merge: integrate main restructuring into dev

- Resolve 57 merge conflicts from codebase restructure
- Port dev feature code to new directory structure:
  * Update import paths to use @/ aliases
  * Add backward-compatible API signatures (createInstance, startInstance, deleteInstance)
  * Add missing type exports (ProjectWithRepos, InstanceHealth, Branch, BranchesResponse)
  * Extend Session and GitRepository types for dev features
  * Extend TerminalComponent props for mobile terminal wrapper
  * Add missing icon names (bell, drag, undo)

Quality gates: tsc pass (0 errors), build pass, 127/131 tests pass
(4 pre-existing failures unrelated to merge)
This commit is contained in:
Developer
2026-06-03 09:23:06 +00:00
279 changed files with 24254 additions and 21693 deletions
+299
View File
@@ -0,0 +1,299 @@
"""Config profile business logic."""
import logging
import uuid
from fastapi import HTTPException, status
from sqlalchemy import select
from sqlalchemy.ext.asyncio import AsyncSession
from sqlalchemy.orm import selectinload
from src.models.config_include import ConfigInclude
from src.models.config_mount import ConfigMount
from src.models.config_profile import ConfigProfile
from src.models.tool_type import ToolType
from src.models.user_config import UserConfig
logger = logging.getLogger(__name__)
MAX_INCLUDES_DEPTH = 10
async def get_owned_profile(
profile_id: uuid.UUID,
user_id: uuid.UUID,
session: AsyncSession,
) -> ConfigProfile:
"""Fetch a config profile and verify ownership."""
profile = await session.get(ConfigProfile, profile_id)
if profile is None or profile.user_id != user_id:
raise HTTPException(
status_code=status.HTTP_404_NOT_FOUND,
detail="config profile not found",
)
return profile
async def _detect_cycle(
session: AsyncSession,
profile_id: uuid.UUID,
visited: set[uuid.UUID] | None = None,
depth: int = 0,
) -> bool:
"""Detect cycles in profile includes using DFS.
Returns True if a cycle is detected.
"""
if depth > MAX_INCLUDES_DEPTH:
return True
if visited is None:
visited = set()
if profile_id in visited:
return True
visited.add(profile_id)
result = await session.execute(
select(ConfigInclude.included_profile_id).where(
ConfigInclude.profile_id == profile_id
)
)
included_ids = result.scalars().all()
for included_id in included_ids:
if await _detect_cycle(session, included_id, visited.copy(), depth + 1):
return True
return False
async def validate_includes_no_cycle(
session: AsyncSession,
profile_id: uuid.UUID,
new_included_id: uuid.UUID | None = None,
) -> None:
"""Validate that adding an include wouldn't create a cycle."""
if new_included_id and await _detect_cycle(session, new_included_id, {profile_id}):
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail="adding this include would create a circular reference",
)
# ---------------------------------------------------------------------------
# Profile CRUD helpers
# ---------------------------------------------------------------------------
async def check_duplicate_name(
session: AsyncSession,
user_id: uuid.UUID,
name: str,
exclude_id: uuid.UUID | None = None,
) -> None:
"""Raise 409 if a profile with the given name already exists."""
query = select(ConfigProfile).where(
ConfigProfile.user_id == user_id,
ConfigProfile.name == name,
)
if exclude_id:
query = query.where(ConfigProfile.id != exclude_id)
existing = await session.scalar(query)
if existing:
raise HTTPException(
status_code=status.HTTP_409_CONFLICT,
detail=f"config profile with name '{name}' already exists",
)
def profile_to_dict(profile: ConfigProfile) -> dict:
"""Serialize a ConfigProfile to a dict."""
return {
"id": str(profile.id),
"user_id": str(profile.user_id),
"name": profile.name,
"description": profile.description,
"created_at": profile.created_at.isoformat() if profile.created_at else None,
"updated_at": profile.updated_at.isoformat() if profile.updated_at else None,
}
# ---------------------------------------------------------------------------
# Include helpers
# ---------------------------------------------------------------------------
async def check_duplicate_include(
session: AsyncSession,
profile_id: uuid.UUID,
included_profile_id: uuid.UUID,
) -> None:
"""Raise 409 if the include already exists."""
existing = await session.scalar(
select(ConfigInclude).where(
ConfigInclude.profile_id == profile_id,
ConfigInclude.included_profile_id == included_profile_id,
)
)
if existing:
raise HTTPException(
status_code=status.HTTP_409_CONFLICT,
detail="this include already exists",
)
def include_to_dict(inc: ConfigInclude, included_name: str | None) -> dict:
"""Serialize a ConfigInclude to a dict."""
return {
"id": str(inc.id),
"profile_id": str(inc.profile_id),
"included_profile_id": str(inc.included_profile_id),
"included_profile_name": included_name,
"order_index": inc.order_index,
"created_at": inc.created_at.isoformat() if inc.created_at else None,
"updated_at": inc.updated_at.isoformat() if inc.updated_at else None,
}
# ---------------------------------------------------------------------------
# Mount helpers
# ---------------------------------------------------------------------------
async def check_duplicate_mount_path(
session: AsyncSession,
profile_id: uuid.UUID,
target_path: str,
exclude_id: uuid.UUID | None = None,
) -> None:
"""Raise 409 if a mount with the given path already exists."""
query = select(ConfigMount).where(
ConfigMount.profile_id == profile_id,
ConfigMount.target_path == target_path,
)
if exclude_id:
query = query.where(ConfigMount.id != exclude_id)
existing = await session.scalar(query)
if existing:
raise HTTPException(
status_code=status.HTTP_409_CONFLICT,
detail=f"mount with path '{target_path}' already exists",
)
def mount_to_dict(mount: ConfigMount) -> dict:
"""Serialize a ConfigMount to a dict."""
return {
"id": str(mount.id),
"profile_id": str(mount.profile_id),
"target_path": mount.target_path,
"files": mount.files,
"mode": mount.mode,
"order_index": mount.order_index,
"created_at": mount.created_at.isoformat() if mount.created_at else None,
"updated_at": mount.updated_at.isoformat() if mount.updated_at else None,
}
# ---------------------------------------------------------------------------
# Default profile helpers
# ---------------------------------------------------------------------------
async def get_or_create_user_config(
session: AsyncSession,
user_id: uuid.UUID,
) -> UserConfig:
"""Get existing user config or create a new one."""
result = await session.execute(select(UserConfig).where(UserConfig.user_id == user_id))
user_config = result.scalar_one_or_none()
if user_config is None:
user_config = UserConfig(user_id=user_id, config={})
session.add(user_config)
return user_config
async def validate_default_profiles(
session: AsyncSession,
user_id: uuid.UUID,
default_profiles: dict[str, str],
) -> None:
"""Validate that all profile IDs in default_profiles belong to the user."""
for tool_type_id, profile_id_str in default_profiles.items():
profile = await session.get(ConfigProfile, uuid.UUID(profile_id_str))
if profile is None:
raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail=f"profile {profile_id_str} not found")
if profile.user_id != user_id:
raise HTTPException(status_code=status.HTTP_403_FORBIDDEN, detail=f"profile {profile_id_str} does not belong to user")
async def get_default_profiles(
session: AsyncSession,
user_id: uuid.UUID,
) -> dict:
"""Get default profiles for a user."""
result = await session.execute(select(UserConfig).where(UserConfig.user_id == user_id))
user_config = result.scalar_one_or_none()
return {"default_profiles": user_config.default_profiles if user_config else {}}
async def set_default_profiles(
session: AsyncSession,
user_id: uuid.UUID,
default_profiles: dict[str, str],
) -> dict:
"""Set default profiles for a user."""
user_config = await get_or_create_user_config(session, user_id)
await validate_default_profiles(session, user_id, default_profiles)
user_config.config = {**user_config.config, "default_profiles": default_profiles}
await session.commit()
await session.refresh(user_config)
return {"default_profiles": user_config.default_profiles}
async def get_default_profile_for_tool_type(
session: AsyncSession,
user_id: uuid.UUID,
tool_type_id: str,
) -> dict:
"""Get default profile for a specific tool type."""
result = await session.execute(select(UserConfig).where(UserConfig.user_id == user_id))
user_config = result.scalar_one_or_none()
profile_id = user_config.default_profiles.get(tool_type_id) if user_config else None
return {"tool_type_id": tool_type_id, "profile_id": profile_id}
# ---------------------------------------------------------------------------
# Include list helper
# ---------------------------------------------------------------------------
async def list_includes_for_profile(
session: AsyncSession,
profile_id: uuid.UUID,
) -> dict:
"""List all includes for a profile."""
result = await session.execute(
select(ConfigInclude)
.where(ConfigInclude.profile_id == profile_id)
.order_by(ConfigInclude.order_index)
)
includes_data = []
for inc in result.scalars().all():
included_profile = await session.get(ConfigProfile, inc.included_profile_id)
includes_data.append(include_to_dict(inc, included_profile.name if included_profile else None))
return {"includes": includes_data}
# ---------------------------------------------------------------------------
# Mount list helper
# ---------------------------------------------------------------------------
async def list_mounts_for_profile(
session: AsyncSession,
profile_id: uuid.UUID,
) -> dict:
"""List all mounts for a profile."""
result = await session.execute(
select(ConfigMount)
.where(ConfigMount.profile_id == profile_id)
.order_by(ConfigMount.order_index)
)
return {"mounts": [mount_to_dict(m) for m in result.scalars().all()]}
-484
View File
@@ -1,484 +0,0 @@
"""Docker service for managing tool instances."""
import logging
import subprocess
import time
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 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_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 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)
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
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}")
+44
View File
@@ -0,0 +1,44 @@
"""Docker services for container and tunnel management."""
from .compose import (
ensure_instance_directory,
execute_compose_command,
render_compose_template,
write_compose_file,
write_env_file,
)
from .config_staging import write_config_files, write_config_folder_files
from .container import (
connect_container_to_network,
find_free_port,
get_container_id,
get_container_logs,
get_container_name,
get_container_status,
)
from .tunnel import (
check_tunnel_health,
recreate_tunnel,
start_cloudflared_tunnel,
stop_cloudflared_tunnel,
)
__all__ = [
"render_compose_template",
"ensure_instance_directory",
"write_compose_file",
"write_env_file",
"execute_compose_command",
"write_config_files",
"write_config_folder_files",
"get_container_id",
"get_container_name",
"connect_container_to_network",
"get_container_status",
"get_container_logs",
"find_free_port",
"start_cloudflared_tunnel",
"stop_cloudflared_tunnel",
"recreate_tunnel",
"check_tunnel_health",
]
+237
View File
@@ -0,0 +1,237 @@
"""Docker Compose file generation and command execution."""
