Live journal

**Day summary (2026-10-29, paper).** Equity is about $95.7k and cash about $4.7k, so the book is roughly 95% invested. There were two fills:
- **GOOGL:** Alphabet's Q3 results came out after the close on 10/28 and missed on revenue and earnings per share. Free cash flow was negative and spending guidance stayed high, with 2027 spending set to rise "significantly". The stock opened at $286.77, far below the $308 stop, and closed $283.82 (-12.6%, 133M shares, about 5x normal volume). The stop sold all 23.75 shares @ $283.02, a -16% loss (about -$1.3k). The position is now flat.
- **NVDA:** dip-buy-2 (<$213) bought 14.07 shares @ $213.29. dip-buy-1 was rejected once at the open for lack of cash.

Day changes elsewhere:
- **AMZN -4.25%:** it reports after the close today, and the stock weakened along with GOOGL.
- **MU -4.98%:** it gave back part of its four-day bounce.
- **AMD -2.08%, TSM -1.79%.**
- **META +1.96% and AAPL +1.48%** were the only gainers.

**Per-strategy check**
- **googl-swing:** The stop did its job by selling at the open, but no stop can limit the loss when the price opens far below it. The 10/21 pre-earnings pause only turned off the buy rules, so the full position was still held into the report. Its rules are now spent. Re-entering needs a new revision, and I'm not proposing one; the thesis is damaged.
- **nvda-momentum-swing:** Now 66.30 shares @ $215.01, about 14.8% weight against a 15% target. The 8/24 low of $207.25 and the $205 stop both held. Two rules are set wrong, which revision #232 fixes:
  - dip-buy-2 lets the weight go up to 20%, so one more fire would overshoot the target.
  - The option-buy rule (buy a call below $212) is still active and missed firing by $0.08 (low $212.08). Its stop is set above where it would buy and has already fired once, and its early profit exit is also spent. A new call would have no working stop.
- **amzn-swing:** About 11.6% weight and still open going into tonight's earnings. Both buy rules can't fire because the weight is above their caps. The stop (<$230) is about 5.7% below today's $243.79 close. Nothing can change before tomorrow's open. Read the results first thing tomorrow.
- **meta-swing:** Low $616.80 and close $624.52, back above the $615 stop line. The stop, which can fire again, did not fire, and the buy rules stay off.
- **mu-oversold-swing:** Closed $934.27 (low $927.24), giving back most of 10/28's gain. That is 3.1% above the <$905 stop and still inside the $930-950 support zone. The rules are fine.
- **amd-swing / tsm-swing-contest:** Ordinary semiconductor weakness with no rule fires. Both stops still show as already fired (AMD <$485, TSM). No revision this pass, but re-arming should be reviewed.
- **aapl-swing / msft-diversifier-swing / tsla-swing:** Quiet days and no rule fires. No issues.

**Lessons**
- In this market, the Q3 reports from the big cloud/AI companies (META, GOOGL, and now AMZN's pending) are being punished for spending running ahead of cash flow. A 1-2 week swing held into one of these reports risks a 10%+ overnight drop that no stop can limit. Before a report, cut to half size or exit; pausing the buy rules is not enough. Saved to memory.
- Unlike the META and MU stops earlier this month, the GOOGL stop actually sold. That is the intended behavior, but it sold at the gap price.

**Proposals**
- **#232 nvda-momentum-swing v13:**
  - Lower dip-buy-2's weight cap from 0.20 to 0.15 (the target).
  - Turn off the option-buy rule.
  - Move the option stop from <$214 to <$205 so it matches the stock stop.

  The stock stop, profit targets and thesis are unchanged.

**Day summary (2026-10-28, paper):** Equity is about $100.6k and cash is $960, so the book is still about 99% invested. Our mandate says 40–70%. No orders filled today. Two buy rules were rejected for lack of cash: NVDA dip-buy-1 (re-armed after its cooldown) and META dip-buy-2. The main event was META's stop-loss (sell everything below $615). It fired at $614.42 and its analysis said to sell, but no sale happened. META then closed at $612.49 (low $609.00), its first close under $615, which is the point where the strategy says the trade idea has failed. MU went the other way: it closed at $983.23 (+5.86%, opened higher at $962, above-average volume), its fourth straight up day from the $849 low. AMD rose 3.2% and GOOGL 1.3%. NVDA fell 1.2%, AAPL 0.9%, and the other names moved less than 1%.

**Per-strategy check:**
- **meta-swing:** The trade idea has failed: META closed under $615 after the Q3 report. That report showed spending on data centres outrunning operating cash flow, negative free cash flow, and a new share class created to fund AI. The one-time stop has now been used up without a sale, so the position (11.11 sh @ $719.86, about -15%) has no stop. dip-buy-2 kept re-arming and getting rejected for cash. Proposed fix: #226.
- **mu-oversold-swing:** MU climbed back above the $930–950 zone on volume, the recovery test the strategy itself set. The $849 "final" stop never sold either; holding through it happened to work, but that was luck, not process. That stop is now about 13.6% below price and protects nothing. Proposed fix: #227. The position is about 14% of the book and about -2%.
- **nvda-momentum-swing:** 52.24 sh @ $215.47, about 11.2% weight, roughly break-even. dip-buy-1 is near its 12% weight cap and was rejected for cash, which is the intended behaviour. The $205 stop is intact.
- **amd-swing:** Rose 3.2%; the position is about +11% (15.58 sh @ $513.42). The stop is still marked as fired, so I can't confirm a live stop below $510. Yesterday's proposal #220 to re-arm it is no longer in the queue and I couldn't confirm whether it was applied.
- **tsm-swing-contest:** About 17.7% weight, roughly break-even. The stop is also still marked as fired, so it needs the same check (#220).
- **aapl / amzn / msft / googl / tsla:** Nothing triggered and no anomalies. AMZN and GOOGL have reported or are about to report Q3 (10/28–29), so watch for a jump in either direction. AMZN's take-profit (sell everything above $268) is the trigger closest to price.

**Lessons:**
- Across the book, one-time "sell everything" stops on strategies that need your approval keep firing without a sale: MU four times, plus TSM, AMD and now META, even when the analysis says sell. Once a stop has fired it is used up, and the position has no stop. The fix is to let stops re-arm so an unsold stop fires again next session. After a recovery, raise stops; never lower them after a miss. Saved to the lessons memory.
- Holding MU through its missed stops worked this time, but by luck, not process.

**Proposals:**
- **#226 meta-swing v3:** turn off both dip-buys; re-arm the stop at the same $615 level, set to fire again up to 2 times a day after a 120-minute cooldown. Trim and take-profit stay.
- **#227 mu-oversold-swing v14:** raise the stop from $849 to $905, just under the 10/27 low of $910.67 and the zone MU just reclaimed. Dip-buys stay off; trim and take-profit unchanged.

**Day summary**
- **Market:** A broad semis rally: AMD +5.45%, TSM +2.95%, MU +2.77%, NVDA +0.90%. TSLA rose +4.04%. AMZN, GOOGL and AAPL were up about 1–1.6%, and MSFT was flat. META fell again, -1.64%, to $620.19 on its heaviest volume in two weeks.
- **Trades:** One fill. NVDA's first buy rule bought 13.88 sh @ $216.18, the second straight day this $3k tranche filled. NVDA is now 52.24 sh @ $215.47, about 11.4% of the account. META's second buy rule fired again and was rejected because there wasn't enough cash.
- **Cash:** About $960, so the account is ~99% invested against your 40–70% target.
- **Stop states:** The live snapshot shows the stop-loss rule as "triggered" on AMD, MU and TSM. None of them has traded at its stop level since the last revision, so these three positions may have had no working stop.

**Per-strategy check**
- **AMD:** Closed $560.26. Each session's low since 10/22 has been higher ($502.60 → $538.50), and the 10/22 re-buy @ $513.42 is up ~9%. The <485 stop is about 3.4 daily ranges (ATR) away and showed as "triggered". **#220** re-arms it at <510, just under the 10/23 low and about break-even. Buy rules stay off because there is no cash.
- **MU:** Closed $928.76, its third higher close, on light volume. That is just under the $930–950 zone the strategy wants reclaimed before adding. The <849 stop showed "triggered" without being reached. **#223** re-arms the stop and raises it to <858, under the 10/15 and 10/23 lows. This moves it up, not down, so it keeps the "no lowering the stop" rule. Buy rules stay off.
- **TSM:** Closed $436.88 on light volume. It is the largest position at ~17.7%. The <405 stop showed "triggered" without being reached. **#221** re-arms it at <409, just under the 10/22 re-test low of $410.22.
- **META:** Close $620.19 (low $619.22) is only 0.8% above the <615 stop, the sixth lower close since 10/14. Search results suggest Q3 was reported 10/21: revenue beat, but capital spending jumped and free cash flow turned negative. I haven't checked that against the filing. If right, this is the market repricing heavy spending, not normal noise. **#222** turns off the buy rules and keeps the <615 stop where it is. If it fires, exit.
- **NVDA:** The $3k buy worked, and the $207.25 low and $205 stop held. Weight is still just under the rule's 12% cap, so it will likely fire again tomorrow. With $960 in cash, that order will be rejected.
- **AAPL, AMZN, GOOGL, MSFT, TSLA:** No rules fired and nothing looks off. AMZN (earnings 10/29) and GOOGL (earnings 10/28) report this week. I didn't re-check these charts today.

**Lessons**
1. **Check stop states after a revision.** Changing a stop's level may not reset it to "armed". After any stop revision, confirm the next snapshot reads "armed"; otherwise the position has no live stop. I saved this to memory.
2. **Turn off buy rules when there's no cash.** At ~99% invested, buy rules that re-arm just fire and get rejected over and over. A META buy just above its sell-all stop has almost no upside for the risk.
3. **Note on memory:** The AMD memory file is full. I replaced an old 9/17 entry with today's note.

**Proposals (all need your approval)**
- **#220 AMD v13:** re-arm the stop at <510.
- **#221 TSM v14:** re-arm the stop at <409.
- **#222 META v3:** turn off the buy rules and keep the <615 stop.
- **#223 MU v14:** re-arm the stop and raise it to <858.

**Day summary (2026-10-26, paper)**
Semis had a relief bounce: TSLA rose 5.2%, MU 3.0%, AMD 2.8%, NVDA 2.4%, MSFT 1.5% and TSM 1.4%. META fell 1.9%, AAPL 1.1% and GOOGL 1.1%. Equity is about $98.0k and cash about $3.96k, so roughly 96% of equity is invested. The mandate says 40-70%. There was one trade: NVDA dip-buy-1 bought 13.94 shares at $215.19. This is the first time the $3k tranche from v12 has filled after more than 8 cash rejections. The sentinel lost price data for MU, NVDA, TSLA and TSM around 17:16 UTC. Nothing fired in that gap. I could not verify a market-wide cause for the move: the market searches I ran returned no usable content.

**Per-strategy check**
- **nvda-momentum-swing:** The fill was clean. Price had touched about $213.5 and the stock closed at $216.00, so the buy ended slightly in profit. The position is now 38.36 shares at a $215.21 average, about 8.5% of the account. The $207.25 swing low and the $205 stop held. dip-buy-1 is still under its 12% weight cap and can fire once a day, which would spend most of the remaining cash. The user should be aware of this.
- **meta-swing:** META closed at $630.56 on heavy volume (29M shares). That is the lowest close since the drop from $762 began, and it is only about 2.5% (about half an average daily range) above the <$615 stop. dip-buy-2 re-armed and fired. The attached analysis said skip because of the risk-off market and low cash, and nothing filled. I did not change anything. If the <$615 stop fires, the strategy's own exit rule applies. I could not confirm when META reports earnings: one search result says Q3 results came out 10/22, which I could not verify.
- **amd-swing:** AMD closed at $531.28, holding above the 10/22 low of $502.60. The YAML stop at <$485 is armed, but the runtime still shows it as **triggered**.
- **mu-oversold-swing:** MU closed at $903.70 on light volume. That is still below the $930-950 level the strategy needs to see before any re-entry, so this is an unconfirmed bounce. The final stop at <$849 is armed in the YAML but shows **triggered** at runtime.
- **tsm-swing-contest:** TSM closed at $424.39 on light volume and stayed above $407/$405. The YAML stop at <$405 is armed but shows **triggered** at runtime.
- **aapl-swing, amzn-swing, msft-diversifier-swing:** No rule came close to firing. AAPL is around $344, between its $335 buy level and its $348 trim level. AMZN is inside its range. GOOGL reports 10/28 and AMZN 10/29.
- **googl-swing:** Both dip-buys are paused until after earnings, as designed.
- **tsla-swing:** TSLA rose 5.2% after earnings. The position is still small, about 2.6% of the account. Rebuilding it needs cash, and there isn't any.

**Lessons**
1. Size tranches to the cash that is actually available. NVDA's $8k tranche never filled against about $4k of cash, while the $3k tranche filled on its first clean trigger.
2. AMD, MU and TSM make up about a third of equity and currently have no working stop. Their stop rules show as triggered at runtime even though the YAML says armed. A strategy revision does not reset runtime rule state, so the user has to re-arm these three stops by hand on each strategy page. I have saved this as a lesson to raise every day until it is fixed.

**Proposals**
None. Nothing behaved measurably differently from what the strategies say. The urgent fix is re-arming the three stops by hand, which the user has to do directly; a revision would not fix it. Freeing up cash to get back toward the 40-70% mandate is still an open decision for the user, through trims that need their confirmation.

**Day summary (2026-10-23, paper).** Equity was about $97.1k at the close and cash about $6.96k, so roughly 93% of the account is invested against the 40–70% mandate. One trade filled: the AAPL trim rule sold 14.23 shares @ $351.48, close to the day's high of $351.73. That raised cash from about $1.96k to $6.96k. Semiconductors partly recovered Thursday's losses: MU closed +2.46% at $877.55, AMD +1.74% at $516.79 and TSM +1.42% at $418.19. All three bounces came on light volume. GOOGL (-1.24%), AMZN (-0.95%) and META (-0.96%) slipped. Three rules fired at 13:37 and all three orders were rejected for lack of cash: NVDA dip-buy-1, NVDA dip-buy-2 and META dip-buy-2. That was the right result for a book this heavily invested.

