Files
Sylpheed/tools/re-capture/probeharness.py
Sylpheed RE agent feb535a8fb re: build a shared probe harness so the same lessons stop being re-learned
Four probes were written from a blank file and each re-learned the same lessons
by losing a run: that a flat run cannot be told from a frozen guest without a
stall witness, that results held to the end of a run are destroyed by a turn
timeout, that a roster count which is not the stage's member count means a
different stage loaded and must be discarded, and that a run's witness state has
to be read before its numbers. Writing each lesson down did not stop the next
probe repeating it, because each probe started from nothing.

probeharness.py makes them structural. Probe(baseline=N) discovers the roster,
rescans up to five times and refuses to start if the count never reaches the
baseline. The witness is calibrated on construction, sampled by tick() and
reported by status() and summary(), so a probe cannot forget it, and when no
witness is found it reports UNVALIDATED rather than zero stalls. emit() flushes
on every line. craft(), strengths(), alive() and heap() supply the
roster-to-craft link, per-record liveness and the raw heap, so a new probe
writes only its own logic.

Verified rather than asserted: deploy_probe.py reimplements the per-record
deployment watch on top of it in about forty lines against wave7_probe's
hundred and fifty, and its first live run was clean -- 116 roster records, 32
witnesses at 10/s, zero stalled samples, seven losses tracked, and the TSV
written incrementally. Nothing about the result is new, which is the point: the
harness reproduces a known-good measurement.

The existing probes are deliberately not ported. They work, and rewriting them
would risk changing results other documents cite. New probes should use the
harness; old ones should be ported when they next need a change.
2026-08-25 05:22:24 +00:00

