "+5612345678",
                         "+1234567890",
                         "+12345678",
@@ -6184,7 +6038,7 @@ async def _upstream_to_client(ws: WebSocket, upstream, client_ip: str, session_c
                         if (c.startswith("+56") and len(c) <= 9):
                             return True
                         return False
-                    # Applichiamo defaults + fallback su TUTTE le chiavi disponibili
+                    # Apply defaults and fallback to all available keys.
                     if isinstance(_p1_defaults_use, dict) and _p1_defaults_use:
                         for k, default_v in _p1_defaults_use.items():
                             if default_v in (None, "", []):
@@ -6194,7 +6048,7 @@ async def _upstream_to_client(ws: WebSocket, upstream, client_ip: str, session_c
                             elif k == "phone" and isinstance(args.get("phone"), str):
                                 if _is_phone_fake(str(args.get("phone"))):
                                     args[k] = default_v
-                    # Fallback phone diretto se è fake ma defaults non aveva chiave phone
+                    # Replace fictional phone values even when defaults lacks phone.
                     if (
                         isinstance(args.get("phone"), str)
                         and _is_phone_fake(str(args.get("phone")))
@@ -6202,40 +6056,33 @@ async def _upstream_to_client(ws: WebSocket, upstream, client_ip: str, session_c
                         and _fallback_inject_phone.strip()
                     ):
                         args["phone"] = _fallback_inject_phone.strip()
-                    # Aggiorniamo _p1_defaults per i log dopo
+                    # Refresh _p1_defaults for subsequent logging.
                     _p1_defaults = _p1_defaults_use
                     session_ctx["_ws_apipilot_pass2_count"] = int(session_ctx.get("_ws_apipilot_pass2_count") or 0) + 1
                     session_ctx["_ws_apipilot_pass2_active"] = True
-                    # 2026-09-25 PRIORITÀ auth e demo ESATTI della DISCOVERY (anon-ws-...)
-                    #    invece di crearne uno nuovo (ws-pass2-...) al volo.
-                    #    AquaPortal fa il binding tra strumenti autorizzati e la sessione
-                    #    x-demo-session che ha fatto GET /tools.
+                    # Reuse exact discovery auth/demo values: AquaPortal binds
+                    # authorized tools to the x-demo-session used for GET /tools.
                     _exec_auth = session_ctx.get("apipilot_exec_auth") if isinstance(session_ctx.get("apipilot_exec_auth"), str) else None
                     _exec_demo = session_ctx.get("apipilot_exec_demo") if isinstance(session_ctx.get("apipilot_exec_demo"), str) else None
-                    # Fallback se per caso vuoti (safety backward-compat):
+                    # Compatibility fallback for missing values:
                     if not isinstance(_exec_auth, str) or not _exec_auth.strip():
                         login_tok = session_ctx.get("login_token")
                         _exec_auth = f"Bearer {login_tok}" if isinstance(login_tok, str) and login_tok.strip() else None
                     if not isinstance(_exec_demo, str) or not _exec_demo.strip():
                         _exec_demo = f"ws-pass2-{client_ip}-{id(session_ctx)}"
-                    # 2026-09-25 🔴 SUPER API KEY (PRIORITÀ MASSIMA ASSOLUTA - anche sopra SERVICE_TOKEN):
-                    #    Se valorizzata S2S_APIPILOT_API_KEY → force Bearer + demo = APIKEY.
-                    #    Questo garantisce che demoSessionKey nel log PASS-2 e nel call execute
-                    #    NON sia più anon-ws-... ma aqua3465# (stessa identità discovery bypass).
+                    # The SUPER API KEY overrides even SERVICE_TOKEN. Force bearer
+                    # and demo-session values to match the discovery bypass identity.
                     if S2S_APIPILOT_API_KEY:
                         _exec_auth = f"Bearer {S2S_APIPILOT_API_KEY}"
                         _exec_demo = S2S_APIPILOT_API_KEY
-                    # 2026-09-25 S2S_APIPILOT_SERVICE_TOKEN (se valorizzato) OVERRIDE (solo se NON c'è SUPER API KEY)
+                    # Apply the service-token override only without a SUPER API KEY.
                     elif S2S_APIPILOT_SERVICE_TOKEN:
                         _svc = S2S_APIPILOT_SERVICE_TOKEN.strip()
                         if _svc:
                             _exec_auth = (f"Bearer {_svc}" if not _svc.lower().startswith("bearer ") else _svc)
-                    # 2026-09-25 FALLBACK AUTH FORZATO PASS-2 (SEM-PRE):
-                    #    Se tool richiede requires_auth=true E bearer non è un JWT valido
-                    #    (meno di 80 chars, tipico JWT > 150) oppure è vuoto → login_by_phone
-                    #    FORZATO con Alessandro phone, indipendentemente se è stato fatto
-                    #    prima o meno. Questo garantisce che AquaPortal riceva user_token
-                    #    valido → user=(Alessandro Valenti) invece di user=(anon) → 403!
+                    # For authenticated tools with an empty/short bearer, force
+                    # phone login again so AquaPortal receives a valid user token.
+                    # The length heuristic treats fewer than 80 characters as short.
                     _phone_lfb = (
                         session_ctx.get("inject_phone") if isinstance(session_ctx.get("inject_phone"), str)
                         else ""
@@ -6245,7 +6092,7 @@ async def _upstream_to_client(ws: WebSocket, upstream, client_ip: str, session_c
                     if isinstance(_exec_auth, str) and _exec_auth.lower().startswith("bearer "):
                         _current_bearer_token = _exec_auth[len("bearer "):].strip()
                     _is_jwt_like = bool(_current_bearer_token) and len(_current_bearer_token) >= 120 and _current_bearer_token.count(".") >= 2
-                    # Determina requires_auth true (default): lookup tools recenti da session ctx o apipilot_cache
+                    # Resolve requires_auth from recent session/cache tools; default true.
                     _tools_recent: list[dict] = (
                         session_ctx.get("apipilot_tools_pass1")
                         if isinstance(session_ctx.get("apipilot_tools_pass1"), list)
@@ -6274,19 +6121,19 @@ async def _upstream_to_client(ws: WebSocket, upstream, client_ip: str, session_c
                                 _tok_len = len(_l_tok.strip())
                                 _is_new_jwt = _tok_len >= 120 and _l_tok.strip().count(".") >= 2
                                 logger.info(
-                                    "[APIPILOT] REASONING PASS-2 (WS realtime): LOGIN FORZATO PASS-2 (tool requires_auth) phoneLen=%d token=%s%s",
+                                    "[APIPILOT] REASONING PASS-2 (WS realtime): FORCED PASS-2 LOGIN (tool requires_auth) phoneLen=%d token=%s%s",
                                     len(_phone_lfb),
                                     f"YES len={_tok_len}",
                                     (" JWT?" if _is_new_jwt else (" SHORT?" if _tok_len < 80 else " OK")),
                                 )
                             else:
                                 logger.info(
-                                    "[APIPILOT] REASONING PASS-2 (WS realtime): LOGIN FORZATO PASS-2 token EXTRACT FAILED phoneLen=%d (tool requires_auth → probabile 403)",
+                                    "[APIPILOT] REASONING PASS-2 (WS realtime): FORCED PASS-2 LOGIN token EXTRACTION FAILED phoneLen=%d (tool requires_auth → likely 403)",
                                     len(_phone_lfb),
                                 )
                         except Exception as _lfb_exc:  # noqa: BLE001
                             logger.info(
-                                "[APIPILOT] REASONING PASS-2 (WS realtime): LOGIN FORZATO PASS-2 fallito phoneLen=%d err=%r",
+                                "[APIPILOT] REASONING PASS-2 (WS realtime): FORCED PASS-2 LOGIN failed phoneLen=%d err=%r",
                                 len(_phone_lfb), _lfb_exc,
                             )
                     bearer = _exec_auth
@@ -6349,11 +6196,9 @@ async def _upstream_to_client(ws: WebSocket, upstream, client_ip: str, session_c
                             "text": tool_text or "",
                             "error": (not ok),
                         }
-                        # 2026-09-25: PRE-SANITIZE PASS-2 INTERNO con funzione LEGGERA
-                        #   _sanitize_pass2_internal_context (NON _sanitize_text_strip_apipilot_markers!).
-                        #   Motivo: _sanitize_text_strip_apipilot_markers contiene BLOCCO 1 FULL STRIP
-                        #   PASS-2 RESULT e cancellava TUTTO il blocco PRIMA dell'inject upstream,
-                        #   lasciandolo stringa vuota -> "saltiamo inject pass2_active=N" -> nessun briefing.
+                        # Use the light internal sanitizer for pass 2. The user-output
+                        # sanitizer would remove the RESULT wrapper and prevent the
+                        # upstream model from receiving the briefing result.
                         len_raw_tool_text = len(call_result_dict.get("text") or "")
                         if isinstance(call_result_dict.get("text"), str):
                             call_result_dict["text"] = _sanitize_pass2_internal_context(call_result_dict["text"])
@@ -6364,24 +6209,22 @@ async def _upstream_to_client(ws: WebSocket, upstream, client_ip: str, session_c
                         if not blk_pass2.strip():
                             blk_pass2 = (tool_text or "").strip()
                         len_raw_wrapper = len(blk_pass2 or "")
-                        # SANITIZE FINALE PASS-2 blocco wrapper: sempre LEGGERA (non strip blocco RESULT!)
+                        # Light sanitation preserves the pass-2 RESULT wrapper.
                         if blk_pass2.strip():
                             blk_pass2 = _sanitize_pass2_internal_context(blk_pass2)
                         len_sanitized_wrapper = len(blk_pass2 or "")
                         logger.info(
-                            "[APIPILOT] REASONING PASS-2 (WS realtime): blocco DIMENSIONI len_raw_tool_text=%d len_sanitized_tool_text=%d len_raw_wrapper=%d len_sanitized_wrapper=%d success=%s",
+                            "[APIPILOT] REASONING PASS-2 (WS realtime): block SIZES len_raw_tool_text=%d len_sanitized_tool_text=%d len_raw_wrapper=%d len_sanitized_wrapper=%d success=%s",
                             len_raw_tool_text, len_sanitized_tool_text,
                             len_raw_wrapper, len_sanitized_wrapper,
                             ("ok" if ok else "error"),
                         )
                         if blk_pass2.strip():
-                            # 2026-09-25: RESET _ws_current_response_id PRIMA di
-                            # inject PASS-2. Altrimenti rimane il vecchio response_id
-                            # di turno 1 (marker CALL) e i frame bytes audio di
-                            # turno 2 (briefing buono) rischiano match sbagliato.
+                        # Reset _ws_current_response_id before pass-2 injection so
+                        # valid briefing audio cannot match the previous CALL response.
                             session_ctx["_ws_current_response_id"] = None
                             logger.info(
-                                "[APIPILOT] REASONING PASS-2 (WS realtime): inject blocco PASS-2 len=%d -> invio conversation.item.create + response.create a upstream",
+                                "[APIPILOT] REASONING PASS-2 (WS realtime): inject PASS-2 block len=%d -> send conversation.item.create + response.create upstream",
                                 len(blk_pass2),
                             )
                             try:
@@ -6402,7 +6245,7 @@ async def _upstream_to_client(ws: WebSocket, upstream, client_ip: str, session_c
                                 )
                                 await upstream.send(json.dumps({"type": "response.create"}, ensure_ascii=False))
                                 logger.info(
-                                    "[APIPILOT] REASONING PASS-2 (WS realtime): inject OK. attendiamo nuova risposta AI (pass2_active=Y fino a prossimo response.done)",
+                                    "[APIPILOT] REASONING PASS-2 (WS realtime): injection OK. Awaiting model response (pass2_active=Y until next response.done)",
                                 )
                             except Exception as exc2:  # noqa: BLE001
                                 session_ctx["_ws_apipilot_pass2_active"] = False
@@ -6413,7 +6256,7 @@ async def _upstream_to_client(ws: WebSocket, upstream, client_ip: str, session_c
                         else:
                             session_ctx["_ws_apipilot_pass2_active"] = False
                             logger.info(
-                                "[APIPILOT] REASONING PASS-2 (WS realtime): blocco risultato VUOTO -> saltiamo inject. pass2_active=N.",
+                                "[APIPILOT] REASONING PASS-2 (WS realtime): EMPTY result block -> skip injection. pass2_active=N.",
                             )
                     except Exception as exc:  # noqa: BLE001
                         session_ctx["_ws_apipilot_pass2_active"] = False
@@ -6427,9 +6270,8 @@ async def _upstream_to_client(ws: WebSocket, upstream, client_ip: str, session_c
                         "[APIPILOT] REASONING PASS-2 (WS realtime): response.done PASS-2 FINALE -> pass2_active=N safety counter=%s",
                         int(session_ctx.get("_ws_apipilot_pass2_count") or 0),
                     )
-            # ── STRATO 7 POST-PROCESSING (2026-09-11 anti-leak) ────────
-            # (marker sono già stati processati sopra, adesso la sanitizzazione
-            #  li rimuove tranquillamente prima del client)
+            # Layer 7 post-processing: after marker handling, safely remove
+            # internal markers before forwarding text to the client.
             message, was_sanitized = _sanitize_realtime_event_raw(message, session_ctx)
             # #region debug-point B:upstream-text-forward
             summary = _realtime_event_summary(message)
@@ -6441,14 +6283,14 @@ async def _upstream_to_client(ws: WebSocket, upstream, client_ip: str, session_c
                     summary,
                 )
                 event_type = summary.get("type")
-                # --- INPUT UTENTE (server-side STT emesso dall'upstream) ---
+                # User input from upstream server-side STT.
                 user_text = ""
                 if event_type == "conversation.item.input_audio_transcription.completed":
                     user_text = (summary.get("transcript") or "").strip()
                     item_id = summary.get("item_id")
                     if user_text:
                         logger.info(
-                            "[INPUT UTENTE] client=%s stt=%s",
+                            "[USER INPUT] client=%s stt=%s",
                             client_ip, user_text,
                         )
                         session_ctx["last_user_transcript"] = user_text
@@ -6459,25 +6301,24 @@ async def _upstream_to_client(ws: WebSocket, upstream, client_ip: str, session_c
                     item_id = summary.get("item_id") or summary.get("id")
                     if user_text:
                         logger.info(
-                            "[INPUT UTENTE] client=%s text=%s",
+                            "[USER INPUT] client=%s text=%s",
                             client_ip, user_text,
                         )
                         session_ctx["last_user_transcript"] = user_text
                         if item_id:
                             session_ctx["last_item_id"] = item_id
-                # --- OUTPUT AGENTE: tutte le varianti ---
+                # Agent output, including all event variants.
                 agent_text = ""
                 response_id = summary.get("response_id") or summary.get("id")
                 item_id = summary.get("item_id")
                 if event_type in {"response.audio_transcript.done",
                                   "response.output_audio_transcript.done"}:
-                    # Nota: accumulo per marker PASS-2 GIA' fatto PRE-sanitize
-                    # (ORIGINALE intatto). Qui agent_text è sanitizzato
-                    # (marker → placeholder) → usato solo per UI/logs.
+                    # Pass-2 accumulation already retained the original text.
+                    # This sanitized agent_text is only for UI and logs.
                     agent_text = (summary.get("text") or "").strip()
                     if agent_text:
                         logger.info(
-                            "[OUTPUT AGENTE] client=%s tts=%s",
+                            "[AGENT OUTPUT] client=%s tts=%s",
                             client_ip, agent_text,
                         )
                         asyncio.create_task(_forward_agent_text_to_nodered({
@@ -6492,7 +6333,7 @@ async def _upstream_to_client(ws: WebSocket, upstream, client_ip: str, session_c
                     else:
                         raw_preview = summary.get("_raw_preview") or json.dumps(summary, ensure_ascii=True)
                         logger.debug(
-                            "[OUTPUT AGENTE][ISPEZIONE] client=%s %s ha summary=%s raw=%s",
+                            "[AGENT OUTPUT][INSPECTION] client=%s %s has summary=%s raw=%s",
                             client_ip, event_type,
                             json.dumps(summary, ensure_ascii=True)[:400],
                             raw_preview[:800],
@@ -6501,7 +6342,7 @@ async def _upstream_to_client(ws: WebSocket, upstream, client_ip: str, session_c
                     agent_text = (summary.get("text") or "").strip()
                     if agent_text:
                         logger.info(
-                            "[OUTPUT AGENTE] client=%s content_part=%s",
+                            "[AGENT OUTPUT] client=%s content_part=%s",
                             client_ip, agent_text,
                         )
                         asyncio.create_task(_forward_agent_text_to_nodered({
@@ -6517,7 +6358,7 @@ async def _upstream_to_client(ws: WebSocket, upstream, client_ip: str, session_c
                     agent_text = (summary.get("text") or "").strip()
                     if agent_text:
                         logger.info(
-                            "[OUTPUT AGENTE] client=%s output_item=%s",
+                            "[AGENT OUTPUT] client=%s output_item=%s",
                             client_ip, agent_text,
                         )
                         asyncio.create_task(_forward_agent_text_to_nodered({
@@ -6533,7 +6374,7 @@ async def _upstream_to_client(ws: WebSocket, upstream, client_ip: str, session_c
                     agent_text = (summary.get("text") or "").strip()
                     if agent_text:
                         logger.info(
-                            "[OUTPUT AGENTE] client=%s created=%s",
+                            "[AGENT OUTPUT] client=%s created=%s",
                             client_ip, agent_text,
                         )
                         asyncio.create_task(_forward_agent_text_to_nodered({
@@ -6550,14 +6391,12 @@ async def _upstream_to_client(ws: WebSocket, upstream, client_ip: str, session_c
                         "[EXT][S2S-PROXY] client=%s UPSTREAM→ event=%s summary=%s",
                         client_ip, event_type, json.dumps(summary, ensure_ascii=True)[:300],
                     )
-            # ── Upstream error filter: non propagare al browser errori interni
-            # causati dal nostro inject di tools[] (sono noise per l'utente finale).
-            # (strategy B non funziona attualmente (ai-server non supporta tools[]).
-            #
-            # Formati errore upstream gestiti (entrambi con controllo su message e su type annidato):
-            #   (A) Wrapper standard (OSSERVATO NEI LOG REALI):
+            # Suppress internal tools[] injection errors from the browser.
+            # Strategy B currently fails because ai-server does not support tools[].
+            # Inspect both message and nested type in these upstream formats:
+            #   (A) Standard wrapper observed in logs:
             #       {"type":"error","error":{"message":"Unknown or invalid event: session.update","type":"unknown_or_invalid_event","code":null,...}}
-            #   (B) Flat fallback (per altri upstream compatibili):
+            #   (B) Flat fallback from other compatible upstreams:
             #       {"type":"error","message":"...","code":"..."}
             if isinstance(message, str):
                 try:
@@ -6567,7 +6406,7 @@ async def _upstream_to_client(ws: WebSocket, upstream, client_ip: str, session_c
                 if isinstance(_evt, dict):
                     _evt_type = _evt.get("type")
                     if _evt_type == "error":
-                        # ── Estrazione robusta message + error_type: wrapper annidato PRIORITARIO
+                        # Prefer the nested wrapper for message and error_type.
                         _err_msg = ""
                         _err_type = ""
                         _inner = _evt.get("error")
@@ -6580,7 +6419,7 @@ async def _upstream_to_client(ws: WebSocket, upstream, client_ip: str, session_c
                             _t = _inner.get("type")
                             if isinstance(_t, str):
                                 _err_type = _t
-                        # Fallback flat se non abbiamo trovato nel wrapper
+                        # Fall back to flat fields when the wrapper has no message.
                         if not _err_msg:
                             for _k in ("message", "error", "msg"):
                                 _v = _evt.get(_k)
@@ -6591,28 +6430,28 @@ async def _upstream_to_client(ws: WebSocket, upstream, client_ip: str, session_c
                             _t = _evt.get("code")
                             if isinstance(_t, str):
                                 _err_type = _t
-                        # ── Decisioni soppressione
+                        # Decide whether to suppress the error.
                         _suppress = False
                         _suppress_reason = ""
                         if "Unknown or invalid event: session.update" in _err_msg:
                             _suppress = True
                             _suppress_reason = (
-                                "rifiuto del nostro inject session.update con tools[] — ai-server attualmente non supporta "
-                                "tools[]. Modifica richiesta in arrivo. Loggo solo server-side e non inoltro al browser."
+                                "injected session.update with tools[] rejected — ai-server currently does not support "
+                                "tools[]. Log only on the server and do not forward to the browser."
                             )
                         elif "session.update" in _err_msg and ("tool" in _err_msg.lower() or "invalid" in _err_msg.lower()):
                             _suppress = True
                             _suppress_reason = (
-                                f"rifiuto di session.update da upstream (message): {_err_msg[:160]}. Non inoltro al browser."
+                                f"upstream rejected session.update (message): {_err_msg[:160]}. Do not forward to the browser."
                             )
                         elif _err_type == "unknown_or_invalid_event" and "session.update" in _err_msg:
                             _suppress = True
                             _suppress_reason = (
-                                f"rifiuto di session.update da upstream (type=unknown_or_invalid_event): {_err_msg[:160]}. Non inoltro al browser."
+                                f"upstream rejected session.update (type=unknown_or_invalid_event): {_err_msg[:160]}. Do not forward to the browser."
                             )
                         if _suppress:
                             logger.info(
-                                "[WS SUPPRESS] suppressed upstream error (non mandato al browser): %s",
+                                "[WS SUPPRESS] suppressed upstream error (not sent to browser): %s",
                                 _suppress_reason,
                             )
                             logger.debug(
@@ -6620,8 +6459,7 @@ async def _upstream_to_client(ws: WebSocket, upstream, client_ip: str, session_c
                                 json.dumps(_evt, ensure_ascii=True)[:600],
                             )
                             return
-                        # ── Log ispezione: se arriviamo qua l'errore NON è stato soppresso.
-                        # Facciamo sempre vedere message+type per capire se aggiungere nuove regole.
+                        # Log unsuppressed errors with message/type to assess new rules.
                         logger.debug(
                             "[WS SUPPRESS] upstream error NOT suppressed (passthrough to browser) — "
                             "evt.error.message=%s evt.error.type=%s evtTopKeys=%s",
diff --git a/s2s-client/style.css b/s2s-client/style.css
index ec438d5..22914f4 100644
--- a/s2s-client/style.css
+++ b/s2s-client/style.css
@@ -143,11 +143,10 @@ body::after {
 }
 
