atlas-iac/testing/tests/test_hermes_execution_pool_mediator.py
2026-09-01 20:43:50 -03:00

448 lines
16 KiB
Python

"""Isolated mediator, SCM gate, and model-facing API contracts."""
from __future__ import annotations
import json
import subprocess
import sys
import threading
import urllib.error
import urllib.request
from pathlib import Path
import pytest
ROOT = Path(__file__).parents[2]
SCRIPTS = ROOT / "services/hermes/scripts"
SCM_SCRIPTS = ROOT / "services/hermes/scm-common/scripts"
sys.path[:0] = [str(SCRIPTS), str(SCM_SCRIPTS)]
import execution_pool_client as client # noqa: E402
import execution_pool_protocol as protocol # noqa: E402
import execution_pool_scm as scm # noqa: E402
KEY = b"d" * 64
RESULT = {
"status": "completed",
"summary": "Completed safely.",
"changed_files": ["safe.py"],
"tests_run": ["pytest"],
"artifacts": [],
"findings": [],
"blockers": [],
}
def binding(**changes):
value = {
"board": "metis", "task_id": "t_deadbeef", "run_id": "42",
"worker_ordinal": 0, "attempt": 1,
}
value.update(changes)
return value
def payload(**changes):
value = {
"context": "safe objective",
"repo_url": "https://scm.bstein.dev/titan/metis.git",
"branch": "wt/t_deadbeef",
"base_branch": "main",
}
value.update(changes)
return value
def assignment(**payload_changes):
return protocol.sign_envelope(
KEY, "assignment", binding(), payload(**payload_changes)
)
class Response:
def __init__(self, body):
self.body = body
def __enter__(self):
return self
def __exit__(self, *_args):
return False
def read(self, _size=-1):
return self.body
class FakeSCM:
def __init__(self):
self.submitted = []
def checkout(self, _envelope):
return {"workspace": "/workspace/run", "baseline_sha": "a" * 40}
def submit(self, envelope, request):
self.submitted.append((envelope, request))
return {"pull_request": "https://scm.bstein.dev/titan/metis/pulls/7"}
def test_result_schema_validation_rejects_every_unsafe_shape():
invalid = [
None,
{},
{"structured": []},
{"structured": {**RESULT, "extra": True}},
{"structured": {**RESULT, "status": "unknown"}},
{"structured": {**RESULT, "summary": ""}},
{"structured": {**RESULT, "tests_run": "pytest"}},
{"structured": {**RESULT, "tests_run": [7]}},
]
for value in invalid:
with pytest.raises(protocol.ProtocolError):
client._validate_result(value)
assert client._validate_result({"structured": dict(RESULT)})["structured"] == RESULT
def test_client_post_verifies_response_and_bounds_body(monkeypatch):
boundary = client.ClientBoundary(KEY, FakeSCM())
ack = protocol.sign_envelope(KEY, "ack", binding(), {"accepted": True})
monkeypatch.setattr(client.urllib.request, "urlopen", lambda *_a, **_k: Response(protocol.canonical_json(ack)))
assert boundary._post("/v1/result", ack)["kind"] == "ack"
monkeypatch.setattr(
client.urllib.request,
"urlopen",
lambda *_a, **_k: Response(b"x" * (protocol.MAX_WIRE_BYTES + 1)),
)
with pytest.raises(protocol.ProtocolError, match="exceeds"):
boundary._post("/v1/result", ack)
def test_poll_materializes_only_ordinal_owned_assignment(monkeypatch):
monkeypatch.setattr(client, "ORDINAL", 0)
boundary = client.ClientBoundary(KEY, FakeSCM())
boundary._post = lambda *_a: protocol.sign_envelope(
KEY,
"ack",
binding(board="", task_id="", run_id="", attempt=0),
{"assignment": None},
)
assert boundary.poll() == {"assignment": None}
boundary._post = lambda *_a: assignment()
result = boundary.poll()["assignment"]
assert result["workspace"] == "/workspace/run"
assert result["protocol_version"] == 2
assert "signature" not in result
boundary._post = lambda *_a: protocol.sign_envelope(
KEY, "assignment", binding(worker_ordinal=1), payload()
)
with pytest.raises(protocol.ProtocolError, match="foreign"):
boundary.poll()
def test_heartbeat_and_finish_require_exact_current_binding(monkeypatch):
