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.
10 lines
680 B
JSON
10 lines
680 B
JSON
{
|
|
"autogen": "linux/(amd64|arm64|loong64|ppc64le|s390x|riscv64|386|arm$)",
|
|
"autotag": "darwin/(amd64|arm64)|freebsd/(amd64|arm64|386|arm$)|linux/(386|amd64|arm$|arm64|loong64|ppc64le|riscv64|s390x)|netbsd/amd64|openbsd/(amd64|arm64)|windows/(amd64|arm64|386)",
|
|
"autoupdate": "linux/amd64",
|
|
"download": [
|
|
{"re": "linux/(amd64|arm64|loong64|ppc64le|s390x|riscv64|386|arm$)", "files": ["https://git.musl-libc.org/cgit/musl/snapshot/musl-7ada6dde6f9dc6a2836c3d92c2f762d35fd229e0.tar.gz"]}
|
|
],
|
|
"test": "darwin/(amd64|arm64)|freebsd/(amd64|arm64|386|arm$)|linux/(386|amd64|arm$|arm64|loong64|ppc64le|riscv64|s390x)|netbsd/amd64|openbsd/(amd64|arm64)|windows/(amd64|arm64|386)"
|
|
}
|