Some checks failed
check agents / check (push) Failing after 14s
- Critic 0.3.0: the hooks look up every disposition citation in the verified Discovery package (app/evidence.py). An unresolved citation fails K-02 and rejects the disposition; whether the records support the basis stays the model's judgement. - Critic 0.3.1: K-02 judges a disposition's citations together (evidence_ref is the primary record), ADR 0013 addendum. - Profiler 0.1.1: represents edges are not dependencies (ADR 0012, now covering ALZ-ASM-02). - Scaffold: builds every prompt before deleting anything. - Tests on Discovery run exec_58ba6a71d00b's package and runs 007 and 009 (15). - Run exec_49e355141382 (RUN-ASM-AZURE-012) passed on crucible-kab-dev. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
53 lines
2.6 KiB
Python
53 lines
2.6 KiB
Python
"""The critic's mechanical checks run in code (F02 ADR 0011); the model judges the rest.
|
|
|
|
`pre_process` works out K-04 to K-07 and K-11 from the producers' records, before the model runs, and shows the
|
|
result to the model as `checked_in_code`. `post_process` then sets those checks, the sign-off queue and the verdict
|
|
in the reply. What the model judged (K-01 to K-03, K-08 to K-10, K-12) is kept as it wrote it; where its reading of a
|
|
code check differs, it's kept in `unverified_claims` for the Engagement Lead.
|
|
|
|
The two hooks run in the same request, so the result passes between them in a ContextVar: one per request, never
|
|
shared between requests that run at once.
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import contextvars
|
|
import logging
|
|
from typing import Any, Optional
|
|
|
|
from app import arithmetic, evidence
|
|
|
|
logger = logging.getLogger(__name__)
|
|
_found: contextvars.ContextVar[Optional[dict]] = contextvars.ContextVar("critic_checked_in_code", default=None)
|
|
|
|
|
|
def pre_process(payload: dict) -> Optional[Any]:
|
|
if (payload.get("preconditions") or {}).get("failed"):
|
|
_found.set(None) # the planner refused: the critic returns fail on K-01 alone, and nothing is checked here
|
|
return None
|
|
found = arithmetic.check(payload)
|
|
found["K-02"] = evidence.resolve(payload) # the lookup only (ADR 0013)
|
|
_found.set(found)
|
|
payload["checked_in_code"] = {
|
|
"note": "K-04, K-05, K-06, K-07 and K-11 are checked in code from the producers' records (ADR 0011), and "
|
|
"their results are set in your reply after you answer. Report them as you find them; the other checks "
|
|
"are yours alone.",
|
|
"K-04": found["K-04"] or "every risk score recalculates",
|
|
"K-05": found["K-05"] or "every confidence recalculates",
|
|
"K-06": found["K-06"] or "every TCO model adds up against the rate card",
|
|
"K-07": found["K-07"] or "the disposition agent routed exactly its dispositions below 0.80",
|
|
"K-11": found["K-11"] or "every record passed the input contract; every category is in the 7R enum",
|
|
"K-02 lookup": found["K-02"] or ("every disposition's evidence_ref resolves to a record in the Discovery "
|
|
"package; judge only whether the cited records support the rule-trace basis"),
|
|
}
|
|
return payload
|
|
|
|
|
|
def post_process(result: dict) -> Optional[dict]:
|
|
found = _found.get()
|
|
if found is None:
|
|
if result.get("verdict") is not None:
|
|
logger.info("critic_code_checks_skipped")
|
|
return None
|
|
_found.set(None)
|
|
return arithmetic.apply(result, found)
|