ruby_llm 1.13.2 → 1.14.1

data/lib/ruby_llm/aliases.json

@@ -10,7 +10,7 @@
   "claude-3-5-sonnet": {
     "anthropic": "claude-3-5-sonnet-20241022",
     "openrouter": "anthropic/claude-3.5-sonnet",
-    "bedrock": "anthropic.claude-3-5-sonnet-20240620-v1:0:200k"
+    "bedrock": "anthropic.claude-3-5-sonnet-20241022-v2:0"
   },
   "claude-3-7-sonnet": {
     "anthropic": "claude-3-7-sonnet-20250219",
@@ -26,8 +26,7 @@
     "bedrock": "anthropic.claude-3-haiku-20240307-v1:0:200k"
   },
   "claude-3-opus": {
-    "anthropic": "claude-3-opus-20240229",
-    "bedrock": "anthropic.claude-3-opus-20240229-v1:0"
+    "anthropic": "claude-3-opus-20240229"
   },
   "claude-3-sonnet": {
     "anthropic": "claude-3-sonnet-20240229",
@@ -62,7 +61,8 @@
   "claude-opus-4-6": {
     "anthropic": "claude-opus-4-6",
     "openrouter": "anthropic/claude-opus-4.6",
-    "bedrock": "anthropic.claude-opus-4-6-v1"
+    "bedrock": "anthropic.claude-opus-4-6-v1",
+    "azure": "claude-opus-4-6"
   },
   "claude-sonnet-4": {
     "anthropic": "claude-sonnet-4-20250514",
@@ -81,7 +81,8 @@
   "claude-sonnet-4-6": {
     "anthropic": "claude-sonnet-4-6",
     "openrouter": "anthropic/claude-sonnet-4.6",
-    "bedrock": "anthropic.claude-sonnet-4-6"
+    "bedrock": "anthropic.claude-sonnet-4-6",
+    "azure": "claude-sonnet-4-6"
   },
   "deepseek-chat": {
     "deepseek": "deepseek-chat",
@@ -189,7 +190,8 @@
   },
   "gemini-3.1-flash-lite-preview": {
     "gemini": "gemini-3.1-flash-lite-preview",
-    "openrouter": "google/gemini-3.1-flash-lite-preview"
+    "openrouter": "google/gemini-3.1-flash-lite-preview",
+    "vertexai": "gemini-3.1-flash-lite-preview"
   },
   "gemini-3.1-pro-preview": {
     "gemini": "gemini-3.1-pro-preview",
@@ -246,18 +248,10 @@
     "openrouter": "openai/gpt-4",
     "azure": "gpt-4"
   },
-  "gpt-4-1106-preview": {
-    "openai": "gpt-4-1106-preview",
-    "openrouter": "openai/gpt-4-1106-preview"
-  },
   "gpt-4-turbo": {
     "openai": "gpt-4-turbo",
     "openrouter": "openai/gpt-4-turbo"
   },
-  "gpt-4-turbo-preview": {
-    "openai": "gpt-4-turbo-preview",
-    "openrouter": "openai/gpt-4-turbo-preview"
-  },
   "gpt-4.1": {
     "openai": "gpt-4.1",
     "openrouter": "openai/gpt-4.1",
@@ -337,7 +331,8 @@
   },
   "gpt-5.1": {
     "openai": "gpt-5.1",
-    "openrouter": "openai/gpt-5.1"
+    "openrouter": "openai/gpt-5.1",
+    "azure": "gpt-5.1"
   },
   "gpt-5.1-codex": {
     "openai": "gpt-5.1-codex",
@@ -367,6 +362,22 @@
     "openai": "gpt-5.3-codex",
     "openrouter": "openai/gpt-5.3-codex"
   },
+  "gpt-5.4": {
+    "openai": "gpt-5.4",
+    "openrouter": "openai/gpt-5.4"
+  },
+  "gpt-5.4-mini": {
+    "openai": "gpt-5.4-mini",
+    "openrouter": "openai/gpt-5.4-mini"
+  },
+  "gpt-5.4-nano": {
+    "openai": "gpt-5.4-nano",
+    "openrouter": "openai/gpt-5.4-nano"
+  },
+  "gpt-5.4-pro": {
+    "openai": "gpt-5.4-pro",
+    "openrouter": "openai/gpt-5.4-pro"
+  },
   "gpt-audio": {
     "openai": "gpt-audio",
     "openrouter": "openai/gpt-audio"
@@ -375,6 +386,14 @@
     "openai": "gpt-audio-mini",
     "openrouter": "openai/gpt-audio-mini"
   },
+  "lyria-3-clip-preview": {
+    "gemini": "lyria-3-clip-preview",
+    "openrouter": "google/lyria-3-clip-preview"
+  },
+  "lyria-3-pro-preview": {
+    "gemini": "lyria-3-pro-preview",
+    "openrouter": "google/lyria-3-pro-preview"
+  },
   "o1": {
     "openai": "o1",
     "openrouter": "openai/o1"

