Module server_config 

Canonical context-size resolver (4-level fallback chain).

Extracted to gglib-core so that crates which cannot depend on gglib-runtime (e.g. gglib-proxy) can still use the same resolution logic for idle-model advertisements in /v1/models.

Re-exports

pub use crate::cache_config::CacheRamSetting;

pub use crate::domain::cache_budget::CACHE_RAM_FLOOR_BYTES;

pub use crate::domain::cache_budget::CACHE_RAM_HEADROOM_BYTES;

pub use crate::domain::cache_budget::CACHE_RAM_UNKNOWN_KV_ALLOWANCE_BYTES;

pub use crate::domain::cache_budget::compute_auto_cache_ram_mb;

Structs

ServerConfigOptions

Caller-supplied overrides for resolve_context_size.

Enums

CtxSizeArg

A parsed --ctx-size CLI flag, before it is resolved against model metadata.

Functions

parse_ctx_size_flag

Parse an optional raw --ctx-size flag into a CtxSizeArg.

resolve_context_size

Resolve context size using the 4-level fallback chain.