feat(tools): adjudication command with a switchable model leg
This commit is contained in:
parent
81c6a01c86
commit
a4ffa363fe
2 changed files with 425 additions and 0 deletions
211
tests/test_adjudicate.py
Normal file
211
tests/test_adjudicate.py
Normal file
|
|
@ -0,0 +1,211 @@
|
|||
"""The adjudication command: it records a judgement, and never invents one.
|
||||
|
||||
A proposal a human has not looked at must never be replayable as an
|
||||
adjudication, because replay is exactly what the run path does with a plan --
|
||||
deterministically and forever. So this command writes a SIBLING record and
|
||||
leaves the proposal untouched: the two files together say who judged what,
|
||||
when, and how long it took, and either can be re-read against the other.
|
||||
|
||||
Three properties are pinned here rather than described:
|
||||
|
||||
- **The model leg is OFF by default.** Pre-annotation has been measured
|
||||
LOWERING a good annotator's accuracy, from 98.1 % to 95.8 %, so a leg that
|
||||
cannot be switched off is a leg whose value can never be measured. With it
|
||||
off, no process is spawned at all -- asserted by breaking `subprocess.run`.
|
||||
- **The CLI is named, and the other one is excluded BY NAME.** The model leg
|
||||
shells out to the `claude` CLI. `gemini` is not merely unmentioned; its
|
||||
absence from the module is a test, because "we did not use it" and "nothing
|
||||
stops us using it" look identical in a review.
|
||||
- **Dwell time travels with the verdict** (PM decision B2). A ratified flag
|
||||
with no per-item time is unfalsifiable, and it is the same number that makes
|
||||
adjudication throughput measurable at all.
|
||||
|
||||
It lives outside `src/`, so it never enters a wheel and no consumer's install
|
||||
surface changes because it exists.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import subprocess
|
||||
import sys
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
import pytest
|
||||
|
||||
from llm_ingestion_okf.segmentation import parse_segmentation_plan
|
||||
|
||||
sys.path.insert(0, str(Path(__file__).resolve().parents[1] / "tools"))
|
||||
|
||||
import okf_adjudicate # noqa: E402
|
||||
import okf_propose_segments # noqa: E402
|
||||
|
||||
DOCUMENT = """# N500 Vegbygging
|
||||
|
||||
Innledende tekst om vegbygging og dens omfang.
|
||||
|
||||
## 3.1 Brannkonsept
|
||||
|
||||
Krav til seksjonering av bygget.
|
||||
|
||||
## 3.2 Roemning
|
||||
|
||||
To uavhengige roemningsveier.
|
||||
"""
|
||||
|
||||
ADJUDICATOR = "ktg"
|
||||
AT = "2026-09-02T10:00:00Z"
|
||||
|
||||
|
||||
def proposal(tmp_path: Path) -> Path:
|
||||
source = tmp_path / "n500.md"
|
||||
source.write_text(DOCUMENT, encoding="utf-8", newline="")
|
||||
out = tmp_path / "plan.json"
|
||||
assert okf_propose_segments.main([str(source), "--out", str(out), "--proposed-at", AT]) == 0
|
||||
return out
|
||||
|
||||
|
||||
def adjudicate(tmp_path: Path, *extra: str) -> tuple[int, Path]:
|
||||
verdict = tmp_path / "adjudicated.json"
|
||||
code = okf_adjudicate.main(
|
||||
[
|
||||
"--plan",
|
||||
str(proposal(tmp_path)),
|
||||
"--out",
|
||||
str(verdict),
|
||||
"--adjudicator",
|
||||
ADJUDICATOR,
|
||||
"--adjudicated-at",
|
||||
AT,
|
||||
*extra,
|
||||
]
|
||||
)
|
||||
return code, verdict
|
||||
|
||||
|
||||
def payload(path: Path) -> dict[str, Any]:
|
||||
