When disclosure_level=0, system prompt only injects skill name + description (summary mode). SkillDetailTool is injected into the tool set, allowing the LLM to load full instructions on-demand via skill_detail(query). This reduces context window consumption when many skills are registered. |
||
|---|---|---|
| .. | ||
| test_request_preprocessor.py | ||
| test_skill_routing.py | ||
| test_sqlite_conversation_store.py | ||