mirror of
https://github.com/agent0ai/agent-zero.git
synced 2026-10-20 02:39:37 +00:00
60073f283a
Add LLMResult.non_llm classmethod for non-LLM AI turns (greeting, intervention progress) so stored metadata does not claim a Responses-API turn. Rename is_thoughts_fallback to looks_like_tool_call (inverted polarity: True when valid A0 response JSON). Rework check to accept any dict containing at least one A0 key (thoughts/headline/tool_name/tool_args); empty dicts and non-A0 dicts fall through to the raw-text fallback branch. Fix drawMessageAgent kvps order to thoughts, tool_name, tool_args keys (reserved keys skipped), then step; reserved keys (thoughts, step, reasoning, tool_name, tool_args, args, headline) win over colliding tool_args keys. Document Hello! seeding turns as few-shot example, drawMessageDefault as deprecated, and plugin get_log_object duplication as intentional. Align context_doctor DOX kvps sentence with code (reasoning only, not thoughts). |
||
|---|---|---|
| .. | ||
| a2a_chat.py | ||
| a2a_chat.py.dox.md | ||
| AGENTS.md | ||
| browser._py | ||
| browser_do._py | ||
| browser_open._py | ||
| call_subordinate.py | ||
| call_subordinate.py.dox.md | ||
| document_query.py | ||
| document_query.py.dox.md | ||
| knowledge_tool._py | ||
| notify_user.py | ||
| notify_user.py.dox.md | ||
| parallel.py | ||
| parallel.py.dox.md | ||
| response.py | ||
| response.py.dox.md | ||
| scheduler.py | ||
| scheduler.py.dox.md | ||
| search_engine.py | ||
| search_engine.py.dox.md | ||
| skills_tool.py | ||
| skills_tool.py.dox.md | ||
| unknown.py | ||
| unknown.py.dox.md | ||
| vision_load.py | ||
| vision_load.py.dox.md | ||
| wait.py | ||
| wait.py.dox.md | ||