hermes-agent/tests/hermes_cli
Edison e752c9454e feat(plugins): add register_auxiliary_task() to PluginContext API
Auxiliary LLM tasks (vision, compression, web_extract, etc.) currently
require modifications to core files for any plugin that needs its own
task slot — specifically the _AUX_TASKS list in hermes_cli/main.py and
the hardcoded env-var bridging dict in gateway/run.py. This violates
the 'plugins must not modify core files' rule and forces every memory
or context plugin that wants its own auxiliary task to either fork
core or open a coupled core+plugin PR.

This change adds a generic plugin surface for auxiliary task
registration:

    ctx.register_auxiliary_task(
        key='memory_retain_filter',
        display_name='Memory retain filter',
        description='hindsight pre-retain dedup/extract',
        defaults={'timeout': 30, 'extra_body': {'reasoning_effort': 'low'}},
    )

After registration, the task automatically:

  - Appears in 'hermes model → Configure auxiliary models' picker via
    a new _all_aux_tasks() merge of built-in + plugin tasks
  - Has its provider/model/base_url/api_key bridged from config.yaml
    to AUXILIARY_<KEY_UPPER>_* env vars at gateway startup
    (gateway/run.py now uses a dynamic bridged-keys set instead of
    a hardcoded per-task dict)
  - Gets plugin-declared defaults (timeout, extra_body, etc.) layered
    underneath user config so unconfigured plugin tasks still work
    (agent/auxiliary_client._get_auxiliary_task_config)
  - Resets to auto via 'Reset all to auto' alongside built-ins

Validation:

  - Rejects shadowing of built-in keys (vision, compression, etc.)
  - Rejects invalid key shapes (must match [A-Za-z0-9_]+)
  - Rejects cross-plugin collisions (clear error)
  - Allows same-plugin re-registration (idempotent updates)

Plugin discovery failures (rare) fall back gracefully — the aux
config UI still shows built-in tasks if get_plugin_auxiliary_tasks()
raises, and gateway env-var bridging keeps working for built-ins.

Built-in tasks remain hardcoded in _AUX_TASKS for stability — they're
the baseline UX, and DEFAULT_CONFIG already ships their defaults.
Plugin tasks layer on top.

Tests: 15 new tests in test_plugin_auxiliary_tasks.py covering API
validation, manager state lifecycle, helper sort order, _all_aux_tasks
merge semantics, _reset_aux_to_auto inclusion of plugin tasks, and
default-layering in auxiliary_client.

Updates the gateway-bridge code-parity test (test_auxiliary_config_bridge)
to assert the new dynamic shape rather than the hardcoded literal env
var names which no longer appear post-refactor.

