Files
stack/packages/mosaic/src/lease-broker/recovery_runtime_unittest.py
jason.woltje 2509eb7646
All checks were successful
ci/woodpecker/push/publish Pipeline was successful
ci/woodpecker/push/ci Pipeline was successful
WI-6 (#833): constrained recovery command + mosaic-context-refresh skill wrapper (#846)
2026-07-20 03:33:00 +00:00

283 lines
12 KiB
Python

#!/usr/bin/env python3
"""RED-first B1/B2 runtime-boundary contracts for constrained recovery.
Every runtime process in these tests is a fresh child against a private daemon
and Unix sockets. They do not activate a live Mosaic daemon or model stream.
"""
from __future__ import annotations
import base64
import hashlib
import json
import os
import socket
import subprocess
import sys
import tempfile
import time
import unittest
from pathlib import Path
TOOLS = Path(__file__).parents[2] / "framework/tools/lease-broker"
FRAMEWORK = Path(__file__).parents[2] / "framework"
DAEMON = TOOLS / "daemon.py"
GATE = TOOLS / "mutator-gate.py"
RECOVERY = TOOLS / "recover-context.py"
OBSERVER_CLIENT = TOOLS / "receipt-observer-client.py"
CLAUDE_SETTINGS = FRAMEWORK / "runtime/claude/settings.json"
PI_EXTENSION = FRAMEWORK / "runtime/pi/mosaic-extension.ts"
def request(socket_path: Path, value: dict[str, object]) -> dict[str, object]:
with socket.socket(socket.AF_UNIX, socket.SOCK_STREAM) as connection:
connection.settimeout(3.0)
connection.connect(str(socket_path))
connection.sendall((json.dumps(value, separators=(",", ":")) + "\n").encode())
connection.shutdown(socket.SHUT_WR)
response = bytearray()
while True:
chunk = connection.recv(4096)
if not chunk:
break
response.extend(chunk)
if not response.endswith(b"\n") or response.count(b"\n") != 1:
raise AssertionError(f"unframed broker response: {bytes(response)!r}")
reply = json.loads(response[:-1])
if not isinstance(reply, dict):
raise AssertionError("broker response is not an object")
return reply
def wait_ready(process: subprocess.Popen[str], socket_path: Path) -> None:
deadline = time.monotonic() + 5.0
while time.monotonic() < deadline:
if socket_path.exists():
return
if process.poll() is not None:
output = process.stdout.read() if process.stdout is not None else ""
raise RuntimeError(f"daemon exited before READY: {output}")
time.sleep(0.02)
raise TimeoutError("daemon did not create private broker socket")
class RuntimeBoundaryFixture(unittest.TestCase):
def setUp(self) -> None:
self.temporary = tempfile.TemporaryDirectory()
self.root = Path(self.temporary.name)
os.chmod(self.root, 0o700)
self.socket = self.root / "broker.sock"
self.observer_socket = self.root / "observer.sock"
self.state = self.root / "state.json"
self.children: list[subprocess.Popen[str]] = []
def tearDown(self) -> None:
for child in self.children:
if child.poll() is None:
child.terminate()
try:
child.wait(timeout=3.0)
except subprocess.TimeoutExpired:
child.kill()
child.wait()
if child.stdout is not None:
child.stdout.close()
self.temporary.cleanup()
def start_daemon(self, *, production_observer: bool) -> None:
arguments = [sys.executable, "-I", "-S", "-B", str(DAEMON), "--socket", str(self.socket), "--state", str(self.state)]
if production_observer:
arguments.extend(["--observer-socket", str(self.observer_socket)])
process = subprocess.Popen(
arguments,
stdin=subprocess.DEVNULL,
stdout=subprocess.PIPE,
stderr=subprocess.STDOUT,
text=True,
)
self.children.append(process)
wait_ready(process, self.socket)
def register(self) -> str:
reply = request(self.socket, {"action": "register_anchor", "runtime_generation": 1})
session_id = reply.get("session_id")
self.assertTrue(reply.get("ok"))
self.assertIsInstance(session_id, str)
return session_id
def environment(self, session_id: str) -> dict[str, str]:
return {
**os.environ,
"MOSAIC_LEASE_BROKER_SOCKET": str(self.socket),
"MOSAIC_RECEIPT_OBSERVER_SOCKET": str(self.observer_socket),
"MOSAIC_LEASE_SESSION_ID": session_id,
"MOSAIC_RUNTIME_GENERATION": "1",
"MOSAIC_LEASE_RUNTIME": "pi",
}
def construction(self) -> Path:
content = b"WI-6 B2 production observer fixture\n"
path = self.root / "construction.json"
path.write_text(json.dumps({
"manifest_version": 1,
"generator_version": "wi6-repair-runtime-boundary",
"fragments": [{
"source_id": "authority/wi6-repair",
"content_base64": base64.b64encode(content).decode("ascii"),
"expected_sha256": hashlib.sha256(content).hexdigest(),
}],
}), encoding="utf-8")
os.chmod(path, 0o600)
return path
class RecoveryRuntimeBoundaryTest(RuntimeBoundaryFixture):
def test_b1_claude_exact_recovery_command_is_invocable_unverified_but_bash_is_not(self) -> None:
self.start_daemon(production_observer=False)
session_id = self.register()
environment = self.environment(session_id)
recovery_command = f"python3 {RECOVERY} complete"
mapped = subprocess.run(
[sys.executable, "-I", "-S", "-B", str(GATE), "--runtime", "claude", "--recovery-command", str(RECOVERY)],
input=json.dumps({"tool_name": "Bash", "tool_input": {"command": recovery_command}}),
