Package {agentr}

Normalize candidate values

Description

Normalize candidate values

Usage

.normalize_candidate_values(x)

Arguments

Value

Character vector.

Normalize implementation prompt input

Description

Normalize implementation prompt input

Usage

.normalize_implementation_prompt_input(x)

Arguments

Value

A normalized implementation payload list.

Safely Read RDS File with Lock Awareness

Description

Reads an .rds file safely by checking if a .lock file exists, indicating that another process may be writing. Retries until the lock disappears or max_attempts is exceeded.

Usage

.safe_read_rds(path, wait = 5, max_attempts = 10)

Arguments

Value

The deserialized R object.

Save a JSON file safely

Description

Save a JSON file safely

Usage

.safe_save_json(object, path, wait = 5, max_attempts = 10)

Arguments

Value

Invisibly returns TRUE.

Safely Save RDS File with Lock

Description

Saves an R object to an .rds file using a simple file-based lock to prevent concurrent writes. If the file is locked by another process, it retries until success or max_attempts is reached.

Usage

.safe_save_rds(object, path, wait = 5, max_attempts = 10)

Arguments

Value

Invisibly returns TRUE on success.

Validate scaffolder action arguments for a specific method

Description

Validate scaffolder action arguments for a specific method

Usage

.validate_scaffolder_action_args(method, args)

Arguments

Value

Validated argument list, invisibly.

Validate scaffolder action references against current state

Description

Validate scaffolder action references against current state

Usage

.validate_scaffolder_action_refs(scaffolder, method, args)

Arguments

Value

Invisibly returns TRUE.

AEConfig

Description

AEConfig

AEConfig

Details

Configuration for the action-execution subsystem.

Methods

⁠$initialize(enabled = TRUE, execution_mode = "guided", tool_budget = "standard", metadata = list())⁠

Create an action-execution config.

⁠$validate()⁠

Validate the config.

⁠$as_list()⁠

Return a serializable representation.

Public fields

Methods

Public methods

• AEConfig$new()

• AEConfig$validate()

• AEConfig$as_list()

• AEConfig$print()

• AEConfig$clone()

Method new()

Create an action-execution config.

Usage

AEConfig$new(
  enabled = TRUE,
  execution_mode = "guided",
  tool_budget = "standard",
  metadata = list()
)

Arguments

Method validate()

Validate the config.

Usage

AEConfig$validate()

Method as_list()

Return a serializable representation.

Usage

AEConfig$as_list()

Method print()

Print a compact config summary.

Usage

AEConfig$print(...)

Arguments

Method clone()

The objects of this class are cloneable with this method.

Usage

AEConfig$clone(deep = FALSE)

Arguments

AffectiveConfig

Description

AffectiveConfig

AffectiveConfig

Details

Lightweight configuration for the affective layer inside RWM.

Methods

⁠$initialize(enabled = TRUE, style = "lightweight", persistence = "session", summary = NULL, metadata = list())⁠

Create an affective-layer config.

⁠$validate()⁠

Validate the config.

⁠$as_list()⁠

Return a serializable representation.

Public fields

Methods

Public methods

• AffectiveConfig$new()

• AffectiveConfig$validate()

• AffectiveConfig$as_list()

• AffectiveConfig$print()

• AffectiveConfig$clone()

Method new()

Create an affective-layer config.

Usage

AffectiveConfig$new(
  enabled = TRUE,
  style = "lightweight",
  persistence = "session",
  summary = NULL,
  metadata = list()
)

Arguments

Method validate()

Validate the config.

Usage

AffectiveConfig$validate()

Method as_list()

Return a serializable representation.

Usage

AffectiveConfig$as_list()

Method print()

Print a compact config summary.

Usage

AffectiveConfig$print(...)

Arguments

Method clone()

The objects of this class are cloneable with this method.

Usage

AffectiveConfig$clone(deep = FALSE)

Arguments

AffectiveState

Description

AffectiveState

AffectiveState

Details

Minimal structured affective layer with inertia-aware updates.

Methods

⁠$initialize(state = default_emotion_state())⁠

Create an affective state container.

⁠$decay(current_time = Sys.time())⁠

Apply time-based decay to the stored affective state.

⁠$update_primary(updates)⁠

Blend named primary-emotion updates into the current state using inertia.

⁠$describe(threshold = 0.2, include_blended = TRUE, method = "geometric")⁠

Return a natural-language description of the current affective state.

⁠$as_list()⁠

Return the raw underlying affective-state list.

Public fields

Methods

Public methods

• AffectiveState$new()

• AffectiveState$decay()

• AffectiveState$update_primary()

• AffectiveState$describe()

• AffectiveState$as_list()

• AffectiveState$clone()

Method new()

Create an AffectiveState with an initial emotion state.

Usage

AffectiveState$new(state = default_emotion_state())

Arguments

Method decay()

Apply time-based decay to the current affective state.

Usage

AffectiveState$decay(current_time = Sys.time())

Arguments

Method update_primary()

Blend named primary-emotion updates into the current affective state.

Usage

AffectiveState$update_primary(updates)

Arguments

Method describe()

Return a natural-language description of the current affective state.

Usage

AffectiveState$describe(
  threshold = 0.2,
  include_blended = TRUE,
  method = "geometric"
)

Arguments

Method as_list()

Return the underlying affective state as a plain list.

Usage

AffectiveState$as_list()

Method clone()

The objects of this class are cloneable with this method.

Usage

AffectiveState$clone(deep = FALSE)

Arguments

AgentCore

Description

AgentCore

AgentCore

Details

Minimal agent container for the agentr cognitive core. An AgentCore combines cognitive and affective state layers and can optionally own a Scaffolder instance for human-in-the-loop workflow elicitation.

Methods

⁠$initialize(id = "agentr-core", name = "agentr", cognition = CognitiveState$new(), affect = AffectiveState$new(), metadata = list())⁠

Create a minimal agent container with cognition and affect.

⁠$attach_scaffolder(scaffolder = NULL)⁠

Attach an existing scaffolder or create a new Scaffolder owned by the agent.

⁠$snapshot()⁠

Return a serializable snapshot of the agent's core state.

Public fields

Methods

Public methods

• AgentCore$new()

• AgentCore$attach_scaffolder()

• AgentCore$snapshot()

• AgentCore$clone()

Method new()

Create an AgentCore with cognition, affect, and free-form metadata.

Usage

AgentCore$new(
  id = "agentr-core",
  name = "agentr",
  cognition = CognitiveState$new(),
  affect = AffectiveState$new(),
  metadata = list()
)

Arguments

Method attach_scaffolder()

Attach an existing scaffolder or create a new one owned by this agent.

Usage

AgentCore$attach_scaffolder(scaffolder = NULL)

Arguments

Method snapshot()

Return a serializable snapshot of the agent core state.

Usage

AgentCore$snapshot()

Method clone()

The objects of this class are cloneable with this method.

Usage

AgentCore$clone(deep = FALSE)

Arguments

AgentScaffoldState

Description

AgentScaffoldState

AgentScaffoldState

Details

Top-level state container for approved agent designs and nested workflow state.

Methods

⁠$initialize(approved_agent_spec = NULL, proposal_state = list(status = "draft", proposals = list()), workflow_state = WorkflowProposalState$new(), metadata = list())⁠

Create an agent scaffold state container.

⁠$validate()⁠

Validate the state object.

⁠$set_approved_agent_spec(spec)⁠

Store an approved AgentSpec.

⁠$approved_workflow()⁠

Return the approved workflow, preferring the approved agent spec when present.

⁠$as_list()⁠

Return a serializable representation.

Public fields

Methods

Public methods

• AgentScaffoldState$new()

• AgentScaffoldState$validate()

• AgentScaffoldState$set_approved_agent_spec()

• AgentScaffoldState$approved_workflow()

• AgentScaffoldState$as_list()

• AgentScaffoldState$print()

• AgentScaffoldState$clone()

Method new()

Create an agent scaffold state container.

Usage

AgentScaffoldState$new(
  approved_agent_spec = NULL,
  proposal_state = list(status = "draft", proposals = list()),
  workflow_state = WorkflowProposalState$new(),
  metadata = list()
)

Arguments

Method validate()

Validate the state object.

Usage

AgentScaffoldState$validate()

Method set_approved_agent_spec()

Store an approved AgentSpec.

Usage

AgentScaffoldState$set_approved_agent_spec(spec)

Arguments

Method approved_workflow()

Return the approved workflow.

Usage

AgentScaffoldState$approved_workflow()

Method as_list()

Return a serializable representation.

Usage

AgentScaffoldState$as_list()

Method print()

Print a compact state summary.

Usage

AgentScaffoldState$print(...)

Arguments

Method clone()

The objects of this class are cloneable with this method.

Usage

AgentScaffoldState$clone(deep = FALSE)

Arguments

AgentSpec

Description

AgentSpec

AgentSpec

Details

Public agent-design artifact combining workflow, memory, knowledge, state, interface, and optional subsystem diagnostic labels.

