refactor(signals): split the Track Record tab and cut the backtest page down

One tab stacked three things that all called themselves a track record:
realized paper P&L, setup-outcome grading under the rejected take-profit model,
and the backtest portfolio simulation. Split into Setups | Paper Trades |
Backtest, one subject each. `track` stays the Paper Trades slug so the legacy
/performance redirect keeps working. The grading diagnostic and its Evaluate /
Reset controls go with Backtest, not Paper Trades — reset_track_record deletes
trade_setups, not paper trades.

BacktestPanel 439 -> 175 lines. Its run settings alone were 106 lines of
hand-rolled sr-only radio cards for two binary choices; they are now two
Dropdowns and a button on one wrapping row, with the per-option prose moved into
the existing explainer. The amber warnings survive as a conditional slot, so a
non-default choice still announces itself but the common path is silent.

The recommendation printed eight findings at equal weight, burying the verdict
in tuning detail. `topic` now splits them: production, benchmark and robustness
stay inline, gate/exit/cutoff collapse behind a disclosure, and any WARNING or
LAGS item is promoted out of the collapsed group regardless of topic. No topic
chips — every backend string already self-prefixes, so a chip would render
"GATE | Gate: ...".

Portfolio metrics are now two tiers: five headline tiles for what the book
returned, then a smaller labelled row for how good that return was (Sortino,
Calmar (MAR), Gain/Pain, Profit Factor $, EV/trade). Reports cached before those
metrics existed hide the second row rather than showing a half-populated line of
dashes.

Extracted EquityCurveChart, PortfolioMonitorPanel and BacktestRecommendationCard,
plus a StatTile primitive and shared formatters for the duplication in the files
this touched. DashboardPage and OpenTradesPanel deliberately keep their own
copies — migrating them is separate scope.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
This commit is contained in:
2026-08-11 22:09:23 +02:00
co-authored by Claude Opus 5
parent 442dc3f04b
commit 13a984a84d
10 changed files with 599 additions and 397 deletions
+65 -329
View File
@@ -9,35 +9,8 @@ import { Disclosure } from '../ui/Disclosure';
import { Dropdown } from '../ui/Dropdown';
import { Section } from '../ui/Section';
import { useToast } from '../ui/Toast';
import type { BacktestCurvePoint, BacktestPortfolioMonitorRun } from '../../lib/types';
function fmtR(v: number | null | undefined): string {
if (v === null || v === undefined) return '—';
return `${v > 0 ? '+' : ''}${v.toFixed(2)}R`;
}
function fmtPct(v: number | null): string {
return v === null ? '—' : `${v.toFixed(1)}%`;
}
function fmtMoney(v: number | null | undefined): string {
if (v === null || v === undefined) return '—';
return v.toLocaleString('en-US', { minimumFractionDigits: 2, maximumFractionDigits: 2 });
}
function fmtSignedPct(v: number | null | undefined): string {
if (v === null || v === undefined) return '—';
return `${v > 0 ? '+' : ''}${v.toFixed(1)}%`;
}
function fmtDrawdown(v: number | null | undefined): string {
return v === null || v === undefined ? '—' : `-${Math.abs(v).toFixed(1)}%`;
}
function fmtDays(v: number | null | undefined): string {
return v === null || v === undefined ? '—' : `${v.toFixed(1)}d`;
}
function rColor(v: number | null): string {
if (v === null) return 'text-gray-400';
if (v > 0) return 'text-emerald-400';
if (v < 0) return 'text-red-400';
return 'text-gray-300';
}
import { BacktestRecommendationCard } from './BacktestRecommendationCard';
import { PortfolioMonitorPanel } from './PortfolioMonitorPanel';
function timeAgo(iso: string): string {
const mins = Math.floor((Date.now() - new Date(iso).getTime()) / 60_000);
@@ -48,95 +21,14 @@ function timeAgo(iso: string): string {
return `${Math.floor(hrs / 24)}d ago`;
}
