Skip to main content

Crate molo_harness

Crate molo_harness 

Source
Expand description

Harness runtime: governed execution for effect-producing agents.

A harness sits outside an AgentKernel. The kernel decides the next action; the harness runtime executes provider requests and routes side-effect requests through policy, approval, executor, output limiting, audit, and transcript recording before feeding observations back to the kernel.

This module deliberately does not include production filesystem, shell, git, browser, or MCP executors. Those belong in higher layers such as a coding-workload SDK. The built-in executors here are for tests, applications that provide their own effect semantics, and validating the runtime boundary.

Modules§

agent
Agents: reasoning loops.
effect
Effect protocol: side-effect requests and observations.
message
Conversation messages.
observability
Lightweight observability record types.
provider
Provider: the interface for communicating with an LLM.
run
Structured run protocol shared by agent implementations and callers.
tool
Tool registry support for agent runtimes.

Structs§

AlwaysAllowApprovalBroker
Approval broker that always allows requests.
AlwaysDenyApprovalBroker
Approval broker that always denies requests.
ApprovalRequest
Approval request passed to an ApprovalBroker.
BasicHarness
Minimal in-process harness implementation.
ClassifiedEffect
Classified effect request.
DefaultPolicyEngine
Risk-based default policy.
DefaultRiskClassifier
Conservative default risk classifier.
ExecutionPolicy
Execution policy passed to an EffectExecutor.
ExecutionPolicySummary
Serializable summary of an execution policy.
HarnessConfig
Harness configuration.
HarnessRuntime
Outer runtime that drives an AgentKernel with a Provider and governed Harness.
HarnessRuntimeConfig
Runtime loop configuration.
LimitedOutput
Output after limiting and redaction.
ModelSummary
Summary of a model observation.
NoopAuditSink
Explicit opt-out audit sink.
NoopEffectExecutor
Executor that refuses every effect without performing side effects.
NoopRedactor
Redactor that leaves output unchanged.
NoopTranscriptStore
Transcript store that drops all records.
OutputLimit
Output size limits.
PatternRedactor
Secret-pattern redactor for examples and tests.
RawEffectOutput
Raw executor output before limiter/redactor processing.
RedactedText
Redacted text and metadata.
RedactionRecord
A redaction that was applied to an exported record or text field.
RouterEffectExecutor
Executor that dispatches by EffectKind.
StaticApprovalBroker
Static approval broker configured with a single decision.
StaticEffectExecutor
Test executor that returns preconfigured outputs by effect id.
VecAuditSink
In-memory audit sink useful for tests.
VecTranscriptStore
In-memory transcript store useful for tests.

Enums§

AgentActionSummary
Summary of an agent action for transcript records.
ApprovalDecision
Approval decision.
ApprovalError
Approval errors.
AuditError
Audit errors.
AuditEvent
Reliable effect-governance audit event.
ExecutionError
Executor errors.
HarnessError
Errors returned by a harness.
HarnessRuntimeError
Errors returned by HarnessRuntime.
NetworkPolicy
Network access policy requested of an executor.
PolicyDecision
Policy decision for a classified effect.
SandboxPolicy
Filesystem/process sandbox policy requested of an executor.
TranscriptError
Transcript errors.
TranscriptRecord
Transcript record for run replay and debugging.

Traits§

ApprovalBroker
Broker that obtains approval from an application-specific authority.
AuditSink
Reliable audit sink.
EffectExecutor
Executes an already approved effect.
Harness
Governs and executes one or more effect requests.
PolicyEngine
Evaluates host policy for a classified effect.
Redactor
Redacts executor output before model/audit/transcript use.
RiskClassifier
Classifies effect risk before policy evaluation.
TranscriptStore
Transcript store for resumable run traces.