hermes-agent/tests
Brian D. Evans 162c7856ca
fix(file-safety): add sandbox-mirror soft guard for writes to per-task .hermes mirrors (#32213)
#32049 reports that under terminal.backend: docker, write_file / patch
calls to authoritative profile state (SOUL.md, memories, etc.) land on
the sandbox-local mirror at
``<HERMES_HOME>/profiles/<name>/sandboxes/<backend>/<task>/home/.hermes/...``
— a path the host Hermes process never reads. The tool reports success,
the user sees no behavior change, and on disk two divergent copies of
SOUL.md (or any other profile file) accumulate.

The existing classify_cross_profile_target guard does not catch this:
its parts[2] check sees "sandboxes" and returns None, and the path is
in-profile from the inner-mirror perspective so even a fixed version
would not fire.

Add a parallel sandbox-mirror classifier in agent/file_safety:

  * classify_sandbox_mirror_target() detects the
    ``…/sandboxes/<backend>/<task>/home/.hermes/…`` shape via path parts.
    Detection is path-shape only — backend-agnostic, does not require
    the file to exist, and works regardless of which HERMES_HOME resolves.
  * get_sandbox_mirror_warning() returns a model-facing warning that
    names the mirror root and the inner authoritative path the agent
    likely meant.

Wire both detectors through tools/file_tools._check_cross_profile_path
so the existing write_file and v4a patch call sites pick up the new
guard with no API change. The bypass kwarg (``cross_profile=True``)
remains shared between the two guards — same "I know what I'm doing"
escape valve after explicit user direction.

This is the defense-in-depth piece of the proposal in #32049 ("any
…/sandboxes/<backend>/…/home/…hermes/… path as sandbox-mirror"). It
catches the host-side speculation case where the agent writes a literal
sandbox-mirror path. The inner-container case (where the bind mount
strips the ``sandboxes/`` prefix from the agent's path view) is out of
scope for this surgical change — that requires either a dispatch-layer
host-side check before the container handoff, or the host-side
``profile_state`` / ``soul`` tool the issue also proposes.

Soft guard, NOT a security boundary — matches the existing
classify_cross_profile_target contract.