import re
import subprocess
import uuid
from pathlib import Path
from typing import Any
from sqlalchemy import select
from sqlalchemy.ext.asyncio import AsyncSession
from src.models.config_profile import ConfigProfile
from src.models.tool_instance import ToolInstance
from src.services.profile_resolver import resolve_profile
def _sanitize_name(name: str) -> str:
"""Sanitize a string for use in Docker/container names."""
sanitized = re.sub(r"[^a-z0-9-]", "-", name.lower())
sanitized = re.sub(r"-+", "-", sanitized)
return sanitized.strip("-")
async def _generate_instance_name(
session: AsyncSession,
project_name: str,
tool_type_name: str,
) -> str:
"""Generate a unique instance name: project-tool-NUM."""
base = f"{_sanitize_name(project_name)}-{_sanitize_name(tool_type_name)}"
base = base.strip("-") or "instance"
result = await session.execute(
select(ToolInstance.name).where(ToolInstance.name.like(f"{base}-%"))
)
names = result.scalars().all()
max_num = 0
for name in names:
parts = name.rsplit("-", 1)
if len(parts) == 2 and parts[0] == base and parts[1].isdigit():
max_num = max(max_num, int(parts[1]))
return f"{base}-{max_num + 1:03d}"
def _modify_compose_file(
compose_path: str,
port_override: int | None = None,
start_command: str | None = None,
working_directory: str | None = None,
extra_volumes: list[dict] | None = None,
) -> None:
"""Modify compose file with runtime overrides."""
import yaml
compose_file = Path(compose_path)
content = compose_file.read_text()
compose_data = yaml.safe_load(content)
if not compose_data or "services" not in compose_data:
return
for service_name, service_config in compose_data["services"].items():
if port_override and "ports" in service_config:
for i, port_mapping in enumerate(service_config["ports"]):
if isinstance(port_mapping, str) and ":" in port_mapping:
_host_port, container_port = port_mapping.split(":", 1)
service_config["ports"][i] = f"{port_override}:{container_port}"
break
if start_command:
service_config["command"] = start_command
if working_directory:
service_config["working_dir"] = working_directory
if extra_volumes:
if "volumes" not in service_config:
service_config["volumes"] = []
for vol in extra_volumes:
source = vol.get("source", "")
target = vol.get("target", "")
vol_type = vol.get("type", "bind")
if vol_type == "bind":
service_config["volumes"].append(f"{source}:{target}")
else:
service_config["volumes"].append(f"{source}:{target}:{vol_type}")
break
compose_file.write_text(yaml.dump(compose_data, default_flow_style=False))
async def _apply_resolved_profile(
profile: ConfigProfile,
instance_dir: str,
env_vars: dict[str, str],
port_override: int | None,
start_command: str | None,
working_directory: str | None,
extra_volumes: list[dict],
) -> tuple[dict[str, str], int | None, str | None, str | None, list[dict]]:
"""Resolve a profile and apply its output to instance configuration."""
resolved = resolve_profile(profile)
if resolved.environment_variables:
env_vars.update(resolved.environment_variables)
if resolved.runtime_hints.start_command is not None:
start_command = resolved.runtime_hints.start_command
if resolved.runtime_hints.working_directory is not None:
working_directory = resolved.runtime_hints.working_directory
if resolved.runtime_hints.port is not None:
port_override = resolved.runtime_hints.port
for target_path, mount in resolved.mounts.items():
safe_name = target_path.strip("/").replace("/", "_")
mount_dir = Path(instance_dir) / "mounts" / safe_name
mount_dir.mkdir(parents=True, exist_ok=True)
for rel_path, content in mount.files.items():
file_path = mount_dir / rel_path
file_path.parent.mkdir(parents=True, exist_ok=True)
file_path.write_text(content)
extra_volumes.append({
"source": str(mount_dir),
"target": target_path,
"type": mount.mode,
})
return env_vars, port_override, start_command, working_directory, extra_volumes
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 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_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 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 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"])
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 +1,79 @@
"""Config folder file staging for Docker instances."""
import logging
from pathlib import Path
logger = logging.getLogger(__name__)
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)
def write_config_folder_files(instance_dir: str, folders: list, project_id: str | None = None) -> list[dict]:
"""Write config folder files to the instance directory and return volume mounts.
Args:
instance_dir: Path to instance directory
folders: List of ConfigFolder objects
project_id: Optional project ID for applying overrides
Returns:
List of volume mount dicts [{"source": "...", "target": "...", "type": "..."}]
"""
instance_path = Path(instance_dir)
volume_mounts = []
for folder in folders:
# Determine mount path (with project override if applicable)
mount_path = folder.mount_path
files = folder.files.copy()
if project_id and folder.project_overrides:
override = folder.project_overrides.get(str(project_id))
if override:
if override.get("mount_path"):
mount_path = override["mount_path"]
if override.get("files"):
files.update(override["files"])
# Write files to instance directory
folder_dir = instance_path / "volumes" / folder.name
folder_dir.mkdir(parents=True, exist_ok=True)
for file_path, content in files.items():
# Security: ensure path doesn't escape folder_dir
full_path = folder_dir / file_path
try:
full_path.resolve().relative_to(folder_dir.resolve())
except ValueError:
logger.warning("Config folder file path escapes directory: %s", file_path)
continue
full_path.parent.mkdir(parents=True, exist_ok=True)
full_path.write_text(content)
# Add volume mount
volume_mounts.append({
"source": str(folder_dir),
"target": mount_path,
"type": "bind",
})
return volume_mounts
+121
View File
@@ -0,0 +1,121 @@
"""Docker container lifecycle and query operations."""
import socket
import subprocess
def get_container_id(instance_name: str) -> str | None:
"""Get the container ID for a compose service.
Args:
instance_name: The service name in compose
Returns:
Container ID or None if not found
"""
result = subprocess.run(
["docker", "ps", "-q", "--filter", f"name={instance_name}"],
capture_output=True,
text=True,
)
if result.returncode == 0 and result.stdout.strip():
return result.stdout.strip().split("\n")[0]
return None
def get_container_name(instance_name: str) -> str | None:
"""Get the full container name for a compose service.
Args:
instance_name: The service name in compose
Returns:
Container name or None if not found
"""
result = subprocess.run(
["docker", "ps", "--format", "{{.Names}}", "--filter", f"name={instance_name}"],
capture_output=True,
text=True,
)
if result.returncode == 0 and result.stdout.strip():
return result.stdout.strip().split("\n")[0]
return None
def connect_container_to_network(container_name: str, network_name: str = "backend") -> 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 (default: backend)
Returns:
True if successful, False otherwise
"""
result = subprocess.run(
["docker", "network", "connect", network_name, container_name],
capture_output=True,
text=True,
)
return result.returncode == 0
def get_container_status(container_id: str) -> str:
"""Get the status of a Docker container.
Args:
container_id: Docker container ID
Returns:
Container status string (running, exited, etc.)
"""
result = subprocess.run(
["docker", "inspect", "-f", "{{.State.Status}}", container_id],
capture_output=True,
text=True,
)
if result.returncode == 0:
return result.stdout.strip()
return "unknown"
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
"""
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}")
+146
View File
@@ -0,0 +1,146 @@
"""Cloudflare tunnel management for Docker instances."""
import logging
import os
import re
import signal
import subprocess
import time
from typing import Any
logger = logging.getLogger(__name__)
def start_cloudflared_tunnel(
container_name: str, port: int, timeout: int = 30
) -> dict[str, str]:
"""Start a temporary Cloudflare tunnel for a container.
Uses 'cloudflared tunnel --url' to create a temporary tunnel
with a random trycloudflare.com URL.
Args:
container_name: Name of the Docker container to tunnel to
port: Port number the container listens on
timeout: Maximum seconds to wait for tunnel URL
Returns:
Dict with 'url' (the public tunnel URL) and 'pid' (process ID)
"""
import select as sel
# First verify the container is accessible
logger.info("Checking connectivity to %s:%d...", container_name, port)
for attempt in range(10):
check = subprocess.run(
["curl", "-s", "-o", "/dev/null", "-w", "%{http_code}",
f"http://{container_name}:{port}"],
capture_output=True,
text=True,
timeout=5,
)
logger.info("Connectivity check %d: http_code=%s", attempt + 1, check.stdout.strip())
if check.returncode == 0:
break
time.sleep(1)
else:
logger.warning("Container %s:%d not responding to curl checks", container_name, port)
# Run cloudflared in background, capture output
logger.info("Starting cloudflared tunnel to http://%s:%d", container_name, port)
proc = subprocess.Popen(
["cloudflared", "tunnel", "--url", f"http://{container_name}:{port}"],
stdout=subprocess.PIPE,
stderr=subprocess.STDOUT,
text=True,
)
# Wait for the URL to appear in output
url_pattern = re.compile(r"https://[a-z0-9-]+\.trycloudflare\.com")
start_time = time.time()
url = None
while time.time() - start_time < timeout:
# Read available output
readable, _, _ = sel.select([proc.stdout], [], [], 1.0)
if readable:
line = proc.stdout.readline()
if line:
match = url_pattern.search(line)
if match:
url = match.group(0)
break
if not url:
proc.terminate()
proc.wait(timeout=5)
raise RuntimeError(
f"Failed to get tunnel URL within {timeout}s. "
f"cloudflared output may contain errors."
)
return {"url": url, "pid": str(proc.pid)}
def stop_cloudflared_tunnel(pid: str) -> None:
"""Stop a cloudflared tunnel process.
Args:
pid: Process ID of the cloudflared tunnel
"""
try:
os.kill(int(pid), signal.SIGTERM)
except ProcessLookupError:
pass # Already stopped
def recreate_tunnel(
container_name: str, port: int, old_pid: str | None = None
) -> dict[str, str]:
"""Recreate a temporary Cloudflare tunnel.
Stops the old tunnel (if pid provided) and starts a new one.
Args:
container_name: Name of the Docker container to tunnel to
port: Port number the container listens on
old_pid: Optional PID of the old tunnel process to stop
Returns:
Dict with 'url' and 'pid' for the new tunnel
"""
if old_pid:
stop_cloudflared_tunnel(old_pid)
return start_cloudflared_tunnel(container_name, port)
def check_tunnel_health(url: str, timeout: int = 10) -> dict[str, Any]:
"""Check if a tunnel URL is healthy.
Args:
url: The tunnel URL to check
timeout: Request timeout in seconds
Returns:
Dict with 'healthy' (bool) and 'status_code' (int or None)
"""
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())
return {
"healthy": 200 <= status_code < 400,
"status_code": status_code,
}
except (ValueError, subprocess.TimeoutExpired, Exception) as e:
return {
"healthy": False,
"status_code": None,
"error": str(e),
}
+1
View File
@@ -0,0 +1 @@
"""Git services package."""
