providers: keep real news bars (snap-back bad-print rule), Oanda retry ladder, scan_kind=failed
2026-09-07 signal-log inspection follow-up — three fixes that do not depend on sample size.
- providers/base.py: the signal-side 10σ outlier filter is now a bad-print filter. A >10σ
close-to-close bar is dropped only when the NEXT close snaps back ≥80% of the way
(OUTLIER_SIGMA / OUTLIER_REVERT_FRACTION); persisting moves and the newest bar are kept.
The unconditional rule deleted ~36 real M5 news bars/yr in the backtester (whole-frame σ)
and a different ~24/yr live (fetch-window σ) — e.g. the 2026-09-04 12:30 UTC NFP bar
vanished from M5+M15 and the 12:35 scan was a byte-identical repeat of 12:30. 3-yr Oanda
drops are now M5 2 / M15 1 / H1 0.
- providers/oanda.py: transient 401/5xx/network faults retry along RETRY_DELAYS_S=(2,5,10)s
under RETRY_BUDGET_S=45s. 11 boundary scans in two days had lost their primary frame at
xx:00:22–:26 UTC; one 2 s retry could not outlast the top-of-hour blip.
- signal_aggregator/_log_signal: a scan whose primary fetch failed logs scan_kind='failed'
(price 0, no signal); analyze_signal_log.parity_report skips it like 'blocked'.
- test_all.py: 466 tests (+6): retry ladder walks all delays, 5xx blip recovers on the third
attempt, retry budget stops the ladder, persisting/newest/partially-retraced 10σ bars kept,
failed-scan row kind, parity skip.
- CLAUDE.md: cleaning rule, retry ladder, failed scan kind, dated current-state note.
Book impact at $0.65 (rule 1 still passes everywhere, both halves positive):
12mo M5 557/+112.21/PF1.56 → 560/+108.81/1.54 M15 397/+73.93/1.53 → 398/+74.61/1.53 H1 identical
3yr M5 857/+161.3/1.53 → 870/+153.6/1.50 M15 1086/+148.7/1.37 → 1092/+151.9/1.38
H1 255/+70.5/1.98 → 253/+70.0/1.98 H4 113/+22.7/1.63 → 114/+21.7/1.59
Only trades on the previously-deleted event bars move; the pinned M5/M15 CSVs are no longer
byte-reproducible and should be regenerated at the next re-pin.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01NDnBxJ2y8GRUM6ZNFJs1hZ
This commit is contained in:
Harwinder Sekhon
+162
-4
@@ -2384,6 +2384,55 @@ def _():
|
||||
"snap-back bar after the spike must be kept (two-bar hole regression)"
|
||||
|
||||
|
||||
@test("Outlier filter keeps a >10σ bar whose move PERSISTS (real news bar)")
|
||||
def _():
|
||||
# 2026-09-07 audit: the 12:30 UTC NFP bar (-1.7%, ~23σ) was deleted
|
||||
# from the signal-side M5/M15 data, hiding the day's most violent bar
|
||||
# from ATR/exhaustion math. Three years of Oanda XAU bars: 155 such
|
||||
# M5 bars, 7 snapped back. A level shift that holds is real price.
|
||||
provider = TwelveDataProvider(PlatformConfig())
|
||||
df = make_ohlcv(n=300, seed=3)
|
||||
k = 150
|
||||
jump_ts = df.index[k]
|
||||
shift = df["Close"].iloc[k - 1] * 0.05 # ~+5% step on a ~0.1%-σ series
|
||||
df.loc[df.index[k]:, ["Open", "High", "Low", "Close"]] += shift
|
||||
cleaned = provider._validate_and_clean(df, "XAU/USD", Timeframe.H1)
|
||||
assert jump_ts in cleaned.index, \
|
||||
"a 10σ move that the next close confirms must be KEPT"
|
||||
assert len(cleaned) == len(df), "no bar may be dropped for a real move"
|
||||
|
||||
|
||||
@test("Outlier filter keeps the NEWEST >10σ bar (no successor to judge it)")
|
||||
def _():
|
||||
# Live at 12:35 on a release day the crash bar IS the last closed
|
||||
# bar. Dropping it would make the scan run on pre-release data (the
|
||||
# 2026-09-04 12:35 scan was a byte-identical repeat of 12:30). With
|
||||
# no next close available the bar is treated as real; a true bad
|
||||
# print on the newest bar is caught on the following scan.
|
||||
provider = TwelveDataProvider(PlatformConfig())
|
||||
df = make_ohlcv(n=300, seed=3)
|
||||
last_ts = df.index[-1]
|
||||
df.loc[last_ts, ["Open", "High", "Low", "Close"]] = df["Close"].iloc[-2] * 1.05
|
||||
cleaned = provider._validate_and_clean(df, "XAU/USD", Timeframe.H1)
|
||||
assert last_ts in cleaned.index, "newest 10σ bar must be kept"
|
||||
|
||||
|
||||
@test("Outlier filter: partial snap-back (below the revert fraction) is a real move")
|
||||
def _():
|
||||
provider = TwelveDataProvider(PlatformConfig())
|
||||
df = make_ohlcv(n=300, seed=3)
|
||||
k = 150
|
||||
base = df["Close"].iloc[k - 1]
|
||||
spike_ts = df.index[k]
