barkibu-kb 1.1.0 → 1.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: d6665ca6f0d74295cacf6bea9ee921b3dba5decc6b5cb3775bbaa0392fd65b86
-  data.tar.gz: 700cae8005557d25ff41c3f9583725686485eff37ccbb0eec11ff07473ad9077
+  metadata.gz: 72ba3947460c029c6dee0dc965b1066b03b645d3bb6a891b291c2383b8d581e3
+  data.tar.gz: d0b5ca779b79f1e7017dbafca93376215faac264ec55210ef1af8f981f352ec5
 SHA512:
-  metadata.gz: 97dac9ae9946f9398bd62b2fda16acbd978c1e4e153e23884ab78ac3a055dec7d201fcbf3a98ed4b65403324af2b03d034a6073f30d15c20690699021fccae74
-  data.tar.gz: f9ed89dff91778420037ad50e7531af48d9b7b6d11c7d92afb1d05cdc31192498310520da51d35aa32e9ed77041e808137f5d9b699fcea24d495f2d17379b475
+  metadata.gz: 0d596248f6f49451a5a4bcb9ea1648b3175b3d8b1d7cbf0665082332841d63c32867e7f408d221f2a47ef7387e1b70836c74af5bfd8e5e37ae9536ea9b19ec42
+  data.tar.gz: e832f256a27bfbe905d6e122b81245370c932dad1801d5772608778851131c9da1e761817e164df8a91e5e770af79804cd2c0cfdc90310148048bd92ef761ea7

data/CHANGELOG.md

@@ -6,7 +6,16 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
 ## [unreleased]
-- See diff: https://github.com/barkibu/kb-ruby/compare/v1.1.0...HEAD
+- See diff: https://github.com/barkibu/kb-ruby/compare/v1.3.0...HEAD
+
+## [1.3.0]
+- Retry transport failures once (`faraday-retry`, already in the Faraday 1.10 bundle, now an explicit dependency). `KB::RetryPolicy` decides by the underlying error, not the Faraday class: failures where the request never left (`Net::OpenTimeout`, `ECONNREFUSED`, `EHOSTUNREACH`, `ENETUNREACH`, `EADDRNOTAVAIL`, `SocketError`) retry for every verb; any other transport failure (read/write timeout, reset, EOF, TLS) retries for GET/HEAD only (and not when the call raised its own `read_timeout:`, so a 30s read isn't doubled); HTTP error responses never retry. New settings `KB.config.request.retries` (default 1, 0 disables) and `retry_interval` (default 0.1s, randomized up to 2x). Worst-case latency is now two attempts' worth of phase budgets.
+- `request.kb_client` payload gains `retries` and `retry_errors` on retried calls; the Datadog subscriber tags them as `kb.retries` / `kb.retry_errors`. The event and span cover all attempts, so a call that succeeded on retry is not an error.
+- `KB::Listable.all` (and so `PetParent.all`, `Pet.all`, `Breed.all`, `Product.all`, `Plan.all`, `Assessment.all`) now wraps `Faraday::ConnectionFailed` in `KB::Error` like every other model call, instead of re-raising it raw. Code rescuing `Faraday::ConnectionFailed` around `.all` must rescue `KB::Error` instead; none of Funnel, Global Admin or connected_health does.
+
+## [1.2.0]
+- `KB::Client` emits one `request.kb_client` `ActiveSupport::Notifications` event per KB call (`KB::Client::REQUEST_EVENT`), wrapping cache lookup, connect, TLS, write, read and parsing. Payload: `verb`, `path`, `base_url`, `cache_hit` (GET only), `status`, plus ActiveSupport's `exception`/`exception_object` when the call raised. Every public method now goes through one private `perform` seam; no behaviour change (same cache keys, params and error classes).
