feat: make owner-only state persistence configurable and turn it off for enclaves

packages/enclave-model-api-example/docker/Dockerfile

@@ -28,6 +28,7 @@ SYFT_ENCLAVE_DATA_OWNERS,\
 SYFT_ENCLAVE_REQUIRE_TEE,\
 SYFT_ENCLAVE_FRESH_STATE,\
 SYFT_ENCLAVE_USE_ENCRYPTION,\
+SYFT_ENCLAVE_PERSIST_OWNER_STATE,\
 SYFT_DEFAULT_JOB_TIMEOUT_SECONDS,\
 SYFT_BOOTSTRAP,\
 SYFT_BOOTSTRAP_WIF_AUDIENCE,\

packages/enclave-model-api-example/src/enclave_model_api/__main__.py

@@ -48,7 +48,8 @@ def main() -> None:
         f"Enclave settings — email={settings.email} data_owners={settings.data_owners} "
         f"token_path={settings.token_path} poll_interval={settings.poll_interval}s "
         f"require_tee={settings.require_tee} fresh_state={settings.fresh_state} "
-        f"use_encryption={settings.use_encryption}"
+        f"use_encryption={settings.use_encryption} "
+        f"persist_owner_state={settings.persist_owner_state}"
     )
     logger.info(
         f"Inference settings — model_owner={inference.model_owner} "
@@ -62,6 +63,7 @@ def main() -> None:
         token_path=settings.token_path,
         data_owners=settings.data_owners,
         encryption=settings.use_encryption,
+        persist_owner_state=settings.persist_owner_state,
     )
     logger.info("SyftEnclaveClient ready")
 

packages/syft-enclave/docker/Dockerfile

@@ -54,6 +54,7 @@ SYFT_ENCLAVE_DATA_OWNERS,\
 SYFT_ENCLAVE_REQUIRE_TEE,\
 SYFT_ENCLAVE_FRESH_STATE,\
 SYFT_ENCLAVE_USE_ENCRYPTION,\
+SYFT_ENCLAVE_PERSIST_OWNER_STATE,\
 SYFT_DEFAULT_JOB_TIMEOUT_SECONDS,\
 SYFT_BOOTSTRAP,\
 SYFT_BOOTSTRAP_WIF_AUDIENCE,\

packages/syft-enclave/src/syft_enclaves/__main__.py

@@ -43,7 +43,8 @@ def main() -> None:
         f"Enclave settings — email={settings.email} data_owners={settings.data_owners} "
         f"token_path={settings.token_path} poll_interval={settings.poll_interval}s "
         f"require_tee={settings.require_tee} fresh_state={settings.fresh_state} "
-        f"use_encryption={settings.use_encryption}"
+        f"use_encryption={settings.use_encryption} "
+        f"persist_owner_state={settings.persist_owner_state}"
     )
 
     logger.info("Building SyftEnclaveClient...")
@@ -52,6 +53,7 @@ def main() -> None:
         token_path=settings.token_path,
         data_owners=settings.data_owners,
         encryption=settings.use_encryption,
+        persist_owner_state=settings.persist_owner_state,
     )
     logger.info("SyftEnclaveClient ready")
 

packages/syft-enclave/src/syft_enclaves/client.py

@@ -435,20 +435,26 @@ def for_enclave(
         token_path: Path | str | None = None,
         data_owners: list[str] | None = None,
         encryption: bool = False,
+        persist_owner_state: bool = False,
     ) -> "SyftEnclaveClient":
         """Build an enclave client backed by a real Google Drive connection.
         Args:
             email: The enclave datasite's email address.
             token_path: Path to a pre-authorized Google Drive OAuth token.
             data_owners: Emails whose approval gates every job on this enclave.
             encryption: Enable end-to-end drive encryption.
+            persist_owner_state: Keep the owner-only state used to restore
+                this datasite later (event log, rolling state, checkpoints).
+                Off by default - an enclave gets ephemeral keys and wipes its
+                state on boot, so there is never anything to restore.
         """
         config = SyftRDSClientConfig.for_jupyter(
             email=email,
             has_ds_role=True,
             has_do_role=True,
             token_path=Path(token_path) if token_path is not None else None,
             encryption=encryption,
+            persist_owner_state=persist_owner_state,
         )
 
