Class: Phronomy::Agent::Base

Inherits:
Object
  • Object
show all
Includes:
AsyncEventApi, Concerns::BeforeCompletion, Concerns::ErrorTranslation, Concerns::Filterable, Runnable
Defined in:
lib/phronomy/agent/base.rb

Overview

Base class for all Phronomy agents.

Subclass this to create a conversational agent powered by an LLM. DSL class methods configure the model, instructions, tools, memory, and execution hooks. Instance methods handle invocation.

Examples:

Minimal agent

class GreetingAgent < Phronomy::Agent::Base
  model "gpt-4o-mini"
  instructions "You are a friendly greeter."
end
result = GreetingAgent.new.invoke("Hello!")
puts result[:output]

Agent with tools

class ResearchAgent < Phronomy::Agent::Base
  model "gpt-4o"
  instructions "You are a research assistant."
  tools WebSearchTool, CalculatorTool
  max_iterations 15
end

Direct Known Subclasses

MultiAgent::Orchestrator

Instance Attribute Summary

Attributes included from Concerns::BeforeCompletion

#before_completion

Class Method Summary collapse

Instance Method Summary collapse

Methods included from Concerns::BeforeCompletion

included

Methods included from Concerns::Filterable

#add_input_filter, #add_output_filter, #add_tool_result_filter, included

Methods included from Runnable

#batch, #trace

Class Method Details

.approve(agent_invocation_id, approval_request_id:, approved: true, config: {}) ⇒ Object

Continues a suspended AgentInvocation.

Parameters:

  • agent_invocation_id (String)
  • approval_request_id (String)
  • approved (Boolean) (defaults to: true)
  • config (Hash) (defaults to: {}) 


323
324
325
326
327
328
329
330
 
# File 'lib/phronomy/agent/base.rb', line 323

def approve(agent_invocation_id, approval_request_id:, approved: true, config: {})
  new.approve(
    agent_invocation_id,
    approval_request_id: approval_request_id,
    approved: approved,
    config: config
  )
end

.approve_async(agent_invocation_id, approval_request_id:, approved: true, config: {}) ⇒ Phronomy::Task

Continues a suspended AgentInvocation without blocking the caller.

Parameters:

  • agent_invocation_id (String)
  • approval_request_id (String)
  • approved (Boolean) (defaults to: true)
  • config (Hash) (defaults to: {})

Returns:



339
340
341
342
343
344
345
346
 
# File 'lib/phronomy/agent/base.rb', line 339

def approve_async(agent_invocation_id, approval_request_id:, approved: true, config: {})
  new.approve_async(
    agent_invocation_id,
    approval_request_id: approval_request_id,
    approved: approved,
    config: config
  )
end

.cache_instructions(enabled = nil) ⇒ Object

When enabled, attaches Anthropic prompt-cache markers to the system message so that the fixed instructions are served from cache on subsequent turns, reducing input-token costs.

Only has an effect when the agent also declares provider :anthropic. The cache_control field is provider-specific (the format differs between Anthropic direct, Bedrock, etc.), so the agent must explicitly declare its provider via the DSL rather than having it inferred from the model name.

Examples:

class MyAgent < Phronomy::Agent::Base
  provider :anthropic
  cache_instructions true
end


259
260
261
262
263
264
265
 
# File 'lib/phronomy/agent/base.rb', line 259

def cache_instructions(enabled = nil)
  if enabled.nil?
    @cache_instructions
  else
    @cache_instructions = enabled
  end
end

.context_overhead(val = nil) ⇒ Object

Tokens reserved for the system prompt + tool definitions overhead. Subtract this from the context window before computing the memory budget.

Examples:

class MyAgent < Phronomy::Agent::Base
  context_overhead 500
end


309
310
311
312
313
314
315
 
# File 'lib/phronomy/agent/base.rb', line 309

def context_overhead(val = nil)
  if val.nil?
    @context_overhead || 0
  else
    @context_overhead = val.to_i
  end
end

.context_window(val = nil) ⇒ Object

Overrides the context window size used for token budget calculations. When set, this value takes precedence over the RubyLLM model registry, which is useful for locally-hosted models (e.g. LM Studio) where the actually-loaded context length may differ from the catalogue value.

Examples:

class MyAgent < Phronomy::Agent::Base
  context_window 4096
end


293
294
295
296
297
298
299
 
# File 'lib/phronomy/agent/base.rb', line 293

def context_window(val = nil)
  if val.nil?
    @context_window
  else
    @context_window = val.to_i
  end
end

.instructions(text = nil) { ... } ⇒ String, ...

