odysseus

mirror of https://github.com/pewdiepie-archdaemon/odysseus.git synced 2026-10-15 03:12:21 +02:00

Files

T

Harshit Ojha b5b76fe46d fix(skills): inject published skills when Auto-approve is off (#6643 )

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

2026-10-13 21:02:23 +01:00

docs

fix(docs): map live VectorRAG result shapes (#5960 )

2026-08-17 00:07:12 +01:00

faces

Odysseus v1.0

2026-05-31 23:58:26 +09:00

hwfit

chore(publication): close pre-integration release blockers

2026-10-05 01:37:49 +01:00

memory

fix(skills): inject published skills when Auto-approve is off (#6643 )