feat: etapa 5 do assistente — revisão de ênfases com timeline

Transforma a etapa "colar decisões" numa tela de lapidação: a sugestão da
IA chega carregada e o editor afina frase a frase o que é ênfase e o que
fica fora. Essa marcação é o norte da etapa 6 — só as frases com ênfase
recebem zoom e legenda dinâmica; as demais ficam com legenda comum.

O campo de colar o JSON sobe para a etapa 4, então a numeração das etapas
não muda e a etapa 6 segue intacta.

Backend (fcpxml/phrase_review.py):
- build_phrase_review funde o _voice_timeline.json com as actions da IA
- trim por frase que anda em fronteira de palavra; corte parcial da IA
  chega como trim em vez de ser arredondado fora
- phrase_review_to_actions volta a cuts/zooms + emphasis_spans
- merge_saved_decisions reaplica só as decisões salvas sobre uma revisão
  remontada da análise atual, para reprocessar a voz não ficar mascarado
- resolve_source acha a mídia: o voice timeline guarda só o nome do arquivo

App (SwiftUI):
- layout de sala de edição: preview em cima, inspector à direita, timeline
  atravessando embaixo com seis trilhas rotuladas
- preview enquadra no formato de entrega lido do .fcpxml (fonte horizontal,
  projeto vertical), com alternância para a mídia original
- reprodução pula os trechos removidos e para no fim do trecho
- zoom manual por trecho marcado, sem guardar escala: a forma vem das
  configurações de Análise de Voz no render
- emoção da fala exposta por frase

Correções encontradas no caminho:
- VideoPlayer (AVKit) aborta em runtime no app compilado por swiftc;
  trocado por AVPlayerLayer (ver Engine/docs/05_EXPERIENCIAS.md #22)
- teste que ainda afirmava o default zoom scale=1.3 removido do parser (#21)

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

code/fcpxml/voice_timeline.py

@@ -56,12 +56,20 @@ VALUE_SCALES = {
         "rate_delta": "0-1, how much the local speaking rate departs from the average",
         "pause_before": "seconds of silence immediately before the word",
         "emphasis": "0-1 combined index; high values are punch-in/highlight candidates",
+        "emotion": "heuristic label from delivery: neutral, excited, tense, calm, reflective",
+        "emotion_confidence": "0-1 confidence in the heuristic emotion label",
+        "arousal": "0-1 vocal activation from energy/rate/pitch movement",
+        "valence": "0-1 rough positive tone; lower values suggest tension/weight",
     },
     "segment": {
         "gap_before": "seconds of silence before this line",
         "take_boundary": "true when the gap is long enough that the take likely restarted here",
         "avg_energy": "0-1 mean loudness across the line",
         "peak_emphasis": "0-1 highest emphasis of any word in the line",
+        "emotion": "dominant delivery emotion across the line",
+        "emotion_confidence": "0-1 confidence in the dominant segment emotion",
+        "arousal": "0-1 mean vocal activation across the line",
+        "valence": "0-1 mean rough positive tone across the line",
     },
 }
 
@@ -92,11 +100,74 @@ def _round_word(word: dict) -> dict:
         "rate_delta": round(word.get("rate_delta", 0.0), 3),
         "pause_before": round(word.get("pause_before", 0.0), 3),
         "emphasis": round(word.get("emphasis", 0.0), 3),
+        "emotion": word.get("emotion", "neutral"),
+        "emotion_confidence": round(word.get("emotion_confidence", 0.0), 3),
+        "arousal": round(word.get("arousal", 0.0), 3),
+        "valence": round(word.get("valence", 0.5), 3),
         "energy_raw": word.get("energy"),
         "pitch_hz": word.get("pitch_hz"),
     }
 