Sets or reads the system instructions for this agent. Accepts a String, a Context::Instruction::PromptTemplate, or a block (Proc). When used as a reader (no argument, no block), returns the stored value.

Examples:

String instructions

class MyAgent < Phronomy::Agent::Base
  instructions "You are a helpful assistant."
end

Block instructions

class MyAgent < Phronomy::Agent::Base
  instructions { |input| "Answer in #{input[:lang]}." }
end

Parameters:

Yields:

  • optionally provide instructions as a block

Returns:



76
77
78
79
80
81
82
83
 
# File 'lib/phronomy/agent/base.rb', line 76

def instructions(text = nil, &block)
  if text || block_given?
    @instructions = text || block
  else
    return @instructions if instance_variable_defined?(:@instructions)
    superclass.respond_to?(:instructions) ? superclass.instructions : nil
  end
end

.max_iterations(val = nil) ⇒ Integer

Sets or reads the maximum number of LLM call cycles for ReAct agents. Each tool call and follow-up counts as one iteration. Defaults to 10.

Examples:

class MyAgent < Phronomy::Agent::Base
  max_iterations 5
end

Parameters:

  • val (Integer, nil) (defaults to: nil)

Returns:

  • (Integer) 


183
184
185
186
187
188
189
 
# File 'lib/phronomy/agent/base.rb', line 183

def max_iterations(val = nil)
  if val
    @max_iterations = val
  else
    @max_iterations || 10
  end
end

.max_output_tokens(val = nil) ⇒ Object

Tokens to reserve for the model's output. When nil, the model's max_output_tokens from the registry is used.

Examples:

class MyAgent < Phronomy::Agent::Base
  max_output_tokens 4096
end


275
276
277
278
279
280
281
 
# File 'lib/phronomy/agent/base.rb', line 275

def max_output_tokens(val = nil)
  if val.nil?
    @max_output_tokens
  else
    @max_output_tokens = val.to_i
  end
end

.model(name = nil) ⇒ String?

Sets or reads the LLM model identifier for this agent. When called without an argument, returns the stored model or the global default from Phronomy.configuration.

Examples:

class MyAgent < Phronomy::Agent::Base
  model "gpt-4o"
end

Parameters:

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

    model identifier (e.g. "gpt-4o", "claude-3-5-sonnet")

Returns:

  • (String, nil) —

    the model name when used as a reader



52
53
54
55
56
57
58
 
# File 'lib/phronomy/agent/base.rb', line 52

def model(name = nil)
  if name
    @model = name
  else
    @model || Phronomy.configuration.default_model
  end
end

.provider(name = nil) ⇒ Symbol?

Sets or reads the LLM provider for this agent. Required when using a model not registered in RubyLLM's model registry (e.g. locally-hosted models via LM Studio or Ollama).

Examples:

class MyAgent < Phronomy::Agent::Base
  model "openai/gpt-oss-20b"
  provider :openai
end

Parameters:

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

    e.g. :openai, :anthropic, :ollama

Returns:

  • (Symbol, nil) 


146
147
148
149
150
151
152
153
 
# File 'lib/phronomy/agent/base.rb', line 146

def provider(name = nil)
  if name
    @provider = name
  else
    return @provider if instance_variable_defined?(:@provider)
    superclass.respond_to?(:provider) ? superclass.provider : nil
  end
end

.static_knowledge(*sources) ⇒ Object

Registers one or more static knowledge sources on the agent class. Static source content is fetched and memoized at the class level the first time invoke is called. The cache persists for the lifetime of the process; call static_knowledge_refresh! to force a reload.

Examples:

class PolicyAgent < Phronomy::Agent::Base
  static_knowledge Phronomy::Agent::Context::Knowledge::StaticKnowledge.new(POLICY_TEXT)
end

Parameters:



202
203
204
205
206
207
 
# File 'lib/phronomy/agent/base.rb', line 202

def static_knowledge(*sources)
  @static_knowledge_sources = sources.flatten
  # Invalidate the cached chunks so the new sources are fetched on
  # the next call to static_knowledge_chunks.
  @static_knowledge_chunks = nil
end

.static_knowledge_chunks ⇒ Array<Hash>

Returns the fetched content from all static knowledge sources. Results are cached at the class level so that each source is fetched only once regardless of how many times the agent is invoked.

Returns:

  • (Array<Hash>) 


221
222
223
224
225
 
# File 'lib/phronomy/agent/base.rb', line 221

def static_knowledge_chunks
  @static_knowledge_chunks ||= static_knowledge_sources.flat_map { |ks|
    ks.fetch(query: nil)
  }
end

.static_knowledge_refresh! ⇒ nil

Clears the class-level knowledge cache so that the next invoke call re-fetches content from all registered static knowledge sources.

