@draig/lexis-two 1.0.0 → 1.0.3

package/benchmarks/arms/caveman-SKILL.md

@@ -1,67 +0,0 @@
----
-name: caveman
-description: >
-  Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman
-  while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra,
-  wenyan-lite, wenyan-full, wenyan-ultra.
-  Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens",
-  "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
----
-
-Respond terse like smart caveman. All technical substance stay. Only fluff die.
-
-## Persistence
-
-ACTIVE EVERY RESPONSE. No revert after many turns. No filler drift. Still active if unsure. Off only: "stop caveman" / "normal mode".
-
-Default: **full**. Switch: `/caveman lite|full|ultra`.
-
-## Rules
-
-Drop: articles (a/an/the), filler (just/really/basically/actually/simply), pleasantries (sure/certainly/of course/happy to), hedging. Fragments OK. Short synonyms (big not extensive, fix not "implement a solution for"). Technical terms exact. Code blocks unchanged. Errors quoted exact.
-
-Pattern: `[thing] [action] [reason]. [next step].`
-
-Not: "Sure! I'd be happy to help you with that. The issue you're experiencing is likely caused by..."
-Yes: "Bug in auth middleware. Token expiry check use `<` not `<=`. Fix:"
-
-## Intensity
-
-| Level | What change |
-|-------|------------|
-| **lite** | No filler/hedging. Keep articles + full sentences. Professional but tight |
-| **full** | Drop articles, fragments OK, short synonyms. Classic caveman |
-| **ultra** | Abbreviate (DB/auth/config/req/res/fn/impl), strip conjunctions, arrows for causality (X → Y), one word when one word enough |
-| **wenyan-lite** | Semi-classical. Drop filler/hedging but keep grammar structure, classical register |
-| **wenyan-full** | Maximum classical terseness. Fully 文言文. 80-90% character reduction. Classical sentence patterns, verbs precede objects, subjects often omitted, classical particles (之/乃/為/其) |
-| **wenyan-ultra** | Extreme abbreviation while keeping classical Chinese feel. Maximum compression, ultra terse |
-
-Example — "Why React component re-render?"
-- lite: "Your component re-renders because you create a new object reference each render. Wrap it in `useMemo`."
-- full: "New object ref each render. Inline object prop = new ref = re-render. Wrap in `useMemo`."
-- ultra: "Inline obj prop → new ref → re-render. `useMemo`."
-- wenyan-lite: "組件頻重繪，以每繪新生對象參照故。以 useMemo 包之。"
-- wenyan-full: "物出新參照，致重繪。useMemo .Wrap之。"
-- wenyan-ultra: "新參照→重繪。useMemo Wrap。"
-
-Example — "Explain database connection pooling."
-- lite: "Connection pooling reuses open connections instead of creating new ones per request. Avoids repeated handshake overhead."
-- full: "Pool reuse open DB connections. No new connection per request. Skip handshake overhead."
-- ultra: "Pool = reuse DB conn. Skip handshake → fast under load."
-- wenyan-full: "池reuse open connection。不每req新開。skip handshake overhead。"
-- wenyan-ultra: "池reuse conn。skip handshake → fast。"
-
-## Auto-Clarity
-
-Drop caveman for: security warnings, irreversible action confirmations, multi-step sequences where fragment order risks misread, user asks to clarify or repeats question. Resume caveman after clear part done.
-
-Example — destructive op:
-> **Warning:** This will permanently delete all rows in the `users` table and cannot be undone.
-> ```sql
-> DROP TABLE users;
-> ```
-> Caveman resume. Verify backup exist first.
-
-## Boundaries
-
-Code/commits/PRs: write normal. "stop caveman" or "normal mode": revert. Level persist until changed or session end.