Methods

⁠$initialize(task, agent_name = "agentr-agent", summary = NULL, subsystems = SubsystemSpec$new(), workflow = NULL, knowledge_spec = NULL, memory_spec = NULL, state_requirements = list(), state_spec = NULL, interfaces = list(), interface_spec = NULL, autonomy_spec = NULL, autonomy_stage = NULL, implementation_targets = list(), metadata = list())⁠

Create an agent-design artifact.

⁠$validate()⁠

Validate the agent design.

⁠$selected_subsystems()⁠

Return the selected subsystem names.

⁠$workflow_spec()⁠

Return the embedded workflow specification.

⁠$design_summary()⁠

Return a one-row summary table.

⁠$as_list()⁠

Return a serializable representation.

⁠$save(file_path)⁠

Save the object with save_agent().

Public fields

Methods

Public methods

• AgentSpec$new()

• AgentSpec$validate()

• AgentSpec$selected_subsystems()

• AgentSpec$workflow_spec()

• AgentSpec$design_summary()

• AgentSpec$as_list()

• AgentSpec$save()

• AgentSpec$print()

• AgentSpec$clone()

Method new()

Create an agent-design artifact.

Usage

AgentSpec$new(
  task,
  agent_name = "agentr-agent",
  summary = NULL,
  subsystems = SubsystemSpec$new(),
  workflow = NULL,
  knowledge_spec = NULL,
  memory_spec = NULL,
  state_requirements = list(),
  state_spec = NULL,
  interfaces = list(),
  interface_spec = NULL,
  autonomy_spec = NULL,
  autonomy_stage = NULL,
  implementation_targets = list(),
  metadata = list()
)

Arguments

Method validate()

Validate the agent design.

Usage

AgentSpec$validate()

Method selected_subsystems()

Return the selected subsystem names.

Usage

AgentSpec$selected_subsystems()

Method workflow_spec()

Return the embedded workflow specification.

Usage

AgentSpec$workflow_spec()

Method design_summary()

Return a one-row summary table.

Usage

AgentSpec$design_summary()

Method as_list()

Return a serializable representation.

Usage

AgentSpec$as_list()

Method save()

Save the object with save_agent().

Usage

AgentSpec$save(file_path)

Arguments

Method print()

Print a compact agent-design summary.

Usage

AgentSpec$print(...)

Arguments

Method clone()

The objects of this class are cloneable with this method.

Usage

AgentSpec$clone(deep = FALSE)

Arguments

CognitiveConfig

Description

CognitiveConfig

CognitiveConfig

Details

Lightweight configuration for the cognitive layer inside RWM.

Methods

⁠$initialize(enabled = TRUE, persistence = "session", memory_types = character(), summary = NULL, metadata = list())⁠

Create a cognitive-layer config.

⁠$validate()⁠

Validate the config.

⁠$as_list()⁠

Return a serializable representation.

Public fields

Methods

Public methods

• CognitiveConfig$new()

• CognitiveConfig$validate()

• CognitiveConfig$as_list()

• CognitiveConfig$print()

• CognitiveConfig$clone()

Method new()

Create a cognitive-layer config.

Usage

CognitiveConfig$new(
  enabled = TRUE,
  persistence = "session",
  memory_types = character(),
  summary = NULL,
  metadata = list()
)

Arguments

Method validate()

Validate the config.

Usage

CognitiveConfig$validate()

Method as_list()

Return a serializable representation.

Usage

CognitiveConfig$as_list()

Method print()

Print a compact config summary.

Usage

CognitiveConfig$print(...)

Arguments

Method clone()

The objects of this class are cloneable with this method.

Usage

CognitiveConfig$clone(deep = FALSE)

Arguments

CognitiveState

Description

CognitiveState

CognitiveState

Details

Minimal structured cognitive layer for agent state representation. This class intentionally provides only a lightweight API for ⁠0.1.3⁠. Its bayes_update() method is a placeholder interface rather than a full inference engine.

Methods

⁠$initialize(beliefs = list(), knowledge = list(), goals = list(), task_context = list(), confidence = numeric(), update_log = list())⁠

Create a lightweight cognitive state container.

⁠$set_belief(name, value, confidence = NULL)⁠

Store or update a named belief and optional confidence value.

⁠$add_knowledge(entry, label = NULL)⁠

Append a knowledge record with timestamped provenance.

⁠$set_goal(id, description, status = "proposed")⁠

Store or update a goal record.

⁠$set_context(...)⁠

Merge named task-context fields into the current cognitive state.

⁠$bayes_update(target, evidence, prior = NULL, note = NULL)⁠

Record a placeholder Bayesian-style update artifact.

⁠$as_list()⁠

Return the cognitive state as a plain list.

⁠$record_update(type, key, value, confidence = NULL)⁠

Append a structured update record to the update log.

Public fields

Methods

Public methods

• CognitiveState$new()

• CognitiveState$set_belief()

• CognitiveState$add_knowledge()

• CognitiveState$set_goal()

• CognitiveState$set_context()

• CognitiveState$bayes_update()

• CognitiveState$as_list()

• CognitiveState$record_update()

• CognitiveState$clone()

Method new()

Create a CognitiveState with beliefs, knowledge, goals, and context.

Usage

CognitiveState$new(
  beliefs = list(),
  knowledge = list(),
  goals = list(),
  task_context = list(),
  confidence = numeric(),
  update_log = list()
)

Arguments

Method set_belief()

Store or update a named belief and optional confidence value.

Usage

CognitiveState$set_belief(name, value, confidence = NULL)

Arguments

Method add_knowledge()

Append a timestamped knowledge record to the cognitive state.

Usage

CognitiveState$add_knowledge(entry, label = NULL)

Arguments

Method set_goal()

Store or update a structured goal record.

Usage

CognitiveState$set_goal(id, description, status = "proposed")

Arguments

Method set_context()

Merge named task-context fields into the current state.

Usage

CognitiveState$set_context(...)

Arguments

Method bayes_update()

Record a placeholder Bayesian-style update artifact.

Usage

CognitiveState$bayes_update(target, evidence, prior = NULL, note = NULL)

Arguments

Method as_list()

Return the cognitive state as a plain list.

Usage

CognitiveState$as_list()

Method record_update()

Append a structured update event to the update log.

Usage

CognitiveState$record_update(type, key, value, confidence = NULL)

Arguments

Method clone()

The objects of this class are cloneable with this method.

Usage

CognitiveState$clone(deep = FALSE)

Arguments

DesignReviewSpec

Description

DesignReviewSpec

DesignReviewSpec

Details

Data contract for a future JS/HTML human review layer. It packages the current design artifacts into stable sections that can be rendered, commented on, and converted back into structured feedback.

Methods

⁠$initialize(...)⁠

Create a design-review data bundle.

⁠$validate()⁠

Validate the bundle sections.

⁠$to_list()⁠

Return a JSON-ready list.

⁠$print(...)⁠

Print a compact summary.

Public fields

Methods

Public methods

• DesignReviewSpec$new()

• DesignReviewSpec$validate()

• DesignReviewSpec$to_list()

• DesignReviewSpec$print()

• DesignReviewSpec$clone()

Method new()

Create a design-review data bundle.

Usage

DesignReviewSpec$new(
  review_id = .design_review_id(),
  agent_name = NA_character_,
  task = NA_character_,
  generated_at = Sys.time(),
  workflow_graph = .workflow_review_section(NULL),
  memory_schema = .memory_review_section(NULL),
  narrative_knowledge = .narrative_knowledge_review_section(NULL),
  graph_knowledge = .graph_knowledge_review_section(NULL),
  proposal_states = list(),
  feedback_schema = .design_review_feedback_schema(),
  metadata = list()
)

Arguments

Method validate()

Validate the design-review bundle.

Usage

DesignReviewSpec$validate()

Method to_list()

Return a JSON-ready list.

Usage

DesignReviewSpec$to_list()

Method print()

Print a compact summary.

Usage

DesignReviewSpec$print(...)

Arguments

Method clone()

The objects of this class are cloneable with this method.

Usage

DesignReviewSpec$clone(deep = FALSE)

Arguments

IACConfig

Description

IACConfig

IACConfig

Details

Configuration for Inter-Agent Communication.

Methods

⁠$initialize(enabled = TRUE, channels = character(), structured_io = TRUE, metadata = list())⁠

Create an Inter-Agent Communication config.

⁠$validate()⁠

Validate the config.

⁠$as_list()⁠

Return a serializable representation.

Public fields

Methods

Public methods

• IACConfig$new()

• IACConfig$validate()

• IACConfig$as_list()

• IACConfig$print()

• IACConfig$clone()

Method new()

Create an Inter-Agent Communication config.

Usage

IACConfig$new(
  enabled = TRUE,
  channels = character(),
  structured_io = TRUE,
  metadata = list()
)

Arguments

Method validate()

Validate the config.

