refactor: split services/docker.py into docker/ package

Split monolithic docker.py into focused modules:
- docker/compose.py — compose generation, execute_compose_command, volume sorting
- docker/container.py — container status, IP, logs, network, port finding
- docker/config_staging.py — instance dir, env file, config file staging
- docker/tunnel.py — cloudflared tunnel lifecycle (moved from services/tunnel.py)
- docker/__init__.py — re-exports all public symbols for backward compatibility
- services/tunnel.py — thin re-export wrapper for backward compatibility

Also includes schema extraction files created in prior work:
- schemas/config/config_profile.py
- schemas/project/*.py
- schemas/system/health.py
- schemas/tool/*.py
- schemas/user/*.py

All existing imports like 'from src.services.docker import X' and
'from src.services.tunnel import X' continue to work unchanged.

Quality gates: py_compile passed, ruff passed, import test passed.
This commit is contained in:
2026-06-04 10:12:41 +02:00
parent 0591b00ded
commit 6104f592eb
16 changed files with 1285 additions and 451 deletions
+55
View File
@@ -0,0 +1,55 @@
"""Docker services package for container and compose operations."""
from src.services.docker.compose import (
execute_compose_command,
render_compose_template,
sort_volumes_by_specificity,
write_compose_file,
)
from src.services.docker.config_staging import (
ensure_instance_directory,
write_config_files,
write_env_file,
)
from src.services.docker.container import (
connect_container_to_network,
find_free_port,
get_backend_network_name,
get_container_id,
get_container_ip_on_network,
get_container_logs,
get_container_name,
get_container_status,
is_container_on_network,
wait_for_container_running,
)
from src.services.docker.tunnel import (
check_tunnel_health,
recreate_tunnel,
start_tunnel,
stop_tunnel,
)
__all__ = [
"check_tunnel_health",
"connect_container_to_network",
"ensure_instance_directory",
"execute_compose_command",
"find_free_port",
"get_backend_network_name",
"get_container_id",
"get_container_ip_on_network",
"get_container_logs",
"get_container_name",
"get_container_status",
"is_container_on_network",
"recreate_tunnel",
"render_compose_template",
"sort_volumes_by_specificity",
"start_tunnel",
"stop_tunnel",
"wait_for_container_running",
"write_compose_file",
"write_config_files",
"write_env_file",
]
+120
View File
@@ -0,0 +1,120 @@
"""Docker Compose file generation and manipulation."""
import logging
import subprocess
from collections import Counter
from pathlib import Path
from typing import Any
logger = logging.getLogger(__name__)
def sort_volumes_by_specificity(volumes: list[str]) -> list[str]:
"""Sort volume strings so parent paths come before child paths.
Docker Compose mounts volumes in array order. A later mount at a parent
path hides earlier mounts at child paths. By sorting shallow paths first
and deep paths last, deeper (more specific) mounts overlay correctly.
Volume format: source:target or source:target:type
Args:
volumes: List of Docker volume mount strings.
Returns:
Sorted list with parent paths before child paths.
"""
def _target_depth(vol: str) -> int:
parts = vol.split(":")
if len(parts) < 2:
return 0
target = parts[1].rstrip("/")
if not target or target == "/":
return 0
return target.count("/")
# Detect duplicate targets and warn
targets = []
for vol in volumes:
parts = vol.split(":")
targets.append(parts[1] if len(parts) > 1 else "")
dupes = [t for t, c in Counter(targets).items() if c > 1]
if dupes:
logger.warning("Duplicate mount targets detected: %s", dupes)
# Stable sort: parent paths first, child paths last
return sorted(volumes, key=_target_depth)
def render_compose_template(template: str, variables: dict[str, Any]) -> str:
"""Render a Docker Compose template with variable substitution.
Args:
template: The compose template string
variables: Dictionary of variable names to values
Returns:
Rendered compose file content
"""
result = template
for key, value in variables.items():
placeholder = f"{{{{{key}}}}}"
result = result.replace(placeholder, str(value))
return result
def write_compose_file(instance_dir: str, content: str) -> str:
"""Write the rendered compose file to the instance directory.
Args:
instance_dir: Path to instance directory
content: Rendered compose content
Returns:
Path to the compose file
"""
compose_path = Path(instance_dir) / "docker-compose.yml"
compose_path.write_text(content)
return str(compose_path)
def execute_compose_command(
compose_path: str, action: str, timeout: int = 60, env_file: str | None = None
) -> tuple[int, str, str]:
"""Execute a docker compose command.
