Class: LLM::Agent

Inherits:
Object
  • Object
show all
Defined in:
lib/llm/agent.rb

Overview

LLM::Agent provides a class-level DSL for defining reusable, preconfigured assistants with defaults for model, tools, schema, and instructions.

It wraps the same stateful runtime surface as LLM::Context: message history, usage, persistence, streaming parameters, and provider-backed requests still flow through an underlying context. The defining behavior of an agent is that it automatically resolves pending tool calls for you during ‘talk` and `respond`, instead of leaving tool loops to the caller.

Notes:

  • Instructions are injected only on the first request.

  • An agent automatically executes tool loops (unlike LLM::Context).

  • Tool loop execution can be configured with ‘concurrency :call`, `:thread`, `:task`, `:fiber`, or `:ractor`.

Examples:

class SystemAdmin < LLM::Agent
  model "gpt-4.1-nano"
  instructions "You are a Linux system admin"
  tools Shell
  schema Result
end

llm = LLM.openai(key: ENV["KEY"])
agent = SystemAdmin.new(llm)
agent.talk("Run 'date'")

Instance Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(llm, params = {}) ⇒ Agent

Returns a new instance of Agent.

Parameters:

  • provider (LLM::Provider) —

    A provider

  • params (Hash) (defaults to: {}) —

    The parameters to maintain throughout the conversation. Any parameter the provider supports can be included and not only those listed here.

Options Hash (params):

  • :model (String) —

    Defaults to the provider’s default model

  • :tools (Array<LLM::Function>, nil) —

    Defaults to nil

  • :schema (#to_json, nil) —

    Defaults to nil

  • :concurrency (Symbol, nil) —

    Defaults to the agent class concurrency



111
112
113
114
115
116
 
# File 'lib/llm/agent.rb', line 111

def initialize(llm, params = {})
  defaults = {model: self.class.model, tools: self.class.tools, schema: self.class.schema}.compact
  @concurrency = params.delete(:concurrency) || self.class.concurrency
  @llm = llm
  @ctx = LLM::Context.new(llm, defaults.merge(params))
end

Instance Attribute Details

#llm ⇒ LLM::Provider (readonly)

Returns a provider

Returns:



37
38
39
 
# File 'lib/llm/agent.rb', line 37

def llm
  @llm
end

Class Method Details

.concurrency(concurrency = nil) ⇒ Symbol?

Set or get the tool execution concurrency.

Parameters:

  • concurrency (Symbol, nil) (defaults to: nil) —

    Controls how pending tool loops are executed:

    • ‘:call`: sequential calls

    • ‘:thread`: concurrent threads

    • ‘:task`: concurrent async tasks

    • ‘:fiber`: concurrent raw fibers

    • ‘:ractor`: concurrent Ruby ractors for class-based tools; MCP tools are not supported, and this mode is especially useful for CPU-bound tool work

Returns:

  • (Symbol, nil) 


95
96
97
98
 
# File 'lib/llm/agent.rb', line 95

def self.concurrency(concurrency = nil)
  return @concurrency if concurrency.nil?
  @concurrency = concurrency
end

.instructions(instructions = nil) ⇒ String?

Set or get the default instructions

Parameters:

  • instructions (String, nil) (defaults to: nil) —

    The system instructions

Returns:

  • (String, nil) —

    Returns the current instructions when no argument is provided



78
79
80
81
 
# File 'lib/llm/agent.rb', line 78

def self.instructions(instructions = nil)
  return @instructions if instructions.nil?
  @instructions = instructions
end

.model(model = nil) ⇒ String?

Set or get the default model

Parameters:

  • model (String, nil) (defaults to: nil) —

    The model identifier

Returns:

  • (String, nil) —

    Returns the current model when no argument is provided



45
46
47
48
 
# File 'lib/llm/agent.rb', line 45

def self.model(model = nil)
  return @model if model.nil?
  @model = model
end

.schema(schema = nil) ⇒ #to_json?

