The trader labels crypto news published after 2026-10-16 15:00 with
the configured model (category and BTC direction) and, four hours
later, backfills BTC/ETH 1m opens at publish, +5m, +1h and +4h from
the klines table. A drawer on the trading page shows the cumulative
returns of trading the labelled direction, after fees. Nothing is
traded; this only collects an out-of-sample record.
Move running, running_changed_at and capital_usdt from the account to
each trading symbol; the migration copies the account capital to every
symbol and leaves them all stopped. Each symbol is sized against its
own capital with a 3x notional cap, and the capitals together must not
exceed account equity. Scheduling, dry-run decisions and the executor
follow the per-symbol flag. The global start/stop button is replaced by
start/stop and capital controls on each symbol's plan card.
Sync account fills into a new trading_fills table every 60s and
reconstruct closed positions from them, so positions opened outside
the program are included and external closes get an exit price.
Positions link to plans by order id. The history drawer gains symbol,
close-date, outcome and source filters, a summary bar and pagination.
When the limit price sat near the far edge of the zone, the stop beyond
the far edge was well inside normal 5m noise (plan #34: 0.11%). The stop
is now the farther of far edge +/- 0.5 x ATR and entry +/- 1 x ATR.
- The model gives a zone and a limit price inside it (below the mark for
longs, above for shorts); the executor places the GTC limit order with
the reduce-only stop right away instead of waiting for a 5m
confirmation and entering at market, so entries pay maker fees
- Stop beyond the far edge of the zone by 0.5 x ATR14(5m), computed with
the quantity at submission and rejected above 1%
- Unfilled limits are cancelled at expiry; a rejected entry cancels the
plan instead of being retried every round
- The model now submits a pending setup (direction, zone, confirm price,
validity); the executor enters at market once a 5m close confirms a
dip into support or a rejection from resistance, and cancels the setup
when the zone breaks, the trigger is missed or the stop is too far
- Stop beyond the confirmation extreme by 0.5 x ATR14(5m), skipped above
1%; fixed take-profit ladders from the fill price (long 60/30/10 at
+0.5/0.75/1%, short 80/20 at -0.5/0.75%); 4h time stop
- While holding, the model may only keep or exit
- Drop the long-term angle from the program, API, tables and page
- Executor reconciles each symbol to its desired orders: journaled ap{id}
client ids, reduce-only quantity stop placed before entries, make-before-
break stop moves, breakeven after TP1, orphan cancel, -2021 market close
- Plan lifecycle: proposed plans are adopted only if the position is
unchanged; holding-mode plans may only tighten the stop
- Program rules: time stop, short-term invalidation close, long-term 4h
review, reevaluate conditions, takeover of unmanaged positions
- Trigger and routine analysis scheduling with a 10 min gap, daily cap and
bounded retries
- Plan endpoint and plan status, fills and countdowns on the trading page
The analyst prompts the model with trading rules, published skills,
account sizing inputs and prefetched market data, exposes read-only
tools plus submit_trade_plan, and validates and sizes the submitted plan
in pure functions covered by pytest. Manual analyses run as dry runs
while trading is stopped; the trading page shows the latest plan and an
analysis detail drawer.
eezd