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 stateful execution boundary in llm.rb.

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.openai(key: ENV["KEY"])
ctx = LLM::Context.new(llm)

prompt = LLM::Prompt.new(llm) do
  system "Be concise and show your reasoning briefly."
  user "If a train goes 60 mph for 1.5 hours, how far does it travel?"
  user "Now double the speed for the same time."
end

ctx.talk(prompt)
ctx.messages.each { |m| puts "[#{m.role}] #{m.content}" }

Defined Under Namespace

Modules: Deserializer, Serializer

Instance Attribute Summary collapse

Instance Method Summary collapse

Methods included from Deserializer

#deserialize, #deserialize_message

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 :completions

  • :model (String) —

    Defaults to the provider’s default model

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

    Defaults to nil

  • :skills (Array<String>, nil) —

    Defaults to nil



82
83
84
85
86
87
88
89
90
91
92
 
# File 'lib/llm/context.rb', line 82

def initialize(llm, params = {})
  @llm = llm
  @mode = params.delete(:mode) || :completions
  @compactor = params.delete(:compactor)
  @guard = params.delete(:guard)
  @transformer = params.delete(:transformer)
  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?
  @messages = LLM::Buffer.new(llm)
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) 


124
125
126
 
# File 'lib/llm/context.rb', line 124

def compacted
  @compacted
end

#llm ⇒ LLM::Provider (readonly)

Returns a provider

Returns:



64
65
66
 
# File 'lib/llm/context.rb', line 64

def llm
  @llm
end

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

Returns the accumulated message history for this context

Returns:



59
60
61
 
# File 'lib/llm/context.rb', line 59

def messages
  @messages
end

#mode ⇒ Symbol (readonly)

Returns the context mode

Returns:

  • (Symbol) 


69
70
71
 
# File 'lib/llm/context.rb', line 69

def mode
  @mode
end

Instance Method Details

#compactor ⇒ LLM::Compactor

Returns a context compactor This feature is inspired by the compaction approach developed by General Intelligence Systems.

Returns:



106
107
108
109
 
# File 'lib/llm/context.rb', line 106

def compactor
  @compactor = LLM::Compactor.new(self, @compactor || {}) unless LLM::Compactor === @compactor
  @compactor
end

#compactor=(compactor) ⇒ LLM::Compactor, ...

Sets a context compactor or compactor config

Parameters:

Returns:



115
116
117
 
# File 'lib/llm/context.rb', line 115

def compactor=(compactor)
  @compactor = compactor
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) 


451
452
453
454
455
456
457
458
 
# File 'lib/llm/context.rb', line 451

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



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

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

#functions ⇒ Array<LLM::Function>

Returns an array of functions that can be called

Returns:



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

def functions
  return_ids = returns.map(&:id)
  @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
      end
    end.extend(LLM::Function::Array)
end

#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) 


235
236
237
238
 
# File 'lib/llm/context.rb', line 235

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

#guard ⇒ #call?

Returns a guard, if configured.

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 built-in implementation is LLM::LoopGuard, which detects repeated tool-call patterns and turns them into in-band LLM::GuardError tool returns.

Returns:

  • (#call, nil) 


139
140
141
142
143
144
 
# File 'lib/llm/context.rb', line 139

def guard
  return if @guard.nil? || @guard == false
  @guard = LLM::LoopGuard.new if @guard == true
  @guard = LLM::LoopGuard.new(@guard) if Hash === @guard
  @guard
end

#guard=(guard) ⇒ #call, ...

Sets a guard or guard config.

Guards must implement ‘call(ctx)` and return either `nil` or a warning string. Returning a warning tells the context to block pending tool work with guarded tool errors instead of continuing the loop.

Parameters:

  • guard (#call, Hash, Boolean, nil)

Returns:

  • (#call, Hash, Boolean, nil) 


155
156
157
 
# File 'lib/llm/context.rb', line 155

def guard=(guard)
  @guard = guard
end

#image_url(url) ⇒ LLM::Object

Recongize an object as a URL to an image

Parameters:

  • url (String) —

    The URL

Returns:



358
359
360
 
# File 'lib/llm/context.rb', line 358

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

#inspect ⇒ String

Returns:

  • (String) 


208
209
210
211
212
 
# File 'lib/llm/context.rb', line 208

def inspect
  "#<#{self.class.name}:0x#{object_id.to_s(16)} " \
  "@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) 


