test: reorganize test structure and add missing unit tests
Reorganize flat tests/ directory to mirror source code structure
(tools/, gateway/, hermes_cli/, integration/). Add 11 new test files
covering previously untested modules: registry, patch_parser,
fuzzy_match, todo_tool, approval, file_tools, gateway session/config/
delivery, and hermes_cli config/models. Total: 147 unit tests passing,
9 integration tests gated behind pytest marker.
2026-02-26 03:20:08 +03:00
|
|
|
"""Shared fixtures for the hermes-agent test suite."""
|
|
|
|
|
|
2026-03-14 03:14:34 -07:00
|
|
|
import asyncio
|
test: reorganize test structure and add missing unit tests
Reorganize flat tests/ directory to mirror source code structure
(tools/, gateway/, hermes_cli/, integration/). Add 11 new test files
covering previously untested modules: registry, patch_parser,
fuzzy_match, todo_tool, approval, file_tools, gateway session/config/
delivery, and hermes_cli config/models. Total: 147 unit tests passing,
9 integration tests gated behind pytest marker.
2026-02-26 03:20:08 +03:00
|
|
|
import os
|
2026-03-12 01:23:28 -07:00
|
|
|
import signal
|
test: reorganize test structure and add missing unit tests
Reorganize flat tests/ directory to mirror source code structure
(tools/, gateway/, hermes_cli/, integration/). Add 11 new test files
covering previously untested modules: registry, patch_parser,
fuzzy_match, todo_tool, approval, file_tools, gateway session/config/
delivery, and hermes_cli config/models. Total: 147 unit tests passing,
9 integration tests gated behind pytest marker.
2026-02-26 03:20:08 +03:00
|
|
|
import sys
|
|
|
|
|
import tempfile
|
|
|
|
|
from pathlib import Path
|
|
|
|
|
from unittest.mock import patch
|
|
|
|
|
|
|
|
|
|
import pytest
|
|
|
|
|
|
|
|
|
|
# Ensure project root is importable
|
|
|
|
|
PROJECT_ROOT = Path(__file__).parent.parent
|
|
|
|
|
if str(PROJECT_ROOT) not in sys.path:
|
|
|
|
|
sys.path.insert(0, str(PROJECT_ROOT))
|
|
|
|
|
|
|
|
|
|
|
2026-03-02 04:34:21 -08:00
|
|
|
@pytest.fixture(autouse=True)
|
|
|
|
|
def _isolate_hermes_home(tmp_path, monkeypatch):
|
|
|
|
|
"""Redirect HERMES_HOME to a temp dir so tests never write to ~/.hermes/."""
|
|
|
|
|
fake_home = tmp_path / "hermes_test"
|
|
|
|
|
fake_home.mkdir()
|
|
|
|
|
(fake_home / "sessions").mkdir()
|
|
|
|
|
(fake_home / "cron").mkdir()
|
|
|
|
|
(fake_home / "memories").mkdir()
|
|
|
|
|
(fake_home / "skills").mkdir()
|
|
|
|
|
monkeypatch.setenv("HERMES_HOME", str(fake_home))
|
feat: first-class plugin architecture (#1555)
Plugin system for extending Hermes with custom tools, hooks, and
integrations — no source code changes required.
Core system (hermes_cli/plugins.py):
- Plugin discovery from ~/.hermes/plugins/, .hermes/plugins/, and
pip entry_points (hermes_agent.plugins group)
- PluginContext with register_tool() and register_hook()
- 6 lifecycle hooks: pre/post tool_call, pre/post llm_call,
on_session_start/end
- Namespace package handling for relative imports in plugins
- Graceful error isolation — broken plugins never crash the agent
Integration (model_tools.py):
- Plugin discovery runs after built-in + MCP tools
- Plugin tools bypass toolset filter via get_plugin_tool_names()
- Pre/post tool call hooks fire in handle_function_call()
CLI:
- /plugins command shows loaded plugins, tool counts, status
- Added to COMMANDS dict for autocomplete
Docs:
- Getting started guide (build-a-hermes-plugin.md) — full tutorial
building a calculator plugin step by step
- Reference page (features/plugins.md) — quick overview + tables
- Covers: file structure, schemas, handlers, hooks, data files,
bundled skills, env var gating, pip distribution, common mistakes
Tests: 16 tests covering discovery, loading, hooks, tool visibility.
