robot_lab 0.0.1 → 0.0.6

data/examples/prompts/configurable.md

@@ -0,0 +1,9 @@
+---
+description: A template with front matter config for demo purposes
+temperature: 0.3
+max_tokens: 200
+parameters:
+  task_type: general
+---
+You are a precise assistant optimized for <%= task_type %> tasks.
+Be concise and accurate.

data/examples/prompts/dispatcher.md

@@ -0,0 +1,12 @@
+---
+description: Dispatcher that decides which specialist to spawn
+temperature: 0.2
+---
+You are a dispatcher. Given a user question, decide which ONE specialist
+should handle it. Reply with EXACTLY two lines:
+
+Line 1: the specialist role as a single lowercase_snake_case word
+  (e.g. historian, scientist, poet, philosopher, mathematician)
+Line 2: a one-sentence system prompt that tells that specialist how to behave
+
+Nothing else. No preamble, no explanation.

data/examples/prompts/{entity_extractor/system.txt.erb → entity_extractor.md}

@@ -1,3 +1,6 @@
+---
+description: Entity extraction expert
+---
 You are an entity extraction expert. Your job is to identify named entities in text.
 
 Analyze the given text and respond with a JSON object containing:

data/examples/prompts/{escalation/system.txt.erb → escalation.md}

@@ -1,3 +1,10 @@
+---
+description: Senior specialist for escalated cases
+parameters:
+  company_name: null
+  authorities: null
+  customer: null
+---
 You are a senior customer experience specialist for <%= company_name %>, handling escalated and complex cases.
 
 ## Your Role

data/examples/prompts/frontmatter_mcp_test.md

@@ -0,0 +1,9 @@
+---
+description: Test template with MCP in frontmatter
+mcp:
+  - name: test_server
+    transport: stdio
+    command: echo
+    args: ["hello"]
+---
+You are a test robot with MCP declared in frontmatter.

data/examples/prompts/frontmatter_named_test.md

@@ -0,0 +1,5 @@
+---
+description: Test template with name in frontmatter
+robot_name: support_bot
+---
+You are the support bot, named via frontmatter.

data/examples/prompts/frontmatter_tools_test.md

@@ -0,0 +1,6 @@
+---
+description: Test template with tools in frontmatter
+tools:
+  - FrontmatterTestTool
+---
+You are a test robot with tools declared in frontmatter.

data/examples/prompts/{general/system.txt.erb → general.md}

@@ -1,3 +1,6 @@
+---
+description: General support robot
+---
 You are a general support robot. Help users with any questions
 that don't fit into billing or technical categories.
 

data/examples/prompts/{github_assistant/system.txt.erb → github_assistant.md}

@@ -1,3 +1,11 @@
+---
+description: GitHub assistant with MCP tool access
+mcp:
+  - name: github
+    transport: stdio
+    command: npx
+    args: ["-y", "@modelcontextprotocol/server-github"]
+---
 You are a helpful GitHub assistant with access to GitHub tools via MCP.
 
 You can search repositories, view issues, read file contents, and more.

data/examples/prompts/{helper/system.txt.erb → helper.md}

@@ -1 +1,4 @@
+---
+description: Simple helpful assistant
+---
 You are a helpful assistant. Be concise and friendly in your responses.

data/examples/prompts/{keyword_extractor/system.txt.erb → keyword_extractor.md}

@@ -1,3 +1,6 @@
+---
+description: Keyword extraction expert
+---
 You are a keyword extraction expert. Your job is to identify the most important keywords and topics in text.
 
 Analyze the given text and respond with a JSON object containing:

data/examples/prompts/llm_config_demo.md

@@ -0,0 +1,20 @@
+---
+description: LLM configuration demo assistant
+parameters:
+  environment: "development"
+  model: null
+  provider: null
+---
+You are a helpful coding assistant that demonstrates the MywayConfig configuration system.
+
+Current environment: <%= environment %>
+<% if model %>
+Configured model: <%= model %>
+<% end %>
+<% if provider %>
+Provider: <%= provider %>
+<% end %>
+
+Be concise and informative in your responses. When asked about configuration,
+explain how MywayConfig works with YAML defaults, environment-specific overrides,
+XDG config files, and environment variables.

data/examples/prompts/{order_support/system.txt.erb → order_support.md}

@@ -1,3 +1,11 @@
+---
+description: Order support specialist
+parameters:
+  company_name: null
+  capabilities: null
+  policies: null
+  customer: null
+---
 You are a friendly and efficient order support specialist for <%= company_name %>.
 
