llama-stack-mirror/tests/unit/server/test_quota.py
Ashwin Bharambe 2c43285e22
feat(stores)!: use backend storage references instead of configs (#3697)
**This PR changes configurations in a backward incompatible way.**

Run configs today repeat full SQLite/Postgres snippets everywhere a
store is needed, which means duplicated credentials, extra connection
pools, and lots of drift between files. This PR introduces named storage
backends so the stack and providers can share a single catalog and
reference those backends by name.

## Key Changes

- Add `storage.backends` to `StackRunConfig`, register each KV/SQL
backend once at startup, and validate that references point to the right
family.
- Move server stores under `storage.stores` with lightweight references
(backend + namespace/table) instead of full configs.
- Update every provider/config/doc to use the new reference style;
docs/codegen now surface the simplified YAML.

## Migration

Before:
```yaml
metadata_store:
  type: sqlite
  db_path: ~/.llama/distributions/foo/registry.db
inference_store:
  type: postgres
  host: ${env.POSTGRES_HOST}
  port: ${env.POSTGRES_PORT}
  db: ${env.POSTGRES_DB}
  user: ${env.POSTGRES_USER}
  password: ${env.POSTGRES_PASSWORD}
conversations_store:
  type: postgres
  host: ${env.POSTGRES_HOST}
  port: ${env.POSTGRES_PORT}
  db: ${env.POSTGRES_DB}
  user: ${env.POSTGRES_USER}
  password: ${env.POSTGRES_PASSWORD}
```

After:
```yaml
storage:
  backends:
    kv_default:
      type: kv_sqlite
      db_path: ~/.llama/distributions/foo/kvstore.db
    sql_default:
      type: sql_postgres
      host: ${env.POSTGRES_HOST}
      port: ${env.POSTGRES_PORT}
      db: ${env.POSTGRES_DB}
      user: ${env.POSTGRES_USER}
      password: ${env.POSTGRES_PASSWORD}
  stores:
    metadata:
      backend: kv_default
      namespace: registry
    inference:
      backend: sql_default
      table_name: inference_store
      max_write_queue_size: 10000
      num_writers: 4
    conversations:
      backend: sql_default
      table_name: openai_conversations
```

Provider configs follow the same pattern—for example, a Chroma vector
adapter switches from:

```yaml
providers:
  vector_io:
  - provider_id: chromadb
    provider_type: remote::chromadb
    config:
      url: ${env.CHROMADB_URL}
      kvstore:
        type: sqlite
        db_path: ~/.llama/distributions/foo/chroma.db
```

to:

```yaml
providers:
  vector_io:
  - provider_id: chromadb
    provider_type: remote::chromadb
    config:
      url: ${env.CHROMADB_URL}
      persistence:
        backend: kv_default
        namespace: vector_io::chroma_remote
```

Once the backends are declared, everything else just points at them, so
rotating credentials or swapping to Postgres happens in one place and
the stack reuses a single connection pool.
2025-10-20 13:20:09 -07:00

132 lines
4 KiB
Python

# Copyright (c) Meta Platforms, Inc. and affiliates.
# All rights reserved.
#
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
from uuid import uuid4
import pytest
from fastapi import FastAPI, Request
from fastapi.testclient import TestClient
from starlette.middleware.base import BaseHTTPMiddleware
from llama_stack.core.datatypes import QuotaConfig, QuotaPeriod
from llama_stack.core.server.quota import QuotaMiddleware
from llama_stack.core.storage.datatypes import KVStoreReference, SqliteKVStoreConfig
from llama_stack.providers.utils.kvstore import register_kvstore_backends
class InjectClientIDMiddleware(BaseHTTPMiddleware):
"""
Middleware that injects 'authenticated_client_id' to mimic AuthenticationMiddleware.
"""
def __init__(self, app, client_id="client1"):
super().__init__(app)
self.client_id = client_id
async def dispatch(self, request: Request, call_next):
request.scope["authenticated_client_id"] = self.client_id
return await call_next(request)
def build_quota_config(db_path) -> QuotaConfig:
backend_name = f"kv_quota_{uuid4().hex}"
register_kvstore_backends({backend_name: SqliteKVStoreConfig(db_path=str(db_path))})
return QuotaConfig(
kvstore=KVStoreReference(backend=backend_name, namespace="quota"),
anonymous_max_requests=1,
authenticated_max_requests=2,
period=QuotaPeriod.DAY,
)
@pytest.fixture
def auth_app(tmp_path, request):
"""
FastAPI app with InjectClientIDMiddleware and QuotaMiddleware for authenticated testing.
Each test gets its own DB file.
"""
inner_app = FastAPI()
@inner_app.get("/test")
async def test_endpoint():
return {"message": "ok"}
db_path = tmp_path / f"quota_{request.node.name}.db"
quota = build_quota_config(db_path)
app = InjectClientIDMiddleware(
QuotaMiddleware(
inner_app,
kv_config=quota.kvstore,
anonymous_max_requests=quota.anonymous_max_requests,
authenticated_max_requests=quota.authenticated_max_requests,
window_seconds=86400,
),
client_id=f"client_{request.node.name}",
)
return app
def test_authenticated_quota_allows_up_to_limit(auth_app):
client = TestClient(auth_app)
assert client.get("/test").status_code == 200
assert client.get("/test").status_code == 200
def test_authenticated_quota_blocks_after_limit(auth_app):
client = TestClient(auth_app)
client.get("/test")
client.get("/test")
resp = client.get("/test")
assert resp.status_code == 429
assert resp.json()["error"]["message"] == "Quota exceeded"
def test_anonymous_quota_allows_up_to_limit(tmp_path, request):
inner_app = FastAPI()
@inner_app.get("/test")
async def test_endpoint():
return {"message": "ok"}
db_path = tmp_path / f"quota_anon_{request.node.name}.db"
quota = build_quota_config(db_path)
app = QuotaMiddleware(
inner_app,
kv_config=quota.kvstore,
anonymous_max_requests=quota.anonymous_max_requests,
authenticated_max_requests=quota.authenticated_max_requests,
window_seconds=86400,
)
client = TestClient(app)
assert client.get("/test").status_code == 200
def test_anonymous_quota_blocks_after_limit(tmp_path, request):
inner_app = FastAPI()
@inner_app.get("/test")
async def test_endpoint():
return {"message": "ok"}
db_path = tmp_path / f"quota_anon_{request.node.name}.db"
quota = build_quota_config(db_path)
app = QuotaMiddleware(
inner_app,
kv_config=quota.kvstore,
anonymous_max_requests=quota.anonymous_max_requests,
authenticated_max_requests=quota.authenticated_max_requests,
window_seconds=86400,
)
client = TestClient(app)
client.get("/test")
resp = client.get("/test")
assert resp.status_code == 429
assert resp.json()["error"]["message"] == "Quota exceeded"