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-specStart with wire contracts, runtime capabilities and validation vocabulary shared by agent hosts.
Suggested entry point
@lssm-tech/lib.ai-agentUse the canonical runtime, task-tree, context compiler, approval and tool orchestration surfaces.
Suggested entry point
@lssm-tech/lib.context-storageLocate context-pack/snapshot contracts and in-memory or supplied storage primitives.
Suggested entry point
@lssm-tech/lib.harnessInspect the reusable execution harness and its declared environment boundaries.
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
- Open manual →
Durable SQLite and Postgres session and checkpoint stores for @lssm-tech/lib.ai-agent
- Open manual →
Deny-by-default Docker and development sandbox adapters for @lssm-tech/lib.ai-agent
- Open manual →
Runtime adapters for the ContractSpec harness system.
- Open manual →
Tenant-safe multiplayer agent session collaboration primitives with deterministic replay.
- Open manual →
Provider-neutral durable agent help, uncertainty and common protocol definitions with exact legacy compatibility.
Start with wire contracts, runtime capabilities and validation vocabulary shared by agent hosts.
- Open manual →
AI agent orchestration with MCP and tool support
Use the canonical runtime, task-tree, context compiler, approval and tool orchestration surfaces.
- Open manual →
Context pack and snapshot storage primitives
Locate context-pack/snapshot contracts and in-memory or supplied storage primitives.
- Open manual →
Execution lanes orchestration contracts and runtime for ContractSpec.
- Open manual →
Harness orchestration, policy, evidence, and evaluation runtime.
Inspect the reusable execution harness and its declared environment boundaries.
- Open manual →
Builder mobile-control primitives for review cards, parity, and deep-link-safe actions.
- Open manual →
Sandboxed runtime primitives for executing governed ContractSpec workloads.
- Open manual →
Voice capabilities: TTS, STT, and conversational AI
- Open manual →
Agent fleet management module — fleet, tree, detail, tool registry, and run console surfaces.
- Open manual →
AI chat interface module
- Open manual →
Context storage module with persistence adapters
- Open manual →
Operator-facing execution lane console module.
Curated but no longer in the workspace: app.agent-host
What connects to this area
Core contracts
Tools and agent lifecycle operations need exact contracts.
Identity and access
Agent principals and delegated subjects must be constructed by a trusted host.
Knowledge and retrieval
Retrieval supplies evidence that the context compiler can classify and budget.
Governance and approvals
A plan or model response does not issue its own authority.