data/lib/ruby_llm/attachment.rb

@@ -1,5 +1,8 @@
 # frozen_string_literal: true
 
+require 'pathname'
+require 'uri'
+
 module RubyLLM
   # A class representing a file attachment.
   class Attachment

data/lib/ruby_llm/configuration.rb

@@ -3,83 +3,64 @@
 module RubyLLM
   # Global configuration for RubyLLM
   class Configuration
-    attr_accessor :openai_api_key,
-                  :openai_api_base,
-                  :openai_organization_id,
-                  :openai_project_id,
-                  :openai_use_system_role,
-                  :azure_api_base,
-                  :azure_api_key,
-                  :azure_ai_auth_token,
-                  :anthropic_api_base,
-                  :anthropic_api_key,
-                  :gemini_api_key,
-                  :gemini_api_base,
-                  :vertexai_project_id,
-                  :vertexai_location,
-                  :vertexai_service_account_key,
-                  :deepseek_api_key,
-                  :deepseek_api_base,
-                  :perplexity_api_key,
-                  :bedrock_api_key,
-                  :bedrock_secret_key,
-                  :bedrock_region,
-                  :bedrock_session_token,
-                  :openrouter_api_base,
-                  :openrouter_api_key,
-                  :xai_api_key,
-                  :ollama_api_base,
-                  :ollama_api_key,
-                  :gpustack_api_base,
-                  :gpustack_api_key,
-                  :mistral_api_key,
-                  # Default models
-                  :default_model,
-                  :default_embedding_model,
-                  :default_moderation_model,
-                  :default_image_model,
-                  :default_transcription_model,
-                  # Model registry
-                  :model_registry_file,
-                  :model_registry_class,
-                  # Rails integration
-                  :use_new_acts_as,
-                  # Connection configuration
-                  :request_timeout,
-                  :max_retries,
-                  :retry_interval,
-                  :retry_backoff_factor,
-                  :retry_interval_randomness,
-                  :http_proxy,
-                  # Logging configuration
-                  :logger,
-                  :log_file,
-                  :log_level,
-                  :log_stream_debug
-    attr_reader :log_regexp_timeout
+    class << self
+      # Declare a single configuration option.
+      def option(key, default = nil)
+        key = key.to_sym
+        return if options.include?(key)
 
-    def initialize
-      @request_timeout = 300
-      @max_retries = 3
-      @retry_interval = 0.1
-      @retry_backoff_factor = 2
-      @retry_interval_randomness = 0.5
-      @http_proxy = nil
+        send(:attr_accessor, key)
+        option_keys << key
+        defaults[key] = default
+      end
+
+      def register_provider_options(options)
+        Array(options).each { |key| option(key, nil) }
+      end
+
+      def options
+        option_keys.dup
+      end
+
+      private
 
