import { readFileSync, writeFileSync } from "node:fs";
import { join } from "node:path";
import { parseFlags } from "../../skills/doc-wiki/scripts/_cli_args.js";
import { loadState, runKey } from "./bench_checkpoint.js";
import type { Arm, BenchState, RunRecord, TicketRecord, TicketsFile } from "./types.js";

const ARMS: readonly Arm[] = ["baseline", "wiki"];

const cell = (r: RunRecord | undefined): string => {
  if (r === undefined || r.status === "pending") return "⏳";
  if (r.status === "passed") return r.detail === "tests-passed-on-retry" ? "✅ (retry)" : "✅";
  if (r.status === "failed") return `❌ ${r.detail ?? ""}`.trim();
  return r.status;
};

export function renderResults(repo: string, tickets: readonly TicketRecord[], state: BenchState): string {
  const lines: string[] = [`## ${repo}`, ""];
  let cost = 0;

  lines.push("| arm | passed/graded (rate) |", "|---|---|");
  const gradedByArm: number[] = [];
  for (const arm of ARMS) {
    let passed = 0;
    let graded = 0;
    for (const t of tickets) {
      const r = state.runs[runKey(t.issue, arm)];
      if (r?.cost_usd !== undefined) cost += r.cost_usd;
      if (r?.status === "passed" || r?.status === "failed") {
        graded += 1;
        if (r.status === "passed") passed += 1;
      }
    }
    gradedByArm.push(graded);
    const rate = graded === 0 ? 0 : Math.round((passed / graded) * 100);
    lines.push(`| ${arm} | ${passed}/${graded} (${rate}%) |`);
  }
  if (new Set(gradedByArm).size > 1) {
    lines.push("", "> Note: arms have unequal graded counts — rates are not directly comparable until grading completes.");
  }
  lines.push("", `Total session cost: $${cost.toFixed(2)}`, "");

  lines.push("| ticket | merged | baseline | wiki |", "|---|---|---|---|");
  for (const t of tickets) {
    const safeTitle = t.title.replace(/\|/g, "\\|");
    lines.push(
      `| #${t.issue} ${safeTitle} | ${t.merged_at.slice(0, 10)} | ${cell(state.runs[runKey(t.issue, "baseline")])} | ${cell(state.runs[runKey(t.issue, "wiki")])} |`,
    );
  }
  lines.push("");
  return lines.join("\n");
}

export async function main(argv: readonly string[]): Promise<number> {
  const { help, values } = parseFlags(argv, { "--repo": "repo", "--out": "out" });
  if (help || values.repo === undefined) {
    process.stderr.write("usage: benchmark report --repo <id> [--out benchmark/RESULTS.md]\n");
    return help ? 0 : 2;
  }
  const repo = String(values.repo);
  const ticketsFile = JSON.parse(readFileSync(join("benchmark", "tickets", `${repo}.json`), "utf8")) as TicketsFile;
  const active = ticketsFile.tickets.filter((t) => t.excluded === undefined);
  const state = loadState(join("benchmark", "runs", repo, "state.json"), repo);
  const md = `# Benchmark Results\n\n> Generated by \`npm run benchmark -- report\`. Methodology: [METHODOLOGY.md](METHODOLOGY.md).\n\n${renderResults(repo, active, state)}`;
  writeFileSync(String(values.out ?? join("benchmark", "RESULTS.md")), md);
  return 0;
}