cc-ci-orchestrator/cc-ci-plan/launch-upgrader.py

#!/usr/bin/env python3
"""
cc-ci upgrader launcher — one-shot weekly recipe-upgrade job agent.

The upgrader runs /upgrade-all to completion, then stops and stays idle so the
run + summary remain viewable in the web UI. The next weekly run starts a fresh
session (start clears any idle/finished session).

Usage:
  launch-upgrader.py start    use-or-create: leave an in-flight run alone, else start fresh
  launch-upgrader.py fresh    always kill any existing session and start fresh
  launch-upgrader.py stop     kill the session
  launch-upgrader.py status   show session state
  launch-upgrader.py attach   tmux attach to the session

Env:
  LOOP_BACKEND     claude (default) | opencode   — also accepts UPGRADER_BACKEND
  LOOP_MODEL       model flag (overrides UPGRADER_MODEL)
  UPGRADER_MODEL   sonnet (default for claude) | tinfoil/deepseek-v4-pro (opencode example)
  UPGRADER_ARGS    extra args passed to /upgrade-all (e.g. "n8n ghost", "--dry-run")

  claude backend:
    CLAUDE_BIN, CLAUDE_FLAGS, REMOTE_CONTROL
  opencode backend:
    OPENCODE_BIN, OPENCODE_SERVER
"""

import os, sys, subprocess, re
from datetime import datetime
from pathlib import Path

# ── config ────────────────────────────────────────────────────────────────────

SESSION = os.environ.get("UPGRADER_SESSION", "cc-ci-upgrader")
WORKDIR = os.environ.get("UPGRADER_DIR",     "/srv/cc-ci")
LOG_DIR = os.environ.get("LOG_DIR",          "/srv/cc-ci/.cc-ci-logs")

# LOOP_BACKEND / LOOP_MODEL take precedence (unified control from the operator).
BACKEND = os.environ.get("LOOP_BACKEND", os.environ.get("UPGRADER_BACKEND", "claude"))
MODEL   = os.environ.get("LOOP_MODEL",   os.environ.get("UPGRADER_MODEL",   "sonnet"))

CLAUDE_BIN     = os.environ.get("CLAUDE_BIN",   "claude")
CLAUDE_FLAGS   = os.environ.get("CLAUDE_FLAGS", "--dangerously-skip-permissions")
REMOTE_CONTROL = os.environ.get("REMOTE_CONTROL", "1") == "1"

OPENCODE_BIN    = os.environ.get("OPENCODE_BIN",    "/home/loops/.local/bin/opencode")
OPENCODE_SERVER = os.environ.get("OPENCODE_SERVER", "http://127.0.0.1:4096")

UPGRADER_ARGS = os.environ.get("UPGRADER_ARGS", "")

# ── helpers ───────────────────────────────────────────────────────────────────

def log(msg):
    ts = datetime.now().strftime("%H:%M:%S")
    print(f"[upgrader {ts}] {msg}", flush=True)

def die(msg):
    log(f"ERROR: {msg}")
    sys.exit(1)

def session_alive():
    return subprocess.run(
        ["tmux", "has-session", "-t", SESSION], capture_output=True
    ).returncode == 0

def session_busy():
    """True while a turn is actively in flight (not idle/finished/wedged)."""
    r = subprocess.run(["tmux", "capture-pane", "-pt", SESSION],
                       capture_output=True, text=True)
    pane = r.stdout if r.returncode == 0 else ""
    return bool(re.search(r"esc to interrupt|⠋|⠙|⠹|⠸|⠼|⠴|⠦|⠧|⠇|⠏|Running tool", pane))

def kill_session():
    subprocess.run(["tmux", "kill-session", "-t", SESSION], capture_output=True)

# ── kickoff prompt ────────────────────────────────────────────────────────────

def build_kickoff():
    args_note = f" with arguments: {UPGRADER_ARGS}" if UPGRADER_ARGS else ""
    return f"""\
*** cc-ci UPGRADER — weekly recipe-upgrade job ***
You are the cc-ci Upgrader: a ONE-SHOT job agent, NOT a perpetual loop. Run the
recipe-upgrade sequence to completion, then STOP. Your cwd is {WORKDIR}; reach the CI
server with `ssh cc-ci`; creds are in {WORKDIR}/.testenv; skills in {WORKDIR}/.claude/skills/.

DO THIS:
1. Invoke the /upgrade-all skill in DEFAULT mode{args_note}
   (read {WORKDIR}/.claude/skills/upgrade-all/SKILL.md for the full procedure). It surveys
   every enrolled recipe and, for each upgradeable one, runs /recipe-upgrade in DEFAULT
   mode — recipe PR only, verified by posting `!testme` on the PR (results visible in the
   PR, iterate up to 3x). A genuinely stale test gets an explanatory PR COMMENT, never a
   test edit.
2. Process recipes via per-recipe SUBAGENTS so your own context stays light. If your
   context usage climbs (~80%), run /compact before continuing.
3. Write + push the weekly summary (the PR list is the actionable output for the operator).
4. WHEN THE RUN IS COMPLETE: STOP. Print the final summary (lead with the PR list) and an
   `UPGRADE RUN COMPLETE` line, then go idle. Do NOT loop, do NOT re-run, and do NOT kill
   your own session — leave it up so the operator can review the output in the web UI.
   Next week's run starts a fresh session (the launcher clears this idle one).