Usage

IACConfig$validate()

Method as_list()

Return a serializable representation.

Usage

IACConfig$as_list()

Method print()

Print a compact config summary.

Usage

IACConfig$print(...)

Arguments

Method clone()

The objects of this class are cloneable with this method.

Usage

IACConfig$clone(deep = FALSE)

Arguments

IntelligentAgent

Description

IntelligentAgent

IntelligentAgent

Details

Runtime-oriented container for an approved agent design.

Methods

⁠$initialize(id = "intelligent-agent", name = NULL, spec, workflow = NULL, subsystems = NULL, runtime_state = list(), metadata = list())⁠

Create a runtime-oriented agent container from an AgentSpec.

⁠$validate()⁠

Validate the runtime container.

⁠$selected_subsystems()⁠

Return the selected subsystem names.

⁠$snapshot()⁠

Return a serializable runtime snapshot.

Public fields

Methods

Public methods

• IntelligentAgent$new()

• IntelligentAgent$validate()

• IntelligentAgent$selected_subsystems()

• IntelligentAgent$snapshot()

• IntelligentAgent$print()

• IntelligentAgent$clone()

Method new()

Create a runtime-oriented agent container from an AgentSpec.

Usage

IntelligentAgent$new(
  id = "intelligent-agent",
  name = NULL,
  spec,
  workflow = NULL,
  subsystems = NULL,
  runtime_state = list(),
  metadata = list()
)

Arguments

Method validate()

Validate the runtime container.

Usage

IntelligentAgent$validate()

Method selected_subsystems()

Return the selected subsystem names.

Usage

IntelligentAgent$selected_subsystems()

Method snapshot()

Return a serializable runtime snapshot.

Usage

IntelligentAgent$snapshot()

Method print()

Print a compact runtime summary.

Usage

IntelligentAgent$print(...)

Arguments

Method clone()

The objects of this class are cloneable with this method.

Usage

IntelligentAgent$clone(deep = FALSE)

Arguments

KnowledgeProposal

Description

KnowledgeProposal

KnowledgeProposal

Details

Proposal object for one candidate knowledge item.

Public fields

Methods

Public methods

• KnowledgeProposal$new()

• KnowledgeProposal$validate()

• KnowledgeProposal$discuss()

• KnowledgeProposal$transition()

• KnowledgeProposal$approve()

• KnowledgeProposal$reject()

• KnowledgeProposal$to_list()

• KnowledgeProposal$print()

• KnowledgeProposal$clone()

Method new()

Create a knowledge proposal.

Usage

KnowledgeProposal$new(
  item,
  id = if (is.list(item) && !is.null(item$id)) paste0("knowledge_proposal_",
    as.character(item$id)[1]) else "knowledge_proposal_1",
  status = "pending",
  notes = NULL,
  conflict_report = list(),
  history = list(),
  metadata = list(),
  created_at = Sys.time(),
  updated_at = created_at,
  approved_at = as.POSIXct(NA),
  rejected_at = as.POSIXct(NA),
  superseded_by = NA_character_,
  supersedes = NA_character_
)

Method validate()

Validate the proposal.

Usage

KnowledgeProposal$validate()

Method discuss()

Append a discussion note.

Usage

KnowledgeProposal$discuss(
  note,
  source = "human",
  confidence = NA_character_,
  timestamp = Sys.time()
)

Method transition()

Apply a status transition.

Usage

KnowledgeProposal$transition(status, note = NULL, timestamp = Sys.time())

Method approve()

Approve the proposal.

Usage

KnowledgeProposal$approve(note = NULL)

Method reject()

Reject the proposal.

Usage

KnowledgeProposal$reject(note = NULL)

Method to_list()

Return a serializable representation.

Usage

KnowledgeProposal$to_list()

Method print()

Print a compact summary.

Usage

KnowledgeProposal$print(...)

Method clone()

The objects of this class are cloneable with this method.

Usage

KnowledgeProposal$clone(deep = FALSE)

Arguments

KnowledgeProposalState

Description

KnowledgeProposalState

KnowledgeProposalState

Details

State container for approved knowledge plus active and historical proposals.

Public fields

Methods

Public methods

• KnowledgeProposalState$new()

• KnowledgeProposalState$validate()

• KnowledgeProposalState$add_proposal()

• KnowledgeProposalState$get_proposal()

• KnowledgeProposalState$list_proposals()

• KnowledgeProposalState$discuss_proposal()

• KnowledgeProposalState$approve_proposal()

• KnowledgeProposalState$reject_proposal()

• KnowledgeProposalState$approved_spec()

• KnowledgeProposalState$as_list()

• KnowledgeProposalState$clone()

Method new()

Create a knowledge proposal state container.

Usage

KnowledgeProposalState$new(
  approved_knowledge_spec = KnowledgeSpec$new(),
  proposals = list(),
  history = list()
)

Method validate()

Validate the state object.

Usage

KnowledgeProposalState$validate()

Method add_proposal()

Add a proposal object.

Usage

KnowledgeProposalState$add_proposal(proposal)

Method get_proposal()

Return one stored proposal.

Usage

KnowledgeProposalState$get_proposal(proposal_id)

Method list_proposals()

List proposals with optional status filtering.

Usage

KnowledgeProposalState$list_proposals(status = NULL)

Method discuss_proposal()

Append a discussion note to one proposal.

Usage

KnowledgeProposalState$discuss_proposal(proposal_id, note, source = "human")

Method approve_proposal()

Approve one proposal and add its item to approved knowledge.

Usage

KnowledgeProposalState$approve_proposal(proposal_id, note = NULL)

Method reject_proposal()

Reject one proposal.

Usage

KnowledgeProposalState$reject_proposal(proposal_id, note = NULL)

Method approved_spec()

Return the approved knowledge specification.

Usage

KnowledgeProposalState$approved_spec()

Method as_list()

Return a serializable representation.

Usage

KnowledgeProposalState$as_list()

Method clone()

The objects of this class are cloneable with this method.

Usage

KnowledgeProposalState$clone(deep = FALSE)

Arguments

KnowledgeSpec

Description

KnowledgeSpec

KnowledgeSpec

Details

Curated domain and epistemic knowledge used to guide agent behavior. items stores narrative knowledge items, graph stores an optional graph-shaped representation, and vector_refs reserves references to external vector stores.

Methods

⁠$initialize(items = list(), graph = NULL, vector_refs = list(), metadata = list())⁠

Create a knowledge specification.

⁠$add_item(item)⁠

Add a narrative knowledge item.

⁠$get_item(id)⁠

Return a narrative knowledge item by id.

⁠$list_items(type = NULL, domain = NULL)⁠

List narrative knowledge items, optionally filtered.

⁠$validate()⁠

Validate the knowledge specification.

⁠$to_list()⁠

Return a serializable list.

⁠$print(...)⁠

Print a compact summary.

Public fields

Methods

Public methods

• KnowledgeSpec$new()

• KnowledgeSpec$add_item()

• KnowledgeSpec$get_item()

• KnowledgeSpec$list_items()

• KnowledgeSpec$validate()

• KnowledgeSpec$to_list()

• KnowledgeSpec$print()

• KnowledgeSpec$clone()

Method new()

Create a knowledge specification.

Usage

KnowledgeSpec$new(
  items = list(),
  graph = NULL,
  vector_refs = list(),
  metadata = list()
)

Arguments

Method add_item()

Add a knowledge item.

Usage

KnowledgeSpec$add_item(item)

Arguments

Method get_item()

Return a knowledge item by id.

Usage

KnowledgeSpec$get_item(id)

Arguments

Method list_items()

List knowledge items with optional filters.

Usage

KnowledgeSpec$list_items(type = NULL, domain = NULL)

Arguments

Method validate()

Validate the knowledge specification.

Usage

KnowledgeSpec$validate()

Method to_list()

Return a serializable representation.

Usage

KnowledgeSpec$to_list()

Method print()

Print a compact summary.

Usage

KnowledgeSpec$print(...)

Arguments

Method clone()

The objects of this class are cloneable with this method.

Usage

KnowledgeSpec$clone(deep = FALSE)

Arguments

LAConfig

Description

LAConfig

LAConfig

Details

Configuration for Learning & Adaptation.

Methods

⁠$initialize(enabled = TRUE, learning_mode = "feedback_driven", feedback_sources = character(), persistence = "session", metadata = list())⁠

Create a learning and adaptation config.

⁠$validate()⁠

Validate the config.

⁠$as_list()⁠

Return a serializable representation.

Public fields

Methods

Public methods

• LAConfig$new()

• LAConfig$validate()

• LAConfig$as_list()

• LAConfig$print()

• LAConfig$clone()

Method new()

Create a learning and adaptation config.

Usage

LAConfig$new(
  enabled = TRUE,
  learning_mode = "feedback_driven",
  feedback_sources = character(),
  persistence = "session",
  metadata = list()
)

Arguments

Method validate()

Validate the config.

