File size: 11,248 Bytes
9aa5185 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 | """Tests for browser_console tool and browser_vision annotate param."""
import json
import os
import sys
from unittest.mock import patch, MagicMock
import pytest
sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", ".."))
# ββ browser_console ββββββββββββββββββββββββββββββββββββββββββββββββββ
class TestBrowserConsole:
"""browser_console() returns console messages + JS errors in one call."""
def test_returns_console_messages_and_errors(self):
from tools.browser_tool import browser_console
console_response = {
"success": True,
"data": {
"messages": [
{"text": "hello", "type": "log", "timestamp": 1},
{"text": "oops", "type": "error", "timestamp": 2},
]
},
}
errors_response = {
"success": True,
"data": {
"errors": [
{"message": "Uncaught TypeError", "timestamp": 3},
]
},
}
with patch("tools.browser_tool._run_browser_command") as mock_cmd:
mock_cmd.side_effect = [console_response, errors_response]
result = json.loads(browser_console(task_id="test"))
assert result["success"] is True
assert result["total_messages"] == 2
assert result["total_errors"] == 1
assert result["console_messages"][0]["text"] == "hello"
assert result["console_messages"][1]["text"] == "oops"
assert result["js_errors"][0]["message"] == "Uncaught TypeError"
def test_passes_clear_flag(self):
from tools.browser_tool import browser_console
empty = {"success": True, "data": {"messages": [], "errors": []}}
with patch("tools.browser_tool._run_browser_command", return_value=empty) as mock_cmd:
browser_console(clear=True, task_id="test")
calls = mock_cmd.call_args_list
# Both console and errors should get --clear
assert calls[0][0] == ("test", "console", ["--clear"])
assert calls[1][0] == ("test", "errors", ["--clear"])
def test_no_clear_by_default(self):
from tools.browser_tool import browser_console
empty = {"success": True, "data": {"messages": [], "errors": []}}
with patch("tools.browser_tool._run_browser_command", return_value=empty) as mock_cmd:
browser_console(task_id="test")
calls = mock_cmd.call_args_list
assert calls[0][0] == ("test", "console", [])
assert calls[1][0] == ("test", "errors", [])
def test_empty_console_and_errors(self):
from tools.browser_tool import browser_console
empty = {"success": True, "data": {"messages": [], "errors": []}}
with patch("tools.browser_tool._run_browser_command", return_value=empty):
result = json.loads(browser_console(task_id="test"))
assert result["total_messages"] == 0
assert result["total_errors"] == 0
assert result["console_messages"] == []
assert result["js_errors"] == []
def test_handles_failed_commands(self):
from tools.browser_tool import browser_console
failed = {"success": False, "error": "No session"}
with patch("tools.browser_tool._run_browser_command", return_value=failed):
result = json.loads(browser_console(task_id="test"))
# Should still return success with empty data
assert result["success"] is True
assert result["total_messages"] == 0
assert result["total_errors"] == 0
# ββ browser_console schema βββββββββββββββββββββββββββββββββββββββββββ
class TestBrowserConsoleSchema:
"""browser_console is properly registered in the tool registry."""
def test_schema_in_browser_schemas(self):
from tools.browser_tool import BROWSER_TOOL_SCHEMAS
names = [s["name"] for s in BROWSER_TOOL_SCHEMAS]
assert "browser_console" in names
def test_schema_has_clear_param(self):
from tools.browser_tool import BROWSER_TOOL_SCHEMAS
schema = next(s for s in BROWSER_TOOL_SCHEMAS if s["name"] == "browser_console")
props = schema["parameters"]["properties"]
assert "clear" in props
assert props["clear"]["type"] == "boolean"
class TestBrowserConsoleToolsetWiring:
"""browser_console must be reachable via toolset resolution."""
def test_in_browser_toolset(self):
from toolsets import TOOLSETS
assert "browser_console" in TOOLSETS["browser"]["tools"]
def test_in_hermes_core_tools(self):
from toolsets import _HERMES_CORE_TOOLS
assert "browser_console" in _HERMES_CORE_TOOLS
def test_in_legacy_toolset_map(self):
from model_tools import _LEGACY_TOOLSET_MAP
assert "browser_console" in _LEGACY_TOOLSET_MAP["browser_tools"]
def test_in_registry(self):
from tools.registry import registry
from tools import browser_tool # noqa: F401
assert "browser_console" in registry._tools
# ββ browser_vision annotate ββββββββββββββββββββββββββββββββββββββββββ
class TestBrowserVisionAnnotate:
"""browser_vision supports annotate parameter."""
