Class: LLM::Agent

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

Overview

LLM::Agent is the recommended entry point for most use-cases. It 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 once unless a system message is already present.
  • An agent automatically executes tool loops (unlike LLM::Context).
  • The automatic tool loop enables the wrapped context's guard by default. The built-in LLM::LoopGuard detects repeated tool-call patterns and blocks stuck execution before more tool work is queued.
  • The default tool attempt budget is 25. After that, the agent sends advisory tool errors back through the model and keeps the loop in-band. Set tool_attempts: nil to disable that advisory behavior.
  • Tool loop execution can be configured with concurrency :sequential, :thread, :async, :fiber, or :ractor.

Examples:

Subclass with defaults

class SystemAdmin < LLM::Agent
  set 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'")

Direct instance

llm = LLM.deepseek(key: ENV["KEY"])
agent = LLM::Agent.new(llm, stream: $stdout)
agent.talk "Hello world"

See Also:

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:

  • llm (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

  • :skills (Array<String>, nil) —

    Defaults to nil

  • :schema (#to_json, nil) —

    Defaults to nil

  • :stream (Object, Proc, nil) —

    Optional stream override for this agent instance

  • :tracer (LLM::Tracer, Proc, nil) —

    Optional tracer override for this agent instance

  • :concurrency (Symbol, Array<Symbol>, nil) —

    Defaults to the agent class concurrency



278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
 
# File 'lib/llm/agent.rb', line 278

def initialize(llm, params = {})
  @llm = llm
  fields = %i[name model skills schema tracer stream tools concurrency instructions confirm]
  fields_ivar = %i[name tracer concurrency instructions confirm]
  fields.each do |field|
    resolvable = params.key?(field) ? params.delete(field) : self.class.public_send(field)
    resolve_symbol = !%i[concurrency].include?(field)
    resolved = resolvable != nil ? resolve_option(self, resolvable, resolve_symbol:) : resolvable
    resolved = [*resolved].map(&:to_s) if field == :confirm && resolved
    if field == :model
      params[field] = resolved unless resolved.nil? || params.key?(field)
    elsif resolved && !fields_ivar.include?(field)
      params[field] ||= resolved
    elsif fields_ivar.include?(field)
      instance_variable_set(:"@#{field}", resolved)
    end
  end
  @ctx = LLM::Context.new(llm, {guard: true}.merge(params))
end

Instance Attribute Details

#llm ⇒ LLM::Provider (readonly)

Returns a provider

Returns:



58
59
60
 
# File 'lib/llm/agent.rb', line 58

def llm
  @llm
end

Class Method Details

.concurrency(concurrency = nil) ⇒ Symbol, ...

Set or get the tool execution concurrency.

Parameters:

  • concurrency (Symbol, Array<Symbol>, nil) (defaults to: nil) —

    Controls how pending tool loops are executed:

    • :sequential: sequential calls
    • :thread: concurrent threads
    • :async: concurrent async tasks
    • :fiber: concurrent scheduler-backed fibers
    • :fork: forked child processes
    • :ractor: concurrent Ruby ractors for class-based tools; MCP tools are not supported, and this mode is especially useful for CPU-bound tool work Usually pass a single strategy. Arrays are only for advanced mixed-work cases and are not needed for normal queued stream tool loops.

Returns:

  • (Symbol, Array<Symbol>, nil) 


189
190
191
192
 
# File 'lib/llm/agent.rb', line 189

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

.confirm(*tool_names, &block) ⇒ Array<String>, ...

Set or get the tool names that require confirmation before they can run.

When a single Symbol is given, it is stored as-is and resolved at initialization time by calling the method with that name on the agent instance. This allows dynamic tool confirmation lists.

Examples:

class MyAgent < LLM::Agent
  confirm :tools_that_need_confirmation

  def tools_that_need_confirmation
    some_condition ? %w[delete destroy] : %w[delete]
  end
end

Parameters:

  • tool_names (String, Symbol, Array<String, Symbol>, Proc) —

    One or more tool names.

  • block (Proc) —

    An optional, lazy-evaluated Proc

Returns:

  • (Array<String>, Proc, Symbol, nil) 


255
256
257
258
259
260
261
262
 
# File 'lib/llm/agent.rb', line 255

def self.confirm(*tool_names, &block)
  return @confirm if tool_names.empty? && !block
  if tool_names.size == 1 && tool_names.grep(Symbol).any?
    @confirm = tool_names.first
  else
    @confirm = block || tool_names.flatten.map(&:to_s)
  end
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



169
170
171
172
 
# File 'lib/llm/agent.rb', line 169

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

.model(model = nil, &block) ⇒ 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



117
118
119
120
 
# File 'lib/llm/agent.rb', line 117

def self.model(model = nil, &block)
  return @model if model.nil? && !block
  @model = block || model
end

.name(name = UNDEFINED, &block) ⇒ String

Set or get an agent's name

Parameters:

  • name (String) (defaults to: UNDEFINED) —

    The agent name

Returns:

  • (String) —

    Return's the agents name



103
104
105
106
107
108
109
 
# File 'lib/llm/agent.rb', line 103

def self.name(name = UNDEFINED, &block)
  if name.equal?(UNDEFINED)
    @name || self.to_s.gsub(/(.)([A-Z])/, '\\1-\\2').downcase
  else
    @name = block || name
  end
end

.schema(schema = nil, &block) ⇒ #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



158
159
160
161
 
# File 'lib/llm/agent.rb', line 158

def self.schema(schema = nil, &block)
  return @schema if schema.nil? && !block
  @schema = block || schema
end

.set(properties) ⇒ void

This method returns an undefined value.

Bulk-assign class-level agent defaults from a Hash.

Each key is resolved by calling the corresponding class method on the agent subclass. An error is raised for unknown keys so that typos are caught early.

Examples:

class AdminAgent < LLM::Agent
  set name: "admin",
      instructions: "You are a system administrator",
      model: "gpt-4.1-nano",
      tools: [Shell, ReadFile]
end

Parameters:

  • properties (Hash)

Options Hash (properties):

  • :instructions (String)
  • :model (String)
  • :tools (Array<LLM::Function>)
  • :skills (Array<String>)
  • :schema (#to_json)
  • :concurrency (Symbol, Array<Symbol>)
  • :tracer (LLM::Tracer, Proc)
  • :stream (Object, Proc)
  • :confirm (String, Symbol, Array<String, Symbol>, Proc)

Raises:

  • (KeyError) —

    when a property key does not match a class-level accessor



87
88
89
90
91
92
93
94
95
 
# File 'lib/llm/agent.rb', line 87

def self.set(properties)
  properties.each do
    if respond_to?(_1)
      public_send(_1, _2)
    else
      raise KeyError, "key not found: #{_1}"
    end
  end
end

.skills(*skills, &block) ⇒ Array<String>?

Set or get the default skills

Parameters:

  • skills (Array<String>, nil) —

    One or more skill directories

Returns:

  • (Array<String>, nil) —

    Returns the current skills when no argument is provided



143
144
145
146
147
148
149
150
 
# File 'lib/llm/agent.rb', line 143

def self.skills(*skills, &block)
  return @skills if skills.empty? && !block
  if skills.size == 1 and skills.grep(Symbol).any?
    @skills = skills.first
  else
    @skills = block || skills.flatten
  end
end

.stream(stream = nil, &block) ⇒ Object, ...

Set or get the default stream.

When a block is provided, it is stored and evaluated lazily against the agent instance during initialization so it can build a fresh stream for each agent.

Examples:

class Agent < LLM::Agent
  stream { MyStream.new }
end

Parameters:

  • stream (Object, Proc, nil) (defaults to: nil)

Yield Returns:

Returns:



229
230
231
232
 
# File 'lib/llm/agent.rb', line 229

def self.stream(stream = nil, &block)
  return @stream if stream.nil? && !block
  @stream = block || stream
end

.tools(*tools, &block) ⇒ Array<LLM::Function>

Set or get the default tools

Parameters:

Returns:

  • (Array<LLM::Function>) —

    Returns the current tools when no argument is provided



128
129
130
131
132
133
134
135
 
# File 'lib/llm/agent.rb', line 128

def self.tools(*tools, &block)
  return @tools || [] if tools.empty? && !block
  if tools.size == 1 and tools.grep(Symbol).any?
    @tools = tools.first
  else
    @tools = block || tools.flatten
  end
end

.tracer(tracer = nil, &block) ⇒ LLM::Tracer, ...