fake_scm = FakeSCM()
boundary = client.ClientBoundary(KEY, fake_scm)
current = assignment()
boundary.current = current
def post(path, envelope):
kind = "heartbeat" if path.endswith("heartbeat") else "result"
protocol.verify_envelope(KEY, envelope, expected_kind=kind)
return protocol.sign_envelope(
KEY, "ack", binding(), {"accepted": True, "duplicate": False}
)
boundary._post = post
assert boundary.heartbeat(
{"binding": binding(), "payload": {"note": "active"}}
)["ack"]["accepted"]
request = {
"binding": binding(),
"payload": {"structured": dict(RESULT), "returncode": 0},
"title": "Safe change",
"body": "Evidence",
}
finished = boundary.finish(request)
assert finished["ack"]["accepted"] and boundary.current is None
assert fake_scm.submitted
assert finished["structured"]["artifacts"] == [
"https://scm.bstein.dev/titan/metis/pulls/7"
]
boundary.current = current
with pytest.raises(protocol.ProtocolError, match="heartbeat payload"):
boundary.heartbeat({"binding": binding(), "payload": "bad"})
with pytest.raises(protocol.ProtocolError, match="object"):
boundary._current_for(None)
with pytest.raises(protocol.ProtocolError, match="does not own"):
boundary._current_for(binding(attempt=2))
def test_noncompleted_finish_never_invokes_scm_and_bad_ack_is_rejected():
fake_scm = FakeSCM()
boundary = client.ClientBoundary(KEY, fake_scm)
boundary.current = assignment()
bad = protocol.sign_envelope(KEY, "ack", binding(attempt=2), {"accepted": True})
boundary._post = lambda *_a: bad
blocked = {**RESULT, "status": "blocked", "blockers": ["capacity"]}
with pytest.raises(protocol.ProtocolError, match="binding changed"):
boundary.finish(
{"binding": binding(), "payload": {"structured": blocked, "returncode": 1}}
)
assert fake_scm.submitted == []
boundary._post = lambda *_a: protocol.sign_envelope(
KEY, "result", binding(), {"accepted": True}
)
with pytest.raises(protocol.ProtocolError, match="binding changed"):
boundary.heartbeat({"binding": binding(), "payload": {}})
def http_request(handler, path, *, body=None):
server = protocol.BoundedHTTPServer(("127.0.0.1", 0), handler, max_workers=2)
thread = threading.Thread(target=server.handle_request)
thread.start()
request = urllib.request.Request(
f"http://127.0.0.1:{server.server_port}{path}",
data=body,
method="POST" if body is not None else "GET",
headers={"Content-Type": "application/json"},
)
try:
with urllib.request.urlopen(request, timeout=3) as response:
return response.status, json.loads(response.read())
except urllib.error.HTTPError as error:
return error.code, json.loads(error.read())
finally:
thread.join(timeout=3)
server.server_close()
def test_model_api_exposes_only_gated_state_machine_operations():
class Boundary:
poll = staticmethod(lambda: {"assignment": None})
heartbeat = staticmethod(lambda request: {"heartbeat": request["payload"]})
finish = staticmethod(lambda request: {"finish": request["payload"]})
handler = client.handler_factory(Boundary())
assert http_request(handler, "/ready") == (
200, {"protocol_version": 2, "ready": True}
)
assert http_request(handler, "/missing")[0] == 404
for operation in ("poll", "heartbeat", "finish"):
body = protocol.canonical_json(
{"operation": operation, "binding": binding(), "payload": {}}
)
assert http_request(handler, "/v1/client", body=body)[0] == 200
for value in (
{"operation": "bypass"},
{"operation": "poll", "authority": "steal"},
):
status, response = http_request(
handler, "/v1/client", body=protocol.canonical_json(value)
)
assert status == 409 and response.get("error")
def test_client_main_validates_ordinal_and_starts_bounded_server(monkeypatch):
monkeypatch.setattr(client, "ORDINAL", -1)
with pytest.raises(SystemExit, match="ORDINAL"):
client.main()
started = []
class Server:
