correx

T

kami 883e23dec7 feat(router,inference,config): pin narration to a configured model_id

[router.narration] model_id selects which provider handles narration turns
instead of generic capability routing — lets a small/fast model own narration
while the main model keeps CHAT/STEERING.

- NarrationSettings.modelId parsed from TOML, threaded via RouterConfig
  .narrationModelId into DefaultRouterFacade.narrate (3-arg route)
- DefaultInferenceRouter: exact-id match against healthy providers, with a
  post-select health check; any miss logs WARN and falls back to capability
  routing (never fails the narration turn)
- onUserInput unchanged — only narrate uses the pinned model (tested)

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

apps

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

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

core

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

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

docs

fix(kernel,router): rehydrate by CAS content hash (F-021) + narration budget

2026-06-09 10:14:04 +04:00

examples/workflows

feat(freestyle): two-phase planning->execution driver (Slice 4)