anti
cb1872c52f
Stage 3 of the realism migration. Replaces orchestrator/scheduler.py's
hardcoded _FILE_TEMPLATES/_USERS (3 templates emitting epoch-suffixed
filenames like notes-1777315854.txt with identical bodies per
template) with a persona-driven realism engine.
New surface:
- SyntheticFile SQLModel (synthetic_files table, UNIQUE on
decky_uuid+path) — per-(decky, path) state for the future
edit-in-place flow. Pre-v1, no _migrate_* helper.
- BaseRepository methods: record_synthetic_file,
update_synthetic_file, list_synthetic_files,
pick_random_synthetic_file_for_edit (used by stage 3b).
- realism/naming.py: per-content-class filename templates,
persona-conditioned. /var/log/cron.log + logrotate skeleton for
system-class; /home/<persona>/TODO.md, scratch.md, etc. for
user-class. Anti-regression test pins "no 8+ digit decimals in
basenames" (the realism failure today).
- realism/bodies.py: deterministic body templates per content_class.
TODO body uses checkbox markdown, script body has a shebang, cron
body matches syslog cron shape ("CRON[PID]: (user) CMD (...)").
- realism/planner.py: pick(deckies, now, rng) returns a Plan.
Diurnal-gated, weighted user/system content split (70/30 user
bias). Create-only in stage 3; edit branch lands in stage 3b.
Scheduler split:
- scheduler.pick is now traffic-only (sync).
- scheduler.pick_file is async, takes a repo, resolves personas
(Topology.email_personas for topology-source deckies; global
realism.personas_pool otherwise), and maps Plan -> FileAction.
- FileAction gains persona/content_class/mtime fields.
Worker:
- _one_tick rolls 50/50 between traffic and file each tick. After a
successful FileAction plant, _record_synthetic_file persists or
patches the synthetic_files row (catching the unique-constraint
collision on re-plant of the same path).
- SSHDriver._run_file passes action.mtime through to plant_file so
files don't all stamp at wall-clock-now.
69 lines
2.1 KiB
Python
69 lines
2.1 KiB
Python
"""Body templates produce realistic, non-empty output per content class."""
|
|
from __future__ import annotations
|
|
|
|
import secrets
|
|
|
|
import pytest
|
|
|
|
from decnet.realism.bodies import make_body
|
|
from decnet.realism.taxonomy import ContentClass
|
|
|
|
|
|
_INERT_CLASSES = (
|
|
ContentClass.NOTE,
|
|
ContentClass.TODO,
|
|
ContentClass.DRAFT,
|
|
ContentClass.SCRIPT,
|
|
ContentClass.LOG_CRON,
|
|
ContentClass.LOG_DAEMON,
|
|
ContentClass.CACHE_TMP,
|
|
)
|
|
|
|
|
|
@pytest.mark.parametrize("cls", _INERT_CLASSES)
|
|
def test_body_is_nonempty(cls: ContentClass) -> None:
|
|
body = make_body(cls, "admin", rand=secrets.SystemRandom())
|
|
assert isinstance(body, str)
|
|
assert body.strip()
|
|
|
|
|
|
def test_todo_body_uses_checkbox_markdown() -> None:
|
|
body = make_body(ContentClass.TODO, "admin")
|
|
# Each line should look like a markdown checkbox; we don't pin the
|
|
# exact distribution because the % checked is randomised.
|
|
for line in body.strip().splitlines():
|
|
assert line.startswith("- [")
|
|
|
|
|
|
def test_script_body_starts_with_shebang() -> None:
|
|
seen_shebangs: set[str] = set()
|
|
rng = secrets.SystemRandom()
|
|
for _ in range(20):
|
|
body = make_body(ContentClass.SCRIPT, "admin", rand=rng)
|
|
assert body.startswith("#!")
|
|
seen_shebangs.add(body.splitlines()[0])
|
|
# We should pick from at least two interpreter shebangs across 20
|
|
# trials; if not, the template list collapsed.
|
|
assert len(seen_shebangs) >= 2
|
|
|
|
|
|
def test_log_cron_body_has_cron_syslog_shape() -> None:
|
|
body = make_body(ContentClass.LOG_CRON, "admin", rand=secrets.SystemRandom())
|
|
for line in body.strip().splitlines():
|
|
assert "CRON[" in line
|
|
assert "CMD (" in line
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"cls",
|
|
[c for c in ContentClass if c.value.startswith("canary_")],
|
|
)
|
|
def test_canary_classes_raise_in_bodies(cls: ContentClass) -> None:
|
|
with pytest.raises(NotImplementedError, match="canary"):
|
|
make_body(cls, "admin")
|
|
|
|
|
|
def test_email_class_raises_in_bodies() -> None:
|
|
with pytest.raises(NotImplementedError, match="email"):
|
|
make_body(ContentClass.EMAIL, "admin")
|