Docs / Introduction
Mental model
Think in hosted abilities: actor, capability, host, policy, context, result, and evidence.
Plain English
CHP gives every useful ability a visible owner, invocation path, rule boundary, and replayable outcome.
Why it exists
A shared mental model keeps docs, manifests, diagrams, examples, and product surfaces aligned.
Formal definition
The CHP model represents capability use as an ordered relationship between actor, capability, host, policy, context, result, and evidence.
Concrete example
Ground the concept before the schema.
[Planning Agent] -> {schedule_technician} @ ServiceOpsHost | manager_approval | job_context -> Confirmed Appointment
Finds an available qualified technician and reserves a service window.
Invocation trace
- 01 Actor
Planning Agent
- 02 Capability
schedule_technician
- 03 Host
ServiceOpsHost
- 04 Policy
manager_approval
- 05 Context
job_context
- 06 Result
Confirmed Appointment
Relationships
Where this sits in the protocol.
Each concept should explain its neighbors so implementation teams can preserve the boundary across manifests, invocation, evidence, and tests.
Actor is the requester.
Capability is the named ability.
Host owns policy, lifecycle, result, and evidence.
Visual model
- 01Actor chooses an ability.
- 02Host validates the boundary.
- 03Result and evidence make the outcome inspectable.
Implementation notes
- Use the notation in examples before introducing schemas.
- Keep policy visible before composition claims.
- Make failure paths part of the model.
Common mistakes
- Starting with transport instead of capability meaning.
- Drawing diagrams that hide the host boundary.
- Explaining composition before governance.
Related concepts