#!/bin/bash
# Feed Hunter — Full pipeline run
# Usage: ./run-pipeline.sh [scroll_pages]
#
# Runs: scrape → triage → generate investigation tasks
# Agent handles investigation + alerts separately

set -e

PAGES=${1:-8}
BASE="/home/wdjones/.openclaw/workspace"
SKILL="$BASE/skills/deep-scraper/scripts"
PROJECT="$BASE/projects/feed-hunter"
DATA="$BASE/data/x-feed"

echo "=== Feed Hunter Pipeline ==="
echo "$(date '+%Y-%m-%d %H:%M:%S %Z')"

# Ensure Chrome is running with debug port
if ! curl -s http://127.0.0.1:9222/json >/dev/null 2>&1; then
    echo "Starting Chrome..."
    bash "$SKILL/launch-chrome-debug.sh"
fi

# Stage 1: Scrape
echo ""
echo "--- Stage 1: Scrape ($PAGES pages) ---"
python3 -u "$SKILL/scrape-x-feed.py" --port 9222 --scroll-pages "$PAGES"

# Find latest scrape
LATEST=$(ls -dt "$DATA"/20* | head -1)
echo "Latest scrape: $LATEST"

# Stage 2: Triage
echo ""
echo "--- Stage 2: Triage ---"
python3 "$SKILL/triage-posts.py" "$LATEST/posts.json"

# Stage 3: Generate investigation tasks
TRIAGE="$LATEST/triage.json"
if [ -f "$TRIAGE" ]; then
    QUEUE=$(python3 -c "import json; d=json.load(open('$TRIAGE')); print(len(d.get('investigation_queue',[])))")
    if [ "$QUEUE" -gt 0 ]; then
        echo ""
        echo "--- Stage 3: Investigation Tasks ---"
        python3 "$PROJECT/investigate.py" "$TRIAGE" --output "$LATEST/investigations"
        echo ""
        echo ">>> $QUEUE posts queued for investigation"
        echo ">>> Agent should read: $LATEST/investigations/"
    else
        echo ""
        echo ">>> No posts worth investigating this run."
    fi
else
    echo ">>> No triage output found."
fi

echo ""
echo "=== Pipeline complete: $LATEST ==="