Loaded up for the 3rd redo
Still on potion-voice
This commit is contained in:
@@ -0,0 +1,390 @@
|
||||
#!/usr/bin/env python3
|
||||
"""render-rubric-grade.py — validate rubric-grade.json and derive reward + grade.md.
|
||||
|
||||
The rubric grader modes (test.sh GRADER_MODE=rubric-trinary | rubric-scalar) have
|
||||
the grader agent score each atomic rubric criterion independently and write
|
||||
/logs/verifier/rubric-grade.json. This script:
|
||||
|
||||
1. validates the shape against the staged criteria manifest
|
||||
(tests/rubric-criteria.json): every expected criterion id exactly once,
|
||||
the form's field present (trinary: verdict pass|partial|fail;
|
||||
scalar: score 0.00-1.00 two decimals), non-empty rationales. The manifest
|
||||
also carries each criterion's severity; a manifest with more than
|
||||
2 criteria of severity 'crux' is rejected outright (hard cap),
|
||||
2. renders grade.md (per-criterion verdicts + rationales),
|
||||
3. derives reward.txt: the severity-weighted mean over criteria of value,
|
||||
where trinary maps pass=1.00 / partial=0.50 / fail=0.00 and scalar uses
|
||||
the score directly. Severity weights: crux=25 (Crux),
|
||||
certain_dealbreaker=5 (Critical), possible_dealbreaker=2 (Major),
|
||||
unlikely_dealbreaker=1 (Minor); dodged_bullet criteria are weighted by
|
||||
their severity like every other category. Criteria whose manifest
|
||||
category is extra_credit carry weight 1 and are included only when their
|
||||
value is > 0 (fulfilled extra credit joins the weighted mean; unfulfilled
|
||||
extra credit is excluded rather than penalized). A non-extra-credit
|
||||
criterion with a null/missing severity falls back to
|
||||
unlikely_dealbreaker (weight 1) with a warning on stderr,
|
||||
4. rewrites rubric-grade.json in normalized form (generator stamp).
|
||||
|
||||
Per-criterion verdicts are the primary artifact — the aggregate is one
|
||||
documented reduction of them, and downstream analysis can re-aggregate from
|
||||
the normalized JSON any other way. The grader itself never sees severity
|
||||
(rubric-criteria.md carries guideline + elaboration only); weighting lives
|
||||
entirely in this aggregation step.
|
||||
|
||||
Exit codes: 0 = ok; 2 = rubric-grade.json missing/unparseable/invalid, or the
|
||||
criteria manifest is bad (including the >2 crux cap violation) — the caller
|
||||
treats that grader sample as invalid. Never writes partial output.
|
||||
Stdlib-only and Python 3.8-compatible on purpose: python3 is the only
|
||||
interpreter guaranteed in every task image.
|
||||
|
||||
Usage:
|
||||
python3 render-rubric-grade.py --criteria tests/rubric-criteria.json \
|
||||
--form trinary [--rubric-json /logs/verifier/rubric-grade.json] \
|
||||
[--out-dir /logs/verifier]
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import os
|
||||
import sys
|
||||
from typing import Any, Dict, List
|
||||
|
||||
RENDER_RUBRIC_GRADE_VERSION = "render-rubric-grade/2.0.0"
|
||||
SCHEMA_VERSION = 1
|
||||
|
||||
FORMS = ("trinary", "scalar")
