构建 agent harness：循环与五种退出方式

const SCRIPTS = {
  // A well-behaved task: list, read, answer.
  plan: (t) =>
    t === 0 ? asks(call("c1", "list_files", {}))
    : t === 1 ? asks(call("c2", "read_file", { path: "errors.log" }))
    : text("errors.log mentions a timeout: worker 7 timed out after 30000 ms."),

  // Never declares itself done.
  runaway: (t) => asks(call(`c${t}`, "list_files", {})),           

  // Guesses a file name, then corrects itself IF it was told what happened.
  recover: (t, all) =>
    t === 0 ? asks(call("c1", "read_file", { path: "timeout.log" }))
    : /Call list_files/.test(all)                                  
      ? (t === 1 ? asks(call("c2", "list_files", {}))
        : t === 2 ? asks(call("c3", "read_file", { path: "errors.log" }))
        : text("errors.log mentions a timeout."))
      : text("I could not read the file, so I do not know."),
};

const turn = messages.filter((m) => m.role === "assistant").length;             
const toolText = messages.filter((m) => m.role === "tool").map((m) => m.content).join("\n");
const message = SCRIPTS[scenario](turn, toolText);

while (true) {
  const reply = await callModel(base, messages, tools, signal);
  messages.push(reply.message);

  const calls = reply.message.tool_calls ?? [];
  if (!calls.length) return reply.message.content;          

  for (const c of calls) {
    const tool = byName.get(c.function.name);
    const result = await tool.run(JSON.parse(c.function.arguments));
    messages.push({ role: "tool", tool_call_id: c.id, name: c.function.name, content: result });
  }
}

plan, cap 20    turns=3  tools=2  in=815  out=70  cost=$0.002470  ms=89  status=completed
   answer: "errors.log mentions a timeout: worker 7 timed out after 30000 ms."
   per-turn prompt tokens: 204, 269, 342

const PRICE_IN = 2.0 / 1e6, PRICE_OUT = 12.0 / 1e6;
export const cost = (u: Usage) => u.prompt_tokens * PRICE_IN + u.completion_tokens * PRICE_OUT;

// at the top of every iteration, before asking the model anything:
if (state.turns >= opts.limits.maxTurns) return stop("max_turns_exceeded", { type: "max_turns" });
if (state.costUsd >= opts.limits.maxBudgetUsd) return stop("budget_exceeded", { type: "max_budget" }); 

// ...and once the reply is back, before anything else happens with it:
state.costUsd += cost(reply.usage);

export type RunStatus =
  | "running" | "completed" | "failed"
  | "max_turns_exceeded" | "budget_exceeded" | "interrupted";

export type Interruption =
  | { type: "approval"; callId: string; toolName: string; args: unknown }
  | { type: "max_turns" } | { type: "max_budget" }
  | { type: "cancelled"; reason: string };

} catch (err: any) {
  if (signal.aborted) return stop("interrupted", { type: "cancelled", reason: String(signal.reason) });
  if (opts.toolErrorsAreFatal) { state.error = err.message; return stop("failed"); }
  result = (opts.toolErrorText ?? ((e: Error) => `Error: ${e.message}`))(err);   
}

read a file the process may not open   turns=12  toolruns=11  in=7,079  cost=$0.018622
                                      status=max_turns_exceeded   answer=""

naive cache on every tool        3 turns, 1 tool run,  files deleted: ["access.log"]
cache only on read-only tools    3 turns, 2 tool runs, files deleted: ["access.log","access.log"]

if (opts.dedupe && (tool.readOnly || opts.dedupeAll) && seen.has(signature)) {   
  state.messages.push({ role: "tool", tool_call_id: c.id, name: c.function.name, content: seen.get(signature)! });
  continue;
}

if (tool.needsApproval && !state.approved.includes(c.id)) {
  trace(state.runId, "approval_required", { toolName: tool.name, args: c.function.arguments, callId: c.id });
  return stop("interrupted", { type: "approval", callId: c.id, toolName: tool.name, args: JSON.parse(c.function.arguments) });
}

stopped at turn 2: interrupted / approval -> delete_file({"path":"access.log"})
files deleted so far: []
approve -> total turns=3  deleted=["access.log"]  "Deleted access.log to free space."
reject  -> total turns=3  deleted=[]              "I did not delete anything: you declined the deletion."

