app.py

"""
Sahel-Agri Voice AI — HuggingFace Spaces (ZeroGPU)
Two-way voice assistant: Bambara / Fula / French / English → voice response

Environment variables (set in Space Settings → Secrets):
  HF_TOKEN               — HF write-access token
  FEEDBACK_REPO_ID       — e.g. ous-sow/sahel-agri-feedback  (dataset, private)
  ADAPTER_REPO_ID        — e.g. ous-sow/sahel-agri-adapters   (model, private)
  WHISPER_MODEL_ID       — default: openai/whisper-small
  KAGGLE_USERNAME        — Kaggle username (for auto-trigger training)
  KAGGLE_KEY             — Kaggle API key  (for auto-trigger training)
  KAGGLE_KERNEL_SLUG     — default: ous-sow/sahel-voice-master-trainer
  AUTO_TRAIN_THRESHOLD   — corrections count that triggers auto-training (default: 50)
"""

from __future__ import annotations

import io
import json
import os
import sys
import tempfile
import threading
from datetime import datetime, timezone
from pathlib import Path

import gradio as gr
import numpy as np

ROOT = Path(__file__).parent
sys.path.insert(0, str(ROOT))

# ── env ───────────────────────────────────────────────────────────────────────
HF_TOKEN         = os.environ.get("HF_TOKEN")
FEEDBACK_REPO_ID = os.environ.get("FEEDBACK_REPO_ID", "ous-sow/sahel-agri-feedback")
ADAPTER_REPO_ID  = os.environ.get("ADAPTER_REPO_ID",  "ous-sow/sahel-agri-adapters")
# whisper-small: ~10s on cpu-basic, good multilingual quality.
# Override via WHISPER_MODEL_ID env var if you upgrade to a GPU Space later.
WHISPER_MODEL_ID     = os.environ.get("WHISPER_MODEL_ID",    "openai/whisper-small")
KAGGLE_USERNAME      = os.environ.get("KAGGLE_USERNAME",      "")
KAGGLE_KEY           = os.environ.get("KAGGLE_KEY",           "")
KAGGLE_KERNEL_SLUG   = os.environ.get("KAGGLE_KERNEL_SLUG",   "ous-sow/sahel-voice-master-trainer")
AUTO_TRAIN_THRESHOLD = int(os.environ.get("AUTO_TRAIN_THRESHOLD", "50"))

# On local CPU (no HF_TOKEN / no spaces package) fall back gracefully
_ON_SPACES = os.environ.get("SPACE_ID") is not None

SUPPORTED_LANGUAGES = {
    "Bambara (bam)":    "bam",
    "Fula (ful)":       "ful",
    "French / Français": "fr",
    "English":          "en",
}

# ── ZeroGPU decorator (no-op locally) ────────────────────────────────────────
try:
    import spaces  # type: ignore
    _gpu = spaces.GPU(duration=55)
except ImportError:
    def _gpu(fn):           # local fallback: plain function
        return fn

# ── Module-level model state (CPU-resident between requests) ─────────────────
_whisper_model      = None   # WhisperForConditionalGeneration (base)
_whisper_processor  = None
_fine_tuned_models  = {}     # lang_code -> WhisperForConditionalGeneration (full checkpoint)
_model_lock         = threading.Lock()
_model_status       = "not loaded"

from src.tts.mms_tts                  import MMSTTSEngine
from src.iot.intent_parser             import IntentParser
from src.iot.sensor_bridge             import SensorBridge
from src.iot.voice_responder           import VoiceResponder
from src.conversation.phrase_matcher   import PhraseMatcher

_tts             = MMSTTSEngine()
_intent_parser   = IntentParser()
_sensor_bridge   = SensorBridge()
_phrase_matcher  = PhraseMatcher()

# HF API — only instantiate when token present
_hf_api = None
if HF_TOKEN:
    from huggingface_hub import HfApi
    _hf_api = HfApi(token=HF_TOKEN)


# ── Model loading ─────────────────────────────────────────────────────────────

def _do_load_whisper():
    global _whisper_model, _whisper_processor, _model_status
    import torch

    # Import concrete Whisper classes directly — bypasses transformers __init__.py
    # Auto-class exports differ between transformers 4.x and 5.x; direct paths are stable.
    try:
        from transformers.models.whisper import WhisperProcessor, WhisperForConditionalGeneration
    except ImportError:
        from transformers.models.whisper.processing_whisper import WhisperProcessor
        from transformers.models.whisper.modeling_whisper import WhisperForConditionalGeneration

    _model_status = "loading…"
    try:
        _whisper_processor = WhisperProcessor.from_pretrained(
            WHISPER_MODEL_ID, token=HF_TOKEN
        )
        try:
            _whisper_model = WhisperForConditionalGeneration.from_pretrained(
                WHISPER_MODEL_ID,
                torch_dtype=torch.float32,
                token=HF_TOKEN,
            )
        except TypeError:
            _whisper_model = WhisperForConditionalGeneration.from_pretrained(
                WHISPER_MODEL_ID,
                token=HF_TOKEN,
            )
        _whisper_model.eval()
        _model_status = f"ready ({WHISPER_MODEL_ID})"
    except Exception as e:
        _model_status = f"error: {e}"


def _ensure_whisper_loaded():
    """Load Whisper to CPU in a background thread on first call. Non-blocking."""
    global _model_status
    with _model_lock:
        # Retry if previous attempt errored (e.g. import failed on first try)
        if _whisper_model is None and "loading" not in _model_status:
            _model_status = "loading…"
            t = threading.Thread(target=_do_load_whisper, daemon=True)
            t.start()
    return _model_status


def get_model_status() -> str:
    s = _ensure_whisper_loaded()
    if "ready" in s:
        return f"🟢 {s}"
    if "loading" in s:
        return f"🟡 {s}"
    if "error" in s:
        return f"🔴 {s}"
    return f"⚪ {s}"


# ── Core GPU pipeline ─────────────────────────────────────────────────────────

@_gpu
def _run_pipeline(audio_path: str, language_code: str):
    """
    Full STT → Intent → Sensor → TTS pipeline.
    Decorated with @spaces.GPU(duration=55) on HF Spaces; plain function locally.
    Returns: (transcript, response_text, (sample_rate, wav_np))
    """
    import asyncio
    import torch

    device = "cuda" if torch.cuda.is_available() else "cpu"

    # ── 1. Whisper STT ────────────────────────────────────────────────────────
    if _whisper_model is None:
        return "⏳ Model still loading…", "", None

    import librosa

    audio_np, _ = librosa.load(audio_path, sr=16000, mono=True)