|
||||
VERDICT_CENTS = {"pass": 100, "partial": 50, "fail": 0}
|
||||
|
||||
# Severity tiers, highest first. The weighted mean uses these weights; the
|
||||
# display names appear in grade.md's summary line.
|
||||
SEVERITY_ORDER = ("crux", "certain_dealbreaker", "possible_dealbreaker", "unlikely_dealbreaker")
|
||||
SEVERITY_WEIGHTS = {
|
||||
"crux": 25,
|
||||
"certain_dealbreaker": 5,
|
||||
"possible_dealbreaker": 2,
|
||||
"unlikely_dealbreaker": 1,
|
||||
}
|
||||
SEVERITY_DISPLAY = {
|
||||
"crux": "Crux",
|
||||
"certain_dealbreaker": "Critical",
|
||||
"possible_dealbreaker": "Major",
|
||||
"unlikely_dealbreaker": "Minor",
|
||||
}
|
||||
DEFAULT_SEVERITY = "unlikely_dealbreaker"
|
||||
EXTRA_CREDIT_WEIGHT = 1
|
||||
MAX_CRUX_CRITERIA = 2
|
||||
|
||||
WEIGHTS_NOTE = " / ".join(
|
||||
"%s %d" % (SEVERITY_DISPLAY[s], SEVERITY_WEIGHTS[s]) for s in SEVERITY_ORDER
|
||||
)
|
||||
|
||||
|
||||
class RubricValidationError(Exception):
|
||||
"""A shape/content problem in rubric-grade.json. Message names the bad path."""
|
||||
|
||||
|
||||
def _fail(path: str, message: str) -> None:
|
||||
raise RubricValidationError("%s: %s" % (path, message))
|
||||
|
||||
|
||||
def _validate_text(value: Any, path: str) -> str:
|
||||
if not isinstance(value, str) or not value.strip():
|
||||
_fail(path, "must be a non-empty string")
|
||||
return value.strip()
|
||||
|
||||
|
||||
def _validate_score_cents(value: Any, path: str) -> int:
|
||||
if isinstance(value, bool) or not isinstance(value, (int, float)):
|
||||
_fail(path, "must be a number")
|
||||
if value < 0 or value > 1:
|
||||
_fail(path, "must be between 0 and 1")
|
||||
cents_float = value * 100
|
||||
cents = int(round(cents_float))
|
||||
if abs(cents_float - cents) >= 1e-6:
|
||||
_fail(path, "must have at most two decimal places")
|
||||
return cents
|
||||
|
||||
|
||||
def load_criteria_manifest(path: str) -> List[Dict[str, Any]]:
|
||||
"""Read the staged criteria manifest: {task, criteria: [{id, category, severity}]}.
|
||||
|
||||
Resolves each criterion's aggregation weight from its severity
|
||||
(extra_credit is always weight 1; a null/missing severity on any other
|
||||
category falls back to unlikely_dealbreaker weight 1 with a stderr
|
||||
warning). Rejects a manifest carrying more than MAX_CRUX_CRITERIA
|
||||
criteria of severity 'crux'.
|
||||
"""
|
||||
with open(path, "r", encoding="utf-8") as f:
|
||||
raw = json.load(f)
|
||||
if not isinstance(raw, dict) or not isinstance(raw.get("criteria"), list):
|
||||
raise RubricValidationError(
|
||||
"%s: must be an object with a 'criteria' array" % path
|
||||
)
|
||||
out = []
|
||||
seen = set()
|
||||
for i, entry in enumerate(raw["criteria"]):
|
||||
where = "%s: criteria[%d]" % (path, i)
|
||||
if not isinstance(entry, dict):
|
||||
raise RubricValidationError(where + ": must be an object")
|
||||
cid = entry.get("id")
|
||||
category = entry.get("category")
|
||||
severity = entry.get("severity")
|
||||
if not isinstance(cid, str) or not cid:
|
||||
raise RubricValidationError(where + ".id: must be a non-empty string")
|
||||
if not isinstance(category, str) or not category:
|
||||
raise RubricValidationError(where + ".category: must be a non-empty string")
|
||||
if severity is not None and not isinstance(severity, str):
|
||||
raise RubricValidationError(where + ".severity: must be a string or null")
|
||||
if cid in seen:
|
||||
raise RubricValidationError(where + ": duplicate id %r" % cid)
|
||||
seen.add(cid)
|
||||
if category == "extra_credit":
|
||||
weight = EXTRA_CREDIT_WEIGHT
|
||||
elif severity in SEVERITY_WEIGHTS:
|
||||
weight = SEVERITY_WEIGHTS[severity]
|
||||
else:
|
||||
if severity is None:
|
||||
reason = "has no severity"
|
||||
else:
|
||||
reason = "has unrecognized severity %r" % severity
|
||||
print(
|
||||
