工作流
五种工作流模式，每种都是由策略路由步骤构成的有界图，生成一条完整的追踪记录。
工作流
五种常见结构。每个标签页展示流程图及本示例中各步骤路由到的模型；点击查看 flow_ir 可获取完整可复制的项（term）。建议先用 POST /x/flow/normalize 进行演练。每个节点声明自身策略（filter + rank），图表中的模型 ID 与成本展示真实路由结果——内部值保持英文。
低成本分类，按质量下限起草，再经过一个强力 no-log 守卫在发送前进行审核——若有问题可拒绝输出。图表中每个节点各自执行策略决策，"已排除"表示未通过筛选的候选，"已解析 · 运行"表示被选中的模型。
查看 flow_ir
["flow", {
"u": {"kind": "input"},
"t": {"kind": "llm", "system": "Classify the ticket and extract the account id as JSON.",
"policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]], ["has_cap", "supports_json_mode"]],
["neg", ["normalize", ["field", "price_out"]]], ["argmax"], ["id"], ["always", {"action": "next_candidate"}]],
"inputs": ["u"]},
"d": {"kind": "llm", "system": "Write a reply using the ticket and the triage.",
"policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]], ["cmp", "bench_intelligence", "ge", 0.55]],
["neg", ["normalize", ["field", "price_out"]]], ["argmax"], ["id"], ["always", {"action": "next_candidate"}]],
"inputs": ["u", "t"], "template": "Ticket:\n$1\n\nTriage:\n$2"},
"g": {"kind": "llm", "system": "Check brand voice, PII, refund limits. Refuse if any fail.",
"policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]], ["is", "no_log"]],
["field", "bench_intelligence"], ["argmax"], ["id"], ["always", {"action": "next_candidate"}]],
"inputs": ["d"]},
"out": {"kind": "output", "inputs": ["g"]}
}]先用低成本模型起草，再用更强的评审者指出缺陷，最后重写——在预算内实现质量跃升。图表中各步骤独立决策，流程依次为"待运行" → "运行中" → "已解析"。
查看 flow_ir
["flow", {
"u": {"kind": "input"},
"d": {"kind": "llm", "system": "Draft an answer.",
"policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]]],
["neg", ["normalize", ["field", "price_out"]]], ["argmax"], ["id"], ["always", {"action": "next_candidate"}]],
"inputs": ["u"]},
"c": {"kind": "llm", "system": "Critique the draft: list concrete flaws and gaps.",
"policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]]],
["field", "bench_intelligence"], ["argmax"], ["id"], ["always", {"action": "next_candidate"}]],
"inputs": ["d"]},
"r": {"kind": "llm", "system": "Rewrite the answer, fixing every point in the critique.",
"policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]]],
["field", "bench_intelligence"], ["argmax"], ["id"], ["always", {"action": "next_candidate"}]],
"inputs": ["u", "d", "c"], "template": "Question:\n$1\n\nDraft:\n$2\n\nCritique:\n$3"},
"out": {"kind": "output", "inputs": ["r"]}
}]从同一策略中进行 N 次带种子的采样（sample 将多个选择分散到排名靠前的模型中），再由裁判择优选出结果。图表中可见并行起草节点各自独立决策的过程。
查看 flow_ir
["flow", {
"u": {"kind": "input"},
"n1": {"kind": "llm", "system": "Answer the question.",
"policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]]],
["field", "bench_intelligence"], ["sample", 0.5], ["id"], ["always", {"action": "next_candidate"}]],
"inputs": ["u"]},
"n2": {"kind": "llm", "system": "Answer the question.",
"policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]]],
["field", "bench_intelligence"], ["sample", 0.5], ["id"], ["always", {"action": "next_candidate"}]],
"inputs": ["u"]},
"n3": {"kind": "llm", "system": "Answer the question.",
"policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]]],
["field", "bench_intelligence"], ["sample", 0.5], ["id"], ["always", {"action": "next_candidate"}]],
"inputs": ["u"]},
"j": {"kind": "llm", "system": "Pick the single best candidate; return it verbatim.",
"policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]]],
["field", "bench_intelligence"], ["argmax"], ["id"], ["always", {"action": "next_candidate"}]],
"inputs": ["n1", "n2", "n3"], "template": "A:\n$1\n\nB:\n$2\n\nC:\n$3"},
"out": {"kind": "output", "inputs": ["j"]}
}]三个按系列（family）固定的模型并行起草，第四个模型综合产出更优的单一答案。每个固定节点使用 family_eq 加常数 zero 评分器（过滤器已将候选限定在单一系列），图表中"最终模型"标签指向综合步骤。
查看 flow_ir
["flow", {
"u": {"kind": "input"},
"a": {"kind": "llm", "system": "Draft an answer.",
"policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]], ["family_eq", "gemini-3.1-pro-preview"]],
["zero"], ["argmax"], ["id"], ["always", {"action": "next_candidate"}]], "inputs": ["u"]},
"b": {"kind": "llm", "system": "Draft an answer.",
"policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]], ["family_eq", "claude-opus-4-8"]],
["zero"], ["argmax"], ["id"], ["always", {"action": "next_candidate"}]], "inputs": ["u"]},
"c": {"kind": "llm", "system": "Draft an answer.",
"policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]], ["family_eq", "deepseek-v4-flash"]],
["zero"], ["argmax"], ["id"], ["always", {"action": "next_candidate"}]], "inputs": ["u"]},
"f": {"kind": "llm", "system": "Synthesize the single best answer from the drafts.",
"policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]]],
["add", ["scale", 0.7, ["normalize", ["field", "bench_intelligence"]]],
["scale", 0.3, ["neg", ["normalize", ["field", "price_in"]]]]],
["argmax"], ["id"], ["always", {"action": "next_candidate"}]],
"inputs": ["a", "b", "c"]},
"out": {"kind": "output", "inputs": ["f"]}
}]推理模型与编程模型在各自过滤器下并行运行，随后由合并步骤整合——适用于混合推理与代码的任务。图表中可见两个分支各自经历"已排除"/ "已解析"过程。
查看 flow_ir
["flow", {
"u": {"kind": "input"},
"rz": {"kind": "llm", "system": "Reason through the problem step by step.",
"policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]], ["is", "cap_reasoning"]],
["field", "bench_intelligence"], ["argmax"], ["id"], ["always", {"action": "next_candidate"}]], "inputs": ["u"]},
"cd": {"kind": "llm", "system": "Produce any code the problem needs.",
"policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]], ["cmp", "bench_coding_rank", "le", 5]],
["add", ["scale", 0.7, ["normalize", ["field", "bench_coding"]]],
["scale", 0.3, ["neg", ["normalize", ["field", "price_out"]]]]],
["argmax"], ["id"], ["always", {"action": "next_candidate"}]], "inputs": ["u"]},
"m": {"kind": "llm", "system": "Merge the reasoning and the code into one answer.",
"policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]]],
["add", ["scale", 0.6, ["normalize", ["field", "bench_intelligence"]]],
["scale", 0.4, ["neg", ["normalize", ["field", "price_out"]]]]],
["argmax"], ["id"], ["always", {"action": "next_candidate"}]],
"inputs": ["rz", "cd"], "template": "Reasoning:\n$1\n\nCode:\n$2"},
"out": {"kind": "output", "inputs": ["m"]}
}]