#!/usr/bin/env bash
set -euo pipefail

# ─── autoresearch.checks.sh ─────────────────────────────────────────────────
# Backpressure checks for the sequence diagram skill.
# ─────────────────────────────────────────────────────────────────────────────

SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
SKILL_FILE="${SCRIPT_DIR}/skill/SKILL.md"
ERRORS=0

# 1. Skill exists and is non-empty
if [[ ! -s "$SKILL_FILE" ]]; then
    echo "FAIL: skill/SKILL.md is missing or empty"
    ERRORS=$((ERRORS + 1))
fi

# 2. Skill is not trivially short
CHAR_COUNT=$(wc -c < "$SKILL_FILE" 2>/dev/null || echo "0")
if (( CHAR_COUNT < 200 )); then
    echo "FAIL: skill/SKILL.md is only ${CHAR_COUNT} chars (min: 200)"
    ERRORS=$((ERRORS + 1))
fi

# 3. Skill is not too long (rough token proxy: 1500 tokens ≈ 6000 chars)
if (( CHAR_COUNT > 6000 )); then
    echo "FAIL: skill/SKILL.md is ${CHAR_COUNT} chars (max: ~6000)"
    ERRORS=$((ERRORS + 1))
fi

# 4. Skill must contain "sequenceDiagram" or "sequence diagram" (it's a diagram skill)
if ! grep -qi 'sequence.diagram' "$SKILL_FILE" 2>/dev/null; then
    echo "FAIL: skill/SKILL.md doesn't mention sequence diagrams"
    ERRORS=$((ERRORS + 1))
fi

# 5. Skill must NOT contain Firehose-specific code (no overfitting)
for term in "BlogController" "EngineeringBlog" "Firehose" "blogex" "priv/blog"; do
    if grep -q "$term" "$SKILL_FILE" 2>/dev/null; then
        echo "FAIL: skill/SKILL.md contains codebase-specific term '${term}'"
        ERRORS=$((ERRORS + 1))
    fi
done

# 6. Valid UTF-8
if ! iconv -f utf-8 -t utf-8 "$SKILL_FILE" > /dev/null 2>&1; then
    echo "FAIL: skill/SKILL.md contains invalid UTF-8"
    ERRORS=$((ERRORS + 1))
fi

if (( ERRORS > 0 )); then
    echo "Checks FAILED with ${ERRORS} error(s)"
    exit 1
else
    echo "All checks passed. Skill: ${CHAR_COUNT} chars."
    exit 0
fi