Usage

LAConfig$validate()

Method as_list()

Return a serializable representation.

Usage

LAConfig$as_list()

Method print()

Print a compact config summary.

Usage

LAConfig$print(...)

Arguments

Method clone()

The objects of this class are cloneable with this method.

Usage

LAConfig$clone(deep = FALSE)

Arguments

MemoryProposal

Description

MemoryProposal

MemoryProposal

Details

Proposal object for a candidate memory schema.

Public fields

Methods

Public methods

• MemoryProposal$new()

• MemoryProposal$validate()

• MemoryProposal$discuss()

• MemoryProposal$transition()

• MemoryProposal$approve()

• MemoryProposal$reject()

• MemoryProposal$to_list()

• MemoryProposal$print()

• MemoryProposal$clone()

Method new()

Create a memory proposal.

Usage

MemoryProposal$new(
  memory_spec,
  id = paste0("memory_proposal_", format(Sys.time(), "%Y%m%d%H%M%S")),
  status = "pending",
  notes = NULL,
  history = list(),
  metadata = list(),
  created_at = Sys.time(),
  updated_at = created_at,
  approved_at = as.POSIXct(NA),
  rejected_at = as.POSIXct(NA),
  superseded_by = NA_character_,
  supersedes = NA_character_
)

Arguments

Method validate()

Validate the proposal.

Usage

MemoryProposal$validate()

Method discuss()

Append a discussion note.

Usage

MemoryProposal$discuss(
  note,
  source = "human",
  confidence = NA_character_,
  timestamp = Sys.time()
)

Arguments

Method transition()

Apply a lifecycle transition.

Usage

MemoryProposal$transition(status, note = NULL, timestamp = Sys.time())

Arguments

Method approve()

Approve the proposal.

Usage

MemoryProposal$approve(note = NULL)

Arguments

Method reject()

Reject the proposal.

Usage

MemoryProposal$reject(note = NULL)

Arguments

Method to_list()

Return a serializable representation.

Usage

MemoryProposal$to_list()

Method print()

Print a compact summary.

Usage

MemoryProposal$print(...)

Arguments

Method clone()

The objects of this class are cloneable with this method.

Usage

MemoryProposal$clone(deep = FALSE)

Arguments

MemoryProposalState

Description

MemoryProposalState

MemoryProposalState

Details

State container for approved memory schema plus candidate proposals.

Public fields

Methods

Public methods

• MemoryProposalState$new()

• MemoryProposalState$validate()

• MemoryProposalState$add_proposal()

• MemoryProposalState$get_proposal()

• MemoryProposalState$list_proposals()

• MemoryProposalState$discuss_proposal()

• MemoryProposalState$approve_proposal()

• MemoryProposalState$reject_proposal()

• MemoryProposalState$approved_spec()

• MemoryProposalState$as_list()

• MemoryProposalState$clone()

Method new()

Create a memory proposal state container.

Usage

MemoryProposalState$new(
  approved_memory_spec = MemorySpec$new(),
  proposals = list(),
  history = list()
)

Arguments

Method validate()

Validate the state object.

Usage

MemoryProposalState$validate()

Method add_proposal()

Add a proposal.

Usage

MemoryProposalState$add_proposal(proposal)

Arguments

Method get_proposal()

Return one proposal.

Usage

MemoryProposalState$get_proposal(proposal_id)

Arguments

Method list_proposals()

List proposals with optional status filtering.

Usage

MemoryProposalState$list_proposals(status = NULL)

Arguments

Method discuss_proposal()

Discuss one proposal.

Usage

MemoryProposalState$discuss_proposal(proposal_id, note, source = "human")

Arguments

Method approve_proposal()

Approve one proposal and replace the approved memory spec.

Usage

MemoryProposalState$approve_proposal(proposal_id, note = NULL)

Arguments

Method reject_proposal()

Reject one proposal.

Usage

MemoryProposalState$reject_proposal(proposal_id, note = NULL)

Arguments

Method approved_spec()

Return the approved memory specification.

Usage

MemoryProposalState$approved_spec()

Method as_list()

Return a serializable representation.

Usage

MemoryProposalState$as_list()

Method clone()

The objects of this class are cloneable with this method.

Usage

MemoryProposalState$clone(deep = FALSE)

Arguments

MemorySpec

Description

MemorySpec

MemorySpec

Details

First-class memory schema for an agent design. MemorySpec records which memory fields exist, what type of memory they represent, how they persist across cold-start runs, and how they are expected to update. It can also carry an optional graph-shaped representation of memory relationships.

Methods

⁠$initialize(fields = list(), graph = NULL, metadata = list())⁠

Create a memory specification.

⁠$add_field(field)⁠

Add one memory field.

⁠$get_field(id)⁠

Return one memory field by id.

⁠$list_fields(memory_type = NULL, persistence = NULL)⁠

Return memory fields, optionally filtered.

⁠$validate()⁠

Validate the memory specification.

⁠$to_list()⁠

Return a serializable list.

⁠$print(...)⁠

Print a compact summary.

Public fields

Methods

Public methods

• MemorySpec$new()

• MemorySpec$add_field()

• MemorySpec$get_field()

• MemorySpec$list_fields()

• MemorySpec$validate()

• MemorySpec$to_list()

• MemorySpec$print()

• MemorySpec$clone()

Method new()

Create a memory specification.

Usage

MemorySpec$new(fields = list(), graph = NULL, metadata = list())

Arguments

Method add_field()

Add one memory field.

Usage

MemorySpec$add_field(field)

Arguments

Method get_field()

Return one memory field by id.

Usage

MemorySpec$get_field(id)

Arguments

Method list_fields()

Return memory fields, optionally filtered by type or persistence policy.

Usage

MemorySpec$list_fields(memory_type = NULL, persistence = NULL)

Arguments

Method validate()

Validate the memory specification.

Usage

MemorySpec$validate()

Method to_list()

Return a serializable list.

Usage

MemorySpec$to_list()

Method print()

Print a compact memory schema summary.

Usage

MemorySpec$print(...)

Arguments

Method clone()

The objects of this class are cloneable with this method.

Usage

MemorySpec$clone(deep = FALSE)

Arguments

PGConfig

Description

PGConfig

PGConfig

Details

Configuration for the Perception & Grounding subsystem.

Methods

⁠$initialize(enabled = TRUE, planning_mode = "task_decomposition", decomposition_style = "dag", metadata = list())⁠

Create a Perception & Grounding config. Legacy field names are preserved for compatibility.

⁠$validate()⁠

Validate the config.

⁠$as_list()⁠

Return a serializable representation.

Public fields

Methods

Public methods

• PGConfig$new()

• PGConfig$validate()

• PGConfig$as_list()

• PGConfig$print()

• PGConfig$clone()

Method new()

Create a Perception & Grounding config.

Usage

PGConfig$new(
  enabled = TRUE,
  planning_mode = "task_decomposition",
  decomposition_style = "dag",
  metadata = list()
)

Arguments

Method validate()

Validate the config.

Usage

PGConfig$validate()

Method as_list()

Return a serializable representation.

Usage

PGConfig$as_list()

Method print()

Print a compact config summary.

Usage

PGConfig$print(...)

Arguments

Method clone()

The objects of this class are cloneable with this method.

Usage

PGConfig$clone(deep = FALSE)

Arguments

RWMConfig

Description

RWMConfig

RWMConfig

Details

Configuration for the Reasoning & World Model subsystem.

Methods

⁠$initialize(cognitive = CognitiveConfig$new(), affective = NULL, persistence = "session", summary = NULL, metadata = list())⁠

Create a Reasoning & World Model config.

⁠$validate()⁠

Validate the config.

⁠$selected_layers()⁠

Return the active inner layers.

⁠$as_list()⁠

Return a serializable representation.

Public fields

Methods

Public methods

• RWMConfig$new()

• RWMConfig$validate()

• RWMConfig$selected_layers()

• RWMConfig$as_list()

• RWMConfig$print()

• RWMConfig$clone()

Method new()

Create an RWM config.

Usage

RWMConfig$new(
  cognitive = CognitiveConfig$new(),
  affective = NULL,
  persistence = "session",
  summary = NULL,
  metadata = list()
)

Arguments

Method validate()

Validate the config.

Usage

RWMConfig$validate()

Method selected_layers()

Return the active inner layers.

Usage

RWMConfig$selected_layers()

Method as_list()

Return a serializable representation.

Usage

RWMConfig$as_list()

Method print()

Print a compact config summary.

Usage

RWMConfig$print(...)

Arguments

Method clone()

The objects of this class are cloneable with this method.

Usage

RWMConfig$clone(deep = FALSE)

Arguments

Scaffolder

Description

Scaffolder

Scaffolder

Details

Human-in-the-loop scaffolding interface for iterative workflow elicitation. A Scaffolder keeps a persistent task-evaluation artifact, supports free-form discussion rounds before structured graph edits, separates workflow-level and node-level review, treats node/edge edits as first-class operations, and manages previewable workflow proposals with explicit lifecycle state.

