hermes-agent/tests/gateway/test_pii_redaction.py
Teknium 39975613b1
test: prune wave 2 + speed fixes — 28,106 → 19,757 test functions, suite wall 315s → 294s
Second, deeper pass over tools/gateway/hermes_cli plus first pass over
the trees wave 1 missed (acp, acp_adapter, skills, computer_use, docker,
dashboard, conformance, monitoring, secret_sources, hermes_state,
providers). Same rubric as wave 1 (AGENTS.md test policy); security,
alternation/caching invariants, issue-number regressions, and E2E kept.

Real test-quality fixes found and rooted out along the way:
- tests/tools/test_command_guards.py made real auxiliary-LLM HTTPS calls
  (DEFAULT_CONFIG smart-approval leaked in) — pinned approval
  mode=manual via autouse fixture: 17.4s → 0.4s.
- test_model_switch_custom_providers.py / test_user_providers_model_switch.py
  silently probed live provider catalogs (~2s/test) — stubbed
  cached_provider_model_ids/provider_model_ids/fetch_api_models.
- test_telegram_noise_filter.py: 15-platform copy-paste matrix over
  shared gateway.run logic → 3 representative platforms (55s → 3.9s).
- test_gateway_shutdown.py: stop()'s 5s interrupt-deadline loop spun on
  MagicMock agents — interrupt.side_effect now clears _running_agents
  (22s → 1.0s).
- test_gateway_inactivity_timeout.py poll-harness timings shrunk 3-5x
  (24s → 1.1s); test_mcp_stability.py backoff/SIGTERM-grace sleeps
  patched (15.4s → 2.5s); test_async_delegation.py negative-drain wait
  5s → 0.5s.
- test_telegram_init_deadline.py: loop-block margin restored to 1.0s
  with rationale comment — the watchdog-dump assertion needs the loop
  blocked well past deadline+grace under parallel load (flaked once in
  the 40-worker verification run at a 0.2s margin).

Verification: full hermetic suite via scripts/run_tests.sh —
2,438 files, 21,718 tests passed, 0 failed, 293.9s wall.
Suite totals vs original baseline: 46,820 → 19,757 test functions
(−57.8%), wall 583.5s → 293.9s (−50%), subprocess CPU 13,564s → 11,623s.
2026-07-29 13:39:40 -07:00

118 lines
4 KiB
Python

"""Tests for PII redaction in gateway session context prompts."""
from gateway.session import (
SessionContext,
SessionSource,
build_session_context_prompt,
_hash_id,
_hash_sender_id,
_hash_chat_id,
)
from gateway.config import Platform, HomeChannel
# ---------------------------------------------------------------------------
# Low-level helpers
# ---------------------------------------------------------------------------
class TestHashHelpers:
def test_hash_id_12_hex_chars(self):
h = _hash_id("user-abc")
assert len(h) == 12
assert all(c in "0123456789abcdef" for c in h)
def test_hash_chat_id_preserves_prefix(self):
result = _hash_chat_id("telegram:12345")
assert result.startswith("telegram:")
assert "12345" not in result
# ---------------------------------------------------------------------------
# Integration: build_session_context_prompt
# ---------------------------------------------------------------------------
def _make_context(
user_id="user-123",
user_name=None,
chat_id="telegram:99999",
platform=Platform.TELEGRAM,
home_channels=None,
):
source = SessionSource(
platform=platform,
chat_id=chat_id,
chat_type="dm",
user_id=user_id,
user_name=user_name,
)
return SessionContext(
source=source,
connected_platforms=[platform],
home_channels=home_channels or {},
)
class TestBuildSessionContextPromptRedaction:
def test_no_redaction_by_default(self):
ctx = _make_context(user_id="user-123")
prompt = build_session_context_prompt(ctx)
assert "user-123" in prompt
def test_user_id_hashed_when_redact_pii(self):
ctx = _make_context(user_id="user-123")
prompt = build_session_context_prompt(ctx, redact_pii=True)
assert "user-123" not in prompt
assert "user_" in prompt # hashed ID present
def test_user_name_not_redacted(self):
ctx = _make_context(user_id="user-123", user_name="Alice")
prompt = build_session_context_prompt(ctx, redact_pii=True)
assert "Alice" in prompt
# user_id should not appear when user_name is present (name takes priority)
assert "user-123" not in prompt
def test_home_channel_id_preserved_without_redaction(self):
hc = {
Platform.TELEGRAM: HomeChannel(
platform=Platform.TELEGRAM,
chat_id="telegram:99999",
name="Home Chat",
)
}
ctx = _make_context(home_channels=hc)
prompt = build_session_context_prompt(ctx, redact_pii=False)
assert "99999" in prompt
def test_redaction_is_deterministic(self):
ctx = _make_context(user_id="+15551234567")
prompt1 = build_session_context_prompt(ctx, redact_pii=True)
prompt2 = build_session_context_prompt(ctx, redact_pii=True)
assert prompt1 == prompt2
def test_discord_ids_not_redacted_even_with_flag(self):
"""Discord needs real IDs for <@user_id> mentions."""
ctx = _make_context(user_id="123456789", platform=Platform.DISCORD)
prompt = build_session_context_prompt(ctx, redact_pii=True)
assert "123456789" in prompt
def test_whatsapp_ids_redacted(self):
ctx = _make_context(user_id="+15551234567", platform=Platform.WHATSAPP)
prompt = build_session_context_prompt(ctx, redact_pii=True)
assert "+15551234567" not in prompt
assert "user_" in prompt
def test_signal_ids_redacted(self):
ctx = _make_context(user_id="+15551234567", platform=Platform.SIGNAL)
prompt = build_session_context_prompt(ctx, redact_pii=True)
assert "+15551234567" not in prompt
assert "user_" in prompt
def test_slack_ids_not_redacted(self):
"""Slack may need IDs for mentions too."""
ctx = _make_context(user_id="U12345ABC", platform=Platform.SLACK)
prompt = build_session_context_prompt(ctx, redact_pii=True)
assert "U12345ABC" in prompt