dionysus-rb 1.4.0 → 1.4.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 8cd74dab3609a68e4919adb2913c5e2d428b2bd044ec785988eae123d125677b
-  data.tar.gz: 15ae10c89ce12d63f0d452bf8ebfb835a8b3593784048c003a28a093a9c77250
+  metadata.gz: aea1780da49737ea39a412112502ccefec1921bcaa8e4d9e3f4a17c01e359cb1
+  data.tar.gz: 0de793797246fa1aa63209eb9713529df3bf3b51aedca2d03be485ab3b140f43
 SHA512:
-  metadata.gz: f3a2a0e0179804ff474dc9bb7575ba565e3c4377f6755cfb31aed5c783b7a3915966af0158a50132155a18c588e44495540d47a7463e475d07260f9db4cea6ef
-  data.tar.gz: 2e4450ae8743746067d81ab3c28614c4293fec570fdb550a9240b44f4e8ed097d7f3ecc110e03f51135c8fcd8237835e0a5a3ca90f754009b9146bd2e83e4866
+  metadata.gz: 9ba62b20fdf34088c43f28bfd71e4fa721b4d512125ca030c16c61eb077354aab5751a05c1ce0192708a7fc87ccd3d3af0a63b8a2f06a48ab903858c928d4ce8
+  data.tar.gz: d67700b960048a4ea6b272d20d193ba4232115665a5a72d0b2171cec6ba089c3bb451ab36fd5092ffbec55a763fca95fa7b8b7299b3f44263122e58aea26932f

data/CHANGELOG.md

@@ -1,5 +1,11 @@
 ## [Unreleased]
 
+## [1.4.1]
+- Stamp `serialized_at` when the attempt that is actually published begins, not before the retry loop. 1.4.0 takes the stamp once and then re-serializes up to `max_snapshot_attempts` times, so a message can be published a whole retry cycle after its own stamp - and the payload it publishes is the one read last, not the one the stamp describes. Consumers rank duplicates by `[serialized_at, offset]`, so the freshest payload ended up carrying the oldest stamp and losing its group to a staler sibling. That is the failure `serialized_at` was added to prevent, reintroduced by the guard added to prevent a different one.
+- Measured on the affected topic over 65 minutes: 205 of 6,572 messages (3.12%) carried an `updated_at` LATER than their own `serialized_at`, the worst by 1,225 ms. A timestamp cannot describe a moment after the one it was taken at, so that alone proves the stamp preceded the payload.
+- `serialize_consistently` now returns `[payload, read_at]`. The looseness between stamp and payload is bounded by a single serialization pass again, as it was before 1.4.0, rather than by the whole retry cycle - so contended records, which retry most, are no longer the ones stamped most wrongly.
+- Covered end to end against a real broker in `spec/serialized_at_tracks_published_attempt_spec.rb`: a contended publish retries while a competing publish serializes once and stamps later, both are read back off the topic, and the real `RemoveDuplicatesStrategy` is asked which survives. The spec fails on 1.4.0 on both assertions.
+
 ## [1.4.0]
 
 ### Fixed

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    dionysus-rb (1.4.0)
+    dionysus-rb (1.4.1)
       activerecord (>= 5)
       activesupport (>= 3.2)
       concurrent-ruby

data/lib/dionysus/producer/karafka_responder_generator.rb

@@ -46,10 +46,10 @@ class Dionysus::Producer::KarafkaResponderGenerator
 
               record = records.sample
 
-              # the offset alone is publish order, and a message published later can carry an
-              # earlier snapshot, so consumers need to know when this payload was actually read
-              serialized_at = config.include_serialized_at_in_payload ? Time.now.utc : nil
-              payload = serialize_consistently(records, topic, batch_options)
+              # consumers rank duplicates by this stamp, so it has to describe the attempt actually
+              # published - with retries that is the last one, not the first
+              payload, read_at = serialize_consistently(records, topic, batch_options)
+              serialized_at = config.include_serialized_at_in_payload ? read_at : nil
 
               event_payload = {
                 event: event,
@@ -88,26 +88,33 @@ class Dionysus::Producer::KarafkaResponderGenerator
       # So serialize, then check whether the records moved underneath it. If they did, the payload
       # is not a snapshot of anything: reload and serialize again. Retries are bounded, and the last
       # attempt is published rather than dropped - a payload that may be torn still beats no message.
+      # returns [payload, read_at] - read_at is when the attempt that produced this payload began
       define_method :serialize_consistently do |records, current_topic, batch_options|
-        next serialize_to_payload(records, current_topic, batch_options) unless config.publish_consistent_snapshots
+        unless config.publish_consistent_snapshots
+          read_at = Time.now.utc
+          next [serialize_to_payload(records, current_topic, batch_options), read_at]
+        end
 
         max_attempts = config.max_snapshot_attempts
         attempts = 0
         loop do
+          read_at = Time.now.utc
           before = snapshot_of(records)
           payload = serialize_to_payload(records, current_topic, batch_options)
           attempts += 1
 
-          # nothing to compare against, so the guard did not run on this message at all
-          break instrument_snapshot("unsupported", attempts, records, current_topic, payload) if before.nil?
+          if before.nil?
+            # nothing to compare against, so the guard did not run on this message at all
+            break [instrument_snapshot("unsupported", attempts, records, current_topic, payload), read_at]
+          end
           if before == committed_snapshot_of(records)
-            break instrument_snapshot("consistent", attempts, records, current_topic, payload)
+            break [instrument_snapshot("consistent", attempts, records, current_topic, payload), read_at]
           end
           if attempts >= max_attempts
             # published anyway: a payload that may be torn beats no message. Nothing downstream can
             # tell this apart from a clean one - the payload carries no marker and the consumer sees
             # an ordinary message - so this counter is the only place the outcome is ever visible.
-            break instrument_snapshot("exhausted", attempts, records, current_topic, payload)
+            break [instrument_snapshot("exhausted", attempts, records, current_topic, payload), read_at]
           end
 
           records.each { |record| record.reload if record.is_a?(ActiveRecord::Base) && record.persisted? }

data/lib/dionysus/version.rb

@@ -3,5 +3,5 @@
 module Dionysus
   module Version
   end
-  VERSION = "1.4.0"
+  VERSION = "1.4.1"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: dionysus-rb
 version: !ruby/object:Gem::Version
-  version: 1.4.0
+  version: 1.4.1
 platform: ruby
 authors:
 - Karol Galanciak
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2026-08-28 00:00:00.000000000 Z
+date: 2026-08-31 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: activerecord