Tests / Test failed: 2, passed: 691
Adds an opt-in dependency supervisor inside the Host Agent that probes,
spawns, and restarts the two local processes the macOS single-machine
real-device workflow depends on: the Appium server (gates Driver.connect())
and the local Runtime API (local inspection). Default-off; gated by
HOST_AGENT_DEPENDENCY_SUPERVISOR_ENABLED plus per-dependency *_SUPERVISED
flags.
Mitigates the live-incident failure mode where forgetting to start Appium
silently keeps devices offline and tasks queued forever with no error
surfaced in Host Agent logs.
Behavior (per openspec change):
- Adopt-don't-fight: probe (TCP + dependency-specific HTTP health check)
before spawn. Healthy listener → adopted (never killed/restarted).
Unhealthy listener → port-conflict error, skip. No listener → spawn.
- Only supervisor-spawned processes are restarted on crash, with capped
exponential backoff (1s/2s/4s/8s, capped at 30s) and a per-process-lifetime
attempt ceiling (HOST_AGENT_DEPENDENCY_RESTART_MAX_ATTEMPTS, default 5).
- Spawn failures (e.g. missing executable) logged distinctly from crashes.
- Graceful stop terminates only spawned children; adopted processes untouched.
- Supervisor starts before the heartbeat loop's first connect_devices() pass
and stops alongside existing heartbeat/console teardown.
Validation: ruff check + format clean, compileall clean, openspec validate
--strict valid. Non-integration suite 503 passed / 44 deselected / 2 failed
(both failures pre-existing from unrelated 03c7c30 LLM_PROVIDER_ENC_KEY;
verified by stashing this change). macOS real-device manual verification
(task 6.4) deferred to a macOS host.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
210 lines
6.7 KiB
Python
210 lines
6.7 KiB
Python
from __future__ import annotations
|
|
|
|
import os
|
|
from collections.abc import Mapping
|
|
from dataclasses import dataclass, field
|
|
from pathlib import Path
|
|
from urllib.parse import urlparse
|
|
|
|
|
|
class HostAgentConfigurationError(ValueError):
|
|
"""Raised when Host Agent process configuration is invalid."""
|
|
|
|
|
|
_LOOPBACK_BIND_HOSTS = frozenset({"127.0.0.1", "localhost", "::1"})
|
|
_AI_PLANNER_TRANSPORTS = frozenset({"direct", "cloud"})
|
|
|
|
|
|
@dataclass(frozen=True)
|
|
class HostAgentConfig:
|
|
control_plane_url: str
|
|
host_id: str = ""
|
|
token: str = field(default="", repr=False)
|
|
identity_path: Path = Path("tasks/host_identity.json")
|
|
local_account_path: Path = Path("tasks/host_local_account.json")
|
|
enrollment_managed: bool = False
|
|
display_name: str | None = None
|
|
heartbeat_interval_seconds: float = 30.0
|
|
poll_timeout_seconds: float = 20.0
|
|
retry_backoff_seconds: float = 1.0
|
|
max_retry_backoff_seconds: float = 30.0
|
|
max_retry_attempts: int = 5
|
|
console_bind_host: str = "127.0.0.1"
|
|
console_port: int = 8765
|
|
console_allow_non_loopback: bool = False
|
|
console_session_ttl_seconds: float = 43200.0
|
|
console_history_limit: int = 200
|
|
ai_planner_transport: str = "direct"
|
|
dependency_supervisor_enabled: bool = False
|
|
appium_supervised: bool = False
|
|
appium_host: str = "127.0.0.1"
|
|
appium_port: int = 4723
|
|
runtime_supervised: bool = False
|
|
runtime_host: str = "127.0.0.1"
|
|
runtime_port: int = 8000
|
|
dependency_restart_max_attempts: int = 5
|
|
|
|
|
|
def load_host_agent_config(
|
|
env: Mapping[str, str] | None = None,
|
|
) -> HostAgentConfig:
|
|
values = os.environ if env is None else env
|
|
control_plane_url = (
|
|
values.get(
|
|
"HOST_AGENT_CONTROL_PLANE_URL",
|
|
"https://amcp.home.jerryyan.top",
|
|
)
|
|
.strip()
|
|
.rstrip("/")
|
|
)
|
|
parsed_url = urlparse(control_plane_url)
|
|
if parsed_url.scheme not in {"http", "https"} or not parsed_url.netloc:
|
|
raise HostAgentConfigurationError(
|
|
"HOST_AGENT_CONTROL_PLANE_URL must be an HTTP(S) URL"
|
|
)
|
|
|
|
identity_path = Path(
|
|
values.get("HOST_AGENT_IDENTITY_PATH", "tasks/host_identity.json").strip()
|
|
)
|
|
local_account_path = Path(
|
|
values.get(
|
|
"HOST_AGENT_LOCAL_ACCOUNT_PATH", "tasks/host_local_account.json"
|
|
).strip()
|
|
)
|
|
|
|
