Files
ForexBot2/app_config.py
T
Harwinder Sekhon 42025da0b0 Local news model: ML-NEWS XAU transformer scores headlines (news_model.py, mode primary)
The owner's DeBERTa-v3-small two-head ONNX model (golden set 72/78, ~72%
agreement with DeepSeek on unseen days) replaces DeepSeek for headline
scoring. DeepSeek keeps event direction, the summary and the dashboard
endpoint.

- news_model.py: vendored ML-NEWS runtime (lazy onnxruntime/tokenizers,
  so the bot starts without them) + load-once, never-raising singleton.
- news_engine: _enrich_headline_scores mode switch (off/fallback/primary),
  _apply_model_sentiment (gold head only: xau_score + XAU entry, never
  USD; not-relevant shows 0.0; never touches _llm_sent_cache),
  _audit_with_deepseek (archive-only labels, deepseek_audit_per_day).
- Owner decision: primary mode writes nothing to logs/newsdata.db except
  audit copies — the model's output is not training data.
- app_config: news_model section (path/threads/mode/deepseek_audit_per_day)
  + NEWS_MODEL_MODE env override; validated at boot.
- news_archive: model rows carry teacher_model xau_transformer@<trained_at>.
- deploy/README-news-model.md (ops for bot + dashboard daemon), unit gets a
  commented NEWS_MODEL_MODE=off line; requirements + onnxruntime, tokenizers.
- test_all.py Module 38 (15 tests, one against the real bundle). Suite 581.
- CLAUDE.md, spec status note, handoff marked implemented.

Books unaffected: news never enters signals; no signal file touched.
2026-09-27 21:02:42 -04:00

709 lines
30 KiB
Python

"""
app_config.py — deployment-settings overlay (config.json)
=========================================================
Loads the gitignored config.json at the repo root ONCE per process.
Deployment surface ONLY: Telegram credentials, data-provider selection
and API keys, scanned pairs/timeframes, per-pair base blocked hours,
alert-quality boot default, log level. Signal logic, weights,
thresholds and gates stay in config.py / pair_signals.
Precedence for every setting: env var → config.json → code default.
A repo-root .env file (gitignored) is loaded at import via setdefault,
so it behaves exactly like real environment variables except that a
real shell export always wins. Secrets have NO code default — with
neither env nor config.json the bot refuses to start
(telegram_bot.main) and data fetches fail with a named error
(data_provider).
Parity contract (test-enforced): with no config.json, or one holding
the config.json.example defaults, every produced PlatformConfig is
byte-identical to the pure-code defaults. apply_pair_overrides() runs
in the pair factory BEFORE the validated per-timeframe deltas, so the
bot, CLI and backtester all see the same overlay (live == backtest).
"""
import json
import logging
import os
from dataclasses import dataclass, field
from typing import Any, Dict, List, Optional
from config import PAIR_INFO, PlatformConfig, Timeframe, XAUUSD
logger = logging.getLogger(__name__)
CONFIG_PATH = os.path.join(
os.path.dirname(os.path.abspath(__file__)), "config.json")
ENV_PATH = os.path.join(
os.path.dirname(os.path.abspath(__file__)), ".env")
def load_dotenv(path: str = ENV_PATH) -> None:
"""Minimal .env loader (no python-dotenv dependency).
KEY=VALUE lines land in os.environ via setdefault — a variable
already exported in the shell always wins, keeping the
env → config.json precedence intact (.env is just a convenient
place to put env vars). Comments, blank lines, ``export `` prefixes
and single/double quotes are handled; anything else is skipped.
"""
try:
with open(path, encoding="utf-8") as fh:
lines = fh.read().splitlines()
except OSError:
return
for line in lines:
line = line.strip()
if not line or line.startswith("#") or "=" not in line:
continue
if line.startswith("export "):
line = line[len("export "):]
key, _, value = line.partition("=")
key, value = key.strip(), value.strip()
if len(value) >= 2 and value[0] == value[-1] and value[0] in "\"'":
value = value[1:-1]
elif value[:1] not in "\"'":
# Unquoted value: whitespace-then-# starts an inline comment
# (KEY=abc # prod). Quote the value to keep a literal " #".
for sep in (" #", "\t#"):
cut = value.find(sep)
if cut != -1:
value = value[:cut].rstrip()
if key:
os.environ.setdefault(key, value)
# Module import == process boot, before any resolver can run.
load_dotenv()
_VALID_QUALITIES = ("A+", "A", "B", "C")
_VALID_LOG_LEVELS = ("DEBUG", "INFO", "WARNING", "ERROR", "CRITICAL")