Set or get the default tracer.

When a block is provided, it is stored and evaluated lazily against the agent instance during initialization so it can build a tracer from the resolved provider.

Examples:

class Agent < LLM::Agent
  tracer { LLM::Tracer::Logger.new(llm, io: $stdout) }
end

Parameters:

Yield Returns:

Returns:



209
210
211
212
 
# File 'lib/llm/agent.rb', line 209

def self.tracer(tracer = nil, &block)
  return @tracer if tracer.nil? && !block
  @tracer = block || tracer
end

Instance Method Details

#ask(prompt, params = {}) ⇒ Object

See Also:



327
328
329
 
# File 'lib/llm/agent.rb', line 327

def ask(prompt, params = {})
  run_loop(prompt, params, :ask)
end

#concurrency ⇒ Symbol, ...

Returns the configured tool execution concurrency.

Returns:

  • (Symbol, Array<Symbol>, nil) 


446
447
448
 
# File 'lib/llm/agent.rb', line 446

def concurrency
  @concurrency
end

#context_window ⇒ Integer

Returns:

  • (Integer)

See Also:



460
461
462
 
# File 'lib/llm/agent.rb', line 460

def context_window
  @ctx.context_window
end

#cost ⇒ LLM::Cost

Returns:

See Also:



453
454
455
 
# File 'lib/llm/agent.rb', line 453

def cost
  @ctx.cost
end

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

Returns:



543
544
545
546
 
# File 'lib/llm/agent.rb', line 543

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

#image_url(url) ⇒ LLM::Object

Returns a tagged object

Parameters:

  • url (String) —

    The URL

Returns:



385
386
387
 
# File 'lib/llm/agent.rb', line 385

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

#inspect ⇒ String

Returns:

  • (String) 


527
528
529
530
 
# File 'lib/llm/agent.rb', line 527

def inspect
  "#<#{LLM::Utils.object_id(self)} " \
  "@llm=#{@llm.class}, @mode=#{mode.inspect}, @messages=#{messages.inspect}>"
end

#interrupt! ⇒ nil Also known as: cancel!

Interrupt the active request, if any.

Returns:

  • (nil) 


366
367
368
 
# File 'lib/llm/agent.rb', line 366

def interrupt!
  @ctx.interrupt!
end

#local_file(path) ⇒ LLM::Object

Returns a tagged object

Parameters:

  • path (String) —

    The path

Returns:



394
395
396
 
# File 'lib/llm/agent.rb', line 394

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

#messages ⇒ LLM::Buffer<LLM::Message>

Returns:



333
334
335
 
# File 'lib/llm/agent.rb', line 333

def messages
  @ctx.messages
end

#mode ⇒ Symbol

Returns:

  • (Symbol) 


439
440
441
 
# File 'lib/llm/agent.rb', line 439

def mode
  @ctx.mode
end

#model ⇒ String

Returns the model an Agent is actively using

Returns:

  • (String) 


433
434
435
 
# File 'lib/llm/agent.rb', line 433

def model
  @ctx.model
end

#name ⇒ String

Returns the agent's name

Returns:

  • (String) 


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

def name
  @name
end

#on_tool_confirmation(fn, strategy) ⇒ LLM::Function::Return

This method is called when confirmation is required before a tool can run.

Parameters:

  • fn (LLM::Function) —

    The pending function call. It can be cancelled through the Function#cancel method.

  • strategy (Symbol, Array<Symbol>) —

    The execution strategy that would be used for the tool call.

Returns:

  • (LLM::Function::Return) —

    Return either fn.task(strategy).wait to approve execution or fn.cancel(...) to cancel the call.