"render-rubric-grade: warning: criterion %r (%s) %s; "
|
||||
"treating as %s (weight %d)"
|
||||
% (cid, category, reason, DEFAULT_SEVERITY, SEVERITY_WEIGHTS[DEFAULT_SEVERITY]),
|
||||
file=sys.stderr,
|
||||
)
|
||||
weight = SEVERITY_WEIGHTS[DEFAULT_SEVERITY]
|
||||
out.append({"id": cid, "category": category, "severity": severity, "weight": weight})
|
||||
if not out:
|
||||
raise RubricValidationError("%s: criteria array is empty" % path)
|
||||
crux_ids = [c["id"] for c in out if c["severity"] == "crux"]
|
||||
if len(crux_ids) > MAX_CRUX_CRITERIA:
|
||||
raise RubricValidationError(
|
||||
"%s: %d criteria carry severity 'crux' (%s) — hard cap is %d per task"
|
||||
% (path, len(crux_ids), ", ".join(crux_ids), MAX_CRUX_CRITERIA)
|
||||
)
|
||||
return out
|
||||
|
||||
|
||||
def validate_rubric_grade(raw: Any, form: str, expected: List[Dict[str, Any]]) -> Dict[str, Any]:
|
||||
"""Validate the grader's rubric-grade.json; return normalized entries by id."""
|
||||
if not isinstance(raw, dict):
|
||||
_fail("$", "top level must be a JSON object")
|
||||
for key in raw:
|
||||
if key not in ("schema_version", "criteria", "closing", "generator"):
|
||||
_fail("$", "unknown key %r" % key)
|
||||
|
||||
version = raw.get("schema_version")
|
||||
if version != SCHEMA_VERSION or isinstance(version, bool):
|
||||
_fail("$.schema_version", "must be %d" % SCHEMA_VERSION)
|
||||
|
||||
entries_raw = raw.get("criteria")
|
||||
if not isinstance(entries_raw, list):
|
||||
_fail("$.criteria", "must be an array")
|
||||
|
||||
value_key = "verdict" if form == "trinary" else "score"
|
||||
forbidden_key = "score" if form == "trinary" else "verdict"
|
||||
|
||||
by_id: Dict[str, Dict[str, Any]] = {}
|
||||
for i, entry in enumerate(entries_raw):
|
||||
path = "$.criteria[%d]" % i
|
||||
if not isinstance(entry, dict):
|
||||
_fail(path, "must be an object")
|
||||
for key in entry:
|
||||
if key not in ("id", value_key, "rationale"):
|
||||
if key == forbidden_key:
|
||||
_fail(
|
||||
path,
|
||||
"%r does not belong in %s form output (use %r)"
|
||||
% (forbidden_key, form, value_key),
|
||||
)
|
||||
_fail(path, "unknown key %r" % key)
|
||||
cid = entry.get("id")
|
||||
if not isinstance(cid, str) or not cid:
|
||||
_fail(path + ".id", "must be a non-empty string")
|
||||
if cid in by_id:
|
||||
_fail(path + ".id", "duplicate criterion id %r" % cid)
|
||||
rationale = _validate_text(entry.get("rationale"), path + ".rationale")
|
||||
|
||||
if form == "trinary":
|
||||
verdict = entry.get(value_key)
|
||||
if verdict not in VERDICT_CENTS:
|
||||
_fail(path + ".verdict", "must be one of 'pass', 'partial', 'fail'")
|
||||
cents = VERDICT_CENTS[verdict]
|
||||
normalized = {"id": cid, "verdict": verdict, "rationale": rationale}
|
||||
else:
|
||||
if value_key not in entry:
|
||||
_fail(path, "missing required key 'score'")
|
||||
cents = _validate_score_cents(entry.get(value_key), path + ".score")
|
||||
normalized = {"id": cid, "score": entry.get(value_key), "rationale": rationale}
|
||||
normalized["_cents"] = cents
|
||||
by_id[cid] = normalized
|
||||
|
||||
expected_ids = [c["id"] for c in expected]
|
||||
missing = [cid for cid in expected_ids if cid not in by_id]
|
||||
unknown = [cid for cid in by_id if cid not in set(expected_ids)]
|
||||
if missing:
|
||||
_fail("$.criteria", "missing criterion id(s): %s" % ", ".join(sorted(missing)))
|
||||
if unknown:
|
||||
_fail("$.criteria", "unknown criterion id(s): %s" % ", ".join(sorted(unknown)))
|
||||
|
||||
closing = raw.get("closing")
|
||||
if closing is not None:
|
||||
closing = _validate_text(closing, "$.closing")
|
||||
|
||||
return {"by_id": by_id, "closing": closing}
|
||||
|
||||
|
||||
def _round_half_up(p: int, q: int) -> int:
|
||||
"""round_half_up(p/q) for q > 0, p >= 0 — exact integer arithmetic."""
