Class: LLM::Context

Inherits:
Object
  • Object
show all
Includes:
Deserializer, Serializer
Defined in:
lib/llm/context.rb,
lib/llm/context/serializer.rb,
lib/llm/context/deserializer.rb

Overview

LLM::Context is the low-level stateful execution boundary in llm.rb. Most users should start with Agent, which wraps Context and manages tool loops automatically. Use Context directly when you need manual control over tool execution.

It holds the evolving runtime state for an LLM workflow: conversation history, tool calls and returns, schema and streaming configuration, accumulated usage, and request ownership for interruption.

This is broader than prompt context alone. A context is the object that lets one-off prompts, streaming turns, tool execution, persistence, retries, and serialized long-lived workflows all run through the same model.

A context can drive the chat completions API that all providers support or the Responses API on providers that expose it.

Examples:

#!/usr/bin/env ruby
require "llm"

llm = LLM.deepseek(key: ENV["KEY"])
ctx = LLM::Context.new(llm, stream: $stdout)
ctx.talk "If a train goes 60 mph for 1.5 hours, how far does it travel?"
ctx.messages.each { |m| puts "[#{m.role}] #{m.content}" }

See Also:

Defined Under Namespace

Modules: Deserializer, Serializer

Instance Attribute Summary collapse

Instance Method Summary collapse

Methods included from Deserializer

#deserialize

Constructor Details

#initialize(llm, params = {}) ⇒ Context

Returns a new instance of Context.

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):

  • :mode (Symbol) —

    Defaults to :responses for OpenAI, otherwise it defaults to :completions.

  • :model (String) —

    Defaults to the provider's default model

  • :compactor (Class<LLM::Compactor>, nil) —

    A compactor class to use for context compaction. Defaults to LLM::Compactor::Null.

  • :compactor_options (Hash) —

    Options passed to the compactor's call method. Defaults to {}.

  • :transformer (Class<LLM::Transformer>, nil) —

    A transformer class to use for message transformation. Defaults to Transformer::Null.

  • :transformer_options (Hash) —

    Options passed to the transformer's call method. Defaults to {}.

  • :guard (Class<LLM::Guard>, nil) —

    A guard class to supervise agentic tool execution. Defaults to Guard::Null.

  • :guard_options (Hash) —

    Options passed to the guard's call method. Defaults to {}.

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

    Defaults to nil

  • :skills (Array<String>, nil) —

    Defaults to nil



98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
 
# File 'lib/llm/context.rb', line 98

def initialize(llm, params = {})
  params = {}.merge!(params)
  @llm = llm
  @mode = params.delete(:mode) || (llm.name == :openai ? :responses : :completions)
  tools = [*params.delete(:tools), *load_skills(params.delete(:skills))]
  @params = {model: llm.default_model, schema: nil}.compact.merge!(params)
  @params[:tools] = tools unless tools.empty?
  @params[:store] ||= false if @mode == :responses
  @messages = LLM::Buffer.new(llm)
  extra = @params.slice(:model, :tools).merge!(ctx: self, tracer:)
  @params[:stream] = LLM::Stream.try(@params[:stream], extra:)
  @compactor = {
    klass: params.delete(:compactor) || LLM::Compactor::Null,
    options: params.delete(:compactor_options) || {}
  }
  @transformer = {
    klass: params.delete(:transformer) || LLM::Transformer::Null,
    options: params.delete(:transformer_options) || {}
  }
  @guard = {
    klass: params.delete(:guard) || LLM::Guard::Null,
    options: params.delete(:guard_options) || {}
  }
end

Instance Attribute Details

#compacted ⇒ Boolean Also known as: compacted?

This method is part of a private API. You should avoid using this method if possible, as it may be removed or be changed in the future.

Returns whether the context has been compacted and no later model response has cleared that state.

