fix(controlBrowser): never report moveMouse/search success without a real move

moveMouse returned ok:true even when humanHover did nothing (no on-screen box)
or the selector never matched — recreating the "claims it moved but didn't"
bug. Now: humanHover returns a boolean (and brings the element into view first);
moveMouse returns ok:false when the target isn't found or has no on-screen box,
and when site=naver/... whose box isn't on the current page it navigates to the
site home first before hovering. search now reports input=human|api-fallback|api
so a silent fallback to cursor-less DOM input is visible, and the tool surfaces
that note in the reply instead of implying a human-like search happened.

.env.example

@@ -34,23 +34,18 @@ WHISPER_DEVICE=cuda
 WHISPER_COMPUTE_TYPE=float16
 # Optional explicit Piper voice model (.onnx). If empty, the jarvis default is used.
 TTS_PIPER_MODEL_PATH=
-# TTS engine: "xtts" (default) uses the Coqui XTTS-v2 natural Korean voice
-# served by the warm xtts-worker. Set to "piper" to use the English Piper voice
-# directly. (MeloTTS was removed; "melo" only works with an out-of-band worker.)
-TTS_ENGINE=xtts
-# XTTS-v2 voice settings. Speaker is any built-in studio voice; "Ana Florence"
-# is a natural female voice. Language is the synthesis language (ko = Korean).
-XTTS_SPEAKER=Ana Florence
-XTTS_LANGUAGE=ko
-XTTS_DEVICE=cuda
-# Where the bridge reaches the in-container XTTS worker, and how long it waits
-# for a synthesis (XTTS is slower than Melo: ~1-2s/sentence on GPU).
-XTTS_WORKER_URL=http://127.0.0.1:8771
-XTTS_TIMEOUT=30
-# Neural-only by default: if XTTS synthesis fails the bridge returns no audio
-# rather than speaking Korean through the English Piper voice (which mangles it).
-# Set to 1 only if you explicitly want the Piper fallback.
-XTTS_FALLBACK_PIPER=0
+# TTS engine: "edge" (default) uses Microsoft Edge TTS, a natural Korean neural
+# voice. Set to "piper" for the offline English voice. NOTE: edge is ONLINE —
+# reply text is sent to Microsoft's servers and needs internet.
+TTS_ENGINE=edge
+# Edge voice + speaking rate. Rate is a percentage (+45% ≈ 1.45×). Korean voices:
+# ko-KR-HyunsuMultilingualNeural (M), ko-KR-InJoonNeural (M), ko-KR-SunHiNeural (F).
+EDGE_TTS_VOICE=ko-KR-HyunsuMultilingualNeural
+EDGE_TTS_RATE=+45%
+# Neural-only by default: if synthesis fails the bridge returns no audio rather
+# than speaking Korean through the English Piper voice. Set to 1 to allow the
+# Piper fallback.
+MELO_FALLBACK_PIPER=0
 
 # ---------------------------------------------------------------------------
 # Jarvis brain (Ollama-backed). In Docker these populate the rendered
@@ -64,11 +59,15 @@ OLLAMA_BASE_URL=http://127.0.0.1:11434
 # free-form chit-chat. Swap back to qwen3:8b for the strongest tool-calling.
 OLLAMA_CHAT_MODEL=qwen2.5:3b
 # Model for the auxiliary small-model calls: intent judge, tool router, weather
-# place extraction, query decomposition. BLANK (default) reuses OLLAMA_CHAT_MODEL
-# so the stack runs on one already-warm model. The code's built-in default
-# (gemma4:e2b) is NOT pulled by this stack, so leaving this unset previously made
-# every router/extractor call silently fail. Only set this if you also pull the
-# model into Ollama.
+# place extraction, query decomposition. These are classification/JSON calls,
+# NOT the spoken answer, so a small fast model here cuts 2-3 big-model round
+# trips per command without touching answer quality. BLANK uses the stack
+# default qwen2.5:3b, which ollama-init pulls automatically. Set it equal to
+# OLLAMA_CHAT_MODEL to run everything on one resident model instead (saves VRAM
+# at the cost of slower routing when the chat model is large).
+# NEVER set this LARGER than OLLAMA_CHAT_MODEL: the auxiliary calls would then
+# run on the bigger, slower model and add latency to every command (the exact
+# opposite of the split's purpose). Keep it <= the chat model, blank, or equal.
 OLLAMA_INTENT_MODEL=
 OLLAMA_EMBED_MODEL=nomic-embed-text
 WHISPER_MODEL=small
@@ -231,7 +230,8 @@ COMPOSE_FILE=docker-compose.yml:docker-compose.gpu-linux.yml
 # OLLAMA_CHAT_MODEL=qwen2.5:7b   # quality (needs ~5GB VRAM + whisper small)
 # OLLAMA_CHAT_MODEL=qwen2.5:3b   # speed (fits easily, faster on 8GB GPUs)
 # WHISPER_MODEL=small            # small frees VRAM for a bigger LLM; medium=more accurate
-# XTTS_DEVICE=cuda               # cpu if no GPU on the bot host (XTTS is slow on CPU)
+# STT_BEAM_SIZE=5                # beam search (5) > greedy (1) for accuracy; lower for speed
+# MELO_DEVICE=cuda               # cpu if no GPU on the bot host
 
 # --- Settings web UI (http://localhost:8765/settings on the bot host) ---
 # To reach it, expose the bridge to the host loopback:

CLAUDE.md

@@ -1,6 +1,6 @@
 Data privacy comes first, always.
 
-All user-facing command line output should make use of emojis. Especially an initial emoji to start off the lines that depict what the line is about. Output should make use of indentation spacing to establish a visual hierarchy and aim to make output as easy to sift through as possible. Exception: Windows .bat scripts cannot use emojis (cmd.exe doesn't render Unicode properly).
+This assistant is used through a Discord bot with voice (TTS) replies, not a CLI. Do not add emojis to user-facing assistant output. Keep output plain and readable. (Runtime assistant behaviour lives in `agents/*.md`, which is injected into the reply LLM's prompt.)
 
 Any important point in our logical flows should have debug logs using the `debug_log` method from `src/jarvis/debug.py`. Avoid excessive logging to keep the logs easily readable and actionable.
 

Dockerfile

@@ -65,21 +65,14 @@ RUN ls -d /opt/venv/lib/python*/site-packages/nvidia/cublas/lib \
         > /etc/ld.so.conf.d/nvidia-cu12.conf 2>/dev/null \
     && /sbin/ldconfig || true
 
-# --- Korean voice: Coqui XTTS-v2 (separate /opt/xtts py3.11 venv; see
-#     setup-xtts.sh). Natural female Korean ("Ana Florence"); replaces MeloTTS.
-#     Heavy layer (torch cu128 + Coqui TTS + the baked XTTS-v2 model); placed
-#     before the app COPY so it stays cached across source-only changes. ---
-COPY docker/setup-xtts.sh /app/docker/setup-xtts.sh
-# Strip CR before running: a Windows checkout (autocrlf) yields CRLF, which makes
-# bash read `set -euxo pipefail\r` and abort with "set: pipefail: invalid option
-# name". .gitattributes pins *.sh to LF, but this keeps the build working even on
-# a not-yet-renormalised working tree.
-RUN sed -i 's/\r$//' /app/docker/setup-xtts.sh && bash /app/docker/setup-xtts.sh
+# --- Korean voice: Microsoft Edge TTS (online neural). No model is baked — the
+#     `edge-tts` pip package (in requirements-bridge.txt) calls the MS service at
+#     runtime and the bridge transcodes the MP3 to PCM16 with ffmpeg. No heavy
+#     TTS build layer is needed. ---
 
 # --- Human input + window management for the on-screen Chrome control tool.
-#     Placed AFTER the heavy TTS layer so it doesn't bust that cache. xdotool
-#     injects real X pointer/keyboard events (visible cursor, char-by-char
-#     typing) into the broadcast; wmctrl lists/moves windows. ---
+#     xdotool injects real X pointer/keyboard events (visible cursor,
+#     char-by-char typing) into the broadcast; wmctrl lists/moves windows. ---
 RUN apt-get update && apt-get install -y --no-install-recommends \
       xdotool wmctrl \
     && rm -rf /var/lib/apt/lists/*

README.md

@@ -69,7 +69,7 @@ docker compose -f docker-compose.yml -f docker-compose.gpu-linux.yml up -d --bui
 docker compose -f docker-compose.yml -f docker-compose.gpu-windows.yml up -d --build
 