# Timeframes the bot's candle-boundary scheduler supports (must have
# TF_CONFIRMATIONS entries in telegram_bot.py).
_SCANNABLE_TFS = ("M5", "M15", "H1", "H4")
_KNOWN_TOP = {"telegram", "data_providers", "scanning", "pairs", "log_level",
"oanda", "deepseek", "agent_panel",
# "market_outlook" is TOLERATED but ignored: the AI market
# outlook was removed 2026-09-15 (last commit 2836024). Live
# config.json files still carry the block and must keep
# loading; load_app_config logs one warning when it is there.
"market_outlook",
"violent_watch", "signal_log", "news_archive", "news_model"}
_KNOWN_OANDA = {
# "account_id" is TOLERATED but ignored: it belonged to the auto-
# execution daemon removed 2026-09-03 (last commit 31002cb). The candle
# provider needs only api_token + base_url; older config.json files
# still carry the key and must keep loading.
"account_id", "api_token", "base_url",
}
_KNOWN_DEEPSEEK = {
"api_key", "model", "enabled", "timeout_seconds", "daily_request_cap",
}
_KNOWN_AGENT_PANEL = {
"enabled", "telegram", "dashboard", "min_quality",
"max_panels_per_day", "reuse_ttl_seconds",
"candles_enabled", "candle_bars_primary", "candle_bars_confirm",
"verdict_source", "personas",
}
_KNOWN_VIOLENT_WATCH = {"enabled", "alert_line", "headsup",
"max_headsup_per_day", "headsup_min_level"}
_KNOWN_SIGNAL_LOG = {"enabled", "path", "log_blocked_scans"}
_KNOWN_NEWS_ARCHIVE = {"enabled", "path"}
_KNOWN_NEWS_MODEL = {"path", "threads", "mode", "deepseek_audit_per_day"}
_NEWS_MODEL_MODES = ("off", "fallback", "primary")
_KNOWN_TELEGRAM = {"token", "chat_id", "channel_id", "alert_min_quality"}
_KNOWN_SCANNING = {"pairs", "timeframes"}
_KNOWN_PAIR_KEYS = {"blocked_hours_utc"}
# Violent-move watch (display-only heads-up) — dark by default.
_VIOLENT_WATCH_DEFAULTS = {
"enabled": False,
"alert_line": True,
"headsup": True,
"max_headsup_per_day": 12,
"headsup_min_level": "hot",
}
_VALID_WATCH_LEVELS = ("watch", "hot")
class AppConfigError(Exception):
"""config.json is present but invalid — fail fast at boot."""
@dataclass
class AppConfig:
telegram_token: str = ""
telegram_chat_id: str = ""
telegram_channel_id: str = "" # "" = channel feed disabled
alert_min_quality: str = "C"
active_provider: str = "twelve_data"
streaming_provider: Optional[str] = None # None = active provider
provider_settings: Dict[str, Dict[str, Any]] = field(default_factory=dict)
scan_pairs: List[str] = field(default_factory=lambda: [XAUUSD])
scan_timeframes: List[Timeframe] = field(default_factory=lambda: [
Timeframe.M5, Timeframe.M15, Timeframe.H1, Timeframe.H4])
pair_overrides: Dict[str, Dict[str, Any]] = field(default_factory=dict)
oanda_settings: Dict[str, Any] = field(default_factory=dict)
deepseek_settings: Dict[str, Any] = field(default_factory=dict)
agent_panel_settings: Dict[str, Any] = field(default_factory=dict)
violent_watch_settings: Dict[str, Any] = field(
default_factory=lambda: dict(_VIOLENT_WATCH_DEFAULTS))
signal_log_settings: Dict[str, Any] = field(default_factory=dict)
news_archive_settings: Dict[str, Any] = field(default_factory=dict)
news_model_settings: Dict[str, Any] = field(default_factory=dict)
log_level: str = "INFO"
def _check_keys(section: Dict[str, Any], known: set, where: str) -> None:
if not isinstance(section, dict):
raise AppConfigError(f"config.json: {where} must be a JSON object")
unknown = sorted(set(section) - known)
if unknown:
raise AppConfigError(
f"config.json: unknown key(s) {unknown} in {where}; "
f"known keys: {sorted(known)}")
def load_app_config(path: str = CONFIG_PATH) -> AppConfig:
"""Parse + validate config.json. Missing file → pure defaults."""
