kami 07819ec82d fix(inference): fold non-L0 SYSTEM entries into the leading system message
Strict chat templates (Qwen3.5) reject any system message after index 0.
Recalled L3 memory, L2 stage summaries, and retrieval entries carry
EntryRole.SYSTEM and rendered as standalone mid-conversation system turns,
making llama-server 400 on every router turn once L3 recall returned hits.
2026-06-11 21:55:28 +04:00
S
Description
No description provided
4.9 MiB
Languages
Kotlin 88.4%
Go 11.4%
Python 0.2%