kami df3ee0bbe0 fix(inference): narration model_id accepts bare provider id from TOML ...

The router matched only the adapter-prefixed registry id
(llama-cpp:narrator) while the operator's [router.narration] model_id
naturally repeats the bare [[providers]] id (narrator), so the match
always failed and narration silently fell back to the slow main model.
Match either form.

2026-06-12 13:56:28 +04:00

..

src/main/kotlin/com/correx/core/inference

fix(inference): narration model_id accepts bare provider id from TOML

2026-06-12 13:56:28 +04:00

build.gradle

feat(router,inference,config): pin narration to a configured model_id

2026-06-10 20:53:28 +04:00