Files
the-nexus/mimo-swarm/scripts/worker-runner.py
Alexander Whitestone dbad1cdf0b
Some checks failed
CI / test (pull_request) Failing after 9s
CI / validate (pull_request) Failing after 14s
Review Approval Gate / verify-review (pull_request) Failing after 3s
fix: closes #1277
2026-04-12 19:27:19 -04:00

235 lines
8.1 KiB
Python
Executable File

#!/usr/bin/env python3
"""
Worker Runner — actual worker that picks up prompts and runs mimo via hermes CLI.
This is what the cron jobs SHOULD call instead of asking the LLM to check files.
"""
import os
import sys
import glob
import subprocess
import json
from datetime import datetime, timezone
STATE_DIR = os.path.expanduser("~/.hermes/mimo-swarm/state")
LOG_DIR = os.path.expanduser("~/.hermes/mimo-swarm/logs")
def log(msg):
ts = datetime.now(timezone.utc).strftime("%Y-%m-%dT%H:%M:%SZ")
print(f"[{ts}] {msg}")
log_file = os.path.join(LOG_DIR, f"runner-{datetime.now().strftime('%Y%m%d')}.log")
with open(log_file, "a") as f:
f.write(f"[{ts}] {msg}\n")
def write_result(worker_id, status, repo=None, issue=None, branch=None, pr=None, error=None):
"""Write a result file — always, even on failure."""
result_file = os.path.join(STATE_DIR, f"result-{worker_id}.json")
data = {
"status": status,
"worker": worker_id,
"timestamp": datetime.now(timezone.utc).isoformat(),
}
if repo: data["repo"] = repo
if issue: data["issue"] = int(issue) if str(issue).isdigit() else issue
if branch: data["branch"] = branch
if pr: data["pr"] = pr
if error: data["error"] = error
with open(result_file, "w") as f:
json.dump(data, f)
def get_oldest_prompt():
"""Get the oldest prompt file with file locking (atomic rename)."""
prompts = sorted(glob.glob(os.path.join(STATE_DIR, "prompt-*.txt")))
if not prompts:
return None
# Prefer non-review prompts
impl = [p for p in prompts if "review" not in os.path.basename(p)]
target = impl[0] if impl else prompts[0]
# Atomic claim: rename to .processing
claimed = target + ".processing"
try:
os.rename(target, claimed)
return claimed
except OSError:
# Another worker got it first
return None
def run_worker(prompt_file):
"""Run the worker: read prompt, execute via hermes, create PR."""
worker_id = os.path.basename(prompt_file).replace("prompt-", "").replace(".txt", "")
with open(prompt_file) as f:
prompt = f.read()
# Extract repo and issue from prompt
repo = None
issue = None
for line in prompt.split("\n"):
if line.startswith("Repository:"):
repo = line.split(":", 1)[1].strip()
if line.startswith("Issue:"):
issue = line.split("#", 1)[1].strip() if "#" in line else line.split(":", 1)[1].strip()
log(f"Worker {worker_id}: repo={repo}, issue={issue}")
if not repo or not issue:
log(f" SKIPPING: couldn't parse repo/issue from prompt")
write_result(worker_id, "parse_error", error="could not parse repo/issue from prompt")
os.remove(prompt_file)
return False
# Clone/pull the repo — unique workspace per worker
import tempfile
work_dir = tempfile.mkdtemp(prefix=f"mimo-{worker_id}-")
clone_url = f"https://forge.alexanderwhitestone.com/{repo}.git"
branch = f"mimo/{worker_id.split('-')[1] if '-' in worker_id else 'code'}/issue-{issue}"
log(f" Workspace: {work_dir}")
result = subprocess.run(
["git", "clone", clone_url, work_dir],
capture_output=True, text=True, timeout=120
)
if result.returncode != 0:
log(f" CLONE FAILED: {result.stderr[:200]}")
write_result(worker_id, "clone_failed", repo=repo, issue=issue, error=result.stderr[:200])
os.remove(prompt_file)
return False
# Checkout branch
subprocess.run(["git", "fetch", "origin", "main"], cwd=work_dir, capture_output=True, timeout=60)
subprocess.run(["git", "checkout", "main"], cwd=work_dir, capture_output=True, timeout=30)
subprocess.run(["git", "pull"], cwd=work_dir, capture_output=True, timeout=30)
subprocess.run(["git", "checkout", "-b", branch], cwd=work_dir, capture_output=True, timeout=30)
# Run mimo via hermes CLI
log(f" Dispatching to hermes (nous/mimo-v2-pro)...")