+- Add an opt-in Datadog subscriber: `require 'kb/instrumentation/datadog'` + `KB::Instrumentation::Datadog.subscribe!` turns each event into a `kb.client.request` APM span, opened on event start and closed on finish so the tracer's Net::HTTP spans nest under it. The span inherits the app's service and stays there (no `span.kind:client`/`peer.service`, so it is not attributed to the knowledge-base service), tags `peer.hostname`, `kb.method`, `kb.cache_hit`, `http.status_code`, and uses low-cardinality resources (`GET /v1/pets/?/contracts`). Motivation: connect timeouts happen before `Net::HTTP#request`, so the Datadog Net::HTTP tracer never sees them and they were invisible on our dashboards. Works with `ddtrace` 1.x and `datadog` 2.x; the tracer stays the app's dependency.
 
 ## [1.1.0]
 - Add `read_timeout:` to `KB::Client#request` to raise the read budget for a single call (e.g. `GET /v1/pets/birthdays`, whose server-side work runs for seconds). Connect and write budgets stay global; the override does not leak into later calls on the same connection.

data/Gemfile.lock

@@ -1,17 +1,18 @@
 PATH
   remote: .
   specs:
-    barkibu-kb (1.1.0)
+    barkibu-kb (1.3.0)
       activemodel (>= 4.0.2)
       activerecord
       activesupport (>= 3.0.0)
       dry-configurable (~> 0.9)
       faraday
       faraday-net_http (~> 1.0)
+      faraday-retry (~> 1.0)
       faraday_middleware
       i18n
-    barkibu-kb-fake (1.1.0)
-      barkibu-kb (= 1.1.0)
+    barkibu-kb-fake (1.3.0)
+      barkibu-kb (= 1.3.0)
       countries
       sinatra
       webmock
@@ -44,12 +45,21 @@ GEM
     base64 (0.3.0)
     bigdecimal (4.1.2)
     byebug (11.1.3)
+    cgi (0.5.2)
     concurrent-ruby (1.3.7)
     connection_pool (3.0.2)
     countries (5.3.1)
       unaccent (~> 0.3)
     crack (0.4.5)
       rexml
+    datadog (2.43.0)
+      cgi
+      datadog-ruby_core_source (~> 3.5, >= 3.5.5)
+      libdatadog (~> 40.0.0.2.0)
+      libddwaf (~> 1.30.0.0.0)
+      logger
+      msgpack
+    datadog-ruby_core_source (3.5.5)
     diff-lcs (1.4.4)
     docile (1.4.0)
     drb (2.2.3)
@@ -84,14 +94,19 @@ GEM
     faraday-retry (1.0.3)
     faraday_middleware (1.2.0)
       faraday (~> 1.0)
+    ffi (1.17.4)
     hashdiff (1.0.1)
     i18n (1.15.2)
       concurrent-ruby (~> 1.0)
     json (2.20.0)
+    libdatadog (40.0.0.2.0)
+    libddwaf (1.30.0.0.2)
+      ffi (~> 1.0)
     logger (1.7.0)
     minitest (6.0.6)
       drb (~> 2.0)
       prism (~> 1.5)
+    msgpack (1.8.5)
     multipart-post (2.3.0)
     mustermann (3.0.0)
       ruby2_keywords (~> 0.0.1)
@@ -173,6 +188,7 @@ DEPENDENCIES
   bigdecimal
   bundler
   byebug
+  datadog (~> 2.0)
   rake (>= 12.3.3)
   rspec (~> 3.0)
   rubocop

data/README.md

@@ -74,6 +74,86 @@ and write budgets stay global:
 KB::Pet.kb_client.request('birthdays', filters: { month: 9, day: 22, size: 1000 }, read_timeout: 30)
 ```
 
+#### Retries
+
+The client retries a failed call once when the failure is in the transport, never
+when KB answered with an HTTP error. Which calls retry depends on whether the
+request can have reached KB (`KB::RetryPolicy`):
+
+| Failure | Retried for |
+|---|---|
+| Never sent: connect/TLS timeout (`Net::OpenTimeout`), connection refused, host/network unreachable, DNS failure | every verb, POST included |
+| Maybe sent: read/write timeout, connection reset, EOF, TLS error mid-stream | GET and HEAD only |
+| HTTP 4xx/5xx | never |
+
+PUT and DELETE are not retried on "maybe sent" failures: `upsert` and
+`PetParent#merge!` are PUTs whose second run is not a no-op on KB's side, and a
+repeated DELETE would turn a success into a 404. A call that raised its own read
+budget (`read_timeout:` on `KB::Client#request`) is not retried on "maybe sent"
+failures either, so a 30s birthdays read can't become 60s; failures that never
+reached KB are still retried.