+196
View File
@@ -0,0 +1,196 @@
"""Git control operations with repo validation."""
import logging
import os
import uuid
from fastapi import HTTPException, status
from sqlalchemy.ext.asyncio import AsyncSession
from src.models.git_repository import GitRepository
from src.models.user import User
from src.schemas.git_repository import (
BranchCreateRequest,
CheckoutRequest,
CommitRequest,
FetchResponse,
MergeRequest,
MergeResponse,
PullResponse,
PushResponse,
StatusResponse,
)
from src.services.git.repository import ensure_repo_on_disk, get_repo_and_validate
from src.utils.git_control import (
checkout_branch,
commit_changes,
create_branch,
delete_branch,
fetch,
get_status,
merge,
pull,
push,
)
logger = logging.getLogger(__name__)
async def get_status_with_validation(
session: AsyncSession,
project_id: uuid.UUID,
repo_id: uuid.UUID,
) -> StatusResponse:
repo = await get_repo_and_validate(session, repo_id, project_id)
ensure_repo_on_disk(repo)
try:
result = get_status(repo.path)
return StatusResponse(
branch=result.branch,
modified=result.modified,
added=result.added,
deleted=result.deleted,
untracked=result.untracked,
renamed=result.renamed,
ahead=result.ahead,
behind=result.behind,
)
except RuntimeError as e:
raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail=str(e))
async def create_branch_with_validation(
session: AsyncSession,
project_id: uuid.UUID,
repo_id: uuid.UUID,
data: BranchCreateRequest,
) -> dict:
repo = await get_repo_and_validate(session, repo_id, project_id)
ensure_repo_on_disk(repo)
try:
create_branch(repo.path, data.name, data.base_branch)
return {"message": f"Branch '{data.name}' created", "branch": data.name}
except RuntimeError as e:
raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail=str(e))
async def delete_branch_with_validation(
session: AsyncSession,
project_id: uuid.UUID,
repo_id: uuid.UUID,
branch_name: str,
force: bool = False,
) -> dict:
repo = await get_repo_and_validate(session, repo_id, project_id)
ensure_repo_on_disk(repo)
try:
delete_branch(repo.path, branch_name, force)
return {"message": f"Branch '{branch_name}' deleted"}
except RuntimeError as e:
raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail=str(e))
async def checkout_branch_with_validation(
session: AsyncSession,
project_id: uuid.UUID,
repo_id: uuid.UUID,
data: CheckoutRequest,
) -> dict:
repo = await get_repo_and_validate(session, repo_id, project_id)
ensure_repo_on_disk(repo)
try:
checkout_branch(repo.path, data.branch)
return {"message": f"Checked out branch '{data.branch}'", "branch": data.branch}
except RuntimeError as e:
raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail=str(e))
async def commit_changes_with_validation(
session: AsyncSession,
project_id: uuid.UUID,
repo_id: uuid.UUID,
data: CommitRequest,
user: User,
) -> dict:
repo = await get_repo_and_validate(session, repo_id, project_id)
ensure_repo_on_disk(repo)
author_name = user.name or "Unknown"
author_email = user.email or "unknown@example.com"
try:
commit_hash = commit_changes(
repo_path=repo.path,
message=data.message,
author_name=author_name,
author_email=author_email,
files=data.files,
)
return {"commit_hash": commit_hash, "message": data.message}
except RuntimeError as e:
raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail=str(e))
async def fetch_with_validation(
session: AsyncSession,
project_id: uuid.UUID,
repo_id: uuid.UUID,
) -> FetchResponse:
repo = await get_repo_and_validate(session, repo_id, project_id)
ensure_repo_on_disk(repo)
try:
fetch(repo.path)
return FetchResponse(message="Fetched from remote")
except RuntimeError as e:
raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail=str(e))
async def pull_with_validation(
session: AsyncSession,
project_id: uuid.UUID,
repo_id: uuid.UUID,
branch: str | None = None,
) -> PullResponse:
repo = await get_repo_and_validate(session, repo_id, project_id)
ensure_repo_on_disk(repo)
try:
pull(repo.path, branch)
return PullResponse(message="Pulled from remote")
except RuntimeError as e:
raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail=str(e))
async def push_with_validation(
session: AsyncSession,
project_id: uuid.UUID,
repo_id: uuid.UUID,
branch: str | None = None,
) -> PushResponse:
repo = await get_repo_and_validate(session, repo_id, project_id)
ensure_repo_on_disk(repo)
try:
push(repo.path, branch)
return PushResponse(message="Pushed to remote")
except RuntimeError as e:
raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail=str(e))
async def merge_with_validation(
session: AsyncSession,
project_id: uuid.UUID,
repo_id: uuid.UUID,
data: MergeRequest,
) -> MergeResponse:
repo = await get_repo_and_validate(session, repo_id, project_id)
ensure_repo_on_disk(repo)
try:
commit_hash = merge(
repo_path=repo.path,
source_branch=data.source_branch,
target_branch=data.target_branch,
message=data.message,
)
return MergeResponse(
commit_hash=commit_hash,
message=data.message or f"Merge {data.source_branch}",
)
except RuntimeError as e:
raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail=str(e))
+150
View File
@@ -0,0 +1,150 @@
"""Git file operations with repo validation."""
import logging
import uuid
from fastapi import HTTPException, status
from sqlalchemy.ext.asyncio import AsyncSession
from src.models.git_repository import GitRepository
from src.models.user import User
from src.schemas.git_repository import (
FileContentResponse,
FileListResponse,
FileUpdateRequest,
FileUpdateResponse,
)
from src.services.git.repository import ensure_repo_on_disk, get_repo_and_validate
from src.utils.git_files import (
commit_file,
get_file_content,
list_branches,
list_tree,
)
logger = logging.getLogger(__name__)
async def list_files(
session: AsyncSession,
project_id: uuid.UUID,
repo_id: uuid.UUID,
branch: str = "main",
path: str = "",
) -> FileListResponse:
repo = await get_repo_and_validate(session, repo_id, project_id)
ensure_repo_on_disk(repo)
try:
entries = list_tree(repo.path, branch=branch, path=path)
return FileListResponse(
path=path,
branch=branch,
entries=[
{
"name": e.name,
"type": e.type,
"path": e.path,
"size": e.size,
"mode": e.mode,
"last_commit": e.last_commit,
}
for e in entries
],
)
except RuntimeError as e:
logger.error(
"Failed to list files for repo %s (path=%s, branch=%s): %s",
repo_id,
path,
branch,
str(e),
exc_info=True,
)
raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail=str(e))
async def get_file(
session: AsyncSession,
project_id: uuid.UUID,
repo_id: uuid.UUID,
branch: str,
path: str,
) -> FileContentResponse:
repo = await get_repo_and_validate(session, repo_id, project_id)
ensure_repo_on_disk(repo)
try:
file_content = get_file_content(repo.path, branch=branch, path=path)
return FileContentResponse(
path=file_content.path,
branch=file_content.branch,
content=file_content.content,
size=file_content.size,
encoding=file_content.encoding,
language=file_content.language,
is_binary=file_content.is_binary,
last_commit=file_content.last_commit,
)
except FileNotFoundError:
raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail="file not found")
except RuntimeError as e:
raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail=str(e))
async def update_file(
session: AsyncSession,
project_id: uuid.UUID,
repo_id: uuid.UUID,
data: FileUpdateRequest,
user: User,
) -> FileUpdateResponse:
repo = await get_repo_and_validate(session, repo_id, project_id)
ensure_repo_on_disk(repo)
author_name = user.name or "Unknown"
author_email = user.email or "unknown@example.com"
try:
commit_hash = commit_file(
repo_path=repo.path,
branch=data.branch,
path=data.path,
content=data.content,
commit_message=data.commit_message,
author_name=author_name,
author_email=author_email,
)
return FileUpdateResponse(
commit_hash=commit_hash,
message=data.commit_message,
branch=data.branch,
)
except RuntimeError as e:
raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail=str(e))
async def list_branches_with_validation(
session: AsyncSession,
project_id: uuid.UUID,
repo_id: uuid.UUID,
) -> dict:
repo = await get_repo_and_validate(session, repo_id, project_id)
ensure_repo_on_disk(repo)
try:
branches, default_branch = list_branches(repo.path)
return {
"branches": [
{
"name": b.name,
"is_default": b.is_default,
"last_commit": b.last_commit,
}
for b in branches
],
"default_branch": default_branch,
}
except RuntimeError as e:
logger.error(
"Failed to list branches for repo %s: %s",
repo_id,
str(e),
exc_info=True,
)
raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail=str(e))
+211
View File
@@ -0,0 +1,211 @@
"""Repository lifecycle and path helpers."""
import logging
import os
import shutil
import subprocess
import uuid
from fastapi import HTTPException, status
from sqlalchemy import select
from sqlalchemy.ext.asyncio import AsyncSession
from src.config import Settings
from src.models.git_repository import GitRepository
from src.models.project import Project
from src.models.user import User
from src.schemas.git_repository import GitRepositoryCreate
from src.utils.git_url_parser import parse_git_url
logger = logging.getLogger(__name__)
def _get_repo_path(user_id: uuid.UUID, project_id: uuid.UUID, name: str) -> str:
"""Generate the filesystem path for a repository."""
base = Settings().repo_base_path or "/data/repos"
return os.path.join(base, str(user_id), str(project_id), f"{name}.git")
def _build_provider_clone_url(owner: str, repo: str) -> str:
"""Build the SSH clone URL for the fixed git provider."""
return f"git@git.commumedia.org:{owner}/{repo}.git"
def _preflight_remote_repository(remote_url: str) -> None:
"""Verify a remote repository is reachable before cloning."""
try:
result = subprocess.run(
["git", "ls-remote", remote_url],
capture_output=True,
text=True,
timeout=60,
)
except subprocess.TimeoutExpired:
raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="remote repository check timed out")
except FileNotFoundError:
raise HTTPException(status_code=status.HTTP_500_INTERNAL_SERVER_ERROR, detail="git command not found")
if result.returncode != 0:
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail="repository not found or inaccessible",
)
def _clone_working_repository(remote_url: str, repo_path: str) -> None:
try:
result = subprocess.run(
["git", "clone", remote_url, repo_path],
capture_output=True,
text=True,
timeout=300,
)
except subprocess.TimeoutExpired:
raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="clone operation timed out")
except FileNotFoundError:
raise HTTPException(status_code=status.HTTP_500_INTERNAL_SERVER_ERROR, detail="git command not found")
if result.returncode != 0:
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail=f"failed to clone repository: {result.stderr}",
)
def _init_working_repository(repo_path: str) -> None:
try:
result = subprocess.run(
["git", "init", "-b", "main", repo_path],
capture_output=True,
text=True,
)
except FileNotFoundError:
raise HTTPException(status_code=status.HTTP_500_INTERNAL_SERVER_ERROR, detail="git command not found")
if result.returncode == 0:
return
fallback = subprocess.run(
["git", "init", repo_path],
capture_output=True,
text=True,
)
if fallback.returncode != 0:
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail=f"failed to initialize repository: {fallback.stderr}",
)
ref_result = subprocess.run(
["git", "-C", repo_path, "symbolic-ref", "HEAD", "refs/heads/main"],
capture_output=True,
text=True,
)
if ref_result.returncode != 0:
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail=f"failed to set initial branch: {ref_result.stderr}",
)
async def get_repo_and_validate(
session: AsyncSession,
repo_id: uuid.UUID,
project_id: uuid.UUID,
) -> GitRepository:
"""Fetch a repository and validate ownership + disk presence."""
repo = await session.get(GitRepository, repo_id)
if repo is None or repo.project_id != project_id:
raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail="repository not found")
return repo
def ensure_repo_on_disk(repo: GitRepository) -> None:
"""Raise 404 if the repository is not present on disk."""
if not os.path.exists(repo.path):
raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail="repository not found on disk")
async def create_repository(
session: AsyncSession,
project_id: uuid.UUID,
data: GitRepositoryCreate,
user: User,
) -> GitRepository:
"""Create a new git repository (clone or init)."""
