lex-llm-vllm 0.1.8 → 0.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 3dd53d60a8e1aed0d2e1af84c39bf869b31070b927a932d18a69f79990fdd1ec
-  data.tar.gz: 739b79d90f9b6744b3eef3ff355978820692337f909cb1bb863270fd0d8114d9
+  metadata.gz: 261a83f8a4243c795e10e759e5f7f0681cd02d91b91041ff6f11f50d498d1f2a
+  data.tar.gz: c136080255383ca0d3417937d3e4988701075fef4df4c33de3e85fbd9f6ae04b
 SHA512:
-  metadata.gz: 3f1c76258f803a948b304fca1e887d4b2d8368057914b761033e7cde5f3f44d926209f1598de2acba905f783443a8cd1015318193dfd594a11febacc9821334a
-  data.tar.gz: af6c18324720d51fb6460b45463955a1944beff9f16edca35b271fb1168dc0a1b3598b4ee3dbce7c1724b0dcef772b83770f330003cea13fee03187761968d23
+  metadata.gz: a521587328074e46f4403783b85d001f6a9a4cab77e31556ea565432dea12535ed9d0c656b8f8212b20d37f196d8c08f86be25955ff25813ca908e03b5fa8e60
+  data.tar.gz: 3b74fa8c6ecfd4c71fb027a5eb13d3d41b7acf1c42cebcbfeea0e4143ec5ef9ad2693020c284eb3377a8f77fe6cd492c85ed9b9af8f515ad32918f152df224a8

data/.rubocop.yml

@@ -12,7 +12,12 @@ Metrics/BlockLength:
   Exclude:
     - "*.gemspec"
     - spec/**/*
+Metrics/ClassLength:
+  Exclude:
+    - lib/legion/extensions/llm/vllm/provider.rb
 Metrics/MethodLength:
   Enabled: false
+RSpec/ExampleLength:
+  Max: 8
 RSpec/MultipleExpectations:
   Enabled: false

data/CHANGELOG.md

@@ -1,5 +1,22 @@
 # Changelog
 
+## 0.2.0 - 2026-05-01
+
+- Add auto-discovery via CredentialSources and AutoRegistration from lex-llm 0.3.0
+- Self-register discovered instances into Call::Registry at require-time
+- Require lex-llm >= 0.3.0
+
+
+## 0.1.9 - 2026-04-30
+
+- Adopt base provider contract from lex-llm 0.1.9
+- Replace local `RegistryEventBuilder` and `RegistryPublisher` with parameterized base versions
+- Delete local `transport/` directory; base gem now ships shared exchange and message classes
+- Remove deprecated `Provider.register` call; provider options registered via `Configuration.register_provider_options`
+- Simplify `default_settings` to a flat hash (no longer delegates to `ProviderSettings.build`)
+- Override `parse_list_models_response` to populate `context_length` from vLLM `max_model_len` field
+- Require `lex-llm >= 0.1.9`
+
 ## 0.1.8 - 2026-04-30
 
 - Add `Legion::Logging::Helper` to all modules and classes for structured logging

data/lex-llm-vllm.gemspec

@@ -26,5 +26,5 @@ Gem::Specification.new do |spec|
   spec.add_dependency 'legion-json', '>= 1.2.1'
   spec.add_dependency 'legion-logging', '>= 1.3.2'
   spec.add_dependency 'legion-settings', '>= 1.3.14'
-  spec.add_dependency 'lex-llm', '>= 0.1.5'
+  spec.add_dependency 'lex-llm', '>= 0.3.0'
 end

data/lib/legion/extensions/llm/vllm/provider.rb

@@ -13,16 +13,14 @@ module Legion
           include Legion::Logging::Helper
 
           class << self
-            attr_writer :registry_publisher
-
             def slug = 'vllm'
-            def local? = true
+            def local? = false
             def configuration_options = %i[vllm_api_base vllm_api_key]
             def configuration_requirements = []
             def capabilities = Capabilities
 
             def registry_publisher
-              @registry_publisher ||= RegistryPublisher.new
+              Vllm.registry_publisher
             end
           end
 