 /* ─── Overlay unlocker TALK mode (S2S_START_SESSION_MODE=TALK) ───
-   Cattura QUALSIASI primo tap/click dell'utente sulla pagina, perché
-   i browser bloccano getUserMedia() fuori da una user gesture. Senza
-   questo layer il doStart() del setTimeout falliva e non si sentiva
-   il greet. Sopra TUTTO tranne i modali <dialog> (z-index auto di dialog
-   vince). */
+   Capture the first tap/click anywhere on the page because browsers block
+   getUserMedia() outside a user gesture. Without this layer, doStart() from
+   setTimeout failed and the greeting was silent. Above all content except
+   <dialog> modals, whose top layer takes priority. */
 .talk-unlocker {
   position: fixed;
   inset: 0;
@@ -466,7 +465,7 @@ a:hover {
   transform: translateY(-0.5px);
 }
 
-/* ── User avatar circle (instead of old "Utente: Nome" text) ──
+/* ── User avatar circle (replaces the old user-name text) ──
  *  - perfectly round badge, matches the 42px icon-btn size in the topbar
  *  - glass + brand gradient 1px border
  *  - two uppercase initials (Alessandro Valenti → AV), bold white
@@ -593,8 +592,8 @@ a:hover {
     height: 36px;
     padding: 0 12px;
   }
-  /* ── Footer (narrow viewport): riduci tracking per non farlo andare
-   *    a capo in malo modo; padding compatto + line-height maggiore */
+  /* ── Footer (narrow viewport): reduce tracking to avoid awkward wrapping;
+   *    use compact padding and a taller line height. */
   .app-footer {
     padding: 8px 14px 14px;
   }
@@ -2425,7 +2424,7 @@ body.cam-on .footer {
    `margin-right:22px` on `.hist-msg.assistant` and `margin-left:6px` on `.hist-msg.user`
    (hard rules on the bubbles themselves so nothing can hide them).
    Bottom padding BUMP 2026-09-04: 96 → 160px. The screenshot showed the last
-   assistant line "...Necesitas más detalles o" cut clean by the footer. 160px
+   assistant line asking for more details cut cleanly by the footer. 160px
    inside the scroll container is 5× the real footer glass height; after we
    snap scrollTop to the absolute max, the last bubble terminates at the TOP
    of a 160px-high transparent region → fully visible, fully above the floating
@@ -2460,7 +2459,7 @@ body.cam-on .footer {
   background-clip: content-box;
 }
 
-/* ─── Chat input row (bottom of chat panel: "sobre el botón") ──────── */
+/* ─── Chat input row (bottom of chat panel, above the button) ──────── */
 /* NOTE: currently HIDDEN in index.html. Kept seamless here so if/when we
    re-enable it the form melts visually into the page bg, no separator frame. */
 .chat-form {
@@ -3474,20 +3473,20 @@ button[data-reports-sidebar-toggle] {
   flex: none;
 }
 /* Per-chip tint cycles (keyword-based, if no data attribute → fallback brand) */
-.reports-hint .reports-list li[data-tint="mortalidad"] { background: linear-gradient(180deg, color-mix(in srgb, #ff6a75 14%, rgba(20,22,32,.55)), rgba(20,22,32,.55)); border-color: color-mix(in srgb, #ff6a75 35%, var(--border)); }
-.reports-hint .reports-list li[data-tint="mortalidad"]::before { background: #ff6a75; box-shadow: 0 0 8px 0 #ff6a75aa; }
-.reports-hint .reports-list li[data-tint="metricas"] { background: linear-gradient(180deg, color-mix(in srgb, #22d3ee 14%, rgba(20,22,32,.55)), rgba(20,22,32,.55)); border-color: color-mix(in srgb, #22d3ee 35%, var(--border)); }
-.reports-hint .reports-list li[data-tint="metricas"]::before { background: #22d3ee; box-shadow: 0 0 8px 0 #22d3eeaa; }
-.reports-hint .reports-list li[data-tint="diario"] { background: linear-gradient(180deg, color-mix(in srgb, #8b5cf6 14%, rgba(20,22,32,.55)), rgba(20,22,32,.55)); border-color: color-mix(in srgb, #8b5cf6 35%, var(--border)); }
-.reports-hint .reports-list li[data-tint="diario"]::before { background: #8b5cf6; box-shadow: 0 0 8px 0 #8b5cf6aa; }
-.reports-hint .reports-list li[data-tint="productos"] { background: linear-gradient(180deg, color-mix(in srgb, #ec4899 14%, rgba(20,22,32,.55)), rgba(20,22,32,.55)); border-color: color-mix(in srgb, #ec4899 35%, var(--border)); }
-.reports-hint .reports-list li[data-tint="productos"]::before { background: #ec4899; box-shadow: 0 0 8px 0 #ec4899aa; }
+.reports-hint .reports-list li[data-tint="mortality"] { background: linear-gradient(180deg, color-mix(in srgb, #ff6a75 14%, rgba(20,22,32,.55)), rgba(20,22,32,.55)); border-color: color-mix(in srgb, #ff6a75 35%, var(--border)); }
+.reports-hint .reports-list li[data-tint="mortality"]::before { background: #ff6a75; box-shadow: 0 0 8px 0 #ff6a75aa; }
+.reports-hint .reports-list li[data-tint="metrics"] { background: linear-gradient(180deg, color-mix(in srgb, #22d3ee 14%, rgba(20,22,32,.55)), rgba(20,22,32,.55)); border-color: color-mix(in srgb, #22d3ee 35%, var(--border)); }
+.reports-hint .reports-list li[data-tint="metrics"]::before { background: #22d3ee; box-shadow: 0 0 8px 0 #22d3eeaa; }
+.reports-hint .reports-list li[data-tint="daily"] { background: linear-gradient(180deg, color-mix(in srgb, #8b5cf6 14%, rgba(20,22,32,.55)), rgba(20,22,32,.55)); border-color: color-mix(in srgb, #8b5cf6 35%, var(--border)); }
+.reports-hint .reports-list li[data-tint="daily"]::before { background: #8b5cf6; box-shadow: 0 0 8px 0 #8b5cf6aa; }
+.reports-hint .reports-list li[data-tint="products"] { background: linear-gradient(180deg, color-mix(in srgb, #ec4899 14%, rgba(20,22,32,.55)), rgba(20,22,32,.55)); border-color: color-mix(in srgb, #ec4899 35%, var(--border)); }
+.reports-hint .reports-list li[data-tint="products"]::before { background: #ec4899; box-shadow: 0 0 8px 0 #ec4899aa; }
 .reports-hint .reports-list li[data-tint="synapse"] { background: linear-gradient(180deg, color-mix(in srgb, #fbbf24 14%, rgba(20,22,32,.55)), rgba(20,22,32,.55)); border-color: color-mix(in srgb, #fbbf24 35%, var(--border)); }
 .reports-hint .reports-list li[data-tint="synapse"]::before { background: #fbbf24; box-shadow: 0 0 8px 0 #fbbf24aa; }
 .reports-hint .reports-list li[data-tint="supply"] { background: linear-gradient(180deg, color-mix(in srgb, #34d399 14%, rgba(20,22,32,.55)), rgba(20,22,32,.55)); border-color: color-mix(in srgb, #34d399 35%, var(--border)); }
 .reports-hint .reports-list li[data-tint="supply"]::before { background: #34d399; box-shadow: 0 0 8px 0 #34d399aa; }
-.reports-hint .reports-list li[data-tint="finanzas"] { background: linear-gradient(180deg, color-mix(in srgb, #22c55e 14%, rgba(20,22,32,.55)), rgba(20,22,32,.55)); border-color: color-mix(in srgb, #22c55e 35%, var(--border)); }
-.reports-hint .reports-list li[data-tint="finanzas"]::before { background: #22c55e; box-shadow: 0 0 8px 0 #22c55eaa; }
+.reports-hint .reports-list li[data-tint="finance"] { background: linear-gradient(180deg, color-mix(in srgb, #22c55e 14%, rgba(20,22,32,.55)), rgba(20,22,32,.55)); border-color: color-mix(in srgb, #22c55e 35%, var(--border)); }
+.reports-hint .reports-list li[data-tint="finance"]::before { background: #22c55e; box-shadow: 0 0 8px 0 #22c55eaa; }
 .reports-hint .reports-list li:hover {
   transform: translateY(-1px) scale(1.01);
   border-color: color-mix(in srgb, var(--brand) 55%, var(--border-strong));
@@ -4055,10 +4054,10 @@ button[data-reports-sidebar-toggle] {
   opacity: 0.5;
 }
 
