#!/usr/bin/env bash
# One-shot emotional voice synthesis using the Phase 9 recipe:
#   - Selective CFG schedule `linear:3.0:1.0:25` (robust default)
#   - Activation steering @ scale 0.3 on mid layers [8, 10, 12]
#   - Reference-clip context conditioning
#
# This is the codified version of the empirical findings logged in
# `docs/perf_history.md` Phase 9. Recipe was tuned for cross-character
# emotional speech (e.g. take a neutral lecture voice, render it angry).
#
# Steering vectors must be pre-extracted via
# `examples/steering_extract` from a labeled emotion corpus (RAVDESS,
# CREMA-D, ESD, etc). Use `scripts/build_ravdess_manifest.sh` to
# convert RAVDESS into a manifest first.
#
# Usage:
#   scripts/emotional_speech.sh \
#       --text "What you want said." \
#       --context-wav <reference voice>.wav \
#       --context-text "Transcript of the reference clip." \
#       --emotion angry \
#       --steering-dir /tmp/ravdess_steering \
#       --out /tmp/out.wav \
#       [--scale 0.3]                 # steering scale, lower = more text fidelity
#       [--cfg-schedule linear:3.0:1.0:25]
#       [--layers 8,10,12]
#
# Recipe defaults are deliberate; override only when you have a reason.
# Sprint 2 measurements:
#   - speaker_cosine vs angry-actor reference rises 0.55 → 0.846 with
#     scale=0.3 stacked on Selective CFG
#   - scale ≥ 0.5 corrupts the output (Moonshine WER 1.0 on Unicode noise)
#   - layers including 0–7 also corrupt (input embedding fidelity loss)
#
# Per-emotion scale sweet spots (RAVDESS-extracted, mid-layer recipe,
# linear:3.0:1.0:25 CFG, single-prompt single-seed measurement — treat
# as starting points, not guarantees):
#   - happy:    0.30 → fluent speech
#   - angry:    0.20 → fluent speech (0.30 produces music-token outputs)
#   - fearful:  0.20 → fluent speech (0.30 produces music-token outputs)
#   - sad:      no robust scale found — model resists "sad" steering on
#               most prompts; one-word outputs at all tested scales
# We leave --scale defaulted to 0.3 because the wrapper can't know which
# emotion is being requested at default-construction time. Override
# with --scale 0.2 when using angry or fearful.

set -euo pipefail

TEXT=""
CTX_WAV=""
CTX_TEXT=""
EMOTION=""
STEERING_DIR=""
OUT=""
TARGET="decoder"  # Default to decoder route (Phase 9 winner: preserves text fidelity).
SCALE=""          # if unset, picked per-(target,emotion) below
CFG_SCHEDULE="linear:3.0:1.0:25"
LAYERS=""         # if unset, picked per-target below
SPEAKER=0
SEED=42

while [[ $# -gt 0 ]]; do
    case "$1" in
        --text) TEXT="$2"; shift 2 ;;
        --context-wav) CTX_WAV="$2"; shift 2 ;;
        --context-text) CTX_TEXT="$2"; shift 2 ;;
        --emotion) EMOTION="$2"; shift 2 ;;
        --steering-dir) STEERING_DIR="$2"; shift 2 ;;
        --out) OUT="$2"; shift 2 ;;
        --target) TARGET="$2"; shift 2 ;;
        --scale) SCALE="$2"; shift 2 ;;
        --cfg-schedule) CFG_SCHEDULE="$2"; shift 2 ;;
        --layers) LAYERS="$2"; shift 2 ;;
        --speaker) SPEAKER="$2"; shift 2 ;;
        --seed) SEED="$2"; shift 2 ;;
        -h|--help) sed -n '2,32p' "$0"; exit 0 ;;
        *) echo "unknown arg: $1" >&2; exit 1 ;;
    esac
done

for v in TEXT CTX_WAV CTX_TEXT EMOTION STEERING_DIR OUT; do
    if [[ -z "${!v}" ]]; then
        echo "error: --${v,,} (or one of the required flags) is unset" >&2
        echo "usage: $0 --text T --context-wav W --context-text C --emotion E --steering-dir D --out O [--target backbone|decoder]" >&2
        exit 1
    fi
done

if [[ "$TARGET" != "backbone" && "$TARGET" != "decoder" ]]; then
    echo "error: --target must be 'backbone' or 'decoder' (got '$TARGET')" >&2
    exit 1
fi

STEERING_FILE="$STEERING_DIR/${EMOTION}.safetensors"
if [[ ! -f "$STEERING_FILE" ]]; then
    echo "error: no steering file for emotion '$EMOTION' at $STEERING_FILE" >&2
    echo "available emotions in $STEERING_DIR:" >&2
    ls "$STEERING_DIR" 2>/dev/null | sed 's/\.safetensors$//' | sed 's/^/  /' >&2 || true
    exit 1
fi

# Per-(target, emotion) scale defaults (Sprint 2 + decoder findings).
if [[ -z "$SCALE" ]]; then
    if [[ "$TARGET" == "decoder" ]]; then
        # Decoder vectors are ~10× smaller magnitude, so scales are 10× higher.
        case "$EMOTION" in
            *) SCALE=1.0 ;;  # only happy benched; conservative default for others
        esac
    else
        case "$EMOTION" in
            angry|fearful|sad) SCALE=0.2 ;;
            happy)             SCALE=0.3 ;;
            *)                 SCALE=0.3 ;;
        esac
    fi
fi

# Per-target default layers.
if [[ -z "$LAYERS" ]]; then
    if [[ "$TARGET" == "decoder" ]]; then
        LAYERS="2,3"     # decoder last-two — empirical no-repetition recipe
    else
        LAYERS="8,10,12" # backbone mid-deep — empirical fluency-preserving recipe
    fi
fi

SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
WORKSPACE_DIR="$(cd "$SCRIPT_DIR/../../../.." && pwd)"
GEN_BIN="$WORKSPACE_DIR/target/release/examples/generate"
if [[ ! -x "$GEN_BIN" ]]; then
    echo "error: missing $GEN_BIN" >&2
    echo "build with: cargo build -p rtx-csm --release --example generate" >&2
    exit 1
fi

echo "→ recipe: target=$TARGET emotion=$EMOTION scale=$SCALE cfg=$CFG_SCHEDULE layers=$LAYERS"
echo "  context: $(basename "$CTX_WAV")"

if [[ "$TARGET" == "decoder" ]]; then
    "$GEN_BIN" \
        --text "$TEXT" --speaker "$SPEAKER" --seed "$SEED" \
        --context-wav "$CTX_WAV" --context-text "$CTX_TEXT" --context-speaker 1 \
        --enable-cfg --cfg-schedule "$CFG_SCHEDULE" \
        --decoder-steering-vec "$STEERING_FILE" \
        --decoder-steering-scale "$SCALE" \
        --decoder-steering-layers "$LAYERS" \
        --out "$OUT"
else
    "$GEN_BIN" \
        --text "$TEXT" --speaker "$SPEAKER" --seed "$SEED" \
        --context-wav "$CTX_WAV" --context-text "$CTX_TEXT" --context-speaker 1 \
        --enable-cfg --cfg-schedule "$CFG_SCHEDULE" \
        --steering-vec "$STEERING_FILE" \
        --steering-scale "$SCALE" \
        --steering-layers "$LAYERS" \
        --out "$OUT"
fi

echo "✓ wrote $OUT"