+
+```ruby
+# config/initializers/kb_ruby.rb
+KB.config.request.retries = 1          # default; 0 disables retries
+KB.config.request.retry_interval = 0.1 # default, seconds; each wait is 1x-2x this
+```
+
+Like the timeouts, these are read when a client builds its connection, i.e. on
+its first call, so set them in an initializer.
+
+Worst case, a call now takes two attempts' worth of phase budgets plus the
+interval, e.g. a GET that read-times-out twice takes about 2 x (1 + 3 + 5)s with
+the default timeouts.
+
+#### Instrumentation
+
+Every KB call emits one `request.kb_client` event through
+`ActiveSupport::Notifications`, wrapping the whole call: cache lookup, TCP
+connect, TLS, write, read and JSON parsing. The payload carries `verb`, `path`,
+`base_url`, `cache_hit` (GET calls only), `status` (when a response arrived),
+`retries` and `retry_errors` (only when the call was retried: the count, and the
+underlying error class of each failed attempt, e.g. `["Net::OpenTimeout"]`) and
+ActiveSupport's `exception` / `exception_object` when the call raised. The event
+covers the whole call including retries, so `exception` is set only when every
+attempt failed. Subscribe to it for logging, metrics or anything else:
+
+```ruby
+ActiveSupport::Notifications.subscribe(KB::Client::REQUEST_EVENT) do |event|
+  Rails.logger.info("KB #{event.payload[:verb]} #{event.payload[:path]} #{event.duration.round}ms")
+end
+```
+
+##### Datadog
+
+A ready-made subscriber turns each event into a `kb.client.request` APM span.
+Opt in from the app's Datadog initializer, after `Datadog.configure`. Works with
+both `ddtrace` 1.x and `datadog` 2.x; the tracer gem is the app's dependency.
+
+```ruby
+# config/initializers/datadog_tracer.rb
+Datadog.configure { |c| ... }
+
+require 'kb/instrumentation/datadog'
+KB::Instrumentation::Datadog.subscribe!
+```
+
+The span opens when the event starts and closes when it finishes, so the
+tracer's own Net::HTTP spans nest under it. It inherits the app's service
+(`c.service`), so nothing new appears in the APM service list, and it carries no
+`span.kind:client` or `peer.service`, so Datadog does not attribute it to the
+knowledge-base service either: it measures the client's whole call, not a KB
+operation. Resources are low-cardinality (`GET /v1/pets/birthdays`,
+`GET /v1/pets/?/contracts`). Tags: `peer.hostname` (the KB host used),
+`kb.method`, `kb.cache_hit` (GET calls only), `http.status_code`, `kb.retries`
+and `kb.retry_errors` (retried calls only), plus the standard
+`error.type`/`error.message` when the call raises. A span with `kb.retries` and
+no error is a failure the retry absorbed.
+
+Why not rely on the Net::HTTP tracer alone: faraday-net_http opens the socket
+before `Net::HTTP#request`, the method that tracer patches, so a connect timeout
+produces no http span at all. This span sees every phase.
