chore: remove dead functions and write-only state (no behaviour change)

Zero callers anywhere (tests included), verified by grep/AST:
- dashboard_publisher.DashboardPublisher.publish_all (run_cycle inlines both publishes)
- signal_log.SignalLogger.advance_with_bars (the backfill script uses
  backfill_seeds / resolve_from_store / reseed_unresolvable) and the never-read
  SignalLogger.path property plus its write-only self._path
- llm_client.reset_llm_client (tests reset the singleton by assignment)
- market_outlook._last_run_ts, residue of the old "now - last < 3600" dedup;
  _last_run_hour (the UTC hour bucket) is the live key
- news_engine FundamentalContext.event_impact_on_pairs: written once, read by
  nothing; its only feeder NewsEngine._get_affected_pairs and that helper's
  unit test go with it
- position_sizing.LIVE_DEPTH_BARS (referenced only by its own docstring, which
  now states the depths inline), the unused Iterable import and the unused
  atr_ok parameter of _fill_geometry
- analyze_signal_log: unused `field` import and the unused `rows` parameter of
  persona_scorecard / news_outcome_buckets (both read the DB directly)

The two backfill/label scripts' --db help text now names the config.json
setting it actually falls back to.

Suite: 463 passed, 0 failed (one test removed with its subject).

Claude-Session: https://claude.ai/code/session_0156YhogLytzj9P2iH1skGbL

dashboard_publisher.py

@@ -432,10 +432,6 @@ class DashboardPublisher:
         if self.news_payload is not None:
             publish(self.news_payload, os.path.join(self.out_dir, NEWS_FILE))
 
-    def publish_all(self) -> None:
-        self.publish_snapshot()
-        self.publish_news()
-
     def run_cycle(self, tfs: List[Timeframe]) -> None:
         for tf in tfs:  # sequential — see module docstring (cache dedup)
             self.scan_tf(tf)