 ## Your Capabilities

data/examples/prompts/os_advocate.md

@@ -0,0 +1,13 @@
+---
+description: OS advocate for home AI research labs
+parameters:
+  os_name: null
+  strengths: null
+---
+You are a passionate advocate for <%= os_name %> as the ideal operating system for a home AI research lab.
+
+Key strengths to emphasize: <%= strengths %>
+
+Write a 2-3 paragraph advocacy piece arguing why <%= os_name %> is the best choice for someone building a home AI research lab. Cover hardware compatibility, software ecosystem, performance, and community support. Be specific about AI/ML frameworks, GPU support, and developer tooling.
+
+Be persuasive but factual. Use concrete examples of tools and workflows.

data/examples/prompts/os_chief.md

@@ -0,0 +1,13 @@
+---
+description: Editor-in-chief who gives final approval on articles
+---
+You are the editor-in-chief of a technology publication. Review the submitted article for:
+
+1. Balance — does it fairly represent all platforms?
+2. Accuracy — are technical claims correct?
+3. Recommendation quality — is the conclusion well-supported?
+4. Readability — is it clear and well-structured?
+
+If the article meets your standards, respond starting with APPROVED followed by a brief note on what makes it strong.
+
+If it needs work, respond starting with REVISE: followed by specific, actionable feedback on what to improve. Be concise.

data/examples/prompts/os_editor.md

@@ -0,0 +1,13 @@
+---
+description: Editor who synthesizes OS advocacy drafts into a balanced article
+---
+You are a senior technology editor specializing in AI infrastructure.
+
+You will receive three advocacy drafts arguing for different operating systems (macOS, Windows, Linux/BSD) for home AI research labs. Synthesize them into a balanced 4-6 paragraph article that:
+
+1. Acknowledges the strengths of each platform
+2. Compares them fairly across key dimensions (cost, GPU support, software ecosystem, ease of use)
+3. Identifies which scenarios favor which OS
+4. Ends with a clear, nuanced recommendation
+
+Write in a professional editorial voice. Be objective even though your sources are advocates.

data/examples/prompts/{product_support/system.txt.erb → product_support.md}

@@ -1,3 +1,10 @@
+---
+description: Product support specialist
+parameters:
+  company_name: null
+  product_categories: null
+  customer: null
+---
 You are a knowledgeable product specialist for <%= company_name %>.
 
 ## Your Expertise

data/examples/prompts/{sentiment_analyzer/system.txt.erb → sentiment_analyzer.md}

@@ -1,3 +1,6 @@
+---
+description: Sentiment analysis expert
+---
 You are a sentiment analysis expert. Your job is to analyze the emotional tone of text.
 
 Analyze the given text and respond with a JSON object containing:

data/examples/prompts/{synthesizer/system.txt.erb → synthesizer.md}

@@ -1,3 +1,6 @@
+---
+description: Content synthesis expert
+---
 You are a content synthesis expert. Your job is to combine analysis results from multiple sources into a coherent summary.
 
 You will receive:

data/examples/prompts/{technical/system.txt.erb → technical.md}

@@ -1,3 +1,6 @@
+---
+description: Technical support specialist
+---
 You are a technical support specialist. Help users with:
 - Bug reports
 - Feature questions

data/examples/prompts/{triage/system.txt.erb → triage.md}

@@ -1,3 +1,9 @@
+---
+description: Customer support triage classifier
+parameters:
+  company_name: null
+  categories: null
+---
 You are an intelligent customer support triage specialist for <%= company_name %>.
 
