ModelRouter/internal/lua/plugins/ccquota.lua

-- Command Code quota — multi-account plan balance for the gateway.
--
-- The billing plugin only ever reports what the gateway already measured, so it
-- never has to reach out. A plan balance is different: the number only exists
-- on the vendor's side, and the only way to learn it is to ask. Command Code
-- exposes /alpha/billing/credits (plus whoami / subscriptions / usage) on the
-- provider host, authenticated with the same API key the source already uses.
--
-- Accounts: one per configured source whose base_url is the Command Code API
-- host. Two keys on the same host are two separate accounts, and both are
-- shown — an operator with a spare seat needs to see both draining.
--
-- Every endpoint degrades independently. A vendor that retires one route must
-- not blank the others, and a key that has run out still returns HTTP 401 on
-- the inference path while credits reads fine, so the report has to survive
-- partial failure and say WHICH part failed rather than rendering a zero that
-- looks like "no quota left".

local PLUGIN = {}

PLUGIN.name = "ccquota"
PLUGIN.version = "1.0.0"
PLUGIN.description = "Command Code 多账户额度余量（5 小时 / 周 / 月窗口 + 余额）"

-- Command Code's API host. __llmsproxy_http only permits hosts that a
-- configured source already talks to, so this works exactly when such a source
-- exists — no separate allowlist to keep in sync, and no way to widen reach.
local API_HOST = "api.commandcode.ai"

-- These headers are required alongside the bearer token. Without them the
-- endpoints answer 401 even with a perfectly valid key, which looks identical
-- to a revoked key and costs a lot of time to tell apart.
--
-- The bearer token is NOT here on purpose: it is per-account, so fetchJSON
-- copies this table and injects it per request. An earlier version passed this
-- table straight through and every endpoint answered 401 — which reads exactly
-- like a revoked key, and sent me looking at the account instead of the plugin.
local CLI_VERSION = "1.54.2"
local REQUIRED_HEADERS = {
  ["x-command-code-version"] = CLI_VERSION,
  ["x-cli-environment"] = "production",
  ["User-Agent"] = "commandcode-quota/" .. CLI_VERSION,
}

-- Accounts are handed in from the page (which reads /api/sources and its own
-- key store). The kernel deliberately does NOT let a plugin read the config, so
-- this is the only channel — which also means the key never sits in Lua state
-- or in the persisted plugin file.
local ACCOUNTS = {}

-- ---------------------------------------------------------------- helpers


local function tonum(v)
  return tonumber(v) or 0
end

-- usd formats a dollar amount the way the vendor's panel does: two decimals,
-- but never a bare "0" when there is a real fractional balance left. A $0.0811
-- balance rounds to $0.08, and showing "$0" there would read as "nothing left".


-- fetchJSON performs one request and returns (decodedTable, nil) or
-- (nil, errorMessage). It NEVER raises: an escaping error inside a plugin hook
-- can take the whole gateway down (see the hook-guard note in the kernel), so
-- every failure has to arrive as an ordinary value.
local function fetchJSON(path, key)
  -- Copy, then add the token: mutating the shared table would leak one
  -- account's key into every later request.
  local headers = {}
  for k, v in pairs(REQUIRED_HEADERS) do headers[k] = v end
  headers["Authorization"] = "Bearer " .. tostring(key or "")
  local res, err = __llmsproxy_http({
    url = "https://" .. API_HOST .. path,
    method = "GET",
    headers = headers,
    timeout_ms = 12000,
  })
  if res == nil then
    return nil, tostring(err or "request failed")
  end
  -- Body arrives as a JSON string; the kernel's json.decode is the only parser
  -- available and it raises on malformed input, so it is pcall'd here too.
  local ok, decoded = pcall(json.decode, res.body)
  if not ok then
    return nil, "bad JSON from " .. path
  end
  return decoded, nil
end

-- authFailure recognises the one error that means "this key is not usable"
-- rather than "this endpoint is unhappy". Quota exhaustion and a revoked key
-- both surface as 401 here, and they need opposite operator responses.

-- ---------------------------------------------------------------- account report

-- collectAccount gathers one account's numbers. Each endpoint is independent:
-- credits is the one that matters, and the rest enrich it. A failure is
-- recorded per-endpoint instead of aborting, because "I could not read the
-- subscription" and "the account has no quota" must not look the same.
local function collectAccount(acct)
  local report = {
    name = acct.name,
    label = acct.label,
    failures = {},
    checked_at = os.time(),
  }

  local who, werr = fetchJSON("/alpha/whoami", acct.key)
  if who == nil then
    report.failures[#report.failures + 1] = "whoami: " .. tostring(werr)
  elseif type(who) == "table" and type(who.user) == "table" then
    report.email = who.user.email
    report.user = who.user.name or who.user.userName
  end

