Crate everruns_contracts 

Shared contracts for the Everruns framework and hosts.

Provider and driver boundaries, capability definitions, model profiles, typed IDs, and shared runtime contracts live here. The default build omits HTTP transport; enable http for the shared protocol drivers and clients. Application authors normally use the same types through everruns.

use everruns_contracts::{CapabilityRef, ModelSpec};
let model = ModelSpec::on("company-gateway", "assistant-v2");
let capability = CapabilityRef::new("vendor.search");
assert_eq!(model.provider.as_str(), "company-gateway");
assert_eq!(capability.id(), "vendor.search");

Re-exports

pub use capability::ActivationSet;

pub use capability::CapabilityError;

pub use capability::CapabilityId;

pub use capability::CapabilityIdIndex;

pub use capability::CapabilityRef;

pub use capability::CapabilitySpec;

pub use capability::CapabilitySpecParts;

pub use capability::GENERIC_HARNESS_NAME;

pub use capability::IntoCapability;

pub use capability::PLUGIN_CAPABILITY_PREFIX;

pub use capability::RESERVED_CAPABILITY_ID_NAMESPACE;

pub use capability::generic_capabilities;

pub use capability::is_plugin_capability;

pub use capability::parse_plugin_capability_id;

pub use capability::plugin_capability_id;

pub use capability::validate_capability_config;

pub use capability::validate_capability_id;

pub use capability::Definition;

pub use capability::json_schema_for;

pub use compact::CompactContent;

pub use compact::CompactContentPart;

pub use compact::CompactInputItem;

pub use compact::CompactOutputItem;

pub use compact::CompactRequest;

pub use compact::CompactResponse;

pub use compact::CompactUsage;

pub use compact::messages_to_compact_input;

pub use credential_provider::CredentialProvider;

pub use credential_provider::EnvCredentialProvider;

pub use credential_provider::ProviderCredentials;

pub use credential_schema::CredentialFormSchema;

pub use credential_schema::assemble_credential_document;

pub use credential_schema::parse_credential_document;

pub use driver_registry::BoxedChatDriver;

pub use driver_registry::BoxedEmbeddingsDriver;

pub use driver_registry::ChatDriver;

pub use driver_registry::DiscoveredModel;

pub use driver_registry::DriverDescriptor;

pub use driver_registry::DriverFactory;

pub use driver_registry::DriverId;

pub use driver_registry::DriverOAuthConfig;

pub use driver_registry::DriverOAuthFlow;

pub use driver_registry::DriverRegistry;

pub use driver_registry::EmbedRequest;

pub use driver_registry::EmbedResponse;

pub use driver_registry::EmbeddingsDriver;

pub use driver_registry::EmbeddingsDriverError;

pub use driver_registry::EmbeddingsDriverFactory;

pub use driver_registry::LlmCallConfig;

pub use driver_registry::LlmCallConfigBuilder;

pub use driver_registry::LlmCompletionMetadata;

pub use driver_registry::LlmContentPart;

pub use driver_registry::LlmResponse;

pub use driver_registry::LlmResponseStream;

pub use driver_registry::LlmStreamError;

pub use driver_registry::LlmStreamEvent;

pub use driver_registry::Message;

pub use driver_registry::MessageContent;

pub use driver_registry::MessageRole;

pub use driver_registry::ProviderConfig;

pub use driver_registry::ProviderMetadata;

pub use driver_registry::ProviderOpaqueContext;

pub use driver_registry::ServiceKind;

pub use driver_registry::fold_system_messages;

pub use error::AgentLoopError;

pub use error::BillingPressureReason;

pub use error::FileSystemError;

pub use error::FileSystemErrorClass;

pub use error::LlmError;

pub use error::LlmErrorKind;

pub use error::Result;

pub use error::StoreResultExt;

pub use error::classify_fs_error;

pub use error::from_json;

pub use error::json_val;

pub use execution_phase::ExecutionPhase;

pub use execution_phase::PhaseSource;

pub use llm_error::RejectedProviderCapability;

pub use llm_retry::LlmRetryConfig;

pub use llm_retry::RateLimitInfo;

pub use llm_retry::RateLimitType;

