mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-31 19:16:29 +00:00
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.
142 lines
5.1 KiB
Python
142 lines
5.1 KiB
Python
"""Tests: redact_sensitive_text is applied in kanban tool handlers.
|
|
|
|
Verifies that secrets embedded in kanban_comment body, kanban_complete
|
|
summary/result/metadata, and kanban_block reason are masked before the
|
|
values reach the DB. Uses the same worker_env fixture pattern as
|
|
test_kanban_tools.py.
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
|
|
import pytest
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Shared fixture — mirrors test_kanban_tools.py
|
|
# ---------------------------------------------------------------------------
|
|
|
|
@pytest.fixture
|
|
def worker_env(monkeypatch, tmp_path):
|
|
"""Isolated HERMES_HOME with a running task; returns the task id."""
|
|
home = tmp_path / ".hermes"
|
|
home.mkdir()
|
|
monkeypatch.setenv("HERMES_HOME", str(home))
|
|
monkeypatch.setenv("HERMES_PROFILE", "test-worker")
|
|
monkeypatch.delenv("HERMES_SESSION_ID", raising=False)
|
|
from pathlib import Path as _Path
|
|
monkeypatch.setattr(_Path, "home", lambda: tmp_path)
|
|
|
|
from hermes_cli import kanban_db as kb
|
|
kb._INITIALIZED_PATHS.clear()
|
|
kb.init_db()
|
|
conn = kb.connect()
|
|
try:
|
|
tid = kb.create_task(conn, title="worker-test", assignee="test-worker")
|
|
kb.claim_task(conn, tid)
|
|
finally:
|
|
conn.close()
|
|
monkeypatch.setenv("HERMES_KANBAN_TASK", tid)
|
|
return tid
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Positive tests — secrets are masked
|
|
# ---------------------------------------------------------------------------
|
|
|
|
def test_kanban_comment_body_scrubbed_github_pat(worker_env):
|
|
"""ghp_ PAT in comment body must be masked before DB write."""
|
|
from tools import kanban_tools as kt
|
|
from hermes_cli import kanban_db as kb
|
|
secret = "ghp_" + "A" * 40
|
|
kt._handle_comment({"task_id": worker_env, "body": f"token: {secret}"})
|
|
conn = kb.connect()
|
|
try:
|
|
comments = kb.list_comments(conn, worker_env)
|
|
finally:
|
|
conn.close()
|
|
assert comments, "expected at least one comment"
|
|
stored = comments[-1].body
|
|
assert secret not in stored
|
|
assert stored # something was stored
|
|
|
|
|
|
def test_kanban_block_reason_scrubbed_jwt(worker_env):
|
|
"""JWT in block reason must be masked before DB write."""
|
|
from tools import kanban_tools as kt
|
|
from hermes_cli import kanban_db as kb
|
|
# Minimal valid-ish JWT (header.payload.sig)
|
|
jwt = (
|
|
"eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9"
|
|
".eyJzdWIiOiIxMjM0NTY3ODkwIn0"
|
|
".dozjgNryP4J3jVmNHl0w5N_5NjP1-iXkpHgcth826Iw"
|
|
)
|
|
kt._handle_block({"reason": f"Bearer {jwt}"})
|
|
conn = kb.connect()
|
|
try:
|
|
run = kb.latest_run(conn, worker_env)
|
|
finally:
|
|
conn.close()
|
|
# block_task stores reason as run.summary
|
|
assert run is not None
|
|
stored = run.summary or ""
|
|
assert jwt not in stored
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Negative test — plain text passes through unchanged
|
|
# ---------------------------------------------------------------------------
|
|
|
|
def test_kanban_comment_no_secret_passthrough(worker_env):
|
|
"""Plain text without credential patterns must pass through unchanged."""
|
|
from tools import kanban_tools as kt
|
|
from hermes_cli import kanban_db as kb
|
|
plain = "hello from the pipeline — no secrets here"
|
|
kt._handle_comment({"task_id": worker_env, "body": plain})
|
|
conn = kb.connect()
|
|
try:
|
|
comments = kb.list_comments(conn, worker_env)
|
|
finally:
|
|
conn.close()
|
|
stored = comments[-1].body
|
|
assert stored == plain
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Negative test — force=True bypasses HERMES_REDACT_SECRETS=false
|
|
# ---------------------------------------------------------------------------
|
|
|
|
def test_scrub_respects_force_flag_regardless_of_config(worker_env, monkeypatch):
|
|
"""force=True must fire even when HERMES_REDACT_SECRETS=false is set."""
|
|
monkeypatch.setenv("HERMES_REDACT_SECRETS", "false")
|
|
from tools import kanban_tools as kt
|
|
from hermes_cli import kanban_db as kb
|
|
secret = "ghp_" + "C" * 40
|
|
kt._handle_comment({"task_id": worker_env, "body": f"token: {secret}"})
|
|
conn = kb.connect()
|
|
try:
|
|
comments = kb.list_comments(conn, worker_env)
|
|
finally:
|
|
conn.close()
|
|
stored = comments[-1].body
|
|
assert secret not in stored
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Negative test — legacy result field is also scrubbed
|
|
# ---------------------------------------------------------------------------
|
|
|
|
def test_kanban_complete_result_field_scrubbed(worker_env):
|
|
"""Legacy result field must be scrubbed just like summary."""
|
|
from tools import kanban_tools as kt
|
|
from hermes_cli import kanban_db as kb
|
|
secret = "sk-" + "D" * 48
|
|
kt._handle_complete({"result": f"finished with key={secret}"})
|
|
conn = kb.connect()
|
|
try:
|
|
run = kb.latest_run(conn, worker_env)
|
|
finally:
|
|
conn.close()
|
|
assert run is not None
|
|
stored = run.summary or run.result if hasattr(run, "result") else run.summary or ""
|
|
assert secret not in (stored or "")
|