-/* ─── Webcam preview (camera tool) — HIDDEN BY DEFAULT OGGI ──────────────────
+/* ─── Webcam preview (camera tool) — CURRENTLY HIDDEN BY DEFAULT ─────────────
  * Floating self-view, bottom-left. Mirrored for the user; the frame sent to
- * the model is drawn un-mirrored. Markup esiste per riattivazione futura.
- * Per usarlo: togli hidden su cam-pip in index.html + scommenta listener in main.js. */
+ * the model is drawn un-mirrored. Markup is retained for future reactivation.
+ * To enable it, remove hidden from cam-pip in index.html and restore the main.js listener. */
 .cam-pip {
   position: fixed;
   left: 20px;
@@ -4285,12 +4284,12 @@ html[data-theme="white"] .app-column {
   margin-left: 0 !important;
 }
 /* ─────────────────────────────────────────────────────────────────────
-   USER FIX 2026-09-10 "la chat deve apparire solo nel chat box":
+   USER FIX 2026-09-10: show the conversation only inside the chat box.
    The dark theme renders a SECOND ephemeral transcript into #bubble-stack
    (floating anchored top-right — the grey/light blue bubbles the user
    circled in red with an X on the last screenshot). Since the white
    mobile theme shows ALL conversation exclusively inside the persistent
-   "Conversación" card (chat-history inside .chat-panel bounded 58dvh),
+   conversation card (chat-history inside .chat-panel bounded 58dvh),
    we kill the parallel floating bubble stack HARD in white theme — both
    the ID and the class, zero width/height/transform so it can't leave
    layout artifacts. */
@@ -4543,8 +4542,8 @@ html[data-theme="white"] .topbar-right {
   display: none;
 }
 
-/* ── Status card: "Listo para conversar / Informes, análisis..." ───────
-     User request 2026-09-10 "nascondi box listo para conversar" — hide the
+/* ── Status card: ready to converse, reports and analysis ─────────────
+     User request 2026-09-10: hide the ready-to-converse box. Hide the
      entire status card in white theme (the grey rounded banner with the
      chart icon and arrow between topbar and mic stage, which the user
      circled with a red X). Previously we hid only the right chevron; now
@@ -4820,7 +4819,7 @@ html[data-theme="white"] .white-stop-btn svg {
   flex: none;
 }
 
-/* ── Quick actions — 3 pills (Resumen / Consultar datos / Crear respuesta).
+/* ── Quick actions — 3 pills (summary / data lookup / response draft).
      User request 2026-09-10 "nascondi le cose in rosso": all 3 quick action
      pills are circled in red → hide the entire quick-actions container. */
 html[data-theme="white"] .quick-actions {
@@ -4830,8 +4829,8 @@ html[data-theme="white"] .quick-action-btn {
   display: none !important;
 }
 
-/* ── Chat panel (Conversación card): white rounded card + "En línea" pill.
-     CRITICAL SCROLL FIX 2026-09-10 (per "non fa lo scrolling della chatbox"):
+/* ── Chat panel: white rounded conversation card + online status pill.
+     CRITICAL SCROLL FIX 2026-09-10: the chat box was not scrolling.
      The previous white-theme override set `flex: 0 0 auto` + `max-height: none`
      which removed every vertical constraint on the chat panel → it grew beyond
      the viewport edge → overflow on the *page* body instead of the chat
@@ -4912,7 +4911,7 @@ html[data-theme="white"] .chat-panel-header {
   border-bottom-width: 1px !important;
   text-decoration: none !important;
 }
-/* "En línea" status pill — green dot + text */
+/* Online status pill — green dot + text */
 html[data-theme="white"] .chat-status-pill {
   display: inline-flex;
   align-items: center;
@@ -4940,10 +4939,9 @@ html[data-theme="white"] .chat-status-dot {
   50%      { box-shadow: 0 0 0 5px rgba(22, 163, 74, 0.08); }
 }
 
-/* ── Chat header actions row: contiene "En línea" status pill + Export button.
-      Aggiunto 2026-09-23: bottone download conversación.
-      Layout orizzontale, allineato a destra, auto-wrap con gap per evitare
-      overflow su schermi stretti.                                                         */
+/* ── Chat header actions row: online status pill + conversation export button.
+      Added 2026-09-23. Horizontal, right-aligned layout with wrapping and gaps
+      to avoid overflow on narrow screens. */
 .chat-header-actions {
   display: inline-flex;
   align-items: center;
@@ -4953,7 +4951,7 @@ html[data-theme="white"] .chat-status-dot {
   flex-wrap: wrap;
   min-width: 0;
 }
-/* Botón export conversación (icon button baseline: coerente con altri .icon-btn). */
+/* Conversation export button, consistent with other .icon-btn controls. */
 .chat-export-btn {
   position: relative;
   display: inline-flex;
@@ -4990,14 +4988,14 @@ html[data-theme="white"] .chat-status-dot {
   pointer-events: none;
   flex: 0 0 auto;
 }
-/* Feedback OK: verde temporáneo al exportar correctamente. */
+/* Successful export feedback: temporarily green. */
 .chat-export-btn.chat-export-ok {
   background: rgba(22, 163, 74, 0.18) !important;
   border-color: rgba(22, 163, 74, 0.34) !important;
   color: #22c55e !important;
   box-shadow: 0 0 0 2px rgba(22, 163, 74, 0.12);
 }
-/* Feedback vacía: pulse ámbar (ningún mensaje para exportar). */
+/* Empty export feedback: amber pulse when there are no messages. */
 .chat-export-btn.chat-export-empty {
   background: rgba(245, 158, 11, 0.18) !important;
   border-color: rgba(245, 158, 11, 0.34) !important;
@@ -5039,7 +5037,7 @@ html[data-theme="white"] .chat-export-btn.chat-export-empty {
 }
 
 /* ──────────────────────────────────────────────────
-   THE SCROLLABLE HISTORY BOX (root cause of "non scorre")
+   THE SCROLLABLE HISTORY BOX (root cause of the scrolling failure)
    Before: max-height:none. Now it's a flex item with flex:1 1 auto inside
    .chat-panel-inner, which has a bounded 100% height of its parent.
    min-height:0 is MANDATORY — without it, flex column children never shrink
@@ -5213,7 +5211,7 @@ html[data-theme="white"] #bubble-stack .bubble.user::before {
 }
 
 /* 6) META label "name HH:MM" on the same single line, ONE pseudo-element.
-      ──── USER FIX 2026-09-10 "perche mette sempre Emilio" ────
+      ──── USER FIX 2026-09-10: remove the hardcoded user name ────
       The previous iteration hardcoded the Spanish names "Vocero" (assistant)
       and "Emilio" (user) plus a fake "16:14" timestamp. Instead we now read
       BOTH values dynamically from data attributes written by ui/chat.js at the
diff --git a/s2s-client/ui/chat.js b/s2s-client/ui/chat.js
index 2cf1184..d8bf853 100644
--- a/s2s-client/ui/chat.js
+++ b/s2s-client/ui/chat.js
@@ -288,7 +288,7 @@ export class ChatView {
    *   inner .{hist|bubble}-body            → data-user-name | data-asst-name + data-timestamp
    *
    * The .{hist|bubble}-body::before pseudo-element in style.css uses attr()
-   * to render the "Nombre  HH:MM" label aligned to the bubble corner; the
+   * to render the "Name  HH:MM" label aligned to the bubble corner; the
    * wrapper .user::before pseudo uses attr(data-user-initials) to paint the
    * circular avatar's 2-letter monogram.
    *
@@ -583,8 +583,8 @@ export class ChatView {
 
   /**
    * Pretty-print the JSON conversation structure to a human-readable plain
-   * text log (one entry per "HH:MM  Nombre: texto"). Tool calls are rendered
-   * as indented blocks ("TOOL: nombre" followed by Input/Output sections).
+   * text log (one entry per "HH:MM  Name: text"). Tool calls are rendered
+   * as indented blocks (tool name followed by input/output sections).
    * @param {ReturnType<ChatView["_serializeConversation"]>} conv
    * @returns {string}
    */
@@ -648,8 +648,8 @@ export class ChatView {
    * Public entry-point wired to the #chat-export-btn in the chat header.
    * Serializes the current conversation and produces TWO downloads:
    *   1. vocero-conversacion-YYYYMMDD-HHMMSS.json  (structured data)
-   *   2. vocero-conversacion-YYYYMMDD-HHMMSS.txt   (log legibile para humanos)
-   * UI feedback: briefly swaps the download icon for a ✓ "hecho" tick then
+   *   2. vocero-conversacion-YYYYMMDD-HHMMSS.txt   (human-readable log)
+   * UI feedback: briefly swaps the download icon for a ✓ completion tick then
    * restores the original SVG so the user gets a visual ack that the export
    * completed (idempotent / errors are logged to console — never throws).
    */
@@ -677,7 +677,7 @@ export class ChatView {
           setTimeout(() => this._exportBtn?.classList.remove("chat-export-empty"), 600);
         }
         if (typeof window !== "undefined" && typeof console !== "undefined") {
-          console.info("[ui/chat.js:exportConversation] No hay mensajes aún — exportación omitida.");
+          console.info("[ui/chat.js:exportConversation] No messages yet — export skipped.");
         }
         return;
       }
@@ -691,7 +691,7 @@ export class ChatView {
       }
     } catch (err) {
       if (typeof window !== "undefined" && typeof console !== "undefined") {
-        console.error("[ui/chat.js:exportConversation] Error exportando conversación:", err);
+        console.error("[ui/chat.js:exportConversation] Conversation export failed:", err);
       }
     }
   }
diff --git a/s2s-client/ws/s2s-ws-client.js b/s2s-client/ws/s2s-ws-client.js
index f6f220e..670a024 100644
--- a/s2s-client/ws/s2s-ws-client.js
+++ b/s2s-client/ws/s2s-ws-client.js
@@ -54,16 +54,14 @@ function reportWsDebug(hypothesisId, location, msg, data = {}) {
 }
 
 // ---------------------------------------------------------------------------
-// 🔎 WS DEBUG TRACER (sempre attivo, 2026-09-24)
-// Banner + stile etichette condiviso per tutta la famiglia di log [S2S-WS:*].
-// Non è più abilitato solo via localStorage.s2s.debug: gli eventi di vita
-// (connect, close, errore) e l'handshake iniziale sono loggati always-on;
-// i messaggi bulk (input_audio_buffer.append) vengono solo contati per non
-// spammare la Console.
+// 🔎 WS DEBUG TRACER (always active, 2026-09-24)
+// Shared banner and label styles for all [S2S-WS:*] logs. Lifecycle events
+// (connect, close, error) and the initial handshake are always logged.
+// Count bulk input_audio_buffer.append messages to avoid console spam.
 // ---------------------------------------------------------------------------
 (function _wsDebugBanner() {
   console.info(
-    "%c🟡 [S2S-WS] client caricato (ws/s2s-ws-client.js v2026-09-24 23:12) — handshake, stato, messaggi chiave e tool-call loggati; PREFETCH APIPILOT strumenti AD OGNI INIZIO SESSIONE + post-login phone (cache per-utente, cambio phone = refresh=true automatico; invalid. cache globale __s2sInvalidateApipilotCache(); anti-leak token; anti-spam audio).",
+    "%c🟡 [S2S-WS] client loaded (ws/s2s-ws-client.js v2026-09-24 23:12) — logging handshake, status, key messages and tool calls; PREFETCH APIPILOT tools AT EVERY SESSION START + after phone login (per-user cache, phone changes trigger refresh=true; global invalidation __s2sInvalidateApipilotCache(); token masking; audio log throttling).",
     "background:#fef3c7;color:#92400e;font-weight:700;padding:4px 8px;border-radius:4px;"
   );
 })();
@@ -79,24 +77,22 @@ function _wsLog(status, tag, msg, ...extra) {
   const badge = `%c[S2S-WS:${tag}]`;
   console.log(`${badge}%c ${msg}`, badgeBg, labelFg, ...extra);
 }
-/** Contatore per audio chunk bulk, per evitare spam. */
+/** Bulk audio chunk counter for throttling logs. */
 let _wsMicChunkCount = 0;
 let _wsMicChunkLastLogTs = 0;
 
 // ---------------------------------------------------------------------------
-// 🔧 APIPILOT PREFETCH AD INIZIO SESSIONE (2026-09-24)
-// Ogni volta che s2s-ws-client avvia una connessione Realtime (metodo connect())
-// viene scaldata la cache ApiPilot lato server chiamando /api/apipilot/tools.
-// Cache TTL lato client 240 s (= TTL server 300 s meno 60 s margine).
-// Il prefetch è FIRE-AND-FORGET: non blocca MAI l'handshake WS, non fallisce
-// connect() anche se il proxy restituisce 5xx.
+// 🔧 APIPILOT PREFETCH AT SESSION START (2026-09-24)
+// Each connect() warms the server-side ApiPilot cache via /api/apipilot/tools.
+// Client cache TTL is 240 s (server TTL 300 s minus a 60 s margin).
+// Prefetch failures, including proxy 5xx responses, do not fail connect().
 // ---------------------------------------------------------------------------
 /** @type {{at:number, data:any, key:string|null}|null} */
 let _apipilotClientCache = null;
-const _APIPILOT_CLIENT_TTL_MS = 240_000; // 4 minuti
-/** Contatore sessioni totali (per log), incrementato ad ogni connect(). */
+const _APIPILOT_CLIENT_TTL_MS = 240_000; // 4 minutes
+/** Session counter for logging, incremented by each connect(). */
 let _wsSessionCounter = 0;
-/** Chiave cache per utente: ultimi 8 cifre phoneNumber o fingerprint token. */
+/** Per-user cache key: last 8 phoneNumber digits or a token fingerprint. */
 function _apipilotUserKey() {
   try {
     // @ts-ignore
@@ -108,38 +104,34 @@ function _apipilotUserKey() {
     return "anon";
   } catch (_) { return "anon"; }
 }
-/** Invalida la cache ApiPilot lato client. Esporta globalmente per main.js (dopo login phone). */
+/** Invalidate the client ApiPilot cache. Exported globally for main.js after phone login. */
 function _invalidateApipilotClientCache() {
   _apipilotClientCache = null;
   console.info(
-    "%c🔧 [S2S-WS:APIPILOT] Cache client invalidata (nuovo login utente o refresh=true forzato)",
+    "%c🔧 [S2S-WS:APIPILOT] Client cache invalidated (new user login or forced refresh=true)",
     "background:#fde68a;color:#92400e;font-weight:700;padding:1px 6px;border-radius:3px;"
   );
 }
 