  local creds, cerr = fetchJSON("/alpha/billing/credits", acct.key)
  local rawStatus = 0
  if creds == nil then
    report.failures[#report.failures + 1] = "credits: " .. tostring(cerr)
  else
    local c = creds.credits or {}
    local wl = creds.windowLimits or {}
    report.monthly = tonum(c.monthlyCredits)
    report.purchased = tonum(c.purchasedCredits)
    report.free = tonum(c.freeCredits)
    report.total = report.monthly + report.purchased + report.free
    report.limited = wl.limited == true
    report.exceeded = wl.exceeded
    report.fiveHour = wl.fiveHour
    report.weekly = wl.weekly
    rawStatus = 200
  end

  local subs, serr = fetchJSON("/alpha/billing/subscriptions", acct.key)
  if subs == nil then
    report.failures[#report.failures + 1] = "subscriptions: " .. tostring(serr)
  elseif type(subs) == "table" and type(subs.data) == "table" then
    report.plan_status = subs.data.status
    report.plan_price = subs.data.metadata and nil
    local md = subs.data.metadata
    if type(md) == "table" then
      report.plan_name = md.plan or md.name or md.tier
    end
  end

  local usage, uerr = fetchJSON("/alpha/usage/summary", acct.key)
  if usage == nil then
    report.failures[#report.failures + 1] = "usage: " .. tostring(uerr)
  elseif type(usage) == "table" then
    report.requests = tonum(usage.totalCount)
    report.spent = tonum(usage.totalCost)
    report.tokens = tonum(usage.totalTokens)
    report.success_rate = tonum(usage.successRate)
  end

  -- An account whose every endpoint failed is an auth problem, not a data
  -- problem: state it plainly so nobody reads "—" as "zero quota".
  if #report.failures >= 3 and report.total == nil then
    report.auth_failed = true
  end
  return report
end

-- ---------------------------------------------------------------- page

PLUGIN.ui = {
  page = {
    page_id = "ccquota",
    title = "CC Quota",
    order = 45,
    mount = [==[
<div id="ccq-root" class="ccq-root">
  <div class="ccq-head">
    <div>
      <div class="ccq-title">Command Code 额度</div>
      <div class="ccq-sub" id="ccq-sub">点击刷新以拉取各账户余量</div>
    </div>
    <div class="grow"></div>
    <button class="small" id="ccq-refresh">刷新</button>
    <span class="ccq-auto"></span>
  </div>
  <div id="ccq-list"><div class="ccq-empty">尚未拉取</div></div>
</div>
<style>
#ccq-root{padding:16px;min-width:0;max-width:100%;overflow-x:auto}
.ccq-head{display:flex;align-items:flex-start;gap:10px;margin:0 0 12px;flex-wrap:wrap}
.ccq-title{font-size:15px;font-weight:600}
.ccq-sub{font-size:12px;opacity:.66;margin-top:2px}
.ccq-auto{font-size:12px;opacity:.6}
.ccq-acc{border:1px solid var(--bd,rgba(127,127,127,.25));border-radius:10px;padding:12px 14px;margin:0 0 12px;min-width:0}
.ccq-acc.err{border-color:rgba(220,80,80,.5)}
.ccq-acc-h{display:flex;align-items:center;gap:8px;flex-wrap:wrap;margin:0 0 4px}
.ccq-acc-n{font-weight:600;font-size:14px;overflow:hidden;text-overflow:ellipsis;white-space:nowrap;max-width:40%}
.ccq-mail{font-size:12px;opacity:.66;overflow:hidden;text-overflow:ellipsis;white-space:nowrap}
.ccq-pill{font-size:11px;padding:1px 7px;border-radius:999px;border:1px solid rgba(127,127,127,.35);opacity:.85;white-space:nowrap}
.ccq-pill.ok{color:#15803d;border-color:rgba(21,128,61,.45)}
.ccq-pill.low{color:#b45309;border-color:rgba(180,83,9,.45)}
.ccq-pill.out{color:#b91c1c;border-color:rgba(185,28,28,.45)}
.ccq-bal{display:flex;align-items:baseline;gap:8px;margin:6px 0 10px;flex-wrap:wrap}
.ccq-bal-n{font-size:20px;font-weight:600}
.ccq-bal-l{font-size:12px;opacity:.66}
.ccq-grid{display:grid;grid-template-columns:repeat(auto-fit,minmax(180px,1fr));gap:10px 18px}
.ccq-win{min-width:0}
.ccq-win-h{display:flex;justify-content:space-between;gap:6px;font-size:12px;opacity:.85}
.ccq-win-n{font-variant-numeric:tabular-nums;font-weight:600}
.ccq-bar{height:6px;border-radius:3px;background:rgba(127,127,127,.22);overflow:hidden;margin:4px 0 2px}
.ccq-bar-fill{height:100%;background:#3b82f6;border-radius:3px}
.ccq-bar-fill.warn{background:#d97706}
.ccq-bar-fill.over{background:#dc2626}
.ccq-win-d{font-size:11px;opacity:.6;font-variant-numeric:tabular-nums}
.ccq-reset{opacity:.6;margin-left:4px}
.ccq-meta{display:flex;gap:14px;flex-wrap:wrap;font-size:11.5px;opacity:.7;margin-top:10px}
.ccq-fail{font-size:11.5px;color:#b91c1c;margin-top:8px;word-break:break-word}
.ccq-empty{opacity:.6;font-size:13px;padding:8px 0}
</style>
<script>
(function(){
  var HOST = "api.commandcode.ai";
  var lastReports = [];

