Replace bot tuning guesses with enforced calibration

CLAUDE.md

@@ -12,6 +12,9 @@ export JAVA_HOME="/Applications/Android Studio.app/Contents/jbr/Contents/Home"
 ./gradlew :engine:jvmTest              # engine tests (JVM)
 ./gradlew :engine:testAndroidHostTest  # same suite, Android variant
 ./gradlew :sim:run --args="50000"      # simulate 50k hands, print bot stats
+./gradlew :sim:test                    # fast calibration-policy tests
+./gradlew :sim:run --args="styles"     # enforced controlled style experiment
+./gradlew :sim:run --args="calibrate"  # enforced 4×100k fixed-pool skill + style calibration
 ./gradlew :app:assembleDebug           # build the APK
 ```
 
@@ -44,12 +47,21 @@ export JAVA_HOME="/Applications/Android Studio.app/Contents/jbr/Contents/Home"
    169 starting hands so `looseness` means "plays the top N%".
 4. **The simulator is how bots get tuned.** Run it after any bot change, across
    several seeds — a single seed will happily agree with a wrong conclusion.
+   The quick 50k run is diagnostic; only `calibrate` is an enforced result.
 5. **A skill parameter must not smuggle in a style change.** Several bugs came
    from exactly this: `positionAwareness` silently reduced hands played,
    `potOddsRespect` systematically loosened weak players (which is a *winning*
    adjustment, so it inverted the gradient), and error direction overwrote style
    entirely. Skill should change how *well* a decision is made, not how loose or
    tight the player is.
+6. **Pot odds are the post-flop baseline.** Never apply a blanket implied-odds
+   discount: it is categorically wrong on the river, and future value on earlier
+   streets must account for future costs and reverse implied odds before it is
+   called an advantage.
+7. **DecisionTrace is the coach contract.** It records raw pot odds, the actual
+   adjusted threshold, every adjustment, intended and chosen actions, and whether
+   a skill error changed the decision. The coach explains these values; it does
+   not reconstruct hidden bot logic.
 
 ## Testing notes
 
@@ -59,8 +71,9 @@ export JAVA_HOME="/Applications/Android Studio.app/Contents/jbr/Contents/Home"
   share one: bots consume RNG proportional to their `equityIterations`, so a
   shared stream means changing a profile silently changes the cards dealt.
 - `./gradlew :sim:run --args="chart"` dumps the starting-hand ranking.
-- Small samples lie. 1,000 hands is not enough to rank profiles — use 50,000+
-  before believing a gradient.
+- Small samples lie. 1,000 hands is not enough to rank profiles. Use the paired
+  4×100k fixed-opponent calibration before accepting a skill change; it computes
+  confidence bounds and exits nonzero when the contract fails.
 
 ## Status
 
@@ -70,14 +83,18 @@ export JAVA_HOME="/Applications/Android Studio.app/Contents/jbr/Contents/Home"
   action order, malformed agent output, **TDA Rule 47** (incomplete raises do not
   reopen betting, but several that cumulatively reach a full raise do), and
   **TDA Rule 20** (odd chip to the first winner left of the button).
-- Bots: profiles play like their labels (Rock 14.5% VPIP against a 12% setting;
-  `ProfileBehaviourTest` asserts this). Win rates are in a plausible range —
-  roughly +20 bb/100 for a strong seat rather than the earlier +113.
-- **Adjacent top tiers are not separable.** Advanced and Expert sit inside
-  seed-to-seed noise of each other over 100k hands. The simulator therefore
-  asserts each level beats the one *two* tiers below it, which holds on every
-  seed tried; claiming strict adjacent ordering from one seed would be reading
-  noise as signal.
+- Bots: controlled style calibration holds style constant against the same five
+  opponents and deal seed. Rock is 10.3% VPIP, Maniac 67.5%; looseness ordering,
+  Calling Station passivity (9.8% PFR, 0.27 AF), Maniac aggression, and PFR
+  relationships all pass.
+- Skill calibration pairs four 100k-hand seeds. Every candidate occupies the same
+  seat against the same fixed opponent pool and deal seed. Advanced and Expert
+  are allowed to overlap, but both must beat Intermediate and Intermediate must
+  beat Beginner with a positive 95% lower confidence bound. Current lower bounds
+  are +26.63, +16.19, and +24.71 bb/100 respectively.
+- Expert differs by mechanism: it alone maintains opponent reads. The aggression
+  prior is measured by the controlled neutral TAG experiment (0.229 observed,
+  0.22 configured), not selected because it looks plausible.
 
 ### Rules invariants that are easy to get wrong