kyle
2f9d3d97e6
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.
39 lines
1.2 KiB
TOML
39 lines
1.2 KiB
TOML
# sift configuration. P0 uses -listen and -deny-prefix; remaining keys are P1+.
|
|
# This file is an example: the service does not assume Nix store paths.
|
|
|
|
listen = "127.0.0.1:8890"
|
|
|
|
# Extra CIDRs blocked by the SSRF guard (pre-check + Control). Home WAN /32s
|
|
# belong here so a fetch of the public IP cannot hairpin into the LAN.
|
|
# Set on-box; do not commit residential addresses to git.
|
|
# deny_prefixes = ["203.0.113.0/24"]
|
|
|
|
# [upstreams]
|
|
# searxng = "http://127.0.0.1:8888"
|
|
# dixie = "http://dixie.scylla-hammerhead.ts.net:11434/v1"
|
|
# honcho = "http://rift.scylla-hammerhead.ts.net:8000"
|
|
|
|
# user_agent = "sift/dev"
|
|
|
|
# [self_ip]
|
|
# sources = ["ddns:example.sn.mynetname.net", "trace:https://1.1.1.1/cdn-cgi/trace"]
|
|
# interval = "10m"
|
|
# keep_previous = "24h"
|
|
# path = "/var/lib/sift/self_ip.json"
|
|
|
|
# [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"]
|