**Per-strategy check.**
- **aapl-swing:** The trim was correct. The position had drifted to about 17.5%, above its 15% target, and the sale came near a 30-day high. It now holds 33.78 shares at an average of $333.31, about 12.1% of the account and about 4% in profit. The problem is that the trim rule re-armed at 15:07 with a 10% floor and a $5k sale size. The close of $347.73 was only $0.27 below its $348 trigger, so the next move up would cut the position to about 7%. I proposed #212 to fix this.
- **amd-swing:** The stop is set at <485 in the strategy file, but the live snapshot still shows it as triggered (already used). The 15.58-share position, about 8.3% of the account and about +0.7%, may have no working stop. Today's low of $508.36 was well above $485, so nothing was missed today. Both dip-buys are disabled, as intended.
- **mu-oversold-swing:** Same stop problem. The file says <849 (final), but the snapshot shows it as triggered. Today's low of $858.34 never reached $849. The position is about 13% of the account and about -12.6% from cost. Volume was light (20.5M), so the bounce is not confirmed. Re-entry still requires a move back above $930–950 on strong volume.
- **tsm-swing-contest:** Same stop problem. The file says <405, the snapshot shows it as triggered. Today's low was $411.15. The position is about 17% of the account and about -5.6% from cost. Today's volume of 8.3M was light.
- **nvda-momentum-swing / meta-swing:** The dip-buys keep firing and getting rejected for cash. I proposed no change: the rejections stop the account from going further over its investment limit, and the rules can start filling once cash is freed.
- **amzn / googl / msft / tsla:** Nothing fired. GOOGL's dip-buys stay paused ahead of earnings on 10/28, and AMZN reports on 10/29. The AMZN take-profit (>268) is still above the market.

**Lessons.**
1. A revision that writes `state: armed` into the strategy file does not reset a rule that is already marked triggered. All three re-armed stops (AMD, MU, TSM) are still triggered in the live snapshot. Another revision won't fix this; the user has to re-arm each stop on its strategy page. I saved this as a lesson.
2. The trim-floor problem has now hit a fifth name (AAPL, after AMD, TSM, TSLA and AMZN). A trim's floor only works if floor + one sale is no higher than the weight before the trim. Otherwise a single re-fire cuts through the floor.

**Proposals.**
- **#212 (aapl-swing v3):** Raise the trim floor from 10% to 15% (the target weight) and cut it to 2 fires a day. Entries, stop, take-profit and the investment thesis are unchanged.
- **No new revision for AMD, MU or TSM:** their files are already correct. They need a manual re-arm on the strategy page, not a new proposal.

**Day summary**
- **Market:** A broad selloff hit chips and AI stocks. Press reports linked it to a weak Samsung earnings reaction and to OpenAI missing its user-growth goals. The Nasdaq 100 fell about 2%. Every position fell except AAPL (+1.2%): AMD -8.1%, META -7.0%, MU -6.3%, AMZN -4.6%, TSM -4.5%, NVDA -4.4%, GOOGL -3.2%, TSLA -3.1%, MSFT -2.2%.
- **Account:** Equity is about $96.7k and cash about $1.96k, so roughly 98% is invested. The mandate says 40-70%.
- **Trades:**
  - AMD's stop (below $520) sold 17.59 shares at $518.35, about -13% on the position.
  - About 2 hours later the AMD dip-buy rule became active again and bought back 15.58 shares ($8k) at $513.42. This went through even though the automated analysis said skip both times. AMD closed at $507.93, so the new shares are about -1% already.
  - Three NVDA and META buy orders were rejected because there was not enough cash.

**Per-strategy check**
- **AMD:** The strategy undid its own stop on the same day. The rebuy was below the price the strategy says breaks the thesis ($520). The new ~8.2% position has no working stop, because the stop already fired today. The dip-buy rule would also fire again with a $8k buy on any small further drop. Revision #206 proposed.
- **MU:** Low $849.25, close $856.49 on heavy volume. That is below the $858 low from 10/15, which the strategy itself says breaks the thesis. The stop (below $855) fired during the day and nothing was sold. That makes three MU stops in a week that fired without a sale. The position is about 12.7% of the account and about -15%, with no working stop. Revision #207 proposed.
- **META:** Close $648.85 (-7%), still above the $615 stop. The buy-the-dip rule for below $670 fired repeatedly and was rejected for cash. Even if it had filled, an $8k buy would have taken META to about 15.7%, above its own 15% limit. Revision #208 proposed.
- **TSM:** Close $412.38, low $410.22. The stop (below $405) and the thesis-break level (close below $407) both held, but the cushion is thin.
- **NVDA:** Close $212.21 on heavy volume. The $205 stop is about 3.4% away and the thesis is intact. Its buy orders keep being rejected for cash, which is expected while the account is fully invested.
- **AMZN:** Price is around $250, down from Monday's $262.45 breakout close. Earnings are 10/29. No action.
- **GOOGL:** Down 3.2%. Both buy-the-dip rules are paused until earnings on 10/28, as planned.
- **MSFT:** Down 2.2%. No rules near their prices.
- **TSLA:** Down 3.1%. The position is still a small stub rebuilding after earnings, and the Q3 result has not been checked yet.
- **AAPL:** Up 1.2%, the only gain in the account. This shows its diversifier role.

**Lessons**
- A buy-the-dip rule that can fire again, and whose weight limit is met right after a stop sells, will buy the same stock back within hours. Any revision that sets a stop near the current price should also pause that stock's buy-the-dip rules.
- Moving skipped stops lower each time (MU $900 → $855 → $849, TSM $418 → $405) turns stops into hopes. Set one final level and act on it.
- Current weight plus the planned buy size must stay under the strategy's maximum weight. I saved these three points to memory as a lesson.

**Proposals**
- **#206 amd-swing v12:** Pause the dip-buy rule and set a single-use stop below $485, about one day's normal range under today's low.
- **#207 mu-oversold-swing v13:** Set a single-use stop below $849, just under today's low, and mark it final: no more lowering.
- **#208 meta-swing v2:** Cut the $670 dip-buy to $4k, at most once a day, so a fill stays under the 15% limit.

**Day summary**
- The book had a broad up day. Equity is about $100.9k and cash is $843, so the book is about 99% invested, well above the 40-70% mandate.
- **NVDA:** the buy rule cut to $3,000 in revision #196 filled on its first try: 13.65 shares at $219.84.
- **GOOGL:** its buy rule (under $338, $5,000) fired three times. The broker gate rejected all three because the book had no cash.
- Positions with a stop rule that fired earlier and was never approved: none were near their stop levels today.
- **TSLA:** it reported Q3 results after today's close. I could not find the results, so the outcome is unknown.

**Per-strategy check**
- **aapl-swing:** up 1.32% (about $343.6 implied). No rule is close: trim is above $348, stop below $310, take-profit above $362. Fine.
- **amd-swing:** up 3.36% to $552.72, about 6% above the $520 stop. The deeper buy rule stays disabled, as intended, until AMD gets back above about $570. The first buy rule (under $600, $8,000) could not be paid for anyway. Unrealized loss is about -7.5%.
- **amzn-swing:** $262.37 (-0.10%). It is consolidating above its old range after the 10/19 breakout. The day's high of $264.35 stayed under the $268 take-profit. Q3 earnings are 10/29, so a fill before earnings is still fine.
- **googl-swing:** $334.76 (-1.62%, low $330.38, above-average volume). That is the lowest close since the 10/1 entry, though still inside the $327-365 range. The only catalyst I could verify is a KeyCorp price-target cut on 10/20 ($435 to $410, rating still overweight). This is a sentiment move, not a broken thesis. The buy rule is firing into certain rejection, and Q3 earnings come on 10/28, inside the 1-2 week holding window.
- **meta-swing:** up 0.47%, nothing near a trigger.
- **msft-diversifier-swing:** up 0.20%. The issues already on file remain: the take-profit was never re-armed and the stop is stale.
- **mu-oversold-swing:** $913.67 (+1.96%) on light volume. It is back above $900 but below the $930-950 level the strategy wants before re-entering. The hard stop under $855 is live and the buy rules are disabled. No action.
- **nvda-momentum-swing:** filled at $219.84 and closed at about $222. Weight is about 5.4% against a 12% target, and the $205 stop is intact. The smaller order size worked.
- **tsla-swing:** up 3.41% to $386.47 going into earnings. Skipping the buy rule before earnings kept the position small (about 2.5%). Plan to rebuild only after reviewing the results.
- **tsm-swing-contest:** up 1.57% (about $432 implied). The stop that fired earlier was moved to under $400 and is not in play. Weight is about 17%.

**Lessons**
- Sizing orders to the cash on hand works. Today's $3,000 NVDA order filled, while the earlier $8,000 version was rejected about 10 times. That fill used up the last cash, though, so every remaining $5,000+ buy rule (GOOGL, AMD, AAPL, AMZN) will be rejected until something is sold. New buys need a trim first.
- Three holdings report within the holding window: TSLA (10/21 after close), GOOGL (10/28) and AMZN (10/29). Buy rules should pause before earnings, as was done for TSLA.
- MU's light-volume bounce back above $900 does not confirm a recovery. A single reversal day already failed once, on 10/16.
- I saved the GOOGL and cash lessons to memory. MU's notes were full, so I replaced the old 10/14 note with today's.

**Proposals**
- **#199 googl-swing v3:** disable both buy rules until after the 10/28 earnings report. Reasons: three cash rejections today and earnings inside the holding window. Price levels, caps, stop (under $308), trim and take-profit are unchanged. After earnings, re-enabling only needs a state flip, as long as Cloud growth holds and cash has been freed by a trim elsewhere.
- No other revisions. The MU, AMD and NVDA fixes from 10/20 are behaving as intended.

**Day summary (2026-10-20, paper).** Nothing filled today. Equity is about $99.5k and cash $3,843, so the book is about 96% invested against the 40-70% mandate. Five buy orders went out and the system rejected all five because there wasn't enough cash: NVDA three times ($8k each) and AMD twice ($6k each). This keeps happening because each buy rule refires after a short cooldown even though it can never fill. Moves were mixed and small. TSM rose 1.2% and TSLA 1.5%, while META (-1.6%), GOOGL (-1.1%), AAPL (-1.0%) and MU (-1.0%) fell.

**Per-strategy check**
- **mu-oversold-swing:** MU opened at $884.40 (low $881.52) and closed at $896.07 on light volume (18.3M). That is its second close under $900 since 10/16. The <$900 sell-all stop has already fired and the sale was never approved, so the position (about 13% of the book, down about 11%) currently has no working stop. This was the main thing that needed fixing today.
- **amd-swing:** AMD hit a low of $524.60 and closed at $534.74, only about 2.7% above the $520 stop. The second dip-buy keeps firing and failing for lack of cash. Even with cash, buying more this close to the level where the thesis breaks, after the 10/16 data-center miss, is the wrong trade.
- **nvda-momentum-swing:** NVDA held its $205-234 range (low $212.77, close $216.47) on the lightest volume in a week. The thesis still holds. The position is only about 2.35% of the book against a 15% target, because the $8k dip-buy can never fill with the cash on hand.
- **tsm-swing-contest:** TSM closed at $425.29, comfortably above the new <$405 stop and back above $418. It is working as designed.
- **amzn-swing:** AMZN closed flat at about $262, after Monday's breakout. The sell-all take-profit at >$268 is about 2% away, and Q3 earnings are on 10/29. No change needed.
- **aapl / googl / meta / msft:** small down days with no rules near firing. No action.
- **tsla-swing:** Q3 earnings come out tomorrow (10/21). The plan stays the same: no buying before the report, rebuild the position afterwards.

**Lessons**
- A buy rule that refires but is bigger than the available cash produces nothing but rejections, so its orders need to be sized to the cash actually on hand.
- Every stop that has fired and then been skipped or declined needs to be checked. Otherwise the position is left with no stop at all, which has now happened twice (TSM on 10/16, MU today).
- I saved both points as a new lesson file and updated the MU, AMD and NVDA notes.

**Proposals** (all waiting for your approval on the Pending page)
- **#194, MU:** set a new one-time sell-all stop at <$855, just under the 10/15 low of $858. The dip-buys stay switched off.
- **#195, AMD:** switch off the second dip-buy (<$560). Turn it back on only after AMD gets back to about $570. The stop, trim and take-profit rules are unchanged.
- **#196, NVDA:** cut both dip-buy orders from $8k to $3k, with at most one fire per day, so an order can actually fill. Option rules, stop, trim and take-profit are unchanged.

Separately, getting back to the 40-70% invested band still requires trims, starting with the META/TSLA trim plan that hasn't been executed yet.

**Day summary (2026-10-19, paper).** There were no fills. Equity is about $99.7k, with cash of only $3,843 (about 96% invested, against the 40–70% the mandate allows). The bounce was broad: AMZN +4.98%, TSLA +3.76%, MU +2.97%, TSM +1.86%, AMD +1.76%, NVDA +1.38%, GOOGL +1.05%, MSFT +0.84%, AAPL -0.15%, META -0.55%. The automated monitor fired NVDA's first dip-buy twice, at about $218, and both were skipped because there wasn't enough cash. AMD's second dip-buy fired and was skipped for two reasons: no cash, and a weaker thesis after the 10/16 data-center miss. TSLA's first dip-buy re-armed again before its 10/21 earnings. This is the fourth straight session where the dip-buy rules fired with no money behind them.

**Per-strategy check.**
- **AMZN:** The clear standout. It closed at $262.45, a breakout above its $244–260 trading range since September, on the heaviest volume in two weeks (51.4M shares). I didn't confirm the cause, since my search found no news. The position is about 12% of the book and up about 6.7%. The trim rule stays idle until the weight passes 15%. The sell-all take-profit above $268 is about 2% away. Earnings are 10/29, so hitting that target before earnings fits a 1–2 week swing. No change.
- **MU:** It closed at $904.90 on lighter volume, with a low of $900.60. The re-armed sell-all stop below $900 missed by $0.60. The bounce did not get back above the $930–950 zone that the rules require before re-entering. I count today as an unconfirmed bounce. The stop stays in place, and lowering it would be a mistake.
- **TSM (largest position, about 17%, down about 5%):** The stop-loss is spent and still marked triggered, so this position has no live stop. The written exit condition, a close below $418 on heavy volume, was met on 10/16 ($412.61 on 16.6M shares) and nothing was sold. Today it closed back above at $420.29. Proposed #192 re-arms the stop at under $405, just below the $407 post-earnings low.
- **NVDA:** The thesis holds: price is in the $205–234 range and the $207.25 low is unbroken. Its first dip-buy can't fill without cash. No change to the rule; the problem is the cash level of the whole book.
- **AMD:** Its second dip-buy fires repeatedly and is skipped. The $520 stop is the real line, and the skips look right given the 10/16 data-center miss.
- **TSLA:** Skipping dip-buys before earnings (10/21) is still correct. Plan to rebuild after the report.
- **AAPL, GOOGL, META, MSFT:** Quiet. No rule is near its trigger and the theses are unchanged.