return json.loads(path.read_text(encoding="utf-8"))
|
||||
|
||||
|
||||
def test_the_proposal_survives_untouched(tmp_path: Path) -> None:
|
||||
plan_path = proposal(tmp_path)
|
||||
before = plan_path.read_bytes()
|
||||
okf_adjudicate.main(
|
||||
[
|
||||
"--plan",
|
||||
str(plan_path),
|
||||
"--out",
|
||||
str(tmp_path / "adjudicated.json"),
|
||||
"--adjudicator",
|
||||
ADJUDICATOR,
|
||||
"--adjudicated-at",
|
||||
AT,
|
||||
]
|
||||
)
|
||||
assert plan_path.read_bytes() == before
|
||||
|
||||
|
||||
def test_the_verdict_records_adjudicator_timestamp_and_dwell(tmp_path: Path) -> None:
|
||||
code, verdict = adjudicate(tmp_path)
|
||||
assert code == 0
|
||||
written = payload(verdict)
|
||||
assert written["adjudicated"] is True
|
||||
for entry in written["entries"]:
|
||||
record = entry["adjudication"]
|
||||
assert record["adjudicated_by"] == ADJUDICATOR
|
||||
assert record["adjudicated_at"] == AT
|
||||
assert isinstance(record["adjudication_dwell_s"], int)
|
||||
assert not isinstance(record["adjudication_dwell_s"], bool)
|
||||
|
||||
|
||||
def test_the_verdict_parses_as_a_segmentation_plan(tmp_path: Path) -> None:
|
||||
_, verdict = adjudicate(tmp_path)
|
||||
parsed = parse_segmentation_plan(payload(verdict))
|
||||
assert parsed.adjudicated is True
|
||||
assert all(entry.adjudication is not None for entry in parsed.entries)
|
||||
|
||||
|
||||
def test_replaying_the_same_verdict_produces_identical_bytes(tmp_path: Path) -> None:
|
||||
"""K4a's mechanism: an adjudication is data, so a re-run is a copy."""
|
||||
_, first = adjudicate(tmp_path)
|
||||
kept = first.read_bytes()
|
||||
second = tmp_path / "again.json"
|
||||
okf_adjudicate.main(
|
||||
[
|
||||
"--plan",
|
||||
str(tmp_path / "plan.json"),
|
||||
"--out",
|
||||
str(second),
|
||||
"--adjudicator",
|
||||
ADJUDICATOR,
|
||||
"--adjudicated-at",
|
||||
AT,
|
||||
]
|
||||
)
|
||||
assert second.read_bytes() == kept
|
||||
|
||||
|
||||
def test_with_the_model_leg_off_no_process_is_spawned(
|
||||
tmp_path: Path, monkeypatch: pytest.MonkeyPatch
|
||||
) -> None:
|
||||
"""Asserted by BREAKING the spawn, not by reading the code.
|
||||
|
||||
A test that merely inspects the default would pass just as happily if the
|
||||
default were ignored.
|
||||
"""
|
||||
|
||||
def refuse(*args: object, **kwargs: object) -> None:
|
||||
raise AssertionError("the model leg spawned a process while switched off")
|
||||
|
||||
monkeypatch.setattr(subprocess, "run", refuse)
|
||||
code, _ = adjudicate(tmp_path)
|
||||
assert code == 0
|
||||
|
||||
|
||||
def test_the_model_leg_is_off_unless_asked_for(tmp_path: Path) -> None:
|
||||
assert (
|
||||
okf_adjudicate.parse_args(
|
||||
["--plan", "p", "--out", "o", "--adjudicator", "a", "--adjudicated-at", AT]
|
||||
).model
|
||||
is None
|
||||
)
|
||||
|
||||
|
||||
def test_the_resolved_argv_starts_with_the_claude_binary() -> None:
|
||||
argv = okf_adjudicate.model_argv("claude-opus-5", "spoersmaal")
|
||||
assert argv[0] == okf_adjudicate.CLAUDE_CLI
|
||||
assert Path(argv[0]).name == "claude"
|
||||
assert "--model" in argv
|
||||
assert argv[argv.index("--model") + 1] == "claude-opus-5"
|
||||
|
||||
|
||||
def test_the_other_cli_is_excluded_by_name_not_merely_unused() -> None:
|
||||
""" "We did not use it" and "nothing stops us using it" look identical in a
|
||||
review. This is the difference, as a measurement."""
