Teknium 2ba1cfeb2e feat(goals): completion contracts for /goal — evidence-based judging (#50501) ... Adds an optional structured completion contract to the standing-goal loop, adapted from OpenAI Codex's /goal guidance (a durable objective works best when it names what done means, how to prove it, what not to break, what's in scope, and when to stop). A contract has five optional fields — outcome, verification, constraints, boundaries, stop_when. When set, the continuation prompt tells the agent to target the verification surface and respect constraints, and the judge marks the goal done only when the verification criterion is met with concrete evidence (command result, file excerpt, test output) instead of a loose "looks done" claim. This tightens the most common /goal failure mode: premature completion / endless over-continuation on an underspecified goal. Two ways to set a contract, both backward compatible (bare /goal <text> behaves exactly as before): - /goal draft <objective> — expands plain text into a full contract via the goal_judge aux model (cache-safe side call), falls back to a free-form goal if the model is unavailable. - /goal <text> with inline 'field: value' lines (verify:, constraints:, boundaries:, stop when:, ...). Plain goals with an incidental colon are not mangled — only known field prefixes are pulled out. - /goal show prints the active contract. Contracts persist in SessionDB.state_meta alongside the goal (survive /resume), compose with /subgoal criteria, and old goal rows load unchanged. CLI + every gateway platform via the shared GoalManager engine; zero new model tools. Tests: +18 in tests/hermes_cli/test_goals.py (parse/serialize/judge-prompt/ draft/fallback), 73/73 green; 42/42 across the broader goal test surface; live E2E roundtrip (set -> persist -> reload -> contract-aware prompts) green.		2026-06-22 12:20:09 -07:00
..
__init__.py
conftest.py
conftest_dashboard_auth.py
test_active_sessions.py
test_anthropic_model_flow_stale_oauth.py
test_anthropic_oauth_flow.py
test_anthropic_picker_curated.py
test_anthropic_provider_persistence.py
test_api_key_providers.py
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_codex_self_heal.py
test_auth_commands.py	feat(providers): remove google-gemini-cli + google-antigravity OAuth providers (#50492)	2026-06-21 19:53:27 -07:00
test_auth_loopback_ssh_hint.py
test_auth_manual_paste.py
test_auth_nous_provider.py
test_auth_profile_fallback.py
test_auth_provider_gate.py
test_auth_qwen_provider.py
test_auth_ssl_macos.py
test_auth_toctou_file_modes.py
test_auth_usable_secret.py
test_auth_xai_oauth_provider.py
test_aux_config.py
test_azure_detect.py
test_azure_foundry_entra.py
test_backup.py	test(backup): add regression tests for restore_quick_snapshot path traversal	2026-06-21 12:44:22 -07:00
test_banner.py	fix(banner): don't advertise toolsets/skills the agent wasn't given (#50497)	2026-06-21 19:08:54 -07:00
test_banner_git_state.py
test_banner_pip_update.py
test_banner_skills.py
test_bedrock_model_picker.py
test_billing_cli.py
test_billing_portal_url.py
test_billing_scope_stepup.py
test_build_info.py
test_bundles.py
test_chat_skills_flag.py
test_claw.py
test_clear_stale_base_url.py
test_cli_active_session_limit.py
test_cli_output.py
test_cmd_update.py
test_cmd_update_docker.py
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
test_commands.py
test_completion.py
test_config.py	Address email pairing review feedback	2026-06-21 22:43:57 -07:00
test_config_drift.py
test_config_env_expansion.py
test_config_env_refs.py
test_config_validation.py
test_container_aware_cli.py
test_container_boot.py	fix(container): detect dashboard role under s6-overlay v3 (#49196) (#50600)	2026-06-22 15:35:38 +10:00
test_context_switch_guard.py	fix(cli): log instead of swallow preflight-warning errors; consistent TUI warning field	2026-06-21 16:31:56 +05:30
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
test_cron_fire_dashboard.py
test_cron_parser_builder.py
test_ctrlg_editor_submit.py	feat(cli): Ctrl+G submits the edited draft on save (TUI parity) (#50560)	2026-06-21 22:43:55 -07:00
test_curator_archive_prune.py
test_curator_recent_run_notice.py
test_curator_run.py
test_curator_status.py