Motivation: this unblocks PR #20262 (hindsight smart retain pipeline)
and similar plugins that need a dedicated aux task slot. The change
is non-breaking — built-in env vars (AUXILIARY_VISION_PROVIDER, etc.)
keep working since they're produced by the same f-string template
that built the hardcoded names.
2026-05-23 17:49:47 -07:00
..
__init__.py
…
conftest.py fix(update): quarantine hermes.exe vs concurrent Windows instance (#26670) (#26677) 2026-05-19 11:10:51 -07:00
test_ai_gateway_models.py
…
test_anthropic_model_flow_stale_oauth.py
…
test_anthropic_oauth_flow.py
…
test_anthropic_provider_persistence.py
…
test_api_key_providers.py fix(tests): catch up 25 stale tests after recent merges (#28626) 2026-05-19 01:28:32 -07:00
test_apply_model_switch_result_context.py
…
test_apply_profile_override.py
…
test_arcee_provider.py
…
test_argparse_flag_propagation.py
…
test_at_context_completion_filter.py
…
test_atomic_json_write.py
…
test_atomic_yaml_write.py
…
test_auth_codex_provider.py
…
test_auth_commands.py Switch to JWT token for inference against Nous, falling back to old opaque token on failure. 2026-05-17 16:56:37 -07:00
test_auth_loopback_ssh_hint.py fix(auth): improve xAI OAuth SSH hint with visual header and auto-detected host 2026-05-18 10:26:55 -07:00
test_auth_manual_paste.py test+docs(oauth): pin manual-paste semantics and document browser-only path (#26923) 2026-05-18 20:10:52 -07:00
test_auth_nous_provider.py fix(auth) fix a few cases where refresh tokens were not rotated. 2026-05-17 16:56:37 -07:00
test_auth_profile_fallback.py
…
test_auth_provider_gate.py
…
test_auth_qwen_provider.py fix(cli): validate runtime token refresh capability in Qwen auth status 2026-05-23 17:47:36 -07:00
test_auth_ssl_macos.py
…
test_auth_toctou_file_modes.py
…
test_auth_xai_oauth_provider.py fix(xai-oauth): pin inference base_url to x.ai origin (#28952) 2026-05-19 14:51:21 -07:00
test_aux_config.py fix(aux): remove stale session_search model menu entry 2026-05-18 20:01:34 -07:00
test_azure_detect.py feat(azure-foundry): add Microsoft Entra ID auth 2026-05-18 10:14:38 -07:00
test_azure_foundry_entra.py feat(azure-foundry): add Microsoft Entra ID auth 2026-05-18 10:14:38 -07:00
test_backup.py
…
test_banner.py
…
test_banner_git_state.py
…
test_banner_pip_update.py
…
test_banner_skills.py
…
test_bedrock_model_picker.py
…
test_bundles.py feat(skills): add skill bundles — alias /<name> loads multiple skills (#28373) 2026-05-18 21:38:05 -07:00
test_chat_skills_flag.py
…
test_claw.py
…
test_clear_stale_base_url.py
…
test_cmd_update.py chore: ruff auto-fix PLR6201 resweep — tuple → set in membership tests (#27355) 2026-05-17 02:29:41 -07:00
test_coalesce_session_args.py
…
test_codex_cli_model_picker.py
…
test_codex_models.py
…
test_codex_runtime_plugin_migration.py
…
test_codex_runtime_switch.py chore: ruff auto-fix PLR6201 resweep — tuple → set in membership tests (#27355) 2026-05-17 02:29:41 -07:00
test_commands.py fix(gateway): prioritize Telegram command menu 2026-05-20 19:14:21 -07:00
test_completion.py
…
test_config.py
…
test_config_drift.py
…
test_config_env_expansion.py
…
test_config_env_refs.py
…
test_config_validation.py
…
test_container_aware_cli.py
…
test_copilot_auth.py
…
test_copilot_catalog_oauth_fallback.py
…
test_copilot_context.py
…
test_copilot_in_model_list.py
…
test_copilot_token_exchange.py
…
test_cron.py feat: add cron job profile support 2026-05-18 17:39:50 +00:00
test_curator_archive_prune.py
…
test_curator_recent_run_notice.py
…
test_curator_run.py
…
test_curator_status.py
…
test_curses_color_compat.py fix(cli): clamp curses color 8 for 8-color terminals (Docker) 2026-05-21 23:40:58 -07:00
test_custom_provider_context_length.py
…
test_custom_provider_model_switch.py fix(model): match custom provider by active base url 2026-05-19 14:50:38 -07:00
test_dashboard_browser_safe_imports.py
…
test_dashboard_lifecycle_flags.py
…
test_dashboard_profiles_nav_label.py
…
test_debug.py
…
test_dep_ensure.py feat(dep_ensure): complete Windows bootstrap — dep_ensure + install.ps1 + detection (#27845) 2026-05-18 16:34:24 +05:30
test_deprecated_cwd_warning.py
…
test_destructive_slash_confirm_gate.py
…
test_detect_api_mode_for_url.py
…
test_determine_api_mode_hostname.py
…
test_dingtalk_auth.py
…
test_discord_skill_clamp_warning.py
…
test_doctor.py fix(doctor): attach codex CLI hint to OpenAI Codex auth warning for #27975 2026-05-19 00:14:39 -07:00
test_doctor_command_install.py
…
test_doctor_dedicated_provider_skip.py
…
test_env_load_cache.py
…
