jinglun010 730230effb fix: tolerate string-encoded skills param for LLM provider compatibility ... Some LLM providers (e.g. qwen3.7-max via DashScope OpenAI-compatible endpoint) serialize array-typed function call parameters as JSON-encoded strings instead of native JSON arrays. This causes Pydantic validation to reject the skills parameter before the function body executes, making every create_agent and load_skill call fail. Changes: - Widen skills type annotation: list[str] -> str | list[str] - Add strict_mode=False to @function_tool decorator - Parse string inputs in function body (json.loads with comma-split fallback) Tested with qwen3.7-max: create_agent successfully spawns child agents that execute 23+ exec_command calls for SQL injection testing. Closes #770		2026-07-15 14:07:11 +08:00
..
__init__.py	Restore load_skill + surface skill catalog in system prompt	2026-05-25 15:02:24 -07:00
tool.py	fix: tolerate string-encoded skills param for LLM provider compatibility	2026-07-15 14:07:11 +08:00