SirRoboGarage/common_libs/guns/bitbrain_net.nim

## bitbrain_net.nim — BITBRAIN (rack id 17): the REAL ADE+SBC gun.
##
## The gun at rack id 16 used to be called `BITBRAIN` while containing no network
## at all; it is now `LEADGAIN` (`guns/lead_gain.nim`, a per-range-band lead-gain
## corrector). This module is the gun that actually runs the algorithm: an ADE
## layer (thresholded random projections with ONLINE threshold adaptation)
## feeding the SBC head from `common_libs/bitbrain/`, with the COUNTED + DECAY
## mode available — the mode that delivers forgetting and true per-class
## probabilities (`docs/bitbrain_counted_sbc.md`).
##
## ── OUTPUT SHAPE: a fine-grained aim correction ON TOP OF Pattern ────────────
## Not a direct aim point from the argmax class. Two reasons:
##   1. the gate test that motivated this (`docs/bitbrain_gate.md`) measured
##      exactly this shape — a class-resolved correction added to Pattern's
##      bearing — so this is the shape with a published measurement behind it;
##   2. Pattern's prediction is already a strong, fully-learned predictor. The
##      network's job is the RESIDUAL angular error, which is a small, signed,
##      zero-centred quantity; replacing the aim point outright would throw away
##      Pattern entirely on the (measured) bet that the net beats it.
## The correction is the PROBABILITY-WEIGHTED MEAN of the class centres under
## `inferProb`, i.e. a continuous readout over `nClasses` discrete cells rather
## than a step function of the argmax. Below `TR_BITBRAIN_MINOBS` resolved
## samples — or when the readout has no evidence — the correction is exactly 0
## and the gun returns Pattern's prediction unchanged.
##
## ── THE INPUT IS A CONFIGURED SET OF FEATURE BLOCKS ─────────────────────────
## The input vector is a concatenation of FEATURE BLOCKS, each independently
## selectable (`TR_BITBRAIN_FEATURES`) and with a settable width. A block is a
## list of scalar QUANTITIES; a block of width `W` lays each quantity out as a
## thermometer (unary) code of `W` slots, so width == resolution: a wider block
## distinguishes more states of that quantity. Slots are 0/255 uint8, which the
## ADE scorer centres at 127 (`DefaultCenter`), so a synapse "matches" when its
## polarity agrees with the slot and a random ADE fires iff its `w` synapses all
## match — a clean thresholded random projection with firing rate 2^-w.
##
## The DEFAULT block set (52 slots) and what each slot means:
##
##   block   quant.  slots  quantity
##   epos     2       8   enemy offset from us, x and y, over the arena span
##   evel     2       6   enemy speed; enemy heading minus the bearing to us
##   eturn    2       4   turn direction this tick; turn consistency over 10
##   eself    2       4   our speed; our heading minus the bearing to the enemy
##   dist     2      10   range; range rate over the last 10 ticks
##   bear     1       4   relative bearing (enemy bearing minus our heading)
##   walls    4       8   distance to each of the four arena walls
##   bull     2       4   live bullet count; nearest bullet's signed lateral offset
##   hzn      1       4   bullet flight time to the current range, h = dist / speed
##
## `docs/state_window_gate.md` measured that a long TEMPORAL WINDOW of states
## destroys recurrence, so there is deliberately NO window block here: the only
## history-derived inputs are the 3 rate/turn quantities above (10 ticks), which
## is the same causal information Pattern itself uses.
##
## ── DEFAULT OFF / PARITY ────────────────────────────────────────────────────
## Admitted ONLY when `TR_RACK_BITBRAIN=both` AND `TR_BITBRAIN_NET=1`. Both
## default off, so the shipped rack never calls `predict`, the network is never
## built (`ensureInit` is lazy), and the shipped bot is byte-for-byte unchanged.
## The default target RNG is a PRIVATE `initRand(seed)`, so construction cannot
## perturb the global selector RNG either.

