Files
trumpsignal-backend/app/services/recovery.py
T
k 7599d4952d fix(trading): close 3 race / lifecycle bugs in adopt-then-release path
1. recovery.py rehydrated adopted trades with no System-2 ladder
   ─────────────────────────────────────────────────────────────────
   On backend restart, recovery resolved stop_ladder / derisk_ladder /
   addon_ladder / peak_trail from trigger_post.category. Adopted trades
   have trigger_post_id=NULL (the user opened on HL manually, there's no
   source post) so all four resolved to None and the trade restarted as
   a vanilla "stop_loss + max_hold" position — the entire System-2 ladder
   logic silently disappeared across any restart.

   Fix: detect System-2 from the row itself (sys2_mode IS NOT NULL falls
   back to the adopted-category constant), then rebuild the full ladder
   set from frozen leverage + mode. derisk_steps_done / addon_steps_done /
   peak_gain_pct on the row let us pick up exactly where we left off.

2. close_and_finalize raced with release_management
   ─────────────────────────────────────────────────────────────────
   on_price_tick snapshots _watched, evaluates per trade, appends to a
   triggered list, then spawns _fire_close as an async task. If
   release_management runs between the snapshot and _fire_close firing,
   close_and_finalize would still close the HL position the user just
   took back manual control of.

   Fix: atomic claim now requires released_at IS NULL by default. New
   `force=True` parameter on close_and_finalize bypasses the guard for
   the explicit user-close API (manual_close passes it) so a deliberate
   user click still works on a released trade.

3. partial_derisk + pyramid_add raced with release_management
   ─────────────────────────────────────────────────────────────────
   Same race shape: a price tick captured before release could still
   trigger a partial reduce-only close, or pyramid INTO a position the
   user is now driving themselves.

   Fix: both functions return idempotent-success if released_at IS NOT
   NULL — match the closed_at handling we already had.

Tests still 64/64 + preflight + smoke all green.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-26 13:18:48 +08:00

