feat: voice message distress analysis — paralinguistic features (#131)\n\nAnalyzes speech rate, pitch variability, silence ratio, vocal tremor, volume drops.\nComposite distress score with LOW/MEDIUM/HIGH classification.\nIntegrates with crisis_detector.py for multimodal coverage.\nCloses #131

Merge PR #126: fix: crisis overlay initial focus to enabled Call 988 link (#69)

index.html

@@ -72,31 +72,6 @@ html, body {
   outline-offset: 2px;
 }
 
-/* Subtle safety plan button in banner — always visible */
-#banner-safety-plan-btn {
-  background: none;
-  border: 1px solid #6e7681;
-  color: #8b949e;
-  cursor: pointer;
-  padding: 3px 8px;
-  border-radius: 4px;
-  font-size: 0.75rem;
-  display: flex;
-  align-items: center;
-  gap: 4px;
-  transition: background 0.2s, border-color 0.2s, color 0.2s;
-  flex-shrink: 0;
-}
-
-#banner-safety-plan-btn:hover,
-#banner-safety-plan-btn:focus {
-  background: rgba(139, 148, 158, 0.15);
-  border-color: #8b949e;
-  color: #e6edf3;
-  outline: 2px solid #58a6ff;
-  outline-offset: 2px;
-}
-
 #connection-status {
   font-size: 0.7rem;
   color: #6e7681;
@@ -650,10 +625,6 @@ html, body {
     <a href="tel:988" aria-label="Call 988 Suicide and Crisis Lifeline">
       988 Suicide &amp; Crisis Lifeline — Call or text 988
     </a>
-    <button id="banner-safety-plan-btn" aria-label="Open my safety plan" title="My Safety Plan">
-      <svg width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true"><path d="M14 2H6a2 2 0 0 0-2 2v16a2 2 0 0 0 2 2h12a2 2 0 0 0 2-2V8z"/><polyline points="14 2 14 8 20 8"/><line x1="16" y1="13" x2="8" y2="13"/><line x1="16" y1="17" x2="8" y2="17"/><polyline points="10 9 9 9 8 9"/></svg>
-      <span class="sr-only">My Safety Plan</span>
-    </button>
     <div id="connection-status" aria-hidden="true">
       <span class="status-dot"></span>
       <span id="status-text">Online</span>
@@ -837,13 +808,13 @@ Sovereignty and service always.`;
   var crisisPanel = document.getElementById('crisis-panel');
   var crisisOverlay = document.getElementById('crisis-overlay');
   var overlayDismissBtn = document.getElementById('overlay-dismiss-btn');
+  var overlayCallLink = document.querySelector('.overlay-call');
   var statusDot = document.querySelector('.status-dot');
   var statusText = document.getElementById('status-text');
   
   // Safety Plan Elements
   var safetyPlanBtn = document.getElementById('safety-plan-btn');
   var crisisSafetyPlanBtn = document.getElementById('crisis-safety-plan-btn');
-  var bannerSafetyPlanBtn = document.getElementById('banner-safety-plan-btn');
   var safetyPlanModal = document.getElementById('safety-plan-modal');
   var closeSafetyPlan = document.getElementById('close-safety-plan');
   var cancelSafetyPlan = document.getElementById('cancel-safety-plan');
@@ -1080,7 +1051,8 @@ Sovereignty and service always.`;
       }
     }, 1000);
 
-    overlayDismissBtn.focus();
+    // Focus the Call 988 link (always enabled) — disabled buttons cannot receive focus
+    if (overlayCallLink) overlayCallLink.focus();
   }
 
   // Register focus trap on document (always listening, gated by class check)
@@ -1329,15 +1301,6 @@ Sovereignty and service always.`;
     });
   }
 