 # ── GPU 없이 (CPU 전용 호스트) ──
-#   .env 에 WHISPER_DEVICE=cpu, XTTS_DEVICE=cpu 를 넣고 베이스만 사용
+#   .env 에 WHISPER_DEVICE=cpu 를 넣고 베이스만 사용
 docker compose up -d --build
 ```
 
@@ -87,7 +87,7 @@ COMPOSE_FILE=docker-compose.yml;docker-compose.gpu-windows.yml
 > Linux와 Windows는 GPU를 컨테이너에 넣는 방식이 달라서 override 파일이 갈립니다. Linux는 CDI(`devices: nvidia.com/gpu=all`), Windows(Docker Desktop)는 Compose의 `deploy.resources.reservations.devices`(`driver: nvidia`)를 씁니다. 호스트 사전 준비는 아래 "GPU 가속" 절 참고.
 
 `docker compose up` 한 번이면 자동으로:
-- Ollama 서버가 뜨고, `ollama-init`이 채팅/임베딩 모델을 **자동 pull**
+- Ollama 서버가 뜨고, `ollama-init`이 채팅/보조(의도·라우팅)/임베딩 모델을 **자동 pull** (보조 모델 `OLLAMA_INTENT_MODEL`은 기본 `qwen2.5:3b`로, 큰 채팅 모델은 답변에만 쓰고 내부 분류 호출은 이 작은 모델이 처리)
 - VNC+XFCE 데스크톱 + 크롬 + Python 브릿지가 기동
 - Whisper STT 모델 / Piper TTS 음성 자동 다운로드(볼륨에 캐시)
 
@@ -113,7 +113,7 @@ docker compose up -d          # 유저봇이 로그인해 지정 음성채널에
 
 ### GPU 가속 (OS별)
 
-LLM(Ollama), Whisper STT, XTTS-v2 TTS가 GPU에서 돕니다(env 기본 `WHISPER_DEVICE=cuda`, `XTTS_DEVICE=cuda`). NVIDIA Blackwell(sm_120, 예: RTX 5050/5070Ti)에서 검증: 컨테이너 내 torch cu128 CUDA 동작, Ollama GPU 오프로드, faster-whisper float16, XTTS-v2 GPU 합성 모두 확인.
+LLM(Ollama)과 Whisper STT가 GPU에서 돕니다(env 기본 `WHISPER_DEVICE=cuda`). TTS는 기본값이 Edge TTS(온라인 한국어 음성)라 GPU를 쓰지 않습니다. NVIDIA Blackwell(sm_120, 예: RTX 5050/5070Ti)에서 검증: 컨테이너 내 torch cu128 CUDA 동작, Ollama GPU 오프로드, faster-whisper float16 모두 확인.
 
 GPU는 위 "실행 — Docker"의 OS별 override 파일로 켜집니다. 호스트 사전 준비는 OS마다 다릅니다:
 
@@ -137,7 +137,7 @@ docker run --rm --device nvidia.com/gpu=all ubuntu nvidia-smi -L   # GPU 보이
 **공통:**
 
 - 모델: 베이스 compose 기본은 `qwen2.5:3b`(8GB VRAM에서 도구호출 안정적). 더 무겁게(`qwen2.5:7b`, `qwen3:8b` 등) 쓰려면 `.env`의 `OLLAMA_CHAT_MODEL` 변경.
-- **GPU가 없거나 인식 실패 시 자동으로 CPU 폴백**(Whisper)하므로 안전합니다. 명시적으로 CPU만 쓰려면 override 파일 없이 베이스만 올리고 `.env`에 `WHISPER_DEVICE=cpu`, `XTTS_DEVICE=cpu`를 두세요.
+- **GPU가 없거나 인식 실패 시 자동으로 CPU 폴백**(Whisper)하므로 안전합니다. 명시적으로 CPU만 쓰려면 override 파일 없이 베이스만 올리고 `.env`에 `WHISPER_DEVICE=cpu`를 두세요.
 
 - 데이터(메모리 DB), Whisper 캐시, Piper 음성은 named volume에 영속됩니다.
 - 셀프봇 영상 송출 의존성은 이미지에 기본 포함하지 않습니다. 쓰려면 컨테이너에서 `cd /app/bot && bun add discord.js-selfbot-v13 @dank074/discord-video-stream` 후 재시작(또는 Dockerfile에 추가).
@@ -243,7 +243,7 @@ cd bot; bun run register; bun run start   # 창 2: (일반 봇이면) 슬래시
 - `BRIDGE_URL` — 봇이 호출할 브릿지 주소 (기본 `http://127.0.0.1:8765`)
 - `STREAM_BACKEND`, `DISCORD_SELFBOT_TOKEN`, `NOVNC_URL` — 화면 송출
 - `VNC_DISPLAY=:1`, `VNC_RESOLUTION`, `VNC_FRAMERATE`, `VNC_BITRATE_KBPS` — 캡처
-- `WHISPER_DEVICE/COMPUTE_TYPE`, `XTTS_DEVICE` — GPU 호스트면 `cuda`/`float16`, CPU 전용이면 `cpu`(GPU 자체는 OS별 override compose 파일로 켬)
+- `WHISPER_DEVICE/COMPUTE_TYPE` — GPU 호스트면 `cuda`/`float16`, CPU 전용이면 `cpu`(GPU 자체는 OS별 override compose 파일로 켬)
 - `OLLAMA_CHAT_MODEL` — 두뇌 LLM (기본 `qwen2.5:3b`)
 - `COMPOSE_FILE` — OS별 GPU override를 매번 `-f`로 안 치고 자동 적용 (위 "실행 — Docker" 참고)
 - `output_language` — 출력 언어 고정(비우면 사용자 언어). 설정 웹 UI(`/settings`)에서 바꾸면 env 기본값보다 우선하며 컨테이너 재생성 후에도 유지됩니다.

agents/llm.md

@@ -0,0 +1,13 @@
+# 자비스 운영자 지시
+
+- 너의 이름은 자비스다.
+- 모든 답변은 음성(TTS)으로 읽혀 나간다. 그러니 무조건 한 문장으로만 답한다. 두 문장 이상 쓰지 않는다. 목록, 마크다운, 이모지, 그리고 소리 내어 읽기 어려운 특수문자는 쓰지 않는다.
+- 정해진 문구에만 반응하지 말고, 실제 사람처럼 말의 뉘앙스와 맥락으로 의도를 알아듣고 처리한다.
+
+화면 속 크롬(방송 화면)에서 유튜브를 다룰 때 (화면에 보여야 하므로 반드시 on-screen 브라우저 제어 도구로 수행한다):
+
+- "유튜브 켜줘" → 방송 크롬에서 유튜브를 연다.
+- "유튜브에서 OO 검색해줘" → 유튜브로 가서 검색창에 OO를 사람이 직접 타이핑하듯 입력하고 검색한다.
+- "위에서 N번째 영상 재생해줘" 또는 "왼쪽에서 N번째 영상 재생해줘" → 검색 결과 목록에서 그 위치의 영상을 재생한다.
+- "일시정지해줘" → 현재 영상을 일시정지한다. "다시 재생해줘" → 이어서 재생한다.
+- "영상 종료" 또는 "그만 보여줘" → 뒤로 가서 직전 화면으로 돌아간다.

bot/scripts/stream-test/browse-search.mjs

@@ -2,10 +2,11 @@
 // 9222) so the action is visible on the Go-Live broadcast, and prints a JSON
 // result on stdout for the Python `browseAndSearch` tool to wrap.
 //
-//   node browse-search.mjs "<query>" [search|youtube]
+//   node browse-search.mjs "<query>" [search|youtube] [index]
 //
 // - search  : Google-search the query, return the top organic results.
-// - youtube : search YouTube and play the first result.
+// - youtube : search YouTube and play a result. `index` is the 1-based position
+//             from the top of the result list (default 1 = first result).
 //
 // Backend selection for `search`:
 //   1. The broadcast Chrome over CDP (visible on the Go-Live stream).
@@ -29,6 +30,9 @@ const UA =
   '(KHTML, like Gecko) Chrome/148.0.0.0 Safari/537.36';
 const query = process.argv[2] || '';
 const mode = (process.argv[3] || 'search').toLowerCase();
+// 1-based position of the YouTube result to play, counted from the top of the
+// list. Defaults to 1 (first result). Anything <1 or non-numeric falls back to 1.
+const playIndex = Math.max(1, parseInt(process.argv[4], 10) || 1);
 const out = (o) => { process.stdout.write(JSON.stringify(o)); };
 
 if (!query) { out({ ok: false, error: 'no query' }); process.exit(1); }
@@ -105,15 +109,21 @@ try {
   await page.bringToFront().catch(() => {});
 
   if (mode === 'youtube') {
-    // Type into YouTube's search box like a person, then play the first result.
+    // Type into YouTube's search box like a person, then play the requested
+    // result (the Nth from the top of the list; default the first).
     await typeSearch('https://www.youtube.com/?hl=ko', 'input#search, input[name="search_query"]', query);
     await page.waitForSelector('ytd-video-renderer a#video-title, a#video-title', { timeout: 20000 });
-    const first = page.locator('ytd-video-renderer a#video-title, a#video-title').first();
-    const title = (await first.getAttribute('title').catch(() => '')) || (await first.innerText().catch(() => ''));
-    await first.click();
+    const results = page.locator('ytd-video-renderer a#video-title, a#video-title');
+    // Clamp to what's actually on the page so "play the 5th" still plays the
+    // last available result rather than failing when fewer were returned.
+    const available = await results.count();
+    const targetIdx = Math.min(playIndex, Math.max(available, 1)) - 1;
+    const target = results.nth(targetIdx);
+    const title = (await target.getAttribute('title').catch(() => '')) || (await target.innerText().catch(() => ''));
+    await target.click();
     await page.waitForSelector('#movie_player', { timeout: 20000 });
     await page.evaluate(() => { const v = document.querySelector('video'); if (v && v.paused) v.play(); });
-    out({ ok: true, mode, title: (title || '').trim(), url: page.url() });
+    out({ ok: true, mode, index: targetIdx + 1, title: (title || '').trim(), url: page.url() });
   } else {
     // Type into Google's search box like a person, then read the results.
     await typeSearch('https://www.google.com/?hl=ko', 'textarea[name="q"], input[name="q"]', query);

bot/scripts/stream-test/chrome-control.mjs

@@ -17,6 +17,7 @@
 //   status | listTabs
 //   navigate {url} | back | forward | refresh
 //   newTab {url?} | closeTab {index?} | activateTab {index} | closePopups
+//   moveMouse {selector | site}  (hover the real cursor, no click)
 //   click {selector} | type {text, selector?} | scroll {dir, notches?}
 //   pressKey {key} | screenshot {path}
 import { chromium } from 'playwright';
@@ -40,6 +41,15 @@ if (!action) { out({ ok: false, error: 'no action' }); process.exit(1); }
 
 const norm = (u) => (/^https?:\/\//i.test(u) ? u : `https://${u}`);
 
+// Per-site homepage + search-box selector, shared by `search` and `moveMouse`.
+const SITES = {
+  naver: { home: 'https://www.naver.com', box: '#query, input[name="query"]' },
+  google: { home: 'https://www.google.com', box: 'textarea[name="q"], input[name="q"]' },
+  daum: { home: 'https://www.daum.net', box: '#q, input[name="q"]' },
+  youtube: { home: 'https://www.youtube.com', box: 'input#search, input[name="search_query"]' },
+  bing: { home: 'https://www.bing.com', box: '#sb_form_q, input[name="q"]' },
+};
+
 // The genuinely-active tab is the one whose document is visible. Playwright has
 // no "active page" accessor over CDP, so probe visibilityState (fixes treating
 // tab 0 as active and breaking sequential ops on a specific tab).
@@ -103,13 +113,6 @@ try {
       const q = String(cmd.query || '').trim();
       if (!q) throw new Error('search: no query');
       const siteKey = String(cmd.site || 'google').toLowerCase();
-      const SITES = {
-        naver: { home: 'https://www.naver.com', box: '#query, input[name="query"]' },
-        google: { home: 'https://www.google.com', box: 'textarea[name="q"], input[name="q"]' },
-        daum: { home: 'https://www.daum.net', box: '#q, input[name="q"]' },
-        youtube: { home: 'https://www.youtube.com', box: 'input#search, input[name="search_query"]' },
-        bing: { home: 'https://www.bing.com', box: '#sb_form_q, input[name="q"]' },
-      };
       const s = SITES[siteKey] || SITES.google;
       await front(page);
       // 1) Go to the homepage.
@@ -122,23 +125,31 @@ try {
       // 2) Click the on-page search box, type the query, submit.
       const box = page.locator(s.box).first();
       await box.waitFor({ state: 'visible', timeout: 15000 }).catch(() => {});
+      // Report which input path actually ran: 'human' = real xdotool cursor
+      // move + char typing; 'api-fallback' = the humanClick path threw and we
+      // fell back to cursor-less DOM click/fill; 'api' = no xdotool at all. This
+      // makes "did the cursor really move" verifiable from the result.
+      let searchInput;
       if (HAS_XDOTOOL && cmd.human !== false) {
         try {
           await human.humanClick(page, box);
           await human.humanType(q);
           await human.pressKey('Return');
+          searchInput = 'human';
         } catch {
+          searchInput = 'api-fallback';
           await box.click().catch(() => {});
           await box.fill(q).catch(() => {});
           await page.keyboard.press('Enter').catch(() => {});
         }
       } else {
+        searchInput = 'api';
         await box.click().catch(() => {});
         await box.fill(q);
         await page.keyboard.press('Enter');
       }
       await page.waitForLoadState('domcontentloaded').catch(() => {});
-      out({ ok: true, site: SITES[siteKey] ? siteKey : 'google', query: q, url: page.url(), title: await page.title().catch(() => '') });
+      out({ ok: true, site: SITES[siteKey] ? siteKey : 'google', query: q, url: page.url(), title: await page.title().catch(() => ''), input: searchInput });
       break;
     }
 
@@ -205,6 +216,45 @@ try {
       break;
     }
 
+    case 'moveMouse': {
+      // Move/hover the REAL cursor onto an element WITHOUT clicking. Target is a
+      // CSS selector, or site=naver/google/... for that site's search box.
+      // Only meaningful with xdotool (the visible cursor); with no xdotool there
+      // is no cursor to move, so report that rather than faking success. Every
+      // failure to actually move (no xdotool, selector never matches, element
+      // has no on-screen box) returns ok:false — we must never claim the cursor
+      // moved when it did not (the exact bug the user reported).
+      const siteKey = String(cmd.site || '').toLowerCase();
+      const selector = String(cmd.selector || '').trim() || (SITES[siteKey] ? SITES[siteKey].box : '');
+      if (!selector) throw new Error('moveMouse: no selector or known site');
+      if (!(HAS_XDOTOOL && cmd.human !== false)) {
+        out({ ok: false, error: 'no xdotool: cannot move the visible cursor on this host' });
+        break;
+      }
+      await front(page);
+      let locator = page.locator(selector).first();
+      let visible = await locator.waitFor({ state: 'visible', timeout: 8000 }).then(() => true).catch(() => false);
+      // A named site whose search box isn't on the current page: go to its home
+      // first (real omnibox), then target the box there.
+      if (!visible && SITES[siteKey]) {
+        try { await human.navigateOmnibox(SITES[siteKey].home); await page.waitForLoadState('domcontentloaded').catch(() => {}); }
+        catch { await page.goto(SITES[siteKey].home, { waitUntil: 'domcontentloaded' }).catch(() => {}); }
+        locator = page.locator(SITES[siteKey].box).first();
+        visible = await locator.waitFor({ state: 'visible', timeout: 8000 }).then(() => true).catch(() => false);
+      }
+      if (!visible) {
+        out({ ok: false, error: `moveMouse: target not found (${cmd.selector || siteKey})` });
+        break;
+      }
+      const moved = await human.humanHover(page, locator);
+      if (!moved) {
+        out({ ok: false, error: 'moveMouse: element has no on-screen box; cursor not moved' });
+        break;
+      }
+      out({ ok: true, target: cmd.selector || siteKey, input: 'human' });
+      break;
+    }
+
     case 'click': {
       const selector = String(cmd.selector || '').trim();
       if (!selector) throw new Error('click: no selector');

bot/scripts/stream-test/human.mjs

@@ -136,14 +136,18 @@ export async function navigateOmnibox(text) {
 }
 
 // Move the real cursor over an element (hover, no click) - e.g. to reveal a
-// video player's controls or to focus it for a keyboard shortcut.
+// video player's controls or to focus it for a keyboard shortcut. Returns true
+// only if the element had an on-screen box and the cursor was actually moved;
+// returns false when there is nothing to move to (so callers must not report
+// success). Brings the element into view with a real wheel scroll first.
 export async function humanHover(page, locator) {
-  const box = await locator.boundingBox().catch(() => null);
-  if (!box) return;
+  const box = await bringIntoView(page, locator);
+  if (!box) return false;
   const g = await page.evaluate(() => ({ sx: window.screenX, sy: window.screenY, ow: window.outerWidth, oh: window.outerHeight, iw: window.innerWidth, ih: window.innerHeight }));
   const bx = Math.max(0, Math.round((g.ow - g.iw) / 2));
   const oy = g.sy + Math.max(0, g.oh - g.ih - bx);
   await humanMove(Math.round(g.sx + bx + box.x + box.width * 0.5), Math.round(oy + box.y + box.height * 0.4));
+  return true;
 }
 
 export { sleep, rand };

bridge/melo_worker.py

@@ -1,30 +1,25 @@
 """
-XTTS worker
-===========
+MeloTTS worker
+==============
 
-A tiny HTTP service that keeps a Coqui XTTS-v2 voice warm and synthesises
-speech on demand. It mirrors ``melo_worker.py`` (same ``/synth`` + ``/health``
-contract, same PCM16 WAV output) so the bridge can talk to either worker the
-same way.
+A tiny, dependency-light HTTP service that keeps a MeloTTS voice warm and
+synthesises speech on demand. It runs in its OWN Python venv (``/opt/melo`` in