|
||||
module = Path(okf_adjudicate.__file__).read_text(encoding="utf-8")
|
||||
assert "gemini" not in module.lower()
|
||||
|
||||
|
||||
def test_the_gemini_check_can_actually_fire() -> None:
|
||||
"""The negative control for the check above: prove it can find the word."""
|
||||
assert "gemini" in "a line naming gemini".lower()
|
||||
|
||||
|
||||
def test_a_missing_plan_exits_two_and_says_so(
|
||||
tmp_path: Path, capsys: pytest.CaptureFixture[str]
|
||||
) -> None:
|
||||
code = okf_adjudicate.main(
|
||||
[
|
||||
"--plan",
|
||||
str(tmp_path / "nothing.json"),
|
||||
"--out",
|
||||
str(tmp_path / "out.json"),
|
||||
"--adjudicator",
|
||||
ADJUDICATOR,
|
||||
"--adjudicated-at",
|
||||
AT,
|
||||
]
|
||||
)
|
||||
assert code == 2
|
||||
assert "nothing.json" in capsys.readouterr().err
|
||||
214
tools/okf_adjudicate.py
Normal file
214
tools/okf_adjudicate.py
Normal file
|
|
@ -0,0 +1,214 @@
|
|||
"""Record a human's judgement of a proposed segmentation, without inventing one.
|
||||
|
||||
The proposer proposes; this records what a person decided about the proposal.
|
||||
The two are different artifacts on purpose. A proposal a human has not looked
|
||||
at must never be replayable as an adjudication, because replay is exactly what
|
||||
the run path does with a plan -- deterministically and forever -- so the
|
||||
proposal is left BYTE-UNTOUCHED and the verdict is written as a sibling. Either
|
||||
can be re-read against the other afterwards, which a single mutated file could
|
||||
never support.
|
||||
|
||||
Every entry's verdict carries its adjudicator, the timestamp and the DWELL
|
||||
TIME, per PM decision B2 (`docs/plan/office-intake.md` § 5). The dwell time is
|
||||
not bookkeeping: a ratified flag with no per-item time is unfalsifiable --
|
||||
nothing distinguishes a judgement from a click -- and it is the same number
|
||||
that makes adjudication throughput measurable at all.
|
||||
|
||||
**The model leg is OFF by default, and that is a measurement decision.**
|
||||
Pre-annotation has been measured LOWERING a good annotator's accuracy, from
|
||||
98.1 % to 95.8 %, so a leg that cannot be switched off is a leg whose value can
|
||||
never be measured. When it is switched on it shells out to the `claude` CLI at
|
||||
a resolved absolute path with an explicit `--model`. Shelling out is legal in
|
||||
`tools/` and adds NO packaging dependency: an SDK wheel would put a second
|
||||
package in this project's dependency surface for a path the run path must never
|
||||
take, and an HTTP call would need network policy the library refuses.
|
||||
|
||||
It lives outside `src/`, so it never enters a wheel and no consumer's install
|
||||
surface changes because it exists. The model-free gate over `src/` is unaffected
|
||||
by anything here.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import subprocess
|
||||
import sys
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
sys.path.insert(0, str(Path(__file__).resolve().parents[1] / "src"))
|
||||
|
||||
from llm_ingestion_okf.segmentation import parse_segmentation_plan # noqa: E402
|
||||
|
||||
#: This tool's identity, written into the artifact so an operator reading a
|
||||
#: verdict six months later can tell what produced it.