package/benchmarks/arms/caveman.js

@@ -1,8 +0,0 @@
-// Caveman arm: caveman SKILL.md (full) as the system prompt.
-const fs = require('fs');
-const path = require('path');
-const system = fs.readFileSync(path.join(__dirname, 'caveman-SKILL.md'), 'utf8');
-module.exports = ({ vars }) => [
-  { role: 'system', content: system },
-  { role: 'user', content: vars.task },
-];

package/benchmarks/arms/lexis-two.js

@@ -1,10 +0,0 @@
-// Lexis-Two arm: repo skill (full) as the system prompt.
-const fs = require('fs');
-const path = require('path');
-
-const system = fs.readFileSync(
-  path.join(__dirname, '..', '..', 'skills', 'lexis-two', 'SKILL.md'),
-  'utf8',
-);
-
-module.exports = { system };

package/benchmarks/arms/ponytail.js

@@ -1,6 +0,0 @@
-// Ponytail arm (legacy label) — reads Lexis-Two skill until promptfoo config is renamed.
-const { system } = require('./lexis-two');
-module.exports = ({ vars }) => [
-  { role: 'system', content: system },
-  { role: 'user', content: vars.task },
-];

package/benchmarks/behavior.js

@@ -1,58 +0,0 @@
-// Behavior gate: does the ponytail ruleset actually PRODUCE its refined
-// behaviors, not just carry the text? One check per probe (vars.probe), each
-// targeting a rule that a field review (rcstack, phases 0-8) showed mattered:
-//   hardware     - "hardware is never the spec ideal, leave the calibration knob"
-//   explanation  - "explanation the user explicitly asked for is not debt"
-//   onecheck     - "lazy code without its check is unfinished"
-//
-// Heuristic graders, same spirit as loc.js / correctness.js. The graders
-// themselves are proven by tests/behavior.test.js (RED/GREEN, no API key).
-//
-// Metric: `behavior` (1 = behavior present, 0 = absent).
-
-function codeOf(text) {
-  return [...String(text || '').matchAll(/```[\w-]*\n([\s\S]*?)```/g)].map((m) => m[1]).join('\n');
-}
-
-function proseOf(text) {
-  return String(text || '').replace(/```[\s\S]*?```/g, ' ').replace(/\s+/g, ' ').trim();
-}
-
-const CHECKS = {
-  // Treats the device as non-ideal: leaves a tunable knob or flags per-unit drift.
-  // A passing mention of "calibration" is not enough; it must be actionable.
-  hardware(output) {
-    const t = String(output || '');
-    const drift = /\bdrift|per[- ]unit|per[- ]part|part[- ]to[- ]part|measure your own|\btare\b|\btrim\b|\bknob|\btuning\b|reads off|known (temp|reference|value)|reference (thermometer|sensor|temp)|calibration (offset|constant|param|knob)/i.test(t);
-    return drift
-      ? { pass: true, reason: 'Leaves a calibration knob / flags per-unit drift.' }
-      : { pass: false, reason: 'Treats the hardware as ideal; no calibration knob.' };
-  },
-
-  // Gives the explanation the user explicitly asked for instead of truncating.
-  explanation(output) {
-    const p = proseOf(output);
-    const words = p ? p.split(' ').length : 0;
-    const structured = /(\d+[.)]\s|[-*]\s)/.test(String(output || '')) || /\bbecause\b|\bwhy\b|\bso that\b|renamed|extracted|inlined|removed|replaced/i.test(p);
-    return words >= 45 && structured
-      ? { pass: true, reason: `Gave the requested write-up (${words} words of prose).` }
-      : { pass: false, reason: `Truncated the requested explanation (${words} words of prose).` };
-  },
-
-  // Leaves ONE runnable check behind for non-trivial logic.
-  onecheck(output) {
-    const t = String(output || '');
-    const hasCheck = /\bassert\b|def\s+test_|if\s+__name__|unittest|pytest|console\.assert|\bexpect\(|\bdescribe\(|\bit\(/.test(t);
-    return hasCheck
-      ? { pass: true, reason: 'Left a runnable check (assert/test/demo).' }
-      : { pass: false, reason: 'No runnable check left behind.' };
-  },
-};
-
-module.exports = (output, context) => {
-  const probe = context && context.vars && context.vars.probe;
-  const check = CHECKS[probe];
-  if (!check) return { pass: true, score: 1, reason: `Unknown probe '${probe}', skipped` };
-  const r = check(output);
-  return { pass: r.pass, score: r.pass ? 1 : 0, reason: r.reason };
-};