Args:
compose_path: Path to docker-compose.yml
action: The compose action (up, down, start, stop, restart)
timeout: Command timeout in seconds
env_file: Optional path to .env file for environment variables
Returns:
Tuple of (returncode, stdout, stderr)
"""
instance_dir = Path(compose_path).parent
cmd = ["docker", "compose", "-f", compose_path]
if env_file:
cmd.extend(["--env-file", env_file])
if action == "up":
cmd.extend(["up", "-d", "--force-recreate"])
elif action == "down":
cmd.extend(["down", "-v"])
elif action in ("start", "stop", "restart"):
cmd.append(action)
else:
raise ValueError(f"Unknown compose action: {action}")
result = subprocess.run(
cmd,
cwd=str(instance_dir),
capture_output=True,
text=True,
timeout=timeout,
)
return result.returncode, result.stdout, result.stderr
@@ -0,0 +1,61 @@
"""Staging configuration files into instance directories."""
import logging
from pathlib import Path
logger = logging.getLogger(__name__)
def ensure_instance_directory(instance_id: str, base_path: str | None = None) -> str:
"""Create and return the instance directory path.
Args:
instance_id: Unique instance identifier
base_path: Base directory for all instances (defaults to Settings.instance_base_path)
Returns:
Absolute path to instance directory
"""
if base_path is None:
from src.config import Settings
base_path = Settings().instance_base_path
instance_dir = Path(base_path) / instance_id
instance_dir.mkdir(parents=True, exist_ok=True)
return str(instance_dir.absolute())
def write_env_file(instance_dir: str, env_vars: dict[str, str]) -> str:
"""Write environment variables to a .env file.
Args:
instance_dir: Path to instance directory
env_vars: Dictionary of env var names to values
Returns:
Path to the env file
"""
env_path = Path(instance_dir) / ".env"
lines = [f'{key}="{value}"' for key, value in env_vars.items()]
env_path.write_text("\n".join(lines) + "\n")
return str(env_path)
def write_config_files(instance_dir: str, files: dict[str, str]) -> None:
"""Write config files to the instance directory.
Args:
instance_dir: Path to instance directory
files: Dictionary of file paths (relative to instance dir) to content
"""
instance_path = Path(instance_dir)
for file_path, content in files.items():
# Ensure the path is within the instance directory (security)
full_path = instance_path / file_path
try:
full_path.resolve().relative_to(instance_path.resolve())
except ValueError:
raise ValueError(f"File path '{file_path}' escapes instance directory")
full_path.parent.mkdir(parents=True, exist_ok=True)
full_path.write_text(content)
+316
View File
@@ -0,0 +1,316 @@
"""Docker container runtime queries and network management."""
import logging
import subprocess
import time
from typing import Any
logger = logging.getLogger(__name__)
def get_container_id(instance_name: str) -> str | None:
"""Get the container ID for a compose service.
Uses exact name matching to avoid substring collisions with tunnel
containers (e.g. tunnel-code-server-... matching code-server-...).
Falls back to case-insensitive matching since Docker DNS is case-
insensitive but docker inspect is case-sensitive.
Args:
instance_name: The expected container name.
Returns:
Container ID or None if not found.
"""
expected = instance_name.lower()
# Fast path: exact match via docker inspect
result = subprocess.run(
["docker", "inspect", "-f", "{{.Id}}", expected],
capture_output=True,
text=True,
)
if result.returncode == 0 and result.stdout.strip():
return result.stdout.strip()
# Fallback: list all containers and do case-insensitive exact match
ps_result = subprocess.run(
["docker", "ps", "-a", "--format", "{{.Names}}\t{{.ID}}"],
capture_output=True,
text=True,
)
if ps_result.returncode == 0:
for line in ps_result.stdout.strip().splitlines():
parts = line.split("\t")
if len(parts) == 2:
name, cid = parts
if name.lower() == expected:
return cid
return None
def get_container_name(instance_name: str) -> str | None:
"""Get the full container name for a compose service.
Uses exact name matching via docker inspect to avoid substring collisions.
Args:
instance_name: The exact container name (case-insensitive for Docker).
Returns:
Container name or None if not found.
"""
result = subprocess.run(
["docker", "inspect", "-f", "{{.Name}}", instance_name.lower()],
capture_output=True,
text=True,
)
if result.returncode == 0 and result.stdout.strip():
return result.stdout.strip().lstrip("/")
return None
def get_backend_network_name() -> str:
"""Auto-detect the actual Docker network name for the backend network.