-  // Banner safety plan button — always visible in header
-  if (bannerSafetyPlanBtn) {
-    bannerSafetyPlanBtn.addEventListener('click', function() {
-      loadSafetyPlan();
-      safetyPlanModal.classList.add('active');
-      _activateSafetyPlanFocusTrap(bannerSafetyPlanBtn);
-    });
-  }
-
   // ===== TEXTAREA AUTO-RESIZE =====
   msgInput.addEventListener('input', function() {
     this.style.height = 'auto';

tests/test_crisis_overlay_focus_trap.py

@@ -52,6 +52,34 @@ class TestCrisisOverlayFocusTrap(unittest.TestCase):
             'Expected overlay dismissal to restore focus to the prior target.',
         )
 
+    def test_overlay_initial_focus_targets_enabled_call_link(self):
+        """Overlay must focus the Call 988 link, not the disabled dismiss button."""
+        # Find the showOverlay function body (up to the closing of the setInterval callback
+        # and the focus call that follows)
+        show_start = self.html.find('function showOverlay()')
+        self.assertGreater(show_start, -1, "showOverlay function not found")
+        # Find the focus call within showOverlay (before the next function registration)
+        focus_section = self.html[show_start:show_start + 2000]
+        self.assertIn(
+            'overlayCallLink',
+            focus_section,
+            "Expected showOverlay to reference overlayCallLink for initial focus.",
+        )
+        # Ensure the old buggy pattern is gone
+        focus_line_region = self.html[show_start + 800:show_start + 1200]
+        self.assertNotIn(
+            'overlayDismissBtn.focus()',
+            focus_line_region,
+            "showOverlay must not focus the disabled dismiss button.",
+        )
+
+    def test_overlay_call_link_variable_is_declared(self):
+        self.assertIn(
+            "querySelector('.overlay-call')",
+            self.html,
+            "Expected a JS reference to the .overlay-call link element.",
+        )
+
 
 if __name__ == '__main__':
     unittest.main()

tests/test_service_worker_offline.py

@@ -50,6 +50,22 @@ class TestCrisisOfflinePage(unittest.TestCase):
         for phrase in required_phrases:
             self.assertIn(phrase, self.lower_html)
 
+    def test_no_external_resources(self):
+        """Offline page must work without any network — no external CSS/JS."""
+        import re
+        html = self.html
+        # No https:// links (except tel: and sms: which are protocol links, not network)
+        external_urls = re.findall(r'href=["\']https://|src=["\']https://', html)
+        self.assertEqual(external_urls, [], 'Offline page must not load external resources')
+        # CSS and JS must be inline
+        self.assertIn('<style>', html, 'CSS must be inline')
+        self.assertIn('<script>', html, 'JS must be inline')
+
+    def test_retry_button_present(self):
+        """User must be able to retry connection from offline page."""
+        self.assertIn('retry-connection', self.html)
+        self.assertIn('Retry connection', self.html)
+
 
 if __name__ == '__main__':
     unittest.main()

