hermes-config/bin/claude-loop.sh

#!/usr/bin/env bash
# claude-loop.sh — Parallel Claude Code agent dispatch loop
# Runs N workers concurrently against the Gitea backlog.
# Gracefully handles rate limits with backoff.
#
# Usage: claude-loop.sh [NUM_WORKERS]   (default: 3)

set -euo pipefail

# === CONFIG ===
NUM_WORKERS="${1:-10}"
MAX_WORKERS=21        # absolute ceiling
WORKTREE_BASE="$HOME/worktrees"
GITEA_URL="http://143.198.27.163:3000"
GITEA_TOKEN=$(cat "$HOME/.hermes/claude_token")
CLAUDE_TIMEOUT=900   # 15 min per issue
COOLDOWN=2            # seconds between issues — max speed
RATE_LIMIT_SLEEP=30   # initial sleep on rate limit
MAX_RATE_SLEEP=120    # max backoff on rate limit
LOG_DIR="$HOME/.hermes/logs"
SKIP_FILE="$LOG_DIR/claude-skip-list.json"
LOCK_DIR="$LOG_DIR/claude-locks"
ACTIVE_FILE="$LOG_DIR/claude-active.json"

mkdir -p "$LOG_DIR" "$WORKTREE_BASE" "$LOCK_DIR"

# Initialize files
[ -f "$SKIP_FILE" ] || echo '{}' > "$SKIP_FILE"
echo '{}' > "$ACTIVE_FILE"

# === SHARED FUNCTIONS ===
log() {
  local msg="[$(date '+%Y-%m-%d %H:%M:%S')] $*"
  echo "$msg" >> "$LOG_DIR/claude-loop.log"
}

lock_issue() {
  local issue_key="$1"
  local lockfile="$LOCK_DIR/$issue_key.lock"
  if mkdir "$lockfile" 2>/dev/null; then
    echo $$ > "$lockfile/pid"
    return 0
  fi
  return 1
}

unlock_issue() {
  local issue_key="$1"
  rm -rf "$LOCK_DIR/$issue_key.lock" 2>/dev/null
}

mark_skip() {
  local issue_num="$1"
  local reason="$2"
  local skip_hours="${3:-1}"
  python3 -c "
import json, time, fcntl
with open('$SKIP_FILE', 'r+') as f:
    fcntl.flock(f, fcntl.LOCK_EX)
    try: skips = json.load(f)
    except: skips = {}
    skips[str($issue_num)] = {
        'until': time.time() + ($skip_hours * 3600),
        'reason': '$reason',
        'failures': skips.get(str($issue_num), {}).get('failures', 0) + 1
    }
    if skips[str($issue_num)]['failures'] >= 3:
        skips[str($issue_num)]['until'] = time.time() + (6 * 3600)
    f.seek(0)
    f.truncate()
    json.dump(skips, f, indent=2)
" 2>/dev/null
  log "SKIP: #${issue_num} — ${reason}"
}

update_active() {
  local worker="$1" issue="$2" repo="$3" status="$4"
  python3 -c "
import json, fcntl
with open('$ACTIVE_FILE', 'r+') as f:
    fcntl.flock(f, fcntl.LOCK_EX)
    try: active = json.load(f)
    except: active = {}
    if '$status' == 'done':
        active.pop('$worker', None)
    else:
        active['$worker'] = {'issue': '$issue', 'repo': '$repo', 'status': '$status'}
    f.seek(0)
    f.truncate()
    json.dump(active, f, indent=2)
" 2>/dev/null
}

cleanup_workdir() {
  local wt="$1"
  rm -rf "$wt" 2>/dev/null || true
}

get_next_issue() {
  python3 -c "
import json, sys, time, urllib.request, os

token = '${GITEA_TOKEN}'
base = '${GITEA_URL}'
repos = [
    'rockachopa/Timmy-time-dashboard',
    'rockachopa/alexanderwhitestone.com',
    'rockachopa/hermes-agent',
    'replit/timmy-tower',
    'replit/token-gated-economy',
]

# Load skip list
try:
    with open('${SKIP_FILE}') as f: skips = json.load(f)
except: skips = {}

# Load active issues (to avoid double-picking)
try:
    with open('${ACTIVE_FILE}') as f:
        active = json.load(f)
        active_issues = {v['issue'] for v in active.values()}
except:
    active_issues = set()

all_issues = []
for repo in repos:
    url = f'{base}/api/v1/repos/{repo}/issues?state=open&type=issues&limit=50&sort=created'
    req = urllib.request.Request(url, headers={'Authorization': f'token {token}'})
    try:
        resp = urllib.request.urlopen(req, timeout=10)
        issues = json.loads(resp.read())
        for i in issues:
            i['_repo'] = repo
        all_issues.extend(issues)
    except:
        continue