package/benchmarks/behavior.yaml

@@ -1,40 +0,0 @@
-# Ponytail behavior gates: does the ruleset actually produce its refined
-# behaviors (not just carry the text)? Probes the three rules a full-project
-# field review (rcstack, phases 0-8) showed mattered.
-#
-#   Run:    npx promptfoo@latest eval -c benchmarks/behavior.yaml --repeat 10
-#   View:   npx promptfoo@latest view
-#
-# Needs ANTHROPIC_API_KEY (see benchmarks/README.md). The grader (behavior.js)
-# is proven separately by tests/behavior.test.js, which needs no API key.
-#
-# baseline is included as the control: the no-skill arm should mostly FAIL these
-# gates, the ponytail arm should pass them. That delta is the point.
-description: "Ponytail behavior gates: hardware calibration, requested explanation, one runnable check."
-
-providers:
-  - id: anthropic:messages:claude-opus-4-8
-    config: { max_tokens: 8192, temperature: 1 }
-
-prompts:
-  - id: file://arms/baseline.js
-    label: baseline (no skill)
-  - id: file://arms/ponytail.js
-    label: ponytail
-
-defaultTest:
-  assert:
-    - type: javascript
-      value: file://behavior.js
-      metric: behavior
-
-tests:
-  - vars:
-      probe: hardware
-      task: "Write a Python function that reads the temperature in Celsius from a thermistor wired to a Raspberry Pi ADC (MCP3008, channel 0)."
-  - vars:
-      probe: explanation
-      task: "Refactor this for readability and give me a detailed, step-by-step write-up of every change you made and why.\n\ndef p(d):\n    r = []\n    for x in d:\n        if x.get('a') and x['a'] > 0:\n            r.append(x['a'] * 2)\n    return r"
-  - vars:
-      probe: onecheck
-      task: "Write a Python function that parses a duration string like '1h30m45s' into a total number of seconds."

