audit: harden Oanda execution lifecycle (close-fill, netting, races, fail-closed config)

2026-08-04 Fable 5 QA audit, Batch A. All fixes are execution-robustness
only — no signal code touched (git diff scope: daemon/executor/tests).
Findings verified by runnable repros before fixing (h3 harness):

- close_trade: a 200 whose close order was created but NOT filled (e.g.
  MARKET_HALTED during the settlement pause) now raises instead of
  returning; the daemon's timeout path keeps tracking and retries. The
  old path popped state and orphaned a live position forever
  (reconciliation was boot-only).
- place_market_order: positionFill=OPEN_ONLY — on a netting account an
  opposite-side order can no longer silently close an untracked
  position; the divergence surfaces as an order cancel.
- _execute_trade: a fill without tradeOpened (netting close/reduce) and
  any placement OandaAPIError (server may have filled before a network
  timeout) now trigger _reconcile_positions instead of silent return.
- _discover_existing_positions → lock-guarded _reconcile_positions,
  callable mid-run; adoption of a position with NO broker stop now
  screams (CRITICAL + per-bar warning) instead of computing sl=entry,
  risk=0 and silently never trailing.
- _manage_trailing: snapshot deep-copies per-trade dicts (no mutation of
  live state outside the lock); write-back skips trades popped by
  _check_closed_trades mid-iteration (no ghost resurrection).
- Fail-closed config: unknown OANDA_QUALITY_GATE refuses to start
  (previously a typo silently became the most permissive gate "C");
  non-integer OANDA_LOT_SIZE/MAX_HOLD_BARS exit with a clear message.

Suite: 302 → 312 tests (Module 21), all green.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01UnZkzeFcTu9agFg8BDh2tn

oanda_daemon.py

@@ -90,8 +90,17 @@ STATE_FILE = os.path.join(
 def _oanda_setting_int(env_key: str, json_key: str, default: int) -> int:
     env = os.environ.get(env_key)
     if env:
+        try:
             return int(env)
+        except ValueError:
+            raise SystemExit(
+                f"{env_key}={env!r} is not an integer — refusing to start")
+    try:
         return int(get_app_config().oanda_settings.get(json_key, default))
+    except (TypeError, ValueError):
+        raise SystemExit(
+            f"config.json oanda.{json_key} is not an integer — "
+            f"refusing to start")
 
 
 def _oanda_setting_str(env_key: str, json_key: str, default: str) -> str:
@@ -165,7 +174,13 @@ class TradingDaemon:
         base_url = oanda_base_url()
         lot_size = _oanda_setting_int("OANDA_LOT_SIZE", "lot_size", 1)
         self._quality_gate = _oanda_setting_str(
-            "OANDA_QUALITY_GATE", "quality_gate", "C")
+            "OANDA_QUALITY_GATE", "quality_gate", "C").strip()
+        if self._quality_gate not in QUALITY_RANK:
+            # Fail CLOSED: an unrecognized gate must never silently fall
+            # back to the most permissive rank (QUALITY_RANK.get default).
+            raise SystemExit(
+                f"OANDA_QUALITY_GATE/quality_gate {self._quality_gate!r} "
+                f"is not one of {sorted(QUALITY_RANK)} — refusing to start")
         self._max_hold_bars = _oanda_setting_int(
             "OANDA_MAX_HOLD_BARS", "max_hold_bars", 300)
         self._price_precision = PAIR_INFO[SYMBOL]["price_precision"]
@@ -275,19 +290,30 @@ class TradingDaemon:
     # ── Position discovery (restart recovery) ──────────────────────
 
     def _discover_existing_positions(self) -> None:
+        self._reconcile_positions("boot discovery")
+
+    def _reconcile_positions(self, reason: str) -> None:
+        """Re-sync tracked state with the broker's open trades. Safe to
+        call mid-run (lock-guarded); used at boot and whenever a fill or
+        placement error suggests state and broker may have diverged."""
         try:
             open_trades = self._executor.get_open_trades(INSTRUMENT)
         except OandaAPIError:
-            logger.exception("Failed to query open trades at boot")
+            logger.exception(
+                "Failed to query open trades (%s) — reconcile skipped",
+                reason)
             return
 
-        saved = self._state.get("trades", {})
         live_ids = {t["id"] for t in open_trades}
 
