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.
This commit is contained in:
Ashwin Bharambe 2025-10-20 13:20:09 -07:00 committed by GitHub
parent add64e8e2a
commit 2c43285e22
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
105 changed files with 2290 additions and 1292 deletions

View file

@ -238,7 +238,7 @@ def instantiate_llama_stack_client(session):
run_config = run_config_from_adhoc_config_spec(config)
run_config_file = tempfile.NamedTemporaryFile(delete=False, suffix=".yaml")
with open(run_config_file.name, "w") as f:
yaml.dump(run_config.model_dump(), f)
yaml.dump(run_config.model_dump(mode="json"), f)
config = run_config_file.name
client = LlamaStackAsLibraryClient(

View file

@ -12,9 +12,15 @@ import pytest
from llama_stack.core.access_control.access_control import default_policy
from llama_stack.core.datatypes import User
from llama_stack.core.storage.datatypes import SqlStoreReference
from llama_stack.providers.utils.sqlstore.api import ColumnType
from llama_stack.providers.utils.sqlstore.authorized_sqlstore import AuthorizedSqlStore
from llama_stack.providers.utils.sqlstore.sqlstore import PostgresSqlStoreConfig, SqliteSqlStoreConfig, sqlstore_impl
from llama_stack.providers.utils.sqlstore.sqlstore import (
PostgresSqlStoreConfig,
SqliteSqlStoreConfig,
register_sqlstore_backends,
sqlstore_impl,
)
def get_postgres_config():
@ -55,8 +61,9 @@ def authorized_store(backend_config):
config_func = backend_config
config = config_func()
base_sqlstore = sqlstore_impl(config)
backend_name = f"sql_{type(config).__name__.lower()}"
register_sqlstore_backends({backend_name: config})
base_sqlstore = sqlstore_impl(SqlStoreReference(backend=backend_name, table_name="authorized_store"))
authorized_store = AuthorizedSqlStore(base_sqlstore, default_policy())
yield authorized_store

View file

@ -0,0 +1,71 @@
# 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.
import yaml
from llama_stack.core.datatypes import StackRunConfig
from llama_stack.core.storage.datatypes import (
PostgresKVStoreConfig,
PostgresSqlStoreConfig,
SqliteKVStoreConfig,
SqliteSqlStoreConfig,
)
def test_starter_distribution_config_loads_and_resolves():
"""Integration: Actual starter config should parse and have correct storage structure."""
with open("llama_stack/distributions/starter/run.yaml") as f:
config_dict = yaml.safe_load(f)
config = StackRunConfig(**config_dict)
# Config should have named backends and explicit store references
assert config.storage is not None
assert "kv_default" in config.storage.backends
assert "sql_default" in config.storage.backends
assert isinstance(config.storage.backends["kv_default"], SqliteKVStoreConfig)
assert isinstance(config.storage.backends["sql_default"], SqliteSqlStoreConfig)
stores = config.storage.stores
assert stores.metadata is not None
assert stores.metadata.backend == "kv_default"
assert stores.metadata.namespace == "registry"
assert stores.inference is not None
assert stores.inference.backend == "sql_default"
assert stores.inference.table_name == "inference_store"
assert stores.inference.max_write_queue_size > 0
assert stores.inference.num_writers > 0
assert stores.conversations is not None
assert stores.conversations.backend == "sql_default"
assert stores.conversations.table_name == "openai_conversations"
def test_postgres_demo_distribution_config_loads():
"""Integration: Postgres demo should use Postgres backend for all stores."""
with open("llama_stack/distributions/postgres-demo/run.yaml") as f:
config_dict = yaml.safe_load(f)
config = StackRunConfig(**config_dict)
# Should have postgres backend
assert config.storage is not None
assert "kv_default" in config.storage.backends
assert "sql_default" in config.storage.backends
postgres_backend = config.storage.backends["sql_default"]
assert isinstance(postgres_backend, PostgresSqlStoreConfig)
assert postgres_backend.host == "${env.POSTGRES_HOST:=localhost}"
kv_backend = config.storage.backends["kv_default"]
assert isinstance(kv_backend, PostgresKVStoreConfig)
stores = config.storage.stores
# Stores target the Postgres backends explicitly
assert stores.metadata is not None
assert stores.metadata.backend == "kv_default"
assert stores.inference is not None
assert stores.inference.backend == "sql_default"