Files
mcp-nextcloud/nextcloud_mcp_server/vector/queue/status.py
T
Chris CoutinhoandClaude Opus 4.8 d883052fb8 feat: add opt-in MCP decomposition hook points (design §10)
Adds the seven §10.2 hook-point modules + five env vars so Astrolabe Cloud can
offload document processing to the external document-processor / embedding
gateway. Purely additive: with every setting unset the server behaves exactly
as today, so self-hosters are unaffected (Deck #92).

Hook points (all default to current monolith behavior):
- config: EMBEDDING_PROVIDER, INGEST_MODE, STATUS_BACKEND,
  COLLECTION_METADATA_SOURCE, FACT_EVENT_EMITTER (+ supporting settings),
  validated in Settings.__post_init__ (fail-fast STATUS_BACKEND=local with
  INGEST_MODE=external); shared canonical.py.
- vector/payload_keys.py + acl_hash.py: cross-impl NAMESPACE/point_id (§2.2)
  and BLAKE2b-128 ACL hash (§11), pinned by fixtures shared with the
  document-processor repo.
- embedding/gateway_client.py: OpenAI-compatible GatewayProvider authenticating
  via M2M OIDC client-credentials (separate realm); manual-only registry entry.
- vector/collection_metadata.py: sentinel-point / API metadata source with env
  fallback.
- vector/queue/: hexagonal ingest producer ports + memory/NATS adapters
  (Postgres seam); INGEST_MODE=external publishes mcp.ingest.requested.{tenant}
  instead of the in-memory stream and skips the in-process processor pool. The
  lifespan becomes a composition root across both deployment branches.
- vector/queue/status.py: STATUS_BACKEND=bus subscriber feeding a StatusStore
  the vector-sync status endpoint reads.
- admin/payload_backfill.py: POST /api/v1/admin/payload-backfill (admin scope);
  processor writes the new payload keys; query-side ACL pre-filter gated behind
  ACL_PREFILTER_ENABLED (default off).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-05-29 13:13:25 +02:00

164 lines
5.4 KiB
Python

"""Status surface for ingest jobs (design §10.1, ``STATUS_BACKEND``).
- ``local``: in-process job state — the memory-stream buffer (today's behavior,
read directly by the status endpoint).
- ``bus``: a background subscriber consumes
``mcp.document.{ready,failed,reparsed}.{tenant_id}`` into a bounded in-process
:class:`StatusStore` that the status endpoint / ``nc_get_vector_sync_status``
read.
**Honest constraint (design §10.2 / decision):** MCP progress notifications
(``ctx.report_progress``) can only be emitted inside an *active tool-call
request*; a background subscriber has no ``ctx`` and the MCP SDK exposes no
out-of-band push. So "surface events as MCP progress notifications" is delivered
via this store (polled by the status endpoint / a tool), not an unsolicited
server push. True server-initiated progress / SSE is a follow-up — the
``on_event`` callback seam is left in place for it.
"""
from __future__ import annotations
import logging
from collections import OrderedDict
from typing import TYPE_CHECKING, Any, Callable
if TYPE_CHECKING:
import anyio
from anyio.abc import TaskStatus
logger = logging.getLogger(__name__)
# Terminal/intermediate document states carried on mcp.document.* subjects.
_VALID_STATES = {"ready", "failed", "reparsed"}
class StatusStore:
"""Bounded LRU of recent document states keyed by ``doc_id``."""
def __init__(self, max_size: int = 10_000):
self._entries: OrderedDict[str, dict[str, Any]] = OrderedDict()
self._max = max_size
def record(
self,
doc_id: str,
state: str,
*,
content_hash: str | None = None,
transitioned_at: str | None = None,
) -> None:
self._entries[doc_id] = {
"state": state,
"content_hash": content_hash,
"transitioned_at": transitioned_at,
}
self._entries.move_to_end(doc_id)
while len(self._entries) > self._max:
self._entries.popitem(last=False)
def get(self, doc_id: str) -> dict[str, Any] | None:
return self._entries.get(doc_id)
def counts(self) -> dict[str, int]:
out: dict[str, int] = {}
for entry in self._entries.values():
out[entry["state"]] = out.get(entry["state"], 0) + 1
return out
def __len__(self) -> int:
return len(self._entries)
def state_from_subject(subject: str) -> str | None:
"""``mcp.document.<state>.<tenant_id>`` → ``<state>`` (or None if unknown)."""
parts = subject.split(".")
if len(parts) >= 4 and parts[0] == "mcp" and parts[1] == "document":
state = parts[2]
if state in _VALID_STATES:
return state
return None
class NatsStatusSubscriber:
"""Consumes ``mcp.document.*.{tenant_id}`` into a :class:`StatusStore`."""
def __init__(
self,
nc: Any,
js: Any,
tenant_id: str,
store: StatusStore,
on_event: Callable[[str, str], None] | None = None,
):
self._nc = nc
self._js = js
self.tenant_id = tenant_id
self.store = store
# on_event(doc_id, state) — seam for a future SSE / progress bridge.
self._on_event = on_event
def handle_message(self, subject: str, data: bytes) -> None:
"""Parse one status message into the store. Unit-testable without NATS."""
import json # noqa: PLC0415
state = state_from_subject(subject)
if state is None:
logger.warning("status.unknown_subject subject=%s", subject)
return
try:
payload = json.loads(data)
doc_id = payload["doc_id"]
except Exception:
logger.warning("status.bad_message subject=%s", subject, exc_info=True)
return
self.store.record(
doc_id,
state,
content_hash=payload.get("content_hash"),
transitioned_at=payload.get("transitioned_at"),
)
if self._on_event is not None:
self._on_event(doc_id, state)
@classmethod
async def connect(
cls, *, url: str, tenant_id: str, store: StatusStore
) -> NatsStatusSubscriber:
import nats # noqa: PLC0415
nc = await nats.connect(url)
js = nc.jetstream()
return cls(nc, js, tenant_id, store)
async def run(
self,
shutdown_event: anyio.Event,
*,
task_status: TaskStatus = None, # type: ignore[assignment]
) -> None:
"""Durable pull-consumer loop. Requires a live broker (integration)."""
import anyio # noqa: PLC0415
subject = f"mcp.document.*.{self.tenant_id}"
sub = await self._js.pull_subscribe(
subject, durable=f"mcp-status-{self.tenant_id}"
)
if task_status is not None:
task_status.started()
while not shutdown_event.is_set():
try:
msgs = await sub.fetch(batch=16, timeout=5)
except Exception:
# fetch timeout when idle — loop and re-check shutdown.
await anyio.sleep(0)
continue
for msg in msgs:
self.handle_message(msg.subject, msg.data)
await msg.ack()
async def aclose(self) -> None:
try:
await self._nc.drain()
except Exception:
logger.warning("NATS status subscriber drain failed", exc_info=True)