-// Stesso identico marker e regole del lato server Python (server.py#L555-L556).
-// Lo ripetiamo identico in JS per garantire:
-//   (1) stessa classifica dedup
-//   (2) stesso formato regole marker AI
-//   (3) dedup by marker stringa <<<APIPILOT_TOOLS_LIST_BEGIN>>> in effectiveReasoningInstructions
-//       (così non appendiamo due volte se sia server che client provano entrambi).
+// Match the Python server's marker and rules for consistent deduplication and
+// AI marker syntax. effectiveReasoningInstructions checks this marker so the
+// client and server do not append the same tools list twice.
 const APIPILOT_PASS1_LIST_MARKER_JS = "<<<APIPILOT_TOOLS_LIST_BEGIN>>>";
 
 /**
- * Restituisce il testo del blocco PASSATA-1 da iniettare nel prompt instructions LLM.
- * FORMATO IDENTICO al Python _resolve_apipilot_reasoning_context_block(tools=[...]).
- *   - Inizio con APIPILOT_PASS1_LIST_MARKER_JS
- *   - Fine con <<<APIPILOT_TOOLS_LIST_END>>>
- *   - Lingua: SPAGNOLO (stesso di profile inject e istruzioni AI)
- *   - Cap description a 500 chars
- *   - Max 100 strumenti
- * @param {any[]|null|undefined} tools Lista da cache oppure null (usa cache corrente)
- * @returns {string} Blocco di testo PASSATA-1 (stringa vuota se lista vuota / nessuno strumento / nessuna cache)
+ * Build the PASS-1 block injected into the LLM instructions prompt.
+ * Match Python _resolve_apipilot_reasoning_context_block(tools=[...]).
+ *   - Start with APIPILOT_PASS1_LIST_MARKER_JS
+ *   - End with <<<APIPILOT_TOOLS_LIST_END>>>
+ *   - Instructions in English; assistant responses remain Spanish
+ *   - Cap descriptions at 500 characters and tools at 100
+ * @param {any[]|null|undefined} tools Cached list, or null to use the current cache
+ * @returns {string} PASS-1 text block, empty when no tools or cache are available
  */
 function buildApipilotPass1PromptBlock(tools) {
   let list = Array.isArray(tools) ? tools : null;
   if (!list) {
-    // Fallback: usa cache client locale corrente (se disponibile)
+    // Fall back to the current client cache, if available.
     const c = _apipilotClientCache;
     if (c && c.data && Array.isArray(c.data.tools)) list = c.data.tools;
   }
@@ -168,25 +160,24 @@ function buildApipilotPass1PromptBlock(tools) {
   console.warn("APIPILOT_PASS1_LIST_MARKER_JS", APIPILOT_PASS1_LIST_MARKER_JS);
   const markers = (
     `${APIPILOT_PASS1_LIST_MARKER_JS}\n` +
-    "### Herramientas dinámicas disponibles (ApiPilot AquaPortal)\n" +
+    "### Available dynamic tools (ApiPilot AquaPortal)\n" +
     "\n" +
-    "Cada herramienta tiene un campo `name` (identificador único, NO lo modifiques, " +
-    "NO camelCase, NO traducir) y un campo `description` que describe el caso de uso.\n" +
+    "Each tool has a `name` field (a unique identifier: DO NOT change, camelCase " +
+    "or translate it) and a `description` field explaining its use case.\n" +
     "\n" +
-    "REGLAS EJECUCIÓN OBLIGATORIAS:\n" +
-    "1. Si la petición DEL USUARIO (transcript) coincide claramente con la `description` " +
-    "de EXACTAMENTE una (1) herramienta de la lista inferior → DEBES emitir EXCLUSIVAMENTE " +
-    "una sola riga come PRIMERA línea de TU RESPUESTA, con questo formato sintattico:\n" +
-    '   <<<APIPILOT_CALL:NAME=nome_herramienta,ARGUMENTS={"parametro1":"valor1","parametro2":"valor2"}>>>\n' +
-    "2. La parte ARGUMENTS={…} DEBE ser JSON válido (virgolette doppie, virgole, senza " +
-    "commenti). Includi SOLAMENTE i campi elencati in `required_parameters:` (se ci sono).\n" +
-    "3. Subito DOPO la riga marker NON aggiungere altro testo (niente spiegazioni, " +
-    "niente anticipazioni). Il motore eseguirà lo strumento e ti risomministrerà il " +
-    "risultato in una seconda chiamata.\n" +
-    "4. Se NESSUNA `description` corrisponde, NON emettere marker e rispondi normalmente.\n" +
-    "5. Se più di una descrizione corrisponde, scegli la più specifica e usa il marker.\n" +
+    "MANDATORY EXECUTION RULES:\n" +
+    "1. If the USER REQUEST (transcript) clearly matches the `description` of " +
+    "EXACTLY one (1) tool below, output ONLY one line as the FIRST line of YOUR " +
+    "RESPONSE, using this exact syntax:\n" +
+    '   <<<APIPILOT_CALL:NAME=tool_name,ARGUMENTS={"parameter1":"value1","parameter2":"value2"}>>>\n' +
+    "2. ARGUMENTS={…} MUST be valid JSON (double quotes, commas, no comments). " +
+    "Include ONLY fields listed in `required_parameters:`, if any.\n" +
+    "3. Do NOT add text after the marker line (no explanations or previews). " +
+    "The engine executes the tool and supplies its result in a second call.\n" +
+    "4. If NO `description` matches, do NOT emit a marker; respond normally in Spanish.\n" +
+    "5. If multiple descriptions match, choose the most specific and use the marker.\n" +
     "\n" +
-    "Lista herramientas (name / description):\n" +
+    "Tools list (name / description):\n" +
     `${entries.join("\n")}\n` +
     "<<<APIPILOT_TOOLS_LIST_END>>>"
   );
@@ -195,7 +186,7 @@ function buildApipilotPass1PromptBlock(tools) {
 }
 
 /**
- * Controlla se le istruzioni in input contengono già il marker PASS1 (dedup).
+ * Check whether the input instructions already contain the PASS1 marker.
  * @param {string|undefined|null} text
  * @returns {boolean}
  */
@@ -204,10 +195,9 @@ function instructionsAlreadyHasApipilotPass1(text) {
 }
 
 /**
- * Espone globalmente una funzione helper per:
- *   - main.js: costruire effectiveReasoningInstructions appendendo la lista.
- *   - altri moduli che volessero leggerla.
- * Il check dedup è fatto automaticamente dal chiamante prima di appendere.
+ * Expose a global helper for main.js to append tools to
+ * effectiveReasoningInstructions, and for other modules to read the list.
+ * The caller checks for duplicates before appending.
  * @returns {{block: string, count: number, marker: string, alreadyPresent:(t:string)=>boolean}}
  */
 function getApipilotPass1ContextInfo() {
@@ -456,12 +446,11 @@ export class S2sWsRealtimeClient extends EventTarget {
    */
   async connect() {
     if (this._ws) throw new Error("Already connected");
-    // Contatore sessioni totali: utile nel tracer per correlare gli eventi
-    // di [S2S-WS:*] a un numero di sessione crescente.
+    // Correlate [S2S-WS:*] events using an increasing session number.
     _wsSessionCounter += 1;
     const sessionIdShort = `#${_wsSessionCounter}`;
     this._sessionSeq = _wsSessionCounter;
-    _wsLog(0, "SESSION", `${sessionIdShort} handshake iniziato — status: creating-session`);
+    _wsLog(0, "SESSION", `${sessionIdShort} handshake started — status: creating-session`);
 
     let connectUrl;
     if (this._directUrl) {
@@ -480,7 +469,7 @@ export class S2sWsRealtimeClient extends EventTarget {
       // keeps a freed slot from being spent on someone who stepped away, and the
       // click is a fresh gesture (re-arms the AudioContext on iOS).
       if (waited) {
-        _wsLog(1, "QUEUE", `${sessionIdShort} tuo turno — attesa click join per confermare slot`);
+        _wsLog(1, "QUEUE", `${sessionIdShort} your turn — waiting for a join click to confirm the slot`);
         await this._awaitJoin(grant);
         if (this._closed) throw _codedError("connect aborted", "aborted");
       }
@@ -497,38 +486,38 @@ export class S2sWsRealtimeClient extends EventTarget {
     }
 
     // Spin up the AudioContext + worklets in parallel with the WS dial,
-    // E IN PARALLELO scaldiamo ApiPilot (strumenti dinamici AquaPortal).
-    // Il prefetch è non bloccante: se fallisce, non fallisce connect().
+    // Also warm ApiPilot (dynamic AquaPortal tools) in parallel.
+    // A failed prefetch does not fail connect().
     const audioReady = this._setupAudio();
     const wsReady = this._openWebSocket(connectUrl);
     const apipilotReady = this._prefetchApipilotTools(sessionIdShort);
     await Promise.all([audioReady, wsReady, apipilotReady.catch(() => void 0)]);
-    _wsLog(1, "SESSION", `${sessionIdShort} connessione stabilita + audio pipeline + apipilot OK`);
+    _wsLog(1, "SESSION", `${sessionIdShort} connection established + audio pipeline + apipilot OK`);
   }
 
   /**
-   * 🔧 PRE-FETCH strumenti ApiPilot ad ogni inizio di sessione Realtime.
-   *  - Proxy sul server: GET api/apipilot/tools?include_unauthorized=true
-   *  - Il wrapper FETCH globale traccia come [FETCH:APIPILOT:TOOLS] in Console.
-   *  - Cache TTL locale 240 s per evitare chiamate ridondanti se l'utente
-   *    chiude e riapre sessioni in rapida successione (server TTL=300 s).
-   *  - SE window.__s2sApipilot=false → salta subito.
-   *  - MAI fallisce: sempre catch interno.
-   * @param {string} sessionIdShort Log tag "sessione #N"
+   * 🔧 Pre-fetch ApiPilot tools at every Realtime session start.
+   *  - Server proxy: GET api/apipilot/tools?include_unauthorized=true
+   *  - The global FETCH wrapper logs [FETCH:APIPILOT:TOOLS] in the console.
+   *  - Local TTL 240 s avoids redundant calls during rapid session restarts
+   *    (server TTL=300 s).
+   *  - Skip immediately when window.__s2sApipilot=false.
+   *  - Catch failures internally.
+   * @param {string} sessionIdShort Log tag "session #N"
    * @returns {Promise<void>}
    */
   async _prefetchApipilotTools(sessionIdShort) {
     try {
-      // @ts-ignore: __s2sApipilot è settato da main.js dopo fetchConfig()
+      // @ts-ignore: main.js sets __s2sApipilot after fetchConfig().
       const enabled = typeof window !== "undefined" && !!window.__s2sApipilot;
       if (!enabled) {
-        _wsLog(2, "APIPILOT", `${sessionIdShort} feature flag apipilot=false sul server — salto prefetch strumenti`);
+        _wsLog(2, "APIPILOT", `${sessionIdShort} server feature flag apipilot=false — skipping tools prefetch`);
         return;
       }
       const currentUser = _apipilotUserKey();
       const now = Date.now();
       const cached = _apipilotClientCache;
-      // HIT cache solo se: (1) ancora fresca TTL (2) stesso utente key (non cambio phone/token tra sessioni)
+      // Use the cache only within its TTL and for the same user key.
       if (cached && (now - cached.at <= _APIPILOT_CLIENT_TTL_MS) && cached.key === currentUser) {
         const ageSec = Math.round((now - cached.at) / 1000);
         const n =
@@ -537,10 +526,10 @@ export class S2sWsRealtimeClient extends EventTarget {
             : Array.isArray(cached.data && cached.data.tools)
               ? cached.data.tools.length
               : "?";
-        _wsLog(1, "APIPILOT", `${sessionIdShort} HIT cache client strumenti (user=${currentUser}, age=${ageSec}s, N=${n}, TTL=${Math.round(_APIPILOT_CLIENT_TTL_MS/1000)}s)`);
+        _wsLog(1, "APIPILOT", `${sessionIdShort} HIT client tools cache (user=${currentUser}, age=${ageSec}s, N=${n}, TTL=${Math.round(_APIPILOT_CLIENT_TTL_MS/1000)}s)`);
         return;
       }
-      // Propaga header x-demo-session se disponibile in window (per auth fingerprint lato server S2S).
+      // Forward x-demo-session when available for the S2S server auth fingerprint.
       /** @type {Record<string,string>} */
       const extraHeaders = {};
       try {
@@ -550,11 +539,11 @@ export class S2sWsRealtimeClient extends EventTarget {
           extraHeaders["x-demo-session"] = window.__s2sDemoSessionToken;
         }
       } catch (_) { /* noop */ }
-      // Usa refresh=true SE è cambiato l'utente (cache.key diversa o null) oppure la cache è stata invalidata globalmente.
+      // Refresh when the user key changes or the cache is missing/expired.
       const needRefresh = !cached || cached.key !== currentUser || (now - cached.at > _APIPILOT_CLIENT_TTL_MS);
       const qsRefresh = needRefresh ? "&refresh=true" : "";
       const t0 = performance.now();
-      _wsLog(0, "APIPILOT", `${sessionIdShort} MISS cache (user=${currentUser}, refresh=${needRefresh ? "Y" : "N"}) → GET api/apipilot/tools (proxy a S2S_APIPILOT_TOOLS_URL server)...`);
+      _wsLog(0, "APIPILOT", `${sessionIdShort} MISS cache (user=${currentUser}, refresh=${needRefresh ? "Y" : "N"}) → GET api/apipilot/tools (server proxy to S2S_APIPILOT_TOOLS_URL)...`);
       const res = await fetch(`api/apipilot/tools?include_unauthorized=true${qsRefresh}`, {
         method: "GET",
         cache: "no-store",
@@ -567,11 +556,11 @@ export class S2sWsRealtimeClient extends EventTarget {
       const j = await res.json().catch(() => ({}));
       const ok = j && j.success && j.data;
       if (!ok) {
-        throw new Error(`envelope non corretto: success=${Boolean(j && j.success)}`);
+        throw new Error(`invalid envelope: success=${Boolean(j && j.success)}`);
       }
       const tools = Array.isArray(j.data.tools) ? j.data.tools : [];
       const count = typeof j.data.count === "number" ? j.data.count : tools.length;
-      // Aggiorna cache locale (in caso di hit la prossima sessione non chiamerà).
+      // Update the local cache so a subsequent session can reuse it.
       _apipilotClientCache = { at: Date.now(), data: { count, tools: tools.slice(0, 100) }, key: currentUser };
       const names = tools
         .slice(0, 5)
@@ -580,16 +569,16 @@ export class S2sWsRealtimeClient extends EventTarget {
       _wsLog(
         1,
         "APIPILOT",
-        `${sessionIdShort} READY strumenti APIPILOT caricati: N=${count}, t=${Math.round(dt)}ms, user=${currentUser} [primi 5: ${names || "(nessuno)"}]`
+        `${sessionIdShort} READY APIPILOT tools loaded: N=${count}, t=${Math.round(dt)}ms, user=${currentUser} [first 5: ${names || "(none)"}]`
       );
     } catch (err) {
       const msg = err instanceof Error ? err.message : String(err);
       _wsLog(
         3,
         "APIPILOT",
-        `${sessionIdShort} prefetch FALLITO: ${msg} — diagnostica lato server log [APIPILOT-DISCOVERY]`
+        `${sessionIdShort} prefetch FAILED: ${msg} — check server logs [APIPILOT-DISCOVERY]`
       );
-      // NON rilanciare: connect() deve comunque andare a buon fine.
+      // Do not rethrow: connect() must still succeed.
     }
   }
 
