report unknown label values to error reporting

snarfed · Oct 21, 2024 · 42006ef · 42006ef
1 parent 1b1c5fd
commit 42006ef
Show file tree

Hide file tree

Showing 5 changed files with 49 additions and 24 deletions.
diff --git a/README.md b/README.md
@@ -1,11 +1,15 @@
 # self-labeler
 
-A [Bluesky](https://bsky.social/)/[AT Protocol](https://atproto.com/)'s [labeler aka mod service](https://bsky.social/about/blog/4-13-2023-moderation) that emits custom [self-labels](https://atproto.com/specs/label#self-labels-in-records) (except [global labels](https://docs.bsky.app/docs/advanced-guides/moderation#global-label-values)) that already exist inside records.
+[bsky.app/profile/self-labeler.snarfed.org](https://bsky.app/profile/self-labeler.snarfed.org) (`did:plc:4wgmwsq4t3tg55ffl3r7ocec`)
+
+A [Bluesky](https://bsky.social/)/[AT Protocol](https://atproto.com/) [labeler aka mod service](https://bsky.social/about/blog/4-13-2023-moderation) that emits custom [self-labels](https://atproto.com/specs/label#self-labels-in-records) (except [global labels](https://docs.bsky.app/docs/advanced-guides/moderation#global-label-values)) that already exist inside records.
 
 Apart from the [global labels](https://docs.bsky.app/docs/advanced-guides/moderation#global-label-values) built into [bsky.app](https://bsky.app/), other custom self-labels are often not displayed or handled by clients. This surfaces those labels and makes them visible.
 
 [Background discussion.](https://github.com/bluesky-social/atproto/discussions/2885)
 
+License: This project is placed in the public domain. You may also use it under the [CC0 License](https://creativecommons.org/publicdomain/zero/1.0/).
+
 
 ## Setup
 
@@ -44,3 +48,8 @@ Apart from the [global labels](https://docs.bsky.app/docs/advanced-guides/modera
             encryption_algorithm=serialization.NoEncryption(),
         ))
     ```
+
+
+### Declaration record
+
+The [labeler declaration record](https://docs.bsky.app/docs/advanced-guides/moderation#labeler-declarations) is `at://did:plc:4wgmwsq4t3tg55ffl3r7ocec/app.bsky.labeler.service/self'. To add a new label value definition to it, run `npx @skyware/labeler add`. [Docs.](https://skyware.js.org/guides/labeler/introduction/getting-started/)
diff --git a/app.py b/app.py
@@ -21,6 +21,8 @@
 import arroba.util
 from cryptography.hazmat.primitives import serialization
 from flask import Flask
+from google.cloud import error_reporting
+import google.cloud.logging
 import lexrpc.flask_server
 import lexrpc.server
 import simple_websocket
@@ -36,8 +38,17 @@
     'sexual',
 ]
 
+KNOWN_LABELS = [
+    'bridged-from-bridgy-fed-activitypub',
+    'bridged-from-bridgy-fed-web',
+]
+
 logger = logging.getLogger(__name__)
 logging.basicConfig()
+logging_client = google.cloud.logging.Client()
+logging_client.setup_logging(log_level=logging.DEBUG)
+
+error_reporting_client = error_reporting.Client()
 
 logger.info('Loading #atproto_label private key from privkey.atproto_label.pem')
 with open('privkey.atproto_label.pem', 'rb') as f:
@@ -83,6 +94,8 @@ def jetstream():
             labels = []
             uri = f'at://{msg["did"]}/{commit["collection"]}/{commit["rkey"]}'
             for val in values:
+                if val not in KNOWN_LABELS:
+                    error_reporting_client.report(f'new label! {val} {uri} {cid}')
                 label = {
                     'ver': 1,
                     'src': msg['did'],
@@ -123,7 +136,6 @@ def subscribe_labels(cursor=None):
 
 
 # start jetstream consumer
-# if LOCAL_SERVER or not DEBUG:
 assert 'jetstream' not in [t.name for t in threading.enumerate()]
 Thread(target=jetstream, name='jetstream').start()
 

diff --git a/app.yaml b/app.yaml
@@ -13,7 +13,7 @@ runtime_config:
 
 resources:
   cpu: 1
-  memory_gb: 1.6
+  memory_gb: 3.6
 
 # can't be internal because Bluesky relay(s) need to be able to connect to us
 # over websocket for subscribeRepos

diff --git a/requirements.txt b/requirements.txt
@@ -11,25 +11,48 @@ charset-normalizer==3.4.0
 cryptography==43.0.3
 dag-cbor==0.3.3
 dag-json==0.3
+deprecated==1.2.14
 dnspython==2.7.0
-Flask==3.0.3
 flask-sock==0.7.0
+Flask==3.0.3
+google-api-core==2.21.0
+google-auth==2.35.0
+google-cloud-appengine-logging==1.4.5
+google-cloud-audit-log==0.3.0
+google-cloud-core==2.4.1
+google-cloud-error-reporting==1.11.1
+google-cloud-error-reporting==1.11.1
+google-cloud-logging==3.11.3
+google-cloud-logging==3.11.3
+googleapis-common-protos==1.65.0
 grapheme==0.6.0
+grpc-google-iam-v1==0.13.1
+grpcio-status==1.67.0
+grpcio==1.67.0
 h11==0.14.0
 idna==3.10
+importlib-metadata==8.4.0
 iterators==0.2.0
 Jinja2==3.1.4
 lexrpc==1.0
 libipld==1.2.3
 MarkupSafe==3.0.2
-multiformats==0.3.1.post4
 multiformats-config==0.3.1
+multiformats==0.3.1.post4
+opentelemetry-api==1.27.0
+proto-plus==1.24.0
+protobuf==5.28.2
+pyasn1-modules==0.4.1
+pyasn1==0.6.1
 pycparser==2.22
 pyjwt==2.9.0
 requests==2.32.3
+rsa==4.9
 simple-websocket==1.1.0
 typing-extensions==4.12.2
 typing-validation==1.2.11.post4
 urllib3==2.2.3
 Werkzeug==3.0.4
+wrapt==1.16.0
 wsproto==1.2.0
+zipp==3.20.2
diff --git a/test_app.py b/test_app.py