Uniformize spam-checker API, part 2: check_event_for_spam

changelog.d/12808.feature

@@ -0,0 +1 @@
+Update to `check_event_for_spam`. Deprecate the current callback signature, replace it with a new signature that is both less ambiguous (replacing booleans with explicit allow/block) and more powerful (ability to return explicit error codes).

docs/modules/spam_checker_callbacks.md

@@ -11,22 +11,29 @@ The available spam checker callbacks are:
 ### `check_event_for_spam`
 
 _First introduced in Synapse v1.37.0_
+_Signature extended to support Allow and Code in Synapse v1.60.0_
+_Boolean and string return value types deprecated in Synapse v1.60.0_
 
 ```python
-async def check_event_for_spam(event: "synapse.events.EventBase") -> Union[bool, str]
+async def check_event_for_spam(event: "synapse.module_api.EventBase") -> Union["synapse.module_api.Allow", "synapse.module_api.errors.Codes", str, bool]
 ```
 
-Called when receiving an event from a client or via federation. The callback must return
-either:
-- an error message string, to indicate the event must be rejected because of spam and 
-  give a rejection reason to forward to clients;
-- the boolean `True`, to indicate that the event is spammy, but not provide further details; or
-- the booelan `False`, to indicate that the event is not considered spammy.
+Called when receiving an event from a client or via federation. The callback must return either:
+  - `synapse.module_api.Allow.ALLOW`, to allow the operation. Other callbacks
+    may still decide to reject it.
+  - `synapse.api.errors.Codes` to reject the operation with an error code. In case
+    of doubt, `synapse.api.errors.Code.FORBIDDEN` is a good error code.
+  - (deprecated) a `str` to reject the operation and specify an error message. Note that clients
+    typically will not localize the error message to the user's preferred locale.
+  - (deprecated) on `False`, behave as `ALLOW`. Deprecated as confusing, as some
+    callbacks in expect `True` to allow and others `True` to reject.
+  - (deprecated) on `True`, behave as `synapse.api.errors.Code.FORBIDDEN`. Deprecated as confusing, as
+    some callbacks in expect `True` to allow and others `True` to reject.
 
 If multiple modules implement this callback, they will be considered in order. If a
-callback returns `False`, Synapse falls through to the next one. The value of the first
-callback that does not return `False` will be used. If this happens, Synapse will not call
-any of the subsequent implementations of this callback.
+callback returns `synapse.module_api.Allow.ALLOW`, Synapse falls through to the next one. The value of the
+first callback that does not return `synapse.module_api.Allow.ALLOW` will be used. If this happens, Synapse
+will not call any of the subsequent implementations of this callback.
 
 ### `user_may_join_room`
 

docs/upgrade.md

@@ -177,7 +177,35 @@ has queries that can be used to check a database for this problem in advance.
 
 </details>
 
+## SpamChecker API's `check_event_for_spam` has a new signature.
 
+The previous signature has been deprecated.
+
+Whereas `check_event_for_spam` callbacks used to return `Union[str, bool]`, they should now return `Union["synapse.module_api.Allow", "synapse.module_api.errors.Codes"]`.
+
+This is part of an ongoing refactoring of the SpamChecker API to make it less ambiguous and more powerful.
+
+If you previously had
+
+```python
+async def check_event_for_spam(event):
+    if ...:
+        # Event is spam
+        return True
+    # Event is not spam
+    return False
+```
+
+you should now rather write
+
+```python
+async def check_event_for_spam(event):
+    if ...:
+        # Event is spam, mark it as forbidden (or some more precise error code).
+        return synapse.module_api.errors.Codes.FORBIDDEN
+    # Event is not spam, mark it as `ALLOW`.
+    return synapse.module_api.Allow.ALLOW
+```
 
 # Upgrading to v1.59.0
 

synapse/api/errors.py

@@ -270,9 +270,7 @@ class UnrecognizedRequestError(SynapseError):
     """An error indicating we don't understand the request you're trying to make"""
 
     def __init__(
-        self,
-        msg: str = "Unrecognized request",
-        errcode: str = Codes.UNRECOGNIZED,
+        self, msg: str = "Unrecognized request", errcode: str = Codes.UNRECOGNIZED
     ):
         super().__init__(400, msg, errcode)
 

synapse/events/spamcheck.py

@@ -27,9 +27,10 @@
     Union,
 )
 
+from synapse.api.errors import Codes
 from synapse.rest.media.v1._base import FileInfo
 from synapse.rest.media.v1.media_storage import ReadableFileWrapper
-from synapse.spam_checker_api import RegistrationBehaviour
+from synapse.spam_checker_api import Allow, Decision, RegistrationBehaviour
 from synapse.types import RoomAlias, UserProfile
 from synapse.util.async_helpers import delay_cancellation, maybe_awaitable
 from synapse.util.metrics import Measure
@@ -40,9 +41,16 @@
 
 logger = logging.getLogger(__name__)
 
+
+# A boolean returned value, kept for backwards compatibility but deprecated.
+DEPRECATED_BOOL = bool
+
+# A string returned value, kept for backwards compatibility but deprecated.
+DEPRECATED_STR = str
+
 CHECK_EVENT_FOR_SPAM_CALLBACK = Callable[
     ["synapse.events.EventBase"],
-    Awaitable[Union[bool, str]],
+    Awaitable[Union[Allow, Codes, DEPRECATED_BOOL, DEPRECATED_STR]],
 ]
 USER_MAY_JOIN_ROOM_CALLBACK = Callable[[str, str, bool], Awaitable[bool]]
 USER_MAY_INVITE_CALLBACK = Callable[[str, str, str], Awaitable[bool]]
@@ -244,7 +252,7 @@ def register_callbacks(
 
     async def check_event_for_spam(
         self, event: "synapse.events.EventBase"
-    ) -> Union[bool, str]:
+    ) -> Union[Decision, str]:
         """Checks if a given event is considered "spammy" by this server.
 