@@ -48,8 +46,12 @@ module Legion
 
           def stream_usage_supported? = true
 
+          def settings
+            Vllm.default_settings
+          end
+
           def api_base
-            config.vllm_api_base || 'http://localhost:8000'
+            normalize_url(config.vllm_api_base || 'localhost:8000')
           end
 
           def headers
@@ -135,6 +137,22 @@ module Legion
             false
           end
 
+          def parse_list_models_response(response, provider, capabilities)
+            response.body.fetch('data', []).map do |model|
+              critical_capabilities = critical_capabilities_for(capabilities, model)
+              Legion::Extensions::Llm::Model::Info.from_hash(
+                id: model.fetch('id'),
+                name: model['id'],
+                provider: provider,
+                created_at: model_created_at(model['created']),
+                context_length: model['max_model_len'],
+                capabilities: critical_capabilities,
+                modalities: modalities_for_capabilities(critical_capabilities),
+                metadata: model
+              )
+            end
+          end
+
           def with_query(path, positional = [], **params)
             pairs = positional + params.compact.map { |key, value| [key.to_s, value] }
             return path if pairs.empty?

data/lib/legion/extensions/llm/vllm/version.rb

@@ -4,7 +4,7 @@ module Legion
   module Extensions
     module Llm
       module Vllm
-        VERSION = '0.1.8'
+        VERSION = '0.2.0'
       end
     end
   end

data/lib/legion/extensions/llm/vllm.rb

@@ -1,9 +1,7 @@
 # frozen_string_literal: true
 
 require 'legion/extensions/llm'
-require 'legion/extensions/llm/vllm/registry_event_builder'
 require 'legion/extensions/llm/vllm/provider'
-require 'legion/extensions/llm/vllm/registry_publisher'
 require 'legion/extensions/llm/vllm/version'
 
 module Legion
@@ -13,29 +11,59 @@ module Legion
       module Vllm
         extend ::Legion::Extensions::Core if ::Legion::Extensions.const_defined?(:Core, false)
         extend Legion::Logging::Helper
+        extend Legion::Extensions::Llm::AutoRegistration
 
         PROVIDER_FAMILY = :vllm
 
         def self.default_settings
-          ::Legion::Extensions::Llm.provider_settings(
-            family: PROVIDER_FAMILY,
-            instance: {
-              endpoint: 'http://localhost:8000',
-              tier: :private,
-              transport: :http,
-              usage: { inference: true, embedding: true },
-              limits: { concurrency: 8 }
-            }
-          )
+          {
+            enabled: false,
+            base_url: 'localhost:8000/v1',
+            default_model: nil,
+            enable_thinking: true,
+            model_whitelist: [],
+            model_blacklist: [],
+            model_cache_ttl: 300,
+            tls: { enabled: false, verify: :peer },
+            instances: {}
+          }
         end
 
         def self.provider_class
           Provider
         end
+
+        def self.registry_publisher
+          @registry_publisher ||= Legion::Extensions::Llm::RegistryPublisher.new(provider_family: PROVIDER_FAMILY)
+        end
+
+        def self.discover_instances
+          instances = {}
+
+          if CredentialSources.http_ok?('http://localhost:8000', path: '/health', timeout: 0.1)
+            instances[:local] = {
+              vllm_api_base: 'http://localhost:8000',
+              tier: :local,
+              capabilities: [:completion]
+            }
+          end
+
+          configured = CredentialSources.setting(:extensions, :llm, :vllm, :instances)
+          if configured.is_a?(Hash)
+            configured.each do |name, config|
+              instances[name.to_sym] = config.merge(tier: :direct)
+            end
+          end
+
+          instances
+        end
+
+        if Legion::Extensions::Llm::Configuration.respond_to?(:register_provider_options)
+          Legion::Extensions::Llm::Configuration.register_provider_options(Provider.configuration_options)
+        end
       end
     end
   end
 end
 
-Legion::Extensions::Llm::Provider.register(Legion::Extensions::Llm::Vllm::PROVIDER_FAMILY,
-                                           Legion::Extensions::Llm::Vllm::Provider)
+Legion::Extensions::Llm::Vllm.register_discovered_instances