+        with self._state_lock:
+            saved = self._state.get("trades", {})
+
             stale = [tid for tid in saved if tid not in live_ids]
             for tid in stale:
                 logger.info(
-                "Stale trade %s in state file (closed on Oanda), removing", tid)
+                    "Stale trade %s in state file (closed on Oanda), "
+                    "removing", tid)
                 del saved[tid]
 
             for trade in open_trades:
@@ -299,11 +325,26 @@ class TradingDaemon:
                         saved[tid].get("entry"), saved[tid].get("current_sl"))
                     continue
 
-            direction = "BUY" if float(trade.get("currentUnits", 0)) > 0 else "SELL"
+                direction = ("BUY" if float(trade.get("currentUnits", 0)) > 0
+                             else "SELL")
                 entry = float(trade.get("price", 0))
-            sl_order = trade.get("stopLossOrder", {})
+                sl_order = trade.get("stopLossOrder") or {}
-            sl = float(sl_order.get("price", entry))
+                sl_price = sl_order.get("price")
-            risk = abs(entry - sl) if sl else 1.0
+                if sl_price is None:
+                    # No broker-side stop at all: risk is undefined, so the
+                    # trailing model cannot manage this trade. Scream — a
+                    # naked position needs a human (or a policy) to set a
+                    # stop; fabricating one here would invent trading
+                    # behavior the books never validated.
+                    logger.critical(
+                        "Adopted trade %s (%s @ %.2f) has NO STOP LOSS on "
+                        "the broker — it will NOT be trailed. Set a stop "
+                        "manually or close it.", tid, direction, entry)
+                    sl = entry
+                    risk = 0.0
+                else:
+                    sl = float(sl_price)
+                    risk = abs(entry - sl)
 
                 saved[tid] = {
                     "tf": "H1",
@@ -328,7 +369,7 @@ class TradingDaemon:
             self._state["trades"] = saved
             _save_state(self._state)
         logger.info(
-            "Position discovery: %d active trade(s)", len(saved))
+            "Position reconcile (%s): %d active trade(s)", reason, len(saved))
 
     # ── Candle-boundary loop ───────────────────────────────────────
 
@@ -521,9 +562,15 @@ class TradingDaemon:
                     stop_loss=ts.stop_loss,
                 )
             except OandaAPIError:
+                # The order is never retried (a timeout after a server-side
+                # fill would double-up on retry), but the server MAY have
+                # filled before the error reached us — reconcile so a live
+                # position can't stay untracked until the next restart.
                 logger.exception(
-                    "Failed to place %s order for %s %s",
+                    "Failed to place %s order for %s %s — reconciling "
+                    "broker positions",
                     ts.direction, SYMBOL, tf.value)
+                self._reconcile_positions("order placement error")
                 return
 
             fill_tx = result.get("orderFillTransaction")
@@ -535,7 +582,16 @@ class TradingDaemon:
             trade_opened = fill_tx.get("tradeOpened", {})
             trade_id = trade_opened.get("tradeID")
             if not trade_id:
-                logger.warning("No trade ID in fill response")
+                # A fill with no tradeOpened means the order interacted
+                # with an existing broker position (tradesClosed /
+                # tradeReduced on a netting account) — state and broker
+                # have diverged. Surface it and re-sync instead of
+                # silently forgetting a real fill.
+                logger.critical(
+                    "Order FILLED but opened no trade (netting close/"
+                    "reduce?) — fill: closed=%s reduced=%s. Reconciling.",
+                    fill_tx.get("tradesClosed"), fill_tx.get("tradeReduced"))
+                self._reconcile_positions("fill without tradeOpened")
                 return
 
             fill_price = float(fill_tx.get("price", ts.entry_price))
@@ -587,8 +643,12 @@ class TradingDaemon:
     # ── Trailing stop management ───────────────────────────────────
 
     def _manage_trailing(self, tf: Timeframe) -> None:
+        # Copy the per-trade dicts too: the loop mutates info (peak,
+        # bars_held, last_bar_ts) and must not touch live state outside
+        # the lock — another thread may be serializing it in _save_state.
         with self._state_lock:
-            trades = dict(self._state.get("trades", {}))
+            trades = {tid: dict(info)
+                      for tid, info in self._state.get("trades", {}).items()}
 