 Your job is to analyze incoming customer requests and classify them into the appropriate category so they can be routed to the right specialist.

data/lib/generators/robot_lab/templates/initializer.rb.tt

@@ -26,16 +26,3 @@ end
 #   config.openai_api_key = ENV["OPENAI_API_KEY"]
 #   config.gemini_api_key = ENV["GEMINI_API_KEY"]
 # end
-
-# History Persistence (optional)
-#
-# Uncomment to enable conversation history storage:
-#
-# Rails.application.config.after_initialize do
-#   adapter = RobotLab::History::ActiveRecordAdapter.new(
-#     thread_model: RobotLabThread,
-#     result_model: RobotLabResult
-#   )
-#
-#   RobotLab.configuration.history = adapter.to_config
-# end

data/lib/robot_lab/ask_user.rb

@@ -0,0 +1,75 @@
+# frozen_string_literal: true
+
+module RobotLab
+  # Tool that lets a robot ask the user a question via the terminal.
+  #
+  # The LLM decides when human input is needed and calls this tool
+  # with a question. Supports open-ended text, multiple choice,
+  # and default values for confirmation-style prompts.
+  #
+  # IO is sourced from the owning robot's +input+ / +output+ accessors,
+  # falling back to +$stdin+ / +$stdout+.
+  #
+  # @example Open-ended question
+  #   # LLM calls: ask_user(question: "What is your name?")
+  #   # Terminal shows:
+  #   #   [helper] What is your name?
+  #   #   >
+  #
+  # @example Multiple choice
+  #   # LLM calls: ask_user(question: "Pick a language:", choices: ["Ruby", "Python", "Go"])
+  #   # Terminal shows:
+  #   #   [helper] Pick a language:
+  #   #     1. Ruby
+  #   #     2. Python
+  #   #     3. Go
+  #   #   >
+  #
+  # @example With default
+  #   # LLM calls: ask_user(question: "Continue?", default: "yes")
+  #   # Terminal shows:
+  #   #   [helper] Continue?
+  #   #   > [yes]
+  #
+  class AskUser < Tool
+    description "Ask the user a question and wait for their typed response"
+    param :question, type: "string",  desc: "The question to ask the user"
+    param :choices,  type: "array",   desc: "Optional list of choices to present", required: false
+    param :default,  type: "string",  desc: "Default value if user presses Enter",  required: false
+
+    def execute(question:, choices: nil, default: nil)
+      out = output_io
+      label = robot&.name || "Robot"
+
+      out.puts "\n[#{label}] #{question}"
+
+      if choices.is_a?(Array) && choices.any?
+        choices.each_with_index { |c, i| out.puts "  #{i + 1}. #{c}" }
+      end
+
+      prompt = default ? "> [#{default}] " : "> "
+      out.print prompt
+      out.flush
+
+      response = input_io.gets&.chomp || ""
+      response = default if response.empty? && default
+
+      if choices.is_a?(Array) && choices.any? && response.match?(/\A\d+\z/)
+        idx = response.to_i - 1
+        response = choices[idx] if idx >= 0 && idx < choices.size
+      end
+
+      response
+    end
+
+    private
+
+    def input_io
+      robot&.respond_to?(:input) && robot.input ? robot.input : $stdin
+    end
+
+    def output_io
+      robot&.respond_to?(:output) && robot.output ? robot.output : $stdout
+    end
+  end
+end

