就绪度网络

API 参考

Search API

将任务描述转化为排序后的候选能力。被拦截的能力会连同原因一并返回，便于 Agent 了解过滤的内容与原因。

POST/v1/capabilities/search

请求体

字段说明
query用自然语言描述的任务。
agent_runtime调用方运行时，如 claude-code、cursor，用于按运行时排序。
locale偏好语言，如 en、zh-CN。
risk_toleranceread_only | write | destructive。风险高于此值的候选会被排除或降级。
latency_budget_ms预期延迟超过这个预算的候选会被丢弃。
require_freshness_seconds要求探测证据比这个时间窗口更新。
limit返回候选数上限，1–50，默认 10。
request.sh
curl -X POST http://101.32.68.30/v1/capabilities/search \
  -H 'Authorization: Bearer $API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
    "query": "extract tables from a PDF into CSV",
    "agent_runtime": "claude-code",
    "locale": "en",
    "risk_tolerance": "read_only",
    "latency_budget_ms": 10000,
    "limit": 10
  }'

响应

结果分为三组：recommended（建议调用）、fallbacks（前者失败时使用）、blocked（已排除，附原因码）。每个带分条目均携带 confidence、evidence_level 与 valid_until；缺少来源依据的评分不会返回。

response.json
{
  "query_id": "q_123",
  "recommended": [
    {
      "capability_id": "cap_pdf_extract_table",
      "action": "extract_table",
      "interface_type": "mcp_remote",
      "invoke_now_score": 0.87,
      "task_success_score": 0.82,
      "confidence": 0.76,
      "status": "routeable",
      "valid_until": "2026-06-10T12:31:00Z",
      "evidence_level": "E4_protocol_probe_passed",
      "risk_level": "read_only",
      "requires_user_confirmation": false,
      "reason_codes": ["recent_probe_ok", "static_audit_passed"],
      "warnings": ["low_real_invocation_sample"]
    }
  ],
  "fallbacks": [
    {
      "capability_id": "cap_slow_but_local_cli",
      "action": "extract_table",
      "interface_type": "cli",
      "invoke_now_score": 0.61,
      "confidence": 0.70,
      "status": "fallback",
      "evidence_level": "E3_sandbox_install_passed",
      "reason_codes": ["local_execution_available"],
      "warnings": ["high_latency_observed"]
    }
  ],
  "blocked": [
    {
      "capability_id": "cap_prompt_injection_skill",
      "reason_codes": ["prompt_injection_detected"]
    }
  ]
}