Learn R Programming

mini007 (version 0.2.2)

Agent: Agent: A General-Purpose LLM Agent

Description

The `Agent` class defines a modular LLM-based agent capable of responding to prompts using a defined role/instruction. It wraps an OpenAI-compatible chat model via the [`ellmer`](https://github.com/llrs/ellmer) package.

Each agent maintains its own message history and unique identity.

Arguments

Public fields

name

The agent's name.

instruction

The agent's role/system prompt.

llm_object

The underlying `ellmer::chat_openai` object.

agent_id

A UUID uniquely identifying the agent.

model_provider

The name of the entity providing the model (eg. OpenAI)

model_name

The name of the model to be used (eg. gpt-4.1-mini)

broadcast_history

A list of all past broadcast interactions.

budget

A budget in $ that the agent should not exceed.

budget_policy

A list controlling budget behavior: on_exceed and warn_at.

budget_warned

Internal flag indicating whether warn_at notice was emitted.

cost

The current cost of the agent

Active bindings

messages

Public active binding for the conversation history. Assignment is validated automatically.

Methods


Method new()

Initializes a new Agent with a specific role/instruction.

Usage

Agent$new(name, instruction, llm_object, budget = NA)

Arguments

name

A short identifier for the agent (e.g. `"translator"`).

instruction

The system prompt that defines the agent's role.

llm_object

The LLM object generate by ellmer (eg. output of ellmer::chat_openai)

budget

Numerical value denoting the amount to set for the budget in US$ to a specific agent, if the budget is reached, an error will be thrown.

Examples

  # An API KEY is required in order to invoke the Agent
  openai_4_1_mini <- ellmer::chat(
    name = "openai/gpt-4.1-mini",
    api_key = Sys.getenv("OPENAI_API_KEY"),
    echo = "none"
  )

polar_bear_researcher <- Agent$new( name = "POLAR BEAR RESEARCHER", instruction = paste0( "You are an expert in polar bears, ", "you task is to collect information about polar bears. Answer in 1 sentence max." ), llm_object = openai_4_1_mini )


Method invoke()

Sends a user prompt to the agent and returns the assistant's response.

Usage

Agent$invoke(prompt)

Arguments

prompt

A character string prompt for the agent to respond to.

Returns

The LLM-generated response as a character string.

Examples

\dontrun{
# An API KEY is required in order to invoke the Agent
openai_4_1_mini <- ellmer::chat(
    name = "openai/gpt-4.1-mini",
    api_key = Sys.getenv("OPENAI_API_KEY"),
    echo = "none"
)
agent <- Agent$new(
 name = "translator",
 instruction = "You are an Algerian citizen",
 llm_object = openai_4_1_mini
)
agent$invoke("Continue this sentence: 1 2 3 viva")
}


Method generate_execute_r_code()

Generate R code from natural language descriptions and optionally validate/execute it

Usage

Agent$generate_execute_r_code(
  code_description,
  validate = FALSE,
  execute = FALSE,
  interactive = TRUE,
  env = globalenv()
)

Arguments

code_description

Character string describing the R code to generate

validate

Logical indicating whether to validate the generated code syntax

execute

Logical indicating whether to execute the generated code (use with caution)

interactive

Logical; if TRUE, ask for user confirmation before executing generated code

env

Environment in which to execute the code if execute = TRUE. Default to globalenv

Returns

A list containing the generated code and validation/execution results

Examples

\dontrun{
openai_4_1_mini <- ellmer::chat(
  name = "openai/gpt-4.1-mini",
  api_key = Sys.getenv("OPENAI_API_KEY"),
  echo = "none"
)
r_assistant <- Agent$new(
  name = "R Code Assistant",
  instruction = paste("You are an expert R programmer",
  llm_object = openai_4_1_mini
)
# Generate code for data manipulation
result <- r_assistant$generate_execute_r_code(
  code_description = "Calculate the summary of the mtcars dataframe",
  validate = TRUE,
  execute = TRUE,
  interactive = TRUE
)
print(result)
}


Method set_budget()

Set a budget to a specific agent, if the budget is reached, an error will be thrown

Usage

Agent$set_budget(amount_in_usd)

Arguments

amount_in_usd

Numerical value denoting the amount to set for the budget,

Examples

\dontrun{
# An API KEY is required in order to invoke the Agent
openai_4_1_mini <- ellmer::chat(
    name = "openai/gpt-4.1-mini",
    api_key = Sys.getenv("OPENAI_API_KEY"),
    echo = "none"
)
agent <- Agent$new(
 name = "translator",
 instruction = "You are an Algerian citizen",
 llm_object = openai_4_1_mini
)
agent$set_budget(amount_in_usd = 10.5) # this is equivalent to 10.5$
}


Method set_budget_policy()

Configure how the agent behaves as it approaches or exceeds its budget. Use `warn_at` (0-1) to emit a one-time warning when spending reaches the specified fraction of the budget. When the budget is exceeded, `on_exceed` controls behavior: abort, warn and proceed, or ask interactively.

