Class Ai

constructor

• new Ai(): Ai

  Returns Ai

Readonlytool

agent

• agent(): AiAgent

  Open a reusable AI agent that maintains connection settings, an accumulated tool registry, an onTurn callback, and a running chatHistory across multiple sendMessage(...) calls. Each sendMessage dispatches through the same usage-gated pipeline as B.ai.call and auto-threads the user message and assistant response into the agent's chatHistory so subsequent calls continue the conversation.

  const tool = B.ai.tool.custom()
    .setName("add_1")
    .setDescription("adds one!")
    .setSchema({
      type: "object",
      properties: { a: { type: "integer" }, b: { type: "integer" } },
      required: ["a", "b"],
    })
    .setExecutor((args) => args.a + args.b + 1);
  
  const agent = B.ai.agent()
    .addTool(tool)
    .setProvider("anthropic")
    .setModel("claude-sonnet-4-5")
    .setSystemPrompt("You are a helpful assistant.");
  
  const r1 = agent.sendMessage("What is 2 + 3?");
  const r2 = agent.sendMessage("Now add 10 to that.");
  Copy

  Returns AiAgent

• agent<const Schemas extends readonly JSONSchema[]>(
      options: AiClientOptions<Schemas>,
  ): AiAgent

  Open a reusable AI agent pre-seeded from options. Equivalent to calling the no-arg agent() and then chaining the corresponding setters / addTool calls — every field on AiClientOptions is copied straight into the agent. After construction, the agent behaves identically to one built via the fluent setters: each sendMessage(...) dispatches through the same usage-gated pipeline as B.ai.call and threads the user message and assistant response into the running chatHistory.

  const tool = B.ai.tool.custom()
    .setName("add_1")
    .setDescription("adds one!")
    .setSchema({
      type: "object",
      properties: { a: { type: "integer" }, b: { type: "integer" } },
      required: ["a", "b"],
    })
    .setExecutor((args) => args.a + args.b + 1);
  
  const agent = B.ai.agent({
    provider: "anthropic",
    model: "claude-sonnet-4-5",
    systemPrompt: "You are a helpful assistant.",
    tools: [tool],
  });
  
  const r1 = agent.sendMessage("What is 2 + 3?");
  const r2 = agent.sendMessage("Now add 10 to that.");
  Copy

  Type Parameters

  • const Schemas extends readonly JSONSchema[]

  Parameters

  • options: AiClientOptions<Schemas>

    Initial agent settings. See AiClientOptions for the full shape.

  Returns AiAgent

call

• call<const Schemas extends readonly JSONSchema[]>(
      options: AiCallOptions<Schemas>,
  ): AiCallResult

  Sends a request to an AI provider and returns the response.

  The call is metered through the web-global AI usage gate under the tenant's Bluestep API key, with usage attributed to the calling user, the current operating Unit, the optional flag, the model, and the script that triggered the call. Pass an apiKey to bypass the proxy and call the provider directly with your own key (no metering).

  When an onTurn callback is supplied, the conversation continues for as many assistant↔user exchanges as the callback drives — analogous to a state-machine agent loop but owned by the script.

  The type parameter Schemas is inferred from the tools tuple's input_schema literals (preserved by the const modifier), so inline tool literals get a typed executor args parameter — typos in argument names and wrong-shape access fail at compile time, matching the safety of B.ai.tool.custom().

  Type Parameters

  • const Schemas extends readonly JSONSchema[]

  Parameters

  • options: AiCallOptions<Schemas>

    Call options. See AiCallOptions for the full shape.

  Returns AiCallResult