lex-metering 0.1.5 → 0.1.6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 13443e923c7850c17785f0e750d1bdb995575da237592758c7578de30c321081
-  data.tar.gz: e054cb9fd8222b5d0616f82afb46669541fccfa54c9de4dbd7f83360cb4e7967
+  metadata.gz: f0014a77ce8b15e51cc4f1ae2edc8804fdd22fc85042fdabe7a556c275ed9d3c
+  data.tar.gz: 26b9fd1245b65d5ae61ec9832c2ec3c80fe857ebb13ec28526d828f873ebb33f
 SHA512:
-  metadata.gz: 561748036537315786f810e594f005f58de6f4b2793ec497967dd00ae7488ac7c75a7fd4f7ddfeeea0f5cdd2da9442b3ffe434f4a419d3f083c63c3cea958a47
-  data.tar.gz: 0dfdb4731304dadc64f56c02e3c71edd939137026b51f057cf5c181412edc4b4b23c02d7bae8ae65451ce8e41c222bd5bbc5a9944991bec3c3dc282ee08c4b21
+  metadata.gz: ca6352cb2ff5ef6b9067f962561679e03042ec6ee9780b2efda08f2d1198cb4bc8013884bc6756e713221193bb4ca949ddcc979b8bd09e2f094800535d170d63
+  data.tar.gz: 30afaffe29668eb64d0a17d52c566c6e87a98cd8d92b08ffc54f7e9552ffc46b5a06d2302558382cf712dcba06a3081282aa78414185bf55bea29a2ceeaabc8f

data/CHANGELOG.md

@@ -1,5 +1,13 @@
 # Changelog
 
+## [0.1.6] - 2026-03-21
+
+### Added
+- `Runners::CostOptimizer` module with `analyze_costs` method for weekly LLM cost analysis
+- `Actor::CostOptimizer` periodic actor (runs weekly) to trigger cost analysis
+- Cost rate tables for Anthropic, OpenAI, Bedrock, and Azure AI models
+- LLM-powered recommendation generation for model rightsizing
+
 ## [0.1.5] - 2026-03-20
 
 ### Added

data/lib/legion/extensions/metering/actors/cost_optimizer.rb

@@ -0,0 +1,39 @@
+# frozen_string_literal: true
+
+module Legion
+  module Extensions
+    module Metering
+      module Actor
+        class CostOptimizer < Legion::Extensions::Actors::Every
+          def runner_class
+            'Legion::Extensions::Metering::Runners::CostOptimizer'
+          end
+
+          def runner_function
+            'analyze_costs'
+          end
+
+          def time
+            604_800 # once per week
+          end
+
+          def run_now?
+            false
+          end
+
+          def use_runner?
+            false
+          end
+
+          def check_subtask?
+            false
+          end
+
+          def generate_task?
+            false
+          end
+        end
+      end
+    end
+  end
+end