# Check for duplicate name
existing = await session.execute(
select(GitRepository).where(
GitRepository.project_id == project_id,
GitRepository.name == data.name,
)
)
if existing.scalar_one_or_none():
raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="repository name already exists")
# Validate and potentially correct the URL
remote_url = data.remote_url
if remote_url and not data.force_original_url:
parse_result = parse_git_url(remote_url)
if parse_result["needs_parsing"] and parse_result["base_url"]:
raise HTTPException(
status_code=status.HTTP_422_UNPROCESSABLE_ENTITY,
detail={
"message": "The provided URL appears to be a browser URL, not a git clone URL",
"suggested_url": parse_result["base_url"],
"original_url": remote_url,
"error_code": "URL_NEEDS_PARSING",
},
)
if parse_result["base_url"]:
remote_url = parse_result["base_url"]
if remote_url:
_preflight_remote_repository(remote_url)
repo_path = _get_repo_path(user.id, project_id, data.name)
os.makedirs(os.path.dirname(repo_path), exist_ok=True)
if remote_url:
_clone_working_repository(remote_url, repo_path)
else:
_init_working_repository(repo_path)
repo = GitRepository(
name=data.name,
path=repo_path,
project_id=project_id,
owner_id=user.id,
is_mirror=False,
remote_url=remote_url,
)
session.add(repo)
await session.commit()
await session.refresh(repo)
return repo
async def delete_repository(
session: AsyncSession,
repo_id: uuid.UUID,
project_id: uuid.UUID,
) -> None:
"""Delete a repository from DB and disk."""
repo = await get_repo_and_validate(session, repo_id, project_id)
if os.path.exists(repo.path):
shutil.rmtree(repo.path)
await session.delete(repo)
await session.commit()
async def list_repositories(
session: AsyncSession,
project_id: uuid.UUID,
) -> list[GitRepository]:
"""List all repositories in a project."""
result = await session.execute(
select(GitRepository).where(GitRepository.project_id == project_id)
)
return list(result.scalars().all())
+420
View File
@@ -0,0 +1,420 @@
"""High-level tool instance lifecycle orchestration.
Coordinates Docker compose, container, tunnel, and config staging services
to create, start, stop, restart, and delete tool instances.
"""
import logging
import os
import shutil
from datetime import datetime
from typing import Any
from fastapi import HTTPException, status
from sqlalchemy import select
from sqlalchemy.ext.asyncio import AsyncSession
from src.models.config_folder import ConfigFolder
from src.models.config_profile import ConfigProfile
from src.models.git_repository import GitRepository
from src.models.project import Project
from src.models.tool_config import ToolConfig
from src.models.tool_instance import ToolInstance
from src.models.tool_type import ToolType
from src.models.user import User
from src.services.docker import compose as compose_svc
from src.services.docker import config_staging
from src.services.docker import container as container_svc
from src.services.docker import tunnel as tunnel_svc
from src.services.docker_build import build_image
from src.services.readiness_probe import execute_probe
logger = logging.getLogger(__name__)
async def create_new_instance(
session: AsyncSession,
project: Project,
repo: GitRepository,
tool_type: ToolType,
user: User,
display_name: str | None,
selected_profile: ConfigProfile | None,
) -> ToolInstance:
"""Create a new tool instance record and its compose file."""
instance_name = await compose_svc._generate_instance_name(
session, project.name, tool_type.name
)
instance_dir = compose_svc.ensure_instance_directory(instance_name)
tool_port = container_svc.find_free_port()
compose_path = await _build_or_render_compose(
tool_type, instance_name, instance_dir, repo, user, project.id, tool_port
)
instance = ToolInstance(
name=instance_name,
display_name=display_name or f"{project.name} / {repo.name} / {tool_type.display_name}",
tool_type_id=tool_type.id,
repository_id=repo.id,
project_id=project.id,
owner_id=user.id,
status="pending",
compose_path=compose_path,
port=tool_port,
selected_profile_id=selected_profile.id if selected_profile else None,
)
session.add(instance)
await session.commit()
await session.refresh(instance)
return instance
async def start_existing_instance(
session: AsyncSession,
instance: ToolInstance,
user: User,
project_id: Any,
) -> dict:
"""Start an existing instance: stage configs, compose up, probe, tunnel."""
if not instance.compose_path or not os.path.exists(instance.compose_path):
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST, detail="compose file not found"
)
instance.status = "building"
await session.commit()
env_vars, config_files, port_override, start_command, working_directory, _extra_env, extra_volumes = await _fetch_tool_configs(
session, user.id, instance.tool_type_id, project_id
)
selected_profile = None
if instance.selected_profile_id:
selected_profile = await session.get(ConfigProfile, instance.selected_profile_id)
if selected_profile and selected_profile.user_id == user.id:
instance_dir = os.path.dirname(instance.compose_path)
env_vars, port_override, start_command, working_directory, extra_volumes = await compose_svc._apply_resolved_profile(
selected_profile,
instance_dir,
env_vars,
port_override,
start_command,
working_directory,
extra_volumes,
)
env_file_path, extra_volumes = await _stage_configs_and_folders(
session, user.id, project_id, os.path.dirname(instance.compose_path),
env_vars, config_files, extra_volumes
)
if port_override or start_command or working_directory or extra_volumes:
compose_svc._modify_compose_file(
instance.compose_path, port_override, start_command, working_directory, extra_volumes
)
returncode, _stdout, stderr = compose_svc.execute_compose_command(
instance.compose_path, "up", env_file=env_file_path
)
if returncode != 0:
instance.status = "error"
await session.commit()
raise HTTPException(
status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
detail=f"failed to start instance: {stderr}",
)
container_id = container_svc.get_container_id(instance.name)
if container_id:
instance.container_id = container_id
container_name = container_svc.get_container_name(instance.name)
if container_name:
instance.container_name = container_name
container_svc.connect_container_to_network(container_name, "backend")
instance.status = "starting"
instance.last_started_at = datetime.now()
await session.commit()
tool_type = await session.get(ToolType, instance.tool_type_id)
success, probe_logs = await _run_readiness_probe(instance, tool_type)
if not success:
instance.status = "failed"
instance.url = None
instance.public_url = None
await session.commit()
return {
"status": "failed",
"error": f"Readiness probe failed: {' '.join(probe_logs)}",
}
instance.status = "running"
await session.commit()
await _start_tunnel_if_web(instance, tool_type)
await session.commit()
return {"status": instance.status, "url": instance.url}
async def restart_existing_instance(
session: AsyncSession,
instance: ToolInstance,
user: User,
project_id: Any,
) -> dict:
"""Restart an instance: re-stage configs, compose restart, tunnel."""
if instance.tunnel_id:
try:
tunnel_svc.stop_cloudflared_tunnel(instance.tunnel_id)
except Exception as exc:
logger.warning("Failed to stop old tunnel: %s", exc)
if not instance.compose_path or not os.path.exists(instance.compose_path):
instance.status = "error"
await session.commit()
return {"status": instance.status}
env_vars, config_files, port_override, start_command, working_directory, _extra_env, extra_volumes = await _fetch_tool_configs(
session, user.id, instance.tool_type_id, project_id
)
stored_profile = None
if instance.selected_profile_id:
stored_profile = await session.get(ConfigProfile, instance.selected_profile_id)
if stored_profile and stored_profile.user_id == user.id:
instance_dir = os.path.dirname(instance.compose_path)
env_vars, port_override, start_command, working_directory, extra_volumes = await compose_svc._apply_resolved_profile(
stored_profile, instance_dir, env_vars, port_override, start_command, working_directory, extra_volumes
)
env_file_path, extra_volumes = await _stage_configs_and_folders(
session, user.id, project_id, os.path.dirname(instance.compose_path),
env_vars, config_files, extra_volumes
)
if port_override or start_command or working_directory or extra_volumes:
compose_svc._modify_compose_file(
instance.compose_path, port_override, start_command, working_directory, extra_volumes
)
returncode, _stdout, _stderr = compose_svc.execute_compose_command(
instance.compose_path, "restart", env_file=env_file_path
)
if returncode != 0:
instance.status = "error"
await session.commit()
return {"status": instance.status}
instance.status = "running"
instance.last_started_at = datetime.now()
tool_type = await session.get(ToolType, instance.tool_type_id)
await _start_tunnel_if_web(instance, tool_type)
await session.commit()
return {"status": instance.status, "url": instance.url}
async def stop_existing_instance(session: AsyncSession, instance: ToolInstance) -> None:
"""Stop an instance and its tunnel."""
if instance.tunnel_id:
try:
tunnel_svc.stop_cloudflared_tunnel(instance.tunnel_id)
except Exception as exc:
logger.warning("Failed to stop tunnel: %s", exc)
if instance.compose_path and os.path.exists(instance.compose_path):
compose_svc.execute_compose_command(instance.compose_path, "stop")
instance.status = "stopped"
instance.last_stopped_at = datetime.now()
instance.url = None
instance.public_url = None
instance.tunnel_id = None
await session.commit()
async def delete_existing_instance(session: AsyncSession, instance: ToolInstance) -> None:
"""Delete an instance, its containers, and its directory."""