188 lines
8.7 KiB
Python

"""
Startup rehydration: re-register TP/SL + max-hold for every open trade in DB.
Called once from lifespan() after tables are ensured. Without this, any deploy
or crash silently drops TP/SL protection on live positions.
"""
import asyncio
import logging
from datetime import datetime, timezone
from sqlalchemy import select
from app.database import AsyncSessionLocal
from app.models import BotTrade, Post, Subscription
logger = logging.getLogger(__name__)
async def rehydrate_open_trades() -> None:
# Imported locally to avoid circular imports at module load
from app.services.bot_engine import close_and_finalize
from app.services.crypto import decrypt_api_key
from app.services.signal_categories import (
get_stop_ladder as _get_stop_ladder,
sys2_derisk_ladder as _sys2_derisk_ladder,
sys2_addon_ladder as _sys2_addon_ladder,
sys2_peak_trail as _sys2_peak_trail,
)
from app.services.tp_sl_monitor import register_trade
async with AsyncSessionLocal() as db:
# Skip released trades: the user has taken back manual control of
# the HL position; re-registering would re-attach the watchdog and
# silently start managing again after a restart.
result = await db.execute(
select(BotTrade).where(
BotTrade.closed_at.is_(None),
BotTrade.released_at.is_(None),
)
)
open_trades = result.scalars().all()
if not open_trades:
logger.info("Rehydration: no open trades.")
return
now = datetime.now(timezone.utc)
for t in open_trades:
sub_res = await db.execute(
select(Subscription).where(Subscription.wallet_address == t.wallet_address)
)
sub = sub_res.scalar_one_or_none()
if sub is None or not sub.hl_api_key:
logger.warning(
"Open trade %d has no subscription/key — marking as closed(abandoned)", t.id
)
t.closed_at = now.replace(tzinfo=None)
continue
try:
api_key = decrypt_api_key(sub.hl_api_key)
except Exception as exc:
logger.error("Cannot decrypt key for trade %d: %s", t.id, exc)
continue
# Use the leverage snapshot from the trade row (stamped at open time).
# Fall back to current Subscription only for legacy rows (pre-migration 005).
trade_leverage = t.leverage if t.leverage is not None else sub.leverage
# Re-register from the trade's FROZEN exit profile (eff_* columns),
# NOT the live Subscription. The trade may be a 90-day System-2
# reversal; using sub.* would rehydrate it with the user's Trump
# stop (1.5%) and 7-day max-hold — silently rewriting its risk on
# every restart. eff_* is stamped at open and never changes.
#
# Legacy rows (opened before this migration) have NULL eff_* —
# fall back to the Subscription so they still get *some* watcher.
eff_sl = t.eff_stop_loss_pct if t.eff_stop_loss_pct is not None else sub.stop_loss_pct
eff_tp = t.eff_take_profit_pct # may legitimately be None (sys2 pure-trail)
eff_tr = t.eff_trailing_stop_pct if t.eff_trailing_stop_pct is not None else sub.trailing_stop_pct
eff_tra = t.eff_trailing_activate_pct if t.eff_trailing_activate_pct is not None else sub.trailing_activate_at_pct
eff_mh = t.eff_max_hold_hours if t.eff_max_hold_hours is not None else (sub.max_hold_hours or 168)
# NOTE: peak_gain_pct is now RESTORED from the row (throttled
# persistence) so a pyramided / in-profit System-2 trade keeps its
# regime across restarts. min_hold still resets on rehydrate, but
# it only matters in the first 30 min of a Trump trade; a restart
# inside that window is rare and the downside (TP can fire early)
# is bounded.
post_res = await db.execute(
select(Post).where(Post.id == t.trigger_post_id)
)
trigger_post = post_res.scalar_one_or_none()
# System-2 detection. Two paths reach here:
# (a) Auto-opened (legacy): trigger_post.category is set
# to e.g. "btc_bottom_reversal_long" → look up via
# the post's category.
# (b) Adopted (current): trigger_post_id is NULL because
# the user opened on HL manually. The trade IS a
# System-2 trade — sys2_mode is non-NULL on the row —
# but it has no source post to read category from.
# Fall back to the adopted-category constant so the
# ladder still rebuilds correctly on restart.
#
# Bug this guards: before this fix, adopted trades restarted
# with stop_ladder=None / derisk=None / addon=None /
# peak_trail=None — the entire System-2 ladder logic was
# silently lost across any backend restart, downgrading the
# trade to a plain stop_loss + max_hold position.
_cat_for_ladders = (
(trigger_post.category if trigger_post else None)
or (
"btc_bottom_reversal_long"
if t.sys2_mode is not None else None
)
)
_stop_ladder = _get_stop_ladder(_cat_for_ladders)
register_trade(
trade_id=t.id,
wallet=t.wallet_address,
api_key=api_key,
leverage=trade_leverage,
asset=t.asset,
side=t.side,
entry_price=t.entry_price,
take_profit_pct=eff_tp,
stop_loss_pct=eff_sl,
trailing_stop_pct=eff_tr,
trailing_activate_at_pct=eff_tra,
invalidation=t.eff_invalidation,
invalidation_price=(
t.eff_invalidation_price
if t.eff_invalidation_price is not None
else (trigger_post.invalidation_price if trigger_post else None)
),
min_hold_until_ts=t.eff_min_hold_until_ts,
stop_ladder=_stop_ladder,
derisk_ladder=(
_sys2_derisk_ladder(t.leverage or 1, t.sys2_mode)
if _stop_ladder else None
),
derisk_done=(t.derisk_steps_done or 0),
addon_ladder=(
_sys2_addon_ladder(t.sys2_mode)
if _stop_ladder else None
),
addon_done=(t.addon_steps_done or 0),
initial_peak=(t.peak_gain_pct or 0.0),
peak_trail=(
_sys2_peak_trail(t.sys2_mode)
if _stop_ladder else None
),
grow_mode=bool(getattr(t, "grow_mode", False)),
)
# Remaining hold from the trade's FROZEN max_hold (e.g. 2160h for
# an sma_reclaim), not the user's Trump setting.
opened_aware = t.opened_at.replace(tzinfo=timezone.utc)
elapsed = (now - opened_aware).total_seconds()
max_hold_seconds = int(eff_mh) * 3600
remaining = max_hold_seconds - elapsed
from app.services.bot_engine import _background_tasks
if remaining <= 0:
logger.info("Trade %d past max-hold on startup — closing now", t.id)
task = asyncio.create_task(
close_and_finalize(
trade_id=t.id, api_key=api_key, leverage=trade_leverage,
asset=t.asset, wallet=t.wallet_address, reason="max_hold_recovery",
)
)
_background_tasks.add(task)
task.add_done_callback(_background_tasks.discard)
else:
async def _delayed_close(trade_id=t.id, key=api_key, lev=trade_leverage,
asset=t.asset, wallet=t.wallet_address, delay=remaining):
await asyncio.sleep(delay)
await close_and_finalize(
trade_id=trade_id, api_key=key, leverage=lev,
asset=asset, wallet=wallet, reason="max_hold",
)
task = asyncio.create_task(_delayed_close())
_background_tasks.add(task)
task.add_done_callback(_background_tasks.discard)
await db.commit()
logger.info("Rehydrated %d open trades.", len(open_trades))