    # Use fine-tuned checkpoint for this language if one has been loaded;
    # otherwise fall back to base Whisper.
    active_model = _fine_tuned_models.get(language_code, _whisper_model)

    active_model.to(device)
    with _model_lock:
        inputs = _whisper_processor.feature_extractor(
            audio_np, sampling_rate=16000, return_tensors="pt"
        )
        input_features = inputs.input_features.to(device)

        # Bambara and Fula have no Whisper language token — pass None so the model
        # auto-detects or falls back to multilingual decoding.
        if language_code in ("bam", "ful"):
            forced_ids = None
        else:
            forced_ids = _whisper_processor.get_decoder_prompt_ids(
                language=language_code, task="transcribe"
            )

        with torch.no_grad():
            predicted_ids = active_model.generate(
                input_features,
                forced_decoder_ids=forced_ids if forced_ids else None,
                max_new_tokens=256,
            )

    transcript = _whisper_processor.batch_decode(
        predicted_ids, skip_special_tokens=True
    )[0].strip()

    # Free GPU VRAM before TTS
    active_model.to("cpu")
    if device == "cuda":
        torch.cuda.empty_cache()

    # ── 2. Phrase library (general conversation — no sensors needed) ─────────
    phrase_match = _phrase_matcher.match(transcript, language_code)
    if phrase_match:
        response_text      = phrase_match["response"]
        english_translation = phrase_match["english"]
    else:
        # ── 3. Intent + sensor data (agricultural queries) ────────────────────
        intent = _intent_parser.parse(transcript, language=language_code)

        try:
            loop = asyncio.new_event_loop()
            sensor_data = loop.run_until_complete(_sensor_bridge.fetch(intent))
            loop.close()
        except Exception:
            from src.iot.sensor_bridge import SensorData
            sensor_data = SensorData(sensor_type="soil", values={
                "moisture_pct": 45.0, "ph": 6.5, "temperature_c": 28.0
            })

        responder = VoiceResponder(language=language_code)
        response_text, english_translation = responder.generate_response(intent, sensor_data)

        # Low-confidence fallback: say "I didn't understand" in the native language
        if intent.action == "unknown" and intent.confidence < 0.15:
            from src.iot.voice_responder import BAMBARA_TEMPLATES, FULA_TEMPLATES
            if language_code == "bam":
                response_text, english_translation = BAMBARA_TEMPLATES["not_understood"]
            elif language_code == "ful":
                response_text, english_translation = FULA_TEMPLATES["not_understood"]

    # ── 3. MMS-TTS (GPU) ──────────────────────────────────────────────────────
    wav_np, sample_rate = _tts.synthesize(response_text, language_code, device=device)

    return transcript, english_translation, response_text, (sample_rate, wav_np)


# ── HF Hub feedback persistence ───────────────────────────────────────────────

def _save_feedback_to_hub(
    audio_path: str | None,
    transcript: str,
    corrected_text: str,
    english_translation: str,
    corrected_english: str,
    response_text: str,
    corrected_response: str,
    rating: int,
    notes: str,
    language_label: str,
) -> str:
    language_code = SUPPORTED_LANGUAGES.get(language_label, "bam")

    if not corrected_text.strip():
        return "⚠️ Corrected transcription is empty — please fill in what was actually said."

    timestamp = datetime.now(timezone.utc).strftime("%Y%m%d_%H%M%S_%f")

    record = {
        "id": timestamp,
        "timestamp": datetime.now(timezone.utc).isoformat(),
        "language": language_code,
        "audio_file": f"audio/{language_code}_{timestamp}.wav",
        "whisper_output": transcript,
        "corrected_text": corrected_text.strip(),
        "english_translation": english_translation.strip(),
        "corrected_english": corrected_english.strip() or english_translation.strip(),
        "response_text": response_text,
        "corrected_response": corrected_response.strip() or response_text.strip(),
        "rating": rating,
        "notes": notes.strip(),
        "is_correction": transcript.strip() != corrected_text.strip(),
        "model": WHISPER_MODEL_ID,
    }

    if _hf_api is None:
        # Local: save to disk instead
        fb_dir = ROOT / "feedback"
        fb_dir.mkdir(exist_ok=True)
        (fb_dir / "audio").mkdir(exist_ok=True)
        corrections_path = fb_dir / "corrections.jsonl"
        if audio_path:
            import shutil
            shutil.copy2(audio_path, fb_dir / "audio" / f"{language_code}_{timestamp}.wav")
        with open(corrections_path, "a", encoding="utf-8") as f:
            f.write(json.dumps(record, ensure_ascii=False) + "\n")
        total = sum(1 for _ in open(corrections_path, encoding="utf-8"))
        return f"✅ Saved locally (#{total}) — HF_TOKEN not set, Hub upload skipped."

    try:
        # Upload audio
        if audio_path:
            _hf_api.upload_file(
                path_or_fileobj=audio_path,
                path_in_repo=f"audio/{language_code}_{timestamp}.wav",
                repo_id=FEEDBACK_REPO_ID,
                repo_type="dataset",
            )

        # Download → append → re-upload corrections.jsonl (with retry on conflict)
        from huggingface_hub import hf_hub_download
        for attempt in range(2):
            try:
                local_jsonl = hf_hub_download(
                    repo_id=FEEDBACK_REPO_ID,
                    filename="corrections.jsonl",
                    repo_type="dataset",
                    token=HF_TOKEN,
                )
                with open(local_jsonl, encoding="utf-8") as f:
                    existing = f.read()
            except Exception:
                existing = ""

            updated = existing + json.dumps(record, ensure_ascii=False) + "\n"
            buf = io.BytesIO(updated.encode("utf-8"))

            try:
                _hf_api.upload_file(
                    path_or_fileobj=buf,
                    path_in_repo="corrections.jsonl",
                    repo_id=FEEDBACK_REPO_ID,
                    repo_type="dataset",
                )
                break
            except Exception as e:
                if attempt == 1:
                    return f"⚠️ Audio uploaded but corrections.jsonl update failed: {e}"

        total = updated.count("\n")
        _maybe_auto_trigger()
        return f"✅ Saved to Hub (#{total}) — {FEEDBACK_REPO_ID}"

    except Exception as e:
        return f"❌ Hub upload error: {e}"


