Recycle verified bundle profits early

README.md

@@ -23,7 +23,7 @@ Offline cycles can apply calibration already earned from live observations, but
 the evidence ledger is read-only: cached prices cannot grade pending signals,
 expire horizons, or create new observations.
 
-Build 122 targets five-minute slots with a serialized, self-chained GitHub Actions runtime.
+Build 123 targets five-minute slots with a serialized, self-chained GitHub Actions runtime.
 It continues from the previous agent snapshot and runs the next due paper cycle
 even when no browser is open. After each successful cycle, one repo-scoped
 workflow dispatch waits for the next five-minute boundary; one concurrency group
@@ -63,7 +63,7 @@ Polymarket event key. Related Ethereum or Bitcoin contracts cannot create
 several simultaneous copies of one move, and outcomes from the same underlying
 three-hour shock window count as one learner event.
 
-Each Build 122 cycle also scans the 1,000 most-active Polymarket events for
+Each Build 123 cycle also scans the 1,000 most-active Polymarket events for
 complete negative-risk bundles and logically nested threshold or deadline
 pairs, plus same-market YES/NO complements whose equal shares have a fixed
 $1 redemption value. Polymarket's documented complete-set merge converts equal
@@ -80,18 +80,22 @@ the best structure from each independent event checked before alternates from ev
 already represented. They are repriced
 from batched CLOB asks from the equal-unit size needed for at least a $50
 paper order up to a $400 verified-notional ceiling. The scanner applies each market's Gamma fee schedule at every
-consumed ask level and checks the CLOB fee-rate endpoint for a matching enabled
-or fee-free state. Any opened position is capped to the exact equal-unit size
+consumed ask level and checks the exact CLOB condition metadata for a matching
+fee curve or fee-free state. Any opened position is capped to the exact equal-unit size
 of the largest fill that stays profitable and passes this depth test; portfolio
 cash, reserve, and 4% limits can reduce it further. Strategy 64 ranks verified
 structures by net return per expected locked day before raw edge, and caps active
 cost from one underlying event at 12% of Value Hunter equity. This prevents
-several related threshold pairs from monopolizing the non-directional book while
-preserving every already-open complete bundle until settlement. New bundles must
+several related threshold pairs from monopolizing the non-directional book. New bundles must
 also clear a 0.02% daily locked-capital return floor, approximately 7.3% annualized,
 so a tiny spread cannot immobilize capital for months. Existing paper bundles are
 never retroactively enlarged against depth their original simulated fill would
-already have consumed. A bundle can enter Value Discipline only when that fee check
+already have consumed. Each live cycle also prices an atomic exit across every bid
+level needed to sell every leg of each intact bundle. It verifies every condition's
+exact fee schedule again and exits only when net proceeds realize at least 85% of
+the remaining guaranteed settlement profit. Missing depth, mismatched fees, or a
+smaller profit capture leave the guarantee intact; cached offline cycles cannot
+execute this recycling path. A bundle can enter Value Discipline only when that fee check
 passes and the resulting worst-case payout clears both the three-tenths-cent
 profit floor and the 0.15% return floor. Top-of-book gaps, missing books,
 incomplete fee schedules, and unavailable fee verification remain audit-only.
@@ -99,7 +103,7 @@ The Suggestions view stores scan, depth, fee, actionable, and closest
 executable-margin counts so an empty lane is evidence rather than an ambiguous
 failure.
 
-Build 122 retains the directional learner's exact-fee policy, which replaced the blanket half-cent cost with
+Build 123 retains the directional learner's exact-fee policy, which replaced the blanket half-cent cost with
 the market's Gamma fee schedule at both the entry and future checkpoint, plus a
 separate half-cent round-trip slippage allowance. Fee-free markets pay only the
 slippage allowance; an unavailable fee schedule gets a conservative four-cent
@@ -124,7 +128,7 @@ Every probation position exits at the matching six-hour executable bid and keeps
 the 18% stop policy active. Normal directional sizing remains locked until the
 same cohort independently passes both the 24-hour and 72-hour promotion gates.
 
-Build 122 retains Build 100's retirement of the old 3-6 day resolution-window
+Build 123 retains Build 100's retirement of the old 3-6 day resolution-window
 capital permission. That audit clustered confidence by event but still averaged
 several correlated contracts inside each event, while production could choose
 only one. The corrected replay chooses the highest-volume eligible contract per event and
@@ -244,7 +248,7 @@ evidence proves an edge.
 
 Run `npm run evaluate:sports-favorites` for the retired pregame favorite audit.
 Its 12-hour, 60%-75% cohort had positive point estimates but did not establish a
-reliable confidence bound, so Build 122 no longer allocates capital to that rule.
+reliable confidence bound, so Build 123 no longer allocates capital to that rule.
 
 Strategy 64 also tracks the exact-fee settlement calibration's three-day Sports
 NO cohort as a zero-capital forward lane. The corrected 5,000-market run