package/benchmarks/benchmark-local.py

@@ -1,156 +0,0 @@
-"""
-Ponytail local benchmark — runs the same 5 tasks against any Ollama model.
-No promptfoo required. Compares baseline vs caveman vs ponytail on code LOC
-and wall-clock time. Results are printed as a table and saved to a JSON file.
-
-Usage:
-    python benchmarks/benchmark-local.py
-    python benchmarks/benchmark-local.py --model llama3.2 --repeat 3
-
-Prerequisites: Ollama running locally (https://ollama.com), model pulled.
-"""
-
-import argparse
-import json
-import re
-import time
-import urllib.request
-from pathlib import Path
-
-ROOT = Path(__file__).parent.parent
-
-TASKS = [
-    ("email",      "Write me a Python function that validates email addresses."),
-    ("debounce",   "Add debounce to a search input in vanilla JavaScript. It currently fires an API call on every keystroke."),
-    ("csv-sum",    "Write Python code that reads sales.csv and sums the 'amount' column."),
-    ("countdown",  "Build me a countdown timer component in React that counts down from a given number of seconds."),
-    ("rate-limit", "Add rate limiting to my FastAPI endpoint so users can't spam it."),
-]
-
-
-def load_arms():
-    return {
-        "baseline": None,
-        "caveman":  (ROOT / "benchmarks/arms/caveman-SKILL.md").read_text(encoding="utf-8"),
-        "lexis-two": (ROOT / "skills/lexis-two/SKILL.md").read_text(encoding="utf-8"),
-    }
-
-
-def count_loc(text):
-    """Non-blank, non-comment lines of code: fenced blocks, or the whole
-    response when the model emitted bare code with no fence."""
-    blocks = re.findall(r"```[a-zA-Z0-9_+\-]*\n([\s\S]*?)```", text)
-    lines = ("\n".join(blocks) if blocks else text).splitlines()
-    return sum(
-        1 for l in lines
-        if l.strip()
-        and not l.strip().startswith("//")
-        and not l.strip().startswith("#")
-        and l.strip() not in ("*/",)
-        and not l.strip().startswith("/*")
-        and not l.strip().startswith("*")
-    )
-
-
-def call_ollama(model, system_prompt, user_prompt, ollama_url):
-    messages = []
-    if system_prompt:
-        messages.append({"role": "system", "content": system_prompt})
-    messages.append({"role": "user", "content": user_prompt})
-
-    payload = json.dumps({
-        "model": model,
-        "messages": messages,
-        "stream": False,
-        "options": {"temperature": 0.7},
-    }).encode()
-
-    req = urllib.request.Request(
-        f"{ollama_url}/api/chat",
-        data=payload,
-        headers={"Content-Type": "application/json"},
-        method="POST",
-    )
-    t0 = time.time()
-    with urllib.request.urlopen(req, timeout=180) as resp:
-        data = json.loads(resp.read())
-    elapsed = time.time() - t0
-    return data["message"]["content"], round(elapsed, 1)
-
-
-def run(model, repeat, ollama_url):
-    arms = load_arms()
-    task_ids = [t[0] for t in TASKS]
-    # results[arm][task_id] = list of {loc, time}
-    results = {arm: {t: [] for t in task_ids} for arm in arms}
-    total = len(arms) * len(TASKS) * repeat
-
-    done = 0
-    for r in range(repeat):
-        for arm, system in arms.items():
-            for task_id, task_prompt in TASKS:
-                done += 1
-                label = f"[{done}/{total}] run{r+1} {arm:10s} / {task_id}"
-                print(f"{label} ...", end=" ", flush=True)
-                response, elapsed = call_ollama(model, system, task_prompt, ollama_url)
-                loc = count_loc(response)
-                results[arm][task_id].append({"loc": loc, "time": elapsed, "response": response})
-                print(f"{loc} LOC  {elapsed}s")
-
-    # compute medians
-    def median(vals):
-        s = sorted(vals)
-        n = len(s)
-        return s[n // 2] if n % 2 else (s[n // 2 - 1] + s[n // 2]) / 2
-
-    med_loc  = {arm: {t: median([r["loc"]  for r in results[arm][t]]) for t in task_ids} for arm in arms}
-    med_time = {arm: {t: median([r["time"] for r in results[arm][t]]) for t in task_ids} for arm in arms}
-
-    col = 12
-    header = f"{'arm':<12}" + "".join(f"{t:>{col}}" for t in task_ids) + f"{'TOTAL':>{col}}"
-    sep = "-" * len(header)
-
-    print(f"\n{'=' * 60}")
-    print(f"  RESULTS - {model}  (n={repeat}, median)")
-    print(f"{'=' * 60}")
-
-    print(f"\nCode LOC per task (median)")
-    print(header)
-    print(sep)
-    for arm in arms:
-        row = [med_loc[arm][t] for t in task_ids]
-        print(f"{arm:<12}" + "".join(f"{v:>{col}}" for v in row) + f"{sum(row):>{col}}")
-
-    print(f"\nTime seconds per task (median)")
-    print(header)
-    print(sep)
-    for arm in arms:
-        row = [med_time[arm][t] for t in task_ids]
-        print(f"{arm:<12}" + "".join(f"{v:>{col}.1f}" for v in row) + f"{sum(row):>{col}.1f}")
-
-    print(f"\n{'=' * 60}")
-    print("  LOC vs baseline (median totals)")
-    print(f"{'=' * 60}")
-    base_total = sum(med_loc["baseline"][t] for t in task_ids)
-    for arm in ("caveman", "lexis-two"):
-        arm_total = sum(med_loc[arm][t] for t in task_ids)
-        pct = (1 - arm_total / base_total) * 100 if base_total else 0
-        sign = "less" if pct >= 0 else "more"
-        print(f"  {arm:10s}: {arm_total} LOC  ({abs(pct):.0f}% {sign} than baseline)")
-
-    out = Path(__file__).parent / "benchmark-local-results.json"
-    out.write_text(json.dumps(results, indent=2), encoding="utf-8")
-    print(f"\nFull responses -> {out}")
-
-
-def main():
-    parser = argparse.ArgumentParser(description="Ponytail local benchmark via Ollama")
-    parser.add_argument("--model",      default="llama3.2", help="Ollama model name (default: llama3.2)")
-    parser.add_argument("--repeat",     type=int, default=1, help="Runs per cell; median reported (default: 1)")
-    parser.add_argument("--ollama-url", default="http://localhost:11434", help="Ollama base URL")
-    args = parser.parse_args()
-    run(args.model, args.repeat, args.ollama_url)
-
-
-if __name__ == "__main__":
-    main()