# ── Adapter reload ────────────────────────────────────────────────────────────

def _reload_adapters_from_hub() -> str:
    """Download full fine-tuned checkpoints from Hub and hot-swap them into memory."""
    global _fine_tuned_models
    if _hf_api is None:
        return "⚠️ HF_TOKEN not set — cannot download checkpoints."
    if _whisper_model is None:
        return "⏳ Base model not loaded yet — wait for model to finish loading and try again."
    try:
        import torch
        from huggingface_hub import snapshot_download
        try:
            from transformers.models.whisper.modeling_whisper import WhisperForConditionalGeneration
        except ImportError:
            from transformers import WhisperForConditionalGeneration

        local_dir = snapshot_download(
            repo_id=ADAPTER_REPO_ID, repo_type="model", token=HF_TOKEN
        )
        results = []
        for lang, subdir in (("bam", "adapters/bambara"), ("ful", "adapters/fula")):
            ckpt_path = Path(local_dir) / subdir
            if not ckpt_path.exists():
                results.append(f"⚠️ {lang}: `{subdir}` not found — run training notebook first")
                continue
            if not (ckpt_path / "config.json").exists():
                results.append(f"⚠️ {lang}: `{subdir}/config.json` missing — incomplete checkpoint")
                continue
            try:
                m = WhisperForConditionalGeneration.from_pretrained(
                    str(ckpt_path), torch_dtype=torch.float32
                )
                m.eval()
                _fine_tuned_models[lang] = m
                results.append(f"✅ {lang}: fine-tuned checkpoint loaded from `{subdir}`")
            except Exception as e:
                results.append(f"❌ {lang}: load failed — {e}")

        summary = "\n".join(results)
        active = ", ".join(_fine_tuned_models) if _fine_tuned_models else "none"
        return f"{summary}\n\n**Active fine-tuned models:** {active}\n**Repo:** `{ADAPTER_REPO_ID}`"
    except Exception as e:
        return f"❌ Checkpoint reload failed: {e}"


def _get_adapter_status() -> str:
    lines = []

    if _fine_tuned_models:
        lines.append(f"**Fine-tuned models loaded:** {', '.join(sorted(_fine_tuned_models))}")
    else:
        lines.append("**Fine-tuned models:** none — using base Whisper for all languages")

    if _hf_api is None:
        lines.append("_HF_TOKEN not set — Hub check skipped._")
        return "\n".join(lines)

    try:
        from huggingface_hub import list_repo_files
        files = list(list_repo_files(ADAPTER_REPO_ID, repo_type="model", token=HF_TOKEN))
        bam_ok = any("bambara" in f and "config.json" in f for f in files)
        ful_ok = any("fula" in f and "config.json" in f for f in files)
        lines += [
            f"\n**Hub repo:** `{ADAPTER_REPO_ID}`",
            f"- Bambara (bam): {'✅ trained checkpoint present' if bam_ok else '⚠️ not yet trained — run Kaggle notebook'}",
            f"- Fula (ful): {'✅ trained checkpoint present' if ful_ok else '⚠️ not yet trained — run Kaggle notebook'}",
        ]
        if bam_ok or ful_ok:
            lines.append("\n_Click **Reload Models** to activate them._")
    except Exception as e:
        lines.append(f"_Could not read Hub repo: {e}_")

    return "\n".join(lines)


# ── Knowledge Base handlers ───────────────────────────────────────────────────

def _import_phrase_pairs(lang_label: str, pairs_text: str) -> str:
    """Import pasted phrase pairs into the phrase library and append to vocabulary.jsonl."""
    if not pairs_text.strip():
        return "⚠️ Nothing entered. Use the format:  native phrase | english translation"
    lang = SUPPORTED_LANGUAGES.get(lang_label, "bam")
    count = _phrase_matcher.import_pairs(lang, pairs_text)
    if count == 0:
        return "⚠️ No valid phrases found. Each line must contain a | separator.\nExample:  I ni ce | Hello, good day"
    _upload_phrase_additions_to_hub(lang)
    # Also append to vocabulary.jsonl so the Kaggle training notebook picks them up
    _append_phrases_to_vocabulary_jsonl(lang, pairs_text)
    total = _phrase_matcher.phrase_count(lang)
    return f"✅ Added {count} phrase(s) for {lang_label}. Library now has {total} phrases. Available immediately."


def _append_phrases_to_vocabulary_jsonl(lang: str, pairs_text: str) -> None:
    """Append phrase pairs to vocabulary.jsonl in the feedback repo (training input)."""
    if _hf_api is None or not FEEDBACK_REPO_ID:
        return
    entries = []
    for line in pairs_text.splitlines():
        if "|" not in line:
            continue
        parts = line.split("|", 1)
        word = parts[0].strip()
        translation = parts[1].strip() if len(parts) > 1 else ""
        if word:
            entries.append({"word": word, "translation": translation, "language": lang})
    if not entries:
        return
    try:
        from huggingface_hub import hf_hub_download
        for attempt in range(2):
            try:
                local = hf_hub_download(
                    repo_id=FEEDBACK_REPO_ID, filename="vocabulary.jsonl",
                    repo_type="dataset", token=HF_TOKEN,
                )
                with open(local, encoding="utf-8") as f:
                    existing = f.read()
            except Exception:
                existing = ""
            new_lines = "".join(json.dumps(e, ensure_ascii=False) + "\n" for e in entries)
            updated = existing + new_lines
            try:
                _hf_api.upload_file(
                    path_or_fileobj=io.BytesIO(updated.encode("utf-8")),
                    path_in_repo="vocabulary.jsonl",
                    repo_id=FEEDBACK_REPO_ID,
                    repo_type="dataset",
                )
                break
            except Exception:
                if attempt == 1:
                    pass  # Silent — phrase library still updated locally
    except Exception:
        pass  # Non-critical — phrase library already saved via _upload_phrase_additions_to_hub


def _upload_phrase_additions_to_hub(lang: str) -> None:
    """Persist user phrase additions to HF Hub so they survive Space restarts."""
    if _hf_api is None or not FEEDBACK_REPO_ID:
        return
    try:
        import io
        data = _phrase_matcher.get_additions_json(lang)
        buf = io.BytesIO(data.encode("utf-8"))
        _hf_api.upload_file(
            path_or_fileobj=buf,
            path_in_repo=f"phrase_additions/{lang}.json",
            repo_id=FEEDBACK_REPO_ID,
            repo_type="dataset",
        )
    except Exception as exc:
        import logging
        logging.getLogger(__name__).warning("Could not upload phrase additions: %s", exc)


def _load_phrase_additions_from_hub() -> None:
    """Download and merge user phrase additions from HF Hub at startup."""
    if _hf_api is None or not FEEDBACK_REPO_ID:
        return
    for lang in ("bam", "ful"):
        try:
            from huggingface_hub import hf_hub_download
            local = hf_hub_download(
                repo_id=FEEDBACK_REPO_ID,
                filename=f"phrase_additions/{lang}.json",
                repo_type="dataset",
                token=HF_TOKEN,
            )
            with open(local, encoding="utf-8") as f:
                data = f.read()
            _phrase_matcher.reload_from_hub_data(lang, data)
        except Exception:
            pass  # No additions saved yet — fine