import std/[math, os, strutils, strformat, algorithm, random]
import gun_harness/gun_interface
import guns/tm_horizon
import guns/pattern_matcher
import bitbrain/bitbrain

export ade, sbc

const
  ## ── env knobs (all resolved once at gun construction) ─────────────────────
  BBN_INPUT_ENV*    = "TR_BITBRAIN_INPUT"      ## total input slots
  BBN_CLASSES_ENV*  = "TR_BITBRAIN_NCLASSES"   ## output resolution
  BBN_NADES_ENV*    = "TR_BITBRAIN_NADES"      ## ADEs per AD
  BBN_WIDTHS_ENV*   = "TR_BITBRAIN_WIDTHS"     ## clause widths, one AD per width
  BBN_FEATURES_ENV* = "TR_BITBRAIN_FEATURES"   ## block:name:width,...
  BBN_SPAN_ENV*     = "TR_BITBRAIN_SPAN"       ## class half-range, degrees
  BBN_MINOBS_ENV*   = "TR_BITBRAIN_MINOBS"     ## resolved samples before trusting
  BBN_LOG_ENV*      = "TR_BITBRAIN_NETLOG"     ## 1 = per-change [bbn] log
  BBN_ADAPT_ENV*    = "TR_BITBRAIN_ADAPT_EVERY"## ADE threshold adaptation interval
  BBN_CALIB_ENV*    = "TR_BITBRAIN_CALIB_EVERY"## (compat alias; same interval)
  BBN_SEED_ENV*     = "TR_BITBRAIN_NETSEED"    ## network seed
  BBN_TARGET_ENV*   = "TR_BITBRAIN_TARGET"     ## ADE target firing rate
  BBN_RESET_ON_TARGET_ENV* = "TR_BITBRAIN_NET_RESET_ON_TARGET"
  BBN_NET_ENV*      = "TR_BITBRAIN_NET"        ## master switch (legacy disambiguator)
  ## The library's own knobs (read inside `common_libs/bitbrain`), re-declared
  ## here so `knownEnvNames()` and the boot report cover the whole gun.
  BBN_MODE_ENV*        = "TR_BITBRAIN_MODE"
  BBN_DECAY_EVERY_ENV* = "TR_BITBRAIN_DECAY_EVERY"
  BBN_DECAY_SHIFT_ENV* = "TR_BITBRAIN_DECAY_SHIFT"
  ## Every env name this gun reads, for the tree-scan guard's known set.
  BitbrainNetEnvNames* = [
    BBN_INPUT_ENV, BBN_CLASSES_ENV, BBN_NADES_ENV, BBN_WIDTHS_ENV,
    BBN_FEATURES_ENV, BBN_SPAN_ENV, BBN_MINOBS_ENV, BBN_LOG_ENV,
    BBN_ADAPT_ENV, BBN_CALIB_ENV, BBN_SEED_ENV, BBN_TARGET_ENV,
    BBN_RESET_ON_TARGET_ENV, BBN_MODE_ENV, BBN_DECAY_EVERY_ENV,
    BBN_DECAY_SHIFT_ENV]
  ## (`BBN_NET_ENV` == `TR_BITBRAIN_NET` is deliberately absent: it is already
  ## registered as `LG_NET_SWITCH_ENV`, the one switch both guns share.)

  ## ── feature blocks ────────────────────────────────────────────────────────
  BB_BLOCKS* = [
    ("epos", 2, 4), ("evel", 2, 3), ("eturn", 2, 2), ("eself", 2, 2),
    ("dist", 2, 5), ("bear", 1, 4), ("walls", 4, 2), ("bull", 2, 2),
    ("hzn", 1, 4)]
  ## Their shipped widths sum to BB_DEFAULT_SLOTS (8+6+4+4+10+4+8+4+4 = 52).
  BB_DEFAULT_SLOTS* = 52
  BB_MAX_SLOTS*     = 4096

  ## ── defaults ──────────────────────────────────────────────────────────────
  BBN_NCLASSES_DEF = 8         ## output resolution
  BBN_NADES_DEF    = 256       ## ADEs per AD
  BBN_WIDTHS_DEF*  = @[4, 5, 6]  ## clause widths: one AD per width, 3 cross SBCs
  BBN_SPAN_DEF     = 40.0
  BBN_MINOBS_DEF   = 32        ## resolved samples before the net is trusted
  BBN_ADAPT_DEF    = 200       ## inputs between threshold-adaptation passes
  BBN_TARGET_DEF   = 0.01      ## paper's target ADE firing rate
  BBN_SEED_DEF     = 20240921
  BBN_PENDING_CAP* = 512
  BBN_HIST*        = 12        ## the short causal history ring (see the note)
  BBN_SBC_VALUE*   = 255'u8   ## a "set" thermometer slot
  BBN_SLOT_CENTRE  = 127       ## DefaultCenter; a synapse matches when 0 or 255

type
  Block = tuple[name: string, nQuant: int, width: int]