-      @default_model = 'gpt-5-nano'
-      @default_embedding_model = 'text-embedding-3-small'
-      @default_moderation_model = 'omni-moderation-latest'
-      @default_image_model = 'gpt-image-1'
-      @default_transcription_model = 'whisper-1'
+      def option_keys = @option_keys ||= []
+      def defaults = @defaults ||= {}
+      private :option
+    end
+
+    # System-level options are declared here.
+    # Provider-specific options are declared in each provider class via
+    # `self.configuration_options` and registered through Provider.register.
+    option :default_model, 'gpt-5.4'
+    option :default_embedding_model, 'text-embedding-3-small'
+    option :default_moderation_model, 'omni-moderation-latest'
+    option :default_image_model, 'gpt-image-1.5'
+    option :default_transcription_model, 'whisper-1'
+
+    option :model_registry_file, -> { File.expand_path('models.json', __dir__) }
+    option :model_registry_class, 'Model'
+
+    option :use_new_acts_as, false
 
-      @model_registry_file = File.expand_path('models.json', __dir__)
-      @model_registry_class = 'Model'
-      @use_new_acts_as = false
+    option :request_timeout, 300
+    option :max_retries, 3
+    option :retry_interval, 0.1
+    option :retry_backoff_factor, 2
+    option :retry_interval_randomness, 0.5
+    option :http_proxy, nil
 
-      @log_file = $stdout
-      @log_level = ENV['RUBYLLM_DEBUG'] ? Logger::DEBUG : Logger::INFO
-      @log_stream_debug = ENV['RUBYLLM_STREAM_DEBUG'] == 'true'
-      self.log_regexp_timeout = Regexp.respond_to?(:timeout) ? (Regexp.timeout || 1.0) : nil
+    option :logger, nil
+    option :log_file, -> { $stdout }
+    option :log_level, -> { ENV['RUBYLLM_DEBUG'] ? Logger::DEBUG : Logger::INFO }
+    option :log_stream_debug, -> { ENV['RUBYLLM_STREAM_DEBUG'] == 'true' }
+    option :log_regexp_timeout, -> { Regexp.respond_to?(:timeout) ? (Regexp.timeout || 1.0) : nil }
+
+    def initialize
+      self.class.send(:defaults).each do |key, default|
+        value = default.respond_to?(:call) ? instance_exec(&default) : default
+        public_send("#{key}=", value)
+      end
     end
 
     def instance_variables

data/lib/ruby_llm/connection.rb

@@ -10,7 +10,6 @@ module RubyLLM
         f.response :logger,
                    RubyLLM.logger,
                    bodies: false,
-                   response: false,
                    errors: true,
                    headers: false,
                    log_level: :debug
@@ -60,8 +59,7 @@ module RubyLLM
     def setup_logging(faraday)
       faraday.response :logger,
                        RubyLLM.logger,
-                       bodies: true,
-                       response: true,
+                       bodies: RubyLLM.logger.debug?,
                        errors: true,
                        headers: false,
                        log_level: :debug do |logger|

data/lib/ruby_llm/error.rb

@@ -7,6 +7,11 @@ module RubyLLM
     attr_reader :response
 
     def initialize(response = nil, message = nil)
+      if response.is_a?(String)
+        message = response
+        response = nil
+      end
+
       @response = response
       super(message || response&.body)
     end

data/lib/ruby_llm/model/info.rb

@@ -48,6 +48,11 @@ module RubyLLM
         name
       end
 
+      def label
+        provider_name = provider_class&.name || provider
+        "#{provider_name} - #{display_name}"
+      end
+
       def max_tokens
         max_output_tokens
       end
@@ -76,18 +81,15 @@ module RubyLLM
         RubyLLM::Provider.resolve provider
       end
 
-      def type # rubocop:disable Metrics/PerceivedComplexity
-        if modalities.output.include?('embeddings') && !modalities.output.include?('text')
-          'embedding'
-        elsif modalities.output.include?('image') && !modalities.output.include?('text')
-          'image'
-        elsif modalities.output.include?('audio') && !modalities.output.include?('text')
-          'audio'
-        elsif modalities.output.include?('moderation')
-          'moderation'
-        else
-          'chat'
-        end
+      def type
+        output = modalities.output
+        return 'embedding' if output.include?('embeddings')
+        return 'moderation' if output.include?('moderation')
+        return 'image' if output.include?('image')
+        return 'audio' if output.include?('audio')
+        return 'video' if output.include?('video')
+
+        'chat'
       end
 
       def to_h