|
||||
# +5% spike, next close gives back only half — a violent real move,
|
||||
# not a bad print (revert fraction 0.5 < OUTLIER_REVERT_FRACTION 0.8).
|
||||
df.loc[spike_ts, ["Open", "High", "Low", "Close"]] = base * 1.05
|
||||
df.loc[df.index[k + 1]:, ["Open", "High", "Low", "Close"]] += base * 0.025
|
||||
cleaned = provider._validate_and_clean(df, "XAU/USD", Timeframe.H1)
|
||||
assert spike_ts in cleaned.index, "half-retraced spike is real price"
|
||||
assert provider.OUTLIER_REVERT_FRACTION == 0.8
|
||||
|
||||
|
||||
@test("Cache: pre-boundary snapshot refetched; boundary-complete snapshot served")
|
||||
def _():
|
||||
def bars_ending(last):
|
||||
@@ -3558,20 +3607,26 @@ def _():
|
||||
f"Expected one retry sleep, got {slept}"
|
||||
|
||||
|
||||
@test("providers.oanda: persistent 401 raises after retry; 4xx never retried")
|
||||
@test("providers.oanda: persistent 401 walks the whole retry ladder then raises; 4xx never retried")
|
||||
def _():
|
||||
orig_sleep = providers.oanda.time.sleep
|
||||
providers.oanda.time.sleep = lambda s: None
|
||||
slept = []
|
||||
providers.oanda.time.sleep = lambda s: slept.append(s)
|
||||
try:
|
||||
ladder = providers.oanda.OandaDataProvider.RETRY_DELAYS_S
|
||||
provider = _make_oanda_provider([
|
||||
_oanda_resp(401, text='{"errorMessage":"Insufficient authorization"}'),
|
||||
_oanda_resp(401, text='{"errorMessage":"Insufficient authorization"}'),
|
||||
_oanda_resp(401, text='{"errorMessage":"Insufficient authorization"}')
|
||||
for _ in range(1 + len(ladder))
|
||||
])
|
||||
try:
|
||||
provider._fetch_oanda_candles("XAU/USD", Timeframe.H1, 300)
|
||||
assert False, "Persistent 401 should raise OandaDataError"
|
||||
except providers.oanda.OandaDataError as e:
|
||||
assert "401" in str(e)
|
||||
assert slept == list(ladder), \
|
||||
f"every ladder delay must be slept before giving up, got {slept}"
|
||||
assert ladder == (2.0, 5.0, 10.0), \
|
||||
"ladder is sized to outlast a 10-15 s top-of-hour provider blip"
|
||||
|
||||
# Non-auth 4xx must fail immediately — only one response queued,
|
||||
# so a retry attempt would IndexError on the empty queue.
|
||||
@@ -3585,6 +3640,55 @@ def _():
|
||||
providers.oanda.time.sleep = orig_sleep
|
||||
|
||||
|
||||
@test("providers.oanda: a 5xx blip that clears on the third attempt recovers")
|
||||
def _():
|
||||
# The 2026-09-07 signal-log audit: 11 boundary scans lost their
|
||||
# primary frame because one 2 s retry could not outlast a ~12 s
|
||||
# provider blip. Two failures then success must recover, having
|
||||
# slept exactly the first two ladder steps.
|
||||
orig_sleep = providers.oanda.time.sleep
|
||||
slept = []
|
||||
providers.oanda.time.sleep = lambda s: slept.append(s)
|
||||
try:
|
||||
provider = _make_oanda_provider([
|
||||
_oanda_resp(502, text="bad gateway"),
|
||||
_oanda_resp(503, text="unavailable"),
|
||||
_oanda_resp(200, candles=[_OANDA_OK_CANDLE]),
|
||||
])
|
||||
df = provider._fetch_oanda_candles("XAU/USD", Timeframe.H1, 300)
|
||||
finally:
|
||||
providers.oanda.time.sleep = orig_sleep
|
||||
assert len(df) == 1, "third attempt must return the frame"
|
||||
assert slept == list(
|
||||
providers.oanda.OandaDataProvider.RETRY_DELAYS_S[:2]), slept
|
||||
|
||||
|
||||
@test("providers.oanda: retry budget stops the ladder before a delay would overrun it")
|
||||
def _():