Returns:

  • (Boolean) 


142
143
144
 
# File 'lib/llm/context.rb', line 142

def compacted
  @compacted
end

#llm ⇒ LLM::Provider (readonly)

Returns a provider

Returns:



63
64
65
 
# File 'lib/llm/context.rb', line 63

def llm
  @llm
end

#messages ⇒ LLM::Buffer<LLM::Message> (readonly)

Returns the accumulated message history for this context

Returns:



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

def messages
  @messages
end

#mode ⇒ Symbol (readonly)

Returns the context mode

Returns:

  • (Symbol) 


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

def mode
  @mode
end

Instance Method Details

#ask(prompt, options = {}) {|String| ... } ⇒ LLM::Response

Ask a question and return the content string directly. Accepts with: for file attachments and a block for streaming. This interface is compatible with RubyLLM's ask method.

Parameters:

  • prompt (String)
  • options (Hash) (defaults to: {})

Options Hash (options):

  • :with (String, Array<String>, nil) —

    File path(s) to attach

  • :stream (#<<, LLM::Stream, nil) —

    A stream target

Yields:

  • (String) —

    content chunks when streaming

Returns:



217
218
219
220
221
222
223
224
225
226
227
228
229
 
# File 'lib/llm/context.rb', line 217

def ask(prompt, options = {}, &block)
  options = {with: nil, stream: nil}.merge!(options || {})
  with, stream = options.values_at(:with, :stream)
  prompt = with ? [prompt, [*with].map { local_file(_1) }] : prompt
  target = if block
    blk = block.dup
    blk.singleton_class.alias_method(:<<, :call)
    blk
  else
    stream
  end
  target ? talk(prompt, stream: target) : talk(prompt)
end

#compactor ⇒ LLM::Compactor

Returns a context compactor

Returns:



133
134
135
 
# File 'lib/llm/context.rb', line 133

def compactor
  @compactor[:klass]
end

#context_window ⇒ Integer

Note:

This method returns 0 when the provider or model can't be found within Registry.

Returns the model's context window. The context window is the maximum amount of input and output tokens a model can consider in a single request.

Returns:

  • (Integer) 


487
488
489
490
491
492
493
494
 
# File 'lib/llm/context.rb', line 487

def context_window
  LLM
    .registry_for(llm)
    .limit(model:)
    .context
rescue LLM::NoSuchModelError, LLM::NoSuchRegistryError
  0
end

#cost ⇒ LLM::Cost

Returns an approximate cost for a given context based on both the provider, and model

Returns:

  • (LLM::Cost) —

    Returns an approximate cost for a given context based on both the provider, and model



475
476
477
 
# File 'lib/llm/context.rb', line 475

def cost
  LLM::Cost.from(self)
end

#guard ⇒ Class<LLM::Guard>

Returns the configured guard class.

Guards are context-level supervisors for agentic execution. A guard can inspect the runtime state and decide whether pending tool work should be blocked before the context keeps looping.

The guard is stamped onto the functions the context binds, so it runs whenever a task is spawned — including tool calls queued from a stream via Stream#on_tool_call. A blocked call yields its in-band guard_error return without executing.

The built-in implementation is LLM::Guard::Loop, which detects repeated tool-call patterns and turns them into in-band guard_error tool returns.

Returns:



162
163
164
 
# File 'lib/llm/context.rb', line 162

def guard
  @guard[:klass]
end

#image_url(url) ⇒ LLM::Object

Recongize an object as a URL to an image

Parameters:

  • url (String) —

    The URL

Returns:



386
387
388
 
# File 'lib/llm/context.rb', line 386

def image_url(url)
  LLM::Object.from(value: url, kind: :image_url)
end

#inspect ⇒ String

Returns:

  • (String) 


233
234
235
236
237
 
# File 'lib/llm/context.rb', line 233

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

#interrupt! ⇒ nil Also known as: cancel!

Interrupt the active request, if any. This is inspired by Go's context cancellation model.

