Sort the new imports and spell the omit words in the replay tests from the change
This commit is contained in:
@@ -4,8 +4,8 @@ import typing
|
||||
|
||||
from loop_claude.cycle.states import Active, Archived, Closing, Ended, Event, HumanTalked, HumanTyped, Interrupting, Judging, QUOTED_ANSWERS_PER_CYCLE, Ruled, State, to_the_human, transition, TypedAnswer, WorkerRan, Working
|
||||
from transcript_archive.write import archive
|
||||
from claude_code.output_limits import BASH_CEILING, BASH_CEILING_CHARACTERS
|
||||
from loop_claude.cycle.worker import AUTO_COMPACT_WINDOW, COMPACT_WINDOW, run_worker, worker_args
|
||||
from claude_code.output_limits import BASH_CEILING, BASH_CEILING_CHARACTERS
|
||||
from loop_claude.cycle.judge import Brief, judge, Rejected
|
||||
from loop_claude.cycle import chunk_items
|
||||
from claude_code.session import delete_session, Session, session_open, transcript_file
|
||||
|
||||
@@ -18,6 +18,7 @@ import uuid
|
||||
sys.path.insert(0, str(pathlib.Path(__file__).resolve().parents[1]))
|
||||
|
||||
from routing_figures import archive, state
|
||||
from claude_code.output_limits import BASH_CEILING_CHARACTERS
|
||||
from routing_figures.calls import Call
|
||||
from loop_claude.project import checkout, model_choice, records
|
||||
from loop_claude.cycle import chunk_items
|
||||
@@ -26,7 +27,6 @@ from project_config.test_project_config import configured
|
||||
from release_plan.release_standing import DefaultPlan, LastCut, UNSEEN_RELEASES
|
||||
from loop_effects.effects import Effects, PYTHON_TIMEOUT
|
||||
from claude_code import entries, reply, session
|
||||
from claude_code.output_limits import BASH_CEILING_CHARACTERS
|
||||
from failure import Failure
|
||||
from loop_claude.verdicts import Finished, Interrupt, Judged, QuotedAnswer, TakenIn, Unfinished
|
||||
from git_cli.git_repo import git
|
||||
|
||||
@@ -2,10 +2,10 @@
|
||||
import sys
|
||||
import typing
|
||||
|
||||
from review_replay.changes import Change
|
||||
from failure import Failure
|
||||
from claude_code.reply import Limited
|
||||
from rung_replay.search import replayed_on
|
||||
from review_replay.changes import Change
|
||||
from review_replay.rounds import Round
|
||||
from model_routing.ladder import Rung
|
||||
|
||||
|
||||
@@ -71,9 +71,9 @@ from transcript_archive.location import archive_root
|
||||
from review_replay.rounds import archived_rounds, Round, sample
|
||||
from rung_replay.archive import archiving, print_report, replay_folder
|
||||
from rung_replay.command import arguments_or_exit, failed, limited_exit
|
||||
from review_replay.changes import Change, CHANGES
|
||||
from review_replay.replay import codes_found, findings_replayed
|
||||
from review_replay.change_comparison import compared
|
||||
from review_replay.changes import Change, CHANGES
|
||||
from loop_effects.effects import Effects
|
||||
from failure import Failure
|
||||
from model_routing.ladder import Ladder, Rung
|
||||
|
||||
@@ -7,8 +7,8 @@ import shutil
|
||||
import sys
|
||||
import tempfile
|
||||
|
||||
from review_replay.changes import Change
|
||||
from review_replay.rounds import authored_by, lost_inputs, reviewed_path, Round
|
||||
from review_replay.changes import Change
|
||||
from claude_code.reply import claude_reply, Limited
|
||||
from git_cli.git_repo import default_ref
|
||||
from loop_effects.effects import Effects
|
||||
|
||||
@@ -15,12 +15,12 @@ import unittest.mock
|
||||