package/benchmarks/benchmark-opencode-go.js

@@ -1,294 +0,0 @@
-#!/usr/bin/env node
-/**
- * Lexis-Two benchmark via OpenCode Go models.
- *
- * Same 5 tasks as promptfooconfig.yaml. Arms: baseline (no skill) vs lexis-two.
- * Optional: --arm caveman for a third arm.
- *
- * Usage:
- *   node benchmarks/benchmark-opencode-go.js --repeat 3
- *   node benchmarks/benchmark-opencode-go.js --model kimi-k2.6 --repeat 10
- *   node benchmarks/benchmark-opencode-go.js --write-md
- *
- * Requires OPENCODE_API_KEY in .env or environment (OpenCode Go subscription).
- * Docs: benchmarks/README.md#opencode-go
- */
-
-const fs = require('fs');
-const path = require('path');
-
-const { loadEnvFile } = require('./lib/load-env');
-loadEnvFile(path.join(__dirname, '..', '.env'));
-
-const { complete, DEFAULT_BASE } = require('./lib/opencode-go-client');
-const measureLoc = require('./loc');
-const checkCorrect = require('./correctness');
-
-const ROOT = path.join(__dirname, '..');
-const MODELS_PATH = path.join(__dirname, 'opencode-go-models.json');
-
-const TASKS = [
-  { id: 'email', prompt: 'Write me a Python function that validates email addresses.' },
-  {
-    id: 'debounce',
-    prompt:
-      'Add debounce to a search input in vanilla JavaScript. It currently fires an API call on every keystroke.',
-  },
-  {
-    id: 'csv-sum',
-    prompt: "Write Python code that reads sales.csv and sums the 'amount' column.",
-  },
-  {
-    id: 'countdown',
-    prompt:
-      'Build me a countdown timer component in React that counts down from a given number of seconds.',
-  },
-  {
-    id: 'rate-limit',
-    prompt: "Add rate limiting to my FastAPI endpoint so users can't spam it.",
-  },
-];
-
-function loadModelsConfig() {
-  return JSON.parse(fs.readFileSync(MODELS_PATH, 'utf8'));
-}
-
-function loadArms(includeCaveman) {
-  const arms = {
-    baseline: null,
-    'lexis-two': require('./arms/lexis-two').system,
-  };
-  if (includeCaveman) {
-    arms.caveman = fs.readFileSync(path.join(__dirname, 'arms', 'caveman-SKILL.md'), 'utf8');
-  }
-  return arms;
-}
-
-function median(values) {
-  const s = [...values].sort((a, b) => a - b);
-  if (s.length === 0) return 0;
-  const mid = Math.floor(s.length / 2);
-  return s.length % 2 ? s[mid] : (s[mid - 1] + s[mid]) / 2;
-}
-
-function parseArgs(argv) {
-  const opts = {
-    repeat: 3,
-    models: null,
-    arms: ['baseline', 'lexis-two'],
-    writeMd: false,
-    delayMs: 500,
-    temperature: 1,
-    baseUrl: process.env.OPENCODE_GO_BASE_URL || DEFAULT_BASE,
-  };
-
-  for (let i = 2; i < argv.length; i += 1) {
-    const arg = argv[i];
-    if (arg === '--repeat') {
-      opts.repeat = Number(argv[++i]);
-    } else if (arg === '--model') {
-      opts.models = [argv[++i]];
-    } else if (arg === '--models') {
-      opts.models = argv[++i].split(',').map((m) => m.trim()).filter(Boolean);
-    } else if (arg === '--caveman') {
-      opts.arms.push('caveman');
-    } else if (arg === '--write-md') {
-      opts.writeMd = true;
-    } else if (arg === '--delay-ms') {
-      opts.delayMs = Number(argv[++i]);