Methods

⁠$initialize(agent = NULL, completion_threshold = 0.75)⁠

Create a scaffolder with empty workflow state and review metadata.

⁠$evaluate_task(task, summary = NULL, workflow_complete = NA, blockers = NULL, next_focus = NULL)⁠

Create or refresh the persistent task-evaluation artifact.

⁠$discuss_task(feedback, source = "human", node_id = NULL, confidence = NA_real_)⁠

Record a free-form human, model, or system discussion round.

⁠$decompose_task(task = self$task, candidates = NULL, suggestions = NULL, nodes = NULL, edges = NULL, notes = NULL)⁠

Create or replace the workflow from linear candidates or non-linear graph suggestions.

⁠$ask_human_complete(node_id)⁠

Create a prompt asking whether a workflow node is complete.

⁠$ask_human_changes()⁠

Create a prompt asking what workflow or edge changes should happen next.

⁠$ask_human_rule(node_id)⁠

Create a prompt requesting a node-specific rule.

⁠$review_workflow(status = "pending", notes = NULL, confidence = NA_real_)⁠

Store workflow-level completeness or revision review state.

⁠$review_node(node_id, status = "pending", notes = NULL, confidence = NA_real_, complete = NULL)⁠

Store node-level correctness or completion review state.

⁠$edit_workflow(add = NULL, insert = NULL, remove = NULL, add_edges = NULL, remove_edges = NULL, rule_specs = list(), confidence = list())⁠

Apply first-class node and edge edits to the current workflow.

⁠$set_node_schema(node_id, input_schema = NULL, output_schema = NULL)⁠

Set input/output schema metadata for one workflow node.

⁠$set_node_nested_workflow(node_id, subworkflow_ref = NULL, nested_workflow = NULL)⁠

Attach a nested workflow reference or embedded nested workflow to one node.

⁠$apply_human_feedback(completeness = NULL, add = NULL, remove = NULL, rule_specs = list(), confidence = list())⁠

Compatibility wrapper for structured human workflow edits.

⁠$recommend_subsystems(task = self$task)⁠

Recommend optional subsystem/capability labels for the current task and workflow.

⁠$subsystem_recommendations()⁠

Return the current subsystem recommendation records.

⁠$subsystem_recommendation_rationale(subsystem = NULL)⁠

Return stored recommendation rationale for one subsystem or all subsystems.

⁠$select_subsystems(subsystems)⁠

Store the selected subsystem configuration.

⁠$selected_subsystems()⁠

Return the currently selected subsystem names.

⁠$label_workflow_subsystems(labels)⁠

Assign subsystem owners to workflow nodes.

⁠$edit_workflow_subsystems(set = NULL, add = NULL, remove = NULL, clear = NULL)⁠

Edit workflow-node subsystem ownership incrementally.

⁠$propose_agent_spec(agent_name = "agentr-agent", summary = NULL, subsystems = NULL, workflow = NULL, workflow_proposal_id = NULL, state_requirements = list(), interfaces = list(), implementation_targets = list(), metadata = list(), source = "model", notes = NULL)⁠

Store a draft agent-spec proposal.

⁠$list_agent_spec_proposals(status = NULL)⁠

Return stored agent-spec proposal summaries.

⁠$get_agent_spec_proposal(proposal_id)⁠

Return a stored agent-spec proposal by id.

⁠$discuss_agent_spec_proposal(proposal_id, feedback, source = "human", confidence = NA_real_)⁠

Attach discussion feedback to a draft agent-spec proposal.

⁠$approve_agent_spec_proposal(proposal_id, approve_linked_workflow = TRUE)⁠

Approve a stored agent-spec proposal and optionally approve its linked workflow proposal.

⁠$approve_agent_spec(agent_name = "agentr-agent", summary = NULL, state_requirements = list(), interfaces = list(), implementation_targets = list(), metadata = list())⁠

Approve an AgentSpec built from the current task, workflow, and optional subsystem labels.

⁠$agent_spec()⁠

Return the approved agent spec or a draft spec built from current state.

⁠$propose_workflow(workflow, source = "model", notes = NULL)⁠

Store a pending workflow proposal for preview and review.

⁠$list_workflow_proposals(status = NULL)⁠

Return a summary table of stored workflow proposals.

⁠$get_workflow_proposal(proposal_id)⁠

Return a stored WorkflowProposal object by identifier.

⁠$approve_workflow_proposal(proposal_id)⁠

Promote a stored workflow proposal to the live workflow and supersede older active proposals when applicable.

⁠$discuss_workflow_proposal(proposal_id, feedback, source = "human", confidence = NA_real_)⁠

Attach free-form discussion feedback to a non-approved workflow proposal and transition it into discussion state when needed.

⁠$workflow_spec()⁠

Validate and return the current workflow specification.

⁠$implementation_spec()⁠

Return an implementation-facing summary of workflow nodes and rules.

⁠$low_confidence_nodes()⁠

Return workflow nodes below the completion threshold.

⁠$get_node(node_id)⁠

Return a single workflow node by identifier.

⁠$record_interaction(type, payload)⁠

Append an interaction event to the scaffolder log.

Public fields

Methods

Public methods

• Scaffolder$new()

• Scaffolder$evaluate_task()

• Scaffolder$discuss_task()

• Scaffolder$decompose_task()

• Scaffolder$ask_human_complete()

• Scaffolder$ask_human_changes()

• Scaffolder$ask_human_rule()

• Scaffolder$review_workflow()

• Scaffolder$review_node()

• Scaffolder$edit_workflow()

• Scaffolder$set_node_schema()

• Scaffolder$set_node_nested_workflow()

• Scaffolder$apply_human_feedback()

• Scaffolder$recommend_subsystems()

• Scaffolder$subsystem_recommendations()

• Scaffolder$subsystem_recommendation_rationale()

• Scaffolder$select_subsystems()

• Scaffolder$selected_subsystems()

• Scaffolder$label_workflow_subsystems()

• Scaffolder$edit_workflow_subsystems()

• Scaffolder$propose_agent_spec()

• Scaffolder$list_agent_spec_proposals()

• Scaffolder$get_agent_spec_proposal()

• Scaffolder$discuss_agent_spec_proposal()

• Scaffolder$approve_agent_spec_proposal()

• Scaffolder$approve_agent_spec()

• Scaffolder$agent_spec()

• Scaffolder$propose_workflow()

• Scaffolder$list_workflow_proposals()

• Scaffolder$get_workflow_proposal()

• Scaffolder$approve_workflow_proposal()

• Scaffolder$discuss_workflow_proposal()

• Scaffolder$workflow_spec()

• Scaffolder$implementation_spec()

• Scaffolder$low_confidence_nodes()

• Scaffolder$get_node()

• Scaffolder$record_interaction()

• Scaffolder$clone()

Method new()

Create a Scaffolder with empty workflow, review, and discussion state.

Usage

Scaffolder$new(agent = NULL, completion_threshold = 0.75)

Arguments

Method evaluate_task()

Create or refresh the persistent task-evaluation artifact.

Usage

Scaffolder$evaluate_task(
  task,
  summary = NULL,
  workflow_complete = NA,
  blockers = NULL,
  next_focus = NULL
)

Arguments

Method discuss_task()

Record a free-form human, model, or system discussion round.

Usage

Scaffolder$discuss_task(
  feedback,
  source = "human",
  node_id = NULL,
  confidence = NA_real_
)

Arguments

Method decompose_task()

Replace the workflow with nodes and edges derived from task suggestions.

Usage

Scaffolder$decompose_task(
  task = self$task,
  candidates = NULL,
  suggestions = NULL,
  nodes = NULL,
  edges = NULL,
  notes = NULL
)

Arguments

Method ask_human_complete()

Build a prompt asking whether a node is complete.

Usage

Scaffolder$ask_human_complete(node_id)

Arguments

Method ask_human_changes()

Build a prompt asking what workflow or edge changes should happen next.

Usage

Scaffolder$ask_human_changes()

Method ask_human_rule()

Build a prompt asking for a node-specific rule.

Usage

Scaffolder$ask_human_rule(node_id)

Arguments

Method review_workflow()

Store workflow-level completeness or revision review state.

Usage

Scaffolder$review_workflow(
  status = "pending",
  notes = NULL,
  confidence = NA_real_
)

Arguments

Method review_node()

Store node-level review status, notes, confidence, and completion state.

Usage

Scaffolder$review_node(
  node_id,
  status = "pending",
  notes = NULL,
  confidence = NA_real_,
  complete = NULL
)

Arguments

Method edit_workflow()

Apply first-class node and edge edits to the current workflow.

Usage

Scaffolder$edit_workflow(
  add = NULL,
  insert = NULL,
  remove = NULL,
  add_edges = NULL,
  remove_edges = NULL,
  rule_specs = list(),
  confidence = list()
)

Arguments

Method set_node_schema()

Set structured input and output schema metadata for one workflow node.