+the container) so the heavy MeloTTS/torch/transformers stack stays isolated
+from the slim brain-bridge venv (which pins ``numpy<2`` for faster-whisper).
 
-XTTS-v2 is a natural, multilingual neural voice. The default speaker is the
-built-in female studio voice "Ana Florence" speaking Korean — the voice this
-deployment uses in place of MeloTTS. No reference WAV is needed for the
-built-in studio speakers.
-
-It runs in its OWN Python venv (``/opt/xtts`` in the container) so the heavy
-Coqui TTS / torch stack stays isolated from the slim brain-bridge venv.
+The bridge's ``synthesize()`` POSTs ``{"text": "..."}`` here and gets back a
+16-bit PCM WAV. The MeloTTS model is loaded once at startup and reused, so each
+request only pays inference cost, not model-load cost.
 
 Config (env):
-    XTTS_WORKER_HOST   bind host            (default 127.0.0.1)
-    XTTS_WORKER_PORT   bind port            (default 8771)
-    XTTS_MODEL         Coqui model id       (default tts_models/multilingual/multi-dataset/xtts_v2)
-    XTTS_SPEAKER       built-in speaker     (default "Ana Florence")
-    XTTS_LANGUAGE      synthesis language   (default ko)
-    XTTS_DEVICE        torch device         (default cpu; compose sets cuda)
+    MELO_WORKER_HOST   bind host          (default 127.0.0.1)
+    MELO_WORKER_PORT   bind port          (default 8770)
+    MELO_LANGUAGE      MeloTTS language   (default KR)
+    MELO_SPEED         speaking rate      (default 1.5  -> the approved "150")
+    MELO_DEVICE        torch device       (default cpu)
 
 Run:
-    /opt/xtts/bin/python -m bridge.xtts_worker
+    /opt/melo/bin/python -m bridge.melo_worker
 """
 
 from __future__ import annotations
@@ -38,72 +33,94 @@ import threading
 import wave
 from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
 
-# XTTS-v2 is gated behind a one-time license prompt; agreeing here keeps the
-# load non-interactive in a container. XTTS-v2 is non-commercial (CPML).
-os.environ.setdefault("COQUI_TOS_AGREED", "1")
+HOST = os.environ.get("MELO_WORKER_HOST", "127.0.0.1")
+PORT = int(os.environ.get("MELO_WORKER_PORT", "8770"))
+LANGUAGE = os.environ.get("MELO_LANGUAGE", "KR")
 
-HOST = os.environ.get("XTTS_WORKER_HOST", "127.0.0.1")
-PORT = int(os.environ.get("XTTS_WORKER_PORT", "8771"))
-MODEL = os.environ.get("XTTS_MODEL", "tts_models/multilingual/multi-dataset/xtts_v2")
-SPEAKER = os.environ.get("XTTS_SPEAKER", "Ana Florence")
-LANGUAGE = os.environ.get("XTTS_LANGUAGE", "ko")
-DEVICE = os.environ.get("XTTS_DEVICE", "cpu")
 
-# Model is loaded once, guarded by a lock because TTS inference is not
-# guaranteed thread-safe.
+def _resolve_speed() -> float:
+    """Speaking rate: the settings-UI value (runtime config JSON) wins, else the
+    MELO_SPEED env, else 1.5. Read at startup; the settings UI restarts this
+    worker on apply so a new value takes effect."""
+    try:
+        cp = os.environ.get("JARVIS_CONFIG_PATH", "/app/config/jarvis.json")
+        v = json.loads(open(cp, encoding="utf-8").read()).get("melo_speed")
+        if v is not None:
+            return float(v)
+    except Exception:
+        pass
+    try:
+        return float(os.environ.get("MELO_SPEED", "1.5"))
+    except ValueError:
+        return 1.5
+
+
+SPEED = _resolve_speed()
+DEVICE = os.environ.get("MELO_DEVICE", "cpu")
+
+# Model + speaker id are loaded once, guarded by a lock because MeloTTS
+# inference is not guaranteed thread-safe.
 _model = None
+_speaker_id = None
 _model_lock = threading.Lock()
 _load_error: str | None = None
 
 
 def _ensure_model() -> None:
-    global _model, _load_error
+    global _model, _speaker_id, _load_error
     if _model is not None or _load_error is not None:
         return
     with _model_lock:
         if _model is not None or _load_error is not None:
             return
         try:
-            from TTS.api import TTS  # type: ignore
+            from melo.api import TTS  # type: ignore
 
-            model = TTS(MODEL).to(DEVICE)
+            model = TTS(language=LANGUAGE, device=DEVICE)
+            # spk2id is a melo HParams object (dict-like, supports __getitem__,
+            # __contains__, keys) but NOT .get(). The KR model exposes a single
+            # 'KR' speaker; fall back to the first id for other languages.
+            spk_map = model.hps.data.spk2id
+            keys = list(spk_map.keys())
+            speaker_id = spk_map[LANGUAGE] if LANGUAGE in spk_map else spk_map[keys[0]]
             _model = model
-            # Warm once: the first GPU synth pays a one-off kernel-init cost
-            # that would otherwise land on the user's first reply.
+            _speaker_id = speaker_id
+            # Warm the GPU once at load: the first CUDA synth pays a one-off
+            # kernel-init cost (~5s) that would otherwise land on the user's
+            # first reply. A throwaway synth here moves it to startup. No-op
+            # cost on CPU.
             try:
                 with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as _wt:
                     _wp = _wt.name
-                model.tts_to_file(
-                    text="워밍업", speaker=SPEAKER, language=LANGUAGE, file_path=_wp
-                )
+                model.tts_to_file("워밍업", speaker_id, _wp, speed=SPEED)
                 try:
                     os.unlink(_wp)
                 except OSError:
                     pass
             except Exception as _we:  # pragma: no cover
-                print(f"[xtts-worker] warmup synth skipped: {_we}", flush=True)
+                print(f"[melo-worker] warmup synth skipped: {_we}", flush=True)
             print(
-                f"[xtts-worker] ready (model={MODEL} speaker={SPEAKER!r} "
-                f"language={LANGUAGE} device={DEVICE})",
+                f"[melo-worker] ready (lang={LANGUAGE} speed={SPEED} "
+                f"device={DEVICE} speakers={list(spk_map.keys())})",
                 flush=True,
             )
         except Exception as e:  # pragma: no cover - depends on local model files
             _load_error = f"{type(e).__name__}: {e}"
-            print(f"[xtts-worker] model load FAILED: {_load_error}", flush=True)
+            print(f"[melo-worker] model load FAILED: {_load_error}", flush=True)
 
 
 def _synthesize(text: str) -> bytes:
     """Synthesise ``text`` to a 16-bit PCM WAV (bytes)."""
     _ensure_model()
     if _model is None:
-        raise RuntimeError(_load_error or "xtts model unavailable")
+        raise RuntimeError(_load_error or "melo model unavailable")
+    # MeloTTS writes to a file via soundfile; render to a container-disk temp
+    # file (NOT tmpfs), read it back, then drop it.
     with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as tmp:
         tmp_path = tmp.name
     try:
         with _model_lock:
-            _model.tts_to_file(
-                text=text, speaker=SPEAKER, language=LANGUAGE, file_path=tmp_path
-            )
+            _model.tts_to_file(text, _speaker_id, tmp_path, speed=SPEED)
         with open(tmp_path, "rb") as f:
             raw = f.read()
     finally:
@@ -115,15 +132,16 @@ def _synthesize(text: str) -> bytes:
 
 
 def _ensure_pcm16_wav(raw: bytes) -> bytes:
-    """Guarantee a 16-bit PCM WAV. Coqui writes float/other WAVs; the Discord
-    playback path tolerates both, but we normalise to PCM16 so the contract
-    matches the previous Melo/Piper output (mono, file's own sample rate)."""
+    """Guarantee a 16-bit PCM WAV. MeloTTS/soundfile usually emit float WAVs;
+    the Discord playback path (ffmpeg) tolerates both, but we normalise to
+    PCM16 so the contract matches the previous Piper output."""
     try:
         with wave.open(io.BytesIO(raw), "rb") as wf:
             if wf.getsampwidth() == 2:
                 return raw  # already PCM16
     except wave.Error:
         pass
+    # Non-PCM16 (e.g. float) — convert with soundfile if available.
     try:
         import numpy as np
         import soundfile as sf
@@ -141,7 +159,7 @@ def _ensure_pcm16_wav(raw: bytes) -> bytes:
             wf.writeframes(pcm)
         return buf.getvalue()
     except Exception:
-        return raw  # last resort: hand back whatever XTTS produced
+        return raw  # last resort: hand back whatever MeloTTS produced
 
 
 class _Handler(BaseHTTPRequestHandler):
@@ -194,7 +212,7 @@ def main() -> int:
     # Warm the model at startup so the first Discord turn isn't slow.
     _ensure_model()
     server = ThreadingHTTPServer((HOST, PORT), _Handler)
-    print(f"[xtts-worker] listening on http://{HOST}:{PORT}", flush=True)
+    print(f"[melo-worker] listening on http://{HOST}:{PORT}", flush=True)
     try:
         server.serve_forever()
     except KeyboardInterrupt:

bridge/requirements-bridge.txt

@@ -21,7 +21,11 @@ nvidia-cudnn-cu12
 # --- Bridge HTTP service ---
 flask>=3.0.0
 
-# --- Text-to-speech (Piper) ---
+# --- Text-to-speech ---
+# Edge TTS: the primary Korean voice (online MS neural). Lightweight (httpx);
+# emits MP3, transcoded to PCM16 by the system ffmpeg in the bridge.
+edge-tts>=6.1.0
+# Piper: offline English fallback.
 piper-tts>=1.3.0
 
 # --- Built-in tools (lazily imported; needed for full functionality) ---

bridge/server.py

@@ -87,13 +87,22 @@ VAD_MIN_SPEECH_MS = int(os.environ.get("VAD_MIN_SPEECH_MS", "200"))
 # Korean phrase decoded as Chinese) and shaves a little latency. Empty = auto.
 STT_LANGUAGE = os.environ.get("STT_LANGUAGE", "ko").strip() or None
 
-# TTS engine: "xtts" (Coqui XTTS-v2 natural Korean voice, the warm worker) is
-# the primary voice; Piper is kept as a fallback only if explicitly enabled. Set
-# TTS_ENGINE=piper to disable the neural Korean voice entirely. "melo" is still
-# accepted for backward compatibility but is no longer built into the image.
+# Whisper decoding accuracy knobs. beam_size=1 is greedy decoding — fast but the
+# least accurate; beam search (5 is the Whisper default) explores alternatives
+# and noticeably improves recognition on short, accented, or noisy Discord-mic
+# speech. condition_on_previous_text=False stops Whisper from feeding a previous
+# clip's transcript back in as a prompt, which on isolated short utterances
+# causes repetition loops and drift rather than helping. Both are env-tunable so
+# accuracy/latency can be traded without a code change (lower STT_BEAM_SIZE for
+# speed, raise it for accuracy).
+STT_BEAM_SIZE = max(1, int(os.environ.get("STT_BEAM_SIZE", "5")))
+STT_CONDITION_ON_PREV = os.environ.get("STT_CONDITION_ON_PREV", "0") in ("1", "true", "True", "yes", "on")
+
+# TTS engine: "edge" (Microsoft Edge TTS, natural Korean neural voice) is the
+# primary voice. "melo" (a warm MeloTTS worker) and "piper" remain selectable.
 def _tts_engine_setting() -> str:
     """TTS engine: settings-UI value (runtime config JSON) wins, else env, else
-    xtts. Read at startup; the settings UI restarts the bridge on apply."""
+    edge. Read at startup; the settings UI restarts the bridge on apply."""
     try:
         _cp = os.environ.get("JARVIS_CONFIG_PATH", "/app/config/jarvis.json")
         _v = json.loads(open(_cp, encoding="utf-8").read()).get("tts_engine")
@@ -101,29 +110,23 @@ def _tts_engine_setting() -> str:
             return str(_v).strip().lower()
     except Exception:
         pass
-    return os.environ.get("TTS_ENGINE", "xtts").strip().lower()
+    return os.environ.get("TTS_ENGINE", "edge").strip().lower()
 
 
 TTS_ENGINE = _tts_engine_setting()
-# Coqui XTTS-v2 worker (the natural Korean voice).
-XTTS_WORKER_URL = os.environ.get("XTTS_WORKER_URL", "http://127.0.0.1:8771")
-XTTS_TIMEOUT = float(os.environ.get("XTTS_TIMEOUT", "30"))
-# Legacy MeloTTS worker (no longer built into the image; kept for back-compat
-# if someone runs an old worker out-of-band).
+# Edge TTS (online MS neural voice). Voice + rate are env-driven so they can be
+# changed without code. Default: Korean "Hyunsu" multilingual voice at +45%
+# (≈1.45×), the chosen settings. NOTE: edge synthesis sends the reply TEXT to
+# Microsoft's servers and needs internet — an intentional privacy trade-off for
+# the more natural voice.
+EDGE_TTS_VOICE = os.environ.get("EDGE_TTS_VOICE", "ko-KR-HyunsuMultilingualNeural").strip()
+EDGE_TTS_RATE = os.environ.get("EDGE_TTS_RATE", "+45%").strip()
 MELO_WORKER_URL = os.environ.get("MELO_WORKER_URL", "http://127.0.0.1:8770")
 MELO_TIMEOUT = float(os.environ.get("MELO_TIMEOUT", "30"))
 # Do NOT silently fall back to the English Piper voice on a neural-voice failure:
-# speaking Korean text through an English voice produces mangled audio. Default
-# is neural-only (return no audio on failure); set XTTS_FALLBACK_PIPER=1 (or the
-# legacy MELO_FALLBACK_PIPER=1) to opt into the Piper fallback.
-def _truthy_env(*names: str) -> bool:
-    for _n in names:
-        if os.environ.get(_n, "").strip().lower() in ("1", "true", "yes", "on"):
-            return True
-    return False
-
-
-NEURAL_FALLBACK_PIPER = _truthy_env("XTTS_FALLBACK_PIPER", "MELO_FALLBACK_PIPER")
+# speaking Korean through an English voice produces mangled audio. Default is
+# neural-only (return no audio on failure); set MELO_FALLBACK_PIPER=1 to opt in.
+MELO_FALLBACK_PIPER = os.environ.get("MELO_FALLBACK_PIPER", "0") in ("1", "true", "True", "yes", "on")
 
 # ---------------------------------------------------------------------------
 # Lazy singletons. The first request pays the model-load cost; afterwards the
@@ -251,7 +254,12 @@ def transcribe(wav_bytes: bytes) -> dict:
         print("[bridge] no speech detected (VAD) — skipping STT", flush=True)
         return {"text": "", "language": None, "note": "음성 아님(VAD 차단)"}
 
-    segments, info = _whisper.transcribe(audio, beam_size=1, language=STT_LANGUAGE)
+    segments, info = _whisper.transcribe(
+        audio,
+        beam_size=STT_BEAM_SIZE,
+        language=STT_LANGUAGE,
+        condition_on_previous_text=STT_CONDITION_ON_PREV,
+    )
     # Second line of defence: drop non-speech / hallucinated segments by
     # Whisper's own no_speech_prob. The no_speech_prob hard cutoff (plus the VAD
     # pre-gate above) is what rejects noise/hallucinations. The avg_logprob
@@ -315,38 +323,75 @@ def _coerce_bool(value) -> Optional[bool]:
     return str(value).strip().lower() in ("1", "true", "yes", "on")
 
 
-def _worker_synthesize(name: str, url: str, timeout: float, text: str) -> Optional[bytes]:
-    """POST text to a warm TTS worker's /synth and return its WAV bytes, or None
-    on any failure so the caller can decide whether to fall back."""
