Skip to main content

Module config

Module config 

Source

Structs§

A2aConfig
Host-owned A2A peer trust. Graphs and agent artifacts can select only an exact endpoint listed here; credentials never enter graph or artifact data.
A2aPeerConfig
One exact remote UAR agent binding. Reusing a token for several agents is explicit: each endpoint still needs its own entry and artifact dependency.
AcpConfig
interface for agent introspection, session management, and streaming run execution — used by IDEs, debuggers, and the BeeAI platform.
ApiKeyAdminPrincipal
Explicit scoped key administrator; a role label alone never grants this power.
AppConfig
ChunkingConfig
Chunking strategy configuration.
Cli
EmbeddingBackendConfig
Embedding backend configuration for RAG and memory.
FailoverConfig
Runtime model failover configuration.
FallbackModel
A single entry in the ordered fallback model list.
FileProcessingConfig
Configuration for file processing and uploads.
GuardrailsConfig
Input guardrail configuration: heuristic prompt-injection and PII/secret screening of chat input before the LLM call.
HarnessConfig
KnowledgeBaseConfig
Configuration for a single knowledge base.
KnowledgeBasesConfig
Top-level configuration for knowledge bases.
KreuzbergChunkingConfig
Kreuzberg text-chunking configuration for RAG pipelines. Field names use Rust conventions (max_characters/overlap) — differs from the Python SDK (max_chars/max_overlap). See kreuzberg SKILL.md pitfalls.
KreuzbergConfig
Kreuzberg local file processing configuration. Kreuzberg is a high-performance document intelligence framework with a Rust core.
LlmBudgetConfig
Budget enforcement configuration.
LlmCacheConfig
Cache configuration for the liter-llm Tower middleware.
LlmConfig
Unified LLM configuration for the liter-llm client.
LlmRateLimitConfig
Rate limiting configuration.
LocalEmbeddingFailoverConfig
Local-only embedding backup configuration.
LocalEmbeddingMemberConfig
One explicitly located local embedding member.
MemoryConfig
Configuration for the in-process agent memory system, backed by surreal-memory + SurrealDB/SurrealKV.
MistralConfig
Mistral OCR configuration.
ModelsConfig
Model files configuration (tokenizer, embeddings, etc.).
NativeToolsConfig
Configuration for native (in-process) tool implementations.
PersistenceConfig
ResilienceConfig
RunsConfig
SandboxRuntimeConfig
Configuration for the sandboxed code-execution subsystem.
SecurityConfig
ServerConfig
ServiceInstanceConfig
Host-configured identity and safe references for this logical UAR service.
SessionsConfig
SkillEvolutionConfig
Configuration for the post-run skill evolution system.
SkillReattachmentBudget
Model-token ceilings for re-attaching active bodies after compaction.
SycophancyConfig
Configuration for the ACP (Agent Communication Protocol) server endpoint.
TrustedHostPrincipal
Exact issuer-controlled service identity allowed to present host grants.
UnstructuredConfig
Unstructured.io configuration (hosted or self-hosted).
VisionConfig
Vision/Image processing configuration.
WorkspaceAuthority
Operator-owned authorization for an exact verified identity and workspace.

Enums§

Command
Top-level binary subcommands. Absent ⇒ run the server (default).
CredentialAction
Credential maintenance never starts the runtime or a network listener.
DeploymentProfile
Identity admission policy is independent of network bind addresses.
EvalAction
eval subcommands.
FailoverStrategy
Selection strategy for picking the next provider when the primary fails.
HarnessMode
Typed assembly is the default after the recorded parity-and-smoke gate.
JwtAlgorithm
Supported verifier algorithms; tokens cannot choose a different policy.
LogFormat
ReasoningEffort
Host-selected reasoning level for one run.
ServiceOwnership
SkillActivationMode
Skill matching suggests catalog entries or activates legacy overlays.
WorkspaceLocation

Functions§

build_client_config
Build a liter_llm::ClientConfig from the merged LlmConfig.
load_llm_config
Load just the merged LlmConfig from all layered configuration sources.