Daily-trend veto on M15 + lot-size / already-open lines (campaign 2026-09-30), and the 2026-10-01 whole-codebase bug review
Two bodies of work that touch the same files, so one commit. Direction and setup-size campaign (2026-09-30 → 10-01, owner's RISK-FIRST rule, written before the runs): - SIGNAL: M15 daily-trend veto (factory override 7, xau_strategy.daily_trend_veto "both"). A finished setup against a clear daily trend (closed D1 bars, Sunday stubs dropped; close vs its 50-bar EMA AND vs the close 60 kept days earlier) is removed as the last step of the core. One definition (signal_aggregator.daily_trend_series) for live, the bar replay and the twin's host side; D1 is a required frame of the M15 scan; mirrored in cuda_signal_kernels.py K2. W3 824 / +205.12R / PF 1.73 / max DD 12.4R vs 1105 / +195.79R / 1.49 / 20.9R; 2019 → 2026 1473 / +223.33R / 1.42 / 41.5R vs 2091 / +192.53R / 1.24 / 64.8R; unseen holdout −4.62R vs −6.63R. - FAILED, not shipped: the veto on M5 (W3 drawdown 10.1R → 15.2R) and on H1 (−9.7R), buy-only and sell-only on M15, the wide-stop cap (xau_strategy.wide_stop_cap_atr stays 0.0, a research knob). - New M15 pins: W2 dfc647ee…, OOS e87b6de1…, W3 ad3b0dbd…. M5 / H1 / H4 pins unchanged. --set xau_strategy.daily_trend_veto=off reproduces the previous M15 pins byte for byte. Twin and reference script MD5-equal on every window; recorder and feature-export parity re-proved; base-rate table rebuilt. - DISPLAY (books byte-identical): exposure.py — the lot size for trade_size.risk_per_trade (new config.json block, off by default, private to the owner) and the count of alerted same-direction plans still open (signals.alerted_at, read-only open_alerted_setups); the daily trend in words on Telegram, the CLI and the dashboard; signals.daily_trend logged. - providers/oanda: a date window with no bars is an empty page, not an error (a D1 pad starting on a Saturday could not be fetched). - Reports only, nothing shipped: seven context screens (no state nominated) and eight outside data sources (none adds a forecast to gold's own daily trend). - Independent verification (report section 5.13): every figure reproduced on both scripts, scoring identical to the previous commit on all four timeframes, no look-ahead. Caveats recorded there: this is a risk filter, not a more accurate direction call; nine tenths of the 2019 → 2026 gain is 2022; the neighbour clause is thin (a simple 100-day average misses the R line by 1.2R); "never adds a trade" is an observation, not a guarantee. Bug review of the whole codebase (2026-10-01). Signal path clean. 17 defects elsewhere, plus 4 found by an independent review of the fixes; all fixed, each with a test; no trade book changed: - telegram_bot: one _deliver_alert for the candle scan and the level break. The row is stamped alerted_at BEFORE the send, on a one-worker alert-db pool, and un-stamped when no chat received it or the task is cancelled mid-stamp, so two alerts at one candle close count each other and no SQLite write runs on the event loop. The 5-bar cooldown counts bars of the scan's own frame (== gpu_backtest._apply_cooldown; clock time released the 22:00 UTC bar after the settlement pause) and is restored from signals.db at start-up. The lot-size line goes to the owner's own chat only (a group the owner ran /autoscan in used to receive it). /status gains a news-model line and escapes failure details. - signal_log: mark_alerted returns the stamp it wrote; unmark_alerted; last_alerted_bars (read-only). - advisory_outcome: candle continuity is judged bar by bar inside the walk; a hole after a trade's exit no longer voids it. The stored-candle replay resolves 108 of 111 logged setups instead of 99, all equal to the live resolver's R. - providers/oanda: an empty date window is accepted only when it is 5 days or shorter and no malformed candle was skipped; a longer one is retried, then refused, instead of being cached as history with a hole. - news_engine: blank RSS titles skipped; one unreadable headline no longer costs the local model its whole batch (checked on the real bundle); model health recorded; no DeepSeek audit call in a process that does not archive; event-direction cache keyed per release; peek_week_events never fetches. - llm_client: chat_json never raises and never logs the API key (requests quotes the Authorization value in InvalidHeader; error bodies are redacted). - signal_aggregator: the scan's news block is guarded; the replay path (use_news=False) assigns exactly the values it did before. - agent_panel: PANEL_PROMPT_VERSION v2.2 — same prompt text, corrected input (event timing over the cached calendar week, headlines newest first). scripts/panel_replay.py replays the logged payload per persona; scripts/label_scan_outcomes.py counts with an ISO cutoff. - test_all.py: no ALTER TABLE … DROP COLUMN (the live box has SQLite 3.34); tests that write Parquet print a notice and return without pyarrow. Verification after the last code change: suite 632 passed, 0 failed (also with both Parquet engines blocked and FB2_BACKEND=cpu, the live box's view); the five reference MD5s reproduce on both backtesters, 0 cache fallbacks; Module 37 green; static Python 3.9 / SQLite 3.34 check clean on every touched file. Evidence: backtest/research/daily_trend_campaign_2026-09-30.md, context_screens_2026-10.md, new_inputs_2026-10.md; CLAUDE.md sections 2, 4, 6, 8, 9, 10 and 11; pair_signals/xauusd.py docstring (M15 override 7).