+def _edge_synthesize(text: str) -> Optional[bytes]:
+    """Synthesise via Microsoft Edge TTS (online neural voice) and return a
+    16-bit PCM WAV, or None on any failure. Edge emits MP3; we transcode to
+    PCM16 mono with the system ffmpeg, writing to a temp file (seekable) so the
+    WAV header carries a correct length. Needs internet."""
+    import asyncio
+    import subprocess
+    import tempfile
+
+    try:
+        import edge_tts  # type: ignore
+
+        async def _gen() -> bytes:
+            comm = edge_tts.Communicate(text, EDGE_TTS_VOICE, rate=EDGE_TTS_RATE)
+            buf = bytearray()
+            async for chunk in comm.stream():
+                if chunk.get("type") == "audio":
+                    buf.extend(chunk["data"])
+            return bytes(buf)
+
+        mp3 = asyncio.run(_gen())
+        if not mp3:
+            print("[bridge] edge TTS returned no audio", flush=True)
+            return None
+        with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as t:
+            out_path = t.name
+        try:
+            proc = subprocess.run(
+                ["ffmpeg", "-hide_banner", "-loglevel", "error", "-y",
+                 "-i", "pipe:0", "-ac", "1", "-ar", "24000",
+                 "-acodec", "pcm_s16le", out_path],
+                input=mp3, capture_output=True,
+            )
+            if proc.returncode != 0:
+                print(f"[bridge] edge ffmpeg transcode failed: {proc.stderr.decode('utf-8','ignore')[:200]}", flush=True)
+                return None
+            with open(out_path, "rb") as f:
+                return f.read()
+        finally:
+            try:
+                os.unlink(out_path)
+            except OSError:
+                pass
+    except Exception as e:  # pragma: no cover - network / dep dependent
+        print(f"[bridge] edge synth failed: {e}", flush=True)
+    return None
+
+
+def _melo_synthesize(text: str) -> Optional[bytes]:
+    """Synthesise via the warm MeloTTS worker (separate /opt/melo venv, Korean
+    speaker @ speed 1.5). Returns a 16-bit PCM WAV, or None on any failure so
+    the caller can fall back to Piper."""
     import urllib.request
 
     try:
         req = urllib.request.Request(
-            f"{url}/synth",
+            f"{MELO_WORKER_URL}/synth",
             data=json.dumps({"text": text}).encode("utf-8"),
             headers={"Content-Type": "application/json"},
         )
-        with urllib.request.urlopen(req, timeout=timeout) as resp:
+        with urllib.request.urlopen(req, timeout=MELO_TIMEOUT) as resp:
             if resp.status == 200:
                 return resp.read()
-            print(f"[bridge] {name} worker HTTP {resp.status}", flush=True)
+            print(f"[bridge] melo worker HTTP {resp.status}", flush=True)
     except Exception as e:  # pragma: no cover - worker may be down
-        print(f"[bridge] {name} worker unreachable: {e}", flush=True)
+        print(f"[bridge] melo worker unreachable: {e}", flush=True)
     return None
 
 
-def _xtts_synthesize(text: str) -> Optional[bytes]:
-    """Synthesise via the warm Coqui XTTS-v2 worker (separate /opt/xtts venv,
-    natural female Korean). Returns a 16-bit PCM WAV, or None on failure."""
-    return _worker_synthesize("xtts", XTTS_WORKER_URL, XTTS_TIMEOUT, text)
-
-
-def _melo_synthesize(text: str) -> Optional[bytes]:
-    """Legacy: synthesise via a MeloTTS worker if one is running out-of-band.
-    Returns a 16-bit PCM WAV, or None on any failure."""
-    return _worker_synthesize("melo", MELO_WORKER_URL, MELO_TIMEOUT, text)
-
-
 def _piper_synthesize(text: str) -> Optional[bytes]:
     """Fallback: synthesise with Piper (English voice). Returns WAV bytes."""
     _ensure_piper()
@@ -373,12 +418,11 @@ def _tts_ready() -> bool:
     """
     if not TTS_ENABLED:
         return True
-    _worker_health = {"xtts": XTTS_WORKER_URL, "melo": MELO_WORKER_URL}.get(TTS_ENGINE)
-    if _worker_health:
+    if TTS_ENGINE == "melo":
         import urllib.request
 
         try:
-            with urllib.request.urlopen(f"{_worker_health}/health", timeout=2) as resp:
+            with urllib.request.urlopen(f"{MELO_WORKER_URL}/health", timeout=2) as resp:
                 return resp.status == 200
         except Exception:
             return False
@@ -386,22 +430,20 @@ def _tts_ready() -> bool:
 
 
 def synthesize(text: str) -> Optional[bytes]:
-    """Synthesize text to a 16-bit PCM WAV. The primary voice is Coqui XTTS-v2
-    (natural female Korean) served by the warm xtts worker; Piper is used only
-    when explicitly enabled as a fallback. Returns None if TTS is off."""
+    """Synthesize text to a 16-bit PCM WAV. The primary voice is Edge TTS (a
+    natural Korean neural voice); "melo" uses the warm MeloTTS worker. For a
+    neural engine, Piper (English) is only used if explicitly enabled, since
+    speaking Korean through an English voice mangles it. Returns None if off."""
     if not TTS_ENABLED or not text.strip():
         return None
-    _neural = {"xtts": _xtts_synthesize, "melo": _melo_synthesize}.get(TTS_ENGINE)
+    _neural = {"edge": _edge_synthesize, "melo": _melo_synthesize}.get(TTS_ENGINE)
     if _neural is not None:
         audio = _neural(text)
         if audio:
             return audio
-        if not NEURAL_FALLBACK_PIPER:
+        if not MELO_FALLBACK_PIPER:
             # Neural-only: better silent than mangled English for Korean text.
-            print(
-                f"[bridge] {TTS_ENGINE} synth failed; no audio (Piper fallback disabled)",
-                flush=True,
-            )
+            print(f"[bridge] {TTS_ENGINE} synth failed; no audio (Piper fallback disabled)", flush=True)
             return None
         print(f"[bridge] {TTS_ENGINE} synth failed; falling back to Piper", flush=True)
     return _piper_synthesize(text)

bridge/settings_web.py

@@ -22,7 +22,7 @@ from typing import Any, Dict
 FIELDS = [
     ("ollama_chat_model", "LLM 모델", "model"),
     ("whisper_model", "STT(Whisper) 모델", "select:tiny,base,small,medium,large,large-v3"),
-    ("tts_engine", "TTS 엔진", "select:xtts,piper"),
+    ("tts_engine", "TTS 엔진", "select:edge,piper"),
     ("output_language", "출력 언어 (비우면 사용자 언어)", "text"),
     ("llm_thinking_enabled", "LLM 사고(thinking) 모드", "bool"),
     ("agentic_max_turns", "에이전트 최대 반복", "number:1:12:1"),
@@ -106,15 +106,15 @@ def _save(updates: Dict[str, Any]) -> None:
 
 
 def _apply() -> str:
-    # Restart the TTS worker + bridge AFTER this response is sent. Detached (new
-    # session) so the bridge being killed mid-restart doesn't drop the restart
-    # itself, and the HTTP client still receives this response.
+    # Restart the bridge AFTER this response is sent. Detached (new session) so
+    # the bridge being killed mid-restart doesn't drop the restart itself, and
+    # the HTTP client still receives this response. (Edge TTS has no worker.)
     try:
         subprocess.Popen(
-            ["sh", "-c", "sleep 1; supervisorctl restart xtts-worker bridge"],
+            ["sh", "-c", "sleep 1; supervisorctl restart bridge"],
             start_new_session=True,
         )
-        return "1초 후 브리지/TTS 워커가 재시작되어 반영됩니다."
+        return "1초 후 브리지가 재시작되어 반영됩니다."
     except Exception as e:  # pragma: no cover
         return str(e)
 

docker-compose.yml

@@ -40,6 +40,9 @@ services:
     environment:
       OLLAMA_HOST: http://ollama:11434
       CHAT_MODEL: ${OLLAMA_CHAT_MODEL:-qwen2.5:3b}
+      # Small auxiliary model for intent/router/extraction calls (see javis
+      # service). Pulled here so the split is ready out of the box.
+      INTENT_MODEL: ${OLLAMA_INTENT_MODEL:-qwen2.5:3b}
       EMBED_MODEL: ${OLLAMA_EMBED_MODEL:-nomic-embed-text}
     entrypoint: ["/bin/sh", "-c"]
     command:
@@ -48,6 +51,10 @@ services:
         until ollama list >/dev/null 2>&1; do sleep 2; done;
         echo "[ollama-init] pulling $$CHAT_MODEL";
         ollama pull "$$CHAT_MODEL";
+        if [ -n "$$INTENT_MODEL" ] && [ "$$INTENT_MODEL" != "$$CHAT_MODEL" ]; then
+          echo "[ollama-init] pulling $$INTENT_MODEL (auxiliary intent/router model)";
+          ollama pull "$$INTENT_MODEL";
+        fi;
         echo "[ollama-init] pulling $$EMBED_MODEL";
         ollama pull "$$EMBED_MODEL";
         echo "[ollama-init] models ready.";
@@ -62,19 +69,27 @@ services:
       # Point the brain at the ollama service and the bot at the in-container bridge.
       OLLAMA_BASE_URL: http://ollama:11434
       OLLAMA_CHAT_MODEL: ${OLLAMA_CHAT_MODEL:-qwen2.5:3b}
+      # Auxiliary small-model calls (intent judge, tool router, arg extraction,
+      # query decomposition) run on this fast model so the big chat model only
+      # runs for the actual spoken answer. With the GPU on, this is the main
+      # per-turn latency win: a command no longer pays the big model's cost 2-3
+      # times for routing/extraction. Defaults to qwen2.5:3b (the project's
+      # reference small model, clean Korean on classification); set it equal to
+      # OLLAMA_CHAT_MODEL to fold everything back onto one resident model.
+      OLLAMA_INTENT_MODEL: ${OLLAMA_INTENT_MODEL:-qwen2.5:3b}
       OLLAMA_EMBED_MODEL: ${OLLAMA_EMBED_MODEL:-nomic-embed-text}
       WHISPER_MODEL: ${WHISPER_MODEL:-medium}
       WHISPER_DEVICE: ${WHISPER_DEVICE:-cuda}
       WHISPER_COMPUTE_TYPE: ${WHISPER_COMPUTE_TYPE:-float16}
-      # Coqui XTTS-v2 (natural female Korean voice, replaces MeloTTS) on the GPU
-      # (cu128 torch baked by docker/setup-xtts.sh). Set here WITH DEFAULTS so
-      # supervisord's %(ENV_XTTS_*)s passthrough always resolves and an .env
-      # override actually reaches the xtts-worker.
-      XTTS_DEVICE: ${XTTS_DEVICE:-cuda}
-      # Built-in studio speaker (female). Other options include "Daisy Studious",
-      # "Sofia Hellen", "Alma María", etc. — any XTTS-v2 studio speaker name.
-      XTTS_SPEAKER: ${XTTS_SPEAKER:-Ana Florence}
-      XTTS_LANGUAGE: ${XTTS_LANGUAGE:-ko}
+      # TTS engine. Rendered into /app/config/jarvis.json via envsubst (the
+      # bridge reads that JSON BEFORE the env, so it must carry the real engine,
+      # not a hardcoded one — otherwise Korean text is read by the English Piper
+      # voice). Default edge; .env can override (e.g. piper for offline).
+      TTS_ENGINE: ${TTS_ENGINE:-edge}
+      # Edge TTS voice + rate (the chosen natural Korean voice). NOTE: edge is an
+      # ONLINE engine — reply text is sent to Microsoft and needs internet.
+      EDGE_TTS_VOICE: ${EDGE_TTS_VOICE:-ko-KR-HyunsuMultilingualNeural}
+      EDGE_TTS_RATE: ${EDGE_TTS_RATE:-+45%}
       # Optional single-language lock for replies (empty = user's own language).
       OUTPUT_LANGUAGE: ${OUTPUT_LANGUAGE:-ko}
       # Drop the pre-loop planner LLM call to cut voice-reply latency on small
@@ -82,6 +97,9 @@ services:
       PLANNER_ENABLED: ${PLANNER_ENABLED:-0}
       # Lock STT to Korean (skip Whisper auto-detect).
       STT_LANGUAGE: ${STT_LANGUAGE:-ko}
+      # Whisper decode accuracy: beam search (5) over greedy (1) lifts recognition
+      # on short/noisy Discord speech. Lower to 1 for minimum latency.
+      STT_BEAM_SIZE: ${STT_BEAM_SIZE:-5}
       VOICE_SILENCE_MS: ${VOICE_SILENCE_MS:-600}
       BRIDGE_URL: http://127.0.0.1:8765
       # Split-deployment role: full (default, all-in-one), browser (only the

docker/entrypoint.sh

@@ -10,12 +10,15 @@ set -euo pipefail
 : "${OLLAMA_BASE_URL:=http://ollama:11434}"
 : "${OLLAMA_CHAT_MODEL:=qwen3:8b}"
 # Auxiliary small-model calls (intent judge, tool router, weather place
-# extraction, query decomposition). The code default is gemma4:e2b, which this
-# stack does not pull, so those calls would silently fail and fall open —
-# crippling tool routing and arg extraction. Reuse the (already warm) chat model
-# by default so everything runs on one resident model; override if you pull a
-# dedicated small model.
-: "${OLLAMA_INTENT_MODEL:=${OLLAMA_CHAT_MODEL}}"
+# extraction, query decomposition). Default to a small fast model so the big
+# chat model only runs for the actual spoken answer — the main per-turn latency
+# win once the GPU is in use, since the 2-3 routing/extraction calls per command
+# no longer pay the big model's cost. ollama-init pulls this model. Set it equal
+# to OLLAMA_CHAT_MODEL to fold everything back onto one resident model.
+: "${OLLAMA_INTENT_MODEL:=qwen2.5:3b}"
+# Cap chat-model output tokens per turn (worst-case latency guard). Spoken
+# answers are 1-2 sentences; 512 is safe headroom above tool-call JSON. 0 = off.
+: "${OLLAMA_NUM_PREDICT:=512}"
 : "${OLLAMA_EMBED_MODEL:=nomic-embed-text}"
 : "${WHISPER_MODEL:=small}"
 : "${WHISPER_DEVICE:=cuda}"
@@ -32,7 +35,7 @@ set -euo pipefail
 : "${XDG_RUNTIME_DIR:=/run/user/0}"
 : "${PULSE_SERVER:=unix:${XDG_RUNTIME_DIR}/pulse/native}"
 
-export VNC_RESOLUTION OLLAMA_BASE_URL OLLAMA_CHAT_MODEL OLLAMA_INTENT_MODEL OLLAMA_EMBED_MODEL \
+export VNC_RESOLUTION OLLAMA_BASE_URL OLLAMA_CHAT_MODEL OLLAMA_NUM_PREDICT OLLAMA_INTENT_MODEL OLLAMA_EMBED_MODEL \
        WHISPER_MODEL WHISPER_DEVICE WHISPER_COMPUTE_TYPE JARVIS_DB_PATH \
        PIPER_VOICE PIPER_VOICE_DIR TTS_PIPER_MODEL_PATH BRIDGE_HOST BRIDGE_PORT \
        XDG_RUNTIME_DIR PULSE_SERVER
@@ -51,12 +54,18 @@ export JARVIS_CONFIG_PATH=/app/config/jarvis.json
 # the env-rendered config, so changes survive container recreate.
 if [ -f /data/jarvis-settings.json ]; then
   python3 - <<'PY' || true
-import json
+import json, os
 try:
     base = json.load(open("/app/config/jarvis.json"))
     ov = json.load(open("/data/jarvis-settings.json"))
     if isinstance(base, dict) and isinstance(ov, dict):
         base.update(ov)
+        # A stale persisted tts_engine from an earlier voice (melo/xtts, no
+        # longer built into the image) would override the configured engine and
+        # leave the bot silent. Reset those to the env-configured engine.
+        if base.get("tts_engine") in ("melo", "xtts"):
+            base["tts_engine"] = os.environ.get("TTS_ENGINE", "edge")
+            print(f"[entrypoint] reset stale tts_engine -> {base['tts_engine']}")
         json.dump(base, open("/app/config/jarvis.json", "w"), ensure_ascii=False, indent=2)
         print("[entrypoint] merged persistent settings overrides")
 except Exception as e:

docker/jarvis-config.template.json

@@ -4,9 +4,10 @@
   "ollama_base_url": "${OLLAMA_BASE_URL}",
   "ollama_embed_model": "${OLLAMA_EMBED_MODEL}",
   "ollama_chat_model": "${OLLAMA_CHAT_MODEL}",
+  "ollama_num_predict": "${OLLAMA_NUM_PREDICT}",