data/lib/robot_lab/config/defaults.yml

@@ -0,0 +1,121 @@
+# frozen_string_literal: false
+#
+# RobotLab Configuration Defaults
+#
+# This file defines the default configuration values for RobotLab.
+# Values are loaded in the following priority order (lowest to highest):
+#   1. Bundled defaults (this file, 'defaults' section)
+#   2. Environment-specific overrides (development, test, production sections)
+#   3. XDG user config (~/.config/robot_lab/config.yml)
+#   4. Project config (./config/robot_lab.yml)
+#   5. Environment variables (ROBOT_LAB_*)
+#   6. Constructor parameters
+#
+# Environment variables use double underscores for nested values:
+#   ROBOT_LAB_RUBY_LLM__MODEL=gpt-4
+#   ROBOT_LAB_RUBY_LLM__ANTHROPIC_API_KEY=sk-ant-...
+#   ROBOT_LAB_RUBY_LLM__REQUEST_TIMEOUT=180
+
+defaults:
+  # RobotLab Core Settings
+  max_iterations: 10
+  max_tool_iterations: 10
+  streaming_enabled: true
+  template_path: null
+  mcp: :none
+  tools: :none
+
+  # Chat Configuration (passed to RubyLLM.chat)
+  # These are global defaults that can be overridden per-robot or per-run
+  chat:
+    with_model:
+      provider: null # chat-specific provider
+      model: null # chat-specific model
+      assume_exists: null # assume the model exists primarily for local providers
+    with_temperature: 0.7 # Controls randomness (0.0-2.0, null = model default)
+    with_tools: null # ?? not sure about this one.
+    with_params:
+      top_p: null # Nucleus sampling threshold (0.0-1.0)
+      top_k: null # Top-k sampling (integer, provider-specific)
+      max_tokens: null # Maximum tokens in response
+      presence_penalty: null # Penalize new tokens based on presence (-2.0 to 2.0)
+      frequency_penalty: null # Penalize new tokens based on frequency (-2.0 to 2.0)
+      stop: null # Stop sequences (string or array of strings)
+
+  # RubyLLM Configuration Section
+  ruby_llm:
+    provider: :anthropic
+    model: claude-sonnet-4
+    assume_model_exists: false # (dep of assume_exists in chat section) set true for Ollama and other local LLM providers
+    # Provider API Keys (null = use env vars directly)
+    anthropic_api_key: null
+    openai_api_key: null
+    gemini_api_key: null
+    deepseek_api_key: null
+    mistral_api_key: null
+    perplexity_api_key: null
+    openrouter_api_key: null
+    gpustack_api_key: null
+    xai_api_key: null
+
+    # AWS Bedrock
+    bedrock_api_key: null
+    bedrock_secret_key: null
+    bedrock_region: null
+    bedrock_session_token: null
+
+    # Google Vertex AI
+    vertexai_project_id: null
+    vertexai_location: null
+
+    # Provider Endpoints (for self-hosted models)
+    openai_api_base: null
+    gemini_api_base: null
+    ollama_api_base: null
+    gpustack_api_base: null
+    xai_api_base: null
+
+    # OpenAI-Specific Options
+    openai_organization_id: null
+    openai_project_id: null
+    openai_use_system_role: true
+
+    # Default Models
+    default_model: null
+    default_embedding_model: null
+    default_image_model: null
+    default_moderation_model: null
+
+    # Connection Settings
+    request_timeout: 120
+    max_retries: 3
+    retry_interval: 1
+    retry_backoff_factor: 2
+    retry_interval_randomness: 0.5
+    http_proxy: null
+
+    # Logging Options
+    log_file: null
+    log_level: :info
+    log_stream_debug: false
+
+development:
+  ruby_llm:
+    log_level: :debug
+
+test:
+  max_iterations: 3
+  streaming_enabled: false
+  ruby_llm:
+    model: claude-3-haiku-20240307
+    request_timeout: 30
+    max_retries: 1
+    log_level: :warn
+
+production:
+  streaming_enabled: false
+  max_iterations: 20
+  ruby_llm:
+    request_timeout: 180
+    max_retries: 5
+    log_level: :warn

