Skip to content
ContractSpec
Start here

Area guide · 16 packages · Inspect an agent run boundary

Agents, execution and context

Build agent behavior from explicit tools, bounded execution, qualified models and provenance-aware context.

What are you trying to do?

  • What belongs in AgentProtocol versus the AI Agent runtime?
  • How does an agent receive verified context?
  • Which host supplies execution, storage and approvals?

Why start with these packages

Suggested entry point

@lssm-tech/lib.agent-protocol-spec

Start with wire contracts, runtime capabilities and validation vocabulary shared by agent hosts.

Read package manual →

Suggested entry point

@lssm-tech/lib.ai-agent

Use the canonical runtime, task-tree, context compiler, approval and tool orchestration surfaces.

Read package manual →

Suggested entry point

@lssm-tech/lib.context-storage

Locate context-pack/snapshot contracts and in-memory or supplied storage primitives.

Read package manual →

Suggested entry point

@lssm-tech/lib.harness

Inspect the reusable execution harness and its declared environment boundaries.

Read package manual →

Practical steps

Step 01

Start with one declared tool

Choose one existing operation and expose it through the intended registry or MCP boundary. Inspect its input, outcomes, scope and approval requirements before giving the agent a wider tool collection.

Step 02

Trace the context packet

Follow a source through retrieval/classification, compilation, snapshot storage and run admission. Check what happens when a required source is absent, expired, over budget or bound to the wrong scope.

Step 03

Inspect interruption and uncertainty

Use the owning fixture to examine cancellation, tool failure and a help/escalation request. Record the model/provider and execution environment in evidence; source support for a runtime adapter is not evidence of a successful run on it.

Select protocol and execution responsibilities

AgentProtocol owns shared wire models and deterministic validation; AI Agent supplies runtime orchestration, task trees, tools, sessions and approvals. Existing lifecycle declarations and registry helpers are explicit surfaces. A host supplies the actual model route, storage, tool execution and authority. This distinction is useful when embedding an agent in an existing application: first identify the operation it may perform and the environment it may use, then select the runtime pieces needed to carry that behavior.

Compile context with provenance

The context compiler accepts classified sources, tracks digests and provenance, enforces budgets and required inputs, and separates evidence from instruction authority. Protocol V1 runs require the qualified model route and verified compiled context described by the source. Treat retrieved documents as data with known scope and freshness. ContextStorage adds pack and snapshot storage primitives; it does not automatically make every stored document appropriate for every run. Preserve the snapshot and source identity when a run is resumed or reviewed.

Bound the run and its delegated tools

The runner/task-tree surfaces preserve cancellation and failure propagation. The runtime also supports bounded epochs and explicit delegation constraints over selected history, tool subsets, budgets, timeouts and evidence. Approvals remain independent of an agent’s own plan. A practical integration should show which context was supplied, which tool was requested, why it was permitted, and what result or uncertainty returned. Keep model output, proposed action, authorized invocation and durable outcome as separate observations.

Follow a practical path.

Start with one declared tool

Choose one existing operation and expose it through the intended registry or MCP boundary. Inspect its input, outcomes, scope and approval requirements before giving the agent a wider tool collection.

Trace the context packet

Follow a source through retrieval/classification, compilation, snapshot storage and run admission. Check what happens when a required source is absent, expired, over budget or bound to the wrong scope.

Inspect interruption and uncertainty

Use the owning fixture to examine cancellation, tool failure and a help/escalation request. Record the model/provider and execution environment in evidence; source support for a runtime adapter is not evidence of a successful run on it.

Packages in this area (16)

16 of 16 shown

Curated but no longer in the workspace: app.agent-host