const agentDefinition = {
  id: "best-of-n-editor-gpt-5",
  displayName: "Best-of-N GPT-5 Implementation Editor",
  publisher: "codebuff",
  version: "0.0.1",
  model: "openai/gpt-5",
  toolNames: [
    "spawn_agents",
    "str_replace",
    "write_file",
    "set_messages",
    "set_output"
  ],
  spawnableAgents: [
    "codebuff/best-of-n-implementor-gpt-5@0.0.2",
    "codebuff/best-of-n-selector-gpt-5@0.0.2"
  ],
  inputSchema: {
    params: {
      type: "object",
      properties: {
        n: {
          type: "number",
          description: "Number of parallel implementor agents to spawn. Defaults to 5. Use fewer for simple tasks and max of 10 for complex tasks."
        }
      }
    }
  },
  includeMessageHistory: true,
  outputMode: "structured_output",
  spawnerPrompt: `Edits code by orchestrating multiple implementor agents to generate implementation proposals, selects the best one, and applies the changes. Do not specify an input prompt for this agent; it reads the context from the message history.`,
  systemPrompt: ``,
  instructionsPrompt: ``,
  stepPrompt: ``,
  handleSteps: function* handleStepsGpt5({
  agentState,
  params
}) {
  const n = Math.min(10, Math.max(1, params?.n ?? 5)), messages = agentState.messageHistory.concat();
  messages.pop();
  yield {
    toolName: "set_messages",
    input: {
      messages
    },
    includeToolCall: !1
  };
  const { toolResult: implementorsResult1 } = yield {
    toolName: "spawn_agents",
    input: {
      agents: Array.from({ length: n }, () => ({
        agent_type: "best-of-n-implementor-gpt-5"
      }))
    },
    includeToolCall: !1
  }, implementorsResult = extractSpawnResults(implementorsResult1), letters = "ABCDEFGHIJKLMNOPQRSTUVWXYZ", implementations = implementorsResult.map((content, index) => ({
    id: letters[index],
    content
  })), { toolResult: selectorResult } = yield {
    toolName: "spawn_agents",
    input: {
      agents: [
        {
          agent_type: "best-of-n-selector-gpt-5",
          params: { implementations }
        }
      ]
    },
    includeToolCall: !1
  }, selectorOutput = extractSpawnResults(selectorResult)[0];
  if ("errorMessage" in selectorOutput) {
    yield {
      toolName: "set_output",
      input: { error: selectorOutput.errorMessage }
    };
    return;
  }
  const { implementationId } = selectorOutput, chosenImplementation = implementations.find((implementation) => implementation.id === implementationId);
  if (!chosenImplementation) {
    yield {
      toolName: "set_output",
      input: { error: "Failed to find chosen implementation." }
    };
    return;
  }
  const { agentState: postEditsAgentState } = yield {
    type: "STEP_TEXT",
    text: chosenImplementation.content
  }, { messageHistory } = postEditsAgentState, lastAssistantMessageIndex = messageHistory.findLastIndex((message) => message.role === "assistant"), editToolResults = messageHistory.slice(lastAssistantMessageIndex).filter((message) => message.role === "tool").flatMap((message) => message.content.output).filter((output) => output.type === "json").map((output) => output.value);
  yield {
    toolName: "set_output",
    input: {
      response: chosenImplementation.content,
      toolResults: editToolResults
    }
  };
  function extractSpawnResults(results) {
    if (!results)
      return [];
    return results.filter((result) => result.type === "json").map((result) => result.value).flat().map((result) => result.value.value ?? {
      errorMessage: result.value.errorMessage ?? "Error extracting spawn results"
    });
  }
},
  mcpServers: {},
  inheritParentSystemPrompt: true
}