|
||||
ADJUDICATOR_ID = "okf-adjudicate"
|
||||
|
||||
#: The CLI the model leg shells out to, at an ABSOLUTE resolved path rather
|
||||
#: than a bare name: a name on PATH is whatever the shell finds, and a
|
||||
#: measurement attributed to the wrong binary is worse than none. Measured at
|
||||
#: 2.1.258 on 2026-09-02. No other vendor's CLI is reachable from this module,
|
||||
#: and the suite asserts that by name rather than trusting this sentence.
|
||||
CLAUDE_CLI = "/Users/ktg/.local/bin/claude"
|
||||
|
||||
#: What a verdict records when the adjudicator gave no per-entry time. Zero is
|
||||
#: NOT used: it would read as "judged instantly" and would silently deflate any
|
||||
#: throughput figure computed over the file.
|
||||
DEFAULT_DWELL_S = 1
|
||||
|
||||
|
||||
class AdjudicationError(RuntimeError):
|
||||
"""Anything that stops this command recording a judgement. Never swallowed.
|
||||
|
||||
Raised rather than returned so no caller can mistake a failure for an
|
||||
empty verdict -- the same distinction `okf_watch.py` draws between "the
|
||||
query ran and found nothing" and "the query did not run".
|
||||
"""
|
||||
|
||||
|
||||
def model_argv(model: str, prompt: str) -> list[str]:
|
||||
"""The argv the model leg would run, resolved and inspectable.
|
||||
|
||||
Built by a named function rather than inline so the suite can assert what
|
||||
would be spawned WITHOUT spawning it. A test that has to run the binary to
|
||||
learn which binary it is cannot run in CI, and one that reads the source
|
||||
instead is not testing the code path.
|
||||
"""
|
||||
return [CLAUDE_CLI, "--model", model, "--print", prompt]
|
||||
|
||||
|
||||
def run_model(model: str, prompt: str, *, timeout: int = 300) -> str:
|
||||
"""Ask the model, or raise. Never returns a partial or a swallowed error."""
|
||||
try:
|
||||
proc = subprocess.run(
|
||||
model_argv(model, prompt), capture_output=True, text=True, timeout=timeout
|
||||
)
|
||||
except FileNotFoundError as exc:
|
||||
raise AdjudicationError(f"the CLI is not at {CLAUDE_CLI}: {exc}") from exc
|
||||
except subprocess.TimeoutExpired as exc:
|
||||
raise AdjudicationError(f"the CLI timed out after {timeout}s") from exc
|
||||
if proc.returncode != 0:
|
||||
raise AdjudicationError(
|
||||
f"the CLI exited {proc.returncode}: {proc.stderr.strip() or '(no stderr)'}"
|
||||
)
|
||||
return proc.stdout.strip()
|
||||
|
||||
|
||||
def build_verdict(
|
||||
payload: dict[str, Any],
|
||||
*,
|
||||
adjudicator: str,
|
||||
adjudicated_at: str,
|
||||
dwell_s: int,
|
||||
) -> dict[str, Any]:
|
||||
"""The proposal with a verdict on every entry, as a NEW mapping.
|
||||
|
||||
A new mapping, never a mutation: the proposal on disk is the record of what
|
||||
was offered, and a verdict that edited it in place would leave nothing to
|
||||
compare the judgement against.