test_curses_arrow_keys.py
test_curses_color_compat.py
test_curses_ui_fuzzy_rank.py
test_curses_ui_search.py
test_custom_provider_context_length.py
test_custom_provider_identity.py
test_custom_provider_model_switch.py
test_dashboard_admin_endpoints.py
test_dashboard_auth_401_reauth.py
test_dashboard_auth_audit.py
test_dashboard_auth_cookies.py
test_dashboard_auth_gate.py	fix(security): close hermes-0day MCP-persistence attack surface	2026-06-21 19:05:27 -07:00
test_dashboard_auth_middleware.py
test_dashboard_auth_password_login.py
test_dashboard_auth_plugin_hook.py
test_dashboard_auth_prefix.py
test_dashboard_auth_provider_base.py
test_dashboard_auth_status_endpoint.py
test_dashboard_auth_stub_provider.py
test_dashboard_auth_ws_auth.py	fix(security): fail-closed when WebSocket peer is empty in loopback mode	2026-06-21 13:33:18 -07:00
test_dashboard_auth_ws_tickets.py
test_dashboard_browser_safe_imports.py
test_dashboard_lifecycle_flags.py
test_dashboard_profiles_nav_label.py
test_dashboard_register.py
test_dashboard_tui_backcompat.py
test_dashboard_unified_launch.py
test_debug.py
test_default_interface_resolution.py
test_dep_ensure.py
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	feat(providers): remove google-gemini-cli + google-antigravity OAuth providers (#50492)	2026-06-21 19:53:27 -07:00
test_doctor_command_install.py
test_doctor_dedicated_provider_skip.py
test_dump_git_commit.py
test_dump_terminal_backend.py
test_ensure_hermes_home_uid_34107.py
test_ensure_utf8_locale.py
test_env_load_cache.py
test_env_loader.py
test_env_sanitize_on_load.py
test_fallback_cmd.py
test_gateway.py
test_gateway_linger.py
test_gateway_platform_gating.py
test_gateway_proc_fallback.py
test_gateway_restart_loop.py
test_gateway_runtime_health.py
test_gateway_s6_dispatch.py
test_gateway_service.py
test_gateway_service_paths.py
test_gateway_windows.py
test_gateway_wsl.py
test_gemini_free_tier_setup_block.py
test_gemini_provider.py
test_gmi_provider.py
test_goals.py	feat(goals): completion contracts for /goal — evidence-based judging (#50501)	2026-06-22 12:20:09 -07:00
test_graphical_browser_detection.py
test_gui_command.py
test_gui_uninstall.py
test_hooks_cli.py
test_ignore_user_config_flags.py
test_image_gen_picker.py
test_install_cua_driver.py	fix(computer_use): probe cua-driver-rs release tag, not monorepo releases/latest	2026-06-22 06:42:30 -07:00
test_inventory.py	fix(picker): keep flat-namespace reseller first-party models in desktop picker	2026-06-22 06:09:08 -07:00
test_inventory_pricing.py
test_kanban_blocked_sticky.py
test_kanban_boards.py
test_kanban_cli.py
test_kanban_cli_dispatch_passthrough.py
test_kanban_core_functionality.py	refactor(kanban): fold worker/orchestrator skills into injected guidance (#50473)	2026-06-21 17:06:48 -07:00
test_kanban_db.py	fix(kanban): bound the cross-process init lock so connect() can't hang forever (#50353)	2026-06-21 12:43:41 -07:00
test_kanban_db_init.py
test_kanban_decompose.py
test_kanban_decompose_db.py
test_kanban_default_assignee.py
test_kanban_diagnostics.py
test_kanban_dispatch_lock.py	fix(kanban): single-writer dispatch lock to prevent orphan-dispatcher DB corruption (#50331)	2026-06-21 12:06:24 -07:00
test_kanban_goal_mode.py	feat(goals): /goal wait <pid> — park the loop on a background process (#50503)	2026-06-22 06:27:29 -07:00
test_kanban_init_lock_bounded.py	fix(kanban): bound the cross-process init lock so connect() can't hang forever (#50353)	2026-06-21 12:43:41 -07:00
test_kanban_lifecycle_hooks.py	feat(kanban): add task lifecycle plugin hooks (claimed/completed/blocked) (#50349)	2026-06-21 12:38:14 -07:00
test_kanban_notify.py
test_kanban_per_profile_cap.py
test_kanban_promote.py
test_kanban_reclaim_claim_lock_guard.py	fix(kanban): make reclaim claim-lock-aware to stop task/run status desync (#50366)	2026-06-21 12:49:07 -07:00
test_kanban_specify.py
test_kanban_specify_db.py
test_kanban_swarm.py
test_kanban_worker_image_extraction.py
test_kanban_worker_spawn_toolsets.py
test_kanban_worker_terminal_cwd.py	fix(kanban): pin worker TERMINAL_CWD to the task workspace (#50348)	2026-06-21 12:43:37 -07:00
test_launcher.py
test_list_picker_providers.py