This commit is contained in:
Harwinder Sekhon
+55
-8
@@ -53,7 +53,10 @@ class DeepSeekClient:
|
||||
daily_cap: int = DEFAULT_DAILY_CAP,
|
||||
enabled: bool = True,
|
||||
):
|
||||
self._api_key = api_key or ""
|
||||
# Whitespace around a key is never part of it, and a trailing line
|
||||
# break (a key pasted from a file) is not a legal header value:
|
||||
# every call would fail before it left the process.
|
||||
self._api_key = (api_key or "").strip()
|
||||
self._model = model
|
||||
self._timeout = timeout
|
||||
self._daily_cap = daily_cap
|
||||
@@ -104,17 +107,36 @@ class DeepSeekClient:
|
||||
self._count += 1
|
||||
return True
|
||||
|
||||
def _redact(self, text: Any) -> str:
|
||||
"""Exception text that is safe to log: never contains the key."""
|
||||
out = str(text)
|
||||
return out.replace(self._api_key, "<api key>") if self._api_key else out
|
||||
|
||||
def chat_json(self, system_prompt: str,
|
||||
user_payload: Dict[str, Any]) -> Optional[Dict[str, Any]]:
|
||||
"""One chat call; returns the model's JSON object or None."""
|
||||
if not self.available or not self._under_cap():
|
||||
"""One chat call; returns the model's JSON object or None.
|
||||
|
||||
Never raises: every caller reads None as "use the fallback", and
|
||||
the news enrichment runs inside a live scan."""
|
||||
if not self.available:
|
||||
return None
|
||||
try:
|
||||
content = json.dumps(user_payload, sort_keys=True)
|
||||
except (TypeError, ValueError) as e:
|
||||
# Before the cap is counted: a payload that cannot be sent
|
||||
# must not spend one of the day's requests.
|
||||
self.last_error = (time.time(), "payload")
|
||||
self._warn_once(
|
||||
"payload", "DeepSeek payload is not JSON-serialisable "
|
||||
"(%s) — call skipped", type(e).__name__)
|
||||
return None
|
||||
if not self._under_cap():
|
||||
return None
|
||||
body = {
|
||||
"model": self._model,
|
||||
"messages": [
|
||||
{"role": "system", "content": system_prompt},
|
||||
{"role": "user",
|
||||
"content": json.dumps(user_payload, sort_keys=True)},
|
||||
{"role": "user", "content": content},
|
||||
],
|
||||
"response_format": {"type": "json_object"},
|
||||
"temperature": 0,
|
||||
@@ -133,19 +155,44 @@ class DeepSeekClient:
|
||||
try:
|
||||
resp = self._session.post(
|
||||
DEEPSEEK_URL, json=body, timeout=self._timeout)
|
||||
except requests.exceptions.InvalidHeader:
|
||||
# requests quotes the offending header VALUE in this error, and
|
||||
# the only header built from configuration is Authorization:
|
||||
# the text would put the API key in the log. Fixed wording.
|
||||
self.last_error = (time.time(), "header")
|
||||
self._warn_once(
|
||||
"header", "DeepSeek call not sent: the API key holds a "
|
||||
"character that is not allowed in an HTTP header (a line "
|
||||
"break?) — check deepseek.api_key / DEEPSEEK_API_KEY")
|
||||
return None
|
||||
except requests.RequestException as e:
|
||||
self.last_error = (time.time(), "network")
|
||||
self._warn_once("network", "DeepSeek call failed: %s", e)
|
||||
self._warn_once("network", "DeepSeek call failed: %s",
|
||||
self._redact(e))
|
||||
return None
|
||||
except Exception as e:
|
||||
# Anything else raised inside the HTTP stack (a header that
|
||||
# cannot be encoded, a transport bug) must not reach a scan
|
||||
# either. Type name only: the text may quote the request.
|
||||
self.last_error = (time.time(), "client")
|
||||
self._warn_once("client", "DeepSeek call failed inside the "
|
||||
"HTTP client: %s", type(e).__name__)
|
||||
return None
|
||||
if resp.status_code != 200:
|
||||
self.last_error = (time.time(), f"http_{resp.status_code}")
|
||||
self._warn_once(
|
||||
f"http_{resp.status_code}",
|
||||
"DeepSeek HTTP %s: %s", resp.status_code, resp.text[:200])
|
||||
"DeepSeek HTTP %s: %s", resp.status_code,
|
||||
# Redact BEFORE cutting: a gateway error page can echo the
|
||||
# request headers, and a key cut at the 200-character
|
||||
# mark would be left partly visible.
|
||||
self._redact(resp.text)[:200])
|
||||
return None
|
||||
try:
|
||||
parsed = self._parse_response(resp.json())
|
||||
except ValueError:
|
||||
except Exception:
|
||||
# ValueError for a body that is not JSON; anything else (a
|
||||
# pathological nesting depth) is just as unusable.
|
||||
parsed = None
|
||||
if parsed is None:
|
||||
self.last_error = (time.time(), "parse")
|
||||
|
||||
Reference in New Issue
Block a user