  Pending = object
    fireTick: int
    horizon: int
    selfX, selfY: float
    baseBearing: float
    input: seq[uint8]
    klass: int

  HistSample = object
    x, y, heading: float

  BitbrainNetGun* = object
    tmh: TmHorizonGun
    initialized: bool
    ## ── resolved config (boot report) ────────────────────────────────────────
    enabled*: bool
    inputWidth*: int
    nClasses*: int
    nAde*: int
    widths*: seq[int]
    blockWidths*: seq[int]   ## per BB_BLOCKS entry; 0 = block disabled
    features*: string        ## the resolved block spec, for the boot report
    maxDeg*: float
    minObs*: int
    adaptEvery*: int
    targetRate*: float
    seed*: int64
    logEnabled*: bool
    resetOnTarget*: bool
    mode*: SbcMode
    decayEvery*: int
    decayShift*: int
    ## ── the network ─────────────────────────────────────────────────────────
    net*: BitBrain
    built: bool
    ## ── learner state ───────────────────────────────────────────────────────
    trained*: int
    sinceAdapt: int
    adapts*: int
    sinceEnqTick: int
    sinceEnqBucket: int
    pending: array[BBN_PENDING_CAP, Pending]
    pendingCount*: int
    pendingDropped*: int
    observedTargetId*: int
    lastTick: int
    ## ── readout ─────────────────────────────────────────────────────────────
    lastShiftDeg*: float
    lastClass*: int
    corrections*: int
    lastLogKey: string
    ## ── the short causal history the rate/turn blocks need ─────────────────
    ## DELIBERATELY SHORT (12 ticks, and only 3 derived quantities use it):
    ## `docs/state_window_gate.md` measured that feeding a long TEMPORAL WINDOW
    ## of states destroys the recurrence this network depends on. This is not
    ## a window block — it is the same 10-tick information Pattern uses.
    hist: seq[HistSample]

# ── config helpers ───────────────────────────────────────────────────────────

proc envStrBbn(name: string): string {.inline.} =
  let v = getEnv(name, "")
  if v.len > 0: v.strip() else: ""

proc envIntBbn(name: string, default: int): int =
  let v = envStrBbn(name)
  if v.len == 0: return default
  try: parseInt(v) except ValueError: default

proc envFloatBbn(name: string, default: float): float =
  let v = envStrBbn(name)
  if v.len == 0: return default
  try: parseFloat(v) except ValueError: default

proc envBoolBbn(name: string, default: bool): bool =
  case envStrBbn(name).toLowerAscii()
  of "1", "true", "yes", "on": true
  of "0", "false", "no", "off": false
  else: default

proc netOn*(): bool =
  ## The master switch. Default OFF: this gun is never admitted by an unset
  ## environment, and while it is off the `TR_BITBRAIN_*` names are the LEGACY
  ## aliases of the LEADGAIN corrector (`guns/lead_gain.nim`).
  envBoolBbn(BBN_NET_ENV, false)

proc blockNames*(): string =
  ## The known block names, comma separated (used in the unknown-block warning).
  for i in 0 ..< BB_BLOCKS.len:
    if i > 0: result.add ","
    result.add BB_BLOCKS[i][0]

proc parseBlockWidths*(value: string): seq[int] =
  ## Parse `TR_BITBRAIN_FEATURES` — a comma-separated `name[:W]` list. A block
  ## that is NOT listed keeps its shipped width; an explicitly listed block may
  ## be switched off with width 0. Unknown names are ignored (with a stderr
  ## warning) so a typo cannot silently change the input size. Unset/empty ->
  ## the shipped widths, byte-identical.
  result = newSeq[int](BB_BLOCKS.len)
  for i, b in BB_BLOCKS: result[i] = b[2]
  if value.len == 0: return
  for part in value.split(','):
    let p = part.strip()
    if p.len == 0: continue
    let ci = p.find(':')
    let nm = (if ci < 0: p else: p[0..<ci]).strip().toLowerAscii()
    var w = -1
    if ci >= 0:
      try: w = parseInt(p[ci+1..^1].strip())
      except ValueError: w = -1
    var found = false
    for i, b in BB_BLOCKS:
      if b[0] == nm:
        found = true
        result[i] = (if w < 0: b[2] else: w)
    if not found:
      stderr.writeLine("[bbn] unknown feature block '" & nm & "' in " &
        BBN_FEATURES_ENV & "; ignored (known: " &
        blockNames() & ")")
  for w in result.mitems: w = max(0, min(w, 64))