|
||||
# A scan fetches three frames; the whole ladder must stay bounded so
|
||||
# an M5 scan finishes inside its bar. With the clock jumped past the
|
||||
# budget after the first failure, no further attempt (and no sleep)
|
||||
# may happen — the queue holds only ONE response, so a second
|
||||
# attempt would IndexError.
|
||||
orig_sleep = providers.oanda.time.sleep
|
||||
orig_mono = providers.oanda.time.monotonic
|
||||
slept = []
|
||||
ticks = iter([0.0, 10_000.0, 10_000.0, 10_000.0])
|
||||
providers.oanda.time.sleep = lambda s: slept.append(s)
|
||||
providers.oanda.time.monotonic = lambda: next(ticks)
|
||||
try:
|
||||
provider = _make_oanda_provider([_oanda_resp(503, text="unavailable")])
|
||||
try:
|
||||
provider._fetch_oanda_candles("XAU/USD", Timeframe.H1, 300)
|
||||
assert False, "budget exhaustion must raise the last error"
|
||||
except providers.oanda.OandaDataError as e:
|
||||
assert "503" in str(e)
|
||||
finally:
|
||||
providers.oanda.time.sleep = orig_sleep
|
||||
providers.oanda.time.monotonic = orig_mono
|
||||
assert slept == [], "no sleep once the budget cannot fit the next delay"
|
||||
|
||||
|
||||
@test("providers.oanda: instrument name mapping")
|
||||
def _():
|
||||
provider = providers.oanda.OandaDataProvider.__new__(
|
||||
@@ -7772,6 +7876,48 @@ def _():
|
||||
os.remove(path)
|
||||
|
||||
|
||||
@test("signal_log: a scan whose PRIMARY fetch fails is logged as scan_kind 'failed'")
|
||||
def _():
|
||||
# 2026-09-07 audit: 11 rows in two days carried price 0 / score 0 /
|
||||
# NEUTRAL F because the top-of-hour Oanda fetch failed; logged as
|
||||
# ordinary scans they polluted NEUTRAL statistics. They are liveness
|
||||
# evidence and readers skip them like ``blocked``.
|
||||
import signal_log as slog
|
||||
fd, path = tempfile.mkstemp(suffix=".db")
|
||||
os.close(fd)
|
||||
os.remove(path)
|
||||
try:
|
||||
os.environ["SIGNAL_LOG_PATH"] = path
|
||||
os.environ.pop("SIGNAL_LOG_ENABLED", None)
|
||||
cfg = PlatformConfig()
|
||||
cfg.xau_strategy.weekend_filter = False # deterministic on any day
|
||||
cfg.xau_strategy.allowed_weekdays = []
|
||||
agg = SignalAggregator(cfg)
|
||||
agg._get_news_engine = lambda: _NoNews()
|
||||
|
||||
def _boom(*a, **k):
|
||||
raise RuntimeError("HTTP 503 at the boundary")
|
||||
agg.data_provider.fetch_ohlcv = _boom
|
||||
report = agg.analyze_pair(symbol="XAU/USD", log_source="test")
|
||||
assert "Primary timeframe data unavailable" in report.warnings
|
||||
import sqlite3
|
||||
conn = sqlite3.connect(path)
|
||||
row = conn.execute(
|
||||
"SELECT scan_kind, gate_reason, signal, quality FROM signals"
|
||||
).fetchone()
|
||||
conn.close()
|
||||
assert row is not None, "the failed scan must still leave a liveness row"
|
||||
assert row[0] == "failed", f"scan_kind must be 'failed', got {row[0]!r}"
|
||||
assert row[1] == "Primary timeframe data unavailable"
|
||||
assert row[2] == "NEUTRAL" and row[3] == "F"
|
||||
finally:
|
||||
os.environ.pop("SIGNAL_LOG_PATH", None)
|
||||
os.environ.pop("SIGNAL_LOG_ENABLED", None)
|
||||
slog.reset_loggers_for_tests()
|
||||
if os.path.exists(path):
|
||||
os.remove(path)
|
||||
|
||||
|
||||
@test("signal_log parity: analyze_from_dataframes never logs")
|
||||
def _():
|
||||
import signal_log as slog
|
||||
@@ -7985,6 +8131,18 @@ def _():
|
||||
assert "config fingerprint" in d["diffs"] and "action" in d["diffs"]
|
||||
assert rep["rows_per_bar"]["telegram/15min"] == 1.5
|
||||
assert rep["rows_per_bar"]["dashboard/15min"] == 1.0
|
||||
# A ``failed`` row (primary fetch lost, price 0) is liveness evidence,
|
||||
# not a scan: it must not count as a source on its bar.
|
||||
import dataclasses
|
||||
failed = dataclasses.replace(
|
||||
_asl_row(6, t0, bar_ts="2026-08-19T12:30:00+00:00", source="cli",
|
||||
quality="F", setup=False, price=0.0,
|
||||
action="NO TRADE — No clear signal"),
|
||||
scan_kind="failed")
|
||||
rep2 = asl.parity_report(rows + [failed])
|
||||
assert rep2["bars_with_2_sources"] == 2
|
||||
assert "cli/15min" not in rep2["rows_per_bar"]
|
||||
assert len(rep2["divergences"]) == 1
|
||||
|
||||
|
||||
@test("analyze_signal_log: load_rows sees WAL-resident rows and never writes")
|
||||
|
||||
Reference in New Issue
Block a user