config = HostAgentConfig(
|
|
control_plane_url=control_plane_url,
|
|
identity_path=identity_path,
|
|
local_account_path=local_account_path,
|
|
enrollment_managed=True,
|
|
display_name=values.get("HOST_AGENT_DISPLAY_NAME") or None,
|
|
heartbeat_interval_seconds=_positive_float(
|
|
values,
|
|
"HOST_AGENT_HEARTBEAT_INTERVAL_SECONDS",
|
|
30.0,
|
|
),
|
|
poll_timeout_seconds=_positive_float(
|
|
values,
|
|
"HOST_AGENT_POLL_TIMEOUT_SECONDS",
|
|
20.0,
|
|
),
|
|
retry_backoff_seconds=_positive_float(
|
|
values,
|
|
"HOST_AGENT_RETRY_BACKOFF_SECONDS",
|
|
1.0,
|
|
),
|
|
max_retry_backoff_seconds=_positive_float(
|
|
values,
|
|
"HOST_AGENT_MAX_RETRY_BACKOFF_SECONDS",
|
|
30.0,
|
|
),
|
|
max_retry_attempts=_positive_int(
|
|
values,
|
|
"HOST_AGENT_MAX_RETRY_ATTEMPTS",
|
|
5,
|
|
),
|
|
console_bind_host=values.get(
|
|
"HOST_AGENT_CONSOLE_BIND_HOST", "127.0.0.1"
|
|
).strip(),
|
|
console_port=_positive_int(values, "HOST_AGENT_CONSOLE_PORT", 8765),
|
|
console_allow_non_loopback=_truthy(
|
|
values, "HOST_AGENT_CONSOLE_ALLOW_NON_LOOPBACK", False
|
|
),
|
|
console_session_ttl_seconds=_positive_float(
|
|
values,
|
|
"HOST_AGENT_CONSOLE_SESSION_TTL_SECONDS",
|
|
43200.0,
|
|
),
|
|
console_history_limit=_positive_int(
|
|
values,
|
|
"HOST_AGENT_CONSOLE_HISTORY_LIMIT",
|
|
200,
|
|
),
|
|
ai_planner_transport=_parse_ai_planner_transport(
|
|
values.get("AI_PLANNER_TRANSPORT")
|
|
),
|
|
dependency_supervisor_enabled=_truthy(
|
|
values, "HOST_AGENT_DEPENDENCY_SUPERVISOR_ENABLED", False
|
|
),
|
|
appium_supervised=_truthy(values, "HOST_AGENT_APPIUM_SUPERVISED", False),
|
|
appium_host=values.get("HOST_AGENT_APPIUM_HOST", "127.0.0.1").strip(),
|
|
appium_port=_positive_int(values, "HOST_AGENT_APPIUM_PORT", 4723),
|
|
runtime_supervised=_truthy(values, "HOST_AGENT_RUNTIME_SUPERVISED", False),
|
|
runtime_host=values.get("HOST_AGENT_RUNTIME_HOST", "127.0.0.1").strip(),
|
|
runtime_port=_positive_int(values, "HOST_AGENT_RUNTIME_PORT", 8000),
|
|
dependency_restart_max_attempts=_positive_int(
|
|
values, "HOST_AGENT_DEPENDENCY_RESTART_MAX_ATTEMPTS", 5
|
|
),
|
|
)
|
|
if config.max_retry_backoff_seconds < config.retry_backoff_seconds:
|
|
raise HostAgentConfigurationError(
|
|
"maximum retry backoff must not be less than initial backoff"
|
|
)
|
|
if (
|
|
config.console_bind_host not in _LOOPBACK_BIND_HOSTS
|
|
and not config.console_allow_non_loopback
|
|
):
|
|
raise HostAgentConfigurationError(
|
|
"HOST_AGENT_CONSOLE_BIND_HOST must be a loopback address "
|
|
f"({', '.join(sorted(_LOOPBACK_BIND_HOSTS))}) unless "
|
|
"HOST_AGENT_CONSOLE_ALLOW_NON_LOOPBACK is set"
|
|
)
|
|
return config
|
|
|
|
|
|
def _parse_ai_planner_transport(value: str | None) -> str:
|
|
if value is None:
|
|
return "direct"
|
|
transport = value.strip().lower()
|
|
if transport not in _AI_PLANNER_TRANSPORTS:
|
|
raise HostAgentConfigurationError(
|
|
"AI_PLANNER_TRANSPORT must be one of "
|
|
f"{', '.join(sorted(_AI_PLANNER_TRANSPORTS))}"
|
|
)
|
|
return transport
|
|
|
|
|
|
def _positive_float(
|
|
values: Mapping[str, str],
|
|
name: str,
|
|
default: float,
|
|
) -> float:
|
|
raw_value = values.get(name)
|
|
if raw_value is None:
|
|
return default
|
|
try:
|
|
value = float(raw_value)
|
|
except ValueError as exc:
|
|
raise HostAgentConfigurationError(f"{name} must be a number") from exc
|
|
if value <= 0:
|
|
raise HostAgentConfigurationError(f"{name} must be greater than zero")
|
|
return value
|
|
|
|
|
|
def _positive_int(
|
|
values: Mapping[str, str],
|
|
name: str,
|
|
default: int,
|
|
) -> int:
|
|
raw_value = values.get(name)
|
|
if raw_value is None:
|
|
return default
|
|
try:
|
|
value = int(raw_value)
|
|
except ValueError as exc:
|
|
raise HostAgentConfigurationError(f"{name} must be an integer") from exc
|
|
if value <= 0:
|
|
raise HostAgentConfigurationError(f"{name} must be greater than zero")
|
|
return value
|
|
|
|
|
|
def _truthy(
|
|
values: Mapping[str, str],
|
|
name: str,
|
|
default: bool,
|
|
) -> bool:
|
|
raw_value = values.get(name)
|
|
if raw_value is None:
|
|
return default
|
|
return raw_value.strip().lower() in {"true", "1"}
|