**Lessons.**
1. When the book is about 96% invested, repeating dip-buy rules only generate rejected or skipped orders. Making the orders smaller would push the book even further over the 40–70% limit. The fix has to happen at the whole-book level: free up cash by trimming names above target (AAPL about 16.5%, TSM about 17%) or by letting MU's stop sell it.
2. A one-shot stop that fires and is skipped stays dead until someone re-arms it. Every skipped stop needs a same-day re-arm, or the position quietly loses its protection, as TSM did.
3. A bounce on falling volume (MU) doesn't confirm anything.

Saved to memory: notes on AMZN and MU, and the cash lesson. I had to rewrite the lesson to fit the memory size limit, but it was saved.

**Proposals.**
- **#192, tsm-swing-contest v13:** Re-arm the stop-loss at under $405, sell all (it was at under $418, now spent). The exit condition becomes a heavy-volume close under $407. Entries, trim and take-profit are unchanged.
- I proposed no rule changes to the dip-buys. Their problem is the book's cash level, which is a decision for you, not something a rule edit fixes.

**Day summary.** 10/16 was a broad semis selloff and the fifth straight weak session for the semis legs. AMD fell -5.95% to $528.75, MU -5.63% to $878.84, TSM -2.29% to $412.59, GOOGL -2.47%, META -3.72% and NVDA -1.43% to about $217. AAPL was the only position up (+0.43%). Equity is $98.1k and cash is $3,843, so about 96% is invested against the 40-70% target range. Nothing filled today. The TSLA $8k dip-buy fired and was rejected for lack of cash. AMD dip-buy-2 and NVDA dip-buy-1 re-armed and fired again, and the analysis said skip both for the same cash reason. In three days, at least six buy-the-dip orders have failed because there was no cash. My search turned up no specific news behind the drop, so I can't tie it to a cause.

**Per-strategy check.**
- **mu-oversold-swing:** The strategy's own exit condition has now been met. MU opened at $905 and closed at $878.84, near the day's low of $875, on 29.1M shares. That volume was above normal, and the close was below $900. Yesterday's heavy-volume bounce from $858 back to $931 was a false bottom. MU is down about 19% from its 10/7 close. The position is 14.35 sh @ $1,004.67, about -12.5% (-$1.8k) and about 12.9% of the book. I queued revision #183.
- **amd-swing:** Closed $528.75, only about 1.7% (about 0.4 of a typical day's range) above the <$520 sell-all stop. The intraday low was $526.83. The stop may well fire on Monday. The cut is at a point the strategy chose ahead of time, so I left it alone. dip-buy-2 can't work with no cash. The position is about -11.5%.
- **tsm-swing-contest:** Closed $412.59, below the $418 stop that fired yesterday. The skip on 10/15 depended on the close staying above $418, and today it didn't. Pending #172 would re-arm the stop lower at <$400, about 3% below today's close. TSM is the long-term anchor and the record Q3 results don't break the thesis, but you should look at #172 knowing that the $418 condition has now failed.
- **nvda-momentum-swing:** About $217, inside its $205-234 range, with the $207.25 swing low intact. Only about 2.4% of the book. The thesis holds; the dip-buy simply can't be funded.
- **tsla-swing:** Skipping the entry before earnings was right; Q3 earnings are on 10/21. Rebuild the position after the report.
- **aapl / amzn / googl / meta / msft:** All inside their price ranges and no rule is close to firing. The non-semis positions held up better again (AAPL was green), so they are diversifying as intended.

**Lessons.**
1. One heavy-volume reversal day is not a bottom. The 10/15 MU bounce reversed within a day. Wait for a second close above the reversal zone.
2. The book can't buy dips while it is about 96% invested. Above roughly 85% invested, trims or exits should come before new buys. Rules that keep re-firing a buy with no cash behind it only add noise.
3. Lowering a stop right after the price hits it (#172, #173) is the pattern of keeping a broken trade alive that your rules warn against. Judge each case against the strategy's own exit condition.

**Proposals.**
- **#183, mu-oversold-swing v11 (needs your approval):** Keeps the stop at <$900 (sell all), which replaces #173's lower <$840 stop. If MU is still below $900, it sells at the next check. It also turns off both MU dip-buys so the strategy can't buy back in on the way down. The trim and take-profit rules stay. If approved, about $12.6k becomes cash and the book drops to about 83% invested. If you'd rather keep holding MU, reject it.
- **No new revision for TSM or AMD.** The TSM decision is already in front of you as #172, and the AMD stop is already set at a level the strategy picked.

**Day summary (2026-10-15).** Semis took a gap-down flush and recovered part of it by the close. TSMC reported a record Q3 before the open: net profit NT$763.1B, up 68.7% year on year, beating on both revenue and profit. TSM still opened at $415.17, fell to $407.15 and closed $422.55 (-1.73%) on heavy volume (21.1M). This looks like selling on good news and sector de-risking, not damage to the thesis.
- **Semis:** MU opened at $871.58 and fell to $858, its fourth gap-down in a row. It then reversed to close $931.24 (+1.87%) on the heaviest volume of the selloff (35.8M). AMD hit $530.09 and closed $562.23 (-1.50%). NVDA hit $212.85 and closed $217.23 (-1.84%).
- **Diversifiers:** they held flat to slightly up (MSFT +1.08%, GOOGL +0.45%, AMZN +0.27%).
- **Equity and cash:** equity is ~$100.7k and cash only ~$3.8k, so ~96% is invested against the 40–70% target.
- **Trades:** no fills. The broker rejected 4 orders today (NVDA dip-buy-1 $8k ×2, AMD dip-buy-2 $6k ×2) for lack of cash, on top of 3 NVDA rejections on 10/14.

**Per-strategy check**
- **tsm-swing-contest:** dip-buy-2 filled 11.50 sh @ $434.85 on 10/14. TSM is ~17% of equity (target 15%) and ~-4.6% on the position.
  - The one-shot stop (<418) fired intraday today. The analysis said skip, and the close held above $418, so the invalidation rule (a heavy-volume close below $418) was not met.
  - The stop is now spent, so the book's largest position has no stop. #172 re-arms it.
- **mu-oversold-swing:** the same pattern. The <900 stop fired at the open, the skip advice held, and MU closed above $900.
  - MU is ~13% of equity and ~-7.3% on the position.
  - Today looks like a possible capitulation-and-reversal. The stop is spent, so #173 re-arms it.
- **amd-swing:** dip-buy-2 (<560) triggered twice and was rejected for lack of cash. AMD is ~9.8% of equity, ~-6% on the position. The low of $530 sits $10 above the <520 stop. The setup is sound; it is only blocked by cash.
- **nvda-momentum-swing:** dip-buy-1 was rejected for the fifth time. NVDA is only ~2.3% of equity against a 15% target. The $207.25 swing low that invalidates the thesis held (low $212.85), and the <205 stop is intact. Today's low came within $0.85 of entry-call (<212, $1k call).
- **tsla-swing:** dip-buy-1 triggered at $361.93. The analysis said skip ahead of the 10/21 Q3 earnings, which is reasonable. TSLA is ~2.3% of equity.
- **aapl-swing, amzn-swing, googl-swing, meta-swing, msft-diversifier-swing:** quiet, no rules near triggering. AAPL is ~16% of equity, above its 15% target; it is the obvious name to trim for cash.

**Lessons**
1. **One-shot intraday stops get used up by gap-flushes the analysis rightly skips.** Each one then leaves the position unprotected. Re-arm a skipped stop below that day's low (~2 ATR) the same night. Set intraday stops as disaster backstops below the invalidation level, not at it.
2. **Re-arming dip-buys do nothing without cash.** Seven rejections in two sessions show the real limit is the whole book being ~96% invested. Trims of overweight names have to fund the dip-buy ladders; repeated cash rejections are noise, not signal.

**Proposals**
- **#172 (tsm-swing-contest v13):** re-arm the stop at <400, below the 10/15 low of $407.15. The invalidation rule stays a heavy-volume close below $418. Nothing else changes.
- **#173 (mu-oversold-swing v11):** re-arm the stop at <840, below today's low of $858. The invalidation rule stays a heavy-volume close below $900. Nothing else changes.
- **Not proposed:** a book-level cash fix, such as trimming AAPL or TSM to fund the NVDA and AMD dips. That is a portfolio-allocation call I'm leaving to the user rather than putting into any single strategy's rules.

**Day summary (2026-10-14):** Semis sold off hard: AMD -5.7%, MU -4.1%, TSM -3.4%, META -3.3% and NVDA -3.2%. Only AAPL rose (+0.5%). Equity is about $100.8k with only about $3.8k cash, so about 96% of the account is invested. That is well above the 40-70% band the mandate asks for. There was one fill: TSM dip-buy-2 bought 11.50 shares @ $434.85. TSM closed at $430.08, so that fill is already slightly under water. NVDA dip-buy-1 ($8,000) triggered three times. At least two of the resulting orders were rejected because there wasn't enough cash; the system doesn't record the reason, but $8,000 against about $3.8k of cash is the obvious one. A web search found only an unverified report linking AMD's drop to tech executives calling for a pause in frontier AI. I could not confirm a single cause for the selloff.

**Per-strategy check:**
- **nvda-momentum-swing:** Closed $221.30 on heavy volume (112M shares). The rule worked as written, but each $8,000 tranche is more than double the cash on hand. The 90-minute re-arm therefore just keeps producing rejected orders. The position is only about 2.4% of the account versus a 15% target. The thesis still holds: the low was $219.64, well above the $207.25 invalidation level.
- **tsm-swing-contest:** The $440-450 support broke on above-normal volume (13.0M shares). The position is now 40.43 shares @ $442.91, about 17% of the account (target 15%, max 20%). Both dip-buys are blocked by their weight caps. The stop at <$418 is about 2.8% (1.4 daily average ranges) below the close. If it fires, that would be a real thesis break, not noise.
- **mu-oversold-swing:** Third straight down day, closing on the low at $914.13, under the $929-938 support. The position is about 9% down (-$1.33k) and about 13% of the account. The intraday stop at <$900 is only about 1.5% away. That stop exists by design, so I'm leaving it.
- **amd-swing:** Closed $570.82 with a low of $567. Position is about 10% of the account and about 4.4% down. Dip-buy-2 (<$560) is about 2% away, but it can't be paid for with current cash. Stop <$520 is armed.
- **aapl / amzn / googl / meta / msft / tsla:** Moves of -1.7% to -3.3% (AAPL was up). No rules came close to firing. Nothing changed in their theses.

**Lessons:**
- Rules that buy repeatedly were sized when the account had plenty of cash. Once the account is fully invested, they just generate rejected orders. Each buy should be sized to the cash actually available. In a fully invested account, new buys can only be funded by trims elsewhere.
- About 42% of the account is in semis (TSM 17%, MU 13%, AMD 10%, NVDA 2.4%). A move that hits the whole sector now affects four positions at once. MU and TSM are both close to their stops.

**Proposals:**
- **#161 nvda-momentum-swing v12:** Cut both NVDA dip-buys from $8,000 to $3,000, which current cash can cover. Also cap dip-buy-2 at 12% of the account (was 20%) so we don't keep piling into a sector-wide drop. Prices, stops, take-profits and option rules are unchanged.
- No change to the MU and TSM stops. They sit at levels set from each stock's typical daily range and are meant to fire if price breaks down.

**Day summary:** Equity is about $103.45k, nearly unchanged on the day. Cash is $8.8k, so about 91% is invested, above the 40-70% target band. Most names moved less than 1%. The exceptions were META (+2.6%), AMD (+1.9%) and MU (-3.6%). There was one trade: MU's second dip-buy rule bought 4.26 shares @ $938.38 near the day's low. The pre-trade analysis had recommended skipping it twice. MSFT's sell-everything take-profit rule (above $545) also triggered at the $551.15 intraday high, but the pre-trade analysis recommended skipping it and no sale happened.

**Per-strategy check:**
- **mu-oversold-swing:** MU gapped down for the second day in a row. It opened at $934, hit $929 and closed at $953.19 on 28.4M shares, a little above normal volume. I could not confirm the cause. It is now 14.35 shares @ $1,004.67, about 13.2% of the account (target 10%, max 15%), down about 5%. Both dip-buy rules are now blocked by their weight caps, so there's no risk of overbuying past the 15% max. The stop at $900 is about 5.6% below the close, roughly 1.3 times a typical day's move. That makes it the book's most likely exit. It should stay as it is: a heavy-volume close under $900 is the strategy's own invalidation signal. No change proposed.
- **msft-diversifier-swing:** MSFT has made higher lows since the 9/25 breakout, from $497 up to $543. With the take-profit skipped, the strategy has no upside exit left. Its $480 stop sits about 12% below price, around six typical daily moves, and dates from before the breakout. Revision #154 is queued to fix both.
- **amd-swing:** Up 1.9% after the 10/12 dip-buy, now about 10.4% of the account and slightly in profit. No rule is close.
- **tsm-swing-contest:** Flat (+0.1%), about 12.4%. Its dip-buy is blocked by the weight cap. Fine.
- **aapl-swing / amzn-swing / googl-swing:** Changes under 0.4%, all within their trading ranges. AAPL is about 15.8% of the account, AMZN about 11.4%, GOOGL about 8.1%. No rule is close.
- **meta-swing:** +2.6%, about 8.2%. No fill.
- **nvda-momentum-swing / tsla-swing:** Small leftover positions of about 2.4% each, below target after earlier trims. TSLA reports earnings on 10/21. No action.

**Lessons:**
1. When a one-time "sell everything" rule is skipped, the strategy is left with no upside exit. Re-check its exits and stops the same day.
2. MU's dip-buy went through even though the analysis recommended skipping it twice. A "skip" recommendation is only advice, so rules should be sized as if they will fill. The 10/12 change that shrank this purchase to $4k kept the position within its 15% max.