proc parseWidths*(value: string): seq[int] =
  ## Parse `TR_BITBRAIN_WIDTHS` — the ADE clause widths, one AD per width, one
  ## cross-AD SBC per unordered pair. Unset -> `BBN_WIDTHS_DEF`.
  if value.len == 0: return BBN_WIDTHS_DEF
  for tok in value.split(','):
    let t = tok.strip()
    if t.len == 0: continue
    var w: int
    try: w = parseInt(t) except ValueError: continue
    if w >= 1 and w <= 64: result.add w
  if result.len == 0: return BBN_WIDTHS_DEF

proc blockWidthsString*(widths: seq[int]): string =
  ## The resolved block spec as the env's own form (boot report).
  for i, w in widths:
    if i > 0: result.add ","
    if w == 0: result.add BB_BLOCKS[i][0] & ":0"
    elif w == BB_BLOCKS[i][2]: result.add BB_BLOCKS[i][0]
    else: result.add BB_BLOCKS[i][0] & ":" & $w

proc derivedSlots*(widths: seq[int]): int =
  for i, b in BB_BLOCKS: result += b[1] * widths[i]

proc blockName*(i: int): string {.inline.} = BB_BLOCKS[i][0]
proc blockQuantities*(i: int): int {.inline.} = BB_BLOCKS[i][1]

# ── construction ─────────────────────────────────────────────────────────────

proc initBitbrainNetGun*(): BitbrainNetGun =
  result.enabled = netOn()
  result.blockWidths = parseBlockWidths(envStrBbn(BBN_FEATURES_ENV))
  result.features = blockWidthsString(result.blockWidths)
  let derived = derivedSlots(result.blockWidths)
  result.inputWidth = clamp(envIntBbn(BBN_INPUT_ENV, derived), 1, BB_MAX_SLOTS)
  result.nClasses = clamp(envIntBbn(BBN_CLASSES_ENV, BBN_NCLASSES_DEF), 2, 4096)
  result.nAde = clamp(envIntBbn(BBN_NADES_ENV, BBN_NADES_DEF), 8, 8192)
  result.widths = parseWidths(envStrBbn(BBN_WIDTHS_ENV))
  result.maxDeg = clamp(envFloatBbn(BBN_SPAN_ENV, BBN_SPAN_DEF), 1.0, 180.0)
  result.minObs = max(1, envIntBbn(BBN_MINOBS_ENV, BBN_MINOBS_DEF))
  result.adaptEvery = max(1, envIntBbn(BBN_ADAPT_ENV, envIntBbn(BBN_CALIB_ENV, BBN_ADAPT_DEF)))
  result.targetRate = clamp(envFloatBbn(BBN_TARGET_ENV, BBN_TARGET_DEF), 0.0001, 0.5)
  result.seed = int64(envIntBbn(BBN_SEED_ENV, BBN_SEED_DEF))
  result.logEnabled = envBoolBbn(BBN_LOG_ENV, false)
  result.resetOnTarget = envBoolBbn(BBN_RESET_ON_TARGET_ENV, true)
  # The SBC storage mode + its decay knobs are the LIBRARY's env names, read
  # here so the gun's resolved config (and the boot report) is the real one.
  result.mode = envSbcMode(smCounted)
  result.decayEvery = envDecayEvery(64)
  result.decayShift = envDecayShift(3)
  result.lastTick = -1
  result.sinceEnqTick = -1
  result.sinceEnqBucket = -1
  result.observedTargetId = -1

proc buildNet*(g: var BitbrainNetGun) =
  ## Build the ADE layers + SBC head. LAZY: the shipped rack never calls it.
  ## Deterministic given the seed, and it uses a PRIVATE `initRand`, so it can
  ## never perturb the global selector RNG.
  if g.built: return
  g.built = true
  var rng = initRand(g.seed)
  # The clause width must not exceed the input width or `initRandomAddressDecoder`
  # cannot draw `w` distinct indices; clamp the widths to the input width.
  var widths = g.widths
  for i, w in widths: widths[i] = min(w, max(2, g.inputWidth))
  g.net = buildRandomBitBrain(widths = widths, nAde = g.nAde,
                              inputWidth = g.inputWidth, nClasses = g.nClasses,
                              seed = g.seed, mode = g.mode,
                              decayEvery = g.decayEvery,
                              decayShift = g.decayShift)
  # The initial threshold is 0, which for 0/255 slots centred at 127 fires every
  # ADE whose `w` synapses all match — rate 2^-w. Homeostatic adaptation then
  # drives each ADE toward the paper's ~1% target rate, online, unsupervised.
  for ad in g.net.ades.mitems:
    for i in 0 ..< ad.nAde: ad.thresholds[i] = int32(127 * ad.width - 1)
  g.tmh = initTmHorizonGun()