         # Note: We do not currently provide the ability to load encryption keys passed during creation of enclave.

packages/syft-enclave/src/syft_enclaves/settings.py

@@ -94,3 +94,16 @@ def _split_data_owners(cls, v: object) -> object:
             "Enabled by default; set false to disable."
         ),
     )
+    persist_owner_state: bool = Field(
+        default=False,
+        description=(
+            "Keep the owner-only state that exists solely to restore this "
+            "datasite later: the append-only event log, the rolling state and "
+            "the checkpoints. Off by default because an enclave can never "
+            "restore — it gets an ephemeral keypair each boot and wipes its "
+            "state under fresh_state — so those writes only spend Drive API "
+            "calls inside the poll loop. Peer-facing state (outbox, "
+            "collections, peers) is unaffected. Set true only for a stateful "
+            "enclave (fresh_state=false)."
+        ),
+    )

packages/syft-enclave/tests/test_settings.py

@@ -38,6 +38,7 @@ def test_defaults_applied_when_required_fields_set(required_env):
     assert settings.log_level == "INFO"
     assert settings.fresh_state is True  # default: always start with a clean slate
     assert settings.use_encryption is True  # default: encryption on
+    assert settings.persist_owner_state is False  # default: an enclave never restores
 
 
 def test_data_owners_parsed_from_comma_separated_string(clean_env):
@@ -112,3 +113,36 @@ def test_use_encryption_can_be_disabled_via_env(required_env):
     required_env.setenv("SYFT_ENCLAVE_USE_ENCRYPTION", "false")
     settings = EnclaveSettings(_env_file=None)
     assert settings.use_encryption is False
+
+
+def test_persist_owner_state_can_be_enabled_via_env(required_env):
+    required_env.setenv("SYFT_ENCLAVE_PERSIST_OWNER_STATE", "true")
+    settings = EnclaveSettings(_env_file=None)
+    assert settings.persist_owner_state is True
+
+
+def test_persist_owner_state_reaches_the_do_syncer_config():
+    """Guard the `**kw` hole between for_enclave and the sync engine.
+
+    ``SyftRDSClientConfig.for_jupyter`` forwards unknown kwargs straight to
+    ``SyftboxManagerConfig.for_jupyter``, so nothing type-checks this hop. A
+    rename on either side would silently give an enclave back the owner state
+    it is not supposed to keep.
+    """
+    from syft_rds.config import SyftRDSClientConfig
+
+    config = SyftRDSClientConfig.for_jupyter(
+        email="enclave@openmined.org",
+        has_do_role=True,
+        has_ds_role=True,
+        persist_owner_state=False,
+    )
+    assert config.sync.persist_owner_state is False
+    assert config.sync.datasite_owner_syncer_config.persist_owner_state is False
+
+    default = SyftRDSClientConfig.for_jupyter(
+        email="enclave@openmined.org",
+        has_do_role=True,
+        has_ds_role=True,
+    )
+    assert default.sync.datasite_owner_syncer_config.persist_owner_state is True

syft/sync/syftbox_manager.py

@@ -113,6 +113,10 @@ class SyftboxManagerConfig(BaseModel):
     has_ds_role: bool = False
     has_do_role: bool = False
     use_in_memory_cache: bool = True
+    # Keep the owner-only state used to restore this datasite later: event
+    # log, rolling state, checkpoints. Off for datasites that can never
+    # restore (see syft-enclave's EnclaveSettings).
+    persist_owner_state: bool = True
 