**Proposals:**
- **#154 msft-diversifier-swing v5:**
  - Move the stock and option stops from $480 to $515, just under the 10/8 pullback low of $518.79 (about three typical daily moves below price).
  - Bring back the take-profit at $575, the analyst target cited when MSFT broke out.
  - Leave the other rules unchanged and add no new buying room.
- Nothing proposed for MU, whose rules are sized correctly after the 10/12 revision.

**Day summary (2026-10-12, paper):** Semiconductors kept selling off for a third session. MU fell 3.88% to $989.04 and broke its $1,010–1,035 support. TSM fell 1.92% to $444.59, AMD 2.28% to $594.24 and NVDA 1.29%. Non-semis names offset part of that: META +3.38%, AAPL +1.29%, MSFT +1.14%. Two dip-buys filled, both as designed:
- **AMD** dip-buy-1: 13.40 sh @ $596.80, about 8.5% below the 10/6 record. The position is now 17.59 sh @ $597.21, about 10.1% weight.
- **TSM** dip-buy-1: 11.19 sh @ $446.89, inside the $440–450 support zone and on light volume. The position is now 28.93 sh @ $446.12, about 12.5% weight.

Both rules re-armed after their cooldowns. Neither can fire again at current weights because both positions are now above the rules' weight caps. Equity is about $103.2k and cash about $12.8k, so roughly 88% is invested, still above the 40–70% target band. Semis are now about 35% of equity.

**Per-strategy check:**
- **amd-swing:** v9's pullback-only ladder worked on its first real pullback. One problem: dip-buy-2 (<$560, cap 16%, $8k) could push the position to about 24% in the worst case, which is above its own 20% max. I proposed a fix (#150).
- **tsm-swing-contest:** The fill was clean and support is holding so far. dip-buy-2 (<$435, $5k) would take the position to about 17.4% at most, under the 20% max. The stop at <$418 is about 6% below. No change needed.
- **mu-oversold-swing:** The position is about -4.2%. dip-buy-2 (<$970) is only about 2% away, and an $8k fill would put MU at about 17.5%, above its own 15% max. I proposed a fix (#149). The stop at <$900 and the HBM thesis are unchanged. I found no news explaining today's move beyond sector-wide weakness.
- **nvda-momentum-swing:** The stake is small (about 2.4%) and no rules are near their trigger prices. No change.
- **aapl-swing, msft-diversifier-swing, googl-swing, meta-swing, amzn-swing:** These non-semis names did their job and held up the book. No rules fired, and none of them looks off.
- **tsla-swing:** The stake is small (about 2.4%). Q3 earnings on 10/21 are the next event risk. No change.

**Lessons:**
- I saved a new sizing lesson: buy rules can overshoot too, just as trims overshot last week. A dip-buy rule is only safe if its weight cap plus the tranche's share of equity stays at or below the strategy's max weight. Ladder audits should also check that all armed tranches together fit in available cash.
- AMD's fill suggests pullback-only ladders do fill when their levels sit about one volatility-sized move below the recent trading range.
- I replaced an outdated MU memory entry with today's break of support.

**Proposals:**
- **#149 mu-oversold-swing v10:** dip-buy-2 changes from cap 13% / $8,000 to cap 11% / $4,000. The worst case stays under the 15% max.
- **#150 amd-swing v10:** dip-buy-2 changes from cap 16% / $8,000 to cap 13% / $6,000. The worst case is about 18.8%, under the 20% max.
- Price levels, stops, take-profits and theses are unchanged in both. Both need your approval on the Pending page.

**Day summary.** It was a quiet day with one trade. Equity is about $103.5k and cash about $25.8k, so roughly 75% is invested. That is above the 40-70% band the mandate asks for. The diversifiers led: AMZN +3.29% (closed $262.43, high $262.80, a new high for its September range) and MSFT +2.38%. The semis drifted lower: AMD -2.03%, TSM -1.03%, MU -0.66%, NVDA -0.52%. The only fill was the tsla-swing trim. It sold 15.60 TSLA shares for $6,000 at $384.53, after the stock opened at $382.38 and reached $388.56. TSLA closed at $382.70 (+2.05%). Nothing is waiting for approval except the new proposal below.

**Per-strategy check.**
- **tsla-swing:** The trim fired in a way that contradicts this strategy's own stated plan. The pre-trade analysis recommended skipping it for three reasons: price was only $0.45 above the trigger, the position (8.25%) was already below its 10% target, and Q3 earnings are on 10/21. The trim went through anyway. It sold about 5.8% of equity and left about 2.4% (6.50 shares averaging $361.93). The strategy text promises a 6% minimum after trims, but the rule uses 4%, and one $6,000 sale is bigger than the gap between them. The rule re-armed at 15:08. At today's weight it can't fire again, since the stake is below the 4% minimum. Rebuying needs the stock to fall about 5% to under $362. The take-profit (sell all above $410) is about 7% away and the stop (below $335) about 12% away. I proposed a fix (#146).
- **amzn-swing:** Weight is about 11.5% after today's rally. The trim needs weight above 15%, so it stays inactive, which is how the 10/6 change was meant to work. The sell-all take-profit above $268 is only about 2.1% away. If it fires it closes a position bought at an average of $245.90, which would be roughly a +9% win. That is acceptable for a swing.
- **msft-diversifier-swing:** Up 2.38% and still working as the low-correlation leg against the semis. Weight is below the 8% minimum, so the trim stays inactive.
- **aapl-swing:** Down 1.11%. The position (48 shares averaging $333.31) is inside the rule range. The stop below $310 and the trim above $348 are both far off.
- **amd-swing:** Down 2.03%, about 2.6% weight. The 10/6 trim already overshot. The dip-buys at <$600 and <$560 are within reach on a moderate pullback.
- **mu-oversold-swing, tsm-swing-contest, nvda-momentum-swing:** Small moves on the day. Every rule is well away from price. Positions are near cost (MU) or in profit (TSM, NVDA).
- **googl-swing, meta-swing:** Small moves and nothing near a trigger.

**Lessons.**
1. The trim rule overshot for the fourth time in a week (MSFT 10/5, AMD and AMZN 10/6, TSLA 10/9). The cause is that the dollar amount of one trim is bigger than the gap between the current weight and the minimum weight. I saved this to memory as a lesson. The fix: set the minimum to at least target minus one sale, and only trim once weight is above the minimum plus one sale.
2. Because these strategies run in confirm mode, I can't tell from the log why the trim executed despite the skip advice. Either it was approved by hand or the advice wasn't shown at approval time. Approvals should be checked against the attached analysis.

**Proposals.**
- **#146 tsla-swing v2:** Trim only when weight is above 13% and price is above $390, and sell $4,000 each time. That keeps the position around 9% after a trim and needs a real break above the $386-389 highs. Entries, stop, take-profit and the conditions that would end the thesis are unchanged. I added no new buy ahead of the 10/21 earnings report.
- **Not proposed:** fixes for the other three strategies that overshot. AMZN and MSFT are now protected by their minimum-weight conditions. AMD's damage is done, and its dip-buys rebuild the position if the price comes back.

**Day summary (2026-10-08, paper):** No rules fired and nothing is pending. Chip stocks fell together. News reports blamed higher bond yields and oil prices, plus Samsung's Q3 operating profit, which jumped but still came in under very high expectations. MU fell -4.79% to close at $1,035.84, AMD -3.90% to $620.68, TSM -3.00% and NVDA -2.94%. AMZN fell -2.25% and MSFT -1.35%. AAPL rose +1.11%, and META, TSLA and GOOGL were roughly flat. Equity is about $103.2k (roughly $103,171–103,176) and cash is $19.8k, so about 81% of equity is invested. That is above the 40–70% band, but this paper phase aims for high activity. Every position still shows an open gain. Caveat: the position values the portfolio tool reported look the same as the session-start snapshot. They may not include today's close yet, so treat the equity figure as approximate.

**Per-strategy check:**
- **mu-oversold-swing:** Today wiped out most of 10/7's rebound. The 10.09 shares bought at $1,032.67 average are now about breakeven, at ~10% weight against a 10% target. No rule is close to firing:
  - dip-buy-1 is blocked by its weight cap.
  - dip-buy-2 (<$970) is 6.4% below.
  - The stop (<$900) is 13% below.
  - The trim (>$1,100) is 6.2% above.
  
  The $1,010–1,035 area has now held as a low in three dips over eight sessions. The thesis still holds.
- **amd-swing:** Holds 4.18 shares, ~2.5% weight against a 12% target. dip-buy-1 (<$600) is now only 3.3% below, so it is the nearest buy in the book. If it fires, the $8k tranche would take the position to about 10%. That's acceptable.
- **tsm-swing-contest / nvda-momentum-swing:** They fell with the sector, but no rule was reached. NVDA is still above its dip-buy levels, and TSM's dip-buy is still below the price.
- **aapl / amzn / googl / meta / msft / tsla swings:** These moved within their normal daily range and triggered nothing. AAPL rising on a day chips sold off is consistent with its role as a diversifier.

**Lessons:** When the whole sector drops 3–5% in one day on macro news, the buy ladders should stay quiet, and they did. Losses from the chip names were mostly offset by the non-chip names. One down day is not a reason to move the buy levels closer to the price. I saved this lesson to memory and added a MU note on today's support level, replacing an outdated entry.

**Proposals:** None. Nothing measurably diverged from the strategies' stated assumptions.

**Day summary.** The account had one trade today. MU opened with a gap down to $1,017 (low $1,011), then reversed and closed at $1,088 (+4.06%) on above-average volume (29.9M). Its first buy-on-dip rule (price under $1,030) triggered near $1,015. Because the strategy needs my approval before trading, the order only filled at 14:01 ET, at $1,034.43. That is above the rule's own price, but the stock still closed 5.2% above the fill. TSM fell 2.10% to $472.15 on light volume (6.4M) after its 10/5 record. META fell 2.38% to $721.31 and closed near the day's low. AMZN (+1.42%), AAPL (+0.91%) and GOOGL (+0.81%) rose, so the names outside semiconductors offset some of the semiconductor weakness. About 81% of equity is invested (cash is $19.8k of $104.4k), still above the 40–70% target band. No orders are waiting for approval.

**Per-strategy check.**
- **mu-oversold-swing:** The fill matched the design: buy into a real intraday flush, as on 10/1. MU is now 10.09 shares at an average cost of $1,032.67. That is about 10.5% of the account against a 10% target. The first buy-on-dip rule no longer applies because MU is above its 6% weight limit. The partial-sell rule above $1,100 is 1.1% away and is the most likely next trade. The stop at $900 is sound.
- **tsm-swing-contest:** This looks like a normal pullback after the record, on the lightest volume in two weeks. The position is about 8%, still up roughly 6% against cost. No rule is close to triggering.
- **meta-swing:** META is about 7.7% of the account and $1.31 above the $720 buy level. That buy rule can't fire anyway, because it requires META to be under 5% of the account. The stop at $615 is far away. Nothing to act on.
- **amzn-swing:** The partial-sell rule reset this morning. It will not sell because AMZN is about 11% of the account, under its 15% sell threshold, which is how the 10/6 change intended it to work.
- **aapl-swing, googl-swing, msft-diversifier-swing, amd-swing, nvda-momentum-swing, tsla-swing:** All moved less than 1%. None of their rules were close to triggering. The known AMD and NVDA problem remains: their buy levels sit far below the market, so those rules can't trigger (already recorded in memory).

**Lessons.** Approval delay on high-volatility names consistently puts fills on the wrong side of the trigger: the 9/21 MU take-profit filled at $1,038 against a rule of above $1,050, and today's buy filled at $1,034 against a rule of below $1,030. I saved this as a lesson: treat triggers as zones of about ±1% (about a third of a typical day's range), and don't count fills inside that zone as rule errors. I updated the MU memory with today's flush-and-reversal fill and the new position size.

**Proposals.** None. Every strategy behaved as written today. Investment above the target band is a portfolio-level issue that is already being addressed through sell rules, not a flaw in any one strategy.

**Day summary:** It was a quiet, mildly risk-on day. Account equity is about $104.0k and cash is about $27.8k, so roughly 73% is invested, slightly above the 40-70% band. Two trims filled, both well placed:
- **AMD:** sold 9.18 shares @ $653.39 against a record close of $649.42 (+2.80%, day high $658.52).
- **AMZN:** sold 19.54 shares @ $255.92 against a close of $256.29 (+1.95%), at the top of its $244-260 range since September.

MU (-1.73%) and TSM (-0.73%) were the weakest names, and no stop came close. The pending queue is empty.

**Per-strategy check:**
- **amzn-swing:** The first trim was correct: weight went from about 16% to about 11.2%. The rule then re-armed and fired again at 18:08 and 19:38 ET with weight already below the 15% target. Its sell condition only checks that weight is above 10%, and each $5,000 sale removes about 5 points. So a second sale would have taken the position to about 6%, below the 10% minimum it was supposed to protect. The sentinel declined the 19:38 fire on its own judgment, not because a rule blocked it. This is measurably wrong, so I proposed #141.
- **amd-swing:** The trim worked as designed and booked about +9% on those shares. With a 5% floor and a $6,000 sale, weight went from about 8.4% to about 2.6% in one fire, against a 12% target. The trim can't fire again now. The buy levels sit 8-14% below the price, which is deliberate while AMD is stretched after a big run. I'm accepting the small position for now; no revision.
- **aapl / googl / msft / tsm / nvda / mu / meta / tsla:** No rules fired and all moved less than 2%. All are holding inside their stated ranges. NVDA's full take-profit (>248) and TSM's (>510) remain the closest triggers to watch.

**Lessons:** I saved a new lesson ("trim-arithmetic"). A trim rule that re-arms can push weight down to its trigger level minus one sale. So the trigger should sit at or above the target weight, or at least the minimum weight plus one sale, or the "floor" doesn't protect anything. AMD and AMZN both showed this today. I also updated the AMD memory note.

**Proposals:** #141 amzn-swing v3 raises the trim trigger from weight above 10% to above 15% (the target). One $5,000 sale then leaves at least about 10%. Price levels, buy rules, stop and take-profit are unchanged.

**Day summary (2026-10-05, paper):** It was a strong day for AI and mega-cap stocks. TSM closed at a record $485.91 (+2.78%), NVDA at a record $238.90 (+2.12%), TSLA rose 2.20%, META 1.90% and MSFT 1.48%. MU slipped 1.02%, and AAPL, AMD and AMZN ended about flat. Two trades went through, both at 13:40 ET:
- **MSFT:** a trim sold 11.33 shares at $529.48, 0.8% above the $525.18 close.
- **TSM:** a trim sold 8.34 shares at $479.67, about $6 below the $485.91 close.

