mirror of
https://github.com/turnstonelabs/turnstone.git
synced 2026-08-27 14:24:47 -06:00
Patrick Buckley
09ea3d164d
* feat: intent validation v1 — advisory LLM judge for tool approvals (#50) Two-tier evaluation pipeline for non-auto-approved tool calls: - Heuristic tier (instant): 23 pattern-based rules across 4 severity levels (critical/high/medium/low) with first-match-wins priority - LLM judge tier (async): multi-turn evaluation with read_file/ list_directory tool access, security-hardened path blocking, forcing message on final turn, four-stage JSON parsing with retry nudge Progressive UI: heuristic verdict badge + judge spinner, LLM verdict upgrade via intent_verdict SSE event, glow on action buttons. Verdict persisted to intent_verdicts table for audit. Prometheus metrics for verdict counts and LLM latency. Enabled by default (--no-judge to opt out). 132 new tests (1938 total). Integration: session, server/WebUI, CLI, MQ bridge, console admin API, Discord channel adapter. Config via [judge] in config.toml or CLI flags. * fix: address PR #50 Copilot review feedback - Fix double JSON encoding of func_args in both heuristic and LLM verdict persistence paths — use pre-serialized string from verdict - Fix confidence 0.0 treated as falsy in channel verdict formatter - Fix timestamp format inconsistency in storage backends (isoformat vs strftime) — now uses strftime consistently - Add on_intent_verdict to eval.py NullUI (mypy fix) - Fix late verdict after approval resolved — store last decision and apply immediately to late-arriving verdicts - Add permission rollback to migration 012 downgrade - Update docs to reflect judge enabled by default - Document confidence_threshold as reserved for v2 * fix: judge per-call timeout and credential recon heuristic - Wrap create_completion() in ThreadPoolExecutor with per-call timeout to prevent indefinite hangs on slow local models. On timeout, replace the executor so subsequent batch items don't queue behind lingering API calls - Add IntentJudge.shutdown() and wire into session.close() for cleanup - Add credential-recon heuristic rule: /etc/passwd, /etc/shadow, /etc/master.passwd access flagged as HIGH/review (reconnaissance pattern even though the command itself is read-only) - 3 new tests for credential file access patterns * fix: denied/blocked tool calls show correct badge on resume - _build_history() detects denied results ("Denied by user") and blocked results ("Blocked") and propagates denied flag to parent assistant entry for frontend consumption - Frontend history replay uses denied flag for badge-denied class instead of hardcoding badge-approved for all historical tool calls - Denial feedback always prefixed with "Denied by user:" so content detection works with custom user feedback - Denied tools visually muted (opacity 0.55, muted tool name) - role="status" on all approval badge elements (accessibility) - Broadened "Blocked" prefix match (catches "Blocked by tool policy")
259 lines
10 KiB
Python
259 lines
10 KiB
Python
"""Tests for intent verdict storage operations."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from datetime import UTC, datetime, timedelta
|
|
|
|
import pytest
|
|
|
|
from turnstone.core.storage._sqlite import SQLiteBackend
|
|
|
|
|
|
@pytest.fixture()
|
|
def db(tmp_path):
|
|
"""Fresh SQLite backend for each test."""
|
|
return SQLiteBackend(str(tmp_path / "test.db"))
|
|
|
|
|
|
def _make_verdict_kwargs(**overrides):
|
|
"""Build default kwargs for create_intent_verdict."""
|
|
defaults = {
|
|
"verdict_id": "v_001",
|
|
"ws_id": "ws-abc",
|
|
"call_id": "tc_001",
|
|
"func_name": "bash",
|
|
"func_args": '{"command":"echo hello"}',
|
|
"intent_summary": "Echo a greeting to stdout",
|
|
"risk_level": "low",
|
|
"confidence": 0.85,
|
|
"recommendation": "approve",
|
|
"reasoning": "Simple echo command with no side effects.",
|
|
"evidence": '["The command only prints text."]',
|
|
"tier": "heuristic",
|
|
"judge_model": "",
|
|
"latency_ms": 2,
|
|
}
|
|
defaults.update(overrides)
|
|
return defaults
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# CRUD Operations
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
class TestIntentVerdictCRUD:
|
|
def test_create_and_get(self, db):
|
|
db.create_intent_verdict(**_make_verdict_kwargs())
|
|
v = db.get_intent_verdict("v_001")
|
|
assert v is not None
|
|
assert v["verdict_id"] == "v_001"
|
|
assert v["ws_id"] == "ws-abc"
|
|
assert v["call_id"] == "tc_001"
|
|
assert v["func_name"] == "bash"
|
|
assert v["func_args"] == '{"command":"echo hello"}'
|
|
assert v["intent_summary"] == "Echo a greeting to stdout"
|
|
assert v["risk_level"] == "low"
|
|
assert v["confidence"] == 0.85
|
|
assert v["recommendation"] == "approve"
|
|
assert v["reasoning"] == "Simple echo command with no side effects."