GUARDRAILS: NEVER merge any PR. NEVER weaken a test. DEFAULT mode only — do NOT pass
--with-tests (updating cc-ci tests is the operator's per-recipe opt-in). Single-writer:
dedicated branches + separate clones, never push main, never touch the build loops'
/cc-ci /cc-ci-adv clones. The shared Swarm is stateful — go sequentially.
"""

# ── launch ────────────────────────────────────────────────────────────────────

def start(mode="use-or-create"):
    import shutil
    if not shutil.which("tmux"):
        die("tmux not found")
    Path(LOG_DIR).mkdir(parents=True, exist_ok=True)

    if session_alive():
        if mode == "use-or-create" and session_busy():
            log(f"{SESSION} already running a job (busy) — leaving it")
            return
        log(f"{SESSION} exists but idle/stale (or fresh requested) — killing it first")
        kill_session()
        import time; time.sleep(1)

    kf = Path(LOG_DIR) / f".kickoff-{SESSION}.txt"
    kf.write_text(build_kickoff())

    model_flag = f"--model '{MODEL}'" if MODEL else ""
    log(f"starting {SESSION} (backend={BACKEND}, model={MODEL}, args='{UPGRADER_ARGS or '<none>'}')")

    if BACKEND == "claude":
        if not shutil.which(CLAUDE_BIN):
            die(f"claude CLI not found — set CLAUDE_BIN (currently: {CLAUDE_BIN})")
        rc  = f"--remote-control '{SESSION}'" if REMOTE_CONTROL else ""
        cmd = f"{CLAUDE_BIN} {rc} {model_flag} {CLAUDE_FLAGS} \"$(cat '{kf}')\""

    elif BACKEND == "opencode":
        if not Path(OPENCODE_BIN).exists():
            die(f"opencode not found at {OPENCODE_BIN}")
        cmd = (
            f"set -a; . /srv/cc-ci/.testenv; set +a; "
            f"{OPENCODE_BIN} {model_flag} run --attach '{OPENCODE_SERVER}' "
            f"--title '{SESSION}' \"$(cat '{kf}')\""
        )
        log(f"  visible at http://oc.commoninternet.net (tailnet only)")
    else:
        die(f"unknown LOOP_BACKEND '{BACKEND}' — use 'claude' or 'opencode'")

    subprocess.run(["tmux", "new-session", "-d", "-s", SESSION, "-c", WORKDIR, cmd])
    subprocess.run(["tmux", "pipe-pane", "-o", "-t", SESSION,
                    f"cat >> '{LOG_DIR}/{SESSION}.log'"])
    log(f"started. attach: tmux attach -t {SESSION}  log: {LOG_DIR}/{SESSION}.log")

# ── main ──────────────────────────────────────────────────────────────────────

def main():
    cmd = sys.argv[1] if len(sys.argv) > 1 else "start"

    if cmd == "start":
        start("use-or-create")
    elif cmd == "fresh":
        start("fresh")
    elif cmd == "stop":
        if session_alive():
            log(f"killing {SESSION}")
            kill_session()
        else:
            log(f"{SESSION} not running")
    elif cmd == "status":
        if session_alive():
            busy = "busy" if session_busy() else "idle/finishing"
            log(f"{SESSION}: RUNNING ({busy})")
            subprocess.run(
                f"ps -eo pid,etime,args | grep '[r]emote-control {SESSION}' || true",
                shell=True)
        else:
            log(f"{SESSION}: stopped")
        log(f"backend: {BACKEND}  model: {MODEL}  args: '{UPGRADER_ARGS or '<none>'}'")
    elif cmd == "attach":
        os.execvp("tmux", ["tmux", "attach", "-t", SESSION])
    else:
        print(f"""cc-ci upgrader launcher — one-shot weekly recipe-upgrade job

  launch-upgrader.py start    use-or-create (leave busy run alone, else start fresh)
  launch-upgrader.py fresh    always kill existing + start fresh
  launch-upgrader.py stop     kill the session
  launch-upgrader.py status   show session state
  launch-upgrader.py attach   tmux attach

Backend: {BACKEND}  (LOOP_BACKEND or UPGRADER_BACKEND env var)
Model:   {MODEL}  (LOOP_MODEL or UPGRADER_MODEL env var)
Args:    {UPGRADER_ARGS or '<none>'}  (UPGRADER_ARGS env var, passed to /upgrade-all)

claude:   viewable at claude.ai/code
opencode: viewable at http://oc.commoninternet.net  server={OPENCODE_SERVER}
""")


if __name__ == "__main__":
    main()