Returns:

  • (nil) 


329
330
331
332
333
334
335
336
 
# File 'lib/llm/context.rb', line 329

def interrupt!
  llm.interrupt!(@owner)
  queue&.interrupt!
  pending_functions.each(&:interrupt!)
  @queue = nil
  @owner = nil
  nil
end

#local_file(path) ⇒ LLM::Object

Recongize an object as a local file

Parameters:

  • path (String) —

    The path

Returns:



396
397
398
 
# File 'lib/llm/context.rb', line 396

def local_file(path)
  LLM::Object.from(value: LLM.File(path), kind: :local_file)
end

#model ⇒ String

Returns the model a Context is actively using

Returns:

  • (String) 


435
436
437
 
# File 'lib/llm/context.rb', line 435

def model
  messages.find(&:assistant?)&.model || @params[:model]
end

#params ⇒ Hash

Returns the default params for this context

Returns:

  • (Hash) 


126
127
128
 
# File 'lib/llm/context.rb', line 126

def params
  @params.dup
end

#pending_functions ⇒ Array<LLM::Function>

Returns an array of functions that can be called

Returns:



242
243
244
245
246
247
248
249
250
251
252
253
254
255
 
# File 'lib/llm/context.rb', line 242

def pending_functions
  return_ids = returns.map(&:id)
  guard = @guard[:klass].new(self)
  @messages
    .select(&:assistant?)
    .flat_map do |msg|
      fns = msg.functions.select { _1.pending? && !return_ids.include?(_1.id) }
      fns.each do |fn|
        fn.tracer = tracer
        fn.model  = msg.model
        fn.guard  = guard
      end
    end.extend(LLM::Function::Array)
end

#pending_functions? ⇒ Boolean

Returns whether there is pending tool work in this context. This prefers queued streamed tool work when present, and otherwise falls back to unresolved functions derived from the message history.

Returns:

  • (Boolean) 


262
263
264
265
 
# File 'lib/llm/context.rb', line 262

def pending_functions?
  pending = queue
  (pending && !pending.empty?) || pending_functions.any?
end

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

Build a role-aware prompt for a single request.

Prefer this method over #build_prompt. The older method name is kept for backward compatibility.

Examples:

prompt = ctx.prompt do
  system "Your task is to assist the user"
  user "Hello, can you assist me?"
end
ctx.talk(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:



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

def prompt(&b)
  LLM::Prompt.new(@llm, &b)
end

#remote_file(res) ⇒ LLM::Object

Reconginize an object as a remote file

Parameters:

Returns:



406
407
408
 
# File 'lib/llm/context.rb', line 406

def remote_file(res)
  LLM::Object.from(value: res, kind: :remote_file)
end

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

Returns tool returns accumulated in this context

Returns:



280
281
282
283
284
285
286
287
288
 
# File 'lib/llm/context.rb', line 280

def returns
  @messages
    .select(&:tool_return?)
    .flat_map do |msg|
      LLM::Function::Return === msg.content ?
        [msg.content] :
        [*msg.content].grep(LLM::Function::Return)
    end
end

#serialize(path:) ⇒ void Also known as: save

This method returns an undefined value.

Save the current context state

Examples:

llm = LLM.openai(key: ENV["KEY"])
ctx = LLM::Context.new(llm)
ctx.talk "Hello"
ctx.save(path: "context.json")

Raises:

  • (SystemCallError) —

    Might raise a number of SystemCallError subclasses



466
467
468
 
# File 'lib/llm/context.rb', line 466

def serialize(path:)
  ::File.binwrite path, LLM.json.dump(to_h)
end

#spawn(function, strategy) ⇒ LLM::Function::Task

Spawns a function through the context.

Parameters:

Returns:



273
274
275
 
# File 'lib/llm/context.rb', line 273

def spawn(function, strategy)
  function.task(strategy)
end

#stream ⇒ LLM::Stream, ...

Returns a stream object, or nil

Returns:

  • (LLM::Stream, #<<, nil) —

    Returns a stream object, or nil



428
429
430
 
# File 'lib/llm/context.rb', line 428

def stream
  @stream || @params[:stream]
end

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

Interact with the context 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"])
ctx = LLM::Context.new(llm)
res = ctx.talk("Hello, what is your name?")
puts res.messages[0].content

Parameters:

  • params (defaults to: {}) —

    The params, including optional :role (defaults to :user), :stream, :tools, :schema etc.

