hermes-bsd/tests/tools
Teknium 4d7fc0f37c feat(gateway,cli): confirm /reload-mcp to warn about prompt cache invalidation
Reloading MCP servers rebuilds the tool set for the active session, which
invalidates the provider prompt cache (tool schemas are baked into the
system prompt). The next message re-sends full input tokens — can be
expensive on long-context or high-reasoning models.

To surface that cost, /reload-mcp now routes through a new slash-confirm
primitive with three options: Approve Once / Always Approve / Cancel.
'Always Approve' persists approvals.mcp_reload_confirm: false so future
reloads run silently.

Coverage:

* Classic CLI (cli.py) — interactive numbered prompt.
* TUI (tui_gateway + Ink ops.ts) — text warning on first call; `now` /
  `always` args skip the gate; `always` also persists the opt-out.
* Messenger gateway — button UI on Telegram (inline keyboard), Discord
  (discord.ui.View), Slack (Block Kit actions); text fallback on every
  other platform via /approve /always /cancel replies intercepted in
  gateway/run.py _handle_message.
* Config key: approvals.mcp_reload_confirm (default true).
* Auto-reload paths (CLI file watcher, TUI config-sync mtime poll) pass
  confirm=true so they do NOT prompt.

Implementation:

* tools/slash_confirm.py — module-level pending-state store used by all
  adapters and by the CLI prompt. Thread-safe register/resolve/clear.
* gateway/platforms/base.py — send_slash_confirm hook (default 'Not
  supported' → text fallback).
* gateway/run.py — _request_slash_confirm helper + text intercept in
  _handle_message (yields to in-progress tool-exec approvals so
  dangerous-command /approve still unblocks the tool thread first).

Tests:

* tests/tools/test_slash_confirm.py — primitive lifecycle + async
  resolution + double-click atomicity (16 tests).
* tests/hermes_cli/test_mcp_reload_confirm_gate.py — default-config
  shape + deep-merge preserves user opt-out (5 tests).

Targeted runs (hermetic): 89 passed (slash-confirm, config gate,
existing agent cache, existing telegram approval buttons).
2026-04-29 21:56:47 -07:00
..
__init__.py
test_accretion_caps.py fix(ci): recover 38 failing tests on main (#17642) 2026-04-29 20:05:32 -07:00
test_ansi_strip.py
test_approval.py fix(approval): close remaining prompt_toolkit deadlock vectors (#15216) 2026-04-27 06:42:32 -07:00
test_approval_heartbeat.py fix(approval): heartbeat activity during gateway approval wait (#11245) 2026-04-16 14:48:50 -07:00
test_approval_plugin_hooks.py feat(plugins): add pre_approval_request / post_approval_response hooks (#16776) 2026-04-27 20:08:33 -07:00
test_base_environment.py fix(env): safely quote ~/ subpaths in wrapped cd commands 2026-04-24 15:25:12 -07:00
test_browser_camofox.py fix(tests): resolve 17 persistent CI test failures (#15084) 2026-04-24 03:46:46 -07:00
test_browser_camofox_persistence.py docs: remove nonexistent CAMOFOX_PROFILE_DIR env var references (#10976) 2026-04-16 04:07:11 -07:00
test_browser_camofox_state.py test: stop testing mutable data — convert change-detectors to invariants (#13363) 2026-04-20 23:20:33 -07:00
test_browser_cdp_override.py Support browser CDP URL from config 2026-04-17 16:05:04 -07:00
test_browser_cdp_tool.py fix(tests): resolve 17 persistent CI test failures (#15084) 2026-04-24 03:46:46 -07:00
test_browser_chromium_check.py fix(browser): detect missing Chromium and fail fast with actionable error (#17039) 2026-04-28 07:03:44 -07:00
test_browser_cleanup.py
test_browser_cloud_fallback.py fix(browser): runtime fallback to local Chromium when cloud provider fails 2026-04-16 04:19:34 -07:00
