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>
This commit is contained in:
Chris Coutinho
2026-05-29 13:13:25 +02:00
co-authored by Claude Opus 4.8
parent c7da612f20
commit d883052fb8
37 changed files with 2534 additions and 55 deletions
+17
View File
@@ -14,6 +14,7 @@ from anyio.streams.memory import MemoryObjectReceiveStream
from httpx import HTTPStatusError
from qdrant_client.models import FieldCondition, Filter, MatchValue, PointStruct
from nextcloud_mcp_server.acl_hash import compute_acl_hash
from nextcloud_mcp_server.client import NextcloudClient
from nextcloud_mcp_server.config import get_settings
from nextcloud_mcp_server.document_processors import get_registry
@@ -25,6 +26,7 @@ from nextcloud_mcp_server.observability.metrics import (
)
from nextcloud_mcp_server.observability.tracing import trace_operation
from nextcloud_mcp_server.search.pdf_highlighter import PDFHighlighter
from nextcloud_mcp_server.vector import payload_keys
from nextcloud_mcp_server.vector.document_chunker import DocumentChunker
from nextcloud_mcp_server.vector.html_processor import html_to_markdown
from nextcloud_mcp_server.vector.placeholder import delete_placeholder_point
@@ -672,6 +674,15 @@ async def _index_document(
indexed_at = int(time.time())
points = []
# Decomposition payload keys (design §10.2) — written even in local mode so
# a future migration to the external processor is friction-free. Computed
# once per document (not per chunk). The local processor has no triage, so
# PIPELINE_TIER is "fast"; ACL hash records at least the owner principal
# (full share enumeration is a follow-up — a missing/partial acl_hash is
# safe because the query-side pre-filter only applies when present + enabled).
_embedding_identity = get_settings().get_embedding_model_name()
_acl_hash = compute_acl_hash([("user", doc_task.user_id)])
# Surface deck card data quality issues at indexing time rather than
# only at verification time (where _verify_deck_cards falls through to
# legacy-data pass-through when board_id/stack_id are missing). This is
@@ -719,6 +730,12 @@ async def _index_document(
"chunk_start_offset": chunk.start_offset,
"chunk_end_offset": chunk.end_offset,
"metadata_version": 2, # v2 includes position metadata
# Decomposition payload keys (design §10.2), additive.
payload_keys.PROCESSOR_VERSION: "monolith-v1",
payload_keys.PARSED_AT: indexed_at,
payload_keys.PIPELINE_TIER: "fast",
payload_keys.EMBEDDING_IDENTITY: _embedding_identity,
payload_keys.ACL_HASH: _acl_hash,
# File-specific metadata (PDF, etc.)
**(
{