if instance.tunnel_id:
try:
tunnel_svc.stop_cloudflared_tunnel(instance.tunnel_id)
except Exception as exc:
logger.warning("Failed to stop tunnel: %s", exc)
if instance.compose_path and os.path.exists(instance.compose_path):
compose_svc.execute_compose_command(instance.compose_path, "down")
instance_dir = os.path.dirname(instance.compose_path)
if os.path.exists(instance_dir):
shutil.rmtree(instance_dir)
await session.delete(instance)
await session.commit()
# ── Internal helpers ───────────────────────────────────────────────────────
async def _build_or_render_compose(
tool_type: ToolType,
instance_name: str,
instance_dir: str,
repo: GitRepository,
user: User,
project_id: Any,
tool_port: int,
) -> str:
"""Build Dockerfile or render compose template."""
if tool_type.definition_type == "dockerfile":
image_tag = f"headquarter/{instance_name}:latest"
if tool_type.dockerfile_template:
returncode, _stdout, stderr = build_image(
instance_dir=instance_dir,
dockerfile=tool_type.dockerfile_template,
tag=image_tag,
build_context=tool_type.build_context,
)
if returncode != 0:
logger.error("Build failed for %s: %s", instance_name, stderr)
raise HTTPException(
status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
detail=f"Failed to build Docker image: {stderr[:500]}",
)
compose_content = (
f'version: "3.8"\nservices:\n app:\n'
f' image: {image_tag}\n'
f' container_name: {instance_name}\n'
f' ports:\n - "{tool_port}:{tool_type.default_port}"\n'
f' volumes:\n - {repo.path}:/workspace\n'
f' restart: unless-stopped\n'
)
else:
variables = {
"REPO_PATH": repo.path,
"INSTANCE_NAME": instance_name,
"INSTANCE_ID": instance_name,
"TOOL_NAME": instance_name,
"TOOL_PORT": tool_port,
"USER_ID": str(user.id),
"PROJECT_ID": str(project_id),
}
compose_content = compose_svc.render_compose_template(
tool_type.compose_template, variables
)
compose_svc.write_compose_file(instance_dir, compose_content)
return os.path.join(instance_dir, "docker-compose.yml")
async def _fetch_tool_configs(
session: AsyncSession,
user_id: Any,
tool_type_id: Any,
project_id: Any,
) -> tuple[dict, dict, Any, Any, Any, dict, list]:
"""Fetch tool configs and return parsed values."""
env_vars: dict[str, str] = {}
config_files: dict[str, str] = {}
port_override = None
start_command = None
working_directory = None
extra_env_vars: dict[str, str] = {}
extra_volumes: list[dict] = []
query = (
select(ToolConfig)
.where(ToolConfig.user_id == user_id, ToolConfig.tool_type_id == tool_type_id)
.where((ToolConfig.project_id == project_id) | (ToolConfig.project_id.is_(None)))
)
configs = (await session.execute(query)).scalars().all()
for cfg in configs:
if cfg.config_type == "env":
env_vars[cfg.key] = cfg.value
elif cfg.config_type == "file" and cfg.file_path:
config_files[cfg.file_path] = cfg.value
if cfg.port_override:
port_override = cfg.port_override
if cfg.start_command:
start_command = cfg.start_command
if cfg.working_directory:
working_directory = cfg.working_directory
if cfg.environment_variables:
extra_env_vars.update(cfg.environment_variables)
if cfg.volumes:
extra_volumes.extend(cfg.volumes)
env_vars.update(extra_env_vars)
return env_vars, config_files, port_override, start_command, working_directory, extra_env_vars, extra_volumes
async def _stage_configs_and_folders(
session: AsyncSession,
user_id: Any,
project_id: Any,
instance_dir: str,
env_vars: dict[str, str],
config_files: dict[str, str],
extra_volumes: list[dict],
) -> tuple[str | None, list[dict]]:
"""Write env/config files and config folders."""
env_file_path: str | None = None
if env_vars:
env_file_path = compose_svc.write_env_file(instance_dir, env_vars)
if config_files:
config_staging.write_config_files(instance_dir, config_files)
folder_query = select(ConfigFolder).where(
ConfigFolder.user_id == user_id, ConfigFolder.is_active.is_(True)
)
folders = (await session.execute(folder_query)).scalars().all()
if folders:
folder_volumes = config_staging.write_config_folder_files(
instance_dir, folders, str(project_id)
)
extra_volumes.extend(folder_volumes)
return env_file_path, extra_volumes
async def _start_tunnel_if_web(instance: ToolInstance, tool_type: ToolType) -> None:
"""Create Cloudflare tunnel for web-enabled tools."""
if "web" not in tool_type.interfaces or not tool_type.default_port:
instance.url = None
instance.public_url = None
return
try:
tunnel_info = tunnel_svc.start_cloudflared_tunnel(
container_name=instance.container_name or instance.name,
port=tool_type.default_port,
)
instance.tunnel_id = tunnel_info["pid"]
instance.public_url = tunnel_info["url"]
instance.url = tunnel_info["url"]
logger.info("Created tunnel for instance %s: %s", instance.id, tunnel_info["url"])
except Exception as exc:
logger.error("Failed to create tunnel for instance %s: %s", instance.id, exc)
instance.status = "error"
instance.url = None
async def _run_readiness_probe(
instance: ToolInstance, tool_type: ToolType
) -> tuple[bool, list[str]]:
"""Run readiness probe if configured."""
if not tool_type.readiness_probe or not instance.container_id:
return True, []
probe = tool_type.readiness_probe
command = probe.get("command", "")
if not command:
return True, []
return await execute_probe(
container_id=instance.container_id,
command=command,
timeout=probe.get("timeout", 30),
interval=probe.get("interval", 2),
)
+251
View File
@@ -0,0 +1,251 @@
"""Profile resolver service for recursive ordered include resolution.
Provides deterministic merge rules, save-independent cycle protection,
and resolved output structures for env vars, runtime hints, mounts,
file trees, and override metadata.
"""
from __future__ import annotations
import uuid
from dataclasses import dataclass, field
from src.models.config_include import ConfigInclude
from src.models.config_mount import ConfigMount
from src.models.config_profile import ConfigProfile
@dataclass
class ResolvedMount:
"""A resolved mount with merged file tree and final mode."""
target_path: str
mode: str # "ro" or "rw"
files: dict[str, str] = field(default_factory=dict)
"""Relative file paths to UTF-8 text content."""
overridden_files: dict[str, list[str]] = field(default_factory=dict)
"""Map of relative file path to list of profile names that contributed
(latest is the winner)."""
mode_overridden_by: str | None = None
"""Name of the profile that set the final mode, if different from first."""
@dataclass
class ResolvedRuntimeHints:
"""Resolved runtime hints from profile layers."""
start_command: str | None = None
working_directory: str | None = None
port: int | None = None
overridden_hints: dict[str, str] = field(default_factory=dict)
"""Map of hint key to profile name that provided the winning value."""
@dataclass
class ResolvedProfileOutput:
"""Complete resolved output for a config profile."""
profile_id: uuid.UUID
profile_name: str
environment_variables: dict[str, str] = field(default_factory=dict)
"""Final merged env vars (later layers win)."""
env_var_sources: dict[str, list[str]] = field(default_factory=dict)
"""Map of env var key to ordered list of contributing profile names
(latest is the winner)."""
runtime_hints: ResolvedRuntimeHints = field(
default_factory=lambda: ResolvedRuntimeHints()
)
mounts: dict[str, ResolvedMount] = field(default_factory=dict)
"""Map of target_path to ResolvedMount."""
resolution_order: list[str] = field(default_factory=list)
"""Ordered list of profile names as they were resolved."""
cycle_detected: bool = False
cycle_path: list[str] | None = None
class ProfileResolutionError(Exception):
"""Raised when profile resolution fails."""
pass
class ProfileCycleError(ProfileResolutionError):
"""Raised when a cycle is detected during profile resolution."""
def __init__(self, cycle_path: list[str]) -> None:
self.cycle_path = cycle_path
path_str = " -> ".join(cycle_path)
super().__init__(f"Profile include cycle detected: {path_str}")
def _merge_env_vars(
current: dict[str, str],
sources: dict[str, list[str]],
profile: ConfigProfile,
) -> None:
"""Merge a profile's env vars into the current dict, tracking sources."""
if not profile.environment_variables:
return
for key, value in profile.environment_variables.items():
current[key] = value
if key not in sources:
sources[key] = []
sources[key].append(profile.name)
def _merge_runtime_hints(
hints: ResolvedRuntimeHints,
profile: ConfigProfile,
) -> None:
"""Merge a profile's runtime hints, tracking overrides."""
if profile.start_command is not None:
hints.start_command = profile.start_command
hints.overridden_hints["start_command"] = profile.name
if profile.working_directory is not None:
hints.working_directory = profile.working_directory
hints.overridden_hints["working_directory"] = profile.name
if profile.port is not None:
hints.port = profile.port
hints.overridden_hints["port"] = profile.name
def _merge_mounts(
mounts: dict[str, ResolvedMount],
profile_mounts: list[ConfigMount],
profile: ConfigProfile,
) -> None:
"""Merge a profile's mounts into the current mounts dict."""
for mount in profile_mounts:
target = mount.target_path
if target not in mounts:
mounts[target] = ResolvedMount(
target_path=target,
mode=mount.mode,
files={},
overridden_files={},
)
resolved = mounts[target]
# Mode override: later wins
if resolved.mode != mount.mode:
resolved.mode = mount.mode
resolved.mode_overridden_by = profile.name
# File tree merge: later wins for same relative path
if mount.files:
for rel_path, content in mount.files.items():
if rel_path not in resolved.files:
resolved.overridden_files[rel_path] = []
else:
if rel_path not in resolved.overridden_files:
resolved.overridden_files[rel_path] = []
resolved.overridden_files[rel_path].append(profile.name)
resolved.files[rel_path] = content
def _resolve_profile_recursive(
profile: ConfigProfile,
visited: set[uuid.UUID],
path: list[str],
resolution_order: list[str],
env_vars: dict[str, str],
env_var_sources: dict[str, list[str]],
runtime_hints: ResolvedRuntimeHints,
mounts: dict[str, ResolvedMount],
) -> None:
"""Recursively resolve a profile and its includes.
Args:
profile: The profile to resolve
visited: Set of already-resolved profile IDs to avoid duplicates
path: Current recursion path for cycle detection
resolution_order: Ordered list of profile names being resolved
env_vars: Accumulated environment variables
env_var_sources: Tracking of which profiles contributed each env var
runtime_hints: Accumulated runtime hints
mounts: Accumulated mounts
Raises:
ProfileCycleError: If a cycle is detected
"""
if profile.name in path:
# Cycle detected
cycle_start = path.index(profile.name)
cycle_path = path[cycle_start:] + [profile.name]
raise ProfileCycleError(cycle_path)
if profile.id in visited:
# Already resolved in another branch (diamond graph)
return
visited.add(profile.id)
path.append(profile.name)
resolution_order.append(profile.name)
# Resolve includes first (in order)
includes: list[ConfigInclude] = list(profile.includes)
includes.sort(key=lambda inc: inc.order_index)
for include in includes:
included_profile = include.included_profile
if included_profile is not None:
_resolve_profile_recursive(
included_profile,
visited,
path,
resolution_order,
env_vars,
env_var_sources,
runtime_hints,
mounts,
)
# Apply this profile's values (later layers win)
_merge_env_vars(env_vars, env_var_sources, profile)
_merge_runtime_hints(runtime_hints, profile)
_merge_mounts(mounts, list(profile.mounts), profile)
path.pop()
def resolve_profile(profile: ConfigProfile) -> ResolvedProfileOutput:
"""Resolve a config profile with all its includes.
