Add bounded six-hour adaptive probation

README.md

@@ -20,7 +20,7 @@ market snapshots. During an outage, cycles continue locally; cached entries are
 allowed for 90 minutes, older snapshots become mark-only, and all cached data
 expires after 24 hours.
 
-Build 118 targets five-minute slots with a serialized, self-chained GitHub Actions runtime.
+Build 119 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
@@ -55,7 +55,7 @@ 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 118 cycle also scans the 1,000 most-active Polymarket events for
+Each Build 119 cycle also scans the 1,000 most-active Polymarket events for
 complete negative-risk bundles and logically nested threshold or deadline
 pairs. Gamma's market-specific fee flag replaces the old blanket 0.5-cent fee
 reserve for markets declared fee-free. The closest 60 structures are then
@@ -74,7 +74,7 @@ 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 118 retains the directional learner's exact-fee policy, which replaced the blanket half-cent cost with
+Build 119 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
@@ -85,12 +85,17 @@ available at reduced weight. The exact-fee replay covered the top 1,000
 active markets and 208 independent events: broad trends, reversals, and
 favorite trends all had 90% upper bounds below zero at 12 hours. A separate
 3,000-recently-closed-market study tested 297 one-decision-per-event settlement
-rules and found zero robust positive rule. Strategy 62 retains online
-directional evidence under fee policy 2 and keeps those lanes observation-only
-until current independent 24-hour and 72-hour cohorts pass the existing
-promotion gate.
+rules and found zero robust positive rule. Strategy 63 retains online
+directional evidence under fee policy 2. A separate probation gate can now use
+capital after at least 12 current-policy independent events produce a net-of-cost
+six-hour lower confidence bound above 1% for every required cohort feature. It
+uses at most 0.5% of equity per position, 1% per-agent total capital, one new
+position per agent cycle, and one owner per Polymarket event across all agents.
+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 118 retains Build 100's retirement of the old 3-6 day resolution-window
+Build 119 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
@@ -210,9 +215,9 @@ 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 118 no longer allocates capital to that rule.
+reliable confidence bound, so Build 119 no longer allocates capital to that rule.
 
-Strategy 62 instead uses the exact-fee settlement calibration's three-day Sports
+Strategy 63 also uses the exact-fee settlement calibration's three-day Sports
 NO cohort as a bounded paper exploration lane. The corrected 5,000-market run
 groups every prop with the same dated contest slug, anchors the decision to the
 published game start, and keeps only the highest-priced eligible NO contract per
@@ -338,7 +343,7 @@ Strategy 54 gives previously opened Politics trend positions that 72-hour observ
 ordinary signal exits. Stops, profit locks, settlement handling, and risk-budget
 reductions remain immediate.
 
-Strategy 62 retains exact Gamma entry and exit taker fees plus a half-cent
+Strategy 63 retains exact Gamma entry and exit taker fees plus a half-cent
 slippage allowance when grading each live walk-forward signal. Confidence uses the largest independent matching bucket,
 not the sum of five overlapping feature buckets, and evidence from older engine
 versions is down-weighted. This prevents a handful of duplicated observations