refactor: centralize llm provider transport
This commit is contained in:
+3
-2
@@ -38,8 +38,9 @@ background scheduler
|
||||
adapters. Root `database.py` remains the legacy schema/composition anchor and combines the
|
||||
feature repository mixins; do not add feature queries to it.
|
||||
- `backend/jobs/` owns job definitions, locks, retries, idempotency, and persisted run state.
|
||||
- `backend/llm/` owns model selection, membership/quota checks, fallback, streaming rules,
|
||||
and call audit. Feature agents only prepare context and provider payloads.
|
||||
- `backend/llm/` owns model selection, membership/quota checks, fallback, provider transport,
|
||||
streaming rules, and call audit. Feature agents only prepare messages and interpret
|
||||
feature-specific results.
|
||||
- `frontend/shared/` is the only browser API/state/Shell/component boundary.
|
||||
- `frontend/pages/` owns page-local behavior. The original runtime was split mechanically;
|
||||
source markers and preservation tests prove that the pieces reassemble to the audited
|
||||
|
||||
Reference in New Issue
Block a user