# Load user phrase additions in background at module import time
threading.Thread(target=_load_phrase_additions_from_hub, daemon=True).start()


def _save_audio_for_training(lang_label: str, audio_path: str | None, transcript: str, source_note: str) -> str:
    """Save uploaded audio + transcription to corrections.jsonl so the Kaggle notebook picks it up."""
    transcript = transcript.strip()
    if audio_path is None:
        return "⚠️ Please upload an audio file first."
    if not transcript:
        return "⚠️ Please type the transcription — what is said in this audio."

    lang = SUPPORTED_LANGUAGES.get(lang_label, "bam")
    timestamp = datetime.now(timezone.utc).strftime("%Y%m%d_%H%M%S_%f")
    # Store under audio/ — same path structure that corrections.jsonl expects
    audio_repo_path = f"audio/{lang}_{timestamp}.wav"

    record = {
        "id": timestamp,
        "timestamp": datetime.now(timezone.utc).isoformat(),
        "language": lang,
        "audio_file": audio_repo_path,
        "transcription": transcript,          # notebook reads this field
        "corrected_text": transcript,          # also populate corrected_text for compatibility
        "source": source_note.strip() or "uploaded",
        "is_correction": False,
        "model": WHISPER_MODEL_ID,
    }

    if _hf_api is None or not FEEDBACK_REPO_ID:
        return "⚠️ HF_TOKEN not set — cannot upload to Hub."

    try:
        # Upload audio to audio/ (same bucket corrections use)
        _hf_api.upload_file(
            path_or_fileobj=audio_path,
            path_in_repo=audio_repo_path,
            repo_id=FEEDBACK_REPO_ID,
            repo_type="dataset",
        )

        # Append to corrections.jsonl (same file the notebook reads)
        from huggingface_hub import hf_hub_download
        for attempt in range(2):
            try:
                local_jsonl = hf_hub_download(
                    repo_id=FEEDBACK_REPO_ID, filename="corrections.jsonl",
                    repo_type="dataset", token=HF_TOKEN,
                )
                with open(local_jsonl, encoding="utf-8") as f:
                    existing = f.read()
            except Exception:
                existing = ""
            updated = existing + json.dumps(record, ensure_ascii=False) + "\n"
            try:
                _hf_api.upload_file(
                    path_or_fileobj=io.BytesIO(updated.encode("utf-8")),
                    path_in_repo="corrections.jsonl",
                    repo_id=FEEDBACK_REPO_ID,
                    repo_type="dataset",
                )
                break
            except Exception as e:
                if attempt == 1:
                    return f"⚠️ Audio uploaded but corrections.jsonl update failed: {e}"

        total = updated.count("\n")
        return (
            f"✅ Saved to training dataset (#{total} total corrections)!\n"
            f"Audio: {audio_repo_path}\n"
            f"Transcription: {transcript[:80]}{'…' if len(transcript) > 80 else ''}\n"
            f"Run the Kaggle notebook to include this in the next model update."
        )
    except Exception as exc:
        return f"❌ Upload failed: {exc}"


# ── Auto-training trigger ─────────────────────────────────────────────────────

def _count_corrections() -> int:
    """Return number of entries in corrections.jsonl on the Hub."""
    if _hf_api is None:
        return 0
    try:
        from huggingface_hub import hf_hub_download
        local = hf_hub_download(
            repo_id=FEEDBACK_REPO_ID, filename="corrections.jsonl",
            repo_type="dataset", token=HF_TOKEN,
        )
        with open(local, encoding="utf-8") as f:
            return sum(1 for l in f if l.strip())
    except Exception:
        return 0


def _trigger_kaggle_training(lang: str = "bam") -> str:
    """Fire the Kaggle kernel via REST API if credentials are configured."""
    if not KAGGLE_USERNAME or not KAGGLE_KEY:
        return "⚠️ KAGGLE_USERNAME / KAGGLE_KEY not set in Space secrets — auto-trigger disabled."
    try:
        import urllib.request, urllib.parse, base64
        token = base64.b64encode(f"{KAGGLE_USERNAME}:{KAGGLE_KEY}".encode()).decode()
        url   = f"https://www.kaggle.com/api/v1/kernels/{KAGGLE_KERNEL_SLUG}/run"
        body  = json.dumps({"enableGpu": True}).encode()
        req   = urllib.request.Request(
            url, data=body, method="POST",
            headers={
                "Authorization": f"Basic {token}",
                "Content-Type":  "application/json",
            },
        )
        with urllib.request.urlopen(req, timeout=15) as r:
            resp = json.loads(r.read())
        return f"✅ Kaggle training triggered! Run ID: {resp.get('currentRunningVersion', 'started')}"
    except Exception as e:
        return f"❌ Kaggle trigger failed: {e}"


def _maybe_auto_trigger() -> None:
    """Called after each correction save. Triggers Kaggle if threshold met."""
    if not KAGGLE_USERNAME or not KAGGLE_KEY:
        return
    count = _count_corrections()
    if count > 0 and count % AUTO_TRAIN_THRESHOLD == 0:
        threading.Thread(target=_trigger_kaggle_training, daemon=True).start()


# ── Bulk upload handler ────────────────────────────────────────────────────────

def _bulk_upload(lang_label: str, zip_file, csv_text: str) -> str:
    """
    Accept a ZIP of audio files + a CSV (filename,transcription) and batch-insert
    all samples into corrections.jsonl.  Audio stored under audio/ in the Hub repo.
    """
    import zipfile, csv

    if _hf_api is None:
        return "⚠️ HF_TOKEN not set — cannot upload."
    if zip_file is None and not csv_text.strip():
        return "⚠️ Upload a ZIP and/or paste a CSV."

    lang   = SUPPORTED_LANGUAGES.get(lang_label, "bam")
    rows   = []   # (audio_bytes_or_None, filename, transcription)

    # Parse CSV
    transcript_map: dict[str, str] = {}
    if csv_text.strip():
        for row in csv.reader(csv_text.strip().splitlines()):
            if len(row) >= 2:
                transcript_map[row[0].strip()] = row[1].strip()

    # Extract ZIP
    if zip_file is not None:
        try:
            with zipfile.ZipFile(zip_file, "r") as zf:
                for name in zf.namelist():
                    if not name.lower().endswith((".wav", ".mp3", ".ogg", ".flac", ".m4a")):
                        continue
                    text = transcript_map.get(name) or transcript_map.get(Path(name).name) or ""
                    if not text:
                        continue
                    rows.append((zf.read(name), Path(name).name, text))
        except Exception as e:
            return f"❌ ZIP read error: {e}"
    elif transcript_map:
        # CSV only — audio-less vocab entries
        for fname, text in transcript_map.items():
            rows.append((None, fname, text))

    if not rows:
        return "⚠️ No matching (audio, transcription) pairs found. Check filenames match CSV."