pub use llm_retry::RetryMetadata;

pub use message::ProviderOpaqueContent;

pub use message::LlmMessage;Deprecated

pub use message::LlmMessageContent;Deprecated

pub use message::LlmMessageRole;Deprecated

pub use model::CostTier;

pub use model::Modality;

pub use model::ModelCost;

pub use model::ModelLimits;

pub use model::ModelModalities;

pub use model::ModelProfile;

pub use model::ModelVendor;

pub use model::ReasoningEffort;

pub use model::ReasoningEffortConfig;

pub use model::ReasoningEffortValue;

pub use model_discovery::DiscoveredProviderModel;

pub use model_discovery::ModelSearchMatch;

pub use model_discovery::ModelSearchResult;

pub use model_discovery::RankedDiscoveredModels;

pub use model_discovery::discover_provider_models;

pub use model_discovery::enrich_with_profiles;

pub use model_discovery::match_models;

pub use model_discovery::normalize_and_enrich;

pub use model_discovery::rank_discovered_models;

pub use model_discovery::search_provider_models;

pub use model_profiles::ModelProfileEntry;

pub use model_profiles::all_profile_entries;

pub use model_profiles::all_profiles;

pub use model_profiles::get_model_profile;

pub use model_profiles::get_model_vendor;

pub use model_profiles::profile_entries_for_provider;

pub use model_profiles::profiles_for_provider;

pub use model_profiles::selected_profiles;

pub use model_profiles::selected_profiles_for_provider;

pub use model_spec::ModelSpec;

pub use model_spec::UnknownProvider;

pub use openai_wire::OpenAiWireError;

pub use provider::ProviderTraceConfig;

pub use reasoning::ReasoningContentPart;

pub use reasoning::ReasoningText;

pub use runtime_provider::BearerAuth;

pub use runtime_provider::Provider;

pub use runtime_provider::ProviderAuth;

pub use runtime_provider::ProviderAuthRequest;

pub use runtime_provider::ProviderEndpoint;

pub use runtime_provider::ProviderKey;

pub use runtime_provider::ProviderRegistry;

pub use runtime_provider::ResolvedProviderRequest;

pub use runtime_provider::RuntimeProvider;

pub use runtime_provider::RuntimeProviderRegistry;

pub use runtime_provider::StaticHeaderAuth;

pub use tool_approval_types::APPROVE_TOOL_CALL_TOOL;

pub use tool_approval_types::TOOL_APPROVAL_CALL_ID_PREFIX;

pub use tool_approval_types::TOOL_APPROVAL_REQUIRED_CODE;

pub use tool_approval_types::TOOL_ARGUMENTS_PREVIEW_BYTES;

pub use tool_approval_types::ToolApprovalRequired;

pub use tool_approval_types::preview_tool_arguments;

pub use tool_types::ASK_USER_TOOL_NAME;

pub use tool_types::BuiltinTool;

pub use tool_types::CONFIRM_URL_ELICITATION_TOOL;

pub use tool_types::ClientSideTool;

pub use tool_types::ConnectionRequired;

pub use tool_types::ConnectionRequiredSubject;

pub use tool_types::DeferrablePolicy;

pub use tool_types::FORM_ELICITATION_CALL_ID_PREFIX;

pub use tool_types::FORM_ELICITATION_REQUIRED_CODE;

pub use tool_types::FormElicitationRequired;

pub use tool_types::MCP_ELICITATION_ARGUMENT;

pub use tool_types::SideEffectClass;

pub use tool_types::ToolCall;

pub use tool_types::ToolDefinition;

pub use tool_types::ToolHints;

pub use tool_types::ToolPolicy;

pub use tool_types::ToolResult;

pub use tool_types::ToolResultImage;

pub use tool_types::URL_ELICITATION_REQUIRED_CODE;

pub use tool_types::UrlElicitationRequired;

pub use tool_types::unattended_ask_user_result;

pub use turn_collector::CollectedTurn;

pub use turn_collector::TurnLimits;

pub use turn_collector::TurnTiming;

pub use turn_collector::collect_turn;

pub use turn_collector::limit_stream;