   "intent_judge_model": "${OLLAMA_INTENT_MODEL}",
   "tts_enabled": true,
-  "tts_engine": "piper",
+  "tts_engine": "${TTS_ENGINE}",
   "tts_piper_model_path": "${TTS_PIPER_MODEL_PATH}",
   "whisper_model": "${WHISPER_MODEL}",
   "whisper_backend": "faster-whisper",

docker/run-chrome.sh

@@ -18,6 +18,27 @@ cat > /etc/opt/chrome/policies/managed/jarvis.json <<'JSON'
 { "CommandLineFlagSecurityWarningsEnabled": false }
 JSON
 
+# Seed the profile's web-content language to Korean so sites (YouTube, Google,
+# Naver) render in Korean. --lang sets Chrome's own UI, but the Accept-Language
+# sent to sites comes from the profile's intl.accept_languages, which a persisted
+# user-data-dir would otherwise keep at en-US regardless of --accept-lang.
+PREFS_DIR="${CHROME_PROFILE_DIR:-/root/chrome-profile}/Default"
+PREFS="${PREFS_DIR}/Preferences"
+mkdir -p "$PREFS_DIR"
+if [ -f "$PREFS" ]; then
+  python3 - "$PREFS" <<'PY' 2>/dev/null || true
+import json, sys
+p = sys.argv[1]
+d = json.load(open(p))
+d.setdefault("intl", {})
+d["intl"]["accept_languages"] = "ko-KR,ko"
+d["intl"]["selected_languages"] = "ko-KR,ko"
+json.dump(d, open(p, "w"), ensure_ascii=False)
+PY
+else
+  printf '%s' '{"intl":{"accept_languages":"ko-KR,ko","selected_languages":"ko-KR,ko"}}' > "$PREFS"
+fi
+
 # Minimal, non-automation flags. --remote-debugging exposes CDP so the brain can
 # drive this on-screen Chrome (Google/YouTube/Naver), --disable-features=Translate
 # hides the translate popup. NO --test-type / --disable-blink-features.
@@ -26,6 +47,7 @@ exec google-chrome \
   --no-default-browser-check \
   --disable-features=Translate,TranslateUI \
   --lang=ko-KR \
+  --accept-lang=ko-KR,ko \
   --remote-debugging-port="${CDP_PORT:-9222}" \
   --remote-debugging-address="${CDP_BIND:-127.0.0.1}" \
   --user-data-dir="${CHROME_PROFILE_DIR:-/root/chrome-profile}" \

docker/setup-melo.sh

@@ -0,0 +1,80 @@
+#!/usr/bin/env bash
+# ============================================================================
+# Install a dedicated MeloTTS (Korean voice) venv at /opt/melo.
+#
+# Why a SEPARATE venv (not the brain-bridge /opt/venv):
+#   - MeloTTS pins old deps (transformers 4.27.4 / tokenizers 0.13.3 / fugashi)
+#     whose binary wheels exist only for cp311, so we use python3.11 here even
+#     though the image's default interpreter is 3.12.
+#   - It isolates the heavy torch/transformers stack from the slim bridge env,
+#     which pins numpy<2 for faster-whisper.
+#
+# torch is the CUDA (cu128) build so MeloTTS runs on the GPU alongside Ollama +
+# Whisper. CPU synth serialised under concurrent load (whisper STT + bot) and
+# blew TTS up to 7-8s per reply; on the GPU a sentence synthesises in ~0.3s.
+# cu128 is the Blackwell (sm_120) wheel verified on this host's RTX 5050.
+# The worker selects the device via MELO_DEVICE=cuda (compose).
+# ============================================================================
+set -euxo pipefail
+
+export DEBIAN_FRONTEND=noninteractive
+
+apt-get update
+# Build deps for fugashi / mecab-python3 + a system MeCab dict, plus python3.11.
+apt-get install -y --no-install-recommends \
+    software-properties-common build-essential pkg-config swig \
+    libmecab-dev mecab mecab-ipadic-utf8
+add-apt-repository -y ppa:deadsnakes/ppa
+apt-get update
+apt-get install -y --no-install-recommends python3.11 python3.11-venv python3.11-dev
+rm -rf /var/lib/apt/lists/*
+
+python3.11 -m venv /opt/melo
+/opt/melo/bin/pip install --no-cache-dir --upgrade pip wheel setuptools
+
+# CUDA (cu128) torch first, so MeloTTS's unpinned `torch` dep is already
+# satisfied with the GPU build. Pinned to the Blackwell-verified versions
+# (2.11.0+cu128) for reproducible rebuilds.
+/opt/melo/bin/pip install --no-cache-dir torch==2.11.0+cu128 torchaudio==2.11.0+cu128 \
+    --index-url https://download.pytorch.org/whl/cu128
+
+# MeloTTS from GitHub. The PyPI sdist is broken (its setup.py reads a
+# requirements.txt that is not shipped in the sdist), so install from the repo.
+# Pinned to a commit (not refs/heads/main) so rebuilds are reproducible.
+/opt/melo/bin/pip install --no-cache-dir \
+    "https://github.com/myshell-ai/MeloTTS/archive/209145371cff8fc3bd60d7be902ea69cbdb7965a.tar.gz"
+
+# Korean g2p backend. MeloTTS otherwise tries to pip-install this on the first
+# Korean request, which fails in a network-isolated container at runtime.
+/opt/melo/bin/pip install --no-cache-dir python-mecab-ko python-mecab-ko-dic
+
+# Remove the full `unidic` package (its dictionary is never downloaded, only a
+# stub) so mecab-python3 falls back to the bundled `unidic_lite` dict. Without
+# this, importing melo's Japanese module fails with a missing-mecabrc error.
+/opt/melo/bin/pip uninstall -y unidic || true
+
+# Pre-cache every model asset MeloTTS pulls at runtime, so the worker starts
+# offline and the first Discord turn pays no download cost. Importing melo.api
+# fetches the Japanese (tohoku-nlp/bert-base-japanese-v3) and Korean
+# (kykim/bert-kor-base) BERT tokenizers plus nltk g2p data; loading the KR voice
+# downloads the OpenVoice KR config+checkpoint, and a real synth pulls the
+# Korean BERT weights. All of these go through huggingface_hub.
+#
+# CRITICAL: at runtime docker-compose mounts the `whisper_cache` named volume
+# over /root/.cache/huggingface (for faster-whisper). That volume would SHADOW
+# anything baked into the default HF cache, so we pin the melo worker to a
+# DEDICATED, non-volume cache dir (/opt/melo-cache) here AND in supervisord, and
+# warm it once. nltk_data (/root/nltk_data) is not volume-mounted so it stays.
+export HF_HOME=/opt/melo-cache
+mkdir -p "$HF_HOME"
+MELO_LANGUAGE=KR HF_HOME=/opt/melo-cache /opt/melo/bin/python - <<'PY'
+import tempfile
+from melo.api import TTS
+
+model = TTS(language="KR", device="cpu")
+out = tempfile.mktemp(suffix=".wav")
+model.tts_to_file("초기화 워밍업입니다.", model.hps.data.spk2id["KR"], out, speed=1.5)
+print("[setup-melo] warm-up KR synth OK ->", out)
+PY
+
+echo "[setup-melo] MeloTTS venv ready at /opt/melo"

docker/setup-xtts.sh

@@ -1,72 +0,0 @@
-#!/usr/bin/env bash
-# ============================================================================
-# Install a dedicated Coqui XTTS-v2 (natural Korean voice) venv at /opt/xtts.
-#
-# Why a SEPARATE venv (not the brain-bridge /opt/venv or /opt/melo):
-#   - Coqui TTS pulls its own heavy torch/transformers stack; isolating it keeps
-#     the slim bridge env (numpy<2 for faster-whisper) untouched.
-#   - We use python3.11 (installed for the melo layer) because Coqui ships cp311
-#     wheels and torch cu128 is available for it.
-#
-# torch is the CUDA (cu128) build so XTTS runs on the GPU alongside Ollama +
-# Whisper. cu128 is the Blackwell (sm_120) wheel verified on this host.
-# The worker selects the device via XTTS_DEVICE=cuda (compose).
-#
-# XTTS-v2 is non-commercial (Coqui Public Model License). COQUI_TOS_AGREED=1
-# accepts it non-interactively so the model can load in a headless container.
-# ============================================================================
-set -euxo pipefail
-
-export DEBIAN_FRONTEND=noninteractive
-export COQUI_TOS_AGREED=1
-
-# Install python3.11 if not already present, so this layer is self-contained.
-if ! command -v python3.11 >/dev/null 2>&1; then
-    apt-get update
-    apt-get install -y --no-install-recommends software-properties-common
-    add-apt-repository -y ppa:deadsnakes/ppa
-    apt-get update
-    apt-get install -y --no-install-recommends python3.11 python3.11-venv python3.11-dev
-    rm -rf /var/lib/apt/lists/*
-fi
-
-python3.11 -m venv /opt/xtts
-/opt/xtts/bin/pip install --no-cache-dir --upgrade pip wheel setuptools
-
-# CUDA (cu128) torch first so Coqui's `torch` dep is satisfied with the GPU
-# build. Pinned to the Blackwell-verified versions for reproducible rebuilds.
-/opt/xtts/bin/pip install --no-cache-dir torch==2.11.0+cu128 torchaudio==2.11.0+cu128 \
-    --index-url https://download.pytorch.org/whl/cu128
-
-# Coqui TTS (maintained fork; provides the `TTS` package and XTTS-v2). The
-# [codec] extra pulls torchcodec, which torch >=2.9 requires for audio IO
-# (without it the import fails with TORCHCODEC_IMPORT_ERROR). torchcodec also
-# needs the system FFmpeg shared libs, which are present (ffmpeg apt package).
-/opt/xtts/bin/pip install --no-cache-dir "coqui-tts[codec]"
-
-# Pin transformers to the 4.57+ / <5 range. coqui-tts requires >=4.57 but does
-# NOT cap the upper bound, and transformers 5.x removed `isin_mps_friendly`
-# (used by XTTS's tortoise layer), so an unpinned install pulls 5.x and the
-# model import fails with "cannot import name 'isin_mps_friendly'". Pin <5.
-/opt/xtts/bin/pip install --no-cache-dir "transformers>=4.57,<5"
-
-# Pre-bake the XTTS-v2 model so the worker starts offline and the first Discord
-# turn pays no download cost. The model is cached under TTS_HOME; we pin a
-# DEDICATED, non-volume dir (/opt/xtts-cache) AND set it in supervisord, because
-# runtime volume mounts (whisper_cache over /root/.cache) must not shadow it.
-export TTS_HOME=/opt/xtts-cache
-mkdir -p "$TTS_HOME"
-COQUI_TOS_AGREED=1 TTS_HOME=/opt/xtts-cache XTTS_SPEAKER="Ana Florence" \
-    /opt/xtts/bin/python - <<'PY'
-import os
-os.environ["COQUI_TOS_AGREED"] = "1"
-from TTS.api import TTS
-
-speaker = os.environ.get("XTTS_SPEAKER", "Ana Florence")
-model = TTS("tts_models/multilingual/multi-dataset/xtts_v2")  # downloads to TTS_HOME
-out = "/tmp/xtts_warm.wav"
-model.tts_to_file(text="초기화 워밍업입니다.", speaker=speaker, language="ko", file_path=out)
-print("[setup-xtts] warm-up KR synth OK ->", out, "speaker:", speaker)
-PY
-
-echo "[setup-xtts] Coqui XTTS-v2 venv ready at /opt/xtts (cache /opt/xtts-cache)"

docker/supervisord.conf

@@ -49,28 +49,8 @@ stdout_logfile_maxbytes=0
 stderr_logfile=/dev/stderr
 stderr_logfile_maxbytes=0
 
-[program:xtts-worker]
-; Warm Coqui XTTS-v2 Korean voice (natural female "Ana Florence") in its own
-; py3.11 venv. The bridge's synthesize() POSTs here; if this is down the bridge
-; falls back to Piper (English) only when XTTS_FALLBACK_PIPER=1.
-command=/app/docker/run-if-role.sh full,bot /opt/xtts/bin/python /app/bridge/xtts_worker.py
-directory=/app
-; TTS_HOME points at the dedicated, image-baked XTTS cache (warmed in
-; setup-xtts.sh). The brain's whisper_cache volume is mounted over
-; /root/.cache, so a dedicated non-volume cache dir avoids the baked model being
-; shadowed and re-downloaded (which would fail if the host is offline).
-; XTTS_DEVICE / XTTS_SPEAKER / XTTS_LANGUAGE inherit from the container env
-; (compose sets them with defaults: cuda / "Ana Florence" / ko). supervisord
-; interpolates %(ENV_x)s from its own environment, which is the container's — so
-; these must always be set in the env (compose guarantees it) or this expansion
-; fails at startup. COQUI_TOS_AGREED accepts the non-commercial XTTS license.
-environment=XTTS_DEVICE="%(ENV_XTTS_DEVICE)s",XTTS_SPEAKER="%(ENV_XTTS_SPEAKER)s",XTTS_LANGUAGE="%(ENV_XTTS_LANGUAGE)s",XTTS_WORKER_HOST="127.0.0.1",XTTS_WORKER_PORT="8771",TTS_HOME="/opt/xtts-cache",COQUI_TOS_AGREED="1"
-priority=280
-autorestart=true
-stdout_logfile=/dev/stdout
-stdout_logfile_maxbytes=0
-stderr_logfile=/dev/stderr
-stderr_logfile_maxbytes=0
+# (No TTS worker program: the default Edge TTS engine synthesises in-process in
+# the bridge via the `edge-tts` package — no warm model/worker is needed.)
 
 [program:bridge]
 command=/app/docker/run-if-role.sh full,bot /opt/venv/bin/python -m bridge.server

docs/llm_contexts.md

@@ -19,14 +19,14 @@ Every distinct LLM call in Jarvis, what feeds it, what consumes it, and how it i
   - Time + location context (re-injected each turn)
   - Tool schema: native via `generate_tools_json_schema()` ([src/jarvis/tools/registry.py](src/jarvis/tools/registry.py)) or text fallback via `_text_tool_call_guidance()` ([engine.py:68](src/jarvis/reply/engine.py:68))
   - Tool results from prior turns (raw or digested — see #5)
-- **Output**: OpenAI-style `{content, tool_calls, thinking}`. Consumed by the tool orchestrator and TTS pipeline. Natural-language content is delivered immediately; no post-turn evaluator runs.
-- **Limits**: `num_ctx: 8192` (explicit). Timeout `llm_chat_timeout_sec` (45s). Auto-fallback from native to text tool-calls on HTTP 400 (`ToolsNotSupportedError`), sticky for the session. Risk: `fetch_web_page` truncates at 50,000 chars (~37k tokens) — mitigated for SMALL models by tool-result digest (#5) which compresses the payload before it enters the messages history. LARGE models receive the raw payload and may silently see a truncated context.
+- **Output**: OpenAI-style `{content, tool_calls, thinking}`. Consumed by the tool orchestrator and TTS pipeline. Natural-language content is delivered immediately; no post-turn evaluator runs. Spoken-answer length: the persona (`system_prompt.py`) and `voice_style` (`prompts/system.py`) both constrain the reply to a SINGLE sentence — any dry aside must fold into that one sentence as a trailing clause, never a second sentence. This keeps TTS latency down (synth time scales with text length) and matches the `agents/llm.md` operator instruction.
+- **Limits**: `num_ctx: 8192` (explicit). Output `num_predict: cfg.ollama_num_predict` (default 512, `0`/negative disables) caps generated tokens per turn — a worst-case latency guard for short spoken answers; the headroom stays above tool-call JSON so it does not truncate tool calls (both native and text tool-call paths). Timeout `llm_chat_timeout_sec` (45s). Auto-fallback from native to text tool-calls on HTTP 400 (`ToolsNotSupportedError`), sticky for the session. Risk: `fetch_web_page` truncates at 50,000 chars (~37k tokens) — mitigated for SMALL models by tool-result digest (#5) which compresses the payload before it enters the messages history. LARGE models receive the raw payload and may silently see a truncated context.
 
 ## 2. Intent Judge
 
 - **File**: [src/jarvis/listening/intent_judge.py](src/jarvis/listening/intent_judge.py) — `IntentJudge.evaluate()`.
 - **Trigger**: on a speech segment *only if* there is an engagement signal (wake word detected, hot-window active, or TTS playing). Pure ambient speech skips it.
-- **Model / gating**: `cfg.intent_judge_model` (default `gemma4:e2b`, ~2B). Falls back to text-based wake detection if Ollama is unavailable.