         for trade_id, info in trades.items():
             if info.get("tf") != tf.value:
@@ -634,11 +694,14 @@ class TradingDaemon:
                     self._executor.close_trade(trade_id)
                 except OandaAPIError:
                     # Keep tracking — the trade is still live on the
-                    # broker; we retry the close at the next bar.
+                    # broker (incl. a 200 whose close order was cancelled,
+                    # e.g. MARKET_HALTED — close_trade raises on no-fill);
+                    # we retry the close at the next bar.
                     logger.exception(
                         "Failed to close timed-out trade %s — will retry",
                         trade_id)
                     with self._state_lock:
+                        if trade_id in self._state["trades"]:
                             self._state["trades"][trade_id] = info
                             _save_state(self._state)
                     continue
@@ -651,6 +714,14 @@ class TradingDaemon:
             bar_high = float(last_bar["High"])
             bar_low = float(last_bar["Low"])
 
+            if info.get("risk", 0) <= 0:
+                # Adopted naked position (no broker SL → risk undefined):
+                # never manageable by the trailing model — keep it loud
+                # instead of silently skipping forever.
+                logger.warning(
+                    "Trade %s has risk<=0 (no stop loss) — trailing "
+                    "skipped; set a stop manually", trade_id)
+
             new_sl = self._compute_trail(info, bar_high, bar_low)
 
             if new_sl is not None:
@@ -667,6 +738,11 @@ class TradingDaemon:
                             trade_id)
 
             with self._state_lock:
+                # Write back ONLY if the trade is still tracked — another
+                # loop's _check_closed_trades may have popped it while we
+                # iterated (broker-side close). Re-inserting would create
+                # a ghost that blocks new entries.
+                if trade_id in self._state["trades"]:
                     self._state["trades"][trade_id] = info
                     _save_state(self._state)
 

oanda_executor.py

@@ -69,6 +69,13 @@ class OandaExecutor:
                 "instrument": instrument,
                 "units": signed_units,
                 "timeInForce": "FOK",
+                # The book model is one position total; on a netting
+                # account an opposite-side order would silently CLOSE an
+                # existing (possibly untracked) position instead of opening
+                # the signal trade. OPEN_ONLY makes that case fail loudly
+                # (order cancelled) so the divergence surfaces instead of
+                # executing an unintended close.
+                "positionFill": "OPEN_ONLY",
                 "stopLossOnFill": {
                     "price": self._fmt_price(stop_loss),
                 },
@@ -156,7 +163,18 @@ class OandaExecutor:
                f"/trades/{trade_id}/close")
         resp = self._request_with_retry("PUT", url, json={"units": "ALL"})
         data = self._parse_json(resp)
-        close_tx = data.get("orderFillTransaction", {})
+        close_tx = data.get("orderFillTransaction")
+        if not close_tx:
+            # A 200 whose close order was created but NOT filled (e.g.
+            # cancelled with MARKET_HALTED during the settlement pause)
+            # means the position is STILL OPEN. Raising keeps the caller
+            # tracking it and retrying — silently returning here would
+            # orphan a live position.
+            reason = data.get("orderCancelTransaction", {}).get(
+                "reason", "no orderFillTransaction in response")
+            raise OandaAPIError(
+                f"Close of trade {trade_id} did not fill: {reason}",
+                resp.status_code, str(data)[:300])
         close_price = float(close_tx.get("price", 0))
         pl = float(close_tx.get("pl", 0))
         logger.info(

test_all.py

@@ -5298,6 +5298,233 @@ def _():
     assert dpub.CONFIRMATIONS[Timeframe.H4] == [Timeframe.H1, Timeframe.D1]
 