+
 ### Exposed Entities
 
 #### Pet Parent 🧍🏾

data/barkibu-kb.gemspec

@@ -39,6 +39,7 @@ Gem::Specification.new do |spec|
   spec.add_dependency 'dry-configurable', '~> 0.9'
   spec.add_development_dependency 'bundler'
   spec.add_development_dependency 'byebug'
+  spec.add_development_dependency 'datadog', '~> 2.0'
   spec.add_development_dependency 'rake', '>= 12.3.3'
   spec.add_development_dependency 'rspec', '~> 3.0'
   spec.add_development_dependency 'rubocop'
@@ -53,5 +54,6 @@ Gem::Specification.new do |spec|
   spec.add_runtime_dependency 'faraday'
   spec.add_runtime_dependency 'faraday-net_http', '~> 1.0'
   spec.add_runtime_dependency 'faraday_middleware'
+  spec.add_runtime_dependency 'faraday-retry', '~> 1.0'
   spec.add_runtime_dependency 'i18n'
 end

data/lib/barkibu-kb.rb

@@ -21,6 +21,9 @@ module KB
     setting :connect_timeout, default: 1
     setting :write_timeout, default: 3
     setting :read_timeout, default: 5
+    # Retries after a transport failure, per KB::RetryPolicy. 0 disables retries.
+    setting :retries, default: 1
+    setting :retry_interval, default: 0.1
   end
 end
 
@@ -29,6 +32,7 @@ require 'kb/inflections'
 require 'kb/cache'
 require 'kb/client_resolver'
 require 'kb/errors'
+require 'kb/retry_policy'
 require 'kb/client'
 
 require 'kb/concerns'

data/lib/kb/client.rb

@@ -1,5 +1,11 @@
 module KB
   class Client
+    # Emitted once per KB call, wrapping cache lookup and the HTTP request.
+    # Payload: verb, path, base_url, cache_hit (GET only), status (when a response arrived),
+    # retries / retry_errors (only when the call was retried, see KB::RetryPolicy),
+    # plus ActiveSupport's exception/exception_object when the call raised.
+    REQUEST_EVENT = 'request.kb_client'.freeze
+
     attr_reader :api_key, :base_url
 
     def initialize(base_url, api_key: ENV['KB_API_KEY'])
@@ -11,47 +17,38 @@ module KB
     # for the few endpoints whose server-side work legitimately runs for seconds
     # (e.g. GET /v1/pets/birthdays). Connect and write budgets stay global.
     def request(sub_path, filters: nil, method: :get, read_timeout: nil)
-      options = request_options(read_timeout)
-      return connection.public_send(method, sub_path, attributes_to_json(filters), &options).body if method != :get
+      return perform(method, sub_path, attributes_to_json(filters), read_timeout: read_timeout) if method != :get
 
       cache_key = "#{@base_url}/#{sub_path}/#{(filters || {}).sort.to_h}"
-      KB::Cache.fetch(cache_key) do
-        connection.public_send(method, sub_path, filters, &options).body
-      end
+      perform(:get, sub_path, filters, cache_key: cache_key, read_timeout: read_timeout)
     end
 
     def all(filters = {})
-      cache_key = "#{@base_url}/#{filters.sort.to_h}"
-
-      KB::Cache.fetch(cache_key) do
-        connection.get('', attributes_case_transform(filters)).body
-      end
+      perform(:get, '', attributes_case_transform(filters), cache_key: "#{@base_url}/#{filters.sort.to_h}")
     end
 
     def find(key, params = {})
       raise Faraday::ResourceNotFound, {} if key.blank?
 
-      KB::Cache.fetch("#{@base_url}/#{key}") do
-        connection.get(key, attributes_case_transform(params)).body
-      end
+      perform(:get, key, attributes_case_transform(params), cache_key: "#{@base_url}/#{key}")
     end
 
     def create(attributes)
-      connection.post('', attributes_to_json(attributes)).body
+      perform(:post, '', attributes_to_json(attributes))
     end
 
     def update(key, attributes)
       clear_cache_for(key)
-      connection.patch(key.to_s, attributes_to_json(attributes)).body
+      perform(:patch, key.to_s, attributes_to_json(attributes))
     end
 
     def destroy(key)
       clear_cache_for(key)
-      connection.delete(key.to_s).body
+      perform(:delete, key.to_s)
     end
 
     def upsert(attributes)
-      connection.put('', attributes_to_json(attributes)).body
+      perform(:put, '', attributes_to_json(attributes))
     end
 
     def clear_cache_for(key)
@@ -60,6 +57,35 @@ module KB
 
     private
 
+    # Every public method ends up here, so this is the one place a KB call is
+    # observable as a whole: cache lookup, connect, TLS, write, read, parse.