Usage

Scaffolder$set_node_schema(node_id, input_schema = NULL, output_schema = NULL)

Arguments

Method set_node_nested_workflow()

Attach a nested workflow reference or embedded nested workflow to one node.

Usage

Scaffolder$set_node_nested_workflow(
  node_id,
  subworkflow_ref = NULL,
  nested_workflow = NULL
)

Arguments

Method apply_human_feedback()

Apply legacy structured human feedback to the workflow.

Usage

Scaffolder$apply_human_feedback(
  completeness = NULL,
  add = NULL,
  remove = NULL,
  rule_specs = list(),
  confidence = list()
)

Arguments

Method recommend_subsystems()

Recommend optional subsystem/capability labels for the current task and workflow.

Usage

Scaffolder$recommend_subsystems(task = self$task)

Arguments

Method subsystem_recommendations()

Return the current subsystem recommendation records.

Usage

Scaffolder$subsystem_recommendations()

Method subsystem_recommendation_rationale()

Return stored recommendation rationale.

Usage

Scaffolder$subsystem_recommendation_rationale(subsystem = NULL)

Arguments

Method select_subsystems()

Store the selected subsystem configuration.

Usage

Scaffolder$select_subsystems(subsystems)

Arguments

Method selected_subsystems()

Return the currently selected subsystem names.

Usage

Scaffolder$selected_subsystems()

Method label_workflow_subsystems()

Assign subsystem owners to workflow nodes.

Usage

Scaffolder$label_workflow_subsystems(labels)

Arguments

Method edit_workflow_subsystems()

Edit workflow-node subsystem ownership incrementally.

Usage

Scaffolder$edit_workflow_subsystems(
  set = NULL,
  add = NULL,
  remove = NULL,
  clear = NULL
)

Arguments

Method propose_agent_spec()

Store a draft agent-spec proposal.

Usage

Scaffolder$propose_agent_spec(
  agent_name = "agentr-agent",
  summary = NULL,
  subsystems = NULL,
  workflow = NULL,
  workflow_proposal_id = NULL,
  state_requirements = list(),
  interfaces = list(),
  implementation_targets = list(),
  metadata = list(),
  source = "model",
  notes = NULL
)

Arguments

Method list_agent_spec_proposals()

Return stored agent-spec proposal summaries.

Usage

Scaffolder$list_agent_spec_proposals(status = NULL)

Arguments

Method get_agent_spec_proposal()

Return a stored agent-spec proposal by id.

Usage

Scaffolder$get_agent_spec_proposal(proposal_id)

Arguments

Method discuss_agent_spec_proposal()

Attach discussion feedback to a draft agent-spec proposal.

Usage

Scaffolder$discuss_agent_spec_proposal(
  proposal_id,
  feedback,
  source = "human",
  confidence = NA_real_
)

Arguments

Method approve_agent_spec_proposal()

Approve a stored agent-spec proposal and optionally approve its linked workflow proposal.

Usage

Scaffolder$approve_agent_spec_proposal(
  proposal_id,
  approve_linked_workflow = TRUE
)

Arguments

Method approve_agent_spec()

Approve an agent spec built from the current scaffolding state.

Usage

Scaffolder$approve_agent_spec(
  agent_name = "agentr-agent",
  summary = NULL,
  state_requirements = list(),
  interfaces = list(),
  implementation_targets = list(),
  metadata = list()
)

Arguments

Method agent_spec()

Return the approved agent spec or a draft spec built from current state.

Usage

Scaffolder$agent_spec()

Method propose_workflow()

Store a pending workflow proposal for preview and review.

Usage

Scaffolder$propose_workflow(workflow, source = "model", notes = NULL)

Arguments

Method list_workflow_proposals()

Return a summary table of stored workflow proposals.

Usage

Scaffolder$list_workflow_proposals(status = NULL)

Arguments

Method get_workflow_proposal()

Return a stored WorkflowProposal object by identifier.

Usage

Scaffolder$get_workflow_proposal(proposal_id)

Arguments

Method approve_workflow_proposal()

Promote a stored workflow proposal to the live workflow and supersede older active proposals when applicable.

Usage

Scaffolder$approve_workflow_proposal(proposal_id)

Arguments

Method discuss_workflow_proposal()

Attach free-form discussion feedback to a non-approved workflow proposal and transition it into discussion state when needed.

Usage

Scaffolder$discuss_workflow_proposal(
  proposal_id,
  feedback,
  source = "human",
  confidence = NA_real_
)

Arguments

Method workflow_spec()

Validate and return the current workflow specification.

Usage

Scaffolder$workflow_spec()

Method implementation_spec()

Return an implementation-facing summary of workflow nodes and rules.

Usage

Scaffolder$implementation_spec()

Method low_confidence_nodes()

Return workflow nodes whose confidence falls below the completion threshold.

Usage

Scaffolder$low_confidence_nodes()

Method get_node()

Return a single workflow node by identifier.

Usage

Scaffolder$get_node(node_id)

Arguments

Method record_interaction()

Append an interaction record to the scaffolder log.

Usage

Scaffolder$record_interaction(type, payload)

Arguments

Method clone()

The objects of this class are cloneable with this method.

Usage

Scaffolder$clone(deep = FALSE)

Arguments

SubsystemSpec

Description

SubsystemSpec

SubsystemSpec

Details

Sparse diagnostic inventory of the selected agent subsystems.

Methods

⁠$initialize(rwm = NULL, pg = NULL, ae = NULL, iac = NULL, la = NULL, metadata = list())⁠

Create an optional subsystem diagnostic inventory.

⁠$validate()⁠

Validate the subsystem diagnostic labels.

⁠$selected_subsystems()⁠

Return the selected subsystem names.

⁠$persistence_requirements()⁠

Return persistence requirements for selected subsystems.

⁠$communication_requirements()⁠

Return communication requirements for selected subsystems.

⁠$summary()⁠

Return a one-row summary table.

⁠$as_list()⁠

Return a serializable representation.

Public fields

Methods

Public methods

• SubsystemSpec$new()

• SubsystemSpec$validate()

• SubsystemSpec$selected_subsystems()

• SubsystemSpec$persistence_requirements()

• SubsystemSpec$communication_requirements()

• SubsystemSpec$summary()

• SubsystemSpec$as_list()

• SubsystemSpec$print()

• SubsystemSpec$clone()

Method new()

Create an optional subsystem diagnostic inventory.

Usage

SubsystemSpec$new(
  rwm = NULL,
  pg = NULL,
  ae = NULL,
  iac = NULL,
  la = NULL,
  metadata = list()
)

Arguments

Method validate()

Validate the subsystem diagnostic labels.

Usage

SubsystemSpec$validate()

Method selected_subsystems()

Return the selected subsystem names.

Usage

SubsystemSpec$selected_subsystems()

Method persistence_requirements()

Return persistence requirements for selected subsystems.

Usage

SubsystemSpec$persistence_requirements()

Method communication_requirements()

Return communication requirements for selected subsystems.

Usage

SubsystemSpec$communication_requirements()

Method summary()

Return a one-row summary table.

Usage

SubsystemSpec$summary()

Method as_list()

Return a serializable representation.

Usage

SubsystemSpec$as_list()

Method print()

Print a compact subsystem summary.

Usage

SubsystemSpec$print(...)

Arguments

Method clone()

The objects of this class are cloneable with this method.

Usage

SubsystemSpec$clone(deep = FALSE)

Arguments

WorkflowProposal

Description

WorkflowProposal

WorkflowProposal

Details

Public workflow proposal object with explicit lifecycle state and persistence helpers.

Methods

⁠$initialize(...)⁠

Create a workflow proposal object.

⁠$validate()⁠

Validate the proposal state and embedded workflow.

⁠$as_list()⁠

Return the proposal as a serializable proposal record.

⁠$summary()⁠

Return a one-row summary data frame.

⁠$transition(to_status, timestamp = Sys.time(), superseded_by = NULL, supersedes = NULL)⁠

Apply a valid lifecycle transition.

⁠$discuss(feedback, source = "human", confidence = NA_real_, timestamp = Sys.time())⁠

Append a discussion round and transition into discussion state when needed.

⁠$graph_data()⁠

Export graph-ready data from the proposed workflow.

⁠$save(file_path)⁠

Save the proposal to disk.

Public fields

Methods

Public methods

• WorkflowProposal$new()

• WorkflowProposal$validate()

• WorkflowProposal$as_list()

• WorkflowProposal$summary()

• WorkflowProposal$transition()

• WorkflowProposal$discuss()

• WorkflowProposal$graph_data()

• WorkflowProposal$save()

• WorkflowProposal$clone()

Method new()

Create a WorkflowProposal.