test_browser_console.py fix(browser): honor auxiliary.vision.temperature for screenshot analysis\n\n- mirror the vision tool's config bridge in browser_vision 2026-04-20 00:32:09 -07:00
test_browser_content_none_guard.py
test_browser_hardening.py
test_browser_homebrew_paths.py fix(browser): detect missing Chromium and fail fast with actionable error (#17039) 2026-04-28 07:03:44 -07:00
test_browser_hybrid_routing.py feat(browser): auto-spawn local Chromium for LAN/localhost URLs in cloud mode (#16136) 2026-04-26 09:57:58 -07:00
test_browser_orphan_reaper.py fix: two process leaks (agent-browser daemons, paste.rs sleepers) (#11843) 2026-04-17 18:46:30 -07:00
test_browser_secret_exfil.py
test_browser_ssrf_local.py fix(security): treat quoted false as false in browser SSRF guards 2026-04-26 18:27:13 -07:00
test_browser_supervisor.py feat(browser): CDP supervisor — dialog detection + response + cross-origin iframe eval (#14540) 2026-04-23 22:23:37 -07:00
test_budget_config.py
test_checkpoint_manager.py feat(checkpoints): auto-prune orphan and stale shadow repos at startup (#16303) 2026-04-26 19:05:52 -07:00
test_clarify_tool.py
test_clipboard.py fix(ci): recover 38 failing tests on main (#17642) 2026-04-29 20:05:32 -07:00
test_code_execution.py perf(tui): avoid importing classic CLI during tool discovery 2026-04-28 22:42:17 -05:00
test_code_execution_modes.py feat(execute_code): add project/strict execution modes, default to project (#11971) 2026-04-18 01:46:25 -07:00
test_command_guards.py feat: add Vercel Sandbox backend 2026-04-29 07:22:33 -07:00
test_config_null_guard.py
test_credential_files.py
test_credential_pool_env_fallback.py fix(auth): hoist get_env_value import + strengthen .env fallback tests 2026-04-26 08:32:09 -07:00
test_cron_approval_mode.py feat(approval): hardline blocklist for unrecoverable commands (#15878) 2026-04-25 22:07:12 -07:00
test_cron_prompt_injection.py
test_cronjob_tools.py fix(cron): accept list-form deliver values so deliver=['telegram'] works (#17456) 2026-04-29 06:35:34 -07:00
test_daytona_environment.py
test_debug_helpers.py
test_delegate.py fix(web): scope dashboard config Reset button to the current tab (#16813) 2026-04-27 21:09:14 -07:00
test_delegate_subagent_timeout_diagnostic.py feat(delegate): diagnostic dump when a subagent times out with 0 API calls (#15105) 2026-04-24 04:58:32 -07:00
test_delegate_toolset_scope.py
test_discord_tool.py feat(discord): split discord_server into discord + discord_admin tools 2026-04-25 04:50:14 -07:00
test_docker_environment.py feat(docker): run container as host user to avoid root-owned bind mounts 2026-04-29 16:16:43 +10:00
test_docker_find.py feat: entry-level Podman support — find_docker() + rootless entrypoint (#10066) 2026-04-14 21:20:37 -07:00
test_dockerfile_pid1_reaping.py fix(docker): materialize bundled TUI Ink package (#16690) 2026-04-28 15:11:47 -05:00
test_env_passthrough.py fix(env_passthrough): reject Hermes provider credentials from skill passthrough (#13523) 2026-04-21 06:14:25 -07:00
test_feishu_tools.py feat: add Feishu document comment intelligent reply with 3-tier access control 2026-04-17 19:04:11 -07:00
test_file_operations.py tools: normalize file tool pagination bounds 2026-04-22 06:11:41 -07:00
test_file_operations_edge_cases.py tools: normalize file tool pagination bounds 2026-04-22 06:11:41 -07:00
test_file_ops_cwd_tracking.py fix(file-ops): follow terminal env's live cwd in _exec instead of init-time cached cwd (#11912) 2026-04-17 19:26:40 -07:00
test_file_read_guards.py fix(file-tools): escalate to BLOCKED on repeated read_file dedup stubs (#16382) 2026-04-27 00:17:26 -07:00
test_file_staleness.py fix(file_tools): resolve bookkeeping paths against live terminal cwd 2026-04-23 15:11:52 -07:00
