Backlog: F3's gaps closed and checked on the PoC, cache_salt against a real vLLM

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
This commit is contained in:
Ilker ManapandClaude Opus 5.5 committed 2026-10-08 16:16:00 +02:00
1 parent 26630274f4
commit 99829b3124
1 file changed
+7 -1
+7 -1
View File
@@ -976,7 +976,13 @@ one); `x-llmgw-sources`; before guardInput; never cached; metrics. Default colle
wins, 30 s cache, `ctl kb default`, console action; never refuse); the
portal chat's Documents picker (collection, default or none; sources listed
under the answer; a header the page sends itself is dropped). `cache_salt` per organization on requests given passages, sent to vLLM
replicas only (chosen replica's engine). Left: returned passages
replicas only (chosen replica's engine). Checked on the PoC 2026-10-08:
vLLM 0.30.0 (cuda01) with TinyLlama-1.1B AWQ run by hand beside the 35B in
the card's last 2.3 GB — a 668-token prompt reused 656 tokens under the same
salt and 0 under another's, with identical text (llmgw cannot place it
there: placement takes whole GPUs). Live on the PoC: a team default answers
a request without the header, `none` turns it off, an explicit header with
k=2 gives two sources and no more, llmgw-kb lists owners by path. Left: returned passages
are not audited per request (the header and the kept request record them).
### F4. Adapter training (L, after F1–F3)