Processes included profiles in configured order, then applies the
selected profile itself. Later layers override earlier layers.
Args:
profile: The root profile to resolve
Returns:
ResolvedProfileOutput with merged env vars, runtime hints, mounts,
and override metadata
Raises:
ProfileCycleError: If a cycle is detected in the include graph
"""
env_vars: dict[str, str] = {}
env_var_sources: dict[str, list[str]] = {}
runtime_hints = ResolvedRuntimeHints()
mounts: dict[str, ResolvedMount] = {}
resolution_order: list[str] = []
_resolve_profile_recursive(
profile,
set(),
[],
resolution_order,
env_vars,
env_var_sources,
runtime_hints,
mounts,
)
return ResolvedProfileOutput(
profile_id=profile.id,
profile_name=profile.name,
environment_variables=env_vars,
env_var_sources=env_var_sources,
runtime_hints=runtime_hints,
mounts=mounts,
resolution_order=resolution_order,
)
+145 -378
View File
@@ -1,426 +1,193 @@
"""Terminal session manager for WebSocket connections."""
import asyncio
import contextlib
import json
import logging
import time
import uuid
from datetime import datetime, timezone
from collections.abc import Coroutine
from typing import Any
from fastapi import WebSocket
from sqlalchemy.dialects.postgresql import insert as pg_insert
from src.database import SessionLocal
from src.models.terminal_session import TerminalSessionModel
from src.services.terminal_session import TerminalSession
logger = logging.getLogger(__name__)
class MaxSessionsExceededError(Exception):
"""Raised when the maximum number of terminal sessions per instance is reached."""
def __init__(self, instance_id: str, max_sessions: int = 5) -> None:
self.instance_id = instance_id
self.max_sessions = max_sessions
super().__init__(
f"Maximum of {max_sessions} terminal sessions reached for instance {instance_id}"
)
_READ_BATCH_INTERVAL_S = 0.016 # 16ms max batching delay
_READ_POLL_TIMEOUT_S = 0.005
_READ_POLL_SLEEP_S = 0.001
_HEARTBEAT_INTERVAL_S = 15.0
_IDLE_TIMEOUT_S = 60.0
class TerminalManager:
"""Manages active terminal sessions with persistence support."""
# Maximum sessions per tool instance
MAX_SESSIONS_PER_INSTANCE = 5
"""Manages active terminal sessions."""
def __init__(self) -> None:
# Track sessions by (instance_id, session_id) for multi-session support
self._sessions: dict[tuple[str, str], TerminalSession] = {}
self._idle_check_task: asyncio.Task | None = None
self._start_idle_check()
def _start_idle_check(self) -> None:
"""Start the idle timeout background task."""
if self._idle_check_task is not None and not self._idle_check_task.done():
return
try:
loop = asyncio.get_running_loop()
self._idle_check_task = loop.create_task(self._idle_check_loop())
except RuntimeError:
# No event loop running yet, will be started lazily
pass
async def _idle_check_loop(self) -> None:
"""Periodically check for idle sessions and clean them up."""
while True:
try:
await asyncio.sleep(60) # Check every minute
await self._cleanup_idle_sessions()
except Exception as exc:
logger.error("Error in idle check loop: %s", exc)
async def _cleanup_idle_sessions(self) -> None:
"""Clean up sessions that have been idle for too long."""
idle_keys = []
for (instance_id, session_id), session in list(self._sessions.items()):
if session.is_idle():
idle_keys.append((instance_id, session_id))
for key in idle_keys:
instance_id, session_id = key
logger.info(
"Cleaning up idle terminal session %s for instance %s",
session_id,
instance_id,
)
session = self._sessions.pop(key, None)
if session:
await session.close()
# Update DB status fire-and-forget
asyncio.create_task(self._mark_closed_in_db(session_id))
async def _insert_db_session_row(
self,
session_id: str,
instance_id: uuid.UUID,
name: str,
) -> None:
"""Insert a TerminalSessionModel row into the database.
Uses ON CONFLICT DO NOTHING to handle races when a session is
restored from DB and then re-inserted.
"""
try:
async with SessionLocal() as db_session:
stmt = (
pg_insert(TerminalSessionModel)
.values(
id=uuid.UUID(session_id),
instance_id=instance_id,
name=name,
status="active",
created_at=datetime.now(timezone.utc),
last_activity_at=datetime.now(timezone.utc),
)
.on_conflict_do_nothing(index_elements=["id"])
)
await db_session.execute(stmt)
await db_session.commit()
logger.debug(
"Inserted terminal session row %s for instance %s",
session_id,
instance_id,
)
except Exception as exc:
logger.error("Failed to insert terminal session row: %s", exc)
async def _mark_closed_in_db(self, session_id: str) -> None:
"""Mark a terminal session as closed in the database."""
try:
async with SessionLocal() as db_session:
db_row = await db_session.get(
TerminalSessionModel, uuid.UUID(session_id)
)
if db_row:
db_row.status = "closed"
db_row.closed_at = datetime.now(timezone.utc)
await db_session.commit()
logger.debug(
"Marked terminal session %s as closed in DB", session_id
)
except Exception as exc:
logger.error("Failed to mark terminal session as closed in DB: %s", exc)
def _count_sessions_for_instance(self, instance_id_str: str) -> int:
"""Count active in-memory sessions for a given instance."""
return sum(1 for (iid, _sid) in self._sessions if iid == instance_id_str)
"""Initialise the terminal manager."""
self._sessions: dict[str, TerminalSession] = {}
self._last_client_message: dict[str, float] = {}
self._background_tasks: set[asyncio.Task[Any]] = set()
async def create_session(
self,
instance_id: uuid.UUID,
container_id: str,
startup_command: str | None = None,
name: str | None = None,
session_id: str | None = None,
websocket: WebSocket,
) -> TerminalSession:
"""Create a new terminal session for an instance.
Enforces a maximum of MAX_SESSIONS_PER_INSTANCE sessions per instance.
Inserts a DB row fire-and-forget.
Args:
instance_id: UUID of the tool instance.
container_id: Docker container ID.
startup_command: Optional startup command to run.
name: Optional session name (auto-generated if omitted).
Returns:
The newly created TerminalSession.
Raises:
MaxSessionsExceededError: If the instance already has max sessions.
"""
instance_id_str = str(instance_id)
if (
self._count_sessions_for_instance(instance_id_str)
>= self.MAX_SESSIONS_PER_INSTANCE
):
raise MaxSessionsExceededError(
instance_id_str, self.MAX_SESSIONS_PER_INSTANCE
)
if session_id is None:
session_id = str(uuid.uuid4())
session = TerminalSession(
session_id=session_id,
instance_id=instance_id,
container_id=container_id,
startup_command=startup_command,
name=name,
)
await session.start(startup_command=startup_command)
key = (instance_id_str, session_id)
self._sessions[key] = session
# Fire-and-forget DB insert (skip if row already exists)
asyncio.create_task(
self._insert_db_session_row(session_id, instance_id, session.name)
)
logger.info(
"Created terminal session %s for instance %s (name=%s)",
session_id,
instance_id,
session.name,
)
return session
async def get_or_create_session(
self,
instance_id: uuid.UUID,
container_id: str,
startup_command: str | None = None,
) -> TerminalSession:
"""Get existing session or create a new one.
Backward-compatible alias that uses 'default' as the session_id.
"""
# Ensure idle check is running (lazy start)
self._start_idle_check()
instance_id_str = str(instance_id)
key = (instance_id_str, "default")
# Check for existing default session
if key in self._sessions:
session = self._sessions[key]
# Check if session is still alive
if session.is_alive():
logger.debug(
"Reattaching to existing terminal session for instance %s",
instance_id,
)
return session
else:
# Session died, clean it up
logger.debug(
"Existing session for instance %s is dead, cleaning up",
instance_id,
)
await session.close()
del self._sessions[key]
# Create new default session
logger.info(
"Creating new default terminal session for instance %s", instance_id
)
"""Create a new terminal session."""
session_id = str(uuid.uuid4())
session = TerminalSession(
session_id=session_id,
instance_id=instance_id,
container_id=container_id,
startup_command=startup_command,
name="Session 1",
)
await session.start(startup_command=startup_command)
self._sessions[key] = session
session = TerminalSession(session_id, instance_id, container_id)
await session.start()
self._sessions[session_id] = session
self._last_client_message[session_id] = time.monotonic()
# Fire-and-forget DB insert
asyncio.create_task(
self._insert_db_session_row(session_id, instance_id, session.name)
)
# Start background tasks for I/O streaming
self._start_task(self._read_loop(session, websocket))
self._start_task(self._write_loop(session, websocket))
self._start_task(self._heartbeat_loop(session, websocket))
return session
def get_session(
self,
instance_id: str,
session_id: str,
) -> TerminalSession | None:
"""Lookup a session by composite key, or by internal session_id."""
session = self._sessions.get((instance_id, session_id))
if session is not None:
return session
# Fallback: search by internal TerminalSession.session_id
for (iid, _sid), sess in self._sessions.items():
if iid == instance_id and sess.session_id == session_id:
return sess
return None
def _start_task(self, coro: Coroutine[Any, Any, None]) -> None:
"""Start a background task and store a reference to prevent GC."""
task = asyncio.create_task(coro)
self._background_tasks.add(task)
task.add_done_callback(self._background_tasks.discard)
def _find_key_by_internal_id(
self,
instance_id: str,
internal_session_id: str,
) -> tuple[str, str] | None:
"""Find the manager dict key for a session by its internal session_id."""
for (iid, sid), session in self._sessions.items():
if iid == instance_id and session.session_id == internal_session_id:
return (iid, sid)
return None
def get_sessions_for_instance(
self,
instance_id: str,
) -> list[TerminalSession]:
"""Return all in-memory sessions for a given instance."""
return [
session
for (iid, _sid), session in self._sessions.items()
if iid == instance_id
]
async def close_session(
self,
instance_id: str,
session_id: str,
) -> None:
"""Close a specific session and update its DB status."""
key = (instance_id, session_id)
session = self._sessions.pop(key, None)
if session:
await session.close()
# Fire-and-forget DB update
asyncio.create_task(self._mark_closed_in_db(session_id))
logger.info(
"Closed terminal session %s for instance %s",
session_id,
instance_id,
)
async def attach_websocket(
async def _read_loop(
self,
session: TerminalSession,
websocket: WebSocket,
) -> None:
"""Attach a WebSocket to an existing session.