|
||||
return (2 * p + q) // (2 * q)
|
||||
|
||||
|
||||
def aggregate(grade: Dict[str, Any], expected: List[Dict[str, Any]]) -> Dict[str, Any]:
|
||||
"""Severity-weighted mean over criteria in cents.
|
||||
|
||||
reward_cents = round_half_up(sum(weight_i * cents_i) / sum(weight_i))
|
||||
over included criteria. extra_credit (weight 1) is included only when its
|
||||
value is > 0; every other criterion is always included at its severity
|
||||
weight.
|
||||
"""
|
||||
weighted_cents = 0
|
||||
total_weight = 0
|
||||
n_included = 0
|
||||
excluded_extra_credit = 0
|
||||
for criterion in expected:
|
||||
entry = grade["by_id"][criterion["id"]]
|
||||
if criterion["category"] == "extra_credit" and entry["_cents"] == 0:
|
||||
excluded_extra_credit += 1
|
||||
continue
|
||||
n_included += 1
|
||||
weighted_cents += criterion["weight"] * entry["_cents"]
|
||||
total_weight += criterion["weight"]
|
||||
if total_weight:
|
||||
reward_cents = _round_half_up(weighted_cents, total_weight)
|
||||
else:
|
||||
reward_cents = 0
|
||||
return {
|
||||
"n_included": n_included,
|
||||
"n_excluded_extra_credit": excluded_extra_credit,
|
||||
"total_weight": total_weight,
|
||||
"reward_cents": reward_cents,
|
||||
}
|
||||
|
||||
|
||||
def _fmt(cents: int) -> str:
|
||||
return "%.2f" % (cents / 100.0)
|
||||
|
||||
|
||||
def render_markdown(
|
||||
grade: Dict[str, Any],
|
||||
agg: Dict[str, Any],
|
||||
expected: List[Dict[str, Any]],
|
||||
form: str,
|
||||
) -> str:
|
||||
excluded = agg["n_excluded_extra_credit"]
|
||||
detail = "severity-weighted mean over %d criteria; weights %s" % (
|
||||
agg["n_included"],
|
||||
WEIGHTS_NOTE,
|
||||
)
|
||||
if excluded:
|
||||
detail += "; %d unfulfilled extra-credit criteri%s excluded" % (
|
||||
excluded,
|
||||
"on" if excluded == 1 else "a",
|
||||
)
|
||||
sections = ["Rubric score (%s): %s (%s)" % (form, _fmt(agg["reward_cents"]), detail)]
|
||||
|
||||
for criterion in expected:
|
||||
entry = grade["by_id"][criterion["id"]]
|
||||
if form == "trinary":
|
||||
shown = entry["verdict"].upper()
|
||||
else:
|
||||
shown = _fmt(entry["_cents"])
|
||||
label = criterion["id"]
|
||||
if criterion["category"] == "extra_credit":
|
||||
label += " (extra credit)"
|
||||
sections.append("## %s — %s\n\n%s" % (label, shown, entry["rationale"]))
|
||||
|
||||
if grade["closing"]:
|
||||
sections.append("## Closing\n\n%s" % grade["closing"])
|
||||
|
||||
return "\n\n".join(sections) + "\n"
|
||||
|
||||
|
||||
def normalized_json(grade: Dict[str, Any], expected: List[Dict[str, Any]], form: str) -> str:
|
||||
def entry(cid: str) -> Dict[str, Any]:
|
||||
e = grade["by_id"][cid]
|
||||
out = {"id": e["id"], "rationale": e["rationale"]}
|
||||
if form == "trinary":
|
||||
out["verdict"] = e["verdict"]
|
||||
else:
|
||||