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: lex-llm-vllm
 version: !ruby/object:Gem::Version
-  version: 0.1.8
+  version: 0.2.0
 platform: ruby
 authors:
 - LegionIO
@@ -57,14 +57,14 @@ dependencies:
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 0.1.5
+        version: 0.3.0
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 0.1.5
+        version: 0.3.0
 description: vLLM provider integration for the LegionIO LLM routing framework.
 email:
 - matthewdiverson@gmail.com
@@ -84,10 +84,6 @@ files:
 - lex-llm-vllm.gemspec
 - lib/legion/extensions/llm/vllm.rb
 - lib/legion/extensions/llm/vllm/provider.rb
-- lib/legion/extensions/llm/vllm/registry_event_builder.rb
-- lib/legion/extensions/llm/vllm/registry_publisher.rb
-- lib/legion/extensions/llm/vllm/transport/exchanges/llm_registry.rb
-- lib/legion/extensions/llm/vllm/transport/messages/registry_event.rb
 - lib/legion/extensions/llm/vllm/version.rb
 homepage: https://github.com/LegionIO/lex-llm-vllm
 licenses:

data/lib/legion/extensions/llm/vllm/registry_event_builder.rb

@@ -1,125 +0,0 @@
-# frozen_string_literal: true
-
-module Legion
-  module Extensions
-    module Llm
-      module Vllm
-        # Builds sanitized lex-llm registry envelopes for vLLM provider state.
-        class RegistryEventBuilder
-          include Legion::Logging::Helper
-
-          def readiness(readiness)
-            registry_event_class.public_send(
-              readiness[:ready] ? :available : :unavailable,
-              provider_offering(readiness),
-              runtime: runtime_metadata,
-              health: readiness_health(readiness),
-              metadata: readiness_metadata(readiness)
-            )
-          end
-
-          def model_available(model, readiness:)
-            registry_event_class.available(
-              model_offering(model),
-              runtime: runtime_metadata,
-              health: model_health(readiness),
-              metadata: model_metadata(model)
-            )
-          end
-
-          private
-
-          def provider_offering(readiness)
-            {
-              provider_family: :vllm,
-              provider_instance: provider_instance,
-              transport: :http,
-              model: 'provider-readiness',
-              usage_type: :inference,
-              capabilities: [],
-              health: readiness_health(readiness),
-              metadata: { lex: :llm_vllm, provider_readiness: true }
-            }
-          end
-
-          def model_offering(model)
-            {
-              provider_family: :vllm,
-              provider_instance: provider_instance,
-              transport: :http,
-              model: model.id,
-              usage_type: usage_type_for(model),
-              capabilities: Array(model.capabilities).map(&:to_sym),
-              limits: model_limits(model),
-              metadata: { lex: :llm_vllm, model_name: model.name }.compact
-            }
-          end
-
-          def readiness_health(readiness)
-            health = {
-              ready: readiness[:ready] == true,
-              status: readiness[:ready] ? :available : :unavailable,
-              checked: readiness.dig(:health, :checked) != false
-            }
-            add_readiness_error(health, readiness[:health])
-          end
-
-          def add_readiness_error(health, source)
-            error = source.is_a?(Hash) ? source : {}
-            error_class = error[:error] || error['error']
-            error_message = error[:message] || error['message']
-            health[:error_class] = error_class if error_class
-            health[:error] = error_message if error_message
-            health
-          end
-
-          def model_health(readiness)
-            ready = readiness.fetch(:ready, true) == true
-            { ready:, status: ready ? :available : :degraded }
-          end
-
-          def readiness_metadata(readiness)
-            {
-              extension: :lex_llm_vllm,
-              provider: :vllm,
-              configured: readiness[:configured] == true,
-              live: readiness[:live] == true
-            }
-          end
-
-          def model_metadata(model)
-            { extension: :lex_llm_vllm, provider: :vllm, model_type: model.type }
-          end
-
-          def runtime_metadata
-            { node: provider_instance }
-          end
-
-          def model_limits(model)
-            {
-              context_window: model.context_window,
-              max_output_tokens: model.max_output_tokens
-            }.compact
-          end
-
-          def usage_type_for(model)
-            model.type == 'embedding' ? :embedding : :inference
-          end
-
-          def provider_instance
-            configured_node = (::Legion::Settings.dig(:node, :canonical_name) if defined?(::Legion::Settings))
-            value = configured_node.to_s.strip
-            value.empty? ? :vllm : value.to_sym
-          rescue StandardError => e
-            handle_exception(e, level: :debug, handled: true, operation: 'vllm.registry.provider_instance')
-            :vllm
-          end
-
-          def registry_event_class
-            ::Legion::Extensions::Llm::Routing::RegistryEvent
-          end
-        end
-      end
-    end
-  end
-end

