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.

app_config.py

@@ -90,7 +90,7 @@ _KNOWN_TOP = {"telegram", "data_providers", "scanning", "pairs", "log_level",
                # 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"}
+               "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
@@ -111,6 +111,8 @@ _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"}
@@ -150,6 +152,7 @@ class AppConfig:
         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"
 
 
@@ -405,6 +408,30 @@ def load_app_config(path: str = CONFIG_PATH) -> AppConfig:
             "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(
@@ -569,6 +596,65 @@ def signal_log_path(app: Optional[AppConfig] = None) -> str:
     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: