Two failure modes addressed:
1. Soft/indirect bullish signals classified as 'mention' instead of 'bullish'
The prompt now explicitly lists casual English and Chinese expressions that
count as bullish/bearish (not mention):
- EN: 'looks interesting here', 'has room to run', 'wouldn't be short'
- ZH: '感觉还有空间', '可以关注', '这里不错', '有上涨空间'
mention is now reserved for ZERO directional lean (historical refs, neutral
examples). Previously the vague boundary caused the model to use mention
conservatively, losing real signals.
2. Category-level calls lost when no specific ticker named
'memecoin season', 'memes look good', '梗币最近不错' had no ticker to attach
to. Added synthetic tickers: MEME, ALTCOIN, DEFI, AI — the model uses these
when the view is about the category, not a specific coin.
Normalizer allows synthetic tickers through the len>12 guard.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Prompt v1 → v2 changes:
1. talks_vs_trades_score (float 0-1) replaces boolean flag
- 0.7-1.0: strong divergence (bullish thesis + reducing, public buy + silent now)
- 0.4-0.69: moderate (risk mgmt language alongside bullish, tone shift)
- 0.1-0.39: weak (minor hedges)
- 0.0: consistent or no position signals
- talks_vs_trades_flag (bool) kept as backward-compat alias (score >= 0.5)
2. post_type field: trade_update | macro_thesis | research | news_recap | opinion | other
Lets downstream filter by content quality before acting on signals.
3. summary cap raised 80→200 chars (2-3 sentences)
80 chars was too tight for 5000-word Substack essays.
4. Chinese-language divergence cues added to prompt
减仓了/止盈/降低了仓位/观望/风控 etc. — most KOL posts are in Chinese or
English with Chinese asides; the old prompt only covered English patterns.
5. max_tokens raised 1500→2000 (Anthropic) and 1500→2000 (OAI non-reasoning)
Complex essays with 5+ tickers were truncating.
Backward-compatible: callers checking talks_vs_trades_flag bool still work.
Version bumped kol-v1→kol-v2 for re-analysis tracking.
72 tests pass.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Batch of the pre-launch audit campaign (BUG-01…14 plus three new features):
Pricing / TP-SL protection
- Add app/services/hl_price_feed.py: supplemental HL allMids poller for
HL-native assets (HYPE, PURR) not listed on Binance. Pumps price_store +
tp_sl_monitor.on_price_tick so bot trades on these assets keep full
stop-loss / take-profit / trailing protection instead of max-hold only.
- Wire feed into main.py lifespan (startup task + graceful shutdown cancel).
Telegram
- Add format_trump_mention + PATH B in _dispatch: crypto-relevant Trump
posts with no directional signal (relevant=True, signal=hold) now alert
the public channel only (no per-subscriber noise).
- Rate limiter (slowapi) on the API; assorted bot/digest fixes.
KOL on-chain
- seed_kol_wallets.py: KOL_FEEDS coverage cross-check; reversibly deactivate
orphaned wallets (handle not in KOL_FEEDS → can never produce divergence)
so the scanner stops burning cycles on them.
Tests / misc
- Fix brittle test_macro_ahr999_uses_same_formula_as_scanner: mock now uses
realistic ms timestamps so the in-progress-day drop fires, matching the
fetcher's bar count (was 0.3179 vs 0.3178 off-by-one).
- Refresh stale notify_signal comment in truth_social.py.
Frontend reduce-action type fix lives in the sibling repo.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
k