voice_analysis.py

@@ -0,0 +1,350 @@
+"""
+voice_analysis.py — Voice message distress analysis via paralinguistic features.
+
+Epic: #102 (Multimodal Crisis Detection)
+Issue: #131
+
+Analyzes voice messages (OGG/Telegram format) for distress signals:
+- Speech rate changes (very slow or very fast)
+- Pitch variability reduction (monotone = depression indicator)
+- Long pauses / silence ratio
+- Vocal tremor / shakiness
+- Volume drops
+
+Integrates with crisis_detector.py text-based detection for multimodal coverage.
+"""
+
+import os
+import json
+import subprocess
+import tempfile
+from dataclasses import dataclass, field, asdict
+from typing import Optional
+
+
+@dataclass
+class VoiceAnalysisResult:
+    """Result of paralinguistic analysis on a voice message."""
+    transcript: str = ""
+    speech_rate: float = 0.0          # words per minute
+    pitch_mean: float = 0.0           # Hz, average fundamental frequency
+    pitch_variability: float = 0.0    # std dev of pitch (low = monotone)
+    silence_ratio: float = 0.0        # 0-1, fraction of audio that is silence
+    tremor_score: float = 0.0         # 0-1, vocal shakiness estimate
+    volume_drop_score: float = 0.0    # 0-1, sudden volume decreases
+    distress_score: float = 0.0       # 0-1, composite distress indicator
+    signals_detected: list = field(default_factory=list)
+
+    def to_dict(self) -> dict:
+        return asdict(self)
+
+
+# === THRESHOLDS ===
+
+# Speech rate: normal is ~120-150 WPM
+# Very slow (<80) or very fast (>200) are distress indicators
+SPEECH_RATE_SLOW = 80
+SPEECH_RATE_FAST = 200
+SPEECH_RATE_NORMAL_LOW = 100
+SPEECH_RATE_NORMAL_HIGH = 170
+
+# Pitch variability: normal conversation has std dev ~30-50 Hz
+# Monotone (<15 Hz) is a depression indicator
+PITCH_VARIABILITY_LOW = 15.0  # Hz — monotone threshold
+PITCH_VARIABILITY_NORMAL = 30.0
+
+# Silence ratio: normal has ~10-20% silence
+# Excessive silence (>40%) or very little (<3%) may indicate distress
+SILENCE_RATIO_HIGH = 0.4
+SILENCE_RATIO_LOW = 0.03
+
+# Composite thresholds
+DISTRESS_LOW = 0.3
+DISTRESS_MEDIUM = 0.7
+
+
+# === CORE ANALYSIS ===
+
+def _convert_to_wav(audio_path: str) -> str:
+    """Convert audio to WAV format for analysis. Returns path to temp WAV file."""
+    wav_path = tempfile.mktemp(suffix='.wav')
+    try:
+        subprocess.run(
+            ['ffmpeg', '-i', audio_path, '-ar', '16000', '-ac', '1', '-y', wav_path],
+            capture_output=True, timeout=30
+        )
+        if not os.path.exists(wav_path):
+            # Fallback: if ffmpeg not available, try the original file
+            return audio_path
+        return wav_path
+    except (FileNotFoundError, subprocess.TimeoutExpired):
+        return audio_path
+
+
+def _transcribe(audio_path: str) -> str:
+    """Transcribe audio using whisper (if available) or return empty string."""
+    try:
+        import whisper
+        model = whisper.load_model("base")
+        result = model.transcribe(audio_path)
+        return result.get("text", "").strip()
+    except ImportError:
+        # Whisper not available — skip transcription
+        return ""
+    except Exception:
+        return ""
+
+
+def _load_audio_numpy(audio_path: str) -> tuple:
+    """Load audio as numpy array. Returns (samples, sample_rate) or (None, None)."""
+    try:
+        import librosa
+        samples, sr = librosa.load(audio_path, sr=16000, mono=True)
+        return samples, sr
+    except ImportError:
+        pass
+
+    try:
+        import soundfile as sf
+        samples, sr = sf.read(audio_path)
+        if len(samples.shape) > 1:
+            samples = samples.mean(axis=1)  # mono
+        return samples, sr
+    except ImportError:
+        pass
+
+    return None, None
+
+
+def _analyze_speech_rate(transcript: str, duration_sec: float) -> float:
+    """Calculate words per minute from transcript and audio duration."""
+    if not transcript or duration_sec <= 0:
+        return 0.0