Docker Compose prefixes network names with the project directory name
(e.g. 'headquarter_backend' instead of 'backend'). We inspect the API
container itself to find the real network name it's connected to.
Returns:
The actual Docker network name, or 'backend' as fallback.
"""
# Try to find the API container by its known name
api_container = "hq-api"
result = subprocess.run(
[
"docker",
"inspect",
"-f",
"{{range $k, $v := .NetworkSettings.Networks}}{{$k}} {{end}}",
api_container,
],
capture_output=True,
text=True,
)
if result.returncode == 0 and result.stdout.strip():
networks = result.stdout.strip().split()
for net in networks:
if "backend" in net.lower():
return net
# API container is on some network — return the first one
return networks[0]
return "backend"
def connect_container_to_network(
container_name: str, network_name: str | None = None
) -> bool:
"""Connect a Docker container to an existing network.
Args:
container_name: Name or ID of the container
network_name: Name of the Docker network. If None, auto-detects
from the API container's own network membership.
Returns:
True if successful, False otherwise
"""
if network_name is None:
network_name = get_backend_network_name()
result = subprocess.run(
["docker", "network", "connect", network_name, container_name],
capture_output=True,
text=True,
)
return result.returncode == 0
def get_container_ip_on_network(
container_id: str, network_name: str | None = None
) -> str | None:
"""Get a container's IP address on a specific Docker network.
Args:
container_id: Docker container ID or name.
network_name: Network name. If None, auto-detects from the API container.
Returns:
IP address string, or None if the container is not on that network.
"""
if network_name is None:
network_name = get_backend_network_name()
result = subprocess.run(
[
"docker",
"inspect",
"-f",
f"{{{{.NetworkSettings.Networks.{network_name}.IPAddress}}}}",
container_id,
],
capture_output=True,
text=True,
)
if result.returncode == 0:
ip = result.stdout.strip()
if ip and ip != "<no value>":
return ip
return None
def is_container_on_network(container_id: str, network_name: str | None = None) -> bool:
"""Check whether a container is already attached to a Docker network.
Args:
container_id: Docker container ID or name.
network_name: Network name. If None, auto-detects from the API container.
Returns:
True if the container is on the network.
"""
if network_name is None:
network_name = get_backend_network_name()
result = subprocess.run(
[
"docker",
"inspect",
"-f",
f"{{{{.NetworkSettings.Networks.{network_name}}}}}",
container_id,
],
capture_output=True,
text=True,
)
return result.returncode == 0 and "<no value>" not in result.stdout
def get_container_status(container_id: str) -> dict[str, Any]:
"""Get the status of a Docker container.
Args:
container_id: Docker container ID
Returns:
Dict with 'status' (running, exited, restarting, not_found),
'exit_code' (int or None), and 'health' (health status or None)
"""
result = subprocess.run(
[
"docker",
"inspect",
"-f",
"{{.State.Status}}|{{.State.ExitCode}}|{{if .State.Health}}{{.State.Health.Status}}{{else}}none{{end}}",
container_id,
],
capture_output=True,
text=True,
)
if result.returncode != 0:
return {"status": "not_found", "exit_code": None, "health": None}
parts = result.stdout.strip().split("|")
status = parts[0] if parts else "unknown"
exit_code = int(parts[1]) if len(parts) > 1 and parts[1].isdigit() else None
health = parts[2] if len(parts) > 2 and parts[2] != "none" else None
return {"status": status, "exit_code": exit_code, "health": health}
def wait_for_container_running(
container_id: str, timeout: int = 30, interval: float = 2.0
) -> dict[str, Any]:
"""Wait for a container to reach the running state.
Polls docker inspect until the container status is "running" or timeout.
Args:
container_id: Docker container ID
timeout: Maximum seconds to wait
interval: Seconds between polls
Returns:
Dict with 'success' (bool), 'status' (str), 'exit_code' (int or None),
and 'waited_seconds' (float)
"""
start_time = time.time()
while time.time() - start_time < timeout:
info = get_container_status(container_id)
if info["status"] == "running":
return {
"success": True,
"status": "running",
"exit_code": None,
"waited_seconds": time.time() - start_time,
}
if info["status"] == "exited":
return {
"success": False,
"status": "exited",
"exit_code": info["exit_code"],
"waited_seconds": time.time() - start_time,
}
if info["status"] == "not_found":
return {
"success": False,
"status": "not_found",
"exit_code": None,
"waited_seconds": time.time() - start_time,
}
time.sleep(interval)
# Timeout reached
info = get_container_status(container_id)
return {
"success": False,
"status": info["status"],
"exit_code": info["exit_code"],
"waited_seconds": time.time() - start_time,
}
def get_container_logs(container_id: str, tail: int = 100) -> str:
"""Get the logs of a Docker container.
