mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-04-25 00:51:20 +00:00
62cbeb6367
Catalog snapshots, config version literals, and enumeration counts are data that changes as designed. Tests that assert on those values add no behavioral coverage — they just break CI on every routine update and cost engineering time to 'fix.' Replace with invariants where one exists, delete where none does. Deleted (pure snapshots): - TestMinimaxModelCatalog (3 tests): 'MiniMax-M2.7 in models' et al - TestGeminiModelCatalog: 'gemini-2.5-pro in models', 'gemini-3.x in models' - test_browser_camofox_state::test_config_version_matches_current_schema (docstring literally said it would break on unrelated bumps) Relaxed (keep plumbing check, drop snapshot): - Xiaomi / Arcee / Kimi moonshot / Kimi coding / HuggingFace static lists: now assert 'provider exists and has >= 1 entry' instead of specific names - HuggingFace main/models.py consistency test: drop 'len >= 6' floor Dynamicized (follow source, not a literal): - 3x test_config.py migration tests: raw['_config_version'] == DEFAULT_CONFIG['_config_version'] instead of hardcoded 21 Fixed stale tests against intentional behavior changes: - test_insights::test_gateway_format_hides_cost: name matches new behavior (no dollar figures); remove contradicting '$' in text assertion - test_config::prefers_api_then_url_then_base_url: flipped per PR #9332; rename + update to base_url > url > api - test_anthropic_adapter: relax assert_called_once() (xdist-flaky) to assert called — contract is 'credential flowed through' - test_interrupt_propagation: add provider/model/_base_url to bare-agent fixture so the stale-timeout code path resolves Fixed stale integration tests against opt-in plugin gate: - transform_tool_result + transform_terminal_output: write plugins.enabled allow-list to config.yaml and reset the plugin manager singleton Source fix (real consistency invariant): - agent/model_metadata.py: add moonshotai/Kimi-K2.6 context length (262144, same as K2.5). test_model_metadata_has_context_lengths was correctly catching the gap. Policy: - AGENTS.md Testing section: new subsection 'Don't write change-detector tests' with do/don't examples. Reviewers should reject catalog-snapshot assertions in new tests. Covers every test that failed on the last completed main CI run (24703345583) except test_modal_sandbox_fixes::test_terminal_tool_present + test_terminal_and_file_toolsets_resolve_all_tools, which now pass both alone and with the full tests/tools/ directory (xdist ordering flake that resolved itself).
60 lines
2.3 KiB
Python
60 lines
2.3 KiB
Python
"""Tests for Hermes-managed Camofox state helpers."""
|
|
|
|
from unittest.mock import patch
|
|
|
|
import pytest
|
|
|
|
|
|
def _load_module():
|
|
from tools import browser_camofox_state as state
|
|
return state
|
|
|
|
|
|
class TestCamofoxStatePaths:
|
|
def test_paths_are_profile_scoped(self, tmp_path):
|
|
state = _load_module()
|
|
with patch.object(state, "get_hermes_home", return_value=tmp_path):
|
|
assert state.get_camofox_state_dir() == tmp_path / "browser_auth" / "camofox"
|
|
|
|
|
|
class TestCamofoxIdentity:
|
|
def test_identity_is_deterministic(self, tmp_path):
|
|
state = _load_module()
|
|
with patch.object(state, "get_hermes_home", return_value=tmp_path):
|
|
first = state.get_camofox_identity("task-1")
|
|
second = state.get_camofox_identity("task-1")
|
|
assert first == second
|
|
|
|
def test_identity_differs_by_task(self, tmp_path):
|
|
state = _load_module()
|
|
with patch.object(state, "get_hermes_home", return_value=tmp_path):
|
|
a = state.get_camofox_identity("task-a")
|
|
b = state.get_camofox_identity("task-b")
|
|
# Same user (same profile), different session keys
|
|
assert a["user_id"] == b["user_id"]
|
|
assert a["session_key"] != b["session_key"]
|
|
|
|
def test_identity_differs_by_profile(self, tmp_path):
|
|
state = _load_module()
|
|
with patch.object(state, "get_hermes_home", return_value=tmp_path / "profile-a"):
|
|
a = state.get_camofox_identity("task-1")
|
|
with patch.object(state, "get_hermes_home", return_value=tmp_path / "profile-b"):
|
|
b = state.get_camofox_identity("task-1")
|
|
assert a["user_id"] != b["user_id"]
|
|
|
|
def test_default_task_id(self, tmp_path):
|
|
state = _load_module()
|
|
with patch.object(state, "get_hermes_home", return_value=tmp_path):
|
|
identity = state.get_camofox_identity()
|
|
assert "user_id" in identity
|
|
assert "session_key" in identity
|
|
assert identity["user_id"].startswith("hermes_")
|
|
assert identity["session_key"].startswith("task_")
|
|
|
|
|
|
class TestCamofoxConfigDefaults:
|
|
def test_default_config_includes_managed_persistence_toggle(self):
|
|
from hermes_cli.config import DEFAULT_CONFIG
|
|
|
|
browser_cfg = DEFAULT_CONFIG["browser"]
|
|
assert browser_cfg["camofox"]["managed_persistence"] is False
|