test_file_state_registry.py feat(delegate): cross-agent file state coordination for concurrent subagents (#13718) 2026-04-21 16:41:26 -07:00
test_file_sync.py
test_file_sync_back.py fix: harden sync_back — PID-suffix temp path, size cap, lifecycle guards 2026-04-16 19:39:21 -07:00
test_file_sync_perf.py
test_file_tools.py fix(tests): resolve 17 persistent CI test failures (#15084) 2026-04-24 03:46:46 -07:00
test_file_tools_container_config.py fix(docker): pass docker_mount_cwd_to_workspace and docker_forward_env to container_config in file_tools 2026-04-20 00:58:16 -07:00
test_file_tools_live.py
test_file_write_safety.py
test_force_dangerous_override.py
test_fuzzy_match.py fix(patch): gate 'did you mean?' to no-match + extend to v4a/skill_manage 2026-04-21 02:03:46 -07:00
test_hardline_blocklist.py fix: address self-review findings for Vercel Sandbox salvage 2026-04-29 07:22:33 -07:00
test_hidden_dir_filter.py
test_homeassistant_tool.py
test_image_generation.py feat(image-gen): add GPT Image 2 to FAL catalog (#13677) 2026-04-21 13:35:31 -07:00
test_image_generation_env.py Normalize FAL_KEY env handling (ignore whitespace-only values) 2026-04-21 02:04:21 -07:00
test_image_generation_plugin_dispatch.py fix(image-gen): force-refresh plugin providers in long-lived sessions 2026-04-23 03:01:18 -07:00
test_init_session_cwd_respect.py fix(cli): respect terminal.cwd config in local terminal backend 2026-04-28 22:16:08 -07:00
test_interrupt.py
test_llm_content_none_guard.py
test_local_background_child_hang.py fix(environments): use incremental UTF-8 decoder in select-based drain 2026-04-19 11:27:50 -07:00
test_local_env_blocklist.py feat: add Vercel Sandbox backend 2026-04-29 07:22:33 -07:00
test_local_interrupt_cleanup.py fix(interrupt): propagate to concurrent-tool workers + opt-in debug trace (#11907) 2026-04-17 20:39:25 -07:00
test_local_shell_init.py fix(terminal): auto-source ~/.profile and ~/.bash_profile so n/nvm PATH survives (#14534) 2026-04-23 05:15:37 -07:00
test_local_tempdir.py
test_managed_browserbase_and_modal.py feat: ungate Tool Gateway — subscription-based access with per-tool opt-in 2026-04-16 12:36:49 -07:00
test_managed_media_gateways.py feat: ungate Tool Gateway — subscription-based access with per-tool opt-in 2026-04-16 12:36:49 -07:00
test_managed_modal_environment.py fix: add activity heartbeats to prevent false gateway inactivity timeouts (#10501) 2026-04-15 13:29:05 -07:00
test_managed_server_tool_support.py
test_managed_tool_gateway.py feat: ungate Tool Gateway — subscription-based access with per-tool opt-in 2026-04-16 12:36:49 -07:00
test_mcp_circuit_breaker.py test(mcp): add failing tests for circuit-breaker recovery 2026-04-21 05:19:03 -07:00
test_mcp_dynamic_discovery.py fix(ci): recover 38 failing tests on main (#17642) 2026-04-29 20:05:32 -07:00
test_mcp_oauth.py fix(mcp-oauth): preserve server_url path for protected-resource validation (#16031) 2026-04-26 05:43:54 -07:00
test_mcp_oauth_bidirectional.py fix(mcp-oauth): bidirectional auth_flow bridge + absolute expires_at (salvage #12025) (#12717) 2026-04-19 16:31:07 -07:00
test_mcp_oauth_cold_load_expiry.py fix(mcp-oauth): bidirectional auth_flow bridge + absolute expires_at (salvage #12025) (#12717) 2026-04-19 16:31:07 -07:00
test_mcp_oauth_integration.py fix(mcp): consolidate OAuth handling, pick up external token refreshes (#11383) 2026-04-16 21:57:10 -07:00
test_mcp_oauth_manager.py fix(mcp): consolidate OAuth handling, pick up external token refreshes (#11383) 2026-04-16 21:57:10 -07:00
test_mcp_probe.py
test_mcp_reconnect_signal.py fix(mcp): consolidate OAuth handling, pick up external token refreshes (#11383) 2026-04-16 21:57:10 -07:00
