p2: digest with in-sift FIFO, SQLite caches, Honcho context, recover
Dixie is capped (max_inflight 2, queue_depth 8, queue_wait 20s) and never queued on llama-server. Streaming chat, thinking off, 45s fallback to clean. Digest and chunk-embedding caches are content-addressed SQLite (Honcho context is not cached). Recover uses the guarded Fetcher. guardian-star is refused in code.
This commit is contained in:
Vendored
+12
@@ -24,3 +24,15 @@ listen = "127.0.0.1:8890"
|
||||
# [digest]
|
||||
# model = "ornith-1.5-9b-uncensored"
|
||||
# thinking = false
|
||||
# cache = "/var/lib/sift/cache.db"
|
||||
#
|
||||
# [dixie]
|
||||
# chat = "http://dixie.scylla-hammerhead.ts.net:11434/v1/chat/completions"
|
||||
# embed = "http://straylight.scylla-hammerhead.ts.net:11437/v1/embeddings"
|
||||
# max_inflight = 2
|
||||
# queue_depth = 8
|
||||
# queue_wait = "20s"
|
||||
#
|
||||
# [context]
|
||||
# honcho = "http://rift.scylla-hammerhead.ts.net:8000"
|
||||
# workspaces = ["hermes-fleet"]
|
||||
|
||||
Reference in New Issue
Block a user