         If the server considers an event spammy, then it will be rejected if
@@ -255,18 +263,36 @@ async def check_event_for_spam(
             event: the event to be checked
 
         Returns:
-            True or a string if the event is spammy. If a string is returned it
-            will be used as the error message returned to the user.
+            - on `ALLOW`, the event is considered good (non-spammy) and should
+                be let through. Other spamcheck filters may still reject it.
+            - on `Code`, the event is considered spammy and is rejected with a specific
+                error message/code.
+            - on `str`, the event is considered spammy and the string is used as error
+                message. This usage is generally discouraged as it doesn't support
+                internationalization.
         """
         for callback in self._check_event_for_spam_callbacks:
             with Measure(
                 self.clock, "{}.{}".format(callback.__module__, callback.__qualname__)
             ):
-                res: Union[bool, str] = await delay_cancellation(callback(event))
-            if res:
-                return res
-
-        return False
+                res: Union[
+                    Decision, DEPRECATED_STR, DEPRECATED_BOOL
+                ] = await delay_cancellation(callback(event))
+                if res is False or res is Allow.ALLOW:
+                    # This spam-checker accepts the event.
+                    # Other spam-checkers may reject it, though.
+                    continue
+                elif res is True:
+                    # This spam-checker rejects the event with deprecated
+                    # return value `True`
+                    return Codes.FORBIDDEN
+                else:
+                    # This spam-checker rejects the event either with a `str`
+                    # or with a `Codes`. In either case, we stop here.
+                    return res
+
+        # No spam-checker has rejected the event, let it pass.
+        return Allow.ALLOW
 
     async def user_may_join_room(
         self, user_id: str, room_id: str, is_invited: bool

synapse/federation/federation_base.py

@@ -15,6 +15,7 @@
 import logging
 from typing import TYPE_CHECKING
 
+import synapse
 from synapse.api.constants import MAX_DEPTH, EventContentFields, EventTypes, Membership
 from synapse.api.errors import Codes, SynapseError
 from synapse.api.room_versions import EventFormatVersions, RoomVersion
@@ -98,9 +99,9 @@ async def _check_sigs_and_hash(
                 )
             return redacted_event
 
-        result = await self.spam_checker.check_event_for_spam(pdu)
+        spam_check = await self.spam_checker.check_event_for_spam(pdu)
 
-        if result:
+        if spam_check is not synapse.spam_checker_api.Allow.ALLOW:
             logger.warning("Event contains spam, soft-failing %s", pdu.event_id)
             # we redact (to save disk space) as well as soft-failing (to stop
             # using the event in prev_events).

synapse/handlers/message.py

@@ -23,6 +23,7 @@
 
 from twisted.internet.interfaces import IDelayedCall
 
+import synapse
 from synapse import event_auth
 from synapse.api.constants import (
     EventContentFields,
@@ -885,11 +886,11 @@ async def create_and_send_nonmember_event(
                 event.sender,
             )
 
-            spam_error = await self.spam_checker.check_event_for_spam(event)
-            if spam_error:
-                if not isinstance(spam_error, str):
-                    spam_error = "Spam is not permitted here"
-                raise SynapseError(403, spam_error, Codes.FORBIDDEN)
+            spam_check = await self.spam_checker.check_event_for_spam(event)
+            if spam_check is not synapse.spam_checker_api.Allow.ALLOW:
+                raise SynapseError(
+                    403, "This message had been rejected as probable spam", spam_check
+                )
 
             ev = await self.handle_new_client_event(
                 requester=requester,

synapse/module_api/__init__.py

@@ -35,6 +35,7 @@
 from twisted.internet import defer
 from twisted.web.resource import Resource
 
+from synapse import spam_checker_api
 from synapse.api.errors import SynapseError
 from synapse.events import EventBase
 from synapse.events.presence_router import (
@@ -139,13 +140,17 @@
 
 PRESENCE_ALL_USERS = PresenceRouter.ALL_USERS
 
+Allow = spam_checker_api.Allow
+# Singleton value used to mark a message as permitted.
+
 __all__ = [
     "errors",
     "make_deferred_yieldable",
     "parse_json_object_from_request",
     "respond_with_html",
     "run_in_background",
     "cached",
+    "Allow",
     "UserID",
     "DatabasePool",
     "LoggingTransaction",

synapse/spam_checker_api/__init__.py

@@ -12,13 +12,34 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 from enum import Enum
+from typing import Union
+
+from synapse.api.errors import Codes
 
 
 class RegistrationBehaviour(Enum):
     """
-    Enum to define whether a registration request should allowed, denied, or shadow-banned.
+    Enum to define whether a registration request should be allowed, denied, or shadow-banned.
     """
 
     ALLOW = "allow"
     SHADOW_BAN = "shadow_ban"
     DENY = "deny"
+
+
+class Allow(Enum):
+    """
+    Singleton to allow events to pass through in SpamChecker APIs.
+    """
+
+    ALLOW = "allow"
+
+
+Decision = Union[Allow, Codes]
+"""
+Union to define whether a request should be allowed or rejected.
+
+To accept a request, return `ALLOW`.
+
+To reject a request without any specific information, use `Codes.FORBIDDEN`.
+"""