Module domain 

domain

Core domain types.

These types represent the pure domain model, independent of any infrastructure concerns (database, filesystem, etc.).

Structure

• agent - Agent loop types (AgentConfig, AgentMessage, AgentEvent, etc.)
• model - Model types (Model, NewModel)
• model_naming - Shared model-naming policy (resolve_model_name, NameSource)
• mcp - MCP server types (McpServer, NewMcpServer, etc.)
• chat - Chat conversation and message types
• gguf - GGUF metadata and capability types
• capabilities - Model capability detection and inference
• thinking - Thinking/reasoning tag parsing and streaming accumulation

Modules

Module	LOC	Complexity	Coverage
cache_budget.rs
capabilities.rs
chat.rs
gguf.rs
inference.rs
inference_profile.rs
kv_estimate.rs
kv_memory.rs
model.rs
model_naming.rs
query.rs
server_config.rs
slot_eviction.rs
agent/
benchmark/
council/
mcp/

Re-exports

pub use query::ModelListQuery;

pub use query::ModelSortBy;

pub use query::SortOrder;

pub use query::apply_query;

pub use benchmark::BenchmarkEvent;

pub use benchmark::BenchmarkModelResult;

pub use benchmark::BenchmarkRun;

pub use benchmark::BenchmarkRunStatus;

pub use benchmark::BenchmarkRunType;

pub use benchmark::CandidateSource;

pub use benchmark::CompareConfig;

pub use benchmark::ModelBenchmarkSummary;

pub use benchmark::ModelCompareResult;

pub use benchmark::ModelPerfResult;

pub use benchmark::PerfConfig;

pub use benchmark::ScoreWeights;

pub use benchmark::SweepSpec;

pub use benchmark::TaskCategory;

pub use benchmark::TaskSuite;

pub use benchmark::TuneCandidateResult;

pub use benchmark::TuneConfig;

pub use benchmark::TuneTask;

pub use benchmark::TuneTaskResult;

pub use inference::DefaultsOrigin;

pub use inference::InferenceConfig;

pub use inference::ModelSamplingContext;

pub use inference_profile::InferenceProfile;

pub use inference_profile::MAX_PROFILE_NAME_LEN;

pub use inference_profile::ProfileNameError;

pub use inference_profile::RESERVED_PROFILE_NAMES;

pub use inference_profile::builtin_templates;

pub use inference_profile::validate_name;

pub use kv_estimate::KvElemsPerToken;

pub use kv_estimate::estimate_kv_bytes_for_context;

pub use kv_estimate::estimate_kv_elems_per_token;

pub use kv_estimate::kv_bytes_per_token;

pub use kv_memory::kv_memory_is_partial;

pub use cache_budget::CACHE_RAM_FLOOR_BYTES;

pub use cache_budget::CACHE_RAM_HEADROOM_BYTES;

pub use cache_budget::CACHE_RAM_LOW_WATERMARK_BYTES;

pub use cache_budget::CACHE_RAM_UNKNOWN_KV_ALLOWANCE_BYTES;

pub use cache_budget::CacheRamHealth;

pub use cache_budget::classify_cache_ram;

pub use cache_budget::compute_auto_cache_ram_mb;

pub use slot_eviction::DISK_BUDGET_FRACTION_DIVISOR;

pub use slot_eviction::SlotFileMeta;

pub use slot_eviction::compute_auto_disk_budget_bytes;

pub use slot_eviction::select_evictions;

pub use mcp::McpEnvEntry;

pub use mcp::McpLifecycle;

pub use mcp::McpServer;

pub use mcp::McpServerConfig;

pub use mcp::McpServerStatus;

pub use mcp::McpServerType;

pub use mcp::McpTool;

pub use mcp::McpToolResult;

pub use mcp::NewMcpServer;

pub use mcp::SEARCH_RESULTS_CAP;

pub use mcp::ToolIndex;

pub use mcp::ToolSummary;

pub use mcp::UpdateMcpServer;

pub use chat::Conversation;

pub use chat::ConversationUpdate;

pub use chat::Message;

pub use chat::MessageRole;

pub use chat::NewConversation;

pub use chat::NewMessage;

pub use gguf::CapabilityFlags;

pub use gguf::GgufCapabilities;

pub use gguf::GgufMetadata;

pub use gguf::GgufValue;

pub use gguf::RawMetadata;

pub use gguf::ReasoningDetection;

pub use gguf::ToolCallingDetection;

pub use model_naming::NameSource;

pub use model_naming::UNKNOWN_MODEL_NAME;

pub use model_naming::declared_name;

pub use model_naming::repo_short_name;

pub use model_naming::resolve_model_name;

pub use model_naming::strip_gguf_suffix;

pub use agent::AGENT_EVENT_CHANNEL_CAPACITY;

pub use agent::AgentConfig;

pub use agent::AgentConfigError;

pub use agent::AgentEvent;

pub use agent::AgentMessage;

pub use agent::AssistantContent;

pub use agent::DEFAULT_MAX_ITERATIONS;

pub use agent::DEFAULT_MAX_PARALLEL_TOOLS;

pub use agent::DEFAULT_MAX_STAGNATION_STEPS;

pub use agent::LlmStreamEvent;

pub use agent::MAX_ITERATIONS_CEILING;

pub use agent::MAX_PARALLEL_TOOLS_CEILING;

pub use agent::MAX_TOOL_TIMEOUT_MS_CEILING;

pub use agent::MIN_CONTEXT_BUDGET_CHARS;

pub use agent::MIN_TOOL_TIMEOUT_MS;

pub use agent::ToolCall;

pub use agent::ToolDefinition;

pub use agent::ToolResult;

pub use capabilities::ChatMessage;

pub use capabilities::MessageContent;

pub use capabilities::ModelCapabilities;

pub use capabilities::capabilities_from_architecture;

pub use capabilities::infer_from_chat_template;

pub use capabilities::transform_messages_for_capabilities;

pub use council::ApprovalKind;

pub use council::CouncilEvent;

pub use council::HitlMode;

pub use council::MAX_DEPTH;

pub use council::MAX_NODES;

pub use council::NodeId;

pub use council::NodeStatus;

pub use council::TaskGraph;

pub use council::TaskGraphError;

pub use council::TaskNode;

Modules

agent

agent

benchmark

benchmark

cache_budget

Auto-sizing math for llama-server’s host-RAM prompt cache (--cache-ram).

capabilities

Model capability detection, inference, and request transformation.

chat

Chat domain types.

council

council

gguf

GGUF domain types.

inference

Inference configuration types.

inference_profile

Named, cross-model sampling profiles.

kv_estimate

KV-cache size estimation from GGUF metadata.

kv_memory

Detection of partial-KV-memory architectures from GGUF metadata.

mcp

mcp

model 🔒

Model domain types.

model_naming

Shared model-naming policy.

query

Model list query, filter, and sort types.

server_config 🔒

Server-level default configuration for models.

slot_eviction

Byte-budget selection for on-disk KV slot cache eviction.

Structs

Model

A model that exists in the system with a database ID.

ModelFile

Represents a single file (shard) belonging to a model.

ModelFilterOptions

Filter options for the model library UI.

NewModel

A model to be inserted into the system (no ID yet).

NewModelFile

A model file entry to be inserted into the system (no ID yet).

RangeValues

A range of numeric values with min and max.

ServerConfig

Server-level defaults for a specific model.

Constants

SYSTEM_TAG_PREFIX

Prefix marking a tag as runtime-load-bearing.

Functions

is_system_tag

Returns true when tag is a system tag that callers must not remove through the standard tag-mutation API.