    # Upload batch
    records = []
    errors  = 0
    for audio_bytes, fname, text in rows:
        ts          = datetime.now(timezone.utc).strftime("%Y%m%d_%H%M%S_%f")
        audio_path  = f"audio/{lang}_{ts}.wav"
        try:
            if audio_bytes:
                _hf_api.upload_file(
                    path_or_fileobj=io.BytesIO(audio_bytes),
                    path_in_repo=audio_path,
                    repo_id=FEEDBACK_REPO_ID,
                    repo_type="dataset",
                )
            records.append({
                "id": ts, "timestamp": datetime.now(timezone.utc).isoformat(),
                "language": lang,
                "audio_file": audio_path if audio_bytes else "",
                "transcription": text, "corrected_text": text,
                "source": f"bulk_upload:{fname}", "is_correction": False,
                "model": WHISPER_MODEL_ID,
            })
        except Exception:
            errors += 1

    # Append all to corrections.jsonl
    from huggingface_hub import hf_hub_download
    for attempt in range(2):
        try:
            local = hf_hub_download(
                repo_id=FEEDBACK_REPO_ID, filename="corrections.jsonl",
                repo_type="dataset", token=HF_TOKEN,
            )
            with open(local, encoding="utf-8") as f:
                existing = f.read()
        except Exception:
            existing = ""
        new_lines = "".join(json.dumps(r, ensure_ascii=False) + "\n" for r in records)
        updated   = existing + new_lines
        try:
            _hf_api.upload_file(
                path_or_fileobj=io.BytesIO(updated.encode("utf-8")),
                path_in_repo="corrections.jsonl",
                repo_id=FEEDBACK_REPO_ID,
                repo_type="dataset",
            )
            break
        except Exception as e:
            if attempt == 1:
                return f"⚠️ Audio uploaded but corrections.jsonl failed: {e}"

    total = updated.count("\n")
    _maybe_auto_trigger()
    return (
        f"✅ Bulk upload complete!\n"
        f"  Uploaded : {len(records)} samples ({errors} errors)\n"
        f"  Dataset  : {total} total corrections\n"
        f"  Auto-train threshold: {AUTO_TRAIN_THRESHOLD} entries"
    )


# ── Internet self-teaching handlers ───────────────────────────────────────────

def _harvest_wikipedia(lang_label: str, max_articles: int = 100) -> str:
    """Fetch Wikipedia text for this language and append to vocabulary.jsonl."""
    if _hf_api is None:
        return "⚠️ HF_TOKEN not set."
    lang = SUPPORTED_LANGUAGES.get(lang_label, "bam")
    if lang not in ("bam", "ful"):
        return "⚠️ Wikipedia harvest only supported for Bambara and Fula."

    from src.data.web_harvester import harvest_wikipedia_text
    entries = harvest_wikipedia_text(lang, max_articles=max_articles)
    if not entries:
        return "⚠️ No text harvested — check network or try again."

    # Append to vocabulary.jsonl
    from huggingface_hub import hf_hub_download
    for attempt in range(2):
        try:
            local = hf_hub_download(
                repo_id=FEEDBACK_REPO_ID, filename="vocabulary.jsonl",
                repo_type="dataset", token=HF_TOKEN,
            )
            with open(local, encoding="utf-8") as f:
                existing = f.read()
        except Exception:
            existing = ""
        new_lines = "".join(json.dumps(e, ensure_ascii=False) + "\n" for e in entries)
        updated   = existing + new_lines
        try:
            _hf_api.upload_file(
                path_or_fileobj=io.BytesIO(updated.encode("utf-8")),
                path_in_repo="vocabulary.jsonl",
                repo_id=FEEDBACK_REPO_ID,
                repo_type="dataset",
            )
            break
        except Exception as e:
            if attempt == 1:
                return f"❌ Upload failed: {e}"

    return (
        f"✅ Wikipedia harvest complete!\n"
        f"  Language : {lang_label}\n"
        f"  Sentences added : {len(entries)}\n"
        f"  Total vocabulary entries: {updated.count(chr(10))}"
    )


def _harvest_hf_dataset(lang_label: str, max_samples: int = 500) -> str:
    """Pull audio+transcription from public HF datasets into corrections.jsonl."""
    if _hf_api is None:
        return "⚠️ HF_TOKEN not set."
    lang = SUPPORTED_LANGUAGES.get(lang_label, "bam")
    if lang not in ("bam", "ful"):
        return "⚠️ HF dataset harvest only supported for Bambara and Fula."

    from src.data.web_harvester import harvest_hf_audio, HF_ASR_SOURCES
    sources = HF_ASR_SOURCES.get(lang, [])
    if not sources:
        return f"⚠️ No HF dataset configured for {lang}."

    records = []
    errors  = 0
    for wav_bytes, text, repo_path in harvest_hf_audio(lang, HF_TOKEN):
        try:
            _hf_api.upload_file(
                path_or_fileobj=io.BytesIO(wav_bytes),
                path_in_repo=repo_path,
                repo_id=FEEDBACK_REPO_ID,
                repo_type="dataset",
            )
            ts = repo_path.split("_")[-1].replace(".wav", "")
            records.append({
                "id": ts, "timestamp": datetime.now(timezone.utc).isoformat(),
                "language": lang,
                "audio_file": repo_path,
                "transcription": text, "corrected_text": text,
                "source": f"hf_harvest:{sources[0]['repo']}",
                "is_correction": False, "model": WHISPER_MODEL_ID,
            })
            if len(records) >= max_samples:
                break
        except Exception:
            errors += 1
            if errors > 20:
                break

    if not records:
        return "⚠️ No samples harvested. Dataset may require accepting terms on HuggingFace first."