Usage

WorkflowProposal$new(
  id,
  workflow,
  status = "pending",
  source = "model",
  notes = NULL,
  discussion_rounds = list(),
  created_at = Sys.time(),
  updated_at = created_at,
  approved_at = as.POSIXct(NA),
  superseded_by = NA_character_,
  supersedes = NA_character_,
  rejected_at = as.POSIXct(NA)
)

Arguments

Method validate()

Validate the proposal.

Usage

WorkflowProposal$validate()

Method as_list()

Return a serializable proposal record.

Usage

WorkflowProposal$as_list()

Method summary()

Return a one-row proposal summary.

Usage

WorkflowProposal$summary()

Method transition()

Apply a valid lifecycle transition.

Usage

WorkflowProposal$transition(
  to_status,
  timestamp = Sys.time(),
  superseded_by = NULL,
  supersedes = NULL
)

Arguments

Method discuss()

Append a discussion round to the proposal.

Usage

WorkflowProposal$discuss(
  feedback,
  source = "human",
  confidence = NA_real_,
  timestamp = Sys.time()
)

Arguments

Method graph_data()

Export graph-ready proposal workflow data.

Usage

WorkflowProposal$graph_data()

Method save()

Save the proposal to disk.

Usage

WorkflowProposal$save(file_path)

Arguments

Method clone()

The objects of this class are cloneable with this method.

Usage

WorkflowProposal$clone(deep = FALSE)

Arguments

WorkflowProposalState

Description

WorkflowProposalState

WorkflowProposalState

Details

Public state container for the approved workflow plus stored workflow proposals.

Methods

⁠$initialize(approved_workflow = new_workflow_spec(...), proposals = list())⁠

Create a workflow proposal state container.

⁠$set_approved_workflow(workflow)⁠

Replace the approved workflow.

⁠$add_proposal(proposal)⁠

Store a proposal object.

⁠$get_proposal(proposal_id)⁠

Return a stored proposal by id.

⁠$list_proposals(status = NULL)⁠

Return a summary table of proposals.

⁠$latest_proposal()⁠

Return the latest stored proposal or NULL.

⁠$active_proposals()⁠

Return active proposal objects.

⁠$proposal_history()⁠

Return proposal history in insertion order.

⁠$approve_proposal(proposal_id, timestamp = Sys.time())⁠

Approve a proposal, update the approved workflow, and supersede older active proposals.

⁠$as_list()⁠

Return a serializable state snapshot.

Public fields

Methods

Public methods

• WorkflowProposalState$new()

• WorkflowProposalState$set_approved_workflow()

• WorkflowProposalState$add_proposal()

• WorkflowProposalState$get_proposal()

• WorkflowProposalState$list_proposals()

• WorkflowProposalState$latest_proposal()

• WorkflowProposalState$active_proposals()

• WorkflowProposalState$proposal_history()

• WorkflowProposalState$approve_proposal()

• WorkflowProposalState$as_list()

• WorkflowProposalState$clone()

Method new()

Create a WorkflowProposalState.

Usage

WorkflowProposalState$new(
  approved_workflow = new_workflow_spec(nodes = .empty_workflow_nodes(), edges =
    .empty_workflow_edges(), task = NULL, metadata = list(evaluation = NULL,
    workflow_review = NULL, discussion_rounds = list())),
  proposals = list()
)

Arguments

Method set_approved_workflow()

Replace the approved workflow.

Usage

WorkflowProposalState$set_approved_workflow(workflow)

Arguments

Method add_proposal()

Store a proposal object.

Usage

WorkflowProposalState$add_proposal(proposal)

Arguments

Method get_proposal()

Return a stored proposal by id.

Usage

WorkflowProposalState$get_proposal(proposal_id)

Arguments

Method list_proposals()

Return proposal summary rows.

Usage

WorkflowProposalState$list_proposals(status = NULL)

Arguments

Method latest_proposal()

Return the latest proposal or NULL.

Usage

WorkflowProposalState$latest_proposal()

Method active_proposals()

Return active proposals.

Usage

WorkflowProposalState$active_proposals()

Method proposal_history()

Return proposal history.

Usage

WorkflowProposalState$proposal_history()

Method approve_proposal()

Approve a stored proposal and supersede older active proposals.

Usage

WorkflowProposalState$approve_proposal(proposal_id, timestamp = Sys.time())

Arguments

Method as_list()

Return a serializable state snapshot.

Usage

WorkflowProposalState$as_list()

Method clone()

The objects of this class are cloneable with this method.

Usage

WorkflowProposalState$clone(deep = FALSE)

Arguments

Add a child task to a task-family workflow

Description

Add a child task to a task-family workflow

Usage

add_child_task_node(workflow, node, tags = character())

Arguments

Value

Updated task-family workflow.

Return standard agentr workspace paths

Description

Return standard agentr workspace paths

Usage

agentr_workspace_paths(workspace)

Arguments

Value

Named list of workspace paths.

Append a decision trace

Description

Append a decision trace

Usage

append_decision_trace(trace, path)

Arguments

Value

Invisibly returns TRUE.

Append a reflection trace

Description

Append a reflection trace

Usage

append_reflection_trace(trace, path)

Arguments

Value

Invisibly returns TRUE.

Apply structured design feedback

Description

Applies feedback through existing scaffolder review/discussion mechanisms when a scaffolder is supplied. Non-workflow feedback is preserved as structured design discussion metadata; it is not auto-executed.

Usage

apply_design_feedback(x, feedback, review_spec = NULL)

Arguments

Value

The mutated Scaffolder object.

Apply an initial LLM response into a workspace proposal state

Description

Apply an initial LLM response into a workspace proposal state

Usage

apply_initial_spec_message(
  workspace,
  target = c("workflow", "agent", "memory", "knowledge"),
  message,
  comment = NULL
)

Arguments

Value

Mutated state object.

Apply a knowledge message

Description

Apply a knowledge message

Usage

apply_knowledge_message(state, message)

Arguments

Value

Mutated state object.

Apply a memory message

Description

Apply a memory message

Usage

apply_memory_message(state, message)

Arguments

Value

Mutated state object.

Apply a node-detail LLM response into a workspace workflow proposal

Description

This is a convenience wrapper for apply_revision_message(target = "workflow", node_id = ...). It previews the proposed node schema or nested workflow edits and stores them as a workflow proposal; approved workflow state is not mutated until the proposal is explicitly approved.

Usage

apply_node_detail_message(workspace, node_id, message, agent_spec_path = NULL)

Arguments

Value

Preview result.

Apply a revision LLM response into a workspace proposal state

Description

Workflow revisions are previewed and stored as proposals; approved specs are not mutated by this function.

Usage

apply_revision_message(
  workspace,
  target = c("workflow", "agent", "memory", "knowledge"),
  message,
  agent_spec_path = NULL,
  node_id = NULL
)

Arguments

Value

Mutated state object or preview result.

Apply a machine-readable scaffolder message

Description

Parses and dispatches a machine-readable scaffolder message into concrete calls on a Scaffolder instance.

Usage

apply_scaffolder_message(
  scaffolder,
  message,
  allowed_methods = scaffolder_action_methods(),
  stop_on_error = TRUE
)

Arguments

Value

A standardized list with applied_actions, workflow_after, human_prompts, and errors.

Approve a workspace proposal

Description

Approve a workspace proposal

Usage

approve_workspace_proposal(
  workspace,
  type = c("workflow", "agent", "memory", "knowledge"),
  proposal_id,
  note = NULL,
  agent_spec_path = NULL
)

Arguments

Value

Approved proposal or spec object.

Build workflow specifications from article extraction JSON

Description

Converts the article-level JSON object produced from build_article_workflow_extraction_prompt() into one validated workflow specification per element of workflows.

Usage

article_workflow_specs_from_json(x)

Arguments

Value

A named list of validated workflow specifications.

Backup an agentr object with a timestamped filename

Description

Saves a timestamped backup of an agentr core object to a specified directory.

Usage

backup_agent(agent, dir)

Arguments

Value

Invisibly returns the backup file path.

Build an LLM prompt for agent design decisions

Description

Creates a prompt that targets subsystem-first agent design while keeping the workflow as a nested component inside the proposed agent specification.

Usage

build_agent_design_prompt(scaffolder, format = "json")

Arguments

Value

Character string prompt.

Build a workflow extraction prompt from an article

Description

Creates a prompt for a reasoning model to infer one or more agentr-compatible workflow specifications from an article describing agentic AI application cases, demonstrations, or methods.

Usage

build_article_workflow_extraction_prompt(
  article_context,
  article_title = NULL,
  task = NULL,
  case_names = NULL,
  extraction_mode = "both",
  format = "json",
  target_agent = "reasoning_model",
  extraction_goal =
    "Infer agentr workflow specs from article-described application cases.",
  constraints = character(),
  extra_context = list()
)

Arguments

Value

Character string prompt.

Build design-review data

Description

Packages an agent design and optional proposal states into a stable, JSON-ready review bundle. This prepares the data contract for a future JS/HTML review interface; it does not render a UI.

