feat(api): add workspace + ingest REST endpoints for Daedalus

Adds the REST API surface that Daedalus calls to manage workspace
lifecycle and dispatch file ingestion. All endpoints under /library/api/:

  POST   /workspaces/                   create workspace (idempotent on
                                        workspace_id; library_type frozen)
  GET    /workspaces/{workspace_id}/    workspace status with item/chunk
                                        counts
  DELETE /workspaces/{workspace_id}/    delete workspace + reachable
                                        content; concept-safe (orphan-only
                                        Concept GC; concepts referenced
                                        elsewhere are preserved)

  POST   /ingest/                       queue a file for ingest. Idempotent
                                        on (library, source_ref, hash):
                                        same triple → return existing job;
                                        new hash → supersede.
  GET    /jobs/{job_id}/                poll job status
  POST   /jobs/{job_id}/retry/          re-dispatch a failed job
  GET    /jobs/?status=&library_uid=    list recent jobs

Workspace-Library lookup uses the unique workspace_id index added in the
schema commit. Concept GC runs as a separate transaction after item/chunk
delete so partial failures don't leave the global graph corrupted.

Tests cover serializer validation, IngestJob ORM behavior, the
(library, source_ref, hash) idempotency query pattern, and auth
boundaries on every new endpoint. Cypher correctness is validated by
manual end-to-end testing — no live Neo4j in unit tests.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
2026-04-29 06:27:08 -04:00
parent c485a8560c
commit f2af28d96d
5 changed files with 725 additions and 7 deletions