app = AppConfig()
if not os.path.exists(path):
logger.warning(
"config.json not found at %s — running on code defaults "
"(secrets must come from environment variables)", path)
return app
try:
with open(path, encoding="utf-8") as fh:
raw = json.load(fh)
except json.JSONDecodeError as e:
raise AppConfigError(f"config.json is not valid JSON: {e}") from e
if not isinstance(raw, dict):
raise AppConfigError("config.json top level must be a JSON object")
_check_keys(raw, _KNOWN_TOP, "top level")
tg = raw.get("telegram", {})
_check_keys(tg, _KNOWN_TELEGRAM, '"telegram"')
app.telegram_token = str(tg.get("token", app.telegram_token))
app.telegram_chat_id = str(tg.get("chat_id", app.telegram_chat_id))
app.telegram_channel_id = str(
tg.get("channel_id", app.telegram_channel_id))
quality = tg.get("alert_min_quality", app.alert_min_quality)
if quality not in _VALID_QUALITIES:
raise AppConfigError(
f'config.json: telegram.alert_min_quality "{quality}" '
f"not in {_VALID_QUALITIES}")
app.alert_min_quality = quality
dp = raw.get("data_providers")
if dp is not None:
if not isinstance(dp, dict):
raise AppConfigError('config.json: "data_providers" must be an object')
app.active_provider = str(dp.get("active", app.active_provider))
app.provider_settings = {}
for name, block in dp.items():
# "active" and "streaming" are reserved scalars, not blocks.
if name in ("active", "streaming"):
continue
if not isinstance(block, dict):
raise AppConfigError(
f'config.json: data_providers.{name} must be an object')
app.provider_settings[name] = dict(block)
if app.active_provider not in app.provider_settings:
raise AppConfigError(
f'config.json: data_providers.active "{app.active_provider}" '
"has no matching provider block")
streaming = dp.get("streaming")
if streaming is not None:
if not isinstance(streaming, str):
raise AppConfigError(
'config.json: data_providers.streaming must be a string '
"(a provider name)")
if streaming not in app.provider_settings:
raise AppConfigError(
f'config.json: data_providers.streaming "{streaming}" '
"has no matching provider block")
app.streaming_provider = streaming
scanning = raw.get("scanning", {})
_check_keys(scanning, _KNOWN_SCANNING, '"scanning"')
if "pairs" in scanning:
pairs = scanning["pairs"]
if not isinstance(pairs, list):
raise AppConfigError('config.json: scanning.pairs must be a list')
bad = [p for p in pairs if p not in PAIR_INFO]
if bad:
raise AppConfigError(
f"config.json: unknown pair(s) {bad} in scanning.pairs; "
f"known: {sorted(PAIR_INFO)}")
app.scan_pairs = list(pairs)
if "timeframes" in scanning:
names = scanning["timeframes"]
if not isinstance(names, list):
raise AppConfigError(
'config.json: scanning.timeframes must be a list')
bad = [n for n in names if n not in _SCANNABLE_TFS]
if bad:
raise AppConfigError(
f"config.json: unsupported timeframe(s) {bad} in "
f"scanning.timeframes; supported: {list(_SCANNABLE_TFS)}")
app.scan_timeframes = [Timeframe[n] for n in names]
pair_section = raw.get("pairs", {})
if not isinstance(pair_section, dict):
raise AppConfigError('config.json: "pairs" must be a JSON object')
for symbol, overrides in pair_section.items():
if symbol not in PAIR_INFO:
raise AppConfigError(
f'config.json: unknown pair "{symbol}" in pairs; '
f"known: {sorted(PAIR_INFO)}")
_check_keys(overrides, _KNOWN_PAIR_KEYS, f'pairs."{symbol}"')
if "blocked_hours_utc" in overrides:
hours = overrides["blocked_hours_utc"]
valid = isinstance(hours, list) and all(
isinstance(h, int) and not isinstance(h, bool)
and 0 <= h <= 23 for h in hours)
if not valid:
raise AppConfigError(
