dd7921d514
Salvaged from PR #1470 by adavyas. Core fix: Honcho tool calls in a multi-session gateway could route to the wrong session because honcho_tools.py relied on process-global state. Now threads session context through the call chain: AIAgent._invoke_tool() → handle_function_call() → registry.dispatch() → handler **kw → _resolve_session_context() Changes: - Add _resolve_session_context() to prefer per-call context over globals - Plumb honcho_manager + honcho_session_key through handle_function_call - Add sync_honcho=False to run_conversation() for synthetic flush turns - Pass honcho_session_key through gateway memory flush lifecycle - Harden gateway PID detection when /proc cmdline is unreadable - Make interrupt test scripts import-safe for pytest-xdist - Wrap BibTeX examples in Jekyll raw blocks for docs build - Fix thread-order-dependent assertion in client lifecycle test - Expand Honcho docs: session isolation, lifecycle, routing internals Dropped from original PR: - Indentation change in _create_request_openai_client that would move client creation inside the lock (causes unnecessary contention) Co-authored-by: adavyas <adavyas@users.noreply.github.com>
118 lines
4.7 KiB
Python
118 lines
4.7 KiB
Python
"""Tests for gateway runtime status tracking."""
|
|
|
|
import json
|
|
import os
|
|
|
|
from gateway import status
|
|
|
|
|
|
class TestGatewayPidState:
|
|
def test_write_pid_file_records_gateway_metadata(self, tmp_path, monkeypatch):
|
|
monkeypatch.setenv("HERMES_HOME", str(tmp_path))
|
|
|
|
status.write_pid_file()
|
|
|
|
payload = json.loads((tmp_path / "gateway.pid").read_text())
|
|
assert payload["pid"] == os.getpid()
|
|
assert payload["kind"] == "hermes-gateway"
|
|
assert isinstance(payload["argv"], list)
|
|
assert payload["argv"]
|
|
|
|
def test_get_running_pid_rejects_live_non_gateway_pid(self, tmp_path, monkeypatch):
|
|
monkeypatch.setenv("HERMES_HOME", str(tmp_path))
|
|
pid_path = tmp_path / "gateway.pid"
|
|
pid_path.write_text(str(os.getpid()))
|
|
|
|
assert status.get_running_pid() is None
|
|
assert not pid_path.exists()
|
|
|
|
def test_get_running_pid_accepts_gateway_metadata_when_cmdline_unavailable(self, tmp_path, monkeypatch):
|
|
monkeypatch.setenv("HERMES_HOME", str(tmp_path))
|
|
pid_path = tmp_path / "gateway.pid"
|
|
pid_path.write_text(json.dumps({
|
|
"pid": os.getpid(),
|
|
"kind": "hermes-gateway",
|
|
"argv": ["python", "-m", "hermes_cli.main", "gateway"],
|
|
"start_time": 123,
|
|
}))
|
|
|
|
monkeypatch.setattr(status.os, "kill", lambda pid, sig: None)
|
|
monkeypatch.setattr(status, "_get_process_start_time", lambda pid: 123)
|
|
monkeypatch.setattr(status, "_read_process_cmdline", lambda pid: None)
|
|
|
|
assert status.get_running_pid() == os.getpid()
|
|
|
|
|
|
class TestGatewayRuntimeStatus:
|
|
def test_write_runtime_status_records_platform_failure(self, tmp_path, monkeypatch):
|
|
monkeypatch.setenv("HERMES_HOME", str(tmp_path))
|
|
|
|
status.write_runtime_status(
|
|
gateway_state="startup_failed",
|
|
exit_reason="telegram conflict",
|
|
platform="telegram",
|
|
platform_state="fatal",
|
|
error_code="telegram_polling_conflict",
|
|
error_message="another poller is active",
|
|
)
|
|
|
|
payload = status.read_runtime_status()
|
|
assert payload["gateway_state"] == "startup_failed"
|
|
assert payload["exit_reason"] == "telegram conflict"
|
|
assert payload["platforms"]["telegram"]["state"] == "fatal"
|
|
assert payload["platforms"]["telegram"]["error_code"] == "telegram_polling_conflict"
|
|
assert payload["platforms"]["telegram"]["error_message"] == "another poller is active"
|
|
|
|
|
|
class TestScopedLocks:
|
|
def test_acquire_scoped_lock_rejects_live_other_process(self, tmp_path, monkeypatch):
|
|
monkeypatch.setenv("HERMES_GATEWAY_LOCK_DIR", str(tmp_path / "locks"))
|
|
lock_path = tmp_path / "locks" / "telegram-bot-token-2bb80d537b1da3e3.lock"
|
|
lock_path.parent.mkdir(parents=True, exist_ok=True)
|
|
lock_path.write_text(json.dumps({
|
|
"pid": 99999,
|
|
"start_time": 123,
|
|
"kind": "hermes-gateway",
|
|
}))
|
|
|
|
monkeypatch.setattr(status.os, "kill", lambda pid, sig: None)
|
|
monkeypatch.setattr(status, "_get_process_start_time", lambda pid: 123)
|
|
|
|
acquired, existing = status.acquire_scoped_lock("telegram-bot-token", "secret", metadata={"platform": "telegram"})
|
|
|
|
assert acquired is False
|
|
assert existing["pid"] == 99999
|
|
|
|
def test_acquire_scoped_lock_replaces_stale_record(self, tmp_path, monkeypatch):
|
|
monkeypatch.setenv("HERMES_GATEWAY_LOCK_DIR", str(tmp_path / "locks"))
|
|
lock_path = tmp_path / "locks" / "telegram-bot-token-2bb80d537b1da3e3.lock"
|
|
lock_path.parent.mkdir(parents=True, exist_ok=True)
|
|
lock_path.write_text(json.dumps({
|
|
"pid": 99999,
|
|
"start_time": 123,
|
|
"kind": "hermes-gateway",
|
|
}))
|
|
|
|
def fake_kill(pid, sig):
|
|
raise ProcessLookupError
|
|
|
|
monkeypatch.setattr(status.os, "kill", fake_kill)
|
|
|
|
acquired, existing = status.acquire_scoped_lock("telegram-bot-token", "secret", metadata={"platform": "telegram"})
|
|
|
|
assert acquired is True
|
|
payload = json.loads(lock_path.read_text())
|
|
assert payload["pid"] == os.getpid()
|
|
assert payload["metadata"]["platform"] == "telegram"
|
|
|
|
def test_release_scoped_lock_only_removes_current_owner(self, tmp_path, monkeypatch):
|
|
monkeypatch.setenv("HERMES_GATEWAY_LOCK_DIR", str(tmp_path / "locks"))
|
|
|
|
acquired, _ = status.acquire_scoped_lock("telegram-bot-token", "secret", metadata={"platform": "telegram"})
|
|
assert acquired is True
|
|
lock_path = tmp_path / "locks" / "telegram-bot-token-2bb80d537b1da3e3.lock"
|
|
assert lock_path.exists()
|
|
|
|
status.release_scoped_lock("telegram-bot-token", "secret")
|
|
assert not lock_path.exists()
|