test_logs.py	refactor(gateway): migrate slack/dingtalk/whatsapp/matrix/feishu/telegram/wecom/email/sms adapters to bundled plugins	2026-06-20 10:26:45 -07:00
test_managed_installs.py
test_managed_scope.py
test_managed_scope_cli_config.py
test_managed_scope_config.py
test_managed_scope_env.py
test_managed_scope_loaders.py
test_managed_scope_overlay.py
test_managed_scope_regression.py
test_managed_scope_surfacing.py
test_managed_scope_writeguard.py
test_managed_uv.py
test_mcp_add_command_dest.py
test_mcp_catalog.py
test_mcp_config.py
test_mcp_reload_confirm_gate.py
test_mcp_security.py	fix(security): close hermes-0day MCP-persistence attack surface	2026-06-21 19:05:27 -07:00
test_mcp_startup.py
test_mcp_tools_config.py
test_memory_providers.py
test_memory_reset.py
test_memory_setup.py
test_memory_setup_provider_arg.py
test_migrate_xai.py
test_model_catalog.py
test_model_cost_guard.py
test_model_normalize.py
test_model_picker_expensive_confirm.py
test_model_picker_viewport.py
test_model_provider_persistence.py	feat(providers): remove google-gemini-cli + google-antigravity OAuth providers (#50492)	2026-06-21 19:53:27 -07:00
test_model_switch_context_display.py
test_model_switch_copilot_api_mode.py
test_model_switch_custom_providers.py	fix(picker): keep flat-namespace reseller first-party models in desktop picker	2026-06-22 06:09:08 -07:00
test_model_switch_opencode_anthropic.py
test_model_switch_persist_default.py
test_model_switch_variant_tags.py
test_model_validation.py
test_models.py
test_models_dev_preferred_merge.py
test_non_ascii_credential.py
test_nous_account.py
test_nous_auth_keepalive.py	fix Nous auth refresh for idle agents	2026-06-21 22:43:48 -07:00
test_nous_auth_status_cache.py
test_nous_hermes_non_agentic.py
test_nous_inference_url_validation.py	fix(auth): heal poisoned Nous inference URL on refresh instead of retaining it	2026-06-20 10:53:45 -07:00
test_nous_subscription.py
test_ollama_cloud_auth.py
test_ollama_cloud_provider.py
test_openai_codex_model_validation_fallback.py
test_openai_picker_curated.py
test_opencode_go_flat_namespace.py
test_opencode_go_in_model_list.py
test_opencode_go_validation_fallback.py
test_overlay_slug_resolution.py
test_path_completion.py
test_picker_prewarm.py
test_pin_kanban_board_env.py
test_pip_install_detection.py
test_placeholder_usage.py
test_plugin_auxiliary_tasks.py
test_plugin_cli_registration.py
test_plugin_scanner_recursion.py
test_plugins.py	docs(plugins): document acting from hooks via ctx.profile_name + dispatch_tool (#50352)	2026-06-21 12:54:40 -07:00
test_plugins_cmd.py
test_plugins_cmd_category_discovery.py
test_plugins_cmd_enable_disable_nested.py
test_plugins_cmd_list.py
test_plugins_transcription_registration.py
test_plugins_tts_registration.py
test_post_setup_gating.py
test_profile_describer.py
test_profile_distribution.py
test_profile_export_credentials.py
test_profiles.py
test_profiles_s6_hooks.py
test_project_plugin_rce_bypass.py	fix(security): restrict dashboard plugin backend import to bundled plugins (#43719)	2026-06-22 17:51:37 +05:30
test_prompt_api_key.py
test_prompt_compose_command.py	feat(cli): /prompt — compose your next prompt in $EDITOR (#50509)	2026-06-21 20:21:33 -07:00
test_prompt_size.py
test_provider_catalog.py	feat(providers): remove google-gemini-cli + google-antigravity OAuth providers (#50492)	2026-06-21 19:53:27 -07:00
test_provider_config_validation.py
test_provider_groups.py
test_provider_live_curated_merge.py
test_provider_parity.py
test_proxy.py
test_psutil_android_extract.py
test_pty_bridge.py
test_reasoning_effort_menu.py
test_reasoning_full_command.py	feat(cli): /reasoning full — show complete thinking, not 10-line clamp (#50499)	2026-06-21 20:21:11 -07:00
test_redact_config_bridge.py
test_regression_16767.py
test_relaunch.py
test_resolve_last_session.py
test_resolve_provider_openrouter_pool.py
test_run_with_idle_timeout.py
test_runtime_provider_resolution.py	fix Nous auth refresh for idle agents	2026-06-21 22:43:48 -07:00
test_safe_mode.py
test_secret_prompt.py
test_secrets_bitwarden_non_tty.py
test_security_advisories.py
test_security_audit.py
test_security_audit_startup.py	feat(security): startup security posture audit (warn-on-load)	2026-06-21 19:05:27 -07:00
test_send_cmd.py
test_service_manager.py
test_session_browse.py