result = subprocess.run(
["hermes", "chat", "-q", prompt, "--provider", "nous", "-m", "xiaomi/mimo-v2-pro",
"--yolo", "-t", "terminal,code_execution", "-Q"],
capture_output=True, text=True, timeout=900, # 15 min timeout
cwd=work_dir
)
log(f" Hermes exit: {result.returncode}")
log(f" Output: {result.stdout[-500:]}")
# Check for changes
status = subprocess.run(
["git", "status", "--porcelain"],
capture_output=True, text=True, cwd=work_dir
)
if not status.stdout.strip():
# Check for commits
log_count = subprocess.run(
["git", "log", "main..HEAD", "--oneline"],
capture_output=True, text=True, cwd=work_dir
)
if not log_count.stdout.strip():
log(f" NO CHANGES — abandoning")
# Release the claim
token = open(os.path.expanduser("~/.config/gitea/token")).read().strip()
import urllib.request
try:
req = urllib.request.Request(
f"https://forge.alexanderwhitestone.com/api/v1/repos/{repo}/issues/{issue}/labels/mimo-claimed",
headers={"Authorization": f"token {token}"},
method="DELETE"
)
urllib.request.urlopen(req, timeout=10)
except:
pass
write_result(worker_id, "abandoned", repo=repo, issue=issue, error="no changes produced")
if os.path.exists(prompt_file):
os.remove(prompt_file)
return False
# Commit dirty files (salvage)
if status.stdout.strip():
subprocess.run(["git", "add", "-A"], cwd=work_dir, capture_output=True, timeout=30)
subprocess.run(
["git", "commit", "-m", f"WIP: issue #{issue} (mimo swarm)"],
cwd=work_dir, capture_output=True, timeout=30
)
# Push
log(f" Pushing {branch}...")
push = subprocess.run(
["git", "push", "origin", branch],
capture_output=True, text=True, cwd=work_dir, timeout=60
)
if push.returncode != 0:
log(f" Push failed, trying force...")
subprocess.run(
["git", "push", "-f", "origin", branch],
capture_output=True, text=True, cwd=work_dir, timeout=60
)
# Create PR via API
token = open(os.path.expanduser("~/.config/gitea/token")).read().strip()
import urllib.request
# Get issue title
try:
req = urllib.request.Request(
f"https://forge.alexanderwhitestone.com/api/v1/repos/{repo}/issues/{issue}",
headers={"Authorization": f"token {token}", "Accept": "application/json"}
)
with urllib.request.urlopen(req, timeout=15) as resp:
issue_data = json.loads(resp.read())
title = issue_data.get("title", f"Issue #{issue}")
except:
title = f"Issue #{issue}"
pr_body = json.dumps({
"title": f"fix: {title}",
"head": branch,
"base": "main",
"body": f"Closes #{issue}\n\nAutomated by mimo-v2-pro swarm.\nWorker: {worker_id}"
}).encode()
try:
req = urllib.request.Request(
f"https://forge.alexanderwhitestone.com/api/v1/repos/{repo}/pulls",
data=pr_body,
headers={
"Authorization": f"token {token}",
"Content-Type": "application/json"
},
method="POST"
)
with urllib.request.urlopen(req, timeout=30) as resp:
pr_data = json.loads(resp.read())
pr_num = pr_data.get("number", "?")
log(f" PR CREATED: #{pr_num}")
except Exception as e:
log(f" PR FAILED: {e}")
pr_num = "?"
# Write result
write_result(worker_id, "completed", repo=repo, issue=issue, branch=branch, pr=pr_num)
# Remove prompt
# Remove prompt file (handles .processing extension)
if os.path.exists(prompt_file):
os.remove(prompt_file)
log(f" DONE — prompt removed")
return True
if __name__ == "__main__":
prompt = get_oldest_prompt()
if not prompt:
print("No prompts in queue")
sys.exit(0)
print(f"Processing: {os.path.basename(prompt)}")
success = run_worker(prompt)
sys.exit(0 if success else 1)