+    def perform(verb, path, payload = nil, cache_key: nil, read_timeout: nil)
+      event = { verb: verb, path: path, base_url: base_url }
+      ActiveSupport::Notifications.instrument(REQUEST_EVENT, event) do
+        if cache_key
+          event[:cache_hit] = true
+          KB::Cache.fetch(cache_key) do
+            event[:cache_hit] = false
+            http(event, payload, read_timeout)
+          end
+        else
+          http(event, payload, read_timeout)
+        end
+      end
+    end
+
+    def http(event, payload, read_timeout)
+      response = connection.public_send(event[:verb], event[:path], payload) do |req|
+        req.options.read_timeout = read_timeout if read_timeout
+        RetryPolicy.track(req, event, read_timeout)
+      end
+      event[:status] = response.status
+      response.body
+    rescue Faraday::ClientError, Faraday::ServerError => e
+      event[:status] = e.response && e.response[:status]
+      raise
+    end
+
     def headers
       {
         'Content-Type': 'application/json',
@@ -79,6 +105,7 @@ module KB
 
     def connection
       @connection ||= Faraday.new(url: base_url, headers: headers, request: request_timeouts) do |conn|
+        conn.request :retry, RetryPolicy.middleware_options
         conn.response :json
         conn.response :raise_error
         if KB.config.log_level == :debugger
@@ -90,12 +117,6 @@ module KB
       end
     end
 
-    def request_options(read_timeout)
-      return nil if read_timeout.nil?
-
-      ->(req) { req.options.read_timeout = read_timeout }
-    end
-
     def request_timeouts
       {
         open_timeout: KB.config.request.connect_timeout,

data/lib/kb/instrumentation/datadog.rb

@@ -0,0 +1,93 @@
+require 'uri'
+require 'active_support/notifications'
+
+module KB
+  module Instrumentation
+    # Opt-in Datadog APM tracing for every KB call, as a subscriber to the
+    # client's `request.kb_client` notification.
+    #
+    #   # config/initializers/datadog_tracer.rb, after Datadog.configure
+    #   require 'kb/instrumentation/datadog'
+    #   KB::Instrumentation::Datadog.subscribe!
+    #
+    # One `kb.client.request` span per call, opened when the event starts and
+    # closed when it finishes, so it wraps cache lookup, TCP connect, TLS,
+    # write, read and JSON parsing, and the tracer's own Net::HTTP spans nest
+    # under it. No service is given, so the span inherits the app's, and it stays
+    # there: the KB host is a plain `peer.hostname` tag, with no `span.kind:client`
+    # or `peer.service` that would attribute it to KB. Works with
+    # `ddtrace` 1.x and `datadog` 2.x; the tracer gem is the app's dependency.
+    module Datadog
+      OPERATION = 'kb.client.request'.freeze
+      # Path segments that are identifiers, collapsed to `?` so resources stay
+      # low-cardinality: `GET /v1/pets/?/contracts` rather than one per pet.
+      IDENTIFIER_SEGMENT = /\A(?:\h{8}-\h{4}-\h{4}-\h{4}-\h{12}|\d+)\z/.freeze
+      SPAN_KEY = :datadog_span
+
+      class TracerMissing < StandardError; end
+
+      class << self
+        def subscribe!
+          unless defined?(::Datadog::Tracing)
+            raise TracerMissing, "Datadog tracing is not loaded; require 'ddtrace' or 'datadog' first"
+          end
+
+          return @subscriber if @subscriber
+
+          @subscriber = ActiveSupport::Notifications.subscribe(KB::Client::REQUEST_EVENT, Subscriber.new)
+        end
+
+        def unsubscribe!
