mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-06-02 07:11:49 +00:00
69b74c15a3
Two small bugs in the kanban dispatcher's CLI surface that were silently degrading two distinct workflows. Bundled because the test files and the surrounding code surface overlap. ## #33488: hermes kanban dispatch ignored kanban.max_in_progress / max_spawn The CLI wrapper in hermes_cli/kanban.py:_cmd_dispatch only passed default_assignee and max_in_progress_per_profile through to dispatch_once. The global concurrency cap (kanban.max_in_progress) and the per-tick spawn limit (kanban.max_spawn) were silently dropped, so operators using 'hermes kanban dispatch' as a one-shot or in a custom loop couldn't reach either cap from config — only the gateway embedded dispatcher honored them. Fix: read both keys from config in the same coerce-positive-int helper that already handled max_in_progress_per_profile. CLI --max still wins over config kanban.max_spawn when both are present (explicit operator signal beats default), but absent --max falls back to config. ## #29415: synthesizer crashed in retry loop on missing skill hermes_cli/kanban_swarm.py:212 hardcoded skills=['avoid-ai-writing'], a skill that doesn't exist in the bundled skills/ directory or any registered hub source. Every synthesizer worker spawn failed at CLI startup with 'Unknown skill(s): avoid-ai-writing' before the agent loop even started — the dispatcher retried up to failure_limit (default 2), then auto-blocked the task, then dependency rules could re-promote it, looping forever until manual intervention. Fix: replace with 'humanizer' which is bundled at skills/creative/humanizer/SKILL.md (description: 'Humanize text: strip AI-isms and add real voice'). That's the obvious intent behind the 'avoid-ai-writing' name, and the skill is platform-portable (linux/macos/windows) so it works on every supported runtime. ## Tests tests/hermes_cli/test_kanban_cli_dispatch_passthrough.py — 4 cases: - CLI passes max_in_progress / max_spawn / default_assignee / max_in_progress_per_profile from config to dispatch_once - CLI --max flag overrides config kanban.max_spawn - Invalid cap values (0, -1, 'abc', '1.5') silently fall through to None - kanban_swarm.py no longer references 'avoid-ai-writing' AND the replacement 'humanizer' skill exists at the expected on-disk path Kanban suite: 468/468 pass (was 464; +4 new regression tests). |
||
|---|---|---|
| .. | ||
| acp | ||
| acp_adapter | ||
| agent | ||
| cli | ||
| cron | ||
| docker | ||
| e2e | ||
| fakes | ||
| gateway | ||
| hermes_cli | ||
| hermes_state | ||
| honcho_plugin | ||
| integration | ||
| openviking_plugin | ||
| plugins | ||
| providers | ||
| run_agent | ||
| scripts | ||
| skills | ||
| stress | ||
| tools | ||
| tui_gateway | ||
| website | ||
| __init__.py | ||
| conftest.py | ||
| run_interrupt_test.py | ||
| test_account_usage.py | ||
| test_atomic_replace_symlinks.py | ||
| test_base_url_hostname.py | ||
| test_batch_runner_checkpoint.py | ||
| test_bitwarden_secrets.py | ||
| test_cli_file_drop.py | ||
| test_cli_manual_compress.py | ||
| test_cli_skin_integration.py | ||
| test_ctx_halving_fix.py | ||
| test_docker_home_override_scripts.py | ||
| test_empty_model_fallback.py | ||
| test_env_loader_secret_sources.py | ||
| test_evidence_store.py | ||
| test_gateway_streaming_nested_config.py | ||
| test_get_tool_definitions_cache_isolation.py | ||
| test_hermes_bootstrap.py | ||
| test_hermes_constants.py | ||
| test_hermes_home_profile_warning.py | ||
| test_hermes_logging.py | ||
| test_hermes_state.py | ||
| test_hermes_state_wal_fallback.py | ||
| test_honcho_client_config.py | ||
| test_honcho_session_context.py | ||
| test_install_sh_browser_install.py | ||
| test_install_sh_pythonpath_sanitization.py | ||
| test_install_sh_root_fhs_uv_python_path.py | ||
| test_install_sh_setup_wizard_tty_probe.py | ||
| test_install_sh_symlink_stomp.py | ||
| test_install_sh_termux_network_prereqs.py | ||
| test_ipv4_preference.py | ||
| test_lazy_session_regressions.py | ||
| test_lint_config.py | ||
| test_live_system_guard_self_test.py | ||
| test_mcp_serve.py | ||
| test_mini_swe_runner.py | ||
| test_minimax_model_validation.py | ||
| test_minimax_oauth.py | ||
| test_minisweagent_path.py | ||
| test_model_picker_scroll.py | ||
| test_model_tools.py | ||
| test_model_tools_async_bridge.py | ||
| test_ollama_num_ctx.py | ||
| test_package_json_lazy_deps.py | ||
| test_packaging_metadata.py | ||
| test_plugin_skills.py | ||
| test_process_loop_event_loop_warning.py | ||
| test_project_metadata.py | ||
| test_retry_utils.py | ||
| test_run_tests_parallel.py | ||
| test_sanitize_tool_error.py | ||
| test_sql_injection.py | ||
| test_subprocess_home_isolation.py | ||
| test_termux_all_extra_compat.py | ||
| test_timezone.py | ||
| test_toolset_distributions.py | ||
| test_toolsets.py | ||
| test_trajectory_compressor.py | ||
| test_trajectory_compressor_async.py | ||
| test_transform_llm_output_hook.py | ||
| test_transform_tool_result_hook.py | ||
| test_tui_gateway_server.py | ||
| test_utils_truthy_values.py | ||
| test_yuanbao_integration.py | ||
| test_yuanbao_markdown.py | ||
| test_yuanbao_pipeline.py | ||
| test_yuanbao_proto.py | ||