mirror of
https://github.com/Strategic-Automation/violin.git
synced 2026-08-14 12:33:37 +02:00
Violin
119e0c1600
Agent was deferring framework feedback and state writes to closeout, then reconstructing what happened from conversation memory after compression — the exact mechanism that fabricates false positives. - Guard now self-logs: _check_command_internal appends a Guard Block/Review row to state/framework_feedback.md at the moment check_command rejects a command (only when the file exists, i.e. benchmark engagements; no-op otherwise). Friction is captured with zero agent bookkeeping. - SKILL.md Operational Contract: 'Record as you go' — after EVERY violin_review_batch, immediately update hypothesis board + coverage matrix + PTT in the same turn; never batch state writes to closeout, never reconstruct tests from memory. State files are the only source of truth. - 5 new tests: block-row append, no-op without file/errors, dedupe, pipe escaping. 243 tests pass, ruff clean.
79 lines
2.9 KiB
Python
79 lines
2.9 KiB
Python
"""Tests for automatic guard-friction logging (framework feedback as it happens)."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from pathlib import Path
|
|
|
|
from plugins.violin_guard.command import CheckResult
|
|
from plugins.violin_guard.handlers.base import _log_guard_friction
|
|
|
|
|
|
def _feedback_file(eng_dir: Path) -> Path:
|
|
return eng_dir / "state" / "framework_feedback.md"
|
|
|
|
|
|
def test_log_guard_friction_appends_block_row(tmp_path: Path) -> None:
|
|
eng_dir = tmp_path / "eng"
|
|
(eng_dir / "state").mkdir(parents=True)
|
|
feedback = _feedback_file(eng_dir)
|
|
feedback.write_text(
|
|
"# Violin Framework Feedback & Friction Log\n\n| Timestamp | Category | Issue | Impact | Prevention |\n|---|---|---|---|---|\n",
|
|
encoding="utf-8",
|
|
)
|
|
result = CheckResult()
|
|
result.add_error("destructive filesystem deletion (rm -rf) is blocked")
|
|
_log_guard_friction(eng_dir, result, "rm -rf /")
|
|
text = feedback.read_text(encoding="utf-8")
|
|
assert "Guard Block" in text
|
|
assert "rm -rf" in text
|
|
assert "destructive filesystem deletion" in text
|
|
|
|
|
|
def test_log_guard_friction_noop_without_file(tmp_path: Path) -> None:
|
|
"""Non-benchmark engagements (no framework_feedback.md) are untouched."""
|
|
eng_dir = tmp_path / "eng"
|
|
(eng_dir / "state").mkdir(parents=True)
|
|
result = CheckResult()
|
|
result.add_error("some block")
|
|
_log_guard_friction(eng_dir, result, "cmd")
|
|
assert not _feedback_file(eng_dir).exists()
|
|
|
|
|
|
def test_log_guard_friction_noop_without_errors(tmp_path: Path) -> None:
|
|
eng_dir = tmp_path / "eng"
|
|
(eng_dir / "state").mkdir(parents=True)
|
|
feedback = _feedback_file(eng_dir)
|
|
feedback.write_text("header\n", encoding="utf-8")
|
|
result = CheckResult()
|
|
result.add_info("all good")
|
|
_log_guard_friction(eng_dir, result, "ok-cmd")
|
|
assert "Guard" not in feedback.read_text(encoding="utf-8")
|
|
|
|
|
|
def test_log_guard_friction_dedupes_identical_rows(tmp_path: Path) -> None:
|
|
eng_dir = tmp_path / "eng"
|
|
(eng_dir / "state").mkdir(parents=True)
|
|
feedback = _feedback_file(eng_dir)
|
|
feedback.write_text(
|
|
"| Timestamp | Category | Issue | Impact | Prevention |\n|---|---|---|---|---|\n",
|
|
encoding="utf-8",
|
|
)
|
|
result = CheckResult()
|
|
result.add_error("same issue twice")
|
|
_log_guard_friction(eng_dir, result, "cmd")
|
|
_log_guard_friction(eng_dir, result, "cmd")
|
|
assert feedback.read_text(encoding="utf-8").count("same issue twice") == 1
|
|
|
|
|
|
def test_log_guard_friction_escapes_pipes(tmp_path: Path) -> None:
|
|
eng_dir = tmp_path / "eng"
|
|
(eng_dir / "state").mkdir(parents=True)
|
|
feedback = _feedback_file(eng_dir)
|
|
feedback.write_text("header\n", encoding="utf-8")
|
|
result = CheckResult()
|
|
result.add_error("a | b | c")
|
|
_log_guard_friction(eng_dir, result, "cmd")
|
|
text = feedback.read_text(encoding="utf-8")
|
|
# the pipe inside the issue must not split the table row into extra cells
|
|
assert text.count("| a \\| b \\| c |") == 1
|