#!/usr/bin/env bash
# gstack-repo-mode — detect solo vs collaborative repo mode
# Usage: source <(gstack-repo-mode)  → sets REPO_MODE variable
# Or:    gstack-repo-mode           → prints REPO_MODE=... line
#
# Detection heuristic (90-day window):
#   Solo:          top author >= 80% of commits
#   Collaborative: top author < 80%
#
# Override: gstack-config set repo_mode solo|collaborative
# Cache:    ~/.gstack/projects/$SLUG/repo-mode.json (7-day TTL)
set -euo pipefail

SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
# Compute SLUG directly (avoid eval of gstack-slug — branch names can contain shell metacharacters)
REMOTE_URL=$(git remote get-url origin 2>/dev/null || true)
if [ -z "$REMOTE_URL" ]; then
  echo "REPO_MODE=unknown"
  exit 0
fi
SLUG=$(echo "$REMOTE_URL" | sed 's|.*[:/]\([^/]*/[^/]*\)\.git$|\1|;s|.*[:/]\([^/]*/[^/]*\)$|\1|' | tr '/' '-')
[ -z "${SLUG:-}" ] && { echo "REPO_MODE=unknown"; exit 0; }

# Validate: only allow known values (prevent shell injection via source <(...))
validate_mode() {
  case "$1" in solo|collaborative|unknown) echo "$1" ;; *) echo "unknown" ;; esac
}

# Config override takes precedence
OVERRIDE=$("$SCRIPT_DIR/gstack-config" get repo_mode 2>/dev/null || true)
if [ -n "$OVERRIDE" ] && [ "$OVERRIDE" != "null" ]; then
  echo "REPO_MODE=$(validate_mode "$OVERRIDE")"
  exit 0
fi

# Check cache (7-day TTL)
CACHE_DIR="$HOME/.gstack/projects/$SLUG"
CACHE_FILE="$CACHE_DIR/repo-mode.json"
if [ -f "$CACHE_FILE" ]; then
  CACHE_AGE=$(( $(date +%s) - $(stat -f %m "$CACHE_FILE" 2>/dev/null || stat -c %Y "$CACHE_FILE" 2>/dev/null || echo 0) ))
  if [ "$CACHE_AGE" -lt 604800 ]; then  # 7 days in seconds
    MODE=$(grep -o '"mode":"[^"]*"' "$CACHE_FILE" | head -1 | cut -d'"' -f4)
    [ -n "$MODE" ] && echo "REPO_MODE=$(validate_mode "$MODE")" && exit 0
  fi
fi

# Compute from git history (90-day window)
# Use default branch (not HEAD) to avoid feature-branch sampling bias
DEFAULT_BRANCH=$(git symbolic-ref refs/remotes/origin/HEAD 2>/dev/null | sed 's|refs/remotes/||' || true)
# Fallback: try origin/main, then origin/master, then HEAD
if [ -z "$DEFAULT_BRANCH" ]; then
  if git rev-parse --verify origin/main &>/dev/null; then
    DEFAULT_BRANCH="origin/main"
  elif git rev-parse --verify origin/master &>/dev/null; then
    DEFAULT_BRANCH="origin/master"
  else
    DEFAULT_BRANCH="HEAD"
  fi
fi
SHORTLOG=$(git shortlog -sn --since="90 days ago" --no-merges "$DEFAULT_BRANCH" 2>/dev/null)
if [ -z "$SHORTLOG" ]; then
  echo "REPO_MODE=unknown"
  exit 0
fi

# Compute TOTAL from ALL authors (not truncated) to avoid solo bias
TOTAL=$(echo "$SHORTLOG" | awk '{s+=$1} END {print s}')
TOP=$(echo "$SHORTLOG" | head -1 | awk '{print $1}')
AUTHORS=$(echo "$SHORTLOG" | wc -l | tr -d ' ')

# Minimum sample: need at least 5 commits to classify
if [ "$TOTAL" -lt 5 ]; then
  echo "REPO_MODE=unknown"
  exit 0
fi

TOP_PCT=$(( TOP * 100 / TOTAL ))

# Solo: top author >= 80% of commits (occasional outside PRs don't change mode)
if [ "$TOP_PCT" -ge 80 ]; then
  MODE=solo
else
  MODE=collaborative
fi

# Cache result atomically (fail silently if ~/.gstack is unwritable)
mkdir -p "$CACHE_DIR" 2>/dev/null || true
CACHE_TMP=$(mktemp "$CACHE_DIR/.repo-mode-XXXXXX" 2>/dev/null || true)
if [ -n "$CACHE_TMP" ]; then
  echo "{\"mode\":\"$MODE\",\"top_pct\":$TOP_PCT,\"authors\":$AUTHORS,\"total\":$TOTAL,\"computed\":\"$(date -u +%Y-%m-%dT%H:%M:%SZ)\"}" > "$CACHE_TMP" 2>/dev/null && mv "$CACHE_TMP" "$CACHE_FILE" 2>/dev/null || rm -f "$CACHE_TMP" 2>/dev/null
fi

echo "REPO_MODE=$MODE"