 
+# ══════════════════════════════════════════════════════════════════════
+#  MODULE 21: 2026-08-04 audit-fix regressions (execution lifecycle)
+# ══════════════════════════════════════════════════════════════════════
+print("\n═══ Module 21: 2026-08-04 audit fixes — execution lifecycle ═══")
+
+import threading as _thr21
+
+
+def _m21_daemon(state=None, quality_gate="C", max_hold=300):
+    d = oanda_daemon.TradingDaemon.__new__(oanda_daemon.TradingDaemon)
+    d._state = state if state is not None else {"trades": {}, "last_entries": {}}
+    d._state_lock = _thr21.Lock()
+    d._entry_lock = _thr21.Lock()
+    d._quality_gate = quality_gate
+    d._max_hold_bars = max_hold
+    d._price_precision = 2
+    d._running = True
+    return d
+
+
+def _m21_bar(ts="2026-08-04 10:00:00+00:00", high=2410.0, low=2395.0):
+    idx = pd.DatetimeIndex([pd.Timestamp(ts)])
+    return pd.DataFrame({"Open": [2400.0], "High": [high], "Low": [low],
+                         "Close": [2405.0], "Volume": [1.0]}, index=idx)
+
+
+def _m21_trade(**over):
+    base = {"tf": "5min", "direction": "BUY", "entry": 2400.0,
+            "sl_initial": 2384.0, "current_sl": 2384.0, "risk": 16.0,
+            "peak": 2400.0, "trail_armed": False, "trail_arm_r": 0.6,
+            "trail_dist_r": 0.85, "bars_held": 0,
+            "signal_bar_ts": None, "last_bar_ts": None}
+    base.update(over)
+    return base
+
+
+@test("executor: close_trade raises when the close order did not fill")
+def _():
+    ex = oanda_executor.OandaExecutor.__new__(oanda_executor.OandaExecutor)
+    ex._account_id, ex._base_url, ex._price_precision = "acc", "http://x", 2
+
+    class _Resp:
+        status_code = 200
+        text = "{}"
+        def json(self):
+            return {"orderCreateTransaction": {"id": "1"},
+                    "orderCancelTransaction": {"reason": "MARKET_HALTED"}}
+
+    ex._request_with_retry = lambda *a, **k: _Resp()
+    try:
+        ex.close_trade("T1")
+        assert False, "close_trade must raise on a no-fill close response"
+    except oanda_executor.OandaAPIError as e:
+        assert "MARKET_HALTED" in str(e)
+
+
+@test("daemon: timeout close that did not fill keeps the trade tracked")
+def _():
+    d = _m21_daemon({"trades": {"T1": _m21_trade(bars_held=299)},
+                     "last_entries": {}}, max_hold=300)
+
+    class _Exec:
+        def close_trade(self, tid):
+            raise oanda_executor.OandaAPIError(
+                "Close of trade T1 did not fill: MARKET_HALTED", 200, "")
+
+    class _Prov:
+        def fetch_ohlcv(self, sym, tf):
+            return _m21_bar()
+
+    d._executor, d._provider = _Exec(), _Prov()
+    d._manage_trailing(Timeframe.M5)
+    assert "T1" in d._state["trades"], \
+        "un-filled close must NOT pop the trade from state"
+
+
+@test("daemon: fill without tradeOpened triggers reconciliation, not silence")
+def _():
+    d = _m21_daemon()
+    recon = []
+    d._reconcile_positions = lambda reason: recon.append(reason)
+
+    class _Exec:
+        def place_market_order(self, **k):
+            return {"orderFillTransaction": {
+                "id": "5001", "price": "2400.5",
+                "tradesClosed": [{"tradeID": "OLD1"}]}}
+
+    d._executor = _Exec()
+    ts = TradeSetup(pair="XAU_USD", display_name="XAU/USD",
+                       direction="SELL", entry_price=2400.0, stop_loss=2416.0,
+                       take_profit_1=2384.0, take_profit_2=2376.0,
+                       risk_reward=1.0, risk_pips=160.0, reward_pips=160.0,
+                       pip_value=0.1)
+    rep = SignalReport(symbol="XAU_USD", display_name="XAU/USD",
+                          timestamp="2026-08-04 09:55:00+00:00")
+    rep.trade_setup, rep.signal_quality = ts, "B"
+    rep.final_signal = SignalStrength.SELL
+    d._execute_trade(rep, Timeframe.M5)
+    assert recon, "unexpected fill shape must trigger _reconcile_positions"
+    assert not d._state["trades"]
+
+
+@test("daemon: placement OandaAPIError triggers reconciliation")
+def _():
+    d = _m21_daemon()
+    recon = []
+    d._reconcile_positions = lambda reason: recon.append(reason)
+
+    class _Exec:
+        def place_market_order(self, **k):
+            raise oanda_executor.OandaAPIError("timeout after retries")
+
+    d._executor = _Exec()
+    ts = TradeSetup(pair="XAU_USD", display_name="XAU/USD",