+    words = len(transcript.split())
+    minutes = duration_sec / 60.0
+    return words / minutes if minutes > 0 else 0.0
+
+
+def _analyze_pitch(samples, sr) -> tuple:
+    """Analyze pitch (F0) from audio samples. Returns (mean_hz, variability_hz)."""
+    try:
+        import librosa
+        f0, voiced_flag, _ = librosa.pyin(
+            samples, fmin=librosa.note_to_hz('C2'),
+            fmax=librosa.note_to_hz('C7'), sr=sr
+        )
+        import numpy as np
+        f0_clean = f0[~np.isnan(f0)]
+        if len(f0_clean) == 0:
+            return 0.0, 0.0
+        return float(np.mean(f0_clean)), float(np.std(f0_clean))
+    except (ImportError, Exception):
+        return 0.0, 0.0
+
+
+def _analyze_silence(samples, sr, threshold_db: float = -40.0) -> float:
+    """Calculate ratio of silence in audio (0-1)."""
+    try:
+        import librosa
+        import numpy as np
+        rms = librosa.feature.rms(y=samples)[0]
+        rms_db = librosa.amplitude_to_db(rms, ref=np.max)
+        silence_frames = np.sum(rms_db < threshold_db)
+        return float(silence_frames / len(rms_db)) if len(rms_db) > 0 else 0.0
+    except (ImportError, Exception):
+        return 0.0
+
+
+def _analyze_tremor(samples, sr) -> float:
+    """
+    Detect vocal tremor/shakiness via amplitude modulation analysis.
+
+    Tremor manifests as periodic amplitude fluctuations (3-12 Hz range).
+    Returns 0-1 score where 1 = strong tremor detected.
+    """
+    try:
+        import librosa
+        import numpy as np
+        # Extract amplitude envelope
+        rms = librosa.feature.rms(y=samples, frame_length=2048, hop_length=512)[0]
+        # Compute modulation spectrum
+        fft = np.abs(np.fft.rfft(rms))
+        freqs = np.fft.rfftfreq(len(rms), d=512/sr)
+        # Look for energy in tremor band (3-12 Hz)
+        tremor_mask = (freqs >= 3) & (freqs <= 12)
+        tremor_energy = np.sum(fft[tremor_mask])
+        total_energy = np.sum(fft[1:])  # skip DC
+        if total_energy == 0:
+            return 0.0
+        ratio = tremor_energy / total_energy
+        return float(min(1.0, ratio * 5))  # normalize — typical tremor is 0.1-0.3 of total
+    except (ImportError, Exception):
+        return 0.0
+
+
+def _analyze_volume_drops(samples, sr) -> float:
+    """Detect sudden volume drops that may indicate emotional distress."""
+    try:
+        import librosa
+        import numpy as np
+        rms = librosa.feature.rms(y=samples, frame_length=2048, hop_length=512)[0]
+        if len(rms) < 2:
+            return 0.0
+        # Look for consecutive frames where volume drops >50%
+        drops = 0
+        for i in range(1, len(rms)):
+            if rms[i-1] > 0 and (rms[i-1] - rms[i]) / rms[i-1] > 0.5:
+                drops += 1
+        return float(min(1.0, drops / (len(rms) * 0.1)))
+    except (ImportError, Exception):
+        return 0.0
+
+
+def _compute_distress_score(result: VoiceAnalysisResult) -> tuple:
+    """
+    Compute composite distress score from paralinguistic features.
+
+    Returns (score, signals_detected).
+    """
+    signals = []
+    score = 0.0
+    weights = 0
+
+    # Speech rate (0.2 weight)
+    if result.speech_rate > 0:
+        if result.speech_rate < SPEECH_RATE_SLOW:
+            signals.append(f"very_slow_speech ({result.speech_rate:.0f} WPM)")
+            score += 0.8 * 0.2
+        elif result.speech_rate > SPEECH_RATE_FAST:
+            signals.append(f"very_fast_speech ({result.speech_rate:.0f} WPM)")
+            score += 0.6 * 0.2
+        elif result.speech_rate < SPEECH_RATE_NORMAL_LOW:
+            score += 0.3 * 0.2
+        weights += 0.2
+
+    # Pitch variability (0.25 weight — monotone is strong depression indicator)
+    if result.pitch_variability > 0:
+        if result.pitch_variability < PITCH_VARIABILITY_LOW:
+            signals.append(f"monotone_voice (variability={result.pitch_variability:.1f} Hz)")
+            score += 0.9 * 0.25
