API

快速开始

1. 访问 仪表盘 → API Keys，点 新建 API Key。复制 sk_ 开头的 key，只会显示一次。
2. 每次请求在 Authorization: Bearer sk_… 里带上这个 key。
3. POST 一个 task 到 /verify/v2。响应是 text/event-stream;消费 SSE 事件直到看到 task_completed。

最简调用：

curl -N -X POST https://api.citetrue.com/verify/v2 \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text":"[1] Vaswani, A., Shazeer, N., Parmar (2017). Attention is all you need."}'

-N 关闭 curl 缓冲，SSE 事件逐行到达。不需要再选 depth——所有引用走同一条流程。一般情况下每条引用消耗 1 积分；遇到比较棘手、需要使用更多数据源和做更多分析的引用，最多消耗 5 积分。

客户端示例

SSE 是一个长连 HTTP 响应，每个事件以空行（\n\n）结尾。跳过不以 data: 开头的行，剩下的 JSON-parse。

浏览器提示：原生 EventSource 不能发 Authorization header——请用 fetch + ReadableStream，见下。

const API = 'https://api.citetrue.com'
const KEY = process.env.API_KEY

async function verify(text) {
  const resp = await fetch(`${API}/verify/v2`, {
    method: 'POST',
    headers: {
      'Authorization': `Bearer ${KEY}`,
      'Content-Type': 'application/json',
    },
    body: JSON.stringify({ text }),
  })
  if (!resp.ok) throw new Error(`${resp.status}: ${await resp.text()}`)

  const reader = resp.body.getReader()
  const decoder = new TextDecoder()
  const refs = []
  let buf = ''

  while (true) {
    const { value, done } = await reader.read()
    if (done) break
    buf += decoder.decode(value, { stream: true })
    let idx
    while ((idx = buf.indexOf('\n\n')) !== -1) {
      const chunk = buf.slice(0, idx); buf = buf.slice(idx + 2)
      for (const line of chunk.split('\n')) {
        if (!line.startsWith('data: ')) continue
        const evt = JSON.parse(line.slice(6))
        if (evt.event === 'ref_completed') {
          refs.push(evt.data.ref)
        }
        if (evt.event === 'task_completed') return { refs, balance: evt.data.balance }
        if (evt.event === 'error') throw new Error(evt.error)
      }
    }
  }
}

const out = await verify('[1] Vaswani, A., Shazeer, N., Parmar (2017). Attention is all you need.')
console.log(out)

鉴权

API key 是长期 Bearer 凭证，形如 sk_<40-char-token>。通过 Authorization header 发送：

Authorization: Bearer sk_AbCd123…

• 可在 Dashboard 吊销某个 key，几秒内生效。
• 一个 key 能做拥有它的用户能做的所有操作。当密码对待——每个集成单独一把、定期轮换。

限速

每把 API key 都有一个 token bucket 限速器：

• 突发： 10 个请求。
• 稳态： 60 个请求/分钟（bucket 以 1 token/s 回补）。
• 超限时请求失败返 429，带 Retry-After header（单位秒）。

限速按 key 分算；同账号不同 key 互不影响。积分另外独立计算，叠加生效。

请求头

Every endpoint accepts the same authentication and content-type headers; only the request body and URL differ.

Responses are 200 OK with Content-Type: text/event-stream.

data: {"event":"<name>","data":{...},"error":""}

POST /verify/v2

Split a text blob into references and verify each. Supply exactly one of text (new task) or taskHash (resume). Every reference goes through the same flow — there is no verification level to choose.

请求体

幂等性: same text + same user returns the cached task on second POST (no re-billing) unless force: true.

Deprecated fields

• depth — still accepted but ignored (1, 5, 20 or omitted all behave the same). Don't send it.
• refHash + parentTaskHash — legacy single-reference mode kept for older clients. It ignores depth and simply finishes that one reference, billed under the normal rules. New integrations shouldn't use it.

请求示例 (text)

{
  "text": "[1] Vaswani, A., Shazeer, N., Parmar (2017). Attention is all you need.\n[2] Piketty, T. (2016). Capital in the twenty-first century. Harvard University Press."
}

请求示例 (resume)

{
  "taskHash": "f0e1d2c3b4a5..."
}

典型事件序列

task_created → refs_created (N refs) →
  [ref_processing + ref_completed] × N (parallel) +
  task_progress × several →
task_completed

Per-ref assessment

Each ref_completed event carries an assessment string from this closed set:

• authentic — paper exists and is the one cited. value contains the matched paper.
• unsure — found something but can't confirm; notices and confidence describe why.
• inauthentic — definitively not found / fabricated / unrelated.
• invalid — input wasn't a citation; pipeline refused to search before any datasource hit.
• error — verification failed on this single ref; sibling refs may still succeed. data.errors[] lists tokens (datasource_unavailable, timeout, rate_limited, parse_failed).
• exceeded — account ran out of credits before this ref could run.

Notices on a result (year mismatch, author mismatch, …) are orthogonal to assessment — even an authentic verdict can carry notices worth showing. data.cost is the total credits this task has charged for the reference (0–5): 1 for most references, up to 5 for tricky ones that needed more data sources and more analysis, 0 if it was already paid for in another task. It covers every connection and resume of the same task, and the same number is sent on every push, replays included — overwrite it, don't add it up across reconnects. data.depth is kept only for compatibility with older clients — ignore it.

SSE 事件

SSE event names emitted during verification. Listen for task_completed as the terminal success event; error for terminal failure.

• task_created — task accepted, hash assigned.
• refs_created — text was split into N refs.
• split_completed — splitting phase finished.
• ref_processing / ref_status — per-ref progress signal.
• ref_completed — per-ref final assessment.
• task_completed — all refs done; carries cost (credits newly charged during this connection, 0 for a pure replay) and the account balance afterwards (can be negative — see Credits & billing).
• task_progress — periodic progress %.
• warn — non-fatal warning.
• error — terminal task-level failure.

GET /credits

GET /credits/v1 — returns current credit balance. Auth required. The balance can be negative (see Credits & billing).

积分与计费

Most references cost 1 credit. Tricky ones that need more data sources and more analysis can cost up to 5. Each reference is charged 1 credit when it's queued; anything extra is added when it finishes. Cached tasks (same text + user) do not re-bill.

Reading the charge: data.cost in ref_completed is the running total this task has charged for that reference — the same number is sent again on reconnects and replays, so overwrite it rather than adding it up. cost in task_completed is what this connection newly charged (0 for a pure replay), so after a reconnect it won't equal the sum of the per-ref costs. balance is the account balance afterwards.

Running out: a reference that hasn't started when the balance can't cover it comes back as exceeded, and the task still ends with task_completed. If you run out of credits mid-check, references already in progress still finish; the overage is deducted at your next credit reset, so balance can be negative.

错误参考

Standard HTTP status codes apply (400 invalid, 401 auth missing/invalid, 402 insufficient credits, 429 rate-limited, 5xx upstream). SSE-level failures arrive as a final error event.

版本与稳定性

Path-versioned (/verify/v2 etc.). Breaking changes bump the version segment; backwards-compatible additions ship in-place.