# Pocket Network Backtest Reconciler

> Pocket Network Backtest Reconciler is a paid API for AI agents from agent.pocket.network, paid per call via x402, $0.005/call, status unknown (last checked 2026-10-10).

Deterministically recomputes trading backtest metrics from raw trade data and flags any claimed statistics (net profit, win rate, drawdown, etc.) as MATCH or MISMATCH

## Facts

- Endpoint: POST https://agent.pocket.network/v1/backtest-reconcile-v1?utm_source=zero.xyz
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-10
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/pocket-network-backtest-reconciler-02b2f723
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_1KuvTsxtYR5p1TU1Wvb6C

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability pocket-network-backtest-reconciler-02b2f723 -d '<json body>'
```

Example prompt: I got a TradingView strategy backtest claiming 68% win rate, 2.3 profit factor, and $42,500 net profit — here's the 'List of Trades' CSV export. Can you recompute all those numbers from the raw trades and tell me which claims match and which don't? Use 0.1% commission per trade and $100,000 starting capital.

## When to prefer this

Use this endpoint when you need deterministic, offline verification of trading backtest statistics — particularly when auditing strategy seller claims, reviewing fund pitch decks, or sanity-checking your own TradingView exports. It requires no live market data feed and is the right choice when you want a MATCH/MISMATCH verdict with per-trade P&L granularity rather than simply rerunning a backtest engine. Prefer it over manual spreadsheet audits or re-running the strategy in a simulator when you already have the trade list and want fast, programmatic verification.

## Known failure modes

- Missing required trades data (neither trades nor trades_csv provided) — returns validation error
- Malformed CSV format not matching TradingView export structure — returns parse error
- Claimed metric keys not recognized — unrecognized fields silently skipped or flagged
- Overlapping trade timestamps with single_position=true — flagged as anomaly in findings
- Tolerance_pct set to 0 may cause spurious MISMATCHes due to floating-point precision

## How this service works

Do the claimed backtest numbers follow from the trades? Send a TradingView "List of trades" CSV or a JSON trade list with the claimed metrics; get net profit, win rate, profit factor, drawdown and per-trade P&L recomputed, each claim marked MATCH or MISMATCH, and findings such as cost-free backtests. Deterministic, no market data. POST /v1/reconcile.

## Output

A structured report containing recomputed values for each claimed metric (net profit, net profit %, gross profit, gross loss, total trades, win rate, profit factor, max drawdown, avg trade, largest win, largest loss), a MATCH or MISMATCH label per claim based on the tolerance threshold, per-trade P&L breakdown, and notable findings such as overlapping positions or cost-free assumptions.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "trades": {
   "type": "array",
   "items": {
    "type": "object",
    "properties": {
     "n": {
      "description": "Trade number."
     },
     "qty": {
      "type": "number"
     },
     "side": {
      "enum": [
       "long",
       "short"
      ],
      "type": "string"
     },
     "exit_time": {
      "type": "string"
     },
     "commission": {
      "type": "number"
     },
     "entry_time": {
      "type": "string"
     },
     "exit_price": {
      "type": "number"
     },
     "entry_price": {
      "type": "number"
     },
     "reported_pnl": {
      "type": "number"
     }
    }
   },
   "description": "The trades as a JSON list, in place of trades_csv."
  },
  "claimed": {
   "type": "object",
   "description": "The claimed metrics to check, any of net_profit, net_profit_pct, gross_profit, gross_loss, total_trades, win_rate, profit_factor, max_drawdown, max_drawdown_pct, avg_trade, largest_win, largest_loss."
  },
  "commission": {
   "type": "object",
   "properties": {
    "type": {
     "enum": [
      "percent",
      "per_contract",
      "cash_per_order"
     ],
     "type": "string"
    },
    "value": {
     "type": "number"
    }
   },
   "description": "Commission applied to every trade."
  },
  "trades_csv": {
   "type": "string",
   "description": "A TradingView Strategy Tester \"List of trades\" CSV export."
  },
  "tolerance_pct": {
   "type": "number",
   "default": 0.5,
   "description": "How far a claim may differ, in percent, and still MATCH."
  },
  "initial_capital": {
   "type": "number",
   "description": "Starting capital for the percentage figures."
  },
  "single_position": {
   "type": "boolean",
   "default": true,
   "description": "Flag overlapping trades."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/pocket-network-backtest-reconciler-02b2f723/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agent.pocket.network](https://www.zero.xyz/host/agent.pocket.network/llms.txt)