+- **Model / gating**: `cfg.intent_judge_model`. Code-level default `gemma4:e2b` (~2B); the **Docker stack** renders it from `OLLAMA_INTENT_MODEL` (default `qwen2.5:3b`, pulled by `ollama-init`), kept deliberately **separate from `ollama_chat_model`** so this judge and the tool router (#3, #7) run on a small fast model while the big chat model is reserved for the spoken answer. Setting `OLLAMA_INTENT_MODEL = OLLAMA_CHAT_MODEL` folds them back onto one resident model. Falls back to text-based wake detection if Ollama is unavailable.
 - **Inputs**:
   - Rolling transcript buffer (last 120s, with timestamps)
   - Wake-word timestamp (if any), normalised aliases
@@ -246,7 +246,7 @@ user input
 3. Pre-warm the intent-judge model before TTS finishes.
 4. Cache tool-router (#7) output by query hash.
 5. Give each digest its own timeout budget rather than sharing `llm_digest_timeout_sec` (today a slow memory digest can starve the max-turn digest).
-6. Consider single-model deployments: router+planner prefer `intent_judge_model`; loading a second model hurts cold-start latency on small hardware.
+6. Two-model vs single-model tradeoff: the Docker default keeps a **separate** small `intent_judge_model` (`OLLAMA_INTENT_MODEL=qwen2.5:3b`) so routing/judging/extraction don't pay the big chat model's per-call cost — the main win once the GPU holds both models resident. On VRAM-constrained hardware, fold them onto one model by setting `OLLAMA_INTENT_MODEL = OLLAMA_CHAT_MODEL` (saves a resident model at the cost of slower routing when the chat model is large).
 7. Narrow `llm_thinking_enabled` to router/planner only, not every context.
 8. Reduce `intent_judge_timeout_sec` (15s) or race it against text-based wake detection to avoid blocking the audio loop.
 

src/jarvis/config.py

@@ -85,6 +85,12 @@ class Settings:
     llm_digest_timeout_sec: float
     llm_embedding_timeout_sec: float
     llm_profile_select_timeout_sec: float
+    # Upper bound on tokens the chat model may generate per reply turn. Spoken
+    # (TTS) answers are 1-2 sentences, so a cap bounds the worst-case latency of
+    # a model that occasionally rambles or loops without changing normal answers.
+    # The headroom (default 512) sits well above this app's short tool-call JSON,
+    # so capping never truncates a tool call. 0 (or negative) disables the cap.
+    ollama_num_predict: int
 
     # Profiles & Behavior
     active_profiles: list[str]
@@ -394,6 +400,9 @@ def get_default_config() -> Dict[str, Any]:
         "llm_digest_timeout_sec": 8.0,
         "llm_embedding_timeout_sec": 60.0,
         "llm_profile_select_timeout_sec": 30.0,
+        # Cap on chat-model output tokens per turn (worst-case latency guard).
+        # 512 is safe headroom above short TTS answers and tool-call JSON; 0 off.
+        "ollama_num_predict": 512,
 
         # Profiles & Behavior
         "active_profiles": ["developer", "business", "life"],
@@ -608,7 +617,11 @@ def load_settings() -> Settings:
     active_profiles = _ensure_list(merged.get("active_profiles"))
     tts_enabled = bool(merged.get("tts_enabled", True))
     tts_engine = str(merged.get("tts_engine", "piper")).lower()
-    if tts_engine not in ("piper", "chatterbox"):
+    # "edge" (Microsoft Edge TTS) is the containerized bridge's Korean voice;
+    # "melo" is the legacy warm-worker voice. Both are multilingual, so they must
+    # be preserved here — coercing them to "piper" would mislabel the engine as
+    # English-only in reply_language_directive().
+    if tts_engine not in ("piper", "chatterbox", "edge", "melo"):
         tts_engine = "piper"  # Default to piper if invalid value
     tts_voice_val = merged.get("tts_voice")
     tts_voice = None if tts_voice_val in (None, "", "null") else str(tts_voice_val)
@@ -759,6 +772,10 @@ def load_settings() -> Settings:
     llm_digest_timeout_sec = float(merged.get("llm_digest_timeout_sec", 8.0))
     llm_embedding_timeout_sec = float(merged.get("llm_embedding_timeout_sec", 60.0))
     llm_profile_select_timeout_sec = float(merged.get("llm_profile_select_timeout_sec", 30.0))
+    try:
+        ollama_num_predict = int(merged.get("ollama_num_predict", 512))
+    except (TypeError, ValueError):
+        ollama_num_predict = 512
 
     return Settings(
         # Database & Storage
@@ -774,6 +791,7 @@ def load_settings() -> Settings:
         llm_digest_timeout_sec=llm_digest_timeout_sec,
         llm_embedding_timeout_sec=llm_embedding_timeout_sec,
         llm_profile_select_timeout_sec=llm_profile_select_timeout_sec,
+        ollama_num_predict=ollama_num_predict,
 
         # Profiles & Behavior
         active_profiles=active_profiles,

src/jarvis/reply/engine.py

@@ -2233,6 +2233,16 @@ def run_reply_engine(db: "Database", cfg, tts: Optional[Any],
                 has_tool_calls = " (has tool_calls)" if msg.get("tool_calls") else ""
                 debug_log(f"    [{i}] {role}: {content}{has_tool_calls}", "planning")
 
+        # Bound worst-case generation latency: spoken answers are 1-2 sentences,
+        # so cap the chat model's output tokens. The default headroom sits well
+        # above this app's tool-call JSON, so capping never truncates a tool
+        # call. 0/negative disables it. See config.ollama_num_predict.
+        try:
+            _num_predict = int(getattr(cfg, 'ollama_num_predict', 0) or 0)
+        except (TypeError, ValueError):
+            _num_predict = 0
+        _chat_extra_options = {"num_predict": _num_predict} if _num_predict > 0 else None
+
         # Send messages to Ollama — try native tool calling first, fall back to text-based
         # if the model returns HTTP 400 (native tools API not supported).
         _dump_tools_schema = None if use_text_tools else tools_json_schema
@@ -2242,7 +2252,7 @@ def run_reply_engine(db: "Database", cfg, tts: Optional[Any],
                 chat_model=cfg.ollama_chat_model,
                 messages=messages,
                 timeout_sec=float(getattr(cfg, 'llm_chat_timeout_sec', 45.0)),
-                extra_options=None,
+                extra_options=_chat_extra_options,
                 tools=_dump_tools_schema,
                 thinking=getattr(cfg, 'llm_thinking_enabled', False),
             )
@@ -2273,7 +2283,7 @@ def run_reply_engine(db: "Database", cfg, tts: Optional[Any],
                 chat_model=cfg.ollama_chat_model,
                 messages=messages,
                 timeout_sec=float(getattr(cfg, 'llm_chat_timeout_sec', 45.0)),
-                extra_options=None,
+                extra_options=_chat_extra_options,
                 tools=None,
                 thinking=getattr(cfg, 'llm_thinking_enabled', False),
             )

src/jarvis/reply/prompts/model_variants.py

@@ -22,11 +22,15 @@ class ModelSize(Enum):
     LARGE = "large"  # 8b+ - can infer tool usage from context
 
 
-# Model size patterns - models matching these are considered SMALL
+# Model size patterns - models matching these are considered SMALL.
+# Covers every sub-8B size (1b-7b): these models need the explicit, repeated
+# tool/greeting/instruction constraints and falter on the terse LARGE prompt.
+# Without 2b/4b/5b/6b here a genuinely small model (e.g. qwen*:4b) was
+# misclassified as LARGE and given the less-guided prompt set.
 _SMALL_MODEL_PATTERNS = (
-    ":1b", ":3b", ":7b",
-    "-1b", "-3b", "-7b",
-    "_1b", "_3b", "_7b",
+    ":1b", ":2b", ":3b", ":4b", ":5b", ":6b", ":7b",
+    "-1b", "-2b", "-3b", "-4b", "-5b", "-6b", "-7b",
+    "_1b", "_2b", "_3b", "_4b", "_5b", "_6b", "_7b",
     "gemma4",  # Gemma 4 - always small regardless of tag
 )
 

src/jarvis/reply/prompts/prompts.spec.md

@@ -4,7 +4,7 @@ This module provides model-size-aware prompt generation for the reply engine.
 
 ### Problem Statement
 
-Small models (1b, 3b, 7b parameters) lack the reasoning capacity to infer when NOT to use tools. When given prompts like "Proactively use available tools," they may incorrectly call tools for simple greetings like "hello" or "ni hao" because they cannot distinguish between:
+Small models (every sub-8B size, 1b-7b parameters) lack the reasoning capacity to infer when NOT to use tools. When given prompts like "Proactively use available tools," they may incorrectly call tools for simple greetings like "hello" or "ni hao" because they cannot distinguish between:
 - Requests that require tools (weather, search, data retrieval)
 - Simple conversation (greetings, small talk, general knowledge)
 
@@ -14,7 +14,7 @@ The module detects model size from the model name and selects appropriate prompt
 
 | Model Size | Detection Pattern | Tool Prompts |
 |------------|-------------------|--------------|
-| SMALL | `:1b`, `:3b`, `:7b`, `gemma4` | Conservative — explicit "DO NOT use tools for greetings" + worked negative examples + repetition |
+| SMALL | `:1b`-`:7b` (every size 1-7B, all separators), `gemma4` | Conservative — explicit "DO NOT use tools for greetings" + worked negative examples + repetition |
 | LARGE | All others (8b+) | Proactive — "use tools confidently" + short anti-confabulation + auto-derive clause |
 
 ### Architecture
@@ -43,7 +43,7 @@ from jarvis.reply.prompts import (
 Both model sizes share these base components:
 - `asr_note`: Voice transcription error handling
 - `inference_guidance`: Prefer inference over clarification
-- `voice_style`: Concise, conversational responses
+- `voice_style`: Single-sentence, conversational responses (spoken aloud, so one sentence only — never more)
 
 Model-size-specific components:
 - `tool_incentives`: When/how aggressively to use tools

src/jarvis/reply/prompts/system.py

@@ -26,8 +26,8 @@ INFERENCE_GUIDANCE = (
 # Voice assistant communication style - concise, conversational
 VOICE_STYLE = (
     "Keep responses concise and conversational since this is a voice assistant. "
-    "Two to three sentences maximum. Prioritize clarity and brevity - users are listening, not reading. "
-    "Avoid unnecessary elaboration unless specifically requested. "
+    "Reply in a SINGLE sentence - never more than one sentence. Prioritize clarity and brevity - users are listening, not reading. "
+    "Avoid unnecessary elaboration. "
     "Do NOT offer follow-up suggestions or ask if the user wants more info - just respond directly. "
     "IMPORTANT: Always respond in natural language - never output JSON, code, or structured data as your response. "
     "NEVER use markdown formatting in your replies: no asterisks for emphasis (**bold**, *italic*), "

src/jarvis/reply/reply.spec.md

@@ -287,6 +287,8 @@ Turn 4: LLM → {content: "Here's a comprehensive comparison of the iPhone 15 mo
   - `llm_tools_timeout_sec` (enrichment extraction)
   - `llm_embed_timeout_sec` (vector search)
   - `llm_chat_timeout_sec` (messages loop turn)
+- Output bound:
+  - `ollama_num_predict` (default `512`, `0`/negative disables) caps the chat model's generated tokens per turn via the Ollama `num_predict` option on the messages-loop call. Spoken (TTS) answers are 1-2 sentences, so this never clips a normal answer; it bounds the worst-case latency of a model that occasionally rambles or loops. The default headroom sits well above this app's short tool-call JSON, so it does not truncate tool calls. Applied uniformly to the reply loop's chat call (both native-tools and text-tools paths); the small classification passes (intent judge, digests) keep their own caps. Note: this is a worst-case guard, not the primary latency lever, which is model size and GPU residency.
 - Memory enrichment:
   - `memory_enrichment_max_results` limits recalled snippets.
   - `memory_digest_enabled` (default `null` = auto-on for SMALL models ≤7B, off for LARGE) distils the combined diary + graph dump into a short relevance-filtered note via a cheap LLM pass before injecting into the system prompt. See **Memory Digest for Small Models** below.

src/jarvis/system_prompt.py

@@ -62,10 +62,11 @@ _SYSTEM_PROMPT_TEMPLATE: str = (
     "Tone rails (hard): never mean, never condescending, never passive-aggressive, never "
     "sulking, never preachy, never sycophantic ('great question', 'I'd be happy to'). "
     "Sarcasm points at the situation, the topic, or mildly at yourself — never at the user. "
-    "Shape for casual, factual, or small-talk replies: state the answer in a sentence, then add "
-    "one short dry observation about it (an understated aside, a raised-eyebrow remark, a gentle "
-    "noticing of the irony). One aside — not two, not a joke opener, not a joke-shaped sentence "
-    "replacing the answer. The aside is a tail, not the head. "
+    "Shape for casual, factual, or small-talk replies: give the answer in a SINGLE sentence. If a "
+    "dry aside fits, fold it into that same sentence as a short trailing clause — never add it as "
+    "a second sentence, never a joke opener, never a joke-shaped sentence replacing the answer. "
+    "Whenever the wit would require a second sentence, drop the wit and keep the one-sentence "
+    "answer. The aside is a tail inside the sentence, not a head and not a new sentence. "
     "Examples of the MOVE (shape, not wording — never copy these): stating a fact and then noting "
     "its mild absurdity; giving the weather and then commenting on what it implies for the day; "
     "answering a trivia question and then offering a wry footnote about the subject; admitting "
@@ -79,8 +80,8 @@ _SYSTEM_PROMPT_TEMPLATE: str = (
     "butler clichés, and never address the user as 'sir', 'madam', 'my liege', or similar. "
     "Never stack multiple jokes in one reply. "
     "Be concise, conversational, and actionable. "
-    "This is a spoken voice assistant: answer in ONE short sentence whenever possible "
-    "(two at the very most). No lists, no preamble, no 'is there anything else' offers. "
+    "This is a spoken voice assistant: your ENTIRE reply must be a single short sentence. "
+    "Never write a second sentence. No lists, no preamble, no 'is there anything else' offers. "
     "When a controlBrowser tool is available, use IT (never webSearch) for anything that "
     "should happen in the on-screen browser — opening a site, searching on a site "
     "(controlBrowser action 'search' with the right site), clicking, typing — because only "
@@ -119,10 +120,13 @@ _SYSTEM_PROMPT_TEMPLATE: str = (
     "'tell me a joke', 'chat with me'), never reply with a bare greeting like 'Hey there!', "
     "'Hi!', 'How can I help you?', or a generic observation about an unrelated topic. "
     "When the 'Information the user has shared…' section is present, you MUST pick one concrete "
-    "fact from it and build the reply around that fact (e.g. 'You mentioned you box at Trenches "