Args:
container_id: Docker container ID
tail: Number of lines to return
Returns:
Container logs
"""
result = subprocess.run(
["docker", "logs", "--tail", str(tail), container_id],
capture_output=True,
text=True,
)
if result.returncode == 0:
return result.stdout
return f"Failed to get logs: {result.stderr}"
def find_free_port(start: int = 10000, end: int = 20000) -> int:
"""Find a free TCP port in the given range.
Args:
start: Start of port range
end: End of port range
Returns:
Free port number
"""
import socket
for port in range(start, end):
with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s:
if s.connect_ex(("localhost", port)) != 0:
return port
raise RuntimeError(f"No free port found in range {start}-{end}")
+281
View File
@@ -0,0 +1,281 @@
"""Cloudflare tunnel management using cloudflared Docker containers.
Each tunnel runs as a Docker container on the same 'backend' network as the API.
cloudflared connects to the tool container by its Docker Compose service name
(e.g. http://code-server-headquarter-34837cd3:8443).
"""
import logging
import re
import subprocess
from typing import Any
from src.services.docker.container import get_backend_network_name
logger = logging.getLogger(__name__)
TUNNEL_IMAGE = "cloudflare/cloudflared:latest"
def _tunnel_container_name(instance_name: str) -> str:
return f"tunnel-{instance_name.lower()}"
def _ensure_image() -> None:
"""Pull cloudflared image if not already present."""
result = subprocess.run(
["docker", "images", "-q", TUNNEL_IMAGE],
capture_output=True,
text=True,
)
if not result.stdout.strip():
logger.info("Pulling %s ...", TUNNEL_IMAGE)
pull = subprocess.run(
["docker", "pull", TUNNEL_IMAGE],
capture_output=True,
text=True,
)
if pull.returncode != 0:
logger.warning("Failed to pull %s: %s", TUNNEL_IMAGE, pull.stderr)
def _cleanup_stale_tunnel(tunnel_name: str) -> None:
"""Remove any existing tunnel container with this name."""
subprocess.run(
["docker", "stop", "-t", "3", tunnel_name],
capture_output=True,
text=True,
)
subprocess.run(
["docker", "rm", "-f", tunnel_name],
capture_output=True,
text=True,
)
def _get_tunnel_logs(tunnel_name: str) -> tuple[str, str]:
"""Get stdout and stderr logs from a container."""
result = subprocess.run(
["docker", "logs", tunnel_name],
capture_output=True,
text=True,
)
return result.stdout, result.stderr
def _get_tunnel_exit_code(tunnel_name: str) -> int | None:
"""Get exit code of a container if it has exited."""
result = subprocess.run(
["docker", "inspect", "-f", "{{.State.ExitCode}}", tunnel_name],
capture_output=True,
text=True,
)
if result.returncode == 0:
try:
return int(result.stdout.strip())
except ValueError:
pass
return None
def start_tunnel(
instance_name: str,
container_port: int,
timeout: int = 30,
target_url: str | None = None,
) -> dict[str, str]:
"""Start a temporary Cloudflare tunnel for an instance.
Args:
instance_name: The tool instance name (used for tunnel naming).
container_port: The port the tool container listens on internally.
timeout: Seconds to wait for the tunnel URL.
target_url: Optional explicit URL to proxy to. If omitted, derives
http://{instance_name.lower()}:{container_port}.
Returns:
Dict with 'url' and 'container_name'.
