Base macro for Graph-of-Thoughts-powered agents.
Wraps use Jido.Agent with Jido.AI.Reasoning.GraphOfThoughts.Strategy wired in,
plus standard state fields and helper functions.
Usage
defmodule MyApp.ResearchSynthesizer do
use Jido.AI.GoTAgent,
name: "research_synthesizer",
description: "Synthesizes research from multiple perspectives",
max_nodes: 30,
max_depth: 6,
aggregation_strategy: :synthesis
endOptions
:name(required) - Agent name:description- Agent description (default: "GoT agent #{name}"):model- Model alias or direct model spec (default: :fast, resolved via Jido.AI.resolve_model/1):max_nodes- Maximum number of nodes in the graph (default: 20):max_depth- Maximum depth of the graph (default: 5):aggregation_strategy-:voting,:weighted, or:synthesis(default::synthesis):generation_prompt- Custom prompt for thought generation:connection_prompt- Custom prompt for finding connections:aggregation_prompt- Custom prompt for aggregation:skills- Additional skills to attach to the agent (TaskSupervisorSkill is auto-included)
Generated Functions
explore/2,3- Async: sends prompt, returns{:ok, %Request{}}for later awaitingawait/1,2- Awaits a specific request's completionexplore_sync/2,3- Sync convenience: sends prompt and waits for resultstrategy_opts/0- Returns the strategy options for CLI accesson_before_cmd/2- Captures request in state before processingon_after_cmd/3- Updates request result when done
Request Tracking
Each explore/2 call returns a Request struct that can be awaited:
{:ok, request} = MyAgent.explore(pid, "Analyze the impact of AI on healthcare")
{:ok, result} = MyAgent.await(request, timeout: 30_000)Or use the synchronous convenience wrapper:
{:ok, result} = MyAgent.explore_sync(pid, "Analyze the impact of AI on healthcare")State Fields
The agent state includes:
:model- The LLM model being used:requests- Map of request_id => request state (for concurrent tracking):last_request_id- ID of the most recent request:last_prompt- The most recent prompt (backward compat):last_result- The final result from the last completed exploration (backward compat):completed- Boolean indicating if the last exploration is complete (backward compat)
Task Supervisor
Each agent instance gets its own Task.Supervisor automatically started via the
Jido.AI.Plugins.TaskSupervisor. This supervisor is used for:
- LLM streaming operations
- Other async operations within the agent's lifecycle
Example
{:ok, pid} = Jido.AgentServer.start(agent: MyApp.ResearchSynthesizer)
# Async pattern (preferred for concurrent requests)
{:ok, request} = MyApp.ResearchSynthesizer.explore(pid, "Analyze the impact of AI on healthcare")
{:ok, result} = MyApp.ResearchSynthesizer.await(request)
# Sync pattern (convenience for simple cases)
{:ok, result} = MyApp.ResearchSynthesizer.explore_sync(pid, "Analyze the impact of AI on healthcare")Aggregation Strategies
:voting- Selects the most common conclusion among thoughts:weighted- Weights thoughts by their scores when aggregating:synthesis- Synthesizes all thoughts into a coherent conclusion (default)