|
|
assert v["evidence"] == '["The command only prints text."]'
|
|
assert v["tier"] == "heuristic"
|
|
assert v["judge_model"] == ""
|
|
assert v["latency_ms"] == 2
|
|
assert v["user_decision"] == ""
|
|
assert "created" in v
|
|
|
|
def test_get_nonexistent(self, db):
|
|
assert db.get_intent_verdict("nonexistent") is None
|
|
|
|
def test_update_user_decision(self, db):
|
|
db.create_intent_verdict(**_make_verdict_kwargs())
|
|
ok = db.update_intent_verdict("v_001", user_decision="approved")
|
|
assert ok is True
|
|
v = db.get_intent_verdict("v_001")
|
|
assert v is not None
|
|
assert v["user_decision"] == "approved"
|
|
|
|
def test_update_mutable_fields(self, db):
|
|
db.create_intent_verdict(**_make_verdict_kwargs())
|
|
ok = db.update_intent_verdict(
|
|
"v_001",
|
|
intent_summary="Updated summary",
|
|
risk_level="high",
|
|
confidence=0.95,
|
|
recommendation="deny",
|
|
reasoning="Changed reasoning",
|
|
evidence='["new evidence"]',
|
|
tier="llm",
|
|
judge_model="gpt-5",
|
|
latency_ms=500,
|
|
)
|
|
assert ok is True
|
|
v = db.get_intent_verdict("v_001")
|
|
assert v is not None
|
|
assert v["intent_summary"] == "Updated summary"
|
|
assert v["risk_level"] == "high"
|
|
assert v["confidence"] == 0.95
|
|
assert v["recommendation"] == "deny"
|
|
assert v["reasoning"] == "Changed reasoning"
|
|
assert v["evidence"] == '["new evidence"]'
|
|
assert v["tier"] == "llm"
|
|
assert v["judge_model"] == "gpt-5"
|
|
assert v["latency_ms"] == 500
|
|
|
|
def test_update_rejects_immutable_fields(self, db):
|
|
"""Non-mutable fields like ws_id, call_id, func_name are rejected."""
|
|
db.create_intent_verdict(**_make_verdict_kwargs())
|
|
# Only non-mutable fields passed — should return False (no valid fields).
|
|
ok = db.update_intent_verdict(
|
|
"v_001",
|
|
ws_id="ws-hacked",
|
|
call_id="tc_hacked",
|
|
func_name="hacked",
|
|
)
|
|
assert ok is False
|
|
v = db.get_intent_verdict("v_001")
|
|
assert v is not None
|
|
assert v["ws_id"] == "ws-abc"
|
|
assert v["call_id"] == "tc_001"
|
|
assert v["func_name"] == "bash"
|
|
|
|
def test_update_nonexistent(self, db):
|
|
ok = db.update_intent_verdict("missing", user_decision="approved")
|
|
assert ok is False
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# List queries
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
class TestIntentVerdictList:
|
|
def test_list_by_ws_id(self, db):
|
|
db.create_intent_verdict(**_make_verdict_kwargs(verdict_id="v1", ws_id="ws-1"))
|
|
db.create_intent_verdict(**_make_verdict_kwargs(verdict_id="v2", ws_id="ws-1"))
|
|
db.create_intent_verdict(**_make_verdict_kwargs(verdict_id="v3", ws_id="ws-2"))
|
|
|
|
results = db.list_intent_verdicts(ws_id="ws-1")
|
|
assert len(results) == 2
|
|
assert all(r["ws_id"] == "ws-1" for r in results)
|
|
|
|
def test_list_by_risk_level(self, db):
|
|
db.create_intent_verdict(**_make_verdict_kwargs(verdict_id="v1", risk_level="low"))
|
|
db.create_intent_verdict(**_make_verdict_kwargs(verdict_id="v2", risk_level="high"))
|
|
db.create_intent_verdict(**_make_verdict_kwargs(verdict_id="v3", risk_level="low"))
|
|
|
|
results = db.list_intent_verdicts(risk_level="high")
|
|
assert len(results) == 1
|
|
assert results[0]["verdict_id"] == "v2"
|
|
|
|
def test_list_by_date_range(self, db):
|
|
now = datetime.now(UTC)