f'config.json: pairs."{symbol}".blocked_hours_utc must '
"be a list of integers in 0-23")
app.pair_overrides = {s: dict(o) for s, o in pair_section.items()}
oanda = raw.get("oanda", {})
_check_keys(oanda, _KNOWN_OANDA, '"oanda"')
app.oanda_settings = dict(oanda)
deepseek = raw.get("deepseek", {})
_check_keys(deepseek, _KNOWN_DEEPSEEK, '"deepseek"')
if "enabled" in deepseek and not isinstance(deepseek["enabled"], bool):
raise AppConfigError(
"config.json: deepseek.enabled must be true or false")
if "timeout_seconds" in deepseek:
ts = deepseek["timeout_seconds"]
if isinstance(ts, bool) or not isinstance(ts, (int, float)) or ts <= 0:
raise AppConfigError(
"config.json: deepseek.timeout_seconds must be a positive "
"number")
if "daily_request_cap" in deepseek:
cap = deepseek["daily_request_cap"]
if isinstance(cap, bool) or not isinstance(cap, int) or cap < 1:
raise AppConfigError(
"config.json: deepseek.daily_request_cap must be a positive "
"integer")
if "model" in deepseek:
if not isinstance(deepseek["model"], str) or not deepseek["model"]:
raise AppConfigError(
"config.json: deepseek.model must be a non-empty string")
app.deepseek_settings = dict(deepseek)
panel = raw.get("agent_panel", {})
_check_keys(panel, _KNOWN_AGENT_PANEL, '"agent_panel"')
for flag in ("enabled", "telegram", "dashboard"):
if flag in panel and not isinstance(panel[flag], bool):
raise AppConfigError(
f"config.json: agent_panel.{flag} must be true or false")
if "min_quality" in panel and panel["min_quality"] not in _VALID_QUALITIES:
raise AppConfigError(
f'config.json: agent_panel.min_quality "{panel["min_quality"]}" '
f"not in {_VALID_QUALITIES}")
if "max_panels_per_day" in panel:
mpd = panel["max_panels_per_day"]
if isinstance(mpd, bool) or not isinstance(mpd, int) or mpd < 1:
raise AppConfigError(
"config.json: agent_panel.max_panels_per_day must be a "
"positive integer")
if "reuse_ttl_seconds" in panel:
ttl = panel["reuse_ttl_seconds"]
if isinstance(ttl, bool) or not isinstance(ttl, (int, float)) \
or ttl < 0:
raise AppConfigError(
"config.json: agent_panel.reuse_ttl_seconds must be a "
"non-negative number")
if "candles_enabled" in panel \
and not isinstance(panel["candles_enabled"], bool):
raise AppConfigError(
"config.json: agent_panel.candles_enabled must be true or false")
for key in ("candle_bars_primary", "candle_bars_confirm"):
if key in panel:
n = panel[key]
if isinstance(n, bool) or not isinstance(n, int) \
or not 1 <= n <= 100:
raise AppConfigError(
f"config.json: agent_panel.{key} must be an integer "
"between 1 and 100")
if "verdict_source" in panel and panel["verdict_source"] not in \
("mean", "macro", "chair"):
raise AppConfigError(
'config.json: agent_panel.verdict_source must be "mean", '
'"macro" or "chair"')
if "personas" in panel:
names = panel["personas"]
valid = ("macro", "technical", "risk", "contrarian")
if (not isinstance(names, list) or not names
or any(not isinstance(n, str) or n not in valid for n in names)
or len(set(names)) != len(names)):
raise AppConfigError(
"config.json: agent_panel.personas must be a non-empty list "
f"of distinct names from {valid}")
if panel.get("verdict_source") == "chair" and len(names) < 2:
raise AppConfigError(
'config.json: agent_panel.verdict_source "chair" needs at '
"least two personas")
if panel.get("verdict_source") == "macro" and "macro" not in names:
raise AppConfigError(
'config.json: agent_panel.verdict_source "macro" needs the '
"macro persona in agent_panel.personas")
app.agent_panel_settings = dict(panel)
if "market_outlook" in raw:
# The AI market-outlook feature was removed 2026-09-15; older
# config.json files still carry its block and must keep loading.
logger.warning(
"config.json: market_outlook block is ignored (feature removed "
"2026-09-15) — delete it")
watch = raw.get("violent_watch", {})
_check_keys(watch, _KNOWN_VIOLENT_WATCH, '"violent_watch"')
for flag in ("enabled", "alert_line", "headsup"):
if flag in watch and not isinstance(watch[flag], bool):
raise AppConfigError(
f"config.json: violent_watch.{flag} must be true or false")
if "max_headsup_per_day" in watch:
cap = watch["max_headsup_per_day"]
if isinstance(cap, bool) or not isinstance(cap, int) or cap < 0:
raise AppConfigError(
"config.json: violent_watch.max_headsup_per_day must be a "
"non-negative integer")
if ("headsup_min_level" in watch
and watch["headsup_min_level"] not in _VALID_WATCH_LEVELS):
raise AppConfigError(
f'config.json: violent_watch.headsup_min_level '
f'"{watch["headsup_min_level"]}" not in {_VALID_WATCH_LEVELS}')
app.violent_watch_settings.update(watch)
slog = raw.get("signal_log", {})
_check_keys(slog, _KNOWN_SIGNAL_LOG, '"signal_log"')
if "enabled" in slog and not isinstance(slog["enabled"], bool):
raise AppConfigError(
"config.json: signal_log.enabled must be true or false")
if "path" in slog and (not isinstance(slog["path"], str)
or not slog["path"]):
raise AppConfigError(
"config.json: signal_log.path must be a non-empty string")
if ("log_blocked_scans" in slog
and not isinstance(slog["log_blocked_scans"], bool)):
raise AppConfigError(
"config.json: signal_log.log_blocked_scans must be true or false")
app.signal_log_settings = dict(slog)
narch = raw.get("news_archive", {})
_check_keys(narch, _KNOWN_NEWS_ARCHIVE, '"news_archive"')
if "enabled" in narch and not isinstance(narch["enabled"], bool):
raise AppConfigError(
"config.json: news_archive.enabled must be true or false")
if "path" in narch and (not isinstance(narch["path"], str)
or not narch["path"]):
raise AppConfigError(
"config.json: news_archive.path must be a non-empty string")
app.news_archive_settings = dict(narch)
nm = raw.get("news_model", {})
_check_keys(nm, _KNOWN_NEWS_MODEL, '"news_model"')
if "mode" in nm and nm["mode"] not in _NEWS_MODEL_MODES:
raise AppConfigError(
'config.json: news_model.mode must be "off", "fallback" or "primary"')
if "threads" in nm and (not isinstance(nm["threads"], int)
or isinstance(nm["threads"], bool)
or nm["threads"] < 1):
raise AppConfigError(
"config.json: news_model.threads must be a positive integer")
if "deepseek_audit_per_day" in nm and (
not isinstance(nm["deepseek_audit_per_day"], int)
or isinstance(nm["deepseek_audit_per_day"], bool)
or nm["deepseek_audit_per_day"] < 0):
raise AppConfigError(
"config.json: news_model.deepseek_audit_per_day must be a "
"non-negative integer")
if nm.get("mode", "off") != "off" and (
not isinstance(nm.get("path"), str) or not nm.get("path")):
raise AppConfigError(
"config.json: news_model.path is required when news_model.mode "
"is not off")
app.news_model_settings = dict(nm)
level = raw.get("log_level", app.log_level)
if level not in _VALID_LOG_LEVELS:
raise AppConfigError(
f'config.json: log_level "{level}" not in {_VALID_LOG_LEVELS}')
app.log_level = level
return app
# ── Process-wide singleton ────────────────────────────────────────────
_cached: Optional[AppConfig] = None
def get_app_config() -> AppConfig:
global _cached
if _cached is None:
_cached = load_app_config()
return _cached
def set_app_config(app: Optional[AppConfig]) -> None:
"""Override the process-wide AppConfig (tests/experiments).
Pass None to re-enable lazy loading from CONFIG_PATH."""
global _cached
_cached = app
# ── Resolution helpers: env var → config.json → default ───────────────
def telegram_token(app: Optional[AppConfig] = None) -> str:
app = app or get_app_config()
return os.environ.get("TELEGRAM_TOKEN") or app.telegram_token
def telegram_chat_id(app: Optional[AppConfig] = None) -> str:
app = app or get_app_config()
return os.environ.get("TELEGRAM_CHAT_ID") or app.telegram_chat_id
def telegram_channel_id(app: Optional[AppConfig] = None) -> str:
"""Env set-but-empty ("") means "disable the feed" and beats JSON,
so this checks None-ness, not truthiness."""