sys.path.insert(0, str(pathlib.Path(__file__).resolve().parents[1]))
|
||||
|
||||
from review_replay.rounds import authored_by, lost_inputs, recorded_findings, reviewed_path, Round, round_from, sample, stamp_seconds
|
||||
from review_replay import changes, main, recall, replay
|
||||
from text_files import compressed
|
||||
from project_config.test_project_config import configured, write_config
|
||||
from loop_effects.effects import Effects, system_effects
|
||||
from claude_code.entries import entry_from
|
||||
from failure import Failure
|
||||
from review_replay import changes, main, recall, replay
|
||||
from review_rules.reviewer_context import reviewer_context
|
||||
from review_rules.review_passes import REVIEWERS
|
||||
from model_routing.ladder import Rung
|
||||
@@ -294,7 +294,7 @@ class Main(unittest.TestCase):
|
||||
context = reviewer_context(self.home)
|
||||
self.assertEqual([prompt.startswith(context) for *_, prompt, _ in self.reviews], [False, False, False, True])
|
||||
self.assertEqual(out, (
|
||||
f"Replayed 1 stability rounds of claude-opus-5-5 projects, which hold 2 🔴 and 🟡 findings, four times on {REFERENCE}: three with CLAUDE.md, one without CLAUDE.md.\n"
|
||||
f"Replayed 1 stability rounds of claude-opus-5-5 projects, which hold 2 🔴 and 🟡 findings, four times on {REFERENCE}: three {changes.OMIT.unchanged}, one {changes.OMIT.changed}.\n"
|
||||
"With CLAUDE.md the three replays found 2, 1 and 2 of them, and missed 0, 1 and 0 of the findings that both of the other two found.\n"
|
||||
"Without CLAUDE.md it found 1 of them, and missed 1 of the 1 findings that both of the first two found:\n"
|
||||
f" {self.checkout} 2026-10-14T10:00:00Z: 🔴 a.txt:1 wrong\n"
|
||||
@@ -354,7 +354,7 @@ class Main(unittest.TestCase):
|
||||
code, out, err = self.run_main(["stability", "claude-opus-5-5", "--omit-claude-md"], lambda rung: {"found": [0, 1]}, review=review)
|
||||
self.assertEqual(code, 0, err)
|
||||
self.assertEqual(out, (
|
||||
f"Replayed 0 stability rounds of claude-opus-5-5 projects, which hold 0 🔴 and 🟡 findings, four times on {REFERENCE}: three with CLAUDE.md, one without CLAUDE.md.\n"
|
||||
f"Replayed 0 stability rounds of claude-opus-5-5 projects, which hold 0 🔴 and 🟡 findings, four times on {REFERENCE}: three {changes.OMIT.unchanged}, one {changes.OMIT.changed}.\n"
|
||||
"Left out 1 more, which a replay failed on; stderr says why.\n"
|
||||
"With CLAUDE.md the three replays found 0, 0 and 0 of them, and missed 0, 0 and 0 of the findings that both of the other two found.\n"
|
||||
"Without CLAUDE.md it found 0 of them. No evidence: the first two replays with CLAUDE.md found none in common, so there is no finding to hold it to.\n"
|
||||
|
||||
@@ -3,8 +3,8 @@
|
||||
A transcript is a `.jsonl` file there, a session's own or a subagent's. Its size is the session's whole thread, so a Read of one puts it all in context. The files Claude Code saves a long Bash result to, under the session's `tool-results/` folder, are `.txt` files and pass: the model is handed their path to read."""
|
||||
import posixpath
|
||||
|
||||
from rule_hook.call import Call, text
|
||||
from rule_hook.rules import Breach
|
||||
from rule_hook.call import Call, text
|
||||
from command_lines.shell_command import resolved
|
||||
|
||||
READS = "the call reads {}, a session transcript that holds every tool result of its session; print only the lines you need with grep or jq"
|
||||
|
||||
Reference in New Issue
Block a user