@@ -670,21 +659,21 @@ export class S2sWsRealtimeClient extends EventTarget {
     const dur = (performance.now() - t0).toFixed(1);
     if (response.status === 402) {
       const body = await response.json().catch(() => ({}));
-      _wsLog(3, "SESSION", `/session HTTP 402: limite giornaliero esaurito (tier=${body?.tier ?? "?"})  dur=${dur} ms`);
+      _wsLog(3, "SESSION", `/session HTTP 402: daily limit exhausted (tier=${body?.tier ?? "?"})  dur=${dur} ms`);
       throw _codedError("Daily conversation limit reached", "limit", { tier: body?.tier });
     }
     if (response.status === 503) {
       const body = await response.json().catch(() => ({}));
       if (body?.state === "at_capacity") {
-        _wsLog(2, "QUEUE:FULL", `/session HTTP 503 state=at_capacity (coda piena)  dur=${dur} ms`);
+        _wsLog(2, "QUEUE:FULL", `/session HTTP 503 state=at_capacity (queue full)  dur=${dur} ms`);
         throw _codedError("The queue is full — try again shortly.", "queue-full");
       }
-      _wsLog(3, "SESSION", `/session HTTP 503 (fallback sconosciuto)  dur=${dur} ms`);
+      _wsLog(3, "SESSION", `/session HTTP 503 (unknown fallback)  dur=${dur} ms`);
       throw new Error("/session failed (503)");
     }
     if (!response.ok) {
       const text = await response.text().catch(() => "");
-      _wsLog(3, "SESSION", `/session fallita HTTP ${response.status}: ${text.slice(0, 180)}  dur=${dur} ms`);
+      _wsLog(3, "SESSION", `/session failed HTTP ${response.status}: ${text.slice(0, 180)}  dur=${dur} ms`);
       throw new Error(`/session failed (${response.status}): ${text}`);
     }
     const json = await response.json();
@@ -692,7 +681,7 @@ export class S2sWsRealtimeClient extends EventTarget {
       _wsLog(
         2,
         "QUEUE:WAIT",
-        `/session → stato=queued  queueId=${json.queue_id ?? "?"} position=${json.position ?? "?"} pollEvery=${json.poll_interval_s ?? "?"}s  dur=${dur} ms`
+        `/session → state=queued  queueId=${json.queue_id ?? "?"} position=${json.position ?? "?"} pollEvery=${json.poll_interval_s ?? "?"}s  dur=${dur} ms`
       );
       return {
         state: "queued",
@@ -724,7 +713,7 @@ export class S2sWsRealtimeClient extends EventTarget {
     _wsLog(
       2,
       "QUEUE:POLL",
-      `Inizio poll coda queueId=${ticket.queueId.slice(0, 10)}… initialPos=${ticket.position} intervalMs=${intervalMs}`
+      `Start queue polling queueId=${ticket.queueId.slice(0, 10)}… initialPos=${ticket.position} intervalMs=${intervalMs}`
     );
     let pollNum = 0;
 
@@ -744,11 +733,11 @@ export class S2sWsRealtimeClient extends EventTarget {
 
       if (response.status === 402) {
         const body = await response.json().catch(() => ({}));
-        _wsLog(3, "QUEUE:LIMIT", `poll #${pollNum} HTTP 402 — limite giornaliero (tier=${body?.tier ?? "?"})`);
+        _wsLog(3, "QUEUE:LIMIT", `poll #${pollNum} HTTP 402 — daily limit (tier=${body?.tier ?? "?"})`);
         throw _codedError("Daily conversation limit reached", "limit", { tier: body?.tier });
       }
       if (response.status === 404) {
-        _wsLog(3, "QUEUE:EXPIRED", `poll #${pollNum} HTTP 404 — ticket scaduto queueId=${this._queueId.slice(0, 10)}…`);
+        _wsLog(3, "QUEUE:EXPIRED", `poll #${pollNum} HTTP 404 — ticket expired queueId=${this._queueId.slice(0, 10)}…`);
         throw _codedError("Queue timed out", "queue-expired");
       }
       if (!response.ok) continue; // 502/503 — transient, retry
@@ -763,7 +752,7 @@ export class S2sWsRealtimeClient extends EventTarget {
         continue;
       }
       // Reached the front and claimed a slot.
-      _wsLog(1, "QUEUE:FRONT", `poll #${pollNum} — RAGGIUNTA la prima posizione. Assegno slot compute.`);
+      _wsLog(1, "QUEUE:FRONT", `poll #${pollNum} — REACHED the front. Assigning compute slot.`);
       this._queueId = "";
       return this._parseGrant(json);
     }
@@ -881,9 +870,8 @@ export class S2sWsRealtimeClient extends EventTarget {
   /** @param {string} connectUrl */
   _openWebSocket(connectUrl) {
     return new Promise((resolve, reject) => {
-      // Non loggiamo l'URL completo (potrebbe contenere session_token in
-      // chiaro nella querystring). Mostriamo solo host + path + un hash della
-      // parte segreta per audit senza leak token.
+      // Mask the full URL, which may contain a plaintext session_token.
+      // Show host + path and secret fingerprints for auditing without leaks.
       let maskedUrl = connectUrl;
       try {
         const u = new URL(connectUrl, window.location.href);
@@ -893,7 +881,7 @@ export class S2sWsRealtimeClient extends EventTarget {
           const isSecret = /token|session|auth|jwt|secret|key/i.test(lower) || String(v).length > 16;
           secretPortions.push(`${k}=${isSecret ? `✂️…${String(v).slice(-4)} (${String(v).length} chars)` : v}`);
         });
-        maskedUrl = `${u.protocol}//${u.host}${u.pathname}  ? ${secretPortions.join(" & ") || "(nessun query param)"}`;
+        maskedUrl = `${u.protocol}//${u.host}${u.pathname}  ? ${secretPortions.join(" & ") || "(no query parameters)"}`;
       } catch {
         // ignore
       }
@@ -905,13 +893,13 @@ export class S2sWsRealtimeClient extends EventTarget {
       const onceOpen = () => {
         ws.removeEventListener("open", onceOpen);
         ws.removeEventListener("error", onceErr);
-        _wsLog(1, "CONNECT", `WebSocket APERTO su ${maskedUrl}  readyState=${ws.readyState}`);
+        _wsLog(1, "CONNECT", `WebSocket OPEN at ${maskedUrl}  readyState=${ws.readyState}`);
         resolve();
       };
       const onceErr = (e) => {
         ws.removeEventListener("open", onceOpen);
         ws.removeEventListener("error", onceErr);
-        _wsLog(3, "CONNECT", `WebSocket IMPOSSIBILE da aprire: event.type=${e?.type ?? "error"}  url=${maskedUrl}`);
+        _wsLog(3, "CONNECT", `WebSocket FAILED to open: event.type=${e?.type ?? "error"}  url=${maskedUrl}`);
         reject(new Error(`WebSocket failed to open: ${e?.type ?? "error"}`));
       };
       ws.addEventListener("open", onceOpen);
@@ -1037,15 +1025,11 @@ export class S2sWsRealtimeClient extends EventTarget {
             `tools=${toolNames || "none"}`
           );
         }
-        // Primo ack del server: se startup mode=TALK vogliamo il comportamento
-        // IDENTICO a quando arriva la frase di wake word "Hola Vocero".
-        // Quindi NON mandiamo shaped response.create con istruzioni di greet
-        // hardcodate, ma invece:
-        //   1. injectiamo "hola vocero" nella conversazione come se l'utente
-        //      l'avesse detto (sendUserText → conversation.item.create user)
-        //   2. requestResponse() VUOTO → il modello risponde esattamente come
-        //      nel codice wake-word in main.js.
-        // Stesso identico risultato, nessuna istruzione custom.
+        // On the first server acknowledgment, TALK startup should behave
+        // exactly like hearing the "Hola Vocero" wake word:
+        //   1. Inject "hola vocero" as a user turn through sendUserText().
+        //   2. Call requestResponse() without custom greeting instructions,
+        //      matching the wake-word path in main.js.
         if (this._startWithResponse && !this._initialResponseSent) {
           this._initialResponseSent = true;
           const phrase = this._startWithResponseText.trim() || "hola vocero";
@@ -1363,7 +1347,7 @@ export class S2sWsRealtimeClient extends EventTarget {
     _wsLog(
       (ev.code === 1000 || ev.code === 1001) ? 1 : (ev.code ? 3 : 2),
       "CLOSE",
-      `WebSocket CHIUSO code=${ev.code ?? "?"} reason=${String(ev.reason ?? "(nessuna)").slice(0, 160)} wasClean=${ev.wasClean}`
+      `WebSocket CLOSED code=${ev.code ?? "?"} reason=${String(ev.reason ?? "(none)").slice(0, 160)} wasClean=${ev.wasClean}`
     );
     if (this._status === "closed" || this._status === "error") return;
     if (ev.code === 1000) {
@@ -1395,13 +1379,12 @@ export class S2sWsRealtimeClient extends EventTarget {
       },
     };
     // ───────────────────────────────────────────────────────────────────────────
-    // 2026-09-25 INIETTA API-PILOT HERRAMIENTAS DINÁMICAS (PASADA-1) nel session.update.
-    // 3 strati di assicurazione (in ordine di priorità crescente, dedup by marker):
-    //   (A) main.js effectiveReasoningInstructions() ha già appeso la lista.
-    //   (B) NOSTRO server.py proxy realtime ri-inietta (se routing lo attraversa).
-    //   (C) QUI s2s-ws-client: ultimo punto di catch-all prima dell'invio al
-    //       canale, GARANTISCE che la lista sia SEMPRE presente in istruzioni
-    //       (anche se qualcuno fa updateSession() con text sovrascritto poco dopo).
+    // 2026-09-25 INJECT API-PILOT DYNAMIC TOOLS (PASS 1) in session.update.
+    // Three safeguards, deduplicated by marker:
+    //   (A) main.js effectiveReasoningInstructions() appends the list.
+    //   (B) The server.py Realtime proxy injects it when routing passes there.
+    //   (C) This client is the final safeguard before sending instructions,
+    //       including after a live updateSession() replaces the prompt.
     {
       const currentInstr = (typeof session.instructions === "string") ? session.instructions : "";
       if (!instructionsAlreadyHasApipilotPass1(currentInstr)) {
@@ -1453,7 +1436,7 @@ export class S2sWsRealtimeClient extends EventTarget {
     const session = { type: "realtime" };
     if (patch.instructions) {
       let instr = patch.instructions;
-      // ── 2026-09-25 catch-all apipilot PASS-1 anche per patch live. ──
+      // ── 2026-09-25 ApiPilot PASS-1 safeguard for live patches too. ──
       if (typeof instr === "string" && !instructionsAlreadyHasApipilotPass1(instr)) {
         try {
           const info = typeof window !== "undefined" && typeof window.__s2sGetApipilotPass1ContextInfo === "function"
@@ -1776,8 +1759,8 @@ export class S2sWsRealtimeClient extends EventTarget {
   /** @param {Record<string, unknown>} event */
   _send(event) {
     if (!this._ws || this._ws.readyState !== WebSocket.OPEN) return;
-    // Anti-spam bulk-rate limiter per eventi audio (~25 al secondo).
-    // Loggiamo un resoconto ogni 250 chunk (circa 10s a 25Hz) invece di ogni singolo.
+    // Throttle bulk audio event logs (~25 events per second).
+    // Log periodic summaries rather than every chunk.
     if (event.type === "input_audio_buffer.append") {
       _wsMicChunkCount += 1;
       const now = performance.now();
@@ -1807,7 +1790,7 @@ export class S2sWsRealtimeClient extends EventTarget {
       this._ws.send(payload || JSON.stringify(event));
       return;
     }
-    // Messaggi non bulk: log sempre [S2S-WS:SEND] con anteprima del payload.
+    // Always log non-bulk messages as [S2S-WS:SEND] with a payload preview.
     let payloadLength = 0;
     let stringifyMs = 0;
     let payload = "";
diff --git a/s2s-reasoning-engine/.env.example b/s2s-reasoning-engine/.env.example
index 56dc990..f6dec51 100644
--- a/s2s-reasoning-engine/.env.example
+++ b/s2s-reasoning-engine/.env.example
@@ -1,7 +1,7 @@
-# Configurazione ambiente per s2s-reasoning-engine
+# Environment configuration for s2s-reasoning-engine
 #
-# Copia questo file in .env nella root del progetto o nella cartella s2s-reasoning-engine/
-# e modifica i valori secondo il tuo deployment.
+# Copy this file to .env in the project root or s2s-reasoning-engine directory
+# and adjust the values for your deployment.
 