Set or get the default schema

Parameters:

  • schema (#to_json, nil) (defaults to: nil) —

    The schema

Returns:

  • (#to_json, nil) —

    Returns the current schema when no argument is provided



67
68
69
70
 
# File 'lib/llm/agent.rb', line 67

def self.schema(schema = nil)
  return @schema if schema.nil?
  @schema = schema
end

.tools(*tools) ⇒ Array<LLM::Function>

Set or get the default tools

Parameters:

Returns:

  • (Array<LLM::Function>) —

    Returns the current tools when no argument is provided



56
57
58
59
 
# File 'lib/llm/agent.rb', line 56

def self.tools(*tools)
  return @tools || [] if tools.empty?
  @tools = tools.flatten
end

Instance Method Details

#call ⇒ Object

Returns:

See Also:



190
191
192
 
# File 'lib/llm/agent.rb', line 190

def call(...)
  @ctx.call(...)
end

#concurrency ⇒ Symbol?

Returns the configured tool execution concurrency.

Returns:

  • (Symbol, nil) 


274
275
276
 
# File 'lib/llm/agent.rb', line 274

def concurrency
  @concurrency
end

#context_window ⇒ Integer

Returns:

  • (Integer)

See Also:



288
289
290
 
# File 'lib/llm/agent.rb', line 288

def context_window
  @ctx.context_window
end

#cost ⇒ LLM::Cost

Returns:

See Also:



281
282
283
 
# File 'lib/llm/agent.rb', line 281

def cost
  @ctx.cost
end

#deserialize(**kw) ⇒ Object Also known as: restore 



323
324
325
 
# File 'lib/llm/agent.rb', line 323

def deserialize(**kw)
  @ctx.deserialize(**kw)
end

#functions ⇒ Array<LLM::Function>

Returns:



176
177
178
 
# File 'lib/llm/agent.rb', line 176

def functions
  @ctx.functions
end

#image_url(url) ⇒ LLM::Object

Returns a tagged object

Parameters:

  • url (String) —

    The URL

Returns:



229
230
231
 
# File 'lib/llm/agent.rb', line 229

def image_url(url)
  @ctx.image_url(url)
end

#inspect ⇒ String

Returns:

  • (String) 


307
308
309
310
 
# File 'lib/llm/agent.rb', line 307

def inspect
  "#<#{self.class.name}:0x#{object_id.to_s(16)} " \
  "@llm=#{@llm.class}, @mode=#{mode.inspect}, @messages=#{messages.inspect}>"
end

#interrupt! ⇒ nil Also known as: cancel!

Interrupt the active request, if any.

Returns:

  • (nil) 


210
211
212
 
# File 'lib/llm/agent.rb', line 210

def interrupt!
  @ctx.interrupt!
end

#local_file(path) ⇒ LLM::Object

Returns a tagged object

Parameters:

  • path (String) —

    The path

Returns:



238
239
240
 
# File 'lib/llm/agent.rb', line 238

def local_file(path)
  @ctx.local_file(path)
end

#messages ⇒ LLM::Buffer<LLM::Message>

Returns:



170
171
172
 
# File 'lib/llm/agent.rb', line 170

def messages
  @ctx.messages
end

#mode ⇒ Symbol

Returns:

  • (Symbol) 


267
268
269
 
# File 'lib/llm/agent.rb', line 267

def mode
  @ctx.mode
end

#model ⇒ String

Returns the model an Agent is actively using

Returns:

  • (String) 


261
262
263
 
# File 'lib/llm/agent.rb', line 261

def model
  @ctx.model
end

#prompt(&b) ⇒ LLM::Prompt Also known as: build_prompt

Parameters:

  • b (Proc) —

    A block that composes messages. If it takes one argument, it receives the prompt object. Otherwise it runs in prompt context.