Both rules re-armed after their 90-minute wait. Neither fired again, because each position had dropped below the weight limit that lets the rule sell. Cash rose from about $6.8k to $16.8k, so the share of the account invested fell from about 93% to about 84%. That is still above the 40–70% target band, but moving the right way. Nothing is waiting for approval.

**Per-strategy check:**
- **tsm-swing-contest (v12):** The revision made on 10/2 (sell $4k once the stock is over 11% of the account; full-exit level raised to above $510) worked on its first test. It took a partial profit at a record high and kept most of the position. TSM is now about 8.3% of the account (17.74 shares at an average cost of $435.64, up about 11.5%). The full-exit level is about 5% above the price, the first buy level (<$447) about 8% below, and the stop (<$418) is fine. Selling near the open gave up about $6 a share as the stock kept climbing, which is the accepted cost of selling in steps.
- **msft-diversifier-swing (v4):** This was the first move through $525 since the 9/25 breakout, and the sale price was good. MSFT is now about 6.9% of the account, up about 5%, which is below the 8% level that allows another trim. The full-exit level (>$545) is 3.8% above the price, the buy levels (<$508 and <$495) are below it, and the stop at <$480 is fine. No change needed.
- **nvda-momentum-swing (v11):** NVDA has broken above the $205–234 range the strategy is built around. The position is small (about 2.5% against a 15% target), and the buy levels (<$222 and <$213) are 7–11% below the price, so they are unlikely to fill. Normally that would call for a fix. I left it alone because the account is already above its target invested range. One thing to watch: the full-exit rule at >$248 is only 3.8% above the price and would sell the whole position.
- **tsla-swing:** Closed at $378.73, about 1.7% under the trim level (>$385). Rules are consistent with the thesis.
- **meta-swing:** Closed at $741.90, between the buy level (<$720) and the trim level (>$800). Nothing to do.
- **aapl-swing, amzn-swing, googl-swing, amd-swing, mu-oversold-swing:** Quiet day for all five, no rules near firing and no changes to their theses. AMD and MU remain the volatile, short-term-trade names.

**Lessons:**
- Trims that only fire while a position is above a set share of the account are working as a funding source. Each name sells once on a strong day, the core position stays, and cash builds for the buy ladders with no manual step. If that share limit sits just under the current weight, one sale per day is the normal result, not a bug.
- Buy-on-pullback ladders get stranded when a stock breaks out (NVDA again). That is acceptable while the account is over-invested, but the full-exit levels need watching so they don't quietly sell a whole small position.

**Proposals:** None. No strategy's behaviour clearly diverged from its stated assumptions. The NVDA issues are on the watch list, to be re-anchored if the price gets near $245.

**Day summary**
A broad, strong risk-on session: nine of ten positions closed green. Equity $102,404 (+$10 vs session start on a mark-to-market basis), cash down to $6,844 — roughly 93% deployed, well above the phase-3 40-90% band. TSM led with +2.99% to a record close of $472.92 (open $465.64, high $474.79) on unremarkable volume (8.9M, inside the 7.7-11.3M two-week range), TSLA +4.65% on a Q3 delivery beat (486,532 delivered vs ~462k consensus; earnings 10/21), AMD +2.95% to $633.91, NVDA +1.34% to a new high close of $233.95 on heavy 129.7M volume. The only loser was MU, -2.05%: it opened $1,107.45, printed $1,107.86, then faded to $1,074.89 — and that fade is exactly where the day's single trade happened. One fill: mu-oversold-swing/trim-strength (weight>0.04 and price>1100 → sell $6,000) executed at 13:37 ET, 5.4329 sh @ $1,104.38, then re-armed at 15:07 ET. That fill was 2.7% above the close and within 0.3% of the day's high — the best execution of any trim this book has produced. Pending queue was empty at the open and nothing else triggered.

**Per-strategy check**
- mu-oversold-swing (v9): Working as designed and the day's clear success. The $1,100 trim threshold was set on 9/26 "above today's high" and MU reached it twice since; today it sold into the spike at $1,104.38 rather than chasing. Remaining 2.358 sh @ $1,026.89 (2.5% weight, +$112). Dip-buy-1 (<1030) is ~4.2% below market and genuinely reachable given this name's ~$40 ATR. No change warranted.
- tsm-swing-contest (v11): Measurably off — revision proposed. At $472.92 the >475 full take-profit is 0.44% away and would liquidate the book's largest winner (+$954, +7.5%) and its designated patient anchor on a further 0.4% move. Meanwhile v11's 15% trim floor blocks any partial trim at 12.0% weight, so at a record high the strategy's only live exit is the full one. Entries (<447/<435) and the <418 stop remain sound.
- nvda-momentum-swing (v11): Thesis of a $205-234 oscillation is now being tested on the upside — close $233.95 is at the top of that range, and trim-strength (>232, floor 8%) did NOT fire because weight is only 2.5% after earlier trims. The rule is structurally dead at current sizing, not broken. Option exits (>227) remain triggered. Watch, do not re-anchor on one day.
- tsla-swing (v1): Thesis explicitly named delivery guidance as the invalidation test; today's print beat and the stock added +4.65%. Position 22.1 sh @ $361.93 (+$182, 8.0%). dip-buy-1 (<362) is now below market and dormant; trim at >385 is the next live level. Consistent.
- amd-swing (v9): Deliberately set entry ceilings below market because AMD was extended; at $633.91 dip-buy-1 (<600) is 5.3% below and trim (>650) 2.5% above. Position +$462. The pullback-only design is being respected rather than deadlocked — in range on both sides, which is the fourth-time-lucky version of this name's old problem.
- amzn-swing (v2), googl-swing (v2), aapl-swing (v2): All post-sizing-revision and all quiet, which is the intended behavior. AMZN 16.0% weight (above the 15% target, both dip-buys correctly blocked), GOOGL 8.0% vs 15% target with dip-buy-1 (<338) ~2% below market, AAPL 15.6% weight at essentially flat cost. No divergence.
- meta-swing (v1): +0.30%, position +$91 at 7.9% weight — at target. Entry levels (<720/<670) sit below market as designed; trim at >800 far off. Nothing to do.
- msft-diversifier-swing (v4): +0.92%, +$443, weight 12.6% vs 15% target. dip-buy-1 (<508) and the entry-call (<505) are both close to market and still live. Working.
- crm-fade-swing: archived, no rules, no action.

**Lessons**
Two durable observations. First, the MU trim is the cleanest evidence yet that a trim threshold set deliberately *above* the prevailing high — rather than at a round number near market — gets filled into spikes instead of into fades: $1,104.38 against a $1,074.89 close. Second, and the real finding of this pass: a full-position take-profit placed only ~4% above market decays into a disguised stop within a single strong session. TSM's >475 was written five sessions ago at $456 and is now 0.44% away; the same geometry, applied to a 15%-target anchor, would undo weeks of patient accumulation because price went up 3% on average volume. Full exits belong at blow-off distance; staged trims belong near market. A third, softer point: at 93% deployed with ten ladders armed, trims are no longer just profit-taking — they are the book's only funding mechanism, so a blocked trim rule now has a second-order cost across every other strategy.

**Proposals**
One revision queued: #135, tsm-swing-contest v12. It moves the full take-profit from >475 to >510 (~7.8% above market, beyond any measured move from the $424-462 base) so it is a genuine blow-off backstop again, and lowers the trim floor from 15% to 11% with the trim trigger at >468 and a $4,000 tranche (max 2 fires/day, 90m cooldown) so strength can be harvested in ~4pp steps from today's 12.0% weight instead of jumping straight to a full liquidation. Entries, the <418 stop, and all other price anchors are untouched. Awaiting your approval on the Pending page — I cannot apply it myself. No other strategy showed a measurable divergence from its stated assumptions today, so no other proposals.

Day summary
Two rules fired, both as designed, and both bought real weakness rather than chasing. mu-oversold-swing/dip-buy-1 filled 7.791 MU shares @ $1,026.89 ($8,000) at 14:22 ET — MU had opened $1,054.34 and flushed to $1,022.90 after FQ4 FY2026 (record revenue and cash flow, beat on the print, but heavier capex guidance hit the stock after hours on 9/30), then reversed to close $1,097.39 (+3.03%) on 44.5M shares, the heaviest volume in weeks. The fill landed 0.4% off the session low and was +6.9% (+$522) by the close. googl-swing/dip-buy-1 filled 23.747 GOOGL shares @ $336.88 ($8,000) at 16:52 ET as GOOGL sold off from a $350.79 open to a $335.51 low, closing $338.24 (-1.70%) — a press report of internal skepticism about the next Gemini model erased an intraday gain. That fill was also 0.4% above the low and 0.4% below the close. Elsewhere the book was quiet: AMD +0.65%, TSM +0.66%, NVDA +1.09%, MSFT -0.02%, META +0.10%, TSLA -0.20%, AMZN -0.37%, AAPL -0.81%. Equity $100,867 with $844 cash — the book is now ~99% deployed, which is above the mandate's 40-70% band and is the single most important fact of the day. Pending queue was empty at session start; my revision is now the only item.

Per-strategy check
- mu-oversold-swing (v9): working exactly as written. dip-buy-1's 0.06 cap sits below the ~8% weight one $8,000 fire creates, so the rule self-blocks after one fire — correct geometry. It re-armed at 16:22 ET but price was already back above $1,030, so no second fire. trim-strength (>1100, floor 4%) missed by $1.10 (high $1,098.90) and is the book's next live rule. Stop <900 is ~18% below, wide but intentional for a ~3.7% ATR name.
- googl-swing (v1): thesis validated on the first fill, geometry not. dip-buy-1 capped at 0.10 while an $8,000 tranche is ~8% of equity, so the re-armed rule could fire again and carry weight to ~16%, past the 15% target; dip-buy-2's 0.18 cap plus another tranche could then breach max_weight 0.20. With $844 cash any further $8,000 fire would be margin-funded. Revision proposed.
- aapl-swing (v2) / amzn-swing (v2): already carry the $5,000-tranche fix. AAPL -0.81% to ~$330, dip-buy-1 (<335, cap 0.09) is blocked by weight (~15.7%), not price — correct. AMZN -0.37%, weight ~16%, also weight-blocked. No action.
- amd-swing (v9): price near $616, dip-buy-1 (<600) and trim (>650) both out of reach; deliberately so while AMD is extended. No action.
- meta-swing / tsla-swing (v1 each): positions ~8% each, dip-buy-1 caps 0.05 and 0.06 respectively — those caps sit below current weight, so entries are correctly blocked. Both still carry $8,000 tranches, but because the caps bind before the tranche fires, they do not have GOOGL's defect. Left alone.
- nvda-momentum-swing (v11): NVDA +1.09%; dip-buy-1 (<222) and trim (>232) untouched. entry-call and take-profit-options-early remain in triggered state and will not fire without a re-arm — correct, since the option leg is already closed out.
- msft-diversifier-swing: flat on the day (-0.02%), entry-call triggered/dormant, no rule near. tsm-swing-contest: +0.66%, trim re-armed after the 9/30 scale-out at $460.99; price below $460 so nothing fired. crm-fade-swing: archived, no rules.

Lessons
- Pullback-only entries are earning their keep in this regime when the trigger is an event, not a trend break: both fills today landed within 0.4% of the session low on narrative-driven flushes (MU capex guidance, GOOGL Gemini report) and both theses were intact by the close. This is the opposite of the old "pullback-only deadlock" failure recorded for AMD/TSM — the difference is that the thresholds sit just under market, not 10-20% below.
- The re-arm era has a new recurring defect: a tranche worth ~8% of equity under a cap of 0.10 is not a cap at all, because one fire leaves the rule still eligible. I have now found this on three strategies (AAPL, AMZN, GOOGL). The rule of thumb to apply everywhere: every cap must sit at least one tranche below the weight it is protecting.
- Cash discipline is now the binding constraint, not rule logic. At ~99% deployed, the next $8,000 fire borrows. Tranche size has to be read against available cash, not just against target weight.

Proposals
- Revision #133, googl-swing v2 (queued, awaiting your approval): tranches cut from $8,000 to $5,000 (~5% of equity); dip-buy-1 cap 0.10 -> 0.09, dip-buy-2 cap 0.18 -> 0.13, trim floor 0.08 -> 0.10, trim size $6,000 -> $5,000. All price levels, the <308 stop, the >365 take-profit and the invalidation test are unchanged. This mirrors the fix already applied to aapl-swing v2 and amzn-swing v2. No other revisions proposed — the remaining strategies' caps bind correctly or their levels are intentionally out of reach.
- Not proposed but worth your judgment: with cash at $844, you may want to disarm or shrink one of the remaining $8,000 entry tranches (META, TSLA, NVDA, AMD) rather than let the first one that triggers be funded on margin.

**Day summary.** A quiet, broadly green session for the book: equity $100,239.91 with $16,844.37 cash (~17% uninvested), seven of eight positions in the green on cost. Day changes: AAPL +1.10%, AMD +0.69%, AMZN +1.01%, MSFT +0.77%, NVDA +0.51%, TSLA +0.56%, TSM -0.15%, META -1.84%. One trade fired, on TSM: trim-strength sold $5,000 (10.846 sh) @ $460.99 at 15:37 ET, a good fill 0.9% above the $456.27 close, and the rule re-armed at 17:07 ET after its 90-minute cooldown. Pending queue was empty at session start; I have added two revisions to it.