 # ─────────────────────────────────────────────────────────────
 # 1) LLM (OpenAI-compatible)
@@ -15,7 +15,7 @@ OPENAI_REASONING_TEMPERATURE=0.2
 OPENAI_REASONING_MAX_TOKENS=512
 
 # ─────────────────────────────────────────────────────────────
-# 2) Aquachile (profilo agente, tool MCP, autenticazione)
+# 2) Aquachile (agent profile, MCP tools, authentication)
 # ─────────────────────────────────────────────────────────────
 S2S_AGENT_PROFILE=https://aquachile.azurianlab.com/api/v1/agents/profile
 S2S_USER_PHONE_AUTH_URL=https://aquachile.azurianlab.com/api/v1/auth/user-by-phone
@@ -32,8 +32,8 @@ NODE_RED_LOG_LEVEL=info
 NODE_RED_CREDENTIAL_SECRET=change-me-in-production
 
 # ─────────────────────────────────────────────────────────────
-# 4) Integrazione con s2s UI (server.py)
+# 4) S2S UI integration (server.py)
 # ─────────────────────────────────────────────────────────────
-# URL raggiungibile dal container Python della UI
-# (se usi rete docker condivisa è http://s2s-reasoning:1880)
+# URL reachable from the Python UI container
+# (for a shared Docker network, use http://s2s-reasoning:1880).
 S2S_REASONING_NODE_RED_URL=http://localhost:1881
diff --git a/s2s-reasoning-engine/Dockerfile b/s2s-reasoning-engine/Dockerfile
index 5bf3f50..959855f 100644
--- a/s2s-reasoning-engine/Dockerfile
+++ b/s2s-reasoning-engine/Dockerfile
@@ -1,30 +1,29 @@
 # s2s-reasoning-engine: Node-RED 5.0 custom image
 
-# Usa Node-RED 5.x ufficiale (immagine Alpine per dimensioni ridotte)
+# Use the official Node-RED 5.x Alpine image to keep the image small.
 FROM nodered/node-red:5.0.3
 
-# Porta di default di Node-RED (esposta in reti containerizzate)
+# Default Node-RED port, exposed to the container network.
 EXPOSE 1880
 
-# 1) Installa nodi aggiuntivi (a livello utente node-red nella cartella dati)
-#    - node-red-contrib-openai: integrazione nativa Chat Completions / Embeddings
-#    - node-red-contrib-http-logger: log HTTP opzionale
-#    - node-red-contrib-cache: cache in-memory per dati Aquachile (opzionale)
-#    - node-red-node-rbe: report-by-exception per deduplicare eventi
+# 1) Install additional nodes in the Node-RED user data directory.
+#    - node-red-contrib-openai: native Chat Completions / Embeddings integration
+#    - node-red-contrib-cache: optional in-memory cache for Aquachile data
+#    - node-red-node-rbe: report-by-exception event deduplication
 RUN cd /data && npm install --no-audit --no-fund \
     node-red-contrib-openai@0.11.0 \
     node-red-contrib-cache@1.1.1 \
     node-red-node-rbe@0.5.0
 
-# 2) Copia file di configurazione e flows iniziali
+# 2) Copy the configuration and initial flows.
 COPY settings.js /data/settings.js
 COPY flows.json /data/flows.json
 
-# 3) Imposta Node-RED per caricare flows statici + disabilita progetto e auth
-#    (per ambiente di sviluppo; in produzione abilitare adminAuth in settings.js)
+# 3) Load static flows with projects and authentication disabled for development.
+#    Enable adminAuth in settings.js for production.
 ENV NODE_RED_FLOWS_FILE=/data/flows.json
 ENV NODE_RED_CREDENTIAL_SECRET=s2s-reasoning-dev-secret
 ENV FLOWS=/data/flows.json
 
-# Avvio Node-RED
+# Start Node-RED.
 CMD ["npm", "start", "--", "--userDir", "/data", "--settings", "/data/settings.js"]
diff --git a/s2s-reasoning-engine/flows.json b/s2s-reasoning-engine/flows.json
index 8dcb37d..f7701c9 100644
--- a/s2s-reasoning-engine/flows.json
+++ b/s2s-reasoning-engine/flows.json
@@ -4,7 +4,7 @@
     "type": "tab",
     "label": "S2S Reasoning",
     "disabled": false,
-    "info": "# Flusso di reasoning S2S — FASE 1: LOG-ONLY\n\nModalità attuale: il flusso NON produce risposte, NON modifica il prompt.\nSi limita a:\n  1. Ricevere POST /api/reasoning dal server demo\n  2. Estrarre transcript, lingua, phoneNumber\n  3. Loggare la richiesta utente su console + sidebar debug\n  4. Risondere HTTP 200 con contratto standard e flag `log_only: true`\n\nContratto risposta (fase 1):\n  { answer: \"\", log_only: true, intent: \"log_only\", usage: {prompt_tokens:0,completion_tokens:0,total_tokens:0}, latency_ms: <ms> }\n",
+    "info": "# S2S reasoning flow — phase 1: log only\n\nThis flow does not generate answers or change the prompt. It:\n  1. Receives POST /api/reasoning from the client server.\n  2. Extracts the transcript, language, and phoneNumber.\n  3. Logs the user request to the console and debug sidebar.\n  4. Returns HTTP 200 with the standard contract and `log_only: true`.\n\nResponse contract (phase 1):\n  { answer: \"\", log_only: true, intent: \"log_only\", usage: {prompt_tokens:0,completion_tokens:0,total_tokens:0}, latency_ms: <ms> }\n",
     "wires": []
   },
   {
@@ -28,8 +28,8 @@
     "id": "parse-request",
     "type": "function",
     "z": "s2s-reasoning-tab",
-    "name": "Parse richiesta (log-only)",
-    "func": "// FASE 1 — LOG-ONLY: nessuna answer generata.\n// Valida e normalizza il payload in arrivo da server.py.\n// msg.req.body = { transcript, instructions, language, user_context, phoneNumber? }\n\nconst body = msg.req?.body || {};\nconst startedAt = Date.now();\n\nconst transcript = String(body.transcript || \"\").trim();\nconst instructions = String(body.instructions || \"\").trim();\nconst language = String(body.language || \"\").trim();\nconst userContext = String(body.user_context || body.user_context || \"\").trim();\nconst phoneNumber = String(body.phoneNumber || body.phone_number || msg.req?.query?.phoneNumber || \"\").trim();\n\nif (!transcript) {\n    msg.statusCode = 400;\n    msg.payload = { error: \"missing_transcript\", detail: \"transcript field is required\" };\n    return [null, msg];  // uscita 2 = errore\n}\n\nconst detectedLang = language || (transcript.match(/[áéíóúñ¿¡]/i) ? \"es-CL\" : \"en-US\");\n\nmsg.state = {\n    startedAt,\n    transcript,\n    instructionsLen: instructions.length,\n    language: detectedLang,\n    userContextLen: userContext.length,\n    phoneNumber: phoneNumber || null,\n    intent: \"log_only\",\n};\n\nmsg.payload = {\n    transcript,\n    language: detectedLang,\n    phone: phoneNumber || \"none\",\n};\n\nreturn [msg, null];",
+    "name": "Parse request (log only)",
+    "func": "// Phase 1: log only; no answer is generated.\n// Validate and normalize the payload received from server.py.\n// msg.req.body = { transcript, instructions, language, user_context, phoneNumber? }\n\nconst body = msg.req?.body || {};\nconst startedAt = Date.now();\n\nconst transcript = String(body.transcript || \"\").trim();\nconst instructions = String(body.instructions || \"\").trim();\nconst language = String(body.language || \"\").trim();\nconst userContext = String(body.user_context || body.user_context || \"\").trim();\nconst phoneNumber = String(body.phoneNumber || body.phone_number || msg.req?.query?.phoneNumber || \"\").trim();\n\nif (!transcript) {\n    msg.statusCode = 400;\n    msg.payload = { error: \"missing_transcript\", detail: \"transcript field is required\" };\n    return [null, msg];  // Output 2 is the error path.\n}\n\nconst detectedLang = language || (transcript.match(/[áéíóúñ¿¡]/i) ? \"es-CL\" : \"en-US\");\n\nmsg.state = {\n    startedAt,\n    transcript,\n    instructionsLen: instructions.length,\n    language: detectedLang,\n    userContextLen: userContext.length,\n    phoneNumber: phoneNumber || null,\n    intent: \"log_only\",\n};\n\nmsg.payload = {\n    transcript,\n    language: detectedLang,\n    phone: phoneNumber || \"none\",\n};\n\nreturn [msg, null];",
     "outputs": 2,
     "timeout": 0,
     "noerr": 0,
@@ -52,8 +52,8 @@
     "id": "log-transcript-console",
     "type": "function",
     "z": "s2s-reasoning-tab",
-    "name": "[LOG] richiesta utente",
-    "func": "// FASE 1 — Stampa la richiesta utente sul log server (Node-RED console)\n// e sul pannello debug sidebar.\n// NON produce alcuna risposta: quella arriva dal backend S2S nativo.\n\nconst state = msg.state || {};\nconst transcript = state.transcript || \"\";\nconst lang = state.language || \"\";\nconst phone = state.phoneNumber || \"none\";\nconst ts = new Date(state.startedAt || Date.now()).toISOString();\n\nconst line = `[S2S NODE_RED LOG_ONLY] ts=${ts} lang=${lang} phone=${phone} transcript=\"${transcript.replace(/\"/g, '\\\\\"')}\"`;\n\nnode.warn(line);\n\nmsg.logLine = line;\nreturn msg;",
+    "name": "[LOG] user request",
+    "func": "// Phase 1: log the user request to the Node-RED console and debug sidebar.\n// The native S2S backend generates the response; this node does not.\n\nconst state = msg.state || {};\nconst transcript = state.transcript || \"\";\nconst lang = state.language || \"\";\nconst phone = state.phoneNumber || \"none\";\nconst ts = new Date(state.startedAt || Date.now()).toISOString();\n\nconst line = `[S2S NODE_RED LOG_ONLY] ts=${ts} lang=${lang} phone=${phone} transcript=\"${transcript.replace(/\"/g, '\\\\\"')}\"`;\n\nnode.warn(line);\n\nmsg.logLine = line;\nreturn msg;",
     "outputs": 1,
     "timeout": 0,
     "noerr": 0,
@@ -89,7 +89,7 @@
     "type": "function",
     "z": "s2s-reasoning-tab",
     "name": "Build 200 (log_only)",
-    "func": "// FASE 1 — Costruisci la risposta HTTP 200.\n// Contratto: answer VUOTA + flag log_only=true.\n// Il client (main.js) vedrà log_only e NON interverrà:\n//   - NON chiama cancelActiveResponse()\n//   - NON usa appendAssistantText()\n//   - NON usa speechSynthesis\n// => la risposta vocale arriva dal backend S2S nativo.\n\nconst state = msg.state || {};\nconst latencyMs = Math.max(0, Date.now() - (state.startedAt || Date.now()));\n\nmsg.statusCode = 200;\nmsg.headers = {\n    \"Content-Type\": \"application/json; charset=utf-8\",\n    \"Cache-Control\": \"no-store\",\n};\nmsg.payload = {\n    answer: \"\",\n    log_only: true,\n    intent: \"log_only\",\n    usage: {\n        prompt_tokens: 0,\n        completion_tokens: 0,\n        total_tokens: 0,\n    },\n    latency_ms: latencyMs,\n    mcp_tools_used: [],\n    caller_profile_keys: [],\n    debug: {\n        phase: \"log_only_fase1\",\n        language: state.language || \"\",\n        phone: state.phoneNumber || null,\n        transcript_len: (state.transcript || \"\").length,\n    },\n};\n\nreturn msg;",
+    "func": "// Phase 1: build the HTTP 200 response with an empty answer and log_only=true.\n// The client leaves the native S2S response untouched: it does not call\n// cancelActiveResponse(), appendAssistantText(), or speechSynthesis.\n\nconst state = msg.state || {};\nconst latencyMs = Math.max(0, Date.now() - (state.startedAt || Date.now()));\n\nmsg.statusCode = 200;\nmsg.headers = {\n    \"Content-Type\": \"application/json; charset=utf-8\",\n    \"Cache-Control\": \"no-store\",\n};\nmsg.payload = {\n    answer: \"\",\n    log_only: true,\n    intent: \"log_only\",\n    usage: {\n        prompt_tokens: 0,\n        completion_tokens: 0,\n        total_tokens: 0,\n    },\n    latency_ms: latencyMs,\n    mcp_tools_used: [],\n    caller_profile_keys: [],\n    debug: {\n        phase: \"log_only_phase1\",\n        language: state.language || \"\",\n        phone: state.phoneNumber || null,\n        transcript_len: (state.transcript || \"\").length,\n    },\n};\n\nreturn msg;",
     "outputs": 1,
     "timeout": 0,
     "noerr": 0,
@@ -165,7 +165,7 @@
     "type": "function",
     "z": "s2s-reasoning-tab",
     "name": "Parse system-response",
-    "func": "// Riceve dal server.py la risposta TTS emessa dal backend S2S nativo.\n// msg.req.body = { tts, response_id?, item_id?, client_ip?, role?, source_event?, user_transcript?, phone? }\n// FASE 1 LOG-ONLY: nessun side-effect oltre al log.\n\nconst body = msg.req?.body || {};\nconst startedAt = Date.now();\n\nconst tts = String(body.tts || body.text || body.response || \"\").trim();\nconst responseId = String(body.response_id || body.responseId || \"\").trim() || null;\nconst itemId = String(body.item_id || body.itemId || \"\").trim() || null;\nconst clientIp = String(body.client_ip || body.clientIp || body.ip || \"\").trim() || null;\nconst role = String(body.role || \"assistant\").trim() || \"assistant\";\nconst sourceEvent = String(body.source_event || body.sourceEvent || \"\").trim() || null;\nconst userTranscript = String(body.user_transcript || body.userTranscript || \"\").trim() || null;\nconst phone = String(body.phone || body.phoneNumber || \"\").trim() || null;\n\nif (!tts) {\n    msg.statusCode = 400;\n    msg.headers = { \"Content-Type\": \"application/json\" };\n    msg.payload = { error: \"missing_tts\", detail: \"field 'tts' (or 'text'/'response') is required\" };\n    return [null, msg];\n}\n\nmsg.state = {\n    startedAt,\n    kind: \"system_response_log\",\n    role,\n    tts,\n    responseId,\n    itemId,\n    clientIp,\n    sourceEvent,\n    userTranscript,\n    phone,\n};\n\nmsg.payload = { tts, role, source: sourceEvent, client: clientIp };\nreturn [msg, null];",
+    "func": "// Receive the native S2S backend's TTS response from server.py.\n// msg.req.body = { tts, response_id?, item_id?, client_ip?, role?, source_event?, user_transcript?, phone? }\n// Phase 1: log only; no other side effects.\n\nconst body = msg.req?.body || {};\nconst startedAt = Date.now();\n\nconst tts = String(body.tts || body.text || body.response || \"\").trim();\nconst responseId = String(body.response_id || body.responseId || \"\").trim() || null;\nconst itemId = String(body.item_id || body.itemId || \"\").trim() || null;\nconst clientIp = String(body.client_ip || body.clientIp || body.ip || \"\").trim() || null;\nconst role = String(body.role || \"assistant\").trim() || \"assistant\";\nconst sourceEvent = String(body.source_event || body.sourceEvent || \"\").trim() || null;\nconst userTranscript = String(body.user_transcript || body.userTranscript || \"\").trim() || null;\nconst phone = String(body.phone || body.phoneNumber || \"\").trim() || null;\n\nif (!tts) {\n    msg.statusCode = 400;\n    msg.headers = { \"Content-Type\": \"application/json\" };\n    msg.payload = { error: \"missing_tts\", detail: \"field 'tts' (or 'text'/'response') is required\" };\n    return [null, msg];\n}\n\nmsg.state = {\n    startedAt,\n    kind: \"system_response_log\",\n    role,\n    tts,\n    responseId,\n    itemId,\n    clientIp,\n    sourceEvent,\n    userTranscript,\n    phone,\n};\n\nmsg.payload = { tts, role, source: sourceEvent, client: clientIp };\nreturn [msg, null];",
     "outputs": 2,
     "timeout": 0,
     "noerr": 0,
@@ -188,8 +188,8 @@
     "id": "log-system-response",
     "type": "function",
     "z": "s2s-reasoning-tab",
-    "name": "[LOG] risposta sistema",
-    "func": "// Stampa la risposta del sistema (TTS dal backend nativo) sul log Node-RED.\n// Formato riga unica ricercabile con grep.\nconst state = msg.state || {};\nconst tts = state.tts || \"\";\nconst role = state.role || \"assistant\";\nconst src = state.sourceEvent || \"\";\nconst user = state.userTranscript || \"\";\nconst phone = state.phone || \"none\";\nconst ts = new Date(state.startedAt || Date.now()).toISOString();\n\nconst userShort = user.length > 120 ? user.slice(0, 117) + \"...\" : user;\nconst ttsShort = tts.length > 240 ? tts.slice(0, 237) + \"...\" : tts;\nconst esc = (s) => String(s || \"\").replace(/\\\\/g, \"\\\\\\\\\").replace(/\"/g, '\\\\\"');\n\nconst line = `[S2S NODE_RED SYSTEM_RESPONSE] ts=${ts} role=${role} phone=${esc(phone)} user=\"${esc(userShort)}\" tts=\"${esc(ttsShort)}\"`;\n\nnode.warn(line);\nmsg.logLine = line;\nreturn msg;",
+    "name": "[LOG] system response",
+    "func": "// Log the native backend's TTS response to Node-RED.\n// Use one searchable line per response.\nconst state = msg.state || {};\nconst tts = state.tts || \"\";\nconst role = state.role || \"assistant\";\nconst src = state.sourceEvent || \"\";\nconst user = state.userTranscript || \"\";\nconst phone = state.phone || \"none\";\nconst ts = new Date(state.startedAt || Date.now()).toISOString();\n\nconst userShort = user.length > 120 ? user.slice(0, 117) + \"...\" : user;\nconst ttsShort = tts.length > 240 ? tts.slice(0, 237) + \"...\" : tts;\nconst esc = (s) => String(s || \"\").replace(/\\\\/g, \"\\\\\\\\\").replace(/\"/g, '\\\\\"');\n\nconst line = `[S2S NODE_RED SYSTEM_RESPONSE] ts=${ts} role=${role} phone=${esc(phone)} user=\"${esc(userShort)}\" tts=\"${esc(ttsShort)}\"`;\n\nnode.warn(line);\nmsg.logLine = line;\nreturn msg;",
     "outputs": 1,
     "timeout": 0,
     "noerr": 0,
@@ -225,7 +225,7 @@
     "type": "function",
     "z": "s2s-reasoning-tab",
     "name": "Build 200 (ack)",
-    "func": "// Risposta minimale: 200 OK + ricevuto=true.\n// Non ritorna dati.\nconst state = msg.state || {};\nconst latencyMs = Math.max(0, Date.now() - (state.startedAt || Date.now()));\nmsg.statusCode = 200;\nmsg.headers = {\n    \"Content-Type\": \"application/json; charset=utf-8\",\n    \"Cache-Control\": \"no-store\",\n};\nmsg.payload = {\n    ricevuto: true,\n    log_only: true,\n    intent: \"system_response_log\",\n    latency_ms: latencyMs,\n};\nreturn msg;",
+    "func": "// Return a minimal HTTP 200 acknowledgment with received=true.\n// No response data is returned.\nconst state = msg.state || {};\nconst latencyMs = Math.max(0, Date.now() - (state.startedAt || Date.now()));\nmsg.statusCode = 200;\nmsg.headers = {\n    \"Content-Type\": \"application/json; charset=utf-8\",\n    \"Cache-Control\": \"no-store\",\n};\nmsg.payload = {\n    received: true,\n    log_only: true,\n    intent: \"system_response_log\",\n    latency_ms: latencyMs,\n};\nreturn msg;",
     "outputs": 1,
     "timeout": 0,
     "noerr": 0,
diff --git a/s2s-reasoning-engine/package.json b/s2s-reasoning-engine/package.json
index d59038b..15b66c2 100644
--- a/s2s-reasoning-engine/package.json
+++ b/s2s-reasoning-engine/package.json
@@ -1,7 +1,7 @@
 {
   "name": "s2s-reasoning-engine",
   "version": "1.0.0",
-  "description": "Node-RED 5.0 reasoning engine per S2S/Aquachile",
+  "description": "Node-RED 5.0 reasoning engine for S2S/Aquachile",
   "main": "settings.js",
   "scripts": {
     "test": "echo \"Error: no test specified\" && exit 1"
diff --git a/s2s-reasoning-engine/settings.js b/s2s-reasoning-engine/settings.js
index f31480d..979f2e2 100644
--- a/s2s-reasoning-engine/settings.js
+++ b/s2s-reasoning-engine/settings.js
@@ -1,26 +1,24 @@
 /**
- * Node-RED 5.0 settings for s2s-reasoning-engine — LOCAL INSTALL (non Docker).
+ * Node-RED 5.0 settings for s2s-reasoning-engine — local installation.
  * File: <project_root>/s2s-reasoning-engine/.node-red/settings.js
- *     oppure  <project_root>/s2s-reasoning-engine/settings.js (master)
+ *     or      <project_root>/s2s-reasoning-engine/settings.js (source)
  *
- * Copiato automaticamente in .node-red/ da start.sh se mancante o più vecchio.
+ * start.sh copies this into .node-red/ when missing or older than the source.
  */
 