proc ensureInit*(g: var BitbrainNetGun) =
  if g.initialized: return
  g.initialized = true
  if not g.enabled: return
  g.buildNet()

# ── the input vector ─────────────────────────────────────────────────────────

proc pushTherm(dst: var seq[uint8], v: float, w: int) =
  ## Lay one quantity out as a `w`-slot thermometer code over [0, 1]. `w` == 0
  ## disables the quantity.
  if w <= 0: return
  var level = int(clamp(v, 0.0, 0.999999) * float(w))
  if level < 0: level = 0
  if level > w - 1: level = w - 1
  for j in 0 ..< w:
    dst.add(if j < level: BBN_SBC_VALUE else: 0'u8)

proc wrapRadNet(r: float): float {.inline.} =
  result = r
  while result > PI: result -= 2.0 * PI
  while result < -PI: result += 2.0 * PI

proc pushHist(g: var BitbrainNetGun, state: WorldState) =
  ## Ring of the last `BBN_HIST` states. One push per tick, in `predict`.
  if g.hist.len == 0:
    for _ in 0 ..< BBN_HIST:
      g.hist.add HistSample(x: state.enemyX, y: state.enemyY,
                            heading: state.enemyHeading)
  g.hist.insert(HistSample(x: state.enemyX, y: state.enemyY,
                           heading: state.enemyHeading), 0)
  g.hist.setLen(BBN_HIST)

proc turnSignal(g: BitbrainNetGun, state: WorldState): (float, float) =
  ## (turn direction this tick, turn consistency over the ring). 0.5 = straight,
  ## 0/1 = a full left/right turn; consistency = fraction of the ring's
  ## consecutive steps that turn the SAME way.
  if g.hist.len < 3:
    return (0.5, 0.5)
  let d0 = wrapRadNet(degToRad(state.enemyHeading - g.hist[0].heading))
  let dir = 0.5 + 0.5 * (if d0 > 0.0: 1.0 elif d0 < 0.0: -1.0 else: 0.0)
  var same = 0
  var total = 0
  for i in 0 ..< g.hist.len - 1:
    let d = wrapRadNet(degToRad(g.hist[i].heading - g.hist[i+1].heading))
    if abs(d) < 1e-9: continue
    inc total
    if (d > 0) == (d0 > 0.0): inc same
  (dir, if total == 0: 0.5 else: float(same) / float(total))

proc rangeSignal(g: BitbrainNetGun, state: WorldState,
                 dist: float): float =
  ## Signed range rate over the ring, in [-1, 1] (approaching / opening), scaled
  ## to +-400 px per tick and clamped. One quantity, ten ticks of history.
  if g.hist.len < 2: return 0.0
  let dPrev = hypot(g.hist[0].x - state.selfX, g.hist[0].y - state.selfY)
  let step = (dist - dPrev) / float(max(1, g.hist.len - 1))
  clamp(step / 400.0, -1.0, 1.0)

proc bulletSignal(g: BitbrainNetGun, state: WorldState): (float, float) =
  ## (live-bullet count / 4, nearest bullet's signed lateral offset in [-1,1]).
  ## The nearest known bullet is the one whose own last-seen tick is the most
  ## recent; with no bullet knowledge both are neutral.
  var best = -1
  var bestAge = high(int)
  for e in state.enemies:
    if e.lastSeenTick < 0: continue
    let age = state.tick - e.lastSeenTick
    if age < bestAge: bestAge = age; best = e.id
  if best < 0: return (0.0, 0.0)
  for e in state.enemies:
    if e.id != best: continue
    let toE = arctan2(e.y - state.selfY, e.x - state.selfX)
    let toB = arctan2(state.enemyY - state.selfY, state.enemyX - state.selfX)
    let lat = wrapRadNet(toB - toE)
    return (0.25, clamp(lat / 0.5, -1.0, 1.0))
  (0.0, 0.0)

