TMPDIR=$(mktemp -d)

# Step 1: try subtitle extraction — use SRT conversion to handle auto-caption dedup
yt-dlp --write-auto-sub --sub-lang "en" --skip-download --convert-subs srt -o "${TMPDIR}/sub" "<url>" 2>/dev/null
TRANSCRIPT=$(cat ${TMPDIR}/sub*.srt 2>/dev/null | grep -v "^[0-9]" | grep -v "^\-\->" | grep -v "^$" | sed 's/<[^>]*>//g' | tr '\n' ' ')

# Step 2: if no subtitles, transcribe via Groq
if [ -z "$TRANSCRIPT" ]; then
  if [ -z "$GROQ_API_KEY" ]; then
    echo "ERROR: No subtitles found and GROQ_API_KEY is not set. Cannot transcribe."
    rm -rf "$TMPDIR"
    exit 1
  fi
  yt-dlp -x --audio-format mp3 --audio-quality 9 -o "${TMPDIR}/audio.%(ext)s" "<url>" 2>/dev/null

  # Check file size — Groq limit: 25MB free tier, 100MB dev tier
  FILESIZE=$(stat -f%z "${TMPDIR}/audio.mp3" 2>/dev/null || stat -c%s "${TMPDIR}/audio.mp3" 2>/dev/null)
  if [ "$FILESIZE" -gt 100000000 ]; then
    echo "ERROR: Audio too large for Groq ($(($FILESIZE/1048576))MB, limit 100MB). Try a shorter video."
    rm -rf "$TMPDIR"
    exit 1
  fi

  TRANSCRIPT=$(curl -s https://api.groq.com/openai/v1/audio/transcriptions \
    -H "Authorization: Bearer $GROQ_API_KEY" \
    -F "file=@${TMPDIR}/audio.mp3" \
    -F "model=whisper-large-v3-turbo" | jq -r '.text')
fi
rm -rf "$TMPDIR"

if [ -z "$X_BEARER_TOKEN" ]; then
  echo "X_BEARER_TOKEN is not set. Ask user to paste thread text."
  exit 1
fi

TWEET_ID=$(echo "<url>" | grep -oE '[0-9]{15,}' | tail -1)

# Fetch root tweet with conversation context
TWEET_DATA=$(curl -s "https://api.twitter.com/2/tweets/${TWEET_ID}?tweet.fields=conversation_id,author_id,text,created_at&expansions=author_id&user.fields=name,username" \
  -H "Authorization: Bearer $X_BEARER_TOKEN")

CONV_ID=$(echo "$TWEET_DATA" | jq -r '.data.conversation_id')
AUTHOR_ID=$(echo "$TWEET_DATA" | jq -r '.data.author_id')

# Fetch thread (search/recent — last 7 days only)
THREAD=$(curl -s "https://api.twitter.com/2/tweets/search/recent?query=conversation_id:${CONV_ID}&tweet.fields=text,created_at,author_id&max_results=100&sort_order=recency" \
  -H "Authorization: Bearer $X_BEARER_TOKEN")

# Filter to author only, reverse to chronological
THREAD_TWEETS=$(echo "$THREAD" | jq -r --arg aid "$AUTHOR_ID" \
  '[.data[] | select(.author_id == $aid)] | reverse | .[].text')