def __init__(self, address, _handler, max_workers):
started.append((address, max_workers))
def serve_forever(self):
return
monkeypatch.setattr(client, "ORDINAL", 2)
monkeypatch.setattr(client, "read_key", lambda _path: KEY)
monkeypatch.setattr(client, "BoundedHTTPServer", Server)
monkeypatch.setattr(client, "SCMBoundary", lambda _key: FakeSCM())
assert client.main() == 0
assert started == [(("0.0.0.0", client.PORT), 4)]
def init_checkout(path, branch="wt/t_deadbeef"):
subprocess.run(["git", "init", "-q", str(path)], check=True)
commands = [
("remote", "add", "origin", "https://scm.bstein.dev/titan/metis.git"),
(
"remote",
"add",
"hermes-broker",
"http://hermes-scm-broker.hermes-scm.svc.cluster.local:9081/"
"git/atlas/metis.git",
),
("checkout", "-qb", branch),
("config", "user.email", "test@example.com"),
("config", "user.name", "Test"),
]
for command in commands:
subprocess.run(["git", "-C", str(path), *command], check=True)
(path / "tracked").write_text("safe\n")
subprocess.run(["git", "-C", str(path), "add", "tracked"], check=True)
subprocess.run(["git", "-C", str(path), "commit", "-qm", "initial"], check=True)
return subprocess.check_output(
["git", "-C", str(path), "rev-parse", "HEAD"], text=True
).strip()
def test_scm_run_and_binding_validation(tmp_path, monkeypatch):
checkout = tmp_path / "checkout"
head = init_checkout(checkout)
assert scm._run("rev-parse", "HEAD", cwd=checkout) == head
with pytest.raises(RuntimeError):
scm._run("rev-parse", "missing", cwd=checkout)
monkeypatch.setattr(scm, "MAX_STATUS_BYTES", 1)
with pytest.raises(protocol.ProtocolError, match="output"):
scm._run("rev-parse", "HEAD", cwd=checkout)
monkeypatch.setattr(scm, "ORDINAL", 0)
assert scm._binding(assignment())[1:] == ("metis", "wt/t_deadbeef", "main")
for envelope in (
{**assignment(), "kind": "result"},
{**assignment(), "payload": []},
assignment(repo_url="https://evil.example/metis.git"),
assignment(branch="main"),
assignment(base_branch="../main"),
protocol.sign_envelope(KEY, "assignment", binding(worker_ordinal=1), payload()),
):
with pytest.raises(protocol.ProtocolError):
scm._binding(envelope)
def test_scm_private_paths_and_text_are_bounded(tmp_path, monkeypatch):
monkeypatch.setattr(scm, "WORKSPACE_ROOT", tmp_path / "workspace")
monkeypatch.setattr(scm, "SCM_ROOT", tmp_path / "state")
target = scm.workspace_path(assignment())
assert target.name == "42"
assert scm._state_path(assignment()).name == "metis-t_deadbeef-42.json"
bad = {**assignment(), "task_id": "../bad"}
with pytest.raises(protocol.ProtocolError, match="binding"):
scm.workspace_path(bad)
state = tmp_path / "regular"
state.write_text("safe")
assert scm._regular_text(state, 10) == "safe"
with pytest.raises(protocol.ProtocolError, match="invalid"):
scm._regular_text(state, 1)
binary = tmp_path / "binary"
binary.write_bytes(b"\xff")
with pytest.raises(protocol.ProtocolError, match="malformed"):
scm._regular_text(binary, 10)
linked_state = tmp_path / "linked-state"
linked_state.mkdir()
(tmp_path / "state-link").symlink_to(linked_state, target_is_directory=True)
monkeypatch.setattr(scm, "SCM_ROOT", tmp_path / "state-link")
with pytest.raises(protocol.ProtocolError):
scm._state_path(assignment())
def test_boundary_verification_existing_checkout_and_missing_baseline(tmp_path, monkeypatch):
workspace = tmp_path / "workspace"
state_root = tmp_path / "state"
monkeypatch.setattr(scm, "WORKSPACE_ROOT", workspace)
monkeypatch.setattr(scm, "SCM_ROOT", state_root)
monkeypatch.setattr(scm, "ORDINAL", 0)
boundary = scm.Boundary(KEY)
assert boundary.verify(assignment())["kind"] == "assignment"
destination = scm.workspace_path(assignment())
baseline = init_checkout(destination)
protocol.atomic_json(
scm._state_path(assignment()),