app = app or get_app_config()
env = os.environ.get("TELEGRAM_CHANNEL_ID")
return env if env is not None else app.telegram_channel_id
# Per-provider env-var overrides for API keys (env → config.json → "").
_PROVIDER_ENV_KEYS = {
"twelve_data": "TWELVE_DATA_API_KEY",
"tiingo": "TIINGO_API_KEY",
}
def provider_api_key(
app: Optional[AppConfig] = None, provider: Optional[str] = None
) -> str:
"""API key for `provider` (default: the ACTIVE provider). The env
override is per-provider (TWELVE_DATA_API_KEY applies only to
twelve_data, TIINGO_API_KEY only to tiingo)."""
app = app or get_app_config()
name = provider or app.active_provider
env_key = _PROVIDER_ENV_KEYS.get(name)
if env_key:
env = os.environ.get(env_key)
if env:
return env
block = app.provider_settings.get(name, {})
return str(block.get("api_key", ""))
# ── Oanda resolution helpers (env → config.json → default) ───────────
def oanda_api_token(app: Optional[AppConfig] = None) -> str:
app = app or get_app_config()
return os.environ.get("OANDA_API_TOKEN") or str(
app.oanda_settings.get("api_token", ""))
def oanda_base_url(app: Optional[AppConfig] = None) -> str:
app = app or get_app_config()
return os.environ.get("OANDA_BASE_URL") or str(
app.oanda_settings.get("base_url", "https://api-fxpractice.oanda.com"))
# ── DeepSeek resolution helper (env → config.json → "") ──────────────
def deepseek_api_key(app: Optional[AppConfig] = None) -> str:
app = app or get_app_config()
return os.environ.get("DEEPSEEK_API_KEY") or str(
app.deepseek_settings.get("api_key", ""))
# ── Violent-move watch resolution helper ─────────────────────────────
def violent_watch_enabled(app: Optional[AppConfig] = None) -> bool:
"""Whether the display-only violent-move watch is on (env wins)."""
env = os.environ.get("VIOLENT_WATCH_ENABLED")
if env:
return env.strip().lower() in ("1", "true", "yes", "on")
app = app or get_app_config()
return bool(app.violent_watch_settings.get("enabled", False))
# ── Process-level database write switch ──────────────────────────────
#: True in every process by default. The dashboard publisher turns it
#: off at startup (owner decision 2026-09-17): it is not always running,
#: so the Telegram bot must be the single writer of signals.db and
#: newsdata.db — two writers were also two processes contending for the
#: same WAL files. Every SQLite writer (signal_log, news_archive) reads
#: the switch through signal_log_enabled() / news_archive_enabled(), so
#: a switched-off process cannot write whatever config.json or the
#: environment says. Read-only users of the databases are unaffected.
_process_db_writes = True
def set_db_writes_for_process(enabled: bool) -> None:
global _process_db_writes
_process_db_writes = bool(enabled)
def db_writes_enabled() -> bool:
return _process_db_writes
# ── Signal-log resolution helpers (env → config.json → default) ──────
def signal_log_enabled(app: Optional[AppConfig] = None) -> bool:
"""Default ON — signal history is the platform's audit trail."""
if not _process_db_writes:
return False
env = os.environ.get("SIGNAL_LOG_ENABLED")
if env:
return env.strip().lower() in ("1", "true", "yes", "on")
app = app or get_app_config()
return bool(app.signal_log_settings.get("enabled", True))
def signal_log_blocked_scans(app: Optional[AppConfig] = None) -> bool:
"""Whether weekend/day-filter early returns are logged (as minimal
rows without news/candles). Default ON — they are liveness evidence;
turn off to keep the history table to real scans only."""
env = os.environ.get("SIGNAL_LOG_BLOCKED_SCANS")
if env:
return env.strip().lower() in ("1", "true", "yes", "on")
app = app or get_app_config()
return bool(app.signal_log_settings.get("log_blocked_scans", True))
def signal_log_path(app: Optional[AppConfig] = None) -> str:
"""Absolute path to the SQLite signal-history DB. A relative config
value resolves against the repo root so CWD never matters."""
