/**
 * Reads token usage out of OpenCode's local SQLite store.
 *
 * Store: `~/.local/share/opencode/opencode.db` (NOT `~/.config/opencode`,
 * which holds only configuration). Usage lives on the `message` table, whose
 * `data` column is a JSON blob carrying `role`, `modelID`, `providerID`,
 * `cost` and a `tokens` object.
 *
 * Two things the real data settled, both of which would corrupt totals
 * silently if assumed instead of checked.
 *
 * **Cache is DISJOINT from input here.** Measured across all 4,674
 * usage-bearing messages on a reference machine, `total` equals
 * `input + output + cache.read + cache.write` — never `input + output` alone
 * unless cache happened to be zero. This is the opposite of Codex, where
 * `cached_input_tokens` is a SUBSET of `input_tokens` and has to be subtracted
 * back out. Three readers now, three conventions; none of them is safe to
 * infer from the others.
 *
 * **OpenCode's own `cost` field is not usable.** It was 0 in all 4,674
 * messages, while the provider mix spanned `github-copilot` (a subscription),
 * `openai` (metered) and `neurolink` (this proxy). A single cost figure for
 * that mixture would be wrong whichever way it was computed, so tokens are
 * reported and cost is declared `unavailable` rather than invented or
 * quietly zeroed.
 *
 * Worth knowing for anyone summing sources: traffic OpenCode sent through the
 * NeuroLink proxy appears under `providerID: "neurolink"` here AND in the
 * proxy's own ledger. The two are independent measurements of the same
 * requests, not additive. On the reference machine that was 41 messages and
 * ~772k tokens against 458M total, so it is small — but it is not zero, and a
 * dashboard adding local usage to proxy usage double-counts exactly that
 * slice.
 */
import type { LocalUsageReader } from "../types/index.js";
export declare function createOpenCodeReader(): Promise<LocalUsageReader>;