    # Append to corrections.jsonl
    from huggingface_hub import hf_hub_download
    for attempt in range(2):
        try:
            local = hf_hub_download(
                repo_id=FEEDBACK_REPO_ID, filename="corrections.jsonl",
                repo_type="dataset", token=HF_TOKEN,
            )
            with open(local, encoding="utf-8") as f:
                existing = f.read()
        except Exception:
            existing = ""
        new_lines = "".join(json.dumps(r, ensure_ascii=False) + "\n" for r in records)
        updated   = existing + new_lines
        try:
            _hf_api.upload_file(
                path_or_fileobj=io.BytesIO(updated.encode("utf-8")),
                path_in_repo="corrections.jsonl",
                repo_id=FEEDBACK_REPO_ID,
                repo_type="dataset",
            )
            break
        except Exception as e:
            if attempt == 1:
                return f"❌ corrections.jsonl update failed: {e}"

    total = updated.count("\n")
    _maybe_auto_trigger()
    return (
        f"✅ HF dataset harvest complete!\n"
        f"  Source   : {sources[0]['repo']}\n"
        f"  Imported : {len(records)} samples ({errors} errors)\n"
        f"  Dataset  : {total} total corrections\n"
    )


# ── Main ask handler ──────────────────────────────────────────────────────────

def handle_ask(audio_path, language_label):
    if audio_path is None:
        return "⚠️ No audio — press Record or upload a file.", "", "", None

    language_code = SUPPORTED_LANGUAGES.get(language_label, "bam")
    status = _ensure_whisper_loaded()

    if _whisper_model is None:
        return f"⏳ Model loading ({status}). Wait a moment and try again.", "", "", None

    try:
        transcript, english_translation, response_text, audio_out = _run_pipeline(audio_path, language_code)
        return transcript, english_translation, response_text, audio_out
    except Exception as e:
        return f"❌ {e}", "", "", None


# ── Gradio UI ─────────────────────────────────────────────────────────────────

def build_ui() -> gr.Blocks:
    with gr.Blocks(title="Sahel-Agri Voice AI") as demo:
        gr.Markdown("# 🌾 Sahel-Agri Voice AI")
        gr.Markdown(
            "Speak in **Bambara** or **Fula** — get agricultural insights spoken back "
            "in your language. Also supports French and English."
        )

        model_status_box = gr.Textbox(
            value=get_model_status(),
            label="Model status",
            interactive=False,
        )
        # gr.Timer polls get_model_status every 3s and updates the box (Gradio 5)
        status_timer = gr.Timer(value=3)
        status_timer.tick(fn=get_model_status, outputs=model_status_box)

        with gr.Tabs() as tabs:

            # ── Tab 1: Voice Assistant ────────────────────────────────────────
            with gr.TabItem("🎙️ Voice Assistant", id="tab_voice"):
                with gr.Row():
                    with gr.Column(scale=1):
                        language_dd = gr.Dropdown(
                            choices=list(SUPPORTED_LANGUAGES.keys()),
                            value="Bambara (bam)",
                            label="Language / Kan",
                        )
                        audio_input = gr.Audio(
                            sources=["microphone", "upload"],
                            type="filepath",
                            label="Record or upload audio",
                        )
                        ask_btn = gr.Button("▶ Ask / Ɲinɛ", variant="primary")

                    with gr.Column(scale=1):
                        transcript_box = gr.Textbox(
                            label="Whisper heard (transcription)",
                            lines=2,
                            placeholder="Your words will appear here…",
                            interactive=False,
                        )
                        translation_box = gr.Textbox(
                            label="English translation",
                            lines=2,
                            placeholder="English meaning will appear here…",
                            interactive=False,
                        )
                        response_box = gr.Textbox(
                            label="Response in your language",
                            lines=2,
                            placeholder="Agricultural advice will appear here…",
                            interactive=False,
                        )
                        audio_output = gr.Audio(
                            label="Voice response",
                            autoplay=True,
                            interactive=False,
                        )
                        correct_btn = gr.Button(
                            "✏️ Something wrong? Send to Correction tab",
                            variant="secondary",
                            size="sm",
                        )

                ask_btn.click(
                    fn=handle_ask,
                    inputs=[audio_input, language_dd],
                    outputs=[transcript_box, translation_box, response_box, audio_output],
                )

            # ── Tab 2: Feedback & Correction ─────────────────────────────────
            with gr.TabItem("📝 Feedback & Correction", id="tab_feedback"):
                gr.Markdown(
                    "Correct what Whisper heard, the English translation, and the response. "
                    "All corrections are saved to the training dataset to improve future accuracy."
                )
                with gr.Row():
                    with gr.Column():
                        fb_lang = gr.Dropdown(
                            choices=list(SUPPORTED_LANGUAGES.keys()),
                            value="Bambara (bam)",
                            label="Language",
                        )
                        fb_audio = gr.Audio(
                            sources=["microphone", "upload"],
                            type="filepath",
                            label="Audio",
                        )
                        gr.Markdown("**Step 1 — Fix the transcription**")
                        fb_transcript = gr.Textbox(
                            label="What Whisper heard",
                            lines=2,
                            placeholder="Auto-filled from Tab 1…",
                        )
                        fb_corrected = gr.Textbox(
                            label="✏️ What was actually said (in Bambara/Fula)",
                            lines=2,
                            placeholder="Type the correct transcription here…",
                        )

                    with gr.Column():
                        gr.Markdown("**Step 2 — Fix the English translation**")
                        fb_english = gr.Textbox(
                            label="Auto-generated English translation",
                            lines=2,
                            placeholder="Auto-filled from Tab 1…",
                        )
                        fb_corrected_english = gr.Textbox(
                            label="✏️ Correct English translation",
                            lines=2,
                            placeholder="Type the correct English meaning here…",
                        )
                        gr.Markdown("**Step 3 — Fix the response**")
                        fb_response = gr.Textbox(
                            label="Auto-generated response",
                            lines=2,
                            placeholder="Auto-filled from Tab 1…",
                        )
                        fb_corrected_response = gr.Textbox(
                            label="✏️ Better response (in farmer's language)",
                            lines=2,
                            placeholder="Type a better response here…",
                        )
                        fb_rating = gr.Slider(
                            minimum=1, maximum=5, step=1, value=3,
                            label="Overall quality (1 = poor, 5 = excellent)",
                        )
                        fb_notes = gr.Textbox(
                            label="Notes (optional)",
                            lines=2,
                            placeholder="e.g. noisy background, strong accent…",
                        )
                        save_btn = gr.Button("💾 Save to Dataset", variant="primary")
                        save_status = gr.Textbox(
                            label="Save status", interactive=False, lines=2
                        )

                save_btn.click(
                    fn=_save_feedback_to_hub,
                    inputs=[
                        fb_audio, fb_transcript, fb_corrected,
                        fb_english, fb_corrected_english,
                        fb_response, fb_corrected_response,
                        fb_rating, fb_notes, fb_lang,
                    ],
                    outputs=[save_status],
                )