env = os.environ.get("SIGNAL_LOG_PATH")
if env:
path = env
else:
app = app or get_app_config()
path = str(app.signal_log_settings.get("path", "logs/signals.db"))
if not os.path.isabs(path):
path = os.path.join(os.path.dirname(os.path.abspath(__file__)), path)
return path
# ── Local news model (env → config.json → default) ───────────────────
#
# The owner's ML-NEWS XAU transformer scores headlines locally
# (news_model.py). "off" is today's DeepSeek/keyword path; "fallback" runs
# the model only on rows DeepSeek left keyword-scored; "primary" scores
# every headline with the model and never calls DeepSeek for headlines
# (except the optional audit sample). NEWS_MODEL_MODE lets one process
# (the dashboard daemon's systemd unit) pick its own mode: each process
# that loads the model holds ~0.6 GB.
def news_model_mode(app: Optional[AppConfig] = None) -> str:
env = os.environ.get("NEWS_MODEL_MODE")
if env:
mode = env.strip().lower()
if mode in _NEWS_MODEL_MODES:
return mode
logger.warning(
'NEWS_MODEL_MODE=%r is not one of %s; using config.json',
env, _NEWS_MODEL_MODES)
app = app or get_app_config()
mode = app.news_model_settings.get("mode", "off")
return mode if mode in _NEWS_MODEL_MODES else "off"
def news_model_path(app: Optional[AppConfig] = None) -> Optional[str]:
"""Absolute path to the bundle directory (model.onnx, tokenizer.json,
meta.json), or None when not configured. A relative value resolves
against the repo root like news_archive_path."""
app = app or get_app_config()
path = app.news_model_settings.get("path")
if not isinstance(path, str) or not path:
return None
if not os.path.isabs(path):
path = os.path.join(os.path.dirname(os.path.abspath(__file__)), path)
return path
def news_model_threads(app: Optional[AppConfig] = None) -> int:
"""ONNX intra-op threads (measured 2026-09-27: 1 → 19 ms per headline,
4 → 9 ms, 16 → 13 ms)."""
app = app or get_app_config()
try:
return max(1, int(app.news_model_settings.get("threads", 4)))
except (TypeError, ValueError):
return 4
def news_model_audit_per_day(app: Optional[AppConfig] = None) -> int:
"""primary mode only: headlines per UTC day also sent to DeepSeek so
the archive keeps receiving fresh training labels. Archive-only, never
displayed. 0 = no DeepSeek headline calls at all (owner decision
2026-09-27)."""
app = app or get_app_config()
try:
return max(0, int(app.news_model_settings.get("deepseek_audit_per_day", 0)))
except (TypeError, ValueError):
return 0
# ── News-archive resolution helpers (env → config.json → default) ────
def news_archive_enabled(app: Optional[AppConfig] = None) -> bool:
"""Default ON — the headline corpus is training data for a local
scorer and cannot be backfilled once a fetch window has passed. It
lives in its own DB so a signals.db rotation cannot take it with it
(which is how three weeks of news were lost on 2026-09-04)."""
if not _process_db_writes:
return False
env = os.environ.get("NEWS_ARCHIVE_ENABLED")
if env:
return env.strip().lower() in ("1", "true", "yes", "on")
app = app or get_app_config()
return bool(app.news_archive_settings.get("enabled", True))
def news_archive_path(app: Optional[AppConfig] = None) -> str:
"""Absolute path to the SQLite headline corpus. A relative config
value resolves against the repo root so CWD never matters."""
env = os.environ.get("NEWS_ARCHIVE_PATH")
if env:
path = env
else:
app = app or get_app_config()
path = str(app.news_archive_settings.get("path", "logs/newsdata.db"))
if not os.path.isabs(path):
path = os.path.join(os.path.dirname(os.path.abspath(__file__)), path)
return path
# ── PlatformConfig overlay ────────────────────────────────────────────
def apply_pair_overrides(
cfg: PlatformConfig, app: Optional[AppConfig] = None
) -> PlatformConfig:
"""Stamp deployment settings from config.json onto a PlatformConfig.
Called by the pair factories BEFORE their validated per-timeframe
deltas, so e.g. the M5 hour-9 append lands on top of the JSON base.
The pair's base blocked_hours_utc is set on BOTH mirrored copies
(xau_strategy + backtest) so they cannot drift.
"""
app = app or get_app_config()
overrides = app.pair_overrides.get(cfg.symbol, {})
if "blocked_hours_utc" in overrides:
hours = list(overrides["blocked_hours_utc"])
cfg.xau_strategy.blocked_hours_utc = hours
cfg.backtest.blocked_hours_utc = list(hours)
cfg.scan_pairs = list(app.scan_pairs)
cfg.scan_timeframes = list(app.scan_timeframes)
return cfg