Files
rdb-discovery/tests/test_guardrails.py
T

322 lines
9.9 KiB
Python

from pathlib import Path
from datetime import datetime, timedelta
import os
import pytest
from rdb_discovery.guardrails import (
check_repeated_reads,
check_repeated_commands,
check_repeated_commands_telemetry,
check_repeated_reads_telemetry,
check_no_recent_file_changes,
check_no_test_run_recorded,
check_run_log_updated,
run_all_guardrails,
format_report,
)
# -- check_repeated_reads --
def test_check_repeated_reads_ok(tmp_path: Path) -> None:
"""No agent history files → status ok."""
result = check_repeated_reads(tmp_path)
assert result["status"] == "ok"
def test_check_repeated_reads_warning(tmp_path: Path) -> None:
"""AGENT_HANDOFF.md mentions the same file >2 times."""
ah = tmp_path / "AGENT_HANDOFF.md"
ah.write_text(
"# Agent Handoff\n\n"
"- README.md\n- README.md\n- README.md\n"
"- TASKS.md\n",
encoding="utf-8",
)
result = check_repeated_reads(tmp_path)
assert result["status"] == "warning"
assert "README.md (3x)" in result["details"]
def test_check_repeated_reads_no_over_threshold(tmp_path: Path) -> None:
"""Files mentioned <=2 times should not trigger warning."""
ah = tmp_path / "AGENT_HANDOFF.md"
ah.write_text(
"# Agent Handoff\n\n"
"- README.md\n- README.md\n"
"- TASKS.md\n- TASKS.md\n",
encoding="utf-8",
)
result = check_repeated_reads(tmp_path)
assert result["status"] == "ok"
# -- check_repeated_commands --
def test_check_repeated_commands_ok_no_log(tmp_path: Path) -> None:
result = check_repeated_commands(tmp_path)
assert result["status"] == "ok"
def test_check_repeated_commands_ok(tmp_path: Path) -> None:
rl = tmp_path / "RUN_LOG.md"
rl.write_text(
"| date | event1 |\n"
"| date | event2 |\n",
encoding="utf-8",
)
result = check_repeated_commands(tmp_path)
assert result["status"] == "ok"
def test_check_repeated_commands_warning(tmp_path: Path) -> None:
rl = tmp_path / "RUN_LOG.md"
line = "| date | Task completed |\n"
rl.write_text(
"# RUN_LOG\n\n| Date | Event | Task | Notes |\n" + line * 5,
encoding="utf-8",
)
result = check_repeated_commands(tmp_path)
assert result["status"] == "warning"
# -- check_repeated_commands_telemetry --
def test_check_repeated_commands_telemetry_no_events(tmp_path: Path) -> None:
"""No telemetry events → status ok with fallback message."""
result = check_repeated_commands_telemetry(tmp_path)
assert result["status"] == "ok"
assert "No telemetry data available" in result["details"]
def test_check_repeated_commands_telemetry_warning(tmp_path: Path) -> None:
"""Same command repeated >3 times in telemetry → warning."""
from rdb_discovery.telemetry import record_event
for _ in range(5):
record_event(tmp_path, "command", "rdb prompt")
result = check_repeated_commands_telemetry(tmp_path)
assert result["status"] == "warning"
assert "rdb prompt" in result["details"]
def test_check_repeated_commands_telemetry_no_over_threshold(tmp_path: Path) -> None:
"""Same command repeated <=3 times → ok."""
from rdb_discovery.telemetry import record_event
for _ in range(3):
record_event(tmp_path, "command", "rdb prompt")
result = check_repeated_commands_telemetry(tmp_path)
assert result["status"] == "ok"
# -- check_repeated_reads_telemetry --
def test_check_repeated_reads_telemetry_no_events(tmp_path: Path) -> None:
"""No telemetry events → status ok with fallback message."""
result = check_repeated_reads_telemetry(tmp_path)
assert result["status"] == "ok"
assert "No telemetry data available" in result["details"]
def test_check_repeated_reads_telemetry_no_read_events(tmp_path: Path) -> None:
"""Only command events, no read events → ok with message."""
from rdb_discovery.telemetry import record_event
record_event(tmp_path, "command", "rdb prompt")
result = check_repeated_reads_telemetry(tmp_path)
assert result["status"] == "ok"
assert "No file read events found" in result["details"]
def test_check_repeated_reads_telemetry_warning(tmp_path: Path) -> None:
"""Same file read >3 times in telemetry → warning."""
from rdb_discovery.telemetry import record_event
for _ in range(5):
record_event(tmp_path, "read", "README.md")
result = check_repeated_reads_telemetry(tmp_path)
assert result["status"] == "warning"
assert "README.md" in result["details"]
def test_check_repeated_reads_telemetry_no_over_threshold(tmp_path: Path) -> None:
"""Same file read <=3 times → ok."""
from rdb_discovery.telemetry import record_event
for _ in range(3):
record_event(tmp_path, "read", "TASKS.md")
result = check_repeated_reads_telemetry(tmp_path)
assert result["status"] == "ok"
# -- check_no_recent_file_changes --
def test_check_no_recent_file_changes_ok(tmp_path: Path) -> None:
"""Files modified recently → ok."""
for rel in ["TASKS.md", "PROJECT_STATE.md"]:
(tmp_path / rel).write_text("x", encoding="utf-8")
# Patch _last_modified to return a recent time
import rdb_discovery.guardrails as mod
original_now = mod._now
def fake_now() -> datetime:
return datetime.now()
mod._now = fake_now
try:
result = check_no_recent_file_changes(tmp_path)
assert result["status"] == "ok"
finally:
mod._now = original_now
def test_check_no_recent_file_changes_warning(tmp_path: Path) -> None:
"""Files modified >48h ago → warning."""