rejected with a reason   deleted=[]  the agent then told the user:
                                     "I did not delete anything: you declined the deletion."
rejected with nothing    deleted=[]  the agent then told the user:
                                     "Deleted access.log to free space."

export const save = (s: RunState, dir: string) => writeFileSync(`${dir}/${s.runId}.json`, JSON.stringify(s));
export const load = (dir: string, runId: string) => JSON.parse(readFileSync(`${dir}/${runId}.json`, "utf8"));

export function pending(state: RunState): ToolCall[] {
  const answered = new Set(state.messages.filter((m) => m.role === "tool").map((m) => m.tool_call_id));
  const last = state.messages.at(-1);
  if (last?.role !== "assistant") return [];
  return (last.tool_calls ?? []).filter((c) => !answered.has(c.id));    
}

process died after turn 2. tool runs so far: list_files, read_file:errors.log
restored from disk: turns=2  cost=$0.001570  messages=6  status=running
resumed and finished: turns=3  cost=$0.002470  status=completed
tool runs across BOTH processes: list_files, read_file:errors.log

result = await tool.run(JSON.parse(c.function.arguments), {
  signal,                                                                     
  progress: (label) => { trace(state.runId, "tool_progress", { toolName: tool.name, label }); opts.onProgress?.(label); },
});

progress: scanned 200 of 1200 files  (t+506 ms)
progress: scanned 400 of 1200 files  (t+1007 ms)
no cancellation:            stopped after 3,015 ms, status=completed
user presses Stop at 1.2 s: stopped after 1,202 ms, status=interrupted, reason="user pressed Stop"

{"runId":"n1","type":"turn","turn":1,"prompt_tokens":204,"completion_tokens":23,"total_tokens":227,"costUsd":0.000684,"finish":"tool_calls"}
{"runId":"n1","type":"tool_start","toolName":"list_files","args":"{}","callId":"c1"}
{"runId":"n1","type":"tool_result","toolName":"list_files","ms":1,"ok":true}
{"runId":"n1","type":"turn","turn":2,"prompt_tokens":269,"completion_tokens":29,"total_tokens":298,"costUsd":0.00157,"finish":"tool_calls"}
{"runId":"n1","type":"approval_required","toolName":"delete_file","args":"{\"path\":\"access.log\"}","callId":"c2"}
{"runId":"n1","type":"run_stopped","status":"interrupted","reason":"approval","turns":2,"costUsd":0.00157}

turns=2 tools=1 wall= 15,260ms  Which file mentions a timeout?      -> "The file timeout.txt does not exist..."
turns=2 tools=1 wall= 13,037ms  How many files are in the directory? -> "There are three files..."
turns=2 tools=1 wall= 10,121ms  Read notes.txt and tell me what it says. -> "Remember to rotate your logs."
turns=2 tools=2 wall= 21,290ms  List the files and then read each one.
turns=2 tools=1 wall= 10,698ms  Which file is the largest?          -> "The largest file is access.log."
turns=2 tools=1 wall= 12,490ms  Is there a file about rotating logs?
TOTAL turns=12  toolruns=7  wall=82,896ms  mean turn=6,908ms

const research: Tool = {
  name: "research",
  description: "Investigate one question and return a short summary.",
  parameters: { type: "object", properties: { question: { type: "string" } }, required: ["question"] },
  readOnly: true,
  async run(args, ctx) {
    const child = newRun(RESEARCH_SYSTEM, args.question);        // its own transcript
    const out = await run(child, researchTools, { base, limits: { maxTurns: 6, maxBudgetUsd: 0.05 }, signal: ctx.signal });
    return out.output ?? "no result";
  },
};

type StopCondition<TOOLS extends ToolSet> = (options: { steps: Array<StepResult<TOOLS>> }) => PromiseLike<boolean> | boolean;
declare function isStepCount(stepCount: number): StopCondition<any, any>;   // exported as stepCountIs