 const path = require("path");
 const fs = require("fs");
 
-// userDir è sempre <s2s-reasoning-engine>/.node-red  (lo script start.sh)
+// start.sh uses <s2s-reasoning-engine>/.node-red as its local user directory.
 const ENGINE_ROOT = path.resolve(__dirname, "..");
 const LOCAL_NODE_MODULES = path.join(ENGINE_ROOT, "node_modules");
 const USERDIR_NODE_MODULES = path.join(__dirname, "node_modules");
 
-// ── Fix per editor "tslib.es6.js 404 / net::ERR_ABORTED" ─────────────────
-// Installazioni npm locali flat (default npm 3+) spostano tslib in
-// node_modules/tslib/ (root) invece che dentro
-// @node-red/editor-client/node_modules/tslib/. L'editor di Node-RED 5
-// carica `/tslib.es6.js` dalla root HTTP: se la cartella nested non esiste,
-// torna 404. Qui aggiorniamo editor-client/public/ con i file tslib mancanti
-// a ogni avvio (sopravvive a npm reinstall se tslib è in root).
+// Fix the editor's "tslib.es6.js 404 / net::ERR_ABORTED" error.
+// Flat npm installations place tslib in the root node_modules/tslib directory
+// rather than @node-red/editor-client/node_modules/tslib. The Node-RED 5 editor
+// loads /tslib.es6.js from the HTTP root. Refresh the editor's public files at
+// startup so the workaround survives dependency reinstallation.
 (function _installTslibVendor() {
     try {
         const tslibRoot = path.join(LOCAL_NODE_MODULES, "tslib");
@@ -49,13 +47,10 @@ module.exports = {
     httpRequestTimeout: 120000,
     httpRequestLegacyMsgOverrides: true,
 
-    // ── Native HTTP helper per function node (SENZA externalModules) ─────
-    // NOTA: non usare functionExternalModules: true — in Node-RED v5 quel
-    // flag può bloccare il caricamento palette (es. "37/41 nodes loading"
-    // durante la verifica di tutti i pkg npm).
-    // Al suo posto usiamo functionGlobalContext: i moduli core Node.js sono
-    // require'd QUI nel settings.js (prima dell'avvio NR) e poi i function
-    // node li recuperano via global.get("_core_https") ecc.
+    // Native HTTP helpers for function nodes, without externalModules.
+    // functionExternalModules can stall palette loading in Node-RED 5.
+    // Load core Node.js modules here before startup and expose them through
+    // functionGlobalContext, accessed with global.get("_core_https") etc.
     functionModuleRequireAllowList: ["https","http","url","path","util","fs","os","buffer","zlib","stream","crypto"],
     functionGlobalContext: {
         _core_https: require("https"),
@@ -63,9 +58,9 @@ module.exports = {
         _core_url:   require("url"),
     },
 
-    // adminAuth: {...}  ← scommentare e valorizzare in produzione
+    // adminAuth: {...}  // Uncomment and configure for production.
 
-    // HTTPS (opzionale in produzione)
+    // HTTPS (optional for production).
     // https: {
     //   key: require("fs").readFileSync(path.join(__dirname, "privkey.pem")),
     //   cert: require("fs").readFileSync(path.join(__dirname, "fullchain.pem"))
@@ -82,20 +77,18 @@ module.exports = {
     },
     csrf: false,
 
-    // ── IMPORTANTE: caricamento nodi extra ─────────────────────────────
-    // Node-RED 5 carica i plugin NODI da:
-    //   1) {userDir}/node_modules     (nostro .node-red/node_modules)
-    //   2) {nodesDir}                 (installazione root del progetto)
+    // Additional node loading: Node-RED 5 looks for plugins in:
+    //   1) {userDir}/node_modules     (our .node-red/node_modules)
+    //   2) {nodesDir}                 (the project-root installation)
     //   3) npm global
-    // Senza nodesDir i pacchetti installati nella ROOT del progetto non
-    // vengono trovati.
+    // Set nodesDir so packages installed at the project root are discovered.
     nodesDir: LOCAL_NODE_MODULES,
 
     externalModules: {
-        autoInstall: true,            // auto-installa nodi mancanti al boot
+        autoInstall: true,            // Install missing nodes at startup.
         autoInstallRetry: 3,
         palette: {
-            allowInstall: true,       // permette Install dall'editor
+            allowInstall: true,       // Allow installation from the editor.
             allowUpload:  true,
             modules: ["node-red-contrib-openai", "node-red-contrib-cache", "node-red-node-rbe"],
             allowList: ["node-red-contrib-*", "node-red-node-*"],
diff --git a/s2s-reasoning-engine/start.sh b/s2s-reasoning-engine/start.sh
index 2b066ff..6299059 100755
--- a/s2s-reasoning-engine/start.sh
+++ b/s2s-reasoning-engine/start.sh
@@ -1,12 +1,12 @@
 #!/usr/bin/env bash
 # =============================================================
-#  start.sh — Avvia Node-RED 5.0 in locale per s2s-reasoning-engine
+#  start.sh — Run Node-RED 5.0 locally for s2s-reasoning-engine
 #
-#  Uso:
-#      ./start.sh                    # porta default 1881
-#      PORT=1900 ./start.sh          # porta custom
-#      LOG_LEVEL=debug ./start.sh    # log più dettagliato
-#      DEBUG=nodes:* ./start.sh      # debug Node-RED interno
+#  Usage:
+#      ./start.sh                    # default port 1881
+#      PORT=1900 ./start.sh          # custom port
+#      LOG_LEVEL=debug ./start.sh    # detailed logging
+#      DEBUG=nodes:* ./start.sh      # internal Node-RED diagnostics
 #  Stop:  Ctrl+C
 # =============================================================
 set -euo pipefail
@@ -17,8 +17,8 @@ PARENT_DIR="$(dirname "$ROOT_DIR")"
 cd "$ROOT_DIR"
 
 # ----------------------------------------------------------
-# 1) Carica env: prima locale .env (se esiste) poi padre ../.env
-#    Il file locale sovrascrive il padre se c'è lo stesso var.
+# 1) Load the local .env first, then the parent ../.env when present.
+#    The parent file takes precedence when both define the same variable.
 # ----------------------------------------------------------
 set -a
 if [ -f "$ROOT_DIR/.env" ]; then
@@ -34,7 +34,7 @@ fi
 set +a
 
 # ----------------------------------------------------------
-# 2) Parametri runtime Node-RED
+# 2) Node-RED runtime parameters
 # ----------------------------------------------------------
 PORT="${PORT:-${NODE_RED_PORT:-1881}}"
 export PORT
@@ -43,11 +43,11 @@ export NODE_RED_LOG_LEVEL="${LOG_LEVEL:-${NODE_RED_LOG_LEVEL:-info}}"
 export NODE_RED_CREDENTIAL_SECRET="${NODE_RED_CREDENTIAL_SECRET:-s2s-reasoning-local-dev}"
 export FLOWS="${FLOWS:-$ROOT_DIR/.node-red/flows.json}"
 
-# UserDir locale (tutto dentro la cartella corrente, NO ~/.node-red)
+# Local user directory; keep state here rather than in ~/.node-red.
 USERDIR="${USERDIR:-$ROOT_DIR/.node-red}"
 SETTINGS="${SETTINGS:-$USERDIR/settings.js}"
 
-# Assicura che la userDir esista e i file base siano presenti.
+# Create the user directory and refresh its configuration from the source files.
 mkdir -p "$USERDIR"
 if [ ! -f "$SETTINGS" ] || [ "$ROOT_DIR/settings.js" -nt "$SETTINGS" ]; then
   cp -f "$ROOT_DIR/settings.js" "$SETTINGS"
@@ -58,15 +58,15 @@ if [ ! -f "$FLOWS" ] || [ "$ROOT_DIR/flows.json" -nt "$FLOWS" ]; then
   echo "[init] copied flows.json -> $FLOWS"
 fi
 
-# Verifica node_modules installati
+# Check that the local Node-RED dependencies are installed.
 if [ ! -d "$ROOT_DIR/node_modules/node-red" ]; then
-  echo "[init] node_modules non trovati. Avvio npm install..."
+  echo "[init] node_modules was not found. Running npm install..."
   npm install --no-audit --no-fund
 fi
 
 echo ""
 echo "╔════════════════════════════════════════════════════════════╗"
-echo "║   s2s-reasoning-engine  —  Node-RED v5 locale             ║"
+echo "║   s2s-reasoning-engine  —  Local Node-RED v5              ║"
 echo "╠════════════════════════════════════════════════════════════╣"
 echo "║   Editor:   http://localhost:${PORT}/                      ║"
 echo "║   API:      http://localhost:${PORT}/api/reasoning         ║"
@@ -76,7 +76,7 @@ echo "╚═══════════════════════
 echo ""
 
 # ----------------------------------------------------------
-# 3) Avvio Node-RED
+# 3) Start Node-RED
 # ----------------------------------------------------------
 exec "$ROOT_DIR/node_modules/.bin/node-red" \
   --userDir "$USERDIR" \
diff --git a/speech_to_speech/LLM/chat_completions_language_model.py b/speech_to_speech/LLM/chat_completions_language_model.py
index 17d2d25..aad2b2a 100644
--- a/speech_to_speech/LLM/chat_completions_language_model.py
+++ b/speech_to_speech/LLM/chat_completions_language_model.py
@@ -196,7 +196,7 @@ class ChatCompletionsApiModelHandler(BaseOpenAICompatibleHandler):
         if self.stream:
             create_kwargs["stream_options"] = {"include_usage": True}
         
-        # Svuota i parametri dei tool per evitare il blocco 400 di NVIDIA NIM
+        # Remove tool parameters to avoid NVIDIA NIM's HTTP 400 response.
         create_kwargs.pop("tools", None)
         create_kwargs.pop("tool_choice", None)
         
diff --git a/speech_to_speech/LLM/lm_output_processor.py b/speech_to_speech/LLM/lm_output_processor.py
index c1fec13..c1d5555 100644
--- a/speech_to_speech/LLM/lm_output_processor.py
+++ b/speech_to_speech/LLM/lm_output_processor.py
@@ -4,7 +4,7 @@ LLM Output Processor
 Intercepts LLM output to:
 1. Extract tool calls and send them via text_output_queue
 2. Forward clean text to TTS pipeline
-3. 2026-09-25: SANITIZE APIPILOT internal markers before clients / TTS (anti-leak tecnico)
+3. Sanitize ApiPilot internal markers before sending output to clients or TTS
 """
 
 from __future__ import annotations
@@ -17,16 +17,15 @@ from queue import Queue
 from speech_to_speech.baseHandler import BaseHandler
 from speech_to_speech.pipeline.events import AssistantTextEvent, ResponseFailedEvent, TokenUsageEvent
 