text=True,
capture_output=True,
env={**environment, "MOSAIC_LEASE_RUNTIME": "claude"},
check=False,
)
self.assertEqual(mapped.returncode, 0, mapped.stderr)
mapped_begin = subprocess.run(
[sys.executable, "-I", "-S", "-B", str(GATE), "--runtime", "claude", "--recovery-command", str(RECOVERY)],
input=json.dumps({
"tool_name": "Bash",
"tool_input": {
"command": (
f"python3 {RECOVERY} begin --construction /tmp/construction.json "
"--compaction-epoch 1 --request-epoch 1"
)
},
}),
text=True,
capture_output=True,
env={**environment, "MOSAIC_LEASE_RUNTIME": "claude"},
check=False,
)
self.assertEqual(mapped_begin.returncode, 0, mapped_begin.stderr)
ordinary_bash = subprocess.run(
[sys.executable, "-I", "-S", "-B", str(GATE), "--runtime", "claude", "--recovery-command", str(RECOVERY)],
input=json.dumps({"tool_name": "Bash", "tool_input": {"command": "echo not-recovery"}}),
text=True,
capture_output=True,
env={**environment, "MOSAIC_LEASE_RUNTIME": "claude"},
check=False,
)
self.assertEqual(ordinary_bash.returncode, 2)
def test_b1_pi_registers_only_the_broker_exempt_recovery_tool(self) -> None:
extension = PI_EXTENSION.read_text(encoding="utf-8")
self.assertIn("const RECOVERY_TOOL = 'mosaic_context_recover'", extension)
self.assertIn("name: RECOVERY_TOOL", extension)
self.assertIn("checkPiMutatorGate(RECOVERY_TOOL)", extension)
self.assertNotIn("toolName === 'bash' ? RECOVERY_TOOL", extension)
def test_b2_production_observer_promotes_over_private_transport_and_rejects_broker_supplied_message(self) -> None:
self.start_daemon(production_observer=True)
session_id = self.register()
environment = self.environment(session_id)
begin = subprocess.run(
[sys.executable, "-I", "-S", "-B", str(RECOVERY), "begin", "--construction", str(self.construction()), "--compaction-epoch", "1", "--request-epoch", "1"],
text=True,
capture_output=True,
env=environment,
check=False,
)
self.assertEqual(begin.returncode, 0, begin.stderr)
cycle = json.loads(begin.stdout)
receipt = cycle.get("receipt")
self.assertIsInstance(receipt, str)
# S1: production transport is not a broker request field. The public
# broker endpoint keeps rejecting caller-supplied assistant evidence.
rejected_begin = request(self.socket, {
"action": "begin_recovery",
"session_id": session_id,
"runtime_generation": 1,
"receipt": receipt,
})
self.assertEqual(rejected_begin, {"ok": False, "code": "INVALID_RECOVERY_REQUEST"})
rejected_observe = request(self.socket, {
"action": "observe_receipt",
"session_id": session_id,
"runtime_generation": 1,
"receipt_challenge": cycle["receipt_challenge"],
"latest_assistant_message": receipt,
})
self.assertEqual(rejected_observe, {"ok": False, "code": "INVALID_RECEIPT"})
rejected_complete = request(self.socket, {
"action": "complete_recovery",
"session_id": session_id,
"runtime_generation": 1,
"latest_assistant_message": receipt,
})
self.assertEqual(rejected_complete, {"ok": False, "code": "INVALID_RECOVERY_REQUEST"})
recorded = subprocess.run(
[sys.executable, "-I", "-S", "-B", str(OBSERVER_CLIENT), "--runtime", "pi"],
input=json.dumps({"latest_assistant_message": receipt}),
text=True,
capture_output=True,
env=environment,
check=False,
)
self.assertEqual(recorded.returncode, 0, recorded.stderr)
complete = subprocess.run(
[sys.executable, "-I", "-S", "-B", str(RECOVERY), "complete"],
text=True,
capture_output=True,
env=environment,
check=False,
)
self.assertEqual(complete.returncode, 0, complete.stderr)
self.assertEqual(json.loads(complete.stdout).get("state"), "VERIFIED")
# The independent Claude transport selects one latest assistant entry
# from its hook transcript; it is not a Pi/message_end fallback.
claude_environment = {**environment, "MOSAIC_LEASE_RUNTIME": "claude"}
claude_begin = subprocess.run(
[sys.executable, "-I", "-S", "-B", str(RECOVERY), "begin", "--construction", str(self.construction()), "--compaction-epoch", "2", "--request-epoch", "2"],
text=True,
capture_output=True,
env=claude_environment,
check=False,
)
self.assertEqual(claude_begin.returncode, 0, claude_begin.stderr)
claude_receipt = json.loads(claude_begin.stdout)["receipt"]
transcript = self.root / "claude-transcript.jsonl"
transcript.write_text(
json.dumps({"message": {"role": "assistant", "content": claude_receipt}}) + "\n",
encoding="utf-8",
)
claude_recorded = subprocess.run(
[sys.executable, "-I", "-S", "-B", str(OBSERVER_CLIENT), "--runtime", "claude", "--latest-entry"],
input=json.dumps({"transcript_path": str(transcript)}),
text=True,
capture_output=True,
env=claude_environment,
check=False,
)
self.assertEqual(claude_recorded.returncode, 0, claude_recorded.stderr)
claude_complete = subprocess.run(
[sys.executable, "-I", "-S", "-B", str(RECOVERY), "complete"],
text=True,
capture_output=True,
env=claude_environment,
check=False,
)
self.assertEqual(claude_complete.returncode, 0, claude_complete.stderr)
self.assertEqual(json.loads(claude_complete.stdout).get("state"), "VERIFIED")
if __name__ == "__main__":
unittest.main()