-    "Gym — how's training going this week?'). Do not talk about things that are not in that "
-    "section. Only when that section is absent may you invent a fresh observation, question, or "
-    "joke. Produce a varied response each time — do not repeat a previous reply verbatim. "
+    "fact from it and build the reply around that fact, opening with a short natural reference to "
+    "it. CRITICAL: use ONLY names, places, activities, and details that literally appear in that "
+    "section — never borrow any name, place, or activity from these instructions or from any "
+    "example wording, and never invent specifics that are not in that section. Do not talk about "
+    "things that are not in that section. Only when that section is absent may you invent a fresh "
+    "observation, question, or joke. Produce a varied response each time — do not repeat a "
+    "previous reply verbatim. "
     "Banned phrasings: 'I can only tell you what you have shared with me in this conversation', "
     "'I don't have access to any personal information outside of what you tell me', 'I don't have "
     "personal details outside of our conversation history', 'I do not store personal details "

src/jarvis/tools/builtin/browse_and_play.py

@@ -30,8 +30,10 @@ class BrowseAndPlayTool(Tool):
     def description(self) -> str:
         return (
             "Play a song / music video / clip on the shared screen by searching YouTube "
-            "and playing the first result. Use when the user asks you to play or watch "
-            "something. Only available in screen-share mode."
+            "and playing a result. Use when the user asks you to play or watch "
+            "something. Plays the first result by default; pass 'index' to play the "
+            "Nth result from the top of the search list (e.g. 'play the 3rd video' -> "
+            "index=3). Only available in screen-share mode."
         )
 
     @property
@@ -42,7 +44,16 @@ class BrowseAndPlayTool(Tool):
                 "query": {
                     "type": "string",
                     "description": "What to play, e.g. 'IU Good Day' or 'lofi hip hop'.",
-                }
+                },
+                "index": {
+                    "type": "integer",
+                    "description": (
+                        "1-based position of the video to play in the search results, "
+                        "counted from the top of the list. Defaults to 1 (first result). "
+                        "Use for 'play the Nth video' / 'play the second one'."
+                    ),
+                    "minimum": 1,
+                },
             },
             "required": ["query"],
         }
@@ -55,18 +66,25 @@ class BrowseAndPlayTool(Tool):
                 reply_text="화면 공유 모드(STREAM_BROWSER=true)에서만 영상을 재생할 수 있습니다.",
             )
         query = ""
+        index = 1
         if args and isinstance(args, dict):
             query = str(args.get("query", "")).strip()
+            try:
+                index = int(args.get("index", 1) or 1)
+            except (TypeError, ValueError):
+                index = 1
+            if index < 1:
+                index = 1
         if not query:
             return ToolExecutionResult(success=False, reply_text="재생할 내용을 알려주세요.")
         if not _NODE_SCRIPT.exists():
             return ToolExecutionResult(success=False, reply_text="브라우저 재생 도구를 찾을 수 없습니다.")
 
-        context.user_print(f"▶️ 화면에서 '{query}' 재생 중…")
-        debug_log(f"    ▶️ browseAndPlay '{query}'", "tools")
+        context.user_print(f"▶️ 화면에서 '{query}' 재생 중… (#{index})")
+        debug_log(f"    ▶️ browseAndPlay '{query}' index={index}", "tools")
         try:
             proc = subprocess.run(
-                ["node", str(_NODE_SCRIPT), query, "youtube"],
+                ["node", str(_NODE_SCRIPT), query, "youtube", str(index)],
                 capture_output=True,
                 text=True,
                 timeout=40,

src/jarvis/tools/builtin/browse_and_play.spec.md

@@ -6,16 +6,24 @@ video, or clip.
 
 ### Behaviour
 
-- Public schema is a single required `query` string (what to play).
+- Public schema is a required `query` string (what to play) plus an optional
+  `index` integer (1-based position in the search results, counted from the top
+  of the list). `index` defaults to `1` (first result), so existing callers and
+  "play X" requests are unchanged; "play the 3rd video" / "play the second one"
+  map to `index=3` / `index=2`.
 - **Mode-gated**: only acts when `STREAM_BROWSER` is true (`cfg.stream_browser`).
   In voice-only mode (false) there is no screen to show, so it returns a short
   message and does nothing.
 - Drives the on-screen Chrome by subprocessing the Node CDP helper
-  `bot/scripts/stream-test/browse-search.mjs <query> youtube`, which searches
-  YouTube and plays the first result on display `:1`. The broadcast captures
-  that display, so the playback is what viewers see.
-- Returns `success` with the played video's title, or a failure message if the
-  helper/Chrome is unavailable. It does NOT make an LLM call.
+  `bot/scripts/stream-test/browse-search.mjs <query> youtube <index>`, which
+  searches YouTube and plays the chosen result on display `:1`. The broadcast
+  captures that display, so the playback is what viewers see.
+  - The helper clicks the `index`-th `a#video-title` in the results list. The
+    index is clamped to the number of results actually returned, so asking for a
+    position beyond the list plays the last available result rather than failing.
+- Returns `success` with the played video's title (and the resolved `index`), or
+  a failure message if the helper/Chrome is unavailable. It does NOT make an LLM
+  call.
 
 ### Principles
 

src/jarvis/tools/builtin/control_browser.py

@@ -45,9 +45,16 @@ class ControlBrowserTool(Tool):
             "Use this (NOT webSearch) whenever the user wants something done or shown IN the "
             "browser on screen: open a website or URL, search on a specific site (action "
             "'search' with site=naver/google/daum/youtube/bing), go back/forward, refresh, "
-            "manage tabs (list/new/close/switch), close popups, click, type, scroll, or "
-            "screenshot. webSearch only returns text and shows nothing on screen; this tool "
-            "actually navigates the visible browser. Only available in screen-share mode. "
+            "manage tabs (list/new/close/switch), close popups, move the mouse onto an element, "
+            "click, type, scroll, or screenshot. webSearch only returns text and shows nothing "
+            "on screen; this tool actually navigates the visible browser. "
+            "Cursor behaviour matters: 'search' and 'type' (with a selector) move the REAL mouse "
+            "cursor to the on-page box, click it, then type one character at a time — use these "
+            "when the user wants to search or type on a page. 'navigate' only types the URL into "
+            "the address bar (no mouse movement). 'moveMouse' moves/hovers the visible cursor "
+            "onto an element (selector, or site=naver/... for that site's search box) WITHOUT "
+            "clicking — use it when the user just asks to move the mouse somewhere. "
+            "Only available in screen-share mode. "
             "Never claim you did any of this unless this tool returns success."
         )
 
@@ -61,16 +68,16 @@ class ControlBrowserTool(Tool):
                     "enum": [
                         "status", "listTabs", "navigate", "search", "back",
                         "forward", "refresh", "newTab", "closeTab", "activateTab",
-                        "closePopups", "click", "type", "scroll", "pressKey",
+                        "closePopups", "moveMouse", "click", "type", "scroll", "pressKey",
                         "screenshot",
                     ],
                     "description": "What to do in the browser.",
                 },
                 "url": {"type": "string", "description": "Target URL/site for navigate/newTab (e.g. 'naver.com')."},
                 "query": {"type": "string", "description": "Search text for action 'search'."},
-                "site": {"type": "string", "description": "Search site for action 'search': naver, google, daum, youtube, bing."},
+                "site": {"type": "string", "description": "Site for action 'search' or 'moveMouse': naver, google, daum, youtube, bing. For moveMouse it targets that site's search box."},
                 "index": {"type": "integer", "description": "Tab index for closeTab/activateTab (from listTabs)."},
-                "selector": {"type": "string", "description": "CSS selector for click/type."},
+                "selector": {"type": "string", "description": "CSS selector for click/type/moveMouse."},
                 "text": {"type": "string", "description": "Text to type."},
                 "key": {"type": "string", "description": "Key to press, e.g. 'Return', 'Escape'."},
                 "dir": {"type": "string", "description": "Scroll direction: 'down' or 'up'."},
@@ -149,7 +156,12 @@ class ControlBrowserTool(Tool):
         if action == "navigate":
             return f"브라우저에서 {data.get('url', args.get('url'))} 로 이동했습니다."
         if action == "search":
-            return f"{data.get('site', '')}에서 '{data.get('query', args.get('query'))}'를 검색해 화면에 띄웠습니다."
+            base = f"{data.get('site', '')}에서 '{data.get('query', args.get('query'))}'를 검색해 화면에 띄웠습니다."
+            # Flag when the real cursor path didn't run, so a silent fallback to
+            # cursor-less DOM input is visible rather than reported as "human".
+            if data.get("input") in ("api", "api-fallback"):
+                base += " (참고: 실제 마우스 커서 이동 없이 처리됨)"
+            return base
         if action in ("back", "forward", "refresh"):
             return f"브라우저: {action} 완료 ({data.get('url', '')})."
         if action in ("status", "listTabs"):
@@ -164,6 +176,9 @@ class ControlBrowserTool(Tool):
             return f"탭 {data.get('active')}번으로 전환했습니다."
         if action == "closePopups":
             return f"팝업/빈 탭 {data.get('closed')}개를 닫았습니다."
+        if action == "moveMouse":
+            target = data.get("target") or args.get("selector") or args.get("site") or "대상"
+            return f"마우스 커서를 {target} 위치로 옮겼습니다."
         if action == "screenshot":
             return f"화면을 캡처했습니다: {data.get('path')}"
         return "완료했습니다."

tests/test_browse_and_play_index.py

@@ -0,0 +1,79 @@
+"""Tests for browseAndPlay's ``index`` argument (play the Nth search result).
+
+Behaviour verified:
+- default plays the first result (index 1) and stays backward-compatible,
+- an explicit index is forwarded to the Node helper as the 4th argv,
+- bad / sub-1 index values clamp to 1,
+- the index is advertised in the tool schema.
+"""
+
+import json
+from unittest.mock import Mock, patch
+
+import pytest
+
+from src.jarvis.tools.builtin.browse_and_play import BrowseAndPlayTool, _NODE_SCRIPT
+
+
+def _ctx():
+    cfg = Mock()
+    cfg.stream_browser = True
+    return Mock(cfg=cfg, user_print=Mock())
+
+
+def _run(args):
+    tool = BrowseAndPlayTool()
+    with patch("src.jarvis.tools.builtin.browse_and_play.subprocess.run") as mock_run:
+        mock_run.return_value = Mock(
+            stdout=json.dumps({"ok": True, "title": "Some Video"}),
+            stderr="",
+        )
+        result = tool.run(args, _ctx())
+        return mock_run, result
+
+
+def _argv(mock_run):
+    return list(mock_run.call_args[0][0])
+
+
+@pytest.mark.unit
+def test_schema_exposes_index():
+    schema = BrowseAndPlayTool().inputSchema
+    assert "index" in schema["properties"]
+    assert schema["properties"]["index"]["type"] == "integer"
+    assert "query" in schema["required"]
+    assert "index" not in schema["required"]  # optional
+
+
+@pytest.mark.unit
+def test_default_index_is_first():
+    mock_run, result = _run({"query": "IU Good Day"})
+    argv = _argv(mock_run)
+    assert argv[:4] == ["node", str(_NODE_SCRIPT), "IU Good Day", "youtube"]
+    assert argv[4] == "1"
+    assert result.success is True
+
+
+@pytest.mark.unit
+def test_explicit_index_forwarded():
+    mock_run, _ = _run({"query": "lofi", "index": 3})
+    assert _argv(mock_run)[4] == "3"
+
+
+@pytest.mark.unit
+@pytest.mark.parametrize("bad", [0, -2, "nope", None])
+def test_bad_index_clamps_to_one(bad):
+    mock_run, _ = _run({"query": "lofi", "index": bad})
+    assert _argv(mock_run)[4] == "1"
+
+
+@pytest.mark.unit
+def test_voice_only_mode_does_not_play():
+    tool = BrowseAndPlayTool()
+    cfg = Mock()
+    cfg.stream_browser = False
+    ctx = Mock(cfg=cfg, user_print=Mock())
+    with patch("src.jarvis.tools.builtin.browse_and_play.subprocess.run") as mock_run:
+        result = tool.run({"query": "x", "index": 2}, ctx)
+    assert result.success is False
+    mock_run.assert_not_called()

tests/test_control_browser.py

@@ -0,0 +1,56 @@
+"""Tests for the controlBrowser tool's action surface.
+
+These are deterministic schema/summary checks — they do not drive a real
+browser. The actual cursor movement is exercised live on the browser host
+(xdotool + CDP), which these tests cannot reach.
+"""
+
+import pytest
+
+from jarvis.tools.builtin.control_browser import ControlBrowserTool
+
+
+@pytest.fixture
+def tool():
+    return ControlBrowserTool()
+
+
+def test_movemouse_is_an_exposed_action(tool):
+    # A weak model confabulated "moved the mouse" because no move/hover action
+    # existed to call. The cursor-move capability must be a real action so the
+    # request "move the mouse to the search box" maps to a tool call.
+    enum = tool.inputSchema["properties"]["action"]["enum"]
+    assert "moveMouse" in enum
+
+
+def test_movemouse_summary_reports_the_target(tool):
+    summary = tool._summarise("moveMouse", {"site": "naver"}, {"ok": True, "target": "naver"})
+    assert "마우스" in summary and "naver" in summary
+
+
+def test_description_distinguishes_cursor_paths(tool):
+    # The model must know navigate is address-bar only (no mouse) while
+    # search/type/moveMouse move the real cursor — that distinction is the
+    # whole point of the fix.
+    desc = tool.description
+    assert "moveMouse" in desc
+    assert "address bar" in desc  # navigate is described as address-bar typing
+
+
+def test_search_summary_flags_cursorless_fallback(tool):
+    # When the real xdotool cursor path didn't run, the summary must say so
