oanda: retry once on transient 401/5xx/network faults in candle fetch

The practice API rejects ~15-20 requests/day with a spurious 401
"Insufficient authorization" while the same token succeeds on adjacent
requests; each one silently cost a full scan cycle on that timeframe.
One retry after RETRY_DELAY_S (2 s) absorbs these plus transient
5xx/network faults. Real credential failures fail both attempts and
raise as before; other 4xx (bad request, 429) are never retried.

Tests: transient-401 recovery, persistent-401 raise, 400 not retried.

Claude-Session: https://claude.ai/code/session_01Tujtmmhxj9mxKjPFSoVjmP

providers/oanda.py

@@ -8,6 +8,7 @@ Oanda's candle JSON, and exposes the real bid/ask spread from MBA candles.
 """
 
 import logging
+import time
 from datetime import datetime
 from typing import Dict, Optional
 
@@ -31,6 +32,7 @@ class OandaDataProvider(BaseDataProvider):
 
     name = "oanda"
     DATA_ERROR = OandaDataError
+    RETRY_DELAY_S = 2.0
 
     OANDA_GRANULARITY = {
         Timeframe.M1: "M1",
@@ -124,11 +126,35 @@ class OandaDataProvider(BaseDataProvider):
         else:
             params["count"] = min(count, self.MAX_BARS_PER_REQUEST)
 
-        try:
-            resp = self._session.get(url, params=params, timeout=30)
-        except requests.RequestException as e:
-            raise OandaDataError(
-                f"Oanda candle fetch failed for {instrument}: {e}") from e
+        # One retry absorbs Oanda's sporadic spurious 401s (~15-20/day on
+        # the practice API — the same token succeeds on adjacent requests)
+        # plus transient 5xx/network faults. A real credential problem
+        # fails both attempts and raises exactly as before. Other 4xx
+        # (bad request, 429) are never retried.
+        last_err: Optional[OandaDataError] = None
+        for attempt in range(2):
+            if attempt:
+                time.sleep(self.RETRY_DELAY_S)
+            try:
+                resp = self._session.get(url, params=params, timeout=30)
+            except requests.RequestException as e:
+                last_err = OandaDataError(
+                    f"Oanda candle fetch failed for {instrument}: {e}")
+                last_err.__cause__ = e
+                continue
+            if resp.status_code == 401 or resp.status_code >= 500:
+                last_err = OandaDataError(
+                    f"Oanda candle fetch failed for {instrument}: "
+                    f"HTTP {resp.status_code}: {resp.text[:300]}")
+                if attempt == 0:
+                    logger.warning(
+                        f"Oanda fetch for {instrument} got HTTP "
+                        f"{resp.status_code}; retrying in "
+                        f"{self.RETRY_DELAY_S}s")
+                continue
+            break
+        else:
+            raise last_err
 
         if resp.status_code != 200:
             raise OandaDataError(

test_all.py

@@ -3453,6 +3453,89 @@ def _():
     assert abs(spread - 0.30) < 0.01, f"Expected spread ~0.30, got {spread}"
 
 
+def _make_oanda_provider(responses):
+    """Bare OandaDataProvider whose session pops canned responses in order."""
+    provider = providers.oanda.OandaDataProvider.__new__(
+        providers.oanda.OandaDataProvider)
+    provider.config = PlatformConfig()
+    provider._base_url = "https://test"
+    provider._cache = {}
+    provider._cache_timestamps = {}
+    provider._cache_outputsize = {}
+    provider._cache_lock = threading.Lock()
+    provider._inflight = {}
+    provider._spread_cache = {}
+    queue = list(responses)
+    provider._session = type("S", (), {
+        "get": lambda self, *a, **k: queue.pop(0),
+        "headers": {},
+    })()
+    return provider
+
+
+def _oanda_resp(status_code, candles=None, text=""):
+    return type("MockResp", (), {
+        "status_code": status_code,
+        "text": text,
+        "json": lambda self: {"candles": candles or [], "instrument": "XAU_USD"},
+    })()
+
+
+_OANDA_OK_CANDLE = {
+    "complete": True,
+    "time": "2026-07-20T10:00:00.000000000Z",
+    "mid": {"o": "2400.00", "h": "2405.00", "l": "2398.00", "c": "2403.00"},
+    "bid": {"o": "2399.85", "h": "2404.85", "l": "2397.85", "c": "2402.85"},
+    "ask": {"o": "2400.15", "h": "2405.15", "l": "2398.15", "c": "2403.15"},
+    "volume": 1234,
+}
+
+
+@test("providers.oanda: transient 401 is retried once and recovers")
+def _():
+    provider = _make_oanda_provider([
+        _oanda_resp(401, text='{"errorMessage":"Insufficient authorization"}'),
+        _oanda_resp(200, candles=[_OANDA_OK_CANDLE]),
+    ])
+    orig_sleep = providers.oanda.time.sleep
+    slept = []
+    providers.oanda.time.sleep = lambda s: slept.append(s)
+    try:
+        df = provider._fetch_oanda_candles("XAU/USD", Timeframe.H1, 300)
+    finally:
+        providers.oanda.time.sleep = orig_sleep
+    assert len(df) == 1, f"Expected recovered fetch with 1 bar, got {len(df)}"
+    assert slept == [providers.oanda.OandaDataProvider.RETRY_DELAY_S], \
+        f"Expected one retry sleep, got {slept}"
+
+
+@test("providers.oanda: persistent 401 raises after retry; 4xx never retried")
+def _():
+    orig_sleep = providers.oanda.time.sleep
+    providers.oanda.time.sleep = lambda s: None
+    try:
+        provider = _make_oanda_provider([
+            _oanda_resp(401, text='{"errorMessage":"Insufficient authorization"}'),
+            _oanda_resp(401, text='{"errorMessage":"Insufficient authorization"}'),
+        ])
+        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)
+
+        # Non-auth 4xx must fail immediately — only one response queued,
+        # so a retry attempt would IndexError on the empty queue.
+        provider = _make_oanda_provider([_oanda_resp(400, text="bad request")])
+        try:
+            provider._fetch_oanda_candles("XAU/USD", Timeframe.H1, 300)
+            assert False, "HTTP 400 should raise OandaDataError"
+        except providers.oanda.OandaDataError as e:
+            assert "400" in str(e)
+    finally:
+        providers.oanda.time.sleep = orig_sleep
+
+
 @test("providers.oanda: instrument name mapping")
 def _():
     provider = providers.oanda.OandaDataProvider.__new__(