vrr/agent-zero
2
0
Fork 0
mirror of https://github.com/agent0ai/agent-zero.git synced 2026-07-09 17:08:29 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 4

Remove legacy skill prompt cleanup

Browse source 
Delete the empty active-skills prompt extension and its unused prompt template now that selected skills are loaded through chat history instead of protocol. Stop clearing legacy loaded_skills keys from protocol/extras in the loaded-skills hook while keeping history reattachment for compacted skill bodies.
This commit is contained in:
Alessandro 2026-07-08 12:42:43 +02:00
parent 0de0fcec0e
commit f8b06e0b12
6 changed files with 5 additions and 39 deletions
Download patch file Download diff file Expand all files Collapse all files

6
extensions/python/message_loop_prompts_after/AGENTS.md
View file

@ -2,14 +2,14 @@
## Purpose
- Own prompt protocol and extras appended around primary message-loop prompt construction.
- Own prompt protocol, prompt extras, and history reattachment around primary message-loop prompt construction.
## Ownership
- Ordered Python files own current datetime, skill recall/load context, agent info, parallel job status, and workdir extras injection.
- Ordered Python files own current datetime, relevant-skill hints, loaded-skill history reattachment, agent info, parallel job status, and workdir extras injection.
- Explicitly loaded skill bodies belong in tool-result history with metadata so they can survive persistence and be reattached after compaction.
- Explicitly loaded skill IDs are chat-wide context data, not agent-local state.
- Legacy active-skill prompt protocol injection must stay empty; selected skills are loaded through history.
- Skills must not write selected or loaded skill bodies into protocol or extras.
## Local Contracts

3
extensions/python/message_loop_prompts_after/_65_include_loaded_skills.py
View file

@ -14,9 +14,6 @@ class IncludeLoadedSkills(Extension):
if not self.agent:
return
loop_data.protocol_persistent.pop("loaded_skills", None)
loop_data.extras_persistent.pop("loaded_skills", None)
skill_names = skills.get_loaded_skill_names(self.agent)
if not skill_names:
return