Package ai.tabforge.workshop.model
package ai.tabforge.workshop.model
Domain model for the Claude Architect Workshop MCP server.
These are pure Java records — no framework dependencies, no SDK imports. They represent the data structures that flow between all layers of the system:
Finding— a single issue discovered by a sub-agentReviewReport— the complete aggregated output of a reviewReviewScope— what to review (changed files vs full project)AgentResult— what a sub-agent returns after calling Claude APIEscalationRequest— sent to Claude Desktop when human input is neededHumanDecision— the developer's response to an escalationSeverity— CRITICAL / WARNING / INFO
CERTIFICATION NOTE — Prompt Engineering & Structured Output (20% of exam):
The JSON schema enforced in every Anthropic API call is derived from
these record types. Finding IS the output contract that every
sub-agent's response_format parameter enforces.
Implemented in Phase 1 Day 3-4.
-
ClassDescriptionWhat a sub-agent returns after executing its analysis pass.Per-agent execution statistics included in the final
ReviewReport.Sent to Claude Desktop when a CRITICAL finding requires a human decision.A single issue discovered by a sub-agent during code review.The developer's response to an escalation — recorded in the audit trail.The three choices available to the developer when an escalation occurs.The final aggregated output of a complete Workshop review.Current lifecycle state of the review session.Defines what to review: which files and which specialist agents to run.Which specialist sub-agents to run.Which files to include in the review.Risk level of a finding discovered by a sub-agent.