"""Read output from the container and send to WebSocket with batching."""
try:
buffer = bytearray()
last_flush = time.monotonic()
Closes existing WebSocket connections only for this specific session.
"""
# Handle concurrent connections - close existing ones within the same session
if session.has_websockets():
logger.debug(
"Closing existing WebSocket connections for session %s (instance %s)",
while session.is_alive() and not session.closed:
data = await session.read_output(select_timeout=_READ_POLL_TIMEOUT_S)
if data:
buffer.extend(data)
now = time.monotonic()
flush_due = buffer and (
now - last_flush >= _READ_BATCH_INTERVAL_S or not data
)
if flush_due:
await websocket.send_bytes(bytes(buffer))
buffer.clear()
last_flush = now
elif not data:
await asyncio.sleep(_READ_POLL_SLEEP_S)
# Flush any remaining data
if buffer:
with contextlib.suppress(Exception):
await websocket.send_bytes(bytes(buffer))
except Exception:
logger.exception("Read loop error for session %s", session.session_id)
finally:
await self._cleanup_session(session)
async def _write_loop(
self,
session: TerminalSession,
websocket: WebSocket,
) -> None:
"""Read input from WebSocket and send to container."""
try:
while session.is_alive() and not session.closed:
message = await websocket.receive()
self._last_client_message[session.session_id] = time.monotonic()
if message["type"] == "websocket.receive":
if "bytes" in message:
await session.write_input(message["bytes"])
elif "text" in message:
text = message["text"]
if text.startswith("{"):
try:
ctrl = json.loads(text)
await self._handle_control_message(
session,
websocket,
ctrl,
)
except json.JSONDecodeError:
logger.debug("Invalid JSON control message: %s", text)
else:
await session.write_input(text.encode("utf-8"))
elif message["type"] == "websocket.disconnect":
break
except Exception:
logger.exception("Write loop error for session %s", session.session_id)
finally:
await self._cleanup_session(session)
async def _handle_control_message(
self,
session: TerminalSession,
websocket: WebSocket,
ctrl: dict[str, Any],
) -> None:
"""Handle a JSON control message from the client."""
msg_type = ctrl.get("type")
if msg_type == "resize":
await session.resize(
ctrl.get("cols", 80),
ctrl.get("rows", 24),
)
elif msg_type == "ping":
await websocket.send_json(
{"type": "pong", "id": ctrl.get("id")},
)
async def _heartbeat_loop(
self,
session: TerminalSession,
websocket: WebSocket,
) -> None:
"""Monitor client activity and close idle connections."""
try:
while session.is_alive() and not session.closed:
await asyncio.sleep(_HEARTBEAT_INTERVAL_S)
last_msg = self._last_client_message.get(session.session_id, 0)
if time.monotonic() - last_msg > _IDLE_TIMEOUT_S:
# Client has been silent for 60s — close connection
with contextlib.suppress(Exception):
await websocket.close(
code=1000,
reason="Idle timeout",
)
break
except Exception:
logger.exception(
"Heartbeat loop error for session %s",
session.session_id,
session.instance_id,
)
for ws in list(session._websockets):
try:
await ws.close(code=4000, reason="New connection established")
except Exception:
pass # noqa: S110
session._websockets.clear()
finally:
await self._cleanup_session(session)
# Attach new WebSocket
session.attach_websocket(websocket)
# Replay buffer
buffer = session.get_buffer()
if buffer:
try:
await websocket.send_bytes(buffer)
except Exception:
pass # noqa: S110
async def detach_websocket(
self,
session: TerminalSession,
websocket: WebSocket,
) -> None:
"""Detach a WebSocket from a session."""
session.detach_websocket(websocket)
async def reset_session(
self,
instance_id: uuid.UUID,
container_id: str,
startup_command: str | None = None,
session_id: str | None = None,
name: str | None = None,
) -> TerminalSession:
"""Reset a session by killing it and creating a new one.
Args:
instance_id: UUID of the tool instance.
container_id: Docker container ID.
startup_command: Optional startup command.
session_id: Specific session to reset. If None, resets the default session.
name: Optional name to preserve for the new session.
Returns:
The newly created TerminalSession.
"""
instance_id_str = str(instance_id)
target_session_id = session_id or "default"
key = (instance_id_str, target_session_id)
# Preserve old name if not provided
old_name = name
if old_name is None and key in self._sessions:
old_name = self._sessions[key].name
# Close existing session if any
if key in self._sessions:
logger.debug(
"Resetting terminal session %s for instance %s",
target_session_id,
instance_id,
)
old_session = self._sessions.pop(key)
await old_session.close()
# Fire-and-forget DB update for old session
asyncio.create_task(self._mark_closed_in_db(old_session.session_id))
# Create new session preserving the same session_id slot
new_session_id = str(uuid.uuid4())
new_session = TerminalSession(
session_id=new_session_id,
instance_id=instance_id,
container_id=container_id,
startup_command=startup_command,
name=old_name or ("Session 1" if target_session_id == "default" else None),
)
await new_session.start(startup_command=startup_command)
self._sessions[key] = new_session
# Fire-and-forget DB insert
asyncio.create_task(
self._insert_db_session_row(new_session_id, instance_id, new_session.name)
)
return new_session
async def _cleanup_session(self, session: TerminalSession) -> None:
"""Clean up a session."""
if session.session_id in self._sessions:
del self._sessions[session.session_id]
self._last_client_message.pop(session.session_id, None)
await session.close()
async def close_all(self) -> None:
"""Close all active sessions."""
sessions = list(self._sessions.values())
self._sessions.clear()
self._last_client_message.clear()
for session in sessions:
await session.close()
if self._idle_check_task and not self._idle_check_task.done():
self._idle_check_task.cancel()
# Global terminal manager instance
terminal_manager = TerminalManager()
+80 -385
View File
@@ -1,136 +1,44 @@
"""High-performance terminal session with asyncio-native I/O.
Replaces blocking select.select() with event-driven asyncio.add_reader()
for sub-frame latency. Includes output batching and flow control.
"""
"""Terminal session management for tool instances."""
import asyncio
import contextlib
import fcntl
import logging
import os
import pty
import signal
import select
import struct
import fcntl
import time
import termios
import uuid
from collections import deque
from typing import Any
logger = logging.getLogger(__name__)
class TerminalSession:
"""Manages a single terminal session with event-driven PTY I/O.
Uses asyncio.add_reader() instead of polling for near-zero read latency.
Output is batched (2ms window) and sent as binary WebSocket frames.
Flow control prevents memory bloat on fast output.
"""
# Circular buffer for replay (10KB)
BUFFER_SIZE = 10 * 1024
# Idle timeout in seconds (30 minutes)
IDLE_TIMEOUT = 30 * 60
# Output batching window in seconds
BATCH_WINDOW_S = 0.002 # 2ms
# Flow control: pause PTY reads when unacknowledged bytes exceed this
FLOW_CONTROL_PAUSE = 64 * 1024
# Flow control: resume PTY reads when unacknowledged bytes drop below this
FLOW_CONTROL_RESUME = 32 * 1024
# Max WebSocket frame size
MAX_FRAME_SIZE = 64 * 1024
# Session number counter per instance_id for auto-naming
_instance_counters: dict[str, int] = {}
"""Manages a single terminal session connected to a docker container."""
def __init__(
self,
session_id: str,
instance_id: uuid.UUID,
container_id: str,
startup_command: str | None = None,
name: str | None = None,
) -> None:
"""Initialize a terminal session."""
self.session_id = session_id
self.instance_id = instance_id
self.container_id = container_id
self.startup_command = startup_command
self.process: asyncio.subprocess.Process | None = None
self._closed = False
self._master_fd: int | None = None
self._slave_fd: int | None = None
self._echo_enabled = True
self._exit_reason: str | None = None
# Circular buffer for output replay
self._output_buffer: deque[bytes] = deque(maxlen=self.BUFFER_SIZE)
self._buffer_size = 0
# WebSocket connections
self._websockets: set[Any] = set()
# Activity tracking
self.last_activity = time.time()
# Terminal size
self._cols = 80
self._rows = 24
# Session metadata
self.name = name or self._generate_name(str(instance_id))
self.status: str = "active"
# Output batching
self._batch_buffer = bytearray()
self._batch_timer: asyncio.TimerHandle | None = None
self._batch_lock = asyncio.Lock()
# Flow control
self._unacknowledged_bytes = 0
self._paused = False
self._read_handler_set = False
self._flow_control_lock = asyncio.Lock()
# Ack timeout fallback
self._ack_timeout_handle: asyncio.TimerHandle | None = None
@classmethod
def _generate_name(cls, instance_id: str) -> str:
"""Generate an auto-incremented session name for the instance."""
count = cls._instance_counters.get(instance_id, 0) + 1
cls._instance_counters[instance_id] = count
return f"Session {count}"
async def start(self, startup_command: str | None = None) -> None:
async def start(self) -> None:
"""Start the docker exec process with a shell using a PTY."""