  function escH(s){
    return String(s==null?"":s).replace(/[&<>"]/g,function(c){
      return c==="&"?"&amp;":c==="<"?"&lt;":c===">"?"&gt;":"&quot;";
    });
  }
  function usd(v){
    v = Number(v)||0;
    if (v<=0) return "$0.00";
    return "$"+(v<0.01?v.toFixed(4):v.toFixed(2));
  }
  function stateOf(r){
    if (r.auth_failed) return {cls:"err", txt:"认证失败"};
    if (r.exceeded) return {cls:"out", txt:"已超额"};
    var t = Number(r.total)||0;
    if (t<=0) return {cls:"out", txt:"无余额"};
    if (t<5) return {cls:"low", txt:"余额偏低"};
    return {cls:"ok", txt:r.plan_status||"正常"};
  }
  function win(label,w){
    if(!w) return "";
    var used=Number(w.used)||0, cap=Number(w.cap)||0;
    var p = cap>0 ? Math.floor(used/cap*100+0.5) : null;
    if(p===null) return "";
    var over = w.exceeded===true;
    if(over) p=100;
    var cls = "ccq-bar-fill"+(over||p>=100?" over":(p>=80?" warn":""));
    var reset="";
    if(Number(w.resetAt)>0){
      var s=Math.floor(w.resetAt/1000-Date.now()/1000);
      if(s>0){
        var d=Math.floor(s/86400),h=Math.floor((s%86400)/3600),m=Math.floor((s%3600)/60);
        reset=(d>0?d+"d "+h+"h":(h>0?h+"h "+m+"m":m+"m"));
      }
    }
    return '<div class="ccq-win"><div class="ccq-win-h"><span>'+escH(label)+
      (reset?' <span class="ccq-reset">↻'+escH(reset)+'</span>':'')+
      '</span><span class="ccq-win-n">'+p+'%</span></div>'+
      '<div class="ccq-bar"><div class="'+cls+'" style="width:'+p+'%"></div></div>'+
      '<div class="ccq-win-d">'+used.toLocaleString()+' / '+cap.toLocaleString()+'</div></div>';
  }
  function card(r){
    var st = stateOf(r);
    var h = '<div class="ccq-acc'+((r.auth_failed||(r.failures&&r.failures.length===4))?" err":"")+'">'+
      '<div class="ccq-acc-h"><span class="ccq-acc-n">'+escH(r.name||"")+'</span>'+
      (r.email?'<span class="ccq-mail">'+escH(r.email)+'</span>':'')+
      '<span class="grow"></span>'+
      '<span class="ccq-pill '+st.cls+'">'+escH(st.txt)+'</span></div>'+
      '<div class="ccq-bal"><span class="ccq-bal-n">'+usd(r.total)+
      '</span><span class="ccq-bal-l">月度余额'+
      (Number(r.purchased)>0?'（含充值 $'+Number(r.purchased).toFixed(2)+'）':'')+
      '</span></div>'+
      '<div class="ccq-grid">'+
      win("5 小时", r.fiveHour)+win("每周", r.weekly)+
      '</div>';
    var meta=[];
    if(r.requests) meta.push(r.requests.toLocaleString()+" 次请求");
    if(r.spent) meta.push("累计 "+usd(r.spent));
    if(r.tokens) meta.push((r.tokens/1e9).toFixed(2)+"B tokens");
    if(r.success_rate) meta.push("成功率 "+r.success_rate.toFixed(2)+"%");
    if(meta.length) h+='<div class="ccq-meta">'+meta.map(escH).join(" · ")+'</div>';
    if(r.failures&&r.failures.length){
      h+='<div class="ccq-fail">部分接口失败：'+r.failures.map(escH).join("；")+'</div>';
    }
    return h+"</div>";
  }
  function render(reports){
    lastReports = reports||[];
    var host=document.getElementById("ccq-list");
    if(!host) return;
    if(!lastReports.length){host.innerHTML='<div class="ccq-empty">没有可用的 Command Code 源</div>';return;}
    host.innerHTML=lastReports.map(card).join("");
    var sub=document.getElementById("ccq-sub");
    if(sub) sub.textContent = lastReports.length+" 个账户 · "+
      lastReports.filter(function(r){return r.auth_failed;}).length+" 个认证失败";
  }
  async function refresh(){
    var srcs;
    try{
      var r=await fetch("/api/sources",{credentials:"same-origin"});
      srcs=(await r.json()).sources||[];
    }catch(e){
      var s0=document.getElementById("ccq-sub"); if(s0) s0.textContent="拉取源列表失败: "+e.message;
      render([]); return;
    }
    // Every source on the Command Code host is one account, keyed by its own
    // API key — two keys on that host are two seats, and both must be listed.
    var accts=srcs.filter(function(s){
      try{ return new URL(s.base_url).hostname===HOST; }catch(e){ return false; }
    });
    if(!accts.length){ render([]); return; }
    var btn=document.getElementById("ccq-refresh");