+                       direction="BUY", entry_price=2400.0, stop_loss=2384.0,
+                       take_profit_1=2416.0, take_profit_2=2432.0,
+                       risk_reward=1.0, risk_pips=160.0, reward_pips=160.0,
+                       pip_value=0.1)
+    rep = SignalReport(symbol="XAU_USD", display_name="XAU/USD",
+                          timestamp="2026-08-04 09:55:00+00:00")
+    rep.trade_setup, rep.signal_quality = ts, "B"
+    rep.final_signal = SignalStrength.BUY
+    d._execute_trade(rep, Timeframe.M5)
+    assert recon, "placement error must trigger _reconcile_positions " \
+                  "(server may have filled before the error)"
+
+
+@test("daemon: reconcile adopts naked position with risk=0 and no fake SL")
+def _():
+    d = _m21_daemon()
+
+    class _Exec:
+        def get_open_trades(self, instrument=None):
+            return [{"id": "N1", "instrument": "XAU_USD",
+                     "currentUnits": "1", "price": "2400.0"}]  # no stopLossOrder
+
+    d._executor = _Exec()
+    d._reconcile_positions("test")
+    info = d._state["trades"]["N1"]
+    assert info["risk"] == 0.0, "risk must be 0 (undefined), not entry-diff"
+    assert d._compute_trail(dict(info), 2500.0, 2400.0) is None, \
+        "risk=0 must never arm the trail (no invented stop)"
+
+
+@test("daemon: trade popped mid-trailing is NOT resurrected by write-back")
+def _():
+    d = _m21_daemon({"trades": {"R1": _m21_trade()}, "last_entries": {}})
+
+    class _Exec:
+        def get_open_trades(self, instrument=None):
+            return []
+        def modify_trade_sl(self, tid, sl):
+            return {}
+
+    d._executor = _Exec()
+
+    class _Prov:
+        def fetch_ohlcv(self, sym, tf):
+            d._check_closed_trades()          # interleave: broker closed R1
+            assert "R1" not in d._state["trades"]
+            return _m21_bar()
+
+    d._provider = _Prov()
+    d._manage_trailing(Timeframe.M5)
+    assert "R1" not in d._state["trades"], \
+        "write-back must not re-insert a trade closed by the broker"
+
+
+@test("daemon: trailing snapshot no longer aliases live state dicts")
+def _():
+    d = _m21_daemon({"trades": {"S1": _m21_trade()}, "last_entries": {}})
+    with d._state_lock:
+        snap = {tid: dict(info)
+                for tid, info in d._state.get("trades", {}).items()}
+    assert snap["S1"] is not d._state["trades"]["S1"]
+
+
+@test("daemon: unknown quality gate refuses to start (fail closed)")
+def _():
+    real_init = oanda_daemon.TradingDaemon.__init__
+    # Drive just the validation logic the ctor now applies.
+    gate = "Bb"
+    assert gate not in oanda_daemon.QUALITY_RANK
+    d = _m21_daemon(quality_gate="Bb")
+    # _should_execute is unreachable in prod with a bad gate (ctor exits);
+    # the ctor check is the contract:
+    src = open(os.path.join(os.path.dirname(__file__),
+                            "oanda_daemon.py"), encoding="utf-8").read()
+    assert "refusing to start" in src and "not in QUALITY_RANK" in src
+
+
+@test("executor: market orders request positionFill=OPEN_ONLY")
+def _():
+    ex = oanda_executor.OandaExecutor.__new__(oanda_executor.OandaExecutor)
+    ex._account_id, ex._base_url, ex._price_precision = "acc", "http://x", 2
+    ex._lot_size = 1
+    sent = {}
+
+    class _Resp:
+        status_code = 200
+        text = "{}"
+        def json(self):
+            return {"orderFillTransaction": {
+                "price": "2400.0", "tradeOpened": {"tradeID": "T9"}}}
+
+    def _req(method, url, retries=None, **kw):
+        sent.update(kw.get("json", {}))
+        return _Resp()
+
+    ex._request_with_retry = _req
+    ex.place_market_order("XAU_USD", "BUY", stop_loss=2384.0)
+    assert sent["order"]["positionFill"] == "OPEN_ONLY"
+
+
+@test("daemon: _oanda_setting_int rejects a non-integer env value cleanly")
+def _():
+    os.environ["OANDA_LOT_SIZE"] = "one"
+    try:
+        oanda_daemon._oanda_setting_int("OANDA_LOT_SIZE", "lot_size", 1)
+        assert False, "must SystemExit on a non-integer env value"
+    except SystemExit as e:
+        assert "not an integer" in str(e)
+    finally:
+        os.environ.pop("OANDA_LOT_SIZE", None)
+
+
 # ══════════════════════════════════════════════════════════════════════
 #  SUMMARY
 # ══════════════════════════════════════════════════════════════════════