data/lib/legion/extensions/metering/runners/cost_optimizer.rb

@@ -0,0 +1,97 @@
+# frozen_string_literal: true
+
+module Legion
+  module Extensions
+    module Metering
+      module Runners
+        module CostOptimizer
+          def analyze_costs(window_days: 7, top_n: 10)
+            drivers = collect_cost_data(window_days: window_days)
+            return { status: 'no_data', window_days: window_days, cost_drivers: [], recommendations: [] } if drivers.empty?
+
+            top_drivers = drivers.sort_by { |d| -(d[:total_cost] || 0) }.first(top_n)
+            recommendations = generate_recommendations(top_drivers)
+
+            {
+              status:          'analyzed',
+              window_days:     window_days,
+              cost_drivers:    top_drivers,
+              recommendations: recommendations[:recommendations] || []
+            }
+          end
+
+          private
+
+          def collect_cost_data(window_days:)
+            return [] unless defined?(Legion::Data) && Legion::Data.respond_to?(:connection) && Legion::Data.connection
+
+            cutoff = Time.now.utc - (window_days * 86_400)
+            ds = Legion::Data.connection[:metering_records]
+                             .where(::Sequel.lit('recorded_at >= ?', cutoff))
+
+            grouped = ds.group(:provider, :model_id)
+                        .select_append do
+                          [sum(total_tokens).as(total_tokens),
+                           sum(input_tokens).as(input_tokens),
+                           sum(output_tokens).as(output_tokens),
+                           count(Sequel.lit('*')).as(call_count)]
+                        end
+
+            grouped.all.map do |row|
+              {
+                extension:    row[:provider],
+                model:        row[:model_id],
+                total_tokens: row[:total_tokens] || 0,
+                total_cost:   estimate_cost(row[:provider], row[:model_id], row[:total_tokens] || 0),
+                call_count:   row[:call_count] || 0
+              }
+            end
+          rescue StandardError
+            []
+          end
+
+          def estimate_cost(provider, model, total_tokens)
+            rate = cost_rate(provider, model)
+            (total_tokens * rate / 1_000_000.0).round(4)
+          end
+
+          def cost_rate(provider, model)
+            rates = {
+              'anthropic' => { 'claude-opus-4-6' => 15.0, 'claude-sonnet-4-6' => 3.0, 'claude-haiku-4-5' => 0.25 },
+              'openai'    => { 'gpt-4o' => 5.0, 'gpt-4o-mini' => 0.15, 'gpt-4.1' => 2.0 },
+              'bedrock'   => { 'default' => 3.0 },
+              'azure-ai'  => { 'default' => 3.0 }
+            }
+            provider_rates = rates[provider&.to_s] || {}
+            provider_rates[model&.to_s] || provider_rates['default'] || 1.0
+          end
+
+          def generate_recommendations(drivers)
+            return { recommendations: [] } unless defined?(Legion::LLM)
+
+            prompt = build_recommendation_prompt(drivers)
+            result = Legion::LLM.chat(message: prompt)
+            ::JSON.parse(result[:content] || '{}', symbolize_names: true)
+          rescue StandardError
+            { recommendations: [] }
+          end
+
+          def build_recommendation_prompt(drivers)
+            lines = drivers.map do |d|
+              "#{d[:extension]}/#{d[:model]}: #{d[:total_tokens]} tokens, $#{d[:total_cost]}, #{d[:call_count]} calls"
+            end
+
+            <<~PROMPT
+              Analyze these LLM cost drivers from the past week and recommend model rightsizing.
+              Focus on cases where a cheaper model could handle the workload.
+
+              #{lines.join("\n")}
+
+              Return JSON: { "recommendations": [{ "extension": "...", "current_model": "...", "suggested_model": "...", "rationale": "...", "estimated_savings_pct": N }] }
+            PROMPT
+          end
+        end
+      end
+    end
+  end
+end

data/lib/legion/extensions/metering/version.rb

@@ -3,7 +3,7 @@
 module Legion
   module Extensions
     module Metering
-      VERSION = '0.1.5'
+      VERSION = '0.1.6'
     end
   end
 end

data/lib/legion/extensions/metering.rb

@@ -1,6 +1,7 @@
 # frozen_string_literal: true
 
 require 'legion/extensions/metering/version'
+require 'legion/extensions/metering/runners/cost_optimizer'
 
 module Legion
   module Extensions

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: lex-metering
 version: !ruby/object:Gem::Version
-  version: 0.1.5
+  version: 0.1.6
 platform: ruby
 authors:
 - Esity
@@ -113,8 +113,10 @@ files:
 - lex-metering.gemspec
 - lib/legion/extensions/metering.rb
 - lib/legion/extensions/metering/actors/cleanup.rb
+- lib/legion/extensions/metering/actors/cost_optimizer.rb
 - lib/legion/extensions/metering/data/migrations/001_add_metering_records.rb
 - lib/legion/extensions/metering/helpers/economics.rb
+- lib/legion/extensions/metering/runners/cost_optimizer.rb
 - lib/legion/extensions/metering/runners/metering.rb
 - lib/legion/extensions/metering/version.rb
 homepage: https://github.com/LegionIO/lex-metering