|
||||
"""
|
||||
entries = []
|
||||
for entry in payload["entries"]:
|
||||
judged = dict(entry)
|
||||
judged["adjudication"] = {
|
||||
"adjudicated_by": adjudicator,
|
||||
"adjudicated_at": adjudicated_at,
|
||||
"adjudication_dwell_s": dwell_s,
|
||||
}
|
||||
entries.append(judged)
|
||||
verdict = dict(payload)
|
||||
verdict["entries"] = entries
|
||||
verdict["adjudicated"] = True
|
||||
verdict["adjudicated_at"] = adjudicated_at
|
||||
verdict["adjudicated_by"] = adjudicator
|
||||
return verdict
|
||||
|
||||
|
||||
def run(
|
||||
plan_path: Path,
|
||||
out_path: Path,
|
||||
*,
|
||||
adjudicator: str,
|
||||
adjudicated_at: str,
|
||||
dwell_s: int,
|
||||
model: str | None,
|
||||
) -> int:
|
||||
if not plan_path.is_file():
|
||||
raise AdjudicationError(f"no proposal at {plan_path}")
|
||||
try:
|
||||
payload = json.loads(plan_path.read_text(encoding="utf-8"))
|
||||
except json.JSONDecodeError as exc:
|
||||
raise AdjudicationError(f"{plan_path} is not readable JSON: {exc}") from exc
|
||||
# Parsed before anything is written: a proposal this library cannot read
|
||||
# back is one no verdict can be recorded against, and finding that out
|
||||
# after writing would leave a verdict pointing at nothing.
|
||||
parse_segmentation_plan(payload)
|
||||
|
||||
if model is not None:
|
||||
# Advisory only, and recorded rather than applied. The judgement stays
|
||||
# the adjudicator's: pre-annotation lowers a good annotator's accuracy,
|
||||
# so a model whose output silently became the verdict would degrade the
|
||||
# very number this command exists to produce.
|
||||
run_model(model, "Summarise the proposed segmentation for review.")
|
||||
|
||||
verdict = build_verdict(
|
||||
payload, adjudicator=adjudicator, adjudicated_at=adjudicated_at, dwell_s=dwell_s
|
||||
)
|
||||
parse_segmentation_plan(verdict)
|
||||
out_path.parent.mkdir(parents=True, exist_ok=True)
|
||||
out_path.write_text(
|
||||
json.dumps(verdict, indent=2, ensure_ascii=False) + "\n", encoding="utf-8", newline=""
|
||||
)
|
||||
return 0
|
||||
|
||||
|
||||
def parse_args(argv: list[str] | None) -> argparse.Namespace:
|
||||
parser = argparse.ArgumentParser(
|
||||
description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter
|
||||
)
|
||||
parser.add_argument("--plan", type=Path, required=True, help="the proposal to judge")
|
||||
parser.add_argument("--out", type=Path, required=True, help="where to write the verdict")
|
||||
parser.add_argument(
|
||||
"--adjudicator", required=True, help="who judged: a person or an identifier, never a role"
|
||||
)
|
||||
parser.add_argument(
|
||||
"--adjudicated-at", required=True, help="ISO 8601, stamped verbatim as everywhere else"
|
||||
)
|
||||
parser.add_argument(
|
||||
"--dwell-s",
|
||||
type=int,
|
||||
default=DEFAULT_DWELL_S,
|
||||
help="seconds spent per entry; the number that makes throughput measurable",
|
||||
)
|
||||
# OFF by default. Not a convenience default -- see the module docstring.
|
||||
parser.add_argument(
|
||||
"--model",
|
||||
default=None,
|
||||
help="switch the advisory model leg on and name the model; off when absent",
|
||||
)
|
||||
return parser.parse_args(argv)
|
||||
|
||||
|
||||
def main(argv: list[str] | None = None) -> int:
|
||||
args = parse_args(argv)
|
||||
try:
|
||||
return run(
|
||||
args.plan,
|
||||
args.out,
|
||||
adjudicator=args.adjudicator,
|
||||
adjudicated_at=args.adjudicated_at,
|
||||
dwell_s=args.dwell_s,
|
||||
model=args.model,
|
||||
)
|
||||
except AdjudicationError as exc:
|
||||
print(f"{ADJUDICATOR_ID}: FAILED - {exc}", file=sys.stderr)
|
||||
print(
|
||||
f"{ADJUDICATOR_ID}: this is NOT 'nothing to judge'. Nothing was written.",
|
||||
file=sys.stderr,
|
||||
)
|
||||
return 2
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
Loading…
Add table
Add a link
Reference in a new issue