function Stat({ label, value, valueClass = 'text-gray-100', sub }: {
label: string; value: string; valueClass?: string; sub?: string;
}) {
return (
<div className="glass p-4">
<p className="section-index">{label}</p>
<p className={`num mt-1.5 text-2xl font-semibold ${valueClass}`}>{value}</p>
{sub && <p className="mt-1 text-xs text-gray-500">{sub}</p>}
</div>
);
}
function curvePath(
points: BacktestCurvePoint[],
min: number,
max: number,
w: number,
h: number,
pad: number,
startMs: number,
endMs: number,
): string {
if (points.length < 2) return '';
const span = Math.max(max - min, 1);
const timeSpan = Math.max(endMs - startMs, 1);
return points
.map((p, i) => {
const t = new Date(p.date).getTime();
const x = pad + ((t - startMs) / timeSpan) * (w - pad * 2);
const value = p.return_pct ?? 0;
const y = pad + (1 - (value - min) / span) * (h - pad * 2);
return `${i === 0 ? 'M' : 'L'}${x.toFixed(1)},${y.toFixed(1)}`;
})
.join(' ');
}
function EquityCurveChart({ run }: { run: BacktestPortfolioMonitorRun }) {
const portfolio = run.equity_curve ?? [];
const benchmark = run.benchmark_curve ?? [];
const values = [...portfolio, ...benchmark]
.map((p) => p.return_pct)
.filter((v): v is number => v !== null && v !== undefined);
if (portfolio.length < 2 || values.length === 0) {
return <Callout variant="empty">No equity curve points for this selection.</Callout>;
}
const min = Math.min(0, ...values);
const max = Math.max(0, ...values);
const times = [...portfolio, ...benchmark]
.map((p) => new Date(p.date).getTime())
.filter((v) => Number.isFinite(v));
if (times.length === 0) {
return <Callout variant="empty">No dated equity curve points for this selection.</Callout>;
}
const startMs = Math.min(...times);
const endMs = Math.max(...times);
const w = 720;
const h = 240;
const pad = 28;
const portfolioPath = curvePath(portfolio, min, max, w, h, pad, startMs, endMs);
const benchmarkPath = curvePath(benchmark, min, max, w, h, pad, startMs, endMs);
const lastPortfolio = portfolio[portfolio.length - 1]?.return_pct ?? null;
const lastBenchmark = benchmark[benchmark.length - 1]?.return_pct ?? run.spy_return_pct;
return (
<div className="glass overflow-hidden">
<div className="flex flex-wrap items-center justify-between gap-3 border-b border-white/[0.05] px-4 py-3">
<div>
<p className="text-sm font-semibold text-gray-100">{run.label}</p>
<p className="text-[11px] text-gray-500">{run.start_date} - {run.end_date}</p>
</div>
<div className="flex gap-4 text-xs">
<span className="text-blue-300">Portfolio {fmtSignedPct(lastPortfolio)}</span>
<span className="text-gray-400">S&P 500 {fmtSignedPct(lastBenchmark)}</span>
</div>
</div>
<svg viewBox={`0 0 ${w} ${h}`} className="h-64 w-full" role="img" aria-label="Portfolio return compared with S&P 500">
<line x1={pad} y1={h - pad} x2={w - pad} y2={h - pad} stroke="rgba(255,255,255,0.12)" />
<line x1={pad} y1={pad} x2={pad} y2={h - pad} stroke="rgba(255,255,255,0.12)" />
{benchmarkPath && (
<path d={benchmarkPath} fill="none" stroke="rgba(156,163,175,0.9)" strokeWidth="2" strokeDasharray="5 5" />
)}
<path d={portfolioPath} fill="none" stroke="rgb(96,165,250)" strokeWidth="3" />
<text x={pad} y={pad - 8} className="fill-gray-500 text-[10px]">{fmtSignedPct(max)}</text>
<text x={pad} y={h - 8} className="fill-gray-500 text-[10px]">{fmtSignedPct(min)}</text>
</svg>
</div>
);
}
const TARGET_MODEL_OPTIONS = [
{ value: 'production_gtl', label: 'Live GTL — production' },
{ value: 'structural_sr', label: 'Structural S/R — comparison' },
];
const CADENCE_OPTIONS = [
{ value: 'weekly', label: 'Weekly — default' },
{ value: 'daily', label: 'Daily — research' },
];
export function BacktestPanel() {
const { data: report, isLoading } = useBacktestReport();
@@ -187,114 +79,58 @@ export function BacktestPanel() {
fundamentals are held neutral (no point-in-time history). ~6 months is roughly one market regime,
so read it as directional.