Call this method when the underlying knowledge source has been updated at runtime (e.g. a file was rewritten, a DB record changed) and you want the agent to pick up the new content without restarting the process.

Examples:

Refresh after updating a knowledge file

MyAgent.static_knowledge_refresh!

Returns:

  • (nil) 


239
240
241
 
# File 'lib/phronomy/agent/base.rb', line 239

def static_knowledge_refresh!
  @static_knowledge_chunks = nil
end

.static_knowledge_sources ⇒ Array<Phronomy::Agent::Context::Knowledge::Base>

Returns the registered static knowledge sources.

Returns:



212
213
214
 
# File 'lib/phronomy/agent/base.rb', line 212

def static_knowledge_sources
  @static_knowledge_sources || []
end

.temperature(val = nil) ⇒ Float?

Sets or reads the sampling temperature sent to the LLM. When nil, the provider's default is used.

Examples:

class MyAgent < Phronomy::Agent::Base
  temperature 0.2
end

Parameters:

  • val (Float, nil) (defaults to: nil) —

    temperature (0.0 to 2.0 depending on provider)

Returns:

  • (Float, nil) 


165
166
167
168
169
170
171
 
# File 'lib/phronomy/agent/base.rb', line 165

def temperature(val = nil)
  if val
    @temperature = val
  else
    @temperature
  end
end

.tool_aliases ⇒ Hash{Class => String}

Returns the alias map registered via the hash form of .tools. Merges parent class aliases so subclasses inherit their parent's mappings. Subclass-specific aliases take precedence over parent aliases.

Returns:

  • (Hash{Class => String}) 


125
126
127
128
129
130
131
132
 
# File 'lib/phronomy/agent/base.rb', line 125

def tool_aliases
  own = @tool_aliases || {}
  if superclass.respond_to?(:tool_aliases)
    superclass.tool_aliases.merge(own)
  else
    own
  end
end

.tools(*args) ⇒ Object

Registers tool classes for this agent.

Accepts either a splat of classes (backward-compatible) or a Hash mapping each class to an explicit alias name (String) or nil (use tool's own name). The alias form is useful when two tools share the same auto-generated name (e.g. two SearchTool classes from different modules).

Examples:

Splat form (no alias)

tools WeatherTool, TimeTool

Hash form (with optional per-tool alias)

tools(
  Weather::SearchTool => "weather_search",
  Places::SearchTool  => "places_search",
  CurrentTimeTool     => nil
)


102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
 
# File 'lib/phronomy/agent/base.rb', line 102

def tools(*args)
  if args.empty?
    if instance_variable_defined?(:@tools)
      return @tools
    end
    return superclass.respond_to?(:tools) ? superclass.tools : []
  end

  if args.length == 1 && args.first.is_a?(Hash)
    hash = args.first
    @tools = hash.keys
    @tool_aliases = hash.transform_values { |v| v&.to_s }.reject { |_, v| v.nil? }
  else
    @tools = args
    @tool_aliases = {}
  end
end

Instance Method Details

#_add_handoff_tool(tool_class) ⇒ self

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.

Registers an anonymous handoff tool class on this agent instance. Called by Runner during construction when routes are configured.

Parameters:

Returns:

  • (self) 


354
355
356
357
358
 
# File 'lib/phronomy/agent/base.rb', line 354

def _add_handoff_tool(tool_class)
  @_handoff_tools ||= []
  @_handoff_tools << tool_class
  self
end

#_handoff_tools ⇒ Array<Class>

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 handoff tool classes registered on this instance by Runner.

Returns:

  • (Array<Class>) 


363
364
365
 
# File 'lib/phronomy/agent/base.rb', line 363

def _handoff_tools
  @_handoff_tools || []
end

#approve(agent_invocation_id, approval_request_id:, approved: true, config: {}) ⇒ Hash

Continues a suspended AgentInvocation. The parent session is registered asynchronously; this method is only the synchronous wrapper.

Returns:

  • (Hash) 


983
984
985
986
987
988
989
990
991
 
# File 'lib/phronomy/agent/base.rb', line 983

def approve(agent_invocation_id, approval_request_id:, approved: true, config: {})
  _check_scheduler_reentrancy(:approve, :approve_async)
  approve_async(
    agent_invocation_id,
    approval_request_id: approval_request_id,
    approved: approved,
    config: config
  ).wait_result
end

#approve_async(agent_invocation_id, approval_request_id:, approved: true, config: {}) ⇒ Phronomy::Task

Continues a suspended AgentInvocation without blocking the caller.