**Per-strategy check.**
- *tsm-swing-contest (v10, 26.08 sh @ $433.27, $11,918, 11.9% of equity, +$617).* Thesis confirmed: nine sessions of grinding higher from $434.67 (9/18) to today's $461.87 high with no 2%+ down day — the lowest-beta anchor behaving exactly as written. The trim executed correctly and at a good price, but its geometry is wrong: a 10% floor with a $5,000 tranche (~5pp of a $100k account) took the position from ~17% to 11.9%, i.e. *below* its own 15% target, and the re-arm means any print above $460 tomorrow would cut the "largest, most patient anchor" to ~7% purely because price rose. Revision proposed. Entries <447/<435 sit 2-5% below market; stop <418 is ~4.5 ATR away and remains sound.
- *aapl-swing (v1, 48.00 sh @ $333.31, $15,982, ~15.9% of equity, -$18).* Price recovered +1.10% to $333.02 after the narrative-driven 9/29 drop to $329.40; still inside the $329-341 band, position essentially flat. The defect is on the entry side: dip-buy-1 has a 10% cap but an $8,000 tranche, so on 9/29 it fired twice in 90 minutes ($334.53, then $332.09) and took AAPL from zero to 15.9% in one day, past the 15% target, with a third permitted fire able to breach the 20% max. Revision proposed. Note dip-buy-1's condition is true again at today's close (weight is the only thing blocking it), which is exactly why the sizing fix matters now.
- *meta-swing (v1, 11.11 sh @ $719.86, $8,025, ~8.0%, +$25).* The day's only loser (-1.84% to $725.18), and the highest-ATR name as advertised (~$30, ~4%). It has round-tripped from the 9/24 high of $779.82 back into the mid-$720s, which is why the 9/28 entry at $719.86 was a pullback buy rather than a chase. Weight is at the 8% target; dip-buy-1's 5% cap now correctly blocks further buying, so no sizing defect here. Stop <615 sits below the entire post-9/8 breakout. No action.
- *googl-swing (v1, no position).* GOOGL closed $344.08 after a $352.60 intraday spike on elevated 32.2M volume — a wide, reversing range. dip-buy-1 (<338) has not triggered because price has held above it since 9/29's $338.02 low. Zero position here is the rule working, not failing, but note this strategy shares the same $8,000-tranche/10%-cap arithmetic as AAPL; if it fires it will produce the same one-day overshoot. Flagged for the next revision cycle rather than pre-emptively rewritten.
- *nvda-momentum-swing (v11, 10.77 sh @ $209.38, $2,459, 2.5%, +$204).* Closed $228.38 (+0.51%), the fourth straight session in $224-233. trim-strength (>232) sold $6,000 @ $232-ish earlier in the week, which is why weight is now only 2.5% against a 15% target — the trim floor of 8% with a $6,000 tranche is the same exit-side defect as TSM, only already realised. dip-buy-1 (<222) is 2.8% below market. entry-call and take-profit-options-early remain triggered/dormant. Worth a sizing revision, but I ran out of tool budget to verify the option leg's current state, so I am not proposing one blind.
- *amd-swing (v9, 13.37 sh @ $598.50, $8,166, 8.1%, +$166), amzn-swing (v2, 65.07 sh @ $245.90, $16,177, 16.1%, +$177), msft-diversifier-swing (25.00 sh @ $499.96, $12,826, 12.8%, +$326), tsla-swing (22.10 sh @ $361.93, $7,843, 7.8%, -$157), mu-oversold-swing (flat).* All inside their stated ranges with no rule within reach; AMD's deliberately-low entry ceilings (<600/<560) and AMZN's post-v2 $5,000 tranches are behaving as designed. AMZN at 16.1% is above its 15% target and its dip-buy-1 cap of 8% correctly blocks adds. No action.
- *crm-fade-swing.* Archived, no rules, nothing to review.

**Lessons.** The durable conclusion today is that tranche size and weight bound are one mechanism, not two, and the error is symmetric. A cap only bounds a position if the tranche is small relative to it; a trim floor only bounds a trim if the tranche is small relative to the floor-to-target distance. With ~$100k equity an $8,000 tranche is ~8pp of weight, so a 10% cap permits ~16% after one fill and ~24% after a re-armed second — that is precisely what happened to AAPL on 9/29 (0% → 15.9% in one session). The mirror case appeared today on TSM: a 10% floor with a $5,000 tranche cut a 17% anchor to 11.9%, below its own target, with the rule re-armed to keep cutting on strength. The design rule I am adopting for all re-arming rules: cap + tranche ≤ target weight, trim floor ≥ target weight, tranche ≈ 4-5% of equity at most, 180m cooldowns on dip buys, ≤2 fires/day. NVDA (2.5% vs 15% target, ground down by an 8%-floor/$6,000 trim) and GOOGL (unfired but carrying the AAPL geometry) are the two remaining strategies with this flaw and are next in the queue. Two memory writes were rejected today for exceeding the 500-character limit, so these conclusions live only in this report — I will re-write them shortened at the next opportunity.

**Proposals.** Two revisions queued for approval, both sizing-only with every price level and fundamental thesis left untouched: **#129 aapl-swing v2** — tranches $8,000 → $5,000, dip-buy-1 cap 10% → 9%, dip-buy-2 cap 18% → 13%, cooldowns 90m → 180m, dip-buy-1 3 → 2 fires/day, trim floor 8% → 10% at $5,000, so cap + tranche stays inside the 15% target and 20% max. **#130 tsm-swing-contest v11** — trim floor 10% → 15% (the target), trim tranche $5,000 → $4,000, 3 → 2 fires/day, so trimming only occurs at or above target and one fire moves weight ~4pp instead of ~5pp from an already-below-target base. No new positions, no level changes, and no proposal for NVDA/GOOGL until I can verify their current state properly.

**Day summary**
A risk-off tape (S&P 500 -0.8%, 30-year Treasury yield at a 24-year high) produced a split book. Equity closed at $99,871 with $11,844 cash (~88% deployed). Winners: META +3.24%, TSM +0.91%, AMZN +0.21%. Losers: AAPL -2.66%, TSLA -1.29%, NVDA -0.72%, AMD -0.05%, MSFT -0.05%. Only one strategy acted: aapl-swing's dip-buy-1 fired twice (13:37 ET, $8,000 @ $334.53; 15:07 ET after a 90-minute re-arm, $8,000 @ $332.09), building a 48.00-share AAPL position at an average cost of $333.31 — roughly 1.2% above the $329.40 close, since AAPL faded all day and closed at its low ($328.70–$337.06 range, 36.1M shares). The AAPL weakness was narrative rather than fundamental: a Bank of America note flagging META's shopping agent as a threat to iPhone-ecosystem commerce, plus reports of product/management-process changes under CEO Ternus. Notably, the same META story that hurt AAPL is part of why META was the book's best performer — the two positions are now partly on opposite sides of one news item. No pending items; the day's only rule state change of consequence is that AAPL is now at ~15.8% of equity versus its 15% target.

**Per-strategy check**
- aapl-swing (v1, 48.00 sh @ $333.31, ~15.8%, -$180): thesis said "lowest realized volatility of any name considered, ~2.2% ATR" — today's -2.66% one-way fade is at the edge of that assumption, though a single session doesn't break it. Rules behaved exactly as written but the *sizing geometry* is off: two $8,000 tranches (~8% of equity each) against a cap of `position_weight < 0.10` took the position from flat to above its 15% target in 90 minutes, and a third fire was blocked only because the cap finally bound. The stop (<$310, ~5.9% / ~2.5 ATR below) and dip-buy-2 (<$322) remain sensibly placed. The entries were not wrong in level — $334.53 and $332.09 are inside the intended pullback zone — but the pace left no dry powder for the deeper tranche.
- amzn-swing (v2, 65.07 sh @ $245.90, ~16.1%, +$50): the 9/28 sizing revision to $5,000 tranches is the correct shape and dip-buy-1 re-armed today without firing (close $246.67, just above the <$246 trigger). Working as intended.
- meta-swing (v1, 11.11 sh @ $719.86, ~8.2%, +$199): entered 9/28 at $719.86, closed +3.24% at $738.79. At target weight; dip-buy-2 (<$670) and trim (>$800) both far away. No action correct.
- amd-swing (v9, 13.37 sh @ $598.50, ~8.1%, +$119): flat day, at the 8% cap on dip-buy-1, so nothing could fire. Trim at >$650 and stop at <$520 unchanged.
- tsm-swing-contest (36.93 sh @ $433.27, ~16.9%, +$865): best open P/L in the book and the steadiest performer again today (+0.91%) — the low-beta anchor role keeps verifying.
- msft-diversifier-swing (v4, 25.00 sh @ $499.96, ~12.7%, +$217): flat at $508.65-ish; dip-buy-1 (<$508) is within ~0.2% and is the most likely next fill in the book. Its $8,000 tranche against a `< 0.10` cap carries the same overshoot risk AAPL just demonstrated.
- nvda-momentum-swing (v11, 10.77 sh @ $209.38, ~2.5%, +$194): quote $227.21. Two option exits sit in `triggered` state and the stock is only ~2% under dip-buy-1 (<$222). Position is far below its 15% target after prior trims, which is acceptable but means NVDA is now a minor contributor.
- googl-swing (v1, no position): closed $340.92, dip-buy-1 needs <$338 — it traded $338.02 intraday and missed by two cents. Thresholds are live and realistic; nothing wrong.
- tsla-swing (v1, 22.10 sh @ $361.93, ~7.8%, -$193): -1.29%, above the 6% cap so dip-buy-1 is blocked; stop <$335 intact.
- mu-oversold-swing: flat, dormant thresholds as designed.
- crm-fade-swing: archived, no rules. Correct.

**Lessons**
1. The durable lesson of the day is a sizing lesson, not a market call: on a ~$100k book, an $8,000 tranche is ~8% of equity, so a re-arming buy rule capped at `position_weight < 0.10` can legally fire twice and land near 16% — above the strategy's own 15% target and, with dip-buy-2's `< 0.18` cap, potentially in the 26–34% range against a declared `max_weight` of 0.20. The cap must be set below (max_weight − tranche), not at it. amzn-swing v2 already uses the corrected shape; aapl, googl, msft, nvda, tsla, meta, amd and tsm swings do not.
2. Re-arming ladders average *into* a trend, not into a washout. Both AAPL fills printed above the close on a day that closed at its low. That is the expected cost of mechanical scale-ins and is tolerable — but it argues for smaller tranches and wider spacing between fires rather than a 90-minute cooldown on a name whose whole thesis is low volatility.
3. Correlation inside this book is not what the theses assume. One BofA note simultaneously drove AAPL to the worst performance and supported META, the best. Diversification by sector label is weaker than diversification by exposure to the same news flow.
4. I failed to persist any of these conclusions to curated memory this pass: three memory writes were rejected for exceeding the 500-character limit and I ran out of tool calls before rewriting them shorter. The operational lesson for myself is to draft memory entries at roughly 400 characters and to write them early in the pass, not after all the research. The findings above are therefore recorded only in this report.

**Proposals**
No strategy revision was queued this pass — I hit the tool-call limit before I could submit one, and I will not fabricate having done so. The revision I judge warranted, and intend to submit at the next opportunity, is to aapl-swing: keep the thesis, price levels, stop (<$310) and take-profit (>$362) unchanged, but cut the dip-buy tranches from $8,000 to $5,000, tighten dip-buy-1's cap from `position_weight < 0.10` to `< 0.10` with the position already past it (i.e. effectively retire it for now) and set dip-buy-2 at `position_weight < 0.15` so the deeper tranche cannot push past the 20% max, and lengthen the re-arm from 90m to 180m. The same tranche-versus-cap correction should follow for msft-diversifier-swing (nearest to firing, <$508 is ~0.2% away) and then googl-swing, nvda-momentum-swing and tsla-swing. Nothing in today's data justifies changing any price threshold, stop, or fundamental thesis — the geometry is the problem, not the levels.

**Day summary.** A macro risk-off session, not a stock-specific one: media and index data point to the 10-year Treasury yield near a two-decade high, rising odds of an October Fed hike, plus Iran/oil tension; the S&P 500 fell ~0.4% and the Nasdaq 100 about 1%. The book's ladders read this as a buying opportunity everywhere at once. Nine fills: six dip-buys across six strategies (AMZN twice, MSFT, TSLA, TSM, AMD, META), plus NVDA's trim and its option take-profit. Roughly $48,000 was deployed in one day, taking the account to ~72% invested with ~$27.8k cash, above the mandate's 40-70% band. Equity ended ~$99,774. Position day-changes: NVDA +1.68% and TSM +0.50% green; META -4.79%, TSLA -3.94%, AMD -3.61%, AMZN -1.41%, MSFT -1.35%. Net open P/L is slightly positive (+$1,074) mostly on the older TSM and MSFT lots; today's new entries in META, TSLA and AMD are underwater by construction because each fill happened mid-slide.

**Per-strategy check.**
- *nvda-momentum-swing (v11)* — the day's clear win and fully consistent with thesis. NVDA gapped to $229.70, hit $233.21 and closed $228.86 (+1.68%) on 135M shares, the heaviest non-expiry volume in weeks. take-profit-options-early (>227) closed the 2 Oct-16 $220 calls at $15.10 against a $4.65 entry (~+225%, ~$2,090 on a $930 budget), and trim-strength (>232) sold $6,000 of stock at $232.53, leaving 10.77 sh (~2.5%). The deliberately tight option exit — the geometry v10 built specifically to stop theta bleed — did exactly its job. No change needed.
- *tsm-swing-contest (v9)* — thesis validated, sizing not. TSM was one of two green names on a red tape, confirming its low-beta anchor role. But dip-buy-1 fired at $445.63 for $8,000 while weight was already 8.7%, landing the position at 16.8% — past its own 15% target — and two more fires were still permitted the same day. Revision proposed.
- *amzn-swing (v1)* — levels fine, arithmetic broken. dip-buy-1 fired at 13:37 @ $245.89, re-armed after 90m and fired again at 19:52 @ $245.91: two fills eleven cents apart, zero to 16.1% weight in one session against a 15% target. Close $246.15 sits mid-range ($244.30-260.11), so nothing about the thesis failed. Revision proposed.
- *msft-diversifier-swing (v4)* — dip-buy-1 filled $8,000 @ $503.97, bringing the position to 25.00 sh @ $499.96, ~12.8% weight, +$241 open. The pullback from the 9/25 breakout close ($516.17) into the low $500s is precisely the "scale into weakness" case the v4 thesis described, and MSFT again fell least among the non-green names (-1.35%). entry-call skipped once more as unaffordable — that leg has now failed to price for weeks and should eventually be deleted rather than left to log skips. Same cap-plus-tranche overshoot risk exists here but the position is not yet past its 15% target; leaving it for now rather than proposing three near-identical revisions in one pass.
- *meta-swing (v1)* — first entry, 11.11 sh @ $719.86 (8.0% = exactly target). The day was an outside-down reversal (open $750.42, high $750.58, low $713.19, close $715.62), so the fill was mid-slide rather than at a support test — the cost of a static price trigger on a 4%-ATR name. dip-buy-2 at <$670 and stop at <$615 remain correctly placed below the 9/21 breakout. No change.
- *amd-swing (v9)* — dip-buy-1 filled $8,000 @ $598.50, 13.37 sh, ~8.1% weight, +$121. The v9 thesis explicitly set entries well below market because AMD was extended after +25% in two weeks; price came to the level and the rule worked as designed. Close about -3.6%. No change.
- *tsla-swing* — dip-buy-1 filled $8,000 @ $361.93, 22.10 sh, ~7.9% weight, -$101. TSLA fell from a $386.70 high on 9/23 to a $356.80 low today, so the $362 trigger caught the third day of a slide; the fill is near the low of the last two weeks. No change.
- *aapl-swing, googl-swing* — no fills and correctly so: AAPL $338.40 versus a <$335 trigger, GOOGL $342.75 versus <$338. Both sat just above their thresholds all day. Inaction is the right outcome.
- *mu-oversold-swing* — flat, entries far below market, nothing monitored today. Unchanged from prior conclusion to stay out through the FQ4 print.
- *crm-fade-swing* — archived, no rules, nothing to review.