pub use url_validation::UrlValidationError;

pub use url_validation::is_blocked_ip;

pub use url_validation::validate_safe_url;

pub use url_validation::validate_url_dns_pinned;

pub use user_facing_error::ErrorDisclosure;

pub use user_facing_error::UserFacingError;

pub use user_facing_error::UserFacingErrorContext;

pub use user_facing_error::UserFacingErrorFields;

pub use user_facing_error::classify_runtime_error_message;

pub use user_facing_error::codes as user_facing_error_codes;

pub use user_facing_error::is_provider_quota_message;

pub use user_facing_error::is_usage_limit_message;

pub use user_facing_error::metadata_keys as user_facing_error_metadata_keys;

pub use user_facing_error::parse_usage_limit_reset_at;

pub use user_facing_error::trim_error_chain_prefixes;

pub use schemars;

pub use serde;

pub use serde_json;

Modules

background_call

Durable hooks for provider-side background responses (EVE-1134).

capability

The neutral Everruns capability contract (EVE-873).

compact

Transport-neutral native compaction request and response contracts.

connector

credential_provider

credential_schema

decision_driver

Decision drivers: the vendor seam behind DecisionsService.

decisions

System decisions.

driver_registry

error

execution_phase

Execution phase for assistant messages in multi-step tool-calling flows.

form_elicitation_types

Wire types for an MCP server’s form mode elicitation, as it crosses from the MCP executor to the engine and the answer API.

hosted_mcp

Credentials for remote MCP servers OpenAI calls on the agent’s behalf (EVE-1115).

knowledge_store

Hosted knowledge retrieval service contracts.

llm_error

How a provider failure is classified, and what is preserved of it.

llm_retry

llm_telemetry

Structured logs for LLM edge cases we want to measure before changing.

message

The provider-agnostic message a driver sends, and what it is made of.

model

Provider-neutral model profile values.

model_discovery

Provider model discovery and display ranking.

model_profile_data

Model profile metadata and the offline registry, keyed by provider wire ID. Model identity, capability metadata, and the offline profile registry.

model_profiles

model_spec

Credential-free model selection.

native_async

Native asynchronous calls are pending provider exchanges, not background-run handles.

native_computer

Native provider computer tools (EVE-1133, computer use phase 2).

openai_compat

OpenAI model constraints checked before a request reaches the network.

openai_computer

OpenAI Responses computer tool wire mapping (EVE-1133).

openai_hosted_tools

OpenAI hosted (provider-executed) tools for the Responses API.

openai_wire

The OpenAI chat-completions JSON shapes, as values Everruns can read and write.

openresponses_types

provider

reasoning

Provider reasoning artifacts.

reasoning_updates

Conversation-scoped Astra configuration, distinct from the request baseline.

rt

Portable async runtime primitives: time, timers and task spawning.

runtime_provider

Runtime providers: service identity, endpoint, authentication, and wire driver.

sandbox_checkpoint

Logical sandbox and authoritative workspace-checkpoint contracts.

secret_scrub

Value-pattern credential scrubbing shared by every path that publishes free-form strings: eval/ATIF exports (server) and the executed arguments on tool.completed (engine). One pattern list, so a new credential shape is covered everywhere at once.

session_sandbox

Provider-neutral managed session sandbox contracts.

session_sqldb

slack_action

Session-bound Slack effects; credentials stay with the control plane. The seam a Slack-native capability acts through (EVE-1024).

stream_accumulator

stream_event

Stream events and completion metadata every chat driver produces.

structured_output

Provider-neutral structured output: ask the model for a reply that validates against a JSON Schema, enforced by the provider rather than by prompting for JSON and hoping.

tool_approval_types

Wire types for a tool call parked on a hard approval gate, as it crosses from the tool_approval capability to the engine and the answer API.

tool_schema_compat

Provider-specific JSON Schema compatibility at the LLM request boundary.

tool_types

tools

Tool outcomes shared by runtimes and provider services.

turn_collector

Collecting a provider stream into one finished turn.

typed_id

url_validation

user_facing_error

vector_store

Vendor-neutral vector store abstraction for Knowledge Indexes.

Attribute Macros

async_trait