def test_schema_has_annotate_param(self):
from tools.browser_tool import BROWSER_TOOL_SCHEMAS
schema = next(s for s in BROWSER_TOOL_SCHEMAS if s["name"] == "browser_vision")
props = schema["parameters"]["properties"]
assert "annotate" in props
assert props["annotate"]["type"] == "boolean"
def test_annotate_false_no_flag(self):
"""Without annotate, screenshot command has no --annotate flag."""
from tools.browser_tool import browser_vision
with (
patch("tools.browser_tool._run_browser_command") as mock_cmd,
patch("tools.browser_tool.call_llm") as mock_call_llm,
patch("tools.browser_tool._get_vision_model", return_value="test-model"),
):
mock_cmd.return_value = {"success": True, "data": {}}
# Will fail at screenshot file read, but we can check the command
try:
browser_vision("test", annotate=False, task_id="test")
except Exception:
pass
if mock_cmd.called:
args = mock_cmd.call_args[0]
cmd_args = args[2] if len(args) > 2 else []
assert "--annotate" not in cmd_args
def test_annotate_true_adds_flag(self):
"""With annotate=True, screenshot command includes --annotate."""
from tools.browser_tool import browser_vision
with (
patch("tools.browser_tool._run_browser_command") as mock_cmd,
patch("tools.browser_tool.call_llm") as mock_call_llm,
patch("tools.browser_tool._get_vision_model", return_value="test-model"),
):
mock_cmd.return_value = {"success": True, "data": {}}
try:
browser_vision("test", annotate=True, task_id="test")
except Exception:
pass
if mock_cmd.called:
args = mock_cmd.call_args[0]
cmd_args = args[2] if len(args) > 2 else []
assert "--annotate" in cmd_args
# ββ auto-recording config ββββββββββββββββββββββββββββββββββββββββββββ
class TestRecordSessionsConfig:
"""browser.record_sessions config option."""
def test_default_config_has_record_sessions(self):
from hermes_cli.config import DEFAULT_CONFIG
browser_cfg = DEFAULT_CONFIG.get("browser", {})
assert "record_sessions" in browser_cfg
assert browser_cfg["record_sessions"] is False
def test_maybe_start_recording_disabled(self):
"""Recording doesn't start when config says record_sessions: false."""
from tools.browser_tool import _maybe_start_recording, _recording_sessions
with (
patch("tools.browser_tool._run_browser_command") as mock_cmd,
patch("builtins.open", side_effect=FileNotFoundError),
):
_maybe_start_recording("test-task")
mock_cmd.assert_not_called()
assert "test-task" not in _recording_sessions
def test_maybe_stop_recording_noop_when_not_recording(self):
"""Stopping when not recording is a no-op."""
from tools.browser_tool import _maybe_stop_recording, _recording_sessions
_recording_sessions.discard("test-task") # ensure not in set
with patch("tools.browser_tool._run_browser_command") as mock_cmd:
_maybe_stop_recording("test-task")
mock_cmd.assert_not_called()
# ββ dogfood skill files ββββββββββββββββββββββββββββββββββββββββββββββ
class TestDogfoodSkill:
"""Dogfood skill files exist and have correct structure."""
@pytest.fixture(autouse=True)
def _skill_dir(self):
# Use the actual repo skills dir (not temp)
self.skill_dir = os.path.join(
os.path.dirname(__file__), "..", "..", "skills", "dogfood"
)
def test_skill_md_exists(self):
assert os.path.exists(os.path.join(self.skill_dir, "SKILL.md"))
def test_taxonomy_exists(self):
assert os.path.exists(
os.path.join(self.skill_dir, "references", "issue-taxonomy.md")
)
def test_report_template_exists(self):
assert os.path.exists(
os.path.join(self.skill_dir, "templates", "dogfood-report-template.md")
)
def test_skill_md_has_frontmatter(self):
with open(os.path.join(self.skill_dir, "SKILL.md")) as f:
content = f.read()
assert content.startswith("---")
assert "name: dogfood" in content
assert "description:" in content
def test_skill_references_browser_console(self):
with open(os.path.join(self.skill_dir, "SKILL.md")) as f:
content = f.read()
assert "browser_console" in content
def test_skill_references_annotate(self):
with open(os.path.join(self.skill_dir, "SKILL.md")) as f:
content = f.read()
assert "annotate" in content
def test_taxonomy_has_severity_levels(self):
with open(
os.path.join(self.skill_dir, "references", "issue-taxonomy.md")
) as f:
content = f.read()
assert "Critical" in content
assert "High" in content
assert "Medium" in content
assert "Low" in content
def test_taxonomy_has_categories(self):
with open(
os.path.join(self.skill_dir, "references", "issue-taxonomy.md")
) as f:
content = f.read()
assert "Functional" in content
assert "Visual" in content
assert "Accessibility" in content
assert "Console" in content
|