TM radial gun: registered (default OFF) + label-bias fix that removes the bias but

retracts its own earlier learning claim

=== TASK 1: REGISTERED AS GUN 14, DEFAULT `off` ===
The radial TM gun is now a first-class rack member (`TMPATTERN`, id 14), forceable
alone with `TR_RACK_TMPATTERN=both` plus every other `TR_RACK_*=off`.
DEFAULT IS `off`, and the justification matters: `both` would let it compete for
selection AND (because the shared VirtualTracker ring is order-sensitive) shift
every other gun's learning order, so it CANNOT leave the default path unchanged.
With `off` its predict and spawnBullets are additionally GATED on rack admission
(the only gun wired that way), so the shipped default never spawns it at all:
zero cost, zero ring perturbation.
Live proof: 1-round battle with only TMPATTERN racked ->
  `gun 14 (TMPattern): vShots=400 selected=104 other-gun selections=0`.
Default-path-unchanged proof: parity checks that the 15-gun default bestGun/
selectGun equals the old 14-gun rack RNG-draw-for-RNG-draw, that gun 14 is never
selected by default, and acceptance 12/12.
Cost: 0.36 ms/tick (predict 0.30 + onResult 0.05) ~= 3% of the 13.16 ms budget.
Tsetlin in the same harness is 1.62 ms/tick, so the new gun is ~4.5x cheaper.

=== TASK 2: THE LABEL-BIAS FIX - AND A RETRACTION ===
Root cause confirmed: under bmPoint a SHORT radial correction resolves the virtual
bullet BEFORE the base arrival tick, so the label was dropped (labelMisses).
Fix: defer the label in a pending queue and flush it once the arrival tick is
recorded; labels still come from the BASE arrival tick.
  labelMisses        4,281,695  ->  0
  training samples   1,071,824  ->  5,345,847  (x5)
  radial head acc         48.8% ->  57.0%   (shuffled control 20.0%)
  bmPoint hit rate     9.4/5.8% ->  9.1/5.7%  (unchanged, within noise)
So the fix IMPROVES LEARNING but NOT the metric.

**RETRACTION OF THE PREVIOUS JOB'S CLAIM.** It reported the radial head's 48.8%
against a 36.7% majority baseline and concluded "conditional learning, not a
constant bias". With the bias removed, the correctly-measured majority baseline is
**58.2%** - so the head at 57.0% is AT/BELOW majority. The earlier apparent
conditional learning was PARTLY AN ARTEFACT OF THE BIASED SAMPLE. The bmPoint
metric win is real (TMRadial > Linear early 16/2 p=0.0013, overall 18/0 p<0.0001;
> shuffled 18/0 p<0.0001) but it comes from a NET-POSITIVE AVERAGE RADIAL SHIFT,
not from beating a majority classifier. Recorded plainly rather than left standing.

Guards: test_tm_pattern_registration 20 (new), test_tm_pattern_rack_live 4 (new),
test_gun_harness 39, test_vbullet_metric 11, test_power_selection 3 (the SIGSEGV is
gone - the knn_gun rewrite is now committed), test_adaptive_radar 41,
test_tfil_ring_weights 24, test_power_policy 26, test_ram_decision 28,
test_rack_membership 38, test_selector_tiebreak 19, test_tm_pattern_learning 3,
acceptance_offline_vs_online 12/12. ModularBot compiles (release).

Note: `common_libs/tests/range_guns.nim` still builds 14 offline drivers (the
offline sweep constructs TmPatternGun directly and acceptance only inspects ids
0..13), so nothing breaks - but a future job wanting it in the offline rack must
add a 15th driver and mirror the live admission gating. gun_stats.jsonl now emits
15 rows; downstream tooling should ignore id 14.

common_libs/gun_harness/selector.nim

@@ -19,21 +19,30 @@ import virtual_bullets
 #   TR_RACK_TSETLIN=1v1      -> 1v1 rack only
 #   TR_RACK_DISPLACE=melee   -> melee rack only
 #   TR_RACK_KNN=off          -> removed from both racks
+#   TR_RACK_TMPATTERN=off    (shipped default for the new TM pattern gun)
 #
 # The mode itself is derived from SERVER truth (`getEnemyCount()`), never from
 # the tracker's known-enemy count, by `rackMode` in virtual_bullets — the same
-# transition the radar uses. Defaults are all-`both`, so an unset environment
-# preserves the pre-change single-rack selection byte-for-byte.
+# transition the radar uses. Every gun except TMPATTERN defaults to `both`, so an
+# unset environment preserves the pre-change single-rack selection byte-for-byte;
+# TMPATTERN defaults to `off` so it cannot alter that selection.
 
 const
-  RackGunNames*: array[14, string] = [
+  RackGunNames*: array[15, string] = [
     "HEADON", "LINEAR", "TSETLIN", "CIRCULAR", "GUESSFACTOR", "PATTERN",
     "WALLBOUNCE", "ACCEL", "STOPSHOT", "DISPLACE", "AVGLEAD", "DECAYGF",
-    "KNN", "TMSELECT"]
+    "KNN", "TMSELECT", "TMPATTERN"]
   RackEnvPrefix* = "TR_RACK_"
-  DefaultRackMembership*: array[14, RackMembership] = [
+  ## Defaults are all-`both` EXCEPT the new TM pattern gun (id 14), which ships
+  ## `off`: it is registered and forceable (`TR_RACK_TMPATTERN=both|1v1|melee`)
+  ## but never spawns a virtual bullet unless explicitly enabled, so the shared
+  ## VirtualTracker ring head — and therefore every other gun's learning order
+  ## and the default selection sequence — is byte-for-byte unchanged. Defaulting
+  ## it to `both` would let it compete for selection and change the default rack.
+  DefaultRackMembership*: array[15, RackMembership] = [
     rmBoth, rmBoth, rmBoth, rmBoth, rmBoth, rmBoth, rmBoth,
-    rmBoth, rmBoth, rmBoth, rmBoth, rmBoth, rmBoth, rmBoth]
+    rmBoth, rmBoth, rmBoth, rmBoth, rmBoth, rmBoth, rmBoth,
+    rmOff]
 
 proc parseRackMembership*(value: string): RackMembership =
   ## Parse a `TR_RACK_<GUN>` value. Empty / unknown values fall back to the