     datasite_owner_syncer_config: DatasiteOwnerSyncerConfig
     peer_manager_config: PeerManagerConfig
@@ -126,6 +130,7 @@ def for_colab(
         has_ds_role: bool = False,
         has_do_role: bool = False,
         encryption: bool = False,
+        persist_owner_state: bool = True,
         crypto_keys_path: Path | None = None,
         skip_peer_on_patch_version_diff: Optional[
             bool
@@ -150,6 +155,7 @@ def for_colab(
         connection_configs = [GdriveConnectionConfig(email=email, token_path=None)]
         datasite_owner_syncer_config = DatasiteOwnerSyncerConfig(
             email=email,
+            persist_owner_state=persist_owner_state,
             syftbox_folder=syftbox_folder,
             collections_folder=collections_folder,
             collection_specs=collection_specs,
@@ -192,6 +198,7 @@ def for_colab(
             has_do_role=has_do_role,
             connection_configs=connection_configs,
             use_in_memory_cache=False,
+            persist_owner_state=persist_owner_state,
             datasite_owner_syncer_config=datasite_owner_syncer_config,
             datasite_watcher_syncer_config=datasite_watcher_syncer_config,
             peer_manager_config=peer_manager_config,
@@ -205,6 +212,7 @@ def for_jupyter(
         has_do_role: bool = False,
         token_path: Path | None = None,
         encryption: bool = False,
+        persist_owner_state: bool = True,
         crypto_keys_path: Path | None = None,
         skip_peer_on_patch_version_diff: Optional[
             bool
@@ -232,6 +240,7 @@ def for_jupyter(
         ]
         datasite_owner_syncer_config = DatasiteOwnerSyncerConfig(
             email=email,
+            persist_owner_state=persist_owner_state,
             syftbox_folder=syftbox_folder,
             collections_folder=collections_folder,
             collection_specs=collection_specs,
@@ -274,6 +283,7 @@ def for_jupyter(
             has_ds_role=has_ds_role,
             has_do_role=has_do_role,
             use_in_memory_cache=False,
+            persist_owner_state=persist_owner_state,
             datasite_owner_syncer_config=datasite_owner_syncer_config,
             datasite_watcher_syncer_config=datasite_watcher_syncer_config,
             peer_manager_config=peer_manager_config,
@@ -288,6 +298,7 @@ def _base_config_for_testing(
         has_ds_role: bool = False,
         has_do_role: bool = False,
         use_in_memory_cache: bool = True,
+        persist_owner_state: bool = True,
         check_versions: bool = False,
         collection_specs: list["CollectionSyncSpec"] | None = None,
     ):
@@ -306,6 +317,7 @@ def _base_config_for_testing(
 