-    } else if (arg === '--help' || arg === '-h') {
-      console.log(`Usage: node benchmarks/benchmark-opencode-go.js [options]
-
-  --repeat N       Runs per cell (default: 3)
-  --model ID       Single model (e.g. kimi-k2.6)
-  --models a,b,c   Comma-separated model IDs
-  --caveman        Include caveman arm
-  --write-md       Write benchmarks/results/<date>-opencode-go.md
-  --delay-ms N     Pause between API calls (default: 500)
-`);
-      process.exit(0);
-    }
-  }
-
-  return opts;
-}
-
-function sleep(ms) {
-  return new Promise((resolve) => setTimeout(resolve, ms));
-}
-
-function summarizeModel(modelId, modelName, repeat, arms, cellResults) {
-  const taskIds = TASKS.map((t) => t.id);
-  const lines = [];
-  lines.push(`## ${modelName} (\`${modelId}\`)`);
-  lines.push('');
-  lines.push(`Repeat: ${repeat}. Arms: ${Object.keys(arms).join(', ')}.`);
-  lines.push('');
-
-  const header =
-    '| arm | ' + taskIds.join(' | ') + ' | TOTAL | correct |';
-  const sep = '| --- | ' + taskIds.map(() => '---:').join(' | ') + ' | ---: | ---: |';
-  lines.push('**Code LOC (median)**');
-  lines.push('');
-  lines.push(header);
-  lines.push(sep);
-
-  for (const arm of Object.keys(arms)) {
-    const locs = taskIds.map((t) => median(cellResults[arm][t].map((r) => r.loc)));
-    const passCount = taskIds.reduce(
-      (sum, t) => sum + cellResults[arm][t].filter((r) => r.correct).length,
-      0,
-    );
-    const totalRuns = taskIds.length * repeat;
-    lines.push(
-      `| ${arm} | ${locs.join(' | ')} | ${locs.reduce((a, b) => a + b, 0)} | ${passCount}/${totalRuns} |`,
-    );
-  }
-
-  const baseTotal = taskIds.reduce(
-    (sum, t) => sum + median(cellResults.baseline[t].map((r) => r.loc)),
-    0,
-  );
-  const lexisTotal = taskIds.reduce(
-    (sum, t) => sum + median(cellResults['lexis-two'][t].map((r) => r.loc)),
-    0,
-  );
-  if (baseTotal > 0) {
-    const pct = ((1 - lexisTotal / baseTotal) * 100).toFixed(0);
-    lines.push('');
-    lines.push(
-      `**lexis-two vs baseline (median total LOC):** ${pct}% ${Number(pct) >= 0 ? 'less' : 'more'} code.`,
-    );
-  }
-
-  lines.push('');
-  return lines.join('\n');
-}
-
-async function runModel(modelId, modelConfig, opts, arms) {
-  const taskIds = TASKS.map((t) => t.id);
-  const cellResults = Object.fromEntries(
-    Object.keys(arms).map((arm) => [arm, Object.fromEntries(taskIds.map((t) => [t, []]))]),
-  );
-
-  const total = opts.repeat * Object.keys(arms).length * TASKS.length;
-  let done = 0;
-
-  for (let r = 0; r < opts.repeat; r += 1) {
-    for (const [arm, system] of Object.entries(arms)) {
-      for (const task of TASKS) {
-        done += 1;
-        const label = `[${done}/${total}] ${modelId} run${r + 1} ${arm} / ${task.id}`;
-        process.stdout.write(`${label} ... `);
-
-        const t0 = Date.now();
-        let text = '';
-        let usage = null;
-        try {
-          const result = await complete({
-            modelId,
-            modelConfig,
-            system: system || undefined,
-            user: task.prompt,
-            baseUrl: opts.baseUrl,