+          ActiveSupport::Notifications.unsubscribe(@subscriber) if @subscriber
+          @subscriber = nil
+        end
+
+        def subscribed?
+          !@subscriber.nil?
+        end
+
+        def resource_for(base_url, verb, path)
+          segments = (URI(base_url).path.split('/') + path.to_s.split('/')).reject(&:empty?)
+          template = segments.map { |segment| segment.match?(IDENTIFIER_SEGMENT) ? '?' : segment }
+          "#{verb.to_s.upcase} /#{template.join('/')}"
+        end
+      end
+
+      class Subscriber
+        def start(_name, _id, payload)
+          span = ::Datadog::Tracing.trace(OPERATION, type: 'http',
+                                                     resource: Datadog.resource_for(payload[:base_url], payload[:verb],
+                                                                                    payload[:path]))
+          # No span.kind:client / peer.service on purpose: the span covers the
+          # client's whole call (cache lookup, connect, parse), so it must not be
+          # inferred onto the knowledge-base service page as one of KB's operations.
+          span.set_tag('peer.hostname', URI(payload[:base_url]).host)
+          span.set_tag('kb.method', payload[:verb].to_s.upcase)
+          payload[SPAN_KEY] = span
+        end
+
+        def finish(_name, _id, payload)
+          span = payload.delete(SPAN_KEY)
+          return unless span
+
+          span.set_tag('kb.cache_hit', payload[:cache_hit].to_s) if payload.key?(:cache_hit)
+          span.set_tag('http.status_code', payload[:status].to_s) if payload[:status]
+          tag_retries(span, payload)
+          span.set_error(payload[:exception_object]) if payload[:exception_object]
+          span.finish
+        end
+
+        private
+
+        # Only on retried calls: `kb.retries` (numeric) and the distinct underlying
+        # errors that triggered them, e.g. `Net::OpenTimeout`.
+        def tag_retries(span, payload)
+          return unless payload[:retries]
+
+          span.set_tag('kb.retries', payload[:retries])
+          span.set_tag('kb.retry_errors', payload[:retry_errors].uniq.join(','))
+        end
+      end
+    end
+  end
+end

data/lib/kb/models/concerns/listable.rb

@@ -11,8 +11,6 @@ module KB
         kb_client.all(filters).map do |pet_parent|
           from_api pet_parent
         end
-      rescue Faraday::ConnectionFailed => e
-        raise e
       rescue Faraday::Error => e
         raise KB::Error.from_faraday(e)
       end

data/lib/kb/retry_policy.rb

@@ -0,0 +1,88 @@
+require 'socket'
+require 'net/http'
+require 'faraday/retry'
+
+module KB
+  # Decides which failed KB calls the client retries.
+  #
+  # Two classes of transport failure, told apart by the underlying Ruby error
+  # rather than the Faraday class (adapters disagree on the Faraday class: the
+  # net_http adapter wraps Net::OpenTimeout as ConnectionFailed, the persistent
+  # one as TimeoutError):
+  #
+  # - never sent: TCP connect / TLS handshake did not complete, so KB cannot have
+  #   seen the request. Safe to retry for every verb, POST included.
+  # - maybe sent: anything else the transport raises (read/write timeout, reset,
+  #   EOF, TLS error mid-stream). KB may have processed it, so only GET/HEAD are
+  #   retried. PUT/DELETE are left out on purpose: `upsert` and `merge!` are PUTs
+  #   whose second run is not a no-op on KB's side, and a repeated DELETE would
+  #   turn a success into a 404.
+  #   A call that raised its own read budget (`read_timeout:`, e.g. 30s for
+  #   birthdays) is not retried on these either, so its worst case isn't doubled.
+  #
+  # HTTP responses (4xx/5xx) are never retried: KB answered.