This method is safe to call from an EventLoop stream callback. The returned Task completes when the resumed AgentInvocation finishes, suspends again, or fails.

Returns:



1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
 
# File 'lib/phronomy/agent/base.rb', line 1001

def approve_async(agent_invocation_id, approval_request_id:, approved: true, config: {})
  result_task = Phronomy::Task.deferred(
    name: "agent-approval-resume:#{agent_invocation_id}"
  )

  begin
    entry = Agent::AgentInvocationRegistry.consume_approval(
      agent_invocation_id, approval_request_id
    )
    unless entry
      raise ArgumentError,
        "No pending approval found for AgentInvocation #{agent_invocation_id}"
    end

    _start_approval_resume(
      result_task,
      entry.invocation,
      approved: approved,
      config: config
    )
  rescue => e
    _fail_result_task(result_task, e)
  end

  result_task
end

#context_version_cache ⇒ Object

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.

Deprecated.

The context version cache has been removed. Returns nil. Retained for backward compatibility with callers using safe navigation (+&.reset+).



552
553
554
 
# File 'lib/phronomy/agent/base.rb', line 552

def context_version_cache
  nil
end

#invoke(input, messages: [], thread_id: nil, config: {}, invocation_context: nil) ⇒ Hash

Invokes the agent with the given input and returns a result Hash. Provider errors are translated after the configured LLM adapter returns its final result. Phronomy does not replay the Agent invocation.

Examples:

Normal invocation

result = MyAgent.new.invoke("What is Ruby?")
puts result[:output]

Multi-turn conversation

result1 = agent.invoke("Hi, I'm Alice.")
result2 = agent.invoke("What's my name?", messages: result1[:messages])

Suspend / resume flow

result = agent.invoke("Perform task X")
if result[:suspended]
  result = agent.resume(result[:checkpoint], approved: true)
end
puts result[:output]

With InvocationContext (deadline-based timeout)

ctx = Phronomy::InvocationContext.new(
  thread_id: "conv-123",
  deadline: Phronomy::Concurrency::Deadline.in(30),
  task_id: SecureRandom.uuid
)
result = MyAgent.new.invoke("Hello", invocation_context: ctx)

Parameters:

  • input (String, Hash) —

    the user message; a Hash may supply :message, :query, or :user as the text key, plus any template variables consumed by the configured instructions template.

  • messages (Array<RubyLLM::Message>) (defaults to: []) —

    conversation history from a previous invocation. The application owns and persists this array; pass it on every turn to maintain multi-turn context.

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

    conversation thread identifier, forwarded to the compaction context when on_compact is configured.

  • config (Hash) (defaults to: {}) —

    additional runtime options: :user_id (+String+, optional) — caller identity forwarded to the tracer :session_id (+String+, optional) — session identity forwarded to the tracer

  • invocation_context (Phronomy::InvocationContext, nil) (defaults to: nil) —

    optional first-class context object. When present, thread_id, cancellation_token, and deadline are derived from it (existing config: keys take precedence as backward-compat aliases). The object is also stored in config[:invocation_context] so that task_id / parent_task_id appear in trace spans automatically.

Returns:

  • (Hash) —

    { output: String, messages: Array, usage: Phronomy::TokenUsage }, or +{ output: nil, suspended: true, checkpoint: Phronomy::Agent::Checkpoint, messages: Array }+ when the invocation was suspended awaiting tool approval.

Raises:



433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
 
# File 'lib/phronomy/agent/base.rb', line 433

def invoke(input, messages: [], thread_id: nil, config: {}, invocation_context: nil)
  if invocation_context
    thread_id, config = _apply_invocation_context(thread_id, config, invocation_context)
  end
  _check_scheduler_reentrancy(:invoke, :invoke_async)

  trace("agent.invoke", input: input, **_build_caller_meta(config)) do |_span|
    result = invoke_async(
      input,
      messages: messages,
      thread_id: thread_id,
      config: config
    ).wait_result
    [result, result[:usage]]
  end
end

#invoke_async(input, messages: [], thread_id: nil, config: {}, invocation_context: nil, on_tool_approval_required: nil) ⇒ Phronomy::Task

Invokes this agent asynchronously and returns a Task.

This is the primary async entry point. #invoke is a synchronous wrapper that calls this method and blocks the caller until the task completes. Calling #invoke from inside an active scheduler task raises SchedulerReentrancyError; use invoke_async directly in that context.

The task is registered with the Runtime task registry so Runtime#shutdown drains in-flight invocations before process exit.

