AgapHost/ai/quota-command-openclaw-plugin/index.js

/**
 * Kimi Quota Command (kb #62) — registers `/quota` on Adolf's Matrix channel.
 *
 * OpenClaw's native-command dispatch (`api.registerCommand`) runs a
 * `/`-prefixed command BEFORE the agent turn: no model is invoked, so this
 * never spends a Kimi turn (unlike asking Adolf in prose "what's my quota").
 * It hits adolf-llm's own GET /usage route (server.js, kb #62 piece 1), which
 * itself talks straight to Kimi's managed-usage API — no LLM anywhere in the
 * path.
 *
 * Gating: `requireAuth: true` (the registerCommand default) restricts the
 * command to `ctx.isAuthorizedSender`, i.e. the same Matrix DM allowlist
 * (`channels.matrix.dm.allowFrom` in openclaw.json) that already gates every
 * other interaction with Adolf. No separate owner-only tier is needed here —
 * it's a read-only status line, not a privileged action.
 */
import { definePluginEntry } from "openclaw/plugin-sdk/plugin-entry";

// adolf-llm is a sibling service on the same `openai` compose network —
// reached by service name, not localhost/host.docker.internal.
const USAGE_URL = "http://adolf-llm:8010/usage";
const FETCH_TIMEOUT_MS = 5000;

function pct(row) {
  return row && typeof row.pct === "number" ? `${row.pct}%` : "n/a";
}

async function fetchUsage() {
  const controller = new AbortController();
  const timer = setTimeout(() => controller.abort(), FETCH_TIMEOUT_MS);
  try {
    const res = await fetch(USAGE_URL, { signal: controller.signal });
    const body = await res.json().catch(() => ({}));
    if (!res.ok) throw new Error(body?.error || `adolf-llm /usage HTTP ${res.status}`);
    return body;
  } finally {
    clearTimeout(timer);
  }
}

export default definePluginEntry({
  id: "quota-command",
  name: "Codex Quota Command",
  description:
    "LLM-free /quota command: reads Adolf's Codex usage from adolf-llm:8010/usage and replies with a compact readout.",
  register(api) {
    api.registerCommand({
      name: "quota",
      description: "Show Codex quota usage for the plan's rate-limit windows — no model call.",
      acceptsArgs: false,
      requireAuth: true,
      handler: async () => {
        try {
          const usage = await fetchUsage();
          // Codex reports up to two plan-defined windows rather than Kimi's
          // fixed 5h/weekly/7d buckets; render whichever exist, shortest
          // first, labelled from the data itself.
          const rows = [usage.secondary, usage.primary]
            .filter((r) => r && typeof r.pct === "number")
            .map((r) => (r.window_label ? `${r.window_label} ${r.pct}%` : pct(r)));
          let line = rows.length ? `Codex: ${rows.join(" · ")}` : "Codex: no rate-limit windows reported";
          if (usage.plan) line += ` (${usage.plan} plan)`;
          if (usage.limit_reached) line += " ⚠ limit reached";
          if (usage.stale) line += ` — stale, ${usage.age_s}s old`;
          return { text: line, suppressReply: true };
        } catch (e) {
          api.logger?.warn?.(`quota-command: fetch failed (${e?.message || e})`);
          return { text: `Codex quota unavailable: ${e?.message || e}`, suppressReply: true };
        }
      },
    });
  },
});