Xubin Ren 411b059dd2 refactor: replace <SILENT_OK> with structured post-run evaluation ...

- Add nanobot/utils/evaluator.py: lightweight LLM tool-call to decide notify/silent after background task execution
- Remove magic token injection from heartbeat and cron prompts
- Clean session history (no more <SILENT_OK> pollution)
- Add tests for evaluator and updated heartbeat three-phase flow

2026-03-14 17:41:08 +08:00

..

test_azure_openai_provider.py

…

test_base_channel.py

…

test_channel_plugins.py

…

test_cli_input.py

…

test_commands.py

…

test_config_migration.py

…

test_config_paths.py

…

test_consolidate_offset.py

…

test_context_prompt_cache.py

…

test_cron_service.py

…

test_dingtalk_channel.py

…

test_docker.sh

…

test_email_channel.py

…

test_evaluator.py

refactor: replace <SILENT_OK> with structured post-run evaluation

2026-03-14 17:41:08 +08:00

test_feishu_post_content.py

…

test_feishu_table_split.py

…

test_filesystem_tools.py

…

test_gemini_thought_signature.py

…

test_heartbeat_service.py

refactor: replace <SILENT_OK> with structured post-run evaluation

2026-03-14 17:41:08 +08:00

test_loop_consolidation_tokens.py

…

test_loop_save_turn.py

…

test_matrix_channel.py

…

test_mcp_tool.py

…

test_memory_consolidation_types.py

…

test_message_tool_suppress.py

…

test_message_tool.py

…

test_provider_retry.py

…

test_qq_channel.py

…

test_restart_command.py

…

test_skill_creator_scripts.py

…

test_slack_channel.py

…

test_task_cancel.py

…

test_telegram_channel.py

…

test_tool_validation.py

…

test_web_search_tool.py

…