Returns:

See Also:



219
220
221
 
# File 'lib/llm/agent.rb', line 219

def prompt(&b)
  @ctx.prompt(&b)
end

#remote_file(res) ⇒ LLM::Object

Returns a tagged object

Parameters:

Returns:



247
248
249
 
# File 'lib/llm/agent.rb', line 247

def remote_file(res)
  @ctx.remote_file(res)
end

#respond(prompt, params = {}) ⇒ LLM::Response

Note:

Not all LLM providers support this API

Maintain a conversation via the responses API. This method immediately sends a request to the LLM and returns the response.

Examples:

llm = LLM.openai(key: ENV["KEY"])
agent = LLM::Agent.new(llm)
res = agent.respond("What is the capital of France?")
puts res.output_text

Parameters:

  • params (Hash) (defaults to: {}) —

    The params passed to the provider, including optional :stream, :tools, :schema etc.

  • prompt (String) —

    The input prompt to be completed

Options Hash (params):

  • :tool_attempts (Integer) —

    The maxinum number of tool call iterations (default 10)

Returns:

  • (LLM::Response) —

    Returns the LLM’s response for this turn.

Raises:



157
158
159
160
161
162
163
164
165
166
 
# File 'lib/llm/agent.rb', line 157

def respond(prompt, params = {})
  max = Integer(params.delete(:tool_attempts) || 10)
  res = @ctx.respond(apply_instructions(prompt), params)
  max.times do
    break if @ctx.functions.empty?
    res = @ctx.respond(call_functions, params)
  end
  raise LLM::ToolLoopError, "pending tool calls remain" unless @ctx.functions.empty?
  res
end

#returns ⇒ Array<LLM::Function::Return>

Returns:

See Also:



183
184
185
 
# File 'lib/llm/agent.rb', line 183

def returns
  @ctx.returns
end

#serialize(**kw) ⇒ void Also known as: save

This method returns an undefined value.



315
316
317
 
# File 'lib/llm/agent.rb', line 315

def serialize(**kw)
  @ctx.serialize(**kw)
end

#talk(prompt, params = {}) ⇒ LLM::Response Also known as: chat

Maintain a conversation via the chat completions API. This method immediately sends a request to the LLM and returns the response.

Examples:

llm = LLM.openai(key: ENV["KEY"])
agent = LLM::Agent.new(llm)
response = agent.talk("Hello, what is your name?")
puts response.choices[0].content

Parameters:

  • params (Hash) (defaults to: {}) —

    The params passed to the provider, including optional :stream, :tools, :schema etc.

  • prompt (String) —

    The input prompt to be completed

Options Hash (params):

  • :tool_attempts (Integer) —

    The maxinum number of tool call iterations (default 10)

Returns:

  • (LLM::Response) —

    Returns the LLM’s response for this turn.

Raises:



131
132
133
134
135
136
137
138
139
140
 
# File 'lib/llm/agent.rb', line 131

def talk(prompt, params = {})
  max = Integer(params.delete(:tool_attempts) || 10)
  res = @ctx.talk(apply_instructions(prompt), params)
  max.times do
    break if @ctx.functions.empty?
    res = @ctx.talk(call_functions, params)
  end
  raise LLM::ToolLoopError, "pending tool calls remain" unless @ctx.functions.empty?
  res
end

#to_h ⇒ Hash

Returns:

  • (Hash)

See Also:



295
296
297
 
# File 'lib/llm/agent.rb', line 295

def to_h
  @ctx.to_h
end

#to_json ⇒ String

Returns:

  • (String) 


301
302
303
 
# File 'lib/llm/agent.rb', line 301

def to_json(...)
  to_h.to_json(...)
end

#tracer ⇒ LLM::Tracer

Returns an LLM tracer

Returns:



254
255
256
 
# File 'lib/llm/agent.rb', line 254

def tracer
  @ctx.tracer
end

#usage ⇒ LLM::Object

Returns:



203
204
205
 
# File 'lib/llm/agent.rb', line 203

def usage
  @ctx.usage
end

#wait ⇒ Array<LLM::Function::Return>

Returns:

See Also:



197
198
199
 
# File 'lib/llm/agent.rb', line 197

def wait(...)
  @ctx.wait(...)
end