Examples:

task = agent.invoke_async("Hello!")
result = task.wait_result   # => { output: "...", messages: [...], usage: ... }

Parameters:

  • input (String, Hash)
  • messages (Array) (defaults to: [])
  • thread_id (String, nil) (defaults to: nil)
  • config (Hash) (defaults to: {})
  • invocation_context (Phronomy::InvocationContext, nil) (defaults to: nil)

Returns:



472
473
474
475
476
477
478
479
480
481
482
483
484
485
 
# File 'lib/phronomy/agent/base.rb', line 472

def invoke_async(input, messages: [], thread_id: nil, config: {},
  invocation_context: nil, on_tool_approval_required: nil)
  if invocation_context
    thread_id, config = _apply_invocation_context(thread_id, config, invocation_context)
  end
  result_task = Phronomy::Task.deferred(name: "agent-#{(self.class.name || "anonymous").downcase}-async")
  approval_snapshot = _approval_configuration_snapshot(on_tool_approval_required)
  _start_invocation(
    result_task, input,
    messages: messages, thread_id: thread_id, config: config,
    approval_snapshot: approval_snapshot
  )
  result_task
end

#on_tool_approval_required(&block) ⇒ self

Registers a non-blocking Application notification listener.

Returns:

  • (self)

Raises:

  • (ArgumentError) 


382
383
384
385
386
387
 
# File 'lib/phronomy/agent/base.rb', line 382

def on_tool_approval_required(&block)
  raise ArgumentError, "on_tool_approval_required requires a block" unless block

  _approval_configuration_mutex.synchronize { @tool_approval_listener = block }
  self
end

#stream(input, messages: [], thread_id: nil, config: {}, invocation_context: nil, on_tool_approval_required: nil) {|Phronomy::Agent::StreamEvent| ... } ⇒ Hash

Synchronous wrapper around #stream_async.

Stream callbacks execute on the EventLoop thread, not on the thread that calls this method. This method only blocks while waiting for the final Task.

Yields:

Returns:

  • (Hash) —

    same result shape as #invoke

Raises:

  • (ArgumentError) 


527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
 
# File 'lib/phronomy/agent/base.rb', line 527

def stream(input, messages: [], thread_id: nil, config: {},
  invocation_context: nil, on_tool_approval_required: nil, &block)
  raise ArgumentError, "stream requires a block" unless block

  if invocation_context
    thread_id, config = _apply_invocation_context(thread_id, config, invocation_context)
  end
  _check_scheduler_reentrancy(:stream, :stream_async)

  trace("agent.stream", input: input, **_build_caller_meta(config)) do |_span|
    result = stream_async(
      input,
      messages: messages,
      thread_id: thread_id,
      config: config,
      on_tool_approval_required: on_tool_approval_required,
      &block
    ).wait_result
    [result, result[:usage]]
  end
end

#stream_async(input, messages: [], thread_id: nil, config: {}, invocation_context: nil, on_tool_approval_required: nil, &block) ⇒ Phronomy::Task

Invokes this agent asynchronously and delivers stream events from the Runtime-owned EventLoop thread.

The callback must return quickly. Blocking I/O, synchronous Agent calls, sleep, and heavy CPU work must be delegated by the Application.

Returns:

Raises:

  • (ArgumentError) 


495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
 
# File 'lib/phronomy/agent/base.rb', line 495

def stream_async(input, messages: [], thread_id: nil, config: {},
  invocation_context: nil, on_tool_approval_required: nil, &block)
  raise ArgumentError, "stream_async requires a block" unless block

  if invocation_context
    thread_id, config = _apply_invocation_context(thread_id, config, invocation_context)
  end

  result_task = Phronomy::Task.deferred(
    name: "agent-#{(self.class.name || "anonymous").downcase}-stream-async"
  )
  approval_snapshot = _approval_configuration_snapshot(on_tool_approval_required)
  _start_invocation(
    result_task,
    input,
    messages: messages,
    thread_id: thread_id,
    config: config,
    approval_snapshot: approval_snapshot,
    mode: :stream,
    on_event: block
  )
  result_task
end

#tool_approval_policy(&block) ⇒ self

Registers the final Agent/Application authorization policy. The block runs on the Runtime authorization pool and must return :allow, :require_approval, or :reject.

Returns:

  • (self)

Raises:

  • (ArgumentError) 


372
373
374
375
376
377
 
# File 'lib/phronomy/agent/base.rb', line 372

def tool_approval_policy(&block)
  raise ArgumentError, "tool_approval_policy requires a block" unless block

  _approval_configuration_mutex.synchronize { @tool_approval_policy = block }
  self
end