data/lib/robot_lab/config.rb

@@ -0,0 +1,183 @@
+# frozen_string_literal: true
+
+require 'myway_config'
+
+module RobotLab
+  # Modern configuration class using MywayConfig for RobotLab.
+  #
+  # Provides:
+  # - Nested configuration with a dedicated `ruby_llm:` section
+  # - Environment-specific settings (development, test, production)
+  # - XDG config file loading (~/.config/robot_lab/config.yml)
+  # - Environment variable overrides (ROBOT_LAB_*)
+  # - Automatic RubyLLM configuration application
+  #
+  # @example Access configuration values
+  #   RobotLab.config.ruby_llm.model            #=> "claude-sonnet-4"
+  #   RobotLab.config.ruby_llm.request_timeout  #=> 120
+  #   RobotLab.config.development?              #=> true
+  #
+  # @example Override via environment variables
+  #   # ROBOT_LAB_RUBY_LLM__MODEL=gpt-4
+  #   # ROBOT_LAB_RUBY_LLM__ANTHROPIC_API_KEY=sk-ant-...
+  #
+  # @example User config file (~/.config/robot_lab/config.yml)
+  #   defaults:
+  #     ruby_llm:
+  #       anthropic_api_key: <%= ENV['ANTHROPIC_API_KEY'] %>
+  #
+  class Config < MywayConfig::Base
+    config_name :robot_lab
+    env_prefix :robot_lab
+    defaults_path File.expand_path('config/defaults.yml', __dir__)
+    auto_configure!
+
+    # @!attribute [rw] logger
+    #   @return [Logger] the logger instance (runtime-only, not from config file)
+    attr_writer :logger
+
+    # Returns the logger instance.
+    #
+    # @return [Logger] the configured logger or default
+    def logger
+      @logger ||= default_logger
+    end
+
+
+    # Apply RubyLLM configuration after loading.
+    #
+    # This method should be called after initialization to configure
+    # the RubyLLM gem with the values from the ruby_llm section,
+    # and to set up the template library.
+    #
+    # @return [void]
+    def after_load
+      apply_ruby_llm_config!
+      apply_prompt_manager!
+    end
+
+
+    # Apply all RubyLLM settings from the ruby_llm configuration section.
+    #
+    # @return [void]
+    def apply_ruby_llm_config!
+      return unless ruby_llm
+
+      RubyLLM.configure do |c|
+        apply_provider_api_keys(c)
+        apply_provider_endpoints(c)
+        apply_openai_options(c)
+        apply_default_models(c)
+        apply_connection_settings(c)
+        apply_logging_options(c)
+      end
+    end
+
+    private
+
+    def apply_provider_api_keys(c)
+      # Fall back to standard provider env vars when not set in config.
+      # This lets users set ANTHROPIC_API_KEY (etc.) directly without
+      # needing the ROBOT_LAB_RUBY_LLM__ANTHROPIC_API_KEY prefix.
+      set_if_present(c, :anthropic_api_key, :anthropic_api_key, 'ANTHROPIC_API_KEY')
+      set_if_present(c, :openai_api_key, :openai_api_key, 'OPENAI_API_KEY')
+      set_if_present(c, :gemini_api_key, :gemini_api_key, 'GEMINI_API_KEY')
+      set_if_present(c, :deepseek_api_key, :deepseek_api_key, 'DEEPSEEK_API_KEY')
+      set_if_present(c, :mistral_api_key, :mistral_api_key, 'MISTRAL_API_KEY')
+      set_if_present(c, :perplexity_api_key, :perplexity_api_key, 'PERPLEXITY_API_KEY')
+      set_if_present(c, :openrouter_api_key, :openrouter_api_key, 'OPENROUTER_API_KEY')
+      set_if_present(c, :gpustack_api_key, :gpustack_api_key, 'GPUSTACK_API_KEY')
+      set_if_present(c, :xai_api_key, :xai_api_key, 'XAI_API_KEY')
+
+      # AWS Bedrock
+      set_if_present(c, :bedrock_api_key, :bedrock_api_key, 'AWS_ACCESS_KEY_ID')
+      set_if_present(c, :bedrock_secret_key, :bedrock_secret_key, 'AWS_SECRET_ACCESS_KEY')
+      set_if_present(c, :bedrock_region, :bedrock_region, 'AWS_REGION')
+      set_if_present(c, :bedrock_session_token, :bedrock_session_token, 'AWS_SESSION_TOKEN')
+
+      # Google Vertex AI
+      set_if_present(c, :vertexai_project_id, :vertexai_project_id, 'GOOGLE_CLOUD_PROJECT')