proc buildInput*(g: var BitbrainNetGun, state: WorldState): seq[uint8] =
  ## (see the header for the block table)
  ## The configured feature-block vector for this state. Block order is fixed
  ## (`BB_BLOCKS`); each block's slot count is `g.blockWidths[i]`. The result is
  ## padded with zero slots or truncated to exactly `g.inputWidth`, so the
  ## ADE codes (drawn once at build time over `inputWidth`) can never index out
  ## of range no matter how the two knobs are combined.
  result = newSeqOfCap[uint8](g.inputWidth)
  let bw = g.blockWidths
  let ex = state.enemyX
  let ey = state.enemyY
  let sx = state.selfX
  let sy = state.selfY
  let wAll = max(1.0, state.arenaWidth)
  let hAll = max(1.0, state.arenaHeight)
  let dx = ex - sx
  let dy = ey - sy
  let dist = max(1e-6, hypot(dx, dy))
  let bearing = arctan2(dy, dx)
  let selfHdg = degToRad(state.selfHeading)
  let enemyHdg = degToRad(state.enemyHeading)

  for bi in 0 ..< BB_BLOCKS.len:
    let w = bw[bi]
    if w <= 0: continue
    case bi
    of 0:                                   # epos — enemy offset over the arena
      pushTherm(result, 0.5 + dx / wAll, w div 2)
      pushTherm(result, 0.5 + dy / hAll, w - w div 2)
    of 1:                                   # evel — speed, heading vs the lane
      pushTherm(result, state.enemySpeed / 16.0, w div 2)
      pushTherm(result, 0.5 + 0.5 * sin(enemyHdg - bearing), w - w div 2)
    of 2:                                   # eturn — turn now, consistency over 10
      let (dir, cons) = turnSignal(g, state)
      pushTherm(result, dir, w div 2)
      pushTherm(result, cons, w - w div 2)
    of 3:                                   # eself — our speed, our heading error
      pushTherm(result, state.selfSpeed / 16.0, w div 2)
      pushTherm(result, 0.5 + 0.5 * sin(selfHdg - bearing), w - w div 2)
    of 4:                                   # dist — range, range rate over 10
      pushTherm(result, dist / 1000.0, w div 2)
      pushTherm(result, 0.5 + 0.5 * rangeSignal(g, state, dist), w - w div 2)
    of 5:                                   # bear — relative bearing
      pushTherm(result, (bearing - selfHdg + PI) / (2.0 * PI), w)
    of 6:                                   # walls — distance to each wall
      pushTherm(result, ex / wAll, w div 4)
      pushTherm(result, (wAll - ex) / wAll, w div 4)
      pushTherm(result, ey / hAll, w div 4)
      pushTherm(result, (hAll - ey) / hAll, w - 3 * (w div 4))
    of 7:                                   # bull — live bullets, lateral offset
      let (n, lat) = bulletSignal(g, state)
      pushTherm(result, n / 4.0, w div 2)
      pushTherm(result, 0.5 + 0.5 * lat, w - w div 2)
    of 8:                                   # hzn — bullet flight time
      pushTherm(result, float(tmhHorizonFor(dist, 11.0)) / 50.0, w)
    else: discard

  if result.len < g.inputWidth:
    for _ in result.len ..< g.inputWidth: result.add 0'u8
  elif result.len > g.inputWidth:
    result.setLen(g.inputWidth)

# ── class geometry ───────────────────────────────────────────────────────────

proc classCenterDeg*(k, nClasses: int, maxDeg: float): float {.inline.} =
  ## Centre (degrees) of correction class `k` over ±maxDeg.
  -maxDeg + (float(k) + 0.5) * (2.0 * maxDeg / float(nClasses))

proc classOf*(errRad, maxDeg: float, nClasses: int): int {.inline.} =
  ## Bin a signed angular error (radians) into one of `nClasses` bins.
  let x = radToDeg(errRad)
  var k = int((x + maxDeg) / (2.0 * maxDeg) * float(nClasses))
  if k < 0: k = 0
  if k >= nClasses: k = nClasses - 1
  k