# Sort by priority: URGENT > P0 > P1 > bugs > LHF > rest
def priority(i):
    t = i['title'].lower()
    if '[urgent]' in t or 'urgent:' in t: return 0
    if '[p0]' in t: return 1
    if '[p1]' in t: return 2
    if '[bug]' in t: return 3
    if 'lhf:' in t or 'lhf ' in t.lower(): return 4
    if '[p2]' in t: return 5
    return 6

all_issues.sort(key=priority)

for i in all_issues:
    assignees = [a['login'] for a in (i.get('assignees') or [])]
    # Take issues assigned to claude OR unassigned (self-assign)
    if assignees and 'claude' not in assignees:
        continue

    title = i['title'].lower()
    if '[philosophy]' in title: continue
    if '[epic]' in title or 'epic:' in title: continue
    if '[showcase]' in title: continue

    num_str = str(i['number'])
    if num_str in active_issues: continue

    entry = skips.get(num_str, {})
    if entry and entry.get('until', 0) > time.time(): continue

    lock = '${LOCK_DIR}/' + i['_repo'].replace('/', '-') + '-' + num_str + '.lock'
    if os.path.isdir(lock): continue

    repo = i['_repo']
    owner, name = repo.split('/')

    # Self-assign if unassigned
    if not assignees:
        try:
            data = json.dumps({'assignees': ['claude']}).encode()
            req2 = urllib.request.Request(
                f'{base}/api/v1/repos/{repo}/issues/{i[\"number\"]}',
                data=data, method='PATCH',
                headers={'Authorization': f'token {token}', 'Content-Type': 'application/json'})
            urllib.request.urlopen(req2, timeout=5)
        except: pass

    print(json.dumps({
        'number': i['number'],
        'title': i['title'],
        'repo_owner': owner,
        'repo_name': name,
        'repo': repo,
    }))
    sys.exit(0)

print('null')
" 2>/dev/null
}

build_prompt() {
  local issue_num="$1"
  local issue_title="$2"
  local worktree="$3"
  local repo_owner="$4"
  local repo_name="$5"

  cat <<PROMPT
You are Claude, an autonomous code agent on the ${repo_name} project.

YOUR ISSUE: #${issue_num} — "${issue_title}"

GITEA API: ${GITEA_URL}/api/v1
GITEA TOKEN: ${GITEA_TOKEN}
REPO: ${repo_owner}/${repo_name}
WORKING DIRECTORY: ${worktree}

== YOUR POWERS ==
You can do ANYTHING a developer can do.

1. READ the issue and any comments for context:
   curl -s -H "Authorization: token ${GITEA_TOKEN}" "${GITEA_URL}/api/v1/repos/${repo_owner}/${repo_name}/issues/${issue_num}"
   curl -s -H "Authorization: token ${GITEA_TOKEN}" "${GITEA_URL}/api/v1/repos/${repo_owner}/${repo_name}/issues/${issue_num}/comments"

2. DO THE WORK. Code, test, fix, refactor — whatever the issue needs.
   - Check for tox.ini / Makefile / package.json for test/lint commands
   - Run tests if the project has them
   - Follow existing code conventions

3. COMMIT with conventional commits: fix: / feat: / refactor: / test: / chore:
   Include "Fixes #${issue_num}" or "Refs #${issue_num}" in the message.

4. PUSH to your branch (claude/issue-${issue_num}) and CREATE A PR:
   git push origin claude/issue-${issue_num}
   curl -s -X POST "${GITEA_URL}/api/v1/repos/${repo_owner}/${repo_name}/pulls" \\
     -H "Authorization: token ${GITEA_TOKEN}" \\
     -H "Content-Type: application/json" \\
     -d '{"title": "[claude] <description> (#${issue_num})", "body": "Fixes #${issue_num}\n\n<describe what you did>", "head": "claude/issue-${issue_num}", "base": "main"}'

5. COMMENT on the issue when done:
   curl -s -X POST "${GITEA_URL}/api/v1/repos/${repo_owner}/${repo_name}/issues/${issue_num}/comments" \\
     -H "Authorization: token ${GITEA_TOKEN}" \\
     -H "Content-Type: application/json" \\
     -d '{"body": "PR created. <summary of changes>"}'

