All Classes and Interfaces

Class	Description
AgentContext	Analogy: Like the work order that the shift leader gives to the worker at the beginning of the shift — it contains exactly what he needs to do (list of files), where is the construction site (projectPath), order number (reviewId), and how much material we can spend (tokenBudget).
AgentResult	What a sub-agent returns after executing its analysis pass.
AgentResultAggregator	Merges findings from all sub-agents into a single, deduplicated list.
AgentSummary	Per-agent execution statistics included in the final ReviewReport.
ApiSmokeTest	Smoke test that verifies both SDKs are correctly on the classpath and that the Anthropic API key is valid.
ArchitectureCheckerAgent
CancelReviewTool
ContextWindowManager	Enforces token budget constraints for each sub-agent API call.
DefaultSubAgent	Base class for all agents.
EscalationRequest	Sent to Claude Desktop when a CRITICAL finding requires a human decision.
Finding	A single issue discovered by a sub-agent during code review.
GetReportTool	MCP Tool: get_report
HumanDecision	The developer's response to an escalation — recorded in the audit trail.
HumanDecision.DecisionType	The three choices available to the developer when an escalation occurs.
Main	Entry point for the Claude Architect Workshop MCP Server.
OrchestratorAgent	The central coordinator of the Workshop review — manages all sub-agents, enforces workflow, handles lifecycle hooks, and decides when to escalate.
PerformanceAnalystAgent
ProgressReporter	SubAgent need reference for OrchestratorAgent.
RespondToEscalationTool	MCP Tool: respond_to_escalation
ReviewReport	The final aggregated output of a complete Workshop review.
ReviewReport.ReviewStatus	Current lifecycle state of the review session.
ReviewScope	Defines what to review: which files and which specialist agents to run.
ReviewScope.FocusFilter	Which specialist sub-agents to run.
ReviewScope.ScopeType	Which files to include in the review.
ReviewSession	When Claude AI periodically calls GetReportTool in order to obtain review status (and so, when GetReportTool calls invalid reference OrchestratorAgent#getStatus() ) the GetReportToll will return JSON filled with data from this class.
SecurityAuditorAgent	Specialist sub-agent that analyzes Jakarta EE source files for security vulnerabilities.
Severity	Risk level of a finding discovered by a sub-agent.
StartReviewTool	MCP Tool: start_review
SubAgent
TaskDecomposer
TransactionAnalystAgent
WorkshopServer	Wires together all MCP tools and starts the server over STDIO transport.