# ── readout ──────────────────────────────────────────────────────────────────

proc netShiftDeg*(g: var BitbrainNetGun, input: openArray[uint8]): float =
  ## The fine-grained correction: the PROBABILITY-WEIGHTED MEAN of the class
  ## centres over the SBC posterior. Returns 0.0 when there is no evidence.
  let (label, scores) = g.net.inferProb(input)
  var sum = 0.0
  var tot = 0.0
  for k in 0 ..< scores.len:
    sum += scores[k] * classCenterDeg(k, g.nClasses, g.maxDeg)
    tot += scores[k]
  g.lastClass = label
  if tot <= 0.0: 0.0 else: sum / tot

proc adaptThresholds*(g: var BitbrainNetGun, input: openArray[uint8]) =
  ## Online homeostasis (unsupervised): accumulate this input's ADE firings and
  ## every `adaptEvery` inputs nudge each threshold toward `targetRate`.
  for ad in g.net.ades.mitems: ad.accumulateFiring(input)
  inc g.sinceAdapt
  if g.sinceAdapt >= g.adaptEvery:
    for ad in g.net.ades.mitems:
      ad.adaptThresholds(interval = g.sinceAdapt, targetRate = g.targetRate)
    g.sinceAdapt = 0
    inc g.adapts

proc resolvePending(g: var BitbrainNetGun, state: WorldState) =
  ## Prequential label resolution: `h` ticks after the fire, the enemy's OBSERVED
  ## bearing from the firing position is the FACT; the required correction is
  ## `observedBearing - baseBearing`, binned into a class, and learned.
  var w = 0
  for i in 0 ..< g.pendingCount:
    let p = g.pending[i]
    let due = p.fireTick + p.horizon
    if due > state.tick:
      g.pending[w] = p
      inc w
    elif due == state.tick:
      let obs = tmhObservedAt(g.tmh, state.tick, p.selfX, p.selfY)
      if obs.ok and (state.tick - obs.lastSeenTick) <= TMH_STALE_MAX:
        let err = wrapRadNet(obs.bearing - p.baseBearing)
        g.net.learn(p.input, classOf(err, g.maxDeg, g.nClasses))
        inc g.trained
      else:
        inc g.pendingDropped
    else:
      inc g.pendingDropped
  g.pendingCount = w

proc bbnLog(g: var BitbrainNetGun, state: WorldState, shiftDeg: float) =
  if not g.logEnabled: return
  let key = fmt"{shiftDeg:.2f}"
  if key == g.lastLogKey: return
  g.lastLogKey = key
  echo fmt"[bbn] t={state.tick} shift={shiftDeg:+.2f}deg class={g.lastClass} " &
       fmt"in={g.inputWidth} ncl={g.nClasses} nAde={g.nAde} " &
       fmt"mode={($g.mode)[7..^1]} trained={g.trained} adapts={g.adapts} " &
       fmt"pend={g.pendingCount} dropped={g.pendingDropped}"

# ── reset hooks ──────────────────────────────────────────────────────────────

proc resetRoundState*(g: var BitbrainNetGun) =
  if not g.initialized: return
  g.tmh.resetRoundState()
  g.pendingCount = 0
  g.hist.setLen(0)
  g.lastTick = -1
  g.sinceEnqTick = -1
  g.sinceEnqBucket = -1
  g.lastLogKey = ""

proc resetLearning*(g: var BitbrainNetGun, reason = "") =
  ## Per-battle / per-enemy wipe of the SBC counters. The ADEs (codes and
  ## adapted thresholds) survive: they are unsupervised structure, not labels.
  if not g.initialized: return
  g.net.resetLearning()
  g.trained = 0
  g.sinceAdapt = 0
  g.adapts = 0
  g.corrections = 0
  g.lastShiftDeg = 0.0
  g.observedTargetId = -1
  g.resetRoundState()
  if reason.len > 0 and g.logEnabled: echo fmt"[bbn-reset] reason={reason}"

proc targetChanged*(g: var BitbrainNetGun, enemyId: int): bool =
  if not g.resetOnTarget: return false
  if enemyId < 0: return false
  if g.observedTargetId >= 0 and enemyId != g.observedTargetId:
    g.resetLearning("target_change")
    g.observedTargetId = enemyId
    return true
  g.observedTargetId = enemyId
  false

