Fix list

Open fixes and ideas for the bots, in priority order. Updated 2026-10-13. Status: TO DO / IN PROGRESS / DONE. Test results for entry ideas: entry knowledge base.

#Fix / ideaWhyBotStatusAdded
1Intraday rescans re-score the whole universe with what is known at that time (move from the open, range, volume vs normal for that time, VWAP, trend...), instead of reusing the premarket scoreRescans change only 1-4 of 50 names, so stocks that start moving during the day never enter the listStar bot ON (trade bot option OFF)DONE 10/13: top 30 beat both premarket scores at every rescan time, both years (10:00 up-runs 53%/57% vs v3 50%/47% vs old 41%/39%); live for the Star bot from 10/1410/13
2min_atr_pct threshold test (4 / 5 / 6 / 7 / 8%)8% blocked all 6 Star-bot buys on 10/13 (5 of 6 then rose); its old-score list is 88% calm stocks. Star bot has it OFF now, trade bot ONbothTO DO10/13
3thin_trading avoid rule: median shares/min over 15 min below a floorRILY 10/12: one 53k-share print made a thin stock pass the volume and liquidity rules (averages)bothTO DO (build OFF + 2-year test)10/12
4Tighter spread limit (e.g. 0.3%, or scaled to the expected move)RILY: a 0.4% spread ate most of the loss; the 1% limit is loose for $5 stocksbothTO DO (record live; no quote history to backtest)10/12
5Extension measured in ATRs (above the open / above VWAP in daily ATRs)TAL 10/12: +1.9% over the open = 0.7 of its whole daily range; the % limits are loose for calm stocksbothTO DO (v2 has ext_hard_max_atr / max_move_x OFF)10/12
6Gap-down: previous close as resistanceTAL stalled at its previous close (gap fill) right after the buyboth TO DO (build OFF + test)10/12
7Report the avoid-rule + news testsNo single rule makes entries positive; min_atr_pct best (-0.007%); all on = 18 trades -0.47%. News at the open = more movers (+5% runs 39-41% vs 26-29%), not better trades-DONE 10/1310/13
7bCombination test: min_atr_pct + lower_low_by_1030 (+ max_above_open_pct)On ATR >= 8% stocks lower_low_by_1030 gave +0.087% (262 trades) and max_above_open +0.011%; must be a real replay of the pairbothTO DO10/13
7cNews flag as a scanner input (premarket news, esp. "why moving", guidance, FDA, earnings)Picks with news reached +5% 39-41% vs 26-29% without, both years -- a mover signal like ATR, not a direction signalscannerTO DO (add to the intraday / v3 score study)10/13
8Replay last Mon-Wed with today's settingsSettings changed since (scanner, orders, guards, stop) -- separate settings vs market days bothTO DO (offered)10/12
9Order-book pressure test (bid vs ask size at entries and V turns)The one signal not testable yet; recording since 10/12 trade botWAIT 2-3 weeks of data10/11
10SEC filing tags 10-year backtestRecording since 10/7 (avoid / catalyst tags); needs history to testboth TO DO10/7
11Star's sells vs the bot's exitsLive 7 days: Star better 28 of 49; 2-year test: Star worse- WATCH (weekly review)10/11
12Compress old decision logs~200-260 MB per bot per day; ~1 month of disk leftbothTO DO (offered)10/11
13Security before go-live: Apache serves /var/www/screener incl. .env files (keys downloaded by outside IPs in Sept); block dotfiles/data, rotate Alpaca keys, report passwordDeferred by the user until the bot is approved to go liveall BEFORE GO-LIVE9/25
-Watch list not updating on rescansChecked 10/13: rescans run every 5 min and apply; the list barely changes because the score is premarket-based -> fix #1Star botEXPLAINED10/13
14A. Market filter: no buy while IWM is below its open (A1) / falling over 30 min (A2)10/14 all 6 buys lost in a falling market; 10/15 rising market, most wonbothTESTED 10/16: WORSE (A1 -0.151%, A2 -0.142% vs live -0.133%) -- drop10/15
15B. Clustering guard: 3+ stocks signalling within 5 min -> only if IWM rising10/14 all 6 buys came 10:40-10:46 on a small market bounce bothTESTED 10/16: only 10 clustered buys in 2 years (-0.38% each) -- negligible10/15
16C. More room to resistance (v2 min 1% -> 5% / 10%)10/14 room 2.6-7% vs 10/15 13-28%bothTESTED 10/16: BEST of A-E: 5% -0.103% (halves -0.17% / -0.03%), 10% -0.105%; not positive. Next: test with min_atr_pct10/15
17D. Volatility-scaled stop (0.25 / 0.35 x daily ATR, max 6%)10/15 CIFR / BLZE stopped at -2% then closed +11% / +5.6%both TESTED 10/16: WORSE (-0.142% / -0.148%) -- drop10/15
18E. Sector trend for crypto stocks: buy only while bitcoin is up since 9:3010/15 BTC +2.7%, miners ran; 10/14 BTC -0.9%, CORZ lost bothTESTED 10/16: no help (-0.134%; crypto buys -0.21% -> -0.30%) -- drop10/15
19noise2 ON for the Star bot's sellsBest sell method 2 weeks running; 10/20 HL / TDOC / PGEN sold seconds-minutes after the buy above VWAP, then +1.2..+2.5%Star botDONE 10/20 10:54 (user): ON, Star bot restarted flat10/20
20Sticky watch list: keep stocks traded today on the list after a rescan drops themHL / TDOC dropped right after the sell -> no re-buy possiblebothTO DO (check on past days first)10/20
2115-minute window edge check: don't let a big bar leaving the 15-bar window flip the rules (also check 30-min buy share / trend)HPK 10/20: a 44k-share sell flush left the window -> buy share 31%->61% in one minute -> buy -> -$47bothTO DO (2-year test)10/20
22Situation-specific entry rules (user's design): tag S1-S28 on every v2 buy; rules S1 window flip, S2 spike wait-and-confirm, S11 flush cool-down"Not one rule fits all" -- HPK 10/20; catalog entry_situations.htmlbothTESTED 10/21: S1/S2/S11 rules do NOT help (keep OFF); harmful situations = S20 calm, S6 extended, S8 near resistance, S3 block print, S21 thin/wide, S10 late -> deep study one by one10/20
23C3: confirm the last 3 full bars at every buy signal (price rising, buy share and volume not falling)HPK 10:06: no up bar in the last 3, flat price -- bought on a window flipbothBUILT (OFF); 6-month test 10/21 16:20 (c3_test.py), then 2 years10/21
-New exchange "TXSE" broke the stock list (scans/rescans failed from 12:51 on 10/19, and the 16:35 reference build)Alpaca listed a Texas Stock Exchange stock our library version rejectsbothFIXED 10/19 evening (raw-list fallback; references rebuilt for 10/20)10/19
-Day-page charts in New York time (axis + trade table were UTC)User 10/13pagesDONE10/13
-Star bot min_atr_pct OFF + restartUser 10/13 12:32Star botDONE10/13
-Star bot: no buy while VWAP is lower than 30 min ago (finished bars; from the first bar if the day is younger). config entry_v2.vwap_down_block_min 30User 11/10 after the Star review (2y replay: loss per trade -0.151/-0.144 -> -0.061/-0.119, 3% stops 474 -> 212; 27 live days: -$629 -> -$115)Star botDONE 11/10, live from 11/11 9:30 (revert: entry_v2.py.bak-2026-11-10-pre-vwap30 + data/config.json.bak-2026-11-10-pre-vwap30)11/10