Usage

build_design_review_data(
  x = NULL,
  workflow = NULL,
  memory_spec = NULL,
  knowledge_spec = NULL,
  graph_spec = NULL,
  workflow_state = NULL,
  knowledge_state = NULL,
  memory_state = NULL,
  proposal_states = list(),
  review_id = .design_review_id(),
  metadata = list()
)

Arguments

Value

A DesignReviewSpec object.

Build an implementation prompt for a coding agent

Description

Creates a second-stage prompt that turns workflow scaffolding output into an implementation-oriented handoff for a coding assistant.

Usage

build_implementation_prompt(
  x,
  language,
  format = "json",
  target_agent = "coding_assistant",
  runtime = NULL,
  style = NULL,
  constraints = character(),
  extra_context = list(),
  include_knowledge = TRUE,
  knowledge_scope = c("referenced", "approved", "all")
)

Arguments

Value

Character string prompt.

Build an initial design prompt into a workspace

Description

Build an initial design prompt into a workspace

Usage

build_initial_spec_prompt(
  workspace,
  target = c("workflow", "agent", "memory", "knowledge"),
  comment,
  out = NULL,
  format = c("markdown", "json")
)

Arguments

Value

Output prompt path.

Build a knowledge conflict-check prompt

Description

Build a knowledge conflict-check prompt

Usage

build_knowledge_conflict_check_prompt(
  knowledge_spec = NULL,
  candidate,
  format = c("markdown", "json")
)

Arguments

Value

Prompt string.

Build a knowledge design prompt

Description

Build a knowledge design prompt

Usage

build_knowledge_design_prompt(knowledge_state, format = c("markdown", "json"))

Arguments

Value

Prompt string.

Build a knowledge elicitation prompt

Description

Build a knowledge elicitation prompt

Usage

build_knowledge_elicitation_prompt(
  context = NULL,
  format = c("markdown", "json")
)

Arguments

Value

Prompt string.

Build a knowledge normalization prompt

Description

Build a knowledge normalization prompt

Usage

build_knowledge_normalization_prompt(
  raw_statement,
  format = c("markdown", "json")
)

Arguments

Value

Prompt string.

Build a memory revision prompt

Description

Build a memory revision prompt

Usage

build_memory_revision_prompt(
  memory_state,
  feedback = NULL,
  format = c("markdown", "json")
)

Arguments

Value

Prompt string.

Build a memory schema prompt

Description

Build a memory schema prompt

Usage

build_memory_schema_prompt(
  context = NULL,
  current_memory = NULL,
  format = c("markdown", "json")
)

Arguments

Value

Prompt string.

Build a node-detail revision prompt

Description

Creates a constrained prompt for revising only one workflow node's interface schema or nested workflow detail. The expected response uses set_node_schema() and/or set_node_nested_workflow() actions.

Usage

build_node_detail_prompt(
  workflow,
  node_id,
  include_nested_workflow = TRUE,
  feedback = NULL,
  format = c("json", "markdown")
)

Arguments

Value

Character string prompt.

Build a revision prompt into a workspace

Description

Build a revision prompt into a workspace

Usage

build_revision_prompt(
  workspace,
  target = c("workflow", "agent", "memory", "knowledge"),
  comment,
  out = NULL,
  agent_spec_path = NULL,
  node_id = NULL,
  format = c("markdown", "json")
)

Arguments

Value

Output prompt path.

Build an LLM prompt for scaffolding decisions

Description

Creates a prompt that describes the scaffolder's available methods, the task context, the current workflow state, and the required machine-readable JSON response format.

Usage

build_scaffolder_prompt(scaffolder, task = NULL, format = "json")

Arguments

Value

Character string prompt.

Build a workflow extraction prompt from existing code

Description

Creates a prompt for a reasoning model to infer an agentr-compatible workflow specification from ad hoc code, scripts, or module summaries that already exist.

Usage

build_workflow_extraction_prompt(
  code_context,
  task = NULL,
  language = NULL,
  format = "json",
  target_agent = "reasoning_model",
  extraction_goal = "Infer a workflow specification consistent with agentr.",
  constraints = character(),
  extra_context = list()
)

Arguments

Value

Character string prompt.

Build an implementation handoff prompt from workspace artifacts

Description

This creates a prompt for a coding assistant or implementation team. It does not execute the approved design.

Usage

build_workspace_implementation_prompt(
  workspace,
  agent_spec_path = NULL,
  out = NULL,
  language = "R",
  target_agent = "coding_assistant",
  runtime = NULL,
  style = NULL,
  constraints = character(),
  include_knowledge = TRUE,
  knowledge_scope = c("referenced", "approved", "all"),
  format = c("markdown", "json")
)

Arguments

Value

Output prompt path.

Create a child-task workflow node

Description

Creates a workflow node that represents one child task inside a parent task-family workflow. The child task can point to a saved workflow through subworkflow_ref and/or embed a reviewable nested_workflow.

Usage

child_task_node(
  id,
  label,
  subworkflow_ref = NA_character_,
  nested_workflow = NULL,
  input_schema = list(),
  output_schema = list(),
  human_required = TRUE,
  owner = "human",
  automation_status = "human_in_loop",
  target_automation_status = NA_character_,
  implementation_hint = NA_character_,
  rule_spec = NA_character_,
  knowledge_refs = character(),
  trace_required = NA
)

Arguments

Value

One-row workflow node data frame.

Collect human-facing questions from scaffolding output

Description

Extracts pending human questions from a standardized dispatch result or, if no dispatch result is supplied, from the scaffolder interaction log.

Usage

collect_scaffolder_questions(scaffolder, dispatch_result = NULL)

Arguments

Value

Data frame of human-facing prompts.

Combine two emotion values

Description

Combine two emotion values

Usage

combine_emotions(a, b, method = "geometric", w1 = 0.5, w2 = 0.5)

Arguments

Value

Numeric scalar.

Compute blended emotions from primary emotions

Description

Compute blended emotions from primary emotions

Usage

compute_blended_emotions(primary, method = "geometric")

Arguments

Value

Named list of blended emotions.

Create a decision trace

Description

Create a decision trace

Usage

create_decision_trace(
  trace_id,
  agent_id,
  workflow_node_id,
  context = list(),
  human_decision,
  rationale,
  outcome = NULL,
  reflection = NULL,
  candidate_knowledge_refs = character(),
  reusable_rule_candidate = TRUE
)

Arguments

Value

Trace list.

Create a reflection trace

Description

Create a reflection trace

Usage

create_reflection_trace(
  trace_id,
  agent_id,
  workflow_node_id,
  reflection,
  outcome = NULL
)

Arguments

Value

Trace list.

Apply time-based decay to an affective state

Description

Apply time-based decay to an affective state

Usage

decay_emotion_state(emotion_state, current_time = Sys.time())

Arguments

Value

Updated affective state list.

Create a default affective state

Description

Initializes a minimal affective state with Plutchik-style primary dimensions, an inertia factor, and a timestamp for time-based decay.

Usage

default_emotion_state(decay_rate = 0.98, inertia = 0.85)

Arguments

Value

A named list.

Create a randomized affective state

Description

Create a randomized affective state

Usage

define_random_emotion_state(
  total_intensity = 1,
  sparsity = 0,
  decay_rate = 0.98,
  inertia = 0.85
)

Arguments

Value

A named list.

Describe an affective state in natural language

Description

Describe an affective state in natural language

Usage

describe_emotional_state(
  emotion_state,
  threshold = 0.2,
  include_blended = TRUE,
  method = "geometric"
)

Arguments

Value

Character string.

Create a structured design-feedback item

Description

Feedback items are the machine-readable output expected from a future JS/HTML review layer. They are intentionally structured rather than free text so they can be routed into workflow, memory, or knowledge revision prompts.

Usage

design_feedback_item(
  target,
  field,
  issue,
  suggestion,
  severity = "medium",
  issue_type = "unclear",
  id = NULL,
  target_id = NULL,
  item_id = NA_character_,
  location = list(),
  status = "open",
  source = "human",
  created_at = Sys.time(),
  metadata = list()
)

Arguments

Value

A validated design-feedback item list.

Build standalone design-review HTML

Description

Creates a standalone, offline HTML/JavaScript review page from a design review bundle or supported design object. The page is review-only: it renders design artifacts and exports structured feedback JSON, but it does not run workflow nodes, call LLM providers, or mutate saved R objects.

Usage

design_review_html(
  x,
  include_workflow = TRUE,
  include_knowledge = TRUE,
  include_memory_schema = TRUE,
  include_feedback_panel = TRUE,
  self_contained = TRUE,
  title = NULL,
  graph_layout = c("grid", "layered", "swimlane", "process"),
  edge_style = c("curved", "straight", "orthogonal"),
  node_color_theme = c("default", "subsystems"),
  ...
)

Arguments

Value

HTML string.

Discover task-local spec files

Description

Discover task-local spec files

Usage

discover_task_specs(task_dir, docs_dir = "docs")

Arguments