feat: proper logging architecture — Docker rotation, persisted service logs, verbosity config

docker-compose.yml:
- Add json-file logging driver (max-size: 10m, max-file: 5) to all 13 containers
- Docker now owns container stdout/stderr rotation automatically
- Add ./data/logs:/app/api/data/logs volume to API — service logs now persist across restarts

log_manager.py:
- Remove container log collection hack (Docker handles it natively)
- Add set_service_level(service, level) — change log level at runtime without restart
- Add get_service_levels() — return current per-service levels
- Simplify get_all_log_file_infos to return only service log files

app.py:
- Add GET /api/logs/verbosity — return current per-service log levels
- Add PUT /api/logs/verbosity — update levels at runtime, persist to config/log_levels.json
- Load persisted log level overrides at startup from log_levels.json
- Simplify rotate endpoint (service logs only, container logs owned by Docker)

wireguard_manager.py:
- get_keys(): return empty strings if key files don't exist (prevents get_status crash
  when wg0.conf is missing at startup and falls through to generate_config)

Logs page (4 tabs):
- API Service Logs: structured JSON logs from Python managers, with search/filter/rotate panel
- Container Logs: live docker logs (read via existing /api/containers/<name>/logs endpoint)
- Verbosity Config: per-service level dropdowns, apply immediately + persist
- Health History: existing health poll table

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-04-21 02:07:57 -04:00
parent 7b39331417
commit f848a1d056
6 changed files with 313 additions and 289 deletions
+19 -72
View File
@@ -498,88 +498,35 @@ class LogManager:
except Exception as e:
return {'error': str(e)}
def collect_container_logs(self, container_name: str, docker_client=None) -> int:
"""Append new docker container stdout/stderr to a persistent log file.
Returns number of new lines written, or -1 on error."""
def set_service_level(self, service: str, level: str):
"""Change log level for a service at runtime."""
try:
import subprocess
log_file = self.log_dir / f'container_{container_name}.log'
# Determine --since timestamp from last line of existing file
since_arg = []
if log_file.exists() and log_file.stat().st_size > 0:
with open(log_file, 'r', encoding='utf-8', errors='ignore') as f:
for line in f:
pass
# Parse last timestamp from docker log line (format: 2006-01-02T15:04:05...)
ts_match = re.match(r'^(\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}\.\d+Z)', line.strip())
if ts_match:
since_arg = ['--since', ts_match.group(1)]
result = subprocess.run(
['docker', 'logs', '--timestamps'] + since_arg + [container_name],
capture_output=True, text=True, timeout=30
)
output = result.stdout + result.stderr
lines = [l for l in output.splitlines() if l.strip()]
if lines:
with open(log_file, 'a', encoding='utf-8') as f:
f.write('\n'.join(lines) + '\n')
return len(lines)
log_level = getattr(logging, level.upper(), logging.INFO)
if service in self.service_loggers:
self.service_loggers[service].setLevel(log_level)
if service in self.handlers and 'file' in self.handlers[service]:
self.handlers[service]['file'].setLevel(log_level)
logger.info(f"Set log level for {service} to {level}")
else:
logger.warning(f"Service logger not found: {service}")
except Exception as e:
logger.error(f"Error collecting container logs for {container_name}: {e}")
return -1
logger.error(f"Error setting log level for {service}: {e}")
def get_container_log_lines(self, container_name: str, lines: int = 100) -> List[str]:
"""Read last N lines from stored container log file."""
try:
log_file = self.log_dir / f'container_{container_name}.log'
if not log_file.exists():
return []
with open(log_file, 'r', encoding='utf-8', errors='ignore') as f:
all_lines = f.readlines()
return [l.rstrip() for l in all_lines[-lines:]] if lines > 0 else [l.rstrip() for l in all_lines]
except Exception as e:
logger.error(f"Error reading container log for {container_name}: {e}")
return []
def rotate_container_log(self, container_name: str):
"""Rotate a stored container log file."""
try:
log_file = self.log_dir / f'container_{container_name}.log'
if not log_file.exists():
return
# Find next available backup index
for i in range(1, self.backup_count + 1):
backup = self.log_dir / f'container_{container_name}.log.{i}'
if not backup.exists():
log_file.rename(backup)
logger.info(f"Rotated container log for {container_name}{backup.name}")
return
# All slots full — remove oldest, shift others
oldest = self.log_dir / f'container_{container_name}.log.{self.backup_count}'
oldest.unlink(missing_ok=True)
for i in range(self.backup_count - 1, 0, -1):
src = self.log_dir / f'container_{container_name}.log.{i}'
if src.exists():
src.rename(self.log_dir / f'container_{container_name}.log.{i + 1}')
log_file.rename(self.log_dir / f'container_{container_name}.log.1')
logger.info(f"Rotated container log for {container_name}")
except Exception as e:
logger.error(f"Error rotating container log for {container_name}: {e}")
def get_service_levels(self) -> Dict[str, str]:
"""Return current log level for each service logger."""
return {
svc: logging.getLevelName(lgr.level)
for svc, lgr in self.service_loggers.items()
}
def get_all_log_file_infos(self) -> List[Dict[str, Any]]:
"""Return size/mtime info for all log files (API service logs + container logs)."""
"""Return size/mtime info for all service log files."""
results = []
for log_file in sorted(self.log_dir.glob('*.log')):
try:
stat = log_file.stat()
name = log_file.stem # e.g. 'wireguard' or 'container_cell-api'
kind = 'container' if name.startswith('container_') else 'service'
label = name[len('container_'):] if kind == 'container' else name
results.append({
'name': name,
'label': label,
'kind': kind,
'name': log_file.stem,
'file': log_file.name,
'size': stat.st_size,
'modified': datetime.fromtimestamp(stat.st_mtime).isoformat(),