            # Wire "Send to Correction" button — populates Tab 2 fields from Tab 1
            correct_btn.click(
                fn=lambda t, tr, r, lang: (t, t, tr, tr, r, r, lang),
                inputs=[transcript_box, translation_box, response_box, language_dd],
                outputs=[fb_transcript, fb_corrected, fb_english, fb_corrected_english,
                         fb_response, fb_corrected_response, fb_lang],
            )

            # ── Tab 3: Knowledge Base ─────────────────────────────────────────
            with gr.TabItem("📚 Knowledge Base"):
                gr.Markdown(
                    "## Teach the assistant new phrases — no technical knowledge required\n\n"
                    "Add phrases the assistant should recognise and respond to. "
                    "Changes take effect **immediately** and are saved to the Hub so they survive restarts."
                )
                with gr.Row():
                    # ── Left: phrase pair import ──────────────────────────────
                    with gr.Column():
                        gr.Markdown(
                            "### ➕ Add phrases manually\n"
                            "One phrase per line in the format:\n"
                            "```\nnative phrase | English translation\n```\n"
                            "**Examples (Bambara):**\n"
                            "```\nI ni ce | Hello, good day\n"
                            "Sanji bɛ na | Rain is coming\n"
                            "N bɛ i dɛmɛ | I will help you\n```\n"
                            "**Examples (Fula):**\n"
                            "```\nJam waali | Hello, peace be with you\n"
                            "Ndiyam wadata | Rain is coming\n"
                            "Mi woni ɗoo | I am here\n```"
                        )
                        kb_lang = gr.Dropdown(
                            choices=["Bambara (bam)", "Fula (ful)"],
                            value="Bambara (bam)",
                            label="Language",
                        )
                        kb_pairs = gr.Textbox(
                            lines=10,
                            placeholder="I ni ce | Hello, good day\nI ni sogoma | Good morning\nSanji bɛ na | Rain is coming",
                            label="Phrase pairs (native | english) — one per line",
                        )
                        kb_import_btn = gr.Button("➕ Add to Knowledge Base", variant="primary")
                        kb_status = gr.Textbox(label="Status", interactive=False, lines=3)

                    # ── Right: audio upload for training ─────────────────────
                    with gr.Column():
                        gr.Markdown(
                            "### 🎬 Add audio from YouTube (or anywhere)\n"
                            "HuggingFace Spaces cannot download YouTube directly, "
                            "so convert the video to audio first on your computer:\n\n"
                            "**Free online converters:**\n"
                            "- [ytmp3.cc](https://ytmp3.cc) — paste YouTube URL → download MP3\n"
                            "- [cobalt.tools](https://cobalt.tools) — paste any video URL → download audio\n"
                            "- [y2mate.com](https://y2mate.com) — paste YouTube URL → download MP3\n\n"
                            "**Good YouTube search terms:**\n"
                            "- Bambara: *'Bamanankan conversation'*, *'Bambara leçon'*, *'donsomana'*\n"
                            "- Fula: *'Fulfulde leçon'*, *'Pular conversation'*, *'Fula radio'*\n\n"
                            "Then upload the MP3/WAV file below with its transcription."
                        )
                        yt_lang = gr.Dropdown(
                            choices=["Bambara (bam)", "Fula (ful)"],
                            value="Bambara (bam)",
                            label="Language spoken in the audio",
                        )
                        yt_audio = gr.Audio(
                            sources=["upload"],
                            type="filepath",
                            label="Upload audio file (MP3 or WAV)",
                        )
                        yt_transcript = gr.Textbox(
                            lines=5,
                            placeholder="Type what is said in the audio (as much as you can).\n"
                                        "Example:\nJam waali. No mbadda. Mi woni ɗoo wallude ma.",
                            label="Transcription — what is said in this audio",
                        )
                        yt_source = gr.Textbox(
                            placeholder="e.g. YouTube: Bambara lesson by Moussa Kouyaté",
                            label="Source (optional — for your records)",
                        )
                        yt_btn = gr.Button("💾 Save Audio for Training", variant="secondary")
                        yt_status = gr.Textbox(label="Status", interactive=False, lines=4)

                kb_import_btn.click(
                    fn=_import_phrase_pairs,
                    inputs=[kb_lang, kb_pairs],
                    outputs=[kb_status],
                )
                yt_btn.click(
                    fn=_save_audio_for_training,
                    inputs=[yt_lang, yt_audio, yt_transcript, yt_source],
                    outputs=[yt_status],
                )

            # ── Tab 4: Model Training ─────────────────────────────────────────
            with gr.TabItem("🔧 Model Training"):
                gr.Markdown(
                    "After collecting audio corrections and YouTube samples, "
                    "run the training notebook to fine-tune the speech model."
                )
                adapter_status_md = gr.Markdown(value=_get_adapter_status())
                reload_btn = gr.Button("🔄 Reload Fine-tuned Models from Hub")
                reload_out = gr.Markdown()

                gr.Markdown("---")
                gr.Markdown(
                    "**Training notebook**: "
                    "`notebooks/kaggle_master_trainer.ipynb` — import to Kaggle, run all cells.\n\n"
                    "**What feeds training:**\n"
                    "- Tab 2 corrections → `corrections.jsonl` in the feedback dataset\n"
                    "- Tab 3 audio uploads → `corrections.jsonl` (same file)\n"
                    "- Tab 3 phrase pairs → `vocabulary.jsonl` (used as synthetic fallback labels)\n\n"
                    "**Feedback dataset**: "
                    f"`{FEEDBACK_REPO_ID}` (auto-updated on each save)\n\n"
                    "**Model checkpoint repo**: "
                    f"`{ADAPTER_REPO_ID}` (updated after training, reload above to activate)"
                )

                reload_btn.click(fn=_reload_adapters_from_hub, outputs=[reload_out])
                reload_btn.click(fn=_get_adapter_status, outputs=[adapter_status_md])