test_env_loader.py fix(env): strip null bytes from .env before python-dotenv loads 2026-05-23 17:17:05 -07:00
test_env_sanitize_on_load.py
…
test_fallback_cmd.py fix(fallback): merge fallback_providers with legacy fallback_model configurations 2026-05-23 05:24:57 -07:00
test_gateway.py fix(gateway): harden Windows gateway install lifecycle 2026-05-19 11:23:15 -07:00
test_gateway_linger.py
…
test_gateway_platform_gating.py
…
test_gateway_proc_fallback.py
…
test_gateway_runtime_health.py
…
test_gateway_service.py ci(tests): add pytest-timeout 60s hard cap to break suite-teardown deadlock (#28861) 2026-05-19 17:27:24 -07:00
test_gateway_service_paths.py
…
test_gateway_windows.py test(gateway-windows): make ctypes.windll monkeypatch tolerant on non-Windows 2026-05-19 11:23:15 -07:00
test_gateway_wsl.py ci(tests): add pytest-timeout 60s hard cap to break suite-teardown deadlock (#28861) 2026-05-19 17:27:24 -07:00
test_gemini_free_tier_setup_block.py
…
test_gemini_provider.py
…
test_gmi_provider.py
…
test_goals.py
…
test_hooks_cli.py
…
test_ignore_user_config_flags.py
…
test_image_gen_picker.py refactor(image_gen): port FAL backend to plugins/image_gen/fal 2026-05-22 04:10:45 -07:00
test_install_cua_driver.py fix(cli): pre-check CUA release asset for Intel macOS before install 2026-05-21 19:17:45 -07:00
test_inventory.py
…
test_kanban_blocked_sticky.py test(kanban): cover sticky blocks for worker-initiated kanban_block (#28712) 2026-05-19 17:26:23 -07:00
test_kanban_boards.py fix(kanban): align board_exists with board discovery rules 2026-05-18 20:17:10 -07:00
test_kanban_cli.py feat(kanban): configure worktree paths and branches 2026-05-18 21:33:08 -07:00
test_kanban_core_functionality.py fix(tests): catch up 25 stale tests after recent merges (#28626) 2026-05-19 01:28:32 -07:00
test_kanban_db.py feat(kanban): warn users that scratch workspaces are deleted on completion (#30949) 2026-05-23 11:27:00 -07:00
test_kanban_db_init.py fix(kanban): serialize DB initialization 2026-05-18 20:17:48 -07:00
test_kanban_decompose.py fix: assign single-task kanban decompositions 2026-05-18 20:26:02 -07:00
test_kanban_decompose_db.py fix(kanban): detect cycles in decompose_triage_task sibling-link pre-validation 2026-05-18 09:40:44 -07:00
test_kanban_diagnostics.py fix(kanban): honor severity thresholds in diagnostics 2026-05-18 20:47:01 -07:00
test_kanban_notify.py fix(tests): allowlist tmp_path for kanban_notify artifact delivery (#30852) 2026-05-23 02:34:34 -07:00
test_kanban_specify.py
…
test_kanban_specify_db.py
…
test_kanban_swarm.py feat(cli): add kanban swarm topology helper 2026-05-18 21:10:12 -07:00
test_launcher.py
…
test_list_picker_providers.py
…
test_logs.py
…
test_managed_installs.py fix(tests): catch up 25 stale tests after recent merges (#28626) 2026-05-19 01:28:32 -07:00
test_mcp_add_command_dest.py
…
test_mcp_config.py
…
test_mcp_reload_confirm_gate.py
…
test_mcp_tools_config.py
…
test_memory_reset.py chore: ruff auto-fix PLR6201 resweep — tuple → set in membership tests (#27355) 2026-05-17 02:29:41 -07:00
test_migrate_xai.py fix(xai): align migrate retirement map with docs 2026-05-20 09:18:23 -07:00
test_model_catalog.py
…
test_model_normalize.py
…
test_model_picker_viewport.py
…
test_model_provider_persistence.py
…
test_model_switch_context_display.py
…
test_model_switch_copilot_api_mode.py
…
test_model_switch_custom_providers.py fix(model-switch): mark bare custom provider as current 2026-05-19 10:57:35 -07:00
test_model_switch_opencode_anthropic.py
…
test_model_switch_variant_tags.py
…
test_model_validation.py
…
test_models.py chore: ruff auto-fix PLR6201 resweep — tuple → set in membership tests (#27355) 2026-05-17 02:29:41 -07:00
test_models_dev_preferred_merge.py
…
test_non_ascii_credential.py
…
test_nous_auth_status_cache.py
…
test_nous_hermes_non_agentic.py
…
test_nous_inference_url_validation.py fix(security): wire Nous URL allowlist into refresh / mint persistence sites 2026-05-22 14:17:40 -07:00
test_nous_subscription.py
…
test_ollama_cloud_auth.py
…
test_ollama_cloud_provider.py
…
test_openai_codex_model_validation_fallback.py
…
test_opencode_go_flat_namespace.py
…
test_opencode_go_in_model_list.py chore: ruff auto-fix PLR6201 resweep — tuple → set in membership tests (#27355) 2026-05-17 02:29:41 -07:00
test_opencode_go_validation_fallback.py
…
test_overlay_slug_resolution.py
…
test_path_completion.py
…
test_pin_kanban_board_env.py
…
test_pip_install_detection.py feat(config): add install-method stamping + Docker detection (#27843) 2026-05-18 16:34:10 +05:30