Co-authored-by: briandevans <252620095+briandevans@users.noreply.github.com>
Co-authored-by: Ben Barclay <ben@nousresearch.com>
2026-06-02 11:29:24 +10:00
..
acp chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
acp_adapter feat(azure-foundry): add Microsoft Entra ID auth 2026-05-18 10:14:38 -07:00
agent fix(file-safety): add sandbox-mirror soft guard for writes to per-task .hermes mirrors (#32213) 2026-06-02 11:29:24 +10:00
cli feat(tools): surface the free tool pool in entitlement + setup (#36153) 2026-06-01 06:32:48 +05:30
cron chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
docker fix(dashboard-auth): share /api/* public allowlist between legacy and OAuth gates 2026-05-29 12:17:12 +10:00
e2e chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
fakes
gateway test(weixin): regression suite for _api_post/_api_get timeout migration 2026-06-01 17:31:40 -07:00
hermes_cli feat(cli): ranked fuzzy search in the curses model picker 2026-06-01 16:58:58 -07:00
hermes_state feat(session_search): single-shape tool with discovery, scroll, browse — no LLM (#27590) 2026-05-17 23:28:45 -07:00
honcho_plugin fix(honcho): harden self-hosted setup paths 2026-05-29 22:29:48 -07:00
integration chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
openviking_plugin
plugins feat(kanban): file attachments on tasks (#35395) 2026-05-30 07:41:04 -07:00
providers chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
run_agent fix(agent): stop reporting broken streams as output-length truncation (#36705) 2026-06-01 03:01:20 -07:00
scripts feat(acp-registry): switch to uvx distribution, drop npm launcher 2026-05-14 22:27:09 -07:00
skills fix(google-workspace): handle Gmail header casing case-insensitively 2026-05-30 02:38:18 -07:00
stress chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
tools test(tools): characterize tool-surface TERMINAL_CWD contract (#29265) 2026-06-01 16:55:04 -07:00
tui_gateway feat(undo): /undo [N] backs up N user turns with prefill + soft-delete 2026-06-01 01:22:38 -07:00
website
__init__.py
conftest.py fix(gateway,cron): reuse existing _HERMES_GATEWAY marker; tighten cron regex 2026-05-30 23:05:56 -07:00
run_interrupt_test.py
test_account_usage.py
test_atomic_replace_symlinks.py
test_base_url_hostname.py
test_batch_runner_checkpoint.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_bitwarden_secrets.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_cli_file_drop.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_cli_manual_compress.py fix(tests): catch up six stale tests after compression/aux/kanban changes (#28465) 2026-05-18 21:43:59 -07:00
test_cli_skin_integration.py
test_ctx_halving_fix.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_docker_home_override_scripts.py docker: opt in to dashboard --insecure via env var, never derive from bind host 2026-05-29 09:56:40 +10:00
test_docker_stage2_browser_discovery.py fix(docker): discover Playwright headless_shell browser (#35717) 2026-06-01 16:06:44 +10:00
test_dockerfile_tini_compat_shim.py fix(docker): add /usr/bin/tini compatibility shim for legacy wrappers (#34192) (#34382) 2026-06-01 13:32:55 +10:00
test_empty_model_fallback.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_env_loader_secret_sources.py fix(secrets): only apply external secrets once per HERMES_HOME per process (#32271) 2026-05-25 15:18:55 -07:00
test_evidence_store.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_gateway_streaming_nested_config.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_get_tool_definitions_cache_isolation.py
test_hermes_bootstrap.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_hermes_constants.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_hermes_home_profile_warning.py
test_hermes_logging.py Add Hermes desktop app (#20059) 2026-05-31 17:46:56 -05:00
test_hermes_state.py Add Hermes desktop app (#20059) 2026-05-31 17:46:56 -05:00
test_hermes_state_compression_locks.py fix(compression): prevent session-id fork from concurrent compressions (#34351) 2026-05-28 21:40:39 -07:00
test_hermes_state_wal_fallback.py fix(kanban): skip redundant WAL pragma on already-WAL connections 2026-05-27 14:31:55 -07:00
test_honcho_client_config.py fix(honcho): harden self-hosted setup paths 2026-05-29 22:29:48 -07:00
test_honcho_session_context.py fix(honcho): align user context peer perspective 2026-05-27 10:49:33 -07:00
test_install_sh_browser_install.py fix(install): support non-sudo service-user installs on apt distros (#25814) 2026-05-14 09:05:31 -07:00
test_install_sh_pythonpath_sanitization.py
test_install_sh_root_fhs_uv_python_path.py test(install): harden uv-python-path regression test against future drift 2026-05-27 13:55:51 -07:00
test_install_sh_setup_wizard_tty_probe.py
test_install_sh_symlink_stomp.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_install_sh_termux_network_prereqs.py
test_ipv4_preference.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_lazy_session_regressions.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_lint_config.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_live_system_guard_self_test.py chore: ruff auto-fix PLR6201 resweep — tuple → set in membership tests (#27355) 2026-05-17 02:29:41 -07:00
test_mcp_serve.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_mini_swe_runner.py
test_minimax_model_validation.py
test_minimax_oauth.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_minisweagent_path.py
test_model_picker_scroll.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_model_tools.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_model_tools_async_bridge.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_ollama_num_ctx.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_package_json_lazy_deps.py fix(update): make Camofox lazy-installed instead of eager (#27055) 2026-05-16 12:15:45 -07:00
test_packaging_metadata.py security: pin patched Starlette (>=1.0.1) for CVE-2026-48710 BadHost (#35118) 2026-05-29 23:23:54 -07:00
test_plugin_skills.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_process_loop_event_loop_warning.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_project_metadata.py fix(stt,tts): restore mistralai — 2.4.8 is clean, ban lifted (#34841) 2026-05-29 13:24:12 -07:00
test_retry_utils.py
test_run_tests_parallel.py test: use subprocesses for each test file (#29016) 2026-05-21 16:40:04 +05:30
test_sanitize_tool_error.py security: sanitize tool error strings before injecting into model context (#26823) 2026-05-16 00:57:39 -07:00
test_sql_injection.py
test_subprocess_home_isolation.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_termux_all_extra_compat.py
test_timezone.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_toolset_distributions.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_toolsets.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_trajectory_compressor.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_trajectory_compressor_async.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_transform_llm_output_hook.py
test_transform_tool_result_hook.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_tui_gateway_server.py fix(desktop): report desktop_contract in lazy session.create info (#36112) 2026-05-31 18:23:10 -05:00
test_utils_truthy_values.py
test_yuanbao_integration.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_yuanbao_markdown.py
test_yuanbao_pipeline.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
test_yuanbao_proto.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00