(tmp_path / "TASKS.md").write_text("x", encoding="utf-8")
import rdb_discovery.guardrails as mod
old_ts = datetime.now() - timedelta(hours=72)
# Set a fake mtime via os.utime (avoids pathlib.touch times= on macOS)
ts = old_ts.timestamp()
(tmp_path / "TASKS.md").touch()
os.utime(str(tmp_path / "TASKS.md"), (ts, ts))
result = check_no_recent_file_changes(tmp_path)
assert result["status"] == "warning"
# -- check_no_test_run_recorded --
def test_check_no_test_run_recorded_ok(tmp_path: Path) -> None:
rl = tmp_path / "RUN_LOG.md"
rl.write_text("# RUN\n\n| date | pytest passed |\n", encoding="utf-8")
result = check_no_test_run_recorded(tmp_path)
assert result["status"] == "ok"
def test_check_no_test_run_recorded_warning(tmp_path: Path) -> None:
rl = tmp_path / "RUN_LOG.md"
rl.write_text("# RUN\n\n| date | task done |\n", encoding="utf-8")
result = check_no_test_run_recorded(tmp_path)
assert result["status"] == "warning"
def test_check_no_test_run_recorded_no_log(tmp_path: Path) -> None:
result = check_no_test_run_recorded(tmp_path)
assert result["status"] == "ok"
# -- check_run_log_updated --
def test_check_run_log_updated_ok(tmp_path: Path) -> None:
tasks = tmp_path / "TASKS.md"
tasks.write_text(
"## TASK-001 - First\nStatus: Done\n",
encoding="utf-8",
)
rl = tmp_path / "RUN_LOG.md"
rl.write_text(
"# RUN\n\n| date | Task completed | TASK-001 |\n",
encoding="utf-8",
)
result = check_run_log_updated(tmp_path)
assert result["status"] == "ok"
def test_check_run_log_updated_warning(tmp_path: Path) -> None:
tasks = tmp_path / "TASKS.md"
tasks.write_text(
"## TASK-001 - First\nStatus: Done\n",
encoding="utf-8",
)
rl = tmp_path / "RUN_LOG.md"
rl.write_text("# RUN\n\n| date | something else |\n", encoding="utf-8")
result = check_run_log_updated(tmp_path)
assert result["status"] == "warning"
def test_check_run_log_updated_no_files(tmp_path: Path) -> None:
result = check_run_log_updated(tmp_path)
assert result["status"] == "ok"
# -- run_all_guardrails --
def test_run_all_guardrails_returns_keys() -> None:
import tempfile
with tempfile.TemporaryDirectory() as td:
root = Path(td)
# Create minimal files so checks don't return 'ok' for missing file
(root / "RUN_LOG.md").write_text("# RUN\n", encoding="utf-8")
result = run_all_guardrails(root)
assert "checks" in result
assert "overall_status" in result
def test_run_all_guardrails_overall_all_clear(tmp_path: Path) -> None:
"""All checks pass → overall 'all clear'."""
# Create files with recent mtimes and ok content
(tmp_path / "TASKS.md").write_text("# TASKS\n", encoding="utf-8")
(tmp_path / "RUN_LOG.md").write_text("# RUN\n| date | pytest passed |\n", encoding="utf-8")
import rdb_discovery.guardrails as mod
old_now = mod._now
now = datetime.now()
class FakePath:
def __init__(self, path: Path):
self._path = path
def exists(self) -> bool:
return self._path.exists()
def stat(self):
class StatResult:
st_mtime = now.timestamp()
return StatResult()
orig_last_modified = mod._last_modified
def fake_last_modified(root: Path, rel: str) -> datetime | None:
p = root / rel
if p.exists():
return now
return None
mod._now = lambda: now
mod._last_modified = fake_last_modified
try:
result = run_all_guardrails(tmp_path)
# Should be clear or have a non-error overall status (guardrails may flag other things)
assert result["overall_status"] in ("all clear", "review recommended")
finally:
mod._now = old_now
mod._last_modified = orig_last_modified
# -- format_report --
def test_format_report_includes_overall() -> None:
results = {
"checks": {"Test check": {"status": "ok", "details": "fine"}},
"overall_status": "all clear",
}
report = format_report(results)
assert "# Guardrail Report" in report
assert "all clear" in report
def test_format_report_with_warning() -> None:
results = {
"checks": {"Test check": {"status": "warning", "details": "watch out"}},
"overall_status": "review recommended",
}
report = format_report(results)
assert "review recommended" in report