fix(qdrant): verify collection existence in the readiness check

Why:
- The chunks collection is now created by an explicit deployment step
  (qdrant_bootstrap), not at startup, which means a process can boot against
  a healthy Qdrant that has no collection at all. /readyz's previous check
  only called get_collections(), so it reported ready in that state — the
  misconfiguration stayed invisible until the first upload failed with a 502
  after already paying for the MinIO write and embedding round trips.

Changes:
- ping_qdrant() now checks collection_exists(collection) instead of just
  reachability.
This commit is contained in:
Ali Zarinkolah
2026-08-20 18:17:56 +03:30
parent cc915f0f1a
commit fa933b08ff
3 changed files with 63 additions and 4 deletions

View File

@@ -23,7 +23,9 @@ async def readyz(request: Request, response: Response) -> dict[str, bool]:
postgres_ready, minio_ready, qdrant_ready = await asyncio.gather( postgres_ready, minio_ready, qdrant_ready = await asyncio.gather(
ping_postgres(resources.db_engine, timeout), ping_postgres(resources.db_engine, timeout),
ping_minio(resources.minio_client, timeout), ping_minio(resources.minio_client, timeout),
ping_qdrant(resources.qdrant_client, timeout), ping_qdrant(
resources.qdrant_client, timeout, collection=resources.settings.qdrant.collection
),
) )
result = { result = {

View File

@@ -9,10 +9,22 @@ def create_client(settings: QdrantSettings) -> AsyncQdrantClient:
return AsyncQdrantClient(url=settings.url, api_key=settings.api_key) return AsyncQdrantClient(url=settings.url, api_key=settings.api_key)
async def ping(client: AsyncQdrantClient, timeout: float) -> bool: async def ping(client: AsyncQdrantClient, timeout: float, *, collection: str) -> bool:
"""Whether Qdrant is reachable **and** the `chunks` collection exists.
Reachability alone is not readiness here. The collection is created by a
deployment step (`python -m src.cli.qdrant_bootstrap`, see ADR-0001
"Collection provisioning"), so a process can boot against a healthy Qdrant
that has no collection at all. Without this check that misconfiguration
stays invisible until the first upload fails with a `502` — after the
request has already paid for the MinIO write and the embedding round trips.
This is the Qdrant analogue of an unapplied Alembic migration, and it
belongs in `/readyz` for the same reason: it is a dependency-readiness
condition, not a process-health one.
"""
try: try:
async with asyncio.timeout(timeout): async with asyncio.timeout(timeout):
await client.get_collections() return await client.collection_exists(collection)
except Exception: except Exception:
return False return False
return True

View File

@@ -0,0 +1,45 @@
"""`/readyz`'s Qdrant probe against a real Qdrant.
The case worth an integration test is the one a fake cannot produce
convincingly: Qdrant is up and answering, but the collection the deployment
step was supposed to create is not there.
"""
import uuid
import pytest
from qdrant_client import AsyncQdrantClient
from src.config import QdrantSettings
from src.infrastructure.qdrant.client import ping
from src.infrastructure.qdrant.collection import ensure_chunks_collection
pytestmark = [
pytest.mark.integration,
pytest.mark.qdrant,
pytest.mark.asyncio(loop_scope="session"),
]
async def test_ping_is_not_ready_when_the_collection_was_never_bootstrapped(
qdrant_client: AsyncQdrantClient, qdrant_settings: QdrantSettings
) -> None:
"""A healthy Qdrant with no collection is *not* ready: uploads would 502."""
assert await ping(qdrant_client, 5.0, collection=qdrant_settings.collection) is False
async def test_ping_is_ready_after_bootstrap(
qdrant_client: AsyncQdrantClient, qdrant_settings: QdrantSettings
) -> None:
await ensure_chunks_collection(qdrant_client, collection=qdrant_settings.collection)
assert await ping(qdrant_client, 5.0, collection=qdrant_settings.collection) is True
async def test_ping_is_not_ready_for_a_different_collection_name(
qdrant_client: AsyncQdrantClient, qdrant_settings: QdrantSettings
) -> None:
"""A misconfigured QDRANT_COLLECTION is as unready as a missing one."""
await ensure_chunks_collection(qdrant_client, collection=qdrant_settings.collection)
assert await ping(qdrant_client, 5.0, collection=f"absent_{uuid.uuid4().hex}") is False