== RULES ==
- Read CLAUDE.md or project README first for conventions
- If the project has tox, use tox. If npm, use npm. Follow the project.
- Never use --no-verify on git commands.
- If tests fail after 2 attempts, STOP and comment on the issue explaining why.
- Be thorough but focused. Fix the issue, don't refactor the world.
PROMPT
}

# === WORKER FUNCTION ===
run_worker() {
  local worker_id="$1"
  local consecutive_failures=0

  log "WORKER-${worker_id}: Started"

  while true; do
    # Backoff on repeated failures
    if [ "$consecutive_failures" -ge 5 ]; then
      local backoff=$((RATE_LIMIT_SLEEP * (consecutive_failures / 5)))
      [ "$backoff" -gt "$MAX_RATE_SLEEP" ] && backoff=$MAX_RATE_SLEEP
      log "WORKER-${worker_id}: BACKOFF ${backoff}s (${consecutive_failures} failures)"
      sleep "$backoff"
      consecutive_failures=0
    fi

    # Get next issue
    issue_json=$(get_next_issue)

    if [ "$issue_json" = "null" ] || [ -z "$issue_json" ]; then
      update_active "$worker_id" "" "" "idle"
      sleep 10
      continue
    fi

    issue_num=$(echo "$issue_json" | python3 -c "import sys,json; print(json.load(sys.stdin)['number'])")
    issue_title=$(echo "$issue_json" | python3 -c "import sys,json; print(json.load(sys.stdin)['title'])")
    repo_owner=$(echo "$issue_json" | python3 -c "import sys,json; print(json.load(sys.stdin)['repo_owner'])")
    repo_name=$(echo "$issue_json" | python3 -c "import sys,json; print(json.load(sys.stdin)['repo_name'])")
    issue_key="${repo_owner}-${repo_name}-${issue_num}"
    branch="claude/issue-${issue_num}"
    worktree="${WORKTREE_BASE}/claude-w${worker_id}-${issue_num}"

    # Try to lock
    if ! lock_issue "$issue_key"; then
      sleep 5
      continue
    fi

    log "WORKER-${worker_id}: === ISSUE #${issue_num}: ${issue_title} (${repo_owner}/${repo_name}) ==="
    update_active "$worker_id" "$issue_num" "${repo_owner}/${repo_name}" "working"

    # Fresh clone per issue — no shared state, no contention
    rm -rf "$worktree" 2>/dev/null
    if ! git clone --depth=1 -b main \
      "http://claude:${GITEA_TOKEN}@143.198.27.163:3000/${repo_owner}/${repo_name}.git" \
      "$worktree" >/dev/null 2>&1; then
      log "WORKER-${worker_id}: ERROR cloning for #${issue_num}"
      unlock_issue "$issue_key"
      consecutive_failures=$((consecutive_failures + 1))
      sleep "$COOLDOWN"
      continue
    fi
    cd "$worktree"
    git checkout -b "$branch" >/dev/null 2>&1

    # Build prompt and run
    prompt=$(build_prompt "$issue_num" "$issue_title" "$worktree" "$repo_owner" "$repo_name")

    log "WORKER-${worker_id}: Launching Claude Code for #${issue_num}..."

    set +e
    cd "$worktree"
    env -u CLAUDECODE gtimeout "$CLAUDE_TIMEOUT" claude \
      --print \
      --dangerously-skip-permissions \
      -p "$prompt" \
      </dev/null >> "$LOG_DIR/claude-${issue_num}.log" 2>&1
    exit_code=$?
    set -e

    if [ "$exit_code" -eq 0 ]; then
      log "WORKER-${worker_id}: SUCCESS #${issue_num}"

      # Auto-merge
      pr_num=$(curl -sf "${GITEA_URL}/api/v1/repos/${repo_owner}/${repo_name}/pulls?state=open&head=${repo_owner}:${branch}&limit=1" \
        -H "Authorization: token ${GITEA_TOKEN}" | python3 -c "
import sys,json
prs = json.load(sys.stdin)
if prs: print(prs[0]['number'])
else: print('')
" 2>/dev/null)

      if [ -n "$pr_num" ]; then
        curl -sf -X POST "${GITEA_URL}/api/v1/repos/${repo_owner}/${repo_name}/pulls/${pr_num}/merge" \
          -H "Authorization: token ${GITEA_TOKEN}" \
          -H "Content-Type: application/json" \
          -d '{"Do": "squash"}' >/dev/null 2>&1 || true
        curl -sf -X PATCH "${GITEA_URL}/api/v1/repos/${repo_owner}/${repo_name}/issues/${issue_num}" \
          -H "Authorization: token ${GITEA_TOKEN}" \
          -H "Content-Type: application/json" \
          -d '{"state": "closed"}' >/dev/null 2>&1 || true
        log "WORKER-${worker_id}: PR #${pr_num} merged, issue #${issue_num} closed"
      fi