</p>
<p className="mt-2 max-w-2xl text-xs text-gray-400">
<strong className="text-gray-300">Live GTL</strong> is the exact target path the scanner and the
scheduled backtest use; <strong className="text-gray-300">Structural S/R</strong> is a comparison
arm sourcing targets from chart structure. <strong className="text-gray-300">Weekly</strong> steps
five sessions at a time and is what the server runs; <strong className="text-gray-300">Daily</strong>
{' '}is roughly 5× the replay work.
</p>
</Disclosure>
<div className="flex w-full flex-col gap-3 sm:w-auto sm:items-end">
<fieldset className="grid w-full grid-cols-1 gap-2 sm:w-[34rem] sm:grid-cols-2">
<legend className="mb-1 text-[11px] font-medium uppercase tracking-wider text-gray-500">
Target model for this run
</legend>
<label
className={`cursor-pointer rounded-lg border px-3 py-2 transition-colors focus-within:ring-2 focus-within:ring-blue-400/60 ${
targetModel === 'production_gtl'
? 'border-blue-400/60 bg-blue-500/10'
: 'border-white/10 bg-white/[0.03] hover:border-white/20'
}`}
>
<input
className="sr-only"
type="radio"
name="backtest-target-model"
value="production_gtl"
checked={targetModel === 'production_gtl'}
onChange={() => setTargetModel('production_gtl')}
/>
<span className="flex items-center justify-between gap-2 text-sm font-medium text-gray-100">
Live GTL
<span className="rounded-full border border-blue-400/40 bg-blue-400/10 px-2 py-0.5 text-[9px] font-semibold uppercase tracking-widest text-blue-300">
Production
</span>
</span>
<span className="mt-1 block text-[11px] leading-4 text-gray-500">
Exact target path used by the live scanner and scheduled backtest.
</span>
</label>
<label
className={`cursor-pointer rounded-lg border px-3 py-2 transition-colors focus-within:ring-2 focus-within:ring-amber-400/60 ${
targetModel === 'structural_sr'
? 'border-amber-400/50 bg-amber-500/10'
: 'border-white/10 bg-white/[0.03] hover:border-white/20'
}`}
>
<input
className="sr-only"
type="radio"
name="backtest-target-model"
value="structural_sr"
checked={targetModel === 'structural_sr'}
onChange={() => setTargetModel('structural_sr')}
/>
<span className="text-sm font-medium text-gray-200">Structural S/R</span>
<span className="mt-1 block text-[11px] leading-4 text-gray-500">
Comparison only; uses chart structure as the target source.
</span>
</label>
</fieldset>
<fieldset className="grid w-full grid-cols-2 gap-2 sm:w-[34rem]">
<legend className="mb-1 text-[11px] font-medium uppercase tracking-wider text-gray-500">
Entry cadence
</legend>
<label
className={`cursor-pointer rounded-lg border px-3 py-2 transition-colors focus-within:ring-2 focus-within:ring-blue-400/60 ${
cadence === 'weekly'
? 'border-blue-400/60 bg-blue-500/10'
: 'border-white/10 bg-white/[0.03] hover:border-white/20'
}`}
>
<input
className="sr-only"
type="radio"
name="backtest-cadence"
value="weekly"
checked={cadence === 'weekly'}
onChange={() => setCadence('weekly')}
/>
<span className="flex items-center justify-between gap-2 text-sm font-medium text-gray-100">
Weekly
<span className="rounded-full border border-blue-400/40 bg-blue-400/10 px-2 py-0.5 text-[9px] font-semibold uppercase tracking-widest text-blue-300">
Default
</span>
</span>
<span className="mt-1 block text-[11px] leading-4 text-gray-500">
Resource-safe server run at five-session intervals.