|
|
|
|
# create_intent_verdict uses datetime.now(UTC) internally, so
|
|
# we test with since/until relative to the auto-created time.
|
|
db.create_intent_verdict(**_make_verdict_kwargs(verdict_id="v1"))
|
|
db.create_intent_verdict(**_make_verdict_kwargs(verdict_id="v2"))
|
|
db.create_intent_verdict(**_make_verdict_kwargs(verdict_id="v3"))
|
|
|
|
# All should be within a recent window
|
|
one_minute_ago = (now - timedelta(minutes=1)).isoformat()
|
|
one_minute_later = (now + timedelta(minutes=1)).isoformat()
|
|
results = db.list_intent_verdicts(since=one_minute_ago, until=one_minute_later)
|
|
assert len(results) == 3
|
|
|
|
# Nothing before a far-past date
|
|
ancient = "2020-01-01T00:00:00"
|
|
results = db.list_intent_verdicts(until=ancient)
|
|
assert len(results) == 0
|
|
|
|
def test_list_pagination(self, db):
|
|
for i in range(10):
|
|
db.create_intent_verdict(**_make_verdict_kwargs(verdict_id=f"v_{i:03d}"))
|
|
|
|
page1 = db.list_intent_verdicts(limit=3, offset=0)
|
|
assert len(page1) == 3
|
|
|
|
page2 = db.list_intent_verdicts(limit=3, offset=3)
|
|
assert len(page2) == 3
|
|
|
|
# Pages should not overlap
|
|
ids1 = {r["verdict_id"] for r in page1}
|
|
ids2 = {r["verdict_id"] for r in page2}
|
|
assert ids1.isdisjoint(ids2)
|
|
|
|
def test_list_ordering_desc(self, db):
|
|
db.create_intent_verdict(**_make_verdict_kwargs(verdict_id="v_aaa"))
|
|
db.create_intent_verdict(**_make_verdict_kwargs(verdict_id="v_bbb"))
|
|
db.create_intent_verdict(**_make_verdict_kwargs(verdict_id="v_ccc"))
|
|
|
|
results = db.list_intent_verdicts()
|
|
# Created timestamps are likely identical (fast inserts), so
|
|
# secondary sort is by verdict_id DESC.
|
|
ids = [r["verdict_id"] for r in results]
|
|
assert ids == ["v_ccc", "v_bbb", "v_aaa"]
|
|
|
|
def test_list_empty(self, db):
|
|
assert db.list_intent_verdicts() == []
|
|
|
|
def test_list_combined_filters(self, db):
|
|
db.create_intent_verdict(
|
|
**_make_verdict_kwargs(verdict_id="v1", ws_id="ws-1", risk_level="high")
|
|
)
|
|
db.create_intent_verdict(
|
|
**_make_verdict_kwargs(verdict_id="v2", ws_id="ws-1", risk_level="low")
|
|
)
|
|
db.create_intent_verdict(
|
|
**_make_verdict_kwargs(verdict_id="v3", ws_id="ws-2", risk_level="high")
|
|
)
|
|
|
|
results = db.list_intent_verdicts(ws_id="ws-1", risk_level="high")
|
|
assert len(results) == 1
|
|
assert results[0]["verdict_id"] == "v1"
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Count queries
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
class TestIntentVerdictCount:
|
|
def test_count_basic(self, db):
|
|
db.create_intent_verdict(**_make_verdict_kwargs(verdict_id="v1"))
|
|
db.create_intent_verdict(**_make_verdict_kwargs(verdict_id="v2"))
|
|
db.create_intent_verdict(**_make_verdict_kwargs(verdict_id="v3"))
|
|
assert db.count_intent_verdicts() == 3
|
|
|
|
def test_count_empty(self, db):
|
|
assert db.count_intent_verdicts() == 0
|
|
|
|
def test_count_with_ws_id(self, db):
|
|
db.create_intent_verdict(**_make_verdict_kwargs(verdict_id="v1", ws_id="ws-1"))
|
|
db.create_intent_verdict(**_make_verdict_kwargs(verdict_id="v2", ws_id="ws-1"))
|
|
db.create_intent_verdict(**_make_verdict_kwargs(verdict_id="v3", ws_id="ws-2"))
|
|
assert db.count_intent_verdicts(ws_id="ws-1") == 2
|
|
|
|
def test_count_with_risk_level(self, db):
|
|
db.create_intent_verdict(**_make_verdict_kwargs(verdict_id="v1", risk_level="low"))
|
|
db.create_intent_verdict(**_make_verdict_kwargs(verdict_id="v2", risk_level="high"))
|
|
db.create_intent_verdict(**_make_verdict_kwargs(verdict_id="v3", risk_level="high"))
|
|
assert db.count_intent_verdicts(risk_level="high") == 2
|
|
|
|
def test_count_matches_list_length(self, db):
|
|
"""Count with filters matches the length of list with same filters."""
|
|
db.create_intent_verdict(
|
|
**_make_verdict_kwargs(verdict_id="v1", ws_id="ws-1", risk_level="high")
|
|
)
|
|
db.create_intent_verdict(
|
|
**_make_verdict_kwargs(verdict_id="v2", ws_id="ws-1", risk_level="low")
|
|
)
|
|
db.create_intent_verdict(
|
|
**_make_verdict_kwargs(verdict_id="v3", ws_id="ws-2", risk_level="high")
|
|
)
|
|
|
|
for ws, rl in [("ws-1", ""), ("", "high"), ("ws-1", "high"), ("ws-2", "low")]:
|
|
count = db.count_intent_verdicts(ws_id=ws, risk_level=rl)
|
|
listed = db.list_intent_verdicts(ws_id=ws, risk_level=rl)
|
|
assert count == len(listed), f"Mismatch for ws_id={ws!r}, risk_level={rl!r}"
|