View File

@@ -0,0 +1,217 @@
"""
Workspace lifecycle endpoints for the Daedalus integration.
A "workspace" in Mnemosyne is a Library scoped to a Daedalus workspace UUID.
It uses the same Library node as a global library; the difference is that
`workspace_id` is set, and search must filter on it.
These endpoints are called by the Daedalus backend (HTTP Basic auth as
the `daedalus-service` user). Daedalus owns the workspace_id; Mnemosyne
just persists what Daedalus tells it.
"""
import logging
from neomodel import db
from rest_framework import status
from rest_framework.decorators import api_view, permission_classes
from rest_framework.permissions import IsAuthenticated
from rest_framework.response import Response
from library.content_types import get_library_type_config
from .serializers import WorkspaceCreateSerializer, WorkspaceStatusSerializer
logger = logging.getLogger(__name__)
def _serialize_workspace(lib):
"""Build a WorkspaceStatus payload from a Library node + chunk/item counts."""
counts, _ = db.cypher_query(
"MATCH (l:Library {workspace_id: $wsid}) "
"OPTIONAL MATCH (l)-[:CONTAINS]->(:Collection)-[:CONTAINS]->(i:Item) "
"OPTIONAL MATCH (i)-[:HAS_CHUNK]->(c:Chunk) "
"RETURN count(DISTINCT i) AS item_count, count(DISTINCT c) AS chunk_count",
{"wsid": lib.workspace_id},
)
item_count = counts[0][0] if counts else 0
chunk_count = counts[0][1] if counts else 0
return {
"workspace_id": lib.workspace_id,
"library_uid": lib.uid,
"name": lib.name,
"library_type": lib.library_type,
"description": lib.description or "",
"item_count": item_count,
"chunk_count": chunk_count,
"created_at": lib.created_at,
}
@api_view(["POST"])
@permission_classes([IsAuthenticated])
def workspace_create(request):
"""
Create a workspace Library, idempotently.
A POST with a `workspace_id` already in use returns the existing
workspace (200) — not an error. The library_type is frozen at first
create; subsequent calls are not allowed to change it.
"""
from library.models import Library
serializer = WorkspaceCreateSerializer(data=request.data)
serializer.is_valid(raise_exception=True)
data = serializer.validated_data
# Idempotent path: workspace already exists.
try:
existing = Library.nodes.get(workspace_id=data["workspace_id"])
except Library.DoesNotExist:
existing = None
if existing is not None:
if existing.library_type != data["library_type"]:
return Response(
{
"detail": (
"library_type is immutable for an existing workspace "
f"(have '{existing.library_type}', "
f"got '{data['library_type']}')."
)
},
status=status.HTTP_409_CONFLICT,
)
logger.info(
"Workspace already exists workspace_id=%s library_uid=%s",
data["workspace_id"], existing.uid,
)
return Response(
WorkspaceStatusSerializer(_serialize_workspace(existing)).data,
status=status.HTTP_200_OK,
)
defaults = get_library_type_config(data["library_type"])
lib = Library(
name=data["name"],
library_type=data["library_type"],
description=data.get("description", ""),
workspace_id=data["workspace_id"],
chunking_config=defaults["chunking_config"],
embedding_instruction=defaults["embedding_instruction"],
reranker_instruction=defaults["reranker_instruction"],
llm_context_prompt=defaults["llm_context_prompt"],
)
lib.save()
logger.info(
"Workspace created workspace_id=%s library_uid=%s library_type=%s",
data["workspace_id"], lib.uid, lib.library_type,
)
return Response(
WorkspaceStatusSerializer(_serialize_workspace(lib)).data,
status=status.HTTP_201_CREATED,
)
@api_view(["GET", "DELETE"])
@permission_classes([IsAuthenticated])
def workspace_detail_or_delete(request, workspace_id):
"""
GET: return workspace status (item/chunk counts, metadata).
DELETE: delete the workspace Library and everything reachable AND unique
to it. Concept-safe: orphan-only Concept GC happens at the end.
Concepts referenced by other libraries (workspace or global) are preserved.
"""
from library.models import Library
if request.method == "GET":
try:
lib = Library.nodes.get(workspace_id=workspace_id)
except Library.DoesNotExist:
return Response(
{"detail": "Workspace not found."},
status=status.HTTP_404_NOT_FOUND,
)
return Response(WorkspaceStatusSerializer(_serialize_workspace(lib)).data)
# DELETE — idempotent: a missing workspace returns 204.
try:
lib = Library.nodes.get(workspace_id=workspace_id)
except Library.DoesNotExist:
return Response(status=status.HTTP_204_NO_CONTENT)
library_uid = lib.uid
library_name = lib.name
# Step 1-4: delete chunks, items, collections, then the library itself.
# We collect Item s3_keys first so the caller can clean up S3
# asynchronously (a future enhancement — for now, the keys are logged).
s3_rows, _ = db.cypher_query(
"MATCH (l:Library {workspace_id: $wsid})-[:CONTAINS]->(:Collection)"
"-[:CONTAINS]->(i:Item) RETURN i.uid, i.s3_key",
{"wsid": workspace_id},
)
item_s3_keys = [(r[0], r[1]) for r in s3_rows if r[1]]
db.cypher_query(
"""
MATCH (l:Library {workspace_id: $wsid})-[:CONTAINS]->(:Collection)
-[:CONTAINS]->(i:Item)-[:HAS_CHUNK]->(c:Chunk)
DETACH DELETE c
""",
{"wsid": workspace_id},
)
db.cypher_query(
"""
MATCH (l:Library {workspace_id: $wsid})-[:CONTAINS]->(:Collection)
-[:CONTAINS]->(i:Item)-[:HAS_IMAGE]->(img:Image)
OPTIONAL MATCH (img)-[:HAS_EMBEDDING]->(emb:ImageEmbedding)
DETACH DELETE img, emb
""",
{"wsid": workspace_id},
)
db.cypher_query(
"""
MATCH (l:Library {workspace_id: $wsid})-[:CONTAINS]->(:Collection)
-[:CONTAINS]->(i:Item)
DETACH DELETE i
""",
{"wsid": workspace_id},
)
db.cypher_query(
"""
MATCH (l:Library {workspace_id: $wsid})-[:CONTAINS]->(col:Collection)
DETACH DELETE col
""",
{"wsid": workspace_id},
)
db.cypher_query(
"MATCH (l:Library {workspace_id: $wsid}) DETACH DELETE l",
{"wsid": workspace_id},
)
# Step 5: orphan Concept garbage collection.
orphan_result, _ = db.cypher_query(
"""
MATCH (con:Concept)
WHERE NOT (con)<-[:REFERENCES]-() AND NOT (con)<-[:MENTIONS]-()
AND NOT (con)<-[:DEPICTS]-()
WITH con
DETACH DELETE con
RETURN count(con) AS deleted
"""
)
orphans_deleted = orphan_result[0][0] if orphan_result else 0
logger.info(
"Workspace deleted workspace_id=%s library_uid=%s name=%s "
"items=%d orphans_deleted=%d",
workspace_id, library_uid, library_name,
len(item_s3_keys), orphans_deleted,
)
return Response(status=status.HTTP_204_NO_CONTENT)