</span>
</label>
<label
className={`cursor-pointer rounded-lg border px-3 py-2 transition-colors focus-within:ring-2 focus-within:ring-amber-400/60 ${
cadence === 'daily'
? 'border-amber-400/50 bg-amber-500/10'
: 'border-white/10 bg-white/[0.03] hover:border-white/20'
}`}
>
<input
className="sr-only"
type="radio"
name="backtest-cadence"
value="daily"
checked={cadence === 'daily'}
onChange={() => setCadence('daily')}
/>
<span className="text-sm font-medium text-gray-200">Daily</span>
<span className="mt-1 block text-[11px] leading-4 text-amber-300/80">
Research run: roughly 5× the replay work; prefer the offline snapshot runner.
</span>
</label>
</fieldset>
{/* flex-wrap is load-bearing: two dropdowns plus the button overflow a
narrow viewport otherwise. */}
<div className="flex flex-wrap items-end gap-2">
<div className="flex flex-col gap-1 text-[11px] uppercase tracking-wider text-gray-500">
<label htmlFor="backtest-target-model">Target model</label>
<Dropdown
id="backtest-target-model"
className="w-56 normal-case tracking-normal"
value={targetModel}
onChange={(v) => setTargetModel(v as BacktestTargetModel)}
options={TARGET_MODEL_OPTIONS}
/>
</div>
<div className="flex flex-col gap-1 text-[11px] uppercase tracking-wider text-gray-500">
<label htmlFor="backtest-cadence">Entry cadence</label>
<Dropdown
id="backtest-cadence"
className="w-44 normal-case tracking-normal"
value={cadence}
onChange={(v) => setCadence(v as BacktestCadence)}
options={CADENCE_OPTIONS}
/>
</div>
<Button onClick={() => run.mutate()} loading={run.isPending} className="shrink-0">
{run.isPending ? 'Starting…' : report ? 'Re-run backtest' : 'Run backtest'}
</Button>
</div>
</div>
{/* Only surfaced for non-default choices — zero noise on the common path,
but a non-production selection still announces itself, which is what
the old always-amber cards were really for. */}
{(cadence === 'daily' || targetModel === 'structural_sr') && (
<div className="space-y-1 text-[11px] text-amber-300/80">
{cadence === 'daily' && (
<p>Daily replays ~5× the work prefer the offline snapshot runner.</p>
)}
{targetModel === 'structural_sr' && (
<p>Comparison arm not the live scanner's target path.</p>
)}
</div>
)}
{isLoading && <Callout variant="empty">Loading…</Callout>}
{!isLoading && !report && (
@@ -319,118 +155,18 @@ export function BacktestPanel() {
</span>
</p>
{monitor && monitorRun ? (
<div className="space-y-3">
<div className="flex flex-wrap items-end justify-between gap-3">
<div>
<p className="section-index">Portfolio monitor</p>
<p className="mt-1 text-xs text-gray-500">
Simulated book for the selected strategy and lookback, compared with the S&P 500.
