feat(host-agent): add optional Appium/Runtime supervisor
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>
This commit is contained in:
2026-07-14 09:28:57 +08:00
co-authored by Claude Opus 4.6
parent 03c7c30067
commit 75879c8a52
12 changed files with 1475 additions and 0 deletions
@@ -173,3 +173,55 @@ def test_console_numeric_fields_reject_invalid_values(
) -> None:
with pytest.raises(HostAgentConfigurationError):
load_host_agent_config(overrides)
def test_dependency_supervisor_defaults_to_disabled() -> None:
config = load_host_agent_config({})
assert config.dependency_supervisor_enabled is False
assert config.appium_supervised is False
assert config.appium_host == "127.0.0.1"
assert config.appium_port == 4723
assert config.runtime_supervised is False
assert config.runtime_host == "127.0.0.1"
assert config.runtime_port == 8000
assert config.dependency_restart_max_attempts == 5
def test_dependency_supervisor_env_vars_parse_bool_and_numeric_fields() -> None:
config = load_host_agent_config(
{
"HOST_AGENT_DEPENDENCY_SUPERVISOR_ENABLED": "true",
"HOST_AGENT_APPIUM_SUPERVISED": "1",
"HOST_AGENT_APPIUM_HOST": "0.0.0.0",
"HOST_AGENT_APPIUM_PORT": "4724",
"HOST_AGENT_RUNTIME_SUPERVISED": "true",
"HOST_AGENT_RUNTIME_HOST": "localhost",
"HOST_AGENT_RUNTIME_PORT": "8001",
"HOST_AGENT_DEPENDENCY_RESTART_MAX_ATTEMPTS": "8",
}
)
assert config.dependency_supervisor_enabled is True
assert config.appium_supervised is True
assert config.appium_host == "0.0.0.0"
assert config.appium_port == 4724
assert config.runtime_supervised is True
assert config.runtime_host == "localhost"
assert config.runtime_port == 8001
assert config.dependency_restart_max_attempts == 8
@pytest.mark.parametrize(
"overrides",
[
{"HOST_AGENT_APPIUM_PORT": "0"},
{"HOST_AGENT_RUNTIME_PORT": "not-a-number"},
{"HOST_AGENT_DEPENDENCY_RESTART_MAX_ATTEMPTS": "-1"},
],
)
def test_dependency_supervisor_numeric_fields_reject_invalid_values(
overrides: dict[str, str],
) -> None:
with pytest.raises(HostAgentConfigurationError):
load_host_agent_config(overrides)