out["score"] = e["score"]
|
||||
return out
|
||||
|
||||
out = {
|
||||
"schema_version": SCHEMA_VERSION,
|
||||
"form": form,
|
||||
"criteria": [entry(c["id"]) for c in expected],
|
||||
"closing": grade["closing"],
|
||||
"generator": {"kind": "grader", "version": RENDER_RUBRIC_GRADE_VERSION},
|
||||
}
|
||||
return json.dumps(out, indent=2, ensure_ascii=False) + "\n"
|
||||
|
||||
|
||||
def main() -> int:
|
||||
parser = argparse.ArgumentParser(
|
||||
description="Render grade.md + reward.txt from rubric-grade.json"
|
||||
)
|
||||
parser.add_argument("--rubric-json", default="/logs/verifier/rubric-grade.json")
|
||||
parser.add_argument("--criteria", required=True, help="staged rubric-criteria.json")
|
||||
parser.add_argument("--form", required=True, choices=FORMS)
|
||||
parser.add_argument("--out-dir", default="/logs/verifier")
|
||||
parser.add_argument("--version", action="version", version=RENDER_RUBRIC_GRADE_VERSION)
|
||||
args = parser.parse_args()
|
||||
|
||||
try:
|
||||
expected = load_criteria_manifest(args.criteria)
|
||||
except (OSError, ValueError, RubricValidationError) as e:
|
||||
print("render-rubric-grade: bad criteria manifest: %s" % e, file=sys.stderr)
|
||||
return 2
|
||||
|
||||
try:
|
||||
with open(args.rubric_json, "r", encoding="utf-8") as f:
|
||||
raw = json.load(f)
|
||||
except OSError as e:
|
||||
print("render-rubric-grade: cannot read %s: %s" % (args.rubric_json, e), file=sys.stderr)
|
||||
return 2
|
||||
except ValueError as e:
|
||||
print(
|
||||
"render-rubric-grade: %s is not valid JSON: %s" % (args.rubric_json, e),
|
||||
file=sys.stderr,
|
||||
)
|
||||
return 2
|
||||
|
||||
try:
|
||||
grade = validate_rubric_grade(raw, args.form, expected)
|
||||
agg = aggregate(grade, expected)
|
||||
except RubricValidationError as e:
|
||||
print("render-rubric-grade: invalid rubric-grade.json: %s" % e, file=sys.stderr)
|
||||
return 2
|
||||
|
||||
markdown = render_markdown(grade, agg, expected, args.form)
|
||||
reward = _fmt(agg["reward_cents"])
|
||||
|
||||
os.makedirs(args.out_dir, exist_ok=True)
|
||||
with open(os.path.join(args.out_dir, "grade.md"), "w", encoding="utf-8") as f:
|
||||
f.write(markdown)
|
||||
with open(os.path.join(args.out_dir, "reward.txt"), "w", encoding="utf-8") as f:
|
||||
f.write(reward + "\n")
|
||||
with open(os.path.join(args.out_dir, "rubric-grade.json"), "w", encoding="utf-8") as f:
|
||||
f.write(normalized_json(grade, expected, args.form))
|
||||
|
||||
print(
|
||||
"render-rubric-grade: ok reward=%s form=%s criteria=%d excluded_extra_credit=%d total_weight=%d"
|
||||
% (reward, args.form, agg["n_included"], agg["n_excluded_extra_credit"], agg["total_weight"])
|
||||
)
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
sys.exit(main())
|
||||
Reference in New Issue
Block a user