- DELETE persistent_shell.py entirely (277 lines removed)
- Remove _SHELL_NOISE_SUBSTRINGS, _clean_shell_noise, _extract_fenced_output
from local.py (unused after fence marker removal)
- Adapt ManagedModalEnvironment to use BaseEnvironment + _wrap_command()
while keeping its own HTTP-based execute()
- Remove _OUTPUT_FENCE constant
42/42 tests passing across all testable backends.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Three root causes addressed:
1. AIAgent no longer defaults base_url to OpenRouter (9 tests)
Tests that assert OpenRouter-specific behavior (prompt caching,
reasoning extra_body, provider preferences) need explicit base_url
and model set on the agent. Updated test_run_agent.py and
test_provider_parity.py.
2. Credential pool auto-seeding from host env (2 tests)
test_auxiliary_client.py tests for Anthropic OAuth and custom
endpoint fallback were not mocking _select_pool_entry, so the
host's credential pool interfered. Added pool + codex mocks.
3. sys.modules corruption cascade (major - ~250 tests)
test_managed_modal_environment.py replaced sys.modules entries
(tools, hermes_cli, agent packages) with SimpleNamespace stubs
but had NO cleanup fixture. Every subsequent test in the process
saw corrupted imports: 'cannot import get_config_path from
<unknown module name>' and 'module tools has no attribute
environments'. Added _restore_tool_and_agent_modules autouse
fixture matching the pattern in test_managed_browserbase_and_modal.py.
This was also the root cause of CI failures (104 failed on main).
- add managed modal and gateway-backed tool integrations\n- improve CLI setup, auth, and configuration for subscriber flows\n- expand tests and docs for managed tool support