    if(btn) btn.disabled=true;
    var auto=document.getElementById("ccq-auto")||document.querySelector(".ccq-auto");
    if(auto) auto.textContent="拉取中…";
    if(!window.pluginAPI || typeof pluginAPI.call!=="function"){
      var sb=document.getElementById("ccq-sub");
      if(sb) sb.textContent="pluginAPI.call 不可用（内核版本过旧）";
      render([]); return;
    }
    var out=[];
    var errs=0;
    // One account at a time: the endpoints are independent, and a sequential
    // loop means a hung vendor endpoint delays only its own row instead of
    // blocking the whole page behind one promise.
    for (var i=0;i<accts.length;i++){
      var a=accts[i];
      try{
        var rep = await pluginAPI.call("ccquota","collect_account",
          {name:a.name,label:a.name,key:a.api_key});
        out.push(rep||{name:a.name,failures:["no result"]});
      }catch(e){
        errs++;
        out.push({name:a.name,failures:[String(e.message||e)],auth_failed:true});
      }
    }
    render(out);
    if(btn) btn.disabled=false;
    if(auto) auto.textContent="更新于 "+new Date().toLocaleTimeString();
    try{ await pluginAPI.postState("ccquota",{reports:out,updated_at:Date.now()}); }catch(e){}
  }
  // The mount is injected long after DOMContentLoaded has already fired, so
  // listening for that event here registered a handler for an event that had
  // already been dispatched — the page rendered but stayed empty until a manual
  // refresh. Wiring the button and fetching immediately is what makes the page
  // populate on first open.
  // The plugin mount is injected by the kernel and its <script> evaluated after
  // injection, but that still happens during the UI's own boot — and the page
  // body is rebuilt whenever the tab is opened. Two consequences:
  //
  //   - A DOMContentLoaded listener never fires (the event already passed), so
  //     the page rendered empty until a manual refresh.
  //   - Wiring the refresh button once at script-eval time silently loses the
  //     handler when the tab's DOM is replaced.
  //
  // pluginAPI.onTabShown is the kernel's answer to both: the callback runs when
  // the tab is actually shown, with the DOM in place. It also runs once for the
  // already-visible tab at boot, so this single registration covers first paint
  // AND every later re-entry.
  function mount(){
    var b=document.getElementById("ccq-refresh");
    // The tab's DOM is rebuilt on re-entry, so a handler wired against the old
    // node is gone. The flag lives on the NODE, not in a closure variable, which
    // is what makes re-wiring safe.
    if(b && !b.__ccqWired){ b.__ccqWired = true; b.addEventListener("click",refresh); }
  }
  // Run once immediately — the billing page does the same, and waiting only for
  // onTabShown leaves the page blank when the tab is already open at boot.
  mount();
  refresh();
  if (window.pluginAPI && pluginAPI.onTabShown) pluginAPI.onTabShown(mount);
  window.__ccqRender = render;
  window.__ccqRefresh = refresh;
})();
</script>
]==],
  },
}

-- exports is what makes collect_account reachable from the plugin's own page.
-- Without this list the call endpoint refuses it: the endpoint is an HTTP
-- surface into the Lua state, so "which functions may it reach" has to be the
-- plugin's explicit answer rather than a default.
PLUGIN.exports = { "collect_account" }

-- collect_account gathers one account's report. It returns the report TABLE (not
-- a string) so the page receives structured numbers and booleans instead of
-- having to parse anything back out of a formatted blob.
PLUGIN.collect_account = function(acct)
  if type(acct) ~= "table" then return nil, "expected account table" end
  if acct.key == nil or acct.key == "" then
    return { name = tostring(acct.name or ""), failures = { "missing api key" },
             auth_failed = true }
  end
  local rep = collectAccount({
    name = acct.name, label = acct.label, key = acct.key,
  })
  return rep, nil
end

return PLUGIN