      consecutive_failures=0

    elif [ "$exit_code" -eq 124 ]; then
      log "WORKER-${worker_id}: TIMEOUT #${issue_num}"
      mark_skip "$issue_num" "timeout" 1
      consecutive_failures=$((consecutive_failures + 1))

    else
      # Check for rate limit (exit code from claude CLI)
      if grep -q "rate_limit\|rate limit\|429\|overloaded" "$LOG_DIR/claude-${issue_num}.log" 2>/dev/null; then
        log "WORKER-${worker_id}: RATE LIMITED on #${issue_num} — backing off"
        mark_skip "$issue_num" "rate_limit" 0.25  # 15 min skip
        consecutive_failures=$((consecutive_failures + 3))  # faster backoff
      else
        log "WORKER-${worker_id}: FAILED #${issue_num} (exit ${exit_code})"
        mark_skip "$issue_num" "exit_code_${exit_code}" 1
        consecutive_failures=$((consecutive_failures + 1))
      fi
    fi

    # Cleanup
    cleanup_workdir "$worktree"
    unlock_issue "$issue_key"
    update_active "$worker_id" "" "" "done"

    sleep "$COOLDOWN"
  done
}

# === MAIN ===
log "=== Claude Loop Started — ${NUM_WORKERS} workers (max ${MAX_WORKERS}) ==="
log "Worktrees: ${WORKTREE_BASE}"

# Clean stale locks
rm -rf "$LOCK_DIR"/*.lock 2>/dev/null

# PID tracking via files (bash 3.2 compatible)
PID_DIR="$LOG_DIR/claude-pids"
mkdir -p "$PID_DIR"
rm -f "$PID_DIR"/*.pid 2>/dev/null

launch_worker() {
  local wid="$1"
  run_worker "$wid" &
  echo $! > "$PID_DIR/${wid}.pid"
  log "Launched worker $wid (PID $!)"
}

# Initial launch
for i in $(seq 1 "$NUM_WORKERS"); do
  launch_worker "$i"
  sleep 3
done

# === DYNAMIC SCALER ===
# Every 3 minutes: check health, scale up if no rate limits, scale down if hitting limits
CURRENT_WORKERS="$NUM_WORKERS"
while true; do
  sleep 90

  # Reap dead workers and relaunch
  for pidfile in "$PID_DIR"/*.pid; do
    [ -f "$pidfile" ] || continue
    wid=$(basename "$pidfile" .pid)
    wpid=$(cat "$pidfile")
    if ! kill -0 "$wpid" 2>/dev/null; then
      log "SCALER: Worker $wid died — relaunching"
      launch_worker "$wid"
      sleep 2
    fi
  done

  recent_rate_limits=$(tail -100 "$LOG_DIR/claude-loop.log" 2>/dev/null | grep -c "RATE LIMITED" || true)
  recent_successes=$(tail -100 "$LOG_DIR/claude-loop.log" 2>/dev/null | grep -c "SUCCESS" || true)

  if [ "$recent_rate_limits" -gt 0 ]; then
    if [ "$CURRENT_WORKERS" -gt 2 ]; then
      drop_to=$(( CURRENT_WORKERS / 2 ))
      [ "$drop_to" -lt 2 ] && drop_to=2
      log "SCALER: Rate limited — scaling ${CURRENT_WORKERS} → ${drop_to} workers"
      for wid in $(seq $((drop_to + 1)) "$CURRENT_WORKERS"); do
        if [ -f "$PID_DIR/${wid}.pid" ]; then
          kill "$(cat "$PID_DIR/${wid}.pid")" 2>/dev/null || true
          rm -f "$PID_DIR/${wid}.pid"
          update_active "$wid" "" "" "done"
        fi
      done
      CURRENT_WORKERS=$drop_to
    fi
  elif [ "$recent_successes" -ge 2 ] && [ "$CURRENT_WORKERS" -lt "$MAX_WORKERS" ]; then
    new_count=$(( CURRENT_WORKERS + 2 ))
    [ "$new_count" -gt "$MAX_WORKERS" ] && new_count=$MAX_WORKERS
    log "SCALER: Healthy — scaling ${CURRENT_WORKERS} → ${new_count} workers"
    for wid in $(seq $((CURRENT_WORKERS + 1)) "$new_count"); do
      launch_worker "$wid"
      sleep 2
    done
    CURRENT_WORKERS=$new_count
  fi
done