mirror of
https://github.com/pewdiepie-archdaemon/odysseus.git
synced 2026-10-22 05:47:51 +00:00
b5b76fe46d
With Auto-approve OFF the agent loop asked get_relevant_skills for min_confidence=2.0, meant as 'published only'. The gate applies the confidence check to published skills too, and confidence is 0-1, so no user skill was ever injected, published or not. The explicit-activation path already treats OFF as status == published. Add a published_only flag to get_relevant_skills and pass it from both callers that used the sentinel (relevance injection and the skill preflight). Auto-approve ON is unchanged: a skill still needs a passing audit and the confidence threshold. Fixes #6634 |
||
|---|---|---|
| .. | ||
| __init__.py | ||
| builtin_skills.py | ||
| memory.py | ||
| memory_extractor.py | ||
| memory_vector.py | ||
| service.py | ||
| skill_extractor.py | ||
| skill_format.py | ||
| skill_importer.py | ||
| skill_lifecycle.py | ||
| skills.py | ||