clay-borg/tools/design-baseline.py

#!/usr/bin/env python3
"""Baseline harness: how findable, reproducible and answered are the
design findings this project has already produced?

The comparator is US, today. The external candidates (rulings databases,
model-checker traces, W3C provisional marks) are practices rather than
runnable software, so per InnerLoop Step 1 their rows are DIRECTIONAL and
cap at `parity`. This is the row that can be measured.
"""
#
# ── SUPERSEDED 2026-08-05 by tools/design.py (ADR-0012 D8) ──────────────
#
# Kept as CB-RES-0007's dated snapshot, NOT as a live instrument. Deleting
# it would erase the evidence for how a wrong number got into a survey.
#
# The adversarial review (C2) dismantled it and every point is true:
#   * FINDINGS below is a hand-maintained dict; `n = len(FINDINGS)` counts
#     the rows someone typed, not findings that exist.
#   * `has_reproduction` is `startswith("scenarios/")` and never stats the
#     file, so the self-test's YES-control is GREEN against a path that
#     2da19a4 deleted. A positive control that controls nothing.
#   * It rejects a named test, which the admissibility rule admits, so its
#     33% is biased downward.
#   * The 4-day figure is two date literals subtracted. Mutated to
#     2020-01-01 it reports 2406 days with every check still green.
#
# **Its 33% is withdrawn as a measured rate.** What survived: 11 files,
# no index, 0 of 10 ruled — all checkable without this tool.
#
import os, re, subprocess, sys, datetime

ROOT = "/home/worsch/clay-borg"
os.chdir(ROOT)

# The findings this project has actually produced, and where each lives.
FINDINGS = {
    "U1..U10 underdetermined points": ["specs/GroundRules.md"],
    "SOLVE on a face-down Problem": ["workplans/CB-WP-0018-the-browser-is-a-client.md",
                                     "evidence/CB-EV-0016-the-browser-is-a-client.md"],
    "GR-A13 wasted SOLVE": ["evidence/CB-EV-0007-stage-0.md"],
    # RESOLVED 2026-08-04: ground-game ruled GR-S01's deal, the engine
    # imports the edition, and the scenario was renamed from
    # `-unreachable-` to `-reachable-`. Kept in the baseline because the
    # baseline is a snapshot of what the survey measured, and a register
    # that drops findings when they close cannot report a close rate.
    "GR-E01 unreachable below 5 seats [RESOLVED]": [
        "evidence/CB-EV-0007-stage-0.md",
        "scenarios/ground/gr-e01-threshold-reachable-2p.yaml",
        "workplans/CB-WP-0021-import-the-edition.md"],
    # FROZEN 2026-08-05. This globbed `provisional: true` live, so it was
    # never a snapshot -- it drifted with the repo. CB-WP-0026 lifted the
    # last five flags (ground-game ruled them 2026-08-03) and the glob went
    # empty, turning this file's own pinned self-test red at 1/6. A dated
    # snapshot that recomputes is a contradiction; the literal list it
    # measured on 2026-08-03 is what belongs here.
    "six provisional defaults": [
        "scenarios/ground/gr-a04-bond-support.yaml",
        "scenarios/ground/gr-d01-darvo-trigger.yaml",
        "scenarios/ground/gr-d05-darvo-reverse.yaml",
        "scenarios/ground/gr-e02-shared-ground.yaml",
        "scenarios/ground/gr-e04-coalitions.yaml",
    ],
    "GR-E03/GR-E04 never played": ["evidence/CB-EV-0007-stage-0.md"],
}

def has_reproduction(paths):
    """A runnable thing: a scenario file, or a named test/command."""
    for p in paths:
        if p.startswith("scenarios/"):
            return True
    return False

def self_test():
    """The control that matters: a harness that read nothing must not
    report a clean baseline. Every path this survey cites must exist, and
    the reproduction test must be able to say NO — one that answered yes
    for everything would report 100% and look excellent."""
    results = []

    def check(name, ok, detail=""):
        results.append((name, ok, detail))

    missing = [p for paths in FINDINGS.values() for p in paths
               if not os.path.exists(p)]
    check("every cited location exists", not missing, ", ".join(missing[:3]))
    check("the finding set is not empty", len(FINDINGS) >= 6, f"{len(FINDINGS)}")
    check("reproduction detection can say NO",
          not has_reproduction(["evidence/CB-EV-0007-stage-0.md"]),
          "a detector that always says yes would report 100%")
    check("reproduction detection can say YES",
          has_reproduction(["scenarios/ground/gr-e01-threshold-unreachable-2p.yaml"]))
    # The number this survey turns on, pinned so a later edit cannot move
    # it silently: 2 of 6 today.
    repro_now = sum(has_reproduction(v) for v in FINDINGS.values())
    check("the measured baseline is 2 of 6", repro_now == 2, f"{repro_now}/6")

    print("design-baseline self-test (positive control)")
    ok = True
    for name, passed, det in results:
        print(f"  [{'ok ' if passed else 'FAIL'}] {name}" + (f"  — {det}" if det else ""))
        ok &= passed
    return 0 if ok else 1


if "--self-test" in sys.argv:
    raise SystemExit(self_test())

print("BASELINE — design findings as they stand, 2026-08-03\n")
places = set()
repro = 0
for name, paths in FINDINGS.items():
    places.update(paths)
    r = has_reproduction(paths)
    repro += r
    print(f"  {'repro' if r else '  -  '}  {len(paths)} location(s)  {name}")

n = len(FINDINGS)
print(f"\n  findings                      {n}")
print(f"  with a runnable reproduction  {repro}/{n} = {100*repro//n}%")
print(f"  distinct files holding them   {len(places)}")
print(f"  single register?              NO — {len(places)} files, no index")

# Time from raised to READ, for the one finding with a timestamp trail.
raised = datetime.date(2026, 7, 30)   # hub message from clay-borg-custodian
read   = datetime.date(2026, 8, 3)    # marked read this session
print(f"\n  U1..U10: raised {raised}, first READ {read} — {(read-raised).days} days")
print(f"  U1..U10: answered? NO — {(read-raised).days}+ days open, 0 of 10 ruled")