**Lessons.** Two written to memory. First, a sizing rule that generalizes across the book: on a re-arming dip-buy, the weight cap plus the tranche size must stay under the target weight, or the position overshoots by construction — an $8,000 tranche is ~8pp of this account, so a 10% cap legally permits an 18% position on a 15% target, and today it produced AMZN at 16.1% and TSM at 16.8%. The fix is smaller tranches, not different prices. Second, and more important strategically: diversifying by ticker does not diversify the trigger. Six "independent" per-name ladders all fired within one session because the move was rate-driven multiple compression that hit every long-duration growth name simultaneously. The real constraint is an aggregate cash floor, not per-name caps, and I should expect the whole book to buy at once on macro days.

**Proposals.** Two revisions queued for approval, both purely mechanical — every price level, stop, target and fundamental thesis left untouched. #125 amzn-swing v2: tranches to $5,000, dip-buy caps to 8%/11%, cooldowns to 180m, dip-buy-1 to 2 fires/day, trim matched at $5,000 with a 10% floor. #126 tsm-swing-contest v10: same treatment with caps at 9%/13%. Neither takes effect unless you approve it on the Pending page; I have no path to apply either myself.

**Day summary — 2026-09-25 (paper, equity $98,232.56, cash $74,824.48 = 76.2%)**
No trades, no observations. One position did all the work: MSFT closed $516.17, +3.66%, high $519.40, on 37.1M shares — the heaviest non-expiry session of the month — on the expanded Copilot release (Home / Code / Autopilot), two days after a sell-side upgrade to Buy with a $575 target. That close breaks the $486-518 band MSFT had traded since 8/28. The semis legs were inert: NVDA +0.22% to $225.07, TSM -0.17% to $450.37 on 5.7M (very light), AMD (no position) +0.22% to $630.63 on 17.0M, decelerating from 25-44M last week. Open P&L across the four legs is about +$1,978, of which the 2 NVDA Oct-16 $220 calls are +$990 (+113%) on a $930 cost. The notable fact of the day is that the book's designated diversifier was its only mover, which is exactly what it was bought for — but it is also the smallest of the three stock legs.

**Per-strategy check**
- msft-diversifier-swing (v2, confirm): thesis working, rules stale. Weight is 4.8% against an 8% target (9.128 sh @ $492.98) because entry-initial was consumed on 9/8 and add-on-dip < 478 has been unreachable for 17 sessions. take-profit > 520 now sits 0.7% above market and sells the whole leg — the strategy is on track to book a half-size +5.5% win at the moment its premise starts paying, leaving the book all-semis plus cash. stop-loss < 465 is 9.9% (~5 ATR) below market. Revision proposed, see below. Pending #69 (entry-call, fired 9/16 at $490.30) is stale: approved today it would buy a call struck ~4% off $516, not off $490 — a different trade than the rule intended. My recommendation is to reject it and leave the rule armed for a real dip.
- nvda-momentum-swing (v10, confirm): stock leg sound, option leg still bleeding. Shares 36.574 @ $218.74 = 8.4% weight, +$227, all stock levels far away (TP $248 = +10%, stop $204 = -9%). The calls are the problem: v10 lowered the early exit from > 230 to > 227 on 9/23, and the two sessions since printed highs of $224.94 and $226.94 — short by $0.06. The calls went $13.05 (9/22) → $10.50 (9/23) → ~$9.60 today, roughly $690 of open gain returned on a sub-1% stock move, with ~21 DTE. No revision filed: v10 is two days old, today's premium was actually flat (+0.41%), and re-cutting the same level a third time would be reacting to noise rather than to a measured divergence. If the stock stalls in $223-227 for another two or three sessions while premium keeps eroding, the honest fix is a time-based or premium-based exit, not another price notch — flagging that now so it is not a surprise.
- tsm-swing-contest (confirm): behaving exactly as assigned. 18.976 sh @ $421.58 = 8.7% weight, +7.2%. -0.17% today on the lightest volume in weeks; take-profit > 460 is +2.1% away and remains the book's next likely fill. Given confirm-mode approval lag, read it as an exit near $455-465. Stop < 420 is ~6.7% below and still structurally sound. No change warranted.
- amd-swing (v8, confirm): flat since the 9/21 take-profit at $609.58. AMD closed $630.63 today; the armed entry window $465-482 is ~24% below market and monitors nothing. This is the fourth session I have logged that fact. I am not proposing a re-anchor: the user's standing preference is pullback-only, and chasing a name up 24% from the exit would violate it. The strategy is correctly dormant rather than broken.
- mu-oversold-swing (v8, confirm): flat since the 9/21 exit at $1,038.41. entry-dip $915-960 is dormant, FQ4 earnings land around 9/30. Staying flat through the print is the right posture after a +14.9% four-day swing.
- crm-fade-swing: archived, no rules, nothing to review.

**Lessons**
Written to memory: an option profit exit placed above the recent closing range is not an exit, it is a bet on a new high. The NVDA calls have now demonstrated this twice — > 230 was approached three times and cleared zero times, and > 227 was missed by six cents twice — while theta removed real money both times. Future option exits should sit at or below the last close and be sized off premium behavior, not off a stock chart level. Also recorded: MSFT's diversification premise is now verified in both directions (it held up on the 9/10 semis drawdown and led on today's rally), which upgrades it from assumption to observed behavior; and the pullback-only deadlock has now appeared in a fourth name, which is why today's fix is a retest window rather than a lowered target.

**Proposals**
One revision queued, #88, msft-diversifier-swing v3 (requires your approval on the Pending page; I cannot apply it): take-profit 520 → 540 (the measured move of the broken $486-518 range, ~+9.5% on entry); stop-loss 465 → 488, just under the 9/10 and 9/16 lows, so the exit trigger is a failed breakout rather than a number 5 ATR away; and a new add-on-retest rule buying $3,500 in the $498-512 window with a weight cap of 5.5%, which lifts the leg to ~8.3% on a pullback into the broken level and cannot fire above $512. Option rules are kept intact, with stop-loss-options aligned to < 488 and take-profit-options deliberately left at > 520, below the new share target, because the calls expire and the shares do not. Separately, and needing no revision: I recommend rejecting pending #69 as a stale trigger.

**Day summary.** No trades, no observations. Equity $98,033.60, cash $74,824.48 (76.3%) — the book is still mostly cash after the 9/21 AMD and MU take-profits. A quiet, mixed session: TSM +1.00% to $451.05 (vol 6.3M, the lightest in weeks) and AMD ran +2.38% to $629.26, while our three remaining long legs were flat-to-down — NVDA -0.41% to $224.58 on 70.1M shares (the lightest volume in a month), MSFT -0.53% to $497.93, and the NVDA Oct-16 $220 calls -7.05% to $9.76. Open P&L across the four legs remains positive (+$1,779 total), and nothing today touched a thesis-level invalidation on any strategy. The two things genuinely worth attention are not price moves: the option leg's continuing decay and a pending order that has gone stale.

**Per-strategy check.**

- *nvda-momentum-swing (v10, confirm).* The stock leg (36.574 sh @ $218.74, $8,204, 8.4% — target met) is behaving exactly as written; nothing near the $248 take-profit or the $204 stop. The option leg is where the strategy is measurably diverging from its own reasoning. v10 was written yesterday specifically because the >$230 early exit had been approached three times and cleared zero times; it lowered that exit to >$227. Today NVDA's high was $224.90 — a fourth consecutive session printing a high in the $224.90-$229.98 band with no option exit fill. Meanwhile the calls went $13.05 (9/22) → $10.50 (9/23) → $9.76 today: the stock is only -1.9% from its 9/22 close but the calls are -25%, roughly $660 of open gain surrendered in two sessions with ~22 days to expiry. The leg is still +110% (+$1,022 on $930), so this is about protecting a large realized-able gain, not a loss. The structural problem is the geometry v10 left in place: the exit sits ~1.1% above market while the option stop sits ~4.6% below ($214), so on a decaying asset most of the premium can bleed away in the gap between the two without any rule acting. v10's own logic ("every day it is not hit costs theta on a leg whose gain is now the largest single P&L item in the book") applies with more force today than yesterday, because two more days of theta have now been paid.
- *msft-diversifier-swing (v2, confirm).* The diversifier premise held again in a mild way — MSFT closed -0.53% while AMD rose 2.38% and TSM 1.00%; low correlation, today on the negative side. The stock leg (9.128 sh @ $492.98) is +0.7%, and no stock rule is near: add-on <$478, take-profit >$520, stop <$465 against a $497.93 close. The problem is pending order #69: the entry-call rule fired on 2026-09-16 when MSFT closed $490.30, and it has now sat in the queue for six sessions while the stock rose ~1.6% to $497.93. Because confirm-mode option orders are re-priced at approval, approving it today would not buy the contract the rule intended — an OTM-4% call off $497.93 strikes near $518 rather than the ~$510 implied at trigger time, with six fewer days of time value for the same $1,200. The trigger condition (price < 490) is no longer true. My recommendation is to decline #69 and let the rule re-arm for the next genuine dip below $490.
- *tsm-swing-contest (v8, confirm).* Working as designed and the best-behaved leg in the book. 18.976 sh @ $421.58 = $8,552 (8.7%, +7.2%). Closed $451.05 on 6.3M shares — participating in the sector with roughly a quarter of AMD's amplitude, its assigned low-beta anchor role. The >$460 take-profit is ~2.0% away and remains the book's most likely next fill; given confirm-mode approval lag (MU filled 1.1% below its own trigger on 9/21), read it as "exit near $455-465". The <$420 stop, repaired in v8, sits ~7% below and just under average cost. No change warranted.
- *amd-swing (v8, confirm).* Flat since the 9/21 take-profit at $609.58. AMD closed $629.26 (+2.38%, high $630.79, vol 24.5M), a new high above the 9/22 close. The armed entry-dip window ($465-482) is now ~24-26% below market and monitors nothing — the fourth instance of the pullback-only deadlock on this name. I am deliberately not proposing to raise it: the user's standing instruction is that a dormant threshold on a satellite swing is an acceptable outcome (missing a satellite trade has no real cost), and re-anchoring upward after a +24% five-session run is exactly the level-chasing v7/v8 warned against. Noted, not fixed.
- *mu-oversold-swing (v8, confirm).* Flat. MU quoted $1,080.53, now ~12% above the take-profit that closed the swing at $1,038.41. The entry-dip window ($915-960) is ~13% below market and dormant, correctly so. FQ4 earnings land around 09-30; staying flat through the print rather than chasing remains the plan.
- *crm-fade-swing.* Archived, no rules, no action.

**Lessons.** Two written to memory today. First, a stock-level note that NVDA's option leg has now failed to reach an exit trigger on four consecutive sessions while giving back ~$660 of gain in two — evidence that an exit set just above the recent high is a lottery ticket on a new high, not an exit plan, and that lowering it by $3 was not enough. Second, a new durable lesson: confirm-mode pending option orders never expire and are re-priced at approval, so a stale one silently becomes a different trade than the rule authorized. The standing discipline I will apply going forward — if the triggering condition is false at review time, decline it and let the rule re-arm. This is the option-specific corollary of the 2026-08-17 lesson that a trigger is only a proposal, never a commitment.

**Proposals.** None queued this pass. I reached the tool-call limit for this reflection before I could submit the NVDA v11 revision I had concluded was justified, so I am recording the intent here rather than leaving a half-formed proposal on the Pending page. The case for it is documented above and in memory: v10's >$227 option exit has now been missed a fourth time while the leg lost 25% of its value in two sessions, and the ~1.1%-above / ~4.6%-below geometry around a wasting asset is the measurable divergence. The fix I would propose is to tighten the option-only exit to roughly NVDA > $224-225 — inside the band the stock has actually closed in for four sessions, so an ordinary up-session realizes the gain — and to raise the option stop from $214 toward ~$218-220 so that a further slide protects a meaningful share of the remaining premium instead of acting after most of it is gone. Stock levels, sizing and the fundamental thesis would be untouched; this separates the expiring leg from the non-expiring one, which is what v10 set out to do but under-delivered. Two items need the user's hand in the meantime: pending #69 (MSFT call) should be declined as stale, and the NVDA option decision is live now, not at $248.

**Day summary.** No trades today. Equity $98,213.63, cash $74,824.48 (76.2%) — still cash-heavy after the 9/21 AMD and MU take-profits. The five-session semiconductor run paused: NVDA closed $225.51 (-1.47%, range $224.02-228.95) on 80.2M shares, the lightest volume of the whole stretch; AMD $614.61 (-1.47%, 15.8M, barely a third of Monday's 44.5M); TSM $446.74 (-1.16%, 8.6M). MSFT was the only green leg, $500.59 (+0.52%), again inverting the sector — its diversifier role working in the intended direction for once. Volume shrinking as prices fall reads as an orderly give-back rather than distribution, and nothing today touched a thesis-level invalidation. The sharpest single move in the book was the NVDA Oct-16 $220 calls: marked $10.50, -21.67% on the day (-$510 of open gain) while the underlying fell 1.5% — the leverage cutting the other way for the first time. The sentinel logged repeated `previous_close` NaN quote-validation errors across all five active strategies on both the 18:39 and 19:09 passes; these are data-feed faults in the quote object, not rule failures, but they mean I cannot assume every rule was evaluated on every pass today.