{"baseline_sha": baseline, "repo": "metis", "branch": "wt/t_deadbeef"},
)
assert boundary.checkout(assignment())["baseline_sha"] == baseline
scm._state_path(assignment()).write_text("{}")
with pytest.raises(protocol.ProtocolError, match="baseline"):
boundary.checkout(assignment())
@pytest.mark.parametrize("feature_exists", [True, False])
def test_new_checkout_uses_broker_and_safe_base_fallback(
tmp_path, monkeypatch, feature_exists
):
monkeypatch.setattr(scm, "WORKSPACE_ROOT", tmp_path / "workspace")
monkeypatch.setattr(scm, "SCM_ROOT", tmp_path / "state")
monkeypatch.setattr(scm, "ORDINAL", 0)
calls = []
def run(*arguments, cwd=None, timeout=300):
calls.append((arguments, cwd, timeout))
if arguments[0] == "clone":
branch = arguments[arguments.index("--branch") + 1]
destination = Path(arguments[-1])
if branch == "wt/t_deadbeef" and not feature_exists:
raise RuntimeError("missing branch")
(destination / ".git").mkdir(parents=True)
return ""
monkeypatch.setattr(scm, "_run", run)
monkeypatch.setattr(scm, "_workspace_identity", lambda *_a: "a" * 40)
result = scm.Boundary(KEY).checkout(assignment())
assert result["baseline_sha"] == "a" * 40
assert any("hermes-scm-broker" in str(call) for call in calls)
if not feature_exists:
assert any(call[0][0] == "checkout" for call in calls)
def test_failed_clone_never_deletes_unmanaged_state(tmp_path, monkeypatch):
monkeypatch.setattr(scm, "WORKSPACE_ROOT", tmp_path / "workspace")
monkeypatch.setattr(scm, "SCM_ROOT", tmp_path / "state")
monkeypatch.setattr(scm, "ORDINAL", 0)
def fail(*arguments, **_kwargs):
destination = Path(arguments[-1])
destination.mkdir(parents=True, exist_ok=True)
(destination / "preserved").write_text("owner data")
raise RuntimeError("clone failed")
monkeypatch.setattr(scm, "_run", fail)
with pytest.raises(protocol.ProtocolError, match="unmanaged"):
scm.Boundary(KEY).checkout(assignment())
assert (scm.workspace_path(assignment()) / "preserved").read_text() == "owner data"
def test_draft_reuse_create_and_submit_gates(tmp_path, monkeypatch):
existing = json.dumps([{"html_url": "https://scm/pulls/1"}]).encode()
monkeypatch.setattr(scm.scm_broker_client, "read", lambda _path: existing)
assert scm.Boundary._draft("metis", "wt/task", "main", "a" * 40, "t", "b") == "https://scm/pulls/1"
monkeypatch.setattr(scm.scm_broker_client, "read", lambda _path: b"[]")
monkeypatch.setattr(
scm.scm_broker_client, "create_draft",
lambda *_a, **_k: json.dumps({"html_url": "https://scm/pulls/2"}).encode(),
)
assert scm.Boundary._draft("metis", "wt/task", "main", "a" * 40, "t", "b") == "https://scm/pulls/2"
monkeypatch.setattr(scm, "WORKSPACE_ROOT", tmp_path / "workspace")
monkeypatch.setattr(scm, "SCM_ROOT", tmp_path / "state")
monkeypatch.setattr(scm, "ORDINAL", 0)
destination = scm.workspace_path(assignment())
destination.mkdir(parents=True)
state = scm._state_path(assignment())
protocol.atomic_json(state, {"baseline_sha": "a" * 40})
boundary = scm.Boundary(KEY)
monkeypatch.setattr(scm, "_workspace_identity", lambda *_a: "b" * 40)
outputs = {"status": "", "rev-list": "1", "push": ""}
def run(*arguments, **_kwargs):
return outputs.get(arguments[0], "")
monkeypatch.setattr(scm, "_run", run)
monkeypatch.setattr(boundary, "_draft", lambda *_a: "https://scm/pulls/3")
result = boundary.submit(assignment(), {"title": "safe", "body": "evidence"})
assert result["pull_request"] == "https://scm/pulls/3"
outputs["status"] = "?? untracked"
with pytest.raises(protocol.ProtocolError, match="uncommitted"):
boundary.submit(assignment(), {})
outputs["status"] = ""
outputs["rev-list"] = "0"
assert boundary.submit(assignment(), {})["pull_request"] == ""
with pytest.raises(protocol.ProtocolError, match="metadata"):
boundary.submit(assignment(), {"title": "x" * 513, "body": "x"})