            # ── Tab 5: Bulk Upload ────────────────────────────────────────────
            with gr.TabItem("📦 Bulk Upload"):
                gr.Markdown(
                    "## Upload many audio samples at once\n\n"
                    "**Step 1** — Prepare a ZIP file containing your audio files (WAV/MP3).\n\n"
                    "**Step 2** — Prepare a CSV with two columns: `filename,transcription`\n"
                    "```\nbam_001.wav,I ni ce a tɔ\nbam_002.wav,Sanji bɛ na sini\n```\n\n"
                    "**Step 3** — Select language, upload ZIP, paste CSV, click Upload."
                )
                with gr.Row():
                    with gr.Column():
                        bulk_lang = gr.Dropdown(
                            choices=["Bambara (bam)", "Fula (ful)"],
                            value="Bambara (bam)", label="Language"
                        )
                        bulk_zip = gr.File(
                            label="ZIP file (audio files)", file_types=[".zip"]
                        )
                        bulk_csv = gr.Textbox(
                            lines=10,
                            label="CSV — filename,transcription (one per line)",
                            placeholder="bam_001.wav,I ni ce a tɔ\nbam_002.wav,Sanji bɛ na sini",
                        )
                        bulk_btn = gr.Button("📤 Upload Batch", variant="primary")
                        bulk_status = gr.Textbox(label="Status", interactive=False, lines=5)
                bulk_btn.click(
                    fn=_bulk_upload,
                    inputs=[bulk_lang, bulk_zip, bulk_csv],
                    outputs=[bulk_status],
                )

            # ── Tab 6: Self-Teaching ──────────────────────────────────────────
            with gr.TabItem("🌐 Self-Teaching"):
                gr.Markdown(
                    "## Teach the model from the internet\n\n"
                    "These tools pull publicly available Bambara and Fula language data "
                    "directly into your training dataset — no manual work required."
                )
                with gr.Row():
                    # Wikipedia harvest
                    with gr.Column():
                        gr.Markdown(
                            "### 📖 Wikipedia Text Harvest\n"
                            "Pulls sentence-length text from Bambara Wikipedia (868 articles) "
                            "or Fula Wikipedia (17,000+ articles) into `vocabulary.jsonl`.\n\n"
                            "Use this to expand vocabulary coverage before a training run."
                        )
                        wiki_lang = gr.Dropdown(
                            choices=["Bambara (bam)", "Fula (ful)"],
                            value="Bambara (bam)", label="Language"
                        )
                        wiki_articles = gr.Slider(
                            minimum=10, maximum=500, value=100, step=10,
                            label="Max articles to fetch"
                        )
                        wiki_btn = gr.Button("📖 Harvest Wikipedia Text", variant="secondary")
                        wiki_status = gr.Textbox(label="Status", interactive=False, lines=4)
                        wiki_btn.click(
                            fn=_harvest_wikipedia,
                            inputs=[wiki_lang, wiki_articles],
                            outputs=[wiki_status],
                        )

                    # HF dataset harvest
                    with gr.Column():
                        gr.Markdown(
                            "### 🤗 HuggingFace Dataset Import\n"
                            "Pulls real audio + transcriptions from:\n"
                            "- **Bambara**: `RobotsMali/jeli-asr` (33,000 samples)\n"
                            "- **Fula**: `google/fleurs ff_sn`\n\n"
                            "Samples are added to `corrections.jsonl` and counted toward "
                            f"the auto-training threshold ({AUTO_TRAIN_THRESHOLD} entries)."
                        )
                        hf_lang = gr.Dropdown(
                            choices=["Bambara (bam)", "Fula (ful)"],
                            value="Bambara (bam)", label="Language"
                        )
                        hf_samples = gr.Slider(
                            minimum=50, maximum=2000, value=500, step=50,
                            label="Max samples to import"
                        )
                        hf_btn = gr.Button("🤗 Import from HuggingFace", variant="primary")
                        hf_status = gr.Textbox(label="Status", interactive=False, lines=5)
                        hf_btn.click(
                            fn=_harvest_hf_dataset,
                            inputs=[hf_lang, hf_samples],
                            outputs=[hf_status],
                        )

                gr.Markdown("---")
                gr.Markdown(
                    "### ⚡ Auto-Training\n"
                    f"When `corrections.jsonl` reaches a multiple of **{AUTO_TRAIN_THRESHOLD}** entries, "
                    "the Kaggle training notebook is triggered automatically.\n\n"
                    "To enable: add `KAGGLE_USERNAME` and `KAGGLE_KEY` in Space Settings → Secrets.\n\n"
                    f"Kernel: `{KAGGLE_KERNEL_SLUG}`"
                )
                with gr.Row():
                    trigger_lang = gr.Dropdown(
                        choices=["Bambara (bam)", "Fula (ful)"],
                        value="Bambara (bam)", label="Language to train"
                    )
                    trigger_btn = gr.Button("⚡ Trigger Training Now", variant="secondary")
                trigger_out = gr.Textbox(label="Status", interactive=False, lines=2)
                trigger_btn.click(
                    fn=lambda l: _trigger_kaggle_training(SUPPORTED_LANGUAGES.get(l, "bam")),
                    inputs=[trigger_lang],
                    outputs=[trigger_out],
                )

    return demo


# ── Entry point ───────────────────────────────────────────────────────────────

if __name__ == "__main__":
    from dotenv import load_dotenv
    load_dotenv()

    # Re-read env after dotenv
    HF_TOKEN         = os.environ.get("HF_TOKEN")
    FEEDBACK_REPO_ID = os.environ.get("FEEDBACK_REPO_ID", "ous-sow/sahel-agri-feedback")
    ADAPTER_REPO_ID  = os.environ.get("ADAPTER_REPO_ID",  "ous-sow/sahel-agri-adapters")
    WHISPER_MODEL_ID = os.environ.get("WHISPER_MODEL_ID",  "openai/whisper-small")

    if HF_TOKEN:
        from huggingface_hub import HfApi
        _hf_api = HfApi(token=HF_TOKEN)

    # Load any previously saved phrase additions from HF Hub
    _load_phrase_additions_from_hub()

    # Kick off background model load immediately
    _ensure_whisper_loaded()

    print(f"Whisper model : {WHISPER_MODEL_ID}")
    print(f"Feedback repo : {FEEDBACK_REPO_ID}")
    print(f"Adapter repo  : {ADAPTER_REPO_ID}")
    print(f"HF_TOKEN set  : {'yes' if HF_TOKEN else 'no (local-only mode)'}")
    print()

    demo = build_ui()
    demo.launch(
        server_port=7860,  # HF Spaces standard port
        inbrowser=False,
        share=False,
        show_api=False,
        ssr_mode=False,    # SSR starts a Node.js process that hangs in HF Spaces containers
    )