test_placeholder_usage.py
…
test_plugin_auxiliary_tasks.py feat(plugins): add register_auxiliary_task() to PluginContext API 2026-05-23 17:49:47 -07:00
test_plugin_cli_registration.py
…
test_plugin_scanner_recursion.py
…
test_plugins.py
…
test_plugins_cmd.py fix(plugins): widen _sanitize_plugin_name for category-namespaced names 2026-05-22 19:50:32 -07:00
test_post_setup_gating.py
…
test_profile_describer.py feat(kanban): orchestrator-driven auto-decomposition on triage (#27572) 2026-05-17 13:54:12 -07:00
test_profile_distribution.py
…
test_profile_export_credentials.py
…
test_profiles.py
…
test_project_plugin_rce_bypass.py test(plugins): regression coverage for project-plugin RCE chain (#29156) 2026-05-23 01:43:52 -07:00
test_prompt_api_key.py
…
test_provider_config_validation.py
…
test_proxy.py feat(proxy): add xai upstream adapter for Grok via OAuth 2026-05-18 20:09:32 -07:00
test_pty_bridge.py test: use subprocesses for each test file (#29016) 2026-05-21 16:40:04 +05:30
test_reasoning_effort_menu.py
…
test_redact_config_bridge.py
…
test_regression_16767.py
…
test_relaunch.py
…
test_resolve_last_session.py
…
test_runtime_provider_resolution.py fix(custom): pass custom provider extra body 2026-05-21 07:48:53 -07:00
test_security_advisories.py
…
test_send_cmd.py fix(review): address Copilot follow-up on sanitizer and file decode errors 2026-05-16 23:00:58 -05:00
test_session_browse.py
…
test_session_handoff.py
…
test_session_recap.py
…
test_sessions_delete.py
…
test_set_config_value.py
…
test_setup.py
…
test_setup_agent_settings.py
…
test_setup_hermes_script.py
…
test_setup_irc.py
…
test_setup_matrix_e2ee.py
…
test_setup_model_provider.py fix(cli): preserve setup config picker writes 2026-05-19 14:23:19 -07:00
test_setup_noninteractive.py
…
test_setup_ollama_cloud_force_refresh.py
…
test_setup_openclaw_migration.py fix(tests): catch up 25 stale tests after recent merges (#28626) 2026-05-19 01:28:32 -07:00
test_setup_prompt_menus.py
…
test_setup_reconfigure.py
…
test_skills_config.py
…
test_skills_hub.py fix(skills-hub): widen identifier-dedup to GitHubSource + fix test patch path 2026-05-20 15:04:01 -07:00
test_skills_install_flags.py
…
test_skills_skip_confirm.py
…
test_skills_subparser.py
…
test_skin_engine.py fix(tui): improve charizard completion menu contrast 2026-05-18 20:05:23 -07:00
test_slack_cli.py
…
test_spotify_auth.py
…
test_startup_plugin_gating.py
…
test_status.py feat(status): show xAI OAuth login state in hermes status 2026-05-17 11:35:57 -07:00
test_status_model_provider.py
…
test_subparser_routing_fallback.py
…
test_subprocess_timeouts.py
…
test_suppress_eio_on_interrupt.py
…
test_teams_pipeline_plugin_cli.py
…
test_tencent_tokenhub_provider.py
…
test_terminal_menu_fallbacks.py
…
test_timeouts.py
…
test_tips.py
…
test_tool_token_estimation.py
…
test_tools_config.py fix: run computer use post-setup when enabling tool 2026-05-22 01:24:11 -07:00
test_tools_disable_enable.py
…
test_tui_bundled.py
…
test_tui_npm_install.py fix(tui): surface verbose tool details (#30225) 2026-05-22 00:16:52 -05:00
test_tui_resume_flow.py perf(termux): speed up bare cli prompt startup 2026-05-22 14:27:38 -07:00
test_update_autostash.py
…
test_update_check.py
…
test_update_concurrent_quarantine.py fix(update): quarantine hermes.exe vs concurrent Windows instance (#26670) (#26677) 2026-05-19 11:10:51 -07:00
test_update_config_clears_custom_fields.py
…
test_update_hangup_protection.py
…
test_update_post_pull_syntax_guard.py feat(update): syntax-validate critical files post-pull, auto-rollback on failure (#28669) 2026-05-19 03:01:02 -07:00
test_update_stale_dashboard.py chore: ruff auto-fix PLR6201 resweep — tuple → set in membership tests (#27355) 2026-05-17 02:29:41 -07:00
test_update_yes_flag.py
…
test_user_providers_model_switch.py
…
test_video_gen_picker.py
…
test_voice_wrapper.py
…
test_web_oauth_dispatch.py refactor(auth): collapse Nous inference fallback controls 2026-05-17 16:56:37 -07:00
test_web_server.py fix(test): deflake two intermittent CI failures 2026-05-22 19:46:18 -07:00
test_web_server_cron_profiles.py feat(kanban): show dashboard cron jobs across profiles 2026-05-18 21:26:45 -07:00
test_web_server_host_header.py
…
test_web_ui_build.py
…
test_webhook_cli.py
…
test_whatsapp_setup_ordering.py
…
test_xai_oauth_pkce_token_exchange.py test(xai-oauth): pin PKCE token-exchange wire format 2026-05-17 12:35:01 -07:00
test_xai_retirement.py fix(xai): align migrate retirement map with docs 2026-05-20 09:18:23 -07:00
test_xiaomi_provider.py
…