# ── Gun interface ────────────────────────────────────────────────────────────

proc isWarmedUp*(g: BitbrainNetGun): bool {.inline.} =
  ## Ready as soon as it has enough resolved samples to have a readout; before
  ## that it is the identity on Pattern, which is always a valid prediction.
  g.trained >= g.minObs

proc networkBytes*(g: BitbrainNetGun): int =
  ## RAM held by the network (ADs + SBC tensors). 0 before the lazy build.
  if not g.built: 0 else: g.net.memoryBytes

proc sbcBytes*(g: BitbrainNetGun): int =
  if not g.built: 0 else: g.net.sbcMemoryBytes

proc predict*(g: var BitbrainNetGun, state: WorldState,
              bulletSpeed: float): GunPrediction =
  g.ensureInit()
  if not g.enabled: return GunPrediction(x: state.enemyX, y: state.enemyY)
  if state.tick < g.lastTick: g.resetRoundState()
  if state.tick != g.lastTick:
    tmhUpdateHistory(g.tmh, state)
    g.resolvePending(state)
    g.pushHist(state)
    g.lastTick = state.tick

  # The base is Pattern; BitBrain only adds a fine-grained correction to it.
  let base = g.tmh.pattern.predict(state, bulletSpeed)
  if bulletSpeed <= 0.0: return base
  let dist = hypot(state.enemyX - state.selfX, state.enemyY - state.selfY)
  let h = tmhHorizonFor(dist, bulletSpeed)
  let hb = tmhHorizonBucket(h)

  var input = buildInput(g, state)
  g.adaptThresholds(input)

  # One deferred training sample per (tick, horizon bucket): `predict` runs once
  # per power bin, so all four horizons contribute evidence.
  if g.sinceEnqTick != state.tick or g.sinceEnqBucket != hb:
    if g.pendingCount < BBN_PENDING_CAP:
      let los = arctan2(state.enemyY - state.selfY, state.enemyX - state.selfX)
      let baseBearing = arctan2(base.y - state.selfY, base.x - state.selfX)
      g.pending[g.pendingCount] = Pending(
        fireTick: state.tick, horizon: h, selfX: state.selfX, selfY: state.selfY,
        baseBearing: baseBearing, input: input,
        klass: classOf(wrapRadNet(baseBearing - los), g.maxDeg, g.nClasses))
      inc g.pendingCount
    else:
      inc g.pendingDropped
    g.sinceEnqTick = state.tick
    g.sinceEnqBucket = hb

  g.lastShiftDeg = 0.0
  if g.trained >= g.minObs:
    g.lastShiftDeg = g.netShiftDeg(input)
  g.bbnLog(state, g.lastShiftDeg)
  if abs(g.lastShiftDeg) < 1e-9: return base
  inc g.corrections
  tmhApplyShift(state.selfX, state.selfY, base.x, base.y, g.lastShiftDeg)

proc onResult*(g: var BitbrainNetGun, e: FeedbackEvent) =
  ## Labels come from our own observation ring, not from virtual-bullet
  ## feedback. The hook exists for the rack.
  discard

proc blockNameIndex*(name: string): int =
  ## Index of the named block in `BB_BLOCKS`, or -1. Used by the tests and the
  ## boot report so a block is addressed by its NAME, never by a bare index.
  for i in 0 ..< BB_BLOCKS.len:
    if BB_BLOCKS[i][0] == name: return i
  -1

proc inferClass*(g: var BitbrainNetGun, input: openArray[uint8]): int =
  ## The argmax class of the SBC posterior. Exposed (rather than letting callers
  ## reach into `g.net`) so the gun's network stays an implementation detail and
  ## so this name cannot be shadowed by the SBC-level `inferProb` export.
  g.net.inferProb(input).label

proc sbcBytesOf*(g: BitbrainNetGun): int =
  let net = g.net
  net.sbcMemoryBytes()

proc sbcsOf*(g: BitbrainNetGun): seq[Sbc] = g.net.sbcs

proc learnSample*(g: var BitbrainNetGun, input: openArray[uint8], klass: int) =
  ## One supervised online step: drive the ADE layer and set/increment the class
  ## in every observed coincidence. Exposed so tests can drive the learner
  ## without replaying a whole deferred-label stream.
  g.net.learn(input, klass)

proc evidenceFor*(g: var BitbrainNetGun, input: openArray[uint8], klass: int): int =
  ## Total SBC evidence the network currently holds for `klass` on `input` (the
  ## summed counters, or the set-bit count in bitset mode). Unlike
  ## `occupancy` — which saturates once a cell is non-zero — this GROWS with
  ## every counted learn, so it is the observable that proves the counted mode
  ## is accumulating rather than just flipping bits.
  g.net.infer(input).counts[klass]