data/lib/legion/extensions/llm/vllm/registry_publisher.rb

@@ -1,94 +0,0 @@
-# frozen_string_literal: true
-
-module Legion
-  module Extensions
-    module Llm
-      module Vllm
-        # Best-effort publisher for vLLM provider availability events.
-        class RegistryPublisher
-          include Legion::Logging::Helper
-
-          APP_ID = 'lex-llm-vllm'
-
-          def initialize(builder: RegistryEventBuilder.new)
-            @builder = builder
-          end
-
-          def publish_readiness_async(readiness)
-            log.info { 'publishing readiness event to llm.registry' }
-            schedule { publish_event(@builder.readiness(readiness)) }
-          end
-
-          def publish_models_async(models, readiness:)
-            log.info { "publishing #{Array(models).size} model event(s) to llm.registry" }
-            schedule do
-              Array(models).each do |model|
-                publish_event(@builder.model_available(model, readiness:))
-              end
-            end
-          end
-
-          private
-
-          def schedule(&)
-            return false unless publishing_available?
-
-            Thread.new do
-              Thread.current.abort_on_exception = false
-              yield
-            rescue StandardError => e
-              handle_exception(e, level: :debug, handled: true, operation: 'vllm.registry.schedule_thread')
-            end
-          rescue StandardError => e
-            handle_exception(e, level: :debug, handled: true, operation: 'vllm.registry.schedule')
-            false
-          end
-
-          def publish_event(event)
-            return false unless publishing_available?
-
-            message_class.new(event:, app_id: APP_ID).publish(spool: false)
-          rescue StandardError => e
-            handle_exception(e, level: :warn, handled: true, operation: 'vllm.registry.publish_event')
-            false
-          end
-
-          def publishing_available?
-            return false unless registry_event_available?
-            return false unless transport_message_available?
-            return true unless defined?(::Legion::Transport::Connection)
-            return true unless ::Legion::Transport::Connection.respond_to?(:session_open?)
-
-            ::Legion::Transport::Connection.session_open?
-          rescue StandardError => e
-            handle_exception(e, level: :debug, handled: true, operation: 'vllm.registry.publishing_available?')
-            false
-          end
-
-          def registry_event_available?
-            defined?(::Legion::Extensions::Llm::Routing::RegistryEvent)
-          end
-
-          def transport_message_available?
-            return true if message_class_defined?
-            return false unless defined?(::Legion::Transport::Message) && defined?(::Legion::Transport::Exchange)
-
-            require 'legion/extensions/llm/vllm/transport/messages/registry_event'
-            message_class_defined?
-          rescue LoadError => e
-            handle_exception(e, level: :debug, handled: true, operation: 'vllm.registry.transport_load')
-            false
-          end
-
-          def message_class_defined?
-            defined?(::Legion::Extensions::Llm::Vllm::Transport::Messages::RegistryEvent)
-          end
-
-          def message_class
-            ::Legion::Extensions::Llm::Vllm::Transport::Messages::RegistryEvent
-          end
-        end
-      end
-    end
-  end
-end

data/lib/legion/extensions/llm/vllm/transport/exchanges/llm_registry.rb

@@ -1,24 +0,0 @@
-# frozen_string_literal: true
-
-module Legion
-  module Extensions
-    module Llm
-      module Vllm
-        module Transport
-          module Exchanges
-            # Topic exchange for vLLM provider availability events.
-            class LlmRegistry < ::Legion::Transport::Exchange
-              def exchange_name
-                'llm.registry'
-              end
-
-              def default_type
-                'topic'
-              end
-            end
-          end
-        end
-      end
-    end
-  end
-end

data/lib/legion/extensions/llm/vllm/transport/messages/registry_event.rb

@@ -1,42 +0,0 @@
-# frozen_string_literal: true
-
-require 'legion/extensions/llm/vllm/transport/exchanges/llm_registry'
-
-module Legion
-  module Extensions
-    module Llm
-      module Vllm
-        module Transport
-          module Messages
-            # Publishes lex-llm RegistryEvent envelopes to the llm.registry exchange.
-            class RegistryEvent < ::Legion::Transport::Message
-              def initialize(event:, **options)
-                super(**event.to_h.merge(options))
-              end
-
-              def exchange
-                Transport::Exchanges::LlmRegistry
-              end
-
-              def routing_key
-                @options[:routing_key] || "llm.registry.#{@options.fetch(:event_type)}"
-              end
-
-              def type
-                'llm.registry.event'
-              end
-
-              def app_id
-                @options[:app_id] || RegistryPublisher::APP_ID
-              end
-
-              def persistent # rubocop:disable Naming/PredicateMethod
-                false
-              end
-            end
-          end
-        end
-      end
-    end
-  end
-end