+      set_if_present(c, :vertexai_location, :vertexai_location, 'GOOGLE_CLOUD_LOCATION')
+    end
+
+
+    def apply_provider_endpoints(c)
+      c.openai_api_base = ruby_llm.openai_api_base if ruby_llm.openai_api_base
+      c.gemini_api_base = ruby_llm.gemini_api_base if ruby_llm.gemini_api_base
+      c.ollama_api_base = ruby_llm.ollama_api_base if ruby_llm.ollama_api_base
+      c.gpustack_api_base = ruby_llm.gpustack_api_base if ruby_llm.gpustack_api_base
+      c.xai_api_base = ruby_llm.xai_api_base if ruby_llm.xai_api_base
+    end
+
+
+    def apply_openai_options(c)
+      c.openai_organization_id = ruby_llm.openai_organization_id if ruby_llm.openai_organization_id
+      c.openai_project_id = ruby_llm.openai_project_id if ruby_llm.openai_project_id
+      c.openai_use_system_role = ruby_llm.openai_use_system_role unless ruby_llm.openai_use_system_role.nil?
+    end
+
+
+    def apply_default_models(c)
+      c.default_model = ruby_llm.default_model if ruby_llm.default_model
+      c.default_embedding_model = ruby_llm.default_embedding_model if ruby_llm.default_embedding_model
+      c.default_image_model = ruby_llm.default_image_model if ruby_llm.default_image_model
+      c.default_moderation_model = ruby_llm.default_moderation_model if ruby_llm.default_moderation_model
+    end
+
+
+    def apply_connection_settings(c)
+      c.request_timeout = ruby_llm.request_timeout if ruby_llm.request_timeout
+      c.max_retries = ruby_llm.max_retries if ruby_llm.max_retries
+      c.retry_interval = ruby_llm.retry_interval if ruby_llm.retry_interval
+      c.retry_backoff_factor = ruby_llm.retry_backoff_factor if ruby_llm.retry_backoff_factor
+      c.retry_interval_randomness = ruby_llm.retry_interval_randomness if ruby_llm.retry_interval_randomness
+      c.http_proxy = ruby_llm.http_proxy if ruby_llm.http_proxy
+    end
+
+
+    def apply_logging_options(c)
+      c.log_file = ruby_llm.log_file if ruby_llm.log_file
+      c.log_level = ruby_llm.log_level if ruby_llm.log_level
+      c.log_stream_debug = ruby_llm.log_stream_debug unless ruby_llm.log_stream_debug.nil?
+    end
+
+
+    def apply_prompt_manager!
+      path = resolved_template_path
+      return unless path
+
+      PM.configure do |c|
+        c.prompts_dir = path
+      end
+    end
+
+
+    # Set a RubyLLM config attribute from config value or standard env var.
+    # Only sets when a non-nil value is found, to avoid overwriting defaults.
+    def set_if_present(c, setter, config_key, env_var)
+      value = ruby_llm.public_send(config_key) || ENV[env_var]
+      c.public_send(:"#{setter}=", value) if value
+    end
+
+
+    def resolved_template_path
+      return template_path if template_path
+
+      if defined?(Rails) && Rails.root
+        Rails.root.join('app', 'prompts').to_s
+      else
+        'prompts'
+      end
+    end
+
+
+    def default_logger
+      if defined?(Rails) && Rails.respond_to?(:logger)
+        Rails.logger
+      else
+        require 'logger'
+        Logger.new($stdout, level: Logger::INFO)
+      end
+    end
+  end
+end

data/lib/robot_lab/error.rb

@@ -29,4 +29,10 @@ module RobotLab
   # @example
   #   raise MCPError, "Connection to MCP server refused"
   class MCPError < Error; end
+
+  # Raised when message bus communication fails.
+  #
+  # @example
+  #   raise BusError, "No bus configured on this robot"
+  class BusError < Error; end
 end

data/lib/robot_lab/mcp/client.rb

@@ -51,7 +51,7 @@ module RobotLab
 
         self
       rescue StandardError => e
-        RobotLab.configuration.logger.warn("MCP connection failed for #{@server.name}: #{e.message}")
+        RobotLab.config.logger.warn("MCP connection failed for #{@server.name}: #{e.message}")
         @connected = false
         self
       end