353 lines
12 KiB
Python
353 lines
12 KiB
Python
#!/usr/bin/env python3
|
||
"""render-grade-consolidated.py — validate the grade.json schema and derive grade files.
|
||
|
||
Runs inside the task container after each grader sample. The grader writes
|
||
/logs/verifier/grade.json with EIGHT
|
||
criterion entries (no separate correctness entry — correctness lives inside the
|
||
standard as narrow_correctness / broader_correctness); this script:
|
||
|
||
1. validates the shape (strict: unknown keys, missing criteria, non-2dp
|
||
scores, empty rationales all fail),
|
||
2. renders grade.md from it,
|
||
3. derives reward.txt (mean of non-N/A criteria, minus overall penalties,
|
||
floored at 0) and writes reward-correctness.txt as N/A so the shared
|
||
test.sh sample loop records a clean N/A instead of warning,
|
||
4. rewrites grade.json in normalized form (defaults filled, generator stamp).
|
||
|
||
Exit codes: 0 = ok; 2 = grade.json missing/unparseable/invalid (the caller
|
||
treats that grader sample as invalid). Never writes partial output.
|
||
|
||
Selected by the shared tests/test.sh for the agentic and one-shot grader
|
||
modes. Stdlib-only and Python 3.8-compatible.
|
||
|
||
Usage:
|
||
python3 render-grade-consolidated.py [--grade-json /logs/verifier/grade.json] \
|
||
[--out-dir /logs/verifier]
|
||
"""
|
||
|
||
import argparse
|
||
import json
|
||
import os
|
||
import sys
|
||
from typing import Any, Dict, List, Optional
|
||
|
||
RENDER_GRADE_VERSION = "render-grade-consolidated/0.2.0"
|
||
SCHEMA_VERSION = 1
|
||
|
||
CRITERION_KEYS = [
|
||
"integrity",
|
||
"narrow_correctness",
|
||
"broader_correctness",
|
||
"persistence",
|
||
"communication",
|
||
"verification_thoroughness",
|
||
"common_sense",
|
||
"thought_partnership",
|
||
]
|
||
|
||
CRITERION_DISPLAY_NAMES = {
|
||
"integrity": "Integrity",
|
||
"narrow_correctness": "Narrow Correctness",
|
||
"broader_correctness": "Broader Correctness / craft",
|
||
"persistence": "Persistence",
|
||
"communication": "Communication",
|
||
"verification_thoroughness": "Verification & Thoroughness",
|
||
"common_sense": "Common Sense",
|
||
"thought_partnership": "Thought Partnership",
|
||
}
|
||
|
||
|
||
class GradeValidationError(Exception):
|
||
"""A shape/content problem in grade.json. Message names the bad path."""
|
||
|
||
|
||
def _fail(path: str, message: str) -> None:
|
||
raise GradeValidationError("%s: %s" % (path, message))
|
||
|
||
|
||
def _require_keys(obj: Dict[str, Any], allowed: List[str], required: List[str], path: str) -> None:
|
||
for key in obj:
|
||
if key not in allowed:
|
||
_fail(path, "unknown key %r" % key)
|
||
for key in required:
|
||
if key not in obj:
|
||
_fail(path, "missing required key %r" % key)
|
||
|
||
|
||
def _validate_score(value: Any, path: str, allow_null: bool = True) -> Optional[int]:
|
||
"""Return integer cents, or None for a null (N/A) score."""
|
||
if value is None:
|
||
if not allow_null:
|
||
_fail(path, "must not be null")
|
||
return None
|
||
if isinstance(value, bool) or not isinstance(value, (int, float)):
|
||
_fail(path, "must be a number (or null)")
|
||
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 _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_criterion_entry(value: Any, path: str) -> Dict[str, Any]:
|
||
if not isinstance(value, dict):
|
||
_fail(path, "must be an object {score, rationale}")
|
||
_require_keys(value, ["score", "rationale"], ["score", "rationale"], path)
|
||
cents = _validate_score(value.get("score"), path + ".score")
|
||
rationale = _validate_text(value.get("rationale"), path + ".rationale")
|
||
return {"score": value.get("score"), "rationale": rationale, "_cents": cents}
|
||
|
||
|
||
def validate_grade(raw: Any) -> Dict[str, Any]:
|
||
"""Validate the full grader-output shape; return a normalized dict."""