         datasite_owner_syncer_config = DatasiteOwnerSyncerConfig(
             email=email,
+            persist_owner_state=persist_owner_state,
             syftbox_folder=syftbox_folder,
             collections_folder=collections_folder,
             collection_specs=collection_specs,
@@ -346,6 +358,7 @@ def _base_config_for_testing(
             has_ds_role=has_ds_role,
             has_do_role=has_do_role,
             use_in_memory_cache=use_in_memory_cache,
+            persist_owner_state=persist_owner_state,
             datasite_owner_syncer_config=datasite_owner_syncer_config,
             datasite_watcher_syncer_config=datasite_watcher_syncer_config,
             peer_manager_config=peer_manager_config,
@@ -361,6 +374,7 @@ def for_google_drive_testing_connection(
         has_ds_role: bool = False,
         has_do_role: bool = False,
         use_in_memory_cache: bool = True,
+        persist_owner_state: bool = True,
         check_versions: bool = False,
         collection_specs: list["CollectionSyncSpec"] | None = None,
     ):
@@ -381,6 +395,7 @@ def for_google_drive_testing_connection(
         ]
         datasite_owner_syncer_config = DatasiteOwnerSyncerConfig(
             email=email,
+            persist_owner_state=persist_owner_state,
             syftbox_folder=syftbox_folder,
             collections_folder=collections_folder,
             collection_specs=collection_specs,
@@ -418,6 +433,7 @@ def for_google_drive_testing_connection(
             email=email,
             syftbox_folder=syftbox_folder,
             write_files=write_files,
+            persist_owner_state=persist_owner_state,
             datasite_owner_syncer_config=datasite_owner_syncer_config,
             datasite_watcher_syncer_config=datasite_watcher_syncer_config,
             has_ds_role=has_ds_role,
@@ -587,6 +603,7 @@ def for_colab(
         has_ds_role: bool = False,
         has_do_role: bool = False,
         encryption: bool = False,
+        persist_owner_state: bool = True,
         crypto_keys_path: Path | None = None,
         skip_peer_on_patch_version_diff: Optional[
             bool
@@ -599,6 +616,7 @@ def for_colab(
                 has_ds_role=has_ds_role,
                 has_do_role=has_do_role,
                 encryption=encryption,
+                persist_owner_state=persist_owner_state,
                 crypto_keys_path=crypto_keys_path,
                 skip_peer_on_patch_version_diff=skip_peer_on_patch_version_diff,
                 force_ignore_peer_version=force_ignore_peer_version,
@@ -614,6 +632,7 @@ def for_jupyter(
         has_do_role: bool = False,
         token_path: Path | None = None,
         encryption: bool = False,
+        persist_owner_state: bool = True,
         crypto_keys_path: Path | None = None,
         skip_peer_on_patch_version_diff: Optional[
             bool
@@ -629,6 +648,7 @@ def for_jupyter(
                 has_do_role=has_do_role,
                 token_path=token_path,
                 encryption=encryption,
+                persist_owner_state=persist_owner_state,
                 crypto_keys_path=crypto_keys_path,
                 skip_peer_on_patch_version_diff=skip_peer_on_patch_version_diff,
                 force_ignore_peer_version=force_ignore_peer_version,
@@ -648,6 +668,7 @@ def _pair_with_google_drive_testing_connection(
         add_peers: bool = True,
         load_peers: bool = False,
         use_in_memory_cache: bool = True,
+        persist_owner_state: bool = True,
         clear_caches: bool = True,
         check_versions: bool = False,
         collection_specs: list["CollectionSyncSpec"] | None = None,
@@ -656,6 +677,7 @@ def _pair_with_google_drive_testing_connection(
             email=do_email,
             syftbox_folder=base_path1,
             use_in_memory_cache=use_in_memory_cache,
+            persist_owner_state=persist_owner_state,
             token_path=do_token_path,
             has_ds_role=False,
             has_do_role=True,
@@ -669,6 +691,7 @@ def _pair_with_google_drive_testing_connection(
             email=ds_email,
             syftbox_folder=base_path2,
             use_in_memory_cache=use_in_memory_cache,
+            persist_owner_state=persist_owner_state,
             token_path=ds_token_path,
             has_ds_role=True,
             has_do_role=False,
@@ -732,6 +755,7 @@ def pair_with_mock_drive_service_connection(
         sync_automatically: bool = False,
         add_peers: bool = True,
         use_in_memory_cache: bool = True,
+        persist_owner_state: bool = True,
         check_versions: bool = False,
         encryption: bool = False,
         collection_specs: list["CollectionSyncSpec"] | None = None,
@@ -750,6 +774,7 @@ def pair_with_mock_drive_service_connection(
             sync_automatically: Whether to sync when DS sends changes
             add_peers: Whether to automatically add and approve peers
             use_in_memory_cache: Whether to use in-memory caches
+            persist_owner_state: Whether the DO keeps restorable owner state
             check_versions: Whether to check protocol/client versions
 
         Returns:
@@ -762,6 +787,7 @@ def pair_with_mock_drive_service_connection(
             has_ds_role=False,
             has_do_role=True,
             use_in_memory_cache=use_in_memory_cache,
+            persist_owner_state=persist_owner_state,
             check_versions=check_versions,
             collection_specs=collection_specs,
         )
@@ -772,6 +798,7 @@ def pair_with_mock_drive_service_connection(
             has_ds_role=True,
             has_do_role=False,
             use_in_memory_cache=use_in_memory_cache,
+            persist_owner_state=persist_owner_state,
             check_versions=check_versions,
             collection_specs=collection_specs,
         )
@@ -933,7 +960,10 @@ def sync(
 
         Args:
             auto_checkpoint: If True, automatically create checkpoint when
-                            event count exceeds threshold (DO only).
+                            event count exceeds threshold (DO only). Has no
+                            effect when this manager was built with
+                            persist_owner_state=False, which keeps no
+                            checkpoints at all.
             checkpoint_threshold: Create checkpoint when events >= this value.
             auto_compact: If True, after each DO sync, compact each peer's
                           outbox if it holds at least `compact_threshold`