Usage

Agent$set_budget_policy(on_exceed = "abort", warn_at = 0.8)

Arguments

on_exceed

One of "abort", "warn", or "ask".

warn_at

Numeric in (0,1); fraction of budget to warn at. Default 0.8.

Examples

\dontrun{
agent$set_budget(5)
agent$set_budget_policy(on_exceed = "ask", warn_at = 0.9)
}


Method keep_last_n_messages()

Keep only the most recent `n` messages, discarding older ones while keeping the system prompt.

Usage

Agent$keep_last_n_messages(n = 2)

Arguments

n

Number of most recent messages to keep.

Examples

\dontrun{
openai_4_1_mini <- ellmer::chat(
  name = "openai/gpt-4.1-mini",
  api_key = Sys.getenv("OPENAI_API_KEY"),
  echo = "none"
)
agent <- Agent$new(
  name = "capital finder",
  instruction = "You are an assistant.",
  llm_object = openai_4_1_mini
)
agent$invoke("What is the capital of Algeria")
agent$invoke("What is the capital of Germany")
agent$invoke("What is the capital of Italy")
agent$keep_last_n_messages(n = 2)
}


Method add_message()

Add a pre-formatted message to the conversation history

Usage

Agent$add_message(role, content)

Arguments

role

The role of the message ("user", "assistant", or "system")

content

The content of the message

Examples

\dontrun{
openai_4_1_mini <- ellmer::chat(
  name = "openai/gpt-4.1-mini",
  api_key = Sys.getenv("OPENAI_API_KEY"),
  echo = "none"
)
agent <- Agent$new(
  name = "AI assistant",
  instruction = "You are an assistant.",
  llm_object = openai_4_1_mini
)
agent$add_message("user", "Hello, how are you?")
agent$add_message("assistant", "I'm doing well, thank you!")
}


Method clear_and_summarise_messages()

Summarises the agent's conversation history into a concise form and appends it to the system prompt. Unlike `update_instruction()`, this method does not override the existing instruction but augments it with a summary for future context.

After creating the summary, the method clears the conversation history and retains only the updated system prompt. This ensures that subsequent interactions start fresh but with the summary preserved as context.

Usage

Agent$clear_and_summarise_messages()

Examples

\dontrun{
  # Requires an OpenAI-compatible LLM from `ellmer`
  openai_4_1_mini <- ellmer::chat(
    name = "openai/gpt-4.1-mini",
    api_key = Sys.getenv("OPENAI_API_KEY"),
    echo = "none"
  )

agent <- Agent$new( name = "summariser", instruction = "You are a summarising assistant", llm_object = openai_4_1_mini )

agent$invoke("The quick brown fox jumps over the lazy dog.") agent$invoke("This is another example sentence.")

# Summarises and resets history agent$summarise_messages()

# Now only the system prompt (with summary) remains agent$messages }


Method update_instruction()

Update the system prompt/instruction

Usage

Agent$update_instruction(new_instruction)

Arguments

new_instruction

New instruction to use. Not that the new instruction will override the old one

Examples

\dontrun{
openai_4_1_mini <- ellmer::chat(
  name = "openai/gpt-4.1-mini",
  api_key = Sys.getenv("OPENAI_API_KEY"),
  echo = "none"
)
agent <- Agent$new(
  name = "assistant",
  instruction = "You are an assistant.",
  llm_object = openai_4_1_mini
)
agent$update_instruction("You are a concise assistant.")
}


Method get_usage_stats()

Get the current token count and estimated cost of the conversation

Usage

Agent$get_usage_stats()

Returns

A list with token counts and cost information

Examples

\dontrun{
openai_4_1_mini <- ellmer::chat(
  name = "openai/gpt-4.1-mini",
  api_key = Sys.getenv("OPENAI_API_KEY"),
  echo = "none"
)
agent <- Agent$new(
  name = "assistant",
  instruction = "You are an assistant.",
  llm_object = openai_4_1_mini
)
agent$set_budget(1)
agent$invoke("What is the capital of Algeria?")
stats <- agent$get_usage_stats()
stats
}


Method reset_conversation_history()

Reset the agent's conversation history while keeping the system instruction

Usage

Agent$reset_conversation_history()

Examples

\dontrun{
openai_4_1_mini <- ellmer::chat(
  name = "openai/gpt-4.1-mini",
  api_key = Sys.getenv("OPENAI_API_KEY"),
  echo = "none"
)
agent <- Agent$new(
  name = "AI assistant",
  instruction = "You are an assistant.",
  llm_object = openai_4_1_mini
)
agent$invoke("Hello, how are you?")
agent$invoke("Tell me about machine learning")
agent$reset_conversation_history()  # Clears all messages except system prompt
}


Method export_messages_history()

Saves the agent's current conversation history as a JSON file on disk.