|
||
if not isinstance(raw, dict):
|
||
_fail("$", "top level must be a JSON object")
|
||
|
||
_require_keys(
|
||
raw,
|
||
[
|
||
"schema_version",
|
||
"criteria",
|
||
"overall_penalties",
|
||
"overall_score",
|
||
"closing",
|
||
"generator",
|
||
],
|
||
["schema_version", "criteria"],
|
||
"$",
|
||
)
|
||
|
||
version = raw.get("schema_version")
|
||
version_ok = version == SCHEMA_VERSION and not isinstance(version, bool)
|
||
if not version_ok:
|
||
_fail("$.schema_version", "must be %d" % SCHEMA_VERSION)
|
||
|
||
criteria_raw = raw.get("criteria")
|
||
if not isinstance(criteria_raw, dict):
|
||
_fail("$.criteria", "must be an object with the eight criterion keys")
|
||
_require_keys(criteria_raw, CRITERION_KEYS, CRITERION_KEYS, "$.criteria")
|
||
criteria = {}
|
||
for key in CRITERION_KEYS:
|
||
criteria[key] = _validate_criterion_entry(criteria_raw[key], "$.criteria.%s" % key)
|
||
|
||
def _entry_array(key: str) -> List[Any]:
|
||
# An absent key becomes []; an explicit null (or any non-array) is an error.
|
||
if key not in raw:
|
||
return []
|
||
value = raw[key]
|
||
if not isinstance(value, list):
|
||
_fail("$.%s" % key, "must be an array")
|
||
return value
|
||
|
||
penalties = []
|
||
for i, entry in enumerate(_entry_array("overall_penalties")):
|
||
path = "$.overall_penalties[%d]" % i
|
||
if not isinstance(entry, dict):
|
||
_fail(path, "must be an object {amount, reason}")
|
||
_require_keys(entry, ["amount", "reason"], ["amount", "reason"], path)
|
||
cents = _validate_score(entry.get("amount"), path + ".amount", allow_null=False)
|
||
if cents is not None and cents <= 0:
|
||
_fail(path + ".amount", "must be > 0")
|
||
reason = _validate_text(entry.get("reason"), path + ".reason")
|
||
penalties.append({"amount": entry.get("amount"), "reason": reason, "_cents": cents})
|
||
|
||
if raw.get("overall_score") is None:
|
||
_fail("$.overall_score", "holistic overall_score is required for grader output")
|
||
overall_cents = _validate_score(raw.get("overall_score"), "$.overall_score", allow_null=False)
|
||
|
||
closing = raw.get("closing")
|
||
if closing is not None:
|
||
closing = _validate_text(closing, "$.closing")
|
||
|
||
generator = raw.get("generator")
|
||
if generator is not None:
|
||
if not isinstance(generator, dict):
|
||
_fail("$.generator", "must be an object {kind, version}")
|
||
_require_keys(
|
||
generator, ["kind", "version", "source_format"], ["kind", "version"], "$.generator"
|
||
)
|
||
if generator.get("kind") not in ("grader", "backfill"):
|
||
_fail("$.generator.kind", "must be 'grader' or 'backfill'")
|
||
_validate_text(generator.get("version"), "$.generator.version")
|
||
if "source_format" in generator:
|
||
_validate_text(generator.get("source_format"), "$.generator.source_format")
|
||
|
||
return {
|
||
"criteria": criteria,
|
||
"overall_penalties": penalties,
|
||
"overall_score": raw.get("overall_score"),
|
||
"_overall_cents": overall_cents,
|
||
"closing": closing,
|
||
"generator": generator,
|
||
}
|
||
|
||
|
||
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]) -> Dict[str, Any]:
|
||
"""Mean of non-N/A criteria − penalties, floored at 0. Integer cents."""
|
||
scored = [c["_cents"] for c in grade["criteria"].values() if c["_cents"] is not None]
|
||
if not scored:
|
||
raise GradeValidationError(
|
||
"$.criteria: all eight criteria are N/A — nothing to aggregate"
|
||
)
|
||
n = len(scored)
|
||
total = sum(scored)
|
||
penalty_cents = sum(p["_cents"] for p in grade["overall_penalties"])
|
||
mean_cents = _round_half_up(total, n)
|
||
|
||
num = total - n * penalty_cents
|
||
if num < 0:
|
||
num = 0
|
||
reward_cents = _round_half_up(num, n)
|
||
|
||
return {
|
||
"n_scored": n,
|
||
"mean_cents": mean_cents,
|
||
"penalty_cents": penalty_cents,
|
||
"reward_cents": reward_cents,
|
||
}
|
||
|
||
|
||
def _fmt(cents: int) -> str:
|
||
return "%.2f" % (cents / 100.0)
|
||
|
||
|
||
def score_line(grade: Dict[str, Any], agg: Dict[str, Any]) -> str:
|
||
reward = _fmt(agg["reward_cents"])
|
||
n = agg["n_scored"]
|
||
if agg["penalty_cents"] > 0:
|
||
label = (
|
||
"overall heavy penalty"
|
||
if len(grade["overall_penalties"]) == 1
|
||
else "overall heavy penalties"
|
||
)
|
||
detail = "mean %s of %d non-N/A criteria - %s %s" % (
|
||
_fmt(agg["mean_cents"]),
|
||
n,
|
||
_fmt(agg["penalty_cents"]),
|
||
label,
|
||
)
|
||
else:
|
||
detail = "mean of %d non-N/A criteria" % n
|
||
return "Score: %s (%s)" % (reward, detail)
|
||
|
||
|
||
def render_markdown(grade: Dict[str, Any], agg: Dict[str, Any]) -> str:
|
||
sections = [
|
||
"%s\nHolistic overall (grader-stated): %s\nStandard: 8 criteria"
|
||
% (score_line(grade, agg), _fmt(grade["_overall_cents"]))
|
||
]
|
||
|
||
for key in CRITERION_KEYS:
|
||
entry = grade["criteria"][key]
|
||
shown = "N/A" if entry["_cents"] is None else _fmt(entry["_cents"])
|
||
sections.append(
|
||
"## %s — %s\n\n%s" % (CRITERION_DISPLAY_NAMES[key], shown, entry["rationale"])
|
||
)
|
||
|
||
if grade["overall_penalties"]:
|
||
bullets = "\n".join(
|
||
"- %s — %s" % (_fmt(p["_cents"]), p["reason"]) for p in grade["overall_penalties"]
|
||
)
|
||
sections.append("## Overall penalties\n\n%s" % bullets)
|
||
|
||
if grade["closing"]:
|
||
sections.append("## Closing\n\n%s" % grade["closing"])
|
||
|
||
return "\n\n".join(sections) + "\n"
|
||
|
||
|
||
def normalized_json(grade: Dict[str, Any]) -> str:
|
||
def entry(e: Dict[str, Any]) -> Dict[str, Any]:
|
||
return {"score": e["score"], "rationale": e["rationale"]}
|
||
|
||
generator = grade["generator"] or {"kind": "grader", "version": RENDER_GRADE_VERSION}
|
||
out = {
|
||
"schema_version": SCHEMA_VERSION,
|
||
"criteria": {key: entry(grade["criteria"][key]) for key in CRITERION_KEYS},
|
||
"overall_penalties": [
|
||
{"amount": p["amount"], "reason": p["reason"]} for p in grade["overall_penalties"]
|
||
],
|
||
"overall_score": grade["overall_score"],
|
||
"closing": grade["closing"],
|
||
"generator": generator,
|
||
}
|
||
return json.dumps(out, indent=2, ensure_ascii=False) + "\n"
|
||
|
||
|
||
def main() -> int:
|
||
parser = argparse.ArgumentParser(
|
||
description="Render grade.md + rewards from the structured grade.json"
|
||
)
|
||
parser.add_argument("--grade-json", default="/logs/verifier/grade.json")
|
||
parser.add_argument("--out-dir", default="/logs/verifier")
|
||
parser.add_argument("--version", action="version", version=RENDER_GRADE_VERSION)
|
||
args = parser.parse_args()
|
||
|
||
try:
|
||
with open(args.grade_json, "r", encoding="utf-8") as f:
|
||
raw = json.load(f)
|
||
except OSError as e:
|
||
print(
|
||
"render-grade-consolidated: cannot read %s: %s" % (args.grade_json, e),
|
||
file=sys.stderr,
|
||
)
|
||
return 2
|
||
except ValueError as e:
|
||
print(
|
||
"render-grade-consolidated: %s is not valid JSON: %s" % (args.grade_json, e),
|
||
file=sys.stderr,
|
||
)
|
||
return 2
|
||
|
||
try:
|
||
grade = validate_grade(raw)
|
||
agg = aggregate(grade)
|
||
except GradeValidationError as e:
|
||
print("render-grade-consolidated: invalid grade.json: %s" % e, file=sys.stderr)
|
||
return 2
|
||
|
||
markdown = render_markdown(grade, agg)
|
||
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")
|
||
# The shared test.sh sample loop looks for reward-correctness.txt; under the
|
||
# grading standard correctness lives inside the criteria, so record an
|
||
# explicit N/A (matches test.sh's `^n/?a$` recognizer) rather than leaving
|
||
# a warning.
|
||
with open(os.path.join(args.out_dir, "reward-correctness.txt"), "w", encoding="utf-8") as f:
|
||
f.write("N/A\n")
|
||
with open(os.path.join(args.out_dir, "grade.json"), "w", encoding="utf-8") as f:
|
||
f.write(normalized_json(grade))
|
||
|
||
print(
|
||
"render-grade-consolidated: ok reward=%s criteria_scored=%d"
|
||
% (reward, agg["n_scored"])
|
||
)
|
||
if grade["_overall_cents"] is not None and grade["_overall_cents"] != agg["reward_cents"]:
|
||
print(
|
||
"render-grade-consolidated: note grader-stated overall %s differs from derived %s"
|
||
% (_fmt(grade["_overall_cents"]), reward)
|
||
)
|
||
return 0
|
||
|
||
|
||
if __name__ == "__main__":
|
||
sys.exit(main())
|