</p>
</div>
<div className="flex flex-wrap gap-2">
<div className="flex flex-col gap-1 text-[11px] uppercase tracking-wider text-gray-500">
<label htmlFor="monitor-strategy">Strategy</label>
<Dropdown
id="monitor-strategy"
className="w-64 normal-case tracking-normal"
value={activeStrategy}
onChange={setSelectedStrategy}
options={monitor.strategies.map((s) => ({
value: s.strategy,
label: `${s.is_production ? 'Production: ' : ''}${s.label}`,
}))}
/>
</div>
<div className="flex flex-col gap-1 text-[11px] uppercase tracking-wider text-gray-500">
<label htmlFor="monitor-lookback">Lookback</label>
<Dropdown
id="monitor-lookback"
className="w-36 normal-case tracking-normal"
value={activeLookback}
onChange={setSelectedLookback}
options={monitor.lookbacks.map((l) => ({ value: l.lookback, label: l.label }))}
/>
</div>
</div>
</div>
<PortfolioMonitorPanel
monitor={monitor}
monitorRun={monitorRun}
activeStrategy={activeStrategy}
activeLookback={activeLookback}
onStrategyChange={setSelectedStrategy}
onLookbackChange={setSelectedLookback}
/>
<div className="grid gap-3 sm:grid-cols-2 lg:grid-cols-5">
<Stat label="CAGR" value={fmtSignedPct(monitorRun.cagr_pct)} valueClass={rColor(monitorRun.cagr_pct)} />
<Stat label="Sharpe" value={monitorRun.sharpe == null ? '—' : monitorRun.sharpe.toFixed(2)} />
<Stat label="Max Drawdown" value={fmtDrawdown(monitorRun.max_drawdown_pct)} valueClass="text-amber-400" />
<Stat
label="Total Return"
value={fmtSignedPct(monitorRun.total_return_pct)}
valueClass={rColor(monitorRun.total_return_pct)}
sub={`vs S&P 500 ${fmtSignedPct(monitorRun.spy_return_pct)}`}
/>
<Stat label="Trades" value={String(monitorRun.trades)} sub={`${fmtPct(monitorRun.win_rate)} win rate`} />
</div>
<EquityCurveChart run={monitorRun} />
<p className="text-[11px] text-gray-500">
Avg hold {fmtDays(monitorRun.avg_hold_days)} · Best {fmtR(monitorRun.best_trade_r)} / Worst{' '}
{fmtR(monitorRun.worst_trade_r)} · Avg P&amp;L per trade {fmtMoney(monitorRun.avg_trade_pnl)}
{monitorRun.reentry_policy === 'gate_reset' ? (
<> · Re-entry after gate failure and fresh qualification</>
) : null}
</p>
{monitorRun.yearly_returns && monitorRun.yearly_returns.length > 0 && (
<div className="glass overflow-x-auto p-4">
<p className="section-index mb-2">Per-year returns</p>
<div className="flex flex-wrap gap-2">
{monitorRun.yearly_returns.map((y) => (
<div key={y.year} className="rounded border border-white/10 px-3 py-1.5">
<span className="num text-xs text-gray-500">{y.year}</span>{' '}
<span className={`num text-sm font-semibold ${rColor(y.return_pct)}`}>
{fmtSignedPct(y.return_pct)}
</span>
</div>
))}
</div>
</div>
)}
{monitor.note && <p className="text-[11px] text-gray-600">{monitor.note}</p>}
</div>
) : (
<Callout variant="empty">
This report predates the portfolio monitor re-run the backtest to populate it.
</Callout>
{report.recommendation && (
<BacktestRecommendationCard recommendation={report.recommendation} />
)}
{report.recommendation && report.recommendation.items.length > 0 && (
<div className="glass border border-blue-400/20 p-4">
<p className="section-index">What this backtest recommends</p>
{report.recommendation.headline && (
<p className="mt-1.5 text-sm font-semibold text-gray-100">
{report.recommendation.headline}
</p>
)}
<ul className="mt-2 space-y-1">
{report.recommendation.items.map((item) => (
<li
key={item.topic + item.text}
className={`text-xs ${item.text.includes('WARNING') || item.text.includes('LAGS') ? 'text-amber-400' : 'text-gray-400'}`}
>
{item.text}
</li>
))}
</ul>
{report.recommendation.note && (
<p className="mt-2 text-[11px] text-gray-600">{report.recommendation.note}</p>
)}
</div>
)}
<p className="text-[11px] text-gray-600">
Strategy research gate tuning, exit sweeps, factor rank-IC now runs locally against a
database snapshot (see README). This page keeps only what says whether the promoted strategy
is worth trading; your realized results up top show what it is actually delivering.
</p>
</>
)}
</div>