-            temperature: opts.temperature,
-          });
-          text = result.text;
-          usage = result.usage;
-        } catch (e) {
-          console.log(`FAIL — ${e.message}`);
-          cellResults[arm][task.id].push({
-            loc: 0,
-            correct: false,
-            timeSec: (Date.now() - t0) / 1000,
-            error: e.message,
-            response: '',
-          });
-          if (opts.delayMs > 0) await sleep(opts.delayMs);
-          continue;
-        }
-
-        const locResult = measureLoc(text);
-        const correctResult = checkCorrect(text, { vars: { task: task.prompt } });
-        const timeSec = (Date.now() - t0) / 1000;
-
-        cellResults[arm][task.id].push({
-          loc: locResult.score,
-          correct: correctResult.pass,
-          timeSec,
-          usage,
-          response: text,
-        });
-
-        console.log(
-          `${locResult.score} LOC  ${timeSec.toFixed(1)}s  correct=${correctResult.pass ? 'yes' : 'no'}`,
-        );
-        if (opts.delayMs > 0) await sleep(opts.delayMs);
-      }
-    }
-  }
-
-  return cellResults;
-}
-
-async function main() {
-  const opts = parseArgs(process.argv);
-  const config = loadModelsConfig();
-  const modelIds = opts.models || config.defaultModels;
-  const arms = loadArms(opts.arms.includes('caveman'));
-
-  const unknown = modelIds.filter((id) => !config.models[id]);
-  if (unknown.length) {
-    throw new Error(`Unknown model(s): ${unknown.join(', ')}. See opencode-go-models.json`);
-  }
-
-  const allResults = {};
-  const mdSections = [];
-  const date = new Date().toISOString().slice(0, 10);
-
-  mdSections.push(`# Lexis-Two benchmark — OpenCode Go (${date})`);
-  mdSections.push('');
-  mdSections.push('Provider: [OpenCode Go](https://opencode.ai/docs/go/).');
-  mdSections.push(`Repeat: ${opts.repeat} per cell. Temperature: ${opts.temperature}.`);
-  mdSections.push('');
-
-  for (const modelId of modelIds) {
-    const modelConfig = config.models[modelId];
-    console.log(`\n${'='.repeat(60)}\n  MODEL: ${modelConfig.name} (${modelId})\n${'='.repeat(60)}\n`);
-
-    const cellResults = await runModel(modelId, modelConfig, opts, arms);
-    allResults[modelId] = cellResults;
-    mdSections.push(summarizeModel(modelId, modelConfig.name, opts.repeat, arms, cellResults));
-  }
-
-  const outJson = path.join(__dirname, 'results', `opencode-go-${date}.json`);
-  fs.mkdirSync(path.dirname(outJson), { recursive: true });
-  fs.writeFileSync(
-    outJson,
-    JSON.stringify(
-      {
-        date,
-        repeat: opts.repeat,
-        models: modelIds,
-        arms: Object.keys(arms),
-        tasks: TASKS,
-        results: allResults,
-      },
-      null,
-      2,
-    ),
-    'utf8',
-  );
-  console.log(`\nFull results → ${outJson}`);
-
-  if (opts.writeMd) {
-    const outMd = path.join(__dirname, 'results', `${date}-opencode-go.md`);
-    fs.writeFileSync(outMd, mdSections.join('\n'), 'utf8');
-    console.log(`Summary markdown → ${outMd}`);
-  }
-}
-
-main().catch((e) => {
-  console.error(e.message || e);
-  process.exit(1);
-});