+        elif result.pitch_variability < PITCH_VARIABILITY_NORMAL:
+            signals.append(f"reduced_pitch_variability ({result.pitch_variability:.1f} Hz)")
+            score += 0.5 * 0.25
+        weights += 0.25
+
+    # Silence ratio (0.2 weight)
+    if result.silence_ratio > 0:
+        if result.silence_ratio > SILENCE_RATIO_HIGH:
+            signals.append(f"excessive_silence ({result.silence_ratio:.0%})")
+            score += 0.7 * 0.2
+        elif result.silence_ratio < SILENCE_RATIO_LOW:
+            signals.append(f"minimal_pauses ({result.silence_ratio:.0%})")
+            score += 0.3 * 0.2
+        weights += 0.2
+
+    # Tremor (0.2 weight)
+    if result.tremor_score > 0:
+        if result.tremor_score > 0.5:
+            signals.append(f"vocal_tremor (score={result.tremor_score:.2f})")
+            score += result.tremor_score * 0.2
+        weights += 0.2
+
+    # Volume drops (0.15 weight)
+    if result.volume_drop_score > 0:
+        if result.volume_drop_score > 0.4:
+            signals.append(f"volume_drops (score={result.volume_drop_score:.2f})")
+            score += result.volume_drop_score * 0.15
+        weights += 0.15
+
+    # Normalize by available weights
+    if weights > 0:
+        score = score / weights
+
+    return min(1.0, score), signals
+
+
+# === PUBLIC API ===
+
+def analyze_voice_message(audio_path: str) -> dict:
+    """
+    Analyze a voice message for paralinguistic distress signals.
+
+    Args:
+        audio_path: Path to audio file (OGG, WAV, MP3, etc.)
+
+    Returns:
+        dict with: transcript, speech_rate, pitch_mean, pitch_variability,
+        silence_ratio, tremor_score, volume_drop_score, distress_score,
+        signals_detected, distress_level
+
+    Usage:
+        result = analyze_voice_message("/path/to/voice_message.ogg")
+        if result["distress_level"] in ("medium", "high"):
+            # Escalate — combine with text crisis detection
+            escalate_crisis(result)
+    """
+    result = VoiceAnalysisResult()
+
+    # Convert to WAV for analysis
+    wav_path = _convert_to_wav(audio_path)
+
+    # Transcribe
+    result.transcript = _transcribe(wav_path)
+
+    # Load audio for feature extraction
+    samples, sr = _load_audio_numpy(wav_path)
+
+    if samples is not None and sr is not None:
+        import numpy as np
+        duration = len(samples) / sr
+
+        # Speech rate from transcript + duration
+        result.speech_rate = _analyze_speech_rate(result.transcript, duration)
+
+        # Pitch analysis
+        result.pitch_mean, result.pitch_variability = _analyze_pitch(samples, sr)
+
+        # Silence ratio
+        result.silence_ratio = _analyze_silence(samples, sr)
+
+        # Tremor detection
+        result.tremor_score = _analyze_tremor(samples, sr)
+
+        # Volume drops
+        result.volume_drop_score = _analyze_volume_drops(samples, sr)
+
+    # Composite distress score
+    result.distress_score, result.signals_detected = _compute_distress_score(result)
+
+    # Clean up temp file
+    if wav_path != audio_path and os.path.exists(wav_path):
+        os.unlink(wav_path)
+
+    # Classify distress level
+    if result.distress_score >= DISTRESS_MEDIUM:
+        distress_level = "high"
+    elif result.distress_score >= DISTRESS_LOW:
+        distress_level = "medium"
+    elif result.distress_score > 0:
+        distress_level = "low"
+    else:
+        distress_level = "none"
+
+    output = result.to_dict()
+    output["distress_level"] = distress_level
+    return output
+
+
+def get_audio_duration(audio_path: str) -> float:
+    """Get audio duration in seconds."""
+    try:
+        import librosa
+        duration = librosa.get_duration(path=audio_path)
+        return float(duration)
+    except (ImportError, Exception):
+        try:
+            import soundfile as sf
+            info = sf.info(audio_path)
+            return float(info.duration)
+        except (ImportError, Exception):
+            return 0.0