test_mcp_stability.py fix(cron): reap orphaned MCP stdio subprocesses after each tick 2026-04-26 18:21:20 -07:00
test_mcp_structured_content.py fix(ci): recover 38 failing tests on main (#17642) 2026-04-29 20:05:32 -07:00
test_mcp_tool.py fix(mcp): preserve nullable schema coercion 2026-04-28 04:58:03 -07:00
test_mcp_tool_401_handling.py fix(mcp): consolidate OAuth handling, pick up external token refreshes (#11383) 2026-04-16 21:57:10 -07:00
test_mcp_tool_issue_948.py
test_mcp_tool_session_expired.py fix(mcp): auto-reconnect + retry once when the transport session expires (#13383) 2026-04-24 05:28:45 -07:00
test_memory_tool.py
test_memory_tool_import_fallback.py
test_mixture_of_agents_tool.py chore(release): map devorun author + convert MoA defaults test to invariant 2026-04-23 15:14:11 -07:00
test_modal_bulk_upload.py
test_modal_sandbox_fixes.py feat: add Vercel Sandbox backend 2026-04-29 07:22:33 -07:00
test_modal_snapshot_isolation.py
test_notify_on_complete.py
test_osv_check.py
test_parse_env_var.py guard terminal_tool import-time env parsing 2026-04-22 14:45:50 -07:00
test_patch_parser.py
test_process_registry.py fix(process): reconcile session.exited against real child exit in poll/wait (#17430) 2026-04-29 04:59:21 -07:00
test_read_loop_detection.py
test_registry.py revert: computer-use cua-driver (PR #16919) (#16927) 2026-04-28 01:57:21 -07:00
test_resolve_path.py fix(file_tools): resolve bookkeeping paths against live terminal cwd 2026-04-23 15:11:52 -07:00
test_rl_training_tool.py
test_schema_sanitizer.py fix: sanitize tool schemas for llama.cpp backends; restore MCP in TUI (#15032) 2026-04-24 02:44:46 -07:00
test_search_hidden_dirs.py
test_send_message_missing_platforms.py fix(send_message): deliver Matrix media via adapter 2026-04-15 17:37:43 -07:00
test_send_message_tool.py fix(gateway): avoid cross-user mirror writes in per-user group sessions 2026-04-26 18:31:24 -07:00
test_session_search.py fix(session-search): exclude current lineage root deterministically in recent mode 2026-04-26 19:03:17 -07:00
test_shared_container_task_id.py feat(terminal): collapse subagent task_ids to shared container (#16177) 2026-04-26 11:55:02 -07:00
test_signal_media.py feat(send_message): add media delivery support for Signal 2026-04-20 13:24:15 -07:00
test_singularity_preflight.py
test_skill_env_passthrough.py
test_skill_improvements.py
test_skill_manager_tool.py feat(skills): refuse skill_manage writes on pinned skills (#17562) 2026-04-29 10:28:25 -07:00
test_skill_size_limits.py
test_skill_usage.py fix(curator): defense-in-depth gates against bundled/hub skills 2026-04-28 22:33:33 -07:00
test_skill_view_path_check.py
test_skill_view_traversal.py
test_skills_guard.py feat(skills-guard): gate agent-created scanner on config.skills.guard_agent_created (default off) 2026-04-23 06:20:47 -07:00
test_skills_hub.py feat(skills): install skills from a direct HTTP(S) URL (#16323) 2026-04-26 20:57:10 -07:00
test_skills_hub_clawhub.py
test_skills_sync.py feat(skills_sync): surface collision with reset-hint 2026-04-23 05:09:08 -07:00
test_skills_tool.py fix: address self-review findings for Vercel Sandbox salvage 2026-04-29 07:22:33 -07:00
test_slash_confirm.py feat(gateway,cli): confirm /reload-mcp to warn about prompt cache invalidation 2026-04-29 21:56:47 -07:00
test_spotify_client.py refactor(spotify): convert to built-in bundled plugin under plugins/spotify (#15174) 2026-04-24 07:06:11 -07:00
test_ssh_bulk_upload.py
test_ssh_environment.py fix(tools): keep SSH ControlMaster socket path under macOS 104-byte limit 2026-04-20 03:07:32 -07:00
test_symlink_prefix_confusion.py
