Files
microfish/backend/tests/test_local_graph_builder.py
Kunthawat Greethong 8b84378fe1 feat: SaaS foundation for CrowdSight
Elevate MiroFish/CrowdSight from single-container dev to a SaaS foundation:

- Local memory backend (Zep-compatible): memory services/models, local graph
  builder + updater, AgentActivity seam, import-boundary isolation; Zep stays
  default, local is opt-in behind MEMORY_BACKEND. Semantic parity not yet proven.
- Durable product persistence: projects/simulations/reports schema (migration
  0007) + tenant/owner-scoped ProductRepository + dual-write + scoped_project
  read-first + ArtifactStore abstraction; durable JobQueue + worker.py.
- SaaS hardening: durable RateLimiter (wired to login), UsageService (LLM
  accounting), redacted AuditService, idempotency, CORS allowlist, safe API
  errors, single-use PasswordResetService + endpoints (covers invite-pending).
- Exactly 3 roles (super_admin/admin/user) with tenant authz policy.
- Admin UI: GET/POST/PATCH /api/admin/users + GET/PUT /api/admin/settings
  (super-admin only, encrypted/masked); AdminView.vue + SettingsView.vue with
  admin/super-admin route guards, th/en i18n.
- Production deploy topology: multi-stage Dockerfile (frontend build + gunicorn
  wsgi + nginx SPA-proxy + supervisord worker), backend/wsgi.py, gunicorn dep.

Backend 197 passed; frontend 10 tests + build green. ruff unavailable (gap).
No commit of credentials; secrets handled via env/.env.example.
Deferred: Zep semantic A/B parity, object storage cutover, mobile QA, EasyPanel
container build of deploy topology.
2026-08-31 13:05:21 +07:00

135 lines
4.4 KiB
Python

from sqlalchemy import create_engine
from app.db import Base, create_session_factory
from app.models.memory import MemoryGraph
from app.services.local_graph_builder import LocalGraphBuilderService
class FakeExtractionClient:
def __init__(self):
self.calls = []
def chat_json(self, messages, temperature=0.3, max_tokens=4096):
self.calls.append(messages)
return {
"entities": [
{
"mention": "Alice",
"canonical_name": "Alice",
"labels": ["Person"],
"aliases": [],
"attributes": {"role": "founder"},
"summary": "Alice founded the local project.",
"confidence": 0.95,
},
{
"mention": "Orbit",
"canonical_name": "Orbit",
"labels": ["Project"],
"aliases": [],
"attributes": {},
"summary": "Orbit is the project discussed in the episode.",
"confidence": 0.9,
},
],
"edges": [
{
"source_entity_ref": "Alice",
"target_entity_ref": "Orbit",
"relation": "FOUNDED",
"fact": "Alice founded Orbit.",
"attributes": {},
"valid_at": None,
"invalid_at": None,
"expired_at": None,
"confidence": 0.92,
"evidence": ["episode-0"],
}
],
"episode_summary": "Alice founded Orbit.",
"unresolved_mentions": [],
}
def make_session_factory():
engine = create_engine("sqlite+pysqlite:///:memory:")
Base.metadata.create_all(engine)
return engine, create_session_factory(engine)
def test_local_graph_builder_persists_scoped_graph_and_extracted_memory():
engine, session_factory = make_session_factory()
client = FakeExtractionClient()
builder = LocalGraphBuilderService(
session_factory,
organization_id="org-a",
project_id="project-a",
extraction_client=client,
)
graph_id = builder.create_graph(name="Orbit")
builder.set_ontology(graph_id, {"entity_types": ["Person", "Project"], "relations": ["FOUNDED"]})
episode_ids = builder.add_text_batches(
graph_id,
["Alice founded Orbit."],
batch_size=3,
)
assert len(episode_ids) == 1
assert episode_ids[0].startswith("episode_")
assert client.calls
data = builder.get_graph_data(graph_id)
assert data["graph_id"] == graph_id
assert data["node_count"] == 2
assert data["edge_count"] == 1
with session_factory() as session:
graph = session.get(MemoryGraph, graph_id)
assert graph.organization_id == "org-a"
assert graph.project_id == "project-a"
assert graph.ontology["relations"] == ["FOUNDED"]
def test_local_graph_builder_reprocessing_is_idempotent_for_episode_and_edge():
engine, session_factory = make_session_factory()
builder = LocalGraphBuilderService(
session_factory,
organization_id="org-a",
project_id="project-a",
extraction_client=FakeExtractionClient(),
)
graph_id = builder.create_graph(name="Orbit")
builder.set_ontology(graph_id, {"entity_types": ["Person", "Project"]})
builder.add_text_batches(graph_id, ["Alice founded Orbit."])
builder.add_text_batches(graph_id, ["Alice founded Orbit."])
data = builder.get_graph_data(graph_id)
assert data["node_count"] == 2
assert data["edge_count"] == 1
def test_local_graph_builder_fails_closed_for_wrong_organization():
engine, session_factory = make_session_factory()
builder = LocalGraphBuilderService(
session_factory,
organization_id="org-a",
project_id="project-a",
extraction_client=FakeExtractionClient(),
)
graph_id = builder.create_graph(name="Orbit")
other_builder = LocalGraphBuilderService(
session_factory,
organization_id="org-b",
project_id="project-b",
extraction_client=FakeExtractionClient(),
)
try:
other_builder.get_graph_data(graph_id)
except ValueError as exc:
assert str(exc) == "memory_graph_not_found"
else:
raise AssertionError("wrong organization must not read graph")