defineAgent carries the agent’s LLM binding and its behavioral settings:
agents/qualifier.ts
Every agent needs both
connector and languageModel — defineAgent throws
at plan time if either is missing. The connector’s integration (OpenAI,
Anthropic, …) determines which model slugs are valid. A harness only accepts
connectors and models that list that runtime (Anthropic for Claude Code /
OpenCode / Deep Agents, OpenAI gpt-5* for Codex).Coding agents
A coding agent runs inside a sandbox with a clone of a project. Setharness to the runtime (claudeCode, codex, openCode, or deepAgents). state picks the project (deploy state) the sandbox clones: its state holds the repository, the project’s directory and its production branch.
Binding to this project
Omitstate and plan/deploy fill in the state this project’s cargo.state.json points at. No GitHub connector is involved: the agent clones, pushes and opens pull requests as the Cargo GitHub app, so the project’s repository must be connected.
connectors/anthropic.ts
agents/coder.ts
plan prints the state it bound (e.g. agent:coder bound to this project's state <uuid>), and the uuid is inside the content hash, so pointing the project at another state redeploys its agents. Pass state: stateRef("<uuid>") to work on another project instead. env adds environment variables for the agent’s shell commands on top of the workspace’s, and runAs is the service user whose temporary CARGO_API_TOKEN the sandbox receives.
Edge cases
Selecting a model
Theconnector handle picks the provider; languageModel picks the model slug within it. Cargo supports the leading LLM providers — OpenAI, Anthropic, and Google Gemini among them — each behind its own connector.
List the model slugs a provider currently exposes rather than hardcoding from memory:
Behavioral parameters
Reasoning steps (maxSteps)
The maximum number of logical sub-tasks the agent can perform to reach a conclusion. Defaults to 8.
Temperature
Controls the creativity and variability of outputs. Defaults to0.2.
Extended thinking (withReasoning)
withReasoning: true lets the model think through the problem before acting — better on hard multi-step tasks, at the cost of latency and tokens. Defaults to false.
Structured output
By default an agent answers in free text (output: { type: "text" }). To make every final answer machine-parseable — for workflows or API consumers downstream — declare a JSON Schema contract:
Evaluator
Theevaluator is an LLM-as-judge that scores each of the agent’s outputs against a natural-language rubric:
threshold are flagged, so you can spot quality regressions without reading every conversation. Pair it with prompt iterations: change the systemPrompt, re-deploy, and compare evaluator pass rates.
Triggers
Agents normally respond to messages, buttriggers make them start work on their own:
connector trigger references its connector by handle or connectorRef(uuid); config is integration-specific. agentConnectorTrigger types that config against the integration’s schema, which a bare object literal can’t do — TypeScript won’t infer a per-element type through an array. A defineConnector handle names its integration, so the helper reads it from there; pass integration: "slack" yourself when there’s no handle to read it from, either because you’re using connectorRef(uuid) or because the trigger names an integration with no specific connector.
A project’s pull requests are the native agent state, declared with agentNativeTrigger({ agentSlug: "state", config }). It is named after the project, not the host: the project’s state chooses where its code lives, and the trigger means “this project’s pull requests” wherever that is. It takes no connector: on GitHub, events arrive from the Cargo GitHub app installed on the repository, and the agent answers as the app. Its config takes allPullRequests, fixFailedChecks, maxCheckFixAttempts, addressReviews and resolveConflicts. agentConnectorTrigger no longer accepts github, so tsc flags a project that still declares it that way: switch it to agentNativeTrigger.
The bare form still works, with config left as a loose object:
Heartbeat
Aheartbeat wakes the agent up on an interval inside an ongoing chat — useful for long-running missions that should make progress without a human prompting each turn:
Optimizing for cost and speed
Once your agent works correctly, consider:- Reduce
maxStepsif tasks complete in fewer steps - Try a faster model and verify quality remains acceptable (the
evaluatorpass rate is the signal) - Lower
temperaturefor more predictable outputs - Limit resources to reduce context size and processing time