# Create a pseudo-terminal on the host
self._master_fd, slave_fd = pty.openpty()
self._master_fd, self._slave_fd = pty.openpty()
self._set_terminal_size(80, 24)
# Set the terminal size initially
self._set_terminal_size(self._cols, self._rows)
logger.debug(
"Starting terminal session %s for container %s with initial size %sx%s",
self.session_id,
self.container_id,
self._cols,
self._rows,
)
# Build the shell command
cmd = startup_command or self.startup_command
if cmd:
shell_cmd = f'bash -c "{cmd}" || true; exec bash -il'
logger.debug(
"Using startup command for session %s: %s",
self.session_id,
cmd,
)
else:
shell_cmd = "bash -il"
# Start docker exec with the slave fd as stdin/stdout/stderr
self.process = await asyncio.create_subprocess_exec(
"docker",
"exec",
@@ -139,287 +47,112 @@ class TerminalSession:
"TERM=xterm-256color",
self.container_id,
"bash",
"-c",
shell_cmd,
stdin=slave_fd,
stdout=slave_fd,
stderr=slave_fd,
"-il",
stdin=self._slave_fd,
stdout=self._slave_fd,
stderr=self._slave_fd,
)
# Close slave fd in parent process
os.close(slave_fd)
os.close(self._slave_fd)
self._slave_fd = None
self._echo_enabled = self._detect_echo_state()
self.last_activity = time.time()
# Start event-driven reading
self._start_reading()
def _start_reading(self) -> None:
"""Register PTY master fd with asyncio event loop for event-driven reads."""
if self._read_handler_set or self._master_fd is None or self._closed:
def _set_terminal_size(self, cols: int, rows: int) -> None:
"""Set the terminal size using TIOCSWINSZ."""
if self._master_fd is None:
return
try:
loop = asyncio.get_event_loop()
loop.add_reader(self._master_fd, self._on_fd_readable)
self._read_handler_set = True
logger.debug("Started event-driven reading for session %s", self.session_id)
except Exception as exc:
logger.error(
"Failed to start reading for session %s: %s", self.session_id, exc
)
tiocswinsz = 0x5414
size = struct.pack("HHHH", rows, cols, 0, 0)
with contextlib.suppress(OSError):
fcntl.ioctl(self._master_fd, tiocswinsz, size)
def _stop_reading(self) -> None:
"""Unregister PTY master fd from asyncio event loop."""
if not self._read_handler_set or self._master_fd is None:
return
def _detect_echo_state(self) -> bool:
"""Detect whether the PTY has echo enabled via termios."""
if self._master_fd is None:
return True
try:
loop = asyncio.get_event_loop()
loop.remove_reader(self._master_fd)
self._read_handler_set = False
except Exception:
pass
attrs = termios.tcgetattr(self._master_fd)
return bool(attrs[3] & termios.ECHO)
except OSError:
return True
def _on_fd_readable(self) -> None:
"""Callback when PTY master fd has data available (called by event loop)."""
async def check_echo_state(self) -> bool | None:
"""Check if echo state changed. Returns new state if changed, None otherwise."""
current = self._detect_echo_state()
if current != self._echo_enabled:
self._echo_enabled = current
return current
return None
@property
def echo_enabled(self) -> bool:
"""Return whether the PTY currently has echo enabled."""
return self._echo_enabled
@property
def closed(self) -> bool:
"""Return whether the session has been closed."""
return self._closed
async def read_output(self, select_timeout: float = 0.1) -> bytes:
"""Read output from the PTY master."""
if self._master_fd is None or self._closed:
return
return b""
try:
data = os.read(self._master_fd, 4096)
except (OSError, IOError) as exc:
logger.debug("PTY read error for session %s: %s", self.session_id, exc)
self._handle_eof()
return
if not data:
# EOF: docker exec process exited
logger.debug("PTY EOF for session %s", self.session_id)
self._handle_eof()
return
self._add_to_buffer(data)
self.last_activity = time.time()
# Queue for batching + flow control
self._queue_output(data)
def _add_to_buffer(self, data: bytes) -> None:
"""Add data to circular buffer, maintaining size limit."""
self._output_buffer.append(data)
self._buffer_size += len(data)
while self._buffer_size > self.BUFFER_SIZE and self._output_buffer:
removed = self._output_buffer.popleft()
self._buffer_size -= len(removed)
def _queue_output(self, data: bytes) -> None:
"""Add output to batch buffer and schedule flush."""
self._batch_buffer.extend(data)
self._unacknowledged_bytes += len(data)
# Check flow control
if self._unacknowledged_bytes > self.FLOW_CONTROL_PAUSE and not self._paused:
self._pause_output()
# Schedule batch flush if not already scheduled
if self._batch_timer is None:
loop = asyncio.get_event_loop()
self._batch_timer = loop.call_later(
self.BATCH_WINDOW_S,
self._flush_batch_sync,
readable, _, _ = select.select(
[self._master_fd],
[],
[],
select_timeout,
)
def _flush_batch_sync(self) -> None:
"""Synchronous entry point for batch flush (called from event loop)."""
self._batch_timer = None
if not self._batch_buffer or not self._websockets:
self._batch_buffer.clear()
return
payload = bytes(self._batch_buffer)
self._batch_buffer.clear()
# Send to all websockets (asyncio.create_task for async send)
dead_sockets = set()
for ws in list(self._websockets):
try:
asyncio.create_task(self._send_bytes(ws, payload))
except Exception:
dead_sockets.add(ws)
if dead_sockets:
self._websockets -= dead_sockets
async def _send_bytes(self, ws: Any, payload: bytes) -> None:
"""Send bytes to a single websocket, catching errors."""
try:
await ws.send_bytes(payload)
except Exception:
self._websockets.discard(ws)
def acknowledge_data(self, char_count: int) -> None:
"""Client acknowledges processing char_count bytes.
Called from the WebSocket handler when the client sends an 'ack' message.
"""
self._unacknowledged_bytes = max(0, self._unacknowledged_bytes - char_count)
if self._paused and self._unacknowledged_bytes < self.FLOW_CONTROL_RESUME:
self._resume_output()
# Reset ack timeout
if self._ack_timeout_handle:
self._ack_timeout_handle.cancel()
loop = asyncio.get_event_loop()
self._ack_timeout_handle = loop.call_later(5.0, self._ack_timeout_fallback)
def _ack_timeout_fallback(self) -> None:
"""If no ack received for 5s, assume client is dead and resume."""
logger.warning(
"Flow control ack timeout for session %s, resuming output",
self.session_id,
)
self._unacknowledged_bytes = 0
if self._paused:
self._resume_output()
def _pause_output(self) -> None:
"""Pause reading from PTY due to flow control."""
self._paused = True
self._stop_reading()
logger.debug(
"Paused output for session %s (%d unacked)",
self.session_id,
self._unacknowledged_bytes,
)
def _resume_output(self) -> None:
"""Resume reading from PTY."""
self._paused = False
self._start_reading()
logger.debug("Resumed output for session %s", self.session_id)
def get_buffer(self) -> bytes:
"""Get buffered output for replay."""
return b"".join(self._output_buffer)
def _handle_eof(self) -> None:
"""Handle PTY EOF: process died, close websockets to force reconnect."""
self._stop_reading()
# Mark process as done so is_alive() returns False
if self.process is not None and self.process.returncode is None:
# Force returncode to a non-None value since the process is dead
# but asyncio.subprocess may not have set it yet
try:
self.process._transport.close() # type: ignore[attr-defined]
except Exception:
pass
# Close all websockets to force frontend reconnection
dead_sockets = set(self._websockets)
self._websockets.clear()
for ws in dead_sockets:
try:
asyncio.create_task(
ws.close(code=4001, reason="Session process exited")
)
except Exception:
pass
logger.info("Session %s EOF handled, websockets closed", self.session_id)
if readable:
return os.read(self._master_fd, 8192)
return b""
except (OSError, ValueError):
return b""
async def write_input(self, data: bytes) -> None:
"""Write input to the PTY master."""
if self._master_fd is None or self._closed:
return
try:
with contextlib.suppress(OSError):
os.write(self._master_fd, data)
self.last_activity = time.time()
except (OSError, IOError) as exc:
logger.debug("PTY write error for session %s: %s", self.session_id, exc)
self._handle_eof()
def _set_terminal_size(self, cols: int, rows: int) -> None:
"""Set the terminal size using TIOCSWINSZ."""
if self._master_fd is None:
logger.warning("Cannot resize: master_fd is None (session not started)")
return
TIOCSWINSZ = 0x5414
size = struct.pack("HHHH", rows, cols, 0, 0)
try:
fcntl.ioctl(self._master_fd, TIOCSWINSZ, size)
logger.debug("Resized PTY to %sx%s (fd=%s)", cols, rows, self._master_fd)
except (OSError, IOError) as e:
logger.error("Failed to resize PTY: %s", e)
async def resize(self, cols: int, rows: int) -> None:
"""Resize the terminal."""
if self._closed:
logger.warning("Cannot resize: session is closed")
return
if cols == self._cols and rows == self._rows:
return
self._cols = cols
self._rows = rows
logger.debug(
"resize() called for session %s: %sx%s", self.session_id, cols, rows
)
self._set_terminal_size(cols, rows)
# Send SIGWINCH to docker exec process
if self.process and self.process.pid:
try:
os.kill(self.process.pid, signal.SIGWINCH)
except ProcessLookupError:
logger.warning("docker exec process %s not found", self.process.pid)
except Exception as e:
logger.warning("Failed to send SIGWINCH: %s", e)
async def reset(self) -> None:
"""Reset the session by killing the process and clearing state."""
self.status = "resetting"
await self.close()
self._closed = False
self._output_buffer.clear()
self._buffer_size = 0
self._websockets.clear()
self._batch_buffer.clear()
self._batch_timer = None
self._unacknowledged_bytes = 0
self._paused = False
self._read_handler_set = False
self.process = None
self._master_fd = None
self.status = "active"
def get_exit_reason(self) -> str | None:
"""Return the reason the session ended, if known."""
return self._exit_reason
async def close(self) -> None:
"""Close the session and cleanup."""
if self._closed:
return
self._closed = True
self.status = "closed"
self._stop_reading()
if self._batch_timer:
self._batch_timer.cancel()
self._batch_timer = None
if self._ack_timeout_handle:
self._ack_timeout_handle.cancel()
self._ack_timeout_handle = None
# Determine exit reason
if self.process is not None and self.process.returncode is not None:
if self.process.returncode == 0:
self._exit_reason = "process_exit"
else:
self._exit_reason = "process_exit"
else:
self._exit_reason = "timeout"
if self._master_fd is not None:
try:
with contextlib.suppress(OSError):
os.close(self._master_fd)
except OSError:
pass
self._master_fd = None
if self.process is not None:
try:
self.process.kill()
await asyncio.wait_for(self.process.wait(), timeout=2.0)
except (asyncio.TimeoutError, ProcessLookupError):
except (TimeoutError, ProcessLookupError):
pass
def is_alive(self) -> bool:
@@ -427,41 +160,3 @@ class TerminalSession:
if self.process is None:
return False
return self.process.returncode is None
def is_idle(self) -> bool:
"""Check if the session has been idle for too long."""
if self._websockets:
return False
return time.time() - self.last_activity > self.IDLE_TIMEOUT
def attach_websocket(self, websocket: Any) -> None:
"""Attach a WebSocket to this session."""
self._websockets.add(websocket)
self.last_activity = time.time()
def detach_websocket(self, websocket: Any) -> None:
"""Detach a WebSocket from this session."""
self._websockets.discard(websocket)
def has_websockets(self) -> bool:
"""Check if any WebSockets are attached."""
return len(self._websockets) > 0
async def send_to_all(self, data: bytes) -> None:
"""Send data to all attached WebSockets (used for control messages)."""
dead_sockets = set()
for ws in self._websockets:
try:
await ws.send_bytes(data)
except Exception:
dead_sockets.add(ws)
for ws in dead_sockets:
self._websockets.discard(ws)
async def read_output(self) -> bytes:
"""Legacy method: read output synchronously.
With event-driven I/O, output is automatically sent to websockets.
This method returns any buffered data for callers that poll.
"""
return b""