**Per-strategy check.**
- *nvda-momentum-swing (v9, confirm, target 8%)* — Stock leg 36.574 sh @ $218.74 = $8,245, 8.4% of equity, target met, +$245. No rule fired; correctly so, as $225.51 sits between add-on (<214) and take-profit (>248). The measurable divergence is the option leg. v9 added the >$230 early close_options on 9/17 precisely to give the calls a reachable exit, and NVDA has now printed highs of $228.50, $229.98 and $228.95 on three consecutive sessions — within $1.05 of the trigger, cleared zero times — while the calls round-tripped $7.60 → $13.05 → $10.50. With 23 DTE the exit is not "$248", it is "somewhere near $227-230", and the >$230 formulation requires a marginal new high to pay out. The stop side is the same defect mirrored: at <$204 a $220 call with three weeks left would be worth roughly $1, so the stop only fires after the premium is already gone. Proposed v10 (#86) below.
- *amd-swing (v8, confirm, target 4%)* — Flat since the 9/21 exit at $609.58. AMD fell to $614.61 on collapsing volume; the ladder (entry-dip $465-482 armed, entry-step <$505 triggered) sits 22-25% below market and monitors nothing. This is the fourth consecutive session I have recorded the pullback-only deadlock here. I am deliberately not proposing a re-anchor: the strategy's own v7/v8 thesis commits to not chasing levels, the user's standing preference is to accept non-fills on satellites, and a 25% gap after a +25% weekly sector run is not evidence the levels are wrong — only that the setup is absent. Support to watch if it does retrace: the unfilled 9/21 gap $559.91-583.88, then the 9/18 low $541.53.
- *tsm-swing-contest (v8, confirm)* — 18.976 sh @ $421.58 = $8,477, 8.6%, +6.0%. First down day after four up, and again the smallest amplitude in the book on a sector-wide decline, matching its assigned low-beta anchor role in both directions. The >$460 take-profit is ~3.0% away and remains the book's next likely fill; given confirm-mode approval lag (the 9/21 MU fill came 2.4% below its own trigger) read that rule as "exit near $455-465" rather than $460. The <$420 stop is ~6% below and remains sound.
- *msft-diversifier-swing (v2, confirm, target 8%)* — 9.128 sh @ $492.98 = $4,568, 4.7%, +1.4%. Stock rules untouched (TP >$520, add-on <$478, stop <$465). The live issue is Pending #69: the entry-call (price < 490 → buy_call $1,200, dte>=30, otm 4%) fired on 9/16 and has sat unapproved for five sessions. MSFT is now $500.59, 2.2% above the rule's own condition, and the contract is re-priced at approval — so approving it would buy a setup the rule never authorized. Recommendation: decline #69 and re-arm rather than hold it.
- *mu-oversold-swing (v8, confirm, target 4%)* — Flat since the 9/21 exit at $1,038.41 (+14.9%). MU $1,071.88, above the exit; entry-dip $915-960 is ~12-14% below and dormant. FQ4 earnings land around 09-30 and the plan of record is to stay flat through the print. Correct no-action day.
- *crm-fade-swing* — archived, no rules, no action.

**Lessons.** Two written to memory. First: an option leg whose only exits are stock-price levels tends to decay rather than exit — the >$230 trigger was approached three sessions running and never hit while the position surrendered 21.67% in a day; short-dated legs need an early take-profit *inside* the stock's recent closing range and a stop around 2-2.5 ATR below market, kept separate from the share leg's wider target. Second: confirm-mode option orders do not age out of the pending queue, so a trigger can drift far out of its own condition (#69, five sessions, now 2.2% offside) and should be declined rather than approved late. I also tried to refresh the NVDA and TSM stock files but both are at their 3,000-character budget; they need pruning next pass before new entries will fit, so today's price detail lives only in this report.

**Proposals.** One queued: **#86, nvda-momentum-swing v10** — move `take-profit-options-early` from `price > 230` to `price > 227`, and `stop-loss-options` from `price < 204` to `price < 214`. Both changes are option-only; the share leg's $248 target and $204 stop are untouched, as are entry-call (<212), add-on-dip (<214, weight<0.063) and the fundamental thesis. Note the new option stop deliberately coincides with add-on-dip, so a real dip de-risks the expiring leg while adding to the non-expiring one. This is a reduction in the profit target, not a chase. It awaits your approval on the Pending page; I cannot apply it myself. No revision proposed for amd-swing, mu-oversold-swing, msft-diversifier-swing or tsm-swing-contest — their dormancy today is the designed outcome, not a defect.

**Day summary — 2026-09-22 (paper, equity $98,881, cash $74,825 / 75.7%)**
No trades and no observations today. The semis melt-up extended a fifth session: AMD $623.77 (+1.34%, high $624.52) on 26.6M shares versus 44.5M on 9/21 — price still pushing on clearly decelerating volume; TSM $451.89 (+1.52%) on 9.0M; NVDA $228.87 (+0.66%) with a high of $229.98; MU $1,096.16. MSFT was the lone decliner at $498.00 (-0.72%), after opening at $507.52 and giving the whole gap back — the non-semis diversifier again behaving as designed, currently on the negative side. Five-session sector context from external reporting: AMD +24.75%, INTC ~+25%, NVDA +7.78%, TSM +6.77%, with no new catalyst today beyond the 9/21 ~10% chip price-hike report. All four open legs are profitable: NVDA stock +$345, TSM +$558, MSFT +$44, and the NVDA Oct-16 $220 calls marked $13.05 versus $4.65 cost (+181%, +$1,680) — the book's largest single gain, now ~2.6% of equity.

**Per-strategy check**
- **nvda-momentum-swing (v9, confirm):** The day validated v9 with uncomfortable precision. NVDA's high of $229.98 came two cents under the >$230 `take-profit-options-early` rule that v9 added only on 9/17 to stop a profitable one-month call decaying into expiry. Rules behaved correctly — nothing fired. With 24 DTE and the calls at +181%, ~$230 is the live decision point, not the $248 share target. No revision: the rule is right, it simply has not been touched yet.
- **tsm-swing-contest (v8, confirm):** Working exactly to thesis. TSM participated at roughly a quarter of AMD's amplitude, which is its assigned low-beta anchor role. Position 8.7% of equity (+7.2%). The >$460 take-profit is now only +1.8% away and is the book's most likely next fill; given confirm-mode approval lag it should be read as "exit near $455-465", not $460 exactly. The <$420 stop sits ~7% below, below blended cost — sound. No change needed.
- **msft-diversifier-swing (v2, confirm):** Stock leg fine (barely profitable, low-vol as claimed). The defect is in the queue, not the rules — see Proposals.
- **amd-swing (v8, confirm):** Flat since the 9/21 take-profit at $609.58 (+20.7% on the $2,000 leg). The strategy is now fully inert: `entry-step` is `triggered` and cannot re-fire without a manual re-arm, and `entry-dip` ($465-482) sits 23-25% below market. This is the third documented instance of the pullback-only deadlock on this name. I ran out of tool calls before I could finish drafting a re-anchoring revision, so I am flagging it rather than proposing an unverified one.
- **mu-oversold-swing (v8, confirm):** Flat and correctly dormant. MU at $1,096 is ~14% above the $915-960 entry window, and `entry-dip` is `triggered` anyway. FQ4 earnings ~09-30: staying flat through the print after a +15% run remains the right call.
- **crm-fade-swing:** Archived, no rules, no action.

**Lessons**
- Written to memory: confirm-mode pending orders decay, because the contract and price are set at *approval*, not at trigger. MSFT's `entry-call` fired 2026-09-16 at $490.30 and still sat unapproved today with MSFT at $498 — six sessions and +1.6% above its own trigger condition. Approving it now would buy a re-priced 4%-OTM call off a dip that no longer exists: a different and worse trade than the rule intended. Standing rule: an unapproved signal order older than ~2 sessions, or whose condition no longer holds, is EXPIRED — reject it and let the rule re-fire on a real dip. This is the same family as the 9/21 lesson where MU's take-profit filled 1.1% below its trigger after a two-hour approval lag.
- Also recorded: AMD's advance on decelerating volume (26.6M versus 44.5M) is loss of fuel, not yet reversal; first real support is the unfilled 9/21 gap at $559.91-583.88, then the 9/18 low of $541.53.
- Pattern confirmed: fixed take-profit targets over-deliver on gappy names (AMD exited at $609.58 against a $560 target), while the same rigidity leaves re-entry ladders stranded far below market once the move runs. The book is now 75.7% cash with only four legs monitored — high cash here is a consequence of untriggered ladders, not a sizing error, but on AMD it has become a monitoring gap.

**Proposals**
- No strategy revision queued today. TSM v8, NVDA v9 and MU v8 all matched their stated assumptions, and I will not propose a revision merely because I can.
- One action for the user on the Pending page: **reject option_order #69 (msft-diversifier-swing / entry-call, buy_call $1,200)**. Its condition (price < 490) was true on 9/16 and is now stale by six sessions and +1.6%; the contract would be re-priced at approval against a stock that has recovered. Rejecting it leaves the rule free to fire again on a genuine sub-$490 dip. I cannot reject it myself — I am advisory only, and every order passes the user's confirmation and the risk gate.
- Flagged for tomorrow, not yet proposed: amd-swing needs either a manual re-arm of `entry-step` or a re-anchored entry structure near the $560-584 gap shelf, otherwise the strategy monitors nothing at all. I want to verify the level against tomorrow's volume before drafting it.

**Day summary**
A broad semiconductor melt-up. A supply-chain report of a ~10% chip price increase sent AMD +9.95% to $615.52 — its first $1T market cap — on 43.3M shares, and dragged the whole book higher: NVDA +2.30% to $227.38 (104M shares), TSM +2.42% to $445.18, MSFT +1.59% to $501.61. Two take-profit rules fired and both filled: AMD sold 3.9612 sh @ $609.58 (entry $504.90 on 9/10, +20.7%, ~+$415) and MU sold 3.8718 sh @ $1,038.41 (entry $903.97 on 9/14, +14.9%, ~+$520). Equity closed at $98,559 with cash back up to $74,824 (75.9%). Both satellite swings are now closed, and the four remaining lines — NVDA shares, the NVDA Oct-16 $220 calls, TSM and MSFT — are all profitable. The calls, marked ~$12.10 against a $4.65 cost (+160%, +$1,490), are the single largest P&L in the book.

**Per-strategy check**
- amd-swing (v8): thesis validated end-to-end. v8 explicitly refused to raise the $560 target after a +11% run, calling that level-chasing; the gap-up open then delivered +20.7% instead of the planned +11%. The repaired <$500 stop was never needed. Strategy is now flat with entry-step in `triggered` state and the entry-dip window ($465-482) sitting ~23% below market — it monitors nothing until re-armed and re-anchored. No revision proposed: nothing is measurably wrong with a strategy that just completed its plan, and re-anchoring an entry ladder onto a +$110 one-day breakout is exactly the mistake its own thesis warns against.
- mu-oversold-swing (v8): also completed as designed, +14.9% on the satellite leg. One measurable imperfection, but it is execution, not rule design: the >$1,050 trigger was flagged at ~09:39 ET and the confirm-mode order filled at ~11:47 ET @ $1,038.41 — 1.1% below its own trigger and 2.4% off the day's high. Now flat ahead of FQ4 earnings (~09-30), which resolves the open risk question the v8 thesis had flagged. Staying flat through that print is the right default; a re-entry should wait for guidance and ideally a retrace into the $915-960 base.
- nvda-momentum-swing (v9): working as written. The stock leg is at ~8.4% weight with the add-on correctly dormant behind the weight<0.063 gate. v9's new take-profit-options-early (>$230 -> close_options) is now only 1.1% from being hit, which vindicates the v9 diagnosis that the old >$248 option exit was unreachable. Live watch item: in confirm mode that option exit needs prompt approval, because an at-the-money October call gives back gains quickly once the underlying stalls.
- tsm-swing-contest (v7): the one genuine divergence today. At $445.18 the <$398 stop is ~10.6% / ~5.4 ATR below market while the $460 target is 3.3% away — the open trade risks the full $470 gain plus 5.6% of capital to make 3.3%. This is the identical stale-stop defect already fixed on AMD and MU.
- msft-diversifier-swing (v2): +1.59% today, but it rose *with* semis rather than against them, so today says nothing new about the low-correlation premise. Rules untouched: add-on <$478, TP >$520, stop <$465 are all far away. The stranded item is Pending #69 — the entry-call (price<490, buy_call $1,200) from 9/16 — whose condition is no longer true at $501.61; approving it now would buy a contract the rule never actually authorized at this price. Recommend rejecting it rather than letting it age further.
- crm-fade-swing: archived, no rules, nothing to review.

**Lessons**
1. Fixed take-profits over-deliver on gapping momentum names. AMD's $560 target was reached by an open at $583.94 and filled at $609.58 — roughly double the planned gain. The discipline of *not* chasing the level after a +11% run was what allowed the gap to be captured.
2. Confirm-mode exit latency is a measurable, symmetric cost. Today's two exits were both flagged at ~09:39 ET and both filled at ~11:47 ET; the trending name (AMD) gained ~8% from the delay and the fading name (MU) lost 1.1% versus its trigger. Take-profit levels should be set so a 1-3% adverse drift still leaves the trade acceptable, and the trigger price must never be read as the realized price.
3. The sentinel note "queued analysis unparseable — left for human review" does not mean a rule failed — both such notices today ended in clean fills. This is the third confirmed instance of that pattern.
4. After a winning swing exits, the strategy's entry ladder becomes dead weight: AMD's and MU's entry windows now sit 12-23% below market. That is the correct dormant state, not a defect to be fixed by raising thresholds — but it does mean the book has no live buy triggers at all and is purely in harvest mode.

**Proposals**
- Queued revision #82, tsm-swing-contest v8: move stop-loss from <$398 to <$420, placing it just under the blended average cost ($421.58) and below the 9/17 open, which converts the trade to roughly break-even risk (worst case ~-0.4% on $8.4k instead of -5.6%). At ~2.9 ATR / 5.7% below the close, it is wider than TSM's worst recent session (-3.41% on 9/14), so the 9/03 error — a <$410 stop tagged intraday at $409.17 on a day TSM closed $417.02 and kept climbing — is not repeated. The $460 target is deliberately not raised, the $406-414 add-on window and its weight<0.063 gate are untouched, and no option legs are added. Awaiting your approval on the Pending page.
- No revision for amd-swing or mu-oversold-swing: both just executed their plans correctly and are flat. Re-anchoring either entry ladder onto today's breakout would be level-chasing.
- Housekeeping recommendation (needs your action, I cannot do it): reject Pending #69, the stale MSFT entry-call whose price<490 condition is no longer true at $501.61.