test_sync_back_backends.py fix: harden sync_back — PID-suffix temp path, size cap, lifecycle guards 2026-04-16 19:39:21 -07:00
test_terminal_compound_background.py fix(terminal): rewrite A && B & to A && { B & } to prevent subshell leak 2026-04-19 16:53:11 -07:00
test_terminal_config_env_sync.py feat(docker): run container as host user to avoid root-owned bind mounts 2026-04-29 16:16:43 +10:00
test_terminal_exit_semantics.py
test_terminal_foreground_timeout_cap.py terminal: steer long-lived server commands to background mode 2026-04-19 16:47:20 -07:00
test_terminal_none_command_guard.py
test_terminal_output_transform_hook.py test: stop testing mutable data — convert change-detectors to invariants (#13363) 2026-04-20 23:20:33 -07:00
test_terminal_requirements.py feat: add Vercel Sandbox backend 2026-04-29 07:22:33 -07:00
test_terminal_timeout_output.py
test_terminal_tool.py fix(security): isolate interactive sudo password cache per session 2026-04-28 01:34:16 -07:00
test_terminal_tool_pty_fallback.py
test_terminal_tool_requirements.py feat: add Vercel Sandbox backend 2026-04-29 07:22:33 -07:00
test_threaded_process_handle.py
test_tirith_security.py
test_todo_tool.py
test_tool_backend_helpers.py fix(cli): coerce use_gateway config flags in tool routing 2026-04-26 19:02:55 -07:00
test_tool_call_parsers.py
test_tool_output_limits.py feat(skills): add design-md skill for Google's DESIGN.md spec (#14876) 2026-04-23 21:51:19 -07:00
test_tool_result_storage.py
test_transcription.py fix(stt): map cloud-only model names to valid local size for faster-whisper (#2544) 2026-04-20 05:18:48 -07:00
test_transcription_dotenv_fallback.py fix(stt): resolve API keys from ~/.hermes/.env via get_env_value (#17140) 2026-04-29 06:25:20 -07:00
test_transcription_tools.py fix(transcription): fall back to CPU when CUDA runtime libs are missing 2026-04-24 02:50:14 -07:00
test_tts_dotenv_fallback.py fix(tts): tolerate missing hermes_cli.config in tts_tool import 2026-04-29 06:25:20 -07:00
test_tts_gemini.py feat(tts): add Google Gemini TTS provider (#11229) 2026-04-16 14:23:16 -07:00
test_tts_kittentts.py feat(tts): complete KittenTTS integration (tools/setup/docs/tests) 2026-04-21 01:28:32 -07:00
test_tts_max_text_length.py fix(tts): use per-provider input-character caps instead of global 4000 (#13743) 2026-04-21 17:49:39 -07:00
test_tts_mistral.py test: remove 8 flaky tests that fail under parallel xdist scheduling (#12784) 2026-04-19 19:38:02 -07:00
test_tts_speed.py
test_url_safety.py fix(security): treat quoted false as false in browser SSRF guards 2026-04-26 18:27:13 -07:00
test_vercel_sandbox_environment.py feat: add Vercel Sandbox backend 2026-04-29 07:22:33 -07:00
test_vision_tools.py test: cover vision config temperature wiring\n\n- add regression tests for auxiliary.vision.temperature and timeout\n- add bugkill3r to AUTHOR_MAP for the salvaged commit 2026-04-20 00:32:09 -07:00
test_voice_cli_integration.py feat(voice): add cli beep toggle 2026-04-21 00:29:29 -07:00
test_voice_mode.py
test_watch_patterns.py fix(terminal): three-layer defense against watch_patterns notification spam (#15642) 2026-04-25 06:41:58 -07:00
test_web_tools_config.py feat(web): expose search result limit 2026-04-28 02:09:30 -07:00
test_web_tools_tavily.py
test_website_policy.py
test_windows_compat.py
test_write_deny.py fix(tests): resolve 17 persistent CI test failures (#15084) 2026-04-24 03:46:46 -07:00
test_yolo_mode.py feat(approval): hardline blocklist for unrecoverable commands (#15878) 2026-04-25 22:07:12 -07:00
test_zombie_process_cleanup.py fix(tests): resolve 17 persistent CI test failures (#15084) 2026-04-24 03:46:46 -07:00