+  module RetryPolicy
+    NOT_SENT_ERRORS = [
+      Net::OpenTimeout,
+      Errno::ECONNREFUSED,
+      Errno::EHOSTUNREACH,
+      Errno::ENETUNREACH,
+      Errno::EADDRNOTAVAIL,
+      SocketError # DNS resolution
+    ].freeze
+    TRANSPORT_ERRORS = [Faraday::ConnectionFailed, Faraday::TimeoutError, Faraday::SSLError].freeze
+    MAYBE_SENT_VERBS = %i[get head].freeze
+
+    module_function
+
+    def retry?(verb, error, own_read_budget: false)
+      return false unless TRANSPORT_ERRORS.any? { |klass| error.is_a?(klass) }
+
+      not_sent?(error) || (MAYBE_SENT_VERBS.include?(verb) && !own_read_budget)
+    end
+
+    def not_sent?(error)
+      cause = root_cause(error)
+      NOT_SENT_ERRORS.any? { |klass| cause.is_a?(klass) }
+    end
+
+    # The Ruby error behind a Faraday error. `wrapped_exception` is Faraday's own
+    # explicit link to it (Ruby's `cause` is only whatever was being rescued at
+    # the raise, usually the same object). Faraday's adapters wrap the Ruby error
+    # one level deep, so one level is enough.
+    def root_cause(error)
+      (error.respond_to?(:wrapped_exception) && error.wrapped_exception) || error.cause || error
+    end
+
+    # Options for faraday-retry's middleware, read from KB.config.request.
+    def middleware_options
+      {
+        max: KB.config.request.retries,
+        interval: KB.config.request.retry_interval,
+        interval_randomness: 1, # 1x-2x the interval, so a burst of callers doesn't retry in lockstep
+        exceptions: TRANSPORT_ERRORS,
+        methods: [], # always ask retry_if
+        retry_if: lambda do |env, error|
+          retry?(env[:method], error, own_read_budget: env[:request].context&.dig(:kb_own_read_budget))
+        end,
+        retry_block: ->(env, _options, _retries_left, error) { record(env, error) }
+      }
+    end
+
+    # Hands the request.kb_client event payload (and whether the call set its own
+    # read budget) to the middleware through the request context, so each retry
+    # is reported on the call's own event.
+    def track(request, event, read_timeout = nil)
+      tracking = { kb_event: event, kb_own_read_budget: !read_timeout.nil? }
+      request.options.context = (request.options.context || {}).merge(tracking)
+    end
+
+    def record(env, error)
+      event = env[:request].context&.dig(:kb_event)
+      return unless event
+
+      event[:retries] = event.fetch(:retries, 0) + 1
+      (event[:retry_errors] ||= []) << root_cause(error).class.name
+    end
+  end
+end

data/lib/kb/version.rb

@@ -1,3 +1,3 @@
 module KB
-  VERSION = '1.1.0'.freeze
+  VERSION = '1.3.0'.freeze
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: barkibu-kb
 version: !ruby/object:Gem::Version
-  version: 1.1.0
+  version: 1.3.0
 platform: ruby
 authors:
 - Léo Figea
@@ -51,6 +51,20 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: datadog
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.0'
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
@@ -247,6 +261,20 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: faraday-retry
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.0'
 - !ruby/object:Gem::Dependency
   name: i18n
   requirement: !ruby/object:Gem::Requirement
@@ -313,6 +341,7 @@ files:
 - lib/kb/fake/bounded_context/pet_family/products.rb
 - lib/kb/fake/bounded_context/rest_resource.rb
 - lib/kb/inflections.rb
+- lib/kb/instrumentation/datadog.rb
 - lib/kb/models.rb
 - lib/kb/models/assessment.rb
 - lib/kb/models/base_model.rb
@@ -337,6 +366,7 @@ files:
 - lib/kb/models/referral.rb
 - lib/kb/models/search_result.rb
 - lib/kb/models/symptom.rb
+- lib/kb/retry_policy.rb
 - lib/kb/type/array_of_conditions_type.rb
 - lib/kb/type/array_of_strings_type.rb
 - lib/kb/type/array_of_symptoms_type.rb