  • prompt (String) —

    The input prompt to be completed

Returns:



188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
 
# File 'lib/llm/context.rb', line 188

def talk(prompt, params = {})
  @owner = @llm.request_owner
  @compactor[:klass].new(self).call(**@compactor[:options])
  repair!(@messages, prompt)
  prompt, params, res = mode == :responses ? respond(prompt, params) : complete(prompt, params)
  self.compacted = false
  if prompt.all?(&:tool_return?)
    @messages.concat prompt.map { LLM::Message.new(@llm.tool_role, _1.content, _1.extra) }
  else
    @messages.concat(prompt)
  end
  @messages.concat([res.choices[-1]].compact)
  res
ensure
  @owner = nil
end

#to_h ⇒ Hash

Returns:

  • (Hash) 


441
442
443
444
445
446
447
448
 
# File 'lib/llm/context.rb', line 441

def to_h
  {
    schema_version: 1,
    model:,
    compacted:,
    messages: @messages.map { serialize_message(_1) }
  }
end

#to_json ⇒ String

Returns:

  • (String) 


452
453
454
 
# File 'lib/llm/context.rb', line 452

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

#tracer ⇒ LLM::Tracer

Returns an LLM tracer

Returns:



413
414
415
 
# File 'lib/llm/context.rb', line 413

def tracer
  @llm.tracer
end

#tracer=(other) ⇒ void

This method returns an undefined value.

Parameters:



421
422
423
 
# File 'lib/llm/context.rb', line 421

def tracer=(other)
  @llm.tracer = other || LLM::Tracer::Null.new(@llm)
end

#transformer ⇒ Class<LLM::Transformer>

Returns the configured transformer class.

Transformers rewrite the most recent message before it is sent to the provider.

Returns:



173
174
175
 
# File 'lib/llm/context.rb', line 173

def transformer
  @transformer[:klass]
end

#usage ⇒ LLM::Object

Returns token usage accumulated in this context

Returns:



342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
 
# File 'lib/llm/context.rb', line 342

def usage
  if usage = @messages.find(&:assistant?)&.usage
    LLM::Object.from(
      input_tokens: usage.input_tokens || 0,
      output_tokens: usage.output_tokens || 0,
      reasoning_tokens: usage.reasoning_tokens || 0,
      input_audio_tokens: usage.input_audio_tokens || 0,
      output_audio_tokens: usage.output_audio_tokens || 0,
      input_image_tokens: usage.input_image_tokens || 0,
      cache_read_tokens: usage.cache_read_tokens || 0,
      cache_write_tokens: usage.cache_write_tokens || 0,
      total_tokens: usage.total_tokens || 0
    )
  else
    ZERO_USAGE
  end
end

#wait(strategy, except: []) ⇒ Array<LLM::Function::Return>

Waits for queued tool work to finish.

This prefers queued streamed tool work when the configured stream exposes a non-empty queue. Otherwise it falls back to waiting on the context's pending functions directly.

Parameters:

  • strategy (Symbol, Array<Symbol>) —

    If the stream queue already has tool work, wait will drain it without using this argument. Otherwise, this controls how pending functions are resolved directly. Use :sequential for sequential execution without spawning.

  • except (Array<LLM::Function>) (defaults to: []) —

    A list of functions to exclude from the wait

Returns:



305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
 
# File 'lib/llm/context.rb', line 305

def wait(strategy, except: [])
  if stream.queue.empty?
    ##
    # Every pending function is spawned as a task that checks its own
    # guard (stamped on the function) before running. Blocked tasks
    # yield their guard's return, so all pending calls still close.
    tools = except.empty? ? pending_functions : pending_functions - except
    @queue = tools.task(strategy)
    returns = @queue.wait
    emit_tool_returns(tools, returns)
    returns
  else
    @queue = stream.queue
    @queue.wait
  end
ensure
  @queue = nil
  @stream = nil
end