200 lines
7.4 KiB
Python

#!/usr/bin/env python3
"""Shared harness for live-memory probes.
Written because the same four lessons were re-learned in four separate one-off
probes, each time by losing a run:
* **stall witness** — flat output is indistinguishable from a frozen guest.
Four probes shipped without one; three produced runs that could not be
interpreted (guest-stalls.md, remaining-ob-hunt.md).
* **incremental save** — two probes deferred results to the end and a turn
timeout destroyed them, the second time four iterations after the lesson was
written down.
* **baseline discard** — a run whose roster count is not the stage's member
count is a different stage and must not be interpreted
(mission-per-record-strength.md).
* **witness first** — a run's stall state must be read before its numbers.
Anything reading live guest memory should start from `Probe`, not from a blank
file.
p = Probe(baseline=116) # None = accept whatever loads
if not p.ok: sys.exit(p.why)
p.log('t\\tvalue') # opens an incrementally-flushed TSV
while p.tick(every=15):
p.emit('%d\\t%d' % (p.elapsed, measure()))
print(p.status()) # includes the stall verdict
"""
import collections, os, struct, sys, time
sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
import gmem, gworld, entities2
import numpy as np
ROSTER_VT = struct.pack('>I', 0x820AF030)
DELTA, WIN, LINK, HULL = 0x130, 0x400, 0x08, 0x154
HEAP_LO, HEAP_HI = 0xBC000000, 0xBE000000
ENT_LO, ENT_HI = entities2.ENT_VA_LO, entities2.ENT_VA_HI
class Probe:
def __init__(self, baseline=None, tsv=None, witness=True, rescans=5):
self.w = gworld.World()
self.fd = self.w.fd
self.t0 = time.time()
self.ok, self.why = False, ''
self.stalled_samples = 0
self._f = None
self.defs = entities2.definitions(self.w)
if not self.defs:
self.why = 'NOT IN A MISSION (no unit definitions)'
return
self.roster = self._scan_vt(ROSTER_VT)
for _ in range(rescans):
if baseline is None or len(self.roster) == baseline:
break
time.sleep(10)
self.roster = self._scan_vt(ROSTER_VT)
if baseline is not None and len(self.roster) != baseline:
self.why = ('DISCARD: roster settled at %d, not the baseline %d '
'(a different stage loaded)' % (len(self.roster), baseline))
return
self.want = {}
for o in self.roster:
va = gmem.primary_va(o)
if va is not None:
self.want[va + LINK] = o
self.ticks, self.rate, self._last = [], None, None
if witness:
self._calibrate()
if tsv:
self.log_path = tsv
self.ok = True
# ---- guest access -------------------------------------------------
def _scan_vt(self, vt):
out = []
for a, b in gmem.extents(self.fd, self.w.size):
pos = a
while pos < b:
m = min(1 << 24, b - pos)
blob = os.pread(self.fd, m, pos)
i = blob.find(vt)
while i != -1:
if (pos + i) % 4 == 0:
out.append(pos + i)
i = blob.find(vt, i + 1)
pos += m
return sorted(out)
def heap(self):
"""Raw bytes of the game heap."""
lo, hi = gmem.va_to_off(HEAP_LO), gmem.va_to_off(HEAP_HI)
out, pos = bytearray(), lo
while pos < hi:
n = min(1 << 24, hi - pos)
out += os.pread(self.fd, n, pos)
pos += n
return bytes(out), lo
def craft(self):
"""[(base_offset, unit_name, roster_offset|None)] — one per live craft."""
lo, hi = gmem.va_to_off(ENT_LO), gmem.va_to_off(ENT_HI)
out, pos = [], lo
while pos < hi:
m = min(1 << 24, hi - pos)
blob = os.pread(self.fd, m, pos)
for needle, nm in self.defs.items():
i = blob.find(needle)
while i != -1:
if (pos + i) % 4 == 0:
base = pos + i - DELTA
own = None
head = os.pread(self.fd, WIN, base)
for j in range(0, len(head) - 3, 4):
(p,) = struct.unpack_from('>I', head, j)
if p in self.want:
own = self.want[p]
break
out.append((base, nm, own))
i = blob.find(needle, i + 1)
pos += m
return out
def alive(self, base):
try:
return struct.unpack('>f', os.pread(self.fd, 4, base + HULL))[0] > 0
except Exception:
return False
def strengths(self):
"""craft alive per roster record."""
per = collections.Counter()
for base, _, own in self.craft():
if own is not None and self.alive(base):
per[own] += 1
return per
# ---- witness ------------------------------------------------------
def _calibrate(self, dt=3.0):
a, _ = self.heap()
time.sleep(dt)
b, _ = self.heap()
A = np.frombuffer(a, dtype='>u4').astype(np.int64)
B = np.frombuffer(b, dtype='>u4').astype(np.int64)
d = B - A
rates = collections.Counter((d[(d > 15) & (d < 600)] // int(dt)).tolist())
band = [r for r in rates if 8 <= r <= 40]
pick = max(band, key=lambda r: rates[r]) if band else None
if pick is None:
return
self.rate = pick
self.ticks = np.nonzero(d // int(dt) == pick)[0][:32]
self._last = B[self.ticks]
def stalled(self):
"""True if the guest did not advance since the previous check."""
if not len(self.ticks):
return None # unknown: no witness
b, _ = self.heap()
now = np.frombuffer(b, dtype='>u4').astype(np.int64)[self.ticks]
moved = int((now > self._last).sum())
self._last = now
return moved == 0
# ---- loop / output ------------------------------------------------
@property
def elapsed(self):
return round(time.time() - self.t0)
def tick(self, every, secs):
if time.time() - self.t0 >= secs:
return False
time.sleep(every)
self._stall = self.stalled()
if self._stall:
self.stalled_samples += 1
return True
def status(self):
s = getattr(self, '_stall', None)
if s is None:
return ' (UNVALIDATED: no witness)'
return ' *** GUEST STALLED ***' if s else ''
def log(self, header, path=None):
self._f = open(path or getattr(self, 'log_path', '/tmp/probe.tsv'), 'w')
self._f.write(header.rstrip('\n') + '\n')
self._f.flush()
def emit(self, line):
"""Write AND flush — never defer results to the end of a run."""
if self._f:
self._f.write(line.rstrip('\n') + '\n')
self._f.flush()
def summary(self):
w = ('%d witnesses at %s/s' % (len(self.ticks), self.rate)
if len(self.ticks) else 'NO WITNESS - run UNVALIDATED')
return ('roster %d, definitions %d, %s, stalled samples %d'
% (len(self.roster), len(self.defs), w, self.stalled_samples))