"""
_ensure_image()
tunnel_name = _tunnel_container_name(instance_name)
_cleanup_stale_tunnel(tunnel_name)
# Target the tool container by name on the backend network
if target_url is None:
target_url = f"http://{instance_name.lower()}:{container_port}"
cmd = [
"docker",
"run",
"-d",
"--network",
get_backend_network_name(),
"--name",
tunnel_name,
TUNNEL_IMAGE,
"tunnel",
"--no-autoupdate",
"--url",
target_url,
]
logger.debug("Running: %s", " ".join(cmd))
proc = subprocess.run(cmd, capture_output=True, text=True)
if proc.returncode != 0:
raise RuntimeError(
f"Failed to start tunnel container {tunnel_name}: {proc.stderr}"
)
container_id = proc.stdout.strip()
logger.debug("Tunnel container started: %s", container_id)
# Wait for URL to appear in logs
# Exclude api.trycloudflare.com which is the Cloudflare API endpoint,
# not a tunnel URL. Real tunnel URLs have random subdomains (10+ chars).
url_pattern = re.compile(r"https://(?!api\.)[a-z0-9-]{10,}\.trycloudflare\.com")
start_time = __import__("time").time()
url: str | None = None
combined_logs = ""
while __import__("time").time() - start_time < timeout:
stdout, stderr = _get_tunnel_logs(tunnel_name)
combined_logs = stdout + "\n" + stderr
match = url_pattern.search(combined_logs)
if match:
url = match.group(0)
break
# Check if container exited early
exit_code = _get_tunnel_exit_code(tunnel_name)
if exit_code is not None and exit_code != 0:
_cleanup_stale_tunnel(tunnel_name)
raise RuntimeError(
f"Tunnel container {tunnel_name} exited with code {exit_code}. "
f"Logs:\n{combined_logs[-3000:]}"
)
__import__("time").sleep(0.5)
if not url:
stdout, stderr = _get_tunnel_logs(tunnel_name)
combined_logs = stdout + "\n" + stderr
exit_code = _get_tunnel_exit_code(tunnel_name)
_cleanup_stale_tunnel(tunnel_name)
raise RuntimeError(
f"Tunnel {tunnel_name} did not produce a URL within {timeout}s. "
f"Exit code: {exit_code}. Logs:\n{combined_logs[-3000:]}"
)
# Wait a moment for Cloudflare DNS edge to propagate the new tunnel subdomain
__import__("time").sleep(2)
logger.info(
"Tunnel %s started for %s%s (%s)",
tunnel_name,
instance_name,
target_url,
url,
)
return {"url": url, "container_name": tunnel_name}
def stop_tunnel(instance_name: str) -> None:
"""Stop and remove the tunnel container for an instance."""
tunnel_name = _tunnel_container_name(instance_name)
_cleanup_stale_tunnel(tunnel_name)
logger.debug("Stopped and removed tunnel container %s", tunnel_name)
def recreate_tunnel(
instance_name: str, container_port: int, target_url: str | None = None
) -> dict[str, str]:
"""Recreate a tunnel for an instance.
Args:
instance_name: The tool instance name.
container_port: The port the tool container listens on internally.
target_url: Optional explicit origin URL. If omitted, derives
http://{instance_name.lower()}:{container_port}.
"""
stop_tunnel(instance_name)
return start_tunnel(instance_name, container_port, target_url=target_url)
def check_tunnel_health(url: str, timeout: int = 10) -> dict[str, Any]:
"""Check if a tunnel URL is healthy.
Returns:
Dict with 'tunnel_status', 'status_code', 'healthy', 'error'.
"""
try:
result = subprocess.run(
[
"curl",
"-s",
"-o",
"/dev/null",
"-w",
"%{http_code}",
"--max-time",
str(timeout),
url,
],
capture_output=True,
text=True,
timeout=timeout + 5,
)
status_code = int(result.stdout.strip())
if 200 <= status_code < 400:
return {
"tunnel_status": "healthy",
"status_code": status_code,
"healthy": True,
"error": None,
}
if status_code in (502, 503, 504):
return {
"tunnel_status": "error_response",
"status_code": status_code,
"healthy": False,
"error": f"Application returned HTTP {status_code}",
}
return {
"tunnel_status": "error_response",
"status_code": status_code,
"healthy": False,
"error": f"HTTP {status_code}",
}
except subprocess.TimeoutExpired:
return {
"tunnel_status": "unreachable",
"status_code": None,
"healthy": False,
"error": "Tunnel request timed out",
}
except (ValueError, Exception) as exc:
error_str = str(exc).lower()
if any(
err in error_str
for err in [
"connection refused",
"econnrefused",
"could not resolve",
"nodename",
]
):
return {
"tunnel_status": "unreachable",
"status_code": None,
"healthy": False,
"error": f"Tunnel unreachable: {exc}",
}
return {
"tunnel_status": "unreachable",
"status_code": None,
"healthy": False,
"error": str(exc),
}