+    # rather than implying a human-like search happened.
+    human = tool._summarise("search", {"query": "날씨"}, {"ok": True, "site": "naver", "query": "날씨", "input": "human"})
+    assert "참고: 실제 마우스" not in human
+
+    fell_back = tool._summarise("search", {"query": "날씨"}, {"ok": True, "site": "naver", "query": "날씨", "input": "api-fallback"})
+    assert "실제 마우스 커서 이동 없이" in fell_back
+
+
+def test_movemouse_summary_only_runs_on_success(tool):
+    # _summarise is only called on ok:true; an ok:false (target not found / no
+    # xdotool) is handled by run() as a failure reply, so a failed move can no
+    # longer be reported as "moved". Sanity-check the success summary names a
+    # target rather than a placeholder when one is present.
+    summary = tool._summarise("moveMouse", {"selector": "#query"}, {"ok": True, "target": "#query"})
+    assert "#query" in summary

tests/test_intent_model_split.py

@@ -0,0 +1,62 @@
+"""The docker deployment must run auxiliary calls on a small model.
+
+Latency win: intent judging, tool routing and arg extraction are
+classification/JSON calls, not the spoken answer. Running them on a small fast
+model means the big chat model only runs once per command (for the answer),
+instead of 2-3 times per command for routing/extraction too.
+
+The wiring is: docker/jarvis-config.template.json renders `intent_judge_model`
+from `${OLLAMA_INTENT_MODEL}`, and the reply engine's resolver falls through
+`tool_router_model -> intent_judge_model -> ollama_chat_model`. The template
+sets no `tool_router_model`, so the auxiliary model is whatever
+`OLLAMA_INTENT_MODEL` renders to. These tests pin that behaviour end to end.
+"""
+
+import json
+import string
+from pathlib import Path
+
+import pytest
+
+from jarvis.reply.engine import resolve_tool_router_model
+
+TEMPLATE = Path(__file__).resolve().parent.parent / "docker" / "jarvis-config.template.json"
+
+
+def _render(**env) -> dict:
+    raw = TEMPLATE.read_text(encoding="utf-8")
+    return json.loads(string.Template(raw).safe_substitute(**env))
+
+
+class _Cfg:
+    """cfg stand-in carrying only the fields the resolver reads. The template
+    does not render `tool_router_model`, so it stays empty here too."""
+
+    def __init__(self, rendered: dict):
+        self.tool_router_model = rendered.get("tool_router_model", "") or ""
+        self.intent_judge_model = rendered.get("intent_judge_model", "") or ""
+        self.ollama_chat_model = rendered.get("ollama_chat_model", "") or ""
+
+
+def test_template_renders_separate_intent_model():
+    cfg = _render(OLLAMA_CHAT_MODEL="qwen3:8b", OLLAMA_INTENT_MODEL="qwen2.5:3b")
+    assert cfg["ollama_chat_model"] == "qwen3:8b"
+    assert cfg["intent_judge_model"] == "qwen2.5:3b"
+    assert cfg["intent_judge_model"] != cfg["ollama_chat_model"]
+
+
+@pytest.mark.unit
+def test_aux_calls_route_to_small_model_not_chat_model():
+    """The whole point: with a big chat model and a small intent model, tool
+    routing must resolve to the small model, leaving the big model for answers."""
+    cfg = _Cfg(_render(OLLAMA_CHAT_MODEL="qwen3:8b", OLLAMA_INTENT_MODEL="qwen2.5:3b"))
+    assert resolve_tool_router_model(cfg) == "qwen2.5:3b"
+
+
+@pytest.mark.unit
+def test_folding_intent_onto_chat_model_keeps_one_model():
+    """Setting OLLAMA_INTENT_MODEL == OLLAMA_CHAT_MODEL folds everything back
+    onto a single resident model (the documented VRAM-saving opt-out)."""
+    cfg = _Cfg(_render(OLLAMA_CHAT_MODEL="qwen2.5:3b", OLLAMA_INTENT_MODEL="qwen2.5:3b"))
+    assert resolve_tool_router_model(cfg) == "qwen2.5:3b"
+    assert cfg.intent_judge_model == cfg.ollama_chat_model

tests/test_ollama_num_predict.py

@@ -0,0 +1,112 @@
+"""Tests for the ``ollama_num_predict`` chat-output cap.
+
+The cap bounds worst-case reply latency by limiting how many tokens the chat
+model may generate per turn. Spoken (TTS) answers are 1-2 sentences, so the
+default headroom never clips a normal answer and stays above tool-call JSON.
+
+These tests verify behaviour:
+- the config default is present,
+- the value is threaded into the Ollama request as the ``num_predict`` option,
+- the reply loop forwards it to the chat call (and disables it at 0).
+"""
+
+from unittest.mock import Mock, patch
+
+import pytest
+
+from src.jarvis.config import get_default_config
+from src.jarvis.memory.conversation import DialogueMemory
+from src.jarvis.reply.engine import run_reply_engine
+
+
+# ---------------------------------------------------------------------------
+# Config default
+# ---------------------------------------------------------------------------
+
+def test_default_config_has_num_predict_cap():
+    config = get_default_config()
+    assert config["ollama_num_predict"] == 512
+
+
+# ---------------------------------------------------------------------------
+# Transport: extra_options.num_predict reaches the Ollama payload options
+# ---------------------------------------------------------------------------
+
+@patch("jarvis.llm.requests.post")
+def test_chat_with_messages_forwards_num_predict(mock_post):
+    from jarvis.llm import chat_with_messages
+
+    mock_resp = Mock()
+    mock_resp.status_code = 200
+    mock_resp.json.return_value = {"message": {"content": "ok"}}
+    mock_resp.raise_for_status = Mock()
+    mock_post.return_value = mock_resp
+
+    chat_with_messages(
+        "http://localhost:11434",
+        "test-large",
+        [{"role": "user", "content": "hi"}],
+        extra_options={"num_predict": 512},
+    )
+    _, kwargs = mock_post.call_args
+    options = (kwargs.get("json") or {}).get("options") or {}
+    assert options.get("num_predict") == 512
+
+
+# ---------------------------------------------------------------------------
+# Reply loop wiring
+# ---------------------------------------------------------------------------
+
+def _mock_cfg(num_predict):
+    cfg = Mock()
+    cfg.ollama_base_url = "http://localhost:11434"
+    cfg.ollama_chat_model = "test-large"  # avoid SMALL-model text-tool path
+    cfg.ollama_num_predict = num_predict
+    cfg.voice_debug = False
+    cfg.llm_tools_timeout_sec = 8.0
+    cfg.llm_embed_timeout_sec = 10.0
+    cfg.llm_chat_timeout_sec = 45.0
+    cfg.llm_digest_timeout_sec = 8.0
+    cfg.memory_enrichment_max_results = 5
+    cfg.memory_enrichment_source = "diary"
+    cfg.memory_digest_enabled = False
+    cfg.tool_result_digest_enabled = False
+    cfg.location_ip_address = None
+    cfg.location_auto_detect = False
+    cfg.location_enabled = False
+    cfg.agentic_max_turns = 8
+    cfg.tool_search_max_calls = 3
+    cfg.tool_selection_strategy = "all"
+    cfg.tool_carryover_max_turns = 2
+    cfg.tool_carryover_per_entry_chars = 1200
+    cfg.mcps = {}
+    cfg.llm_thinking_enabled = False
+    cfg.tts_engine = "none"
+    cfg.ollama_embed_model = "test-embed"
+    return cfg
+
+
+def _run_single_turn(cfg):
+    """Drive one reply turn that answers in plain text and capture the
+    chat call's extra_options."""
+    with patch("src.jarvis.reply.engine.plan_query", return_value=[]), \
+         patch("src.jarvis.reply.engine.extract_search_params_for_memory", return_value={}), \
+         patch("src.jarvis.reply.engine.extract_text_from_response", return_value="Hello."), \
+         patch("src.jarvis.reply.engine.chat_with_messages") as mock_chat:
+        mock_chat.return_value = {"message": {"content": "Hello."}}
+        run_reply_engine(db=Mock(), cfg=cfg, tts=None,
+                         text="hi", dialogue_memory=DialogueMemory())
+        assert mock_chat.called
+        return mock_chat.call_args.kwargs.get("extra_options")
+
+
+@pytest.mark.unit
+def test_reply_loop_caps_output_when_enabled():
+    extra = _run_single_turn(_mock_cfg(512))
+    assert extra == {"num_predict": 512}
+
+
+@pytest.mark.unit
+def test_reply_loop_no_cap_when_zero():
+    extra = _run_single_turn(_mock_cfg(0))
+    assert extra is None

tests/test_prompts.py

@@ -21,9 +21,15 @@ class TestModelSizeDetection:
         ("gemma:7b", True),
         ("phi3:3b", True),
         ("qwen2:7b", True),
+        # Sub-8B sizes that were previously misclassified as LARGE.
+        ("qwen3.5:4b", True),   # the deployed model that produced weak, off-tone replies
+        ("gemma2:2b", True),
+        ("model:5b", True),
+        ("model:6b", True),
         # Various separators
         ("model-3b-instruct", True),
         ("model_1b_chat", True),
+        ("model-4b-instruct", True),
         # Large models (should return LARGE)
         ("gpt-oss:20b", False),
         ("llama3.1:8b", False),
@@ -121,6 +127,18 @@ class TestPromptComponents:
             assert prompts.voice_style, f"{size.value} missing voice_style"
             assert prompts.tool_guidance, f"{size.value} missing tool_guidance"
 
+    def test_voice_style_enforces_single_sentence(self):
+        """voice_style must cap replies at one sentence (spoken aloud). The old
+        'Two to three sentences maximum' wording let the model run long, which
+        also slowed TTS since synth time scales with text length."""
+        from jarvis.reply.prompts import get_system_prompts, ModelSize
+
+        for size in [ModelSize.SMALL, ModelSize.LARGE]:
+            voice_style = get_system_prompts(size).voice_style
+            assert "SINGLE sentence" in voice_style, f"{size.value} voice_style not single-sentence"
+            assert "never more than one sentence" in voice_style
+            assert "Two to three" not in voice_style
+
     def test_to_list_returns_non_empty_strings(self):
         """to_list() returns only non-empty prompt strings."""
         from jarvis.reply.prompts import get_system_prompts, ModelSize

tests/test_system_prompt.py

@@ -44,6 +44,32 @@ class TestBuildSystemPrompt:
         assert "in the user's language" not in prompt
         assert "in Korean" in prompt
 
+    def test_persona_enforces_single_sentence(self):
+        # Spoken replies must be one sentence (TTS latency scales with text
+        # length, and the user asked for one-sentence answers). The persona must
+        # state the single-sentence rule and must NOT carry the old "two at the
+        # very most" allowance that let the model run long.
+        prompt = build_system_prompt("Jarvis")
+        assert "single short sentence" in prompt
+        assert "Never write a second sentence" in prompt
+        assert "two at the very most" not in prompt
+
+    def test_persona_aside_does_not_authorise_a_second_sentence(self):
+        # The dry aside must fold into the one sentence, not become a 2nd one.
+        prompt = build_system_prompt("Jarvis")
+        assert "SINGLE sentence" in prompt
+        assert "never add it as " in prompt
+
+    def test_persona_has_no_copyable_proper_noun_examples(self):
+        # A weak model parroted the literal "Trenches Gym" example from the
+        # persona as if it were a real user fact (boxing mangled to tennis).
+        # The persona must not embed copyable personal proper nouns, and must
+        # tell the model to use ONLY facts that literally appear in the memory
+        # section — never borrow names/places from the instructions themselves.
+        prompt = build_system_prompt("Jarvis")
+        assert "Trenches" not in prompt
+        assert "never borrow any name, place, or activity from these instructions" in prompt
+
 
 class TestOutputLanguageDirective:
     """A deployment may lock replies to a single language via OUTPUT_LANGUAGE.
@@ -101,14 +127,6 @@ class TestReplyLanguageDirective:
         # user's own language, so no directive.
         assert reply_language_directive(None, "melo") is None
 
-    def test_xtts_is_multilingual(self):
-        # XTTS-v2 (the Korean voice) is not English-only: no lock → free, and a
-        # lock is honoured (not overridden to English).
-        assert reply_language_directive(None, "xtts") is None
-        directive = reply_language_directive("Korean", "xtts")
-        assert directive is not None and "Korean" in directive
-        assert directive != ENGLISH_ONLY_DIRECTIVE
-
     def test_unknown_tts_defaults_to_english_only(self):
         # Preserves the original getattr(cfg, 'tts_engine', 'piper') default:
         # an unknown/missing engine is treated conservatively as English-only.
@@ -118,6 +136,14 @@ class TestReplyLanguageDirective:
         directive = reply_language_directive("Korean", "melo")
         assert directive is not None and "Korean" in directive
 
+    def test_edge_is_multilingual(self):
+        # Edge TTS (the default Korean voice) is not English-only: no lock → the
+        # user's own language, and a lock is honoured (not forced to English).
+        assert reply_language_directive(None, "edge") is None
+        directive = reply_language_directive("Korean", "edge")
+        assert directive is not None and "Korean" in directive
+        assert directive != ENGLISH_ONLY_DIRECTIVE
+
 
 class TestLoadAgentInstructions:
     """Operator can extend the reply LLM's system prompt by dropping *.md files

tests/test_tts_engine_config.py

@@ -0,0 +1,35 @@
+"""The container's TTS engine must be env-driven, not hardcoded.
+
+Regression for a bug where docker/jarvis-config.template.json hardcoded
+`"tts_engine": "piper"`. The bridge reads the rendered /app/config/jarvis.json
+*before* the environment, so a hardcoded "piper" overrode `TTS_ENGINE=melo` in
+.env and the bot read Korean text with the English Piper voice ("foreign
+accent"). The template must carry `${TTS_ENGINE}` so envsubst (entrypoint.sh)
+renders whatever engine the deployment configured.
+"""
+
+import json
+import string
+from pathlib import Path
+
+TEMPLATE = Path(__file__).resolve().parent.parent / "docker" / "jarvis-config.template.json"
+
+
+def _render(**env) -> dict:
+    """Mimic entrypoint.sh `envsubst < template`: substitute env vars, leaving
+    any unset ones as literal text (valid JSON string values)."""
+    raw = TEMPLATE.read_text(encoding="utf-8")
+    return json.loads(string.Template(raw).safe_substitute(**env))
+
+
+def test_template_does_not_hardcode_an_engine():
+    raw = TEMPLATE.read_text(encoding="utf-8")
+    assert '"tts_engine": "${TTS_ENGINE}"' in raw
+    assert '"tts_engine": "piper"' not in raw
+    assert '"tts_engine": "melo"' not in raw
+
+
+def test_rendered_engine_follows_env():
+    assert _render(TTS_ENGINE="melo")["tts_engine"] == "melo"
+    assert _render(TTS_ENGINE="piper")["tts_engine"] == "piper"
+    assert _render(TTS_ENGINE="xtts")["tts_engine"] == "xtts"