2026-03-16 07:17:36 -07:00
|
|
|
# Reset plugin singleton so tests don't leak plugins from ~/.hermes/plugins/
|
|
|
|
|
try:
|
|
|
|
|
import hermes_cli.plugins as _plugins_mod
|
|
|
|
|
monkeypatch.setattr(_plugins_mod, "_plugin_manager", None)
|
|
|
|
|
except Exception:
|
|
|
|
|
pass
|
2026-03-14 20:48:29 -07:00
|
|
|
# Tests should not inherit the agent's current gateway/messaging surface.
|
|
|
|
|
# Individual tests that need gateway behavior set these explicitly.
|
|
|
|
|
monkeypatch.delenv("HERMES_SESSION_PLATFORM", raising=False)
|
|
|
|
|
monkeypatch.delenv("HERMES_SESSION_CHAT_ID", raising=False)
|
|
|
|
|
monkeypatch.delenv("HERMES_SESSION_CHAT_NAME", raising=False)
|
|
|
|
|
monkeypatch.delenv("HERMES_GATEWAY_SESSION", raising=False)
|
2026-03-02 04:34:21 -08:00
|
|
|
|
|
|
|
|
|
test: reorganize test structure and add missing unit tests
Reorganize flat tests/ directory to mirror source code structure
(tools/, gateway/, hermes_cli/, integration/). Add 11 new test files
covering previously untested modules: registry, patch_parser,
fuzzy_match, todo_tool, approval, file_tools, gateway session/config/
delivery, and hermes_cli config/models. Total: 147 unit tests passing,
9 integration tests gated behind pytest marker.
2026-02-26 03:20:08 +03:00
|
|
|
@pytest.fixture()
|
|
|
|
|
def tmp_dir(tmp_path):
|
|
|
|
|
"""Provide a temporary directory that is cleaned up automatically."""
|
|
|
|
|
return tmp_path
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
@pytest.fixture()
|
|
|
|
|
def mock_config():
|
|
|
|
|
"""Return a minimal hermes config dict suitable for unit tests."""
|
|
|
|
|
return {
|
|
|
|
|
"model": "test/mock-model",
|
|
|
|
|
"toolsets": ["terminal", "file"],
|
|
|
|
|
"max_turns": 10,
|
|
|
|
|
"terminal": {
|
|
|
|
|
"backend": "local",
|
|
|
|
|
"cwd": "/tmp",
|
|
|
|
|
"timeout": 30,
|
|
|
|
|
},
|
|
|
|
|
"compression": {"enabled": False},
|
|
|
|
|
"memory": {"memory_enabled": False, "user_profile_enabled": False},
|
|
|
|
|
"command_allowlist": [],
|
|
|
|
|
}
|
2026-03-12 01:23:28 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
# ── Global test timeout ─────────────────────────────────────────────────────
|
|
|
|
|
# Kill any individual test that takes longer than 30 seconds.
|
|
|
|
|
# Prevents hanging tests (subprocess spawns, blocking I/O) from stalling the
|
|
|
|
|
# entire test suite.
|
|
|
|
|
|
|
|
|
|
def _timeout_handler(signum, frame):
|
|
|
|
|
raise TimeoutError("Test exceeded 30 second timeout")
|
|
|
|
|
|
2026-03-14 03:14:34 -07:00
|
|
|
@pytest.fixture(autouse=True)
|
|
|
|
|
def _ensure_current_event_loop(request):
|
|
|
|
|
"""Provide a default event loop for sync tests that call get_event_loop().
|
|
|
|
|
|
|
|
|
|
Python 3.11+ no longer guarantees a current loop for plain synchronous tests.
|
|
|
|
|
A number of gateway tests still use asyncio.get_event_loop().run_until_complete(...).
|
|
|
|
|
Ensure they always have a usable loop without interfering with pytest-asyncio's
|
|
|
|
|
own loop management for @pytest.mark.asyncio tests.