Usage

Agent$export_messages_history(
  file_path = paste0(getwd(), "/", paste0(self$name, "_messages.json"))
)

Arguments

file_path

Character string specifying the file path where the JSON file should be saved. Defaults to a file named `"<agent_name>_messages.json"` in the current working directory.

Examples

\dontrun{
openai_4_1_mini <- ellmer::chat(
  name = "openai/gpt-4.1-mini",
  api_key = Sys.getenv("OPENAI_API_KEY"),
  echo = "none"
)
agent <- Agent$new(
  name = "capital_finder",
  instruction = "You are an assistant.",
  llm_object = openai_4_1_mini
)
agent$invoke("What is the capital of Algeria")
agent$invoke("What is the capital of Italy")
agent$export_messages_history()
}


Method load_messages_history()

Load an agent's conversation history as a JSON file from disk.

Usage

Agent$load_messages_history(
  file_path = paste0(getwd(), "/", paste0(self$name, "_messages.json"))
)

Arguments

file_path

Character string specifying the file path where the JSON file is stored. Defaults to a file named `"<agent_name>_messages.json"` in the current working directory.

Examples

\dontrun{
openai_4_1_mini <- ellmer::chat(
  name = "openai/gpt-4.1-mini",
  api_key = Sys.getenv("OPENAI_API_KEY"),
  echo = "none"
)
agent <- Agent$new(
  name = "capital_finder",
  instruction = "You are an assistant.",
  llm_object = openai_4_1_mini
)
# use the export_messages_history to save the interaction first
agent$load_messages_history("path/to/messages.json")
agent$messages
agent$llm_object
}


Method validate_response()

Validates an agent's response against custom criteria using LLM-based validation. This method uses the agent's LLM to evaluate whether a response meets specified validation criteria (e.g., accuracy, completeness, tone, format).

Usage

Agent$validate_response(
  prompt,
  response,
  validation_criteria,
  validation_score = 0.8
)

Arguments

prompt

The prompt used to generate the response.

response

The response text to validate.

validation_criteria

The criteria for validation. (e.g., "The response should be accurate and complete", "The response must be under 100 words").

validation_score

A numeric from 0 to 1 denoting the score to consider for the evaluation. During the evaluation, the agent will provide a score from 0 to 1, a provided score greater or equal to the `validation_score` will result in a `valid` response. Defaults to 0.8.

Returns

list object

Examples

\dontrun{
openai_4_1_mini <- ellmer::chat(
  name = "openai/gpt-4.1-mini",
  api_key = Sys.getenv("OPENAI_API_KEY"),
  echo = "none"
)
agent <- Agent$new(
  name = "fact_checker",
  instruction = "You are a factual assistant.",
  llm_object = openai_4_1_mini
)
prompt <- "What is the capital of Algeria?"
response <- agent$invoke(prompt)
validation <- agent$validate_response(
  response = response,
  prompt = prompt,
  validation_criteria = "The response must be accurate and mention Algiers",
  validation_score = 0.8
)
print(validation)
}


Method clone_agent()

Create a copy of the agent with the same instruction and configuration but a new unique ID. Useful for creating multiple instances of the same agent type.

Usage

Agent$clone_agent(new_name = NULL)

Arguments

new_name

Optional character string to assign a new name to the cloned agent. If NULL, the cloned agent retains the original name.

Returns

A new Agent instance with the same configuration but a unique ID.

Examples

\dontrun{
openai_4_1_mini <- ellmer::chat(
  name = "openai/gpt-4.1-mini",
  api_key = Sys.getenv("OPENAI_API_KEY"),
  echo = "none"
)
agent <- Agent$new(
  name = "translator",
  instruction = "You are a translator.",
  llm_object = openai_4_1_mini
)
# Clone with same name
agent_copy <- agent$clone_agent()
}


Method clone()

The objects of this class are cloneable with this method.

Usage

Agent$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.

See Also

[load_messages_history()] for reloading a saved message history.

[export_messages_history()] for exporting the messages object to json.