The agent.py event_generator() function invokes get_ironclaw_client() to obtain the appropriate agent client for message processing. StreamingResponse wraps the agent.py event_generator() function to stream data asynchronously to the client. The POST /api/v1/agent/sessions/{id}/message endpoint handles requests by executing the agent.py event_generator() function.

Agent configuration includes the AGENTS.md file.

The agentStore.findings data is connected to the FindingsPanelNew component for frontend rendering.

Budget Analyzer is a DS-STAR agent specialized in financial and budget analysis queries. Agent Selector directs queries to the Budget Analyzer agent

Agent command for file extraction; queued jobs are now correctly processed after fixing the function name mismatch, enabling full pipeline operation.

Agent configuration includes the MEMORY.md file.

DataLens spawns Opus sub-agent for system design decisions, complex refactoring, ambiguous requirements, or high-stakes decisions. DataLens Agent (Opus) developed the project goal field design proposal. Phase 2 Strategy Research & Decision Point involves the use of Opus 4.6 agent for generating PHASE2_UNIFIED_STRATEGY.md document DataLens agent spawns Opus sub-agent to handle system design decisions, complex refactoring, ambiguous requirements, and high-stakes decisions. Opus 4.6 created the PHASE2_UNIFIED_STRATEGY.md which contains pipeline design, tool justifications, and question-to-data mapping. Opus 4.6 and Sonnet 4.6 together were used to triangulate decision for the Phase 2 strategy due to GPT-5.2 unavailability. Opus 4.6 created the PHASE2_SCOPE_DECISION.md which compares MVP vs Ambitious approaches, provides timeline, risk analyses, and file type strategies. Opus 4.6 recommends text extraction from all 48 PDFs with OCR only where relevant due to medium-high ROI and 2-3 hours effort estimation. Opus 4.6 recommends parsing all DOCX files if policy questions are real; otherwise selectively processing top 20, valuing DOCX as having high ROI for 3-4 hours effort. Opus 4.6 recommends processing all 3 PPTX files due to low cost and consistent summary value. Opus 4.6 recommends processing all 2 MSG files as they provide governance signals. Opus 4.6 recommends the MVP approach as a minimum viable product completing 25 of 35 analytical questions in 5 to 7 days with selective ingestion. Opus 4.6 recommends against full 153-file load due to complexity and risk, suggesting a phased selective ingestion instead. Opus analysis investigates the behavior of agent_skills.py process_message() to diagnose async exception issues.

Policy Researcher is a DS-STAR agent specialized in policy and compliance question answering. Agent Selector directs queries to the Policy Researcher agent

A tool used within the agent to execute SQL queries on DuckDB for structured data retrieval.

The command for spawning sessions uses the 'sonnet' model, requiring specific parameters and following strict protocols.

Sonnet 4.6 created the PHASE2_IMPLEMENTATION_PLAN.md containing the go/no-go recommendation and effort versus value analysis. Opus 4.6 and Sonnet 4.6 together were used to triangulate decision for the Phase 2 strategy due to GPT-5.2 unavailability.

DataLens is focused on data analysis projects, while TerrainLens is handled by the main agent, indicating separation of concerns between the two agents. The DataLens Master Implementation Plan depends on TerrainLens usage for GPU resources allocation during Ollama calls. DataLens agent focuses on data analysis and must stay focused on its project, as TerrainLens is handled by the main agent and is a separate concern. DataLens focuses on data analysis and explicitly excludes handling TerrainLens, which is managed by the main agent.