SubAgent Examples

View Source
repo_root = Path.expand("..", __DIR__)

deps =
  if File.exists?(Path.join(repo_root, "mix.exs")) do
    [{:ptc_runner, path: repo_root}, {:llm_client, path: Path.join(repo_root, "llm_client")}]
  else
    [{:ptc_runner, "~> 0.5.0"}]
  end

Mix.install(deps ++ [{:req_llm, "~> 1.0"}, {:kino, "~> 0.14"}], consolidate_protocols: false)

Setup

Add your API key in the Secrets panel (ss) for cloud models. Ollama works without a key.

# For testing locally and reloading the library
# IEx.Helpers.recompile()
api_key = System.get_env("LB_OPENROUTER_API_KEY") || System.get_env("OPENROUTER_API_KEY")
if api_key, do: System.put_env("OPENROUTER_API_KEY", api_key)
if(api_key, do: "API key configured", else: "No API key - Ollama only")
model_options =
  if Code.ensure_loaded?(LLMClient) do
    LLMClient.list_models()
    |> Enum.filter(& &1.available)
    |> Enum.map(&{&1.model_id, "#{&1.alias} - #{&1.description}"})
    |> Enum.sort_by(&elem(&1, 1))
  else
    [
      {"openrouter:anthropic/claude-haiku-4.5", "haiku - Claude Haiku 4.5"},
      {"openrouter:google/gemini-2.5-flash", "gemini - Gemini 2.5 Flash"},
      {"openrouter:deepseek/deepseek-chat-v3-0324", "deepseek - DeepSeek V3"}
    ]
  end

model_input = Kino.Input.select("Model", model_options)
model = Kino.Input.read(model_input)

my_llm =
  if Code.ensure_loaded?(LLMClient) do
    fn %{system: system, messages: messages} ->
      case LLMClient.generate_text(model, [%{role: :system, content: system} | messages], receive_timeout: 60_000) do
        {:ok, r} -> {:ok, r}
        error -> error
      end
    end
  else
    fn %{system: system, messages: messages} ->
      case ReqLLM.generate_text(model, [%{role: :system, content: system} | messages], receive_timeout: 30_000) do
        {:ok, r} -> {:ok, %{content: ReqLLM.Response.text(r), tokens: ReqLLM.Response.usage(r)}}
        error -> error
      end
    end
  end

"Ready: #{model}"

Output Modes

SubAgents support two output modes:

ModeUse WhenOutput
:jsonClassification, extraction, summarizationStructured JSON
:ptc_lisp (default)Computation, tool orchestration, multi-step reasoningPTC-Lisp program result

JSON Mode - Direct LLM Tasks

Use output: :json when the LLM can answer directly without computation:

alias PtcRunner.SubAgent
alias PtcRunner.SubAgent.Debug

review = "Great product, fast shipping! Would buy again."

{:ok, step} = SubAgent.run(
  "Classify as positive/negative/neutral with confidence 0.0-1.0: {{review}}",
  output: :json,
  signature: "(review :string) -> {sentiment :string, confidence :float}",
  context: %{review: review},
  llm: my_llm
)

Debug.print_trace(step, raw: true)
step.return

PTC-Lisp Mode - Computational Tasks

The default mode. The LLM writes a program to solve tasks that need accurate computation:

{:ok, step} = SubAgent.run(
  "How many r's are in raspberry?",
  llm: my_llm,
  max_turns: 1
)

Debug.print_trace(step, raw: true)
step.return

Execution Modes

max_turnsModeBehavior
1Single-shotOne LLM call, answer immediately
> 1 (default: 10)Multi-turnCan iterate, fix errors, explore data

Single-shot is faster and cheaper - use when the task is straightforward.

Multi-turn allows the LLM to inspect results with println, retry on errors, and call return when confident.

Signatures

Signatures define input/output types. They work with both output modes.

Format: (input1 :type, input2 :type) -> output_type

TypeExamples
:string, :int, :float, :boolPrimitives
{field :type, ...}Object with named fields
[element_type]List of elements
{:optional, :type}Optional field
# Input: two strings, Output: object with score and explanation
sig1 = "(text1 :string, text2 :string) -> {similarity :float, explanation :string}"

# Input: list of items, Output: object with categorized lists
sig2 = "(items [{name :string, price :float}]) -> {expensive [{name :string}], cheap [{name :string}]}"

# Output only (no inputs from context)
sig3 = "{count :int, items [:string]}"

:ok

Compiled SubAgents

Compile an agent once to derive reusable PTC-Lisp logic. Runs without further LLM calls:

agent = SubAgent.new(
  prompt: "Count r's in {{word}}",
  signature: "(word :string) -> :int"
)

{:ok, compiled} = SubAgent.compile(agent, llm: my_llm)

IO.puts("Compiled source:\n#{compiled.source}")
# Execute on multiple inputs - no LLM calls
words = ["strawberry", "raspberry", "program", "error"]

for word <- words do
  step = compiled.execute.(%{"word" => word})
  "#{word}: #{step.return}"
end

Working with Tools

Tools let agents fetch external data or perform actions:

expenses = [
  %{"id" => 1, "category" => "travel", "amount" => 450.00, "vendor" => "Airlines Inc"},
  %{"id" => 2, "category" => "food", "amount" => 32.50, "vendor" => "Cafe Luna"},
  %{"id" => 3, "category" => "travel", "amount" => 189.00, "vendor" => "Hotel Central"},
  %{"id" => 4, "category" => "office", "amount" => 299.99, "vendor" => "Tech Store"},
  %{"id" => 5, "category" => "food", "amount" => 28.00, "vendor" => "Deli Express"}
]

tools = %{
  "list-expenses" => {fn _ -> expenses end,
    signature: "() -> [{id :int, category :string, amount :float, vendor :string}]",
    description: "Returns all expense records"
  }
}

Kino.DataTable.new(expenses)
{:ok, step} = SubAgent.run(
  "What is the total travel expense?",
  tools: tools,
  signature: "{total :float}",
  llm: my_llm
)

Debug.print_trace(step, raw: true)
step.return

Interactive Query

question_input = Kino.Input.textarea("Question", default: "Show spending by category")
question = Kino.Input.read(question_input)

case SubAgent.run(question, tools: tools, llm: my_llm) do
  {:ok, step} ->
    Debug.print_trace(step)
    step.return

  {:error, step} ->
    Debug.print_trace(step)
    "Failed: #{step.fail.message}"
end

Debug Options

# Preview the prompt before running
agent = SubAgent.new(prompt: "What is 2 + 2?")
SubAgent.preview_prompt(agent).system |> IO.puts()

print_trace options:

OptionDescription
raw: trueShow raw LLM input/output
messages: trueShow all messages including system prompt
usage: trueShow token usage
view: :compressedShow what LLM sees (compressed format)

Learn More