test_session_handoff.py
test_session_recap.py
test_sessions_delete.py
test_set_config_value.py	fix(config): redact api_key in config show/set output (#50245) (#50313)	2026-06-21 11:50:31 -07:00
test_setup.py	refactor(gateway): migrate slack/dingtalk/whatsapp/matrix/feishu/telegram/wecom/email/sms adapters to bundled plugins	2026-06-20 10:26:45 -07:00
test_setup_agent_settings.py
test_setup_blank_slate.py	feat(setup): Blank Slate setup mode — minimal agent, opt in to everything (#36733)	2026-06-20 10:45:55 -07:00
test_setup_hermes_script.py
test_setup_irc.py
test_setup_matrix_e2ee.py
test_setup_menu_curses_migration.py
test_setup_model_provider.py
test_setup_noninteractive.py
test_setup_ollama_cloud_force_refresh.py
test_setup_openclaw_migration.py
test_setup_prompt_menus.py
test_setup_reconfigure.py
test_signal_handler_kanban_worker.py
test_skills_config.py
test_skills_hub.py
test_skills_install_flags.py
test_skills_skip_confirm.py
test_skills_subparser.py
test_skin_engine.py
test_slack_cli.py
test_spotify_auth.py	fix(spotify): quarantine dead tokens on terminal refresh failure	2026-06-20 23:23:47 -07:00
test_startup_plugin_gating.py
test_status.py
test_status_model_provider.py
test_subcommands_batch.py
test_subcommands_followup.py
test_subcommands_profile_gateway.py
test_subparser_routing_fallback.py
test_subprocess_timeouts.py
test_suppress_eio_on_interrupt.py
test_system_stats_platform.py
test_systemd_optional_directives.py
test_teams_pipeline_plugin_cli.py
test_telegram_managed_bot.py
test_tencent_tokenhub_provider.py
test_terminal_menu_fallbacks.py
test_timeouts.py
test_timestamps_command.py	feat(cli): /timestamps command + timestamps in /history (#50506)	2026-06-21 22:44:25 -07:00
test_tips.py
test_tool_token_estimation.py
test_tools_config.py
test_tools_disable_enable.py
test_tts_picker.py
test_tui_bundled.py
test_tui_heap_sizing.py
test_tui_mouse_residue_suppression.py
test_tui_npm_install.py	fix(cli): auto-restore a deleted ui-tui workspace from git before TUI launch	2026-06-21 13:10:22 -07:00
test_tui_resume_flow.py
test_uninstall_node_symlinks.py
test_update_autostash.py
test_update_check.py	fix(update): don't count across shallow-clone boundary (bogus '12492 commits behind') (#50784)	2026-06-22 05:39:11 -07:00
test_update_concurrent_quarantine.py	fix(gateway): cold-start installed Windows gateway after update when none was running (#50804)	2026-06-22 06:02:31 -07:00
test_update_config_clears_custom_fields.py	fix(model): clear stale endpoint credentials across switches	2026-06-19 19:58:26 -07:00
test_update_hangup_protection.py
test_update_interrupted_recovery.py
test_update_modified_notice.py
test_update_post_pull_syntax_guard.py
test_update_stale_dashboard.py
test_update_yes_flag.py
test_update_zip_atomic_replace.py	fix(cli): make ZIP-update directory replace atomic so it can't delete ui-tui	2026-06-21 13:10:22 -07:00
test_update_zip_symlink_reject.py
test_user_providers_model_switch.py
test_uv_tool_update.py
test_verify_core_dependencies.py
test_video_gen_picker.py
test_voice_wrapper.py
test_web_oauth_dispatch.py	feat(providers): remove google-gemini-cli + google-antigravity OAuth providers (#50492)	2026-06-21 19:53:27 -07:00
test_web_server.py	fix(security): restrict dashboard plugin backend import to bundled plugins (#43719)	2026-06-22 17:51:37 +05:30
test_web_server_boot_handshake.py	test(web_server): add integration tests for desktop boot handshake fix	2026-06-21 12:29:18 -07:00
test_web_server_cron_profiles.py
test_web_server_files.py
test_web_server_fs.py
test_web_server_host_header.py
test_web_server_messaging_profiles.py
test_web_server_oauth_write.py
test_web_server_profile_unification.py
test_web_server_pty_import.py
test_web_server_session_search.py
test_web_server_skill_editor.py
test_web_server_skills_profiles.py
test_web_ui_build.py
test_webhook_cli.py
test_whatsapp_cloud_setup.py
test_whatsapp_setup_ordering.py
test_win_pty_bridge.py
test_windows_native_docs.py
test_xai_curated_models.py
test_xai_model_flow.py
test_xai_oauth_pkce_token_exchange.py
test_xai_oauth_profile_auth.py
test_xai_oauth_refresh.py
test_xai_oauth_writethrough.py
test_xai_provider_labels.py
test_xai_retirement.py
test_xiaomi_provider.py