v2 plan: note the router /props autoload fact and the v2.1 follow-up

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
This commit is contained in:
2026-09-25 10:12:29 -07:00
co-authored by Claude Fable 5.1
parent 6c8cbbc78d
commit 962ea2aea4
+6
View File
@@ -67,3 +67,9 @@ reason.
2's fp differs from turn 1's, yet the test expects reuse") and the session ended on a
malformed tool call. Test fault (mine): later turns are now appended after the first user
message. Resumed from the working tree.
- 2026-09-25, learned from titan's router (llama-server b10964) while v2 ran: in router mode a
plain `GET /props` answers `n_ctx: 0` (`role: router`), and `GET /props?model=X` **autoloads X**
when `models_autoload` is on — the same trap as `/slots?model=X`. Task 01's poller therefore
learns nothing on a real router and the guard stays inert there. Follow-up for v2.1: query
`/props?model=X` only for models `/v1/models` lists as loaded, never for others. Not a defect
in what the tasks asked for; a gap in what the owner knew when writing them.