Reusing answers: a response cache per project, exact match, opt-in with a TTL
llmgw keys cache --project P --ttl 1h [--any] | --off, and Cache answers… on the console's project menu. The same request — project, endpoint, canonical model and the body without stream, stream_options, user, metadata, store and service_tier, keys sorted — is answered from the gateway's memory for the TTL. Only reproducible answers (temperature 0 or a seed; embeddings, rerank, score) unless --any; only a whole 200 from the model asked for, not a fallback's, a canary's, or one a guardrail changed. Looked up after the limits and the input guardrails; the output policy judges a reused answer; no_store and stored conversations bypass it. Streamed answers are kept put back together and streamed back as chunks. x-llmgw-cache: hit|miss|bypass, Age on a hit, Cache-Control: no-cache or x-llmgw-cache: no to bypass. A hit is recorded with no tokens and no cost, marked cache_hit (migration 0027) and shown by ctl request. An LRU bounded by router.cache.max_bytes and max_entry_bytes; llmgw_cache_requests_total, llmgw_cache_bytes, llmgw_cache_entries. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
This commit is contained in:
1 parent
30f7f3474a
commit
44f3a9e31d
27 files changed
+2066
-11
No files matched your search
@@ -159,6 +159,12 @@ router:
|
||||
# back to a client that did not ask for it.
|
||||
inject_usage: true
|
||||
max_body_bytes: 33554432
|
||||
# Memory for the answers of projects that reuse them (llmgw keys cache),
|
||||
# all together; the least recently used go first. Nothing is reused until a
|
||||
# project turns it on.
|
||||
# cache:
|
||||
# max_bytes: 134217728 # 128 MB
|
||||
# max_entry_bytes: 1048576 # 1 MB
|
||||
|
||||
timeouts:
|
||||
dial: 5s
|
||||
|
||||
Reference in new issue
Block a user