 
+def _emotion_for_word(word: dict, enabled: bool, sensitivity: float) -> dict:
+    """Classify delivery emotion from normalized acoustic features.
+
+    This is deliberately a local heuristic rather than a claimed clinical
+    emotion model. It gives the editor a useful signal about delivery shape
+    while degrading predictably when acoustic extraction is unavailable.
+    """
+    if not enabled:
+        return {
+            "emotion": "neutral",
+            "emotion_confidence": 0.0,
+            "arousal": 0.0,
+            "valence": 0.5,
+        }
+
+    energy = float(word.get("energy_norm", 0.0))
+    pitch = float(word.get("pitch_delta", 0.0))
+    rate = float(word.get("rate_delta", 0.0))
+    pause = min(float(word.get("pause_before", 0.0)) / 2.0, 1.0)
+    emphasis = float(word.get("emphasis", 0.0))
+
+    arousal = max(0.0, min(1.0, energy * 0.45 + pitch * 0.25 + rate * 0.20 + emphasis * 0.10))
+    valence = max(0.0, min(1.0, 0.55 + energy * 0.15 - pause * 0.20 - rate * 0.10))
+
+    if arousal >= 0.68 and valence >= 0.50:
+        label = "excited"
+        confidence = arousal
+    elif arousal >= 0.58 and valence < 0.50:
+        label = "tense"
+        confidence = max(arousal, 1.0 - valence)
+    elif arousal <= 0.28 and pause >= 0.25:
+        label = "reflective"
+        confidence = max(1.0 - arousal, pause)
+    elif arousal <= 0.35:
+        label = "calm"
+        confidence = 1.0 - arousal
+    else:
+        label = "neutral"
+        confidence = 1.0 - abs(arousal - 0.5) * 2.0
+
+    confidence = max(0.0, min(1.0, confidence))
+    if confidence < sensitivity:
+        label = "neutral"
+    return {
+        "emotion": label,
+        "emotion_confidence": confidence,
+        "arousal": arousal,
+        "valence": valence,
+    }
+
+
+def annotate_emotions(words: Sequence[dict], enabled: bool, sensitivity: float) -> List[dict]:
+    """Attach heuristic emotion labels to enriched word rows."""
+    return [
+        {**w, **_emotion_for_word(w, enabled, sensitivity)}
+        for w in words
+    ]
+
+
 def enrich_words(
     words: Sequence[dict],
     pitch_track: Optional[Sequence] = None,
@@ -166,6 +237,13 @@ def _segment_rows(segments: Sequence[dict], words: Sequence[dict]) -> List[dict]
         in_seg = [w for w in words if start <= float(w.get("start", 0.0)) < end]
         energies = [w["energy_norm"] for w in in_seg]
         emphases = [w["emphasis"] for w in in_seg]
+        arousals = [w.get("arousal", 0.0) for w in in_seg]
+        valences = [w.get("valence", 0.5) for w in in_seg]
+        emotions = [w.get("emotion", "neutral") for w in in_seg]
+        dominant = max(set(emotions), key=emotions.count) if emotions else "neutral"
+        emotion_confidences = [
+            w.get("emotion_confidence", 0.0) for w in in_seg if w.get("emotion") == dominant
+        ]
         gap = max(0.0, start - previous_end)
         rows.append(
             {
@@ -181,6 +259,13 @@ def _segment_rows(segments: Sequence[dict], words: Sequence[dict]) -> List[dict]
                 "take_boundary": gap >= TAKE_BOUNDARY_GAP,
                 "avg_energy": round(sum(energies) / len(energies), 3) if energies else 0.0,
                 "peak_emphasis": round(max(emphases), 3) if emphases else 0.0,
+                "emotion": dominant,
+                "emotion_confidence": (
+                    round(sum(emotion_confidences) / len(emotion_confidences), 3)
+                    if emotion_confidences else 0.0
+                ),
+                "arousal": round(sum(arousals) / len(arousals), 3) if arousals else 0.0,
+                "valence": round(sum(valences) / len(valences), 3) if valences else 0.5,
                 "words": [_round_word(w) for w in in_seg],
             }
         )
@@ -425,6 +510,8 @@ def build_voice_timeline(
     weights: EmphasisWeights = EmphasisWeights(),
     peak_percentile: float = 0.02,
     emphasis_floor: float = 0.25,
+    emotion_enabled: bool = False,
+    emotion_sensitivity: float = 0.5,
     progress_cb: Optional[Callable[[float, str], None]] = None,
 ) -> dict:
     """Build the consolidated voice timeline for one media file.
@@ -445,6 +532,7 @@ def build_voice_timeline(
 
     report(0.5, "Calculando ênfase...")
     words = enrich_words(transcript.get("words", []), pitch_track, energy_track, weights)
+    words = annotate_emotions(words, emotion_enabled, emotion_sensitivity)
 
     report(0.7, "Identificando participantes...")
     tracks = diarize(media_path, hf_token, num_speakers) if hf_token else None
@@ -465,6 +553,7 @@ def build_voice_timeline(
             "transcript": bool(transcript.get("words")),
             "acoustics": pitch_track is not None or energy_track is not None,
             "speakers": tracks is not None,
+            "emotion": bool(emotion_enabled),
         },
         "scales": VALUE_SCALES,
         "summary": _summary(