Files

78 lines
3.3 KiB
Python

"""The verdicts judge.verdict_from builds from the judge's reply; run.rule then stamps every verdict but Finished with the items the chunk takes. They sit in a module of their own, since routing.py reads them and run.py imports routing.py."""
import dataclasses
from transcript_archive.judge_run import JudgeRun
from claude_code.tokens import Tokens
@dataclasses.dataclass(frozen=True)
class TakenIn:
"""The highest L, and the highest E + I, among the plan items the worker names on its latest `Chunk items:` line, as the entry point reads them (run.py's Cycle.taken_in). The item the chunk was routed on counts only where the worker names it."""
# The highest L among them, 0 for none: an escalation steps up from the rung that L picks, and an unfinished verdict also raises the worker to it.
highest_likelihood: int = 0
# The highest E + I among them, 0 for none: after an unfinished verdict, it routes the next cycle's reviewers.
highest_escape_and_impact: int = 0
@dataclasses.dataclass(frozen=True)
class Judged:
"""What the judge run that gave a verdict found beside it, which the cycle archives with the verdict."""
# In dollars, as its reply records; 0 where it records none.
cost: float = 0.0
# Its reply's usage, on the judge's model.
tokens: Tokens = Tokens()
# The human's whole typed answer that holds the judge's quote of a reversal of a choice the worker took on its own recommendation; empty for none, and where no typed answer holds the quote.
reversed: str = ""
# The prompt it read and its reply, which the archive keeps beside the verdict. Left out of comparisons and reprs, so that equal verdicts stay equal whatever prompt they came from.
run: JudgeRun | None = dataclasses.field(default=None, compare=False, repr=False)
@dataclasses.dataclass(frozen=True)
class Interrupt:
evidence: str
question: str
# The judge's quote showing that the worker's cited escalation trigger fired; empty for none.
escalation: str = ""
taken_in: TakenIn = TakenIn()
release_ready: bool = False
# How many transcript entries the judge read, which escalation_mark.stamped stamps. An escalation the verdict carries moves the route's mark there. None means it was never stamped, and then its escalation doesn't step the worker.
entries_read: int | None = None
judged: Judged = Judged()
# The [human] line from earlier in the chunk that answered the same question, and the words of it that leave the question open; empty for none. cycle.judge.re_ask_checked turns the Interrupt into an Unfinished where the question doesn't quote them.
answered_before: str = ""
left_open: str = ""
@dataclasses.dataclass(frozen=True)
class QuotedAnswer:
"""The worker asked a question that the premises or the records answer. The answer field quotes the passage."""
evidence: str
question: str
answer: str
# As on Interrupt.
escalation: str = ""
taken_in: TakenIn = TakenIn()
entries_read: int | None = None
judged: Judged = Judged()
@dataclasses.dataclass(frozen=True)
class Finished:
evidence: str
judged: Judged = Judged()
@dataclasses.dataclass(frozen=True)
class Unfinished:
evidence: str
# As on Interrupt.
escalation: str = ""
taken_in: TakenIn = TakenIn()
entries_read: int | None = None
judged: Judged = Judged()
Verdict = Interrupt | QuotedAnswer | Finished | Unfinished
# The verdicts that may carry an escalation.
Escalating = Interrupt | QuotedAnswer | Unfinished