560
561
562
 
# File 'lib/llm/agent.rb', line 560

def on_tool_confirmation(fn, strategy)
  fn.cancel
end

#params ⇒ Hash

Returns:

  • (Hash)

See Also:



508
509
510
 
# File 'lib/llm/agent.rb', line 508

def params
  @ctx.params
end

#pending_functions ⇒ Array<LLM::Function>

Returns:



339
340
341
 
# File 'lib/llm/agent.rb', line 339

def pending_functions
  @tracer ? @llm.with_tracer(@tracer) { @ctx.pending_functions } : @ctx.pending_functions
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:



375
376
377
 
# File 'lib/llm/agent.rb', line 375

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

#remote_file(res) ⇒ LLM::Object

Returns a tagged object

Parameters:

Returns:



403
404
405
 
# File 'lib/llm/agent.rb', line 403

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

#repl(name: self.name, path: nil, tools: [], skills: [], tracer: false, trace: nil) ⇒ void

Note:

By default this method disables the tracer for the duration of the repl session, and restores it afterwards.

This method returns an undefined value.

Start a minimalist repl that can interact with the agent and its current state. This method requires the 'curses' gem to be installed and available to require.

Parameters:

  • name (String) (defaults to: self.name) —

    The agent's name. Defaults to #name.

  • path (String) (defaults to: nil) —

    The path to a file where runtime state is read from, and written to

  • tools (Array<LLM::Tool>) (defaults to: []) —

    Extra tools to attach for the repl session

  • skills (Array<String>) (defaults to: []) —

    Extra skills to attach for the repl session

  • tracer (Boolean) (defaults to: false) —

    When true, the tracer is kept alive during the repl session. Default is false.



488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
 
# File 'lib/llm/agent.rb', line 488

def repl(name: self.name, path: nil, tools: [], skills: [], tracer: false, trace: nil)
  if trace != nil
    warn "llm.rb: trace option is deprecated, use tracer instead"
    tracer = trace
  end
  if !tracer
    previous    = self.tracer
    self.tracer = nil
  end
  require_relative "repl" unless defined?(::LLM::Repl)
  LLM::Repl.new(agent: self, name:, path:, tools:, skills:).start
ensure
  if !tracer
    self.tracer = previous
  end
end

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

Returns:

See Also:



346
347
348
 
# File 'lib/llm/agent.rb', line 346

def returns
  @ctx.returns
end

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

This method returns an undefined value.



535
536
537
 
# File 'lib/llm/agent.rb', line 535

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

#stream ⇒ LLM::Stream, ...

Returns a stream object, or nil

Returns:

  • (LLM::Stream, #<<, nil) —

    Returns a stream object, or nil



426
427
428
 
# File 'lib/llm/agent.rb', line 426

def stream
  @ctx.stream
end

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

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 before the agent sends in-band advisory tool errors back through the model (default 25). Set to nil to disable advisory tool-limit returns.

Returns:



321
322
323
 
# File 'lib/llm/agent.rb', line 321

def talk(prompt, params = {})
  run_loop(prompt, params, :talk)
end

#to_h ⇒ Hash

Returns:

  • (Hash)

See Also:



515
516
517
 
# File 'lib/llm/agent.rb', line 515

def to_h
  @ctx.to_h
end

#to_json ⇒ String

Returns:

  • (String) 


521
522
523
 
# File 'lib/llm/agent.rb', line 521

def to_json(...)
  LLM.json.dump(to_h, ...)
end

#tracer ⇒ LLM::Tracer

Returns an LLM tracer

Returns:



410
411
412
 
# File 'lib/llm/agent.rb', line 410

def tracer
  @tracer || @ctx.tracer
end

#tracer=(other) ⇒ void

This method returns an undefined value.

Parameters:



418
419
420
421
 
# File 'lib/llm/agent.rb', line 418

def tracer=(other)
  @ctx.tracer = other
  @tracer = other
end

#usage ⇒ LLM::Object

Returns:



359
360
361
 
# File 'lib/llm/agent.rb', line 359

def usage
  @ctx.usage
end

#wait ⇒ Array<LLM::Function::Return>

Returns:

See Also:



353
354
355
 
# File 'lib/llm/agent.rb', line 353

def wait(...)
  @tracer ? @llm.with_tracer(@tracer) { @ctx.wait(...) } : @ctx.wait(...)
end