-# 2026-09-25 SANITIZE APIPILOT CALL/RESULT markers in LLM output BEFORE:
-#   (a) AssistantTextEvent viene mandato ai client WS (e loggato come <<< TEXT:/ASSISTANT:)
-#   (b) TTSInput viene mandato a Qwen3-TTS (che lo pronuncerebbe ad alta voce).
-# Formati osservati reali oggi (upstream Vocero start_pipeline_rag):
-#   1) <<<APIPILOT_CALL:NAME=tool,ARGUMENTS=json>>>   standard 3x
+# Sanitize ApiPilot CALL/RESULT markers before emitting AssistantTextEvent
+# to WebSocket clients or TTSInput to Qwen3-TTS, which would speak the markers.
+# Observed formats from upstream Vocero start_pipeline_rag:
+#   1) <<<APIPILOT_CALL:NAME=tool,ARGUMENTS=json>>>   standard triple brackets
 #   2) <APIPILOT_CALL:NAME=get_user_briefing,ARGUMENTS={"format":"voice"}
-#                                 singolo '<' '>' + args inventati da AI (format=voice)
-#   3) <<<APIPILOT_CALL:...}>  \n>>                      spezzato multi-riga
-#   4) >>>APIPILOT_CALL:...<<<                            invertito (errore sintassi AI)
-#   5) <<<APIPILOT_RESULT:PASS2>>> + blocco result.
+#                                 single brackets and model-generated arguments
+#   3) <<<APIPILOT_CALL:...}>  \n>>                      split across lines
+#   4) >>>APIPILOT_CALL:...<<<                            inverted brackets
+#   5) <<<APIPILOT_RESULT:PASS2>>> followed by a result block
 _APIPILOT_CALL_NORM = re.compile(
     r"[<]{1,3}\s*APIPILOT_CALL:NAME=([A-Za-z0-9_.-]+),ARGUMENTS=(.*?)[>]{1,3}",
     re.IGNORECASE | re.DOTALL,
@@ -64,7 +63,7 @@ def _sanitize_apipilot_before_client_and_tts(text: str) -> tuple[str, bool, str]
     if _APIPILOT_RESULT.search(new_text):
         new_text = _APIPILOT_RESULT.sub(" ", new_text)
         found_result = True
-    # safety catchall frammenti marker senza wrapper (se marker troncato mid-stream)
+    # Catch marker fragments without a wrapper, including mid-stream truncation.
     low = new_text.lower()
     if "apipilot" in low and ("call" in low or "result" in low or "name=" in low or "arguments=" in low):
         new_text = re.sub(r"(?i)\bAPIPILOT(?:_CALL|_RESULT)?\b", " ", new_text)
@@ -184,8 +183,8 @@ class LMOutputProcessor(BaseHandler[LLMOut, TTSIn]):
 
         logger.debug(f"LM processor: text='{lm_output.text}', tools={lm_output.tools}")
 
-        # 2026-09-25 SANITIZE SINGOLO PUNTO CENTRALE: PRIMA di AssistantTextEvent (client/log)
-        #    E PRIMA di TTSInput (Qwen3-TTS che pronuncerebbe marker APIPILOT CALL).
+        # Sanitize centrally before AssistantTextEvent and TTSInput so neither
+        # clients nor Qwen3-TTS receive internal ApiPilot markers.
         clean_text = lm_output.text
         any_sanitized = False
         sanitize_tag = ""
@@ -193,14 +192,14 @@ class LMOutputProcessor(BaseHandler[LLMOut, TTSIn]):
             clean_text, any_sanitized, sanitize_tag = _sanitize_apipilot_before_client_and_tts(clean_text)
             if any_sanitized:
                 logger.warning(
-                    "[LM-OUTPUT-APIPILOT-SANITIZE] %s — tool=%s rawLen=%d cleanLen=%d (rimosso / sostituito con placeholder spagnolo PRIMA di client + TTS).",
+                    "[LM-OUTPUT-APIPILOT-SANITIZE] %s — tool=%s rawLen=%d cleanLen=%d (removed or replaced with the Spanish placeholder before client/TTS output).",
                     sanitize_tag or "-",
                     (sanitize_tag if sanitize_tag else "marker"),
                     len(lm_output.text or ""),
                     len(clean_text or ""),
                 )
-                # evita che lo stesso chunk (marker solo) arrivi a TTS come "" → Hello.
-                # Se dopo sanitize testo vuoto MA avevamo trovato marker → placeholder.
+                # Use the placeholder when sanitization removes the entire chunk,
+                # avoiding empty text that would trigger the TTS greeting fallback.
                 if not clean_text.strip():
                     clean_text = _APIPILOT_SPANISH_PLACEHOLDER
 
diff --git a/speech_to_speech/TTS/qwen3_tts_handler.py b/speech_to_speech/TTS/qwen3_tts_handler.py
index 7718b91..e8dc21e 100644
--- a/speech_to_speech/TTS/qwen3_tts_handler.py
+++ b/speech_to_speech/TTS/qwen3_tts_handler.py
@@ -13,16 +13,15 @@ import re
 import tempfile
 import unicodedata
 
-# 2026-09-25 SANITIZE APIPILOT MARKERS PRIMA DI TTS (anti-leak pronunciato da Qwen3).
-#   Lato server S2S Python abbiamo gia' gate + sanitize ma come DOPPIA RETE
-#   di sicurezza sanitizziamo DIRETTAMENTE il testo che entra in Qwen3-TTS.
-#   Formati osservati reali oggi:
-#     (a) <<<APIPILOT_CALL:NAME=tool,ARGUMENTS=json>>>    standard 3 parentesi
+# Sanitize ApiPilot markers directly before TTS as an additional safeguard
+# alongside the S2S relay's audio gating and sanitization.
+# Observed formats:
+#     (a) <<<APIPILOT_CALL:NAME=tool,ARGUMENTS=json>>>    standard triple brackets
 #     (b) <APIPILOT_CALL:NAME=tool,ARGUMENTS={"format":"voice"}
-#                                                         singolo < > (caso user oggi)
-#     (c) <<<APIPILOT_CALL:...}>   \n>>                    spezzato piu' righe
-#     (d) >>>APIPILOT_CALL:...<<<                          invertito
-#   Regola: CALL -> placeholder spagnolo (frase naturale utente), RESULT -> strip.
+#                                                         single brackets
+#     (c) <<<APIPILOT_CALL:...}>   \n>>                    split across lines
+#     (d) >>>APIPILOT_CALL:...<<<                          inverted brackets
+# Replace CALL with a natural Spanish utterance; strip RESULT markers.
 _APIPILOT_CALL_NORMAL_RE = re.compile(
     r"[<]{1,3}\s*APIPILOT_CALL:NAME=([A-Za-z0-9_.-]+),ARGUMENTS=(.*?)[>]{1,3}",
     re.IGNORECASE | re.DOTALL,
@@ -39,7 +38,7 @@ _APIPILOT_SPANISH_PLACEHOLDER = "Voy a consultar tus datos, un momento por favor
 
 
 def _tts_sanitize_apipilot_markers(text: str) -> tuple[str, bool, str]:
-    """Rimuove marker APIPILOT dal testo TTS.
+    """Remove ApiPilot markers from TTS text.
 
     Returns (sanitized_text, found_any, log_tag).
     """
@@ -48,7 +47,7 @@ def _tts_sanitize_apipilot_markers(text: str) -> tuple[str, bool, str]:
     found_call = False
     found_result = False
     tool_name = ""
-    # 1) marker CALL standard + invertito -> placeholder spagnolo
+    # 1) Replace standard/inverted CALL markers with the Spanish placeholder.
     def _repl_call(m: re.Match) -> str:
         nonlocal found_call, tool_name
         found_call = True
@@ -62,11 +61,11 @@ def _tts_sanitize_apipilot_markers(text: str) -> tuple[str, bool, str]:
     text2 = _APIPILOT_CALL_NORMAL_RE.sub(_repl_call, text)
     if not found_call:
         text2 = _APIPILOT_CALL_INVERTED_RE.sub(_repl_call, text2)
-    # 2) marker RESULT -> strip silenzioso (non sono pronunciabili)
+    # 2) Strip RESULT markers silently; they must not be spoken.
     if _APIPILOT_RESULT_RE.search(text2):
         found_result = True
         text2 = _APIPILOT_RESULT_RE.sub(" ", text2)
-    # 3) safety: FRAMMENTI marker singoli che non hanno wrapper completo
+    # 3) Catch marker fragments without a complete wrapper.
     low = text2.lower()
     if "apipilot" in low and ("call" in low or "result" in low):
         import re as _re_sf
@@ -782,18 +781,16 @@ class Qwen3TTSHandler(BaseHandler[TTSIn, TTSOut]):
         coalesced_text, _language_code, _saw_end_of_response = self._coalesce_pending_tts_input(tts_input)
 
         raw_text = coalesced_text or "Hello."
-        # 2026-09-25 SANITIZE APIPILOT PRIMA DI TTS (doppia rete sicurezza):
-        #   Anche se lato server S2s Python abbiamo gia' gate audio drop + sanitize,
-        #   Qwen3-TTS puo' ricevere marker per race / nuovi formati. Quindi QUI
-        #   eliminiamo / sostituiamo con placeholder PRIMA di chiamare generate().
+        # A race or a new marker format can bypass relay sanitization. Strip or
+        # replace markers again before passing text to the TTS model.
         text, found_marker, sanitize_tag = _tts_sanitize_apipilot_markers(raw_text)
         if found_marker:
             logger.warning(
-                "[TTS-APIPILOT-SANITIZE] marker=%s rawLen=%d sanitizedLen=%d → sostituito con placeholder spagnolo / strip.",
+                "[TTS-APIPILOT-SANITIZE] marker=%s rawLen=%d sanitizedLen=%d → replaced with the Spanish placeholder or stripped.",
                 sanitize_tag, len(raw_text or ""), len(text or ""),
             )
         if not text.strip():
-            # Safety se il marker era l'unica cosa: ripetiamo placeholder invece di Hello.
+            # Use the Spanish placeholder when the marker was the entire utterance.
             text = _APIPILOT_SPANISH_PLACEHOLDER
 
         model_type = self._model_type()
diff --git a/speech_to_speech/api/openai_realtime/handlers/session.py b/speech_to_speech/api/openai_realtime/handlers/session.py
index 7b7e425..1901552 100644
--- a/speech_to_speech/api/openai_realtime/handlers/session.py
+++ b/speech_to_speech/api/openai_realtime/handlers/session.py
@@ -30,7 +30,7 @@ class SessionHandler(RealtimeBaseHandler):
         """
         s = event.session
 	
-	# Forza il bypass della voce inviata dal browser
+        # Ignore the voice supplied by the browser.
         if hasattr(s, "voice") and s.voice is not None:
             s.voice = None
         elif isinstance(s, dict) and "voice" in s:
diff --git a/speech_to_speech/api/openai_realtime/service.py b/speech_to_speech/api/openai_realtime/service.py
index 98567aa..10d785d 100644
--- a/speech_to_speech/api/openai_realtime/service.py
+++ b/speech_to_speech/api/openai_realtime/service.py
@@ -277,11 +277,10 @@ class RealtimeService:
         try:
             return model_cls.model_validate(raw)  # type: ignore[return-value]
         except ValidationError as e:
-            # ── Retrocompatibilità session.update ─────────────────────────────────
-            # Il formato standard OpenAI Realtime GA annida instructions/tools/tool_choice
-            # DENTRO "session": { ... }. Per tollerare anche client che li mandano
-            # alla RADICE (es. bug prima della Fase 2 MCP), ricostruiamo qui il payload
-            # corretto e riproviamo la validazione. Funziona SOLO per session.update.
+            # Backward-compatible session.update parsing.
+            # OpenAI Realtime GA nests instructions/tools/tool_choice in "session".
+            # Accept older clients that send them at the root by rebuilding the
+            # nested payload and retrying validation, only for session.update.
             if event_type == "session.update":
                 try:
                     raw_dict = dict(raw) if not isinstance(raw, dict) else raw
@@ -290,7 +289,7 @@ class RealtimeService:
                         normalized_inner = dict(session_inner)
                     else:
                         normalized_inner = {}
-                    # Promuovi campi noti dalla root → inner se mancanti (fallback flat)
+                    # Promote known root fields into the inner session when missing.
                     SESSION_KNOWN_TOP_LEVEL = (
                         "instructions",
                         "tools",
diff --git a/speech_to_speech/arguments_classes/chat_tts_arguments.py b/speech_to_speech/arguments_classes/chat_tts_arguments.py
index 9390c1d..4d1caa5 100644
--- a/speech_to_speech/arguments_classes/chat_tts_arguments.py
+++ b/speech_to_speech/arguments_classes/chat_tts_arguments.py
@@ -14,6 +14,6 @@ class ChatTTSHandlerArguments:
     chat_tts_chunk_size: int = field(
         default=512,
         metadata={
-            "help": "Sets the size of the audio data chunk processed per cycle, balancing playback latency and CPU load.. Default is 512。."
+            "help": "Sets the size of the audio data chunk processed per cycle, balancing playback latency and CPU load. Default is 512."
         },
     )
diff --git a/start_ui.sh b/start_ui.sh
index 7ebdeea..12a57f0 100755
--- a/start_ui.sh
+++ b/start_ui.sh
@@ -13,32 +13,32 @@ fi
 S2S_PROXY_TARGET="${S2S_PROXY_TARGET:-ws://ai-server:12345/v1/realtime}"
 
 if ! command -v python3 >/dev/null 2>&1; then
-  echo "Errore: python3 non trovato."
+  echo "Error: python3 was not found."
   exit 1
 fi
 
 if [ ! -d "$VENV_DIR" ]; then
-  echo "Creazione ambiente virtuale in .venv..."
+  echo "Creating the virtual environment in .venv..."
   python3 -m venv "$VENV_DIR"
 fi
 
 source "$VENV_DIR/bin/activate"
 
 if [ ! -f "$REQ_FILE" ]; then
-  echo "Errore: file requirements non trovato: $REQ_FILE"
+  echo "Error: requirements file was not found: $REQ_FILE"
   exit 1
 fi
 
 if ! python -c "import fastapi, uvicorn, httpx, huggingface_hub, dotenv" >/dev/null 2>&1; then
-  echo "Installazione dipendenze da s2s-client/requirements.txt..."
+  echo "Installing dependencies from s2s-client/requirements.txt..."
   python -m pip install -r "$REQ_FILE"
 fi
 
 export S2S_PROXY_TARGET
 
-echo "💻 Avvio dell'interfaccia S2S Client UI (Porta $UI_PORT)..."
-echo "🔌 Proxy realtime verso $S2S_PROXY_TARGET"
-echo " Premi Ctrl+C in questo terminale per fermarla."
+echo "💻 Starting the S2S client UI (port $UI_PORT)..."
+echo "🔌 Realtime proxy target: $S2S_PROXY_TARGET"
+echo " Press Ctrl+C in this terminal to stop it."
 echo "----------------------------------------------------"
 
 cd "$ROOT_DIR"