|
|
|
|
|
"""
|
|
|
|
|
if request.node.get_closest_marker("asyncio") is not None:
|
|
|
|
|
yield
|
|
|
|
|
return
|
|
|
|
|
|
|
|
|
|
try:
|
|
|
|
|
loop = asyncio.get_event_loop_policy().get_event_loop()
|
|
|
|
|
except RuntimeError:
|
|
|
|
|
loop = None
|
|
|
|
|
|
|
|
|
|
created = loop is None or loop.is_closed()
|
|
|
|
|
if created:
|
|
|
|
|
loop = asyncio.new_event_loop()
|
|
|
|
|
asyncio.set_event_loop(loop)
|
|
|
|
|
|
|
|
|
|
try:
|
|
|
|
|
yield
|
|
|
|
|
finally:
|
|
|
|
|
if created and loop is not None:
|
|
|
|
|
try:
|
|
|
|
|
loop.close()
|
|
|
|
|
finally:
|
|
|
|
|
asyncio.set_event_loop(None)
|
|
|
|
|
|
|
|
|
|
|
2026-03-12 01:23:28 -07:00
|
|
|
@pytest.fixture(autouse=True)
|
|
|
|
|
def _enforce_test_timeout():
|
fix(approval): show full command in dangerous command approval (#1553)
* fix: prevent infinite 400 failure loop on context overflow (#1630)
When a gateway session exceeds the model's context window, Anthropic may
return a generic 400 invalid_request_error with just 'Error' as the
message. This bypassed the phrase-based context-length detection,
causing the agent to treat it as a non-retryable client error. Worse,
the failed user message was still persisted to the transcript, making
the session even larger on each attempt — creating an infinite loop.
Three-layer fix:
1. run_agent.py — Fallback heuristic: when a 400 error has a very short
generic message AND the session is large (>40% of context or >80
messages), treat it as a probable context overflow and trigger
compression instead of aborting.
2. run_agent.py + gateway/run.py — Don't persist failed messages:
when the agent returns failed=True before generating any response,
skip writing the user's message to the transcript/DB. This prevents
the session from growing on each failure.
3. gateway/run.py — Smarter error messages: detect context-overflow
failures and suggest /compact or /reset specifically, instead of a
generic 'try again' that will fail identically.
* fix(skills): detect prompt injection patterns and block cache file reads
Adds two security layers to prevent prompt injection via skills hub
cache files (#1558):
1. read_file: blocks direct reads of ~/.hermes/skills/.hub/ directory
(index-cache, catalog files). The 3.5MB clawhub_catalog_v1.json
was the original injection vector — untrusted skill descriptions
in the catalog contained adversarial text that the model executed.
2. skill_view: warns when skills are loaded from outside the trusted
~/.hermes/skills/ directory, and detects common injection patterns
in skill content ("ignore previous instructions", "<system>", etc.).
Cherry-picked from PR #1562 by ygd58.
* fix(tools): chunk long messages in send_message_tool before dispatch (#1552)
Long messages sent via send_message tool or cron delivery silently
failed when exceeding platform limits. Gateway adapters handle this
via truncate_message(), but the standalone senders in send_message_tool
bypassed that entirely.
- Apply truncate_message() chunking in _send_to_platform() before
dispatching to individual platform senders
- Remove naive message[i:i+2000] character split in _send_discord()
in favor of centralized smart splitting
- Attach media files to last chunk only for Telegram
- Add regression tests for chunking and media placement
Cherry-picked from PR #1557 by llbn.
* fix(approval): show full command in dangerous command approval (#1553)
Previously the command was truncated to 80 chars in CLI (with a
[v]iew full option), 500 chars in Discord embeds, and missing entirely
in Telegram/Slack approval messages. Now the full command is always
displayed everywhere:
- CLI: removed 80-char truncation and [v]iew full menu option
- Gateway (TG/Slack): approval_required message includes full command
in a code block
- Discord: embed shows full command up to 4096-char limit
- Windows: skip SIGALRM-based test timeout (Unix-only)
- Updated tests: replaced view-flow tests with direct approval tests
Cherry-picked from PR #1566 by crazywriter1.
---------
Co-authored-by: buray <ygd58@users.noreply.github.com>
Co-authored-by: lbn <llbn@users.noreply.github.com>
Co-authored-by: crazywriter1 <53251494+crazywriter1@users.noreply.github.com>
2026-03-17 02:02:33 -07:00
|
|
|
"""Kill any individual test that takes longer than 30 seconds.
|
|
|
|
|
SIGALRM is Unix-only; skip on Windows."""
|
|
|
|
|
if sys.platform == "win32":
|
|
|
|
|
yield
|
|
|
|
|
return
|
2026-03-12 01:23:28 -07:00
|
|
|
old = signal.signal(signal.SIGALRM, _timeout_handler)
|
|
|
|
|
signal.alarm(30)
|
|
|
|
|
yield
|
|
|
|
|
signal.alarm(0)
|
|
|
|
|
signal.signal(signal.SIGALRM, old)
|