Files
obsidian-wiki/tests/test_mcp_ingest.py
T
Codex e7adfbe9a6 fix(mcp): stage ingest uploads outside vault
Move remote MCP ingest uploads from the vault inbox to the MCP runtime staging area so uploaded files are not accepted into the vault before wiki-ingest processes them.

Reject ingest runtime roots that resolve inside the vault, and update the generated OpenCode prompt plus docs to describe uploads as temporary staging inputs.

Validation: python3 -m unittest discover -v; python3 -m py_compile obsidian_wiki/mcp_ingest.py tests/test_mcp_ingest.py; git diff --check
2026-07-05 15:04:16 +00:00

202 lines
7.4 KiB
Python

import base64
import json
import subprocess
import tempfile
import time
import unittest
from pathlib import Path
from unittest.mock import patch
from obsidian_wiki.mcp_ingest import (
IngestError,
IngestManager,
parse_bool,
)
class McpIngestTests(unittest.TestCase):
def setUp(self):
self.tempdir = tempfile.TemporaryDirectory()
self.root = Path(self.tempdir.name)
self.vault = self.root / "vault"
self.project = self.root / "project"
self.runtime = self.project / ".runtime" / "mcp-ingest"
self.vault.mkdir()
self.project.mkdir()
self.manager = IngestManager(
vault_path=self.vault,
project_root=self.project,
runtime_root=self.runtime,
opencode_path=Path("/usr/bin/opencode"),
max_file_bytes=100,
max_chunk_bytes=8,
)
def tearDown(self):
self.tempdir.cleanup()
def test_parse_bool_accepts_enabled_values_only(self):
self.assertTrue(parse_bool("1"))
self.assertTrue(parse_bool("true"))
self.assertTrue(parse_bool("YES"))
self.assertFalse(parse_bool(""))
self.assertFalse(parse_bool("0"))
self.assertFalse(parse_bool("false"))
def test_uploads_are_staged_in_runtime_not_vault(self):
upload = self.manager.create_upload(file_name="drawing.pdf", size_bytes=0, sha256=self._sha256(b""))
upload_path = Path(upload["path"]).resolve()
self.assertTrue(upload_path.is_relative_to((self.runtime / "uploads").resolve()))
self.assertFalse(upload_path.is_relative_to(self.vault.resolve()))
def test_runtime_root_must_not_be_inside_vault(self):
with self.assertRaises(IngestError):
IngestManager(
vault_path=self.vault,
project_root=self.project,
runtime_root=self.vault / ".runtime" / "mcp-ingest",
)
def test_upload_chunk_lifecycle_verifies_offset_size_and_sha(self):
payload = b"hello ingest"
upload = self.manager.create_upload(
file_name="drawing.pdf",
size_bytes=len(payload),
sha256="sha256:" + self._sha256(payload),
project="bjd",
doc_type_hint="drawing",
)
first = self.manager.append_upload_chunk(
upload["upload_id"],
offset=0,
data_base64=base64.b64encode(payload[:5]).decode("ascii"),
)
self.assertEqual(first["received_bytes"], 5)
with self.assertRaises(IngestError):
self.manager.append_upload_chunk(
upload["upload_id"],
offset=3,
data_base64=base64.b64encode(payload[5:]).decode("ascii"),
)
second = self.manager.append_upload_chunk(
upload["upload_id"],
offset=5,
data_base64=base64.b64encode(payload[5:]).decode("ascii"),
)
self.assertEqual(second["received_bytes"], len(payload))
complete = self.manager.complete_upload(upload["upload_id"])
self.assertEqual(complete["state"], "complete")
self.assertEqual(Path(complete["path"]).read_bytes(), payload)
def test_upload_rejects_unsafe_names_oversized_files_and_large_chunks(self):
with self.assertRaises(IngestError):
self.manager.create_upload(file_name="../secret.pdf", size_bytes=10, sha256="a" * 64)
with self.assertRaises(IngestError):
self.manager.create_upload(file_name="large.pdf", size_bytes=101, sha256="a" * 64)
upload = self.manager.create_upload(file_name="ok.pdf", size_bytes=20, sha256=self._sha256(b"x" * 20))
with self.assertRaises(IngestError):
self.manager.append_upload_chunk(
upload["upload_id"],
offset=0,
data_base64=base64.b64encode(b"x" * 9).decode("ascii"),
)
def test_start_ingest_job_constructs_restricted_opencode_command(self):
payload = b"source data"
upload = self._complete_upload("source.pdf", payload)
popen = FakePopen()
with patch("obsidian_wiki.mcp_ingest.subprocess.Popen", return_value=popen) as popen_mock:
job = self.manager.start_ingest_job([upload["upload_id"]], note="customer asked for drawings")
args = popen_mock.call_args.args[0]
self.assertEqual(args[:5], ["/usr/bin/opencode", "run", "--format", "json", "--auto"])
self.assertIn("--dir", args)
self.assertEqual(args[args.index("--dir") + 1], str(self.project))
self.assertIn("--title", args)
self.assertIn(f"MCP ingest {job['job_id']}", args)
prompt = args[-1]
self.assertIn("/wiki-ingest", prompt)
self.assertIn(str(Path(upload["path"])), prompt)
self.assertIn("temporary runtime staging files", prompt)
self.assertIn("Do not ingest any file outside this list.", prompt)
self.assertIn("obsidian-wiki file-index rebuild", prompt)
self.assertNotIn("../secret", prompt)
popen.returncode = 0
self.manager.refresh_jobs()
status = self.manager.get_job_status(job["job_id"])
self.assertEqual(status["state"], "succeeded")
self.assertEqual(status["exit_code"], 0)
def test_jobs_queue_one_at_a_time_and_cancel_queued_job(self):
first = self._complete_upload("first.pdf", b"first")
second = self._complete_upload("second.pdf", b"second")
popen = FakePopen(returncode=None)
with patch("obsidian_wiki.mcp_ingest.subprocess.Popen", return_value=popen):
first_job = self.manager.start_ingest_job([first["upload_id"]])
second_job = self.manager.start_ingest_job([second["upload_id"]])
self.assertEqual(self.manager.get_job_status(first_job["job_id"])["state"], "running")
self.assertEqual(self.manager.get_job_status(second_job["job_id"])["state"], "queued")
cancelled = self.manager.cancel_ingest_job(second_job["job_id"])
self.assertEqual(cancelled["state"], "cancelled")
def _complete_upload(self, name: str, payload: bytes) -> dict:
upload = self.manager.create_upload(name, len(payload), self._sha256(payload))
offset = 0
while offset < len(payload):
chunk = payload[offset : offset + self.manager.max_chunk_bytes]
self.manager.append_upload_chunk(
upload["upload_id"],
offset=offset,
data_base64=base64.b64encode(chunk).decode("ascii"),
)
offset += len(chunk)
return self.manager.complete_upload(upload["upload_id"])
def _sha256(self, payload: bytes) -> str:
import hashlib
return hashlib.sha256(payload).hexdigest()
class FakePopen:
def __init__(self, returncode=None):
self.returncode = returncode
self.pid = 12345
self.terminated = False
def poll(self):
return self.returncode
def wait(self, timeout=None):
deadline = time.monotonic() + (timeout or 0)
while self.returncode is None and (timeout is None or time.monotonic() < deadline):
time.sleep(0.01)
if self.returncode is None:
raise subprocess.TimeoutExpired("fake", timeout)
return self.returncode
def terminate(self):
self.terminated = True
self.returncode = -15
def kill(self):
self.returncode = -9
if __name__ == "__main__":
unittest.main()