299
300
301
302
303
304
305
306
307
308
 
# File 'lib/llm/context.rb', line 299

def interrupt!
  pending = functions.to_a
  llm.interrupt!(@owner)
  queue&.interrupt!
  return if pending.empty?
  pending.each(&:interrupt!)
  returns = pending.map { _1.cancel(reason: "function call cancelled") }
  @messages << LLM::Message.new(@llm.tool_role, returns)
  nil
end

#local_file(path) ⇒ LLM::Object

Recongize an object as a local file

Parameters:

  • path (String) —

    The path

Returns:



368
369
370
 
# File 'lib/llm/context.rb', line 368

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) 


399
400
401
 
# File 'lib/llm/context.rb', line 399

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

#params ⇒ Hash

Returns the default params for this context

Returns:

  • (Hash) 


97
98
99
 
# File 'lib/llm/context.rb', line 97

def params
  @params.dup
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:



347
348
349
 
# File 'lib/llm/context.rb', line 347

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

#remote_file(res) ⇒ LLM::Object

Reconginize an object as a remote file

Parameters:

Returns:



378
379
380
 
# File 'lib/llm/context.rb', line 378

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:



258
259
260
261
262
263
264
265
266
 
# File 'lib/llm/context.rb', line 258

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



430
431
432
 
# File 'lib/llm/context.rb', line 430

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

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

Spawns a function through the context.

When a guard is configured, this method can return an in-band guarded tool error instead of spawning work.

Parameters:

Returns:



249
250
251
252
253
 
# File 'lib/llm/context.rb', line 249

def spawn(function, strategy)
  warning = guard&.call(self)
  return guarded_return_for(function, warning) if warning
  function.spawn(strategy)
end

#stream ⇒ LLM::Stream, ...

Returns a stream object, or nil

Returns:

  • (LLM::Stream, #<<, nil) —

    Returns a stream object, or nil



392
393
394
 
# File 'lib/llm/context.rb', line 392

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

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

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:

  • (LLM::Response) —

    Returns the LLM’s response for this turn.



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

def talk(prompt, params = {})
  @owner = @llm.request_owner
  compactor.compact!(prompt) if compactor.compact?(prompt)
  prompt, params, res = mode == :responses ? respond(prompt, params) : complete(prompt, params)
  self.compacted = false
  role = params[:role] || @llm.user_role
  role = @llm.tool_role if params[:role].nil? && [*prompt].grep(LLM::Function::Return).any?
  @messages.concat LLM::Prompt === prompt ? prompt.to_a : [LLM::Message.new(role, prompt)]
  @messages.concat [res.choices[-1]]
  res
end

#to_h ⇒ Hash

Returns:

  • (Hash) 


405
406
407
408
409
410
411
412
 
# File 'lib/llm/context.rb', line 405

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

#to_json ⇒ String

Returns:

  • (String) 


416
417
418
 
# File 'lib/llm/context.rb', line 416

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

#tracer ⇒ LLM::Tracer

Returns an LLM tracer

Returns:



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

def tracer
  @llm.tracer
end

#transformer ⇒ #call?

Returns a transformer, if configured.

Transformers can rewrite outgoing prompts and params before a request is sent to the provider.

Returns:

  • (#call, nil) 


166
167
168
 
# File 'lib/llm/context.rb', line 166

def transformer
  @transformer
end

#transformer=(transformer) ⇒ #call?

Sets a transformer.

Transformers must implement ‘call(ctx, prompt, params)` and return a two-element array of `[prompt, params]`.

Parameters:

  • transformer (#call, nil)

Returns:

  • (#call, nil) 


178
179
180
 
# File 'lib/llm/context.rb', line 178

def transformer=(transformer)
  @transformer = transformer
end

#usage ⇒ LLM::Object

Returns token usage accumulated in this context

Returns:



314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
 
# File 'lib/llm/context.rb', line 314

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) ⇒ 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 `:call` for sequential execution without spawning.

Returns:



281
282
283
284
285
286
287
288
289
290
291
292
293
 
# File 'lib/llm/context.rb', line 281

def wait(strategy)
  if LLM::Stream === stream && !stream.queue.empty?
    @queue = stream.queue
    @queue.wait
  else
    return guarded_returns if guarded_returns
    @queue = functions.spawn(strategy)
    @queue.wait
  end
ensure
  @queue = nil
  @stream = nil
end